Hugging Face's logo

floflodebilbao
/
long_T5_sum_approach

Transformers
TensorBoard
Safetensors
longt5
text2text-generation
Generated from Trainer
Model card Files
xet
Metrics Community
floflodebilbao commited on
Commit
3fa13d0
·
verified ·
1 Parent(s): 5e78bd9

End of training

Browse files
Files changed (4) hide show
  1. README.md +26 -18
  2. model.safetensors +1 -1
  3. runs/Jul10_14-36-18_tardis/events.out.tfevents.1752150979.tardis.66384.0 +3 -0
  4. training_args.bin +1 -1
README.md CHANGED
@@ -22,21 +22,21 @@ should probably proofread and complete it, then remove this comment. -->
22
 
23
  This model is a fine-tuned version of [google/long-t5-tglobal-base](https://huggingface.co/google/long-t5-tglobal-base) on an unknown dataset.
24
  It achieves the following results on the evaluation set:
25
- - Loss: 19.5442
26
- - Rouge1: 0.2643
27
- - Rouge2: 0.0857
28
- - Rougel: 0.1972
29
- - Rougelsum: 0.1959
30
- - Gen Len: 61.36
31
- - Bleu: 0.0407
32
- - Precisions: 0.0643
33
  - Brevity Penalty: 1.0
34
- - Length Ratio: 1.7551
35
- - Translation Length: 2143.0
36
  - Reference Length: 1221.0
37
- - Precision: 0.8378
38
- - Recall: 0.8703
39
- - F1: 0.8537
40
  - Hashcode: roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1)
41
 
42
  ## Model description
@@ -64,16 +64,24 @@ The following hyperparameters were used during training:
64
  - total_train_batch_size: 16
65
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
66
  - lr_scheduler_type: linear
67
- - num_epochs: 15
68
 
69
  ### Training results
70
 
71
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | Bleu | Precisions | Brevity Penalty | Length Ratio | Translation Length | Reference Length | Precision | Recall | F1 | Hashcode |
72
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|:------:|:----------:|:---------------:|:------------:|:------------------:|:----------------:|:---------:|:------:|:------:|:---------------------------------------------------------:|
73
- | 24.6478 | 1.0 | 7 | 26.0662 | 0.2663 | 0.0839 | 0.1997 | 0.1987 | 62.06 | 0.0363 | 0.0615 | 1.0 | 1.7961 | 2193.0 | 1221.0 | 0.8345 | 0.8702 | 0.8519 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |
74
- | 22.4374 | 2.0 | 14 | 23.4955 | 0.2719 | 0.0894 | 0.2003 | 0.1992 | 62.06 | 0.0424 | 0.0666 | 1.0 | 1.7723 | 2164.0 | 1221.0 | 0.836 | 0.8713 | 0.8532 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |
75
- | 20.7959 | 3.0 | 21 | 21.3631 | 0.2703 | 0.0887 | 0.1983 | 0.1973 | 61.76 | 0.0421 | 0.0662 | 1.0 | 1.7682 | 2159.0 | 1221.0 | 0.8377 | 0.8713 | 0.8541 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |
76
- | 19.0876 | 4.0 | 28 | 19.5442 | 0.2643 | 0.0857 | 0.1972 | 0.1959 | 61.36 | 0.0407 | 0.0643 | 1.0 | 1.7551 | 2143.0 | 1221.0 | 0.8378 | 0.8703 | 0.8537 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |
 
 
 
 
 
 
 
 
77
 
78
 
79
  ### Framework versions
 
22
 
23
  This model is a fine-tuned version of [google/long-t5-tglobal-base](https://huggingface.co/google/long-t5-tglobal-base) on an unknown dataset.
24
  It achieves the following results on the evaluation set:
25
+ - Loss: 7.4155
26
+ - Rouge1: 0.2826
27
+ - Rouge2: 0.1063
28
+ - Rougel: 0.2061
29
+ - Rougelsum: 0.2052
30
+ - Gen Len: 63.0
31
+ - Bleu: 0.0492
32
+ - Precisions: 0.0722
33
  - Brevity Penalty: 1.0
34
+ - Length Ratio: 1.8591
35
+ - Translation Length: 2270.0
36
  - Reference Length: 1221.0
37
+ - Precision: 0.8414
38
+ - Recall: 0.8739
39
+ - F1: 0.8573
40
  - Hashcode: roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1)
41
 
42
  ## Model description
 
64
  - total_train_batch_size: 16
65
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
66
  - lr_scheduler_type: linear
67
+ - num_epochs: 12
68
 
