End of training

README.md

@@ -34,15 +34,15 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0001
-- train_batch_size: 16
+- train_batch_size: 8
 - eval_batch_size: 2
 - seed: 42
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 64
+- total_train_batch_size: 32
 - optimizer: Use adamw_torch 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: 100
-- training_steps: 2000
+- training_steps: 10000
 - mixed_precision_training: Native AMP
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7a8ab768b55bb68e0b30489e1896bb03431ef0798f7eba38dd7b800ea77e07c
+oid sha256:159596209f61ff6b789f3cceed0c4cb2b83e67ce690c85c53f5be13699cb41f7
 size 617574792

runs/Nov16_23-00-16_45fc0e654a1d/events.out.tfevents.1731798021.45fc0e654a1d.738.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd9636957235fb4e6caf858ef26bff28198c7ad6d27f073c16c4c5db434e42aa
-size 22243
+oid sha256:33e08fd981d021be3848e61dbe69c90f09a0e0a0e0c7b64c339c658c75a1dd76
+size 35717

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96e6d57b65a000697afea5bd48e4a5fdb9b0a243504aabb2a95325a2d9cf422c
+oid sha256:bc9d81b843d6be93816be420c3c290ece402abef62527f97a246e9ca42a5d107
 size 5432