Model save

README.md

@@ -33,7 +33,7 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
-- train_batch_size: 500
+- train_batch_size: 512
 - eval_batch_size: 8
 - seed: 42
 - distributed_type: multi-GPU
@@ -48,7 +48,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.31.0
-- Pytorch 2.3.0+cu121
-- Datasets 2.19.1
-- Tokenizers 0.13.3
+- Transformers 4.42.3
+- Pytorch 2.3.1+cu118
+- Datasets 2.20.0
+- Tokenizers 0.19.1

generation_config.json

@@ -312,5 +312,5 @@
     "transcribe": 50359,
     "translate": 50358
   },
-  "transformers_version": "4.31.0"
+  "transformers_version": "4.42.3"
 }

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e16c0bf5f78ce9b95d81dbb241eac683db4050843d3a639c53c64b757a5b685
+size 4992706480

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25cdee243d237ba7ee45aa77888f7daadaeeffa9c2d714529adac27e2098f080
+size 1446212088