End of training

README.md

@@ -33,21 +33,17 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 16
-- eval_batch_size: 16
+- train_batch_size: 32
+- eval_batch_size: 32
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - num_epochs: 5
 - mixed_precision_training: Native AMP
 
-### Training results
-
-
-
 ### Framework versions
 
-- Transformers 4.39.3
+- Transformers 4.38.2
 - Pytorch 2.1.2
 - Datasets 2.18.0
 - Tokenizers 0.15.2

config.json

@@ -55,7 +55,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.39.3",
+  "transformers_version": "4.38.2",
   "use_cache": true,
   "vocab_size": 32128
 }

generation_config.json

@@ -3,5 +3,5 @@
   "decoder_start_token_id": 0,
   "eos_token_id": 1,
   "pad_token_id": 0,
-  "transformers_version": "4.39.3"
+  "transformers_version": "4.38.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbc5b53b7fa09edcf1d6a4dc254f3d82940b8be7f20a6504d6dbb97ee21bf5cc
+oid sha256:881ecd3d2e20cfb1ddf96ac598ad90a610007dfa4ff04cfc024e4afd118bc686
 size 242041896

runs/Jun04_07-45-34_671879f8d761/events.out.tfevents.1717487135.671879f8d761.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77106d6c80c8d58156764793f6d10b9745c609c11bc0d41f918d70dd5f6fcba2
+size 5601

runs/Jun04_07-57-46_671879f8d761/events.out.tfevents.1717487867.671879f8d761.34.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06ed2dec11326b62cde976bff1b5a1fd01bcf0f45853fc3673657da2fae9db3c
+size 5601

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f6e5baba2825b4a0a164a52b42a4a231f9638a7b7e4685807c83f615dcff0fc
-size 5176
+oid sha256:ea18c3e483000f5ee232ca6dcb7c63f6512aefbbf2414fd1fccaca3d2b7330f0
+size 5112