End of training

README.md

@@ -33,15 +33,15 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0005
-- train_batch_size: 3
+- train_batch_size: 4
 - eval_batch_size: 20
 - seed: 42
 - gradient_accumulation_steps: 128
-- total_train_batch_size: 384
+- total_train_batch_size: 512
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 1000
-- num_epochs: 50
+- num_epochs: 20
 - mixed_precision_training: Native AMP
 
 ### Training results

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:634215e2779d1ba8171e25055378316c8f119c382f18b56a3c62eea16c9a24a2
+oid sha256:7ab13d7f6d3e036a3c8e49ef2818461c817fb7561347c0a5264e680af1c59186
 size 497774208

runs/Jan25_16-34-42_88ad906a8219/events.out.tfevents.1706200483.88ad906a8219.185.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84e309fc496e22b0f071e2f759999f61a550788e2aecd112ecd6f2007cb584d4
+size 4862

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53c0a87fefaafd26a0a7b80c221d9c9f087c42fbc83aac1f088f15d9bc0cce9c
+oid sha256:a2219aa01133f6277081082e2deeb3c963ca7463df419565afe452339bed9aa9
 size 4536