69
  ### Training results
70
 
71
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | Bleu | Precisions | Brevity Penalty | Length Ratio | Translation Length | Reference Length | Precision | Recall | F1 | Hashcode |
72
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|:------:|:----------:|:---------------:|:------------:|:------------------:|:----------------:|:---------:|:------:|:------:|:---------------------------------------------------------:|
73
+ | No log | 1.0 | 7 | 24.9448 | 0.2712 | 0.0914 | 0.2009 | 0.2009 | 62.3 | 0.0448 | 0.0682 | 1.0 | 1.8034 | 2202.0 | 1221.0 | 0.8369 | 0.872 | 0.854 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |
74
+ | No log | 2.0 | 14 | 22.3346 | 0.272 | 0.0918 | 0.2029 | 0.2028 | 62.18 | 0.0446 | 0.068 | 1.0 | 1.8116 | 2212.0 | 1221.0 | 0.8374 | 0.8719 | 0.8542 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |
75
+ | No log | 3.0 | 21 | 20.5424 | 0.2747 | 0.0981 | 0.2024 | 0.2014 | 62.36 | 0.0451 | 0.0687 | 1.0 | 1.8321 | 2237.0 | 1221.0 | 0.8394 | 0.8723 | 0.8555 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |
76
+ | No log | 4.0 | 28 | 18.9191 | 0.2817 | 0.1109 | 0.2093 | 0.2087 | 62.42 | 0.0532 | 0.0754 | 1.0 | 1.8165 | 2218.0 | 1221.0 | 0.8397 | 0.8746 | 0.8567 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |
77
+ | No log | 5.0 | 35 | 17.4649 | 0.28 | 0.1103 | 0.2079 | 0.2071 | 62.42 | 0.0537 | 0.0761 | 1.0 | 1.8141 | 2215.0 | 1221.0 | 0.8399 | 0.8739 | 0.8565 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |
78
+ | No log | 6.0 | 42 | 16.0864 | 0.291 | 0.1082 | 0.2125 | 0.2118 | 62.68 | 0.0527 | 0.0762 | 1.0 | 1.8305 | 2235.0 | 1221.0 | 0.8425 | 0.8758 | 0.8588 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |
79
+ | No log | 7.0 | 49 | 14.7017 | 0.296 | 0.112 | 0.2185 | 0.2176 | 62.78 | 0.0537 | 0.0767 | 1.0 | 1.8256 | 2229.0 | 1221.0 | 0.8433 | 0.8765 | 0.8595 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |
80
+ | No log | 8.0 | 56 | 13.1332 | 0.2904 | 0.1039 | 0.213 | 0.2131 | 62.78 | 0.047 | 0.0714 | 1.0 | 1.8239 | 2227.0 | 1221.0 | 0.8421 | 0.8751 | 0.8582 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |
81
+ | No log | 9.0 | 63 | 11.3128 | 0.2812 | 0.0975 | 0.2032 | 0.2031 | 62.8 | 0.043 | 0.0674 | 1.0 | 1.8436 | 2251.0 | 1221.0 | 0.8405 | 0.8729 | 0.8563 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |
82
+ | No log | 10.0 | 70 | 9.4296 | 0.2744 | 0.0957 | 0.1972 | 0.1977 | 63.0 | 0.0431 | 0.067 | 1.0 | 1.8518 | 2261.0 | 1221.0 | 0.8399 | 0.8727 | 0.856 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |
83
+ | No log | 11.0 | 77 | 7.9702 | 0.278 | 0.0973 | 0.1966 | 0.1971 | 63.0 | 0.0432 | 0.0674 | 1.0 | 1.8501 | 2259.0 | 1221.0 | 0.84 | 0.8732 | 0.8562 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |
84
+ | No log | 12.0 | 84 | 7.4155 | 0.2826 | 0.1063 | 0.2061 | 0.2052 | 63.0 | 0.0492 | 0.0722 | 1.0 | 1.8591 | 2270.0 | 1221.0 | 0.8414 | 0.8739 | 0.8573 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |
85
 
86
 
87
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:96958ff48eed315669d024583c5abb8deb7261c417525b8dff8bcc31da90e019
3
  size 1187780840
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c21122d7b9546595577586999502a71e8fdce2ffe6238d8f59a192487e5e10ac
3
  size 1187780840
runs/Jul10_14-36-18_tardis/events.out.tfevents.1752150979.tardis.66384.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:545ff3956ca3e724ef66b9941cf45243121931307bebf4598084827e84fe3fdb
3
+ size 19278
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f3e8d850c3ffd6713407d68a90cbd14091cf27650a3438bb58b83394037bef3f
3
  size 5905
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d935486008916a5193daf9dadf6ae0bb6a112bdb8132b1b1b43eb4d797444993
3
  size 5905