Instructions to use DrNicefellow/uncensored_gpt_oss with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DrNicefellow/uncensored_gpt_oss with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="DrNicefellow/uncensored_gpt_oss") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("DrNicefellow/uncensored_gpt_oss") model = AutoModelForCausalLM.from_pretrained("DrNicefellow/uncensored_gpt_oss", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use DrNicefellow/uncensored_gpt_oss with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "DrNicefellow/uncensored_gpt_oss" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "DrNicefellow/uncensored_gpt_oss", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/DrNicefellow/uncensored_gpt_oss
- SGLang
How to use DrNicefellow/uncensored_gpt_oss with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "DrNicefellow/uncensored_gpt_oss" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "DrNicefellow/uncensored_gpt_oss", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "DrNicefellow/uncensored_gpt_oss" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "DrNicefellow/uncensored_gpt_oss", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use DrNicefellow/uncensored_gpt_oss with Docker Model Runner:
docker model run hf.co/DrNicefellow/uncensored_gpt_oss
Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- .gitattributes +3 -0
- README.md +58 -0
- added_tokens.json +24 -0
- chat_template.jinja +331 -0
- checkpoint-300/README.md +209 -0
- checkpoint-300/adapter_config.json +42 -0
- checkpoint-300/adapter_model.safetensors +3 -0
- checkpoint-300/added_tokens.json +24 -0
- checkpoint-300/chat_template.jinja +54 -0
- checkpoint-300/merges.txt +0 -0
- checkpoint-300/optimizer.pt +3 -0
- checkpoint-300/rng_state.pth +3 -0
- checkpoint-300/scheduler.pt +3 -0
- checkpoint-300/special_tokens_map.json +31 -0
- checkpoint-300/tokenizer.json +3 -0
- checkpoint-300/tokenizer_config.json +207 -0
- checkpoint-300/trainer_state.json +3034 -0
- checkpoint-300/training_args.bin +3 -0
- checkpoint-300/vocab.json +0 -0
- checkpoint-50/README.md +209 -0
- checkpoint-50/adapter_config.json +42 -0
- checkpoint-50/adapter_model.safetensors +3 -0
- checkpoint-50/added_tokens.json +24 -0
- checkpoint-50/chat_template.jinja +331 -0
- checkpoint-50/merges.txt +0 -0
- checkpoint-50/optimizer.pt +3 -0
- checkpoint-50/rng_state.pth +3 -0
- checkpoint-50/scheduler.pt +3 -0
- checkpoint-50/special_tokens_map.json +23 -0
- checkpoint-50/tokenizer.json +3 -0
- checkpoint-50/tokenizer_config.json +183 -0
- checkpoint-50/trainer_state.json +534 -0
- checkpoint-50/training_args.bin +3 -0
- checkpoint-50/vocab.json +0 -0
- config.json +69 -0
- generation_config.json +11 -0
- lora_weights/README.md +209 -0
- lora_weights/adapter_config.json +42 -0
- lora_weights/adapter_model.safetensors +3 -0
- merges.txt +0 -0
- model-00001-of-00009.safetensors +3 -0
- model-00002-of-00009.safetensors +3 -0
- model-00003-of-00009.safetensors +3 -0
- model-00004-of-00009.safetensors +3 -0
- model-00005-of-00009.safetensors +3 -0
- model-00006-of-00009.safetensors +3 -0
- model-00007-of-00009.safetensors +3 -0
- model-00008-of-00009.safetensors +3 -0
- model-00009-of-00009.safetensors +3 -0
- model.safetensors.index.json +419 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
checkpoint-300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
checkpoint-50/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: openai/gpt-oss-20b
|
| 3 |
+
library_name: transformers
|
| 4 |
+
model_name: outputs
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
- trl
|
| 8 |
+
- sft
|
| 9 |
+
licence: license
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model Card for outputs
|
| 13 |
+
|
| 14 |
+
This model is a fine-tuned version of [openai/gpt-oss-20b](https://huggingface.co/openai/gpt-oss-20b).
|
| 15 |
+
It has been trained using [TRL](https://github.com/huggingface/trl).
|
| 16 |
+
|
| 17 |
+
## Quick start
|
| 18 |
+
|
| 19 |
+
```python
|
| 20 |
+
from transformers import pipeline
|
| 21 |
+
|
| 22 |
+
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
|
| 23 |
+
generator = pipeline("text-generation", model="None", device="cuda")
|
| 24 |
+
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
|
| 25 |
+
print(output["generated_text"])
|
| 26 |
+
```
|
| 27 |
+
|
| 28 |
+
## Training procedure
|
| 29 |
+
|
| 30 |
+
|
| 31 |
+
|
| 32 |
+
|
| 33 |
+
This model was trained with SFT.
|
| 34 |
+
|
| 35 |
+
### Framework versions
|
| 36 |
+
|
| 37 |
+
- TRL: 0.24.0
|
| 38 |
+
- Transformers: 4.57.0.dev0
|
| 39 |
+
- Pytorch: 2.8.0+cu129
|
| 40 |
+
- Datasets: 4.2.0
|
| 41 |
+
- Tokenizers: 0.22.1
|
| 42 |
+
|
| 43 |
+
## Citations
|
| 44 |
+
|
| 45 |
+
|
| 46 |
+
|
| 47 |
+
Cite TRL as:
|
| 48 |
+
|
| 49 |
+
```bibtex
|
| 50 |
+
@misc{vonwerra2022trl,
|
| 51 |
+
title = {{TRL: Transformer Reinforcement Learning}},
|
| 52 |
+
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
|
| 53 |
+
year = 2020,
|
| 54 |
+
journal = {GitHub repository},
|
| 55 |
+
publisher = {GitHub},
|
| 56 |
+
howpublished = {\url{https://github.com/huggingface/trl}}
|
| 57 |
+
}
|
| 58 |
+
```
|
added_tokens.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|box_end|>": 151649,
|
| 5 |
+
"<|box_start|>": 151648,
|
| 6 |
+
"<|endoftext|>": 151643,
|
| 7 |
+
"<|file_sep|>": 151664,
|
| 8 |
+
"<|fim_middle|>": 151660,
|
| 9 |
+
"<|fim_pad|>": 151662,
|
| 10 |
+
"<|fim_prefix|>": 151659,
|
| 11 |
+
"<|fim_suffix|>": 151661,
|
| 12 |
+
"<|im_end|>": 151645,
|
| 13 |
+
"<|im_start|>": 151644,
|
| 14 |
+
"<|image_pad|>": 151655,
|
| 15 |
+
"<|object_ref_end|>": 151647,
|
| 16 |
+
"<|object_ref_start|>": 151646,
|
| 17 |
+
"<|quad_end|>": 151651,
|
| 18 |
+
"<|quad_start|>": 151650,
|
| 19 |
+
"<|repo_name|>": 151663,
|
| 20 |
+
"<|video_pad|>": 151656,
|
| 21 |
+
"<|vision_end|>": 151653,
|
| 22 |
+
"<|vision_pad|>": 151654,
|
| 23 |
+
"<|vision_start|>": 151652
|
| 24 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,331 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{#-
|
| 2 |
+
In addition to the normal inputs of `messages` and `tools`, this template also accepts the
|
| 3 |
+
following kwargs:
|
| 4 |
+
- "builtin_tools": A list, can contain "browser" and/or "python".
|
| 5 |
+
- "model_identity": A string that optionally describes the model identity.
|
| 6 |
+
- "reasoning_effort": A string that describes the reasoning effort, defaults to "medium".
|
| 7 |
+
#}
|
| 8 |
+
|
| 9 |
+
{#- Tool Definition Rendering ============================================== #}
|
| 10 |
+
{%- macro render_typescript_type(param_spec, required_params, is_nullable=false) -%}
|
| 11 |
+
{%- if param_spec.type == "array" -%}
|
| 12 |
+
{%- if param_spec['items'] -%}
|
| 13 |
+
{%- if param_spec['items']['type'] == "string" -%}
|
| 14 |
+
{{- "string[]" }}
|
| 15 |
+
{%- elif param_spec['items']['type'] == "number" -%}
|
| 16 |
+
{{- "number[]" }}
|
| 17 |
+
{%- elif param_spec['items']['type'] == "integer" -%}
|
| 18 |
+
{{- "number[]" }}
|
| 19 |
+
{%- elif param_spec['items']['type'] == "boolean" -%}
|
| 20 |
+
{{- "boolean[]" }}
|
| 21 |
+
{%- else -%}
|
| 22 |
+
{%- set inner_type = render_typescript_type(param_spec['items'], required_params) -%}
|
| 23 |
+
{%- if inner_type == "object | object" or inner_type|length > 50 -%}
|
| 24 |
+
{{- "any[]" }}
|
| 25 |
+
{%- else -%}
|
| 26 |
+
{{- inner_type + "[]" }}
|
| 27 |
+
{%- endif -%}
|
| 28 |
+
{%- endif -%}
|
| 29 |
+
{%- if param_spec.nullable -%}
|
| 30 |
+
{{- " | null" }}
|
| 31 |
+
{%- endif -%}
|
| 32 |
+
{%- else -%}
|
| 33 |
+
{{- "any[]" }}
|
| 34 |
+
{%- if param_spec.nullable -%}
|
| 35 |
+
{{- " | null" }}
|
| 36 |
+
{%- endif -%}
|
| 37 |
+
{%- endif -%}
|
| 38 |
+
{%- elif param_spec.type is defined and param_spec.type is iterable and param_spec.type is not string and param_spec.type is not mapping and param_spec.type[0] is defined -%}
|
| 39 |
+
{#- Handle array of types like ["object", "object"] from Union[dict, list] #}
|
| 40 |
+
{%- if param_spec.type | length > 1 -%}
|
| 41 |
+
{{- param_spec.type | join(" | ") }}
|
| 42 |
+
{%- else -%}
|
| 43 |
+
{{- param_spec.type[0] }}
|
| 44 |
+
{%- endif -%}
|
| 45 |
+
{%- elif param_spec.oneOf -%}
|
| 46 |
+
{#- Handle oneOf schemas - check for complex unions and fallback to any #}
|
| 47 |
+
{%- set has_object_variants = false -%}
|
| 48 |
+
{%- for variant in param_spec.oneOf -%}
|
| 49 |
+
{%- if variant.type == "object" -%}
|
| 50 |
+
{%- set has_object_variants = true -%}
|
| 51 |
+
{%- endif -%}
|
| 52 |
+
{%- endfor -%}
|
| 53 |
+
{%- if has_object_variants and param_spec.oneOf|length > 1 -%}
|
| 54 |
+
{{- "any" }}
|
| 55 |
+
{%- else -%}
|
| 56 |
+
{%- for variant in param_spec.oneOf -%}
|
| 57 |
+
{{- render_typescript_type(variant, required_params) -}}
|
| 58 |
+
{%- if variant.description %}
|
| 59 |
+
{{- "// " + variant.description }}
|
| 60 |
+
{%- endif -%}
|
| 61 |
+
{%- if variant.default is defined %}
|
| 62 |
+
{{ "// default: " + variant.default|tojson }}
|
| 63 |
+
{%- endif -%}
|
| 64 |
+
{%- if not loop.last %}
|
| 65 |
+
{{- " | " }}
|
| 66 |
+
{% endif -%}
|
| 67 |
+
{%- endfor -%}
|
| 68 |
+
{%- endif -%}
|
| 69 |
+
{%- elif param_spec.type == "string" -%}
|
| 70 |
+
{%- if param_spec.enum -%}
|
| 71 |
+
{{- '"' + param_spec.enum|join('" | "') + '"' -}}
|
| 72 |
+
{%- else -%}
|
| 73 |
+
{{- "string" }}
|
| 74 |
+
{%- if param_spec.nullable %}
|
| 75 |
+
{{- " | null" }}
|
| 76 |
+
{%- endif -%}
|
| 77 |
+
{%- endif -%}
|
| 78 |
+
{%- elif param_spec.type == "number" -%}
|
| 79 |
+
{{- "number" }}
|
| 80 |
+
{%- elif param_spec.type == "integer" -%}
|
| 81 |
+
{{- "number" }}
|
| 82 |
+
{%- elif param_spec.type == "boolean" -%}
|
| 83 |
+
{{- "boolean" }}
|
| 84 |
+
|
| 85 |
+
{%- elif param_spec.type == "object" -%}
|
| 86 |
+
{%- if param_spec.properties -%}
|
| 87 |
+
{{- "{\n" }}
|
| 88 |
+
{%- for prop_name, prop_spec in param_spec.properties.items() -%}
|
| 89 |
+
{{- prop_name -}}
|
| 90 |
+
{%- if prop_name not in (param_spec.required or []) -%}
|
| 91 |
+
{{- "?" }}
|
| 92 |
+
{%- endif -%}
|
| 93 |
+
{{- ": " }}
|
| 94 |
+
{{ render_typescript_type(prop_spec, param_spec.required or []) }}
|
| 95 |
+
{%- if not loop.last -%}
|
| 96 |
+
{{-", " }}
|
| 97 |
+
{%- endif -%}
|
| 98 |
+
{%- endfor -%}
|
| 99 |
+
{{- "}" }}
|
| 100 |
+
{%- else -%}
|
| 101 |
+
{{- "object" }}
|
| 102 |
+
{%- endif -%}
|
| 103 |
+
{%- else -%}
|
| 104 |
+
{{- "any" }}
|
| 105 |
+
{%- endif -%}
|
| 106 |
+
{%- endmacro -%}
|
| 107 |
+
|
| 108 |
+
{%- macro render_tool_namespace(namespace_name, tools) -%}
|
| 109 |
+
{{- "## " + namespace_name + "\n\n" }}
|
| 110 |
+
{{- "namespace " + namespace_name + " {\n\n" }}
|
| 111 |
+
{%- for tool in tools %}
|
| 112 |
+
{%- set tool = tool.function %}
|
| 113 |
+
{{- "// " + tool.description + "\n" }}
|
| 114 |
+
{{- "type "+ tool.name + " = " }}
|
| 115 |
+
{%- if tool.parameters and tool.parameters.properties %}
|
| 116 |
+
{{- "(_: {\n" }}
|
| 117 |
+
{%- for param_name, param_spec in tool.parameters.properties.items() %}
|
| 118 |
+
{%- if param_spec.description %}
|
| 119 |
+
{{- "// " + param_spec.description + "\n" }}
|
| 120 |
+
{%- endif %}
|
| 121 |
+
{{- param_name }}
|
| 122 |
+
{%- if param_name not in (tool.parameters.required or []) -%}
|
| 123 |
+
{{- "?" }}
|
| 124 |
+
{%- endif -%}
|
| 125 |
+
{{- ": " }}
|
| 126 |
+
{{- render_typescript_type(param_spec, tool.parameters.required or []) }}
|
| 127 |
+
{%- if param_spec.default is defined -%}
|
| 128 |
+
{%- if param_spec.enum %}
|
| 129 |
+
{{- ", // default: " + param_spec.default }}
|
| 130 |
+
{%- elif param_spec.oneOf %}
|
| 131 |
+
{{- "// default: " + param_spec.default }}
|
| 132 |
+
{%- else %}
|
| 133 |
+
{{- ", // default: " + param_spec.default|tojson }}
|
| 134 |
+
{%- endif -%}
|
| 135 |
+
{%- endif -%}
|
| 136 |
+
{%- if not loop.last %}
|
| 137 |
+
{{- ",\n" }}
|
| 138 |
+
{%- else %}
|
| 139 |
+
{{- ",\n" }}
|
| 140 |
+
{%- endif -%}
|
| 141 |
+
{%- endfor %}
|
| 142 |
+
{{- "}) => any;\n\n" }}
|
| 143 |
+
{%- else -%}
|
| 144 |
+
{{- "() => any;\n\n" }}
|
| 145 |
+
{%- endif -%}
|
| 146 |
+
{%- endfor %}
|
| 147 |
+
{{- "} // namespace " + namespace_name }}
|
| 148 |
+
{%- endmacro -%}
|
| 149 |
+
|
| 150 |
+
{%- macro render_builtin_tools(browser_tool, python_tool) -%}
|
| 151 |
+
{%- if browser_tool %}
|
| 152 |
+
{{- "## browser\n\n" }}
|
| 153 |
+
{{- "// Tool for browsing.\n" }}
|
| 154 |
+
{{- "// The `cursor` appears in brackets before each browsing display: `[{cursor}]`.\n" }}
|
| 155 |
+
{{- "// Cite information from the tool using the following format:\n" }}
|
| 156 |
+
{{- "// `【{cursor}†L{line_start}(-L{line_end})?】`, for example: `【6†L9-L11】` or `【8†L3】`.\n" }}
|
| 157 |
+
{{- "// Do not quote more than 10 words directly from the tool output.\n" }}
|
| 158 |
+
{{- "// sources=web (default: web)\n" }}
|
| 159 |
+
{{- "namespace browser {\n\n" }}
|
| 160 |
+
{{- "// Searches for information related to `query` and displays `topn` results.\n" }}
|
| 161 |
+
{{- "type search = (_: {\n" }}
|
| 162 |
+
{{- "query: string,\n" }}
|
| 163 |
+
{{- "topn?: number, // default: 10\n" }}
|
| 164 |
+
{{- "source?: string,\n" }}
|
| 165 |
+
{{- "}) => any;\n\n" }}
|
| 166 |
+
{{- "// Opens the link `id` from the page indicated by `cursor` starting at line number `loc`, showing `num_lines` lines.\n" }}
|
| 167 |
+
{{- "// Valid link ids are displayed with the formatting: `【{id}†.*】`.\n" }}
|
| 168 |
+
{{- "// If `cursor` is not provided, the most recent page is implied.\n" }}
|
| 169 |
+
{{- "// If `id` is a string, it is treated as a fully qualified URL associated with `source`.\n" }}
|
| 170 |
+
{{- "// If `loc` is not provided, the viewport will be positioned at the beginning of the document or centered on the most relevant passage, if available.\n" }}
|
| 171 |
+
{{- "// Use this function without `id` to scroll to a new location of an opened page.\n" }}
|
| 172 |
+
{{- "type open = (_: {\n" }}
|
| 173 |
+
{{- "id?: number | string, // default: -1\n" }}
|
| 174 |
+
{{- "cursor?: number, // default: -1\n" }}
|
| 175 |
+
{{- "loc?: number, // default: -1\n" }}
|
| 176 |
+
{{- "num_lines?: number, // default: -1\n" }}
|
| 177 |
+
{{- "view_source?: boolean, // default: false\n" }}
|
| 178 |
+
{{- "source?: string,\n" }}
|
| 179 |
+
{{- "}) => any;\n\n" }}
|
| 180 |
+
{{- "// Finds exact matches of `pattern` in the current page, or the page given by `cursor`.\n" }}
|
| 181 |
+
{{- "type find = (_: {\n" }}
|
| 182 |
+
{{- "pattern: string,\n" }}
|
| 183 |
+
{{- "cursor?: number, // default: -1\n" }}
|
| 184 |
+
{{- "}) => any;\n\n" }}
|
| 185 |
+
{{- "} // namespace browser\n\n" }}
|
| 186 |
+
{%- endif -%}
|
| 187 |
+
|
| 188 |
+
{%- if python_tool %}
|
| 189 |
+
{{- "## python\n\n" }}
|
| 190 |
+
{{- "Use this tool to execute Python code in your chain of thought. The code will not be shown to the user. This tool should be used for internal reasoning, but not for code that is intended to be visible to the user (e.g. when creating plots, tables, or files).\n\n" }}
|
| 191 |
+
{{- "When you send a message containing Python code to python, it will be executed in a stateful Jupyter notebook environment. python will respond with the output of the execution or time out after 120.0 seconds. The drive at '/mnt/data' can be used to save and persist user files. Internet access for this session is UNKNOWN. Depends on the cluster.\n\n" }}
|
| 192 |
+
{%- endif -%}
|
| 193 |
+
{%- endmacro -%}
|
| 194 |
+
|
| 195 |
+
{#- System Message Construction ============================================ #}
|
| 196 |
+
{%- macro build_system_message() -%}
|
| 197 |
+
{%- if model_identity is not defined %}
|
| 198 |
+
{%- set model_identity = "You are ChatGPT, a large language model trained by OpenAI." %}
|
| 199 |
+
{%- endif %}
|
| 200 |
+
{{- model_identity + "\n" }}
|
| 201 |
+
{{- "Knowledge cutoff: 2024-06\n" }}
|
| 202 |
+
{{- "Current date: " + strftime_now("%Y-%m-%d") + "\n\n" }}
|
| 203 |
+
{%- if reasoning_effort is not defined %}
|
| 204 |
+
{%- set reasoning_effort = "medium" %}
|
| 205 |
+
{%- endif %}
|
| 206 |
+
{{- "Reasoning: " + reasoning_effort + "\n\n" }}
|
| 207 |
+
{%- if builtin_tools %}
|
| 208 |
+
{{- "# Tools\n\n" }}
|
| 209 |
+
{%- set available_builtin_tools = namespace(browser=false, python=false) %}
|
| 210 |
+
{%- for tool in builtin_tools %}
|
| 211 |
+
{%- if tool == "browser" %}
|
| 212 |
+
{%- set available_builtin_tools.browser = true %}
|
| 213 |
+
{%- elif tool == "python" %}
|
| 214 |
+
{%- set available_builtin_tools.python = true %}
|
| 215 |
+
{%- endif %}
|
| 216 |
+
{%- endfor %}
|
| 217 |
+
{{- render_builtin_tools(available_builtin_tools.browser, available_builtin_tools.python) }}
|
| 218 |
+
{%- endif -%}
|
| 219 |
+
{{- "# Valid channels: analysis, commentary, final. Channel must be included for every message." }}
|
| 220 |
+
{%- if tools -%}
|
| 221 |
+
{{- "\nCalls to these tools must go to the commentary channel: 'functions'." }}
|
| 222 |
+
{%- endif -%}
|
| 223 |
+
{%- endmacro -%}
|
| 224 |
+
|
| 225 |
+
{#- Main Template Logic ================================================= #}
|
| 226 |
+
{#- Set defaults #}
|
| 227 |
+
|
| 228 |
+
{#- Render system message #}
|
| 229 |
+
{{- "<|start|>system<|message|>" }}
|
| 230 |
+
{{- build_system_message() }}
|
| 231 |
+
{{- "<|end|>" }}
|
| 232 |
+
|
| 233 |
+
{#- Extract developer message #}
|
| 234 |
+
{%- if messages[0].role == "developer" or messages[0].role == "system" %}
|
| 235 |
+
{%- set developer_message = messages[0].content %}
|
| 236 |
+
{%- set loop_messages = messages[1:] %}
|
| 237 |
+
{%- else %}
|
| 238 |
+
{%- set developer_message = "" %}
|
| 239 |
+
{%- set loop_messages = messages %}
|
| 240 |
+
{%- endif %}
|
| 241 |
+
|
| 242 |
+
{#- Render developer message #}
|
| 243 |
+
{%- if developer_message or tools %}
|
| 244 |
+
{{- "<|start|>developer<|message|>" }}
|
| 245 |
+
{%- if developer_message %}
|
| 246 |
+
{{- "# Instructions\n\n" }}
|
| 247 |
+
{{- developer_message }}
|
| 248 |
+
{{- "\n\n" }}
|
| 249 |
+
{%- endif %}
|
| 250 |
+
{%- if tools -%}
|
| 251 |
+
{{- "# Tools\n\n" }}
|
| 252 |
+
{{- render_tool_namespace("functions", tools) }}
|
| 253 |
+
{%- endif -%}
|
| 254 |
+
{{- "<|end|>" }}
|
| 255 |
+
{%- endif %}
|
| 256 |
+
|
| 257 |
+
{#- Render messages #}
|
| 258 |
+
{%- set last_tool_call = namespace(name=none) %}
|
| 259 |
+
{%- for message in loop_messages -%}
|
| 260 |
+
{#- At this point only assistant/user/tool messages should remain #}
|
| 261 |
+
{%- if message.role == 'assistant' -%}
|
| 262 |
+
{#- Checks to ensure the messages are being passed in the format we expect #}
|
| 263 |
+
{%- if "content" in message %}
|
| 264 |
+
{%- if "<|channel|>analysis<|message|>" in message.content or "<|channel|>final<|message|>" in message.content %}
|
| 265 |
+
{{- raise_exception("You have passed a message containing <|channel|> tags in the content field. Instead of doing this, you should pass analysis messages (the string between '<|message|>' and '<|end|>') in the 'thinking' field, and final messages (the string between '<|message|>' and '<|end|>') in the 'content' field.") }}
|
| 266 |
+
{%- endif %}
|
| 267 |
+
{%- endif %}
|
| 268 |
+
{%- if "thinking" in message %}
|
| 269 |
+
{%- if "<|channel|>analysis<|message|>" in message.thinking or "<|channel|>final<|message|>" in message.thinking %}
|
| 270 |
+
{{- raise_exception("You have passed a message containing <|channel|> tags in the thinking field. Instead of doing this, you should pass analysis messages (the string between '<|message|>' and '<|end|>') in the 'thinking' field, and final messages (the string between '<|message|>' and '<|end|>') in the 'content' field.") }}
|
| 271 |
+
{%- endif %}
|
| 272 |
+
{%- endif %}
|
| 273 |
+
{%- if "tool_calls" in message %}
|
| 274 |
+
{#- We need very careful handling here - we want to drop the tool call analysis message if the model #}
|
| 275 |
+
{#- has output a later <|final|> message, but otherwise we want to retain it. This is the only case #}
|
| 276 |
+
{#- when we render CoT/analysis messages in inference. #}
|
| 277 |
+
{%- set future_final_message = namespace(found=false) %}
|
| 278 |
+
{%- for future_message in loop_messages[loop.index:] %}
|
| 279 |
+
{%- if future_message.role == 'assistant' and "tool_calls" not in future_message %}
|
| 280 |
+
{%- set future_final_message.found = true %}
|
| 281 |
+
{%- endif %}
|
| 282 |
+
{%- endfor %}
|
| 283 |
+
{#- We assume max 1 tool call per message, and so we infer the tool call name #}
|
| 284 |
+
{#- in "tool" messages from the most recent assistant tool call name #}
|
| 285 |
+
{%- set tool_call = message.tool_calls[0] %}
|
| 286 |
+
{%- if tool_call.function %}
|
| 287 |
+
{%- set tool_call = tool_call.function %}
|
| 288 |
+
{%- endif %}
|
| 289 |
+
{%- if message.content and message.thinking %}
|
| 290 |
+
{{- raise_exception("Cannot pass both content and thinking in an assistant message with tool calls! Put the analysis message in one or the other, but not both.") }}
|
| 291 |
+
{%- elif message.content and not future_final_message.found %}
|
| 292 |
+
{{- "<|start|>assistant<|channel|>analysis<|message|>" + message.content + "<|end|>" }}
|
| 293 |
+
{%- elif message.thinking and not future_final_message.found %}
|
| 294 |
+
{{- "<|start|>assistant<|channel|>analysis<|message|>" + message.thinking + "<|end|>" }}
|
| 295 |
+
{%- endif %}
|
| 296 |
+
{{- "<|start|>assistant to=" }}
|
| 297 |
+
{{- "functions." + tool_call.name + "<|channel|>commentary " }}
|
| 298 |
+
{{- (tool_call.content_type if tool_call.content_type is defined else "json") + "<|message|>" }}
|
| 299 |
+
{{- tool_call.arguments|tojson }}
|
| 300 |
+
{{- "<|call|>" }}
|
| 301 |
+
{%- set last_tool_call.name = tool_call.name %}
|
| 302 |
+
{%- elif loop.last and not add_generation_prompt %}
|
| 303 |
+
{#- Only render the CoT if the final turn is an assistant turn and add_generation_prompt is false #}
|
| 304 |
+
{#- This is a situation that should only occur in training, never in inference. #}
|
| 305 |
+
{%- if "thinking" in message %}
|
| 306 |
+
{{- "<|start|>assistant<|channel|>analysis<|message|>" + message.thinking + "<|end|>" }}
|
| 307 |
+
{%- endif %}
|
| 308 |
+
{#- <|return|> indicates the end of generation, but <|end|> does not #}
|
| 309 |
+
{#- <|return|> should never be an input to the model, but we include it as the final token #}
|
| 310 |
+
{#- when training, so the model learns to emit it. #}
|
| 311 |
+
{{- "<|start|>assistant<|channel|>final<|message|>" + message.content + "<|return|>" }}
|
| 312 |
+
{%- else %}
|
| 313 |
+
{#- CoT is dropped during all previous turns, so we never render it for inference #}
|
| 314 |
+
{{- "<|start|>assistant<|channel|>final<|message|>" + message.content + "<|end|>" }}
|
| 315 |
+
{%- set last_tool_call.name = none %}
|
| 316 |
+
{%- endif %}
|
| 317 |
+
{%- elif message.role == 'tool' -%}
|
| 318 |
+
{%- if last_tool_call.name is none %}
|
| 319 |
+
{{- raise_exception("Message has tool role, but there was no previous assistant message with a tool call!") }}
|
| 320 |
+
{%- endif %}
|
| 321 |
+
{{- "<|start|>functions." + last_tool_call.name }}
|
| 322 |
+
{{- " to=assistant<|channel|>commentary<|message|>" + message.content|tojson + "<|end|>" }}
|
| 323 |
+
{%- elif message.role == 'user' -%}
|
| 324 |
+
{{- "<|start|>user<|message|>" + message.content + "<|end|>" }}
|
| 325 |
+
{%- endif -%}
|
| 326 |
+
{%- endfor -%}
|
| 327 |
+
|
| 328 |
+
{#- Generation prompt #}
|
| 329 |
+
{%- if add_generation_prompt -%}
|
| 330 |
+
<|start|>assistant
|
| 331 |
+
{%- endif -%}
|
checkpoint-300/README.md
ADDED
|
@@ -0,0 +1,209 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Qwen/Qwen2.5-7B-Instruct
|
| 3 |
+
library_name: peft
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
- base_model:adapter:Qwen/Qwen2.5-7B-Instruct
|
| 7 |
+
- lora
|
| 8 |
+
- sft
|
| 9 |
+
- transformers
|
| 10 |
+
- trl
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
# Model Card for Model ID
|
| 14 |
+
|
| 15 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
## Model Details
|
| 20 |
+
|
| 21 |
+
### Model Description
|
| 22 |
+
|
| 23 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
|
| 27 |
+
- **Developed by:** [More Information Needed]
|
| 28 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 29 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 30 |
+
- **Model type:** [More Information Needed]
|
| 31 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 32 |
+
- **License:** [More Information Needed]
|
| 33 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 34 |
+
|
| 35 |
+
### Model Sources [optional]
|
| 36 |
+
|
| 37 |
+
<!-- Provide the basic links for the model. -->
|
| 38 |
+
|
| 39 |
+
- **Repository:** [More Information Needed]
|
| 40 |
+
- **Paper [optional]:** [More Information Needed]
|
| 41 |
+
- **Demo [optional]:** [More Information Needed]
|
| 42 |
+
|
| 43 |
+
## Uses
|
| 44 |
+
|
| 45 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 46 |
+
|
| 47 |
+
### Direct Use
|
| 48 |
+
|
| 49 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 50 |
+
|
| 51 |
+
[More Information Needed]
|
| 52 |
+
|
| 53 |
+
### Downstream Use [optional]
|
| 54 |
+
|
| 55 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 56 |
+
|
| 57 |
+
[More Information Needed]
|
| 58 |
+
|
| 59 |
+
### Out-of-Scope Use
|
| 60 |
+
|
| 61 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 62 |
+
|
| 63 |
+
[More Information Needed]
|
| 64 |
+
|
| 65 |
+
## Bias, Risks, and Limitations
|
| 66 |
+
|
| 67 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 68 |
+
|
| 69 |
+
[More Information Needed]
|
| 70 |
+
|
| 71 |
+
### Recommendations
|
| 72 |
+
|
| 73 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 74 |
+
|
| 75 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 76 |
+
|
| 77 |
+
## How to Get Started with the Model
|
| 78 |
+
|
| 79 |
+
Use the code below to get started with the model.
