update model card README.md

README.md

@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.0437
+- Loss: 1.7110
 
 ## Model description
 
@@ -34,11 +34,9 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0001
-- train_batch_size: 32
-- eval_batch_size: 64
+- train_batch_size: 128
+- eval_batch_size: 256
 - seed: 42
-- gradient_accumulation_steps: 8
-- total_train_batch_size: 256
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.1
@@ -47,23 +45,13 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 6.3538 | 0.32 | 500 | 4.7231 |
-| 4.2863 | 0.64 | 1000 | 3.7473 |
-| 3.5828 | 0.96 | 1500 | 3.2410 |
-| 3.1699 | 1.28 | 2000 | 2.9410 |
-| 2.9123 | 1.6 | 2500 | 2.7295 |
-| 2.7413 | 1.92 | 3000 | 2.5568 |
-| 2.5181 | 2.24 | 3500 | 2.4281 |
-| 2.394 | 2.56 | 4000 | 2.3263 |
-| 2.3157 | 2.88 | 4500 | 2.2393 |
-| 2.1822 | 3.2 | 5000 | 2.1750 |
-| 2.091 | 3.52 | 5500 | 2.1231 |
-| 2.0489 | 3.84 | 6000 | 2.0844 |
-| 1.9873 | 4.16 | 6500 | 2.0609 |
-| 1.9335 | 4.48 | 7000 | 2.0487 |
-| 1.9307 | 4.8 | 7500 | 2.0437 |
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 3.7436 | 1.0 | 12796 | 2.5429 |
+| 2.3292 | 2.0 | 25592 | 2.0711 |
+| 1.9439 | 3.0 | 38388 | 1.8447 |
+| 1.7059 | 4.0 | 51184 | 1.7325 |
+| 1.5775 | 5.0 | 63980 | 1.7110 |
 
 
 ### Framework versions