End of training

README.md

@@ -1,15 +1,17 @@
 ---
 base_model: openai-community/gpt2
+datasets: HuggingFaceFW/fineweb-edu
 library_name: transformers
 model_name: gpt2-RMT-2
 tags:
 - generated_from_trainer
+- open-r1
 licence: license
 ---
 
 # Model Card for gpt2-RMT-2
 
-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

@@ -1,8 +1,8 @@
 {
-    "eval_runtime": 0.22,
+    "eval_runtime": 0.4815,
     "eval_samples": 100,
-    "eval_samples_per_second": 218.143,
-    "eval_steps_per_second": 13.634,
+    "eval_samples_per_second": 99.696,
+    "eval_steps_per_second": 12.462,
     "total_flos": 0.0,
     "train_loss": 4.772621268656716,
     "train_runtime": 29.2884,

config.json

@@ -32,8 +32,7 @@
       "max_length": 50
     }
   },
-  "torch_dtype": "bfloat16",
   "transformers_version": "4.50.0.dev0",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 50257
 }

eval_results.json

@@ -1,6 +1,6 @@
 {
-    "eval_runtime": 0.22,
+    "eval_runtime": 0.4815,
     "eval_samples": 100,
-    "eval_samples_per_second": 218.143,
-    "eval_steps_per_second": 13.634
+    "eval_samples_per_second": 99.696,
+    "eval_steps_per_second": 12.462
 }