Model save

README.md

@@ -38,16 +38,20 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 3
+- train_batch_size: 1
 - eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 8
-- total_train_batch_size: 24
+- gradient_accumulation_steps: 16
+- 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
 - num_epochs: 3
 
+### Training results
+
+
+
 ### Framework versions
 
 - PEFT 0.12.0

runs/Feb16_17-37-14_ip-172-31-3-189/events.out.tfevents.1739727451.ip-172-31-3-189.1963.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d89bcd60f2afc85bc8e31ae164a9846c6b1ed6b0cf7625fcf8978f831840965f
-size 7307
+oid sha256:c3b672746a5219828b282c6f001894732e39ed8d6c5032d58c9a903b2598769f
+size 7655