Training complete
Browse files- README.md +279 -0
- config.json +59 -0
- generation_config.json +14 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- runs/Jul02_13-20-24_nmuj44l284/events.out.tfevents.1719926514.nmuj44l284.78.0 +3 -0
- runs/Jul02_13-20-24_nmuj44l284/events.out.tfevents.1719927416.nmuj44l284.78.1 +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
ADDED
|
@@ -0,0 +1,279 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- summarization
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: finetune-led-35000
|
| 7 |
+
results: []
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 11 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 12 |
+
|
| 13 |
+
# finetune-led-35000
|
| 14 |
+
|
| 15 |
+
This model was trained from scratch on an unknown dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 1.8474
|
| 18 |
+
- Rouge1 Precision: 0.2576
|
| 19 |
+
- Rouge1 Recall: 0.3438
|
| 20 |
+
- Rouge1 Fmeasure: 0.2911
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 5e-05
|
| 40 |
+
- train_batch_size: 8
|
| 41 |
+
- eval_batch_size: 8
|
| 42 |
+
- seed: 42
|
| 43 |
+
- gradient_accumulation_steps: 4
|
| 44 |
+
- total_train_batch_size: 32
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: linear
|
| 47 |
+
- num_epochs: 2
|
| 48 |
+
- mixed_precision_training: Native AMP
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 Fmeasure | Rouge1 Precision | Rouge1 Recall |
|
| 53 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------------:|:----------------:|:-------------:|
|
| 54 |
+
| 2.0001 | 0.01 | 10 | 2.8444 | 0.2732 | 0.2484 | 0.3213 |
|
| 55 |
+
| 1.7409 | 0.01 | 20 | 2.6895 | 0.2682 | 0.2375 | 0.3203 |
|
| 56 |
+
| 1.6096 | 0.02 | 30 | 2.6335 | 0.2797 | 0.246 | 0.3362 |
|
| 57 |
+
| 1.7452 | 0.03 | 40 | 2.5817 | 0.285 | 0.251 | 0.3417 |
|
| 58 |
+
| 1.6212 | 0.03 | 50 | 2.5765 | 0.2899 | 0.253 | 0.3515 |
|
| 59 |
+
| 1.6743 | 0.04 | 60 | 2.4425 | 0.2705 | 0.241 | 0.3188 |
|
| 60 |
+
| 1.5229 | 0.04 | 70 | 2.5146 | 0.2802 | 0.2501 | 0.3294 |
|
| 61 |
+
| 1.5681 | 0.05 | 80 | 2.4785 | 0.2665 | 0.2302 | 0.3273 |
|
| 62 |
+
| 1.5811 | 0.06 | 90 | 2.3622 | 0.287 | 0.2577 | 0.3349 |
|
| 63 |
+
| 1.5642 | 0.06 | 100 | 2.4053 | 0.2779 | 0.2449 | 0.3322 |
|
| 64 |
+
| 1.5175 | 0.07 | 110 | 2.3818 | 0.2862 | 0.2577 | 0.3324 |
|
| 65 |
+
| 1.5073 | 0.08 | 120 | 2.3930 | 0.2905 | 0.25 | 0.3587 |
|
| 66 |
+
| 1.5336 | 0.12 | 130 | 2.3619 | 0.2755 | 0.2456 | 0.3242 |
|
| 67 |
+
| 1.5155 | 0.13 | 140 | 2.3696 | 0.2752 | 0.243 | 0.3284 |
|
| 68 |
+
| 1.5124 | 0.14 | 150 | 2.3240 | 0.2788 | 0.2478 | 0.3296 |
|
| 69 |
+
