End of training

README.md

@@ -33,15 +33,15 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0005
-- train_batch_size: 32
-- eval_batch_size: 32
+- train_batch_size: 45
+- eval_batch_size: 45
 - seed: 42
 - gradient_accumulation_steps: 8
-- total_train_batch_size: 256
+- total_train_batch_size: 360
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 1000
-- num_epochs: 5
+- num_epochs: 10
 
 ### Training results
 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45e2484d77e06f429f4f41c9bad1504dd7ef0f74f8a1d389f27827cbcaa2b90c
+oid sha256:dfd8498b6207a76a87d6bebbcc0bd9c53aa211bbb99c08ab3ae092270e8a1b4c
 size 497774208

runs/Feb20_06-39-18_48423b5e2aad/events.out.tfevents.1708411159.48423b5e2aad.21862.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b4b41593e6c8abf7483c5786f4343181b9d47761bf82ee415918e6374712c7e
+size 4184

runs/Feb20_06-41-02_48423b5e2aad/events.out.tfevents.1708411263.48423b5e2aad.22467.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b875827bdaf496500ab2088666a21e8477b38c5ba7268056b7cac1c0b7d3a93
+size 4184

runs/Feb20_06-42-29_48423b5e2aad/events.out.tfevents.1708411350.48423b5e2aad.22915.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2be9c62f1acd00cd28c8ca9455b9a6e05379f9a76e32550125a2824d44a07ed0
+size 4436

runs/Feb20_06-45-30_48423b5e2aad/events.out.tfevents.1708411531.48423b5e2aad.23742.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93c2ff1fba1f82c84a023b942654367dc4e28bbafa88779538fb7cb4b9ac0f98
+size 4790

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:404e0af4a2ba6a84a77db144b0fe1fabe325af88fe4a155d3f792b2307abac6d
+oid sha256:bcf03737adee3206634cc7e543d6c76c8b027b96d84f199fdaaa69c09ad4da01
 size 4600