Model save

README.md

@@ -1,17 +1,15 @@
 ---
 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) on the [HuggingFaceH4/Bespoke-Stratos-17k](https://huggingface.co/datasets/HuggingFaceH4/Bespoke-Stratos-17k) dataset.
+This model is a fine-tuned version of [openai-community/gpt2](https://huggingface.co/openai-community/gpt2).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -27,14 +25,14 @@ print(output["generated_text"])
 
 ## Training procedure
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/s18574s18574-/huggingface/runs/6c36vz5o) 
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/s18574s18574-/huggingface/runs/qz7kfrzp) 
 
 
 This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.16.0.dev0
+- TRL: 0.15.2
 - Transformers: 4.50.0.dev0
 - Pytorch: 2.5.1
 - Datasets: 3.3.2

all_results.json

@@ -1,12 +1,12 @@
 {
-    "eval_runtime": 4.1108,
+    "eval_runtime": 0.22,
     "eval_samples": 100,
-    "eval_samples_per_second": 266.861,
-    "eval_steps_per_second": 66.898,
+    "eval_samples_per_second": 218.143,
+    "eval_steps_per_second": 13.634,
     "total_flos": 0.0,
-    "train_loss": 2.0137617991367285,
-    "train_runtime": 996.2065,
-    "train_samples": 16610,
-    "train_samples_per_second": 92.083,
-    "train_steps_per_second": 5.756
+    "train_loss": 4.772621268656716,
+    "train_runtime": 29.2884,
+    "train_samples": 19883,
+    "train_samples_per_second": 36.093,
+    "train_steps_per_second": 2.288
 }

config.json

@@ -1,6 +1,5 @@
 {
   "_attn_implementation_autoset": true,
-  "_name_or_path": "openai-community/gpt2",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -35,6 +34,6 @@
   },
   "torch_dtype": "bfloat16",
   "transformers_version": "4.50.0.dev0",
-  "use_cache": true,
+  "use_cache": false,
   "vocab_size": 50257
 }

eval_results.json

@@ -1,6 +1,6 @@
 {
-    "eval_runtime": 4.1108,
+    "eval_runtime": 0.22,
     "eval_samples": 100,
-    "eval_samples_per_second": 266.861,
-    "eval_steps_per_second": 66.898
+    "eval_samples_per_second": 218.143,
+    "eval_steps_per_second": 13.634
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:992d4bcdb3356997a0a168440f993d5c27b000e48ba6ea568caf99b214bf322f
+oid sha256:2e3c2740535e03f24f5cb574ba61bf881f6b6c33883fc13ee4948a731051a5ab
 size 326110968

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e07ea7caa7f567049c6ac949b18c3c222e52a15c44b05ed9bc048bb7eda52472
+size 248944286

tokenizer_config.json

@@ -11,7 +11,6 @@
     }
   },
   "bos_token": "<|endoftext|>",
-  "chat_template": "{% for message in messages %}{{ message['role'] }}: {{ message['content'] }}\n{% endfor %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
   "extra_special_tokens": {},

train_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 2.0137617991367285,
-    "train_runtime": 996.2065,
-    "train_samples": 16610,
-    "train_samples_per_second": 92.083,
-    "train_steps_per_second": 5.756
+    "train_loss": 4.772621268656716,
+    "train_runtime": 29.2884,
+    "train_samples": 19883,
+    "train_samples_per_second": 36.093,
+    "train_steps_per_second": 2.288
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdef709c27929e8ae9c8e3a5424f8df2c8a0dc367fd631551cc0f01060414d18
+oid sha256:be3f4e5fc95a8a097fc233c1e01227f2b9fb455b30c25f6543ddfec1b328f220
 size 7352