Hugging Face's logo

kitty528
/
my_article_to_song_generation_model

Transformers
TensorBoard
Safetensors
t5
text2text-generation
Generated from Trainer
text-generation-inference
Model card Files
xet
 Metrics Community
kitty528 commited on
Commit
609790a
·
verified ·
1 Parent(s): f2a2946

End of training

Browse files
Files changed (5) hide show
  1. README.md +12 -37
  2. model.safetensors +1 -1
  3. runs/Jan30_21-16-39_91e10a40f47a/events.out.tfevents.1706649406.91e10a40f47a.1334.2 +3 -0
  4. tokenizer.json +2 -2
  5. training_args.bin +1 -1
README.md CHANGED
@@ -17,7 +17,7 @@ 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 the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 1.6515
21
  - Rouge1: 0.0
22
  - Rouge2: 0.0
23
  - Rougel: 0.0
@@ -49,48 +49,23 @@ The following hyperparameters were used during training:
49
  - total_train_batch_size: 10
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: linear
52
- - num_epochs: 35
53
  - mixed_precision_training: Native AMP
54
 
55
  ### Training results
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
58
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
59
- | No log | 1.0 | 6 | 16.2560 | 0.0609 | 0.0143 | 0.0529 | 0.0528 | 19.0 |
60
- | No log | 2.0 | 12 | 14.2686 | 0.0602 | 0.0128 | 0.0516 | 0.0516 | 19.0 |
61
- | No log | 3.0 | 18 | 12.3755 | 0.0639 | 0.0134 | 0.0548 | 0.0548 | 19.0 |
62
- | No log | 4.0 | 24 | 10.4025 | 0.067 | 0.0115 | 0.0547 | 0.0547 | 19.0 |
63
- | No log | 5.0 | 30 | 8.6351 | 0.0682 | 0.0131 | 0.0551 | 0.0553 | 19.0 |
64
- | No log | 6.0 | 36 | 7.3856 | 0.0682 | 0.0131 | 0.0551 | 0.0553 | 19.0 |
65
- | No log | 7.0 | 42 | 6.3727 | 0.0687 | 0.0131 | 0.0557 | 0.0557 | 19.0 |
66
- | No log | 8.0 | 48 | 5.4948 | 0.0683 | 0.0136 | 0.0557 | 0.0558 | 19.0 |
67
- | No log | 9.0 | 54 | 4.6428 | 0.0683 | 0.0132 | 0.0554 | 0.0553 | 19.0 |
68
- | No log | 10.0 | 60 | 3.8533 | 0.0683 | 0.0132 | 0.0554 | 0.0553 | 19.0 |
69
- | No log | 11.0 | 66 | 3.1973 | 0.0524 | 0.0105 | 0.0412 | 0.0419 | 15.2 |
70
- | No log | 12.0 | 72 | 2.7078 | 0.0419 | 0.0074 | 0.0336 | 0.034 | 11.4 |
71
- | No log | 13.0 | 78 | 2.3688 | 0.0266 | 0.0052 | 0.0234 | 0.0237 | 7.6 |
72
- | No log | 14.0 | 84 | 2.1534 | 0.007 | 0.002 | 0.0065 | 0.0065 | 1.9 |
73
- | No log | 15.0 | 90 | 2.0260 | 0.0052 | 0.0015 | 0.0052 | 0.0052 | 1.9 |
74
- | No log | 16.0 | 96 | 1.9478 | 0.0024 | 0.001 | 0.0024 | 0.0024 | 0.95 |
75
- | No log | 17.0 | 102 | 1.8972 | 0.0024 | 0.001 | 0.0024 | 0.0024 | 0.95 |
76
- | No log | 18.0 | 108 | 1.8585 | 0.0024 | 0.001 | 0.0024 | 0.0024 | 0.95 |
77
- | No log | 19.0 | 114 | 1.8262 | 0.0024 | 0.001 | 0.0024 | 0.0024 | 0.95 |
78
- | No log | 20.0 | 120 | 1.7977 | 0.0024 | 0.001 | 0.0024 | 0.0024 | 0.95 |
79
- | No log | 21.0 | 126 | 1.7731 | 0.0038 | 0.0014 | 0.0033 | 0.0033 | 0.95 |
80
- | No log | 22.0 | 132 | 1.7483 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
81
- | No log | 23.0 | 138 | 1.7304 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
82
- | No log | 24.0 | 144 | 1.7155 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
83
- | No log | 25.0 | 150 | 1.7025 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
84
- | No log | 26.0 | 156 | 1.6914 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
85
- | No log | 27.0 | 162 | 1.6825 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
86
- | No log | 28.0 | 168 | 1.6755 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
87
- | No log | 29.0 | 174 | 1.6691 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
88
- | No log | 30.0 | 180 | 1.6640 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
89
- | No log | 31.0 | 186 | 1.6599 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
90
- | No log | 32.0 | 192 | 1.6566 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
91
- | No log | 33.0 | 198 | 1.6541 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
92
- | No log | 34.0 | 204 | 1.6524 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
93
- | No log | 35.0 | 210 | 1.6515 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
94
 
95
 
96
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 2.5079
21
  - Rouge1: 0.0
22
  - Rouge2: 0.0
23
  - Rougel: 0.0
 
49
  - total_train_batch_size: 10
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: linear
52
+ - num_epochs: 10
53
  - mixed_precision_training: Native AMP
54
 
55
  ### Training results
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
58
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
59
+ | No log | 1.0 | 6 | 2.6066 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
60
+ | No log | 2.0 | 12 | 2.5867 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
61
+ | No log | 3.0 | 18 | 2.5701 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
62
+ | No log | 4.0 | 24 | 2.5554 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
63
+ | No log | 5.0 | 30 | 2.5405 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
64
+ | No log | 6.0 | 36 | 2.5292 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
65
+ | No log | 7.0 | 42 | 2.5207 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
66
+ | No log | 8.0 | 48 | 2.5145 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
67
+ | No log | 9.0 | 54 | 2.5102 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
68
+ | No log | 10.0 | 60 | 2.5079 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
 
70
 
71
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:13d1315192efdd5f8d73975969897f4e82f965b0bb18151af0aca0264eb9f9c5
3
  size 242041896
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cca326d6989648278aa81e7e52ec74a3385f6de53d62d1a3f80fcf0b2226e557
3
  size 242041896
runs/Jan30_21-16-39_91e10a40f47a/events.out.tfevents.1706649406.91e10a40f47a.1334.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2218f817926c351394ccc826d050c4b81e2e87c712100beb3de88543bd577e6
3
+ size 10775
tokenizer.json CHANGED
@@ -2,13 +2,13 @@
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
- "max_length": 500,
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
9
  "padding": {
10
  "strategy": {
11
- "Fixed": 500
12
  },
13
  "direction": "Right",
14
  "pad_to_multiple_of": null,
 
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
+ "max_length": 80,
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
9
  "padding": {
10
  "strategy": {
11
+ "Fixed": 80
12
  },
13
  "direction": "Right",
14
  "pad_to_multiple_of": null,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8eb3a3313d92212b54d80b64f130aa5e726ea6d7d6cf5d582427fa73d8654677
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d06af59cd4c47cf11338a4bb392a8fba8af4458811516b4eedab9a17833f76cf
3
  size 4728