Model save

README.md

@@ -8,7 +8,7 @@ tags:
 datasets:
 - medalpaca/medical_meadow_medqa
 model-index:
-- name: qlora-qwen-25-7b-instruct
+- name: qlora-qwen-25-7b-instruct-2
   results: []
 ---
 
@@ -55,7 +55,7 @@ wandb_log_model:
 
 gradient_accumulation_steps: 1
 micro_batch_size: 1
-num_epochs: 1
+num_epochs: 2
 optimizer: adamw_torch
 lr_scheduler: cosine
 learning_rate: 0.00002
@@ -103,23 +103,22 @@ wandb_watch:
 wandb_name: 
 wandb_log_model: 
 
-hub_model_id: neginashz/qlora-qwen-25-7b-instruct
+hub_model_id: neginashz/qlora-qwen-25-7b-instruct-2
 hub_strategy: 
 early_stopping_patience:
 
 resume_from_checkpoint:
 auto_resume_from_checkpoints: true
-early_stopping_patience:
 
 ```
 
 </details><br>
 
-# qlora-qwen-25-7b-instruct
+# qlora-qwen-25-7b-instruct-2
 
 This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the medalpaca/medical_meadow_medqa dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1303
+- Loss: 0.1257
 
 ## Model description
 
@@ -148,8 +147,8 @@ The following hyperparameters were used during training:
 - total_eval_batch_size: 4
 - 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_steps: 2
-- num_epochs: 1
+- lr_scheduler_warmup_steps: 4
+- num_epochs: 2
 
 ### Training results
 
@@ -159,6 +158,10 @@ The following hyperparameters were used during training:
 | 0.1456        | 0.5   | 36   | 0.1333          |
 | 0.121         | 0.75  | 54   | 0.1312          |
 | 0.1328        | 1.0   | 72   | 0.1303          |
+| 0.1336        | 1.25  | 90   | 0.1276          |
+| 0.1228        | 1.5   | 108  | 0.1263          |
+| 0.1199        | 1.75  | 126  | 0.1260          |
+| 0.1393        | 2.0   | 144  | 0.1257          |
 
 
 ### Framework versions