Add files using upload-large-folder tool
Browse files- README.md +14 -28
- checkpoint-600/README.md +126 -0
- checkpoint-600/added_tokens.json +28 -0
- checkpoint-600/args.json +409 -0
- checkpoint-600/chat_template.jinja +120 -0
- checkpoint-600/config.json +68 -0
- checkpoint-600/generation_config.json +13 -0
- checkpoint-600/merges.txt +0 -0
- checkpoint-600/model-00001-of-00004.safetensors +3 -0
- checkpoint-600/model-00002-of-00004.safetensors +3 -0
- checkpoint-600/model-00003-of-00004.safetensors +3 -0
- checkpoint-600/model-00004-of-00004.safetensors +3 -0
- checkpoint-600/model.safetensors.index.json +758 -0
- checkpoint-600/preprocessor_config.json +21 -0
- checkpoint-600/special_tokens_map.json +31 -0
- checkpoint-600/tokenizer.json +3 -0
- checkpoint-600/tokenizer_config.json +240 -0
- checkpoint-600/trainer_state.json +1002 -0
- checkpoint-600/training_args.bin +3 -0
- checkpoint-600/video_preprocessor_config.json +41 -0
- checkpoint-600/vocab.json +0 -0
README.md
CHANGED
|
@@ -10,22 +10,24 @@ tags:
|
|
| 10 |
- sft
|
| 11 |
---
|
| 12 |
|
| 13 |
-
# EgoTools 8B v3.3
|
| 14 |
|
| 15 |
-
|
| 16 |
|
| 17 |
-
|
| 18 |
|
| 19 |
-
|
|
|
|
|
|
|
|
|
|
| 20 |
|
| 21 |
-
The
|
| 22 |
|
| 23 |
## Training Setup
|
| 24 |
|
| 25 |
| Field | Value |
|
| 26 |
|---|---:|
|
| 27 |
| Base model | `Qwen/Qwen3-VL-8B-Instruct` |
|
| 28 |
-
| Local base snapshot | `models--Qwen--Qwen3-VL-8B-Instruct/snapshots/0c351dd01ed87e9c1b53cbc748cba10e6187ff3b` |
|
| 29 |
| Framework | `ms-swift` / Transformers |
|
| 30 |
| Tuning type | Full-parameter SFT |
|
| 31 |
| Trainable params | 8.19B / 8.77B, VLM LLM trainable; ViT and aligner frozen |
|
|
@@ -38,7 +40,6 @@ The run was still in progress when this checkpoint was exported. Treat this as a
|
|
| 38 |
| Effective batch size | 128 samples |
|
| 39 |
| Epochs | 1 |
|
| 40 |
| Max steps | 907 |
|
| 41 |
-
| Saved step | 300 |
|
| 42 |
| Learning rate | `2.3e-6` |
|
| 43 |
| LR scheduler | `constant` |
|
| 44 |
| Warmup | 0 |
|
|
@@ -49,7 +50,7 @@ The run was still in progress when this checkpoint was exported. Treat this as a
|
|
| 49 |
| Image token budget | 1024 |
|
| 50 |
| Save interval | every 300 steps |
|
| 51 |
|
| 52 |
-
Important note: this run used a constant `2.3e-6` LR. Earlier V2 exploratory runs used `5e-6` with cosine decay and 3% warmup;
|
| 53 |
|
| 54 |
## Training Data
|
| 55 |
|
|
@@ -59,10 +60,6 @@ Main local training file:
|
|
| 59 |
|
| 60 |
`data_v3_3/egotools_v3_3_sft_final_clips.swift.jsonl`
|
| 61 |
|
| 62 |
-
Video references point to local clips under:
|
| 63 |
-
|
| 64 |
-
`data_v3_3/video_clips`
|
| 65 |
-
|
| 66 |
### Overall Mix
|
| 67 |
|
| 68 |
| Family | Rows | Ratio |
|
|
@@ -107,20 +104,9 @@ The MCQ portion was deterministically balanced by option count.
|
|
| 107 |
|
| 108 |
## Checkpoint Metrics
|
| 109 |
|
| 110 |
-
|
| 111 |
-
|
| 112 |
-
|
|
| 113 |
-
|-
|
| 114 |
-
| Global step | 300 / 907 |
|
| 115 |
-
| Epoch | 0.3309 |
|
| 116 |
-
| Recent logged loss at step 300 | 0.8521 |
|
| 117 |
-
| Token accuracy at step 300 | 0.7638 |
|
| 118 |
-
| Learning rate | 2.3e-6 |
|
| 119 |
-
| Reported memory | 38.56 GiB |
|
| 120 |
-
| Average training speed | 127.60 s/iter |
|
| 121 |
-
|
| 122 |
-
No evaluation set was run for this checkpoint.
|
| 123 |
-
|
| 124 |
-
## Intended Use
|
| 125 |
|
| 126 |
-
|
|
|
|
| 10 |
- sft
|
| 11 |
---
|
| 12 |
|
| 13 |
+
# EgoTools 8B v3.3
|
| 14 |
|
| 15 |
+
This repository stores intermediate checkpoints from full-parameter SFT of `Qwen/Qwen3-VL-8B-Instruct` on EgoTools v3.3.
|
| 16 |
|
| 17 |
+
Available checkpoints:
|
| 18 |
|
| 19 |
+
| Checkpoint | Location | Step | Epoch | Notes |
|
| 20 |
+
|---|---|---:|---:|---|
|
| 21 |
+
| checkpoint-300 | repository root | 300 / 907 | 0.3309 | First uploaded intermediate checkpoint. |
|
| 22 |
+
| checkpoint-600 | `checkpoint-600/` | 600 / 907 | 0.6619 | Second uploaded intermediate checkpoint. |
|
| 23 |
|
| 24 |
+
The repository root currently contains the `checkpoint-300` model files. `checkpoint-600` is stored in the `checkpoint-600/` subdirectory.
|
| 25 |
|
| 26 |
## Training Setup
|
| 27 |
|
| 28 |
| Field | Value |
|
| 29 |
|---|---:|
|
| 30 |
| Base model | `Qwen/Qwen3-VL-8B-Instruct` |
|
|
|
|
| 31 |
| Framework | `ms-swift` / Transformers |
|
| 32 |
| Tuning type | Full-parameter SFT |
|
| 33 |
| Trainable params | 8.19B / 8.77B, VLM LLM trainable; ViT and aligner frozen |
|
|
|
|
| 40 |
| Effective batch size | 128 samples |
|
| 41 |
| Epochs | 1 |
|
| 42 |
| Max steps | 907 |
|
|
|
|
| 43 |
| Learning rate | `2.3e-6` |
|
| 44 |
| LR scheduler | `constant` |
|
| 45 |
| Warmup | 0 |
|
|
|
|
| 50 |
| Image token budget | 1024 |
|
| 51 |
| Save interval | every 300 steps |
|
| 52 |
|
| 53 |
+
Important note: this run used a constant `2.3e-6` LR. Earlier V2 exploratory runs used `5e-6` with cosine decay and 3% warmup; these v3.3 checkpoints do not use that schedule.
|
| 54 |
|
| 55 |
## Training Data
|
| 56 |
|
|
|
|
| 60 |
|
| 61 |
`data_v3_3/egotools_v3_3_sft_final_clips.swift.jsonl`
|
| 62 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 63 |
### Overall Mix
|
| 64 |
|
| 65 |
| Family | Rows | Ratio |
|
|
|
|
| 104 |
|
| 105 |
## Checkpoint Metrics
|
| 106 |
|
| 107 |
+
| Checkpoint | Loss | Token accuracy | LR |
|
| 108 |
+
|---|---:|---:|---:|
|
| 109 |
+
| checkpoint-300 | 0.8521 | 0.7638 | 2.3e-6 |
|
| 110 |
+
| checkpoint-600 | 0.8500 | 0.7705 | 2.3e-6 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 111 |
|
| 112 |
+
No evaluation set was run for these intermediate checkpoints.
|
checkpoint-600/README.md
ADDED
|
@@ -0,0 +1,126 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Qwen/Qwen3-VL-8B-Instruct
|
| 3 |
+
library_name: transformers
|
| 4 |
+
pipeline_tag: image-text-to-text
|
| 5 |
+
tags:
|
| 6 |
+
- qwen3-vl
|
| 7 |
+
- video-language-model
|
| 8 |
+
- egocentric-video
|
| 9 |
+
- ms-swift
|
| 10 |
+
- sft
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
# EgoTools 8B v3.3 - Checkpoint 600
|
| 14 |
+
|
| 15 |
+
Intermediate checkpoint from full-parameter SFT of `Qwen/Qwen3-VL-8B-Instruct` on EgoTools v3.3.
|
| 16 |
+
|
| 17 |
+
This is `checkpoint-600` from the run:
|
| 18 |
+
|
| 19 |
+
`egotools_qwen3vl8b_v3_3_full_base_direct_8gpu_64f_bs2_acc8_20260505_235414`
|
| 20 |
+
|
| 21 |
+
The run was still in progress when this checkpoint was exported. Treat this as an intermediate model, not the final checkpoint.
|
| 22 |
+
|
| 23 |
+
## Training Setup
|
| 24 |
+
|
| 25 |
+
| Field | Value |
|
| 26 |
+
|---|---:|
|
| 27 |
+
| Base model | `Qwen/Qwen3-VL-8B-Instruct` |
|
| 28 |
+
| Local base snapshot | `models--Qwen--Qwen3-VL-8B-Instruct/snapshots/0c351dd01ed87e9c1b53cbc748cba10e6187ff3b` |
|
| 29 |
+
| Framework | `ms-swift` / Transformers |
|
| 30 |
+
| Tuning type | Full-parameter SFT |
|
| 31 |
+
| Trainable params | 8.19B / 8.77B, VLM LLM trainable; ViT and aligner frozen |
|
| 32 |
+
| GPUs | 8 x NVIDIA A100-SXM4-40GB |
|
| 33 |
+
| Precision | BF16 |
|
| 34 |
+
| DeepSpeed | ZeRO-3, no optimizer/parameter offload |
|
| 35 |
+
| Attention | FlashAttention |
|
| 36 |
+
| Per-device batch size | 2 |
|
| 37 |
+
| Gradient accumulation | 8 |
|
| 38 |
+
| Effective batch size | 128 samples |
|
| 39 |
+
| Epochs | 1 |
|
| 40 |
+
| Max steps | 907 |
|
| 41 |
+
| Saved step | 600 |
|
| 42 |
+
| Learning rate | `2.3e-6` |
|
| 43 |
+
| LR scheduler | `constant` |
|
| 44 |
+
| Warmup | 0 |
|
| 45 |
+
| Weight decay | 0.1 |
|
| 46 |
+
| Max sequence length | 8192 |
|
| 47 |
+
| Video frame sampling | up to 64 frames |
|
| 48 |
+
| Video token budget | 128 |
|
| 49 |
+
| Image token budget | 1024 |
|
| 50 |
+
| Save interval | every 300 steps |
|
| 51 |
+
|
| 52 |
+
Important note: this run used a constant `2.3e-6` LR. Earlier V2 exploratory runs used `5e-6` with cosine decay and 3% warmup; this checkpoint does not use that schedule.
|
| 53 |
+
|
| 54 |
+
## Training Data
|
| 55 |
+
|
| 56 |
+
Dataset: EgoTools v3.3 SFT, converted to ms-swift video-clip format.
|
| 57 |
+
|
| 58 |
+
Main local training file:
|
| 59 |
+
|
| 60 |
+
`data_v3_3/egotools_v3_3_sft_final_clips.swift.jsonl`
|
| 61 |
+
|
| 62 |
+
Video references point to local clips under:
|
| 63 |
+
|
| 64 |
+
`data_v3_3/video_clips`
|
| 65 |
+
|
| 66 |
+
### Overall Mix
|
| 67 |
+
|
| 68 |
+
| Family | Rows | Ratio |
|
| 69 |
+
|---|---:|---:|
|
| 70 |
+
| Multiple-choice QA | 104,613 | 90.16% |
|
| 71 |
+
| Caption / narration completion | 9,473 | 8.16% |
|
| 72 |
+
| Open-ended QA | 1,945 | 1.68% |
|
| 73 |
+
| Total | 116,031 | 100.00% |
|
| 74 |
+
|
| 75 |
+
### Sample Type Mix
|
| 76 |
+
|
| 77 |
+
| Sample type | Rows | Ratio |
|
| 78 |
+
|---|---:|---:|
|
| 79 |
+
| `mcq` | 63,276 | 54.53% |
|
| 80 |
+
| `narration_mcq` | 17,591 | 15.16% |
|
| 81 |
+
| `egoschema_caption_mcq` | 11,830 | 10.20% |
|
| 82 |
+
| `egoplan_next_action_mcq` | 7,990 | 6.89% |
|
| 83 |
+
| `caption_completion` | 7,532 | 6.49% |
|
| 84 |
+
| `egoschema_fused_mcq` | 3,926 | 3.38% |
|
| 85 |
+
| `egothink_open_qa` | 1,945 | 1.68% |
|
| 86 |
+
| `narration_completion` | 1,941 | 1.67% |
|
| 87 |
+
|
| 88 |
+
### Option / Answer Balance
|
| 89 |
+
|
| 90 |
+
The MCQ portion was deterministically balanced by option count.
|
| 91 |
+
|
| 92 |
+
| Option count | Answer distribution |
|
| 93 |
+
|---:|---|
|
| 94 |
+
| 4 options | A: 1,998; B: 1,997; C: 1,998; D: 1,997 |
|
| 95 |
+
| 5 options | A: 6,669; B: 6,669; C: 6,670; D: 6,669; E: 6,670 |
|
| 96 |
+
| 8 options | A: 7,910; B: 7,909; C: 7,910; D: 7,910; E: 7,909; F: 7,910; G: 7,909; H: 7,909 |
|
| 97 |
+
|
| 98 |
+
### Video Coverage
|
| 99 |
+
|
| 100 |
+
| Field | Value |
|
| 101 |
+
|---|---:|
|
| 102 |
+
| Unique video references | 362 |
|
| 103 |
+
| Unique generated clips | 13,100 |
|
| 104 |
+
| Missing video rows | 0 |
|
| 105 |
+
| Full train-video references | 92,572 |
|
| 106 |
+
| Train-segment clip references | 23,459 |
|
| 107 |
+
|
| 108 |
+
## Checkpoint Metrics
|
| 109 |
+
|
| 110 |
+
At `checkpoint-600`:
|
| 111 |
+
|
| 112 |
+
| Metric | Value |
|
| 113 |
+
|---|---:|
|
| 114 |
+
| Global step | 600 / 907 |
|
| 115 |
+
| Epoch | 0.6619 |
|
| 116 |
+
| Recent logged loss at step 600 | 0.8500 |
|
| 117 |
+
| Token accuracy at step 600 | 0.7705 |
|
| 118 |
+
| Learning rate | 2.3e-6 |
|
| 119 |
+
| Reported memory | 38.56 GiB |
|
| 120 |
+
| Average training speed | ~127.5 s/iter |
|
| 121 |
+
|
| 122 |
+
No evaluation set was run for this checkpoint.
|
| 123 |
+
|
| 124 |
+
## Intended Use
|
| 125 |
+
|
| 126 |
+
This checkpoint is intended for internal EgoTools experiments and checkpoint-level comparison. It is not a final released model.
