End of training

README.md

@@ -32,7 +32,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.000495111742193923
+- learning_rate: 0.0008110550790053218
 - train_batch_size: 163
 - eval_batch_size: 163
 - seed: 42
@@ -50,7 +50,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.36.2
-- Pytorch 2.0.1
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu121
 - Datasets 2.16.1
 - Tokenizers 0.15.0

config.json

@@ -33,7 +33,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.36.2",
+  "transformers_version": "4.35.2",
   "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": "4.36.2"
+  "transformers_version": "4.35.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4056ca2a52f93b2d7a468d1e6f31ccbb2153e179f73b3f4bb2a609e58fe51bb7
+oid sha256:f200963cfbaaf57eed884d0133dd209a2e03ffb1aee6f26f99256fbff64fcbd3
 size 497774208

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a117f75cb33904658b65387c15767525713f09e6ae1d2faa404a84bdc21fadd
-size 4283
+oid sha256:82faa550bdb53f471d2b3b57dbfcd7c575b5252cd8a46cd5660d331d885da92b
+size 4600