metadata
license: other
library_name: peft
tags:
- generated_from_trainer
base_model: Qwen/Qwen1.5-7B
metrics:
- accuracy
model-index:
- name: lex_glue
results: []
lex_glue
This model is a fine-tuned version of Qwen/Qwen1.5-7B on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.6125
- Accuracy: 0.5507
- F1 Macro: 0.4051
- F1 Micro: 0.5507
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- total_train_batch_size: 32
- total_eval_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | F1 Micro |
|---|---|---|---|---|---|---|
| 2.3973 | 0.32 | 50 | 2.1948 | 0.38 | 0.1677 | 0.38 |
| 1.6438 | 0.64 | 100 | 1.8118 | 0.4271 | 0.2466 | 0.4271 |
| 1.7379 | 0.96 | 150 | 1.7119 | 0.4771 | 0.2704 | 0.4771 |
| 1.409 | 1.27 | 200 | 1.7488 | 0.4871 | 0.2973 | 0.4871 |
| 1.2443 | 1.59 | 250 | 1.6798 | 0.5364 | 0.3334 | 0.5364 |
| 1.1602 | 1.91 | 300 | 1.6132 | 0.5243 | 0.3573 | 0.5243 |
| 1.1191 | 2.23 | 350 | 1.6507 | 0.5386 | 0.3914 | 0.5386 |
| 0.8907 | 2.55 | 400 | 1.6125 | 0.5507 | 0.4051 | 0.5507 |
| 0.9012 | 2.87 | 450 | 1.6445 | 0.5529 | 0.4088 | 0.5529 |
Framework versions
- PEFT 0.9.0
- Transformers 4.39.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2