|
checkpoint-600/added_tokens.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</think>": 151668,
|
| 3 |
+
"</tool_call>": 151658,
|
| 4 |
+
"</tool_response>": 151666,
|
| 5 |
+
"<think>": 151667,
|
| 6 |
+
"<tool_call>": 151657,
|
| 7 |
+
"<tool_response>": 151665,
|
| 8 |
+
"<|box_end|>": 151649,
|
| 9 |
+
"<|box_start|>": 151648,
|
| 10 |
+
"<|endoftext|>": 151643,
|
| 11 |
+
"<|file_sep|>": 151664,
|
| 12 |
+
"<|fim_middle|>": 151660,
|
| 13 |
+
"<|fim_pad|>": 151662,
|
| 14 |
+
"<|fim_prefix|>": 151659,
|
| 15 |
+
"<|fim_suffix|>": 151661,
|
| 16 |
+
"<|im_end|>": 151645,
|
| 17 |
+
"<|im_start|>": 151644,
|
| 18 |
+
"<|image_pad|>": 151655,
|
| 19 |
+
"<|object_ref_end|>": 151647,
|
| 20 |
+
"<|object_ref_start|>": 151646,
|
| 21 |
+
"<|quad_end|>": 151651,
|
| 22 |
+
"<|quad_start|>": 151650,
|
| 23 |
+
"<|repo_name|>": 151663,
|
| 24 |
+
"<|video_pad|>": 151656,
|
| 25 |
+
"<|vision_end|>": 151653,
|
| 26 |
+
"<|vision_pad|>": 151654,
|
| 27 |
+
"<|vision_start|>": 151652
|
| 28 |
+
}
|
checkpoint-600/args.json
ADDED
|
@@ -0,0 +1,409 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"output_dir": "/mnt/raid10/sltian/egotools_dev_data/workspace/ms-swift/output/egotools_qwen3vl8b_v3_3_full_base_direct_8gpu_64f_bs2_acc8_20260505_235414",
|
| 3 |
+
"overwrite_output_dir": false,
|
| 4 |
+
"do_train": false,
|
| 5 |
+
"do_eval": false,
|
| 6 |
+
"do_predict": false,
|
| 7 |
+
"eval_strategy": "no",
|
| 8 |
+
"prediction_loss_only": false,
|
| 9 |
+
"per_device_train_batch_size": 2,
|
| 10 |
+
"per_device_eval_batch_size": 1,
|
| 11 |
+
"per_gpu_train_batch_size": null,
|
| 12 |
+
"per_gpu_eval_batch_size": null,
|
| 13 |
+
"gradient_accumulation_steps": 8,
|
| 14 |
+
"eval_accumulation_steps": null,
|
| 15 |
+
"eval_delay": 0,
|
| 16 |
+
"torch_empty_cache_steps": null,
|
| 17 |
+
"learning_rate": 2.3e-06,
|
| 18 |
+
"weight_decay": 0.1,
|
| 19 |
+
"adam_beta1": 0.9,
|
| 20 |
+
"adam_beta2": 0.95,
|
| 21 |
+
"adam_epsilon": 1e-08,
|
| 22 |
+
"max_grad_norm": 1.0,
|
| 23 |
+
"num_train_epochs": 1.0,
|
| 24 |
+
"max_steps": -1,
|
| 25 |
+
"lr_scheduler_type": "constant",
|
| 26 |
+
"lr_scheduler_kwargs": null,
|
| 27 |
+
"warmup_ratio": 0.0,
|
| 28 |
+
"warmup_steps": 0,
|
| 29 |
+
"log_level": "passive",
|
| 30 |
+
"log_level_replica": "warning",
|
| 31 |
+
"log_on_each_node": true,
|
| 32 |
+
"logging_dir": "/mnt/raid10/sltian/egotools_dev_data/workspace/ms-swift/output/egotools_qwen3vl8b_v3_3_full_base_direct_8gpu_64f_bs2_acc8_20260505_235414/runs",
|
| 33 |
+
"logging_strategy": "steps",
|
| 34 |
+
"logging_first_step": true,
|
| 35 |
+
"logging_steps": 5,
|
| 36 |
+
"logging_nan_inf_filter": true,
|
| 37 |
+
"save_strategy": "steps",
|
| 38 |
+
"save_steps": 300.0,
|
| 39 |
+
"save_total_limit": 4,
|
| 40 |
+
"save_safetensors": true,
|
| 41 |
+
"save_on_each_node": false,
|
| 42 |
+
"save_only_model": true,
|
| 43 |
+
"restore_callback_states_from_checkpoint": false,
|
| 44 |
+
"no_cuda": false,
|
| 45 |
+
"use_cpu": false,
|
| 46 |
+
"use_mps_device": false,
|
| 47 |
+
"seed": 42,
|
| 48 |
+
"data_seed": 42,
|
| 49 |
+
"jit_mode_eval": false,
|
| 50 |
+
"bf16": true,
|
| 51 |
+
"fp16": false,
|
| 52 |
+
"fp16_opt_level": "O1",
|
| 53 |
+
"half_precision_backend": "auto",
|
| 54 |
+
"bf16_full_eval": false,
|
| 55 |
+
"fp16_full_eval": false,
|
| 56 |
+
"tf32": null,
|
| 57 |
+
"local_rank": 0,
|
| 58 |
+
"ddp_backend": null,
|
| 59 |
+
"tpu_num_cores": null,
|
| 60 |
+
"tpu_metrics_debug": false,
|
| 61 |
+
"debug": null,
|
| 62 |
+
"dataloader_drop_last": false,
|
| 63 |
+
"eval_steps": 300.0,
|
| 64 |
+
"dataloader_num_workers": 8,
|
| 65 |
+
"dataloader_prefetch_factor": null,
|
| 66 |
+
"past_index": -1,
|
| 67 |
+
"run_name": "/mnt/raid10/sltian/egotools_dev_data/workspace/ms-swift/output/egotools_qwen3vl8b_v3_3_full_base_direct_8gpu_64f_bs2_acc8_20260505_235414",
|
| 68 |
+
"disable_tqdm": null,
|
| 69 |
+
"remove_unused_columns": true,
|
| 70 |
+
"label_names": null,
|
| 71 |
+
"load_best_model_at_end": false,
|
| 72 |
+
"metric_for_best_model": "loss",
|
| 73 |
+
"greater_is_better": false,
|
| 74 |
+
"ignore_data_skip": false,
|
| 75 |
+
"fsdp": [],
|
| 76 |
+
"fsdp_min_num_params": 0,
|
| 77 |
+
"fsdp_config": null,
|
| 78 |
+
"fsdp_transformer_layer_cls_to_wrap": null,
|
| 79 |
+
"accelerator_config": {
|
| 80 |
+
"dispatch_batches": false
|
| 81 |
+
},
|
| 82 |
+
"parallelism_config": null,
|
| 83 |
+
"deepspeed": {
|
| 84 |
+
"fp16": {
|
| 85 |
+
"enabled": "auto",
|
| 86 |
+
"loss_scale": 0,
|
| 87 |
+
"loss_scale_window": 1000,
|
| 88 |
+
"initial_scale_power": 16,
|
| 89 |
+
"hysteresis": 2,
|
| 90 |
+
"min_loss_scale": 1
|
| 91 |
+
},
|
| 92 |
+
"bf16": {
|
| 93 |
+
"enabled": "auto"
|
| 94 |
+
},
|
| 95 |
+
"zero_optimization": {
|
| 96 |
+
"stage": 3,
|
| 97 |
+
"offload_optimizer": {
|
| 98 |
+
"device": "none",
|
| 99 |
+
"pin_memory": true
|
| 100 |
+
},
|
| 101 |
+
"offload_param": {
|
| 102 |
+
"device": "none",
|
| 103 |
+
"pin_memory": true
|
| 104 |
+
},
|
| 105 |
+
"overlap_comm": false,
|
| 106 |
+
"contiguous_gradients": true,
|
| 107 |
+
"sub_group_size": 1000000000.0,
|
| 108 |
+
"reduce_bucket_size": "auto",
|
| 109 |
+
"zero_quantized_weights": false,
|
| 110 |
+
"zero_quantized_gradients": false,
|
| 111 |
+
"stage3_prefetch_bucket_size": "auto",
|
| 112 |
+
"stage3_param_persistence_threshold": "auto",
|
| 113 |
+
"stage3_max_live_parameters": 1000000000.0,
|
| 114 |
+
"stage3_max_reuse_distance": 1000000000.0,
|
| 115 |
+
"stage3_gather_16bit_weights_on_model_save": true
|
| 116 |
+
},
|
| 117 |
+
"gradient_accumulation_steps": "auto",
|
| 118 |
+
"gradient_clipping": "auto",
|
| 119 |
+
"steps_per_print": 2000,
|
| 120 |
+
"train_batch_size": "auto",
|
| 121 |
+
"train_micro_batch_size_per_gpu": "auto",
|
| 122 |
+
"wall_clock_breakdown": false
|
| 123 |
+
},
|
| 124 |
+
"label_smoothing_factor": 0.0,
|
| 125 |
+
"optim": "adamw_torch",
|
| 126 |
+
"optim_args": null,
|
| 127 |
+
"adafactor": false,
|
| 128 |
+
"group_by_length": false,
|
| 129 |
+
"length_column_name": "length",
|
| 130 |
+
"report_to": [
|
| 131 |
+
"tensorboard"
|
| 132 |
+
],
|
| 133 |
+
"project": "huggingface",
|
| 134 |
+
"trackio_space_id": "trackio",
|
| 135 |
+
"ddp_find_unused_parameters": null,
|
| 136 |
+
"ddp_bucket_cap_mb": null,
|
| 137 |
+
"ddp_broadcast_buffers": null,
|
| 138 |
+
"dataloader_pin_memory": true,
|
| 139 |
+
"dataloader_persistent_workers": false,
|
| 140 |
+
"skip_memory_metrics": true,
|
| 141 |
+
"use_legacy_prediction_loop": false,
|
| 142 |
+
"push_to_hub": false,
|
| 143 |
+
"resume_from_checkpoint": null,
|
| 144 |
+
"hub_model_id": null,
|
| 145 |
+
"hub_strategy": "every_save",
|
| 146 |
+
"hub_token": null,
|
| 147 |
+
"hub_private_repo": null,
|
| 148 |
+
"hub_always_push": false,
|
| 149 |
+
"hub_revision": null,
|
| 150 |
+
"gradient_checkpointing": true,
|
| 151 |
+
"gradient_checkpointing_kwargs": null,
|
| 152 |
+
"include_inputs_for_metrics": false,
|
| 153 |
+
"include_for_metrics": [],
|
| 154 |
+
"eval_do_concat_batches": true,
|
| 155 |
+
"fp16_backend": "auto",
|
| 156 |
+
"push_to_hub_model_id": null,
|
| 157 |
+
"push_to_hub_organization": null,
|
| 158 |
+
"push_to_hub_token": null,
|
| 159 |
+
"mp_parameters": "",
|
| 160 |
+
"auto_find_batch_size": false,
|
| 161 |
+
"full_determinism": false,
|
| 162 |
+
"torchdynamo": null,
|
| 163 |
+
"ray_scope": "last",
|
| 164 |
+
"ddp_timeout": 18000000,
|
| 165 |
+
"torch_compile": false,
|
| 166 |
+
"torch_compile_backend": null,
|
| 167 |
+
"torch_compile_mode": null,
|
| 168 |
+
"include_tokens_per_second": false,
|
| 169 |
+
"include_num_input_tokens_seen": false,
|
| 170 |
+
"neftune_noise_alpha": null,
|
| 171 |
+
"optim_target_modules": null,
|
| 172 |
+
"batch_eval_metrics": false,
|
| 173 |
+
"eval_on_start": false,
|
| 174 |
+
"use_liger_kernel": false,
|
| 175 |
+
"liger_kernel_config": null,
|
| 176 |
+
"eval_use_gather_object": false,
|
| 177 |
+
"average_tokens_across_devices": true,
|
| 178 |
+
"sortish_sampler": false,
|
| 179 |
+
"predict_with_generate": false,
|
| 180 |
+
"generation_max_length": null,
|
| 181 |
+
"generation_num_beams": null,
|
| 182 |
+
"generation_config": null,
|
| 183 |
+
"tuner_backend": "peft",
|
| 184 |
+
"vit_gradient_checkpointing": false,
|
| 185 |
+
"router_aux_loss_coef": 0.0,
|
| 186 |
+
"enable_dft_loss": false,
|
| 187 |
+
"enable_channel_loss": false,
|
| 188 |
+
"safe_serialization": true,
|
| 189 |
+
"max_shard_size": "5GB",
|
| 190 |
+
"check_model": true,
|
| 191 |
+
"acc_strategy": "token",
|
| 192 |
+
"train_dataloader_shuffle": true,
|
| 193 |
+
"max_epochs": null,
|
| 194 |
+
"aligner_lr": null,
|
| 195 |
+
"vit_lr": null,
|
| 196 |
+
"use_logits_to_keep": null,
|
| 197 |
+
"ds3_gather_for_generation": true,
|
| 198 |
+
"resume_only_model": false,
|
| 199 |
+
"optimizer": null,
|
| 200 |
+
"loss_type": null,
|
| 201 |
+
"eval_metric": null,
|
| 202 |
+
"callbacks": [],
|
| 203 |
+
"early_stop_interval": null,
|
| 204 |
+
"eval_use_evalscope": false,
|
| 205 |
+
"eval_dataset": [],
|
| 206 |
+
"eval_dataset_args": null,
|
| 207 |
+
"eval_limit": null,
|
| 208 |
+
"eval_generation_config": null,
|
| 209 |
+
"extra_eval_args": null,
|
| 210 |
+
"tuner_type": "full",
|
| 211 |
+
"use_galore": false,
|
| 212 |
+
"galore_target_modules": null,
|
| 213 |
+
"galore_rank": 128,
|
| 214 |
+
"galore_update_proj_gap": 50,
|
| 215 |
+
"galore_scale": 1.0,
|
| 216 |
+
"galore_proj_type": "std",
|
| 217 |
+
"galore_optim_per_parameter": false,
|
| 218 |
+
"galore_with_embedding": false,
|
| 219 |
+
"galore_quantization": false,
|
| 220 |
+
"galore_proj_quant": false,
|
| 221 |
+
"galore_proj_bits": 4,
|
| 222 |
+
"galore_proj_group_size": 256,
|
| 223 |
+
"galore_cos_threshold": 0.4,
|
| 224 |
+
"galore_gamma_proj": 2,
|
| 225 |
+
"galore_queue_size": 5,
|
| 226 |
+
"lisa_activated_layers": 0,
|
| 227 |
+
"lisa_step_interval": 20,
|
| 228 |
+
"use_flash_ckpt": false,
|
| 229 |
+
"use_ray": false,
|
| 230 |
+
"ray_exp_name": null,
|
| 231 |
+
"device_groups": null,
|
| 232 |
+
"model": "/home/sltian/.cache/huggingface/hub/models--Qwen--Qwen3-VL-8B-Instruct/snapshots/0c351dd01ed87e9c1b53cbc748cba10e6187ff3b",
|
| 233 |
+
"model_type": "qwen3_vl",
|
| 234 |
+
"model_revision": null,
|
| 235 |
+
"task_type": "causal_lm",
|
| 236 |
+
"torch_dtype": "bfloat16",
|
| 237 |
+
"attn_impl": "flash_attn",
|
| 238 |
+
"experts_impl": null,
|
| 239 |
+
"new_special_tokens": [],
|
| 240 |
+
"num_labels": null,
|
| 241 |
+
"problem_type": null,
|
| 242 |
+
"rope_scaling": null,
|
| 243 |
+
"device_map": null,
|
| 244 |
+
"max_memory": {},
|
| 245 |
+
"max_model_len": null,
|
| 246 |
+
"local_repo_path": null,
|
| 247 |
+
"init_strategy": null,
|
| 248 |
+
"template": "qwen3_vl",
|
| 249 |
+
"system": null,
|
| 250 |
+
"max_length": 8192,
|
| 251 |
+
"truncation_strategy": "delete",
|
| 252 |
+
"max_pixels": null,
|
| 253 |
+
"agent_template": null,
|
| 254 |
+
"norm_bbox": null,
|
| 255 |
+
"use_chat_template": true,
|
| 256 |
+
"padding_side": "right",
|
| 257 |
+
"padding_free": false,
|
| 258 |
+
"loss_scale": "default",
|
| 259 |
+
"sequence_parallel_size": 1,
|
| 260 |
+
"template_backend": "swift",
|
| 261 |
+
"response_prefix": null,
|
| 262 |
+
"enable_thinking": null,
|
| 263 |
+
"add_non_thinking_prefix": true,
|
| 264 |
+
"dataset": [
|
| 265 |
+
"/mnt/raid10/sltian/egotools_dev_data/workspace/ms-swift/data_v3_3/egotools_v3_3_sft_final_clips.swift.jsonl"
|
| 266 |
+
],
|
| 267 |
+
"val_dataset": [],
|
| 268 |
+
"cached_dataset": [],
|
| 269 |
+
"cached_val_dataset": [],
|
| 270 |
+
"split_dataset_ratio": 0.0,
|
| 271 |
+
"dataset_num_proc": 16,
|
| 272 |
+
"load_from_cache_file": false,
|
| 273 |
+
"dataset_shuffle": true,
|
| 274 |
+
"val_dataset_shuffle": false,
|
| 275 |
+
"streaming": false,
|
| 276 |
+
"interleave_prob": null,
|
| 277 |
+
"stopping_strategy": "first_exhausted",
|
| 278 |
+
"shuffle_buffer_size": 1000,
|
| 279 |
+
"download_mode": "reuse_dataset_if_exists",
|
| 280 |
+
"columns": {},
|
| 281 |
+
"strict": false,
|
| 282 |
+
"disable_auto_column_mapping": false,
|
| 283 |
+
"model_name": null,
|
| 284 |
+
"model_author": null,
|
| 285 |
+
"custom_dataset_info": [],
|
| 286 |
+
"quant_method": null,
|
| 287 |
+
"quant_bits": null,
|
| 288 |
+
"hqq_axis": null,
|
| 289 |
+
"bnb_4bit_compute_dtype": "bfloat16",
|
| 290 |
+
"bnb_4bit_quant_type": "nf4",
|
| 291 |
+
"bnb_4bit_use_double_quant": true,
|
| 292 |
+
"bnb_4bit_quant_storage": null,
|
| 293 |
+
"max_new_tokens": 64,
|
| 294 |
+
"temperature": 0.0,
|
| 295 |
+
"top_k": null,
|
| 296 |
+
"top_p": null,
|
| 297 |
+
"repetition_penalty": null,
|
| 298 |
+
"num_beams": 1,
|
| 299 |
+
"stream": false,
|
| 300 |
+
"stop_words": [],
|
| 301 |
+
"logprobs": false,
|
| 302 |
+
"top_logprobs": null,
|
| 303 |
+
"structured_outputs_regex": null,
|
| 304 |
+
"adapters": [],
|
| 305 |
+
"external_plugins": [],
|
| 306 |
+
"custom_register_path": [],
|
| 307 |
+
"model_kwargs": {},
|
| 308 |
+
"enable_npu_model_patch": true,
|
| 309 |
+
"load_args": false,
|
| 310 |
+
"load_data_args": false,
|
| 311 |
+
"packing": false,
|
| 312 |
+
"packing_length": null,
|
| 313 |
+
"packing_num_proc": 1,
|
| 314 |
+
"lazy_tokenize": true,
|
| 315 |
+
"use_hf": false,
|
| 316 |
+
"ignore_args_error": false,
|
| 317 |
+
"use_swift_lora": false,
|
| 318 |
+
"freeze_parameters": [
|
| 319 |
+
"model.visual",
|
| 320 |
+
"model.visual.merger",
|
| 321 |
+
"model.visual.deepstack_merger_list"
|
| 322 |
+
],
|
| 323 |
+
"freeze_parameters_regex": null,
|
| 324 |
+
"freeze_parameters_ratio": 0.0,
|
| 325 |
+
"trainable_parameters": [],
|
| 326 |
+
"trainable_parameters_regex": null,
|
| 327 |
+
"freeze_llm": false,
|
| 328 |
+
"freeze_vit": true,
|
| 329 |
+
"freeze_aligner": true,
|
| 330 |
+
"target_modules": [
|
| 331 |
+
"all-linear"
|
| 332 |
+
],
|
| 333 |
+
"target_regex": null,
|
| 334 |
+
"target_parameters": null,
|
| 335 |
+
"modules_to_save": [],
|
| 336 |
+
"lora_rank": 8,
|
| 337 |
+
"lora_alpha": 32,
|
| 338 |
+
"lora_dropout": 0.05,
|
| 339 |
+
"lora_bias": "none",
|
| 340 |
+
"lora_dtype": null,
|
| 341 |
+
"lorap_lr_ratio": null,
|
| 342 |
+
"use_rslora": false,
|
| 343 |
+
"use_dora": false,
|
| 344 |
+
"lora_ga_batch_size": 2,
|
| 345 |
+
"lora_ga_iters": 2,
|
| 346 |
+
"lora_ga_max_length": 1024,
|
| 347 |
+
"lora_ga_direction": "ArB2r",
|
| 348 |
+
"lora_ga_scale": "stable",
|
| 349 |
+
"lora_ga_stable_gamma": 16,
|
| 350 |
+
"init_weights": true,
|
| 351 |
+
"fourier_n_frequency": 2000,
|
| 352 |
+
"fourier_scaling": 300.0,
|
| 353 |
+
"boft_block_size": 4,
|
| 354 |
+
"boft_block_num": 0,
|
| 355 |
+
"boft_n_butterfly_factor": 1,
|
| 356 |
+
"boft_dropout": 0.0,
|
| 357 |
+
"vera_rank": 256,
|
| 358 |
+
"vera_projection_prng_key": 0,
|
| 359 |
+
"vera_dropout": 0.0,
|
| 360 |
+
"vera_d_initial": 0.1,
|
| 361 |
+
"adapter_act": "gelu",
|
| 362 |
+
"adapter_length": 128,
|
| 363 |
+
"adalora_target_r": 8,
|
| 364 |
+
"adalora_init_r": 12,
|
| 365 |
+
"adalora_tinit": 0,
|
| 366 |
+
"adalora_tfinal": 0,
|
| 367 |
+
"adalora_deltaT": 1,
|
| 368 |
+
"adalora_beta1": 0.85,
|
| 369 |
+
"adalora_beta2": 0.85,
|
| 370 |
+
"adalora_orth_reg_weight": 0.5,
|
| 371 |
+
"llamapro_num_new_blocks": 4,
|
| 372 |
+
"llamapro_num_groups": null,
|
| 373 |
+
"reft_layer_key": null,
|
| 374 |
+
"reft_layers": null,
|
| 375 |
+
"reft_rank": 4,
|
| 376 |
+
"reft_intervention_type": "LoreftIntervention",
|
| 377 |
+
"reft_args": null,
|
| 378 |
+
"swanlab_token": null,
|
| 379 |
+
"swanlab_project": "ms-swift",
|
| 380 |
+
"swanlab_workspace": null,
|
| 381 |
+
"swanlab_exp_name": null,
|
| 382 |
+
"swanlab_notification_method": null,
|
| 383 |
+
"swanlab_webhook_url": null,
|
| 384 |
+
"swanlab_secret": null,
|
| 385 |
+
"swanlab_sender_email": null,
|
| 386 |
+
"swanlab_receiver_email": null,
|
| 387 |
+
"swanlab_smtp_server": null,
|
| 388 |
+
"swanlab_smtp_port": null,
|
| 389 |
+
"swanlab_email_language": "zh",
|
| 390 |
+
"swanlab_mode": "cloud",
|
| 391 |
+
"add_version": false,
|
| 392 |
+
"create_checkpoint_symlink": false,
|
| 393 |
+
"zero_hpz_partition_size": null,
|
| 394 |
+
"deepspeed_autotp_size": null,
|
| 395 |
+
"swift_version": "4.2.0.dev0",
|
| 396 |
+
"ckpt_dir": null,
|
| 397 |
+
"rank": 0,
|
| 398 |
+
"global_world_size": 8,
|
| 399 |
+
"local_world_size": 8,
|
| 400 |
+
"model_suffix": "Qwen3-VL-8B-Instruct",
|
| 401 |
+
"model_info": "ModelInfo(model_type='qwen3_vl', model_dir='/home/sltian/.cache/huggingface/hub/models--Qwen--Qwen3-VL-8B-Instruct/snapshots/0c351dd01ed87e9c1b53cbc748cba10e6187ff3b', torch_dtype=torch.bfloat16, max_model_len=262144, quant_method=None, quant_bits=None, rope_scaling={'mrope_interleaved': True, 'mrope_section': [24, 20, 20], 'rope_type': 'default'}, is_moe_model=False, is_multimodal=True, config=None, task_type='causal_lm', num_labels=None)",
|
| 402 |
+
"model_meta": "ModelMeta(model_type='qwen3_vl', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3-VL-2B-Instruct', hf_model_id='Qwen/Qwen3-VL-2B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-2B-Thinking', hf_model_id='Qwen/Qwen3-VL-2B-Thinking', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-2B-Instruct-FP8', hf_model_id='Qwen/Qwen3-VL-2B-Instruct-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-2B-Thinking-FP8', hf_model_id='Qwen/Qwen3-VL-2B-Thinking-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-4B-Instruct', hf_model_id='Qwen/Qwen3-VL-4B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-4B-Thinking', hf_model_id='Qwen/Qwen3-VL-4B-Thinking', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-4B-Instruct-FP8', hf_model_id='Qwen/Qwen3-VL-4B-Instruct-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-4B-Thinking-FP8', hf_model_id='Qwen/Qwen3-VL-4B-Thinking-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-8B-Instruct', hf_model_id='Qwen/Qwen3-VL-8B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-8B-Thinking', hf_model_id='Qwen/Qwen3-VL-8B-Thinking', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-8B-Instruct-FP8', hf_model_id='Qwen/Qwen3-VL-8B-Instruct-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-8B-Thinking-FP8', hf_model_id='Qwen/Qwen3-VL-8B-Thinking-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-32B-Instruct', hf_model_id='Qwen/Qwen3-VL-32B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-32B-Thinking', hf_model_id='Qwen/Qwen3-VL-32B-Thinking', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-32B-Instruct-FP8', hf_model_id='Qwen/Qwen3-VL-32B-Instruct-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-32B-Thinking-FP8', hf_model_id='Qwen/Qwen3-VL-32B-Thinking-FP8', model_path=None, ms_revision=None, hf_revision=None)], template='qwen3_vl', ignore_patterns=None, requires=None, tags=[])], loader=<class 'swift.model.models.qwen.Qwen3VLLoader'>, template='qwen3_vl', model_arch=MultiModelKeys(arch_name='qwen3_vl', embedding=None, module_list=None, lm_head=None, q_proj=None, k_proj=None, v_proj=None, o_proj=None, attention=None, mlp=None, down_proj=None, qkv_proj=None, qk_proj=None, qa_proj=None, qb_proj=None, kv_proj=None, kva_proj=None, kvb_proj=None, language_model=['model.language_model', 'lm_head'], aligner=['model.visual.merger', 'model.visual.deepstack_merger_list'], vision_tower=['model.visual'], generator=[]), mcore_model_type=None, architectures=['Qwen3VLForConditionalGeneration'], additional_saved_files=[], torch_dtype=None, is_multimodal=True, is_reward=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.57', 'qwen_vl_utils>=0.0.14', 'decord'], tags=[])",
