Model save

README.md

@@ -34,8 +34,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
-- train_batch_size: 64
-- eval_batch_size: 64
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: constant_with_warmup
@@ -45,7 +45,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.52.0
+- Transformers 4.54.1
 - Pytorch 2.5.1+cu121
 - Datasets 3.6.0
 - Tokenizers 0.21.2

config.json

@@ -53,7 +53,7 @@
   "pad_token_id": 50257,
   "scale_embedding": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.52.0",
+  "transformers_version": "4.54.1",
   "use_cache": false,
   "use_weighted_layer_sum": false,
   "vocab_size": 51865

generation_config.json

@@ -171,5 +171,5 @@
     "transcribe": 50359,
     "translate": 50358
   },
-  "transformers_version": "4.52.0"
+  "transformers_version": "4.54.1"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d55215a3ae962ce88d5a3cf9de3486557240c3384f1df2a1042dd9ea889389c
+oid sha256:14b3ea22a1053e97838e804254d9862defe91c34d46966590b33eba73c881f53
 size 5560