metadata
tags:
- generated_from_trainer
model-index:
- name: myBit-Llama2-jp-127M-10
results: []
myBit-Llama2-jp-127M-10
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.1243
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 |
|---|---|---|---|
| 4.9389 | 0.05 | 2000 | 4.0087 |
| 3.8646 | 0.1 | 4000 | 3.7527 |
| 3.6878 | 0.15 | 6000 | 3.6071 |
| 3.5599 | 0.2 | 8000 | 3.5164 |
| 3.4959 | 0.25 | 10000 | 3.4739 |
| 3.4566 | 0.29 | 12000 | 3.4410 |
| 3.434 | 0.34 | 14000 | 3.4302 |
| 3.4188 | 0.39 | 16000 | 3.4179 |
| 3.4049 | 0.44 | 18000 | 3.3980 |
| 3.3951 | 0.49 | 20000 | 3.3955 |
| 3.3875 | 0.54 | 22000 | 3.3807 |
| 3.3658 | 0.59 | 24000 | 3.3594 |
| 3.349 | 0.64 | 26000 | 3.3399 |
| 3.3346 | 0.69 | 28000 | 3.3215 |
| 3.3137 | 0.74 | 30000 | 3.2983 |
| 3.271 | 0.79 | 32000 | 3.2683 |
| 3.2571 | 0.83 | 34000 | 3.2367 |
| 3.2199 | 0.88 | 36000 | 3.2097 |
| 3.2008 | 0.93 | 38000 | 3.1874 |
| 3.1581 | 0.98 | 40000 | 3.1243 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2