End of training

README.md

@@ -31,13 +31,13 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 3e-06
-- train_batch_size: 4
+- train_batch_size: 14
 - eval_batch_size: 8
 - seed: 42
 - distributed_type: multi-GPU
 - num_devices: 8
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 128
+- total_train_batch_size: 448
 - total_eval_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1353e5e7205ba13fbad2302a4289d7ccac4993d1de74ea5edf7856e190ca7f7b
+oid sha256:aef21d2cd287e183b30e9d742ab0df6f2c867f8e7d17234aa15d89ca8e177531
 size 4945242264

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29127715776aab33698d9e4349edea76cbfc487f56e188bdda01b6f57561e062
+oid sha256:fefa2c12ef73d5c994d9ab94bfe284386b4b3c3a7def090412f523a7470fac65
 size 67121608

runs/Aug03_14-04-32_p1-r01-n2.pok.ibm.com/events.out.tfevents.1722708345.p1-r01-n2.pok.ibm.com.1129041.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84f8f063a934431a3460006a1f3123dc3cfa67062dd58cd3021c8f496c689f84
+size 777908

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8636be1c40fd1c9751dc4c7c4a7f78bc301943c53c07e7dd8f6fcd34f615e963
+oid sha256:ee5329adf865d9baa8d1df410e2fbcc616893fb88f6ed31666801ee27e92cf35
 size 7160