End of training

README.md

@@ -1,9 +1,11 @@
 ---
 base_model: KotshinZ/gpt2-RMT-7
+datasets: HuggingFaceFW/fineweb-edu
 library_name: transformers
 model_name: gpt2-RMT-8
 tags:
 - generated_from_trainer
+- open-r1
 - trl
 - sft
 licence: license
@@ -11,7 +13,7 @@ licence: license
 
 # Model Card for gpt2-RMT-8
 
-This model is a fine-tuned version of [KotshinZ/gpt2-RMT-7](https://huggingface.co/KotshinZ/gpt2-RMT-7).
+This model is a fine-tuned version of [KotshinZ/gpt2-RMT-7](https://huggingface.co/KotshinZ/gpt2-RMT-7) 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

@@ -1,4 +1,8 @@
 {
+    "eval_runtime": 0.2777,
+    "eval_samples": 100,
+    "eval_samples_per_second": 43.211,
+    "eval_steps_per_second": 3.601,
     "total_flos": 5452245613150208.0,
     "train_loss": 3.1222703313253013,
     "train_runtime": 348.715,

eval_results.json

@@ -1,7 +1,6 @@
 {
-    "eval_loss": 1.9101824760437012,
-    "eval_runtime": 2.9445,
+    "eval_runtime": 0.2777,
     "eval_samples": 100,
-    "eval_samples_per_second": 372.563,
-    "eval_steps_per_second": 93.395
+    "eval_samples_per_second": 43.211,
+    "eval_steps_per_second": 3.601
 }