|
--- |
|
license: gemma |
|
base_model: google/gemma-2b |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: G0519ABLATION1V1 |
|
results: [] |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# G0519ABLATION1V1 |
|
|
|
This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1220 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 3.2296 | 0.09 | 10 | 2.9618 | |
|
| 2.6424 | 0.18 | 20 | 2.1739 | |
|
| 1.7328 | 0.27 | 30 | 1.1890 | |
|
| 0.7887 | 0.36 | 40 | 0.3608 | |
|
| 0.233 | 0.45 | 50 | 0.1685 | |
|
| 0.1612 | 0.54 | 60 | 0.1533 | |
|
| 0.1514 | 0.63 | 70 | 0.1494 | |
|
| 0.1517 | 0.73 | 80 | 0.1488 | |
|
| 0.142 | 0.82 | 90 | 0.1491 | |
|
| 0.1459 | 0.91 | 100 | 0.1478 | |
|
| 0.1487 | 1.0 | 110 | 0.1481 | |
|
| 0.1431 | 1.09 | 120 | 0.1477 | |
|
| 0.1443 | 1.18 | 130 | 0.1467 | |
|
| 0.1448 | 1.27 | 140 | 0.1453 | |
|
| 0.1465 | 1.36 | 150 | 0.1442 | |
|
| 0.1404 | 1.45 | 160 | 0.1448 | |
|
| 0.1428 | 1.54 | 170 | 0.1444 | |
|
| 0.1424 | 1.63 | 180 | 0.1405 | |
|
| 0.1421 | 1.72 | 190 | 0.1413 | |
|
| 0.1371 | 1.81 | 200 | 0.1390 | |
|
| 0.1376 | 1.9 | 210 | 0.1339 | |
|
| 0.1351 | 1.99 | 220 | 0.1293 | |
|
| 0.1296 | 2.08 | 230 | 0.1285 | |
|
| 0.1277 | 2.18 | 240 | 0.1271 | |
|
| 0.1269 | 2.27 | 250 | 0.1276 | |
|
| 0.1286 | 2.36 | 260 | 0.1252 | |
|
| 0.1283 | 2.45 | 270 | 0.1267 | |
|
| 0.1244 | 2.54 | 280 | 0.1252 | |
|
| 0.1213 | 2.63 | 290 | 0.1230 | |
|
| 0.12 | 2.72 | 300 | 0.1220 | |
|
| 0.1263 | 2.81 | 310 | 0.1219 | |
|
| 0.1238 | 2.9 | 320 | 0.1220 | |
|
| 0.1256 | 2.99 | 330 | 0.1220 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.36.0.dev0 |
|
- Pytorch 2.1.2+cu121 |
|
- Datasets 2.14.6 |
|
- Tokenizers 0.14.0 |
|
|