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-bi
 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-bi
 
-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/gx7biz59) 
+[<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/84w7xho9) 
 
 
 This model was trained with SFT.

all_results.json

@@ -1,17 +1,8 @@
 {
-    "eval_reasoning_loss": 0.8857828378677368,
-    "eval_reasoning_runtime": 28.8571,
-    "eval_reasoning_samples_per_second": 4.47,
-    "eval_reasoning_steps_per_second": 1.144,
-    "eval_samples": 100,
-    "eval_utility_loss": 1.152946949005127,
-    "eval_utility_runtime": 10.899,
-    "eval_utility_samples_per_second": 4.496,
-    "eval_utility_steps_per_second": 1.193,
     "total_flos": 0.0,
-    "train_loss": 2.020134010978244,
-    "train_runtime": 33509.3321,
+    "train_loss": 2.0463369701511103,
+    "train_runtime": 33791.3424,
     "train_samples": 16610,
-    "train_samples_per_second": 0.645,
-    "train_steps_per_second": 0.081
+    "train_samples_per_second": 0.64,
+    "train_steps_per_second": 0.08
 }

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
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14baa8bc510eca0e32f01713bd9ad4c0d569dfa03a88290ad31c62a537fd06f6
+oid sha256:2705ec14c9a45e0c5c39c302aa3f7bb701584199d84c28f205f18a435bf1628c
 size 3087467144

train_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 2.020134010978244,
-    "train_runtime": 33509.3321,
+    "train_loss": 2.0463369701511103,
+    "train_runtime": 33791.3424,
     "train_samples": 16610,
-    "train_samples_per_second": 0.645,
-    "train_steps_per_second": 0.081
+    "train_samples_per_second": 0.64,
+    "train_steps_per_second": 0.08
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90616ac6b4ffd35fd1e28a627ec2a90584ca3f0b29d25dcaeb1486aef983a8e5
+oid sha256:9542005676ca25c23c61de82538dd4403881d0f7319af9ac1b14e2854ec4cd07
 size 6008