metadata
license: apache-2.0
tags:
- generated_from_trainer
base_model: t5-small
model-index:
- name: flash-cards-3
results: []
flash-cards-3
This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.7948
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: 0.0001
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.4513 | 0.02 | 100 | 2.1769 |
| 2.0154 | 0.05 | 200 | 2.1152 |
| 1.9263 | 0.07 | 300 | 2.0674 |
| 1.8961 | 0.1 | 400 | 2.0238 |
| 1.8337 | 0.12 | 500 | 2.0077 |
| 1.8257 | 0.15 | 600 | 1.9759 |
| 1.7823 | 0.17 | 700 | 1.9606 |
| 1.7577 | 0.2 | 800 | 1.9522 |
| 1.7334 | 0.22 | 900 | 1.9317 |
| 1.7246 | 0.25 | 1000 | 1.9378 |
| 1.7257 | 0.27 | 1100 | 1.9243 |
| 1.699 | 0.3 | 1200 | 1.9139 |
| 1.716 | 0.32 | 1300 | 1.9115 |
| 1.696 | 0.35 | 1400 | 1.9026 |
| 1.668 | 0.37 | 1500 | 1.8991 |
| 1.6892 | 0.4 | 1600 | 1.8887 |
| 1.6557 | 0.42 | 1700 | 1.8877 |
| 1.6801 | 0.44 | 1800 | 1.8882 |
| 1.6523 | 0.47 | 1900 | 1.8778 |
| 1.649 | 0.49 | 2000 | 1.8725 |
| 1.6599 | 0.52 | 2100 | 1.8718 |
| 1.6394 | 0.54 | 2200 | 1.8740 |
| 1.6288 | 0.57 | 2300 | 1.8703 |
| 1.6403 | 0.59 | 2400 | 1.8645 |
| 1.6387 | 0.62 | 2500 | 1.8677 |
| 1.6172 | 0.64 | 2600 | 1.8583 |
| 1.6347 | 0.67 | 2700 | 1.8672 |
| 1.627 | 0.69 | 2800 | 1.8506 |
| 1.6053 | 0.72 | 2900 | 1.8533 |
| 1.6181 | 0.74 | 3000 | 1.8557 |
| 1.6146 | 0.77 | 3100 | 1.8492 |
| 1.5963 | 0.79 | 3200 | 1.8527 |
| 1.5977 | 0.82 | 3300 | 1.8581 |
| 1.5787 | 0.84 | 3400 | 1.8490 |
| 1.6129 | 0.87 | 3500 | 1.8396 |
| 1.5929 | 0.89 | 3600 | 1.8360 |
| 1.5866 | 0.91 | 3700 | 1.8421 |
| 1.5594 | 0.94 | 3800 | 1.8485 |
| 1.5946 | 0.96 | 3900 | 1.8300 |
| 1.5622 | 0.99 | 4000 | 1.8351 |
| 1.5798 | 1.01 | 4100 | 1.8374 |
| 1.5718 | 1.04 | 4200 | 1.8368 |
| 1.5517 | 1.06 | 4300 | 1.8287 |
| 1.5576 | 1.09 | 4400 | 1.8271 |
| 1.5605 | 1.11 | 4500 | 1.8331 |
| 1.5467 | 1.14 | 4600 | 1.8236 |
| 1.5396 | 1.16 | 4700 | 1.8229 |
| 1.5463 | 1.19 | 4800 | 1.8288 |
| 1.553 | 1.21 | 4900 | 1.8230 |
| 1.5571 | 1.24 | 5000 | 1.8231 |
| 1.5451 | 1.26 | 5100 | 1.8192 |
| 1.5278 | 1.29 | 5200 | 1.8180 |
| 1.5285 | 1.31 | 5300 | 1.8220 |
| 1.5403 | 1.33 | 5400 | 1.8190 |
| 1.5189 | 1.36 | 5500 | 1.8276 |
| 1.5495 | 1.38 | 5600 | 1.8230 |
| 1.5169 | 1.41 | 5700 | 1.8185 |
| 1.516 | 1.43 | 5800 | 1.8174 |
