Model save

README.md

@@ -36,11 +36,11 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 3
+- train_batch_size: 2
 - eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 8
-- total_train_batch_size: 24
+- gradient_accumulation_steps: 64
+- total_train_batch_size: 128
 - optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: constant
 - lr_scheduler_warmup_ratio: 0.03

runs/Mar12_18-55-21_ip-10-246-124-97/events.out.tfevents.1741805731.ip-10-246-124-97.4081.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c289b0a8210c7a31432089d3051a76ab4fbc1d98315048370756036c1e1d1977
-size 7097
+oid sha256:1863d0b7bdf58ffe13813659aba8ce41ca22dd4786e45d551cd868acd4389788
+size 7445