| 1.5187 | 0.15 | 160 | 2.2883 | 0.2739 | 0.2438 | 0.3225 |
|
| 70 |
+
| 1.4642 | 0.16 | 170 | 2.3006 | 0.2769 | 0.2442 | 0.3307 |
|
| 71 |
+
| 1.6535 | 0.16 | 180 | 2.2766 | 0.2716 | 0.2435 | 0.3165 |
|
| 72 |
+
| 1.4924 | 0.17 | 190 | 2.3077 | 0.2782 | 0.2463 | 0.3303 |
|
| 73 |
+
| 1.5221 | 0.18 | 200 | 2.2725 | 0.2829 | 0.2502 | 0.3357 |
|
| 74 |
+
| 1.388 | 0.19 | 210 | 2.2555 | 0.2811 | 0.2502 | 0.3305 |
|
| 75 |
+
| 1.5172 | 0.2 | 220 | 2.2519 | 0.2758 | 0.2458 | 0.3243 |
|
| 76 |
+
| 1.498 | 0.21 | 230 | 2.2585 | 0.2809 | 0.2428 | 0.3437 |
|
| 77 |
+
| 1.447 | 0.22 | 240 | 2.2110 | 0.2745 | 0.2457 | 0.3206 |
|
| 78 |
+
| 1.4637 | 0.23 | 250 | 2.2511 | 0.2854 | 0.252 | 0.3395 |
|
| 79 |
+
| 1.5084 | 0.24 | 260 | 2.2070 | 0.2876 | 0.2547 | 0.341 |
|
| 80 |
+
| 1.4347 | 0.25 | 270 | 2.2558 | 0.2852 | 0.2493 | 0.344 |
|
| 81 |
+
| 1.3108 | 0.26 | 280 | 2.2498 | 0.2815 | 0.2488 | 0.3349 |
|
| 82 |
+
| 1.3894 | 0.27 | 290 | 2.2302 | 0.2794 | 0.2454 | 0.3347 |
|
| 83 |
+
| 1.4392 | 0.27 | 300 | 2.2021 | 0.276 | 0.2412 | 0.3327 |
|
| 84 |
+
| 1.3774 | 0.28 | 310 | 2.1958 | 0.2763 | 0.244 | 0.3286 |
|
| 85 |
+
| 1.3696 | 0.29 | 320 | 2.1657 | 0.2811 | 0.2512 | 0.3292 |
|
| 86 |
+
| 1.4186 | 0.3 | 330 | 2.1533 | 0.2807 | 0.251 | 0.3288 |
|
| 87 |
+
| 1.3073 | 0.31 | 340 | 2.1890 | 0.2805 | 0.2486 | 0.3324 |
|
| 88 |
+
| 1.3533 | 0.32 | 350 | 2.1639 | 0.2836 | 0.2546 | 0.3302 |
|
| 89 |
+
| 1.3691 | 0.33 | 360 | 2.1255 | 0.2765 | 0.25 | 0.3188 |
|
| 90 |
+
| 1.3716 | 0.34 | 370 | 2.1436 | 0.2818 | 0.2512 | 0.3315 |
|
| 91 |
+
| 1.3985 | 0.35 | 380 | 2.1160 | 0.2859 | 0.2555 | 0.3351 |
|
| 92 |
+
| 1.2993 | 0.36 | 390 | 2.1417 | 0.2756 | 0.2442 | 0.3262 |
|
| 93 |
+
| 1.3453 | 0.37 | 400 | 2.1459 | 0.2875 | 0.256 | 0.3386 |
|
| 94 |
+
| 1.4036 | 0.37 | 410 | 2.1200 | 0.2811 | 0.2506 | 0.33 |
|
| 95 |
+
| 1.3784 | 0.38 | 420 | 2.0878 | 0.2885 | 0.2592 | 0.335 |
|
| 96 |
+
| 1.2923 | 0.39 | 430 | 2.1342 | 0.2873 | 0.2535 | 0.3423 |
|
| 97 |
+
| 1.3629 | 0.4 | 440 | 2.0887 | 0.2848 | 0.2546 | 0.3328 |
|
| 98 |
+
| 1.4151 | 0.41 | 450 | 2.0905 | 0.2857 | 0.254 | 0.3365 |
|
| 99 |
+
| 1.3679 | 0.42 | 460 | 2.0829 | 0.285 | 0.2525 | 0.3375 |
|
| 100 |
+
| 1.339 | 0.43 | 470 | 2.0786 | 0.2791 | 0.2452 | 0.334 |
|
| 101 |
+
| 1.4258 | 0.44 | 480 | 2.0726 | 0.2877 | 0.2603 | 0.3317 |
|
| 102 |
+
| 1.4056 | 0.45 | 490 | 2.0995 | 0.2891 | 0.2556 | 0.3428 |
|
| 103 |
+
| 1.3548 | 0.46 | 500 | 2.0637 | 0.2757 | 0.2481 | 0.3199 |
|
| 104 |
+
| 1.3253 | 0.47 | 510 | 2.0638 | 0.2794 | 0.25 | 0.3266 |
|
| 105 |
+
| 1.264 | 0.48 | 520 | 2.0609 | 0.2861 | 0.2587 | 0.3296 |
|
| 106 |
+
