End of training

README.md

@@ -1,15 +1,17 @@
 ---
 base_model: openai-community/gpt2
+datasets: HuggingFaceH4/Bespoke-Stratos-17k
 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 [HuggingFaceH4/Bespoke-Stratos-17k](https://huggingface.co/datasets/HuggingFaceH4/Bespoke-Stratos-17k) dataset.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

all_results.json

@@ -1,8 +1,8 @@
 {
-    "eval_runtime": 0.2427,
+    "eval_runtime": 2.7326,
     "eval_samples": 100,
-    "eval_samples_per_second": 197.801,
-    "eval_steps_per_second": 12.363,
+    "eval_samples_per_second": 208.955,
+    "eval_steps_per_second": 52.33,
     "total_flos": 0.0,
     "train_loss": 3.0202497909698995,
     "train_runtime": 60.0371,

config.json

@@ -1,7 +1,8 @@
 {
+  "_attn_implementation_autoset": true,
   "activation_function": "gelu_new",
   "architectures": [
-    "RecurrentWrapper"
+    "GPT2LMHeadModel"
   ],
   "attn_pdrop": 0.1,
   "bos_token_id": 50256,

eval_results.json

@@ -1,6 +1,6 @@
 {
-    "eval_runtime": 0.2427,
+    "eval_runtime": 2.7326,
     "eval_samples": 100,
-    "eval_samples_per_second": 197.801,
-    "eval_steps_per_second": 12.363
+    "eval_samples_per_second": 208.955,
+    "eval_steps_per_second": 52.33
 }