metadata
base_model: Qwen/Qwen2.5-0.5B-Instruct
datasets:
- generator
library_name: peft
license: apache-2.0
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: trained_model
results: []
trained_model
This model is a fine-tuned version of Qwen/Qwen2.5-0.5B-Instruct on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 0.5432
- Bertscore Precision: 0.9305
- Bertscore Recall: 0.9338
- Bertscore F1: 0.9321
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Bertscore Precision | Bertscore Recall | Bertscore F1 |
|---|---|---|---|---|---|---|
| No log | 0.9664 | 18 | 1.1003 | 0.8802 | 0.8897 | 0.8849 |
| 1.7123 | 1.9866 | 37 | 0.6787 | 0.9207 | 0.9228 | 0.9218 |
| 1.7123 | 2.9530 | 55 | 0.5895 | 0.9300 | 0.9330 | 0.9315 |
| 0.5828 | 3.9732 | 74 | 0.5516 | 0.9330 | 0.9355 | 0.9342 |
| 0.4501 | 4.8322 | 90 | 0.5432 | 0.9305 | 0.9338 | 0.9321 |
Framework versions
- PEFT 0.13.0
- Transformers 4.45.1
- Pytorch 2.5.1+cpu
- Datasets 3.0.1
- Tokenizers 0.20.0