Downloads · 30 days
4
1% of all-time downloads
Pythia-410m-4000_steps
PiyushLavaniya/Pythia-410m-4000_steps
Pythia-410m-4000_steps is a text generation model from PiyushLavaniya. 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
413
Public
Repo size
3.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin1.6 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Model type
- gpt_neox
- Access
- Public
- Created
- Oct 26, 2023
- Updated
- Oct 26, 2023
- SHA
- 07986637
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. -->
instruction_finetuned_4000_steps
This model is a fine-tuned version of PiyushLavaniya/Pythia-410m-1200_steps on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.1724
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: 1e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1
- training_steps: 4000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.3084 | 0.01 | 120 | 1.2513 |
| 1.2838 | 0.02 | 240 | 1.2586 |
| 1.6928 | 0.03 | 360 | 1.2545 |
| 1.026 | 0.04 | 480 | 1.2530 |
| 1.2245 | 0.05 | 600 | 1.2526 |
| 1.3283 | 0.06 | 720 | 1.2527 |
| 1.1885 | 0.07 | 840 | 1.2428 |
| 1.3262 | 0.08 | 960 | 1.2439 |
| 1.4632 | 0.09 | 1080 | 1.2399 |
| 1.4186 | 0.1 | 1200 | 1.2345 |
| 0.9493 | 0.11 | 1320 | 1.2343 |
| 1.4698 | 0.12 | 1440 | 1.2253 |
| 0.7633 | 0.13 | 1560 | 1.2262 |
| 1.1568 | 0.14 | 1680 | 1.2237 |
| 1.5223 | 0.15 | 1800 | 1.2190 |
| 1.7801 | 0.16 | 1920 | 1.2147 |
| 1.2809 | 0.17 | 2040 | 1.2099 |
| 1.2552 | 0.18 | 2160 | 1.2073 |
| 1.1965 | 0.19 | 2280 | 1.2035 |
| 1.205 | 0.21 | 2400 | 1.2026 |
| 1.2114 | 0.22 | 2520 | 1.1997 |
| 1.344 | 0.23 | 2640 | 1.1945 |
| 1.3919 | 0.24 | 2760 | 1.1916 |
| 1.4231 | 0.25 | 2880 | 1.1888 |
| 1.2136 | 0.26 | 3000 | 1.1859 |
| 0.8669 | 0.27 | 3120 | 1.1849 |
| 1.3909 | 0.28 | 3240 | 1.1823 |
| 1.2214 | 0.29 | 3360 | 1.1801 |
| 1.238 | 0.3 | 3480 | 1.1780 |
| 1.4586 | 0.31 | 3600 | 1.1757 |
| 1.0247 | 0.32 | 3720 | 1.1744 |
| 1.0334 | 0.33 | 3840 | 1.1731 |
| 1.2078 | 0.34 | 3960 | 1.1724 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1
- Task
- Text Generation
- Library
- transformers
- Type
- gpt_neox
- License
- apache-2.0
- Created
- Oct 26, 2023
- Updated
- Oct 26, 2023