End of training

README.md

@@ -1,9 +1,9 @@
 ---
+license: apache-2.0
 library_name: peft
-license: bsd-3-clause
-base_model: Salesforce/codet5p-770m
 tags:
 - generated_from_trainer
+base_model: Qwen/Qwen2.5-Coder-0.5B-Instruct
 model-index:
 - name: results_stage1
   results: []
@@ -14,9 +14,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # results_stage1
 
-This model is a fine-tuned version of [Salesforce/codet5p-770m](https://huggingface.co/Salesforce/codet5p-770m) on the None dataset.
+This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-0.5B-Instruct) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 8.4104
+- Loss: 4.3536
 
 ## Model description
 
@@ -36,27 +36,26 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 2
+- train_batch_size: 1
 - eval_batch_size: 8
 - 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
+- num_epochs: 2
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 40   | 9.4289          |
-| No log        | 2.0   | 80   | 8.7898          |
-| No log        | 3.0   | 120  | 8.4104          |
+| No log        | 1.0   | 80   | 5.6802          |
+| No log        | 2.0   | 160  | 4.3536          |
 
 
 ### Framework versions
 
-- PEFT 0.14.0
-- Transformers 4.47.1
-- Pytorch 2.5.1+cu121
-- Datasets 3.2.0
-- Tokenizers 0.21.0
+- PEFT 0.11.1
+- Transformers 4.41.2
+- Pytorch 2.3.1+cu121
+- Datasets 2.19.2
+- Tokenizers 0.19.1