G0515HMA3H
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: 0.1153
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 |
---|---|---|---|
3.1972 | 0.09 | 10 | 2.8225 |
2.5213 | 0.18 | 20 | 2.0451 |
1.5809 | 0.27 | 30 | 1.0082 |
0.6146 | 0.36 | 40 | 0.2677 |
0.198 | 0.45 | 50 | 0.1607 |
0.1542 | 0.54 | 60 | 0.1510 |
0.1498 | 0.63 | 70 | 0.1487 |
0.1509 | 0.73 | 80 | 0.1518 |
0.145 | 0.82 | 90 | 0.1489 |
0.1463 | 0.91 | 100 | 0.1471 |
0.1486 | 1.0 | 110 | 0.1473 |
0.1427 | 1.09 | 120 | 0.1465 |
0.1434 | 1.18 | 130 | 0.1450 |
0.1442 | 1.27 | 140 | 0.1407 |
0.1434 | 1.36 | 150 | 0.1392 |
0.1343 | 1.45 | 160 | 0.1376 |
0.1372 | 1.54 | 170 | 0.1366 |
0.135 | 1.63 | 180 | 0.1317 |
0.1367 | 1.72 | 190 | 0.1341 |
0.1322 | 1.81 | 200 | 0.1260 |
0.128 | 1.9 | 210 | 0.1229 |
0.1286 | 1.99 | 220 | 0.1223 |
0.1185 | 2.08 | 230 | 0.1197 |
0.1164 | 2.18 | 240 | 0.1187 |
0.1126 | 2.27 | 250 | 0.1199 |
0.1169 | 2.36 | 260 | 0.1184 |
0.1162 | 2.45 | 270 | 0.1199 |
0.1135 | 2.54 | 280 | 0.1179 |
0.1094 | 2.63 | 290 | 0.1156 |
0.1092 | 2.72 | 300 | 0.1155 |
0.116 | 2.81 | 310 | 0.1155 |
0.1142 | 2.9 | 320 | 0.1154 |
0.1128 | 2.99 | 330 | 0.1153 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.14.0
Model tree for Litzy619/G0515HMA3H
Base model
google/gemma-2b
Finetuned
this model