forked from p04798526/LLaMA-Factory-Mirror
1.5 KiB
1.5 KiB
| base_model | library_name | license | tags | model-index | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| /home/user/.cache/modelscope/hub/modelscope/Llama-2-7b-ms | peft | other |
|
|
sft
This model is a fine-tuned version of /home/user/.cache/modelscope/hub/modelscope/Llama-2-7b-ms on the identity and the alpaca_en_demo datasets. It achieves the following results on the evaluation set:
- Loss: nan
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: 8
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- total_eval_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 20
- num_epochs: 3.0
- mixed_precision_training: Native AMP
Training results
Framework versions
- PEFT 0.12.0
- Transformers 4.43.4
- Pytorch 2.4.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1