<!-- 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. -->
checkpoints_3_12
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0095
- Map@3: 0.7278
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: 1e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 0
- gradient_accumulation_steps: 8
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss | Map@3 |
|---|---|---|---|---|
| 1.2279 | 0.04 | 200 | 1.0085 | 0.7305 |
| 1.2068 | 0.08 | 400 | 1.0804 | 0.7313 |
| 1.1809 | 0.13 | 600 | 1.0225 | 0.7302 |
| 1.0666 | 0.17 | 800 | 1.2032 | 0.7248 |
| 1.0671 | 0.21 | 1000 | 1.0308 | 0.7243 |
| 1.0396 | 0.25 | 1200 | 1.0818 | 0.7183 |
| 1.0183 | 0.29 | 1400 | 1.1960 | 0.7205 |
| 0.9193 | 0.34 | 1600 | 1.2615 | 0.7072 |
| 0.9277 | 0.38 | 1800 | 1.1993 | 0.7230 |
| 0.9777 | 0.42 | 2000 | 1.2120 | 0.7203 |
| 0.9021 | 0.46 | 2200 | 1.4372 | 0.7208 |
| 0.9538 | 0.51 | 2400 | 1.1713 | 0.7167 |
| 0.9536 | 0.55 | 2600 | 1.2319 | 0.7225 |
| 0.8825 | 0.59 | 2800 | 1.1445 | 0.7257 |
| 0.9923 | 0.63 | 3000 | 1.0981 | 0.7195 |
| 1.0443 | 0.67 | 3200 | 1.0991 | 0.7268 |
| 1.0926 | 0.72 | 3400 | 1.1384 | 0.7332 |
| 1.1126 | 0.76 | 3600 | 1.0627 | 0.7287 |
| 1.1415 | 0.8 | 3800 | 1.0397 | 0.7317 |
| 1.2765 | 0.84 | 4000 | 1.0114 | 0.7285 |
| 1.2241 | 0.88 | 4200 | 1.0126 | 0.7295 |
| 1.2353 | 0.93 | 4400 | 1.0098 | 0.7278 |
| 1.275 | 0.97 | 4600 | 1.0095 | 0.7278 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
