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: 22
+- train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 2
-- total_train_batch_size: 44
+- total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant
 - lr_scheduler_warmup_ratio: 0.03

runs/Feb06_11-39-13_2a876dc09aa4/events.out.tfevents.1707219564.2a876dc09aa4.1574.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96f979a5c53d586e6ff184bc7b20bff19db2d5dd11cfbd079a0a9a977bfcffb4
-size 5251
+oid sha256:34afb2395d113d9b2ef7d03c211c821c1814474c6b2f719bae774c99482062f2
+size 5599