--- license: apache-2.0 base_model: google/flan-t5-base tags: - generated_from_trainer model-index: - name: flan-t5-ellis-way-v2 results: [] --- # flan-t5-ellis-way-v2 This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.1617 ## 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: 1 - eval_batch_size: 1 - seed: 42 - gradient_accumulation_steps: 16 - total_train_batch_size: 16 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 500 - num_epochs: 200 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:------:|:-----:|:---------------:| | 1.0607 | 1.71 | 500 | 0.8848 | | 0.8287 | 3.42 | 1000 | 0.7583 | | 0.7292 | 5.13 | 1500 | 0.7125 | | 0.734 | 6.84 | 2000 | 0.6789 | | 0.6723 | 8.55 | 2500 | 0.6560 | | 0.6169 | 10.26 | 3000 | 0.6440 | | 0.5983 | 11.97 | 3500 | 0.6257 | | 0.591 | 13.68 | 4000 | 0.6267 | | 0.5581 | 15.39 | 4500 | 0.6153 | | 0.5225 | 17.1 | 5000 | 0.6148 | | 0.5249 | 18.81 | 5500 | 0.6138 | | 0.5052 | 20.52 | 6000 | 0.6106 | | 0.4441 | 22.23 | 6500 | 0.6065 | | 0.455 | 23.94 | 7000 | 0.6107 | | 0.4198 | 25.65 | 7500 | 0.6175 | | 0.3975 | 27.36 | 8000 | 0.6147 | | 0.3991 | 29.07 | 8500 | 0.6161 | | 0.4088 | 30.78 | 9000 | 0.6215 | | 0.373 | 32.49 | 9500 | 0.6229 | | 0.3769 | 34.2 | 10000 | 0.6200 | | 0.3619 | 35.91 | 10500 | 0.6280 | | 0.3522 | 37.61 | 11000 | 0.6354 | | 0.3412 | 39.32 | 11500 | 0.6396 | | 0.3325 | 41.03 | 12000 | 0.6420 | | 0.3235 | 42.74 | 12500 | 0.6477 | | 0.313 | 44.45 | 13000 | 0.6592 | | 0.2881 | 46.16 | 13500 | 0.6690 | | 0.3132 | 47.87 | 14000 | 0.6713 | | 0.2774 | 49.58 | 14500 | 0.6858 | | 0.2797 | 51.29 | 15000 | 0.6813 | | 0.2725 | 53.0 | 15500 | 0.6872 | | 0.2561 | 54.71 | 16000 | 0.7032 | | 0.244 | 56.42 | 16500 | 0.7145 | | 0.2467 | 58.13 | 17000 | 0.7287 | | 0.2483 | 59.84 | 17500 | 0.7305 | | 0.2461 | 61.55 | 18000 | 0.7261 | | 0.2297 | 63.26 | 18500 | 0.7400 | | 0.2372 | 64.97 | 19000 | 0.7393 | | 0.2192 | 66.68 | 19500 | 0.7504 | | 0.2045 | 68.39 | 20000 | 0.7618 | | 0.1823 | 70.1 | 20500 | 0.7855 | | 0.2013 | 71.81 | 21000 | 0.7768 | | 0.2011 | 73.52 | 21500 | 0.7907 | | 0.1819 | 75.23 | 22000 | 0.8015 | | 0.1805 | 76.94 | 22500 | 0.7997 | | 0.1779 | 78.65 | 23000 | 0.8211 | | 0.1716 | 80.36 | 23500 | 0.8221 | | 0.1643 | 82.07 | 24000 | 0.8393 | | 0.1586 | 83.78 | 24500 | 0.8258 | | 0.1613 | 85.49 | 25000 | 0.8411 | | 0.1493 | 87.2 | 25500 | 0.8518 | | 0.1549 | 88.91 | 26000 | 0.8599 | | 0.1479 | 90.62 | 26500 | 