End of training

README.md

@@ -34,12 +34,12 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0001
-- train_batch_size: 4
+- train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 4
+- gradient_accumulation_steps: 2
 - total_train_batch_size: 16
-- optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- optimizer: Use OptimizerNames.ADAMW_HF with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 50
 - num_epochs: 3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f79e83febb25aa96705b16c551dacf6391a44e8d51024268fc2f2045ca2a267
+oid sha256:8ae883dbec5aeb4362f75208ed3c0cebd36a93fa76ebf6aadc383bb5173b36f6
 size 1015025832

runs/Feb09_16-20-37_c2086264edf0/events.out.tfevents.1739118046.c2086264edf0.4250.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e33b571a47ee7e2be1f4734686be09d285667ef9276d44b23f70e607f4b373a2
+size 8244

runs/Feb09_16-22-08_c2086264edf0/events.out.tfevents.1739118131.c2086264edf0.4250.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5187f7bbe47fc88daab045f93eed1bf5338e8dbf4a284986ecd9a37c383541c5
+size 8591

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a26aa2a0b96a5561a973dd8942e124c0d14780ced24a069310fee894815331f8
+oid sha256:2f7e07f79cd208495acbf6f3bef5b23b1f1819a24fc298c9f787c72895d3311b
 size 5368