End of training

README.md

@@ -32,12 +32,12 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0008088856555012102
-- train_batch_size: 150
-- eval_batch_size: 150
+- learning_rate: 0.0008638211997224419
+- train_batch_size: 163
+- eval_batch_size: 163
 - seed: 42
 - gradient_accumulation_steps: 8
-- total_train_batch_size: 1200
+- total_train_batch_size: 1304
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 1000
@@ -50,7 +50,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.35.2
-- Pytorch 2.1.0+cu121
+- Transformers 4.36.2
+- 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": "4.36.2",
   "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": "4.35.2"
+  "transformers_version": "4.36.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d47e2dd688dc32bf058d09947443d101da0854d6527f476e7bf466870364eae
+oid sha256:c33cfd301532e3c688cbea62cb62ba1b6e3c41b9398d0f97743eb6d9f5a5aca4
 size 497774208

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0075fb0345bb6570ba5b9ecd54577c67065df113c1d48a9cdfbad96da8db27fe
-size 4600
+oid sha256:96eee7054590a2354e587989eae413ec11086d34cc0af78202c891db493e1c6c
+size 4283