| 1.3307 | 0.48 | 530 | 2.0396 | 0.2823 | 0.2559 | 0.3243 |
|
| 107 |
+
| 1.3536 | 0.49 | 540 | 2.0464 | 0.2824 | 0.2532 | 0.3288 |
|
| 108 |
+
| 1.2592 | 0.5 | 550 | 2.0480 | 0.2876 | 0.2592 | 0.3333 |
|
| 109 |
+
| 1.358 | 0.51 | 560 | 2.0432 | 0.2818 | 0.2528 | 0.3284 |
|
| 110 |
+
| 1.3227 | 0.52 | 570 | 2.0560 | 0.2831 | 0.2502 | 0.3365 |
|
| 111 |
+
| 1.3189 | 0.53 | 580 | 2.0311 | 0.2823 | 0.251 | 0.3321 |
|
| 112 |
+
| 1.3367 | 0.54 | 590 | 2.0498 | 0.285 | 0.2538 | 0.335 |
|
| 113 |
+
| 1.3473 | 0.55 | 600 | 2.0690 | 0.2773 | 0.2452 | 0.3292 |
|
| 114 |
+
| 1.2846 | 0.56 | 610 | 2.0555 | 0.2796 | 0.2473 | 0.3321 |
|
| 115 |
+
| 1.3066 | 0.57 | 620 | 2.0684 | 0.2799 | 0.245 | 0.3366 |
|
| 116 |
+
| 1.3193 | 0.58 | 630 | 2.0467 | 0.2852 | 0.2536 | 0.336 |
|
| 117 |
+
| 1.269 | 0.59 | 640 | 2.0381 | 0.2859 | 0.2561 | 0.3337 |
|
| 118 |
+
| 1.2906 | 0.59 | 650 | 2.0191 | 0.2831 | 0.2514 | 0.3338 |
|
| 119 |
+
| 1.2981 | 0.6 | 660 | 2.0184 | 0.2783 | 0.249 | 0.3251 |
|
| 120 |
+
| 1.2888 | 0.61 | 670 | 2.0295 | 0.2827 | 0.2515 | 0.3331 |
|
| 121 |
+
| 1.3179 | 0.62 | 680 | 2.0121 | 0.2885 | 0.2611 | 0.333 |
|
| 122 |
+
| 1.3313 | 0.63 | 690 | 2.0296 | 0.2739 | 0.2427 | 0.3245 |
|
| 123 |
+
| 1.1749 | 0.64 | 700 | 2.0419 | 0.2809 | 0.2507 | 0.3298 |
|
| 124 |
+
| 1.3023 | 0.65 | 710 | 2.0275 | 0.2838 | 0.2504 | 0.3379 |
|
| 125 |
+
| 1.262 | 0.66 | 720 | 1.9974 | 0.286 | 0.2539 | 0.3378 |
|
| 126 |
+
| 1.2906 | 0.67 | 730 | 1.9839 | 0.2839 | 0.252 | 0.3357 |
|
| 127 |
+
| 1.24 | 0.68 | 740 | 2.0041 | 0.286 | 0.2528 | 0.3401 |
|
| 128 |
+
| 1.239 | 0.69 | 750 | 2.0116 | 0.2789 | 0.2455 | 0.3326 |
|
| 129 |
+
| 1.1972 | 0.69 | 760 | 2.0293 | 0.2861 | 0.2536 | 0.3385 |
|
| 130 |
+
| 1.2114 | 0.7 | 770 | 2.0271 | 0.2738 | 0.2436 | 0.322 |
|
| 131 |
+
| 1.2711 | 0.71 | 780 | 2.0084 | 0.2881 | 0.2548 | 0.3417 |
|
| 132 |
+
| 1.262 | 0.72 | 790 | 1.9984 | 0.2806 | 0.2488 | 0.3322 |
|
| 133 |
+
| 1.2616 | 0.73 | 800 | 1.9715 | 0.2856 | 0.2541 | 0.3364 |
|
| 134 |
+
| 1.2765 | 0.74 | 810 | 1.9718 | 0.2825 | 0.2494 | 0.3356 |
|
| 135 |
+
| 1.2151 | 0.75 | 820 | 1.9947 | 0.2857 | 0.2513 | 0.341 |
|
| 136 |
+
| 1.3165 | 0.76 | 830 | 1.9854 | 0.2863 | 0.2524 | 0.3411 |
|
| 137 |
+
| 1.2704 | 0.77 | 840 | 1.9858 | 0.2903 | 0.2569 | 0.3443 |
|
| 138 |
+
| 1.3032 | 0.78 | 850 | 1.9774 | 0.2926 | 0.2583 | 0.3481 |
|
| 139 |
+
| 1.2461 | 0.79 | 860 | 1.9596 | 0.2847 | 0.2556 | 0.3314 |
|
| 140 |
+
| 1.2288 | 0.8 | 870 | 1.9873 | 0.2868 | 0.2547 | 0.339 |
|
| 141 |
+
| 1.2278 | 0.8 | 880 | 1.9712 | 0.289 | 0.2546 | 0.3455 |
|
| 142 |
+
| 1.2119 | 0.81 | 890 | 1.9862 | 0.2822 | 0.2478 | 0.338 |
|
| 143 |
+
