End of training

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 6.7928
+- Loss: 7.6745
 
 ## Model description
 
@@ -43,18 +43,15 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
-- num_epochs: 5
+- num_epochs: 2
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| No log        | 0.9655 | 7    | 7.2346          |
-| 6.9032        | 1.9310 | 14   | 7.0206          |
-| 6.1385        | 2.8966 | 21   | 6.8292          |
-| 6.1385        | 4.0    | 29   | 6.8003          |
-| 5.8596        | 4.8276 | 35   | 6.7928          |
+| No log        | 0.9655 | 7    | 8.0728          |
+| 8.6453        | 1.9310 | 14   | 7.6745          |
 
 
 ### Framework versions

generation_config.json

@@ -1,6 +1,6 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 50256,
+  "bos_token_id": 0,
   "eos_token_id": "<|endoftext|>",
   "transformers_version": "4.44.2"
 }