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_ins-pt-bf16
 tags:
 - generated_from_trainer
-- open-r1
 - trl
 - sft
 licence: license
@@ -13,7 +11,7 @@ licence: license
 
 # Model Card for qwen2.5_1.5b_ins-pt-bf16
 
-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/sheepy928/r1fp4/runs/a00adzvk) 
+ 
 
 
 This model was trained with SFT.

all_results.json

@@ -5,9 +5,9 @@
     "eval_samples_per_second": 7.147,
     "eval_steps_per_second": 0.893,
     "total_flos": 768626978193408.0,
-    "train_loss": 2.0993992060908564,
-    "train_runtime": 74825.3444,
-    "train_samples": 16610,
-    "train_samples_per_second": 2.888,
-    "train_steps_per_second": 0.09
+    "train_loss": 0.0,
+    "train_runtime": 1.3815,
+    "train_samples": 1000,
+    "train_samples_per_second": 2424.882,
+    "train_steps_per_second": 152.008
 }

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": 151665
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 768626978193408.0,
-    "train_loss": 2.0993992060908564,
-    "train_runtime": 74825.3444,
-    "train_samples": 16610,
-    "train_samples_per_second": 2.888,
-    "train_steps_per_second": 0.09
+    "train_loss": 0.0,
+    "train_runtime": 1.3815,
+    "train_samples": 1000,
+    "train_samples_per_second": 2424.882,
+    "train_steps_per_second": 152.008
 }

trainer_state.json

@@ -571,17 +571,16 @@
     },
     {
       "epoch": 9.985936343449296,
-      "mean_token_accuracy": 0.638465811965812,
       "step": 6750,
       "total_flos": 768626978193408.0,
-      "train_loss": 2.0993992060908564,
-      "train_runtime": 74825.3444,
-      "train_samples_per_second": 2.888,
-      "train_steps_per_second": 0.09
+      "train_loss": 0.0,
+      "train_runtime": 1.3815,
+      "train_samples_per_second": 2424.882,
+      "train_steps_per_second": 152.008
     }
   ],
   "logging_steps": 200,
-  "max_steps": 6750,
+  "max_steps": 210,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 10,
   "save_steps": 500,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f17d98c150bdf9c737a07533dad8e08c6b61155597b70938a02299b0ad1a6d4
-size 7160
+oid sha256:63001b5aa7df486aef58ad93dc19fc01e6610c1d3a104d0728864438cdf62595
+size 5816