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:c91cd0707cafbded9a5b2f1cdc0fd72b4b94453829d17e2678383fef8007a673
+oid sha256:2a295472c2acc68e61cbe54144e9619b54e203942d43ba5f555710522d6698ae
 size 4988482416

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35dbb0205b4774bab50b09817dd6a51e7000601cef8e4c965db97932e78ffde6
+oid sha256:c104dddd69e51e727c17c02bde262cca2ef6be4b23553a445a8e0e36134ecced
 size 4981244328

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:672a1e9cac330ba1c90249bc2ec74453b6611af39c638126900e9acbc2a029be
+oid sha256:eb643106c5f1b0a017cf4c2f1c43e43d599c44eb77ef20aa1d19327ea9a4d755
 size 4228306968

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da5e91618c86ce00274f20a0fb69e6c7206107f38507e1b4fee06b2b63d828a7
+oid sha256:d51fd9c41378e9f567ba27afad8ef92d1b8effa259f2ad0083a99287fc647332
 size 1244659840

runs/Jun08_11-36-33_sn4622116170/events.out.tfevents.1717846593.sn4622116170

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a0c4d8a211661ba8b44d722a9cef315d93fb067d3a8e43e0867cc8122ae5287
+size 5075

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acd3e2f8d90f79d8d175fce41f9b671f16d0adb769199fea9eb04ff42617ab61
+oid sha256:c2382467dbc6785a49e8f9f03e2b5f4ce2e4776f356d7d63f8d2283001237749
 size 4984