metadata
library_name: peft
license: other
base_model: Salesforce/Llama-xLAM-2-8b-fc-r
tags:
- base_model:adapter:Salesforce/Llama-xLAM-2-8b-fc-r
- llama-factory
- lora
- transformers
pipeline_tag: text-generation
model-index:
- name: xlam_8B_pythonic_zhtw_lr1e-5_ep1
results: []
xlam_8B_pythonic_zhtw_lr1e-5_ep1
This model is a fine-tuned version of Salesforce/Llama-xLAM-2-8b-fc-r on the multi_turn_miss_func_zh_tw_function_mix_sharegpt, the multi_turn_miss_param_zh_tw_function_mix_sharegpt and the multi_turn_zh_tw_function_mix_sharegpt datasets. It achieves the following results on the evaluation set:
- Loss: 0.8609
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: 1e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Use OptimizerNames.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_ratio: 0.03
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.1577 | 0.3108 | 450 | 0.9477 |
| 0.7223 | 0.6217 | 900 | 0.8704 |
| 0.8008 | 0.9325 | 1350 | 0.8607 |
Framework versions
- PEFT 0.17.0
- Transformers 4.55.2
- Pytorch 2.4.1+cu121
- Datasets 4.0.0
- Tokenizers 0.21.4