End of training

README.md

@@ -40,11 +40,11 @@ The following hyperparameters were used during training:
 - train_batch_size: 1
 - eval_batch_size: 2
 - seed: 42
-- gradient_accumulation_steps: 16
-- total_train_batch_size: 16
+- gradient_accumulation_steps: 32
+- total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 72
+- num_epochs: 108
 
 ### Training results
 

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95d0b4e211c9cb3104d0f131a44ba724edf119b4f693bbdfc696dda513a599df
+oid sha256:7f51cad0d5d0b35eb2b65ae4c904d05feaeb31dbeb23e10d3586f7355a39ce3f
 size 4988482416

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab8736e382bec18498295614addb1ca783a23b750054ee7977847e0a369f0eec
+oid sha256:fef736739f5a21add8726169b4cab8e270d43d0ecc9bb0f0d3cecc6c8aae08cd
 size 4981244328

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf3edcb9f714e957f83e64cfb37865083fee2e1c25ca815f1de57ea79cc588c5
+oid sha256:abd860978319abf7f518bf1663ff6f852b69b8d40e38e3527ce6c97733770d5d
 size 4228306968

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2555485986ddf62f02d9d5ecb5f8f423330bf31d354af8f82ecc3efc642265ba
+oid sha256:22989a8e3282d537eaf86defabb1c22ef8a1945a0551551a992f4be0bda819f5
 size 1244659840

runs/Jun08_10-13-36_sn4622116170/events.out.tfevents.1717841617.sn4622116170

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86d48fb9ad9a5c4bfc09396597b462c119c46c6f6f424558aeaf2a925c22d5eb
+size 5065

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:590662000891fb61a757a885f305fa9f85dd2dc919949e5fc71346de12390d7a
+oid sha256:ec973e594737b9b0e99e5ff204021a2685f9d90d6cf2bc4a43b14265db2a4ad4
 size 4984