|
| 403 |
+
"model_dir": "/home/sltian/.cache/huggingface/hub/models--Qwen--Qwen3-VL-8B-Instruct/snapshots/0c351dd01ed87e9c1b53cbc748cba10e6187ff3b",
|
| 404 |
+
"template_meta": "QwenTemplateMeta(template_type='qwen3_vl', prefix=[], prompt=['<|im_start|>user\\n{{QUERY}}<|im_end|>\\n<|im_start|>assistant\\n'], chat_sep=['<|im_end|>\\n'], suffix=['<|im_end|>\\n'], template_cls=<class 'swift.template.templates.qwen.Qwen3VLTemplate'>, system_prefix=['<|im_start|>system\\n{{SYSTEM}}<|im_end|>\\n'], default_system=None, auto_add_bos=False, stop_words=['<|endoftext|>'], agent_template='hermes', is_thinking=False, thinking_prefix='<think>\\n', non_thinking_prefix='', history_thinking_prefix='')",
|
| 405 |
+
"_val_dataset_exists": false,
|
| 406 |
+
"hub": "<class 'swift.hub.hub.MSHub'>",
|
| 407 |
+
"evaluation_strategy": "steps",
|
| 408 |
+
"training_args": "Seq2SeqTrainingArguments(output_dir='/mnt/raid10/sltian/egotools_dev_data/workspace/ms-swift/output/egotools_qwen3vl8b_v3_3_full_base_direct_8gpu_64f_bs2_acc8_20260505_235414', overwrite_output_dir=False, do_train=False, do_eval=False, do_predict=False, eval_strategy=<IntervalStrategy.NO: 'no'>, prediction_loss_only=False, per_device_train_batch_size=2, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=8, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=2.3e-06, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=1.0, max_steps=-1, lr_scheduler_type=<SchedulerType.CONSTANT: 'constant'>, lr_scheduler_kwargs=None, warmup_ratio=0.0, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/mnt/raid10/sltian/egotools_dev_data/workspace/ms-swift/output/egotools_qwen3vl8b_v3_3_full_base_direct_8gpu_64f_bs2_acc8_20260505_235414/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=300, save_total_limit=4, save_safetensors=True, save_on_each_node=False, save_only_model=True, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=300.0, dataloader_num_workers=8, dataloader_prefetch_factor=2, past_index=-1, run_name='/mnt/raid10/sltian/egotools_dev_data/workspace/ms-swift/output/egotools_qwen3vl8b_v3_3_full_base_direct_8gpu_64f_bs2_acc8_20260505_235414', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), parallelism_config=None, deepspeed={'fp16': {'enabled': 'auto', 'loss_scale': 0, 'loss_scale_window': 1000, 'initial_scale_power': 16, 'hysteresis': 2, 'min_loss_scale': 1}, 'bf16': {'enabled': 'auto'}, 'zero_optimization': {'stage': 3, 'offload_optimizer': {'device': 'none', 'pin_memory': True}, 'offload_param': {'device': 'none', 'pin_memory': True}, 'overlap_comm': False, 'contiguous_gradients': True, 'sub_group_size': 1000000000.0, 'reduce_bucket_size': 'auto', 'zero_quantized_weights': False, 'zero_quantized_gradients': False, 'stage3_prefetch_bucket_size': 'auto', 'stage3_param_persistence_threshold': 'auto', 'stage3_max_live_parameters': 1000000000.0, 'stage3_max_reuse_distance': 1000000000.0, 'stage3_gather_16bit_weights_on_model_save': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': 2000, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False}, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH: 'adamw_torch'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], project='huggingface', trackio_space_id='trackio', ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=None, hub_always_push=False, hub_revision=None, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=18000000, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, include_tokens_per_second=None, include_num_input_tokens_seen=None, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, liger_kernel_config=None, eval_use_gather_object=False, average_tokens_across_devices=None, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=None, tuner_backend='peft', vit_gradient_checkpointing=False, router_aux_loss_coef=0.0, enable_dft_loss=False, enable_channel_loss=False, safe_serialization=True, max_shard_size='5GB', check_model=True, acc_strategy='token', train_dataloader_shuffle=True, max_epochs=None, aligner_lr=None, vit_lr=None, use_logits_to_keep=None, ds3_gather_for_generation=True, resume_only_model=False, optimizer=None, loss_type=None, eval_metric=None, callbacks=[], early_stop_interval=None, eval_use_evalscope=False, eval_dataset=[], eval_dataset_args=None, eval_limit=None, eval_generation_config=None, extra_eval_args=None, tuner_type='full', use_galore=False, galore_target_modules=None, galore_rank=128, galore_update_proj_gap=50, galore_scale=1.0, galore_proj_type='std', galore_optim_per_parameter=False, galore_with_embedding=False, galore_quantization=False, galore_proj_quant=False, galore_proj_bits=4, galore_proj_group_size=256, galore_cos_threshold=0.4, galore_gamma_proj=2, galore_queue_size=5, lisa_activated_layers=0, lisa_step_interval=20, use_flash_ckpt=False)"
|
| 409 |
+
}
|
checkpoint-600/chat_template.jinja
ADDED
|
@@ -0,0 +1,120 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0].role == 'system' %}
|
| 4 |
+
{%- if messages[0].content is string %}
|
| 5 |
+
{{- messages[0].content }}
|
| 6 |
+
{%- else %}
|
| 7 |
+
{%- for content in messages[0].content %}
|
| 8 |
+
{%- if 'text' in content %}
|
| 9 |
+
{{- content.text }}
|
| 10 |
+
{%- endif %}
|
| 11 |
+
{%- endfor %}
|
| 12 |
+
{%- endif %}
|
| 13 |
+
{{- '\n\n' }}
|
| 14 |
+
{%- endif %}
|
| 15 |
+
{{- "# 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>" }}
|
| 16 |
+
{%- for tool in tools %}
|
| 17 |
+
{{- "\n" }}
|
| 18 |
+
{{- tool | tojson }}
|
| 19 |
+
{%- endfor %}
|
| 20 |
+
{{- "\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" }}
|
| 21 |
+
{%- else %}
|
| 22 |
+
{%- if messages[0].role == 'system' %}
|
| 23 |
+
{{- '<|im_start|>system\n' }}
|
| 24 |
+
{%- if messages[0].content is string %}
|
| 25 |
+
{{- messages[0].content }}
|
| 26 |
+
{%- else %}
|
| 27 |
+
{%- for content in messages[0].content %}
|
| 28 |
+
{%- if 'text' in content %}
|
| 29 |
+
{{- content.text }}
|
| 30 |
+
{%- endif %}
|
| 31 |
+
{%- endfor %}
|
| 32 |
+
{%- endif %}
|
| 33 |
+
{{- '<|im_end|>\n' }}
|
| 34 |
+
{%- endif %}
|
| 35 |
+
{%- endif %}
|
| 36 |
+
{%- set image_count = namespace(value=0) %}
|
| 37 |
+
{%- set video_count = namespace(value=0) %}
|
| 38 |
+
{%- for message in messages %}
|
| 39 |
+
{%- if message.role == "user" %}
|
| 40 |
+
{{- '<|im_start|>' + message.role + '\n' }}
|
| 41 |
+
{%- if message.content is string %}
|
| 42 |
+
{{- message.content }}
|
| 43 |
+
{%- else %}
|
| 44 |
+
{%- for content in message.content %}
|
| 45 |
+
{%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
|
| 46 |
+
{%- set image_count.value = image_count.value + 1 %}
|
| 47 |
+
{%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
|
| 48 |
+
<|vision_start|><|image_pad|><|vision_end|>
|
| 49 |
+
{%- elif content.type == 'video' or 'video' in content %}
|
| 50 |
+
{%- set video_count.value = video_count.value + 1 %}
|
| 51 |
+
{%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
|
| 52 |
+
<|vision_start|><|video_pad|><|vision_end|>
|
| 53 |
+
{%- elif 'text' in content %}
|
| 54 |
+
{{- content.text }}
|
| 55 |
+
{%- endif %}
|
| 56 |
+
{%- endfor %}
|
| 57 |
+
{%- endif %}
|
| 58 |
+
{{- '<|im_end|>\n' }}
|
| 59 |
+
{%- elif message.role == "assistant" %}
|
| 60 |
+
{{- '<|im_start|>' + message.role + '\n' }}
|
| 61 |
+
{%- if message.content is string %}
|
| 62 |
+
{{- message.content }}
|
| 63 |
+
{%- else %}
|
| 64 |
+
{%- for content_item in message.content %}
|
| 65 |
+
{%- if 'text' in content_item %}
|
| 66 |
+
{{- content_item.text }}
|
| 67 |
+
{%- endif %}
|
| 68 |
+
{%- endfor %}
|
| 69 |
+
{%- endif %}
|
| 70 |
+
{%- if message.tool_calls %}
|
| 71 |
+
{%- for tool_call in message.tool_calls %}
|
| 72 |
+
{%- if (loop.first and message.content) or (not loop.first) %}
|
| 73 |
+
{{- '\n' }}
|
| 74 |
+
{%- endif %}
|
| 75 |
+
{%- if tool_call.function %}
|
| 76 |
+
{%- set tool_call = tool_call.function %}
|
| 77 |
+
{%- endif %}
|
| 78 |
+
{{- '<tool_call>\n{"name": "' }}
|
| 79 |
+
{{- tool_call.name }}
|
| 80 |
+
{{- '", "arguments": ' }}
|
| 81 |
+
{%- if tool_call.arguments is string %}
|
| 82 |
+
{{- tool_call.arguments }}
|
| 83 |
+
{%- else %}
|
| 84 |
+
{{- tool_call.arguments | tojson }}
|
| 85 |
+
{%- endif %}
|
| 86 |
+
{{- '}\n</tool_call>' }}
|
| 87 |
+
{%- endfor %}
|
| 88 |
+
{%- endif %}
|
| 89 |
+
{{- '<|im_end|>\n' }}
|
| 90 |
+
{%- elif message.role == "tool" %}
|
| 91 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 92 |
+
{{- '<|im_start|>user' }}
|
| 93 |
+
{%- endif %}
|
| 94 |
+
{{- '\n<tool_response>\n' }}
|
| 95 |
+
{%- if message.content is string %}
|
| 96 |
+
{{- message.content }}
|
| 97 |
+
{%- else %}
|
| 98 |
+
{%- for content in message.content %}
|
| 99 |
+
{%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
|
| 100 |
+
{%- set image_count.value = image_count.value + 1 %}
|
| 101 |
+
{%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
|
| 102 |
+
<|vision_start|><|image_pad|><|vision_end|>
|
| 103 |
+
{%- elif content.type == 'video' or 'video' in content %}
|
| 104 |
+
{%- set video_count.value = video_count.value + 1 %}
|
| 105 |
+
{%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
|
| 106 |
+
<|vision_start|><|video_pad|><|vision_end|>
|
| 107 |
+
{%- elif 'text' in content %}
|
| 108 |
+
{{- content.text }}
|
| 109 |
+
{%- endif %}
|
| 110 |
+
{%- endfor %}
|
| 111 |
+
{%- endif %}
|
| 112 |
+
{{- '\n</tool_response>' }}
|
| 113 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 114 |
+
{{- '<|im_end|>\n' }}
|
| 115 |
+
{%- endif %}
|
| 116 |
+
{%- endif %}
|
| 117 |
+
{%- endfor %}
|
| 118 |
+
{%- if add_generation_prompt %}
|
| 119 |
+
{{- '<|im_start|>assistant\n' }}
|
| 120 |
+
{%- endif %}
|
checkpoint-600/config.json
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3VLForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"dtype": "bfloat16",
|
| 6 |
+
"eos_token_id": 151645,
|
| 7 |
+
"hidden_size": 4096,
|
| 8 |
+
"image_token_id": 151655,
|
| 9 |
+
"model_type": "qwen3_vl",
|
| 10 |
+
"pad_token_id": 151643,
|
| 11 |
+
"text_config": {
|
| 12 |
+
"attention_bias": false,
|
| 13 |
+
"attention_dropout": 0.0,
|
| 14 |
+
"bos_token_id": 151643,
|
| 15 |
+
"dtype": "bfloat16",
|
| 16 |
+
"eos_token_id": 151645,
|
| 17 |
+
"head_dim": 128,
|
| 18 |
+
"hidden_act": "silu",
|
| 19 |
+
"hidden_size": 4096,
|
| 20 |
+
"initializer_range": 0.02,
|
| 21 |
+
"intermediate_size": 12288,
|
| 22 |
+
"max_position_embeddings": 262144,
|
| 23 |
+
"model_type": "qwen3_vl_text",
|
| 24 |
+
"num_attention_heads": 32,
|
| 25 |
+
"num_hidden_layers": 36,
|
| 26 |
+
"num_key_value_heads": 8,
|
| 27 |
+
"pad_token_id": 151643,
|
| 28 |
+
"rms_norm_eps": 1e-06,
|
| 29 |
+
"rope_scaling": {
|
| 30 |
+
"mrope_interleaved": true,
|
| 31 |
+
"mrope_section": [
|
| 32 |
+
24,
|
| 33 |
+
20,
|
| 34 |
+
20
|
| 35 |
+
],
|
| 36 |
+
"rope_type": "default"
|
| 37 |
+
},
|
| 38 |
+
"rope_theta": 5000000,
|
| 39 |
+
"use_cache": false,
|
| 40 |
+
"vocab_size": 151936
|
| 41 |
+
},
|
| 42 |
+
"tie_word_embeddings": false,
|
| 43 |
+
"transformers_version": "4.57.6",
|
| 44 |
+
"video_token_id": 151656,
|
| 45 |
+
"vision_config": {
|
| 46 |
+
"deepstack_visual_indexes": [
|
| 47 |
+
8,
|
| 48 |
+
16,
|
| 49 |
+
24
|
| 50 |
+
],
|
| 51 |
+
"depth": 27,
|
| 52 |
+
"dtype": "bfloat16",
|
| 53 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 54 |
+
"hidden_size": 1152,
|
| 55 |
+
"in_channels": 3,
|
| 56 |
+
"initializer_range": 0.02,
|
| 57 |
+
"intermediate_size": 4304,
|
| 58 |
+
"model_type": "qwen3_vl",
|
| 59 |
+
"num_heads": 16,
|
| 60 |
+
"num_position_embeddings": 2304,
|
| 61 |
+
"out_hidden_size": 4096,
|
| 62 |
+
"patch_size": 16,
|
| 63 |
+
"spatial_merge_size": 2,
|
| 64 |
+
"temporal_patch_size": 2
|
| 65 |
+
},
|
| 66 |
+
"vision_end_token_id": 151653,
|
| 67 |
+
"vision_start_token_id": 151652
|
| 68 |
+
}
|
checkpoint-600/generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"temperature": 0.7,
|
| 10 |
+
"top_k": 20,
|
| 11 |
+
"top_p": 0.8,
|
| 12 |
+
"transformers_version": "4.57.6"
|
| 13 |
+
}
|
checkpoint-600/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-600/model-00001-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:573c542ec159e8fcee028a2d842c3ed622036a2b880b4a85672d65e53108d639
|
| 3 |
+
size 4998056552
|
checkpoint-600/model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b08454374b70cf7bf1279e6d0a42c0c4d282713f341ce62fd3b15516a615689
|
| 3 |
+
size 4915962464
|
checkpoint-600/model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9b3e3a9381ebea7977c8c73673ab7f483cfa77f1c1039ce04bd17bf910e49d0e
|
| 3 |
+
size 4915962496
|
checkpoint-600/model-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dcd31dfdc27a049b2fae3319912b5b75a97bd81f316bfa82c75e561f923ae0be
|
| 3 |
+
size 2704357976
|
checkpoint-600/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,758 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 770288,
|
| 4 |
+
"total_size": 17534247392
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"lm_head.weight": "model-00004-of-00004.safetensors",
|
| 8 |
+
"model.language_model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
| 9 |
+
"model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 10 |
+
"model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 11 |
+
"model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 12 |
+
"model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 13 |
+
"model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 14 |
+
"model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 15 |
+
"model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 16 |
+
"model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 17 |
+
"model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 18 |
+
"model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 19 |
+
"model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 20 |
+
"model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 21 |
+
"model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 22 |
+
"model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 23 |
+
"model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 24 |
+
"model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 25 |
+
"model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 26 |
+
"model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 27 |
+
"model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 28 |
+
"model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 29 |
+
"model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 30 |
+
"model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 31 |
+
"model.language_model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 32 |
+
"model.language_model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 33 |
+
"model.language_model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 34 |
+
"model.language_model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 35 |
+
"model.language_model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 36 |
+
"model.language_model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 37 |
+
"model.language_model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 38 |
+
"model.language_model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 39 |
+
"model.language_model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 40 |
+
"model.language_model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 41 |
+
"model.language_model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 42 |
+
"model.language_model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 43 |
+
"model.language_model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 44 |
+
"model.language_model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 45 |
+
"model.language_model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 46 |
+
"model.language_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 47 |
+
"model.language_model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 48 |
+
"model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 49 |
+
"model.language_model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 50 |
+
"model.language_model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 51 |
+
"model.language_model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 52 |
+
"model.language_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 53 |
+
"model.language_model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 54 |
+
"model.language_model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 55 |
+
"model.language_model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 56 |
+
"model.language_model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 57 |
+
"model.language_model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 58 |
+
"model.language_model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 59 |
+
"model.language_model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 60 |
+
"model.language_model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 61 |
+
"model.language_model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 62 |
+
"model.language_model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 63 |
