End of training

README.md

@@ -32,7 +32,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0002983470790288263
+- learning_rate: 0.0008088856555012102
 - train_batch_size: 150
 - eval_batch_size: 150
 - 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 sha256:79cec8c67ce9c58d9ac64c1f4b646f0e0e117542b2b76cec5a3e5cd74f6caedd
+oid sha256:2d47e2dd688dc32bf058d09947443d101da0854d6527f476e7bf466870364eae
 size 497774208

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69b17fe0c0c534b0cad4593461bdb77ee3e0b3f6b5ce1cb784d5daa1dc062e03
-size 4283
+oid sha256:0075fb0345bb6570ba5b9ecd54577c67065df113c1d48a9cdfbad96da8db27fe
+size 4600