Model save

README.md

@@ -1,11 +1,9 @@
 ---
 base_model: Qwen/Qwen2.5-Math-1.5B-Instruct
-datasets: flyingbugs/OpenR1-Math-220k-pruned-keep-0.5-end-start-0.5
 library_name: transformers
 model_name: Qwen2.5-1.5B-Open-R1-Distill-eos-epic
 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-eos-epic
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-Math-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Math-1.5B-Instruct) on the [flyingbugs/OpenR1-Math-220k-pruned-keep-0.5-end-start-0.5](https://huggingface.co/datasets/flyingbugs/OpenR1-Math-220k-pruned-keep-0.5-end-start-0.5) dataset.
+This model is a fine-tuned version of [Qwen/Qwen2.5-Math-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Math-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/jjh233/huggingface/runs/3r9dxsmv) 
+[<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/jjh233/huggingface/runs/kqqiclkk) 
 
 
 This model was trained with SFT.

all_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 962656789856256.0,
     "train_loss": 0.0,
-    "train_runtime": 1.0579,
+    "train_runtime": 0.9086,
     "train_samples": 93733,
-    "train_samples_per_second": 63710.085,
-    "train_steps_per_second": 499.109
+    "train_samples_per_second": 74179.853,
+    "train_steps_per_second": 581.129
 }

config.json

@@ -39,7 +39,7 @@
     "full_attention",
     "full_attention"
   ],
-  "max_position_embeddings": 4096,
+  "max_position_embeddings": 32768,
   "max_window_layers": 21,
   "model_type": "qwen2",
   "num_attention_heads": 12,
@@ -47,12 +47,12 @@
   "num_key_value_heads": 2,
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
-  "rope_theta": 10000.0,
+  "rope_theta": 300000.0,
   "sliding_window": null,
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.54.0",
-  "use_cache": true,
+  "use_cache": false,
   "use_sliding_window": false,
   "vocab_size": 151936
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 962656789856256.0,
     "train_loss": 0.0,
-    "train_runtime": 1.0579,
+    "train_runtime": 0.9086,
     "train_samples": 93733,
-    "train_samples_per_second": 63710.085,
-    "train_steps_per_second": 499.109
+    "train_samples_per_second": 74179.853,
+    "train_steps_per_second": 581.129
 }

trainer_state.json

@@ -749,9 +749,9 @@
       "step": 528,
       "total_flos": 962656789856256.0,
       "train_loss": 0.0,
-      "train_runtime": 1.0579,
-      "train_samples_per_second": 63710.085,
-      "train_steps_per_second": 499.109
+      "train_runtime": 0.9086,
+      "train_samples_per_second": 74179.853,
+      "train_steps_per_second": 581.129
     }
   ],
   "logging_steps": 5,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b92e82046467d743bafc37b78b07bdde765260981b7b2c7ed14341172f5ea31
+oid sha256:67da04646652ec9d2434e4c07428c19d09a1fc76aa0f4b1534eab216b437bf58
 size 8017