+
"model.language_model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 64 |
+
"model.language_model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 65 |
+
"model.language_model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 66 |
+
"model.language_model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 67 |
+
"model.language_model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 68 |
+
"model.language_model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 69 |
+
"model.language_model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 70 |
+
"model.language_model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 71 |
+
"model.language_model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 72 |
+
"model.language_model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 73 |
+
"model.language_model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 74 |
+
"model.language_model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 75 |
+
"model.language_model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 76 |
+
"model.language_model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 77 |
+
"model.language_model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 78 |
+
"model.language_model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 79 |
+
"model.language_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 80 |
+
"model.language_model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 81 |
+
"model.language_model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 82 |
+
"model.language_model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 83 |
+
"model.language_model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 84 |
+
"model.language_model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 85 |
+
"model.language_model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 86 |
+
"model.language_model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 87 |
+
"model.language_model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 88 |
+
"model.language_model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 89 |
+
"model.language_model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 90 |
+
"model.language_model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 91 |
+
"model.language_model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 92 |
+
"model.language_model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 93 |
+
"model.language_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 94 |
+
"model.language_model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 95 |
+
"model.language_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 96 |
+
"model.language_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 97 |
+
"model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 98 |
+
"model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 99 |
+
"model.language_model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 100 |
+
"model.language_model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 101 |
+
"model.language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 102 |
+
"model.language_model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 103 |
+
"model.language_model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 104 |
+
"model.language_model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 105 |
+
"model.language_model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 106 |
+
"model.language_model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 107 |
+
"model.language_model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 108 |
+
"model.language_model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 109 |
+
"model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 110 |
+
"model.language_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 111 |
+
"model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 112 |
+
"model.language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 113 |
+
"model.language_model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 114 |
+
"model.language_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 115 |
+
"model.language_model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 116 |
+
"model.language_model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 117 |
+
"model.language_model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 118 |
+
"model.language_model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 119 |
+
"model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 120 |
+
"model.language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 121 |
+
"model.language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 122 |
+
"model.language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 123 |
+
"model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 124 |
+
"model.language_model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 125 |
+
"model.language_model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 126 |
+
"model.language_model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 127 |
+
"model.language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 128 |
+
"model.language_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 129 |
+
"model.language_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 130 |
+
"model.language_model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 131 |
+
"model.language_model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 132 |
+
"model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 133 |
+
"model.language_model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 134 |
+
"model.language_model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 135 |
+
"model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 136 |
+
"model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 137 |
+
"model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 138 |
+
"model.language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 139 |
+
"model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 140 |
+
"model.language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 141 |
+
"model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 142 |
+
"model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 143 |
+
"model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 144 |
+
"model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 145 |
+
"model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 146 |
+
"model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 147 |
+
"model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 148 |
+
"model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 149 |
+
"model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 150 |
+
"model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 151 |
+
"model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 152 |
+
"model.language_model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 153 |
+
"model.language_model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 154 |
+
"model.language_model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 155 |
+
"model.language_model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 156 |
+
"model.language_model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 157 |
+
"model.language_model.layers.20.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 158 |
+
"model.language_model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 159 |
+
"model.language_model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 160 |
+
"model.language_model.layers.20.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 161 |
+
"model.language_model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 162 |
+
"model.language_model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 163 |
+
"model.language_model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 164 |
+
"model.language_model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 165 |
+
"model.language_model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 166 |
+
"model.language_model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 167 |
+
"model.language_model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 168 |
+
"model.language_model.layers.21.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 169 |
+
"model.language_model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 170 |
+
"model.language_model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 171 |
+
"model.language_model.layers.21.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 172 |
+
"model.language_model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 173 |
+
"model.language_model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 174 |
+
"model.language_model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 175 |
+
"model.language_model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 176 |
+
"model.language_model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 177 |
+
"model.language_model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 178 |
+
"model.language_model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 179 |
+
"model.language_model.layers.22.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 180 |
+
"model.language_model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 181 |
+
"model.language_model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 182 |
+
"model.language_model.layers.22.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 183 |
+
"model.language_model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 184 |
+
"model.language_model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 185 |
+
"model.language_model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 186 |
+
"model.language_model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 187 |
+
"model.language_model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 188 |
+
"model.language_model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 189 |
+
"model.language_model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 190 |
+
"model.language_model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 191 |
+
"model.language_model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 192 |
+
"model.language_model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 193 |
+
"model.language_model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 194 |
+
"model.language_model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 195 |
+
"model.language_model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 196 |
+
"model.language_model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 197 |
+
"model.language_model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 198 |
+
"model.language_model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 199 |
+
"model.language_model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 200 |
+
"model.language_model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 201 |
+
"model.language_model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 202 |
+
"model.language_model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 203 |
+
"model.language_model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 204 |
+
"model.language_model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 205 |
+
"model.language_model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 206 |
+
"model.language_model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 207 |
+
"model.language_model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 208 |
+
"model.language_model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 209 |
+
"model.language_model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 210 |
+
"model.language_model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 211 |
+
"model.language_model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 212 |
+
"model.language_model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 213 |
+
"model.language_model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 214 |
+
"model.language_model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 215 |
+
"model.language_model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 216 |
+
"model.language_model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 217 |
+
"model.language_model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 218 |
+
"model.language_model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 219 |
+
"model.language_model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 220 |
+
"model.language_model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 221 |
+
"model.language_model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 222 |
+
"model.language_model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 223 |
+
"model.language_model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 224 |
+
"model.language_model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 225 |
+
"model.language_model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 226 |
+
"model.language_model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 227 |
+
"model.language_model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 228 |
+
"model.language_model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 229 |
+
"model.language_model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 230 |
+
"model.language_model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 231 |
+
"model.language_model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 232 |
+
"model.language_model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 233 |
+
"model.language_model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 234 |
+
"model.language_model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 235 |
+
"model.language_model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 236 |
+
"model.language_model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 237 |
+
"model.language_model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 238 |
+
"model.language_model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 239 |
+
"model.language_model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 240 |
+
"model.language_model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 241 |
+
"model.language_model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 242 |
+
"model.language_model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 243 |
+
"model.language_model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 244 |
+
"model.language_model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 245 |
+
"model.language_model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 246 |
+
"model.language_model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 247 |
+
"model.language_model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 248 |
+
"model.language_model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 249 |
+
"model.language_model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 250 |
+
"model.language_model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 251 |
+
"model.language_model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 252 |
+
"model.language_model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 253 |
+
"model.language_model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 254 |
+
"model.language_model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 255 |
+
"model.language_model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 256 |
+
"model.language_model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 257 |
+
"model.language_model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 258 |
+
"model.language_model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 259 |
+
"model.language_model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 260 |
+
"model.language_model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 261 |
+
"model.language_model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 262 |
+
"model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 263 |
+
"model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 264 |
+
"model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 265 |
+
"model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 266 |
+
"model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 267 |
+
"model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 268 |
+
"model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 269 |
+
"model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 270 |
+
"model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 271 |
+
"model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 272 |
+
"model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 273 |
+
"model.language_model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 274 |
+
"model.language_model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 275 |
+
"model.language_model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 276 |
+
"model.language_model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 277 |
+
"model.language_model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 278 |
+
"model.language_model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 279 |
+
"model.language_model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 280 |
+
"model.language_model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 281 |
+
"model.language_model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 282 |
+
"model.language_model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 283 |
+
"model.language_model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 284 |
+
"model.language_model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 285 |
+
"model.language_model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 286 |
+
"model.language_model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 287 |
+
"model.language_model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 288 |
+
"model.language_model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 289 |
+
"model.language_model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 290 |
+
