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/wiz-llm/huggingface/runs/jltfpdg4) 
+[<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/wiz-llm/huggingface/runs/qwehe2lf) 
 
 
 This model was trained with SFT.

all_results.json

@@ -4,10 +4,10 @@
     "eval_samples": 100,
     "eval_samples_per_second": 50.773,
     "eval_steps_per_second": 4.33,
-    "total_flos": 6.086450124265882e+17,
-    "train_loss": 0.7795855527453952,
-    "train_runtime": 1563.698,
+    "total_flos": 6.0804602683856e+18,
+    "train_loss": 0.5375538207954831,
+    "train_runtime": 15535.6447,
     "train_samples": 16610,
-    "train_samples_per_second": 13.828,
-    "train_steps_per_second": 0.288
+    "train_samples_per_second": 13.918,
+    "train_steps_per_second": 0.29
 }

config.json

@@ -23,7 +23,7 @@
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.48.3",
-  "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 sha256:2dcd2f149cdef4158a6f23e8179407ab9d448909d1b650d4ffc367022325264b
+oid sha256:79be26674747a92c23413f08e44c7cda7dc644283a42139f7403826c25f86b45
 size 3087467144

train_results.json

@@ -1,8 +1,8 @@
 {
-    "total_flos": 6.086450124265882e+17,
-    "train_loss": 0.7795855527453952,
-    "train_runtime": 1563.698,
+    "total_flos": 6.0804602683856e+18,
+    "train_loss": 0.5375538207954831,
+    "train_runtime": 15535.6447,
     "train_samples": 16610,
-    "train_samples_per_second": 13.828,
-    "train_steps_per_second": 0.288
+    "train_samples_per_second": 13.918,
+    "train_steps_per_second": 0.29
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72122ccf30f93fbe97f780dc2c7f02967ca49a5b985b874b480e08ff0d47af57
+oid sha256:f003acc175b2c1e0fbe739697792557688335760d4528d999ed43c23d3e9be10
 size 7416