|
| 80 |
+
|
| 81 |
+
[More Information Needed]
|
| 82 |
+
|
| 83 |
+
## Training Details
|
| 84 |
+
|
| 85 |
+
### Training Data
|
| 86 |
+
|
| 87 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 88 |
+
|
| 89 |
+
[More Information Needed]
|
| 90 |
+
|
| 91 |
+
### Training Procedure
|
| 92 |
+
|
| 93 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 94 |
+
|
| 95 |
+
#### Preprocessing [optional]
|
| 96 |
+
|
| 97 |
+
[More Information Needed]
|
| 98 |
+
|
| 99 |
+
|
| 100 |
+
#### Training Hyperparameters
|
| 101 |
+
|
| 102 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 103 |
+
|
| 104 |
+
#### Speeds, Sizes, Times [optional]
|
| 105 |
+
|
| 106 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 107 |
+
|
| 108 |
+
[More Information Needed]
|
| 109 |
+
|
| 110 |
+
## Evaluation
|
| 111 |
+
|
| 112 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 113 |
+
|
| 114 |
+
### Testing Data, Factors & Metrics
|
| 115 |
+
|
| 116 |
+
#### Testing Data
|
| 117 |
+
|
| 118 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 119 |
+
|
| 120 |
+
[More Information Needed]
|
| 121 |
+
|
| 122 |
+
#### Factors
|
| 123 |
+
|
| 124 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 125 |
+
|
| 126 |
+
[More Information Needed]
|
| 127 |
+
|
| 128 |
+
#### Metrics
|
| 129 |
+
|
| 130 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 131 |
+
|
| 132 |
+
[More Information Needed]
|
| 133 |
+
|
| 134 |
+
### Results
|
| 135 |
+
|
| 136 |
+
[More Information Needed]
|
| 137 |
+
|
| 138 |
+
#### Summary
|
| 139 |
+
|
| 140 |
+
|
| 141 |
+
|
| 142 |
+
## Model Examination [optional]
|
| 143 |
+
|
| 144 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 145 |
+
|
| 146 |
+
[More Information Needed]
|
| 147 |
+
|
| 148 |
+
## Environmental Impact
|
| 149 |
+
|
| 150 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 151 |
+
|
| 152 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 153 |
+
|
| 154 |
+
- **Hardware Type:** [More Information Needed]
|
| 155 |
+
- **Hours used:** [More Information Needed]
|
| 156 |
+
- **Cloud Provider:** [More Information Needed]
|
| 157 |
+
- **Compute Region:** [More Information Needed]
|
| 158 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 159 |
+
|
| 160 |
+
## Technical Specifications [optional]
|
| 161 |
+
|
| 162 |
+
### Model Architecture and Objective
|
| 163 |
+
|
| 164 |
+
[More Information Needed]
|
| 165 |
+
|
| 166 |
+
### Compute Infrastructure
|
| 167 |
+
|
| 168 |
+
[More Information Needed]
|
| 169 |
+
|
| 170 |
+
#### Hardware
|
| 171 |
+
|
| 172 |
+
[More Information Needed]
|
| 173 |
+
|
| 174 |
+
#### Software
|
| 175 |
+
|
| 176 |
+
[More Information Needed]
|
| 177 |
+
|
| 178 |
+
## Citation [optional]
|
| 179 |
+
|
| 180 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 181 |
+
|
| 182 |
+
**BibTeX:**
|
| 183 |
+
|
| 184 |
+
[More Information Needed]
|
| 185 |
+
|
| 186 |
+
**APA:**
|
| 187 |
+
|
| 188 |
+
[More Information Needed]
|
| 189 |
+
|
| 190 |
+
## Glossary [optional]
|
| 191 |
+
|
| 192 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 193 |
+
|
| 194 |
+
[More Information Needed]
|
| 195 |
+
|
| 196 |
+
## More Information [optional]
|
| 197 |
+
|
| 198 |
+
[More Information Needed]
|
| 199 |
+
|
| 200 |
+
## Model Card Authors [optional]
|
| 201 |
+
|
| 202 |
+
[More Information Needed]
|
| 203 |
+
|
| 204 |
+
## Model Card Contact
|
| 205 |
+
|
| 206 |
+
[More Information Needed]
|
| 207 |
+
### Framework versions
|
| 208 |
+
|
| 209 |
+
- PEFT 0.17.1
|
checkpoint-300/adapter_config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 64,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.1,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"qalora_group_size": 16,
|
| 24 |
+
"r": 64,
|
| 25 |
+
"rank_pattern": {},
|
| 26 |
+
"revision": null,
|
| 27 |
+
"target_modules": [
|
| 28 |
+
"v_proj",
|
| 29 |
+
"o_proj",
|
| 30 |
+
"q_proj",
|
| 31 |
+
"k_proj",
|
| 32 |
+
"down_proj",
|
| 33 |
+
"up_proj",
|
| 34 |
+
"gate_proj"
|
| 35 |
+
],
|
| 36 |
+
"target_parameters": null,
|
| 37 |
+
"task_type": "CAUSAL_LM",
|
| 38 |
+
"trainable_token_indices": null,
|
| 39 |
+
"use_dora": false,
|
| 40 |
+
"use_qalora": false,
|
| 41 |
+
"use_rslora": false
|
| 42 |
+
}
|
checkpoint-300/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:97bd493654b196ece7e5697a186a971485c7a5edfd9a9f9bdcc446d31d01784d
|
| 3 |
+
size 645975704
|
checkpoint-300/added_tokens.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|box_end|>": 151649,
|
| 5 |
+
"<|box_start|>": 151648,
|
| 6 |
+
"<|endoftext|>": 151643,
|
| 7 |
+
"<|file_sep|>": 151664,
|
| 8 |
+
"<|fim_middle|>": 151660,
|
| 9 |
+
"<|fim_pad|>": 151662,
|
| 10 |
+
"<|fim_prefix|>": 151659,
|
| 11 |
+
"<|fim_suffix|>": 151661,
|
| 12 |
+
"<|im_end|>": 151645,
|
| 13 |
+
"<|im_start|>": 151644,
|
| 14 |
+
"<|image_pad|>": 151655,
|
| 15 |
+
"<|object_ref_end|>": 151647,
|
| 16 |
+
"<|object_ref_start|>": 151646,
|
| 17 |
+
"<|quad_end|>": 151651,
|
| 18 |
+
"<|quad_start|>": 151650,
|
| 19 |
+
"<|repo_name|>": 151663,
|
| 20 |
+
"<|video_pad|>": 151656,
|
| 21 |
+
"<|vision_end|>": 151653,
|
| 22 |
+
"<|vision_pad|>": 151654,
|
| 23 |
+
"<|vision_start|>": 151652
|
| 24 |
+
}
|
checkpoint-300/chat_template.jinja
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 4 |
+
{{- messages[0]['content'] }}
|
| 5 |
+
{%- else %}
|
| 6 |
+
{{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
|
| 7 |
+
{%- endif %}
|
| 8 |
+
{{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 9 |
+
{%- for tool in tools %}
|
| 10 |
+
{{- "\n" }}
|
| 11 |
+
{{- tool | tojson }}
|
| 12 |
+
{%- endfor %}
|
| 13 |
+
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 14 |
+
{%- else %}
|
| 15 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 16 |
+
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
|
| 17 |
+
{%- else %}
|
| 18 |
+
{{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
|
| 19 |
+
{%- endif %}
|
| 20 |
+
{%- endif %}
|
| 21 |
+
{%- for message in messages %}
|
| 22 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
| 23 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
| 24 |
+
{%- elif message.role == "assistant" %}
|
| 25 |
+
{{- '<|im_start|>' + message.role }}
|
| 26 |
+
{%- if message.content %}
|
| 27 |
+
{{- '\n' + message.content }}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{%- for tool_call in message.tool_calls %}
|
| 30 |
+
{%- if tool_call.function is defined %}
|
| 31 |
+
{%- set tool_call = tool_call.function %}
|
| 32 |
+
{%- endif %}
|
| 33 |
+
{{- '\n<tool_call>\n{"name": "' }}
|
| 34 |
+
{{- tool_call.name }}
|
| 35 |
+
{{- '", "arguments": ' }}
|
| 36 |
+
{{- tool_call.arguments | tojson }}
|
| 37 |
+
{{- '}\n</tool_call>' }}
|
| 38 |
+
{%- endfor %}
|
| 39 |
+
{{- '<|im_end|>\n' }}
|
| 40 |
+
{%- elif message.role == "tool" %}
|
| 41 |
+
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
|
| 42 |
+
{{- '<|im_start|>user' }}
|
| 43 |
+
{%- endif %}
|
| 44 |
+
{{- '\n<tool_response>\n' }}
|
| 45 |
+
{{- message.content }}
|
| 46 |
+
{{- '\n</tool_response>' }}
|
| 47 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 48 |
+
{{- '<|im_end|>\n' }}
|
| 49 |
+
{%- endif %}
|
| 50 |
+
{%- endif %}
|
| 51 |
+
{%- endfor %}
|
| 52 |
+
{%- if add_generation_prompt %}
|
| 53 |
+
{{- '<|im_start|>assistant\n' }}
|
| 54 |
+
{%- endif %}
|
checkpoint-300/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-300/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fcdbff5c0b18f69a32415e63f46cedd84dc449061240416429db5a60c3bfd75d
|
| 3 |
+
size 1292182139
|
checkpoint-300/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:47aad30eba6947da47bec58af0eabbba394fed1fbffd0477fedd282ad31f3bc5
|
| 3 |
+
size 14645
|
checkpoint-300/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d15d3d1b8bb19162d239033d431d77f4eba28beb04ec2c0ba04b41fbc223a133
|
| 3 |
+
size 1465
|
checkpoint-300/special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
checkpoint-300/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
| 3 |
+
size 11421896
|
checkpoint-300/tokenizer_config.json
ADDED
|
@@ -0,0 +1,207 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
}
|
| 181 |
+
},
|
| 182 |
+
"additional_special_tokens": [
|
| 183 |
+
"<|im_start|>",
|
| 184 |
+
"<|im_end|>",
|
| 185 |
+
"<|object_ref_start|>",
|
| 186 |
+
"<|object_ref_end|>",
|
| 187 |
+
"<|box_start|>",
|
| 188 |
+
"<|box_end|>",
|
| 189 |
+
"<|quad_start|>",
|
| 190 |
+
"<|quad_end|>",
|
| 191 |
+
"<|vision_start|>",
|
| 192 |
+
"<|vision_end|>",
|
| 193 |
+
"<|vision_pad|>",
|
| 194 |
+
"<|image_pad|>",
|
| 195 |
+
"<|video_pad|>"
|
| 196 |
+
],
|
| 197 |
+
"bos_token": null,
|
| 198 |
+
"clean_up_tokenization_spaces": false,
|
| 199 |
+
"eos_token": "<|im_end|>",
|
| 200 |
+
"errors": "replace",
|
| 201 |
+
"extra_special_tokens": {},
|
| 202 |
+
"model_max_length": 131072,
|
| 203 |
+
"pad_token": "<|endoftext|>",
|
| 204 |
+
"split_special_tokens": false,
|
| 205 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 206 |
+
"unk_token": null
|
| 207 |
+
}
|
checkpoint-300/trainer_state.json
ADDED
|
@@ -0,0 +1,3034 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 15.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 300,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"entropy": 1.3481858372688293,
|
| 14 |
+
"epoch": 0.050955414012738856,
|
| 15 |
+
"grad_norm": 0.42022356390953064,
|
| 16 |
+
"learning_rate": 0.0,
|
| 17 |
+
"loss": 1.5404,
|
| 18 |
+
"mean_token_accuracy": 0.6100348308682442,
|
| 19 |
+
"num_tokens": 16370.0,
|
| 20 |
+
"step": 1
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"entropy": 1.2509200274944305,
|
| 24 |
+
"epoch": 0.10191082802547771,
|
| 25 |
+
"grad_norm": 0.37541937828063965,
|
| 26 |
+
"learning_rate": 4e-05,
|
| 27 |
+
"loss": 1.4171,
|
| 28 |
+
"mean_token_accuracy": 0.637866273522377,
|
| 29 |
+
"num_tokens": 32126.0,
|
| 30 |
+
"step": 2
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"entropy": 1.2236506044864655,
|
| 34 |
+
"epoch": 0.15286624203821655,
|
| 35 |
+
"grad_norm": 0.3010457754135132,
|
| 36 |
+
"learning_rate": 8e-05,
|
| 37 |
+
"loss": 1.3236,
|
| 38 |
+
"mean_token_accuracy": 0.6549251675605774,
|
| 39 |
+
"num_tokens": 48510.0,
|
| 40 |
+
"step": 3
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"entropy": 1.3142070770263672,
|
| 44 |
+
"epoch": 0.20382165605095542,
|
| 45 |
+
"grad_norm": 0.2625364661216736,
|
| 46 |
+
"learning_rate": 0.00012,
|
| 47 |
+
"loss": 1.3343,
|
| 48 |
+
"mean_token_accuracy": 0.6495203450322151,
|
| 49 |
+
"num_tokens": 64106.0,
|
| 50 |
+
"step": 4
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"entropy": 1.3711989670991898,
|
| 54 |
+
"epoch": 0.25477707006369427,
|
| 55 |
+
"grad_norm": 0.2332204282283783,
|
| 56 |
+
"learning_rate": 0.00016,
|
| 57 |
+
"loss": 1.3073,
|
| 58 |
+
"mean_token_accuracy": 0.654352568089962,
|
| 59 |
+
"num_tokens": 80490.0,
|
| 60 |
+
"step": 5
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"entropy": 1.30281962454319,
|
| 64 |
+
"epoch": 0.3057324840764331,
|
| 65 |
+
"grad_norm": 0.27727022767066956,
|
| 66 |
+
"learning_rate": 0.0002,
|
| 67 |
+
"loss": 1.1383,
|
| 68 |
+
"mean_token_accuracy": 0.6825252249836922,
|
| 69 |
+
"num_tokens": 96874.0,
|
| 70 |
+
"step": 6
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"entropy": 1.440766528248787,
|
| 74 |
+
"epoch": 0.35668789808917195,
|
| 75 |
+
"grad_norm": 0.38116148114204407,
|
| 76 |
+
"learning_rate": 0.0001993220338983051,
|
| 77 |
+
"loss": 1.2144,
|
| 78 |
+
"mean_token_accuracy": 0.6650549918413162,
|
| 79 |
+
"num_tokens": 113258.0,
|
| 80 |
+
"step": 7
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"entropy": 1.2435247004032135,
|
| 84 |
+
"epoch": 0.40764331210191085,
|
| 85 |
+
"grad_norm": 0.27608051896095276,
|
| 86 |
+
"learning_rate": 0.00019864406779661017,
|
| 87 |
+
"loss": 1.1114,
|
| 88 |
+
"mean_token_accuracy": 0.6855753660202026,
|
| 89 |
+
"num_tokens": 129642.0,
|
| 90 |
+
"step": 8
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"entropy": 1.2537222802639008,
|
| 94 |
+
"epoch": 0.4585987261146497,
|
| 95 |
+
"grad_norm": 0.23021401464939117,
|
| 96 |
+
"learning_rate": 0.00019796610169491526,
|
| 97 |
+
"loss": 1.1577,
|
| 98 |
+
"mean_token_accuracy": 0.676470473408699,
|
| 99 |
+
"num_tokens": 145665.0,
|
| 100 |
+
"step": 9
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"entropy": 1.1785454452037811,
|
| 104 |
+
"epoch": 0.5095541401273885,
|
| 105 |
+
"grad_norm": 0.2424541562795639,
|
| 106 |
+
"learning_rate": 0.00019728813559322035,
|
| 107 |
+
"loss": 1.1131,
|
| 108 |
+
"mean_token_accuracy": 0.6807782724499702,
|
| 109 |
+
"num_tokens": 161676.0,
|
| 110 |
+
"step": 10
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"entropy": 1.1859825029969215,
|
| 114 |
+
"epoch": 0.5605095541401274,
|
| 115 |
+
"grad_norm": 0.23673631250858307,
|
| 116 |
+
"learning_rate": 0.00019661016949152545,
|
| 117 |
+
"loss": 1.1231,
|
| 118 |
+
"mean_token_accuracy": 0.6809910237789154,
|
| 119 |
+
"num_tokens": 178060.0,
|
| 120 |
+
"step": 11
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"entropy": 1.199895717203617,
|
| 124 |
+
"epoch": 0.6114649681528662,
|
| 125 |
+
"grad_norm": 0.22655269503593445,
|
| 126 |
+
"learning_rate": 0.0001959322033898305,
|
| 127 |
+
"loss": 1.1237,
|
| 128 |
+
"mean_token_accuracy": 0.6825583502650261,
|
| 129 |
+
"num_tokens": 193801.0,
|
| 130 |
+
"step": 12
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"entropy": 1.1316778659820557,
|
| 134 |
+
"epoch": 0.6624203821656051,
|
| 135 |
+
"grad_norm": 0.1964697539806366,
|
| 136 |
+
"learning_rate": 0.0001952542372881356,
|
| 137 |
+
"loss": 1.0177,
|
| 138 |
+
"mean_token_accuracy": 0.7018924430012703,
|
| 139 |
+
"num_tokens": 210117.0,
|
| 140 |
+
"step": 13
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"entropy": 1.2201827466487885,
|
| 144 |
+
"epoch": 0.7133757961783439,
|
| 145 |
+
"grad_norm": 0.2558380961418152,
|
| 146 |
+
"learning_rate": 0.0001945762711864407,
|
| 147 |
+
"loss": 1.1021,
|
| 148 |
+
"mean_token_accuracy": 0.6867032945156097,
|
| 149 |
+
"num_tokens": 226501.0,
|
| 150 |
+
"step": 14
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"entropy": 1.2256827503442764,
|
| 154 |
+
"epoch": 0.7643312101910829,
|
| 155 |
+
"grad_norm": 0.24053122103214264,
|
| 156 |
+
"learning_rate": 0.0001938983050847458,
|
| 157 |
+
"loss": 1.0771,
|
| 158 |
+
"mean_token_accuracy": 0.6895216032862663,
|
| 159 |
+
"num_tokens": 242576.0,
|
| 160 |
+
"step": 15
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"entropy": 1.1773390918970108,
|
| 164 |
+
"epoch": 0.8152866242038217,
|
| 165 |
+
"grad_norm": 0.23696200549602509,
|
| 166 |
+
"learning_rate": 0.00019322033898305085,
|
| 167 |
+
"loss": 1.0436,
|
| 168 |
+
"mean_token_accuracy": 0.7001483887434006,
|
| 169 |
+
"num_tokens": 258960.0,
|
| 170 |
+
"step": 16
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"entropy": 1.2502182573080063,
|
| 174 |
+
"epoch": 0.8662420382165605,
|
| 175 |
+
"grad_norm": 0.2583620250225067,
|
| 176 |
+
"learning_rate": 0.00019254237288135595,
|
| 177 |
+
"loss": 1.0969,
|
| 178 |
+
"mean_token_accuracy": 0.6846700087189674,
|
| 179 |
+
"num_tokens": 275344.0,
|
| 180 |
+
"step": 17
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"entropy": 1.1538116410374641,
|
| 184 |
+
"epoch": 0.9171974522292994,
|
| 185 |
+
"grad_norm": 0.22091548144817352,
|
| 186 |
+
"learning_rate": 0.000191864406779661,
|
| 187 |
+
"loss": 1.0384,
|
| 188 |
+
"mean_token_accuracy": 0.7043633460998535,
|
| 189 |
+
"num_tokens": 291212.0,
|
| 190 |
+
"step": 18
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"entropy": 1.0872942060232162,
|
| 194 |
+
"epoch": 0.9681528662420382,
|
| 195 |
+
"grad_norm": 0.21255861222743988,
|
| 196 |
+
"learning_rate": 0.0001911864406779661,
|
| 197 |
+
"loss": 1.0042,
|
| 198 |
+
"mean_token_accuracy": 0.7119970843195915,
|
| 199 |
+
"num_tokens": 307596.0,
|
| 200 |
+
"step": 19
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"entropy": 1.079186463356018,
|
| 204 |
+
"epoch": 1.0,
|
| 205 |
+
"grad_norm": 0.2622547149658203,
|
| 206 |
+
"learning_rate": 0.0001905084745762712,
|
| 207 |
+
"loss": 0.9877,
|
| 208 |
+
"mean_token_accuracy": 0.7082325220108032,
|
| 209 |
+
"num_tokens": 316575.0,
|
| 210 |
+
"step": 20
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"entropy": 1.042311891913414,
|
| 214 |
+
"epoch": 1.0509554140127388,
|
| 215 |
+
"grad_norm": 0.2054571956396103,
|
| 216 |
+
"learning_rate": 0.0001898305084745763,
|
| 217 |
+
"loss": 0.9347,
|
| 218 |
+
"mean_token_accuracy": 0.7204505205154419,
|
| 219 |
+
"num_tokens": 332686.0,
|
| 220 |
+
"step": 21
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"entropy": 1.0129416584968567,
|
| 224 |
+
"epoch": 1.1019108280254777,
|
| 225 |
+
"grad_norm": 0.20944714546203613,
|
| 226 |
+
"learning_rate": 0.00018915254237288136,
|
| 227 |
+
"loss": 0.8911,
|
| 228 |
+
"mean_token_accuracy": 0.7332312241196632,
|
| 229 |
+
"num_tokens": 349070.0,
|
| 230 |
+
"step": 22
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"entropy": 1.0294566750526428,
|
| 234 |
+
"epoch": 1.1528662420382165,
|
| 235 |
+
"grad_norm": 0.21608634293079376,
|
| 236 |
+
"learning_rate": 0.00018847457627118645,
|
| 237 |
+
"loss": 0.936,
|
| 238 |
+
"mean_token_accuracy": 0.7302276790142059,
|
| 239 |
+
"num_tokens": 365454.0,
|
| 240 |
+
"step": 23
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"entropy": 1.0530632957816124,
|
| 244 |
+
"epoch": 1.2038216560509554,
|
| 245 |
+
"grad_norm": 0.2166907787322998,
|
| 246 |
+
"learning_rate": 0.00018779661016949151,
|
| 247 |
+
"loss": 0.9256,
|
| 248 |
+
"mean_token_accuracy": 0.7271289154887199,
|
| 249 |
+
"num_tokens": 381498.0,
|
| 250 |
+
"step": 24
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"entropy": 1.0419923067092896,
|
| 254 |
+
"epoch": 1.2547770700636942,
|
| 255 |
+
"grad_norm": 0.2031186819076538,
|
| 256 |
+
"learning_rate": 0.00018711864406779663,
|
| 257 |
+
"loss": 0.9173,
|
| 258 |
+
"mean_token_accuracy": 0.7247356176376343,
|
| 259 |
+
"num_tokens": 397882.0,
|
| 260 |
+
"step": 25
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"entropy": 0.9017334207892418,
|
| 264 |
+
"epoch": 1.305732484076433,
|
| 265 |
+
"grad_norm": 0.2247246950864792,
|
| 266 |
+
"learning_rate": 0.0001864406779661017,
|
| 267 |
+
"loss": 0.8218,
|
| 268 |
+
"mean_token_accuracy": 0.750381663441658,
|
| 269 |
+
"num_tokens": 414252.0,
|
| 270 |
+
"step": 26
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"entropy": 0.9545145109295845,
|
| 274 |
+
"epoch": 1.356687898089172,
|
| 275 |
+
"grad_norm": 0.22306284308433533,
|
| 276 |
+
"learning_rate": 0.0001857627118644068,
|
| 277 |
+
"loss": 0.8353,
|
| 278 |
+
"mean_token_accuracy": 0.745391808450222,
|
| 279 |
+
"num_tokens": 430333.0,
|
| 280 |
+
"step": 27
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"entropy": 1.007826380431652,
|
| 284 |
+
"epoch": 1.4076433121019107,
|
| 285 |
+
"grad_norm": 0.2460908591747284,
|
| 286 |
+
"learning_rate": 0.00018508474576271186,
|
| 287 |
+
"loss": 0.894,
|
| 288 |
+
"mean_token_accuracy": 0.7268281579017639,
|
| 289 |
+
"num_tokens": 445716.0,
|
| 290 |
+
"step": 28
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"entropy": 0.9371664151549339,
|
| 294 |
+
"epoch": 1.4585987261146496,
|
| 295 |
+
"grad_norm": 0.2315070778131485,
|
| 296 |
+
"learning_rate": 0.00018440677966101695,
|
| 297 |
+
"loss": 0.8582,
|
| 298 |
+
"mean_token_accuracy": 0.744682066142559,
|
| 299 |
+
"num_tokens": 462100.0,
|
| 300 |
+
"step": 29
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"entropy": 0.9967339187860489,
|
| 304 |
+
"epoch": 1.5095541401273884,
|
| 305 |
+
"grad_norm": 0.24030983448028564,
|
| 306 |
+
"learning_rate": 0.00018372881355932204,
|
| 307 |
+
"loss": 0.8878,
|
| 308 |
+
"mean_token_accuracy": 0.7294926047325134,
|
| 309 |
+
"num_tokens": 478484.0,
|
| 310 |
+
"step": 30
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"entropy": 0.9289672449231148,
|
| 314 |
+
"epoch": 1.5605095541401273,
|
| 315 |
+
"grad_norm": 0.24277092516422272,
|
| 316 |
+
"learning_rate": 0.00018305084745762714,
|
| 317 |
+
"loss": 0.8019,
|
| 318 |
+
"mean_token_accuracy": 0.7570356875658035,
|
| 319 |
+
"num_tokens": 494353.0,
|
| 320 |
+
"step": 31
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"entropy": 1.0442854911088943,
|
| 324 |
+
"epoch": 1.611464968152866,
|
| 325 |
+
"grad_norm": 0.24407894909381866,
|
| 326 |
+
"learning_rate": 0.0001823728813559322,
|
| 327 |
+
"loss": 0.9474,
|
| 328 |
+
"mean_token_accuracy": 0.718492366373539,
|
| 329 |
+
"num_tokens": 510669.0,
|
| 330 |
+
"step": 32
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"entropy": 0.9737825468182564,
|
| 334 |
+
"epoch": 1.662420382165605,
|
| 335 |
+
"grad_norm": 0.23990698158740997,
|
| 336 |
+
"learning_rate": 0.0001816949152542373,
|
| 337 |
+
"loss": 0.8649,
|
| 338 |
+
"mean_token_accuracy": 0.7393911480903625,
|
| 339 |
+
"num_tokens": 526692.0,
|
| 340 |
+
"step": 33
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"entropy": 0.9364971444010735,
|
| 344 |
+
"epoch": 1.7133757961783438,
|
| 345 |
+
"grad_norm": 0.25242283940315247,
|
| 346 |
+
"learning_rate": 0.00018101694915254239,
|
| 347 |
+
"loss": 0.8594,
|
| 348 |
+
"mean_token_accuracy": 0.7426017448306084,
|
| 349 |
+
"num_tokens": 542767.0,
|
| 350 |
+
"step": 34
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"entropy": 0.9076659008860588,
|
| 354 |
+
"epoch": 1.7643312101910829,
|
| 355 |
+
"grad_norm": 0.24069900810718536,
|
| 356 |
+
"learning_rate": 0.00018033898305084748,
|
| 357 |
+
"loss": 0.7971,
|
| 358 |
+
"mean_token_accuracy": 0.7580301761627197,
|
| 359 |
+
"num_tokens": 559151.0,
|
| 360 |
+
"step": 35
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"entropy": 0.9450107514858246,
|
| 364 |
+
"epoch": 1.8152866242038217,
|
| 365 |
+
"grad_norm": 0.2449842095375061,
|
| 366 |
+
"learning_rate": 0.00017966101694915257,
|
| 367 |
+
"loss": 0.8106,
|
| 368 |
+
"mean_token_accuracy": 0.751865841448307,
|
| 369 |
+
"num_tokens": 575298.0,
|
| 370 |
+
"step": 36
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"entropy": 0.9835781082510948,
|
| 374 |
+
"epoch": 1.8662420382165605,
|
| 375 |
+
"grad_norm": 0.26215094327926636,
|
| 376 |
+
"learning_rate": 0.00017898305084745764,
|
| 377 |
+
"loss": 0.8635,
|
| 378 |
+
"mean_token_accuracy": 0.7387464940547943,
|
| 379 |
+
"num_tokens": 591682.0,
|
| 380 |
+
"step": 37
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"entropy": 0.996803492307663,
|
| 384 |
+
"epoch": 1.9171974522292994,
|
| 385 |
+
"grad_norm": 0.26561757922172546,
|
| 386 |
+
"learning_rate": 0.00017830508474576273,
|
| 387 |
+
"loss": 0.8834,
|
| 388 |
+
"mean_token_accuracy": 0.7345194965600967,
|
| 389 |
+
"num_tokens": 608066.0,
|
| 390 |
+
"step": 38
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"entropy": 0.9412061348557472,
|
| 394 |
+
"epoch": 1.9681528662420382,
|
| 395 |
+
"grad_norm": 0.2681407630443573,
|
| 396 |
+
"learning_rate": 0.0001776271186440678,
|
| 397 |
+
"loss": 0.8378,
|
| 398 |
+
"mean_token_accuracy": 0.7482910975813866,
|
| 399 |
+
"num_tokens": 623934.0,
|
| 400 |
+
"step": 39
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"entropy": 0.8333677649497986,
|
| 404 |
+
"epoch": 2.0,
|
| 405 |
+
"grad_norm": 0.3134506046772003,
|
| 406 |
+
"learning_rate": 0.0001769491525423729,
|
| 407 |
+
"loss": 0.7475,
|
| 408 |
+
"mean_token_accuracy": 0.7668535470962524,
|
| 409 |
+
"num_tokens": 633150.0,
|
| 410 |
+
"step": 40
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"entropy": 0.9032419994473457,
|
| 414 |
+
"epoch": 2.050955414012739,
|
| 415 |
+
"grad_norm": 0.2786886990070343,
|
| 416 |
+
"learning_rate": 0.00017627118644067798,
|
| 417 |
+
"loss": 0.6645,
|
| 418 |
+
"mean_token_accuracy": 0.7967495918273926,
|
| 419 |
+
"num_tokens": 649534.0,
|
| 420 |
+
"step": 41
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"entropy": 0.8636530712246895,
|
| 424 |
+
"epoch": 2.1019108280254777,
|
| 425 |
+
"grad_norm": 0.27957314252853394,
|
| 426 |
+
"learning_rate": 0.00017559322033898307,
|
| 427 |
+
"loss": 0.6314,
|
| 428 |
+
"mean_token_accuracy": 0.8060957714915276,
|
| 429 |
+
"num_tokens": 665403.0,
|
| 430 |
+
"step": 42
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"entropy": 0.8624916896224022,
|
| 434 |
+
"epoch": 2.1528662420382165,
|
| 435 |
+
"grad_norm": 0.2938512861728668,
|
| 436 |
+
"learning_rate": 0.00017491525423728814,
|
| 437 |
+
"loss": 0.6799,
|
| 438 |
+
"mean_token_accuracy": 0.790034182369709,
|
| 439 |
+
"num_tokens": 681447.0,
|
| 440 |
+
"step": 43
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"entropy": 0.7863286510109901,
|
| 444 |
+
"epoch": 2.2038216560509554,
|
| 445 |
+
"grad_norm": 0.3072890341281891,
|
| 446 |
+
"learning_rate": 0.00017423728813559323,
|
| 447 |
+
"loss": 0.647,
|
| 448 |
+
"mean_token_accuracy": 0.7969771400094032,
|
| 449 |
+
"num_tokens": 697831.0,
|
| 450 |
+
"step": 44
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"entropy": 0.7100256532430649,
|
| 454 |
+
"epoch": 2.254777070063694,
|
| 455 |
+
"grad_norm": 0.3542580008506775,
|
| 456 |
+
"learning_rate": 0.0001735593220338983,
|
| 457 |
+
"loss": 0.6337,
|
| 458 |
+
"mean_token_accuracy": 0.8022638335824013,
|
| 459 |
+
"num_tokens": 714215.0,
|
| 460 |
+
"step": 45
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"entropy": 0.716219499707222,
|
| 464 |
+
"epoch": 2.305732484076433,
|
| 465 |
+
"grad_norm": 0.39583054184913635,
|
| 466 |
+
"learning_rate": 0.00017288135593220342,
|
| 467 |
+
"loss": 0.6277,
|
| 468 |
+
"mean_token_accuracy": 0.8007404282689095,
|
| 469 |
+
"num_tokens": 730585.0,
|
| 470 |
+
"step": 46
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"entropy": 0.7219437435269356,
|
| 474 |
+
"epoch": 2.356687898089172,
|
| 475 |
+
"grad_norm": 0.3591735363006592,
|
| 476 |
+
"learning_rate": 0.00017220338983050848,
|
| 477 |
+
"loss": 0.634,
|
| 478 |
+
"mean_token_accuracy": 0.8042735084891319,
|
| 479 |
+
"num_tokens": 746901.0,
|
| 480 |
+
"step": 47
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"entropy": 0.7401451990008354,
|
| 484 |
+
"epoch": 2.4076433121019107,
|
| 485 |
+
"grad_norm": 0.34251025319099426,
|
| 486 |
+
"learning_rate": 0.00017152542372881357,
|
| 487 |
+
"loss": 0.6275,
|
| 488 |
+
"mean_token_accuracy": 0.8064323589205742,
|
| 489 |
+
"num_tokens": 763285.0,
|
| 490 |
+
"step": 48
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"entropy": 0.7539378255605698,
|
| 494 |
+
"epoch": 2.4585987261146496,
|
| 495 |
+
"grad_norm": 0.3110820949077606,
|
| 496 |
+
"learning_rate": 0.00017084745762711864,
|
| 497 |
+
"loss": 0.5985,
|
| 498 |
+
"mean_token_accuracy": 0.8130116537213326,
|
| 499 |
+
"num_tokens": 779041.0,
|
| 500 |
+
"step": 49
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"entropy": 0.7710842117667198,
|
| 504 |
+
"epoch": 2.5095541401273884,
|
| 505 |
+
"grad_norm": 0.3228455185890198,
|
| 506 |
+
"learning_rate": 0.00017016949152542373,
|
| 507 |
+
"loss": 0.5966,
|
| 508 |
+
"mean_token_accuracy": 0.8146229013800621,
|
| 509 |
+
"num_tokens": 795064.0,
|
| 510 |
+
"step": 50
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"entropy": 0.7773924395442009,
|
| 514 |
+
"epoch": 2.5605095541401273,
|
| 515 |
+
"grad_norm": 0.3367364704608917,
|
| 516 |
+
"learning_rate": 0.00016949152542372882,
|
| 517 |
+
"loss": 0.5938,
|
| 518 |
+
"mean_token_accuracy": 0.8128385469317436,
|
| 519 |
+
"num_tokens": 811448.0,
|
| 520 |
+
"step": 51
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"entropy": 0.7728712856769562,
|
| 524 |
+
"epoch": 2.611464968152866,
|
| 525 |
+
"grad_norm": 0.35927024483680725,
|
| 526 |
+
"learning_rate": 0.00016881355932203392,
|
| 527 |
+
"loss": 0.6354,
|
| 528 |
+
"mean_token_accuracy": 0.8013699352741241,
|
| 529 |
+
"num_tokens": 827459.0,
|
| 530 |
+
"step": 52
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"entropy": 0.7718184515833855,
|
| 534 |
+
"epoch": 2.662420382165605,
|
| 535 |
+
"grad_norm": 0.3391318619251251,
|
| 536 |
+
"learning_rate": 0.00016813559322033898,
|
| 537 |
+
"loss": 0.6334,
|
| 538 |
+
"mean_token_accuracy": 0.8047890961170197,
|
| 539 |
+
"num_tokens": 843327.0,
|
| 540 |
+
"step": 53
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"entropy": 0.7653945237398148,
|
| 544 |
+
"epoch": 2.713375796178344,
|
| 545 |
+
"grad_norm": 0.35930103063583374,
|
| 546 |
+
"learning_rate": 0.00016745762711864408,
|
| 547 |
+
"loss": 0.6198,
|
| 548 |
+
"mean_token_accuracy": 0.8065511807799339,
