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
@@ -27,7 +25,7 @@ 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/qiwktvbf) 
+[<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/ov7s46ya) 
 
 
 This model was trained with SFT.

all_results.json

@@ -1,12 +1,8 @@
 {
-    "eval_runtime": 4.1628,
-    "eval_samples": 100,
-    "eval_samples_per_second": 263.526,
-    "eval_steps_per_second": 66.062,
     "total_flos": 0.0,
-    "train_loss": 2.839574353448276,
-    "train_runtime": 8.9764,
+    "train_loss": 2.8374191810344827,
+    "train_runtime": 8.8944,
     "train_samples": 16610,
-    "train_samples_per_second": 102.195,
-    "train_steps_per_second": 6.461
+    "train_samples_per_second": 103.136,
+    "train_steps_per_second": 6.521
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58d5e0dc13a323943aae2894b7668f8dbe8ce152207af552e1747c76b2052c2d
+oid sha256:69f688ffe91216be05cfd64b0ce40b518c8f32580576fa7393b2e094b090329c
 size 326110968

train_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 2.839574353448276,
-    "train_runtime": 8.9764,
+    "train_loss": 2.8374191810344827,
+    "train_runtime": 8.8944,
     "train_samples": 16610,
-    "train_samples_per_second": 102.195,
-    "train_steps_per_second": 6.461
+    "train_samples_per_second": 103.136,
+    "train_steps_per_second": 6.521
 }

trainer_state.json

@@ -10,53 +10,53 @@
   "log_history": [
     {
       "epoch": 0.0008720676724513823,
-      "grad_norm": 8.504547119140625,
+      "grad_norm": 9.03160572052002,
       "learning_rate": 1.9709418174260523e-05,
-      "loss": 3.0672,
-      "mean_token_accuracy": 0.4417563572525978,
+      "loss": 3.068,
+      "mean_token_accuracy": 0.44124266058206557,
       "step": 10
     },
     {
       "epoch": 0.0017441353449027645,
-      "grad_norm": 7.896213531494141,
+      "grad_norm": 15.666545867919922,
       "learning_rate": 1.6631226582407954e-05,
-      "loss": 2.9109,
-      "mean_token_accuracy": 0.44279598593711855,
+      "loss": 2.9078,
+      "mean_token_accuracy": 0.4430650696158409,
       "step": 20
     },
     {
       "epoch": 0.002616203017354147,
-      "grad_norm": 5.716647148132324,
+      "grad_norm": 16.191038131713867,
       "learning_rate": 1.1205366802553231e-05,
       "loss": 2.8492,
-      "mean_token_accuracy": 0.4517245590686798,
+      "mean_token_accuracy": 0.45182240307331084,
       "step": 30
     },
     {
       "epoch": 0.003488270689805529,
-      "grad_norm": 11.646272659301758,
+      "grad_norm": 10.86160945892334,
       "learning_rate": 5.352768279562315e-06,
-      "loss": 2.7641,
-      "mean_token_accuracy": 0.45660469830036166,
+      "loss": 2.7617,
+      "mean_token_accuracy": 0.4569960877299309,
       "step": 40
     },
     {
       "epoch": 0.004360338362256911,
-      "grad_norm": 85.00694274902344,
+      "grad_norm": 14.749295234680176,
       "learning_rate": 1.1454397434679022e-06,
-      "loss": 2.6703,
-      "mean_token_accuracy": 0.46954501122236253,
+      "loss": 2.6656,
+      "mean_token_accuracy": 0.47067025154829023,
       "step": 50
     },
     {
       "epoch": 0.005057992500218017,
-      "mean_token_accuracy": 0.4595768079161644,
+      "mean_token_accuracy": 0.45992845110595226,
       "step": 58,
       "total_flos": 0.0,
-      "train_loss": 2.839574353448276,
-      "train_runtime": 8.9764,
-      "train_samples_per_second": 102.195,
-      "train_steps_per_second": 6.461
+      "train_loss": 2.8374191810344827,
+      "train_runtime": 8.8944,
+      "train_samples_per_second": 103.136,
+      "train_steps_per_second": 6.521
     }
   ],
   "logging_steps": 10,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:687b30bdda8c062f901bc710f949dce7a9b706604d6917216cf1a525db3f22c7
+oid sha256:2f5848278ac435ff22cb803cb15c110d68ebe13c30adcb298632fdfa7845ac04
 size 7352