Downloads · 30 days
0
O0428HMA9
Litzy619/O0428HMA9
O0428HMA9 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
Repo size
101 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin101 MB · 98%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Apr 30, 2024
- Updated
- Apr 30, 2024
- SHA
- 88b74acd
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. -->
O0428HMA9
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: 0.0545
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: 100
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.6202 | 0.09 | 10 | 0.2442 |
| 0.1807 | 0.18 | 20 | 0.1525 |
| 0.1486 | 0.27 | 30 | 0.1701 |
| 0.1564 | 0.36 | 40 | 0.1538 |
| 0.1507 | 0.45 | 50 | 0.1492 |
| 0.1511 | 0.54 | 60 | 0.1474 |
| 0.1491 | 0.63 | 70 | 0.1472 |
| 0.1496 | 0.73 | 80 | 0.1551 |
| 0.1466 | 0.82 | 90 | 0.1500 |
| 0.1496 | 0.91 | 100 | 0.1495 |
| 0.1516 | 1.0 | 110 | 0.1463 |
| 0.1509 | 1.09 | 120 | 0.1321 |
| 0.3642 | 1.18 | 130 | 0.2426 |
| 0.179 | 1.27 | 140 | 0.1081 |
| 0.1519 | 1.36 | 150 | 0.1300 |
| 0.272 | 1.45 | 160 | 0.0911 |
| 0.0746 | 1.54 | 170 | 0.0694 |
| 0.0657 | 1.63 | 180 | 0.0619 |
| 0.0678 | 1.72 | 190 | 0.0584 |
| 0.0578 | 1.81 | 200 | 0.0592 |
| 0.0577 | 1.9 | 210 | 0.0612 |
| 0.0599 | 1.99 | 220 | 0.0554 |
| 0.0587 | 2.08 | 230 | 0.0568 |
| 0.0538 | 2.18 | 240 | 0.0564 |
| 0.0562 | 2.27 | 250 | 0.0581 |
| 0.0591 | 2.36 | 260 | 0.0568 |
| 0.0537 | 2.45 | 270 | 0.0551 |
| 0.0523 | 2.54 | 280 | 0.0557 |
| 0.0548 | 2.63 | 290 | 0.0566 |
| 0.056 | 2.72 | 300 | 0.0545 |
| 0.0569 | 2.81 | 310 | 0.0543 |
| 0.0584 | 2.9 | 320 | 0.0545 |
| 0.0604 | 2.99 | 330 | 0.0545 |
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