"model.language_model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 291 |
+
"model.language_model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 292 |
+
"model.language_model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 293 |
+
"model.language_model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 294 |
+
"model.language_model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 295 |
+
"model.language_model.layers.32.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 296 |
+
"model.language_model.layers.32.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 297 |
+
"model.language_model.layers.32.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 298 |
+
"model.language_model.layers.32.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 299 |
+
"model.language_model.layers.32.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 300 |
+
"model.language_model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 301 |
+
"model.language_model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 302 |
+
"model.language_model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 303 |
+
"model.language_model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 304 |
+
"model.language_model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 305 |
+
"model.language_model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 306 |
+
"model.language_model.layers.33.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 307 |
+
"model.language_model.layers.33.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 308 |
+
"model.language_model.layers.33.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 309 |
+
"model.language_model.layers.33.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 310 |
+
"model.language_model.layers.33.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 311 |
+
"model.language_model.layers.33.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
| 312 |
+
"model.language_model.layers.33.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 313 |
+
"model.language_model.layers.33.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 314 |
+
"model.language_model.layers.33.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
| 315 |
+
"model.language_model.layers.33.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 316 |
+
"model.language_model.layers.33.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 317 |
+
"model.language_model.layers.34.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 318 |
+
"model.language_model.layers.34.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 319 |
+
"model.language_model.layers.34.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 320 |
+
"model.language_model.layers.34.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 321 |
+
"model.language_model.layers.34.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 322 |
+
"model.language_model.layers.34.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
| 323 |
+
"model.language_model.layers.34.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 324 |
+
"model.language_model.layers.34.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 325 |
+
"model.language_model.layers.34.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
| 326 |
+
"model.language_model.layers.34.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 327 |
+
"model.language_model.layers.34.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 328 |
+
"model.language_model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 329 |
+
"model.language_model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 330 |
+
"model.language_model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 331 |
+
"model.language_model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 332 |
+
"model.language_model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 333 |
+
"model.language_model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
| 334 |
+
"model.language_model.layers.35.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 335 |
+
"model.language_model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 336 |
+
"model.language_model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
| 337 |
+
"model.language_model.layers.35.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 338 |
+
"model.language_model.layers.35.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 339 |
+
"model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 340 |
+
"model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 341 |
+
"model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 342 |
+
"model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 343 |
+
"model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 344 |
+
"model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 345 |
+
"model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 346 |
+
"model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 347 |
+
"model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 348 |
+
"model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 349 |
+
"model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 350 |
+
"model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 351 |
+
"model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 352 |
+
"model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 353 |
+
"model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 354 |
+
"model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 355 |
+
"model.language_model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 356 |
+
"model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 357 |
+
"model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 358 |
+
"model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 359 |
+
"model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 360 |
+
"model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 361 |
+
"model.language_model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 362 |
+
"model.language_model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 363 |
+
"model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 364 |
+
"model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 365 |
+
"model.language_model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 366 |
+
"model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 367 |
+
"model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 368 |
+
"model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 369 |
+
"model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 370 |
+
"model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 371 |
+
"model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 372 |
+
"model.language_model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 373 |
+
"model.language_model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 374 |
+
"model.language_model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 375 |
+
"model.language_model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 376 |
+
"model.language_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 377 |
+
"model.language_model.layers.7.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 378 |
+
"model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 379 |
+
"model.language_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 380 |
+
"model.language_model.layers.7.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 381 |
+
"model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 382 |
+
"model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 383 |
+
"model.language_model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 384 |
+
"model.language_model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 385 |
+
"model.language_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 386 |
+
"model.language_model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 387 |
+
"model.language_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 388 |
+
"model.language_model.layers.8.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 389 |
+
"model.language_model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 390 |
+
"model.language_model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 391 |
+
"model.language_model.layers.8.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 392 |
+
"model.language_model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 393 |
+
"model.language_model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 394 |
+
"model.language_model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 395 |
+
"model.language_model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 396 |
+
"model.language_model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 397 |
+
"model.language_model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 398 |
+
"model.language_model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 399 |
+
"model.language_model.layers.9.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 400 |
+
"model.language_model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 401 |
+
"model.language_model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 402 |
+
"model.language_model.layers.9.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 403 |
+
"model.language_model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 404 |
+
"model.language_model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 405 |
+
"model.language_model.norm.weight": "model-00004-of-00004.safetensors",
|
| 406 |
+
"model.visual.blocks.0.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 407 |
+
"model.visual.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 408 |
+
"model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 409 |
+
"model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 410 |
+
"model.visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 411 |
+
"model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 412 |
+
"model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 413 |
+
"model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 414 |
+
"model.visual.blocks.0.norm1.bias": "model-00001-of-00004.safetensors",
|
| 415 |
+
"model.visual.blocks.0.norm1.weight": "model-00001-of-00004.safetensors",
|
| 416 |
+
"model.visual.blocks.0.norm2.bias": "model-00001-of-00004.safetensors",
|
| 417 |
+
"model.visual.blocks.0.norm2.weight": "model-00001-of-00004.safetensors",
|
| 418 |
+
"model.visual.blocks.1.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 419 |
+
"model.visual.blocks.1.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 420 |
+
"model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 421 |
+
"model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 422 |
+
"model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 423 |
+
"model.visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 424 |
+
"model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 425 |
+
"model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 426 |
+
"model.visual.blocks.1.norm1.bias": "model-00001-of-00004.safetensors",
|
| 427 |
+
"model.visual.blocks.1.norm1.weight": "model-00001-of-00004.safetensors",
|
| 428 |
+
"model.visual.blocks.1.norm2.bias": "model-00001-of-00004.safetensors",
|
| 429 |
+
"model.visual.blocks.1.norm2.weight": "model-00001-of-00004.safetensors",
|
| 430 |
+
"model.visual.blocks.10.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 431 |
+
"model.visual.blocks.10.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 432 |
+
"model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 433 |
+
"model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 434 |
+
"model.visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 435 |
+
"model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 436 |
+
"model.visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 437 |
+
"model.visual.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 438 |
+
"model.visual.blocks.10.norm1.bias": "model-00001-of-00004.safetensors",
|
| 439 |
+
"model.visual.blocks.10.norm1.weight": "model-00001-of-00004.safetensors",
|
| 440 |
+
"model.visual.blocks.10.norm2.bias": "model-00001-of-00004.safetensors",
|
| 441 |
+
"model.visual.blocks.10.norm2.weight": "model-00001-of-00004.safetensors",
|
| 442 |
+
"model.visual.blocks.11.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 443 |
+
"model.visual.blocks.11.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 444 |
+
"model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 445 |
+
"model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 446 |
+
"model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 447 |
+
"model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 448 |
+
"model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 449 |
+
"model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 450 |
+
"model.visual.blocks.11.norm1.bias": "model-00001-of-00004.safetensors",
|
| 451 |
+
"model.visual.blocks.11.norm1.weight": "model-00001-of-00004.safetensors",
|
| 452 |
+
"model.visual.blocks.11.norm2.bias": "model-00001-of-00004.safetensors",
|
| 453 |
+
"model.visual.blocks.11.norm2.weight": "model-00001-of-00004.safetensors",
|
| 454 |
+
"model.visual.blocks.12.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 455 |
+
"model.visual.blocks.12.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 456 |
+
"model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 457 |
+
"model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 458 |
+
"model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 459 |
+
"model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 460 |
+
"model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 461 |
+
"model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 462 |
+
"model.visual.blocks.12.norm1.bias": "model-00001-of-00004.safetensors",
|
| 463 |
+
"model.visual.blocks.12.norm1.weight": "model-00001-of-00004.safetensors",
|
| 464 |
+
"model.visual.blocks.12.norm2.bias": "model-00001-of-00004.safetensors",
|
| 465 |
+
"model.visual.blocks.12.norm2.weight": "model-00001-of-00004.safetensors",
|
| 466 |
+
"model.visual.blocks.13.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 467 |
+
"model.visual.blocks.13.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 468 |
+
"model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 469 |
+
"model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 470 |
+
"model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 471 |
+
"model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 472 |
+
"model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 473 |
+
"model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 474 |
+
"model.visual.blocks.13.norm1.bias": "model-00001-of-00004.safetensors",
|
| 475 |
+
"model.visual.blocks.13.norm1.weight": "model-00001-of-00004.safetensors",
|
| 476 |
+
"model.visual.blocks.13.norm2.bias": "model-00001-of-00004.safetensors",
|
| 477 |
+
"model.visual.blocks.13.norm2.weight": "model-00001-of-00004.safetensors",
|
| 478 |
+
"model.visual.blocks.14.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 479 |
+
"model.visual.blocks.14.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 480 |
+
"model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 481 |
+
"model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 482 |
+
"model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 483 |
+
"model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 484 |
+
"model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 485 |
+
"model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 486 |
+
"model.visual.blocks.14.norm1.bias": "model-00001-of-00004.safetensors",
|
| 487 |
+
"model.visual.blocks.14.norm1.weight": "model-00001-of-00004.safetensors",
|
| 488 |
+
"model.visual.blocks.14.norm2.bias": "model-00001-of-00004.safetensors",
|
| 489 |
+
"model.visual.blocks.14.norm2.weight": "model-00001-of-00004.safetensors",
|
| 490 |
+
"model.visual.blocks.15.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 491 |
+
"model.visual.blocks.15.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 492 |
+
"model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 493 |
+
"model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 494 |
+
"model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 495 |
+
"model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 496 |
+
"model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 497 |
+
"model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 498 |
+
"model.visual.blocks.15.norm1.bias": "model-00001-of-00004.safetensors",
|
| 499 |
+
"model.visual.blocks.15.norm1.weight": "model-00001-of-00004.safetensors",
|
| 500 |
+
"model.visual.blocks.15.norm2.bias": "model-00001-of-00004.safetensors",
|
| 501 |
+
"model.visual.blocks.15.norm2.weight": "model-00001-of-00004.safetensors",
|
| 502 |
+
"model.visual.blocks.16.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 503 |
+
"model.visual.blocks.16.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 504 |
+
"model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 505 |
+
"model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 506 |
+
"model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 507 |
+
"model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 508 |
+
"model.visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 509 |
+
"model.visual.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 510 |
+
"model.visual.blocks.16.norm1.bias": "model-00001-of-00004.safetensors",
|
| 511 |
+
"model.visual.blocks.16.norm1.weight": "model-00001-of-00004.safetensors",
|
| 512 |
+
"model.visual.blocks.16.norm2.bias": "model-00001-of-00004.safetensors",
|
| 513 |
+
"model.visual.blocks.16.norm2.weight": "model-00001-of-00004.safetensors",
|
| 514 |
+
"model.visual.blocks.17.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 515 |
+
"model.visual.blocks.17.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 516 |
+
"model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 517 |
+
"model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 518 |
+
"model.visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 519 |
+
"model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 520 |
+
"model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 521 |
