Downloads · 30 days
15
22% of all-time downloads
pythia-70m-sft-function-calling
borkh/pythia-70m-sft-function-calling
pythia-70m-sft-function-calling is a text generation model from borkh. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
68
Public
Parameters
70.4M
2.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors282 MB · 99%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Model type
- gpt_neox
- Access
- Public
- Created
- Nov 12, 2023
- Updated
- Nov 12, 2023
- SHA
- 57b983e6
Try a prompt
Base models
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. -->
pythia-70m-sft-function-calling
This model is a fine-tuned version of EleutherAI/pythia-70m on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9858
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: 5
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.2294 | 0.11 | 2000 | 1.2844 |
| 1.115 | 0.22 | 4000 | 1.1689 |
| 1.0368 | 0.33 | 6000 | 1.1194 |
| 1.0346 | 0.44 | 8000 | 1.0797 |
| 0.9951 | 0.55 | 10000 | 1.0522 |
| 0.9832 | 0.66 | 12000 | 1.0325 |
| 0.9931 | 0.77 | 14000 | 1.0093 |
| 0.9502 | 0.88 | 16000 | 0.9944 |
| 0.9649 | 0.99 | 18000 | 0.9858 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu121
- Datasets 2.14.6
- Tokenizers 0.14.1
- Task
- Text Generation
- Library
- transformers
- Type
- gpt_neox
- License
- apache-2.0
- Created
- Nov 12, 2023
- Updated
- Nov 12, 2023