Training complete

README.md

@@ -1,4 +1,5 @@
 ---
+library_name: transformers
 license: mit
 base_model: danghuy1999/gpt2-viwiki
 tags:
@@ -38,7 +39,7 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 10
+- num_epochs: 50
 - mixed_precision_training: Native AMP
 
 ### Training results
@@ -47,7 +48,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.35.2
+- Transformers 4.44.2
 - Pytorch 2.4.1+cu121
-- Datasets 2.16.1
-- Tokenizers 0.15.2
+- Datasets 3.0.0
+- Tokenizers 0.19.1

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": "4.44.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63c6032f45e2f1a5c579b0d63886600772c0f9fdadd883737d2011fa5a0ea548
+oid sha256:3b7fcbfc5905f2ddbe227ce276dca6b02352ac54adddf975796a18df31899013
 size 497774208

runs/Sep26_02-42-37_d651a29f6237/events.out.tfevents.1727318785.d651a29f6237.313.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54c1da94c71f16e200dc9e19ad9ddf0dc06c5255dae3a4295083bfb42a76f896
-size 6164
+oid sha256:eea475a20324ac060b74eea12908e698cdca97b54829a0782462b750bacf9c07
+size 6729