| 1.3363 | 0.82 | 900 | 1.9555 | 0.2871 | 0.2576 | 0.3349 |
|
| 144 |
+
| 1.2324 | 0.83 | 910 | 1.9394 | 0.2878 | 0.2588 | 0.3339 |
|
| 145 |
+
| 1.2528 | 0.84 | 920 | 1.9593 | 0.2801 | 0.2498 | 0.3289 |
|
| 146 |
+
| 1.2572 | 0.85 | 930 | 1.9500 | 0.2825 | 0.2507 | 0.3337 |
|
| 147 |
+
| 1.2045 | 0.86 | 940 | 1.9586 | 0.2901 | 0.2589 | 0.3401 |
|
| 148 |
+
| 1.2173 | 0.87 | 950 | 1.9551 | 0.281 | 0.2487 | 0.3328 |
|
| 149 |
+
| 1.2315 | 0.88 | 960 | 1.9307 | 0.2842 | 0.2533 | 0.3337 |
|
| 150 |
+
| 1.2445 | 0.89 | 970 | 1.9362 | 0.2853 | 0.2537 | 0.336 |
|
| 151 |
+
| 1.2491 | 0.9 | 980 | 1.9614 | 0.2829 | 0.2482 | 0.3397 |
|
| 152 |
+
| 1.3081 | 0.91 | 990 | 1.9500 | 0.2857 | 0.2513 | 0.3411 |
|
| 153 |
+
| 1.1928 | 0.91 | 1000 | 1.9439 | 0.2826 | 0.2514 | 0.333 |
|
| 154 |
+
| 1.2243 | 0.92 | 1010 | 1.9074 | 0.2883 | 0.259 | 0.3346 |
|
| 155 |
+
| 1.2662 | 0.93 | 1020 | 1.9143 | 0.2912 | 0.2593 | 0.3422 |
|
| 156 |
+
| 1.2223 | 0.94 | 1030 | 1.9342 | 0.2899 | 0.2581 | 0.3408 |
|
| 157 |
+
| 1.2499 | 0.95 | 1040 | 1.9352 | 0.2835 | 0.2507 | 0.3366 |
|
| 158 |
+
| 1.3395 | 0.96 | 1050 | 1.9284 | 0.2864 | 0.2548 | 0.3375 |
|
| 159 |
+
| 1.1908 | 0.97 | 1060 | 1.9471 | 0.2853 | 0.2528 | 0.3376 |
|
| 160 |
+
| 1.2473 | 0.98 | 1070 | 1.9462 | 0.2941 | 0.2613 | 0.3472 |
|
| 161 |
+
| 1.2139 | 0.99 | 1080 | 1.9317 | 0.2859 | 0.2534 | 0.338 |
|
| 162 |
+
| 1.2534 | 1.0 | 1090 | 1.9278 | 0.2938 | 0.2594 | 0.3488 |
|
| 163 |
+
| 1.2204 | 1.01 | 1100 | 1.9177 | 0.2912 | 0.2596 | 0.341 |
|
| 164 |
+
| 1.2399 | 1.01 | 1110 | 1.9236 | 0.2903 | 0.2568 | 0.3443 |
|
| 165 |
+
| 1.1541 | 1.02 | 1120 | 1.9441 | 0.2889 | 0.2548 | 0.3431 |
|
| 166 |
+
| 1.1038 | 1.03 | 1130 | 1.9223 | 0.2925 | 0.2626 | 0.3399 |
|
| 167 |
+
| 1.1177 | 1.04 | 1140 | 1.9244 | 0.2881 | 0.2565 | 0.338 |
|
| 168 |
+
| 1.1224 | 1.05 | 1150 | 1.9324 | 0.2884 | 0.2547 | 0.3428 |
|
| 169 |
+
| 1.104 | 1.06 | 1160 | 1.9188 | 0.2798 | 0.2482 | 0.3304 |
|
| 170 |
+
| 1.175 | 1.07 | 1170 | 1.9042 | 0.2915 | 0.2618 | 0.3388 |
|
| 171 |
+
| 1.102 | 1.08 | 1180 | 1.9325 | 0.2853 | 0.253 | 0.3372 |
|
| 172 |
+
| 1.0829 | 1.09 | 1190 | 1.9503 | 0.2819 | 0.2478 | 0.3371 |
|
| 173 |
+
| 1.1842 | 1.1 | 1200 | 1.9360 | 0.2784 | 0.2438 | 0.3346 |
|
| 174 |
+
| 1.1552 | 1.11 | 1210 | 1.9055 | 0.286 | 0.254 | 0.3369 |
|
| 175 |
+
| 1.1266 | 1.12 | 1220 | 1.9106 | 0.286 | 0.2555 | 0.3345 |
|
| 176 |
+
| 1.1288 | 1.13 | 1230 | 1.9072 | 0.2865 | 0.2566 | 0.3336 |
|
| 177 |
+
| 1.1722 | 1.13 | 1240 | 1.9114 | 0.2856 | 0.2539 | 0.3364 |
|
| 178 |
+
| 1.1514 | 1.14 | 1250 | 1.9180 | 0.2906 | 0.2561 | 0.3461 |
|
| 179 |
+
