Downloads · 30 days
19
18% of all-time downloads
gpt2-sft-lima
pkarypis/gpt2-sft-lima
gpt2-sft-lima is a text generation model from pkarypis. 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
103
Public
Parameters
68M
273 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors136 MB · 98%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Model type
- llama
- Access
- Public
- Created
- Apr 25, 2024
- Updated
- Apr 25, 2024
- SHA
- 47701616
Try a prompt
Base models
Datasets
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. -->
gpt2-sft-lima
This model is a fine-tuned version of JackFram/llama-68m on the GAIR/lima dataset. It achieves the following results on the evaluation set:
- Loss: 5.5083
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: 32
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- total_train_batch_size: 128
- total_eval_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 2.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.6492 | 1.0 | 6 | 5.7124 |
| 3.457 | 2.0 | 12 | 5.5083 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.2
- Datasets 2.14.6
- Tokenizers 0.15.2
- Task
- Text Generation
- Library
- transformers
- Type
- llama
- License
- apache-2.0
- Created
- Apr 25, 2024
- Updated
- Apr 25, 2024