trained-tinyllama
This model is a fine-tuned version of PY007/TinyLlama-1.1B-intermediate-step-715k-1.5T on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9312
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: 2e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.9528 | 1.92 | 50 | 0.9625 |
| 0.9252 | 3.85 | 100 | 0.9312 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
- Downloads last month
- 1
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for Xiaowen-dg/trained-tinyllama
Evaluation results
- acc on agievalself-reported0.433
- acc on winograndeself-reported0.736
- acc on gsgsm8kself-reported0.6
- en_content_to_title_acc on gdprself-reported0.7
- en_title_to_content_acc on gdprself-reported0.6
- acc on truthfulqaself-reported0.501