Model save

README.md

@@ -56,6 +56,8 @@ The following hyperparameters were used during training:
 - train_batch_size: 32
 - eval_batch_size: 32
 - seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 128
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
@@ -63,13 +65,13 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.0           | 1.0   | 47   | nan             | 0.4890   |
-| 0.0           | 2.0   | 94   | nan             | 0.4890   |
-| 0.0           | 3.0   | 141  | nan             | 0.4890   |
-| 0.0           | 4.0   | 188  | nan             | 0.4890   |
-| 0.0           | 5.0   | 235  | nan             | 0.4890   |
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
+|:-------------:|:------:|:----:|:---------------:|:--------:|
+| 0.0           | 0.9362 | 11   | nan             | 0.4890   |
+| 0.0           | 1.9574 | 23   | nan             | 0.4890   |
+| 0.0           | 2.9787 | 35   | nan             | 0.4890   |
+| 0.0           | 4.0    | 47   | nan             | 0.4890   |
+| 0.0           | 4.6809 | 55   | nan             | 0.4890   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9b84a6340a0458daa4a0e3b1e040dd4844afc189be7a88a1672b8991b71b586
+oid sha256:780eabfb1ede8e9e88f021a6b3eb3e36687167bee7cd7ec380ba2499c1df5c17
 size 94302952