Model save

README.md

@@ -1,11 +1,9 @@
 ---
 base_model: Qwen/Qwen3-0.6B
-datasets: dnotitia/Magpie_Claude35_no_think_1k_samples
 library_name: transformers
 model_name: Qwen3-0.6B-Distill
 tags:
 - generated_from_trainer
-- open-r1
 - trl
 - sft
 licence: license
@@ -13,7 +11,7 @@ licence: license
 
 # Model Card for Qwen3-0.6B-Distill
 
-This model is a fine-tuned version of [Qwen/Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B) on the [dnotitia/Magpie_Claude35_no_think_1k_samples](https://huggingface.co/datasets/dnotitia/Magpie_Claude35_no_think_1k_samples) dataset.
+This model is a fine-tuned version of [Qwen/Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -29,7 +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/jeehwon/huggingface/runs/7aj0t15a) 
+[<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/jeehwon/huggingface/runs/wmyciqe4) 
 
 
 This model was trained with SFT.

all_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 241025679360.0,
-    "train_loss": 1.798710823059082,
-    "train_runtime": 28.1411,
+    "train_loss": 0.0,
+    "train_runtime": 1.8142,
     "train_samples": 1000,
-    "train_samples_per_second": 35.535,
-    "train_steps_per_second": 0.284
+    "train_samples_per_second": 551.204,
+    "train_steps_per_second": 4.41
 }

config.json

@@ -24,7 +24,7 @@
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.52.0.dev0",
-  "use_cache": true,
+  "use_cache": false,
   "use_sliding_window": false,
   "vocab_size": 151936
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 241025679360.0,
-    "train_loss": 1.798710823059082,
-    "train_runtime": 28.1411,
+    "train_loss": 0.0,
+    "train_runtime": 1.8142,
     "train_samples": 1000,
-    "train_samples_per_second": 35.535,
-    "train_steps_per_second": 0.284
+    "train_samples_per_second": 551.204,
+    "train_steps_per_second": 4.41
 }

trainer_state.json

@@ -19,13 +19,12 @@
     },
     {
       "epoch": 1.0,
-      "num_tokens": 341202.0,
       "step": 8,
       "total_flos": 241025679360.0,
-      "train_loss": 1.798710823059082,
-      "train_runtime": 28.1411,
-      "train_samples_per_second": 35.535,
-      "train_steps_per_second": 0.284
+      "train_loss": 0.0,
+      "train_runtime": 1.8142,
+      "train_samples_per_second": 551.204,
+      "train_steps_per_second": 4.41
     }
   ],
   "logging_steps": 5,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ef742d59d27360db3fe16667eb3c58136e19765240fb3cc3b01780091d55532
+oid sha256:bcc81f5e1ddde42d1d153d91507165b3de763cc592147a0d5a963c5e5a807b85
 size 7288