End of training

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/bert_uncased_L-4_H-256_A-4](https://huggingface.co/google/bert_uncased_L-4_H-256_A-4) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.6978
+- Loss: 1.8908
 
 ## Model description
 
@@ -46,11 +46,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step  | Validation Loss |
 |:-------------:|:-----:|:-----:|:---------------:|
-| 1.7784        | 1.0   | 2609  | 1.7227          |
-| 1.7718        | 2.0   | 5218  | 1.7214          |
-| 1.7689        | 3.0   | 7827  | 1.6998          |
-| 1.7564        | 4.0   | 10436 | 1.7032          |
-| 1.7456        | 5.0   | 13045 | 1.6978          |
+| 1.9632        | 1.0   | 2609  | 1.9119          |
+| 1.9577        | 2.0   | 5218  | 1.9042          |
+| 1.9384        | 3.0   | 7827  | 1.9122          |
+| 1.9366        | 4.0   | 10436 | 1.8922          |
+| 1.9389        | 5.0   | 13045 | 1.8908          |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5ac48948a09b21a50b4e9ff89122ddcb26e9997cc120028155e9493f3df8246
+oid sha256:e8dae4c620ce240794226525c489e29d4ef72bde1d24c6cc6fa700c714ee16d5
 size 44831439