End of training

README.md

@@ -33,16 +33,15 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.001
-- train_batch_size: 64
-- eval_batch_size: 16
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 256
+- total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 100
 - num_epochs: 4
-- mixed_precision_training: Native AMP
 
 ### Training results
 

adapter.mus.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b681dbf74aa2fd2690d0da68c7c31106d5bfee6d57e214b8a0e79c6eeedfab8
+oid sha256:412a9ed5d1763a8790f73c63ea77294851b317bd79ce5ee382e25ddd8ef994c5
 size 8834400

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4632d5761f6ab76bacda01d973e73f46112985f3e0e464593f8f1c0ad5178418
+oid sha256:25a4d46f71c2c7f7ed91e0e8dcd9e911ee23df2bb8aacd4690851a447e175957
 size 3858926736

runs/May19_18-46-40_patas-gn3/events.out.tfevents.1716170375.patas-gn3.735544.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:942494903b189eb939ff98f66f6e0640ca360ad38c79e20eba0a75d7ad402c3b
+size 446

runs/May19_22-25-58_patas-gn2/events.out.tfevents.1716182767.patas-gn2.1327345.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac4b9eeed2963c8b8a8072aff65fb96ff2ad4a479fecc24c7aeaa8be6e2fc497
+size 6464

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1539ae51f695e8f19871303447f899cba09bd537470d8a07074273d286a371ab
+oid sha256:ec7d4c201ec703d2fb169aafcfa2f848c46c1d43f8586727a1dabf3a388a653f
 size 4527