End of training

README.md

@@ -36,8 +36,8 @@ The following hyperparameters were used during training:
 - seed: 42
 - distributed_type: multi-GPU
 - num_devices: 2
-- gradient_accumulation_steps: 64
-- total_train_batch_size: 2048
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 512
 - total_eval_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c63605532bcac5521fabe43c6e609d9102ad4bf4bc88dc20b57962b94330b20d
+oid sha256:1e237becf7503296526376f7495ba57eae7f011ca4039801958b7738a7fe3678
 size 2023586384

runs/Jun29_12-31-08_dgx-51/events.out.tfevents.1719635552.dgx-51.1119244.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4d41956e2909044b95bc1a7a1b41028852459ca8cf847a9956144583f8b0036
+size 981944

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:752effdf0ab330d6a6b2c2c2afb19b10c704c71176c89b41ed387bb1a0ab50c3
-size 6968
+oid sha256:cdeda7ed914475cbffebbc009ec5c33ad2f07cd0e20927a1acb00e6d3c6ccf23
+size 7160