End of training

README.md

@@ -31,7 +31,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
+- learning_rate: 5e-06
 - train_batch_size: 18
 - eval_batch_size: 18
 - seed: 42
@@ -47,7 +47,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.38.1
+- Transformers 4.38.2
 - Pytorch 2.1.0+cu121
 - Datasets 2.18.0
 - Tokenizers 0.15.2

config.json

@@ -23,7 +23,7 @@
   "rotary_pct": 0.25,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.38.1",
+  "transformers_version": "4.38.2",
   "use_cache": true,
   "use_parallel_residual": true,
   "vocab_size": 50254

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 0,
   "eos_token_id": 0,
-  "transformers_version": "4.38.1"
+  "transformers_version": "4.38.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fe655340e7e79753250787b46ec665952c7a91d46828b9f65a4d937a3178386
+oid sha256:429468649123b324a3fca2da4a25dbae918e0313cd362b79a337f8d41818ac6c
 size 121885144

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f30b06dc652c37daf8d968857b4d3212215158cc3fd0de1c3ec110dd21a4a23
+oid sha256:46976aeab505b49e66dfe620a309ac489e16843d9692b549ec4110af05bec4c8
 size 4856