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:b7962d7c3520c2332144e9285dbc9402310c17a048f437aaa6541eabaef730ec
+oid sha256:f6d8dcad2465331140e72fdfa929b0336c96422e837c12b12f0cc9275de971b4
 size 4988482416

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0f1f6e7fc684d59c503fa463c689ef59d9c4042ad88d4aba4623891a56e20cd
+oid sha256:e2fe4b708635243c89da3b4eaea5ac0afec6dd1f6b11c482d629a06b280bfadb
 size 4981244328

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86f7ec7a5c07a82546c8843b830b76f8db2a63cf3f064288e0040402259599dd
+oid sha256:8af13ba60a5ff085fbb1ceb8c92d336d573fc5d07ab18a5682b2d8fac6b81dd3
 size 4228306968

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4df72c7bb7d9d5079e61c90a3a59fc53e7a314ec052f752b6b37272a567d022
+oid sha256:54752590a178c4e5cf56725d3798f001827d75340e4b8c024af1d447de57ef61
 size 1244659840

runs/Jun08_10-55-05_sn4622116170/events.out.tfevents.1717844106.sn4622116170

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7bf74791aaf5bc41e986ff8009f95ee64f7893298a88bfee401c42dce521d4b
+size 5065

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed73e5ae9e395d464cfad31c85b68541a6b91009604f515b13b43f64a5602315
+oid sha256:0a56b1d362ca24edcd091997b9b596a677c0992c5d4ff22f5da775e3c674d9dc
 size 4984