Model save

README.md

@@ -42,7 +42,7 @@ The following hyperparameters were used during training:
 - gradient_accumulation_steps: 8
 - total_train_batch_size: 64
 - total_eval_batch_size: 8
-- 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: cosine
 - lr_scheduler_warmup_ratio: 0.03
 - num_epochs: 1.0
@@ -53,7 +53,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.45.0
-- Pytorch 2.5.1+cu124
+- Transformers 4.46.3
+- Pytorch 2.5.1+cu118
 - Datasets 2.18.0
 - Tokenizers 0.20.3

generation_config.json

@@ -1,16 +1,13 @@
 {
-  "attn_implementation": "flash_attention_2",
   "bos_token_id": 151643,
   "do_sample": true,
   "eos_token_id": [
     151645,
     151643
   ],
-  "num_labels": 5,
   "pad_token_id": 151643,
-  "problem_type": "regression",
   "temperature": 0.01,
   "top_k": 1,
   "top_p": 0.001,
-  "transformers_version": "4.45.0"
+  "transformers_version": "4.46.3"
 }