End of training

README.md

@@ -14,6 +14,8 @@ should probably proofread and complete it, then remove this comment. -->
 # redit_gpt
 
 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: 3.4867
 
 ## Model description
 
@@ -41,11 +43,18 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 1000
-- num_epochs: 1
+- num_epochs: 3
 - mixed_precision_training: Native AMP
 
 ### Training results
 
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 5.2446        | 0.5891 | 1000 | 4.2133          |
+| 3.9883        | 1.1782 | 2000 | 3.7935          |
+| 3.7198        | 1.7673 | 3000 | 3.6230          |
+| 3.5341        | 2.3564 | 4000 | 3.5221          |
+| 3.4378        | 2.9455 | 5000 | 3.4867          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fc8b244f4430e5264f14daf0b40ca2d5ab5a953e89d4be4b1c4b2daca3c3008
+oid sha256:47eb29c5d8bf6367e35de2e30cd46e862be5fd81e375a3d1681984f6f6c0cdf8
 size 497774208