+
"model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 522 |
+
"model.visual.blocks.17.norm1.bias": "model-00001-of-00004.safetensors",
|
| 523 |
+
"model.visual.blocks.17.norm1.weight": "model-00001-of-00004.safetensors",
|
| 524 |
+
"model.visual.blocks.17.norm2.bias": "model-00001-of-00004.safetensors",
|
| 525 |
+
"model.visual.blocks.17.norm2.weight": "model-00001-of-00004.safetensors",
|
| 526 |
+
"model.visual.blocks.18.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 527 |
+
"model.visual.blocks.18.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 528 |
+
"model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 529 |
+
"model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 530 |
+
"model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 531 |
+
"model.visual.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 532 |
+
"model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 533 |
+
"model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 534 |
+
"model.visual.blocks.18.norm1.bias": "model-00001-of-00004.safetensors",
|
| 535 |
+
"model.visual.blocks.18.norm1.weight": "model-00001-of-00004.safetensors",
|
| 536 |
+
"model.visual.blocks.18.norm2.bias": "model-00001-of-00004.safetensors",
|
| 537 |
+
"model.visual.blocks.18.norm2.weight": "model-00001-of-00004.safetensors",
|
| 538 |
+
"model.visual.blocks.19.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 539 |
+
"model.visual.blocks.19.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 540 |
+
"model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 541 |
+
"model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 542 |
+
"model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 543 |
+
"model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 544 |
+
"model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 545 |
+
"model.visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 546 |
+
"model.visual.blocks.19.norm1.bias": "model-00001-of-00004.safetensors",
|
| 547 |
+
"model.visual.blocks.19.norm1.weight": "model-00001-of-00004.safetensors",
|
| 548 |
+
"model.visual.blocks.19.norm2.bias": "model-00001-of-00004.safetensors",
|
| 549 |
+
"model.visual.blocks.19.norm2.weight": "model-00001-of-00004.safetensors",
|
| 550 |
+
"model.visual.blocks.2.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 551 |
+
"model.visual.blocks.2.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 552 |
+
"model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 553 |
+
"model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 554 |
+
"model.visual.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 555 |
+
"model.visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 556 |
+
"model.visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 557 |
+
"model.visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 558 |
+
"model.visual.blocks.2.norm1.bias": "model-00001-of-00004.safetensors",
|
| 559 |
+
"model.visual.blocks.2.norm1.weight": "model-00001-of-00004.safetensors",
|
| 560 |
+
"model.visual.blocks.2.norm2.bias": "model-00001-of-00004.safetensors",
|
| 561 |
+
"model.visual.blocks.2.norm2.weight": "model-00001-of-00004.safetensors",
|
| 562 |
+
"model.visual.blocks.20.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 563 |
+
"model.visual.blocks.20.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 564 |
+
"model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 565 |
+
"model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 566 |
+
"model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 567 |
+
"model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 568 |
+
"model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 569 |
+
"model.visual.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 570 |
+
"model.visual.blocks.20.norm1.bias": "model-00001-of-00004.safetensors",
|
| 571 |
+
"model.visual.blocks.20.norm1.weight": "model-00001-of-00004.safetensors",
|
| 572 |
+
"model.visual.blocks.20.norm2.bias": "model-00001-of-00004.safetensors",
|
| 573 |
+
"model.visual.blocks.20.norm2.weight": "model-00001-of-00004.safetensors",
|
| 574 |
+
"model.visual.blocks.21.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 575 |
+
"model.visual.blocks.21.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 576 |
+
"model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 577 |
+
"model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 578 |
+
"model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 579 |
+
"model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 580 |
+
"model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 581 |
+
"model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 582 |
+
"model.visual.blocks.21.norm1.bias": "model-00001-of-00004.safetensors",
|
| 583 |
+
"model.visual.blocks.21.norm1.weight": "model-00001-of-00004.safetensors",
|
| 584 |
+
"model.visual.blocks.21.norm2.bias": "model-00001-of-00004.safetensors",
|
| 585 |
+
"model.visual.blocks.21.norm2.weight": "model-00001-of-00004.safetensors",
|
| 586 |
+
"model.visual.blocks.22.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 587 |
+
"model.visual.blocks.22.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 588 |
+
"model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 589 |
+
"model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 590 |
+
"model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 591 |
+
"model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 592 |
+
"model.visual.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 593 |
+
"model.visual.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 594 |
+
"model.visual.blocks.22.norm1.bias": "model-00001-of-00004.safetensors",
|
| 595 |
+
"model.visual.blocks.22.norm1.weight": "model-00001-of-00004.safetensors",
|
| 596 |
+
"model.visual.blocks.22.norm2.bias": "model-00001-of-00004.safetensors",
|
| 597 |
+
"model.visual.blocks.22.norm2.weight": "model-00001-of-00004.safetensors",
|
| 598 |
+
"model.visual.blocks.23.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 599 |
+
"model.visual.blocks.23.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 600 |
+
"model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 601 |
+
"model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 602 |
+
"model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 603 |
+
"model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 604 |
+
"model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 605 |
+
"model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 606 |
+
"model.visual.blocks.23.norm1.bias": "model-00001-of-00004.safetensors",
|
| 607 |
+
"model.visual.blocks.23.norm1.weight": "model-00001-of-00004.safetensors",
|
| 608 |
+
"model.visual.blocks.23.norm2.bias": "model-00001-of-00004.safetensors",
|
| 609 |
+
"model.visual.blocks.23.norm2.weight": "model-00001-of-00004.safetensors",
|
| 610 |
+
"model.visual.blocks.24.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 611 |
+
"model.visual.blocks.24.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 612 |
+
"model.visual.blocks.24.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 613 |
+
"model.visual.blocks.24.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 614 |
+
"model.visual.blocks.24.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 615 |
+
"model.visual.blocks.24.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 616 |
+
"model.visual.blocks.24.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 617 |
+
"model.visual.blocks.24.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 618 |
+
"model.visual.blocks.24.norm1.bias": "model-00001-of-00004.safetensors",
|
| 619 |
+
"model.visual.blocks.24.norm1.weight": "model-00001-of-00004.safetensors",
|
| 620 |
+
"model.visual.blocks.24.norm2.bias": "model-00001-of-00004.safetensors",
|
| 621 |
+
"model.visual.blocks.24.norm2.weight": "model-00001-of-00004.safetensors",
|
| 622 |
+
"model.visual.blocks.25.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 623 |
+
"model.visual.blocks.25.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 624 |
+
"model.visual.blocks.25.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 625 |
+
"model.visual.blocks.25.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 626 |
+
"model.visual.blocks.25.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 627 |
+
"model.visual.blocks.25.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 628 |
+
"model.visual.blocks.25.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 629 |
+
"model.visual.blocks.25.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 630 |
+
"model.visual.blocks.25.norm1.bias": "model-00001-of-00004.safetensors",
|
| 631 |
+
"model.visual.blocks.25.norm1.weight": "model-00001-of-00004.safetensors",
|
| 632 |
+
"model.visual.blocks.25.norm2.bias": "model-00001-of-00004.safetensors",
|
| 633 |
+
"model.visual.blocks.25.norm2.weight": "model-00001-of-00004.safetensors",
|
| 634 |
+
"model.visual.blocks.26.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 635 |
+
"model.visual.blocks.26.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 636 |
+
"model.visual.blocks.26.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 637 |
+
"model.visual.blocks.26.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 638 |
+
"model.visual.blocks.26.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 639 |
+
"model.visual.blocks.26.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 640 |
+
"model.visual.blocks.26.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 641 |
+
"model.visual.blocks.26.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 642 |
+
"model.visual.blocks.26.norm1.bias": "model-00001-of-00004.safetensors",
|
| 643 |
+
"model.visual.blocks.26.norm1.weight": "model-00001-of-00004.safetensors",
|
| 644 |
+
"model.visual.blocks.26.norm2.bias": "model-00001-of-00004.safetensors",
|
| 645 |
+
"model.visual.blocks.26.norm2.weight": "model-00001-of-00004.safetensors",
|
| 646 |
+
"model.visual.blocks.3.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 647 |
+
"model.visual.blocks.3.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 648 |
+
"model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 649 |
+
"model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 650 |
+
"model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 651 |
+
"model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 652 |
+
"model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 653 |
+
"model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 654 |
+
"model.visual.blocks.3.norm1.bias": "model-00001-of-00004.safetensors",
|
| 655 |
+
"model.visual.blocks.3.norm1.weight": "model-00001-of-00004.safetensors",
|
| 656 |
+
"model.visual.blocks.3.norm2.bias": "model-00001-of-00004.safetensors",
|
| 657 |
+
"model.visual.blocks.3.norm2.weight": "model-00001-of-00004.safetensors",
|
| 658 |
+
"model.visual.blocks.4.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 659 |
+
"model.visual.blocks.4.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 660 |
+
"model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 661 |
+
"model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 662 |
+
"model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 663 |
+
"model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 664 |
+
"model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 665 |
+
"model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 666 |
+
"model.visual.blocks.4.norm1.bias": "model-00001-of-00004.safetensors",
|
| 667 |
+
"model.visual.blocks.4.norm1.weight": "model-00001-of-00004.safetensors",
|
| 668 |
+
"model.visual.blocks.4.norm2.bias": "model-00001-of-00004.safetensors",
|
| 669 |
+
"model.visual.blocks.4.norm2.weight": "model-00001-of-00004.safetensors",
|
| 670 |
+
"model.visual.blocks.5.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 671 |
+
"model.visual.blocks.5.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 672 |
+
"model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 673 |
+
"model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 674 |
+
"model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 675 |
+
"model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 676 |
+
"model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 677 |
+
"model.visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 678 |
+
"model.visual.blocks.5.norm1.bias": "model-00001-of-00004.safetensors",
|
| 679 |
+
"model.visual.blocks.5.norm1.weight": "model-00001-of-00004.safetensors",
|
| 680 |
+
"model.visual.blocks.5.norm2.bias": "model-00001-of-00004.safetensors",
|
| 681 |
+
"model.visual.blocks.5.norm2.weight": "model-00001-of-00004.safetensors",
|
| 682 |
+
"model.visual.blocks.6.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 683 |
+
"model.visual.blocks.6.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 684 |
+
"model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 685 |
+
"model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 686 |
+
"model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 687 |
+
"model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 688 |
+
"model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 689 |
+
"model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 690 |
+
"model.visual.blocks.6.norm1.bias": "model-00001-of-00004.safetensors",
|
| 691 |
+
"model.visual.blocks.6.norm1.weight": "model-00001-of-00004.safetensors",
|
| 692 |
+
"model.visual.blocks.6.norm2.bias": "model-00001-of-00004.safetensors",
|
| 693 |
+
"model.visual.blocks.6.norm2.weight": "model-00001-of-00004.safetensors",
|
| 694 |
+
"model.visual.blocks.7.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 695 |
+
"model.visual.blocks.7.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 696 |
+
"model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 697 |
+
"model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 698 |
+
"model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 699 |
+
"model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 700 |
+
"model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 701 |
+
"model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 702 |
+
"model.visual.blocks.7.norm1.bias": "model-00001-of-00004.safetensors",
|
| 703 |
+
"model.visual.blocks.7.norm1.weight": "model-00001-of-00004.safetensors",
|
| 704 |
+
"model.visual.blocks.7.norm2.bias": "model-00001-of-00004.safetensors",
|
| 705 |
+
"model.visual.blocks.7.norm2.weight": "model-00001-of-00004.safetensors",
|
| 706 |
+
"model.visual.blocks.8.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 707 |
+
"model.visual.blocks.8.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 708 |
+
"model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 709 |
+
"model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 710 |
+
"model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 711 |
+
"model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 712 |
+
"model.visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 713 |
+
"model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 714 |
+
"model.visual.blocks.8.norm1.bias": "model-00001-of-00004.safetensors",
|
| 715 |
+
"model.visual.blocks.8.norm1.weight": "model-00001-of-00004.safetensors",
|
| 716 |
+
"model.visual.blocks.8.norm2.bias": "model-00001-of-00004.safetensors",
|
| 717 |
+
"model.visual.blocks.8.norm2.weight": "model-00001-of-00004.safetensors",
|
| 718 |
+
"model.visual.blocks.9.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 719 |
+
"model.visual.blocks.9.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 720 |
+
"model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 721 |
+
"model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 722 |
+
"model.visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 723 |
+
"model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 724 |
+
"model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 725 |
+
"model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 726 |
+
"model.visual.blocks.9.norm1.bias": "model-00001-of-00004.safetensors",
|
| 727 |
+
"model.visual.blocks.9.norm1.weight": "model-00001-of-00004.safetensors",
|
| 728 |
+
"model.visual.blocks.9.norm2.bias": "model-00001-of-00004.safetensors",
|
| 729 |
+
"model.visual.blocks.9.norm2.weight": "model-00001-of-00004.safetensors",
|
| 730 |
+
"model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 731 |
+
"model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 732 |
+
"model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 733 |
+
"model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 734 |
+
"model.visual.deepstack_merger_list.0.norm.bias": "model-00001-of-00004.safetensors",
|
| 735 |
+
"model.visual.deepstack_merger_list.0.norm.weight": "model-00001-of-00004.safetensors",
|
| 736 |
+
"model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 737 |
+
"model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 738 |
+
"model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 739 |
+
"model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 740 |
+
"model.visual.deepstack_merger_list.1.norm.bias": "model-00001-of-00004.safetensors",
|
| 741 |
+
"model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00004.safetensors",
|
| 742 |
+
"model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 743 |
+
"model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 744 |
+
"model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 745 |
+
"model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 746 |
+
"model.visual.deepstack_merger_list.2.norm.bias": "model-00001-of-00004.safetensors",
|
| 747 |
+
"model.visual.deepstack_merger_list.2.norm.weight": "model-00001-of-00004.safetensors",
|
| 748 |
+
"model.visual.merger.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 749 |
+
"model.visual.merger.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 750 |
+
"model.visual.merger.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 751 |
+
"model.visual.merger.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 752 |
+
"model.visual.merger.norm.bias": "model-00001-of-00004.safetensors",
|
| 753 |
+
"model.visual.merger.norm.weight": "model-00001-of-00004.safetensors",
