G0515HMA17H
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: 0.1169
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 |
---|---|---|---|
3.1545 | 0.09 | 10 | 2.8275 |
2.3966 | 0.18 | 20 | 1.7564 |
1.191 | 0.27 | 30 | 0.5236 |
0.2859 | 0.36 | 40 | 0.1764 |
0.1586 | 0.45 | 50 | 0.1535 |
0.1514 | 0.54 | 60 | 0.1510 |
0.1514 | 0.63 | 70 | 0.1501 |
0.1514 | 0.73 | 80 | 0.1503 |
0.1426 | 0.82 | 90 | 0.1491 |
0.1455 | 0.91 | 100 | 0.1498 |
0.1492 | 1.0 | 110 | 0.1495 |
0.1447 | 1.09 | 120 | 0.1484 |
0.145 | 1.18 | 130 | 0.1469 |
0.1457 | 1.27 | 140 | 0.1455 |
0.1474 | 1.36 | 150 | 0.1475 |
0.1415 | 1.45 | 160 | 0.1463 |
0.1417 | 1.54 | 170 | 0.1426 |
0.141 | 1.63 | 180 | 0.1400 |
0.1393 | 1.72 | 190 | 0.1394 |
0.1371 | 1.81 | 200 | 0.1332 |
0.1332 | 1.9 | 210 | 0.1314 |
0.1313 | 1.99 | 220 | 0.1248 |
0.1249 | 2.08 | 230 | 0.1261 |
0.1242 | 2.18 | 240 | 0.1266 |
0.1227 | 2.27 | 250 | 0.1227 |
0.1231 | 2.36 | 260 | 0.1213 |
0.1232 | 2.45 | 270 | 0.1218 |
0.1169 | 2.54 | 280 | 0.1200 |
0.1143 | 2.63 | 290 | 0.1182 |
0.1119 | 2.72 | 300 | 0.1174 |
0.118 | 2.81 | 310 | 0.1170 |
0.119 | 2.9 | 320 | 0.1169 |
0.1191 | 2.99 | 330 | 0.1169 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.14.0
Model tree for Litzy619/G0515HMA17H
Base model
google/gemma-2b
Finetuned
this model