Downloads · 30 days
0
Kaggle-Science-LLM
Adi-ds/Kaggle-Science-LLM
Kaggle-Science-LLM is a machine learning model from Adi-ds. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
should probably proofread and complete it, then remove this comment. --
Access
Public
Updated Oct 28, 2023
Repo size
269 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin134 MB · 98%
At a glance
- Access
- Public
- Created
- Aug 8, 2023
- Updated
- Oct 28, 2023
- SHA
- b9548ec1
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
Kaggle-Science-LLM
This model is a fine-tuned version of meta-llama/Llama-2-7b-hf on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 4.4145
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: 1.5e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 69
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.03
- training_steps: 50
- label_smoothing_factor: 0.1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 6.6679 | 0.01 | 5 | 6.5113 |
| 6.4844 | 0.02 | 10 | 6.3461 |
| 6.2521 | 0.02 | 15 | 6.1616 |
| 6.0889 | 0.03 | 20 | 5.9515 |
| 5.8295 | 0.04 | 25 | 5.7202 |
| 5.6072 | 0.05 | 30 | 5.4724 |
| 5.339 | 0.06 | 35 | 5.2136 |
| 5.0985 | 0.06 | 40 | 4.9514 |
| 4.8879 | 0.07 | 45 | 4.6861 |
| 4.6319 | 0.08 | 50 | 4.4145 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3
- Created
- Aug 8, 2023
- Updated
- Oct 28, 2023