Training complete

README.md

@@ -40,7 +40,7 @@ The following hyperparameters were used during training:
 - train_batch_size: 32
 - eval_batch_size: 64
 - seed: 42
-- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - num_epochs: 3
 - mixed_precision_training: Native AMP
@@ -51,7 +51,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.46.2
+- Transformers 4.45.2
 - Pytorch 2.5.1+cu121
 - Datasets 3.1.0
 - Tokenizers 0.20.3

generation_config.json

@@ -12,5 +12,5 @@
   "num_beams": 4,
   "pad_token_id": 46275,
   "renormalize_logits": true,
-  "transformers_version": "4.46.2"
+  "transformers_version": "4.45.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23e0d8894883d106c7fefd931b5ee647e5856c191dfe1cb918e4cc3df8822aa6
+oid sha256:5e6e144efcc29fc46b9d4925b8115d7290ce27f093655549c50d3aef771442a8
 size 271541392

runs/Dec02_08-31-51_4bb14ee925ea/events.out.tfevents.1733128992.4bb14ee925ea.1931.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07753b81c7eb437492b39f8e07289bffbd9f06bd2aeb0c8dbb54218533ae91cb
-size 9134
+oid sha256:b2c66ae84da2c81c77cbdf797b877c934c3e11ef5c61e480ce2baa3f833fe3b0
+size 11176