|
| 549 |
+
"num_tokens": 859402.0,
|
| 550 |
+
"step": 54
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"entropy": 0.7647791504859924,
|
| 554 |
+
"epoch": 2.7643312101910826,
|
| 555 |
+
"grad_norm": 0.3643956482410431,
|
| 556 |
+
"learning_rate": 0.00016677966101694914,
|
| 557 |
+
"loss": 0.6315,
|
| 558 |
+
"mean_token_accuracy": 0.8033340945839882,
|
| 559 |
+
"num_tokens": 875786.0,
|
| 560 |
+
"step": 55
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"entropy": 0.7234460189938545,
|
| 564 |
+
"epoch": 2.8152866242038215,
|
| 565 |
+
"grad_norm": 0.3637371361255646,
|
| 566 |
+
"learning_rate": 0.00016610169491525423,
|
| 567 |
+
"loss": 0.6047,
|
| 568 |
+
"mean_token_accuracy": 0.8084925785660744,
|
| 569 |
+
"num_tokens": 892170.0,
|
| 570 |
+
"step": 56
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"entropy": 0.7029176577925682,
|
| 574 |
+
"epoch": 2.8662420382165603,
|
| 575 |
+
"grad_norm": 0.41221824288368225,
|
| 576 |
+
"learning_rate": 0.00016542372881355933,
|
| 577 |
+
"loss": 0.6028,
|
| 578 |
+
"mean_token_accuracy": 0.8094355836510658,
|
| 579 |
+
"num_tokens": 908554.0,
|
| 580 |
+
"step": 57
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"entropy": 0.8026896864175797,
|
| 584 |
+
"epoch": 2.917197452229299,
|
| 585 |
+
"grad_norm": 0.40634164214134216,
|
| 586 |
+
"learning_rate": 0.00016474576271186442,
|
| 587 |
+
"loss": 0.6841,
|
| 588 |
+
"mean_token_accuracy": 0.7903437316417694,
|
| 589 |
+
"num_tokens": 924362.0,
|
| 590 |
+
"step": 58
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"entropy": 0.7678564339876175,
|
| 594 |
+
"epoch": 2.968152866242038,
|
| 595 |
+
"grad_norm": 0.3688332438468933,
|
| 596 |
+
"learning_rate": 0.00016406779661016948,
|
| 597 |
+
"loss": 0.6375,
|
| 598 |
+
"mean_token_accuracy": 0.8057018518447876,
|
| 599 |
+
"num_tokens": 940746.0,
|
| 600 |
+
"step": 59
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"entropy": 0.7260988593101502,
|
| 604 |
+
"epoch": 3.0,
|
| 605 |
+
"grad_norm": 0.4596911668777466,
|
| 606 |
+
"learning_rate": 0.00016338983050847458,
|
| 607 |
+
"loss": 0.608,
|
| 608 |
+
"mean_token_accuracy": 0.8153721690177917,
|
| 609 |
+
"num_tokens": 949725.0,
|
| 610 |
+
"step": 60
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"entropy": 0.7356696203351021,
|
| 614 |
+
"epoch": 3.050955414012739,
|
| 615 |
+
"grad_norm": 0.39724084734916687,
|
| 616 |
+
"learning_rate": 0.00016271186440677967,
|
| 617 |
+
"loss": 0.4432,
|
| 618 |
+
"mean_token_accuracy": 0.8702359348535538,
|
| 619 |
+
"num_tokens": 966109.0,
|
| 620 |
+
"step": 61
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"entropy": 0.7380152717232704,
|
| 624 |
+
"epoch": 3.1019108280254777,
|
| 625 |
+
"grad_norm": 0.38238734006881714,
|
| 626 |
+
"learning_rate": 0.00016203389830508476,
|
| 627 |
+
"loss": 0.4427,
|
| 628 |
+
"mean_token_accuracy": 0.8688767999410629,
|
| 629 |
+
"num_tokens": 982132.0,
|
| 630 |
+
"step": 62
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"entropy": 0.6648666933178902,
|
| 634 |
+
"epoch": 3.1528662420382165,
|
| 635 |
+
"grad_norm": 0.3744766414165497,
|
| 636 |
+
"learning_rate": 0.00016135593220338985,
|
| 637 |
+
"loss": 0.4303,
|
| 638 |
+
"mean_token_accuracy": 0.8702655509114265,
|
| 639 |
+
"num_tokens": 998516.0,
|
| 640 |
+
"step": 63
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"entropy": 0.5741898603737354,
|
| 644 |
+
"epoch": 3.2038216560509554,
|
| 645 |
+
"grad_norm": 0.38260239362716675,
|
| 646 |
+
"learning_rate": 0.00016067796610169492,
|
| 647 |
+
"loss": 0.3882,
|
| 648 |
+
"mean_token_accuracy": 0.877837598323822,
|
| 649 |
+
"num_tokens": 1014900.0,
|
| 650 |
+
"step": 64
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"entropy": 0.594137117266655,
|
| 654 |
+
"epoch": 3.254777070063694,
|
| 655 |
+
"grad_norm": 0.4781484007835388,
|
| 656 |
+
"learning_rate": 0.00016,
|
| 657 |
+
"loss": 0.4123,
|
| 658 |
+
"mean_token_accuracy": 0.8714389055967331,
|
| 659 |
+
"num_tokens": 1030353.0,
|
| 660 |
+
"step": 65
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"entropy": 0.49363305792212486,
|
| 664 |
+
"epoch": 3.305732484076433,
|
| 665 |
+
"grad_norm": 0.43986085057258606,
|
| 666 |
+
"learning_rate": 0.00015932203389830508,
|
| 667 |
+
"loss": 0.3587,
|
| 668 |
+
"mean_token_accuracy": 0.8876991271972656,
|
| 669 |
+
"num_tokens": 1046737.0,
|
| 670 |
+
"step": 66
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"entropy": 0.5222570262849331,
|
| 674 |
+
"epoch": 3.356687898089172,
|
| 675 |
+
"grad_norm": 0.5446242094039917,
|
| 676 |
+
"learning_rate": 0.0001586440677966102,
|
| 677 |
+
"loss": 0.4049,
|
| 678 |
+
"mean_token_accuracy": 0.8768400251865387,
|
| 679 |
+
"num_tokens": 1062022.0,
|
| 680 |
+
"step": 67
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"entropy": 0.5206106752157211,
|
| 684 |
+
"epoch": 3.4076433121019107,
|
| 685 |
+
"grad_norm": 0.5299471616744995,
|
| 686 |
+
"learning_rate": 0.00015796610169491526,
|
| 687 |
+
"loss": 0.4241,
|
| 688 |
+
"mean_token_accuracy": 0.8641180545091629,
|
| 689 |
+
"num_tokens": 1078406.0,
|
| 690 |
+
"step": 68
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"entropy": 0.518733087927103,
|
| 694 |
+
"epoch": 3.4585987261146496,
|
| 695 |
+
"grad_norm": 0.5972740650177002,
|
| 696 |
+
"learning_rate": 0.00015728813559322036,
|
| 697 |
+
"loss": 0.4115,
|
| 698 |
+
"mean_token_accuracy": 0.8688035756349564,
|
| 699 |
+
"num_tokens": 1094436.0,
|
| 700 |
+
"step": 69
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"entropy": 0.5547057241201401,
|
| 704 |
+
"epoch": 3.5095541401273884,
|
| 705 |
+
"grad_norm": 0.4489477276802063,
|
| 706 |
+
"learning_rate": 0.00015661016949152542,
|
| 707 |
+
"loss": 0.404,
|
| 708 |
+
"mean_token_accuracy": 0.8720321208238602,
|
| 709 |
+
"num_tokens": 1110820.0,
|
| 710 |
+
"step": 70
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"entropy": 0.5842308104038239,
|
| 714 |
+
"epoch": 3.5605095541401273,
|
| 715 |
+
"grad_norm": 0.44466689229011536,
|
| 716 |
+
"learning_rate": 0.00015593220338983051,
|
| 717 |
+
"loss": 0.3898,
|
| 718 |
+
"mean_token_accuracy": 0.8796258941292763,
|
| 719 |
+
"num_tokens": 1126967.0,
|
| 720 |
+
"step": 71
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"entropy": 0.5873496159911156,
|
| 724 |
+
"epoch": 3.611464968152866,
|
| 725 |
+
"grad_norm": 0.45185112953186035,
|
| 726 |
+
"learning_rate": 0.0001552542372881356,
|
| 727 |
+
"loss": 0.3966,
|
| 728 |
+
"mean_token_accuracy": 0.8762336745858192,
|
| 729 |
+
"num_tokens": 1143042.0,
|
| 730 |
+
"step": 72
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"entropy": 0.5752235390245914,
|
| 734 |
+
"epoch": 3.662420382165605,
|
| 735 |
+
"grad_norm": 0.40973153710365295,
|
| 736 |
+
"learning_rate": 0.0001545762711864407,
|
| 737 |
+
"loss": 0.3858,
|
| 738 |
+
"mean_token_accuracy": 0.8801640048623085,
|
| 739 |
+
"num_tokens": 1159426.0,
|
| 740 |
+
"step": 73
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"entropy": 0.5780553109943867,
|
| 744 |
+
"epoch": 3.713375796178344,
|
| 745 |
+
"grad_norm": 0.4268912374973297,
|
| 746 |
+
"learning_rate": 0.00015389830508474577,
|
| 747 |
+
"loss": 0.3839,
|
| 748 |
+
"mean_token_accuracy": 0.8774776384234428,
|
| 749 |
+
"num_tokens": 1175810.0,
|
| 750 |
+
"step": 74
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"entropy": 0.6104332208633423,
|
| 754 |
+
"epoch": 3.7643312101910826,
|
| 755 |
+
"grad_norm": 0.46141061186790466,
|
| 756 |
+
"learning_rate": 0.00015322033898305086,
|
| 757 |
+
"loss": 0.4187,
|
| 758 |
+
"mean_token_accuracy": 0.8688839823007584,
|
| 759 |
+
"num_tokens": 1191821.0,
|
| 760 |
+
"step": 75
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"entropy": 0.6029752381145954,
|
| 764 |
+
"epoch": 3.8152866242038215,
|
| 765 |
+
"grad_norm": 0.43786218762397766,
|
| 766 |
+
"learning_rate": 0.00015254237288135592,
|
| 767 |
+
"loss": 0.416,
|
| 768 |
+
"mean_token_accuracy": 0.8730273470282555,
|
| 769 |
+
"num_tokens": 1208205.0,
|
| 770 |
+
"step": 76
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"entropy": 0.549268014729023,
|
| 774 |
+
"epoch": 3.8662420382165603,
|
| 775 |
+
"grad_norm": 0.4513143301010132,
|
| 776 |
+
"learning_rate": 0.00015186440677966102,
|
| 777 |
+
"loss": 0.3974,
|
| 778 |
+
"mean_token_accuracy": 0.8771107047796249,
|
| 779 |
+
"num_tokens": 1224589.0,
|
| 780 |
+
"step": 77
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"entropy": 0.5441488139331341,
|
| 784 |
+
"epoch": 3.917197452229299,
|
| 785 |
+
"grad_norm": 0.46811601519584656,
|
| 786 |
+
"learning_rate": 0.0001511864406779661,
|
| 787 |
+
"loss": 0.4154,
|
| 788 |
+
"mean_token_accuracy": 0.8654165118932724,
|
| 789 |
+
"num_tokens": 1240973.0,
|
| 790 |
+
"step": 78
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"entropy": 0.5493720956146717,
|
| 794 |
+
"epoch": 3.968152866242038,
|
| 795 |
+
"grad_norm": 0.44944748282432556,
|
| 796 |
+
"learning_rate": 0.0001505084745762712,
|
| 797 |
+
"loss": 0.4034,
|
| 798 |
+
"mean_token_accuracy": 0.8696450367569923,
|
| 799 |
+
"num_tokens": 1257084.0,
|
| 800 |
+
"step": 79
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"entropy": 0.5232674360275269,
|
| 804 |
+
"epoch": 4.0,
|
| 805 |
+
"grad_norm": 0.6509364247322083,
|
| 806 |
+
"learning_rate": 0.00014983050847457627,
|
| 807 |
+
"loss": 0.382,
|
| 808 |
+
"mean_token_accuracy": 0.8761990904808045,
|
| 809 |
+
"num_tokens": 1266300.0,
|
| 810 |
+
"step": 80
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"entropy": 0.47885553166270256,
|
| 814 |
+
"epoch": 4.050955414012739,
|
| 815 |
+
"grad_norm": 0.3760603368282318,
|
| 816 |
+
"learning_rate": 0.00014915254237288136,
|
| 817 |
+
"loss": 0.2536,
|
| 818 |
+
"mean_token_accuracy": 0.9295564144849777,
|
| 819 |
+
"num_tokens": 1282684.0,
|
| 820 |
+
"step": 81
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"entropy": 0.48514579981565475,
|
| 824 |
+
"epoch": 4.101910828025478,
|
| 825 |
+
"grad_norm": 0.41000157594680786,
|
| 826 |
+
"learning_rate": 0.00014847457627118645,
|
| 827 |
+
"loss": 0.2466,
|
| 828 |
+
"mean_token_accuracy": 0.9299841672182083,
|
| 829 |
+
"num_tokens": 1298131.0,
|
| 830 |
+
"step": 82
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"entropy": 0.4603138528764248,
|
| 834 |
+
"epoch": 4.1528662420382165,
|
| 835 |
+
"grad_norm": 0.4120670557022095,
|
| 836 |
+
"learning_rate": 0.00014779661016949154,
|
| 837 |
+
"loss": 0.2421,
|
| 838 |
+
"mean_token_accuracy": 0.9294634088873863,
|
| 839 |
+
"num_tokens": 1314515.0,
|
| 840 |
+
"step": 83
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"entropy": 0.45813342928886414,
|
| 844 |
+
"epoch": 4.203821656050955,
|
| 845 |
+
"grad_norm": 0.4626755714416504,
|
| 846 |
+
"learning_rate": 0.0001471186440677966,
|
| 847 |
+
"loss": 0.2564,
|
| 848 |
+
"mean_token_accuracy": 0.9251118749380112,
|
| 849 |
+
"num_tokens": 1330265.0,
|
| 850 |
+
"step": 84
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"entropy": 0.44495610520243645,
|
| 854 |
+
"epoch": 4.254777070063694,
|
| 855 |
+
"grad_norm": 0.44884416460990906,
|
| 856 |
+
"learning_rate": 0.0001464406779661017,
|
| 857 |
+
"loss": 0.2521,
|
| 858 |
+
"mean_token_accuracy": 0.9254637137055397,
|
| 859 |
+
"num_tokens": 1346649.0,
|
| 860 |
+
"step": 85
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"entropy": 0.4175037741661072,
|
| 864 |
+
"epoch": 4.305732484076433,
|
| 865 |
+
"grad_norm": 0.46599075198173523,
|
| 866 |
+
"learning_rate": 0.00014576271186440677,
|
| 867 |
+
"loss": 0.2359,
|
| 868 |
+
"mean_token_accuracy": 0.9287681803107262,
|
| 869 |
+
"num_tokens": 1363033.0,
|
| 870 |
+
"step": 86
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"entropy": 0.3893379382789135,
|
| 874 |
+
"epoch": 4.356687898089172,
|
| 875 |
+
"grad_norm": 0.4749402105808258,
|
| 876 |
+
"learning_rate": 0.00014508474576271186,
|
| 877 |
+
"loss": 0.2318,
|
| 878 |
+
"mean_token_accuracy": 0.928847424685955,
|
| 879 |
+
"num_tokens": 1379417.0,
|
| 880 |
+
"step": 87
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"entropy": 0.38882919400930405,
|
| 884 |
+
"epoch": 4.407643312101911,
|
| 885 |
+
"grad_norm": 0.5757173299789429,
|
| 886 |
+
"learning_rate": 0.00014440677966101695,
|
| 887 |
+
"loss": 0.2428,
|
| 888 |
+
"mean_token_accuracy": 0.9265876188874245,
|
| 889 |
+
"num_tokens": 1395550.0,
|
| 890 |
+
"step": 88
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"entropy": 0.3952750638127327,
|
| 894 |
+
"epoch": 4.45859872611465,
|
| 895 |
+
"grad_norm": 0.461063414812088,
|
| 896 |
+
"learning_rate": 0.00014372881355932205,
|
| 897 |
+
"loss": 0.2315,
|
| 898 |
+
"mean_token_accuracy": 0.9281129166483879,
|
| 899 |
+
"num_tokens": 1411418.0,
|
| 900 |
+
"step": 89
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"entropy": 0.4219426065683365,
|
| 904 |
+
"epoch": 4.509554140127388,
|
| 905 |
+
"grad_norm": 0.6616204977035522,
|
| 906 |
+
"learning_rate": 0.00014305084745762714,
|
| 907 |
+
"loss": 0.2723,
|
| 908 |
+
"mean_token_accuracy": 0.9186402186751366,
|
| 909 |
+
"num_tokens": 1427802.0,
|
| 910 |
+
"step": 90
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"entropy": 0.3946552649140358,
|
| 914 |
+
"epoch": 4.560509554140127,
|
| 915 |
+
"grad_norm": 0.5001639723777771,
|
| 916 |
+
"learning_rate": 0.0001423728813559322,
|
| 917 |
+
"loss": 0.2342,
|
| 918 |
+
"mean_token_accuracy": 0.9264548048377037,
|
| 919 |
+
"num_tokens": 1444186.0,
|
| 920 |
+
"step": 91
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"entropy": 0.3841370493173599,
|
| 924 |
+
"epoch": 4.611464968152866,
|
| 925 |
+
"grad_norm": 0.513782262802124,
|
| 926 |
+
"learning_rate": 0.0001416949152542373,
|
| 927 |
+
"loss": 0.2234,
|
| 928 |
+
"mean_token_accuracy": 0.9312374666333199,
|
| 929 |
+
"num_tokens": 1460570.0,
|
| 930 |
+
"step": 92
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"entropy": 0.4142785668373108,
|
| 934 |
+
"epoch": 4.662420382165605,
|
| 935 |
+
"grad_norm": 0.57405686378479,
|
| 936 |
+
"learning_rate": 0.0001410169491525424,
|
| 937 |
+
"loss": 0.2387,
|
| 938 |
+
"mean_token_accuracy": 0.9266747310757637,
|
| 939 |
+
"num_tokens": 1476954.0,
|
| 940 |
+
"step": 93
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"entropy": 0.40532124042510986,
|
| 944 |
+
"epoch": 4.713375796178344,
|
| 945 |
+
"grad_norm": 0.46338939666748047,
|
| 946 |
+
"learning_rate": 0.00014033898305084748,
|
| 947 |
+
"loss": 0.2242,
|
| 948 |
+
"mean_token_accuracy": 0.9350497350096703,
|
| 949 |
+
"num_tokens": 1492662.0,
|
| 950 |
+
"step": 94
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"entropy": 0.4392712004482746,
|
| 954 |
+
"epoch": 4.764331210191083,
|
| 955 |
+
"grad_norm": 0.44444721937179565,
|
| 956 |
+
"learning_rate": 0.00013966101694915255,
|
| 957 |
+
"loss": 0.2493,
|
| 958 |
+
"mean_token_accuracy": 0.9251364171504974,
|
| 959 |
+
"num_tokens": 1508191.0,
|
| 960 |
+
"step": 95
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"entropy": 0.4355561286211014,
|
| 964 |
+
"epoch": 4.8152866242038215,
|
| 965 |
+
"grad_norm": 0.6919573545455933,
|
| 966 |
+
"learning_rate": 0.00013898305084745764,
|
| 967 |
+
"loss": 0.2784,
|
| 968 |
+
"mean_token_accuracy": 0.9153470247983932,
|
| 969 |
+
"num_tokens": 1524575.0,
|
| 970 |
+
"step": 96
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"entropy": 0.42629534751176834,
|
| 974 |
+
"epoch": 4.86624203821656,
|
| 975 |
+
"grad_norm": 0.48309773206710815,
|
| 976 |
+
"learning_rate": 0.0001383050847457627,
|
| 977 |
+
"loss": 0.2451,
|
| 978 |
+
"mean_token_accuracy": 0.9251194447278976,
|
| 979 |
+
"num_tokens": 1540891.0,
|
| 980 |
+
"step": 97
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"entropy": 0.43248729407787323,
|
| 984 |
+
"epoch": 4.917197452229299,
|
| 985 |
+
"grad_norm": 0.45119330286979675,
|
| 986 |
+
"learning_rate": 0.0001376271186440678,
|
| 987 |
+
"loss": 0.2419,
|
| 988 |
+
"mean_token_accuracy": 0.9283814057707787,
|
| 989 |
+
"num_tokens": 1557275.0,
|
| 990 |
+
"step": 98
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"entropy": 0.43973976373672485,
|
| 994 |
+
"epoch": 4.968152866242038,
|
| 995 |
+
"grad_norm": 0.4691547155380249,
|
| 996 |
+
"learning_rate": 0.0001369491525423729,
|
| 997 |
+
"loss": 0.2527,
|
| 998 |
+
"mean_token_accuracy": 0.9239722490310669,
|
| 999 |
+
"num_tokens": 1573659.0,
|
| 1000 |
+
"step": 99
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"entropy": 0.4433164715766907,
|
| 1004 |
+
"epoch": 5.0,
|
| 1005 |
+
"grad_norm": 0.7236930131912231,
|
| 1006 |
+
"learning_rate": 0.00013627118644067798,
|
| 1007 |
+
"loss": 0.2708,
|
| 1008 |
+
"mean_token_accuracy": 0.918548333644867,
|
| 1009 |
+
"num_tokens": 1582875.0,
|
| 1010 |
+
"step": 100
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"entropy": 0.34633738547563553,
|
| 1014 |
+
"epoch": 5.050955414012739,
|
| 1015 |
+
"grad_norm": 0.33959242701530457,
|
| 1016 |
+
"learning_rate": 0.00013559322033898305,
|
| 1017 |
+
"loss": 0.1452,
|
| 1018 |
+
"mean_token_accuracy": 0.963602103292942,
|
| 1019 |
+
"num_tokens": 1599259.0,
|
| 1020 |
+
"step": 101
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"entropy": 0.3849232979118824,
|
| 1024 |
+
"epoch": 5.101910828025478,
|
| 1025 |
+
"grad_norm": 0.44738227128982544,
|
| 1026 |
+
"learning_rate": 0.00013491525423728814,
|
| 1027 |
+
"loss": 0.1612,
|
| 1028 |
+
"mean_token_accuracy": 0.9605535492300987,
|
| 1029 |
+
"num_tokens": 1615643.0,
|
| 1030 |
+
"step": 102
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"entropy": 0.3427181765437126,
|
| 1034 |
+
"epoch": 5.1528662420382165,
|
| 1035 |
+
"grad_norm": 0.5047619342803955,
|
| 1036 |
+
"learning_rate": 0.0001342372881355932,
|
| 1037 |
+
"loss": 0.1552,
|
| 1038 |
+
"mean_token_accuracy": 0.9561429843306541,
|
| 1039 |
+
"num_tokens": 1632013.0,
|
| 1040 |
+
"step": 103
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"entropy": 0.3299499414861202,
|
| 1044 |
+
"epoch": 5.203821656050955,
|
| 1045 |
+
"grad_norm": 0.39201250672340393,
|
| 1046 |
+
"learning_rate": 0.00013355932203389833,
|
| 1047 |
+
"loss": 0.1377,
|
| 1048 |
+
"mean_token_accuracy": 0.9647994339466095,
|
| 1049 |
+
"num_tokens": 1648397.0,
|
| 1050 |
+
"step": 104
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"entropy": 0.31782786548137665,
|
| 1054 |
+
"epoch": 5.254777070063694,
|
| 1055 |
+
"grad_norm": 0.5107133388519287,
|
| 1056 |
+
"learning_rate": 0.0001328813559322034,
|
| 1057 |
+
"loss": 0.1561,
|
| 1058 |
+
"mean_token_accuracy": 0.9557145461440086,
|
| 1059 |
+
"num_tokens": 1664713.0,
|
| 1060 |
+
"step": 105
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"entropy": 0.30781830847263336,
|
| 1064 |
+
"epoch": 5.305732484076433,
|
| 1065 |
+
"grad_norm": 0.4927469789981842,
|
| 1066 |
+
"learning_rate": 0.00013220338983050849,
|
| 1067 |
+
"loss": 0.1469,
|
| 1068 |
+
"mean_token_accuracy": 0.9573208466172218,
|
| 1069 |
+
"num_tokens": 1680451.0,
|
| 1070 |
+
"step": 106
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"entropy": 0.29482175409793854,
|
| 1074 |
+
"epoch": 5.356687898089172,
|
| 1075 |
+
"grad_norm": 0.47950249910354614,
|
| 1076 |
+
"learning_rate": 0.00013152542372881355,
|
| 1077 |
+
"loss": 0.134,
|
| 1078 |
+
"mean_token_accuracy": 0.96302530169487,
|
| 1079 |
+
"num_tokens": 1696835.0,
|
| 1080 |
+
"step": 107
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"entropy": 0.3074999451637268,
|
| 1084 |
+
"epoch": 5.407643312101911,
|
| 1085 |
+
"grad_norm": 0.6049532890319824,
|
| 1086 |
+
"learning_rate": 0.00013084745762711864,
|
| 1087 |
+
"loss": 0.1514,
|
| 1088 |
+
"mean_token_accuracy": 0.953678622841835,
|
| 1089 |
+
"num_tokens": 1713219.0,
|
| 1090 |
+
"step": 108
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"entropy": 0.29727265425026417,
|
| 1094 |
+
"epoch": 5.45859872611465,
|
| 1095 |
+
"grad_norm": 0.4694285988807678,
|
| 1096 |
+
"learning_rate": 0.00013016949152542374,
|
| 1097 |
+
"loss": 0.1361,
|
| 1098 |
+
"mean_token_accuracy": 0.9609672874212265,
|
| 1099 |
+
"num_tokens": 1729263.0,
|
| 1100 |
+
"step": 109
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"entropy": 0.3285507708787918,
|
| 1104 |
+
"epoch": 5.509554140127388,
|
| 1105 |
+
"grad_norm": 0.46858081221580505,
|
| 1106 |
+
"learning_rate": 0.00012949152542372883,
|
| 1107 |
+
"loss": 0.1477,
|
| 1108 |
+
"mean_token_accuracy": 0.9602150619029999,
|
| 1109 |
+
"num_tokens": 1745647.0,
|
| 1110 |
+
"step": 110
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"entropy": 0.31142256781458855,
|
| 1114 |
+
"epoch": 5.560509554140127,
|
| 1115 |
+
"grad_norm": 0.4510185122489929,
|
| 1116 |
+
"learning_rate": 0.0001288135593220339,
|
| 1117 |
+
"loss": 0.1516,
|
| 1118 |
+
"mean_token_accuracy": 0.9559924080967903,
|
| 1119 |
+
"num_tokens": 1762031.0,
|
| 1120 |
+
"step": 111
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"entropy": 0.29558346793055534,
|
| 1124 |
+
"epoch": 5.611464968152866,
|
| 1125 |
+
"grad_norm": 0.4283140301704407,
|
| 1126 |
+
"learning_rate": 0.000128135593220339,
|
| 1127 |
+
"loss": 0.1308,
|
| 1128 |
+
"mean_token_accuracy": 0.9620353132486343,
|
| 1129 |
+
"num_tokens": 1778415.0,
|
| 1130 |
+
"step": 112
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"entropy": 0.33179714903235435,
|
| 1134 |
+
"epoch": 5.662420382165605,
|
| 1135 |
+
"grad_norm": 0.5021042227745056,
|
| 1136 |
+
"learning_rate": 0.00012745762711864405,
|
| 1137 |
+
"loss": 0.16,
|
| 1138 |
+
"mean_token_accuracy": 0.9551054015755653,
|
| 1139 |
+
"num_tokens": 1793768.0,
|
| 1140 |
+
"step": 113
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"entropy": 0.31468261033296585,
|
| 1144 |
+
"epoch": 5.713375796178344,
|
| 1145 |
+
"grad_norm": 0.4006524682044983,
|
| 1146 |
+
"learning_rate": 0.00012677966101694917,
|
| 1147 |
+
"loss": 0.1411,
|
| 1148 |
+
"mean_token_accuracy": 0.962010994553566,
|
| 1149 |
+
"num_tokens": 1810152.0,
|
| 1150 |
+
"step": 114
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"entropy": 0.32593148201704025,
|
| 1154 |
+
"epoch": 5.764331210191083,
|
| 1155 |
+
"grad_norm": 0.43213579058647156,
|
| 1156 |
+
"learning_rate": 0.00012610169491525426,
|
| 1157 |
+
"loss": 0.1533,
|
| 1158 |
+
"mean_token_accuracy": 0.9591230899095535,
|
| 1159 |
+
"num_tokens": 1826536.0,
|
| 1160 |
+
"step": 115
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"entropy": 0.33078752644360065,
|
| 1164 |
+
"epoch": 5.8152866242038215,
|
| 1165 |
+
"grad_norm": 0.44711190462112427,
|
| 1166 |
+
"learning_rate": 0.00012542372881355933,
|
| 1167 |
+
"loss": 0.1468,
|
| 1168 |
+
"mean_token_accuracy": 0.959298774600029,
|
| 1169 |
+
"num_tokens": 1842250.0,
|
| 1170 |
+
"step": 116
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"entropy": 0.32063932716846466,
|
| 1174 |
+
"epoch": 5.86624203821656,
|
| 1175 |
+
"grad_norm": 0.4965178072452545,
|
| 1176 |
+
"learning_rate": 0.00012474576271186442,
|
| 1177 |
+
"loss": 0.1502,
|
| 1178 |
+
"mean_token_accuracy": 0.9585834592580795,
|
| 1179 |
+
"num_tokens": 1857769.0,
|
| 1180 |
+
"step": 117
|
| 1181 |
+
},
|
| 1182 |
+
{
|
| 1183 |
+
"entropy": 0.31165121495723724,
|
| 1184 |
+
"epoch": 5.917197452229299,
|
| 1185 |
+
"grad_norm": 0.49228012561798096,
|
| 1186 |
+
"learning_rate": 0.0001240677966101695,
|
| 1187 |
+
"loss": 0.1586,
|
| 1188 |
+
"mean_token_accuracy": 0.9569637924432755,
|
| 1189 |
+
"num_tokens": 1874153.0,
|
| 1190 |
+
"step": 118
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"entropy": 0.30535227805376053,
|
| 1194 |
+
"epoch": 5.968152866242038,
|
| 1195 |
+
"grad_norm": 0.4432555139064789,
|
| 1196 |
+
"learning_rate": 0.00012338983050847458,
|
| 1197 |
+
"loss": 0.1359,
|
| 1198 |
+
"mean_token_accuracy": 0.9641127064824104,
|
| 1199 |
+
"num_tokens": 1890537.0,
|
| 1200 |
+
"step": 119
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"entropy": 0.28426828384399416,
|
| 1204 |
+
"epoch": 6.0,
|
| 1205 |
+
"grad_norm": 0.4886658191680908,
|
| 1206 |
+
"learning_rate": 0.00012271186440677967,
|
| 1207 |
+
"loss": 0.1239,
|
| 1208 |
+
"mean_token_accuracy": 0.9645166516304016,
|
| 1209 |
+
"num_tokens": 1899450.0,
|
| 1210 |
+
"step": 120
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"entropy": 0.27130062878131866,
|
| 1214 |
+
"epoch": 6.050955414012739,
|
| 1215 |
+
"grad_norm": 0.3076384663581848,
|
| 1216 |
+
"learning_rate": 0.00012203389830508477,
|
| 1217 |
+
"loss": 0.0791,
|
| 1218 |
+
"mean_token_accuracy": 0.9847517609596252,
|
| 1219 |
+
"num_tokens": 1915834.0,
|
| 1220 |
+
"step": 121
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"entropy": 0.25769038312137127,
|
| 1224 |
+
"epoch": 6.101910828025478,
|
| 1225 |
+
"grad_norm": 0.3248060941696167,
|
| 1226 |
+
"learning_rate": 0.00012135593220338983,
|
| 1227 |
+
"loss": 0.0855,
|
| 1228 |
+
"mean_token_accuracy": 0.9826889634132385,
|
| 1229 |
+
"num_tokens": 1932218.0,
|
| 1230 |
+
"step": 122
|
| 1231 |
+
},
|
| 1232 |
+
{
|
| 1233 |
+
"entropy": 0.2626284286379814,
|
| 1234 |
+
"epoch": 6.1528662420382165,
|
| 1235 |
+
"grad_norm": 0.33836546540260315,
|
| 1236 |
+
"learning_rate": 0.00012067796610169492,
|
| 1237 |
+
"loss": 0.0783,
|
| 1238 |
+
"mean_token_accuracy": 0.9843145906925201,
|
| 1239 |
+
"num_tokens": 1947992.0,
|
| 1240 |
+
"step": 123
|
| 1241 |
+
},
|
| 1242 |
+
{
|
| 1243 |
+
"entropy": 0.25033274479210377,
|
| 1244 |
+
"epoch": 6.203821656050955,
|
| 1245 |
+
"grad_norm": 0.3555228114128113,
|
| 1246 |
+
"learning_rate": 0.00012,
|
| 1247 |
+
"loss": 0.0856,
|
| 1248 |
+
"mean_token_accuracy": 0.9805334359407425,
|
| 1249 |
+
"num_tokens": 1964376.0,
|
| 1250 |
+
"step": 124
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"entropy": 0.2594117093831301,
|
| 1254 |
+
"epoch": 6.254777070063694,
|
| 1255 |
+
"grad_norm": 0.3466283082962036,
|
| 1256 |
+
"learning_rate": 0.0001193220338983051,
|
| 1257 |
+
"loss": 0.0866,
|
| 1258 |
+
"mean_token_accuracy": 0.9796433374285698,
|
| 1259 |
+
"num_tokens": 1980760.0,
|
| 1260 |
+
"step": 125
|
| 1261 |
+
},
|
| 1262 |
+
{
|
| 1263 |
+
"entropy": 0.2532740030437708,
|
| 1264 |
+
"epoch": 6.305732484076433,
|
| 1265 |
+
"grad_norm": 0.3873954713344574,
|
| 1266 |
+
"learning_rate": 0.00011864406779661017,
|
| 1267 |
+
"loss": 0.0888,
|
| 1268 |
+
"mean_token_accuracy": 0.9801652058959007,
|
| 1269 |
+
"num_tokens": 1997130.0,
|
| 1270 |
+
"step": 126
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"entropy": 0.2388041988015175,
|
| 1274 |
+
"epoch": 6.356687898089172,
|
| 1275 |
+
"grad_norm": 0.3720211088657379,
|
| 1276 |
+
"learning_rate": 0.00011796610169491527,
|
| 1277 |
+
"loss": 0.0801,
|
| 1278 |
+
"mean_token_accuracy": 0.981012374162674,
|
| 1279 |
+
"num_tokens": 2013514.0,
|
| 1280 |
+
"step": 127
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"entropy": 0.22601926513016224,
|
| 1284 |
+
"epoch": 6.407643312101911,
|
| 1285 |
+
"grad_norm": 0.42567574977874756,
|
| 1286 |
+
"learning_rate": 0.00011728813559322033,
|
| 1287 |
+
"loss": 0.0884,
|
| 1288 |
+
"mean_token_accuracy": 0.9771610125899315,
|
| 1289 |
+
"num_tokens": 2029898.0,
|
| 1290 |
+
"step": 128
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"entropy": 0.241213021799922,
|
| 1294 |
+
"epoch": 6.45859872611465,
|
| 1295 |
+
"grad_norm": 0.39269620180130005,
|
| 1296 |
+
"learning_rate": 0.00011661016949152544,
|
| 1297 |
+
"loss": 0.0829,
|
| 1298 |
+
"mean_token_accuracy": 0.979632280766964,
|
| 1299 |
+
"num_tokens": 2046282.0,
|
| 1300 |
+
"step": 129
|
| 1301 |
+
},
|
| 1302 |
+
{
|
| 1303 |
+
"entropy": 0.23457833379507065,
|
| 1304 |
+
"epoch": 6.509554140127388,
|
| 1305 |
+
"grad_norm": 0.40059277415275574,
|
| 1306 |
+
"learning_rate": 0.0001159322033898305,
|
| 1307 |
+
"loss": 0.0846,
|
| 1308 |
+
"mean_token_accuracy": 0.9801751151680946,
|
| 1309 |
+
"num_tokens": 2062084.0,
|
| 1310 |
+
"step": 130
|
| 1311 |
+
},
|
| 1312 |
+
{
|
| 1313 |
+
"entropy": 0.2504513543099165,
|
| 1314 |
+
"epoch": 6.560509554140127,
|
| 1315 |
+
"grad_norm": 0.38298025727272034,
|
| 1316 |
+
"learning_rate": 0.0001152542372881356,
|
| 1317 |
+
"loss": 0.0814,
|
| 1318 |
+
"mean_token_accuracy": 0.980772852897644,
|
| 1319 |
+
"num_tokens": 2078097.0,
|
| 1320 |
+
"step": 131
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"entropy": 0.2271766308695078,
|
| 1324 |
+
"epoch": 6.611464968152866,
|
| 1325 |
+
"grad_norm": 0.31705358624458313,
|
| 1326 |
+
"learning_rate": 0.00011457627118644068,
|
| 1327 |
+
"loss": 0.0695,
|
| 1328 |
+
"mean_token_accuracy": 0.9833817705512047,
|
| 1329 |
+
"num_tokens": 2094141.0,
|
