learn3r commited on
Commit
0f84021
1 Parent(s): ee5ddb3

Model save

Browse files
Files changed (1) hide show
  1. README.md +26 -38
README.md CHANGED
@@ -1,24 +1,11 @@
1
  ---
2
- base_model: /exports/eddie/scratch/s1970716/models/summarization/longt5_xl_summ_screen_bp_only/checkpoint-210
3
  tags:
4
  - generated_from_trainer
5
- datasets:
6
- - learn3r/summ_screen_fd_bp
7
  metrics:
8
  - rouge
9
  model-index:
10
  - name: longt5_xl_summ_screen_bp_only_30
11
- results:
12
- - task:
13
- name: Summarization
14
- type: summarization
15
- dataset:
16
- name: learn3r/summ_screen_fd_bp
17
- type: learn3r/summ_screen_fd_bp
18
- metrics:
19
- - name: Rouge1
20
- type: rouge
21
- value: 40.4943
22
  ---
23
 
24
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -26,14 +13,14 @@ should probably proofread and complete it, then remove this comment. -->
26
 
27
  # longt5_xl_summ_screen_bp_only_30
28
 
29
- This model is a fine-tuned version of [/exports/eddie/scratch/s1970716/models/summarization/longt5_xl_summ_screen_bp_only/checkpoint-210](https://huggingface.co//exports/eddie/scratch/s1970716/models/summarization/longt5_xl_summ_screen_bp_only/checkpoint-210) on the learn3r/summ_screen_fd_bp dataset.
30
  It achieves the following results on the evaluation set:
31
- - Loss: 2.2397
32
- - Rouge1: 40.4943
33
- - Rouge2: 16.4695
34
- - Rougel: 28.0964
35
- - Rougelsum: 38.3693
36
- - Gen Len: 246.3491
37
 
38
  ## Model description
39
 
@@ -56,30 +43,31 @@ The following hyperparameters were used during training:
56
  - train_batch_size: 8
57
  - eval_batch_size: 8
58
  - seed: 42
59
- - distributed_type: multi-GPU
60
- - num_devices: 4
61
  - gradient_accumulation_steps: 32
62
- - total_train_batch_size: 1024
63
- - total_eval_batch_size: 32
64
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
65
  - lr_scheduler_type: constant
66
  - num_epochs: 15.0
67
 
68
  ### Training results
69
 
70
- | Training Loss | Epoch | Step | Gen Len | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
71
- |:-------------:|:-----:|:----:|:--------:|:---------------:|:-------:|:-------:|:-------:|:---------:|
72
- | 0.324 | 0.97 | 14 | 246.7396 | 2.2376 | 40.4388 | 16.4662 | 28.0771 | 38.3405 |
73
- | 0.324 | 4.83 | 15 | 2.5727 | 30.0123 | 12.3701 | 21.2834 | 28.891 | 503.5651 |
74
- | 0.3036 | 5.95 | 19 | 2.2659 | 27.8421 | 11.1942 | 20.4713 | 26.6097 | 506.9527 |
75
- | 0.2941 | 6.78 | 22 | 2.2636 | 40.8304 | 17.3615 | 28.0971 | 39.0943 | 284.2308 |
76
- | 0.2642 | 7.9 | 26 | 2.2864 | 38.3377 | 15.8119 | 26.4838 | 36.5174 | 341.2515 |
77
- | 0.2604 | 8.73 | 29 | 2.4551 | 33.2021 | 13.6577 | 23.3288 | 31.8326 | 435.2633 |
78
- | 0.2237 | 9.84 | 33 | 2.6153 | 40.3297 | 15.3786 | 28.1208 | 38.2426 | 234.6124 |
79
- | 0.1904 | 10.96 | 37 | 2.6665 | 39.6006 | 14.9586 | 27.2453 | 37.6744 | 174.5740 |
80
- | 0.2247 | 11.79 | 40 | 2.7224 | 30.5957 | 13.3496 | 21.9712 | 29.22 | 500.5828 |
81
- | 0.182 | 12.9 | 44 | 3.2715 | 41.6828 | 17.0818 | 28.087 | 39.5947 | 259.6568 |
82
- | 0.182 | 13.18 | 45 | 2.3973 | 31.9833 | 14.0141 | 22.6823 | 30.6424 | 484.3964 |
 
