End of training

README.md

@@ -1,9 +1,11 @@
 ---
 base_model: openai-community/gpt2
+datasets: HuggingFaceFW/fineweb-edu
 library_name: transformers
 model_name: gpt2-RMT-2-mem512
 tags:
 - generated_from_trainer
+- open-r1
 - trl
 - sft
 licence: license
@@ -11,7 +13,7 @@ licence: license
 
 # Model Card for gpt2-RMT-2-mem512
 
-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": 7.8522,
+    "eval_runtime": 0.3782,
     "eval_samples": 100,
-    "eval_samples_per_second": 376.2,
-    "eval_steps_per_second": 23.56,
+    "eval_samples_per_second": 245.873,
+    "eval_steps_per_second": 15.863,
     "total_flos": 5418484972388352.0,
     "train_loss": 3.606253622488408,
     "train_runtime": 424.9732,

eval_results.json

@@ -1,6 +1,6 @@
 {
-    "eval_runtime": 7.8522,
+    "eval_runtime": 0.3782,
     "eval_samples": 100,
-    "eval_samples_per_second": 376.2,
-    "eval_steps_per_second": 23.56
+    "eval_samples_per_second": 245.873,
+    "eval_steps_per_second": 15.863
 }