TerryHenrickson
commited on
Commit
•
51369b3
1
Parent(s):
2fcd4fe
Training in progress, step 500
Browse files- README.md +29 -49
- added_tokens.json +2 -1
- config.json +1 -1
- model.safetensors +2 -2
- runs/Feb17_13-03-54_6fd38e49e7fc/events.out.tfevents.1708175035.6fd38e49e7fc.23634.0 +2 -2
- runs/Feb19_09-07-25_3e139e734b2e/events.out.tfevents.1708333646.3e139e734b2e.332.0 +3 -0
- tokenizer.json +18 -0
- tokenizer_config.json +16 -0
- training_args.bin +1 -1
README.md
CHANGED
@@ -17,12 +17,12 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss: 0.
|
21 |
-
- Rouge1:
|
22 |
-
- Rouge2:
|
23 |
-
- Rougel:
|
24 |
-
- Rougelsum:
|
25 |
-
- Gen Len:
|
26 |
|
27 |
## Model description
|
28 |
|
@@ -47,53 +47,33 @@ The following hyperparameters were used during training:
|
|
47 |
- seed: 42
|
48 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
49 |
- lr_scheduler_type: linear
|
50 |
-
- num_epochs:
|
51 |
- mixed_precision_training: Native AMP
|
52 |
|
53 |
### Training results
|
54 |
|
55 |
-
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len
|
56 |
-
|
57 |
-
| No log | 1.0 | 90 | 3.
|
58 |
-
| No log | 2.0 | 180 |
|
59 |
-
| No log | 3.0 | 270 |
|
60 |
-
| No log | 4.0 | 360 | 0.
|
61 |
-
| No log | 5.0 | 450 | 0.
|
62 |
-
| 2.
|
63 |
-
| 2.
|
64 |
-
| 2.
|
65 |
-
| 2.
|
66 |
-
| 2.
|
67 |
-
| 2.
|
68 |
-
| 0.
|
69 |
-
| 0.
|
70 |
-
| 0.
|
71 |
-
| 0.
|
72 |
-
| 0.
|
73 |
-
| 0.
|
74 |
-
| 0.
|
75 |
-
| 0.
|
76 |
-
| 0.
|
77 |
-
| 0.2699 | 21.0 | 1890 | 0.1942 | 99.3849 | 99.2668 | 99.399 | 99.388 | 94.4222 |
|
78 |
-
| 0.2699 | 22.0 | 1980 | 0.1900 | 99.1136 | 99.0255 | 99.1074 | 99.0893 | 92.5528 |
|
79 |
-
| 0.236 | 23.0 | 2070 | 0.1861 | 99.2462 | 99.1628 | 99.2568 | 99.2378 | 92.9806 |
|
80 |
-
| 0.236 | 24.0 | 2160 | 0.1828 | 99.3348 | 99.2435 | 99.3313 | 99.3233 | 93.0083 |
|
81 |
-
| 0.236 | 25.0 | 2250 | 0.1792 | 99.6636 | 99.5859 | 99.6665 | 99.6692 | 94.2806 |
|
82 |
-
| 0.236 | 26.0 | 2340 | 0.1762 | 99.7247 | 99.6578 | 99.7251 | 99.7271 | 94.1417 |
|
83 |
-
| 0.236 | 27.0 | 2430 | 0.1738 | 99.4961 | 99.4165 | 99.5065 | 99.5036 | 93.5083 |
|
84 |
-
| 0.2128 | 28.0 | 2520 | 0.1710 | 99.7151 | 99.6645 | 99.7248 | 99.7198 | 93.7944 |
|
85 |
-
| 0.2128 | 29.0 | 2610 | 0.1687 | 99.7679 | 99.7155 | 99.7692 | 99.7688 | 93.9444 |
|
86 |
-
| 0.2128 | 30.0 | 2700 | 0.1668 | 99.7679 | 99.7155 | 99.7692 | 99.7688 | 93.9444 |
|
87 |
-
| 0.2128 | 31.0 | 2790 | 0.1647 | 99.7602 | 99.6983 | 99.7552 | 99.7602 | 93.9417 |
|
88 |
-
| 0.2128 | 32.0 | 2880 | 0.1629 | 99.7602 | 99.6983 | 99.7552 | 99.7602 | 93.9444 |
|
89 |
-
| 0.2128 | 33.0 | 2970 | 0.1614 | 99.7679 | 99.7155 | 99.7692 | 99.7688 | 93.9444 |
|
90 |
-
| 0.1981 | 34.0 | 3060 | 0.1600 | 99.7679 | 99.7155 | 99.7692 | 99.7688 | 93.9444 |
|
91 |
-
| 0.1981 | 35.0 | 3150 | 0.1591 | 99.7679 | 99.7155 | 99.7692 | 99.7688 | 93.9444 |
|
92 |
-
| 0.1981 | 36.0 | 3240 | 0.1583 | 99.7679 | 99.7155 | 99.7692 | 99.7688 | 93.9361 |
|
93 |
-
| 0.1981 | 37.0 | 3330 | 0.1577 | 99.7679 | 99.7155 | 99.7692 | 99.7688 | 93.9417 |
|
94 |
-
