metadata
language:
- zh
license: other
library_name: peft
tags:
- trl
- sft
- nycu-112-2-deeplearning-hw2
- generated_from_trainer
base_model: taide/Llama3-TAIDE-LX-8B-Chat-Alpha1
datasets:
- DandinPower/ZH-Reading-Comprehension-Llama-Instruct
model-index:
- name: taide_llama3_8b_lora_completion_only
results: []
taide_llama3_8b_lora_completion_only
This model is a fine-tuned version of taide/Llama3-TAIDE-LX-8B-Chat-Alpha1 on the DandinPower/ZH-Reading-Comprehension-Llama-Instruct dataset. It achieves the following results on the evaluation set:
- Loss: 0.0968
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: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- total_eval_batch_size: 2
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 700
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.1474 | 0.3690 | 250 | 0.1201 |
| 0.1072 | 0.7380 | 500 | 0.1581 |
| 0.098 | 1.1070 | 750 | 0.1148 |
| 0.0963 | 1.4760 | 1000 | 0.1044 |
| 0.0502 | 1.8450 | 1250 | 0.1064 |
| 0.05 | 2.2140 | 1500 | 0.1017 |
| 0.0239 | 2.5830 | 1750 | 0.1015 |
| 0.0443 | 2.9520 | 2000 | 0.0968 |
Framework versions
- PEFT 0.10.0
- Transformers 4.40.0
- Pytorch 2.2.2+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1