Model save

README.md

@@ -37,10 +37,10 @@ The following hyperparameters were used during training:
 - eval_batch_size: 2
 - seed: 42
 - distributed_type: multi-GPU
-- num_devices: 4
+- num_devices: 8
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 16
-- total_eval_batch_size: 8
+- total_train_batch_size: 32
+- total_eval_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - num_epochs: 1

runs/Feb02_01-56-44_r2d2-devbox-526kp/events.out.tfevents.1738461455.r2d2-devbox-526kp.2518.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28ccc51e9bb54e85585268f095605f430e3657869d9dade6628c168021f40ed5
+size 4674

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f1e03fe384ebd6443ee7e0629177b2ee31dcb7aa441e4a881e3451860c281e7
+oid sha256:0aa9a2d2e6fe5ce2f1ced9459d88d1cedbc90751689d22221d8c30ec597a5a18
 size 5816