Hugging Face's logo

tomvoelker
/
gpt22gpt2-gpt2-cnn-dailymail-seed42

Transformers
TensorBoard
Safetensors
encoder-decoder
text2text-generation
Generated from Trainer
Model card Files
xet
 Metrics Community
tomvoelker commited on
Commit
03b7098
·
verified ·
1 Parent(s): cadc3b6

Model save

Browse files
Files changed (1) hide show
  1. README.md +18 -18
README.md CHANGED
@@ -16,11 +16,11 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 2.3910
20
- - Rouge1: 0.3114
21
- - Rouge2: 0.0950
22
- - Rougel: 0.1838
23
- - Rougelsum: 0.2907
24
 
25
  ## Model description
26
 
@@ -54,19 +54,19 @@ The following hyperparameters were used during training:
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
56
  |:-------------:|:------:|:-----:|:---------------:|:------:|:------:|:------:|:---------:|
57
- | 3.2585 | 0.2229 | 2000 | 3.0468 | 0.2041 | 0.0368 | 0.1271 | 0.1916 |
58
- | 3.021 | 0.4458 | 4000 | 2.8241 | 0.2451 | 0.0547 | 0.1491 | 0.2294 |
59
- | 2.9032 | 0.6687 | 6000 | 2.7090 | 0.2664 | 0.0654 | 0.1592 | 0.2487 |
60
- | 2.8327 | 0.8916 | 8000 | 2.6427 | 0.2751 | 0.0703 | 0.1634 | 0.2565 |
61
- | 2.6888 | 1.1145 | 10000 | 2.5945 | 0.2838 | 0.0756 | 0.1684 | 0.2646 |
62
- | 2.6639 | 1.3374 | 12000 | 2.5529 | 0.2909 | 0.0794 | 0.1717 | 0.2712 |
63
- | 2.6351 | 1.5603 | 14000 | 2.5159 | 0.2917 | 0.0809 | 0.1724 | 0.2718 |
64
- | 2.6154 | 1.7832 | 16000 | 2.4803 | 0.2993 | 0.0859 | 0.1765 | 0.2794 |
65
- | 2.5888 | 2.0061 | 18000 | 2.4529 | 0.3042 | 0.0891 | 0.1793 | 0.2837 |
66
- | 2.508 | 2.2290 | 20000 | 2.4338 | 0.3061 | 0.0910 | 0.1808 | 0.2854 |
67
- | 2.4864 | 2.4519 | 22000 | 2.4147 | 0.3079 | 0.0924 | 0.1818 | 0.2867 |
68
- | 2.472 | 2.6748 | 24000 | 2.3994 | 0.3100 | 0.0940 | 0.1833 | 0.2893 |
69
- | 2.4727 | 2.8977 | 26000 | 2.3910 | 0.3114 | 0.0950 | 0.1838 | 0.2907 |
70
 
71
 
72
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 2.3527
20
+ - Rouge1: 0.2544
21
+ - Rouge2: 0.0686
22
+ - Rougel: 0.1560
23
+ - Rougelsum: 0.2385
24
 
25
  ## Model description
26
 
 
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
56
  |:-------------:|:------:|:-----:|:---------------:|:------:|:------:|:------:|:---------:|
57
+ | 3.2453 | 0.2229 | 2000 | 3.0408 | 0.2031 | 0.0365 | 0.1269 | 0.1906 |
58
+ | 3.0421 | 0.4458 | 4000 | 2.8456 | 0.2380 | 0.0513 | 0.1453 | 0.2232 |
59
+ | 2.9227 | 0.6687 | 6000 | 2.7288 | 0.2595 | 0.0617 | 0.1558 | 0.2424 |
60
+ | 2.8436 | 0.8916 | 8000 | 2.6556 | 0.2584 | 0.0632 | 0.1555 | 0.2416 |
61
+ | 2.6961 | 1.1145 | 10000 | 2.5992 | 0.2578 | 0.0642 | 0.1570 | 0.2410 |
62
+ | 2.6662 | 1.3374 | 12000 | 2.5513 | 0.2749 | 0.0717 | 0.1642 | 0.2571 |
63
+ | 2.6312 | 1.5603 | 14000 | 2.5081 | 0.2530 | 0.0638 | 0.1543 | 0.2366 |
64
+ | 2.6058 | 1.7832 | 16000 | 2.4639 | 0.2636 | 0.0717 | 0.1601 | 0.2469 |
65
+ | 2.5725 | 2.0061 | 18000 | 2.4292 | 0.2567 | 0.0689 | 0.1560 | 0.2407 |
66
+ | 2.4892 | 2.2290 | 20000 | 2.4027 | 0.2707 | 0.0746 | 0.1640 | 0.2531 |
67
+ | 2.4647 | 2.4519 | 22000 | 2.3801 | 0.2508 | 0.0664 | 0.1540 | 0.2350 |
68
+ | 2.4479 | 2.6748 | 24000 | 2.3620 | 0.2638 | 0.0727 | 0.1608 | 0.2473 |
69
+ | 2.4474 | 2.8977 | 26000 | 2.3527 | 0.2544 | 0.0686 | 0.1560 | 0.2385 |
70
 
71
 
72
  ### Framework versions