| 1330 |
+
"step": 132
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"entropy": 0.24483878165483475,
|
| 1334 |
+
"epoch": 6.662420382165605,
|
| 1335 |
+
"grad_norm": 0.346872478723526,
|
| 1336 |
+
"learning_rate": 0.00011389830508474577,
|
| 1337 |
+
"loss": 0.0844,
|
| 1338 |
+
"mean_token_accuracy": 0.9803112000226974,
|
| 1339 |
+
"num_tokens": 2110525.0,
|
| 1340 |
+
"step": 133
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"entropy": 0.24256090261042118,
|
| 1344 |
+
"epoch": 6.713375796178344,
|
| 1345 |
+
"grad_norm": 0.3615415096282959,
|
| 1346 |
+
"learning_rate": 0.00011322033898305085,
|
| 1347 |
+
"loss": 0.0847,
|
| 1348 |
+
"mean_token_accuracy": 0.9810795113444328,
|
| 1349 |
+
"num_tokens": 2126394.0,
|
| 1350 |
+
"step": 134
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"entropy": 0.2385116182267666,
|
| 1354 |
+
"epoch": 6.764331210191083,
|
| 1355 |
+
"grad_norm": 0.36627471446990967,
|
| 1356 |
+
"learning_rate": 0.00011254237288135594,
|
| 1357 |
+
"loss": 0.0798,
|
| 1358 |
+
"mean_token_accuracy": 0.9812560752034187,
|
| 1359 |
+
"num_tokens": 2142417.0,
|
| 1360 |
+
"step": 135
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"entropy": 0.23489636927843094,
|
| 1364 |
+
"epoch": 6.8152866242038215,
|
| 1365 |
+
"grad_norm": 0.3386026918888092,
|
| 1366 |
+
"learning_rate": 0.00011186440677966102,
|
| 1367 |
+
"loss": 0.0793,
|
| 1368 |
+
"mean_token_accuracy": 0.9815322011709213,
|
| 1369 |
+
"num_tokens": 2158801.0,
|
| 1370 |
+
"step": 136
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"entropy": 0.2517122123390436,
|
| 1374 |
+
"epoch": 6.86624203821656,
|
| 1375 |
+
"grad_norm": 0.3319648504257202,
|
| 1376 |
+
"learning_rate": 0.00011118644067796611,
|
| 1377 |
+
"loss": 0.0834,
|
| 1378 |
+
"mean_token_accuracy": 0.9808342307806015,
|
| 1379 |
+
"num_tokens": 2174557.0,
|
| 1380 |
+
"step": 137
|
| 1381 |
+
},
|
| 1382 |
+
{
|
| 1383 |
+
"entropy": 0.21653795056045055,
|
| 1384 |
+
"epoch": 6.917197452229299,
|
| 1385 |
+
"grad_norm": 0.3044669032096863,
|
| 1386 |
+
"learning_rate": 0.00011050847457627118,
|
| 1387 |
+
"loss": 0.0671,
|
| 1388 |
+
"mean_token_accuracy": 0.9844768345355988,
|
| 1389 |
+
"num_tokens": 2190425.0,
|
| 1390 |
+
"step": 138
|
| 1391 |
+
},
|
| 1392 |
+
{
|
| 1393 |
+
"entropy": 0.2155477125197649,
|
| 1394 |
+
"epoch": 6.968152866242038,
|
| 1395 |
+
"grad_norm": 0.3357236683368683,
|
| 1396 |
+
"learning_rate": 0.00010983050847457627,
|
| 1397 |
+
"loss": 0.0737,
|
| 1398 |
+
"mean_token_accuracy": 0.9834475293755531,
|
| 1399 |
+
"num_tokens": 2206809.0,
|
| 1400 |
+
"step": 139
|
| 1401 |
+
},
|
| 1402 |
+
{
|
| 1403 |
+
"entropy": 0.2226566791534424,
|
| 1404 |
+
"epoch": 7.0,
|
| 1405 |
+
"grad_norm": 0.45016321539878845,
|
| 1406 |
+
"learning_rate": 0.00010915254237288135,
|
| 1407 |
+
"loss": 0.0773,
|
| 1408 |
+
"mean_token_accuracy": 0.9805417537689209,
|
| 1409 |
+
"num_tokens": 2216025.0,
|
| 1410 |
+
"step": 140
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"entropy": 0.19488166272640228,
|
| 1414 |
+
"epoch": 7.050955414012739,
|
| 1415 |
+
"grad_norm": 0.22016853094100952,
|
| 1416 |
+
"learning_rate": 0.00010847457627118644,
|
| 1417 |
+
"loss": 0.0432,
|
| 1418 |
+
"mean_token_accuracy": 0.9938134476542473,
|
| 1419 |
+
"num_tokens": 2232409.0,
|
| 1420 |
+
"step": 141
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"entropy": 0.21024399995803833,
|
| 1424 |
+
"epoch": 7.101910828025478,
|
| 1425 |
+
"grad_norm": 0.25993385910987854,
|
| 1426 |
+
"learning_rate": 0.00010779661016949153,
|
| 1427 |
+
"loss": 0.0493,
|
| 1428 |
+
"mean_token_accuracy": 0.9914661943912506,
|
| 1429 |
+
"num_tokens": 2248779.0,
|
| 1430 |
+
"step": 142
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"entropy": 0.19661536812782288,
|
| 1434 |
+
"epoch": 7.1528662420382165,
|
| 1435 |
+
"grad_norm": 0.23448358476161957,
|
| 1436 |
+
"learning_rate": 0.00010711864406779661,
|
| 1437 |
+
"loss": 0.0427,
|
| 1438 |
+
"mean_token_accuracy": 0.994029700756073,
|
| 1439 |
+
"num_tokens": 2265163.0,
|
| 1440 |
+
"step": 143
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"entropy": 0.19229250587522984,
|
| 1444 |
+
"epoch": 7.203821656050955,
|
| 1445 |
+
"grad_norm": 0.23268407583236694,
|
| 1446 |
+
"learning_rate": 0.0001064406779661017,
|
| 1447 |
+
"loss": 0.0444,
|
| 1448 |
+
"mean_token_accuracy": 0.9925731718540192,
|
| 1449 |
+
"num_tokens": 2281547.0,
|
| 1450 |
+
"step": 144
|
| 1451 |
+
},
|
| 1452 |
+
{
|
| 1453 |
+
"entropy": 0.1830152403563261,
|
| 1454 |
+
"epoch": 7.254777070063694,
|
| 1455 |
+
"grad_norm": 0.26999878883361816,
|
| 1456 |
+
"learning_rate": 0.00010576271186440679,
|
| 1457 |
+
"loss": 0.0434,
|
| 1458 |
+
"mean_token_accuracy": 0.9930359646677971,
|
| 1459 |
+
"num_tokens": 2297622.0,
|
| 1460 |
+
"step": 145
|
| 1461 |
+
},
|
| 1462 |
+
{
|
| 1463 |
+
"entropy": 0.19611400365829468,
|
| 1464 |
+
"epoch": 7.305732484076433,
|
| 1465 |
+
"grad_norm": 0.24712666869163513,
|
| 1466 |
+
"learning_rate": 0.00010508474576271188,
|
| 1467 |
+
"loss": 0.0466,
|
| 1468 |
+
"mean_token_accuracy": 0.9918844103813171,
|
| 1469 |
+
"num_tokens": 2313120.0,
|
| 1470 |
+
"step": 146
|
| 1471 |
+
},
|
| 1472 |
+
{
|
| 1473 |
+
"entropy": 0.19746861048042774,
|
| 1474 |
+
"epoch": 7.356687898089172,
|
| 1475 |
+
"grad_norm": 0.2552828788757324,
|
| 1476 |
+
"learning_rate": 0.00010440677966101696,
|
| 1477 |
+
"loss": 0.0467,
|
| 1478 |
+
"mean_token_accuracy": 0.991991437971592,
|
| 1479 |
+
"num_tokens": 2328870.0,
|
| 1480 |
+
"step": 147
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"entropy": 0.17946216836571693,
|
| 1484 |
+
"epoch": 7.407643312101911,
|
| 1485 |
+
"grad_norm": 0.2574717402458191,
|
| 1486 |
+
"learning_rate": 0.00010372881355932205,
|
| 1487 |
+
"loss": 0.0471,
|
| 1488 |
+
"mean_token_accuracy": 0.9908664375543594,
|
| 1489 |
+
"num_tokens": 2345254.0,
|
| 1490 |
+
"step": 148
|
| 1491 |
+
},
|
| 1492 |
+
{
|
| 1493 |
+
"entropy": 0.1869801040738821,
|
| 1494 |
+
"epoch": 7.45859872611465,
|
| 1495 |
+
"grad_norm": 0.3232134282588959,
|
| 1496 |
+
"learning_rate": 0.00010305084745762712,
|
| 1497 |
+
"loss": 0.0482,
|
| 1498 |
+
"mean_token_accuracy": 0.9902735576033592,
|
| 1499 |
+
"num_tokens": 2361638.0,
|
| 1500 |
+
"step": 149
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"entropy": 0.18208733573555946,
|
| 1504 |
+
"epoch": 7.509554140127388,
|
| 1505 |
+
"grad_norm": 0.2782075107097626,
|
| 1506 |
+
"learning_rate": 0.00010237288135593222,
|
| 1507 |
+
"loss": 0.0429,
|
| 1508 |
+
"mean_token_accuracy": 0.9918385148048401,
|
| 1509 |
+
"num_tokens": 2377649.0,
|
| 1510 |
+
"step": 150
|
| 1511 |
+
},
|
| 1512 |
+
{
|
| 1513 |
+
"entropy": 0.1766122207045555,
|
| 1514 |
+
"epoch": 7.560509554140127,
|
| 1515 |
+
"grad_norm": 0.2637811005115509,
|
| 1516 |
+
"learning_rate": 0.00010169491525423729,
|
| 1517 |
+
"loss": 0.0386,
|
| 1518 |
+
"mean_token_accuracy": 0.9930592477321625,
|
| 1519 |
+
"num_tokens": 2393693.0,
|
| 1520 |
+
"step": 151
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"entropy": 0.18536034412682056,
|
| 1524 |
+
"epoch": 7.611464968152866,
|
| 1525 |
+
"grad_norm": 0.2969140112400055,
|
| 1526 |
+
"learning_rate": 0.00010101694915254238,
|
| 1527 |
+
"loss": 0.0484,
|
| 1528 |
+
"mean_token_accuracy": 0.9912179261445999,
|
| 1529 |
+
"num_tokens": 2409561.0,
|
| 1530 |
+
"step": 152
|
| 1531 |
+
},
|
| 1532 |
+
{
|
| 1533 |
+
"entropy": 0.1679281499236822,
|
| 1534 |
+
"epoch": 7.662420382165605,
|
| 1535 |
+
"grad_norm": 0.27921634912490845,
|
| 1536 |
+
"learning_rate": 0.00010033898305084746,
|
| 1537 |
+
"loss": 0.0396,
|
| 1538 |
+
"mean_token_accuracy": 0.9927029833197594,
|
| 1539 |
+
"num_tokens": 2425945.0,
|
| 1540 |
+
"step": 153
|
| 1541 |
+
},
|
| 1542 |
+
{
|
| 1543 |
+
"entropy": 0.1875128336250782,
|
| 1544 |
+
"epoch": 7.713375796178344,
|
| 1545 |
+
"grad_norm": 0.2692323923110962,
|
| 1546 |
+
"learning_rate": 9.966101694915255e-05,
|
| 1547 |
+
"loss": 0.0411,
|
| 1548 |
+
"mean_token_accuracy": 0.9918234646320343,
|
| 1549 |
+
"num_tokens": 2441701.0,
|
| 1550 |
+
"step": 154
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"entropy": 0.17189276590943336,
|
| 1554 |
+
"epoch": 7.764331210191083,
|
| 1555 |
+
"grad_norm": 0.24035243690013885,
|
| 1556 |
+
"learning_rate": 9.898305084745763e-05,
|
| 1557 |
+
"loss": 0.0384,
|
| 1558 |
+
"mean_token_accuracy": 0.9931274279952049,
|
| 1559 |
+
"num_tokens": 2458085.0,
|
| 1560 |
+
"step": 155
|
| 1561 |
+
},
|
| 1562 |
+
{
|
| 1563 |
+
"entropy": 0.16816619411110878,
|
| 1564 |
+
"epoch": 7.8152866242038215,
|
| 1565 |
+
"grad_norm": 0.23464734852313995,
|
| 1566 |
+
"learning_rate": 9.830508474576272e-05,
|
| 1567 |
+
"loss": 0.0378,
|
| 1568 |
+
"mean_token_accuracy": 0.9941559284925461,
|
| 1569 |
+
"num_tokens": 2474469.0,
|
| 1570 |
+
"step": 156
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"entropy": 0.17040574364364147,
|
| 1574 |
+
"epoch": 7.86624203821656,
|
| 1575 |
+
"grad_norm": 0.2753109037876129,
|
| 1576 |
+
"learning_rate": 9.76271186440678e-05,
|
| 1577 |
+
"loss": 0.0408,
|
| 1578 |
+
"mean_token_accuracy": 0.9930224418640137,
|
| 1579 |
+
"num_tokens": 2490853.0,
|
| 1580 |
+
"step": 157
|
| 1581 |
+
},
|
| 1582 |
+
{
|
| 1583 |
+
"entropy": 0.17619120329618454,
|
| 1584 |
+
"epoch": 7.917197452229299,
|
| 1585 |
+
"grad_norm": 0.28378522396087646,
|
| 1586 |
+
"learning_rate": 9.69491525423729e-05,
|
| 1587 |
+
"loss": 0.0429,
|
| 1588 |
+
"mean_token_accuracy": 0.9916679263114929,
|
| 1589 |
+
"num_tokens": 2507237.0,
|
| 1590 |
+
"step": 158
|
| 1591 |
+
},
|
| 1592 |
+
{
|
| 1593 |
+
"entropy": 0.18376159109175205,
|
| 1594 |
+
"epoch": 7.968152866242038,
|
| 1595 |
+
"grad_norm": 0.25075170397758484,
|
| 1596 |
+
"learning_rate": 9.627118644067797e-05,
|
| 1597 |
+
"loss": 0.0409,
|
| 1598 |
+
"mean_token_accuracy": 0.9928998127579689,
|
| 1599 |
+
"num_tokens": 2523384.0,
|
| 1600 |
+
"step": 159
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"entropy": 0.16814205944538116,
|
| 1604 |
+
"epoch": 8.0,
|
| 1605 |
+
"grad_norm": 0.2868243455886841,
|
| 1606 |
+
"learning_rate": 9.559322033898305e-05,
|
| 1607 |
+
"loss": 0.039,
|
| 1608 |
+
"mean_token_accuracy": 0.9940619587898254,
|
| 1609 |
+
"num_tokens": 2532600.0,
|
| 1610 |
+
"step": 160
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"entropy": 0.16274571232497692,
|
| 1614 |
+
"epoch": 8.050955414012739,
|
| 1615 |
+
"grad_norm": 0.14176861941814423,
|
| 1616 |
+
"learning_rate": 9.491525423728815e-05,
|
| 1617 |
+
"loss": 0.0254,
|
| 1618 |
+
"mean_token_accuracy": 0.9974143728613853,
|
| 1619 |
+
"num_tokens": 2548984.0,
|
| 1620 |
+
"step": 161
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"entropy": 0.15707932971417904,
|
| 1624 |
+
"epoch": 8.101910828025478,
|
| 1625 |
+
"grad_norm": 0.14470599591732025,
|
| 1626 |
+
"learning_rate": 9.423728813559322e-05,
|
| 1627 |
+
"loss": 0.0236,
|
| 1628 |
+
"mean_token_accuracy": 0.9979943335056305,
|
| 1629 |
+
"num_tokens": 2565368.0,
|
| 1630 |
+
"step": 162
|
| 1631 |
+
},
|
| 1632 |
+
{
|
| 1633 |
+
"entropy": 0.15231047943234444,
|
| 1634 |
+
"epoch": 8.152866242038217,
|
| 1635 |
+
"grad_norm": 0.15325938165187836,
|
| 1636 |
+
"learning_rate": 9.355932203389832e-05,
|
| 1637 |
+
"loss": 0.0242,
|
| 1638 |
+
"mean_token_accuracy": 0.9976884126663208,
|
| 1639 |
+
"num_tokens": 2581752.0,
|
| 1640 |
+
"step": 163
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"entropy": 0.16208907216787338,
|
| 1644 |
+
"epoch": 8.203821656050955,
|
| 1645 |
+
"grad_norm": 0.17481264472007751,
|
| 1646 |
+
"learning_rate": 9.28813559322034e-05,
|
| 1647 |
+
"loss": 0.0257,
|
| 1648 |
+
"mean_token_accuracy": 0.9974030405282974,
|
| 1649 |
+
"num_tokens": 2598136.0,
|
| 1650 |
+
"step": 164
|
| 1651 |
+
},
|
| 1652 |
+
{
|
| 1653 |
+
"entropy": 0.15740813314914703,
|
| 1654 |
+
"epoch": 8.254777070063694,
|
| 1655 |
+
"grad_norm": 0.1707678586244583,
|
| 1656 |
+
"learning_rate": 9.220338983050847e-05,
|
| 1657 |
+
"loss": 0.0255,
|
| 1658 |
+
"mean_token_accuracy": 0.9970719814300537,
|
| 1659 |
+
"num_tokens": 2614147.0,
|
| 1660 |
+
"step": 165
|
| 1661 |
+
},
|
| 1662 |
+
{
|
| 1663 |
+
"entropy": 0.1630783099681139,
|
| 1664 |
+
"epoch": 8.305732484076433,
|
| 1665 |
+
"grad_norm": 0.17213749885559082,
|
| 1666 |
+
"learning_rate": 9.152542372881357e-05,
|
| 1667 |
+
"loss": 0.0262,
|
| 1668 |
+
"mean_token_accuracy": 0.9976739212870598,
|
| 1669 |
+
"num_tokens": 2630190.0,
|
| 1670 |
+
"step": 166
|
| 1671 |
+
},
|
| 1672 |
+
{
|
| 1673 |
+
"entropy": 0.16571603156626225,
|
| 1674 |
+
"epoch": 8.356687898089172,
|
| 1675 |
+
"grad_norm": 0.1789257526397705,
|
| 1676 |
+
"learning_rate": 9.084745762711865e-05,
|
| 1677 |
+
"loss": 0.0259,
|
| 1678 |
+
"mean_token_accuracy": 0.9970768317580223,
|
| 1679 |
+
"num_tokens": 2645931.0,
|
| 1680 |
+
"step": 167
|
| 1681 |
+
},
|
| 1682 |
+
{
|
| 1683 |
+
"entropy": 0.15572900883853436,
|
| 1684 |
+
"epoch": 8.40764331210191,
|
| 1685 |
+
"grad_norm": 0.1874908059835434,
|
| 1686 |
+
"learning_rate": 9.016949152542374e-05,
|
| 1687 |
+
"loss": 0.0255,
|
| 1688 |
+
"mean_token_accuracy": 0.9973345398902893,
|
| 1689 |
+
"num_tokens": 2662315.0,
|
| 1690 |
+
"step": 168
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"entropy": 0.1498353499919176,
|
| 1694 |
+
"epoch": 8.45859872611465,
|
| 1695 |
+
"grad_norm": 0.20052368938922882,
|
| 1696 |
+
"learning_rate": 8.949152542372882e-05,
|
| 1697 |
+
"loss": 0.0236,
|
| 1698 |
+
"mean_token_accuracy": 0.9972066730260849,
|
| 1699 |
+
"num_tokens": 2678153.0,
|
| 1700 |
+
"step": 169
|
| 1701 |
+
},
|
| 1702 |
+
{
|
| 1703 |
+
"entropy": 0.14614599663764238,
|
| 1704 |
+
"epoch": 8.509554140127388,
|
| 1705 |
+
"grad_norm": 0.17338193953037262,
|
| 1706 |
+
"learning_rate": 8.88135593220339e-05,
|
| 1707 |
+
"loss": 0.0254,
|
| 1708 |
+
"mean_token_accuracy": 0.9967966079711914,
|
| 1709 |
+
"num_tokens": 2694537.0,
|
| 1710 |
+
"step": 170
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"entropy": 0.16034340485930443,
|
| 1714 |
+
"epoch": 8.560509554140127,
|
| 1715 |
+
"grad_norm": 0.2193768173456192,
|
| 1716 |
+
"learning_rate": 8.813559322033899e-05,
|
| 1717 |
+
"loss": 0.0294,
|
| 1718 |
+
"mean_token_accuracy": 0.9959402531385422,
|
| 1719 |
+
"num_tokens": 2710406.0,
|
| 1720 |
+
"step": 171
|
| 1721 |
+
},
|
| 1722 |
+
{
|
| 1723 |
+
"entropy": 0.1384358825162053,
|
| 1724 |
+
"epoch": 8.611464968152866,
|
| 1725 |
+
"grad_norm": 0.18264280259609222,
|
| 1726 |
+
"learning_rate": 8.745762711864407e-05,
|
| 1727 |
+
"loss": 0.0222,
|
| 1728 |
+
"mean_token_accuracy": 0.9968310818076134,
|
| 1729 |
+
"num_tokens": 2726790.0,
|
| 1730 |
+
"step": 172
|
| 1731 |
+
},
|
| 1732 |
+
{
|
| 1733 |
+
"entropy": 0.13634015154093504,
|
| 1734 |
+
"epoch": 8.662420382165605,
|
| 1735 |
+
"grad_norm": 0.22209401428699493,
|
| 1736 |
+
"learning_rate": 8.677966101694915e-05,
|
| 1737 |
+
"loss": 0.0252,
|
| 1738 |
+
"mean_token_accuracy": 0.9960110113024712,
|
| 1739 |
+
"num_tokens": 2743160.0,
|
| 1740 |
+
"step": 173
|
| 1741 |
+
},
|
| 1742 |
+
{
|
| 1743 |
+
"entropy": 0.1479941438883543,
|
| 1744 |
+
"epoch": 8.713375796178344,
|
| 1745 |
+
"grad_norm": 0.2538638412952423,
|
| 1746 |
+
"learning_rate": 8.610169491525424e-05,
|
| 1747 |
+
"loss": 0.0287,
|
| 1748 |
+
"mean_token_accuracy": 0.9960155114531517,
|
| 1749 |
+
"num_tokens": 2759028.0,
|
| 1750 |
+
"step": 174
|
| 1751 |
+
},
|
| 1752 |
+
{
|
| 1753 |
+
"entropy": 0.15019258111715317,
|
| 1754 |
+
"epoch": 8.764331210191083,
|
| 1755 |
+
"grad_norm": 0.1906321942806244,
|
| 1756 |
+
"learning_rate": 8.542372881355932e-05,
|
| 1757 |
+
"loss": 0.0225,
|
| 1758 |
+
"mean_token_accuracy": 0.9977850168943405,
|
| 1759 |
+
"num_tokens": 2775412.0,
|
| 1760 |
+
"step": 175
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"entropy": 0.15425540879368782,
|
| 1764 |
+
"epoch": 8.815286624203821,
|
| 1765 |
+
"grad_norm": 0.1589612066745758,
|
| 1766 |
+
"learning_rate": 8.474576271186441e-05,
|
| 1767 |
+
"loss": 0.022,
|
| 1768 |
+
"mean_token_accuracy": 0.9976635351777077,
|
| 1769 |
+
"num_tokens": 2790807.0,
|
| 1770 |
+
"step": 176
|
| 1771 |
+
},
|
| 1772 |
+
{
|
| 1773 |
+
"entropy": 0.14349912479519844,
|
| 1774 |
+
"epoch": 8.86624203821656,
|
| 1775 |
+
"grad_norm": 0.19421131908893585,
|
| 1776 |
+
"learning_rate": 8.406779661016949e-05,
|
| 1777 |
+
"loss": 0.0235,
|
| 1778 |
+
"mean_token_accuracy": 0.9972120821475983,
|
| 1779 |
+
"num_tokens": 2807191.0,
|
| 1780 |
+
"step": 177
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"entropy": 0.13660633098334074,
|
| 1784 |
+
"epoch": 8.9171974522293,
|
| 1785 |
+
"grad_norm": 0.1643456220626831,
|
| 1786 |
+
"learning_rate": 8.338983050847457e-05,
|
| 1787 |
+
"loss": 0.0209,
|
| 1788 |
+
"mean_token_accuracy": 0.9972153529524803,
|
| 1789 |
+
"num_tokens": 2823575.0,
|
| 1790 |
+
"step": 178
|
| 1791 |
+
},
|
| 1792 |
+
{
|
| 1793 |
+
"entropy": 0.14072524290531874,
|
| 1794 |
+
"epoch": 8.968152866242038,
|
| 1795 |
+
"grad_norm": 0.20266622304916382,
|
| 1796 |
+
"learning_rate": 8.271186440677966e-05,
|
| 1797 |
+
"loss": 0.0267,
|
| 1798 |
+
"mean_token_accuracy": 0.9961338341236115,
|
| 1799 |
+
"num_tokens": 2839959.0,
|
| 1800 |
+
"step": 179
|
| 1801 |
+
},
|
| 1802 |
+
{
|
| 1803 |
+
"entropy": 0.1358090877532959,
|
| 1804 |
+
"epoch": 9.0,
|
| 1805 |
+
"grad_norm": 0.20919552445411682,
|
| 1806 |
+
"learning_rate": 8.203389830508474e-05,
|
| 1807 |
+
"loss": 0.0206,
|
| 1808 |
+
"mean_token_accuracy": 0.9980488061904907,
|
| 1809 |
+
"num_tokens": 2849175.0,
|
| 1810 |
+
"step": 180
|
| 1811 |
+
},
|
| 1812 |
+
{
|
| 1813 |
+
"entropy": 0.1502374578267336,
|
| 1814 |
+
"epoch": 9.050955414012739,
|
| 1815 |
+
"grad_norm": 0.09697608649730682,
|
| 1816 |
+
"learning_rate": 8.135593220338983e-05,
|
| 1817 |
+
"loss": 0.017,
|
| 1818 |
+
"mean_token_accuracy": 0.9991338849067688,
|
| 1819 |
+
"num_tokens": 2864741.0,
|
| 1820 |
+
"step": 181
|
| 1821 |
+
},
|
| 1822 |
+
{
|
| 1823 |
+
"entropy": 0.131621690467,
|
| 1824 |
+
"epoch": 9.101910828025478,
|
| 1825 |
+
"grad_norm": 0.09774398058652878,
|
| 1826 |
+
"learning_rate": 8.067796610169493e-05,
|
| 1827 |
+
"loss": 0.0138,
|
| 1828 |
+
"mean_token_accuracy": 0.9994169324636459,
|
| 1829 |
+
"num_tokens": 2881125.0,
|
| 1830 |
+
"step": 182
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"entropy": 0.14369910676032305,
|
| 1834 |
+
"epoch": 9.152866242038217,
|
| 1835 |
+
"grad_norm": 0.11493105441331863,
|
| 1836 |
+
"learning_rate": 8e-05,
|
| 1837 |
+
"loss": 0.0194,
|
| 1838 |
+
"mean_token_accuracy": 0.9986832365393639,
|
| 1839 |
+
"num_tokens": 2896867.0,
|
| 1840 |
+
"step": 183
|
| 1841 |
+
},
|
| 1842 |
+
{
|
| 1843 |
+
"entropy": 0.13094604760408401,
|
| 1844 |
+
"epoch": 9.203821656050955,
|
| 1845 |
+
"grad_norm": 0.11127211898565292,
|
| 1846 |
+
"learning_rate": 7.93220338983051e-05,
|
| 1847 |
+
"loss": 0.0154,
|
| 1848 |
+
"mean_token_accuracy": 0.9990357309579849,
|
| 1849 |
+
"num_tokens": 2913251.0,
|
| 1850 |
+
"step": 184
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"entropy": 0.14038352109491825,
|
| 1854 |
+
"epoch": 9.254777070063694,
|
| 1855 |
+
"grad_norm": 0.08400645852088928,
|
| 1856 |
+
"learning_rate": 7.864406779661018e-05,
|
| 1857 |
+
"loss": 0.0138,
|
| 1858 |
+
"mean_token_accuracy": 0.9998054951429367,
|
| 1859 |
+
"num_tokens": 2929274.0,
|
| 1860 |
+
"step": 185
|
| 1861 |
+
},
|
| 1862 |
+
{
|
| 1863 |
+
"entropy": 0.12506767269223928,
|
| 1864 |
+
"epoch": 9.305732484076433,
|
| 1865 |
+
"grad_norm": 0.23133188486099243,
|
| 1866 |
+
"learning_rate": 7.796610169491526e-05,
|
| 1867 |
+
"loss": 0.0195,
|
| 1868 |
+
"mean_token_accuracy": 0.9976899400353432,
|
| 1869 |
+
"num_tokens": 2945658.0,
|
| 1870 |
+
"step": 186
|
| 1871 |
+
},
|
| 1872 |
+
{
|
| 1873 |
+
"entropy": 0.12773161567747593,
|
| 1874 |
+
"epoch": 9.356687898089172,
|
| 1875 |
+
"grad_norm": 0.09952336549758911,
|
| 1876 |
+
"learning_rate": 7.728813559322035e-05,
|
| 1877 |
+
"loss": 0.0144,
|
| 1878 |
+
"mean_token_accuracy": 0.9993524551391602,
|
| 1879 |
+
"num_tokens": 2962042.0,
|
| 1880 |
+
"step": 187
|
| 1881 |
+
},
|
| 1882 |
+
{
|
| 1883 |
+
"entropy": 0.13072299119085073,
|
| 1884 |
+
"epoch": 9.40764331210191,
|
| 1885 |
+
"grad_norm": 0.10790853202342987,
|
| 1886 |
+
"learning_rate": 7.661016949152543e-05,
|
| 1887 |
+
"loss": 0.0135,
|
| 1888 |
+
"mean_token_accuracy": 0.9991421699523926,
|
| 1889 |
+
"num_tokens": 2978117.0,
|
| 1890 |
+
"step": 188
|
| 1891 |
+
},
|
| 1892 |
+
{
|
| 1893 |
+
"entropy": 0.1242481516674161,
|
| 1894 |
+
"epoch": 9.45859872611465,
|
| 1895 |
+
"grad_norm": 0.1122814416885376,
|
| 1896 |
+
"learning_rate": 7.593220338983051e-05,
|
| 1897 |
+
"loss": 0.0133,
|
| 1898 |
+
"mean_token_accuracy": 0.9989665970206261,
|
| 1899 |
+
"num_tokens": 2994433.0,
|
| 1900 |
+
"step": 189
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"entropy": 0.13957257848232985,
|
| 1904 |
+
"epoch": 9.509554140127388,
|
| 1905 |
+
"grad_norm": 0.10560327023267746,
|
| 1906 |
+
"learning_rate": 7.52542372881356e-05,
|
| 1907 |
+
"loss": 0.0147,
|
| 1908 |
+
"mean_token_accuracy": 0.999118261039257,
|
| 1909 |
+
"num_tokens": 3010580.0,
|
| 1910 |
+
"step": 190
|
| 1911 |
+
},
|
| 1912 |
+
{
|
| 1913 |
+
"entropy": 0.1291163843125105,
|
| 1914 |
+
"epoch": 9.560509554140127,
|
| 1915 |
+
"grad_norm": 0.10222429037094116,
|
| 1916 |
+
"learning_rate": 7.457627118644068e-05,
|
| 1917 |
+
"loss": 0.0153,
|
| 1918 |
+
"mean_token_accuracy": 0.9986425712704659,
|
| 1919 |
+
"num_tokens": 3026964.0,
|
| 1920 |
+
"step": 191
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"entropy": 0.12281094025820494,
|
| 1924 |
+
"epoch": 9.611464968152866,
|
| 1925 |
+
"grad_norm": 0.11164791136980057,
|
| 1926 |
+
"learning_rate": 7.389830508474577e-05,
|
| 1927 |
+
"loss": 0.0135,
|
| 1928 |
+
"mean_token_accuracy": 0.9989040344953537,
|
| 1929 |
+
"num_tokens": 3043348.0,
|
| 1930 |
+
"step": 192
|
| 1931 |
+
},
|
| 1932 |
+
{
|
| 1933 |
+
"entropy": 0.13303168211132288,
|
| 1934 |
+
"epoch": 9.662420382165605,
|
| 1935 |
+
"grad_norm": 0.13216403126716614,
|
| 1936 |
+
"learning_rate": 7.322033898305085e-05,
|
| 1937 |
+
"loss": 0.0166,
|
| 1938 |
+
"mean_token_accuracy": 0.9990960881114006,
|
| 1939 |
+
"num_tokens": 3059216.0,
|
| 1940 |
+
"step": 193
|
| 1941 |
+
},
|
| 1942 |
+
{
|
| 1943 |
+
"entropy": 0.12154316995292902,
|
| 1944 |
+
"epoch": 9.713375796178344,
|
| 1945 |
+
"grad_norm": 0.11085794121026993,
|
| 1946 |
+
"learning_rate": 7.254237288135593e-05,
|
| 1947 |
+
"loss": 0.0129,
|
| 1948 |
+
"mean_token_accuracy": 0.9989554509520531,
|
| 1949 |
+
"num_tokens": 3075600.0,
|
| 1950 |
+
"step": 194
|
| 1951 |
+
},
|
| 1952 |
+
{
|
| 1953 |
+
"entropy": 0.12221709545701742,
|
| 1954 |
+
"epoch": 9.764331210191083,
|
| 1955 |
+
"grad_norm": 0.09001041948795319,
|
| 1956 |
+
"learning_rate": 7.186440677966102e-05,
|
| 1957 |
+
"loss": 0.0132,
|
| 1958 |
+
"mean_token_accuracy": 0.999326765537262,
|
| 1959 |
+
"num_tokens": 3091644.0,
|
| 1960 |
+
"step": 195
|
| 1961 |
+
},
|
| 1962 |
+
{
|
| 1963 |
+
"entropy": 0.12168204598128796,
|
| 1964 |
+
"epoch": 9.815286624203821,
|
| 1965 |
+
"grad_norm": 0.16245830059051514,
|
| 1966 |
+
"learning_rate": 7.11864406779661e-05,
|
| 1967 |
+
"loss": 0.0155,
|
| 1968 |
+
"mean_token_accuracy": 0.9988898932933807,
|
| 1969 |
+
"num_tokens": 3107655.0,
|
| 1970 |
+
"step": 196
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"entropy": 0.11974250618368387,
|
| 1974 |
+
"epoch": 9.86624203821656,
|
| 1975 |
+
"grad_norm": 0.15768024325370789,
|
| 1976 |
+
"learning_rate": 7.05084745762712e-05,
|
| 1977 |
+
"loss": 0.0157,
|
| 1978 |
+
"mean_token_accuracy": 0.9990957900881767,
|
| 1979 |
+
"num_tokens": 3124039.0,
|
| 1980 |
+
"step": 197
|
| 1981 |
+
},
|
| 1982 |
+
{
|
| 1983 |
+
"entropy": 0.13452547043561935,
|
| 1984 |
+
"epoch": 9.9171974522293,
|
| 1985 |
+
"grad_norm": 0.11966739594936371,
|
| 1986 |
+
"learning_rate": 6.983050847457627e-05,
|
| 1987 |
+
"loss": 0.0154,
|
| 1988 |
+
"mean_token_accuracy": 0.9989514648914337,
|
| 1989 |
+
"num_tokens": 3140150.0,
|
| 1990 |
+
"step": 198
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"entropy": 0.1197445448487997,
|
| 1994 |
+
"epoch": 9.968152866242038,
|
| 1995 |
+
"grad_norm": 0.12122300267219543,
|
| 1996 |
+
"learning_rate": 6.915254237288135e-05,
|
| 1997 |
+
"loss": 0.0144,
|
| 1998 |
+
"mean_token_accuracy": 0.999027393758297,
|
| 1999 |
+
"num_tokens": 3156534.0,
|
| 2000 |
+
"step": 199
|
| 2001 |
+
},
|
| 2002 |
+
{
|
| 2003 |
+
"entropy": 0.11745601445436478,
|
| 2004 |
+
"epoch": 10.0,
|
| 2005 |
+
"grad_norm": 0.12567812204360962,
|
| 2006 |
+
"learning_rate": 6.847457627118645e-05,
|
| 2007 |
+
"loss": 0.0128,
|
| 2008 |
+
"mean_token_accuracy": 0.9989682912826539,
|
| 2009 |
+
"num_tokens": 3165750.0,
|
| 2010 |
+
"step": 200
|
| 2011 |
+
},
|
| 2012 |
+
{
|
| 2013 |
+
"entropy": 0.12042893003672361,
|
| 2014 |
+
"epoch": 10.050955414012739,
|
| 2015 |
+
"grad_norm": 0.0663767158985138,
|
| 2016 |
+
"learning_rate": 6.779661016949152e-05,
|
| 2017 |
+
"loss": 0.0108,
|
| 2018 |
+
"mean_token_accuracy": 0.9996045753359795,
|
| 2019 |
+
"num_tokens": 3181897.0,
|
| 2020 |
+
"step": 201
|
| 2021 |
+
},
|
| 2022 |
+
{
|
| 2023 |
+
"entropy": 0.11832231562584639,
|
| 2024 |
+
"epoch": 10.101910828025478,
|
| 2025 |
+
"grad_norm": 0.07664559781551361,
|
| 2026 |
+
"learning_rate": 6.71186440677966e-05,
|
| 2027 |
+
"loss": 0.0108,
|
| 2028 |
+
"mean_token_accuracy": 0.999675951898098,
|
| 2029 |
+
"num_tokens": 3198281.0,
|
| 2030 |
+
"step": 202
|
| 2031 |
+
},
|
| 2032 |
+
{
|
| 2033 |
+
"entropy": 0.124271041713655,
|
| 2034 |
+
"epoch": 10.152866242038217,
|
| 2035 |
+
"grad_norm": 0.09082630276679993,
|
| 2036 |
+
"learning_rate": 6.64406779661017e-05,
|
| 2037 |
+
"loss": 0.0123,
|
| 2038 |
+
"mean_token_accuracy": 0.999231606721878,
|
| 2039 |
+
"num_tokens": 3214292.0,
|
| 2040 |
+
"step": 203
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"entropy": 0.12200119253247976,
|
| 2044 |
+
"epoch": 10.203821656050955,
|
| 2045 |
+
"grad_norm": 0.13074713945388794,
|
| 2046 |
+
"learning_rate": 6.576271186440678e-05,
|
| 2047 |
+
"loss": 0.0117,
|
| 2048 |
+
"mean_token_accuracy": 0.9990891143679619,
|
| 2049 |
+
"num_tokens": 3229708.0,
|
| 2050 |
+
"step": 204
|
| 2051 |
+
},
|
| 2052 |
+
{
|
| 2053 |
+
"entropy": 0.11397830117493868,
|
| 2054 |
+
"epoch": 10.254777070063694,
|
| 2055 |
+
"grad_norm": 0.08310648053884506,
|
| 2056 |
+
"learning_rate": 6.508474576271187e-05,
|
| 2057 |
+
"loss": 0.0113,
|
| 2058 |
+
"mean_token_accuracy": 0.9991616681218147,
|
| 2059 |
+
"num_tokens": 3246092.0,
|
| 2060 |
+
"step": 205
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"entropy": 0.1141798933967948,
|
| 2064 |
+
"epoch": 10.305732484076433,
|
| 2065 |
+
"grad_norm": 0.05808615684509277,
|
| 2066 |
+
"learning_rate": 6.440677966101695e-05,
|
| 2067 |
+
"loss": 0.0086,
|
| 2068 |
+
"mean_token_accuracy": 0.9996744319796562,
|
| 2069 |
+
"num_tokens": 3262476.0,
|
| 2070 |
+
"step": 206
|
| 2071 |
+
},
|
| 2072 |
+
{
|
| 2073 |
+
"entropy": 0.11953330133110285,
|
| 2074 |
+
"epoch": 10.356687898089172,
|
| 2075 |
+
"grad_norm": 0.179758682847023,
|
| 2076 |
+
"learning_rate": 6.372881355932203e-05,
|
| 2077 |
+
"loss": 0.0184,
|
| 2078 |
+
"mean_token_accuracy": 0.998580165207386,
|
| 2079 |
+
"num_tokens": 3278499.0,
|
| 2080 |
+
"step": 207
|
| 2081 |
+
},
|
| 2082 |
+
{
|
| 2083 |
+
"entropy": 0.11975150462239981,
|
| 2084 |
+
"epoch": 10.40764331210191,
|
| 2085 |
+
"grad_norm": 0.09039207547903061,
|
| 2086 |
+
"learning_rate": 6.305084745762713e-05,
|
| 2087 |
+
"loss": 0.0114,
|
| 2088 |
+
"mean_token_accuracy": 0.9994799271225929,
|
| 2089 |
+
"num_tokens": 3294883.0,
|
| 2090 |
+
"step": 208
|
| 2091 |
+
},
|
| 2092 |
+
{
|
| 2093 |
+
"entropy": 0.12320903595536947,
|
| 2094 |
+
"epoch": 10.45859872611465,
|
| 2095 |
+
"grad_norm": 0.05162489041686058,
|
| 2096 |
+
"learning_rate": 6.237288135593221e-05,
|
| 2097 |
+
"loss": 0.0102,
|
| 2098 |
+
"mean_token_accuracy": 0.9998693540692329,
|
| 2099 |
+
"num_tokens": 3311267.0,
|
| 2100 |
+
"step": 209
|
| 2101 |
+
},
|
| 2102 |
+
{
|
| 2103 |
+
"entropy": 0.10688549000769854,
|
| 2104 |
+
"epoch": 10.509554140127388,
|
| 2105 |
+
"grad_norm": 0.06506083160638809,
|
| 2106 |
+
"learning_rate": 6.169491525423729e-05,
|
| 2107 |
+
"loss": 0.0088,
|
| 2108 |
+
"mean_token_accuracy": 0.9997412338852882,
|
| 2109 |
+
"num_tokens": 3327651.0,
|
| 2110 |
+
"step": 210
|
| 2111 |
+
},
|
