myBit-Llama2-jp-127M-9
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.1237
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 |
---|---|---|---|
4.942 | 0.05 | 2000 | 4.0108 |
3.8538 | 0.1 | 4000 | 3.7539 |
3.6851 | 0.15 | 6000 | 3.6035 |
3.5576 | 0.2 | 8000 | 3.5148 |
3.4927 | 0.25 | 10000 | 3.4689 |
3.4527 | 0.29 | 12000 | 3.4396 |
3.4297 | 0.34 | 14000 | 3.4145 |
3.4097 | 0.39 | 16000 | 3.4084 |
3.3969 | 0.44 | 18000 | 3.3821 |
3.3848 | 0.49 | 20000 | 3.3827 |
3.3804 | 0.54 | 22000 | 3.3771 |
3.3732 | 0.59 | 24000 | 3.3658 |
3.3548 | 0.64 | 26000 | 3.3471 |
3.3324 | 0.69 | 28000 | 3.3222 |
3.3189 | 0.74 | 30000 | 3.3045 |
3.2819 | 0.79 | 32000 | 3.2491 |
3.2398 | 0.83 | 34000 | 3.2330 |
3.2202 | 0.88 | 36000 | 3.1948 |
3.1791 | 0.93 | 38000 | 3.1656 |
3.1466 | 0.98 | 40000 | 3.1237 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 5
Inference API (serverless) does not yet support model repos that contain custom code.