| 1.1642 | 1.15 | 1260 | 1.9226 | 0.2918 | 0.2571 | 0.3475 |
|
| 180 |
+
| 1.1464 | 1.16 | 1270 | 1.9004 | 0.2819 | 0.2525 | 0.3283 |
|
| 181 |
+
| 1.1829 | 1.17 | 1280 | 1.9181 | 0.2935 | 0.2568 | 0.3524 |
|
| 182 |
+
| 1.17 | 1.18 | 1290 | 1.9031 | 0.2848 | 0.2523 | 0.3369 |
|
| 183 |
+
| 1.0751 | 1.19 | 1300 | 1.9334 | 0.2875 | 0.2531 | 0.3428 |
|
| 184 |
+
| 1.1327 | 1.2 | 1310 | 1.8966 | 0.2891 | 0.2568 | 0.3407 |
|
| 185 |
+
| 1.1319 | 1.21 | 1320 | 1.9076 | 0.2902 | 0.2575 | 0.3422 |
|
| 186 |
+
| 1.106 | 1.22 | 1330 | 1.8941 | 0.2908 | 0.259 | 0.3413 |
|
| 187 |
+
| 1.1721 | 1.23 | 1340 | 1.8956 | 0.2945 | 0.2609 | 0.3479 |
|
| 188 |
+
| 1.1964 | 1.23 | 1350 | 1.9140 | 0.2851 | 0.2513 | 0.3389 |
|
| 189 |
+
| 1.1195 | 1.24 | 1360 | 1.9168 | 0.2917 | 0.2561 | 0.3483 |
|
| 190 |
+
| 1.1352 | 1.25 | 1370 | 1.8962 | 0.286 | 0.253 | 0.3389 |
|
| 191 |
+
| 1.1164 | 1.26 | 1380 | 1.9050 | 0.2916 | 0.258 | 0.3453 |
|
| 192 |
+
| 1.1219 | 1.27 | 1390 | 1.9054 | 0.2872 | 0.2551 | 0.3386 |
|
| 193 |
+
| 1.1571 | 1.28 | 1400 | 1.8845 | 0.2896 | 0.2574 | 0.3402 |
|
| 194 |
+
| 1.2033 | 1.29 | 1410 | 1.8985 | 0.2852 | 0.2532 | 0.3362 |
|
| 195 |
+
| 1.1114 | 1.3 | 1420 | 1.8956 | 0.2882 | 0.2559 | 0.3395 |
|
| 196 |
+
| 1.1268 | 1.31 | 1430 | 1.8955 | 0.2895 | 0.2563 | 0.3424 |
|
| 197 |
+
| 1.1347 | 1.32 | 1440 | 1.8883 | 0.2865 | 0.2524 | 0.3412 |
|
| 198 |
+
| 1.0345 | 1.33 | 1450 | 1.8960 | 0.2895 | 0.2571 | 0.3412 |
|
| 199 |
+
| 1.1231 | 1.34 | 1460 | 1.8873 | 0.29 | 0.2575 | 0.3415 |
|
| 200 |
+
| 1.236 | 1.34 | 1470 | 1.8744 | 0.2898 | 0.2578 | 0.34 |
|
| 201 |
+
| 1.1054 | 1.35 | 1480 | 1.8867 | 0.2884 | 0.2546 | 0.3425 |
|
| 202 |
+
| 1.1393 | 1.36 | 1490 | 1.8907 | 0.2927 | 0.2605 | 0.344 |
|
| 203 |
+
| 1.1004 | 1.37 | 1500 | 1.8953 | 0.288 | 0.2543 | 0.3416 |
|
| 204 |
+
| 1.1482 | 1.38 | 1510 | 1.8731 | 0.288 | 0.2568 | 0.3377 |
|
| 205 |
+
| 1.1701 | 1.39 | 1520 | 1.8868 | 0.2866 | 0.2525 | 0.3411 |
|
| 206 |
+
| 1.1233 | 1.4 | 1530 | 1.8803 | 0.2882 | 0.2562 | 0.3385 |
|
| 207 |
+
| 1.0685 | 1.41 | 1540 | 1.8843 | 0.2935 | 0.262 | 0.3433 |
|
| 208 |
+
| 1.0657 | 1.42 | 1550 | 1.8748 | 0.2892 | 0.2553 | 0.3437 |
|
| 209 |
+
| 1.1275 | 1.43 | 1560 | 1.8804 | 0.2881 | 0.2553 | 0.3405 |
|
| 210 |
+
| 1.0883 | 1.44 | 1570 | 1.8803 | 0.2868 | 0.2527 | 0.3412 |
|
| 211 |
+
| 1.1096 | 1.45 | 1580 | 1.8862 | 0.2927 | 0.2586 | 0.3472 |
|
| 212 |
+
| 1.1521 | 1.45 | 1590 | 1.8724 | 0.288 | 0.2564 | 0.3379 |
|
| 213 |
+
| 1.142 | 1.46 | 1600 | 1.8788 | 0.2926 | 0.2593 | 0.3454 |
|
| 214 |
+
| 1.0451 | 1.47 | 1610 | 1.8684 | 0.2863 | 0.2571 | 0.3324 |
|
| 215 |
+
