Downloads · 30 days
0
G0519ABLATION1V3
Litzy619/G0519ABLATION1V3
G0519ABLATION1V3 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 gemma.
should probably proofread and complete it, then remove this comment. --
Access
Public
Updated May 19, 2024
Parameters
2.5B
10.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors10.1 GB · 99%
At a glance
- License
- gemma
- Access
- Public
- Created
- May 19, 2024
- Updated
- May 19, 2024
- SHA
- 8da20b53
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. -->
G0519ABLATION1V3
This model is a fine-tuned version of google/gemma-2b on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1140
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: 60
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.8863 | 0.09 | 10 | 1.9768 |
| 1.3136 | 0.18 | 20 | 0.5887 |
| 0.2921 | 0.27 | 30 | 0.1691 |
| 0.1597 | 0.36 | 40 | 0.1507 |
| 0.1484 | 0.45 | 50 | 0.1511 |
| 0.152 | 0.54 | 60 | 0.1504 |
| 0.1491 | 0.63 | 70 | 0.1491 |
| 0.1496 | 0.73 | 80 | 0.1484 |
| 0.1428 | 0.82 | 90 | 0.1484 |
| 0.1446 | 0.91 | 100 | 0.1480 |
| 0.1484 | 1.0 | 110 | 0.1486 |
| 0.1428 | 1.09 | 120 | 0.1491 |
| 0.1453 | 1.18 | 130 | 0.1483 |
| 0.1453 | 1.27 | 140 | 0.1462 |
| 0.1477 | 1.36 | 150 | 0.1450 |
| 0.1406 | 1.45 | 160 | 0.1445 |
| 0.1415 | 1.54 | 170 | 0.1452 |
| 0.1437 | 1.63 | 180 | 0.1403 |
| 0.1408 | 1.72 | 190 | 0.1377 |
| 0.1345 | 1.81 | 200 | 0.1333 |
| 0.1342 | 1.9 | 210 | 0.1299 |
| 0.1335 | 1.99 | 220 | 0.1288 |
| 0.1236 | 2.08 | 230 | 0.1238 |
| 0.1197 | 2.18 | 240 | 0.1215 |
| 0.1174 | 2.27 | 250 | 0.1190 |
| 0.1206 | 2.36 | 260 | 0.1177 |
| 0.1184 | 2.45 | 270 | 0.1176 |
| 0.1135 | 2.54 | 280 | 0.1159 |
| 0.1092 | 2.63 | 290 | 0.1153 |
| 0.1104 | 2.72 | 300 | 0.1150 |
| 0.1165 | 2.81 | 310 | 0.1141 |
| 0.1165 | 2.9 | 320 | 0.1140 |
| 0.1144 | 2.99 | 330 | 0.1140 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.14.0
- License
- gemma
- Created
- May 19, 2024
- Updated
- May 19, 2024