Model save

README.md

@@ -1,17 +1,16 @@
 ---
 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
-- trl
-- sft
+- open-r1
 licence: license
 ---
 
-# Model Card for Qwen2.5-1.5B-Open-R1-Distill
+# Model Card for None
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct).
+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.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -20,14 +19,14 @@ 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="ChenDRAG/Qwen2.5-1.5B-Open-R1-Distill", device="cuda")
+generator = pipeline("text-generation", model="None", 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/ojbm1qwt) 
+[<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) 
 
 
 This model was trained with SFT.

all_results.json

@@ -1,8 +1,8 @@
 {
-    "total_flos": 2937605436813312.0,
-    "train_loss": 0.8297107517719269,
-    "train_runtime": 42.4708,
+    "total_flos": 427315691520.0,
+    "train_loss": 0.0,
+    "train_runtime": 2.1723,
     "train_samples": 100,
-    "train_samples_per_second": 2.355,
-    "train_steps_per_second": 0.141
+    "train_samples_per_second": 46.034,
+    "train_steps_per_second": 0.46
 }

config.json

@@ -23,7 +23,7 @@
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.49.0.dev0",
-  "use_cache": false,
+  "use_cache": true,
   "use_sliding_window": false,
   "vocab_size": 151936
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4734070617070f746b58b580fa2ddf9444e9a2b0b21faaeff0f0233be1222769
+oid sha256:92ebae36cd2df3923a2524f695d1a18f61dea8aaf923959966556af36d6e43ff
 size 3087467144

runs/Feb17_02-30-57_8f59999e8611/events.out.tfevents.1739759469.8f59999e8611.119099.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:977e270f83280329b32b2a7172282796430e10f43e6527c3c35e3fe5881fba77
+size 6272

runs/Feb17_02-33-36_8f59999e8611/events.out.tfevents.1739759635.8f59999e8611.123913.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22d7c11cd4029576ff26572239db75ce96d5efff623465bf328b8149fa59e5b3
+size 6209

runs/Feb17_02-36-20_8f59999e8611/events.out.tfevents.1739759798.8f59999e8611.130416.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04335c80070cf72380ba3ef095e9e5e71aed4745b09ebdb10a4f58030a936d59
+size 6210

train_results.json

@@ -1,8 +1,8 @@
 {
-    "total_flos": 2937605436813312.0,
-    "train_loss": 0.8297107517719269,
-    "train_runtime": 42.4708,
+    "total_flos": 427315691520.0,
+    "train_loss": 0.0,
+    "train_runtime": 2.1723,
     "train_samples": 100,
-    "train_samples_per_second": 2.355,
-    "train_steps_per_second": 0.141
+    "train_samples_per_second": 46.034,
+    "train_steps_per_second": 0.46
 }

trainer_state.json

@@ -1,34 +1,25 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.96,
-  "eval_steps": 100,
-  "global_step": 6,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 2,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.8,
-      "grad_norm": 1.609375,
-      "learning_rate": 1.9098300562505266e-06,
-      "loss": 0.8248,
-      "mean_token_accuracy": 0.7740710348407838,
-      "step": 5
-    },
-    {
-      "epoch": 0.96,
-      "mean_token_accuracy": 0.7635029501317351,
-      "step": 6,
-      "total_flos": 2937605436813312.0,
-      "train_loss": 0.8297107517719269,
-      "train_runtime": 42.4708,
-      "train_samples_per_second": 2.355,
-      "train_steps_per_second": 0.141
+      "epoch": 1.0,
+      "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
     }
   ],
-  "logging_steps": 5,
-  "max_steps": 6,
+  "logging_steps": 500,
+  "max_steps": 1,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 500,
@@ -38,13 +29,13 @@
         "should_epoch_stop": false,
         "should_evaluate": false,
         "should_log": false,
-        "should_save": false,
-        "should_training_stop": false
+        "should_save": true,
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2937605436813312.0,
+  "total_flos": 427315691520.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65529b6d979e05bcd41a7fc218b22003e53c740b022f317f959e3bad0ee633bd
+oid sha256:7a4d6fd11ad02d7543ed5a479292a62376452da8c54cfaec33b422758a4027fa
 size 6008