lmind_hotpot_train8000_eval7405_v1_docidx_meta-llama_Llama-2-7b-hf_lora2
This model is a fine-tuned version of meta-llama/Llama-2-7b-hf on the tyzhu/lmind_hotpot_train8000_eval7405_v1_docidx dataset. It achieves the following results on the evaluation set:
- Loss: 0.7676
- Accuracy: 0.7929
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
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- total_eval_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 10.0
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
1.108 | 1.0 | 839 | 1.3252 | 0.7537 |
1.0489 | 2.0 | 1678 | 1.2690 | 0.7580 |
0.9812 | 3.0 | 2517 | 1.1602 | 0.7631 |
0.902 | 4.0 | 3357 | 1.0981 | 0.7679 |
0.8047 | 5.0 | 4196 | 1.0106 | 0.7727 |
0.7028 | 6.0 | 5035 | 0.9448 | 0.7777 |
0.6141 | 7.0 | 5874 | 0.8789 | 0.7818 |
0.5393 | 8.0 | 6714 | 0.8737 | 0.7859 |
0.4595 | 9.0 | 7553 | 0.8019 | 0.7896 |
0.3927 | 10.0 | 8390 | 0.7676 | 0.7929 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.14.1
Model tree for tyzhu/lmind_hotpot_train8000_eval7405_v1_docidx_meta-llama_Llama-2-7b-hf_lora2
Base model
meta-llama/Llama-2-7b-hfDataset used to train tyzhu/lmind_hotpot_train8000_eval7405_v1_docidx_meta-llama_Llama-2-7b-hf_lora2
Evaluation results
- Accuracy on tyzhu/lmind_hotpot_train8000_eval7405_v1_docidxself-reported0.793