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
-- eval_batch_size: 2
+- train_batch_size: 1
+- eval_batch_size: 1
 - seed: 42
 - gradient_accumulation_steps: 2
-- total_train_batch_size: 6
+- total_train_batch_size: 2
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant
 - lr_scheduler_warmup_ratio: 0.03

runs/Feb06_11-53-34_a1bf0fb7a359/events.out.tfevents.1707220423.a1bf0fb7a359.1311.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf4863642258debaeb5a7dd3cd52e458238eadfa918d2fcd6360b928fad1a5a6
-size 5251
+oid sha256:fb9ffbc10c77829824bd6e069da27c4f1fcf87d3b54844e16640bdab891fdf44
+size 5599