| 0.1981 | 38.0 | 3420 | 0.1572 | 99.7679 | 99.7155 | 99.7692 | 99.7688 | 93.9417 |
|
95 |
-
| 0.1905 | 39.0 | 3510 | 0.1569 | 99.8039 | 99.7623 | 99.8048 | 99.8038 | 94.0083 |
|
96 |
-
| 0.1905 | 40.0 | 3600 | 0.1568 | 99.7679 | 99.7155 | 99.7692 | 99.7688 | 93.9417 |
|
97 |
|
98 |
|
99 |
### Framework versions
|
|
|
17 |
|
18 |
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.2397
|
21 |
+
- Rouge1: 39.9145
|
22 |
+
- Rouge2: 33.183
|
23 |
+
- Rougel: 39.9484
|
24 |
+
- Rougelsum: 39.9376
|
25 |
+
- Gen Len: 19.0
|
26 |
|
27 |
## Model description
|
28 |
|
|
|
47 |
- seed: 42
|
48 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
49 |
- lr_scheduler_type: linear
|
50 |
+
- num_epochs: 20
|
51 |
- mixed_precision_training: Native AMP
|
52 |
|
53 |
### Training results
|
54 |
|
55 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|
56 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
|
57 |
+
| No log | 1.0 | 90 | 3.4654 | 9.8007 | 0.2231 | 9.4993 | 9.501 | 18.6889 |
|
58 |
+
| No log | 2.0 | 180 | 2.1906 | 10.4443 | 0.2158 | 9.8828 | 9.8755 | 18.8972 |
|
59 |
+
| No log | 3.0 | 270 | 1.3067 | 11.7213 | 0.5145 | 10.913 | 10.9345 | 18.8528 |
|
60 |
+
| No log | 4.0 | 360 | 0.7369 | 14.9807 | 1.4227 | 13.7179 | 13.7131 | 18.8333 |
|
61 |
+
| No log | 5.0 | 450 | 0.6143 | 19.8511 | 4.6089 | 18.0244 | 17.9558 | 18.7083 |
|
62 |
+
| 2.447 | 6.0 | 540 | 0.5312 | 23.1026 | 8.6515 | 20.7866 | 20.757 | 18.7139 |
|
63 |
+
| 2.447 | 7.0 | 630 | 0.4782 | 21.9961 | 9.3626 | 19.7651 | 19.7488 | 18.5944 |
|
64 |
+
| 2.447 | 8.0 | 720 | 0.4365 | 16.4406 | 6.5397 | 14.9694 | 14.9816 | 18.6639 |
|
65 |
+
| 2.447 | 9.0 | 810 | 0.3603 | 6.9337 | 3.7397 | 6.6337 | 6.6621 | 18.9028 |
|
66 |
+
| 2.447 | 10.0 | 900 | 0.2696 | 24.2884 | 19.0601 | 24.1044 | 24.1488 | 18.9694 |
|
67 |
+
| 2.447 | 11.0 | 990 | 0.2590 | 39.2002 | 32.3107 | 39.202 | 39.1928 | 19.0 |
|
68 |
+
| 0.572 | 12.0 | 1080 | 0.2546 | 39.0083 | 32.1464 | 39.0296 | 38.9988 | 19.0 |
|
69 |
+
| 0.572 | 13.0 | 1170 | 0.2486 | 39.519 | 32.7114 | 39.5614 | 39.5391 | 19.0 |
|
70 |
+
| 0.572 | 14.0 | 1260 | 0.2465 | 39.589 | 32.8014 | 39.6298 | 39.6092 | 19.0 |
|
71 |
+
| 0.572 | 15.0 | 1350 | 0.2444 | 39.5831 | 32.7959 | 39.6266 | 39.6123 | 19.0 |
|
72 |
+
| 0.572 | 16.0 | 1440 | 0.2427 | 39.7174 | 32.9525 | 39.7513 | 39.7311 | 19.0 |
|
73 |
+
| 0.3469 | 17.0 | 1530 | 0.2412 | 39.8478 | 33.0999 | 39.8901 | 39.8708 | 19.0 |
|
74 |
+
| 0.3469 | 18.0 | 1620 | 0.2401 | 39.8528 | 33.1031 | 39.8819 | 39.873 | 19.0 |
|
75 |
+
| 0.3469 | 19.0 | 1710 | 0.2398 | 39.9283 | 33.1964 | 39.9502 | 39.9533 | 19.0 |
|
76 |
+
| 0.3469 | 20.0 | 1800 | 0.2397 | 39.9145 | 33.183 | 39.9484 | 39.9376 | 19.0 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
77 |
|
78 |
|
79 |
### Framework versions
|
added_tokens.json
CHANGED
@@ -1,4 +1,5 @@
|
|
1 |
{
|
|
|
2 |
"{": 32100,
|
3 |
-
"}":
|
4 |
}
|
|
|
1 |
{
|
2 |
+
"<": 32101,
|
3 |
"{": 32100,
|
4 |
+
"}": 32102
|
5 |
}
|
config.json
CHANGED
@@ -57,5 +57,5 @@
|
|
57 |
"torch_dtype": "float32",
|
58 |
"transformers_version": "4.35.2",
|
59 |
"use_cache": true,
|
60 |
-
"vocab_size":
