Model save

README.md

@@ -41,7 +41,7 @@ The following hyperparameters were used during training:
 - seed: 42
 - gradient_accumulation_steps: 4
 - total_train_batch_size: 16
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- 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
 - num_epochs: 100
@@ -54,7 +54,7 @@ The following hyperparameters were used during training:
 ### Framework versions
 
 - PEFT 0.13.2
-- Transformers 4.44.2
+- Transformers 4.46.1
 - Pytorch 2.5.0+cu121
 - Datasets 3.0.2
-- Tokenizers 0.19.1
+- Tokenizers 0.20.1

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3b2f7b103e26ef3974fa84fb4dc551da14ed5390a13d80d8636a4d30368ded1
+oid sha256:f32ffec62a97f2b64cb0af15a99ae7b88ab6c0ff7807f08986f8102205d4d7da
 size 73430448

runs/Oct29_21-06-16_a7cc945e97ed/events.out.tfevents.1730236103.a7cc945e97ed.3776.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a676b1959d3838a400c87e5bfc787ce37cccc8ab51ddbf12b56d3d34d624e10c
-size 5539
+oid sha256:9096b14f57574e836a7798718a0a3b98012598f39b34a8c57156458f2203c378
+size 5887