0.8742 | | 0.1485 | 92.33 | 27000 | 0.8752 | | 0.1378 | 94.04 | 27500 | 0.8784 | | 0.1357 | 95.75 | 28000 | 0.8893 | | 0.1395 | 97.46 | 28500 | 0.9146 | | 0.1277 | 99.17 | 29000 | 0.9052 | | 0.1272 | 100.88 | 29500 | 0.9145 | | 0.1305 | 102.59 | 30000 | 0.9219 | | 0.1212 | 104.3 | 30500 | 0.9261 | | 0.1221 | 106.01 | 31000 | 0.9443 | | 0.1162 | 107.72 | 31500 | 0.9420 | | 0.1175 | 109.43 | 32000 | 0.9465 | | 0.1092 | 111.13 | 32500 | 0.9682 | | 0.1141 | 112.84 | 33000 | 0.9717 | | 0.1104 | 114.55 | 33500 | 0.9667 | | 0.1031 | 116.26 | 34000 | 0.9839 | | 0.1037 | 117.97 | 34500 | 0.9852 | | 0.1131 | 119.68 | 35000 | 0.9852 | | 0.0965 | 121.39 | 35500 | 1.0028 | | 0.0975 | 123.1 | 36000 | 1.0021 | | 0.0968 | 124.81 | 36500 | 1.0105 | | 0.0964 | 126.52 | 37000 | 1.0223 | | 0.0938 | 128.23 | 37500 | 1.0217 | | 0.0931 | 129.94 | 38000 | 1.0297 | | 0.0861 | 131.65 | 38500 | 1.0355 | | 0.0907 | 133.36 | 39000 | 1.0438 | | 0.0914 | 135.07 | 39500 | 1.0437 | | 0.0869 | 136.78 | 40000 | 1.0455 | | 0.0842 | 138.49 | 40500 | 1.0635 | | 0.0859 | 140.2 | 41000 | 1.0559 | | 0.0854 | 141.91 | 41500 | 1.0519 | | 0.0799 | 143.62 | 42000 | 1.0687 | | 0.0805 | 145.33 | 42500 | 1.0685 | | 0.0786 | 147.04 | 43000 | 1.0736 | | 0.0726 | 148.75 | 43500 | 1.0865 | | 0.0818 | 150.46 | 44000 | 1.0878 | | 0.0793 | 152.17 | 44500 | 1.0877 | | 0.0757 | 153.88 | 45000 | 1.0996 | | 0.0731 | 155.59 | 45500 | 1.0994 | | 0.0751 | 157.3 | 46000 | 1.1119 | | 0.0729 | 159.01 | 46500 | 1.1097 | | 0.0686 | 160.72 | 47000 | 1.0965 | | 0.0681 | 162.43 | 47500 | 1.1212 | | 0.0705 | 164.14 | 48000 | 1.1200 | | 0.0712 | 165.85 | 48500 | 1.1177 | | 0.0646 | 167.56 | 49000 | 1.1298 | | 0.0656 | 169.27 | 49500 | 1.1298 | | 0.0699 | 170.98 | 50000 | 1.1339 | | 0.067 | 172.69 | 50500 | 1.1436 | | 0.0647 | 174.4 | 51000 | 1.1394 | | 0.0669 | 176.11 | 51500 | 1.1472 | | 0.0624 | 177.82 | 52000 | 1.1522 | | 0.07 | 179.53 | 52500 | 1.1453 | | 0.0692 | 181.24 | 53000 | 1.1482 | | 0.0633 | 182.95 | 53500 | 1.1533 | | 0.0611 | 184.65 | 54000 | 1.1526 | | 0.067 | 186.36 | 54500 | 1.1538 | | 0.06 | 188.07 | 55000 | 1.1582 | | 0.0652 | 189.78 | 55500 | 1.1565 | | 0.0602 | 191.49 | 56000 | 1.1577 | | 0.0622 | 193.2 | 56500 | 1.1606 | | 0.0652 | 194.91 | 57000 | 1.1603 | | 0.0626 | 196.62 | 57500 | 1.1617 | | 0.0563 | 198.33 | 58000 | 1.1617 | ### Framework versions - Transformers 4.38.2 - Pytorch 2.1.0 - Datasets 2.18.0 - Tokenizers 0.15.2