Model save

README.md

@@ -33,16 +33,14 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
-- train_batch_size: 8
-- eval_batch_size: 16
+- learning_rate: 0.0003
+- train_batch_size: 2
+- eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 2
-- total_train_batch_size: 16
-- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 100
-- num_epochs: 5
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 50
 - mixed_precision_training: Native AMP
 
 ### Training results
@@ -51,7 +49,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.57.1
-- Pytorch 2.8.0+cu126
+- Transformers 4.53.3
+- Pytorch 2.6.0+cu124
 - Datasets 4.4.1
-- Tokenizers 0.22.1
+- Tokenizers 0.21.2

generation_config.json

@@ -1,9 +1,7 @@
 {
   "_from_model_config": true,
   "decoder_start_token_id": 0,
-  "eos_token_id": [
-    1
-  ],
+  "eos_token_id": 1,
   "pad_token_id": 0,
-  "transformers_version": "4.57.1"
+  "transformers_version": "4.53.3"
 }