--- license: mit base_model: facebook/bart-large-cnn tags: - generated_from_trainer model-index: - name: bart-large-cnn-finetuned-prompt_generation results: [] --- # bart-large-cnn-finetuned-prompt_generation This model is a fine-tuned version of [facebook/bart-large-cnn](https://huggingface.co./facebook/bart-large-cnn) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 2.8294 - Map: 0.4211 - Ndcg@10: 0.6088 ## 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: 3e-07 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 100 ### Training results | Training Loss | Epoch | Step | Validation Loss | Map | Ndcg@10 | |:-------------:|:-----:|:----:|:---------------:|:------:|:-------:| | No log | 1.0 | 2 | 3.6607 | 0.3400 | 0.4882 | | No log | 2.0 | 4 | 3.6575 | 0.3 | 0.4282 | | No log | 3.0 | 6 | 3.6485 | 0.3183 | 0.5016 | | No log | 4.0 | 8 | 3.6279 | 0.3183 | 0.4899 | | No log | 5.0 | 10 | 3.6199 | 0.3183 | 0.4899 | | No log | 6.0 | 12 | 3.6119 | 0.3123 | 0.5016 | | No log | 7.0 | 14 | 3.6076 | 0.3323 | 0.5299 | | No log | 8.0 | 16 | 3.5413 | 0.3523 | 0.5733 | | No log | 9.0 | 18 | 3.5274 | 0.345 | 0.5333 | | No log | 10.0 | 20 | 3.5184 | 0.3200 | 0.4816 | | No log | 11.0 | 22 | 3.5041 | 0.3200 | 0.5016 | | No log | 12.0 | 24 | 3.4935 | 0.3133 | 0.4899 | | No log | 13.0 | 26 | 3.4858 | 0.31 | 0.4951 | | No log | 14.0 | 28 | 3.4763 | 0.31 | 0.5068 | | No log | 15.0 | 30 | 3.3761 | 0.34 | 0.5434 | | No log | 16.0 | 32 | 3.3314 | 0.345 | 0.5751 | | No log | 17.0 | 34 | 3.3103 | 0.3283 | 0.5468 | | No log | 18.0 | 36 | 3.2951 | 0.3233 | 0.5151 | | No log | 19.0 | 38 | 3.2811 | 0.3233 | 0.5034 | | No log | 20.0 | 40 | 3.2708 | 0.3167 | 0.4834 | | No log | 21.0 | 42 | 3.2625 | 0.3233 | 0.4834 | | No log | 22.0 | 44 | 3.2471 | 0.3133 | 0.4834 | | No log | 23.0 | 46 | 3.2308 | 0.3067 | 0.5034 | | No log | 24.0 | 48 | 3.2171 | 0.2867 | 0.4634 | | No log | 25.0 | 50 | 3.2068 | 0.2933 | 0.4751 | | No log | 26.0 | 52 | 3.1972 | 0.2890 | 0.4803 | | No log | 27.0 | 54 | 3.1892 | 0.2757 | 0.4252 | | No log | 28.0 | 56 | 3.1812 | 0.2823 | 0.4252 | | No log | 29.0 | 58 | 3.1681 | 0.309 | 0.4769 | | No log | 30.0 | 60 | 3.1422 | 0.3223 | 0.4969 | | No log | 31.0 | 62 | 3.1154 | 0.309 | 0.4769 | | No log | 32.0 | 64 | 3.0906 | 0.369 | 0.5539 | | No log | 33.0 | 66 | 3.0680 | 0.3850 | 0.5486 | | No log | 34.0 | 68 | 3.0476 | 0.3567 | 0.5139 | | No log | 35.0 | 70 | 3.0301 | 0.3347 | 0.4909 | | No log | 36.0 | 72 | 3.0159 | 0.2861 | 0.4581 | | No log | 37.0 | 74 | 3.0040 | 0.2887 | 0.4678 | | No log | 38.0 | 76 | 2.9937 | 0.3003 | 0.4374 | | No log | 39.0 | 78 | 2.9842 | 0.2723 | 0.3950 | | No log | 40.0 | 80 | 2.9759 | 0.3052 | 0.4695 | | No log | 41.0 | 82 | 2.9686 | 0.2867 | 0.4459 | | No log | 42.0 | 84 | 2.9622 | 0.3099 | 0.4764 | | No log | 43.0 | 86 | 2.9565 | 0.3141 | 0.5019 | | No log | 44.0 | 88 | 2.9512 | 0.325 | 0.5204 | | No log | 45.0 | 90 | 2.9462 | 0.3050 | 0.5004 | | No log | 46.0 | 92 | 2.9416 | 0.325 | 0.5151 | | No log | 47.0 | 94 | 2.9372 | 0.3183 | 0.4951 | | No log | 48.0 | 96 | 2.9325 | 0.318 | 0.5235 | | No log | 49.0 | 98 | 2.9278 | 0.318 | 0.5269 | | No log | 50.0 | 100 | 2.9228 | 0.3155 | 0.5380 | | No log | 51.0 | 102 | 2.9178 | 0.2795 | 0.4823 | | No log | 52.0 | 104 | 2.9127 | 0.3329 | 0.5655 | | No log | 53.0 | 106 | 2.9081 | 0.3127 | 0.5455 | | No log | 54.0 | 108 | 2.9037 | 0.3195 | 0.5642 | | No log | 55.0 | 110 | 2.8995 | 0.3145 | 0.5442 | | No log | 56.0 | 112 | 2.8957 | 0.3245 | 0.5759 | | No log | 57.0 | 114 | 2.8922 | 0.3798 | 0.6383 | | No log | 58.0 | 116 | 2.8886 | 0.3788 | 0.6405 | | No log | 59.0 | 118 | 2.8854 | 0.3920 | 0.6502 | | No log | 60.0 | 120 | 2.8822 | 0.3920 | 0.6376 | | No log | 61.0 | 122 | 2.8793 | 0.4255 | 0.6796 | | No log | 62.0 | 124 | 2.8766 | 0.4288 | 0.7089 | | No log | 63.0 | 126 | 2.8738 | 0.4340 | 0.7048 | | No log | 64.0 | 128 | 2.8712 | 0.4273 | 0.6889 | | No log | 65.0 | 130 | 2.8688 | 0.4173 | 0.7067 | | No log | 66.0 | 132 | 2.8665 | 0.4233 | 0.6802 | | No log | 67.0 | 134 | 2.8642 | 0.3973 | 0.6309 | | No log | 68.0 | 136 | 2.8620 | 0.4107 | 0.6574 | | No log | 69.0 | 138 | 2.8599 | 0.4173 | 0.6774 | | No log | 70.0 | 140 | 2.8580 | 0.3907 | 0.6109 | | No log | 71.0 | 142 | 2.8560 | 0.4407 | 0.6596 | | No log | 72.0 | 144 | 2.8542 | 0.4007 | 0.6196 | | No log | 73.0 | 146 | 2.8525 | 0.4207 | 0.6396 | | No log | 74.0 | 148 | 2.8508 | 0.4173 | 0.6596 | | No log | 75.0 | 150 | 2.8491 | 0.4107 | 0.6303 | | No log | 76.0 | 152 | 2.8476 | 0.3973 | 0.5986 | | No log | 77.0 | 154 | 2.8460 | 0.4040 | 0.6186 | | No log | 78.0 | 156 | 2.8447 | 0.414 | 0.6747 | | No log | 79.0 | 158 | 2.8433 | 0.4167 | 0.6673 | | No log | 80.0 | 160 | 2.8420 | 0.4457 | 0.6813 | | No log | 81.0 | 162 | 2.8409 | 0.4257 | 0.6512 | | No log | 82.0 | 164 | 2.8397 | 0.4607 | 0.7073 | | No log | 83.0 | 166 | 2.8387 | 0.4257 | 0.6048 | | No log | 84.0 | 168 | 2.8377 | 0.4207 | 0.6048 | | No log | 85.0 | 170 | 2.8366 | 0.369 | 0.5248 | | No log | 86.0 | 172 | 2.8357 | 0.4111 | 0.5971 | | No log | 87.0 | 174 | 2.8350 | 0.389 | 0.5448 | | No log | 88.0 | 176 | 2.8342 | 0.4028 | 0.5771 | | No log | 89.0 | 178 | 2.8334 | 0.374 | 0.5448 | | No log | 90.0 | 180 | 2.8328 | 0.374 | 0.5565 | | No log | 91.0 | 182 | 2.8321 | 0.4078 | 0.5971 | | No log | 92.0 | 184 | 2.8316 | 0.4011 | 0.5888 | | No log | 93.0 | 186 | 2.8311 | 0.374 | 0.5565 | | No log | 94.0 | 188 | 2.8308 | 0.3811 | 0.5688 | | No log | 95.0 | 190 | 2.8304 | 0.374 | 0.5565 | | No log | 96.0 | 192 | 2.8302 | 0.3911 | 0.5888 | | No log | 97.0 | 194 | 2.8300 | 0.3611 | 0.5488 | | No log | 98.0 | 196 | 2.8297 | 0.414 | 0.5848 | | No log | 99.0 | 198 | 2.8295 | 0.3878 | 0.5888 | | No log | 100.0 | 200 | 2.8294 | 0.4211 | 0.6088 | ### Framework versions - Transformers 4.34.1 - Pytorch 2.1.0+cu118 - Datasets 2.14.6 - Tokenizers 0.14.1