| 1.5355 | 1.46 | 5900 | 1.8199 |
| 1.5321 | 1.48 | 6000 | 1.8167 |
| 1.5335 | 1.51 | 6100 | 1.8122 |
| 1.5236 | 1.53 | 6200 | 1.8140 |
| 1.5232 | 1.56 | 6300 | 1.8106 |
| 1.5233 | 1.58 | 6400 | 1.8120 |
| 1.5053 | 1.61 | 6500 | 1.8102 |
| 1.5056 | 1.63 | 6600 | 1.8162 |
| 1.5074 | 1.66 | 6700 | 1.8153 |
| 1.5204 | 1.68 | 6800 | 1.8129 |
| 1.5115 | 1.71 | 6900 | 1.8119 |
| 1.4929 | 1.73 | 7000 | 1.8127 |
| 1.5278 | 1.76 | 7100 | 1.8102 |
| 1.4959 | 1.78 | 7200 | 1.8087 |
| 1.5028 | 1.8 | 7300 | 1.8091 |
| 1.5169 | 1.83 | 7400 | 1.8057 |
| 1.5181 | 1.85 | 7500 | 1.8078 |
| 1.5164 | 1.88 | 7600 | 1.8012 |
| 1.5071 | 1.9 | 7700 | 1.8052 |
| 1.5299 | 1.93 | 7800 | 1.8019 |
| 1.4985 | 1.95 | 7900 | 1.8058 |
| 1.5185 | 1.98 | 8000 | 1.8002 |
| 1.5377 | 2.0 | 8100 | 1.7989 |
| 1.4731 | 2.03 | 8200 | 1.8086 |
| 1.4956 | 2.05 | 8300 | 1.8058 |
| 1.4683 | 2.08 | 8400 | 1.8024 |
| 1.4965 | 2.1 | 8500 | 1.8037 |
| 1.4895 | 2.13 | 8600 | 1.8046 |
| 1.4995 | 2.15 | 8700 | 1.8026 |
| 1.491 | 2.18 | 8800 | 1.8030 |
| 1.4749 | 2.2 | 8900 | 1.8020 |
| 1.4952 | 2.22 | 9000 | 1.8007 |
| 1.4788 | 2.25 | 9100 | 1.8001 |
| 1.4983 | 2.27 | 9200 | 1.7966 |
| 1.497 | 2.3 | 9300 | 1.7967 |
| 1.4708 | 2.32 | 9400 | 1.7974 |
| 1.4793 | 2.35 | 9500 | 1.8003 |
| 1.4726 | 2.37 | 9600 | 1.8012 |
| 1.4788 | 2.4 | 9700 | 1.7967 |
| 1.4828 | 2.42 | 9800 | 1.7985 |
| 1.4686 | 2.45 | 9900 | 1.8011 |
| 1.4941 | 2.47 | 10000 | 1.7970 |
| 1.4721 | 2.5 | 10100 | 1.7976 |
| 1.4557 | 2.52 | 10200 | 1.7973 |
| 1.4866 | 2.55 | 10300 | 1.7971 |
| 1.481 | 2.57 | 10400 | 1.7972 |
| 1.4986 | 2.6 | 10500 | 1.7949 |
| 1.4911 | 2.62 | 10600 | 1.7964 |
| 1.483 | 2.65 | 10700 | 1.7954 |
| 1.4994 | 2.67 | 10800 | 1.7928 |
| 1.4674 | 2.69 | 10900 | 1.7968 |
| 1.4693 | 2.72 | 11000 | 1.7952 |
| 1.4774 | 2.74 | 11100 | 1.7965 |
| 1.4885 | 2.77 | 11200 | 1.7949 |
| 1.4802 | 2.79 | 11300 | 1.7940 |
| 1.4712 | 2.82 | 11400 | 1.7950 |
| 1.4896 | 2.84 | 11500 | 1.7942 |
| 1.4887 | 2.87 | 11600 | 1.7944 |
| 1.4789 | 2.89 | 11700 | 1.7958 |
| 1.4963 | 2.92 | 11800 | 1.7942 |
| 1.4976 | 2.94 | 11900 | 1.7941 |
| 1.4737 | 2.97 | 12000 | 1.7947 |
| 1.4654 | 2.99 | 12100 | 1.7948 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu116
- Datasets 2.8.0
- Tokenizers 0.13.2