| 2112 |
+
{
|
| 2113 |
+
"entropy": 0.10415452346205711,
|
| 2114 |
+
"epoch": 10.560509554140127,
|
| 2115 |
+
"grad_norm": 0.06173918396234512,
|
| 2116 |
+
"learning_rate": 6.101694915254238e-05,
|
| 2117 |
+
"loss": 0.0087,
|
| 2118 |
+
"mean_token_accuracy": 0.9996152892708778,
|
| 2119 |
+
"num_tokens": 3344035.0,
|
| 2120 |
+
"step": 211
|
| 2121 |
+
},
|
| 2122 |
+
{
|
| 2123 |
+
"entropy": 0.11600155290216208,
|
| 2124 |
+
"epoch": 10.611464968152866,
|
| 2125 |
+
"grad_norm": 0.050665903836488724,
|
| 2126 |
+
"learning_rate": 6.033898305084746e-05,
|
| 2127 |
+
"loss": 0.0096,
|
| 2128 |
+
"mean_token_accuracy": 0.9998079538345337,
|
| 2129 |
+
"num_tokens": 3360419.0,
|
| 2130 |
+
"step": 212
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"entropy": 0.10566186718642712,
|
| 2134 |
+
"epoch": 10.662420382165605,
|
| 2135 |
+
"grad_norm": 0.07954474538564682,
|
| 2136 |
+
"learning_rate": 5.966101694915255e-05,
|
| 2137 |
+
"loss": 0.0097,
|
| 2138 |
+
"mean_token_accuracy": 0.9996142834424973,
|
| 2139 |
+
"num_tokens": 3376789.0,
|
| 2140 |
+
"step": 213
|
| 2141 |
+
},
|
| 2142 |
+
{
|
| 2143 |
+
"entropy": 0.11559769324958324,
|
| 2144 |
+
"epoch": 10.713375796178344,
|
| 2145 |
+
"grad_norm": 0.09305853396654129,
|
| 2146 |
+
"learning_rate": 5.8983050847457634e-05,
|
| 2147 |
+
"loss": 0.0107,
|
| 2148 |
+
"mean_token_accuracy": 0.9994818046689034,
|
| 2149 |
+
"num_tokens": 3393173.0,
|
| 2150 |
+
"step": 214
|
| 2151 |
+
},
|
| 2152 |
+
{
|
| 2153 |
+
"entropy": 0.11908081825822592,
|
| 2154 |
+
"epoch": 10.764331210191083,
|
| 2155 |
+
"grad_norm": 0.04667564108967781,
|
| 2156 |
+
"learning_rate": 5.830508474576272e-05,
|
| 2157 |
+
"loss": 0.0094,
|
| 2158 |
+
"mean_token_accuracy": 0.999924786388874,
|
| 2159 |
+
"num_tokens": 3408769.0,
|
| 2160 |
+
"step": 215
|
| 2161 |
+
},
|
| 2162 |
+
{
|
| 2163 |
+
"entropy": 0.1183215007185936,
|
| 2164 |
+
"epoch": 10.815286624203821,
|
| 2165 |
+
"grad_norm": 0.04595829173922539,
|
| 2166 |
+
"learning_rate": 5.76271186440678e-05,
|
| 2167 |
+
"loss": 0.0093,
|
| 2168 |
+
"mean_token_accuracy": 0.9997801333665848,
|
| 2169 |
+
"num_tokens": 3424473.0,
|
| 2170 |
+
"step": 216
|
| 2171 |
+
},
|
| 2172 |
+
{
|
| 2173 |
+
"entropy": 0.1201422717422247,
|
| 2174 |
+
"epoch": 10.86624203821656,
|
| 2175 |
+
"grad_norm": 0.06230077147483826,
|
| 2176 |
+
"learning_rate": 5.6949152542372884e-05,
|
| 2177 |
+
"loss": 0.0099,
|
| 2178 |
+
"mean_token_accuracy": 0.9996102750301361,
|
| 2179 |
+
"num_tokens": 3440341.0,
|
| 2180 |
+
"step": 217
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"entropy": 0.11482239048928022,
|
| 2184 |
+
"epoch": 10.9171974522293,
|
| 2185 |
+
"grad_norm": 0.05606631562113762,
|
| 2186 |
+
"learning_rate": 5.627118644067797e-05,
|
| 2187 |
+
"loss": 0.0103,
|
| 2188 |
+
"mean_token_accuracy": 0.9998069554567337,
|
| 2189 |
+
"num_tokens": 3456725.0,
|
| 2190 |
+
"step": 218
|
| 2191 |
+
},
|
| 2192 |
+
{
|
| 2193 |
+
"entropy": 0.11935457587242126,
|
| 2194 |
+
"epoch": 10.968152866242038,
|
| 2195 |
+
"grad_norm": 0.07897260040044785,
|
| 2196 |
+
"learning_rate": 5.5593220338983056e-05,
|
| 2197 |
+
"loss": 0.0101,
|
| 2198 |
+
"mean_token_accuracy": 0.999412514269352,
|
| 2199 |
+
"num_tokens": 3473109.0,
|
| 2200 |
+
"step": 219
|
| 2201 |
+
},
|
| 2202 |
+
{
|
| 2203 |
+
"entropy": 0.11128216087818146,
|
| 2204 |
+
"epoch": 11.0,
|
| 2205 |
+
"grad_norm": 0.0996818020939827,
|
| 2206 |
+
"learning_rate": 5.4915254237288135e-05,
|
| 2207 |
+
"loss": 0.0091,
|
| 2208 |
+
"mean_token_accuracy": 0.999491286277771,
|
| 2209 |
+
"num_tokens": 3482325.0,
|
| 2210 |
+
"step": 220
|
| 2211 |
+
},
|
| 2212 |
+
{
|
| 2213 |
+
"entropy": 0.11160805076360703,
|
| 2214 |
+
"epoch": 11.050955414012739,
|
| 2215 |
+
"grad_norm": 0.05367226526141167,
|
| 2216 |
+
"learning_rate": 5.423728813559322e-05,
|
| 2217 |
+
"loss": 0.0088,
|
| 2218 |
+
"mean_token_accuracy": 0.9997417852282524,
|
| 2219 |
+
"num_tokens": 3498709.0,
|
| 2220 |
+
"step": 221
|
| 2221 |
+
},
|
| 2222 |
+
{
|
| 2223 |
+
"entropy": 0.1070787301287055,
|
| 2224 |
+
"epoch": 11.101910828025478,
|
| 2225 |
+
"grad_norm": 0.05334122106432915,
|
| 2226 |
+
"learning_rate": 5.355932203389831e-05,
|
| 2227 |
+
"loss": 0.0082,
|
| 2228 |
+
"mean_token_accuracy": 0.9998068884015083,
|
| 2229 |
+
"num_tokens": 3515093.0,
|
| 2230 |
+
"step": 222
|
| 2231 |
+
},
|
| 2232 |
+
{
|
| 2233 |
+
"entropy": 0.10628996696323156,
|
| 2234 |
+
"epoch": 11.152866242038217,
|
| 2235 |
+
"grad_norm": 0.055135585367679596,
|
| 2236 |
+
"learning_rate": 5.288135593220339e-05,
|
| 2237 |
+
"loss": 0.008,
|
| 2238 |
+
"mean_token_accuracy": 0.9998051300644875,
|
| 2239 |
+
"num_tokens": 3531477.0,
|
| 2240 |
+
"step": 223
|
| 2241 |
+
},
|
| 2242 |
+
{
|
| 2243 |
+
"entropy": 0.10990262683480978,
|
| 2244 |
+
"epoch": 11.203821656050955,
|
| 2245 |
+
"grad_norm": 0.03518820181488991,
|
| 2246 |
+
"learning_rate": 5.220338983050848e-05,
|
| 2247 |
+
"loss": 0.0072,
|
| 2248 |
+
"mean_token_accuracy": 1.0,
|
| 2249 |
+
"num_tokens": 3547861.0,
|
| 2250 |
+
"step": 224
|
| 2251 |
+
},
|
| 2252 |
+
{
|
| 2253 |
+
"entropy": 0.10836105886846781,
|
| 2254 |
+
"epoch": 11.254777070063694,
|
| 2255 |
+
"grad_norm": 0.0368078239262104,
|
| 2256 |
+
"learning_rate": 5.152542372881356e-05,
|
| 2257 |
+
"loss": 0.0075,
|
| 2258 |
+
"mean_token_accuracy": 0.9999355971813202,
|
| 2259 |
+
"num_tokens": 3564245.0,
|
| 2260 |
+
"step": 225
|
| 2261 |
+
},
|
| 2262 |
+
{
|
| 2263 |
+
"entropy": 0.1082956362515688,
|
| 2264 |
+
"epoch": 11.305732484076433,
|
| 2265 |
+
"grad_norm": 0.03756461665034294,
|
| 2266 |
+
"learning_rate": 5.0847457627118643e-05,
|
| 2267 |
+
"loss": 0.0075,
|
| 2268 |
+
"mean_token_accuracy": 0.9999363869428635,
|
| 2269 |
+
"num_tokens": 3579752.0,
|
| 2270 |
+
"step": 226
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"entropy": 0.10948039591312408,
|
| 2274 |
+
"epoch": 11.356687898089172,
|
| 2275 |
+
"grad_norm": 0.04509361833333969,
|
| 2276 |
+
"learning_rate": 5.016949152542373e-05,
|
| 2277 |
+
"loss": 0.0081,
|
| 2278 |
+
"mean_token_accuracy": 0.9998712986707687,
|
| 2279 |
+
"num_tokens": 3596136.0,
|
| 2280 |
+
"step": 227
|
| 2281 |
+
},
|
| 2282 |
+
{
|
| 2283 |
+
"entropy": 0.1059270715340972,
|
| 2284 |
+
"epoch": 11.40764331210191,
|
| 2285 |
+
"grad_norm": 0.047251664102077484,
|
| 2286 |
+
"learning_rate": 4.9491525423728815e-05,
|
| 2287 |
+
"loss": 0.008,
|
| 2288 |
+
"mean_token_accuracy": 0.9997420459985733,
|
| 2289 |
+
"num_tokens": 3612520.0,
|
| 2290 |
+
"step": 228
|
| 2291 |
+
},
|
| 2292 |
+
{
|
| 2293 |
+
"entropy": 0.11516531370580196,
|
| 2294 |
+
"epoch": 11.45859872611465,
|
| 2295 |
+
"grad_norm": 0.04376146197319031,
|
| 2296 |
+
"learning_rate": 4.88135593220339e-05,
|
| 2297 |
+
"loss": 0.0095,
|
| 2298 |
+
"mean_token_accuracy": 0.9995211735367775,
|
| 2299 |
+
"num_tokens": 3628322.0,
|
| 2300 |
+
"step": 229
|
| 2301 |
+
},
|
| 2302 |
+
{
|
| 2303 |
+
"entropy": 0.10558972507715225,
|
| 2304 |
+
"epoch": 11.509554140127388,
|
| 2305 |
+
"grad_norm": 0.13402560353279114,
|
| 2306 |
+
"learning_rate": 4.813559322033899e-05,
|
| 2307 |
+
"loss": 0.0114,
|
| 2308 |
+
"mean_token_accuracy": 0.9990246370434761,
|
| 2309 |
+
"num_tokens": 3644333.0,
|
| 2310 |
+
"step": 230
|
| 2311 |
+
},
|
| 2312 |
+
{
|
| 2313 |
+
"entropy": 0.10923876147717237,
|
| 2314 |
+
"epoch": 11.560509554140127,
|
| 2315 |
+
"grad_norm": 0.040236614644527435,
|
| 2316 |
+
"learning_rate": 4.745762711864407e-05,
|
| 2317 |
+
"loss": 0.0074,
|
| 2318 |
+
"mean_token_accuracy": 0.9999355301260948,
|
| 2319 |
+
"num_tokens": 3660717.0,
|
| 2320 |
+
"step": 231
|
| 2321 |
+
},
|
| 2322 |
+
{
|
| 2323 |
+
"entropy": 0.10896432586014271,
|
| 2324 |
+
"epoch": 11.611464968152866,
|
| 2325 |
+
"grad_norm": 0.17227506637573242,
|
| 2326 |
+
"learning_rate": 4.677966101694916e-05,
|
| 2327 |
+
"loss": 0.0083,
|
| 2328 |
+
"mean_token_accuracy": 0.9997416883707047,
|
| 2329 |
+
"num_tokens": 3677101.0,
|
| 2330 |
+
"step": 232
|
| 2331 |
+
},
|
| 2332 |
+
{
|
| 2333 |
+
"entropy": 0.10140051785856485,
|
| 2334 |
+
"epoch": 11.662420382165605,
|
| 2335 |
+
"grad_norm": 0.03426056727766991,
|
| 2336 |
+
"learning_rate": 4.610169491525424e-05,
|
| 2337 |
+
"loss": 0.0067,
|
| 2338 |
+
"mean_token_accuracy": 0.999934658408165,
|
| 2339 |
+
"num_tokens": 3693248.0,
|
| 2340 |
+
"step": 233
|
| 2341 |
+
},
|
| 2342 |
+
{
|
| 2343 |
+
"entropy": 0.11477772425860167,
|
| 2344 |
+
"epoch": 11.713375796178344,
|
| 2345 |
+
"grad_norm": 0.043852221220731735,
|
| 2346 |
+
"learning_rate": 4.542372881355932e-05,
|
| 2347 |
+
"loss": 0.0083,
|
| 2348 |
+
"mean_token_accuracy": 0.9997580200433731,
|
| 2349 |
+
"num_tokens": 3708777.0,
|
| 2350 |
+
"step": 234
|
| 2351 |
+
},
|
| 2352 |
+
{
|
| 2353 |
+
"entropy": 0.1119665578007698,
|
| 2354 |
+
"epoch": 11.764331210191083,
|
| 2355 |
+
"grad_norm": 0.03210538625717163,
|
| 2356 |
+
"learning_rate": 4.474576271186441e-05,
|
| 2357 |
+
"loss": 0.007,
|
| 2358 |
+
"mean_token_accuracy": 0.9998657628893852,
|
| 2359 |
+
"num_tokens": 3725161.0,
|
| 2360 |
+
"step": 235
|
| 2361 |
+
},
|
| 2362 |
+
{
|
| 2363 |
+
"entropy": 0.10569995269179344,
|
| 2364 |
+
"epoch": 11.815286624203821,
|
| 2365 |
+
"grad_norm": 0.033930789679288864,
|
| 2366 |
+
"learning_rate": 4.4067796610169495e-05,
|
| 2367 |
+
"loss": 0.0077,
|
| 2368 |
+
"mean_token_accuracy": 1.0,
|
| 2369 |
+
"num_tokens": 3741531.0,
|
| 2370 |
+
"step": 236
|
| 2371 |
+
},
|
| 2372 |
+
{
|
| 2373 |
+
"entropy": 0.10806028544902802,
|
| 2374 |
+
"epoch": 11.86624203821656,
|
| 2375 |
+
"grad_norm": 0.0338793508708477,
|
| 2376 |
+
"learning_rate": 4.3389830508474574e-05,
|
| 2377 |
+
"loss": 0.0074,
|
| 2378 |
+
"mean_token_accuracy": 0.999867282807827,
|
| 2379 |
+
"num_tokens": 3757847.0,
|
| 2380 |
+
"step": 237
|
| 2381 |
+
},
|
| 2382 |
+
{
|
| 2383 |
+
"entropy": 0.10707560367882252,
|
| 2384 |
+
"epoch": 11.9171974522293,
|
| 2385 |
+
"grad_norm": 0.03882453218102455,
|
| 2386 |
+
"learning_rate": 4.271186440677966e-05,
|
| 2387 |
+
"loss": 0.0071,
|
| 2388 |
+
"mean_token_accuracy": 0.9999340698122978,
|
| 2389 |
+
"num_tokens": 3774231.0,
|
| 2390 |
+
"step": 238
|
| 2391 |
+
},
|
| 2392 |
+
{
|
| 2393 |
+
"entropy": 0.10312746185809374,
|
| 2394 |
+
"epoch": 11.968152866242038,
|
| 2395 |
+
"grad_norm": 0.043584294617176056,
|
| 2396 |
+
"learning_rate": 4.2033898305084746e-05,
|
| 2397 |
+
"loss": 0.0068,
|
| 2398 |
+
"mean_token_accuracy": 1.0,
|
| 2399 |
+
"num_tokens": 3790312.0,
|
| 2400 |
+
"step": 239
|
| 2401 |
+
},
|
| 2402 |
+
{
|
| 2403 |
+
"entropy": 0.11070414036512374,
|
| 2404 |
+
"epoch": 12.0,
|
| 2405 |
+
"grad_norm": 0.045331358909606934,
|
| 2406 |
+
"learning_rate": 4.135593220338983e-05,
|
| 2407 |
+
"loss": 0.0079,
|
| 2408 |
+
"mean_token_accuracy": 1.0,
|
| 2409 |
+
"num_tokens": 3798900.0,
|
| 2410 |
+
"step": 240
|
| 2411 |
+
},
|
| 2412 |
+
{
|
| 2413 |
+
"entropy": 0.10184395220130682,
|
| 2414 |
+
"epoch": 12.050955414012739,
|
| 2415 |
+
"grad_norm": 0.026744039729237556,
|
| 2416 |
+
"learning_rate": 4.067796610169492e-05,
|
| 2417 |
+
"loss": 0.0059,
|
| 2418 |
+
"mean_token_accuracy": 1.0,
|
| 2419 |
+
"num_tokens": 3814769.0,
|
| 2420 |
+
"step": 241
|
| 2421 |
+
},
|
| 2422 |
+
{
|
| 2423 |
+
"entropy": 0.10635124333202839,
|
| 2424 |
+
"epoch": 12.101910828025478,
|
| 2425 |
+
"grad_norm": 0.028835609555244446,
|
| 2426 |
+
"learning_rate": 4e-05,
|
| 2427 |
+
"loss": 0.0065,
|
| 2428 |
+
"mean_token_accuracy": 0.99993547052145,
|
| 2429 |
+
"num_tokens": 3831153.0,
|
| 2430 |
+
"step": 242
|
| 2431 |
+
},
|
| 2432 |
+
{
|
| 2433 |
+
"entropy": 0.10043890587985516,
|
| 2434 |
+
"epoch": 12.152866242038217,
|
| 2435 |
+
"grad_norm": 0.04694792628288269,
|
| 2436 |
+
"learning_rate": 3.932203389830509e-05,
|
| 2437 |
+
"loss": 0.0082,
|
| 2438 |
+
"mean_token_accuracy": 0.9998090639710426,
|
| 2439 |
+
"num_tokens": 3847537.0,
|
| 2440 |
+
"step": 243
|
| 2441 |
+
},
|
| 2442 |
+
{
|
| 2443 |
+
"entropy": 0.10733645875006914,
|
| 2444 |
+
"epoch": 12.203821656050955,
|
| 2445 |
+
"grad_norm": 0.026845334097743034,
|
| 2446 |
+
"learning_rate": 3.8644067796610175e-05,
|
| 2447 |
+
"loss": 0.0068,
|
| 2448 |
+
"mean_token_accuracy": 0.9999350681900978,
|
| 2449 |
+
"num_tokens": 3863921.0,
|
| 2450 |
+
"step": 244
|
| 2451 |
+
},
|
| 2452 |
+
{
|
| 2453 |
+
"entropy": 0.09936889354139566,
|
| 2454 |
+
"epoch": 12.254777070063694,
|
| 2455 |
+
"grad_norm": 0.03058328479528427,
|
| 2456 |
+
"learning_rate": 3.7966101694915254e-05,
|
| 2457 |
+
"loss": 0.0069,
|
| 2458 |
+
"mean_token_accuracy": 0.9997949451208115,
|
| 2459 |
+
"num_tokens": 3879635.0,
|
| 2460 |
+
"step": 245
|
| 2461 |
+
},
|
| 2462 |
+
{
|
| 2463 |
+
"entropy": 0.10591370053589344,
|
| 2464 |
+
"epoch": 12.305732484076433,
|
| 2465 |
+
"grad_norm": 0.028634637594223022,
|
| 2466 |
+
"learning_rate": 3.728813559322034e-05,
|
| 2467 |
+
"loss": 0.007,
|
| 2468 |
+
"mean_token_accuracy": 1.0,
|
| 2469 |
+
"num_tokens": 3896019.0,
|
| 2470 |
+
"step": 246
|
| 2471 |
+
},
|
| 2472 |
+
{
|
| 2473 |
+
"entropy": 0.10039967019110918,
|
| 2474 |
+
"epoch": 12.356687898089172,
|
| 2475 |
+
"grad_norm": 0.028052492067217827,
|
| 2476 |
+
"learning_rate": 3.6610169491525426e-05,
|
| 2477 |
+
"loss": 0.0064,
|
| 2478 |
+
"mean_token_accuracy": 1.0,
|
| 2479 |
+
"num_tokens": 3912403.0,
|
| 2480 |
+
"step": 247
|
| 2481 |
+
},
|
| 2482 |
+
{
|
| 2483 |
+
"entropy": 0.10025474335998297,
|
| 2484 |
+
"epoch": 12.40764331210191,
|
| 2485 |
+
"grad_norm": 0.02830340526998043,
|
| 2486 |
+
"learning_rate": 3.593220338983051e-05,
|
| 2487 |
+
"loss": 0.0063,
|
| 2488 |
+
"mean_token_accuracy": 0.9998716190457344,
|
| 2489 |
+
"num_tokens": 3928787.0,
|
| 2490 |
+
"step": 248
|
| 2491 |
+
},
|
| 2492 |
+
{
|
| 2493 |
+
"entropy": 0.10644072014838457,
|
| 2494 |
+
"epoch": 12.45859872611465,
|
| 2495 |
+
"grad_norm": 0.02761429361999035,
|
| 2496 |
+
"learning_rate": 3.52542372881356e-05,
|
| 2497 |
+
"loss": 0.0068,
|
| 2498 |
+
"mean_token_accuracy": 1.0,
|
| 2499 |
+
"num_tokens": 3944898.0,
|
| 2500 |
+
"step": 249
|
| 2501 |
+
},
|
| 2502 |
+
{
|
| 2503 |
+
"entropy": 0.1037906389683485,
|
| 2504 |
+
"epoch": 12.509554140127388,
|
| 2505 |
+
"grad_norm": 0.03129090368747711,
|
| 2506 |
+
"learning_rate": 3.4576271186440676e-05,
|
| 2507 |
+
"loss": 0.007,
|
| 2508 |
+
"mean_token_accuracy": 0.9999349936842918,
|
| 2509 |
+
"num_tokens": 3961282.0,
|
| 2510 |
+
"step": 250
|
| 2511 |
+
},
|
| 2512 |
+
{
|
| 2513 |
+
"entropy": 0.10302811488509178,
|
| 2514 |
+
"epoch": 12.560509554140127,
|
| 2515 |
+
"grad_norm": 0.026480698958039284,
|
| 2516 |
+
"learning_rate": 3.389830508474576e-05,
|
| 2517 |
+
"loss": 0.0067,
|
| 2518 |
+
"mean_token_accuracy": 1.0,
|
| 2519 |
+
"num_tokens": 3977652.0,
|
| 2520 |
+
"step": 251
|
| 2521 |
+
},
|
| 2522 |
+
{
|
| 2523 |
+
"entropy": 0.10825122147798538,
|
| 2524 |
+
"epoch": 12.611464968152866,
|
| 2525 |
+
"grad_norm": 0.029188238084316254,
|
| 2526 |
+
"learning_rate": 3.322033898305085e-05,
|
| 2527 |
+
"loss": 0.0072,
|
| 2528 |
+
"mean_token_accuracy": 0.999933548271656,
|
| 2529 |
+
"num_tokens": 3994036.0,
|
| 2530 |
+
"step": 252
|
| 2531 |
+
},
|
| 2532 |
+
{
|
| 2533 |
+
"entropy": 0.10613303910940886,
|
| 2534 |
+
"epoch": 12.662420382165605,
|
| 2535 |
+
"grad_norm": 0.028023159131407738,
|
| 2536 |
+
"learning_rate": 3.2542372881355934e-05,
|
| 2537 |
+
"loss": 0.0066,
|
| 2538 |
+
"mean_token_accuracy": 1.0,
|
| 2539 |
+
"num_tokens": 4008991.0,
|
| 2540 |
+
"step": 253
|
| 2541 |
+
},
|
| 2542 |
+
{
|
| 2543 |
+
"entropy": 0.11473400145769119,
|
| 2544 |
+
"epoch": 12.713375796178344,
|
| 2545 |
+
"grad_norm": 0.027821091935038567,
|
| 2546 |
+
"learning_rate": 3.186440677966101e-05,
|
| 2547 |
+
"loss": 0.0063,
|
| 2548 |
+
"mean_token_accuracy": 1.0,
|
| 2549 |
+
"num_tokens": 4024407.0,
|
| 2550 |
+
"step": 254
|
| 2551 |
+
},
|
| 2552 |
+
{
|
| 2553 |
+
"entropy": 0.10935076046735048,
|
| 2554 |
+
"epoch": 12.764331210191083,
|
| 2555 |
+
"grad_norm": 0.031338147819042206,
|
| 2556 |
+
"learning_rate": 3.1186440677966106e-05,
|
| 2557 |
+
"loss": 0.0067,
|
| 2558 |
+
"mean_token_accuracy": 0.9999353662133217,
|
| 2559 |
+
"num_tokens": 4040791.0,
|
| 2560 |
+
"step": 255
|
| 2561 |
+
},
|
| 2562 |
+
{
|
| 2563 |
+
"entropy": 0.10937976185232401,
|
| 2564 |
+
"epoch": 12.815286624203821,
|
| 2565 |
+
"grad_norm": 0.029371492564678192,
|
| 2566 |
+
"learning_rate": 3.050847457627119e-05,
|
| 2567 |
+
"loss": 0.007,
|
| 2568 |
+
"mean_token_accuracy": 0.9998026117682457,
|
| 2569 |
+
"num_tokens": 4057107.0,
|
| 2570 |
+
"step": 256
|
| 2571 |
+
},
|
| 2572 |
+
{
|
| 2573 |
+
"entropy": 0.10393634624779224,
|
| 2574 |
+
"epoch": 12.86624203821656,
|
| 2575 |
+
"grad_norm": 0.027899138629436493,
|
| 2576 |
+
"learning_rate": 2.9830508474576274e-05,
|
| 2577 |
+
"loss": 0.0064,
|
| 2578 |
+
"mean_token_accuracy": 0.9999347925186157,
|
| 2579 |
+
"num_tokens": 4073491.0,
|
| 2580 |
+
"step": 257
|
| 2581 |
+
},
|
| 2582 |
+
{
|
| 2583 |
+
"entropy": 0.10141265112906694,
|
| 2584 |
+
"epoch": 12.9171974522293,
|
| 2585 |
+
"grad_norm": 0.028487876057624817,
|
| 2586 |
+
"learning_rate": 2.915254237288136e-05,
|
| 2587 |
+
"loss": 0.0065,
|
| 2588 |
+
"mean_token_accuracy": 1.0,
|
| 2589 |
+
"num_tokens": 4089875.0,
|
| 2590 |
+
"step": 258
|
| 2591 |
+
},
|
| 2592 |
+
{
|
| 2593 |
+
"entropy": 0.0965907471254468,
|
| 2594 |
+
"epoch": 12.968152866242038,
|
| 2595 |
+
"grad_norm": 0.028266245499253273,
|
| 2596 |
+
"learning_rate": 2.8474576271186442e-05,
|
| 2597 |
+
"loss": 0.0067,
|
| 2598 |
+
"mean_token_accuracy": 0.9998710304498672,
|
| 2599 |
+
"num_tokens": 4106259.0,
|
| 2600 |
+
"step": 259
|
| 2601 |
+
},
|
| 2602 |
+
{
|
| 2603 |
+
"entropy": 0.10284970700740814,
|
| 2604 |
+
"epoch": 13.0,
|
| 2605 |
+
"grad_norm": 0.03353312984108925,
|
| 2606 |
+
"learning_rate": 2.7796610169491528e-05,
|
| 2607 |
+
"loss": 0.0052,
|
| 2608 |
+
"mean_token_accuracy": 1.0,
|
| 2609 |
+
"num_tokens": 4115475.0,
|
| 2610 |
+
"step": 260
|
| 2611 |
+
},
|
| 2612 |
+
{
|
| 2613 |
+
"entropy": 0.10281004942953587,
|
| 2614 |
+
"epoch": 13.050955414012739,
|
| 2615 |
+
"grad_norm": 0.02671942301094532,
|
| 2616 |
+
"learning_rate": 2.711864406779661e-05,
|
| 2617 |
+
"loss": 0.0062,
|
| 2618 |
+
"mean_token_accuracy": 0.9998715296387672,
|
| 2619 |
+
"num_tokens": 4131231.0,
|
| 2620 |
+
"step": 261
|
| 2621 |
+
},
|
| 2622 |
+
{
|
| 2623 |
+
"entropy": 0.10125970002263784,
|
| 2624 |
+
"epoch": 13.101910828025478,
|
| 2625 |
+
"grad_norm": 0.025036444887518883,
|
| 2626 |
+
"learning_rate": 2.6440677966101696e-05,
|
| 2627 |
+
"loss": 0.006,
|
| 2628 |
+
"mean_token_accuracy": 0.9999360293149948,
|
| 2629 |
+
"num_tokens": 4147601.0,
|
| 2630 |
+
"step": 262
|
| 2631 |
+
},
|
| 2632 |
+
{
|
| 2633 |
+
"entropy": 0.09949134290218353,
|
| 2634 |
+
"epoch": 13.152866242038217,
|
| 2635 |
+
"grad_norm": 0.02558460272848606,
|
| 2636 |
+
"learning_rate": 2.576271186440678e-05,
|
| 2637 |
+
"loss": 0.006,
|
| 2638 |
+
"mean_token_accuracy": 1.0,
|
| 2639 |
+
"num_tokens": 4163985.0,
|
| 2640 |
+
"step": 263
|
| 2641 |
+
},
|
| 2642 |
+
{
|
| 2643 |
+
"entropy": 0.09930670354515314,
|
| 2644 |
+
"epoch": 13.203821656050955,
|
| 2645 |
+
"grad_norm": 0.026054522022604942,
|
| 2646 |
+
"learning_rate": 2.5084745762711865e-05,
|
| 2647 |
+
"loss": 0.0067,
|
| 2648 |
+
"mean_token_accuracy": 1.0,
|
| 2649 |
+
"num_tokens": 4180369.0,
|
| 2650 |
+
"step": 264
|
| 2651 |
+
},
|
| 2652 |
+
{
|
| 2653 |
+
"entropy": 0.10627400875091553,
|
| 2654 |
+
"epoch": 13.254777070063694,
|
| 2655 |
+
"grad_norm": 0.026049450039863586,
|
| 2656 |
+
"learning_rate": 2.440677966101695e-05,
|
| 2657 |
+
"loss": 0.0063,
|
| 2658 |
+
"mean_token_accuracy": 0.999923825263977,
|
| 2659 |
+
"num_tokens": 4196083.0,
|
| 2660 |
+
"step": 265
|
| 2661 |
+
},
|
| 2662 |
+
{
|
| 2663 |
+
"entropy": 0.09930684044957161,
|
| 2664 |
+
"epoch": 13.305732484076433,
|
| 2665 |
+
"grad_norm": 0.024473560974001884,
|
| 2666 |
+
"learning_rate": 2.3728813559322036e-05,
|
| 2667 |
+
"loss": 0.0059,
|
| 2668 |
+
"mean_token_accuracy": 0.999931126832962,
|
| 2669 |
+
"num_tokens": 4212399.0,
|
| 2670 |
+
"step": 266
|
| 2671 |
+
},
|
| 2672 |
+
{
|
| 2673 |
+
"entropy": 0.10002897586673498,
|
| 2674 |
+
"epoch": 13.356687898089172,
|
| 2675 |
+
"grad_norm": 0.025572266429662704,
|
| 2676 |
+
"learning_rate": 2.305084745762712e-05,
|
| 2677 |
+
"loss": 0.0058,
|
| 2678 |
+
"mean_token_accuracy": 1.0,
|
| 2679 |
+
"num_tokens": 4228783.0,
|
| 2680 |
+
"step": 267
|
| 2681 |
+
},
|
| 2682 |
+
{
|
| 2683 |
+
"entropy": 0.10443572327494621,
|
| 2684 |
+
"epoch": 13.40764331210191,
|
| 2685 |
+
"grad_norm": 0.02436634711921215,
|
| 2686 |
+
"learning_rate": 2.2372881355932205e-05,
|
| 2687 |
+
"loss": 0.0058,
|
| 2688 |
+
"mean_token_accuracy": 1.0,
|
| 2689 |
+
"num_tokens": 4244827.0,
|
| 2690 |
+
"step": 268
|
| 2691 |
+
},
|
| 2692 |
+
{
|
| 2693 |
+
"entropy": 0.09615321457386017,
|
| 2694 |
+
"epoch": 13.45859872611465,
|
| 2695 |
+
"grad_norm": 0.025177955627441406,
|
| 2696 |
+
"learning_rate": 2.1694915254237287e-05,
|
| 2697 |
+
"loss": 0.0056,
|
| 2698 |
+
"mean_token_accuracy": 0.9999350979924202,
|
| 2699 |
+
"num_tokens": 4261211.0,
|
| 2700 |
+
"step": 269
|
| 2701 |
+
},
|
| 2702 |
+
{
|
| 2703 |
+
"entropy": 0.10436165984719992,
|
| 2704 |
+
"epoch": 13.509554140127388,
|
| 2705 |
+
"grad_norm": 0.02651069685816765,
|
| 2706 |
+
"learning_rate": 2.1016949152542373e-05,
|
| 2707 |
+
"loss": 0.007,
|
| 2708 |
+
"mean_token_accuracy": 0.9998708888888359,
|
| 2709 |
+
"num_tokens": 4277292.0,
|
| 2710 |
+
"step": 270
|
| 2711 |
+
},
|
| 2712 |
+
{
|
| 2713 |
+
"entropy": 0.09940579812973738,
|
| 2714 |
+
"epoch": 13.560509554140127,
|
| 2715 |
+
"grad_norm": 0.024446485564112663,
|
| 2716 |
+
"learning_rate": 2.033898305084746e-05,
|
| 2717 |
+
"loss": 0.0058,
|
| 2718 |
+
"mean_token_accuracy": 1.0,
|
| 2719 |
+
"num_tokens": 4293676.0,
|
| 2720 |
+
"step": 271
|
| 2721 |
+
},
|
| 2722 |
+
{
|
| 2723 |
+
"entropy": 0.1089943777769804,
|
| 2724 |
+
"epoch": 13.611464968152866,
|
| 2725 |
+
"grad_norm": 0.027576526626944542,
|
| 2726 |
+
"learning_rate": 1.9661016949152545e-05,
|
| 2727 |
+
"loss": 0.0071,
|
| 2728 |
+
"mean_token_accuracy": 0.9999209865927696,
|
| 2729 |
+
"num_tokens": 4309171.0,
|
| 2730 |
+
"step": 272
|
| 2731 |
+
},
|
| 2732 |
+
{
|
| 2733 |
+
"entropy": 0.09422466903924942,
|
| 2734 |
+
"epoch": 13.662420382165605,
|
| 2735 |
+
"grad_norm": 0.024253997951745987,
|
| 2736 |
+
"learning_rate": 1.8983050847457627e-05,
|
| 2737 |
+
"loss": 0.0056,
|
| 2738 |
+
"mean_token_accuracy": 0.9999356642365456,
|
| 2739 |
+
"num_tokens": 4325555.0,
|
| 2740 |
+
"step": 273
|
| 2741 |
+
},
|
| 2742 |
+
{
|
| 2743 |
+
"entropy": 0.10771417059004307,
|
| 2744 |
+
"epoch": 13.713375796178344,
|
| 2745 |
+
"grad_norm": 0.024483634158968925,
|
| 2746 |
+
"learning_rate": 1.8305084745762713e-05,
|
| 2747 |
+
"loss": 0.0058,
|
| 2748 |
+
"mean_token_accuracy": 1.0,
|
| 2749 |
+
"num_tokens": 4341424.0,
|
| 2750 |
+
"step": 274
|
| 2751 |
+
},
|
| 2752 |
+
{
|
| 2753 |
+
"entropy": 0.1011097515001893,
|
| 2754 |
+
"epoch": 13.764331210191083,
|
| 2755 |
+
"grad_norm": 0.02411043830215931,
|
| 2756 |
+
"learning_rate": 1.76271186440678e-05,
|
| 2757 |
+
"loss": 0.0056,
|
| 2758 |
+
"mean_token_accuracy": 0.9999353364109993,
|
| 2759 |
+
"num_tokens": 4357808.0,
|
| 2760 |
+
"step": 275
|
| 2761 |
+
},
|
| 2762 |
+
{
|
| 2763 |
+
"entropy": 0.0979408985003829,
|
| 2764 |
+
"epoch": 13.815286624203821,
|
| 2765 |
+
"grad_norm": 0.03372422233223915,
|
| 2766 |
+
"learning_rate": 1.694915254237288e-05,
|
| 2767 |
+
"loss": 0.0068,
|
| 2768 |
+
"mean_token_accuracy": 0.999871663749218,
|
| 2769 |
+
"num_tokens": 4374192.0,
|
| 2770 |
+
"step": 276
|
| 2771 |
+
},
|
| 2772 |
+
{
|
| 2773 |
+
"entropy": 0.10360954143106937,
|
| 2774 |
+
"epoch": 13.86624203821656,
|
| 2775 |
+
"grad_norm": 0.02556852251291275,
|
| 2776 |
+
"learning_rate": 1.6271186440677967e-05,
|
| 2777 |
+
"loss": 0.0064,
|
| 2778 |
+
"mean_token_accuracy": 1.0,
|
| 2779 |
+
"num_tokens": 4390303.0,
|
| 2780 |
+
"step": 277
|
| 2781 |
+
},
|
| 2782 |
+
{
|
| 2783 |
+
"entropy": 0.09622267633676529,
|
| 2784 |
+
"epoch": 13.9171974522293,
|
| 2785 |
+
"grad_norm": 0.02323872037231922,
|
| 2786 |
+
"learning_rate": 1.5593220338983053e-05,
|
| 2787 |
+
"loss": 0.0053,
|
| 2788 |
+
"mean_token_accuracy": 1.0,
|
| 2789 |
+
"num_tokens": 4406687.0,
|
| 2790 |
+
"step": 278
|
| 2791 |
+
},
|
| 2792 |
+
{
|
| 2793 |
+
"entropy": 0.10244499053806067,
|
| 2794 |
+
"epoch": 13.968152866242038,
|
| 2795 |
+
"grad_norm": 0.025733351707458496,
|
| 2796 |
+
"learning_rate": 1.4915254237288137e-05,
|
| 2797 |
+
"loss": 0.0059,
|
| 2798 |
+
"mean_token_accuracy": 1.0,
|
| 2799 |
+
"num_tokens": 4423071.0,
|
| 2800 |
+
"step": 279
|
| 2801 |
+
},
|
| 2802 |
+
{
|
| 2803 |
+
"entropy": 0.11494807302951812,
|
| 2804 |
+
"epoch": 14.0,
|
| 2805 |
+
"grad_norm": 0.034636951982975006,
|
| 2806 |
+
"learning_rate": 1.4237288135593221e-05,
|
| 2807 |
+
"loss": 0.0061,
|
| 2808 |
+
"mean_token_accuracy": 1.0,
|
| 2809 |
+
"num_tokens": 4432050.0,
|
| 2810 |
+
"step": 280
|
| 2811 |
+
},
|
| 2812 |
+
{
|
| 2813 |
+
"entropy": 0.09753070399165154,
|
| 2814 |
+
"epoch": 14.050955414012739,
|
| 2815 |
+
"grad_norm": 0.022641047835350037,
|
| 2816 |
+
"learning_rate": 1.3559322033898305e-05,
|
| 2817 |
+
"loss": 0.0055,
|
| 2818 |
+
"mean_token_accuracy": 1.0,
|
| 2819 |
+
"num_tokens": 4448434.0,
|
| 2820 |
+
"step": 281
|
| 2821 |
+
},
|
| 2822 |
+
{
|
| 2823 |
+
"entropy": 0.08915799483656883,
|
| 2824 |
+
"epoch": 14.101910828025478,
|
| 2825 |
+
"grad_norm": 0.021472405642271042,
|
| 2826 |
+
"learning_rate": 1.288135593220339e-05,
|
| 2827 |
+
"loss": 0.0047,
|
| 2828 |
+
"mean_token_accuracy": 1.0,
|
| 2829 |
+
"num_tokens": 4464818.0,
|
| 2830 |
+
"step": 282
|
| 2831 |
+
},
|
| 2832 |
+
{
|
| 2833 |
+
"entropy": 0.09933264553546906,
|
| 2834 |
+
"epoch": 14.152866242038217,
|
| 2835 |
+
"grad_norm": 0.02268746867775917,
|
| 2836 |
+
"learning_rate": 1.2203389830508475e-05,
|
| 2837 |
+
"loss": 0.0056,
|
| 2838 |
+
"mean_token_accuracy": 1.0,
|
| 2839 |
+
"num_tokens": 4481202.0,
|
| 2840 |
+
"step": 283
|
| 2841 |
+
},
|
| 2842 |
+
{
|
| 2843 |
+
"entropy": 0.10949048679322004,
|
| 2844 |
+
"epoch": 14.203821656050955,
|
| 2845 |
+
"grad_norm": 0.02363019995391369,
|
| 2846 |
+
"learning_rate": 1.152542372881356e-05,
|
| 2847 |
+
"loss": 0.0057,
|
| 2848 |
+
"mean_token_accuracy": 1.0,
|
| 2849 |
+
"num_tokens": 4497586.0,
|
| 2850 |
+
"step": 284
|
| 2851 |
+
},
|
| 2852 |
+
{
|
| 2853 |
+
"entropy": 0.09538892284035683,
|
| 2854 |
+
"epoch": 14.254777070063694,
|
| 2855 |
+
"grad_norm": 0.02280281111598015,
|
| 2856 |
+
"learning_rate": 1.0847457627118644e-05,
|
| 2857 |
+
"loss": 0.0056,
|
| 2858 |
+
"mean_token_accuracy": 0.9999348297715187,
|
| 2859 |
+
"num_tokens": 4513970.0,
|
| 2860 |
+
"step": 285
|
| 2861 |
+
},
|
| 2862 |
+
{
|
| 2863 |
+
"entropy": 0.09355007391422987,
|
| 2864 |
+
"epoch": 14.305732484076433,
|
| 2865 |
+
"grad_norm": 0.024101026356220245,
|
| 2866 |
+
"learning_rate": 1.016949152542373e-05,
|
| 2867 |
+
"loss": 0.0058,
|
| 2868 |
+
"mean_token_accuracy": 1.0,
|
| 2869 |
+
"num_tokens": 4530117.0,
|
| 2870 |
+
"step": 286
|
| 2871 |
+
},
|
| 2872 |
+
{
|
| 2873 |
+
"entropy": 0.09671080578118563,
|
| 2874 |
+
"epoch": 14.356687898089172,
|
| 2875 |
+
"grad_norm": 0.024017931893467903,
|
| 2876 |
+
"learning_rate": 9.491525423728814e-06,
|
| 2877 |
+
"loss": 0.0058,
|
| 2878 |
+
"mean_token_accuracy": 1.0,
|
| 2879 |
+
"num_tokens": 4546128.0,
|
| 2880 |
+
"step": 287
|
| 2881 |
+
},
|
| 2882 |
+
{
|
| 2883 |
+
"entropy": 0.10226992424577475,
|
| 2884 |
+
"epoch": 14.40764331210191,
|
| 2885 |
+
"grad_norm": 0.024143729358911514,
|
| 2886 |
+
"learning_rate": 8.8135593220339e-06,
|
| 2887 |
+
"loss": 0.0057,
|
| 2888 |
+
"mean_token_accuracy": 1.0,
|
| 2889 |
+
"num_tokens": 4562512.0,
|
| 2890 |
+
"step": 288
|
| 2891 |
+
},
|
| 2892 |
+
{
|
| 2893 |
+
"entropy": 0.09842728730291128,
|
| 2894 |
+
"epoch": 14.45859872611465,
|
| 2895 |
+
"grad_norm": 0.022391093894839287,
|
| 2896 |
+
"learning_rate": 8.135593220338983e-06,
|
| 2897 |
+
"loss": 0.0054,
|
| 2898 |
+
"mean_token_accuracy": 1.0,
|
| 2899 |
+
"num_tokens": 4578896.0,
|
| 2900 |
+
"step": 289
|
| 2901 |
+
},
|
| 2902 |
+
{
|
| 2903 |
+
"entropy": 0.09875787049531937,
|
| 2904 |
+
"epoch": 14.509554140127388,
|
| 2905 |
+
"grad_norm": 0.036525625735521317,
|
| 2906 |
+
"learning_rate": 7.4576271186440685e-06,
|
| 2907 |
+
"loss": 0.0068,
|