|
| 754 |
+
"model.visual.patch_embed.proj.bias": "model-00001-of-00004.safetensors",
|
| 755 |
+
"model.visual.patch_embed.proj.weight": "model-00001-of-00004.safetensors",
|
| 756 |
+
"model.visual.pos_embed.weight": "model-00001-of-00004.safetensors"
|
| 757 |
+
}
|
| 758 |
+
}
|
checkpoint-600/preprocessor_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"size": {
|
| 3 |
+
"longest_edge": 16777216,
|
| 4 |
+
"shortest_edge": 65536
|
| 5 |
+
},
|
| 6 |
+
"patch_size": 16,
|
| 7 |
+
"temporal_patch_size": 2,
|
| 8 |
+
"merge_size": 2,
|
| 9 |
+
"image_mean": [
|
| 10 |
+
0.5,
|
| 11 |
+
0.5,
|
| 12 |
+
0.5
|
| 13 |
+
],
|
| 14 |
+
"image_std": [
|
| 15 |
+
0.5,
|
| 16 |
+
0.5,
|
| 17 |
+
0.5
|
| 18 |
+
],
|
| 19 |
+
"processor_class": "Qwen3VLProcessor",
|
| 20 |
+
"image_processor_type": "Qwen2VLImageProcessorFast"
|
| 21 |
+
}
|
checkpoint-600/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-600/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
| 3 |
+
size 11422654
|
checkpoint-600/tokenizer_config.json
ADDED
|
@@ -0,0 +1,240 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"151665": {
|
| 182 |
+
"content": "<tool_response>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "</tool_response>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"151667": {
|
| 198 |
+
"content": "<think>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"151668": {
|
| 206 |
+
"content": "</think>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
}
|
| 213 |
+
},
|
| 214 |
+
"additional_special_tokens": [
|
| 215 |
+
"<|im_start|>",
|
| 216 |
+
"<|im_end|>",
|
| 217 |
+
"<|object_ref_start|>",
|
| 218 |
+
"<|object_ref_end|>",
|
| 219 |
+
"<|box_start|>",
|
| 220 |
+
"<|box_end|>",
|
| 221 |
+
"<|quad_start|>",
|
| 222 |
+
"<|quad_end|>",
|
| 223 |
+
"<|vision_start|>",
|
| 224 |
+
"<|vision_end|>",
|
| 225 |
+
"<|vision_pad|>",
|
| 226 |
+
"<|image_pad|>",
|
| 227 |
+
"<|video_pad|>"
|
| 228 |
+
],
|
| 229 |
+
"bos_token": null,
|
| 230 |
+
"clean_up_tokenization_spaces": false,
|
| 231 |
+
"eos_token": "<|im_end|>",
|
| 232 |
+
"errors": "replace",
|
| 233 |
+
"extra_special_tokens": {},
|
| 234 |
+
"model_max_length": 262144,
|
| 235 |
+
"pad_token": "<|endoftext|>",
|
| 236 |
+
"processor_class": "Qwen3VLProcessor",
|
| 237 |
+
"split_special_tokens": false,
|
| 238 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 239 |
+
"unk_token": null
|
| 240 |
+
}
|
checkpoint-600/trainer_state.json
ADDED
|
@@ -0,0 +1,1002 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.6618863761720905,
|
| 6 |
+
"eval_steps": 300.0,
|
| 7 |
+
"global_step": 600,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0011031439602868175,
|
| 14 |
+
"grad_norm": 80.42967325823248,
|
| 15 |
+
"learning_rate": 2.3e-06,
|
| 16 |
+
"loss": 1.6655548810958862,
|
| 17 |
+
"step": 1,
|
| 18 |
+
"token_acc": 0.6208588957055214
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 0.005515719801434087,
|
| 22 |
+
"grad_norm": 12.936447236966638,
|
| 23 |
+
"learning_rate": 2.3e-06,
|
| 24 |
+
"loss": 1.6539018154144287,
|
| 25 |
+
"step": 5,
|
| 26 |
+
"token_acc": 0.6644312612844984
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.011031439602868174,
|
| 30 |
+
"grad_norm": 7.485145348211075,
|
| 31 |
+
"learning_rate": 2.3e-06,
|
| 32 |
+
"loss": 1.1399970054626465,
|
| 33 |
+
"step": 10,
|
| 34 |
+
"token_acc": 0.716547901821061
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 0.01654715940430226,
|
| 38 |
+
"grad_norm": 7.10761756326815,
|
| 39 |
+
"learning_rate": 2.3e-06,
|
| 40 |
+
"loss": 1.1828346252441406,
|
| 41 |
+
"step": 15,
|
| 42 |
+
"token_acc": 0.6928796755295178
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.02206287920573635,
|
| 46 |
+
"grad_norm": 5.659684098393193,
|
| 47 |
+
"learning_rate": 2.3e-06,
|
| 48 |
+
"loss": 1.0604573249816895,
|
| 49 |
+
"step": 20,
|
| 50 |
+
"token_acc": 0.7371653156472611
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.027578599007170437,
|
| 54 |
+
"grad_norm": 6.432203040875114,
|
| 55 |
+
"learning_rate": 2.3e-06,
|
| 56 |
+
"loss": 1.0374173164367675,
|
| 57 |
+
"step": 25,
|
| 58 |
+
"token_acc": 0.7369089984748348
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.03309431880860452,
|
| 62 |
+
"grad_norm": 6.0637637354614125,
|
| 63 |
+
"learning_rate": 2.3e-06,
|
| 64 |
+
"loss": 0.9596109390258789,
|
| 65 |
+
"step": 30,
|
| 66 |
+
"token_acc": 0.7449127906976745
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.03861003861003861,
|
| 70 |
+
"grad_norm": 5.9792048911606335,
|
| 71 |
+
"learning_rate": 2.3e-06,
|
| 72 |
+
"loss": 0.9912214279174805,
|
| 73 |
+
"step": 35,
|
| 74 |
+
"token_acc": 0.7413617886178862
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.0441257584114727,
|
| 78 |
+
"grad_norm": 6.031366828095079,
|
| 79 |
+
"learning_rate": 2.3e-06,
|
| 80 |
+
"loss": 1.0473726272583008,
|
| 81 |
+
"step": 40,
|
| 82 |
+
"token_acc": 0.727144535840188
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.049641478212906785,
|
| 86 |
+
"grad_norm": 6.186527950833231,
|
| 87 |
+
"learning_rate": 2.3e-06,
|
| 88 |
+
"loss": 0.9992570877075195,
|
| 89 |
+
"step": 45,
|
| 90 |
+
"token_acc": 0.7360217714002969
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.05515719801434087,
|
| 94 |
+
"grad_norm": 5.923085345386395,
|
| 95 |
+
"learning_rate": 2.3e-06,
|
| 96 |
+
"loss": 1.002680206298828,
|
| 97 |
+
"step": 50,
|
| 98 |
+
"token_acc": 0.7391618497109826
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.06067291781577496,
|
| 102 |
+
"grad_norm": 4.9260097226563255,
|
| 103 |
+
"learning_rate": 2.3e-06,
|
| 104 |
+
"loss": 0.8863202095031738,
|
| 105 |
+
"step": 55,
|
| 106 |
+
"token_acc": 0.7527737578388809
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.06618863761720904,
|
| 110 |
+
"grad_norm": 5.560254131314214,
|
| 111 |
+
"learning_rate": 2.3e-06,
|
| 112 |
+
"loss": 0.9248697280883789,
|
| 113 |
+
"step": 60,
|
| 114 |
+
"token_acc": 0.7579394848712178
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.07170435741864313,
|
| 118 |
+
"grad_norm": 5.180260599645047,
|
| 119 |
+
"learning_rate": 2.3e-06,
|
| 120 |
+
"loss": 1.004658317565918,
|
| 121 |
+
"step": 65,
|
| 122 |
+
"token_acc": 0.7360208062418726
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.07722007722007722,
|
| 126 |
+
"grad_norm": 6.299333554712354,
|
| 127 |
+
"learning_rate": 2.3e-06,
|
| 128 |
+
"loss": 0.9439926147460938,
|
| 129 |
+
"step": 70,
|
| 130 |
+
"token_acc": 0.751812046988253
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.0827357970215113,
|
| 134 |
+
"grad_norm": 5.622631000909693,
|
| 135 |
+
"learning_rate": 2.3e-06,
|
| 136 |
+
"loss": 0.8676441192626954,
|
| 137 |
+
"step": 75,
|
| 138 |
+
"token_acc": 0.760814889336016
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.0882515168229454,
|
| 142 |
+
"grad_norm": 5.613397002114218,
|
| 143 |
+
"learning_rate": 2.3e-06,
|
| 144 |
+
"loss": 0.8931824684143066,
|
| 145 |
+
"step": 80,
|
| 146 |
+
"token_acc": 0.7616038882138517
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.09376723662437948,
|
| 150 |
+
"grad_norm": 5.897499862699952,
|
| 151 |
+
"learning_rate": 2.3e-06,
|
| 152 |
+
"loss": 1.0003661155700683,
|
| 153 |
+
"step": 85,
|
| 154 |
+
"token_acc": 0.7361477572559367
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.09928295642581357,
|
| 158 |
+
"grad_norm": 5.838989842949948,
|
| 159 |
+
"learning_rate": 2.3e-06,
|
| 160 |
+
"loss": 0.8919829368591309,
|
| 161 |
+
"step": 90,
|
| 162 |
+
"token_acc": 0.7569311663479924
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.10479867622724766,
|
| 166 |
+
"grad_norm": 5.732772113211347,
|
| 167 |
+
"learning_rate": 2.3e-06,
|
| 168 |
+
"loss": 0.9857375144958496,
|
| 169 |
+
"step": 95,
|
| 170 |
+
"token_acc": 0.7319040543409042
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.11031439602868175,
|
| 174 |
+
"grad_norm": 5.887155914575355,
|
| 175 |
+
"learning_rate": 2.3e-06,
|
| 176 |
+
"loss": 0.9643180847167969,
|
| 177 |
+
"step": 100,
|
| 178 |
+
"token_acc": 0.7468728678644531
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.11583011583011583,
|
| 182 |
+
"grad_norm": 5.409153898947996,
|
| 183 |
+
"learning_rate": 2.3e-06,
|
| 184 |
+
"loss": 0.9775169372558594,
|
| 185 |
+
"step": 105,
|
| 186 |
+
"token_acc": 0.7443522360534809
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.12134583563154992,
|
| 190 |
+
"grad_norm": 5.738347427048291,
|
| 191 |
+
"learning_rate": 2.3e-06,
|
| 192 |
+
"loss": 1.0265106201171874,
|
| 193 |
+
"step": 110,
|
| 194 |
+
"token_acc": 0.7265641025641025
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.126861555432984,
|
| 198 |
+
"grad_norm": 5.38681474950728,
|
| 199 |
+
"learning_rate": 2.3e-06,
|
| 200 |
+
"loss": 0.9541057586669922,
|
| 201 |
+
"step": 115,
|
| 202 |
+
"token_acc": 0.747302805082714
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.13237727523441808,
|
| 206 |
+
"grad_norm": 5.856303394018206,
|
| 207 |
+
"learning_rate": 2.3e-06,
|
| 208 |
+
"loss": 0.8228609085083007,
|
| 209 |
+
"step": 120,
|
| 210 |
+
"token_acc": 0.7779299014238773
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.13789299503585217,
|
| 214 |
+
"grad_norm": 6.568516319919617,
|
| 215 |
+
"learning_rate": 2.3e-06,
|
| 216 |
+
"loss": 0.9721288681030273,
|
| 217 |
+
"step": 125,
|
| 218 |
+
"token_acc": 0.7395016151361329
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.14340871483728626,
|
| 222 |
+
"grad_norm": 5.54045872938136,
|
| 223 |
+
"learning_rate": 2.3e-06,
|
| 224 |
+
"loss": 0.9882600784301758,
|
| 225 |
+
"step": 130,
|
| 226 |
+
"token_acc": 0.7350409836065573
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.14892443463872035,
|
| 230 |
+
"grad_norm": 5.612320181227532,
|
| 231 |
+
"learning_rate": 2.3e-06,
|
| 232 |
+
"loss": 0.9342703819274902,
|
| 233 |
+
"step": 135,
|
| 234 |
+
"token_acc": 0.7464104263309035
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.15444015444015444,
|
| 238 |
+
"grad_norm": 5.925987985108847,
|
| 239 |
+
"learning_rate": 2.3e-06,
|
| 240 |
+
"loss": 0.9266027450561524,
|
| 241 |
+
"step": 140,
|
| 242 |
+
"token_acc": 0.7487753673897831
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.15995587424158852,
|
| 246 |
+
"grad_norm": 5.59653045493395,
|
| 247 |
+
"learning_rate": 2.3e-06,
|
| 248 |
+
"loss": 0.8937458038330078,
|
| 249 |
+
"step": 145,
|
| 250 |
+
"token_acc": 0.7624970664163342
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.1654715940430226,
|
| 254 |
+
"grad_norm": 5.374039667260155,
|
| 255 |
+
"learning_rate": 2.3e-06,
|
| 256 |
+
"loss": 0.8537099838256836,
|
| 257 |
+
"step": 150,
|
| 258 |
+
"token_acc": 0.7640309304065852
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.1709873138444567,
|
| 262 |
+
"grad_norm": 5.376937826461383,
|
| 263 |
+
"learning_rate": 2.3e-06,
|
| 264 |
+
"loss": 0.8238465309143066,
|
| 265 |
+
"step": 155,
|
| 266 |
+
"token_acc": 0.7761599210266535
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.1765030336458908,
|
| 270 |
+
"grad_norm": 6.0245180163205285,
|
| 271 |
+
"learning_rate": 2.3e-06,
|
| 272 |
+
"loss": 0.8189101219177246,
|
| 273 |
+
"step": 160,
|
| 274 |
+
"token_acc": 0.7774302840761012
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.18201875344732488,
|
| 278 |
+
"grad_norm": 5.571460118689288,
|
| 279 |
+
"learning_rate": 2.3e-06,
|
| 280 |
+
"loss": 0.8788368225097656,
|
| 281 |
+
"step": 165,
|
| 282 |
+
"token_acc": 0.760459995106435
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.18753447324875896,
|
| 286 |
+
"grad_norm": 5.088793082374291,
|
| 287 |
+
"learning_rate": 2.3e-06,
|
| 288 |
+
"loss": 0.8897226333618165,
|
| 289 |
+
"step": 170,
|
| 290 |
+
"token_acc": 0.7589285714285714
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.19305019305019305,
|
| 294 |
+
"grad_norm": 5.578076711526945,
|
| 295 |
+
"learning_rate": 2.3e-06,
|
| 296 |
+
"loss": 0.8561611175537109,
|
| 297 |
+
"step": 175,
|
| 298 |
+
"token_acc": 0.7607285429141717
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 0.19856591285162714,
|
| 302 |
+
"grad_norm": 5.81713562547314,
|
| 303 |
+
"learning_rate": 2.3e-06,
|
| 304 |
+
"loss": 0.8790461540222168,
|
| 305 |
+
"step": 180,
|
| 306 |
+
"token_acc": 0.753576372865713
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 0.20408163265306123,
|
| 310 |
+
"grad_norm": 5.254765297480428,
|
| 311 |
+
"learning_rate": 2.3e-06,
|
| 312 |
+
"loss": 0.7894742965698243,
|
| 313 |
+
"step": 185,
|
| 314 |
+
"token_acc": 0.7727930535455861
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.20959735245449532,
|
| 318 |
+
"grad_norm": 5.076375360468776,
|
| 319 |
+
"learning_rate": 2.3e-06,
|
| 320 |
+
"loss": 0.8446966171264648,
|
| 321 |
+
"step": 190,
|
| 322 |
+
"token_acc": 0.7672064777327935
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 0.2151130722559294,
|
| 326 |
+
"grad_norm": 5.763028979469674,
|
| 327 |
+
"learning_rate": 2.3e-06,
|
| 328 |
+
"loss": 0.961794662475586,
|
| 329 |
+
"step": 195,
|
| 330 |
+
"token_acc": 0.7398701589433624
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 0.2206287920573635,
|
| 334 |
+
"grad_norm": 5.351427081900536,
|
| 335 |
+
"learning_rate": 2.3e-06,
|
| 336 |
+
"loss": 0.9339935302734375,
|
| 337 |
+
"step": 200,
|
| 338 |
+
"token_acc": 0.7431607506217499
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.22614451185879758,
|
| 342 |
+
"grad_norm": 5.713651299205875,
|
| 343 |
+
"learning_rate": 2.3e-06,
|
| 344 |
+
"loss": 0.918415641784668,
|
| 345 |
+
"step": 205,
|
| 346 |
+
"token_acc": 0.7481903926299627
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.23166023166023167,
|
| 350 |
+
"grad_norm": 5.8891737450130535,
|
| 351 |
+
"learning_rate": 2.3e-06,
|
| 352 |
+
"loss": 0.9010303497314454,
|
| 353 |
+
"step": 210,
|
| 354 |
+
"token_acc": 0.7571428571428571
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.23717595146166576,
|
| 358 |
+
"grad_norm": 5.4902683255452915,
|
| 359 |
+
"learning_rate": 2.3e-06,
|
| 360 |
+
"loss": 0.8169702529907227,
|
| 361 |
+
"step": 215,
|
| 362 |
+
"token_acc": 0.7799597180261832
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.24269167126309985,
|
| 366 |
+
"grad_norm": 5.777757326601303,
|
| 367 |
+
"learning_rate": 2.3e-06,
|
| 368 |
+
"loss": 0.9132566452026367,
|
| 369 |
+
"step": 220,
|
| 370 |
+
"token_acc": 0.7451829400303096
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.24820739106453393,
|
| 374 |
+
"grad_norm": 5.440176086672954,
|
| 375 |
+
"learning_rate": 2.3e-06,
|
| 376 |
+
"loss": 0.9655065536499023,
|
| 377 |
+
"step": 225,
|
| 378 |
+
"token_acc": 0.7356965174129353
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 0.253723110865968,
|
| 382 |
+
"grad_norm": 5.65109550423067,
|
| 383 |
+
"learning_rate": 2.3e-06,
|
| 384 |
+
"loss": 0.9338722229003906,
|
| 385 |
+
"step": 230,
|
| 386 |
+
"token_acc": 0.740830755634114
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 0.2592388306674021,
|
| 390 |
+
"grad_norm": 5.558767495868624,
|
| 391 |
+
"learning_rate": 2.3e-06,
|
| 392 |
+
"loss": 0.9302779197692871,
|
| 393 |
+
"step": 235,
|
| 394 |
+
"token_acc": 0.7472228044435129
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.26475455046883617,
|
| 398 |
+
"grad_norm": 5.0652164247691,
|
| 399 |
+
"learning_rate": 2.3e-06,
|
| 400 |
+
"loss": 0.8661215782165528,
|
| 401 |
+
"step": 240,
|
| 402 |
+
"token_acc": 0.7648968235566891
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.2702702702702703,
|
| 406 |
+
"grad_norm": 5.301144006085399,
|
| 407 |
+
"learning_rate": 2.3e-06,
|
| 408 |
+
"loss": 0.9218810081481934,
|
| 409 |
+
"step": 245,
|
| 410 |
+
"token_acc": 0.7493386243386243
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.27578599007170435,
|
| 414 |
+
"grad_norm": 5.6495062752144625,
|
| 415 |
+
"learning_rate": 2.3e-06,
|
| 416 |
+
"loss": 0.7810210227966309,
|
| 417 |
+
"step": 250,
|
| 418 |
+
"token_acc": 0.7860394537177542
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.28130170987313846,
|
| 422 |
+
"grad_norm": 5.522127957882286,
|
| 423 |
+
"learning_rate": 2.3e-06,
|
| 424 |
+
"loss": 0.8038553237915039,
|
| 425 |
+
"step": 255,
|
| 426 |
+
"token_acc": 0.7727514635444386
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 0.2868174296745725,
|
| 430 |
+
"grad_norm": 5.2610053652109405,
|
| 431 |
+
"learning_rate": 2.3e-06,
|
| 432 |
+
"loss": 0.8923781394958497,
|
| 433 |
+
"step": 260,
|
| 434 |
+
"token_acc": 0.7542778918548939
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.29233314947600664,
|
| 438 |
+
"grad_norm": 5.613909953834712,
|
| 439 |
+
"learning_rate": 2.3e-06,
|
| 440 |
+
"loss": 0.8282554626464844,
|
| 441 |
+
"step": 265,
|
| 442 |
+
"token_acc": 0.7708383377372088
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 0.2978488692774407,
|
| 446 |
+
"grad_norm": 4.960174308621677,
|
| 447 |
+
"learning_rate": 2.3e-06,
|
| 448 |
+
"loss": 0.939533805847168,
|
| 449 |
+
"step": 270,
|
| 450 |
+
"token_acc": 0.745945945945946
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.3033645890788748,
|
| 454 |
+
"grad_norm": 5.338393166552948,
|
| 455 |
+
"learning_rate": 2.3e-06,
|
| 456 |
+
"loss": 0.7566696166992187,
|
| 457 |
+
"step": 275,
|
| 458 |
+
"token_acc": 0.7783882783882784
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.3088803088803089,
|
| 462 |
+
"grad_norm": 5.85539301408898,
|
| 463 |
+
"learning_rate": 2.3e-06,
|
| 464 |
+
"loss": 0.7774906158447266,
|
| 465 |
+
"step": 280,
|
| 466 |
+
"token_acc": 0.778774673160728
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.314396028681743,
|
| 470 |
+
"grad_norm": 5.5554378762103305,
|
| 471 |
+
"learning_rate": 2.3e-06,
|
| 472 |
+
"loss": 0.8302905082702636,
|
| 473 |
+
"step": 285,
|
| 474 |
+
"token_acc": 0.7736331119059785
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.31991174848317705,
|
| 478 |
+
"grad_norm": 5.64607545742485,
|
| 479 |
+
"learning_rate": 2.3e-06,
|
| 480 |
+
"loss": 0.8949955940246582,
|
| 481 |
+
"step": 290,
|
| 482 |
+
"token_acc": 0.7522200563136235
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.32542746828461117,
|
| 486 |
+
"grad_norm": 5.545223764081705,
|
| 487 |
+
"learning_rate": 2.3e-06,
|
| 488 |
+
"loss": 0.9496533393859863,
|
| 489 |
+
