machinelearningzuu
commited on
Commit
•
f9c9ac5
1
Parent(s):
63683e0
update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,120 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: t5-small
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: lesson-summarization
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# lesson-summarization
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the None dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 2.5713
|
19 |
+
|
20 |
+
## Model description
|
21 |
+
|
22 |
+
More information needed
|
23 |
+
|
24 |
+
## Intended uses & limitations
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Training and evaluation data
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training procedure
|
33 |
+
|
34 |
+
### Training hyperparameters
|
35 |
+
|
36 |
+
The following hyperparameters were used during training:
|
37 |
+
- learning_rate: 2e-05
|
38 |
+
- train_batch_size: 1
|
39 |
+
- eval_batch_size: 1
|
40 |
+
- seed: 42
|
41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
+
- lr_scheduler_type: linear
|
43 |
+
- num_epochs: 200
|
44 |
+
|
45 |
+
### Training results
|
46 |
+
|
47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
+
|:-------------:|:------:|:-----:|:---------------:|
|
49 |
+
| 2.9037 | 3.12 | 200 | 2.2456 |
|
50 |
+
| 2.5914 | 6.25 | 400 | 2.1498 |
|
51 |
+
| 2.393 | 9.38 | 600 | 2.1002 |
|
52 |
+
| 2.2409 | 12.5 | 800 | 2.0754 |
|
53 |
+
| 2.1515 | 15.62 | 1000 | 2.0683 |
|
54 |
+
| 2.0633 | 18.75 | 1200 | 2.0541 |
|
55 |
+
| 1.9418 | 21.88 | 1400 | 2.0603 |
|
56 |
+
| 1.837 | 25.0 | 1600 | 2.0788 |
|
57 |
+
| 1.7715 | 28.12 | 1800 | 2.0754 |
|
58 |
+
| 1.6957 | 31.25 | 2000 | 2.0815 |
|
59 |
+
| 1.6079 | 34.38 | 2200 | 2.0940 |
|
60 |
+
| 1.5947 | 37.5 | 2400 | 2.1094 |
|
61 |
+
| 1.4603 | 40.62 | 2600 | 2.1147 |
|
62 |
+
| 1.4621 | 43.75 | 2800 | 2.1354 |
|
63 |
+
| 1.4021 | 46.88 | 3000 | 2.1519 |
|
64 |
+
| 1.3394 | 50.0 | 3200 | 2.1670 |
|
65 |
+
| 1.2866 | 53.12 | 3400 | 2.1921 |
|
66 |
+
| 1.2681 | 56.25 | 3600 | 2.2045 |
|
67 |
+
| 1.1866 | 59.38 | 3800 | 2.2194 |
|
68 |
+
| 1.2098 | 62.5 | 4000 | 2.2302 |
|
69 |
+
| 1.1386 | 65.62 | 4200 | 2.2400 |
|
70 |
+
| 1.0853 | 68.75 | 4400 | 2.2634 |
|
71 |
+
| 1.0888 | 71.88 | 4600 | 2.2810 |
|
72 |
+
| 1.0408 | 75.0 | 4800 | 2.2909 |
|
73 |
+
| 1.0309 | 78.12 | 5000 | 2.3059 |
|
74 |
+
| 0.9523 | 81.25 | 5200 | 2.3249 |
|
75 |
+
| 0.9671 | 84.38 | 5400 | 2.3333 |
|
76 |
+
| 0.9413 | 87.5 | 5600 | 2.3543 |
|
77 |
+
| 0.9127 | 90.62 | 5800 | 2.3636 |
|
78 |
+
| 0.9095 | 93.75 | 6000 | 2.3676 |
|
79 |
+
| 0.8952 | 96.88 | 6200 | 2.3756 |
|
80 |
+
| 0.857 | 100.0 | 6400 | 2.3878 |
|
81 |
+
| 0.8474 | 103.12 | 6600 | 2.4148 |
|
82 |
+
| 0.8215 | 106.25 | 6800 | 2.4231 |
|
83 |
+
| 0.8172 | 109.38 | 7000 | 2.4243 |
|
84 |
+
| 0.7761 | 112.5 | 7200 | 2.4489 |
|
85 |
+
| 0.7737 | 115.62 | 7400 | 2.4718 |
|
86 |
+
| 0.7476 | 118.75 | 7600 | 2.4614 |
|
87 |
+
| 0.7345 | 121.88 | 7800 | 2.4705 |
|
88 |
+
| 0.7426 | 125.0 | 8000 | 2.4740 |
|
89 |
+
| 0.7151 | 128.12 | 8200 | 2.4833 |
|
90 |
+
| 0.7191 | 131.25 | 8400 | 2.4786 |
|
91 |
+
| 0.6818 | 134.38 | 8600 | 2.4882 |
|
92 |
+
| 0.6862 | 137.5 | 8800 | 2.4938 |
|
93 |
+
| 0.6929 | 140.62 | 9000 | 2.4977 |
|
94 |
+
| 0.6494 | 143.75 | 9200 | 2.5195 |
|
95 |
+
| 0.6689 | 146.88 | 9400 | 2.5185 |
|
96 |
+
| 0.6492 | 150.0 | 9600 | 2.5259 |
|
97 |
+
| 0.6384 | 153.12 | 9800 | 2.5259 |
|
98 |
+
| 0.6435 | 156.25 | 10000 | 2.5287 |
|
99 |
+
| 0.6251 | 159.38 | 10200 | 2.5284 |
|
100 |
+
| 0.6295 | 162.5 | 10400 | 2.5398 |
|
101 |
+
| 0.6324 | 165.62 | 10600 | 2.5442 |
|
102 |
+
| 0.6252 | 168.75 | 10800 | 2.5481 |
|
103 |
+
| 0.6108 | 171.88 | 11000 | 2.5455 |
|
104 |
+
| 0.6034 | 175.0 | 11200 | 2.5502 |
|
105 |
+
| 0.5969 | 178.12 | 11400 | 2.5601 |
|
106 |
+
| 0.5949 | 181.25 | 11600 | 2.5617 |
|
107 |
+
| 0.6183 | 184.38 | 11800 | 2.5679 |
|
108 |
+
| 0.5805 | 187.5 | 12000 | 2.5687 |
|
109 |
+
| 0.6032 | 190.62 | 12200 | 2.5708 |
|
110 |
+
| 0.5955 | 193.75 | 12400 | 2.5709 |
|
111 |
+
| 0.5961 | 196.88 | 12600 | 2.5713 |
|
112 |
+
| 0.5914 | 200.0 | 12800 | 2.5713 |
|
113 |
+
|
114 |
+
|
115 |
+
### Framework versions
|
116 |
+
|
117 |
+
- Transformers 4.31.0
|
118 |
+
- Pytorch 1.13.1
|
119 |
+
- Datasets 2.12.0
|
120 |
+
- Tokenizers 0.13.3
|