| 1.1294 | 1.48 | 1620 | 1.8704 | 0.2902 | 0.2569 | 0.3427 |
|
| 216 |
+
| 1.1671 | 1.49 | 1630 | 1.8756 | 0.2909 | 0.259 | 0.3413 |
|
| 217 |
+
| 1.2252 | 1.5 | 1640 | 1.8618 | 0.2937 | 0.2599 | 0.347 |
|
| 218 |
+
| 1.0834 | 1.51 | 1650 | 1.8776 | 0.2909 | 0.2589 | 0.3416 |
|
| 219 |
+
| 1.0417 | 1.52 | 1660 | 1.8658 | 0.2911 | 0.2592 | 0.342 |
|
| 220 |
+
| 1.1036 | 1.53 | 1670 | 1.8789 | 0.289 | 0.2553 | 0.343 |
|
| 221 |
+
| 1.1575 | 1.54 | 1680 | 1.8608 | 0.2927 | 0.2597 | 0.3452 |
|
| 222 |
+
| 1.058 | 1.55 | 1690 | 1.8804 | 0.2921 | 0.2585 | 0.3455 |
|
| 223 |
+
| 1.1251 | 1.55 | 1700 | 1.8682 | 0.2973 | 0.2637 | 0.3503 |
|
| 224 |
+
| 1.0818 | 1.56 | 1710 | 1.8800 | 0.2887 | 0.2544 | 0.3432 |
|
| 225 |
+
| 1.1346 | 1.57 | 1720 | 1.8577 | 0.289 | 0.2564 | 0.3404 |
|
| 226 |
+
| 1.1024 | 1.58 | 1730 | 1.8681 | 0.2946 | 0.2608 | 0.3482 |
|
| 227 |
+
| 1.0823 | 1.59 | 1740 | 1.8603 | 0.2908 | 0.2584 | 0.342 |
|
| 228 |
+
| 1.0562 | 1.6 | 1750 | 1.8670 | 0.2931 | 0.2584 | 0.3484 |
|
| 229 |
+
| 1.1128 | 1.61 | 1760 | 1.8576 | 0.2926 | 0.2603 | 0.3439 |
|
| 230 |
+
| 1.0769 | 1.62 | 1770 | 1.8709 | 0.2902 | 0.2568 | 0.3434 |
|
| 231 |
+
| 1.0422 | 1.63 | 1780 | 1.8597 | 0.2911 | 0.2587 | 0.3425 |
|
| 232 |
+
| 1.1912 | 1.64 | 1790 | 1.8648 | 0.2911 | 0.2574 | 0.3448 |
|
| 233 |
+
| 1.1349 | 1.65 | 1800 | 1.8667 | 0.2933 | 0.2606 | 0.3453 |
|
| 234 |
+
| 1.1195 | 1.66 | 1810 | 1.8684 | 0.2899 | 0.2568 | 0.3422 |
|
| 235 |
+
| 1.1186 | 1.66 | 1820 | 1.8581 | 0.2908 | 0.2579 | 0.3434 |
|
| 236 |
+
| 1.0795 | 1.67 | 1830 | 1.8639 | 0.2907 | 0.2561 | 0.3462 |
|
| 237 |
+
| 1.1394 | 1.68 | 1840 | 1.8467 | 0.2929 | 0.2602 | 0.3446 |
|
| 238 |
+
| 1.0743 | 1.69 | 1850 | 1.8682 | 0.291 | 0.2585 | 0.3428 |
|
| 239 |
+
| 1.0954 | 1.7 | 1860 | 1.8504 | 0.2928 | 0.2603 | 0.3445 |
|
| 240 |
+
| 1.0938 | 1.71 | 1870 | 1.8604 | 0.2916 | 0.2589 | 0.3436 |
|
| 241 |
+
| 1.1093 | 1.72 | 1880 | 1.8427 | 0.2897 | 0.2581 | 0.3398 |
|
| 242 |
+
| 1.1399 | 1.73 | 1890 | 1.8715 | 0.2891 | 0.2561 | 0.3422 |
|
| 243 |
+
| 1.1574 | 1.74 | 1900 | 1.8448 | 0.2893 | 0.2568 | 0.3409 |
|
| 244 |
+
| 1.1244 | 1.75 | 1910 | 1.8594 | 0.2927 | 0.2597 | 0.3453 |
|
| 245 |
+
| 1.1205 | 1.76 | 1920 | 1.8492 | 0.2922 | 0.2606 | 0.3425 |
|
| 246 |
+
| 1.1218 | 1.77 | 1930 | 1.8547 | 0.2906 | 0.2591 | 0.3401 |
|
| 247 |
+
| 1.1208 | 1.77 | 1940 | 1.8605 | 0.2924 | 0.2588 | 0.3459 |
|
| 248 |
+
| 1.0983 | 1.78 | 1950 | 1.8425 | 0.2933 | 0.2611 | 0.3442 |
|
| 249 |
+
| 1.1992 | 1.79 | 1960 | 1.8587 | 0.2907 | 0.2565 | 0.3455 |
|
| 250 |
+
| 1.1724 | 1.8 | 1970 | 1.8413 | 0.2909 | 0.2576 | 0.3435 |
|
| 251 |
+
