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: 1.2048
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 |
---|---|---|---|
1.3782 | 0.01 | 1 | 1.4211 |
1.1948 | 0.2 | 14 | 1.2273 |
1.0953 | 0.4 | 28 | 1.2137 |
1.1464 | 0.6 | 42 | 1.2099 |
1.1481 | 0.81 | 56 | 1.2080 |
1.0277 | 1.01 | 70 | 1.2022 |
0.9344 | 1.21 | 84 | 1.2049 |
1.1294 | 1.41 | 98 | 1.2033 |
1.0933 | 1.61 | 112 | 1.2002 |
0.987 | 1.81 | 126 | 1.1996 |
0.9491 | 2.01 | 140 | 1.1972 |
0.9673 | 2.22 | 154 | 1.2058 |
0.99 | 2.42 | 168 | 1.2048 |
0.9241 | 2.62 | 182 | 1.2049 |
0.9204 | 2.82 | 196 | 1.2048 |
Framework versions
- Transformers 4.34.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.14.0
- Downloads last month
- 4
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
๐
Ask for provider support
Model tree for winglian/llama-neft-exp2
Base model
meta-llama/Llama-2-7b-hf