<!-- 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. -->
unifiedqa-v2-t5-base-1363200-finetuned-qa-doqa
This model is a fine-tuned version of allenai/unifiedqa-v2-t5-base-1363200 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3126
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: 5e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.7767 | 0.05 | 115 | 0.4286 |
0.5099 | 0.1 | 230 | 0.3798 |
0.4811 | 0.15 | 345 | 0.3663 |
0.3736 | 0.2 | 460 | 0.3412 |
0.3717 | 0.25 | 575 | 0.3333 |
0.3849 | 0.3 | 690 | 0.3532 |
0.4335 | 0.35 | 805 | 0.3266 |
0.3628 | 0.4 | 920 | 0.3149 |
0.3419 | 0.45 | 1035 | 0.3244 |
0.3268 | 0.5 | 1150 | 0.3359 |
0.3534 | 0.55 | 1265 | 0.3280 |
0.3806 | 0.6 | 1380 | 0.3274 |
0.3566 | 0.65 | 1495 | 0.3279 |
0.4598 | 0.7 | 1610 | 0.3082 |
0.3416 | 0.75 | 1725 | 0.3210 |
0.3154 | 0.8 | 1840 | 0.3064 |
0.3165 | 0.85 | 1955 | 0.3045 |
0.2985 | 0.9 | 2070 | 0.3126 |
0.327 | 0.95 | 2185 | 0.3090 |
0.3246 | 1.0 | 2300 | 0.3122 |
0.2495 | 1.05 | 2415 | 0.3105 |
0.2271 | 1.1 | 2530 | 0.3143 |
0.2611 | 1.15 | 2645 | 0.3149 |
0.2819 | 1.2 | 2760 | 0.3140 |
0.2583 | 1.25 | 2875 | 0.3072 |
0.2708 | 1.3 | 2990 | 0.3112 |
0.264 | 1.35 | 3105 | 0.3153 |
0.2533 | 1.4 | 3220 | 0.3103 |
0.2192 | 1.45 | 3335 | 0.3160 |
0.2568 | 1.5 | 3450 | 0.3170 |
0.2692 | 1.55 | 3565 | 0.3148 |
0.2501 | 1.6 | 3680 | 0.3112 |
0.2205 | 1.65 | 3795 | 0.3200 |
0.2896 | 1.7 | 3910 | 0.3196 |
0.2546 | 1.75 | 4025 | 0.3160 |
0.2857 | 1.8 | 4140 | 0.3122 |
0.2813 | 1.85 | 4255 | 0.3133 |
0.2395 | 1.9 | 4370 | 0.3118 |
0.2523 | 1.95 | 4485 | 0.3126 |
0.25 | 2.0 | 4600 | 0.3126 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2