| 1.1344 | 1.81 | 1980 | 1.8494 | 0.2904 | 0.2583 | 0.3413 |
|
| 252 |
+
| 1.1469 | 1.82 | 1990 | 1.8463 | 0.2911 | 0.2581 | 0.3437 |
|
| 253 |
+
| 1.1491 | 1.83 | 2000 | 1.8530 | 0.2905 | 0.2568 | 0.3441 |
|
| 254 |
+
| 1.0913 | 1.84 | 2010 | 1.8493 | 0.2913 | 0.258 | 0.3443 |
|
| 255 |
+
| 1.1298 | 1.85 | 2020 | 1.8465 | 0.2905 | 0.2573 | 0.3433 |
|
| 256 |
+
| 1.1202 | 1.86 | 2030 | 1.8488 | 0.2892 | 0.256 | 0.3419 |
|
| 257 |
+
| 1.1439 | 1.87 | 2040 | 1.8494 | 0.2911 | 0.2584 | 0.3428 |
|
| 258 |
+
| 1.0328 | 1.87 | 2050 | 1.8469 | 0.2907 | 0.2582 | 0.3423 |
|
| 259 |
+
| 1.1347 | 1.88 | 2060 | 1.8426 | 0.29 | 0.2576 | 0.341 |
|
| 260 |
+
| 1.094 | 1.89 | 2070 | 1.8480 | 0.2905 | 0.2577 | 0.3425 |
|
| 261 |
+
| 1.1201 | 1.9 | 2080 | 1.8542 | 0.2896 | 0.2568 | 0.3415 |
|
| 262 |
+
| 1.1475 | 1.91 | 2090 | 1.8520 | 0.29 | 0.2574 | 0.3416 |
|
| 263 |
+
| 1.0793 | 1.92 | 2100 | 1.8506 | 0.2897 | 0.2569 | 0.3414 |
|
| 264 |
+
| 1.0669 | 1.93 | 2110 | 1.8484 | 0.2907 | 0.2577 | 0.3426 |
|
| 265 |
+
| 1.1276 | 1.94 | 2120 | 1.8487 | 0.2904 | 0.2573 | 0.3427 |
|
| 266 |
+
| 1.0902 | 1.95 | 2130 | 1.8487 | 0.2904 | 0.2575 | 0.3423 |
|
| 267 |
+
| 1.1449 | 1.96 | 2140 | 1.8490 | 0.2898 | 0.2569 | 0.3419 |
|
| 268 |
+
| 1.1142 | 1.97 | 2150 | 1.8505 | 0.29 | 0.2569 | 0.3424 |
|
| 269 |
+
| 1.1475 | 1.98 | 2160 | 1.8501 | 0.2895 | 0.2561 | 0.3424 |
|
| 270 |
+
| 1.0663 | 1.98 | 2170 | 1.8485 | 0.2906 | 0.2571 | 0.3434 |
|
| 271 |
+
| 1.1454 | 1.99 | 2180 | 1.8475 | 0.2907 | 0.2573 | 0.3435 |
|
| 272 |
+
|
| 273 |
+
|
| 274 |
+
### Framework versions
|
| 275 |
+
|
| 276 |
+
- Transformers 4.35.2
|
| 277 |
+
- Pytorch 2.1.1+cu121
|
| 278 |
+
- Datasets 2.14.5
|
| 279 |
+
- Tokenizers 0.15.1
|
config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "./finetune/led/checkpoint-2180",
|
| 3 |
+
"activation_dropout": 0.0,
|
| 4 |
+
"activation_function": "gelu",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"LEDForConditionalGeneration"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"attention_window": [
|
| 10 |
+
1024,
|
| 11 |
+
1024,
|
| 12 |
+
1024,
|
| 13 |
+
1024,
|
| 14 |
+
1024,
|
| 15 |
+
1024
|
| 16 |
+
],
|
| 17 |
+
"bos_token_id": 0,
|
| 18 |
+
"classif_dropout": 0.0,
|
| 19 |
+
"classifier_dropout": 0.0,
|
| 20 |
+
"d_model": 768,
|
| 21 |
+
"decoder_attention_heads": 12,
|
| 22 |
+
"decoder_ffn_dim": 3072,
|
| 23 |
+
"decoder_layerdrop": 0.0,
|
| 24 |
+
"decoder_layers": 6,
|
| 25 |
+
"decoder_start_token_id": 2,
|
| 26 |
+
"dropout": 0.1,
|
| 27 |
+
"early_stopping": true,
|
| 28 |
+
"encoder_attention_heads": 12,
|
| 29 |
+
"encoder_ffn_dim": 3072,
|
| 30 |
+
"encoder_layerdrop": 0.0,