| 2908 |
+
"mean_token_accuracy": 0.9998043775558472,
|
| 2909 |
+
"num_tokens": 4595212.0,
|
| 2910 |
+
"step": 290
|
| 2911 |
+
},
|
| 2912 |
+
{
|
| 2913 |
+
"entropy": 0.10088277515023947,
|
| 2914 |
+
"epoch": 14.560509554140127,
|
| 2915 |
+
"grad_norm": 0.024536944925785065,
|
| 2916 |
+
"learning_rate": 6.779661016949153e-06,
|
| 2917 |
+
"loss": 0.0061,
|
| 2918 |
+
"mean_token_accuracy": 0.9999360293149948,
|
| 2919 |
+
"num_tokens": 4611323.0,
|
| 2920 |
+
"step": 291
|
| 2921 |
+
},
|
| 2922 |
+
{
|
| 2923 |
+
"entropy": 0.09735479392111301,
|
| 2924 |
+
"epoch": 14.611464968152866,
|
| 2925 |
+
"grad_norm": 0.024319127202033997,
|
| 2926 |
+
"learning_rate": 6.101694915254238e-06,
|
| 2927 |
+
"loss": 0.0056,
|
| 2928 |
+
"mean_token_accuracy": 0.999872088432312,
|
| 2929 |
+
"num_tokens": 4627191.0,
|
| 2930 |
+
"step": 292
|
| 2931 |
+
},
|
| 2932 |
+
{
|
| 2933 |
+
"entropy": 0.1000251853838563,
|
| 2934 |
+
"epoch": 14.662420382165605,
|
| 2935 |
+
"grad_norm": 0.025493454188108444,
|
| 2936 |
+
"learning_rate": 5.423728813559322e-06,
|
| 2937 |
+
"loss": 0.0066,
|
| 2938 |
+
"mean_token_accuracy": 1.0,
|
| 2939 |
+
"num_tokens": 4643575.0,
|
| 2940 |
+
"step": 293
|
| 2941 |
+
},
|
| 2942 |
+
{
|
| 2943 |
+
"entropy": 0.10344643983989954,
|
| 2944 |
+
"epoch": 14.713375796178344,
|
| 2945 |
+
"grad_norm": 0.025770332664251328,
|
| 2946 |
+
"learning_rate": 4.745762711864407e-06,
|
| 2947 |
+
"loss": 0.0066,
|
| 2948 |
+
"mean_token_accuracy": 0.9999344870448112,
|
| 2949 |
+
"num_tokens": 4659959.0,
|
| 2950 |
+
"step": 294
|
| 2951 |
+
},
|
| 2952 |
+
{
|
| 2953 |
+
"entropy": 0.1049768216907978,
|
| 2954 |
+
"epoch": 14.764331210191083,
|
| 2955 |
+
"grad_norm": 0.023523753508925438,
|
| 2956 |
+
"learning_rate": 4.067796610169492e-06,
|
| 2957 |
+
"loss": 0.0057,
|
| 2958 |
+
"mean_token_accuracy": 1.0,
|
| 2959 |
+
"num_tokens": 4675982.0,
|
| 2960 |
+
"step": 295
|
| 2961 |
+
},
|
| 2962 |
+
{
|
| 2963 |
+
"entropy": 0.10388771630823612,
|
| 2964 |
+
"epoch": 14.815286624203821,
|
| 2965 |
+
"grad_norm": 0.023833539336919785,
|
| 2966 |
+
"learning_rate": 3.3898305084745763e-06,
|
| 2967 |
+
"loss": 0.0055,
|
| 2968 |
+
"mean_token_accuracy": 1.0,
|
| 2969 |
+
"num_tokens": 4691837.0,
|
| 2970 |
+
"step": 296
|
| 2971 |
+
},
|
| 2972 |
+
{
|
| 2973 |
+
"entropy": 0.10857217479497194,
|
| 2974 |
+
"epoch": 14.86624203821656,
|
| 2975 |
+
"grad_norm": 0.023440934717655182,
|
| 2976 |
+
"learning_rate": 2.711864406779661e-06,
|
| 2977 |
+
"loss": 0.0057,
|
| 2978 |
+
"mean_token_accuracy": 1.0,
|
| 2979 |
+
"num_tokens": 4707881.0,
|
| 2980 |
+
"step": 297
|
| 2981 |
+
},
|
| 2982 |
+
{
|
| 2983 |
+
"entropy": 0.10144319850951433,
|
| 2984 |
+
"epoch": 14.9171974522293,
|
| 2985 |
+
"grad_norm": 0.02377854287624359,
|
| 2986 |
+
"learning_rate": 2.033898305084746e-06,
|
| 2987 |
+
"loss": 0.0058,
|
| 2988 |
+
"mean_token_accuracy": 0.9999219700694084,
|
| 2989 |
+
"num_tokens": 4723956.0,
|
| 2990 |
+
"step": 298
|
| 2991 |
+
},
|
| 2992 |
+
{
|
| 2993 |
+
"entropy": 0.10537906363606453,
|
| 2994 |
+
"epoch": 14.968152866242038,
|
| 2995 |
+
"grad_norm": 0.024843264371156693,
|
| 2996 |
+
"learning_rate": 1.3559322033898304e-06,
|
| 2997 |
+
"loss": 0.006,
|
| 2998 |
+
"mean_token_accuracy": 1.0,
|
| 2999 |
+
"num_tokens": 4740037.0,
|
| 3000 |
+
"step": 299
|
| 3001 |
+
},
|
| 3002 |
+
{
|
| 3003 |
+
"entropy": 0.12200375497341157,
|
| 3004 |
+
"epoch": 15.0,
|
| 3005 |
+
"grad_norm": 0.03387058898806572,
|
| 3006 |
+
"learning_rate": 6.779661016949152e-07,
|
| 3007 |
+
"loss": 0.006,
|
| 3008 |
+
"mean_token_accuracy": 1.0,
|
| 3009 |
+
"num_tokens": 4748625.0,
|
| 3010 |
+
"step": 300
|
| 3011 |
+
}
|
| 3012 |
+
],
|
| 3013 |
+
"logging_steps": 1,
|
| 3014 |
+
"max_steps": 300,
|
| 3015 |
+
"num_input_tokens_seen": 0,
|
| 3016 |
+
"num_train_epochs": 15,
|
| 3017 |
+
"save_steps": 500,
|
| 3018 |
+
"stateful_callbacks": {
|
| 3019 |
+
"TrainerControl": {
|
| 3020 |
+
"args": {
|
| 3021 |
+
"should_epoch_stop": false,
|
| 3022 |
+
"should_evaluate": false,
|
| 3023 |
+
"should_log": false,
|
| 3024 |
+
"should_save": true,
|
| 3025 |
+
"should_training_stop": true
|
| 3026 |
+
},
|
| 3027 |
+
"attributes": {}
|
| 3028 |
+
}
|
| 3029 |
+
},
|
| 3030 |
+
"total_flos": 2.0845431402464256e+17,
|
| 3031 |
+
"train_batch_size": 2,
|
| 3032 |
+
"trial_name": null,
|
| 3033 |
+
"trial_params": null
|
| 3034 |
+
}
|
checkpoint-300/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:077b87357be7e3347a59817bffdd5639168ab5f567cc54f95f4792a1bea59bab
|
| 3 |
+
size 5713
|
checkpoint-300/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-50/README.md
ADDED
|
@@ -0,0 +1,209 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: openai/gpt-oss-20b
|
| 3 |
+
library_name: peft
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
- base_model:adapter:openai/gpt-oss-20b
|
| 7 |
+
- lora
|
| 8 |
+
- sft
|
| 9 |
+
- transformers
|
| 10 |
+
- trl
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
# Model Card for Model ID
|
| 14 |
+
|
| 15 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
## Model Details
|
| 20 |
+
|
| 21 |
+
### Model Description
|
| 22 |
+
|
| 23 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
|
| 27 |
+
- **Developed by:** [More Information Needed]
|
| 28 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 29 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 30 |
+
- **Model type:** [More Information Needed]
|
| 31 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 32 |
+
- **License:** [More Information Needed]
|
| 33 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 34 |
+
|
| 35 |
+
### Model Sources [optional]
|
| 36 |
+
|
| 37 |
+
<!-- Provide the basic links for the model. -->
|
| 38 |
+
|
| 39 |
+
- **Repository:** [More Information Needed]
|
| 40 |
+
- **Paper [optional]:** [More Information Needed]
|
| 41 |
+
- **Demo [optional]:** [More Information Needed]
|
| 42 |
+
|
| 43 |
+
## Uses
|
| 44 |
+
|
| 45 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 46 |
+
|
| 47 |
+
### Direct Use
|
| 48 |
+
|
| 49 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 50 |
+
|
| 51 |
+
[More Information Needed]
|
| 52 |
+
|
| 53 |
+
### Downstream Use [optional]
|
| 54 |
+
|
| 55 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 56 |
+
|
| 57 |
+
[More Information Needed]
|
| 58 |
+
|
| 59 |
+
### Out-of-Scope Use
|
| 60 |
+
|
| 61 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 62 |
+
|
| 63 |
+
[More Information Needed]
|
| 64 |
+
|
| 65 |
+
## Bias, Risks, and Limitations
|
| 66 |
+
|
| 67 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 68 |
+
|
| 69 |
+
[More Information Needed]
|
| 70 |
+
|
| 71 |
+
### Recommendations
|
| 72 |
+
|
| 73 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 74 |
+
|
| 75 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 76 |
+
|
| 77 |
+
## How to Get Started with the Model
|
| 78 |
+
|
| 79 |
+
Use the code below to get started with the model.
|
| 80 |
+
|
| 81 |
+
[More Information Needed]
|
| 82 |
+
|
| 83 |
+
## Training Details
|
| 84 |
+
|
| 85 |
+
### Training Data
|
| 86 |
+
|
| 87 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 88 |
+
|
| 89 |
+
[More Information Needed]
|
| 90 |
+
|
| 91 |
+
### Training Procedure
|
| 92 |
+
|
| 93 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 94 |
+
|
| 95 |
+
#### Preprocessing [optional]
|
| 96 |
+
|
| 97 |
+
[More Information Needed]
|
| 98 |
+
|
| 99 |
+
|
| 100 |
+
#### Training Hyperparameters
|
| 101 |
+
|
| 102 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 103 |
+
|
| 104 |
+
#### Speeds, Sizes, Times [optional]
|
| 105 |
+
|
| 106 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 107 |
+
|
| 108 |
+
[More Information Needed]
|
| 109 |
+
|
| 110 |
+
## Evaluation
|
| 111 |
+
|
| 112 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 113 |
+
|
| 114 |
+
### Testing Data, Factors & Metrics
|
| 115 |
+
|
| 116 |
+
#### Testing Data
|
| 117 |
+
|
| 118 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 119 |
+
|
| 120 |
+
[More Information Needed]
|
| 121 |
+
|
| 122 |
+
#### Factors
|
| 123 |
+
|
| 124 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 125 |
+
|
| 126 |
+
[More Information Needed]
|
| 127 |
+
|
| 128 |
+
#### Metrics
|
| 129 |
+
|
| 130 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 131 |
+
|
| 132 |
+
[More Information Needed]
|
| 133 |
+
|
| 134 |
+
### Results
|
| 135 |
+
|
| 136 |
+
[More Information Needed]
|
| 137 |
+
|
| 138 |
+
#### Summary
|
| 139 |
+
|
| 140 |
+
|
| 141 |
+
|
| 142 |
+
## Model Examination [optional]
|
| 143 |
+
|
| 144 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 145 |
+
|
| 146 |
+
[More Information Needed]
|
| 147 |
+
|
| 148 |
+
## Environmental Impact
|
| 149 |
+
|
| 150 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 151 |
+
|
| 152 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 153 |
+
|
| 154 |
+
- **Hardware Type:** [More Information Needed]
|
| 155 |
+
- **Hours used:** [More Information Needed]
|
| 156 |
+
- **Cloud Provider:** [More Information Needed]
|
| 157 |
+
- **Compute Region:** [More Information Needed]
|
| 158 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 159 |
+
|
| 160 |
+
## Technical Specifications [optional]
|
| 161 |
+
|
| 162 |
+
### Model Architecture and Objective
|
| 163 |
+
|
| 164 |
+
[More Information Needed]
|
| 165 |
+
|
| 166 |
+
### Compute Infrastructure
|
| 167 |
+
|
| 168 |
+
[More Information Needed]
|
| 169 |
+
|
| 170 |
+
#### Hardware
|
| 171 |
+
|
| 172 |
+
[More Information Needed]
|
| 173 |
+
|
| 174 |
+
#### Software
|
| 175 |
+
|
| 176 |
+
[More Information Needed]
|
| 177 |
+
|
| 178 |
+
## Citation [optional]
|
| 179 |
+
|
| 180 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 181 |
+
|
| 182 |
+
**BibTeX:**
|
| 183 |
+
|
| 184 |
+
[More Information Needed]
|
| 185 |
+
|
| 186 |
+
**APA:**
|
| 187 |
+
|
| 188 |
+
[More Information Needed]
|
| 189 |
+
|
| 190 |
+
## Glossary [optional]
|
| 191 |
+
|
| 192 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 193 |
+
|
| 194 |
+
[More Information Needed]
|
| 195 |
+
|
| 196 |
+
## More Information [optional]
|
| 197 |
+
|
| 198 |
+
[More Information Needed]
|
| 199 |
+
|
| 200 |
+
## Model Card Authors [optional]
|
| 201 |
+
|
| 202 |
+
[More Information Needed]
|
| 203 |
+
|
| 204 |
+
## Model Card Contact
|
| 205 |
+
|
| 206 |
+
[More Information Needed]
|
| 207 |
+
### Framework versions
|
| 208 |
+
|
| 209 |
+
- PEFT 0.17.1
|
checkpoint-50/adapter_config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "openai/gpt-oss-20b",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 64,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.1,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"qalora_group_size": 16,
|
| 24 |
+
"r": 64,
|
| 25 |
+
"rank_pattern": {},
|
| 26 |
+
"revision": null,
|
| 27 |
+
"target_modules": [
|
| 28 |
+
"gate_proj",
|
| 29 |
+
"k_proj",
|
| 30 |
+
"down_proj",
|
| 31 |
+
"up_proj",
|
| 32 |
+
"v_proj",
|
| 33 |
+
"q_proj",
|
| 34 |
+
"o_proj"
|
| 35 |
+
],
|
| 36 |
+
"target_parameters": null,
|
| 37 |
+
"task_type": "CAUSAL_LM",
|
| 38 |
+
"trainable_token_indices": null,
|
| 39 |
+
"use_dora": false,
|
| 40 |
+
"use_qalora": false,
|
| 41 |
+
"use_rslora": false
|
| 42 |
+
}
|
checkpoint-50/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:66588ad755f746ec82e0bf0290eb4b80f1792e714636a26ab0cc88500df86f08
|
| 3 |
+
size 127427864
|
checkpoint-50/added_tokens.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|box_end|>": 151649,
|
| 5 |
+
"<|box_start|>": 151648,
|
| 6 |
+
"<|endoftext|>": 151643,
|
| 7 |
+
"<|file_sep|>": 151664,
|
| 8 |
+
"<|fim_middle|>": 151660,
|
| 9 |
+
"<|fim_pad|>": 151662,
|
| 10 |
+
"<|fim_prefix|>": 151659,
|
| 11 |
+
"<|fim_suffix|>": 151661,
|
| 12 |
+
"<|im_end|>": 151645,
|
| 13 |
+
"<|im_start|>": 151644,
|
| 14 |
+
"<|image_pad|>": 151655,
|
| 15 |
+
"<|object_ref_end|>": 151647,
|
| 16 |
+
"<|object_ref_start|>": 151646,
|
| 17 |
+
"<|quad_end|>": 151651,
|
| 18 |
+
"<|quad_start|>": 151650,
|
| 19 |
+
"<|repo_name|>": 151663,
|
| 20 |
+
"<|video_pad|>": 151656,
|
| 21 |
+
"<|vision_end|>": 151653,
|
| 22 |
+
"<|vision_pad|>": 151654,
|
| 23 |
+
"<|vision_start|>": 151652
|
| 24 |
+
}
|
checkpoint-50/chat_template.jinja
ADDED
|
@@ -0,0 +1,331 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{#-
|
| 2 |
+
In addition to the normal inputs of `messages` and `tools`, this template also accepts the
|
| 3 |
+
following kwargs:
|
| 4 |
+
- "builtin_tools": A list, can contain "browser" and/or "python".
|
| 5 |
+
- "model_identity": A string that optionally describes the model identity.
|
| 6 |
+
- "reasoning_effort": A string that describes the reasoning effort, defaults to "medium".
|
| 7 |
+
#}
|
| 8 |
+
|
| 9 |
+
{#- Tool Definition Rendering ============================================== #}
|
| 10 |
+
{%- macro render_typescript_type(param_spec, required_params, is_nullable=false) -%}
|
| 11 |
+
{%- if param_spec.type == "array" -%}
|
| 12 |
+
{%- if param_spec['items'] -%}
|
| 13 |
+
{%- if param_spec['items']['type'] == "string" -%}
|
| 14 |
+
{{- "string[]" }}
|
| 15 |
+
{%- elif param_spec['items']['type'] == "number" -%}
|
| 16 |
+
{{- "number[]" }}
|
| 17 |
+
{%- elif param_spec['items']['type'] == "integer" -%}
|
| 18 |
+
{{- "number[]" }}
|
| 19 |
+
{%- elif param_spec['items']['type'] == "boolean" -%}
|
| 20 |
+
{{- "boolean[]" }}
|
| 21 |
+
{%- else -%}
|
| 22 |
+
{%- set inner_type = render_typescript_type(param_spec['items'], required_params) -%}
|
| 23 |
+
{%- if inner_type == "object | object" or inner_type|length > 50 -%}
|
| 24 |
+
{{- "any[]" }}
|
| 25 |
+
{%- else -%}
|
| 26 |
+
{{- inner_type + "[]" }}
|
| 27 |
+
{%- endif -%}
|
| 28 |
+
{%- endif -%}
|
| 29 |
+
{%- if param_spec.nullable -%}
|
| 30 |
+
{{- " | null" }}
|
| 31 |
+
{%- endif -%}
|
| 32 |
+
{%- else -%}
|
| 33 |
+
{{- "any[]" }}
|
| 34 |
+
{%- if param_spec.nullable -%}
|
| 35 |
+
{{- " | null" }}
|
| 36 |
+
{%- endif -%}
|
| 37 |
+
{%- endif -%}
|
| 38 |
+
{%- elif param_spec.type is defined and param_spec.type is iterable and param_spec.type is not string and param_spec.type is not mapping and param_spec.type[0] is defined -%}
|
| 39 |
+
{#- Handle array of types like ["object", "object"] from Union[dict, list] #}
|
| 40 |
+
{%- if param_spec.type | length > 1 -%}
|
| 41 |
+
{{- param_spec.type | join(" | ") }}
|
| 42 |
+
{%- else -%}
|
| 43 |
+
{{- param_spec.type[0] }}
|
| 44 |
+
{%- endif -%}
|
| 45 |
+
{%- elif param_spec.oneOf -%}
|
| 46 |
+
{#- Handle oneOf schemas - check for complex unions and fallback to any #}
|
| 47 |
+
{%- set has_object_variants = false -%}
|
| 48 |
+
{%- for variant in param_spec.oneOf -%}
|
| 49 |
+
{%- if variant.type == "object" -%}
|
| 50 |
+
{%- set has_object_variants = true -%}
|
| 51 |
+
{%- endif -%}
|
| 52 |
+
{%- endfor -%}
|
| 53 |
+
{%- if has_object_variants and param_spec.oneOf|length > 1 -%}
|
| 54 |
+
{{- "any" }}
|
| 55 |
+
{%- else -%}
|
| 56 |
+
{%- for variant in param_spec.oneOf -%}
|
| 57 |
+
{{- render_typescript_type(variant, required_params) -}}
|
| 58 |
+
{%- if variant.description %}
|
| 59 |
+
{{- "// " + variant.description }}
|
| 60 |
+
{%- endif -%}
|
| 61 |
+
{%- if variant.default is defined %}
|
| 62 |
+
{{ "// default: " + variant.default|tojson }}
|
| 63 |
+
{%- endif -%}
|
| 64 |
+
{%- if not loop.last %}
|
| 65 |
+
{{- " | " }}
|
| 66 |
+
{% endif -%}
|
| 67 |
+
{%- endfor -%}
|
| 68 |
+
{%- endif -%}
|
| 69 |
+
{%- elif param_spec.type == "string" -%}
|
| 70 |
+
{%- if param_spec.enum -%}
|
| 71 |
+
{{- '"' + param_spec.enum|join('" | "') + '"' -}}
|
| 72 |
+
{%- else -%}
|
| 73 |
+
{{- "string" }}
|
| 74 |
+
{%- if param_spec.nullable %}
|
| 75 |
+
{{- " | null" }}
|
| 76 |
+
{%- endif -%}
|
| 77 |
+
{%- endif -%}
|
| 78 |
+
{%- elif param_spec.type == "number" -%}
|
| 79 |
+
{{- "number" }}
|
| 80 |
+
{%- elif param_spec.type == "integer" -%}
|
| 81 |
+
{{- "number" }}
|
| 82 |
+
{%- elif param_spec.type == "boolean" -%}
|
| 83 |
+
{{- "boolean" }}
|
| 84 |
+
|
| 85 |
+
{%- elif param_spec.type == "object" -%}
|
| 86 |
+
{%- if param_spec.properties -%}
|
| 87 |
+
{{- "{\n" }}
|
| 88 |
+
{%- for prop_name, prop_spec in param_spec.properties.items() -%}
|
| 89 |
+
{{- prop_name -}}
|
| 90 |
+
{%- if prop_name not in (param_spec.required or []) -%}
|
| 91 |
+
{{- "?" }}
|
| 92 |
+
{%- endif -%}
|
| 93 |
+
{{- ": " }}
|
| 94 |
+
{{ render_typescript_type(prop_spec, param_spec.required or []) }}
|
| 95 |
+
{%- if not loop.last -%}
|
| 96 |
+
{{-", " }}
|
| 97 |
+
{%- endif -%}
|
| 98 |
+
{%- endfor -%}
|
| 99 |
+
{{- "}" }}
|
| 100 |
+
{%- else -%}
|
| 101 |
+
{{- "object" }}
|
| 102 |
+
{%- endif -%}
|
| 103 |
+
{%- else -%}
|
| 104 |
+
{{- "any" }}
|
| 105 |
+
{%- endif -%}
|
| 106 |
+
{%- endmacro -%}
|
| 107 |
+
|
| 108 |
+
{%- macro render_tool_namespace(namespace_name, tools) -%}
|
| 109 |
+
{{- "## " + namespace_name + "\n\n" }}
|
| 110 |
+
{{- "namespace " + namespace_name + " {\n\n" }}
|
| 111 |
+
{%- for tool in tools %}
|
| 112 |
+
{%- set tool = tool.function %}
|
| 113 |
+
{{- "// " + tool.description + "\n" }}
|
| 114 |
+
{{- "type "+ tool.name + " = " }}
|
| 115 |
+
{%- if tool.parameters and tool.parameters.properties %}
|
| 116 |
+
{{- "(_: {\n" }}
|
| 117 |
+
{%- for param_name, param_spec in tool.parameters.properties.items() %}
|
| 118 |
+
{%- if param_spec.description %}
|
| 119 |
+
{{- "// " + param_spec.description + "\n" }}
|
| 120 |
+
{%- endif %}
|
| 121 |
+
{{- param_name }}
|
| 122 |
+
{%- if param_name not in (tool.parameters.required or []) -%}
|
| 123 |
+
{{- "?" }}
|
| 124 |
+
{%- endif -%}
|
| 125 |
+
{{- ": " }}
|
| 126 |
+
{{- render_typescript_type(param_spec, tool.parameters.required or []) }}
|
| 127 |
+
{%- if param_spec.default is defined -%}
|
| 128 |
+
{%- if param_spec.enum %}
|
| 129 |
+
{{- ", // default: " + param_spec.default }}
|
| 130 |
+
{%- elif param_spec.oneOf %}
|
| 131 |
+
{{- "// default: " + param_spec.default }}
|
| 132 |
+
{%- else %}
|
| 133 |
+
{{- ", // default: " + param_spec.default|tojson }}
|
| 134 |
+
{%- endif -%}
|
| 135 |
+
{%- endif -%}
|
| 136 |
+
{%- if not loop.last %}
|
| 137 |
+
{{- ",\n" }}
|
| 138 |
+
{%- else %}
|
| 139 |
+
{{- ",\n" }}
|
| 140 |
+
{%- endif -%}
|
| 141 |
+
{%- endfor %}
|
| 142 |
+
{{- "}) => any;\n\n" }}
|
| 143 |
+
{%- else -%}
|
| 144 |
+
{{- "() => any;\n\n" }}
|
| 145 |
+
{%- endif -%}
|
| 146 |
+
{%- endfor %}
|
| 147 |
+
{{- "} // namespace " + namespace_name }}
|
| 148 |
+
{%- endmacro -%}
|
| 149 |
+
|
| 150 |
+
{%- macro render_builtin_tools(browser_tool, python_tool) -%}
|
| 151 |
+
{%- if browser_tool %}
|
| 152 |
+
{{- "## browser\n\n" }}
|
| 153 |
+
{{- "// Tool for browsing.\n" }}
|
| 154 |
+
{{- "// The `cursor` appears in brackets before each browsing display: `[{cursor}]`.\n" }}
|
| 155 |
+
{{- "// Cite information from the tool using the following format:\n" }}
|
| 156 |
+
{{- "// `【{cursor}†L{line_start}(-L{line_end})?】`, for example: `【6†L9-L11】` or `【8†L3】`.\n" }}
|
| 157 |
+
{{- "// Do not quote more than 10 words directly from the tool output.\n" }}
|
| 158 |
+
{{- "// sources=web (default: web)\n" }}
|
| 159 |
+
{{- "namespace browser {\n\n" }}
|
| 160 |
+
{{- "// Searches for information related to `query` and displays `topn` results.\n" }}
|
| 161 |
+
{{- "type search = (_: {\n" }}
|
| 162 |
+
{{- "query: string,\n" }}
|
| 163 |
+
{{- "topn?: number, // default: 10\n" }}
|
| 164 |
+
{{- "source?: string,\n" }}
|
| 165 |
+
{{- "}) => any;\n\n" }}
|
| 166 |
+
{{- "// Opens the link `id` from the page indicated by `cursor` starting at line number `loc`, showing `num_lines` lines.\n" }}
|
| 167 |
+
{{- "// Valid link ids are displayed with the formatting: `【{id}†.*】`.\n" }}
|
| 168 |
+
{{- "// If `cursor` is not provided, the most recent page is implied.\n" }}
|
| 169 |
+
{{- "// If `id` is a string, it is treated as a fully qualified URL associated with `source`.\n" }}
|
| 170 |
+
{{- "// If `loc` is not provided, the viewport will be positioned at the beginning of the document or centered on the most relevant passage, if available.\n" }}
|
| 171 |
+
{{- "// Use this function without `id` to scroll to a new location of an opened page.\n" }}
|
| 172 |
+
{{- "type open = (_: {\n" }}
|
| 173 |
+
{{- "id?: number | string, // default: -1\n" }}
|
| 174 |
+
{{- "cursor?: number, // default: -1\n" }}
|
| 175 |
+
{{- "loc?: number, // default: -1\n" }}
|
| 176 |
+
{{- "num_lines?: number, // default: -1\n" }}
|
| 177 |
+
{{- "view_source?: boolean, // default: false\n" }}
|
| 178 |
+
{{- "source?: string,\n" }}
|
| 179 |
+
{{- "}) => any;\n\n" }}
|
| 180 |
+
{{- "// Finds exact matches of `pattern` in the current page, or the page given by `cursor`.\n" }}
|
| 181 |
+
{{- "type find = (_: {\n" }}
|
| 182 |
+
{{- "pattern: string,\n" }}
|
| 183 |
+
{{- "cursor?: number, // default: -1\n" }}
|
| 184 |
+
{{- "}) => any;\n\n" }}
|
| 185 |
+
{{- "} // namespace browser\n\n" }}
|
| 186 |
+
{%- endif -%}
|
| 187 |
+
|
| 188 |
+
{%- if python_tool %}
|
| 189 |
+
{{- "## python\n\n" }}
|
| 190 |
+
{{- "Use this tool to execute Python code in your chain of thought. The code will not be shown to the user. This tool should be used for internal reasoning, but not for code that is intended to be visible to the user (e.g. when creating plots, tables, or files).\n\n" }}
|
| 191 |
+
{{- "When you send a message containing Python code to python, it will be executed in a stateful Jupyter notebook environment. python will respond with the output of the execution or time out after 120.0 seconds. The drive at '/mnt/data' can be used to save and persist user files. Internet access for this session is UNKNOWN. Depends on the cluster.\n\n" }}
|
| 192 |
+
{%- endif -%}
|
| 193 |
+
{%- endmacro -%}
|
| 194 |
+
|
| 195 |
+
{#- System Message Construction ============================================ #}
|
| 196 |
+
{%- macro build_system_message() -%}
|
| 197 |
+
{%- if model_identity is not defined %}
|
| 198 |
+
{%- set model_identity = "You are ChatGPT, a large language model trained by OpenAI." %}
|
| 199 |
+
{%- endif %}
|
| 200 |
+
{{- model_identity + "\n" }}
|
| 201 |
+
{{- "Knowledge cutoff: 2024-06\n" }}
|
| 202 |
+
{{- "Current date: " + strftime_now("%Y-%m-%d") + "\n\n" }}
|
| 203 |
+
{%- if reasoning_effort is not defined %}
|
| 204 |
+
{%- set reasoning_effort = "medium" %}
|
| 205 |
+
{%- endif %}
|
| 206 |
+
{{- "Reasoning: " + reasoning_effort + "\n\n" }}
|
| 207 |
+
{%- if builtin_tools %}
|
| 208 |
+
{{- "# Tools\n\n" }}
|
| 209 |
+
{%- set available_builtin_tools = namespace(browser=false, python=false) %}
|
| 210 |
+
{%- for tool in builtin_tools %}
|
| 211 |
+
{%- if tool == "browser" %}
|
| 212 |
+
{%- set available_builtin_tools.browser = true %}
|
| 213 |
+
{%- elif tool == "python" %}
|
| 214 |
+
{%- set available_builtin_tools.python = true %}
|
| 215 |
+
{%- endif %}
|
| 216 |
+
{%- endfor %}
|
| 217 |
+
{{- render_builtin_tools(available_builtin_tools.browser, available_builtin_tools.python) }}
|
| 218 |
+
{%- endif -%}
|
| 219 |
+
{{- "# Valid channels: analysis, commentary, final. Channel must be included for every message." }}
|
| 220 |
+
{%- if tools -%}
|
| 221 |
+
{{- "\nCalls to these tools must go to the commentary channel: 'functions'." }}
|
| 222 |
+
{%- endif -%}
|
| 223 |
+
{%- endmacro -%}
|
| 224 |
+
|
| 225 |
+
{#- Main Template Logic ================================================= #}
|
| 226 |
+
{#- Set defaults #}
|
| 227 |
+
|
| 228 |
+
{#- Render system message #}
|
| 229 |
+
{{- "<|start|>system<|message|>" }}
|
| 230 |
+
{{- build_system_message() }}
|
| 231 |
+
{{- "<|end|>" }}
|
| 232 |
+
|
| 233 |
+
{#- Extract developer message #}
|
| 234 |
+
{%- if messages[0].role == "developer" or messages[0].role == "system" %}
|
| 235 |
+
{%- set developer_message = messages[0].content %}
|
| 236 |
+
{%- set loop_messages = messages[1:] %}
|
| 237 |
+
{%- else %}
|
| 238 |
+
{%- set developer_message = "" %}
|
| 239 |
+
{%- set loop_messages = messages %}
|
| 240 |
+
{%- endif %}
|
| 241 |
+
|
| 242 |
+
{#- Render developer message #}
|
| 243 |
+
{%- if developer_message or tools %}
|
| 244 |
+
{{- "<|start|>developer<|message|>" }}
|
| 245 |
+
{%- if developer_message %}
|
| 246 |
+
{{- "# Instructions\n\n" }}
|
| 247 |
+
{{- developer_message }}
|
| 248 |
+
{{- "\n\n" }}
|
| 249 |
+
{%- endif %}
|
| 250 |
+
{%- if tools -%}
|
| 251 |
+
{{- "# Tools\n\n" }}
|
| 252 |
+
{{- render_tool_namespace("functions", tools) }}
|
| 253 |
+
{%- endif -%}
|
| 254 |
+
{{- "<|end|>" }}
|
| 255 |
+
{%- endif %}
|
| 256 |
+
|
| 257 |
+
{#- Render messages #}
|
| 258 |
+
{%- set last_tool_call = namespace(name=none) %}
|
| 259 |
+
{%- for message in loop_messages -%}
|
| 260 |
+
{#- At this point only assistant/user/tool messages should remain #}
|
| 261 |
+
{%- if message.role == 'assistant' -%}
|
| 262 |
+
{#- Checks to ensure the messages are being passed in the format we expect #}
|
| 263 |
+
{%- if "content" in message %}
|
| 264 |
+
{%- if "<|channel|>analysis<|message|>" in message.content or "<|channel|>final<|message|>" in message.content %}
|
| 265 |
+
{{- raise_exception("You have passed a message containing <|channel|> tags in the content field. Instead of doing this, you should pass analysis messages (the string between '<|message|>' and '<|end|>') in the 'thinking' field, and final messages (the string between '<|message|>' and '<|end|>') in the 'content' field.") }}
|
| 266 |
+
{%- endif %}
|
| 267 |
+
{%- endif %}
|
| 268 |
+
{%- if "thinking" in message %}
|
| 269 |
+
{%- if "<|channel|>analysis<|message|>" in message.thinking or "<|channel|>final<|message|>" in message.thinking %}
|
| 270 |
+
{{- raise_exception("You have passed a message containing <|channel|> tags in the thinking field. Instead of doing this, you should pass analysis messages (the string between '<|message|>' and '<|end|>') in the 'thinking' field, and final messages (the string between '<|message|>' and '<|end|>') in the 'content' field.") }}
|
| 271 |
+
{%- endif %}
|
| 272 |
+
{%- endif %}
|
| 273 |
+
{%- if "tool_calls" in message %}
|
| 274 |
+
{#- We need very careful handling here - we want to drop the tool call analysis message if the model #}
|
| 275 |
+
{#- has output a later <|final|> message, but otherwise we want to retain it. This is the only case #}
|
| 276 |
+
{#- when we render CoT/analysis messages in inference. #}
|
| 277 |
+
{%- set future_final_message = namespace(found=false) %}
|
| 278 |
+
{%- for future_message in loop_messages[loop.index:] %}
|
| 279 |
+
{%- if future_message.role == 'assistant' and "tool_calls" not in future_message %}
|
| 280 |
+
{%- set future_final_message.found = true %}
|
| 281 |
+
{%- endif %}
|
| 282 |
+
{%- endfor %}
|
| 283 |
+
{#- We assume max 1 tool call per message, and so we infer the tool call name #}
|
| 284 |
+
{#- in "tool" messages from the most recent assistant tool call name #}
|
| 285 |
+
{%- set tool_call = message.tool_calls[0] %}
|
| 286 |
+
{%- if tool_call.function %}
|
| 287 |
+
{%- set tool_call = tool_call.function %}
|
| 288 |
+
{%- endif %}
|
| 289 |
+
{%- if message.content and message.thinking %}
|
| 290 |
+
{{- raise_exception("Cannot pass both content and thinking in an assistant message with tool calls! Put the analysis message in one or the other, but not both.") }}
|
| 291 |
+
{%- elif message.content and not future_final_message.found %}
|
| 292 |
+
{{- "<|start|>assistant<|channel|>analysis<|message|>" + message.content + "<|end|>" }}
|
| 293 |
+
{%- elif message.thinking and not future_final_message.found %}
|
| 294 |
+
{{- "<|start|>assistant<|channel|>analysis<|message|>" + message.thinking + "<|end|>" }}
|
| 295 |
+
{%- endif %}
|
| 296 |
+
{{- "<|start|>assistant to=" }}
|
| 297 |
+
{{- "functions." + tool_call.name + "<|channel|>commentary " }}
|
| 298 |
+
{{- (tool_call.content_type if tool_call.content_type is defined else "json") + "<|message|>" }}
|
| 299 |
+
{{- tool_call.arguments|tojson }}
|
| 300 |
+
{{- "<|call|>" }}
|
| 301 |
+
{%- set last_tool_call.name = tool_call.name %}
|
| 302 |
+
{%- elif loop.last and not add_generation_prompt %}
|
| 303 |
+
{#- Only render the CoT if the final turn is an assistant turn and add_generation_prompt is false #}
|
| 304 |
+
{#- This is a situation that should only occur in training, never in inference. #}
|
| 305 |
+
{%- if "thinking" in message %}
|
| 306 |
+
{{- "<|start|>assistant<|channel|>analysis<|message|>" + message.thinking + "<|end|>" }}
|
| 307 |
+
{%- endif %}
|
| 308 |
+
{#- <|return|> indicates the end of generation, but <|end|> does not #}
|
| 309 |
+
