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 sha256:39e80a37d91940d4068bea330a4c51d1c402018f3517959871213c6d6613fd83
+oid sha256:f4ac49c9b44db9fb2673c146959e707cd3af2bddbbb98defecaef14da248d73c
 size 4945242264

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a5aebc068e4ebb2a6a9932eabdb94e653bf707eff3e3e42371fe2e6daa499f8
+oid sha256:8eb07af0c5d5e94d7fb94fb21ac51c27183f29790ea4d882ebd8a6e638bb72b5
 size 67121608

runs/Aug03_14-02-12_p1-r01-n4.pok.ibm.com/events.out.tfevents.1722708206.p1-r01-n4.pok.ibm.com.1132758.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bed730cdc79c3e0f3f3e77d38779f80b2f5f97e79b049ae659a8f5060b2809d0
+size 777908

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21684ce7ab3e4073c478206995c4f1b11e7d5bc1536466fdd49182aa79faf7e8
+oid sha256:f119c8ece7812a53b3964a7164c355bb1bac4a24223d578c8698bc65123f8ac8
 size 7224