tweetsum
This model is a fine-tuned version of meta-llama/Llama-2-7b-hf on the dialogstudio dataset. It achieves the following results on the evaluation set:
- Loss: 1.8487
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: 0.0001
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.8454 | 0.6 | 33 | 1.8960 |
| 1.7774 | 1.2 | 66 | 1.8618 |
| 1.7614 | 1.8 | 99 | 1.8451 |
| 1.6242 | 2.4 | 132 | 1.8505 |
| 1.6076 | 3.0 | 165 | 1.8487 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cu117
- Datasets 2.20.0
- Tokenizers 0.13.3
- Downloads last month
- 1
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for sahlebrahim/tweetsum
Base model
meta-llama/Llama-2-7b-hf