Model save

README.md

@@ -38,15 +38,15 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 1
+- train_batch_size: 16
 - eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 8
-- total_train_batch_size: 8
+- total_train_batch_size: 128
 - 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
+- num_epochs: 5
 
 ### Training results
 

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e752b8471e58ae2dd6f1c9cf0b8773c5cac7c770ea21af39523c57c44eabdf21
+oid sha256:b0e0ea9aa8f78cce58ebe3db78f86f1a8e1e1848729b825b8d9f31f7a95899f3
 size 3208737208

runs/Sep09_09-05-54_hpcsgn04/events.out.tfevents.1725872766.hpcsgn04.2550794.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4389c7a8cf61068b87086b3bb5bf2c4cc58777c4cd56e0769fc1046f54f0261
-size 5913
+oid sha256:440351f2e80bb0b6c458ef8c3a015b6be7a87f3c5ea82e21aec7b5abf5002617
+size 6261