"step": 295,
|
| 490 |
+
"token_acc": 0.739816799844085
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 0.3309431880860452,
|
| 494 |
+
"grad_norm": 5.102348588101583,
|
| 495 |
+
"learning_rate": 2.3e-06,
|
| 496 |
+
"loss": 0.8521288871765137,
|
| 497 |
+
"step": 300,
|
| 498 |
+
"token_acc": 0.7637759710930443
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 0.33645890788747934,
|
| 502 |
+
"grad_norm": 5.799379698214005,
|
| 503 |
+
"learning_rate": 2.3e-06,
|
| 504 |
+
"loss": 0.8561582565307617,
|
| 505 |
+
"step": 305,
|
| 506 |
+
"token_acc": 0.7558797909407665
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.3419746276889134,
|
| 510 |
+
"grad_norm": 5.245842611420519,
|
| 511 |
+
"learning_rate": 2.3e-06,
|
| 512 |
+
"loss": 0.855079460144043,
|
| 513 |
+
"step": 310,
|
| 514 |
+
"token_acc": 0.7621547591874002
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.3474903474903475,
|
| 518 |
+
"grad_norm": 5.339700948065717,
|
| 519 |
+
"learning_rate": 2.3e-06,
|
| 520 |
+
"loss": 0.8615094184875488,
|
| 521 |
+
"step": 315,
|
| 522 |
+
"token_acc": 0.7575689616505943
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.3530060672917816,
|
| 526 |
+
"grad_norm": 5.608312178321082,
|
| 527 |
+
"learning_rate": 2.3e-06,
|
| 528 |
+
"loss": 0.8664688110351563,
|
| 529 |
+
"step": 320,
|
| 530 |
+
"token_acc": 0.7657678244972578
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 0.35852178709321564,
|
| 534 |
+
"grad_norm": 5.41193963454708,
|
| 535 |
+
"learning_rate": 2.3e-06,
|
| 536 |
+
"loss": 0.83935546875,
|
| 537 |
+
"step": 325,
|
| 538 |
+
"token_acc": 0.7757989753598439
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 0.36403750689464975,
|
| 542 |
+
"grad_norm": 5.220504527588121,
|
| 543 |
+
"learning_rate": 2.3e-06,
|
| 544 |
+
"loss": 0.8449893951416015,
|
| 545 |
+
"step": 330,
|
| 546 |
+
"token_acc": 0.772705078125
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 0.3695532266960838,
|
| 550 |
+
"grad_norm": 5.4190449827537135,
|
| 551 |
+
"learning_rate": 2.3e-06,
|
| 552 |
+
"loss": 0.8168981552124024,
|
| 553 |
+
"step": 335,
|
| 554 |
+
"token_acc": 0.7692491630798661
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 0.37506894649751793,
|
| 558 |
+
"grad_norm": 5.590435008250206,
|
| 559 |
+
"learning_rate": 2.3e-06,
|
| 560 |
+
"loss": 0.8648731231689453,
|
| 561 |
+
"step": 340,
|
| 562 |
+
"token_acc": 0.7575426322693485
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.380584666298952,
|
| 566 |
+
"grad_norm": 5.174005161957214,
|
| 567 |
+
"learning_rate": 2.3e-06,
|
| 568 |
+
"loss": 0.9896360397338867,
|
| 569 |
+
"step": 345,
|
| 570 |
+
"token_acc": 0.7302983932670237
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.3861003861003861,
|
| 574 |
+
"grad_norm": 5.511715259575185,
|
| 575 |
+
"learning_rate": 2.3e-06,
|
| 576 |
+
"loss": 0.8663737297058105,
|
| 577 |
+
"step": 350,
|
| 578 |
+
"token_acc": 0.7572226268511775
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.39161610590182017,
|
| 582 |
+
"grad_norm": 5.295113853870287,
|
| 583 |
+
"learning_rate": 2.3e-06,
|
| 584 |
+
"loss": 0.8019681930541992,
|
| 585 |
+
"step": 355,
|
| 586 |
+
"token_acc": 0.7747044917257683
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 0.3971318257032543,
|
| 590 |
+
"grad_norm": 5.2190425564256415,
|
| 591 |
+
"learning_rate": 2.3e-06,
|
| 592 |
+
"loss": 0.8304034233093261,
|
| 593 |
+
"step": 360,
|
| 594 |
+
"token_acc": 0.7567389875082183
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 0.40264754550468834,
|
| 598 |
+
"grad_norm": 5.594923827868745,
|
| 599 |
+
"learning_rate": 2.3e-06,
|
| 600 |
+
"loss": 0.8835367202758789,
|
| 601 |
+
"step": 365,
|
| 602 |
+
"token_acc": 0.7492839832562238
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 0.40816326530612246,
|
| 606 |
+
"grad_norm": 5.399822330777811,
|
| 607 |
+
"learning_rate": 2.3e-06,
|
| 608 |
+
"loss": 0.8703033447265625,
|
| 609 |
+
"step": 370,
|
| 610 |
+
"token_acc": 0.7619047619047619
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 0.4136789851075565,
|
| 614 |
+
"grad_norm": 5.718517969581787,
|
| 615 |
+
"learning_rate": 2.3e-06,
|
| 616 |
+
"loss": 0.7746540069580078,
|
| 617 |
+
"step": 375,
|
| 618 |
+
"token_acc": 0.7788509162951956
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.41919470490899063,
|
| 622 |
+
"grad_norm": 5.358207310874379,
|
| 623 |
+
"learning_rate": 2.3e-06,
|
| 624 |
+
"loss": 0.7805415630340576,
|
| 625 |
+
"step": 380,
|
| 626 |
+
"token_acc": 0.7823351786612984
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.4247104247104247,
|
| 630 |
+
"grad_norm": 5.240031526062139,
|
| 631 |
+
"learning_rate": 2.3e-06,
|
| 632 |
+
"loss": 0.892514419555664,
|
| 633 |
+
"step": 385,
|
| 634 |
+
"token_acc": 0.7574438845625286
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.4302261445118588,
|
| 638 |
+
"grad_norm": 5.090203604118294,
|
| 639 |
+
"learning_rate": 2.3e-06,
|
| 640 |
+
"loss": 0.7661482810974121,
|
| 641 |
+
"step": 390,
|
| 642 |
+
"token_acc": 0.7836170737725142
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 0.43574186431329287,
|
| 646 |
+
"grad_norm": 5.270675577305129,
|
| 647 |
+
"learning_rate": 2.3e-06,
|
| 648 |
+
"loss": 0.7520760059356689,
|
| 649 |
+
"step": 395,
|
| 650 |
+
"token_acc": 0.7893167028199566
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 0.441257584114727,
|
| 654 |
+
"grad_norm": 5.4625302980431165,
|
| 655 |
+
"learning_rate": 2.3e-06,
|
| 656 |
+
"loss": 0.8551373481750488,
|
| 657 |
+
"step": 400,
|
| 658 |
+
"token_acc": 0.7630287450338864
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 0.44677330391616105,
|
| 662 |
+
"grad_norm": 5.249069454600804,
|
| 663 |
+
"learning_rate": 2.3e-06,
|
| 664 |
+
"loss": 0.910746955871582,
|
| 665 |
+
"step": 405,
|
| 666 |
+
"token_acc": 0.7516659262549977
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 0.45228902371759516,
|
| 670 |
+
"grad_norm": 5.236854652942137,
|
| 671 |
+
"learning_rate": 2.3e-06,
|
| 672 |
+
"loss": 0.8199291229248047,
|
| 673 |
+
"step": 410,
|
| 674 |
+
"token_acc": 0.7682183767974653
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.4578047435190292,
|
| 678 |
+
"grad_norm": 6.027185729170618,
|
| 679 |
+
"learning_rate": 2.3e-06,
|
| 680 |
+
"loss": 0.8450562477111816,
|
| 681 |
+
"step": 415,
|
| 682 |
+
"token_acc": 0.7607934655775963
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.46332046332046334,
|
| 686 |
+
"grad_norm": 4.870989267188852,
|
| 687 |
+
"learning_rate": 2.3e-06,
|
| 688 |
+
"loss": 0.9044759750366211,
|
| 689 |
+
"step": 420,
|
| 690 |
+
"token_acc": 0.7498462169366413
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.4688361831218974,
|
| 694 |
+
"grad_norm": 5.291951695042281,
|
| 695 |
+
"learning_rate": 2.3e-06,
|
| 696 |
+
"loss": 0.8467486381530762,
|
| 697 |
+
"step": 425,
|
| 698 |
+
"token_acc": 0.7576541612764123
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 0.4743519029233315,
|
| 702 |
+
"grad_norm": 5.62593903563829,
|
| 703 |
+
"learning_rate": 2.3e-06,
|
| 704 |
+
"loss": 0.8833629608154296,
|
| 705 |
+
"step": 430,
|
| 706 |
+
"token_acc": 0.7509285051067781
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 0.4798676227247656,
|
| 710 |
+
"grad_norm": 5.128799172526207,
|
| 711 |
+
"learning_rate": 2.3e-06,
|
| 712 |
+
"loss": 0.8988676071166992,
|
| 713 |
+
"step": 435,
|
| 714 |
+
"token_acc": 0.7490849938999593
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 0.4853833425261997,
|
| 718 |
+
"grad_norm": 5.239699648307152,
|
| 719 |
+
"learning_rate": 2.3e-06,
|
| 720 |
+
"loss": 0.7166192054748535,
|
| 721 |
+
"step": 440,
|
| 722 |
+
"token_acc": 0.7969401947148818
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 0.49089906232763375,
|
| 726 |
+
"grad_norm": 5.4681083200632905,
|
| 727 |
+
"learning_rate": 2.3e-06,
|
| 728 |
+
"loss": 0.9467007637023925,
|
| 729 |
+
"step": 445,
|
| 730 |
+
"token_acc": 0.7396415494314897
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.49641478212906787,
|
| 734 |
+
"grad_norm": 4.685989886939226,
|
| 735 |
+
"learning_rate": 2.3e-06,
|
| 736 |
+
"loss": 0.7727291584014893,
|
| 737 |
+
"step": 450,
|
| 738 |
+
"token_acc": 0.7793472966390648
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.5019305019305019,
|
| 742 |
+
"grad_norm": 5.538988406196133,
|
| 743 |
+
"learning_rate": 2.3e-06,
|
| 744 |
+
"loss": 0.8206657409667969,
|
| 745 |
+
"step": 455,
|
| 746 |
+
"token_acc": 0.7731393129770993
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 0.507446221731936,
|
| 750 |
+
"grad_norm": 4.63939429197835,
|
| 751 |
+
"learning_rate": 2.3e-06,
|
| 752 |
+
"loss": 0.8562620162963868,
|
| 753 |
+
"step": 460,
|
| 754 |
+
"token_acc": 0.7662946428571429
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.5129619415333702,
|
| 758 |
+
"grad_norm": 5.1240560151191445,
|
| 759 |
+
"learning_rate": 2.3e-06,
|
| 760 |
+
"loss": 0.7872621536254882,
|
| 761 |
+
"step": 465,
|
| 762 |
+
"token_acc": 0.7787717601547389
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 0.5184776613348042,
|
| 766 |
+
"grad_norm": 5.189600840792027,
|
| 767 |
+
"learning_rate": 2.3e-06,
|
| 768 |
+
"loss": 0.8223024368286133,
|
| 769 |
+
"step": 470,
|
| 770 |
+
"token_acc": 0.7725631768953068
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 0.5239933811362383,
|
| 774 |
+
"grad_norm": 4.625349854858132,
|
| 775 |
+
"learning_rate": 2.3e-06,
|
| 776 |
+
"loss": 0.7645779609680176,
|
| 777 |
+
"step": 475,
|
| 778 |
+
"token_acc": 0.7779833487511564
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 0.5295091009376723,
|
| 782 |
+
"grad_norm": 5.392461676265602,
|
| 783 |
+
"learning_rate": 2.3e-06,
|
| 784 |
+
"loss": 0.863577938079834,
|
| 785 |
+
"step": 480,
|
| 786 |
+
"token_acc": 0.7583280288563548
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.5350248207391064,
|
| 790 |
+
"grad_norm": 5.809387834675999,
|
| 791 |
+
"learning_rate": 2.3e-06,
|
| 792 |
+
"loss": 0.7966668128967285,
|
| 793 |
+
"step": 485,
|
| 794 |
+
"token_acc": 0.7756534365924492
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.5405405405405406,
|
| 798 |
+
"grad_norm": 5.304450067691333,
|
| 799 |
+
"learning_rate": 2.3e-06,
|
| 800 |
+
"loss": 0.9444230079650879,
|
| 801 |
+
"step": 490,
|
| 802 |
+
"token_acc": 0.7450345423143351
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 0.5460562603419746,
|
| 806 |
+
"grad_norm": 5.583804788469441,
|
| 807 |
+
"learning_rate": 2.3e-06,
|
| 808 |
+
"loss": 0.9105037689208985,
|
| 809 |
+
"step": 495,
|
| 810 |
+
"token_acc": 0.7439771335238873
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 0.5515719801434087,
|
| 814 |
+
"grad_norm": 6.054938244093431,
|
| 815 |
+
"learning_rate": 2.3e-06,
|
| 816 |
+
"loss": 0.9297395706176758,
|
| 817 |
+
"step": 500,
|
| 818 |
+
"token_acc": 0.7482532288799492
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 0.5570876999448428,
|
| 822 |
+
"grad_norm": 5.391503075184599,
|
| 823 |
+
"learning_rate": 2.3e-06,
|
| 824 |
+
"loss": 0.846977424621582,
|
| 825 |
+
"step": 505,
|
| 826 |
+
"token_acc": 0.7518848526387937
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 0.5626034197462769,
|
| 830 |
+
"grad_norm": 5.030658472043065,
|
| 831 |
+
"learning_rate": 2.3e-06,
|
| 832 |
+
"loss": 0.8991237640380859,
|
| 833 |
+
"step": 510,
|
| 834 |
+
"token_acc": 0.7539121114683816
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 0.568119139547711,
|
| 838 |
+
"grad_norm": 5.104958695838692,
|
| 839 |
+
"learning_rate": 2.3e-06,
|
| 840 |
+
"loss": 0.8426759719848633,
|
| 841 |
+
"step": 515,
|
| 842 |
+
"token_acc": 0.7644656228727025
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.573634859349145,
|
| 846 |
+
"grad_norm": 6.009882223493915,
|
| 847 |
+
"learning_rate": 2.3e-06,
|
| 848 |
+
"loss": 0.7240866661071778,
|
| 849 |
+
"step": 520,
|
| 850 |
+
"token_acc": 0.7948649371489703
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.5791505791505791,
|
| 854 |
+
"grad_norm": 5.637457445639113,
|
| 855 |
+
"learning_rate": 2.3e-06,
|
| 856 |
+
"loss": 0.8636373519897461,
|
| 857 |
+
"step": 525,
|
| 858 |
+
"token_acc": 0.7649465787679018
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 0.5846662989520133,
|
| 862 |
+
"grad_norm": 5.3912830874814555,
|
| 863 |
+
"learning_rate": 2.3e-06,
|
| 864 |
+
"loss": 0.8545609474182129,
|
| 865 |
+
"step": 530,
|
| 866 |
+
"token_acc": 0.7600548446069469
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.5901820187534473,
|
| 870 |
+
"grad_norm": 5.223533669476021,
|
| 871 |
+
"learning_rate": 2.3e-06,
|
| 872 |
+
"loss": 0.7941525936126709,
|
| 873 |
+
"step": 535,
|
| 874 |
+
"token_acc": 0.7761698022190062
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 0.5956977385548814,
|
| 878 |
+
"grad_norm": 5.115121860566828,
|
| 879 |
+
"learning_rate": 2.3e-06,
|
| 880 |
+
"loss": 0.8650318145751953,
|
| 881 |
+
"step": 540,
|
| 882 |
+
"token_acc": 0.7646005817856344
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 0.6012134583563155,
|
| 886 |
+
"grad_norm": 4.715835836641467,
|
| 887 |
+
"learning_rate": 2.3e-06,
|
| 888 |
+
"loss": 0.8254315376281738,
|
| 889 |
+
"step": 545,
|
| 890 |
+
"token_acc": 0.7698187377156585
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 0.6067291781577496,
|
| 894 |
+
"grad_norm": 5.200096789536537,
|
| 895 |
+
"learning_rate": 2.3e-06,
|
| 896 |
+
"loss": 0.7865041255950928,
|
| 897 |
+
"step": 550,
|
| 898 |
+
"token_acc": 0.7788415509813308
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.6122448979591837,
|
| 902 |
+
"grad_norm": 5.62598549880936,
|
| 903 |
+
"learning_rate": 2.3e-06,
|
| 904 |
+
"loss": 0.9002869606018067,
|
| 905 |
+
"step": 555,
|
| 906 |
+
"token_acc": 0.7615146147032772
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.6177606177606177,
|
| 910 |
+
"grad_norm": 6.376332687516541,
|
| 911 |
+
"learning_rate": 2.3e-06,
|
| 912 |
+
"loss": 0.8603617668151855,
|
| 913 |
+
"step": 560,
|
| 914 |
+
"token_acc": 0.758905299739357
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 0.6232763375620518,
|
| 918 |
+
"grad_norm": 5.370356585251875,
|
| 919 |
+
"learning_rate": 2.3e-06,
|
| 920 |
+
"loss": 0.8701972961425781,
|
| 921 |
+
"step": 565,
|
| 922 |
+
"token_acc": 0.7542935653766888
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 0.628792057363486,
|
| 926 |
+
"grad_norm": 4.884591590707582,
|
| 927 |
+
"learning_rate": 2.3e-06,
|
| 928 |
+
"loss": 0.840721321105957,
|
| 929 |
+
"step": 570,
|
| 930 |
+
"token_acc": 0.7689443714410863
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 0.63430777716492,
|
| 934 |
+
"grad_norm": 5.138799986301503,
|
| 935 |
+
"learning_rate": 2.3e-06,
|
| 936 |
+
"loss": 0.7376739501953125,
|
| 937 |
+
"step": 575,
|
| 938 |
+
"token_acc": 0.7904834996162702
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 0.6398234969663541,
|
| 942 |
+
"grad_norm": 5.3450150515914885,
|
| 943 |
+
"learning_rate": 2.3e-06,
|
| 944 |
+
"loss": 0.755347728729248,
|
| 945 |
+
"step": 580,
|
| 946 |
+
"token_acc": 0.7790931989924433
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 0.6453392167677882,
|
| 950 |
+
"grad_norm": 4.895436117128604,
|
| 951 |
+
"learning_rate": 2.3e-06,
|
| 952 |
+
"loss": 0.8265247344970703,
|
| 953 |
+
"step": 585,
|
| 954 |
+
"token_acc": 0.7729456991830851
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.6508549365692223,
|
| 958 |
+
"grad_norm": 5.143509534036041,
|
| 959 |
+
"learning_rate": 2.3e-06,
|
| 960 |
+
"loss": 0.8215790748596191,
|
| 961 |
+
"step": 590,
|
| 962 |
+
"token_acc": 0.7608391608391608
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.6563706563706564,
|
| 966 |
+
"grad_norm": 5.082286518166302,
|
| 967 |
+
"learning_rate": 2.3e-06,
|
| 968 |
+
"loss": 0.8152825355529785,
|
| 969 |
+
"step": 595,
|
| 970 |
+
"token_acc": 0.7685413399058929
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 0.6618863761720905,
|
| 974 |
+
"grad_norm": 5.326424315651092,
|
| 975 |
+
"learning_rate": 2.3e-06,
|
| 976 |
+
"loss": 0.8500395774841308,
|
| 977 |
+
"step": 600,
|
| 978 |
+
"token_acc": 0.7704613957801993
|
| 979 |
+
}
|
| 980 |
+
],
|
| 981 |
+
"logging_steps": 5,
|
| 982 |
+
"max_steps": 907,
|
| 983 |
+
"num_input_tokens_seen": 0,
|
| 984 |
+
"num_train_epochs": 1,
|
| 985 |
+
"save_steps": 300,
|
| 986 |
+
"stateful_callbacks": {
|
| 987 |
+
"TrainerControl": {
|
| 988 |
+
"args": {
|
| 989 |
+
"should_epoch_stop": false,
|
| 990 |
+
"should_evaluate": false,
|
| 991 |
+
"should_log": false,
|
| 992 |
+
"should_save": true,
|
| 993 |
+
"should_training_stop": false
|
| 994 |
+
},
|
| 995 |
+
"attributes": {}
|
| 996 |
+
}
|
| 997 |
+
},
|
| 998 |
+
"total_flos": 1514130748997632.0,
|
| 999 |
+
"train_batch_size": 2,
|
| 1000 |
+
"trial_name": null,
|
| 1001 |
+
"trial_params": null
|
| 1002 |
+
}
|
checkpoint-600/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:18fd96b67c75b829732956d628c7144a777aafee73cff635baaf1b12e763548c
|
| 3 |
+
size 9592
|
checkpoint-600/video_preprocessor_config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"crop_size": null,
|
| 3 |
+
"data_format": "channels_first",
|
| 4 |
+
"default_to_square": true,
|
| 5 |
+
"device": null,
|
| 6 |
+
"do_center_crop": null,
|
| 7 |
+
"do_convert_rgb": true,
|
| 8 |
+
"do_normalize": true,
|
| 9 |
+
"do_rescale": true,
|
| 10 |
+
"do_resize": true,
|
| 11 |
+
"do_sample_frames": true,
|
| 12 |
+
"fps": 2,
|
| 13 |
+
"image_mean": [
|
| 14 |
+
0.5,
|
| 15 |
+
0.5,
|
| 16 |
+
0.5
|
| 17 |
+
],
|
| 18 |
+
"image_std": [
|
| 19 |
+
0.5,
|
| 20 |
+
0.5,
|
| 21 |
+
0.5
|
| 22 |
+
],
|
| 23 |
+
"input_data_format": null,
|
| 24 |
+
"max_frames": 768,
|
| 25 |
+
"merge_size": 2,
|
| 26 |
+
"min_frames": 4,
|
| 27 |
+
"num_frames": null,
|
| 28 |
+
"pad_size": null,
|
| 29 |
+
"patch_size": 16,
|
| 30 |
+
"processor_class": "Qwen3VLProcessor",
|
| 31 |
+
"resample": 3,
|
| 32 |
+
"rescale_factor": 0.00392156862745098,
|
| 33 |
+
"return_metadata": false,
|
| 34 |
+
"size": {
|
| 35 |
+
"longest_edge": 25165824,
|
| 36 |
+
"shortest_edge": 4096
|
| 37 |
+
},
|
| 38 |
+
"temporal_patch_size": 2,
|
| 39 |
+
"video_metadata": null,
|
| 40 |
+
"video_processor_type": "Qwen3VLVideoProcessor"
|
| 41 |
+
}
|
checkpoint-600/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|