Downloads · 30 days
0
O0430HMA1
Litzy619/O0430HMA1
O0430HMA1 is a machine learning model from Litzy619. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
Access
Public
Updated Apr 30, 2024
Parameters
1.2B
5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors4.8 GB · 97%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Apr 30, 2024
- Updated
- Apr 30, 2024
- SHA
- cf519bd7
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. -->
O0430HMA1
This model is a fine-tuned version of allenai/OLMo-1B on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0203
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: 0.0003
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine_with_restarts
- lr_scheduler_warmup_steps: 80
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.0135 | 0.09 | 10 | 0.3204 |
| 0.1991 | 0.18 | 20 | 0.1575 |
| 0.15 | 0.27 | 30 | 0.1643 |
| 0.1573 | 0.36 | 40 | 0.1525 |
| 0.1495 | 0.45 | 50 | 0.1508 |
| 0.1514 | 0.54 | 60 | 0.1491 |
| 0.149 | 0.63 | 70 | 0.1476 |
| 0.15 | 0.73 | 80 | 0.1597 |
| 0.146 | 0.82 | 90 | 0.1489 |
| 0.1504 | 0.91 | 100 | 0.1455 |
| 0.1358 | 1.0 | 110 | 0.0842 |
| 0.1868 | 1.09 | 120 | 0.1344 |
| 0.1262 | 1.18 | 130 | 0.1144 |
| 0.1965 | 1.27 | 140 | 0.1019 |
| 0.0895 | 1.36 | 150 | 0.0772 |
| 0.0653 | 1.45 | 160 | 0.0576 |
| 0.043 | 1.54 | 170 | 0.0449 |
| 0.0641 | 1.63 | 180 | 0.0361 |
| 0.0392 | 1.72 | 190 | 0.0259 |
| 0.0275 | 1.81 | 200 | 0.0246 |
| 0.0256 | 1.9 | 210 | 0.0254 |
| 0.023 | 1.99 | 220 | 0.0246 |
| 0.0278 | 2.08 | 230 | 0.0241 |
| 0.0246 | 2.18 | 240 | 0.0227 |
| 0.0201 | 2.27 | 250 | 0.0251 |
| 0.0229 | 2.36 | 260 | 0.0223 |
| 0.0196 | 2.45 | 270 | 0.0213 |
| 0.0167 | 2.54 | 280 | 0.0210 |
| 0.0236 | 2.63 | 290 | 0.0207 |
| 0.0199 | 2.72 | 300 | 0.0204 |
| 0.0207 | 2.81 | 310 | 0.0203 |
| 0.0207 | 2.9 | 320 | 0.0203 |
| 0.0217 | 2.99 | 330 | 0.0203 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.14.1
- License
- apache-2.0
- Created
- Apr 30, 2024
- Updated
- Apr 30, 2024