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 sha256:9e2c2cf972f92feb4cb7bfff29f47169efc54f9d148ad517a11e65a5699f9d6f
+oid sha256:4d6781a83d3c24b05120e15997a964ede125a121a986bc16e4ade87c05e6f6d4
 size 4988482416

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4bd5e026a672a99916f06beb46ff3c2303ced0f2d956f4a21b7300d3cff00ac
+oid sha256:cb2947331bc75857bb7a942992db5f839a83ab4eee1dcbd0202a5f7544910978
 size 4981244328

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33129519d3726fa1daa13e1e8e47607896a813ff235b82e7359adf13a9c35552
+oid sha256:ea3da436705575deb74b2fd60eac8e49abcca1d0866783f78c1262f471f385eb
 size 4228306968

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7220bfc64fb6df0e3b7d004e8bc8e741b11647fdefaf1833e3f53613c2c884aa
+oid sha256:c57c18a21aae142c7bedd7ef7b266fb192d42d0d77f851cbde460dff6998c16e
 size 1244659840

runs/Jun08_06-44-10_sn4622116170/events.out.tfevents.1717829051.sn4622116170

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b355509ae807d4ddb6ced90620e9b16b2559ff34a40adb55075961bdb517a9a9
+size 5069

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cf313556baab682c2d5feda81197f727528e654e1d34b1e06e739bf5a31d8aa
+oid sha256:74c37be99764da6af1482ade03df66651043eaa398a3e7158d3573fe25705593
 size 4984