End of training

README.md

@@ -42,7 +42,6 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 1000
 - num_epochs: 4
-- mixed_precision_training: Native AMP
 
 ### Training results
 
@@ -50,7 +49,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.37.1
-- Pytorch 2.1.2+cu121
+- Transformers 4.37.2
+- Pytorch 2.1.2+cpu
 - Datasets 2.16.1
 - Tokenizers 0.15.1

config.json

@@ -33,7 +33,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.37.1",
+  "transformers_version": "4.37.2",
   "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": "4.37.1"
+  "transformers_version": "4.37.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6157ef38efd3b73825a09dc508cb64de46c7fa0ca27dec03928f8e77fabff3ec
+oid sha256:443bdda554eacf7be250a15e586d98314843eb15030b44dab2c070365cceab57
 size 497774208

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bfe61e508210a589bdb56af876336951bad3c8a6bd4cfa628a2a14755466e99
+oid sha256:c8c0a9c78f4bcafdae8e384456f35821acc7902d3d39b050d3851c8bf618268e
 size 4728