End of training

README.md

@@ -1,9 +1,11 @@
 ---
 base_model: openai-community/gpt2
+datasets: HuggingFaceFW/fineweb-edu
 library_name: transformers
 model_name: gpt2-SFT
 tags:
 - generated_from_trainer
+- open-r1
 - trl
 - sft
 licence: license
@@ -11,7 +13,7 @@ licence: license
 
 # Model Card for gpt2-SFT
 
-This model is a fine-tuned version of [openai-community/gpt2](https://huggingface.co/openai-community/gpt2).
+This model is a fine-tuned version of [openai-community/gpt2](https://huggingface.co/openai-community/gpt2) on the [HuggingFaceFW/fineweb-edu](https://huggingface.co/datasets/HuggingFaceFW/fineweb-edu) dataset.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

all_results.json

@@ -1,9 +1,9 @@
 {
-    "eval_loss": 1.6588891744613647,
-    "eval_runtime": 2.2929,
+    "eval_loss": 2.982074737548828,
+    "eval_runtime": 1.7363,
     "eval_samples": 100,
-    "eval_samples_per_second": 239.436,
-    "eval_steps_per_second": 60.186,
+    "eval_samples_per_second": 53.562,
+    "eval_steps_per_second": 6.911,
     "total_flos": 15459466346496.0,
     "train_loss": 3.207212707142771,
     "train_runtime": 884.063,

config.json

@@ -33,6 +33,6 @@
   },
   "torch_dtype": "bfloat16",
   "transformers_version": "4.50.0.dev0",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 50257
 }

eval_results.json

@@ -1,7 +1,7 @@
 {
-    "eval_loss": 1.6588891744613647,
-    "eval_runtime": 2.2929,
+    "eval_loss": 2.982074737548828,
+    "eval_runtime": 1.7363,
     "eval_samples": 100,
-    "eval_samples_per_second": 239.436,
-    "eval_steps_per_second": 60.186
+    "eval_samples_per_second": 53.562,
+    "eval_steps_per_second": 6.911
 }