metadata
license: apache-2.0
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
tags:
- generated_from_trainer
model-index:
- name: myBit-Llama2-jp-127M-test-8
results: []
myBit-Llama2-jp-127M-test-8
This model is a fine-tuned version of TinyLlama/TinyLlama-1.1B-Chat-v1.0 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 4.5927
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: 250
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 9.4805 | 0.04 | 100 | 8.6095 |
| 7.8321 | 0.07 | 200 | 7.0695 |
| 6.8097 | 0.11 | 300 | 6.5242 |
| 6.1628 | 0.15 | 400 | 5.9676 |
| 5.7241 | 0.18 | 500 | 5.5946 |
| 5.5282 | 0.22 | 600 | 5.4358 |
| 5.5317 | 0.26 | 700 | 5.3903 |
| 5.399 | 0.29 | 800 | 5.3153 |
| 5.2444 | 0.33 | 900 | 5.1738 |
| 5.1217 | 0.37 | 1000 | 5.0826 |
| 5.0392 | 0.4 | 1100 | 5.0498 |
| 5.0022 | 0.44 | 1200 | 4.9668 |
| 4.9574 | 0.48 | 1300 | 4.9327 |
| 4.8924 | 0.51 | 1400 | 4.8715 |
| 4.8545 | 0.55 | 1500 | 4.8475 |
| 4.8104 | 0.58 | 1600 | 4.8027 |
| 4.7834 | 0.62 | 1700 | 4.7821 |
| 4.7563 | 0.66 | 1800 | 4.7486 |
| 4.7112 | 0.69 | 1900 | 4.7241 |
| 4.701 | 0.73 | 2000 | 4.7091 |
| 4.678 | 0.77 | 2100 | 4.6785 |
| 4.6376 | 0.8 | 2200 | 4.6615 |
| 4.6264 | 0.84 | 2300 | 4.6454 |
| 4.6032 | 0.88 | 2400 | 4.6245 |
| 4.5949 | 0.91 | 2500 | 4.6137 |
| 4.5861 | 0.95 | 2600 | 4.5992 |
| 4.5783 | 0.99 | 2700 | 4.5927 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2