Model save

README.md

@@ -14,7 +14,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model was trained from scratch on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2963
+- eval_loss: 0.3947
+- eval_runtime: 1.0892
+- eval_samples_per_second: 82.628
+- eval_steps_per_second: 11.017
+- epoch: 6.0
+- step: 4842
 
 ## Model description
 
@@ -40,23 +45,7 @@ The following hyperparameters were used during training:
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: cosine_with_restarts
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 10.0
-
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 1.076         | 1.0   | 807  | 0.7889          |
-| 0.9412        | 2.0   | 1614 | 0.5343          |
-| 0.5653        | 3.0   | 2421 | 0.4825          |
-| 0.6135        | 4.0   | 3228 | 0.4739          |
-| 0.5656        | 5.0   | 4035 | 0.4182          |
-| 0.3505        | 6.0   | 4842 | 0.3435          |
-| 0.1471        | 7.0   | 5649 | 0.3291          |
-| 0.3406        | 8.0   | 6456 | 0.3240          |
-| 0.2795        | 9.0   | 7263 | 0.3131          |
-| 0.1624        | 10.0  | 8070 | 0.2963          |
-
+- num_epochs: 100.0
 
 ### Framework versions
 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60775266ea854a4cfee5090bbba80acd5d169eab1853f2d2a4e0b9e3417e7e85
+oid sha256:b803b18b9b815bf6ab8c1517a4e22064d26d75d126644651a3f2ae1fea27b545
 size 496281000