Model save

README.md

@@ -39,14 +39,18 @@ The following hyperparameters were used during training:
 - train_batch_size: 2
 - eval_batch_size: 8
 - seed: 42
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - num_epochs: 3
 - mixed_precision_training: Native AMP
 
+### Training results
+
+
+
 ### Framework versions
 
-- Transformers 4.45.2
+- Transformers 4.46.0.dev0
 - Pytorch 2.4.0+cu121
 - Datasets 3.0.1
 - Tokenizers 0.20.1

generation_config.json

@@ -4,5 +4,5 @@
   "eos_token_id": 2,
   "forced_eos_token_id": 2,
   "pad_token_id": 1,
-  "transformers_version": "4.45.2"
+  "transformers_version": "4.46.0.dev0"
 }

runs/Oct22_04-59-01_c71da081ab17/events.out.tfevents.1729573148.c71da081ab17.81.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07b5b83a789b85ef9db624173855177e53b7299e6a195017c8f494258a0dc381
-size 11053
+oid sha256:0b5e7ff657319fb1450e8f0094ce6f2d0a67cffd00ccad620de405d4c38e96d7
+size 11407