Model save

README.md

@@ -37,12 +37,12 @@ The following hyperparameters were used during training:
 - train_batch_size: 1
 - eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 128
-- total_train_batch_size: 128
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 2
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.95) and epsilon=1e-07 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 50
-- num_epochs: 1
+- num_epochs: 3
 
 ### Training results
 

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ec56d8a80d38f59a1b72f1edf0ca609fb314a7d31002718463cb669c2bf929c
+oid sha256:df4251d1dcbad41707e2f4a7edc798099157416441907796ac915ae9d8fc7b94
 size 4997504848

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7504bb8749de9e17d04ed1b0b6ff51cbcee9f91301ba7ca400d2cfc007065ce2
+oid sha256:97ff61ec4958a313324ca1c5afe3bbc291971a2ffa0d546740467cc4eaa7433e
 size 4952333128

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbde98581f804f88ac0c6d340fe575d2be41d9c4e4532276215707df80138683
+oid sha256:6f597754fca4f360064938547d21895c91080b400c43aea0bf215ff23943f026
 size 1199389232

runs/Mar14_21-04-19_020ce662e38a/events.out.tfevents.1741986277.020ce662e38a.13353.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31f6402a60f0cc7e5b4aa20c4a34f24b2f346d7de0136ad8a4447146f4e53f9b
-size 9172
+oid sha256:0f83d9f54e003e6affec3552bdbd82e8d2147025d5e6c440eacf2c7f40832baf
+size 9727