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:bda9cddd879046484c67ca23dd15c5537973bfc43ff768efc7d15b8592facc9f
+oid sha256:f35b23b66e3f30982b8e9f0d51d70e3296c56ea7520c4f13eeb594995ba8476a
 size 4988482416

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d34a560c0239213d2675594a0d70b237f4b483dc2e460cc8ca7142f74f48829
+oid sha256:9b00a62a72994416ffe8eec0bb344a0e7ed8e0ff8c8e8c2e7f979e9cf847da0b
 size 4981244328

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb8eb3a7e191739bfb043629e009f79fcefc46389471f8f9f9a97d170a88fc9a
+oid sha256:adddd3efcbabc464798416397f992e815510e8d500832d18dfc1e87628a52bce
 size 4228306968

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f3e6561226a7d24e743a9b21a60553ca526a13b05151494036ba5720ecbdce7
+oid sha256:0a0d1160c7fd96f558370fb6273f6b289a19e8d656650e0b0566d08f3670c022
 size 1244659840

runs/Jun08_12-55-38_sn4622116170/events.out.tfevents.1717851339.sn4622116170

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14aeffae1240b00b967b49c463f25f5363dbf27844a19ad5eef444b9f9ef5642
+size 5079

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecd0324be687d3f8fa07a720e85d6706b5b43018ad27dff8bd9a3e8c90f3abda
+oid sha256:3283d6c00b394b1de2c3cdddc749f92377c2dbdb1a502266f4baa6e3f69aae48
 size 4984