Model save

README.md

@@ -1,11 +1,9 @@
 ---
 base_model: Qwen/Qwen2.5-1.5B-Instruct
-datasets: HuggingFaceH4/Bespoke-Stratos-17k
 library_name: transformers
 model_name: Qwen2.5-1.5B-Open-R1-Distill
 tags:
 - generated_from_trainer
-- open-r1
 - trl
 - sft
 licence: license
@@ -13,7 +11,7 @@ licence: license
 
 # Model Card for Qwen2.5-1.5B-Open-R1-Distill
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) on the [HuggingFaceH4/Bespoke-Stratos-17k](https://huggingface.co/datasets/HuggingFaceH4/Bespoke-Stratos-17k) dataset.
+This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct).
 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/fandou-team/huggingface/runs/h4rp27ul) 
+[<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/fandou-team/huggingface/runs/mlhp0slv) 
 
 
 This model was trained with SFT.

all_results.json

@@ -1,13 +1,13 @@
 {
-    "eval_loss": 0.8163658380508423,
-    "eval_runtime": 27.8561,
+    "eval_loss": 0.8189318776130676,
+    "eval_runtime": 25.7782,
     "eval_samples": 100,
-    "eval_samples_per_second": 4.631,
-    "eval_steps_per_second": 1.185,
-    "total_flos": 6.963239723036836e+17,
-    "train_loss": 0.8130570470603183,
-    "train_runtime": 16907.9466,
-    "train_samples": 16610,
-    "train_samples_per_second": 1.279,
-    "train_steps_per_second": 0.16
+    "eval_samples_per_second": 5.004,
+    "eval_steps_per_second": 1.28,
+    "total_flos": 7.883277455484518e+16,
+    "train_loss": 1.23619465266957,
+    "train_runtime": 1783.7305,
+    "train_samples": 1000,
+    "train_samples_per_second": 1.374,
+    "train_steps_per_second": 0.172
 }

config.json

@@ -23,7 +23,7 @@
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.50.0.dev0",
-  "use_cache": true,
+  "use_cache": false,
   "use_sliding_window": false,
   "vocab_size": 151936
 }

eval_results.json

@@ -1,7 +1,7 @@
 {
-    "eval_loss": 0.8163658380508423,
-    "eval_runtime": 27.8561,
+    "eval_loss": 0.8189318776130676,
+    "eval_runtime": 25.7782,
     "eval_samples": 100,
-    "eval_samples_per_second": 4.631,
-    "eval_steps_per_second": 1.185
+    "eval_samples_per_second": 5.004,
+    "eval_steps_per_second": 1.28
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff8f07333721657a12a144e73f781bf470a8869ed07001d138e2af54909caa49
+oid sha256:6b9e135338ccbcb41894671cf453ef57e6c7d91ab38971f504ddf7c18121e9bd
 size 3087467144

train_results.json

@@ -1,8 +1,8 @@
 {
-    "total_flos": 6.963239723036836e+17,
-    "train_loss": 0.8130570470603183,
-    "train_runtime": 16907.9466,
-    "train_samples": 16610,
-    "train_samples_per_second": 1.279,
-    "train_steps_per_second": 0.16
+    "total_flos": 7.883277455484518e+16,
+    "train_loss": 1.23619465266957,
+    "train_runtime": 1783.7305,
+    "train_samples": 1000,
+    "train_samples_per_second": 1.374,
+    "train_steps_per_second": 0.172
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a3aaedae259de62814cdd89a22b1c443e5268d04cc8991a790e5ba09aea0031
+oid sha256:16e0eecb3877ce3141a1924f2e9b7e2d1875869ac04ca58d2b2c3de4cdb406a1
 size 6008