Model save

README.md

@@ -1,11 +1,9 @@
 ---
 base_model: Qwen/Qwen2.5-1.5B-Instruct
-datasets: open-r1/OpenR1-Math-220k
 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 [open-r1/OpenR1-Math-220k](https://huggingface.co/datasets/open-r1/OpenR1-Math-220k) 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/iiau_video/huggingface/runs/4yfktfsq) 
+[<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/iiau_video/huggingface/runs/tl1l9xcs) 
 
 
 This model was trained with SFT.

all_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 1.0370150067486065e+19,
-    "train_loss": 0.6670452614286247,
-    "train_runtime": 10315.9028,
+    "train_loss": 0.0,
+    "train_runtime": 2.1944,
     "train_samples": 93733,
-    "train_samples_per_second": 9.086,
-    "train_steps_per_second": 0.142
+    "train_samples_per_second": 42714.599,
+    "train_steps_per_second": 667.608
 }

config.json

@@ -23,7 +23,7 @@
   "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": 1.0370150067486065e+19,
-    "train_loss": 0.6670452614286247,
-    "train_runtime": 10315.9028,
+    "train_loss": 0.0,
+    "train_runtime": 2.1944,
     "train_samples": 93733,
-    "train_samples_per_second": 9.086,
-    "train_steps_per_second": 0.142
+    "train_samples_per_second": 42714.599,
+    "train_steps_per_second": 667.608
 }

trainer_state.json

@@ -2357,10 +2357,10 @@
       "epoch": 1.0,
       "step": 1465,
       "total_flos": 1.0370150067486065e+19,
-      "train_loss": 0.6670452614286247,
-      "train_runtime": 10315.9028,
-      "train_samples_per_second": 9.086,
-      "train_steps_per_second": 0.142
+      "train_loss": 0.0,
+      "train_runtime": 2.1944,
+      "train_samples_per_second": 42714.599,
+      "train_steps_per_second": 667.608
     }
   ],
   "logging_steps": 5,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d290fe4a0d8434b2518f5721b65cfac6a5224c126f1d13de1e1c6071b0934229
+oid sha256:213aedc9d673323bc7ec203d4f39d68c485e314dd34fbddd5bef710a0f5072d6
 size 5944