End of training

README.md

@@ -32,7 +32,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0007174853329837569
+- learning_rate: 0.00015653632054398028
 - train_batch_size: 163
 - eval_batch_size: 163
 - seed: 42
@@ -50,7 +50,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.35.2
-- Pytorch 2.1.0+cu121
+- Transformers 4.36.1
+- Pytorch 2.0.1
 - Datasets 2.16.1
 - Tokenizers 0.15.0

config.json

@@ -33,7 +33,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.35.2",
+  "transformers_version": "4.36.1",
   "use_cache": true,
   "vocab_size": 50257
 }

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 50256,
   "eos_token_id": 50256,
-  "transformers_version": "4.35.2"
+  "transformers_version": "4.36.1"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3973ddc07927f2788b099de05927e501b9bf1662abf52df9970e213396ba988
+oid sha256:db55a9140f838a13344a8cc74bd1ab4da43ff7d9363931330c889c9adfd9416c
 size 497774208

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:961e40d817a33b88c1bc3e54fbd291a3fde8f242451c99e8a0c151c65230946a
-size 4600
+oid sha256:097977a027c66f94f012b25a18f8e5b8fa0c9ab9f8362f3a09ff4a808bbb9328
+size 4283