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 sha256:8d7cfbb41322984af2c475854717758de67a99d9493aa2f72b65c7692b1ea85e
+oid sha256:b0d8264e8d97a1a26f40a35e34fdd299fca272abba1625e4d55284028d8362c8
 size 4945242264

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22502d55e6d7a91d78652b6ddfbdc0b9c9768cc1b14d0fcb36ef30c16921a044
+oid sha256:88de1037832f25fe738e39cbe28bf83cf44fb90bb76e7f6d002d586fadd0e6d3
 size 67121608

runs/Aug04_05-13-33_p1-r01-n3.pok.ibm.com/events.out.tfevents.1722762885.p1-r01-n3.pok.ibm.com.2337298.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dfce46886339cbd6ab7ffeafc5630117362d3e6766aa06dd0baef6436cf0a3a
+size 730934

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7c33b4e68d7bf63e908b11ff003d3f90e6b4005d0d70020298c12602ae283e1
-size 7160
+oid sha256:bb028d4ecdab10e78ad7f3ef06bee13e420befe6ec8dec4e03febe16968bf73f
+size 7224