Model save

README.md

@@ -1,8 +1,8 @@
 ---
-license: mit
+license: other
+base_model: apple/OpenELM-270M
 tags:
 - generated_from_trainer
-base_model: gpt2
 model-index:
 - name: gpt2-evy
   results: []
@@ -13,9 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # gpt2-evy
 
-This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
+This model is a fine-tuned version of [apple/OpenELM-270M](https://huggingface.co/apple/OpenELM-270M) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.3026
+- Loss: 2.1525
 
 ## Model description
 
@@ -35,24 +35,28 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 1
+- train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 7
+- num_epochs: 20
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 54   | 1.4017          |
-| 1.3671        | 2.0   | 108  | 1.3194          |
-| 1.3671        | 3.0   | 162  | 1.3072          |
-| 0.957         | 4.0   | 216  | 1.3015          |
-| 0.957         | 5.0   | 270  | 1.2899          |
-| 0.729         | 6.0   | 324  | 1.3037          |
-| 0.729         | 7.0   | 378  | 1.3026          |
+| No log        | 1.0   | 4    | 1.3157          |
+| No log        | 2.0   | 8    | 1.3995          |
+| No log        | 3.0   | 12   | 1.5098          |
+| No log        | 4.0   | 16   | 1.6855          |
+| No log        | 5.0   | 20   | 1.7936          |
+| No log        | 6.0   | 24   | 1.8727          |
+| No log        | 7.0   | 28   | 1.9813          |
+| No log        | 8.0   | 32   | 2.0602          |
+| No log        | 9.0   | 36   | 2.1174          |
+| No log        | 10.0  | 40   | 2.1440          |
+| No log        | 11.0  | 44   | 2.1525          |
 
 
 ### Framework versions

generation_config.json

@@ -1,6 +1,6 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 50256,
-  "eos_token_id": 50256,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
   "transformers_version": "4.40.1"
 }