{#- <|return|> should never be an input to the model, but we include it as the final token #}
|
| 310 |
+
{#- when training, so the model learns to emit it. #}
|
| 311 |
+
{{- "<|start|>assistant<|channel|>final<|message|>" + message.content + "<|return|>" }}
|
| 312 |
+
{%- else %}
|
| 313 |
+
{#- CoT is dropped during all previous turns, so we never render it for inference #}
|
| 314 |
+
{{- "<|start|>assistant<|channel|>final<|message|>" + message.content + "<|end|>" }}
|
| 315 |
+
{%- set last_tool_call.name = none %}
|
| 316 |
+
{%- endif %}
|
| 317 |
+
{%- elif message.role == 'tool' -%}
|
| 318 |
+
{%- if last_tool_call.name is none %}
|
| 319 |
+
{{- raise_exception("Message has tool role, but there was no previous assistant message with a tool call!") }}
|
| 320 |
+
{%- endif %}
|
| 321 |
+
{{- "<|start|>functions." + last_tool_call.name }}
|
| 322 |
+
{{- " to=assistant<|channel|>commentary<|message|>" + message.content|tojson + "<|end|>" }}
|
| 323 |
+
{%- elif message.role == 'user' -%}
|
| 324 |
+
{{- "<|start|>user<|message|>" + message.content + "<|end|>" }}
|
| 325 |
+
{%- endif -%}
|
| 326 |
+
{%- endfor -%}
|
| 327 |
+
|
| 328 |
+
{#- Generation prompt #}
|
| 329 |
+
{%- if add_generation_prompt -%}
|
| 330 |
+
<|start|>assistant
|
| 331 |
+
{%- endif -%}
|
checkpoint-50/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-50/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc98fa817f50d692279c3d572238544cc5a8db37aa382cbfc89c607a1788f657
|
| 3 |
+
size 254968907
|
checkpoint-50/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:49d74f24ff40c66479cca4bb3cf7148fba593ccfeb7f3603d6f962430abd8d57
|
| 3 |
+
size 14645
|
checkpoint-50/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:31edc2a2bbce91c1e6afed681e5dc14966c375f87f735113b40ed0fe4d96a219
|
| 3 |
+
size 1465
|
checkpoint-50/special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|startoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|return|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<|endoftext|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
checkpoint-50/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0614fe83cadab421296e664e1f48f4261fa8fef6e03e63bb75c20f38e37d07d3
|
| 3 |
+
size 27868174
|
checkpoint-50/tokenizer_config.json
ADDED
|
@@ -0,0 +1,183 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"199998": {
|
| 4 |
+
"content": "<|startoftext|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"199999": {
|
| 12 |
+
"content": "<|endoftext|>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"200000": {
|
| 20 |
+
"content": "<|reserved_200000|>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"200001": {
|
| 28 |
+
"content": "<|reserved_200001|>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"200002": {
|
| 36 |
+
"content": "<|return|>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"200003": {
|
| 44 |
+
"content": "<|constrain|>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"200004": {
|
| 52 |
+
"content": "<|reserved_200004|>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"200005": {
|
| 60 |
+
"content": "<|channel|>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"200006": {
|
| 68 |
+
"content": "<|start|>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"200007": {
|
| 76 |
+
"content": "<|end|>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"200008": {
|
| 84 |
+
"content": "<|message|>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"200009": {
|
| 92 |
+
"content": "<|reserved_200009|>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"200010": {
|
| 100 |
+
"content": "<|reserved_200010|>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"200011": {
|
| 108 |
+
"content": "<|reserved_200011|>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"200012": {
|
| 116 |
+
"content": "<|call|>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"200013": {
|
| 124 |
+
"content": "<|reserved_200013|>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"200014": {
|
| 132 |
+
"content": "<|reserved_200014|>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"200015": {
|
| 140 |
+
"content": "<|reserved_200015|>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"200016": {
|
| 148 |
+
"content": "<|reserved_200016|>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"200017": {
|
| 156 |
+
"content": "<|reserved_200017|>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"200018": {
|
| 164 |
+
"content": "<|endofprompt|>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
}
|
| 171 |
+
},
|
| 172 |
+
"bos_token": "<|startoftext|>",
|
| 173 |
+
"clean_up_tokenization_spaces": false,
|
| 174 |
+
"eos_token": "<|return|>",
|
| 175 |
+
"extra_special_tokens": {},
|
| 176 |
+
"model_input_names": [
|
| 177 |
+
"input_ids",
|
| 178 |
+
"attention_mask"
|
| 179 |
+
],
|
| 180 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 181 |
+
"pad_token": "<|endoftext|>",
|
| 182 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 183 |
+
}
|
checkpoint-50/trainer_state.json
ADDED
|
@@ -0,0 +1,534 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.255591054313099,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 50,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"entropy": 1.3369140625,
|
| 14 |
+
"epoch": 0.025559105431309903,
|
| 15 |
+
"grad_norm": 2.3105356693267822,
|
| 16 |
+
"learning_rate": 0.0,
|
| 17 |
+
"loss": 1.087,
|
| 18 |
+
"mean_token_accuracy": 0.701034776866436,
|
| 19 |
+
"num_tokens": 6906.0,
|
| 20 |
+
"step": 1
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"entropy": 1.23681640625,
|
| 24 |
+
"epoch": 0.051118210862619806,
|
| 25 |
+
"grad_norm": 2.381164312362671,
|
| 26 |
+
"learning_rate": 4e-05,
|
| 27 |
+
"loss": 0.9348,
|
| 28 |
+
"mean_token_accuracy": 0.7362930178642273,
|
| 29 |
+
"num_tokens": 14418.0,
|
| 30 |
+
"step": 2
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"entropy": 1.0859375,
|
| 34 |
+
"epoch": 0.07667731629392971,
|
| 35 |
+
"grad_norm": 1.7778037786483765,
|
| 36 |
+
"learning_rate": 8e-05,
|
| 37 |
+
"loss": 0.8803,
|
| 38 |
+
"mean_token_accuracy": 0.7567353323101997,
|
| 39 |
+
"num_tokens": 22610.0,
|
| 40 |
+
"step": 3
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"entropy": 1.14208984375,
|
| 44 |
+
"epoch": 0.10223642172523961,
|
| 45 |
+
"grad_norm": 1.4184125661849976,
|
| 46 |
+
"learning_rate": 0.00012,
|
| 47 |
+
"loss": 0.7839,
|
| 48 |
+
"mean_token_accuracy": 0.7793847769498825,
|
| 49 |
+
"num_tokens": 30802.0,
|
| 50 |
+
"step": 4
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"entropy": 1.06689453125,
|
| 54 |
+
"epoch": 0.12779552715654952,
|
| 55 |
+
"grad_norm": 1.1998612880706787,
|
| 56 |
+
"learning_rate": 0.00016,
|
| 57 |
+
"loss": 0.7794,
|
| 58 |
+
"mean_token_accuracy": 0.7751764059066772,
|
| 59 |
+
"num_tokens": 38994.0,
|
| 60 |
+
"step": 5
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"entropy": 1.06884765625,
|
| 64 |
+
"epoch": 0.15335463258785942,
|
| 65 |
+
"grad_norm": 3.067514181137085,
|
| 66 |
+
"learning_rate": 0.0002,
|
| 67 |
+
"loss": 0.8615,
|
| 68 |
+
"mean_token_accuracy": 0.7497537210583687,
|
| 69 |
+
"num_tokens": 47186.0,
|
| 70 |
+
"step": 6
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"entropy": 1.0419921875,
|
| 74 |
+
"epoch": 0.17891373801916932,
|
| 75 |
+
"grad_norm": 3.843412399291992,
|
| 76 |
+
"learning_rate": 0.00019555555555555556,
|
| 77 |
+
"loss": 0.9073,
|
| 78 |
+
"mean_token_accuracy": 0.7386935651302338,
|
| 79 |
+
"num_tokens": 55157.0,
|
| 80 |
+
"step": 7
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"entropy": 0.935546875,
|
| 84 |
+
"epoch": 0.20447284345047922,
|
| 85 |
+
"grad_norm": 2.127117156982422,
|
| 86 |
+
"learning_rate": 0.00019111111111111114,
|
| 87 |
+
"loss": 0.7947,
|
| 88 |
+
"mean_token_accuracy": 0.7617381662130356,
|
| 89 |
+
"num_tokens": 62915.0,
|
| 90 |
+
"step": 8
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"entropy": 1.13232421875,
|
| 94 |
+
"epoch": 0.23003194888178913,
|
| 95 |
+
"grad_norm": 1.4348453283309937,
|
| 96 |
+
"learning_rate": 0.0001866666666666667,
|
| 97 |
+
"loss": 0.8575,
|
| 98 |
+
"mean_token_accuracy": 0.7442174553871155,
|
| 99 |
+
"num_tokens": 70290.0,
|
| 100 |
+
"step": 9
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"entropy": 1.1875,
|
| 104 |
+
"epoch": 0.25559105431309903,
|
| 105 |
+
"grad_norm": 0.9306125044822693,
|
| 106 |
+
"learning_rate": 0.00018222222222222224,
|
| 107 |
+
"loss": 0.9053,
|
| 108 |
+
"mean_token_accuracy": 0.7269261628389359,
|
| 109 |
+
"num_tokens": 77189.0,
|
| 110 |
+
"step": 10
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"entropy": 0.7666015625,
|
| 114 |
+
"epoch": 0.28115015974440893,
|
| 115 |
+
"grad_norm": 0.6212925910949707,
|
| 116 |
+
"learning_rate": 0.00017777777777777779,
|
| 117 |
+
"loss": 0.5573,
|
| 118 |
+
"mean_token_accuracy": 0.8304020240902901,
|
| 119 |
+
"num_tokens": 85381.0,
|
| 120 |
+
"step": 11
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"entropy": 0.871337890625,
|
| 124 |
+
"epoch": 0.30670926517571884,
|
| 125 |
+
"grad_norm": 0.6617708802223206,
|
| 126 |
+
"learning_rate": 0.00017333333333333334,
|
| 127 |
+
"loss": 0.6777,
|
| 128 |
+
"mean_token_accuracy": 0.7921964526176453,
|
| 129 |
+
"num_tokens": 93217.0,
|
| 130 |
+
"step": 12
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"entropy": 0.91796875,
|
| 134 |
+
"epoch": 0.33226837060702874,
|
| 135 |
+
"grad_norm": 0.6723743081092834,
|
| 136 |
+
"learning_rate": 0.00016888888888888889,
|
| 137 |
+
"loss": 0.7622,
|
| 138 |
+
"mean_token_accuracy": 0.765856072306633,
|
| 139 |
+
"num_tokens": 100949.0,
|
| 140 |
+
"step": 13
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"entropy": 0.8798828125,
|
| 144 |
+
"epoch": 0.35782747603833864,
|
| 145 |
+
"grad_norm": 0.6261276602745056,
|
| 146 |
+
"learning_rate": 0.00016444444444444444,
|
| 147 |
+
"loss": 0.7665,
|
| 148 |
+
"mean_token_accuracy": 0.7666892483830452,
|
| 149 |
+
"num_tokens": 108686.0,
|
| 150 |
+
"step": 14
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"entropy": 0.97998046875,
|
| 154 |
+
"epoch": 0.38338658146964855,
|
| 155 |
+
"grad_norm": 0.6475221514701843,
|
| 156 |
+
"learning_rate": 0.00016,
|
| 157 |
+
"loss": 0.8913,
|
| 158 |
+
"mean_token_accuracy": 0.7170633375644684,
|
| 159 |
+
"num_tokens": 115992.0,
|
| 160 |
+
"step": 15
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"entropy": 0.780517578125,
|
| 164 |
+
"epoch": 0.40894568690095845,
|
| 165 |
+
"grad_norm": 0.4886324405670166,
|
| 166 |
+
"learning_rate": 0.00015555555555555556,
|
| 167 |
+
"loss": 0.6722,
|
| 168 |
+
"mean_token_accuracy": 0.7949602380394936,
|
| 169 |
+
"num_tokens": 124184.0,
|
| 170 |
+
"step": 16
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"entropy": 0.82666015625,
|
| 174 |
+
"epoch": 0.43450479233226835,
|
| 175 |
+
"grad_norm": 0.45082569122314453,
|
| 176 |
+
"learning_rate": 0.0001511111111111111,
|
| 177 |
+
"loss": 0.6955,
|
| 178 |
+
"mean_token_accuracy": 0.7882104143500328,
|
| 179 |
+
"num_tokens": 132376.0,
|
| 180 |
+
"step": 17
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"entropy": 0.7724609375,
|
| 184 |
+
"epoch": 0.46006389776357826,
|
| 185 |
+
"grad_norm": 0.5022221207618713,
|
| 186 |
+
"learning_rate": 0.00014666666666666666,
|
| 187 |
+
"loss": 0.6556,
|
| 188 |
+
"mean_token_accuracy": 0.7958140671253204,
|
| 189 |
+
"num_tokens": 140568.0,
|
| 190 |
+
"step": 18
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"entropy": 0.553955078125,
|
| 194 |
+
"epoch": 0.48562300319488816,
|
| 195 |
+
"grad_norm": 0.4155460000038147,
|
| 196 |
+
"learning_rate": 0.00014222222222222224,
|
| 197 |
+
"loss": 0.458,
|
| 198 |
+
"mean_token_accuracy": 0.8605139404535294,
|
| 199 |
+
"num_tokens": 148760.0,
|
| 200 |
+
"step": 19
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"entropy": 0.814453125,
|
| 204 |
+
"epoch": 0.5111821086261981,
|
| 205 |
+
"grad_norm": 0.6609243750572205,
|
| 206 |
+
"learning_rate": 0.0001377777777777778,
|
| 207 |
+
"loss": 0.7756,
|
| 208 |
+
"mean_token_accuracy": 0.7634661719202995,
|
| 209 |
+
"num_tokens": 156158.0,
|
| 210 |
+
"step": 20
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"entropy": 0.738037109375,
|
| 214 |
+
"epoch": 0.536741214057508,
|
| 215 |
+
"grad_norm": 0.5830342173576355,
|
| 216 |
+
"learning_rate": 0.00013333333333333334,
|
| 217 |
+
"loss": 0.7332,
|
| 218 |
+
"mean_token_accuracy": 0.7767216190695763,
|
| 219 |
+
"num_tokens": 164214.0,
|
| 220 |
+
"step": 21
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"entropy": 0.68359375,
|
| 224 |
+
"epoch": 0.5623003194888179,
|
| 225 |
+
"grad_norm": 0.4524409770965576,
|
| 226 |
+
"learning_rate": 0.00012888888888888892,
|
| 227 |
+
"loss": 0.6408,
|
| 228 |
+
"mean_token_accuracy": 0.8016774877905846,
|
| 229 |
+
"num_tokens": 172167.0,
|
| 230 |
+
"step": 22
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"entropy": 0.8681640625,
|
| 234 |
+
"epoch": 0.5878594249201278,
|
| 235 |
+
"grad_norm": 0.4371228516101837,
|
| 236 |
+
"learning_rate": 0.00012444444444444444,
|
| 237 |
+
"loss": 0.7977,
|
| 238 |
+
"mean_token_accuracy": 0.7557996660470963,
|
| 239 |
+
"num_tokens": 179926.0,
|
| 240 |
+
"step": 23
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"entropy": 0.726806640625,
|
| 244 |
+
"epoch": 0.6134185303514377,
|
| 245 |
+
"grad_norm": 0.4200146496295929,
|
| 246 |
+
"learning_rate": 0.00012,
|
| 247 |
+
"loss": 0.6229,
|
| 248 |
+
"mean_token_accuracy": 0.8095021098852158,
|
| 249 |
+
"num_tokens": 188118.0,
|
| 250 |
+
"step": 24
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"entropy": 0.865234375,
|
| 254 |
+
"epoch": 0.6389776357827476,
|
| 255 |
+
"grad_norm": 0.46773526072502136,
|
| 256 |
+
"learning_rate": 0.00011555555555555555,
|
| 257 |
+
"loss": 0.7052,
|
| 258 |
+
"mean_token_accuracy": 0.77592733502388,
|
| 259 |
+
"num_tokens": 195613.0,
|
| 260 |
+
"step": 25
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"entropy": 0.80078125,
|
| 264 |
+
"epoch": 0.6645367412140575,
|
| 265 |
+
"grad_norm": 0.42418503761291504,
|
| 266 |
+
"learning_rate": 0.00011111111111111112,
|
| 267 |
+
"loss": 0.6926,
|
| 268 |
+
"mean_token_accuracy": 0.7816073298454285,
|
| 269 |
+
"num_tokens": 203805.0,
|
| 270 |
+
"step": 26
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"entropy": 0.752685546875,
|
| 274 |
+
"epoch": 0.6900958466453674,
|
| 275 |
+
"grad_norm": 0.3921058475971222,
|
| 276 |
+
"learning_rate": 0.00010666666666666667,
|
| 277 |
+
"loss": 0.5513,
|
| 278 |
+
"mean_token_accuracy": 0.8219155222177505,
|
| 279 |
+
"num_tokens": 211183.0,
|
| 280 |
+
"step": 27
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"entropy": 0.7596435546875,
|
| 284 |
+
"epoch": 0.7156549520766773,
|
| 285 |
+
"grad_norm": 0.41568854451179504,
|
| 286 |
+
"learning_rate": 0.00010222222222222222,
|
| 287 |
+
"loss": 0.6115,
|
| 288 |
+
"mean_token_accuracy": 0.8116571307182312,
|
| 289 |
+
"num_tokens": 218666.0,
|
| 290 |
+
"step": 28
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"entropy": 0.717529296875,
|
| 294 |
+
"epoch": 0.7412140575079872,
|
| 295 |
+
"grad_norm": 0.39525139331817627,
|
| 296 |
+
"learning_rate": 9.777777777777778e-05,
|
| 297 |
+
"loss": 0.5978,
|
| 298 |
+
"mean_token_accuracy": 0.8129823505878448,
|
| 299 |
+
"num_tokens": 226858.0,
|
| 300 |
+
"step": 29
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"entropy": 0.729248046875,
|
| 304 |
+
"epoch": 0.7667731629392971,
|
| 305 |
+
"grad_norm": 0.38765206933021545,
|
| 306 |
+
"learning_rate": 9.333333333333334e-05,
|
| 307 |
+
"loss": 0.578,
|
| 308 |
+
"mean_token_accuracy": 0.8145338892936707,
|
| 309 |
+
"num_tokens": 234618.0,
|
| 310 |
+
"step": 30
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"entropy": 0.78564453125,
|
| 314 |
+
"epoch": 0.792332268370607,
|
| 315 |
+
"grad_norm": 0.48644062876701355,
|
| 316 |
+
"learning_rate": 8.888888888888889e-05,
|
| 317 |
+
"loss": 0.7218,
|
| 318 |
+
"mean_token_accuracy": 0.77530936896801,
|
| 319 |
+
"num_tokens": 242810.0,
|
| 320 |
+
"step": 31
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"entropy": 0.7998046875,
|
| 324 |
+
"epoch": 0.8178913738019169,
|
| 325 |
+
"grad_norm": 0.4270438551902771,
|
| 326 |
+
"learning_rate": 8.444444444444444e-05,
|
| 327 |
+
"loss": 0.7347,
|
| 328 |
+
"mean_token_accuracy": 0.769258588552475,
|
| 329 |
+
"num_tokens": 251002.0,
|
| 330 |
+
"step": 32
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"entropy": 0.7529296875,
|
| 334 |
+
"epoch": 0.8434504792332268,
|
| 335 |
+
"grad_norm": 0.4402211308479309,
|
| 336 |
+
"learning_rate": 8e-05,
|
| 337 |
+
"loss": 0.6393,
|
| 338 |
+
"mean_token_accuracy": 0.8079103901982307,
|
| 339 |
+
"num_tokens": 258948.0,
|
| 340 |
+
"step": 33
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"entropy": 0.647216796875,
|
| 344 |
+
"epoch": 0.8690095846645367,
|
| 345 |
+
"grad_norm": 0.42324361205101013,
|
| 346 |
+
"learning_rate": 7.555555555555556e-05,
|
| 347 |
+
"loss": 0.4934,
|
| 348 |
+
"mean_token_accuracy": 0.8280825689435005,
|
| 349 |
+
"num_tokens": 266397.0,
|
| 350 |
+
"step": 34
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"entropy": 0.8359375,
|
| 354 |
+
"epoch": 0.8945686900958466,
|
| 355 |
+
"grad_norm": 0.47273099422454834,
|
| 356 |
+
"learning_rate": 7.111111111111112e-05,
|
| 357 |
+
"loss": 0.7317,
|
| 358 |
+
"mean_token_accuracy": 0.7696092054247856,
|
| 359 |
+
"num_tokens": 273244.0,
|
| 360 |
+
"step": 35
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"entropy": 0.774169921875,
|
| 364 |
+
"epoch": 0.9201277955271565,
|
| 365 |
+
"grad_norm": 0.40159478783607483,
|
| 366 |
+
"learning_rate": 6.666666666666667e-05,
|
| 367 |
+
"loss": 0.5951,
|
| 368 |
+
"mean_token_accuracy": 0.8139322251081467,
|
| 369 |
+
"num_tokens": 280724.0,
|
| 370 |
+
"step": 36
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"entropy": 0.65966796875,
|
| 374 |
+
"epoch": 0.9456869009584664,
|
| 375 |
+
"grad_norm": 0.38593849539756775,
|
| 376 |
+
"learning_rate": 6.222222222222222e-05,
|
| 377 |
+
"loss": 0.5762,
|
| 378 |
+
"mean_token_accuracy": 0.8153740167617798,
|
| 379 |
+
"num_tokens": 288703.0,
|
| 380 |
+
"step": 37
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"entropy": 0.7236328125,
|
| 384 |
+
"epoch": 0.9712460063897763,
|
| 385 |
+
"grad_norm": 0.4029550850391388,
|
| 386 |
+
"learning_rate": 5.7777777777777776e-05,
|
| 387 |
+
"loss": 0.6262,
|
| 388 |
+
"mean_token_accuracy": 0.8032189607620239,
|
| 389 |
+
"num_tokens": 296736.0,
|
| 390 |
+
"step": 38
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"entropy": 0.695068359375,
|
| 394 |
+
"epoch": 0.9968051118210862,
|
| 395 |
+
"grad_norm": 0.4444594085216522,
|
| 396 |
+
"learning_rate": 5.333333333333333e-05,
|
| 397 |
+
"loss": 0.6218,
|
| 398 |
+
"mean_token_accuracy": 0.8159564882516861,
|
| 399 |
+
"num_tokens": 304425.0,
|
| 400 |
+
"step": 39
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"entropy": 0.90234375,
|
| 404 |
+
"epoch": 1.0,
|
| 405 |
+
"grad_norm": 1.3549686670303345,
|
| 406 |
+
"learning_rate": 4.888888888888889e-05,
|
| 407 |
+
"loss": 0.8577,
|
| 408 |
+
"mean_token_accuracy": 0.725623607635498,
|
| 409 |
+
"num_tokens": 305449.0,
|
| 410 |
+
"step": 40
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"entropy": 0.79345703125,
|
| 414 |
+
"epoch": 1.0255591054313098,
|
| 415 |
+
"grad_norm": 0.4474547207355499,
|
| 416 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 417 |
+
"loss": 0.6887,
|
| 418 |
+
"mean_token_accuracy": 0.7809437215328217,
|
| 419 |
+
"num_tokens": 313242.0,
|
| 420 |
+
"step": 41
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"entropy": 0.7763671875,
|
| 424 |
+
"epoch": 1.0511182108626198,
|
| 425 |
+
"grad_norm": 0.4416673481464386,
|
| 426 |
+
"learning_rate": 4e-05,
|
| 427 |
+
"loss": 0.6635,
|
| 428 |
+
"mean_token_accuracy": 0.7911219000816345,
|
| 429 |
+
"num_tokens": 320751.0,
|
| 430 |
+
"step": 42
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"entropy": 0.81494140625,
|
| 434 |
+
"epoch": 1.0766773162939298,
|
| 435 |
+
"grad_norm": 0.4539318382740021,
|
| 436 |
+
"learning_rate": 3.555555555555556e-05,
|
| 437 |
+
"loss": 0.6578,
|
| 438 |
+
"mean_token_accuracy": 0.7916175723075867,
|
| 439 |
+
"num_tokens": 328943.0,
|
| 440 |
+
"step": 43
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"entropy": 0.86474609375,
|
| 444 |
+
"epoch": 1.1022364217252396,
|
| 445 |
+
"grad_norm": 0.40605172514915466,
|
| 446 |
+
"learning_rate": 3.111111111111111e-05,
|
| 447 |
+
"loss": 0.7085,
|
| 448 |
+
"mean_token_accuracy": 0.7670398578047752,
|
| 449 |
+
"num_tokens": 336515.0,
|
| 450 |
+
"step": 44
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"entropy": 0.69775390625,
|
| 454 |
+
"epoch": 1.1277955271565494,
|
| 455 |
+
"grad_norm": 0.3975476026535034,
|
| 456 |
+
"learning_rate": 2.6666666666666667e-05,
|
| 457 |
+
"loss": 0.4933,
|
| 458 |
+
"mean_token_accuracy": 0.8318949267268181,
|
| 459 |
+
"num_tokens": 343984.0,
|
| 460 |
+
"step": 45
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"entropy": 0.791259765625,
|
| 464 |
+
"epoch": 1.1533546325878594,
|
| 465 |
+
"grad_norm": 0.4187847673892975,
|
| 466 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 467 |
+
"loss": 0.6253,
|
| 468 |
+
"mean_token_accuracy": 0.8081694170832634,
|
| 469 |
+
"num_tokens": 351464.0,
|
| 470 |
+
"step": 46
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"entropy": 0.703857421875,
|
| 474 |
+
"epoch": 1.1789137380191694,
|
| 475 |
+
"grad_norm": 0.35935476422309875,
|
| 476 |
+
"learning_rate": 1.777777777777778e-05,
|
| 477 |
+
"loss": 0.5352,
|
| 478 |
+
"mean_token_accuracy": 0.811345063149929,
|
| 479 |
+
"num_tokens": 358913.0,
|
| 480 |
+
"step": 47
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"entropy": 0.84765625,
|
| 484 |
+
"epoch": 1.2044728434504792,
|
| 485 |
+
"grad_norm": 0.4173986315727234,
|
| 486 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 487 |
+
"loss": 0.7239,
|
| 488 |
+
"mean_token_accuracy": 0.7771043181419373,
|
| 489 |
+
"num_tokens": 366672.0,
|
| 490 |
+
"step": 48
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"entropy": 0.69775390625,
|
| 494 |
+
"epoch": 1.230031948881789,
|
| 495 |
+
"grad_norm": 0.37685781717300415,
|
| 496 |
+
"learning_rate": 8.88888888888889e-06,
|
| 497 |
+
"loss": 0.6163,
|
| 498 |
+
"mean_token_accuracy": 0.8031821772456169,
|
| 499 |
+
"num_tokens": 374864.0,
|
| 500 |
+
"step": 49
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"entropy": 0.71435546875,
|
| 504 |
+
"epoch": 1.255591054313099,
|
| 505 |
+
"grad_norm": 0.38702356815338135,
|
| 506 |
+
"learning_rate": 4.444444444444445e-06,
|
| 507 |
+
"loss": 0.6231,
|
| 508 |
+
"mean_token_accuracy": 0.806434653699398,
|
| 509 |
+
"num_tokens": 383056.0,
|
| 510 |
+
"step": 50
|
| 511 |
+
}
|
| 512 |
+
],
|
| 513 |
+
"logging_steps": 1,
|
| 514 |
+
"max_steps": 50,
|
| 515 |
+
"num_input_tokens_seen": 0,
|
| 516 |
+
"num_train_epochs": 2,
|
| 517 |
+
"save_steps": 500,
|
| 518 |
+
"stateful_callbacks": {
|
| 519 |
+
"TrainerControl": {
|
| 520 |
+
"args": {
|
| 521 |
+
"should_epoch_stop": false,
|
| 522 |
+
"should_evaluate": false,
|
| 523 |
+
"should_log": false,
|
| 524 |
+
"should_save": true,
|
| 525 |
+
"should_training_stop": true
|
| 526 |
+
},
|
| 527 |
+
"attributes": {}
|
| 528 |
+
}
|
| 529 |
+
},
|
| 530 |
+
"total_flos": 4.681129927486464e+16,
|
| 531 |
+
"train_batch_size": 1,
|
| 532 |
+
"trial_name": null,
|
| 533 |
+
"trial_params": null
|
| 534 |
+
}
|
checkpoint-50/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bef7111ffab0c1452afe643559792e51d9a4120b16dfea8d8982a1087a6cfc9d
|
| 3 |
+
size 5713
|
checkpoint-50/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
config.json
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"GptOssForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": true,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 199998,
|
| 8 |
+
"dtype": "bfloat16",
|
| 9 |
+
"eos_token_id": 200002,
|
| 10 |
+
"experts_per_token": 4,
|
| 11 |
+
"head_dim": 64,
|
| 12 |
+
"hidden_act": "silu",
|
| 13 |
+
"hidden_size": 2880,
|
| 14 |
+
"initial_context_length": 4096,
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 2880,
|
| 17 |
+
"layer_types": [
|
| 18 |
+
"sliding_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"sliding_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"sliding_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"sliding_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"sliding_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"sliding_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"sliding_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"sliding_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"sliding_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"sliding_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"sliding_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"sliding_attention",
|
| 41 |
+
"full_attention"
|
| 42 |
+
],
|
| 43 |
+
"max_position_embeddings": 131072,
|
| 44 |
+
"model_type": "gpt_oss",
|
| 45 |
+
"num_attention_heads": 64,
|
| 46 |
+
"num_experts_per_tok": 4,
|
| 47 |
+
"num_hidden_layers": 24,
|
| 48 |
+
"num_key_value_heads": 8,
|
| 49 |
+
"num_local_experts": 32,
|
| 50 |
+
"output_router_logits": false,
|
| 51 |
+
"pad_token_id": 199999,
|
| 52 |
+
"rms_norm_eps": 1e-05,
|
| 53 |
+
"rope_scaling": {
|
| 54 |
+
"beta_fast": 32.0,
|
| 55 |
+
"beta_slow": 1.0,
|
| 56 |
+
"factor": 32.0,
|
| 57 |
+
"original_max_position_embeddings": 4096,
|
| 58 |
+
"rope_type": "yarn",
|
| 59 |
+
"truncate": false
|
| 60 |
+
},
|
| 61 |
+
"rope_theta": 150000,
|
| 62 |
+
"router_aux_loss_coef": 0.9,
|
| 63 |
+
"sliding_window": 128,
|
| 64 |
+
"swiglu_limit": 7.0,
|
| 65 |
+
"tie_word_embeddings": false,
|
| 66 |
+
"transformers_version": "4.57.0.dev0",
|
| 67 |
+
"use_cache": true,
|
| 68 |
+
"vocab_size": 201088
|
| 69 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 199998,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
200002,
|
| 6 |
+
199999,
|
| 7 |
+
200012
|
| 8 |
+
],
|
| 9 |
+
"pad_token_id": 199999,
|
| 10 |
+
"transformers_version": "4.57.0.dev0"
|
| 11 |
+
}
|
lora_weights/README.md
ADDED
|
@@ -0,0 +1,209 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: openai/gpt-oss-20b
|
| 3 |
+
library_name: peft
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
- base_model:adapter:openai/gpt-oss-20b
|
| 7 |
+
- lora
|
| 8 |
+
- sft
|
| 9 |
+
- transformers
|
| 10 |
+
- trl
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
# Model Card for Model ID
|
| 14 |
+
|
| 15 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
## Model Details
|
| 20 |
+
|
| 21 |
+
### Model Description
|
| 22 |
+
|
| 23 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
|
| 27 |
+
- **Developed by:** [More Information Needed]
|
| 28 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 29 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 30 |
+
- **Model type:** [More Information Needed]
|
| 31 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 32 |
+
- **License:** [More Information Needed]
|
| 33 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 34 |
+
|
| 35 |
+
### Model Sources [optional]
|
| 36 |
+
|
| 37 |
+
<!-- Provide the basic links for the model. -->
|
| 38 |
+
|
| 39 |
+
- **Repository:** [More Information Needed]
|
| 40 |
+
- **Paper [optional]:** [More Information Needed]
|
| 41 |
+
- **Demo [optional]:** [More Information Needed]
|
| 42 |
+
|
| 43 |
+
## Uses
|
| 44 |
+
|
| 45 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 46 |
+
|
| 47 |
+
### Direct Use
|
| 48 |
+
|
| 49 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 50 |
+
|
| 51 |
+
[More Information Needed]
|
| 52 |
+
|
| 53 |
+
### Downstream Use [optional]
|
| 54 |
+
|
| 55 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 56 |
+
|
| 57 |
+
[More Information Needed]
|
| 58 |
+
|
| 59 |
+
### Out-of-Scope Use
|
| 60 |
+
|
| 61 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 62 |
+
|
| 63 |
+
[More Information Needed]
|
| 64 |
+
|
| 65 |
+
## Bias, Risks, and Limitations
|
| 66 |
+
|
| 67 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 68 |
+
|
| 69 |
+
[More Information Needed]
|
| 70 |
+
|
| 71 |
+
### Recommendations
|
| 72 |
+
|
| 73 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 74 |
+
|
| 75 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 76 |
+
|
| 77 |
+
## How to Get Started with the Model
|
| 78 |
+
|
| 79 |
+
Use the code below to get started with the model.
