Add evaluation results on the plain_text config and validation split of launch/gov_report

#10
by autoevaluator HF staff - opened
Files changed (1) hide show
  1. README.md +33 -0
README.md CHANGED
@@ -383,6 +383,39 @@ model-index:
383
  type: gen_len
384
  value: 132.7475
385
  verified: true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
386
  ---
387
 
388
  # long-t5-tglobal-base-16384 + BookSum
 
383
  type: gen_len
384
  value: 132.7475
385
  verified: true
386
+ - task:
387
+ type: summarization
388
+ name: Summarization
389
+ dataset:
390
+ name: launch/gov_report
391
+ type: launch/gov_report
392
+ config: plain_text
393
+ split: validation
394
+ metrics:
395
+ - name: ROUGE-1
396
+ type: rouge
397
+ value: 37.9246
398
+ verified: true
399
+ - name: ROUGE-2
400
+ type: rouge
401
+ value: 8.5837
402
+ verified: true
403
+ - name: ROUGE-L
404
+ type: rouge
405
+ value: 18.0274
406
+ verified: true
407
+ - name: ROUGE-LSUM
408
+ type: rouge
409
+ value: 34.0816
410
+ verified: true
411
+ - name: loss
412
+ type: loss
413
+ value: 2.56695818901062
414
+ verified: true
415
+ - name: gen_len
416
+ type: gen_len
417
+ value: 220.3747
418
+ verified: true
419
  ---
420
 
421
  # long-t5-tglobal-base-16384 + BookSum