 
 
 
83
 
84
 
85
  ### Framework versions
 
1
  ---
 
2
  tags:
3
  - generated_from_trainer
 
 
4
  metrics:
5
  - rouge
6
  model-index:
7
  - name: longt5_xl_summ_screen_bp_only_30
8
+ results: []
 
 
 
 
 
 
 
 
 
 
9
  ---
10
 
11
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
13
 
14
  # longt5_xl_summ_screen_bp_only_30
15
 
16
+ This model was trained from scratch on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 3.4990
19
+ - Rouge1: 32.5815
20
+ - Rouge2: 14.2951
21
+ - Rougel: 22.4501
22
+ - Rougelsum: 31.2928
23
+ - Gen Len: 499.3107
24
 
25
  ## Model description
26
 
 
43
  - train_batch_size: 8
44
  - eval_batch_size: 8
45
  - seed: 42
 
 
46
  - gradient_accumulation_steps: 32
47
+ - total_train_batch_size: 256
 
48
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
  - lr_scheduler_type: constant
50
  - num_epochs: 15.0
51
 
52
  ### Training results
53
 
54
+ | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
55
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:--------:|
56
+ | 0.324 | 0.97 | 14 | 2.2376 | 40.4388 | 16.4662 | 28.0771 | 38.3405 | 246.7396 |
57
+ | 0.2707 | 1.95 | 28 | 2.3204 | 40.2873 | 16.7641 | 27.3895 | 38.2689 | 307.3787 |
58
+ | 0.2217 | 2.99 | 43 | 2.5281 | 31.9916 | 13.8136 | 22.1895 | 30.623 | 501.9320 |
59
+ | 0.1776 | 3.97 | 57 | 2.7530 | 31.7535 | 13.8852 | 22.8653 | 30.3796 | 489.6183 |
60
+ | 0.1424 | 4.94 | 71 | 2.6578 | 32.117 | 14.2141 | 22.3733 | 30.8328 | 502.1124 |
61
+ | 0.1449 | 5.98 | 86 | 2.5508 | 35.3448 | 13.8478 | 24.9044 | 33.6108 | 357.3136 |
62
+ | 0.1191 | 6.96 | 100 | 3.1622 | 37.2189 | 16.0076 | 25.7011 | 35.294 | 408.8669 |
63
+ | 0.0879 | 8.0 | 115 | 2.8510 | 39.8825 | 16.8073 | 27.2428 | 37.9568 | 318.2278 |
64
+ | 0.0899 | 8.97 | 129 | 2.9138 | 31.7139 | 13.7066 | 21.8844 | 30.5075 | 500.4053 |
65
+ | 0.0656 | 9.95 | 143 | 3.1616 | 33.055 | 14.5841 | 22.5883 | 31.7565 | 488.1686 |
66
+ | 0.0542 | 10.99 | 158 | 3.3630 | 43.7514 | 18.9011 | 29.9017 | 41.6887 | 198.8077 |
67
+ | 0.0557 | 11.97 | 172 | 3.3826 | 42.3089 | 18.2735 | 29.0356 | 40.4154 | 270.9675 |
68
+ | 0.0542 | 12.94 | 186 | 3.4408 | 40.7691 | 16.529 | 28.3999 | 38.9723 | 186.7308 |
69
+ | 0.0596 | 13.98 | 201 | 3.5253 | 37.0037 | 15.9098 | 25.2808 | 35.3868 | 398.4704 |
70
+ | 0.0385 | 14.61 | 210 | 3.4990 | 32.5815 | 14.2951 | 22.4501 | 31.2928 | 499.3107 |
71
 
72
 
73
  ### Framework versions