Training in progress, step 620

README.md

@@ -4,11 +4,8 @@ library_name: transformers
 model_name: Qwen3-4B-Base-SFT-tr5
 tags:
 - generated_from_trainer
-- trackio
-- sft
 - trl
-- trackio:https://huggingface.co/spaces/hf-imo-colab/trackio-distillation-sft
-- trl-internal
+- sft
 licence: license
 ---
 
@@ -30,7 +27,7 @@ print(output["generated_text"])
 
 ## Training procedure
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/huggingface/imo-distillation/runs/fvlg88kc) 
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/huggingface/imo-distillation/runs/rwhiohbr) 
 
 
 This model was trained with SFT.

config.json

@@ -65,7 +65,7 @@
   "sliding_window": null,
   "tie_word_embeddings": true,
   "transformers_version": "5.3.0.dev0",
-  "use_cache": true,
+  "use_cache": false,
   "use_sliding_window": false,
   "vocab_size": 151936
 }

generation_config.json

@@ -1,6 +1,8 @@
 {
   "do_sample": false,
-  "eos_token_id": 151643,
+  "eos_token_id": [
+    151643
+  ],
   "max_new_tokens": 2048,
   "pad_token_id": 151643,
   "transformers_version": "5.3.0.dev0"

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12b69e1833887117f3ab0c686945d0c483eb3ab0f3e34574d274c1b004d4fe6b
+oid sha256:68f82c8594386b72e0be03c688f8a7c1c3b2d46ddb0a79d49888cb430b43940c
 size 8044982080

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a282ed565619bce54554b67302f59d5f8ed0657bb4cbb1e7ce5d17dc4b3b765
+oid sha256:6455c6ec9c97ef7bba70922931b589528f81f5237ba44cf493b1ed5856fe4135
 size 7569