Edit model card

ptt5-xlsumm-cstnews-1024

This model is a fine-tuned version of arthurmluz/ptt5-xlsumm-30epochs on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 1.2582
  • Rouge1: 0.2812
  • Rouge2: 0.213
  • Rougel: 0.2582
  • Rougelsum: 0.2747
  • Gen Len: 19.0

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: 2e-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: 30

Training results

Training Loss Epoch Step Validation Loss Rouge1 Rouge2 Rougel Rougelsum Gen Len
No log 1.0 47 1.4425 0.2155 0.1096 0.1749 0.2026 19.0
No log 2.0 94 1.3388 0.2385 0.1386 0.1902 0.2251 19.0
No log 3.0 141 1.2907 0.2491 0.1664 0.2162 0.2399 19.0
No log 4.0 188 1.2664 0.2588 0.1828 0.2282 0.2497 19.0
1.6936 5.0 235 1.2464 0.2636 0.1898 0.2363 0.256 19.0
1.6936 6.0 282 1.2430 0.2707 0.2005 0.2454 0.2645 19.0
1.6936 7.0 329 1.2320 0.2717 0.2023 0.2463 0.2654 19.0
1.6936 8.0 376 1.2276 0.2733 0.2054 0.2461 0.2692 19.0
1.2963 9.0 423 1.2237 0.2753 0.2114 0.2482 0.2701 19.0
1.2963 10.0 470 1.2225 0.2784 0.2143 0.2506 0.2732 19.0
1.2963 11.0 517 1.2247 0.2753 0.2117 0.2495 0.2702 19.0
1.2963 12.0 564 1.2244 0.2792 0.2137 0.2533 0.2738 19.0
1.1352 13.0 611 1.2285 0.2797 0.2125 0.2542 0.2742 19.0
1.1352 14.0 658 1.2287 0.2751 0.2096 0.2507 0.2684 19.0
1.1352 15.0 705 1.2325 0.2727 0.2089 0.2503 0.2672 19.0
1.1352 16.0 752 1.2330 0.2769 0.2143 0.2552 0.2711 19.0
1.1352 17.0 799 1.2353 0.2769 0.2143 0.2552 0.2711 19.0
1.0196 18.0 846 1.2352 0.2831 0.2176 0.261 0.2771 19.0
1.0196 19.0 893 1.2400 0.2838 0.2184 0.2611 0.2771 19.0
1.0196 20.0 940 1.2406 0.2838 0.2184 0.2611 0.2771 19.0
1.0196 21.0 987 1.2457 0.2771 0.2109 0.2554 0.2711 19.0
0.912 22.0 1034 1.2471 0.2771 0.2109 0.2554 0.2711 19.0
0.912 23.0 1081 1.2499 0.278 0.2094 0.2552 0.2714 19.0
0.912 24.0 1128 1.2508 0.278 0.2094 0.2552 0.2714 19.0
0.912 25.0 1175 1.2541 0.282 0.2139 0.2588 0.275 19.0
0.8667 26.0 1222 1.2563 0.282 0.2139 0.2588 0.275 19.0
0.8667 27.0 1269 1.2569 0.2812 0.213 0.2582 0.2747 19.0
0.8667 28.0 1316 1.2577 0.2812 0.213 0.2582 0.2747 19.0
0.8667 29.0 1363 1.2582 0.2812 0.213 0.2582 0.2747 19.0
0.8561 30.0 1410 1.2582 0.2812 0.213 0.2582 0.2747 19.0

Framework versions

  • Transformers 4.34.0
  • Pytorch 2.0.1+cu117
  • Datasets 2.14.5
  • Tokenizers 0.14.1
Downloads last month
3
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for arthurmluz/ptt5-xlsumm-cstnews

Finetuned
(4)
this model