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 sha256:6bec01e560d8ef3c125972431272d77fba775609ab2d8c73f53e71fdadc4ff21
+oid sha256:f5a07c8b2772744364da550e8d7a3d386e48f61d0369e4e18a1d0069f651a2f8
 size 4988482416

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08eca672cdb8a420b6618d778cf09434ca3acfa38729f853432f9b1d40699f14
+oid sha256:569ae14f5daf10aa05aff579368c2679d9a967015ccb6314f368f35d7abf7a84
 size 4981244328

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1d98ec90aced857804f64a053e23b8ecbfddd0c0872125211976f1bcdede704
+oid sha256:07b1e015fd6dabed057e855ab19cf8c0d1aab056b8469cacb3a56429f931310a
 size 4228306968

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b59871201cea101b78b2d3e60ffaafe65c1cf92cfc7d9c9835270f95efd5c65a
+oid sha256:5b4145d4511acc5cb4345c6e56d09fd4c7579860e9c6140e177a60a784321cc3
 size 1244659840

runs/Jun08_14-14-40_sn4622116170/events.out.tfevents.1717856081.sn4622116170

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87321b24540ad7c1d562f0a95787ff6ca1cb7f5d60e94cb0e5a0a1d8b32b03b8
+size 5069

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cd62dc3961caec7f561ccb6da78e5997dec332645100bb83285dc8207136dbd
+oid sha256:323a77f4c7be4bf9301ae4066bdc14ce38623318ec16438f0ad004e9e4ba1dc2
 size 4984