End of training

README.md

@@ -33,15 +33,15 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0005
-- train_batch_size: 1
+- train_batch_size: 2
 - eval_batch_size: 20
 - seed: 42
 - gradient_accumulation_steps: 128
-- total_train_batch_size: 128
+- total_train_batch_size: 256
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 1000
-- num_epochs: 2
+- num_epochs: 50
 - mixed_precision_training: Native AMP
 
 ### Training results

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:324cc28a196240d0ecc23730222054f8e99ad25bc2ef3bdd2399f34dc1c3a33a
+oid sha256:dd868c2043b883addee755c09ba3254435651e9403558298e58c3da3e1c84286
 size 497774208

runs/Jan25_14-52-44_4335406a8083/events.out.tfevents.1706194365.4335406a8083.3018.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d26e236536ab494ccffe535778a5bbb927bfafd67674a28a1bdc88c6d81fb0a
+size 4860

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:672f9a01c8810fa2b9fe5e11cbf1ffcb5b1e1ce487e77fe0e91fb9bdfd55850c
+oid sha256:a415cd808b2cf27e4244a92abe0ebba0662a1e5dac2f00bc93f234d1ba9df7b6
 size 4536