|
| 31 |
+
"encoder_layers": 6,
|
| 32 |
+
"eos_token_id": 2,
|
| 33 |
+
"id2label": {
|
| 34 |
+
"0": "LABEL_0",
|
| 35 |
+
"1": "LABEL_1",
|
| 36 |
+
"2": "LABEL_2"
|
| 37 |
+
},
|
| 38 |
+
"init_std": 0.02,
|
| 39 |
+
"is_encoder_decoder": true,
|
| 40 |
+
"label2id": {
|
| 41 |
+
"LABEL_0": 0,
|
| 42 |
+
"LABEL_1": 1,
|
| 43 |
+
"LABEL_2": 2
|
| 44 |
+
},
|
| 45 |
+
"length_penalty": 2.0,
|
| 46 |
+
"max_decoder_position_embeddings": 1024,
|
| 47 |
+
"max_encoder_position_embeddings": 16384,
|
| 48 |
+
"max_length": 128,
|
| 49 |
+
"min_length": 40,
|
| 50 |
+
"model_type": "led",
|
| 51 |
+
"no_repeat_ngram_size": 3,
|
| 52 |
+
"num_beams": 2,
|
| 53 |
+
"num_hidden_layers": 6,
|
| 54 |
+
"pad_token_id": 1,
|
| 55 |
+
"torch_dtype": "float32",
|
| 56 |
+
"transformers_version": "4.35.2",
|
| 57 |
+
"use_cache": false,
|
| 58 |
+
"vocab_size": 50265
|
| 59 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 0,
|
| 3 |
+
"decoder_start_token_id": 2,
|
| 4 |
+
"early_stopping": true,
|
| 5 |
+
"eos_token_id": 2,
|
| 6 |
+
"length_penalty": 2.0,
|
| 7 |
+
"max_length": 128,
|
| 8 |
+
"min_length": 40,
|
| 9 |
+
"no_repeat_ngram_size": 3,
|
| 10 |
+
"num_beams": 2,
|
| 11 |
+
"pad_token_id": 1,
|
| 12 |
+
"transformers_version": "4.35.2",
|
| 13 |
+
"use_cache": false
|
| 14 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:84f03560dcd70c3b0d3d81aa9ad4f4721ed05ac309f63573d6543dc0f863b994
|
| 3 |
+
size 647614116
|
runs/Jul02_13-20-24_nmuj44l284/events.out.tfevents.1719926514.nmuj44l284.78.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:25828e4f6edd30a360f9e86861efeada7df4d9387b4786bf0c9646fe114a8084
|
| 3 |
+
size 5527
|
runs/Jul02_13-20-24_nmuj44l284/events.out.tfevents.1719927416.nmuj44l284.78.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:31abe7ebf4a3efc2aa48e2a779b4af0aea92bee674cff3ce8ff681d2ab0db2cd
|
| 3 |
+
size 535
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": true,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"50264": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": true,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": true,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"mask_token": "<mask>",
|
| 51 |
+
"model_max_length": 16384,
|
| 52 |
+
"pad_token": "<pad>",
|
| 53 |
+
"sep_token": "</s>",
|
| 54 |
+
"tokenizer_class": "LEDTokenizer",
|
| 55 |
+
"trim_offsets": true,
|
| 56 |
+
"unk_token": "<unk>"
|
| 57 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8a6d32d8e6360f4de14bd9d32f4ca6210b2685efa831d5216eaa8cff3a2bc09d
|
| 3 |
+
size 4728
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|