|
61 |
}
|
|
|
57 |
"torch_dtype": "float32",
|
58 |
"transformers_version": "4.35.2",
|
59 |
"use_cache": true,
|
60 |
+
"vocab_size": 32103
|
61 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1eb4dc6fba72057b3cca4caa08f0ea1b3ed9b9fd7fa327344b1ab52701bd47e4
|
3 |
+
size 241990696
|
runs/Feb17_13-03-54_6fd38e49e7fc/events.out.tfevents.1708175035.6fd38e49e7fc.23634.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7bdd99d5d48223b7dd1ffe5561370b234e415ea3884b6d2f54f69dcbd9c4115c
|
3 |
+
size 14074
|
runs/Feb19_09-07-25_3e139e734b2e/events.out.tfevents.1708333646.3e139e734b2e.332.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c9b02277c64ec7ccdb6d62aad46818efa4a2c61fd96a9fa7d5d8c0d0f54130dc
|
3 |
+
size 6420
|
tokenizer.json
CHANGED
@@ -44,6 +44,15 @@
|
|
44 |
"normalized": true,
|
45 |
"special": false
|
46 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
47 |
{
|
48 |
"id": 6306,
|
49 |
"content": "[",
|
@@ -964,6 +973,15 @@
|
|
964 |
},
|
965 |
{
|
966 |
"id": 32101,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
967 |
"content": "}",
|
968 |
"single_word": false,
|
969 |
"lstrip": false,
|
|
|
44 |
"normalized": true,
|
45 |
"special": false
|
46 |
},
|
47 |
+
{
|
48 |
+
"id": 3155,
|
49 |
+
"content": ">",
|
50 |
+
"single_word": false,
|
51 |
+
"lstrip": false,
|
52 |
+
"rstrip": false,
|
53 |
+
"normalized": true,
|
54 |
+
"special": false
|
55 |
+
},
|
56 |
{
|
57 |
"id": 6306,
|
58 |
"content": "[",
|
|
|
973 |
},
|
974 |
{
|
975 |
"id": 32101,
|
976 |
+
"content": "<",
|
977 |
+
"single_word": false,
|
978 |
+
"lstrip": false,
|
979 |
+
"rstrip": false,
|
980 |
+
"normalized": true,
|
981 |
+
"special": false
|
982 |
+
},
|
983 |
+
{
|
984 |
+
"id": 32102,
|
985 |
"content": "}",
|
986 |
"single_word": false,
|
987 |
"lstrip": false,
|
tokenizer_config.json
CHANGED
@@ -32,6 +32,14 @@
|
|
32 |
"single_word": false,
|
33 |
"special": false
|
34 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
35 |
"6306": {
|
36 |
"content": "[",
|
37 |
"lstrip": false,
|
@@ -849,6 +857,14 @@
|
|
849 |
"special": false
|
850 |
},
|
851 |
"32101": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
852 |
"content": "}",
|
853 |
"lstrip": false,
|
854 |
"normalized": true,
|
|
|
32 |
"single_word": false,
|
33 |
"special": false
|
34 |
},
|
35 |
+
"3155": {
|
36 |
+
"content": ">",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": true,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": false
|
42 |
+
},
|
43 |
"6306": {
|
44 |
"content": "[",
|
45 |
"lstrip": false,
|
|
|
857 |
"special": false
|
858 |
},
|
859 |
"32101": {
|
860 |
+
"content": "<",
|
861 |
+
"lstrip": false,
|
862 |
+
"normalized": true,
|
863 |
+
"rstrip": false,
|
864 |
+
"single_word": false,
|
865 |
+
"special": false
|
866 |
+
},
|
867 |
+
"32102": {
|
868 |
"content": "}",
|
869 |
"lstrip": false,
|
870 |
"normalized": true,
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4728
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0409db644164a757bfff2c00eb548d6754af8d407fc21bed949472163c3941ef
|
3 |
size 4728
|