metadata
base_model: meta-llama/Llama-2-7b-hf
tags:
- generated_from_trainer
model-index:
- name: out
results: []
out
This model is a fine-tuned version of meta-llama/Llama-2-7b-hf on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.2049
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: 3.8e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 2
- total_train_batch_size: 128
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.3761 | 0.01 | 1 | 1.4211 |
| 1.1922 | 0.2 | 14 | 1.2246 |
| 1.095 | 0.4 | 28 | 1.2137 |
| 1.1475 | 0.6 | 42 | 1.2152 |
| 1.1639 | 0.81 | 56 | 1.2224 |
| 1.0431 | 1.01 | 70 | 1.2131 |
| 0.9464 | 1.21 | 84 | 1.2100 |
| 1.1368 | 1.41 | 98 | 1.2060 |
| 1.0991 | 1.61 | 112 | 1.2022 |
| 0.9896 | 1.81 | 126 | 1.2014 |
| 0.9592 | 2.01 | 140 | 1.1991 |
| 0.9789 | 2.22 | 154 | 1.2054 |
| 1.0028 | 2.42 | 168 | 1.2048 |
| 0.9374 | 2.62 | 182 | 1.2051 |
| 0.9318 | 2.82 | 196 | 1.2049 |
Framework versions
- Transformers 4.34.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.14.0