metadata
tags:
- generated_from_trainer
model-index:
- name: myBit-Llama2-jp-127M-test-24
results: []
myBit-Llama2-jp-127M-test-24
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- eval_loss: 3.1684
- eval_runtime: 327.4267
- eval_samples_per_second: 653.725
- eval_steps_per_second: 6.811
- epoch: 0.39
- step: 16000
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 |
|---|---|---|---|
| 4.7147 | 0.05 | 2000 | 3.781438 |
| 3.6139 | 0.1 | 4000 | 3.518407 |
| 3.4595 | 0.15 | 6000 | 3.387526 |
| 3.3389 | 0.2 | 8000 | 3.296978 |
| 3.2725 | 0.25 | 10000 | 3.245793 |
| 3.2286 | 0.29 | 12000 | 3.211367 |
| 3.1991 | 0.34 | 14000 | 3.186454 |
| 3.1745 | 0.39 | 16000 | 3.168446 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- mybitnet 0.5.2