Model save

README.md

@@ -1,16 +1,17 @@
 ---
 base_model: Qwen/Qwen2.5-1.5B-Instruct
-datasets: ChenDRAG/OM220k
 library_name: transformers
+model_name: Qwen2.5-1.5B-Open-R1-Distill
 tags:
 - generated_from_trainer
-- open-r1
+- trl
+- sft
 licence: license
 ---
 
-# Model Card for None
+# 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 [ChenDRAG/OM220k](https://huggingface.co/datasets/ChenDRAG/OM220k) 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
@@ -19,14 +20,14 @@ It has been trained using [TRL](https://github.com/huggingface/trl).
 from transformers import pipeline
 
 question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
-generator = pipeline("text-generation", model="None", device="cuda")
+generator = pipeline("text-generation", model="ChenDRAG/Qwen2.5-1.5B-Open-R1-Distill", device="cuda")
 output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
 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/noteam2235/huggingface/runs/6bxdmvd8) 
+[<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/noteam2235/huggingface/runs/ctc7qeil) 
 
 
 This model was trained with SFT.

all_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 427315691520.0,
     "train_loss": 0.0,
-    "train_runtime": 2.1723,
+    "train_runtime": 3.3707,
     "train_samples": 100,
-    "train_samples_per_second": 46.034,
-    "train_steps_per_second": 0.46
+    "train_samples_per_second": 10.977,
+    "train_steps_per_second": 0.593
 }

config.json

@@ -23,7 +23,7 @@
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.49.0.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 sha256:92ebae36cd2df3923a2524f695d1a18f61dea8aaf923959966556af36d6e43ff
+oid sha256:081546ce9a9403a817de3a122319a951510c3396cd7631c26afdac41207fedc4
 size 3087467144

train_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 427315691520.0,
     "train_loss": 0.0,
-    "train_runtime": 2.1723,
+    "train_runtime": 3.3707,
     "train_samples": 100,
-    "train_samples_per_second": 46.034,
-    "train_steps_per_second": 0.46
+    "train_samples_per_second": 10.977,
+    "train_steps_per_second": 0.593
 }

trainer_state.json

@@ -13,13 +13,13 @@
       "step": 2,
       "total_flos": 427315691520.0,
       "train_loss": 0.0,
-      "train_runtime": 2.1723,
-      "train_samples_per_second": 46.034,
-      "train_steps_per_second": 0.46
+      "train_runtime": 3.3707,
+      "train_samples_per_second": 10.977,
+      "train_steps_per_second": 0.593
     }
   ],
   "logging_steps": 500,
-  "max_steps": 1,
+  "max_steps": 2,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 500,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a4d6fd11ad02d7543ed5a479292a62376452da8c54cfaec33b422758a4027fa
+oid sha256:61d29d81d710536ac7d16eccea481e3bdb272b565be4989aeb12e5534122506f
 size 6008