End of training

README.md

@@ -36,8 +36,8 @@ The following hyperparameters were used during training:
 - seed: 42
 - distributed_type: multi-GPU
 - num_devices: 8
-- gradient_accumulation_steps: 8
-- total_train_batch_size: 512
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 256
 - total_eval_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant_with_warmup

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24da273f3000a1644ddb512fb200018f650003544d27794946bf0c24a219bb8f
+oid sha256:ae4f9a9590ec058e29cd31f1971a0c5361e9309a0be99d1693919d24dfeef268
 size 4977795456

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bafd078a24a31dc7505cb51806bb354366d77267052fc81b95955c7bae14fa2
+oid sha256:5b70bed7b603a639d0c1507df512824601da5e750cd8da6a4021d8436d091ddc
 size 4967384136

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:444dbf6860e8b5d52032db39624651f3aef77ef8ce9c12aeff433122741a70b9
+oid sha256:9a9e1a815f1da55f2d3522630ac918de2a9abcbe51b97bf99145add8dfcbdc24
 size 3769470736

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e93f5707962db6cf5f0e547b37611c17913e6102cd15868c6bdbaeba1bee6edb
+oid sha256:ac80e464e836a59de9c574a59a96864bfbea03c1bc3f823d0c40ab928706566a
 size 7224