metadata
tags:
- generated_from_trainer
model-index:
- name: myBit-Llama2-jp-127M-test-18
results: []
myBit-Llama2-jp-127M-test-18
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.8286
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: 0.00024
- train_batch_size: 96
- eval_batch_size: 96
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: polynomial
- lr_scheduler_warmup_steps: 500
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 8.9871 | 0.07 | 200 | 7.5435 |
| 6.2033 | 0.15 | 400 | 5.2273 |
| 4.7747 | 0.22 | 600 | 4.5503 |
| 4.3996 | 0.3 | 800 | 4.3403 |
| 4.2393 | 0.37 | 1000 | 4.2145 |
| 4.1416 | 0.45 | 1200 | 4.1301 |
| 4.0555 | 0.52 | 1400 | 4.0648 |
| 3.9921 | 0.6 | 1600 | 4.0114 |
| 3.9456 | 0.67 | 1800 | 3.9596 |
| 3.8916 | 0.75 | 2000 | 3.9247 |
| 3.8529 | 0.82 | 2200 | 3.8887 |
| 3.8241 | 0.9 | 2400 | 3.8575 |
| 3.7951 | 0.97 | 2600 | 3.8286 |
Framework versions
- Transformers 4.39.1
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2