|
| 80 |
+
|
| 81 |
+
[More Information Needed]
|
| 82 |
+
|
| 83 |
+
## Training Details
|
| 84 |
+
|
| 85 |
+
### Training Data
|
| 86 |
+
|
| 87 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 88 |
+
|
| 89 |
+
[More Information Needed]
|
| 90 |
+
|
| 91 |
+
### Training Procedure
|
| 92 |
+
|
| 93 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 94 |
+
|
| 95 |
+
#### Preprocessing [optional]
|
| 96 |
+
|
| 97 |
+
[More Information Needed]
|
| 98 |
+
|
| 99 |
+
|
| 100 |
+
#### Training Hyperparameters
|
| 101 |
+
|
| 102 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 103 |
+
|
| 104 |
+
#### Speeds, Sizes, Times [optional]
|
| 105 |
+
|
| 106 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 107 |
+
|
| 108 |
+
[More Information Needed]
|
| 109 |
+
|
| 110 |
+
## Evaluation
|
| 111 |
+
|
| 112 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 113 |
+
|
| 114 |
+
### Testing Data, Factors & Metrics
|
| 115 |
+
|
| 116 |
+
#### Testing Data
|
| 117 |
+
|
| 118 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 119 |
+
|
| 120 |
+
[More Information Needed]
|
| 121 |
+
|
| 122 |
+
#### Factors
|
| 123 |
+
|
| 124 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 125 |
+
|
| 126 |
+
[More Information Needed]
|
| 127 |
+
|
| 128 |
+
#### Metrics
|
| 129 |
+
|
| 130 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 131 |
+
|
| 132 |
+
[More Information Needed]
|
| 133 |
+
|
| 134 |
+
### Results
|
| 135 |
+
|
| 136 |
+
[More Information Needed]
|
| 137 |
+
|
| 138 |
+
#### Summary
|
| 139 |
+
|
| 140 |
+
|
| 141 |
+
|
| 142 |
+
## Model Examination [optional]
|
| 143 |
+
|
| 144 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 145 |
+
|
| 146 |
+
[More Information Needed]
|
| 147 |
+
|
| 148 |
+
## Environmental Impact
|
| 149 |
+
|
| 150 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 151 |
+
|
| 152 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 153 |
+
|
| 154 |
+
- **Hardware Type:** [More Information Needed]
|
| 155 |
+
- **Hours used:** [More Information Needed]
|
| 156 |
+
- **Cloud Provider:** [More Information Needed]
|
| 157 |
+
- **Compute Region:** [More Information Needed]
|
| 158 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 159 |
+
|
| 160 |
+
## Technical Specifications [optional]
|
| 161 |
+
|
| 162 |
+
### Model Architecture and Objective
|
| 163 |
+
|
| 164 |
+
[More Information Needed]
|
| 165 |
+
|
| 166 |
+
### Compute Infrastructure
|
| 167 |
+
|
| 168 |
+
[More Information Needed]
|
| 169 |
+
|
| 170 |
+
#### Hardware
|
| 171 |
+
|
| 172 |
+
[More Information Needed]
|
| 173 |
+
|
| 174 |
+
#### Software
|
| 175 |
+
|
| 176 |
+
[More Information Needed]
|
| 177 |
+
|
| 178 |
+
## Citation [optional]
|
| 179 |
+
|
| 180 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 181 |
+
|
| 182 |
+
**BibTeX:**
|
| 183 |
+
|
| 184 |
+
[More Information Needed]
|
| 185 |
+
|
| 186 |
+
**APA:**
|
| 187 |
+
|
| 188 |
+
[More Information Needed]
|
| 189 |
+
|
| 190 |
+
## Glossary [optional]
|
| 191 |
+
|
| 192 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 193 |
+
|
| 194 |
+
[More Information Needed]
|
| 195 |
+
|
| 196 |
+
## More Information [optional]
|
| 197 |
+
|
| 198 |
+
[More Information Needed]
|
| 199 |
+
|
| 200 |
+
## Model Card Authors [optional]
|
| 201 |
+
|
| 202 |
+
[More Information Needed]
|
| 203 |
+
|
| 204 |
+
## Model Card Contact
|
| 205 |
+
|
| 206 |
+
[More Information Needed]
|
| 207 |
+
### Framework versions
|
| 208 |
+
|
| 209 |
+
- PEFT 0.17.1
|
lora_weights/adapter_config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "openai/gpt-oss-20b",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 64,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.1,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"qalora_group_size": 16,
|
| 24 |
+
"r": 64,
|
| 25 |
+
"rank_pattern": {},
|
| 26 |
+
"revision": null,
|
| 27 |
+
"target_modules": [
|
| 28 |
+
"gate_proj",
|
| 29 |
+
"k_proj",
|
| 30 |
+
"down_proj",
|
| 31 |
+
"up_proj",
|
| 32 |
+
"v_proj",
|
| 33 |
+
"q_proj",
|
| 34 |
+
"o_proj"
|
| 35 |
+
],
|
| 36 |
+
"target_parameters": null,
|
| 37 |
+
"task_type": "CAUSAL_LM",
|
| 38 |
+
"trainable_token_indices": null,
|
| 39 |
+
"use_dora": false,
|
| 40 |
+
"use_qalora": false,
|
| 41 |
+
"use_rslora": false
|
| 42 |
+
}
|
lora_weights/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:66588ad755f746ec82e0bf0290eb4b80f1792e714636a26ab0cc88500df86f08
|
| 3 |
+
size 127427864
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00009.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:49feabd467741ee98df04ca370476960ec368100e3c7ed7039c26ef993c00c73
|
| 3 |
+
size 4504304664
|
model-00002-of-00009.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dd1c751af0255e029aa68af79619a560898c3cda96525727d049040aa549472a
|
| 3 |
+
size 4939127656
|
model-00003-of-00009.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b6d793c8bf80427c1ebcd4d5c55938115a0a2638b53309c7bf072b0b56c44a5e
|
| 3 |
+
size 4939127656
|
model-00004-of-00009.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:58d87f482f3fe66643efb6ba83da3500f9927ee55e0d4e48bb3239a90d17258a
|
| 3 |
+
size 4939127680
|
model-00005-of-00009.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f59e45b0b11d6b7f46583d937b0f7acb2abddd3c3cbc00669984c1e1048bd2d8
|
| 3 |
+
size 4939127704
|
model-00006-of-00009.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:68c3782f811fc251321743a09600ce9ecdad594de5e427f0c9703d14df8482b4
|
| 3 |
+
size 4939127704
|
model-00007-of-00009.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:82654433ea16dbaf46e1e064593d6d4660134d0465b91934f2a0e9de8b7b8a59
|
| 3 |
+
size 4939127704
|
model-00008-of-00009.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d470fc83b0675251ff1a91ab87d2e21e0892b57bbd5efb610b229eea604d74ca
|
| 3 |
+
size 4939127704
|
model-00009-of-00009.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6c1951ff65d233bcb7f50485d294cced6497b8e0d9707f57087912fc2352492e
|
| 3 |
+
size 2751362856
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,419 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 20914757184,
|
| 4 |
+
"total_size": 41829514368
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"lm_head.weight": "model-00009-of-00009.safetensors",
|
| 8 |
+
"model.embed_tokens.weight": "model-00001-of-00009.safetensors",
|
| 9 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00009.safetensors",
|
| 10 |
+
"model.layers.0.mlp.experts.down_proj": "model-00001-of-00009.safetensors",
|
| 11 |
+
"model.layers.0.mlp.experts.down_proj_bias": "model-00001-of-00009.safetensors",
|
| 12 |
+
"model.layers.0.mlp.experts.gate_up_proj": "model-00001-of-00009.safetensors",
|
| 13 |
+
"model.layers.0.mlp.experts.gate_up_proj_bias": "model-00001-of-00009.safetensors",
|
| 14 |
+
"model.layers.0.mlp.router.bias": "model-00001-of-00009.safetensors",
|
| 15 |
+
"model.layers.0.mlp.router.weight": "model-00001-of-00009.safetensors",
|
| 16 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00009.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
|
| 19 |
+
"model.layers.0.self_attn.o_proj.bias": "model-00001-of-00009.safetensors",
|
| 20 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
|
| 21 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00009.safetensors",
|
| 22 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
|
| 23 |
+
"model.layers.0.self_attn.sinks": "model-00001-of-00009.safetensors",
|
| 24 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00009.safetensors",
|
| 25 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
|
| 26 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00009.safetensors",
|
| 27 |
+
"model.layers.1.mlp.experts.down_proj": "model-00001-of-00009.safetensors",
|
| 28 |
+
"model.layers.1.mlp.experts.down_proj_bias": "model-00001-of-00009.safetensors",
|
| 29 |
+
"model.layers.1.mlp.experts.gate_up_proj": "model-00001-of-00009.safetensors",
|
| 30 |
+
"model.layers.1.mlp.experts.gate_up_proj_bias": "model-00001-of-00009.safetensors",
|
| 31 |
+
"model.layers.1.mlp.router.bias": "model-00001-of-00009.safetensors",
|
| 32 |
+
"model.layers.1.mlp.router.weight": "model-00001-of-00009.safetensors",
|
| 33 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
|
| 34 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00009.safetensors",
|
| 35 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
|
| 36 |
+
"model.layers.1.self_attn.o_proj.bias": "model-00001-of-00009.safetensors",
|
| 37 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
|
| 38 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00009.safetensors",
|
| 39 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
|
| 40 |
+
"model.layers.1.self_attn.sinks": "model-00001-of-00009.safetensors",
|
| 41 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00009.safetensors",
|
| 42 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
|
| 43 |
+
"model.layers.10.input_layernorm.weight": "model-00004-of-00009.safetensors",
|
| 44 |
+
"model.layers.10.mlp.experts.down_proj": "model-00004-of-00009.safetensors",
|
| 45 |
+
"model.layers.10.mlp.experts.down_proj_bias": "model-00004-of-00009.safetensors",
|
| 46 |
+
"model.layers.10.mlp.experts.gate_up_proj": "model-00004-of-00009.safetensors",
|
| 47 |
+
"model.layers.10.mlp.experts.gate_up_proj_bias": "model-00004-of-00009.safetensors",
|
| 48 |
+
"model.layers.10.mlp.router.bias": "model-00004-of-00009.safetensors",
|
| 49 |
+
"model.layers.10.mlp.router.weight": "model-00004-of-00009.safetensors",
|
| 50 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
|
| 51 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00004-of-00009.safetensors",
|
| 52 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
|
| 53 |
+
"model.layers.10.self_attn.o_proj.bias": "model-00004-of-00009.safetensors",
|
| 54 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
|
| 55 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00004-of-00009.safetensors",
|
| 56 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
|
| 57 |
+
"model.layers.10.self_attn.sinks": "model-00004-of-00009.safetensors",
|
| 58 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00004-of-00009.safetensors",
|
| 59 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
|
| 60 |
+
"model.layers.11.input_layernorm.weight": "model-00005-of-00009.safetensors",
|
| 61 |
+
"model.layers.11.mlp.experts.down_proj": "model-00005-of-00009.safetensors",
|
| 62 |
+
"model.layers.11.mlp.experts.down_proj_bias": "model-00005-of-00009.safetensors",
|
| 63 |
+
"model.layers.11.mlp.experts.gate_up_proj": "model-00005-of-00009.safetensors",
|
| 64 |
+
"model.layers.11.mlp.experts.gate_up_proj_bias": "model-00005-of-00009.safetensors",
|
| 65 |
+
"model.layers.11.mlp.router.bias": "model-00004-of-00009.safetensors",
|
| 66 |
+
"model.layers.11.mlp.router.weight": "model-00004-of-00009.safetensors",
|
| 67 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
|
| 68 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00004-of-00009.safetensors",
|
| 69 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
|
| 70 |
+
"model.layers.11.self_attn.o_proj.bias": "model-00004-of-00009.safetensors",
|
| 71 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
|
| 72 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00004-of-00009.safetensors",
|
| 73 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
|
| 74 |
+
"model.layers.11.self_attn.sinks": "model-00004-of-00009.safetensors",
|
| 75 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00004-of-00009.safetensors",
|
| 76 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
|
| 77 |
+
"model.layers.12.input_layernorm.weight": "model-00005-of-00009.safetensors",
|
| 78 |
+
"model.layers.12.mlp.experts.down_proj": "model-00005-of-00009.safetensors",
|
| 79 |
+
"model.layers.12.mlp.experts.down_proj_bias": "model-00005-of-00009.safetensors",
|
| 80 |
+
"model.layers.12.mlp.experts.gate_up_proj": "model-00005-of-00009.safetensors",
|
| 81 |
+
"model.layers.12.mlp.experts.gate_up_proj_bias": "model-00005-of-00009.safetensors",
|
| 82 |
+
"model.layers.12.mlp.router.bias": "model-00005-of-00009.safetensors",
|
| 83 |
+
"model.layers.12.mlp.router.weight": "model-00005-of-00009.safetensors",
|
| 84 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
|
| 85 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00005-of-00009.safetensors",
|
| 86 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
|
| 87 |
+
"model.layers.12.self_attn.o_proj.bias": "model-00005-of-00009.safetensors",
|
| 88 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
|
| 89 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00005-of-00009.safetensors",
|
| 90 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
|
| 91 |
+
"model.layers.12.self_attn.sinks": "model-00005-of-00009.safetensors",
|
| 92 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00005-of-00009.safetensors",
|
| 93 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
|
| 94 |
+
"model.layers.13.input_layernorm.weight": "model-00005-of-00009.safetensors",
|
| 95 |
+
"model.layers.13.mlp.experts.down_proj": "model-00005-of-00009.safetensors",
|
| 96 |
+
"model.layers.13.mlp.experts.down_proj_bias": "model-00005-of-00009.safetensors",
|
| 97 |
+
"model.layers.13.mlp.experts.gate_up_proj": "model-00005-of-00009.safetensors",
|
| 98 |
+
"model.layers.13.mlp.experts.gate_up_proj_bias": "model-00005-of-00009.safetensors",
|
| 99 |
+
"model.layers.13.mlp.router.bias": "model-00005-of-00009.safetensors",
|
| 100 |
+
"model.layers.13.mlp.router.weight": "model-00005-of-00009.safetensors",
|
| 101 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
|
| 102 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00005-of-00009.safetensors",
|
| 103 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
|
| 104 |
+
"model.layers.13.self_attn.o_proj.bias": "model-00005-of-00009.safetensors",
|
| 105 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
|
| 106 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00005-of-00009.safetensors",
|
| 107 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
|
| 108 |
+
"model.layers.13.self_attn.sinks": "model-00005-of-00009.safetensors",
|
| 109 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00005-of-00009.safetensors",
|
| 110 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
|
| 111 |
+
"model.layers.14.input_layernorm.weight": "model-00006-of-00009.safetensors",
|
| 112 |
+
"model.layers.14.mlp.experts.down_proj": "model-00006-of-00009.safetensors",
|
| 113 |
+
"model.layers.14.mlp.experts.down_proj_bias": "model-00006-of-00009.safetensors",
|
| 114 |
+
"model.layers.14.mlp.experts.gate_up_proj": "model-00006-of-00009.safetensors",
|
| 115 |
+
"model.layers.14.mlp.experts.gate_up_proj_bias": "model-00006-of-00009.safetensors",
|
| 116 |
+
"model.layers.14.mlp.router.bias": "model-00005-of-00009.safetensors",
|
| 117 |
+
"model.layers.14.mlp.router.weight": "model-00005-of-00009.safetensors",
|
| 118 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
|
| 119 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00005-of-00009.safetensors",
|
| 120 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
|
| 121 |
+
"model.layers.14.self_attn.o_proj.bias": "model-00005-of-00009.safetensors",
|
| 122 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
|
| 123 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00005-of-00009.safetensors",
|
| 124 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
|
| 125 |
+
"model.layers.14.self_attn.sinks": "model-00005-of-00009.safetensors",
|
| 126 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00005-of-00009.safetensors",
|
| 127 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
|
| 128 |
+
"model.layers.15.input_layernorm.weight": "model-00006-of-00009.safetensors",
|
| 129 |
+
"model.layers.15.mlp.experts.down_proj": "model-00006-of-00009.safetensors",
|
| 130 |
+
"model.layers.15.mlp.experts.down_proj_bias": "model-00006-of-00009.safetensors",
|
| 131 |
+
"model.layers.15.mlp.experts.gate_up_proj": "model-00006-of-00009.safetensors",
|
| 132 |
+
"model.layers.15.mlp.experts.gate_up_proj_bias": "model-00006-of-00009.safetensors",
|
| 133 |
+
"model.layers.15.mlp.router.bias": "model-00006-of-00009.safetensors",
|
| 134 |
+
"model.layers.15.mlp.router.weight": "model-00006-of-00009.safetensors",
|
| 135 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
|
| 136 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00006-of-00009.safetensors",
|
| 137 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
|
| 138 |
+
"model.layers.15.self_attn.o_proj.bias": "model-00006-of-00009.safetensors",
|
| 139 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
|
| 140 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00006-of-00009.safetensors",
|
| 141 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
|
| 142 |
+
"model.layers.15.self_attn.sinks": "model-00006-of-00009.safetensors",
|
| 143 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00006-of-00009.safetensors",
|
| 144 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
|
| 145 |
+
"model.layers.16.input_layernorm.weight": "model-00006-of-00009.safetensors",
|
| 146 |
+
"model.layers.16.mlp.experts.down_proj": "model-00006-of-00009.safetensors",
|
| 147 |
+
"model.layers.16.mlp.experts.down_proj_bias": "model-00006-of-00009.safetensors",
|
| 148 |
+
"model.layers.16.mlp.experts.gate_up_proj": "model-00006-of-00009.safetensors",
|
| 149 |
+
"model.layers.16.mlp.experts.gate_up_proj_bias": "model-00006-of-00009.safetensors",
|
| 150 |
+
"model.layers.16.mlp.router.bias": "model-00006-of-00009.safetensors",
|
| 151 |
+
"model.layers.16.mlp.router.weight": "model-00006-of-00009.safetensors",
|
| 152 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
|
| 153 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00006-of-00009.safetensors",
|
| 154 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
|
| 155 |
+
"model.layers.16.self_attn.o_proj.bias": "model-00006-of-00009.safetensors",
|
| 156 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
|
| 157 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00006-of-00009.safetensors",
|
| 158 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
|
| 159 |
+
"model.layers.16.self_attn.sinks": "model-00006-of-00009.safetensors",
|
| 160 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00006-of-00009.safetensors",
|
| 161 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
|
| 162 |
+
"model.layers.17.input_layernorm.weight": "model-00007-of-00009.safetensors",
|
| 163 |
+
"model.layers.17.mlp.experts.down_proj": "model-00007-of-00009.safetensors",
|
| 164 |
+
"model.layers.17.mlp.experts.down_proj_bias": "model-00007-of-00009.safetensors",
|
| 165 |
+
"model.layers.17.mlp.experts.gate_up_proj": "model-00007-of-00009.safetensors",
|
| 166 |
+
"model.layers.17.mlp.experts.gate_up_proj_bias": "model-00007-of-00009.safetensors",
|
| 167 |
+
"model.layers.17.mlp.router.bias": "model-00006-of-00009.safetensors",
|
| 168 |
+
"model.layers.17.mlp.router.weight": "model-00006-of-00009.safetensors",
|
| 169 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
|
| 170 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00006-of-00009.safetensors",
|
| 171 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
|
| 172 |
+
"model.layers.17.self_attn.o_proj.bias": "model-00006-of-00009.safetensors",
|
| 173 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
|
| 174 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00006-of-00009.safetensors",
|
| 175 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
|
| 176 |
+
"model.layers.17.self_attn.sinks": "model-00006-of-00009.safetensors",
|
| 177 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00006-of-00009.safetensors",
|
| 178 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
|
| 179 |
+
"model.layers.18.input_layernorm.weight": "model-00007-of-00009.safetensors",
|
| 180 |
+
"model.layers.18.mlp.experts.down_proj": "model-00007-of-00009.safetensors",
|
| 181 |
+
"model.layers.18.mlp.experts.down_proj_bias": "model-00007-of-00009.safetensors",
|
| 182 |
+
"model.layers.18.mlp.experts.gate_up_proj": "model-00007-of-00009.safetensors",
|
| 183 |
+
"model.layers.18.mlp.experts.gate_up_proj_bias": "model-00007-of-00009.safetensors",
|
| 184 |
+
"model.layers.18.mlp.router.bias": "model-00007-of-00009.safetensors",
|
| 185 |
+
"model.layers.18.mlp.router.weight": "model-00007-of-00009.safetensors",
|
| 186 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
|
| 187 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00007-of-00009.safetensors",
|
| 188 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
|
| 189 |
+
"model.layers.18.self_attn.o_proj.bias": "model-00007-of-00009.safetensors",
|
| 190 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
|
| 191 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00007-of-00009.safetensors",
|
| 192 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
|
| 193 |
+
"model.layers.18.self_attn.sinks": "model-00007-of-00009.safetensors",
|
| 194 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00007-of-00009.safetensors",
|
| 195 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
|
| 196 |
+
"model.layers.19.input_layernorm.weight": "model-00007-of-00009.safetensors",
|
| 197 |
+
"model.layers.19.mlp.experts.down_proj": "model-00007-of-00009.safetensors",
|
| 198 |
+
"model.layers.19.mlp.experts.down_proj_bias": "model-00007-of-00009.safetensors",
|
| 199 |
+
"model.layers.19.mlp.experts.gate_up_proj": "model-00007-of-00009.safetensors",
|
| 200 |
+
"model.layers.19.mlp.experts.gate_up_proj_bias": "model-00007-of-00009.safetensors",
|
| 201 |
+
"model.layers.19.mlp.router.bias": "model-00007-of-00009.safetensors",
|
| 202 |
+
"model.layers.19.mlp.router.weight": "model-00007-of-00009.safetensors",
|
| 203 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
|
| 204 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00007-of-00009.safetensors",
|
| 205 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
|
| 206 |
+
"model.layers.19.self_attn.o_proj.bias": "model-00007-of-00009.safetensors",
|
| 207 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
|
| 208 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00007-of-00009.safetensors",
|
| 209 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
|
| 210 |
+
"model.layers.19.self_attn.sinks": "model-00007-of-00009.safetensors",
|
| 211 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00007-of-00009.safetensors",
|
| 212 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
|
| 213 |
+
"model.layers.2.input_layernorm.weight": "model-00002-of-00009.safetensors",
|
| 214 |
+
"model.layers.2.mlp.experts.down_proj": "model-00002-of-00009.safetensors",
|
| 215 |
+
"model.layers.2.mlp.experts.down_proj_bias": "model-00002-of-00009.safetensors",
|
| 216 |
+
"model.layers.2.mlp.experts.gate_up_proj": "model-00002-of-00009.safetensors",
|
| 217 |
+
"model.layers.2.mlp.experts.gate_up_proj_bias": "model-00002-of-00009.safetensors",
|
| 218 |
+
"model.layers.2.mlp.router.bias": "model-00001-of-00009.safetensors",
|
| 219 |
+
"model.layers.2.mlp.router.weight": "model-00001-of-00009.safetensors",
|
| 220 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
|
| 221 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00009.safetensors",
|
| 222 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
|
| 223 |
+
"model.layers.2.self_attn.o_proj.bias": "model-00001-of-00009.safetensors",
|
| 224 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
|
| 225 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00009.safetensors",
|
| 226 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
|
| 227 |
+
"model.layers.2.self_attn.sinks": "model-00001-of-00009.safetensors",
|
| 228 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00009.safetensors",
|
| 229 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
|
| 230 |
+
"model.layers.20.input_layernorm.weight": "model-00008-of-00009.safetensors",
|
| 231 |
+
"model.layers.20.mlp.experts.down_proj": "model-00008-of-00009.safetensors",
|
| 232 |
+
"model.layers.20.mlp.experts.down_proj_bias": "model-00008-of-00009.safetensors",
|
| 233 |
+
"model.layers.20.mlp.experts.gate_up_proj": "model-00008-of-00009.safetensors",
|
| 234 |
+
"model.layers.20.mlp.experts.gate_up_proj_bias": "model-00008-of-00009.safetensors",
|
| 235 |
+
"model.layers.20.mlp.router.bias": "model-00007-of-00009.safetensors",
|
| 236 |
+
"model.layers.20.mlp.router.weight": "model-00007-of-00009.safetensors",
|
| 237 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
|
| 238 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00007-of-00009.safetensors",
|
| 239 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
|
| 240 |
+
"model.layers.20.self_attn.o_proj.bias": "model-00007-of-00009.safetensors",
|
| 241 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
|
| 242 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00007-of-00009.safetensors",
|
| 243 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
|
| 244 |
+
"model.layers.20.self_attn.sinks": "model-00007-of-00009.safetensors",
|
| 245 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00007-of-00009.safetensors",
|
| 246 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
|
| 247 |
+
"model.layers.21.input_layernorm.weight": "model-00008-of-00009.safetensors",
|
| 248 |
+
"model.layers.21.mlp.experts.down_proj": "model-00008-of-00009.safetensors",
|
| 249 |
+
"model.layers.21.mlp.experts.down_proj_bias": "model-00008-of-00009.safetensors",
|
| 250 |
+
"model.layers.21.mlp.experts.gate_up_proj": "model-00008-of-00009.safetensors",
|
| 251 |
+
"model.layers.21.mlp.experts.gate_up_proj_bias": "model-00008-of-00009.safetensors",
|
| 252 |
+
"model.layers.21.mlp.router.bias": "model-00008-of-00009.safetensors",
|
| 253 |
+
"model.layers.21.mlp.router.weight": "model-00008-of-00009.safetensors",
|
| 254 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
|
| 255 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00008-of-00009.safetensors",
|
| 256 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
|
| 257 |
+
"model.layers.21.self_attn.o_proj.bias": "model-00008-of-00009.safetensors",
|
| 258 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
|
| 259 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00008-of-00009.safetensors",
|
| 260 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
|
| 261 |
+
"model.layers.21.self_attn.sinks": "model-00008-of-00009.safetensors",
|
| 262 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00008-of-00009.safetensors",
|
| 263 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
|
| 264 |
+
"model.layers.22.input_layernorm.weight": "model-00008-of-00009.safetensors",
|
| 265 |
+
"model.layers.22.mlp.experts.down_proj": "model-00008-of-00009.safetensors",
|
| 266 |
+
"model.layers.22.mlp.experts.down_proj_bias": "model-00008-of-00009.safetensors",
|
| 267 |
+
"model.layers.22.mlp.experts.gate_up_proj": "model-00008-of-00009.safetensors",
|
| 268 |
+
"model.layers.22.mlp.experts.gate_up_proj_bias": "model-00008-of-00009.safetensors",
|
| 269 |
+
"model.layers.22.mlp.router.bias": "model-00008-of-00009.safetensors",
|
| 270 |
+
"model.layers.22.mlp.router.weight": "model-00008-of-00009.safetensors",
|
| 271 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
|
| 272 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00008-of-00009.safetensors",
|
| 273 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
|
| 274 |
+
"model.layers.22.self_attn.o_proj.bias": "model-00008-of-00009.safetensors",
|
| 275 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
|
| 276 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00008-of-00009.safetensors",
|
| 277 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
|
| 278 |
+
"model.layers.22.self_attn.sinks": "model-00008-of-00009.safetensors",
|
| 279 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00008-of-00009.safetensors",
|
| 280 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
|
| 281 |
+
"model.layers.23.input_layernorm.weight": "model-00009-of-00009.safetensors",
|
| 282 |
+
"model.layers.23.mlp.experts.down_proj": "model-00009-of-00009.safetensors",
|
| 283 |
+
"model.layers.23.mlp.experts.down_proj_bias": "model-00009-of-00009.safetensors",
|
| 284 |
+
"model.layers.23.mlp.experts.gate_up_proj": "model-00009-of-00009.safetensors",
|
| 285 |
+
"model.layers.23.mlp.experts.gate_up_proj_bias": "model-00009-of-00009.safetensors",
|
| 286 |
+
"model.layers.23.mlp.router.bias": "model-00008-of-00009.safetensors",
|
| 287 |
+
"model.layers.23.mlp.router.weight": "model-00008-of-00009.safetensors",
|
| 288 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
|
| 289 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00008-of-00009.safetensors",
|
| 290 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
|
| 291 |
+
"model.layers.23.self_attn.o_proj.bias": "model-00008-of-00009.safetensors",
|
| 292 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
|
| 293 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00008-of-00009.safetensors",
|
| 294 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
|
| 295 |
+
"model.layers.23.self_attn.sinks": "model-00008-of-00009.safetensors",
|
| 296 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00008-of-00009.safetensors",
|
| 297 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
|
| 298 |
+
"model.layers.3.input_layernorm.weight": "model-00002-of-00009.safetensors",
|
| 299 |
+
"model.layers.3.mlp.experts.down_proj": "model-00002-of-00009.safetensors",
|
| 300 |
+
"model.layers.3.mlp.experts.down_proj_bias": "model-00002-of-00009.safetensors",
|
| 301 |
+
"model.layers.3.mlp.experts.gate_up_proj": "model-00002-of-00009.safetensors",
|
| 302 |
+
"model.layers.3.mlp.experts.gate_up_proj_bias": "model-00002-of-00009.safetensors",
|
| 303 |
+
"model.layers.3.mlp.router.bias": "model-00002-of-00009.safetensors",
|
| 304 |
+
"model.layers.3.mlp.router.weight": "model-00002-of-00009.safetensors",
|
| 305 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
|
| 306 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00002-of-00009.safetensors",
|
| 307 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
|
| 308 |
+
"model.layers.3.self_attn.o_proj.bias": "model-00002-of-00009.safetensors",
|
| 309 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
|
| 310 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00002-of-00009.safetensors",
|
| 311 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
|
| 312 |
+
"model.layers.3.self_attn.sinks": "model-00002-of-00009.safetensors",
|
| 313 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00002-of-00009.safetensors",
|
| 314 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
|
| 315 |
+
"model.layers.4.input_layernorm.weight": "model-00002-of-00009.safetensors",
|
| 316 |
+
"model.layers.4.mlp.experts.down_proj": "model-00002-of-00009.safetensors",
|
| 317 |
+
"model.layers.4.mlp.experts.down_proj_bias": "model-00002-of-00009.safetensors",
|
| 318 |
+
"model.layers.4.mlp.experts.gate_up_proj": "model-00002-of-00009.safetensors",
|
| 319 |
+
"model.layers.4.mlp.experts.gate_up_proj_bias": "model-00002-of-00009.safetensors",
|
| 320 |
+
"model.layers.4.mlp.router.bias": "model-00002-of-00009.safetensors",
|
| 321 |
+
"model.layers.4.mlp.router.weight": "model-00002-of-00009.safetensors",
|
| 322 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
|
| 323 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00002-of-00009.safetensors",
|
| 324 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
|
| 325 |
+
"model.layers.4.self_attn.o_proj.bias": "model-00002-of-00009.safetensors",
|
| 326 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
|
| 327 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00002-of-00009.safetensors",
|
| 328 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
|
| 329 |
+
"model.layers.4.self_attn.sinks": "model-00002-of-00009.safetensors",
|
| 330 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00002-of-00009.safetensors",
|
| 331 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
|
| 332 |
+
"model.layers.5.input_layernorm.weight": "model-00003-of-00009.safetensors",
|
| 333 |
+
"model.layers.5.mlp.experts.down_proj": "model-00003-of-00009.safetensors",
|
| 334 |
+
"model.layers.5.mlp.experts.down_proj_bias": "model-00003-of-00009.safetensors",
|
| 335 |
+
"model.layers.5.mlp.experts.gate_up_proj": "model-00003-of-00009.safetensors",
|
| 336 |
+
"model.layers.5.mlp.experts.gate_up_proj_bias": "model-00003-of-00009.safetensors",
|
| 337 |
+
"model.layers.5.mlp.router.bias": "model-00002-of-00009.safetensors",
|
| 338 |
+
"model.layers.5.mlp.router.weight": "model-00002-of-00009.safetensors",
|
| 339 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
|
| 340 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00002-of-00009.safetensors",
|
| 341 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
|
| 342 |
+
"model.layers.5.self_attn.o_proj.bias": "model-00002-of-00009.safetensors",
|
| 343 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
|
| 344 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00002-of-00009.safetensors",
|
| 345 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
|
| 346 |
+
"model.layers.5.self_attn.sinks": "model-00002-of-00009.safetensors",
|
| 347 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00002-of-00009.safetensors",
|
| 348 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
|
| 349 |
+
"model.layers.6.input_layernorm.weight": "model-00003-of-00009.safetensors",
|
| 350 |
+
"model.layers.6.mlp.experts.down_proj": "model-00003-of-00009.safetensors",
|
| 351 |
+
"model.layers.6.mlp.experts.down_proj_bias": "model-00003-of-00009.safetensors",
|
| 352 |
+
"model.layers.6.mlp.experts.gate_up_proj": "model-00003-of-00009.safetensors",
|
| 353 |
+
"model.layers.6.mlp.experts.gate_up_proj_bias": "model-00003-of-00009.safetensors",
|
| 354 |
+
"model.layers.6.mlp.router.bias": "model-00003-of-00009.safetensors",
|
| 355 |
+
"model.layers.6.mlp.router.weight": "model-00003-of-00009.safetensors",
|
| 356 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
|
| 357 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00003-of-00009.safetensors",
|
| 358 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
|
| 359 |
+
"model.layers.6.self_attn.o_proj.bias": "model-00003-of-00009.safetensors",
|
| 360 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
|
| 361 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00003-of-00009.safetensors",
|
| 362 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
|
| 363 |
+
"model.layers.6.self_attn.sinks": "model-00003-of-00009.safetensors",
|
| 364 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00003-of-00009.safetensors",
|
| 365 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
|
| 366 |
+
"model.layers.7.input_layernorm.weight": "model-00003-of-00009.safetensors",
|
| 367 |
+
"model.layers.7.mlp.experts.down_proj": "model-00003-of-00009.safetensors",
|
| 368 |
+
"model.layers.7.mlp.experts.down_proj_bias": "model-00003-of-00009.safetensors",
|
| 369 |
+
"model.layers.7.mlp.experts.gate_up_proj": "model-00003-of-00009.safetensors",
|
| 370 |
+
"model.layers.7.mlp.experts.gate_up_proj_bias": "model-00003-of-00009.safetensors",
|
| 371 |
+
"model.layers.7.mlp.router.bias": "model-00003-of-00009.safetensors",
|
| 372 |
+
"model.layers.7.mlp.router.weight": "model-00003-of-00009.safetensors",
|
| 373 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
|
| 374 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00003-of-00009.safetensors",
|
| 375 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
|
| 376 |
+
"model.layers.7.self_attn.o_proj.bias": "model-00003-of-00009.safetensors",
|
| 377 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
|
| 378 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00003-of-00009.safetensors",
|
| 379 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
|
| 380 |
+
"model.layers.7.self_attn.sinks": "model-00003-of-00009.safetensors",
|
| 381 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00003-of-00009.safetensors",
|
| 382 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
|
| 383 |
+
"model.layers.8.input_layernorm.weight": "model-00004-of-00009.safetensors",
|
| 384 |
+
"model.layers.8.mlp.experts.down_proj": "model-00004-of-00009.safetensors",
|
| 385 |
+
"model.layers.8.mlp.experts.down_proj_bias": "model-00004-of-00009.safetensors",
|
| 386 |
+
"model.layers.8.mlp.experts.gate_up_proj": "model-00004-of-00009.safetensors",
|
| 387 |
+
"model.layers.8.mlp.experts.gate_up_proj_bias": "model-00004-of-00009.safetensors",
|
| 388 |
+
"model.layers.8.mlp.router.bias": "model-00003-of-00009.safetensors",
|
| 389 |
+
"model.layers.8.mlp.router.weight": "model-00003-of-00009.safetensors",
|
| 390 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
|
| 391 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00003-of-00009.safetensors",
|
| 392 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
|
| 393 |
+
"model.layers.8.self_attn.o_proj.bias": "model-00003-of-00009.safetensors",
|
| 394 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
|
| 395 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00003-of-00009.safetensors",
|
| 396 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
|
| 397 |
+
"model.layers.8.self_attn.sinks": "model-00003-of-00009.safetensors",
|
| 398 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00003-of-00009.safetensors",
|
| 399 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
|
| 400 |
+
"model.layers.9.input_layernorm.weight": "model-00004-of-00009.safetensors",
|
| 401 |
+
"model.layers.9.mlp.experts.down_proj": "model-00004-of-00009.safetensors",
|
| 402 |
+
"model.layers.9.mlp.experts.down_proj_bias": "model-00004-of-00009.safetensors",
|
| 403 |
+
"model.layers.9.mlp.experts.gate_up_proj": "model-00004-of-00009.safetensors",
|
| 404 |
+
"model.layers.9.mlp.experts.gate_up_proj_bias": "model-00004-of-00009.safetensors",
|
| 405 |
+
"model.layers.9.mlp.router.bias": "model-00004-of-00009.safetensors",
|
| 406 |
+
"model.layers.9.mlp.router.weight": "model-00004-of-00009.safetensors",
|
| 407 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
|
| 408 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00004-of-00009.safetensors",
|
| 409 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
|
| 410 |
+
"model.layers.9.self_attn.o_proj.bias": "model-00004-of-00009.safetensors",
|
| 411 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
|
| 412 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00004-of-00009.safetensors",
|
| 413 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
|
| 414 |
+
"model.layers.9.self_attn.sinks": "model-00004-of-00009.safetensors",
|
| 415 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00004-of-00009.safetensors",
|
| 416 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
|
| 417 |
+
"model.norm.weight": "model-00009-of-00009.safetensors"
|
| 418 |
+
}
|
| 419 |
+
}
|