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: 1.1450
  • Rouge1: 0.2635
  • Rouge2: 0.2018
  • Rougel: 0.2421
  • Rougelsum: 0.2586
  • 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 1.3343 0.2102 0.108 0.1696 0.1927 19.0
No log 2.0 94 1.2369 0.2236 0.1347 0.1817 0.2103 18.9677
No log 3.0 141 1.1886 0.2301 0.1508 0.1939 0.2167 18.871
No log 4.0 188 1.1635 0.2506 0.1844 0.2273 0.2415 18.871
1.6578 5.0 235 1.1491 0.2521 0.1888 0.2309 0.2462 18.871
1.6578 6.0 282 1.1369 0.2594 0.1985 0.2372 0.2527 18.871
1.6578 7.0 329 1.1308 0.2611 0.1998 0.2399 0.2543 18.871
1.6578 8.0 376 1.1277 0.2579 0.1959 0.2361 0.2521 18.871
1.259 9.0 423 1.1209 0.261 0.1967 0.2382 0.2544 19.0
1.259 10.0 470 1.1200 0.2625 0.1991 0.2403 0.2549 19.0
1.259 11.0 517 1.1163 0.2617 0.1995 0.2403 0.2555 19.0
1.259 12.0 564 1.1162 0.2662 0.2014 0.2435 0.26 19.0
1.1096 13.0 611 1.1183 0.2676 0.2029 0.2466 0.2614 19.0
1.1096 14.0 658 1.1149 0.2677 0.2015 0.2454 0.2611 19.0
1.1096 15.0 705 1.1182 0.2677 0.2015 0.2454 0.2611 19.0
1.1096 16.0 752 1.1211 0.2663 0.2043 0.2467 0.2616 19.0
1.1096 17.0 799 1.1246 0.2654 0.2018 0.2445 0.261 19.0
0.9916 18.0 846 1.1246 0.2665 0.2038 0.2455 0.2615 19.0
0.9916 19.0 893 1.1278 0.2661 0.2035 0.2457 0.2622 19.0
0.9916 20.0 940 1.1273 0.265 0.2028 0.2439 0.2614 19.0
0.9916 21.0 987 1.1326 0.2661 0.2035 0.2457 0.2622 19.0
0.9003 22.0 1034 1.1372 0.2656 0.2027 0.2449 0.2615 19.0
0.9003 23.0 1081 1.1406 0.264 0.1994 0.2418 0.2591 19.0
0.9003 24.0 1128 1.1407 0.2644 0.2015 0.2419 0.2591 19.0
0.9003 25.0 1175 1.1430 0.263 0.1998 0.2415 0.2586 19.0
0.8442 26.0 1222 1.1426 0.2635 0.2018 0.2421 0.2586 19.0
0.8442 27.0 1269 1.1439 0.2635 0.2018 0.2421 0.2586 19.0
0.8442 28.0 1316 1.1451 0.2635 0.2018 0.2421 0.2586 19.0
0.8442 29.0 1363 1.1448 0.2635 0.2018 0.2421 0.2586 19.0
0.8285 30.0 1410 1.1450 0.2635 0.2018 0.2421 0.2586 19.0

Framework versions

  • Transformers 4.34.0
  • Pytorch 2.0.1+cu117
  • Datasets 2.14.5
  • Tokenizers 0.14.1
Downloads last month
4
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-1024

Finetuned
(4)
this model