metadata
tags:
- generated_from_trainer
model-index:
- name: myBit-Llama2-jp-127M-test-23
results: []
myBit-Llama2-jp-127M-test-23
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- eval_loss: 3.7610
- eval_runtime: 323.9734
- eval_samples_per_second: 660.693
- eval_steps_per_second: 6.883
- epoch: 0.29
- step: 12000
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: 0.0024
- train_batch_size: 96
- eval_batch_size: 96
- seed: 42
- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 5000
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.8240 | 0.05 | 2000 | 4.082750 |
| 3.8518 | 0.1 | 4000 | 3.693951 |
| 3.6357 | 0.15 | 6000 | 3.606057 |
| 3.6164 | 0.2 | 8000 | 3.641231 |
| 3.6208 | 0.25 | 10000 | 3.646924 |
| 3.6360 | 0.29 | 12000 | 3.760965 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- mybitnet 0.5.1