update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
model-index:
|
6 |
+
- name: flan-t5-base-extraction-cnndm_8000-all-loss-ep50
|
7 |
+
results: []
|
8 |
+
---
|
9 |
+
|
10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
11 |
+
should probably proofread and complete it, then remove this comment. -->
|
12 |
+
|
13 |
+
# flan-t5-base-extraction-cnndm_8000-all-loss-ep50
|
14 |
+
|
15 |
+
This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the None dataset.
|
16 |
+
It achieves the following results on the evaluation set:
|
17 |
+
- Loss: 1.7340
|
18 |
+
- Hint Hit Num: 2.3422
|
19 |
+
- Hint Precision: 0.4261
|
20 |
+
- Num: 5.4786
|
21 |
+
- Gen Len: 18.9996
|
22 |
+
|
23 |
+
## Model description
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Intended uses & limitations
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training and evaluation data
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training procedure
|
36 |
+
|
37 |
+
### Training hyperparameters
|
38 |
+
|
39 |
+
The following hyperparameters were used during training:
|
40 |
+
- learning_rate: 2e-05
|
41 |
+
- train_batch_size: 60
|
42 |
+
- eval_batch_size: 400
|
43 |
+
- seed: 1799
|
44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
+
- lr_scheduler_type: linear
|
46 |
+
- num_epochs: 50
|
47 |
+
|
48 |
+
### Training results
|
49 |
+
|
50 |
+
| Training Loss | Epoch | Step | Validation Loss | Hint Hit Num | Hint Precision | Num | Gen Len |
|
51 |
+
|:-------------:|:-----:|:----:|:---------------:|:------------:|:--------------:|:------:|:-------:|
|
52 |
+
| 2.4434 | 0.75 | 100 | 1.9136 | 2.1212 | 0.4054 | 5.2222 | 18.9802 |
|
53 |
+
| 2.1367 | 1.49 | 200 | 1.8314 | 2.2656 | 0.4192 | 5.406 | 18.9969 |
|
54 |
+
| 2.0682 | 2.24 | 300 | 1.8232 | 2.2491 | 0.422 | 5.3241 | 18.9982 |
|
55 |
+
| 2.0331 | 2.99 | 400 | 1.7910 | 2.3106 | 0.4271 | 5.4092 | 18.999 |
|
56 |
+
| 1.9952 | 3.73 | 500 | 1.7794 | 2.2826 | 0.4217 | 5.4027 | 18.9992 |
|
57 |
+
| 1.9603 | 4.48 | 600 | 1.7714 | 2.3004 | 0.4245 | 5.4066 | 18.9994 |
|
58 |
+
| 1.9473 | 5.22 | 700 | 1.7633 | 2.3693 | 0.4321 | 5.4749 | 18.9996 |
|
59 |
+
| 1.9293 | 5.97 | 800 | 1.7619 | 2.2834 | 0.4222 | 5.3942 | 18.9997 |
|
60 |
+
| 1.9092 | 6.72 | 900 | 1.7556 | 2.3342 | 0.4263 | 5.4603 | 18.9999 |
|
61 |
+
| 1.8954 | 7.46 | 1000 | 1.7560 | 2.3196 | 0.4262 | 5.4271 | 18.9994 |
|
62 |
+
| 1.886 | 8.21 | 1100 | 1.7389 | 2.3588 | 0.4307 | 5.4604 | 18.9996 |
|
63 |
+
| 1.8532 | 8.96 | 1200 | 1.7499 | 2.3351 | 0.4279 | 5.4403 | 18.9998 |
|
64 |
+
| 1.8496 | 9.7 | 1300 | 1.7390 | 2.3407 | 0.4267 | 5.4666 | 18.9996 |
|
65 |
+
| 1.8309 | 10.45 | 1400 | 1.7436 | 2.337 | 0.4281 | 5.4377 | 18.9992 |
|
66 |
+
| 1.8208 | 11.19 | 1500 | 1.7375 | 2.3605 | 0.4292 | 5.4822 | 18.9997 |
|
67 |
+
| 1.8082 | 11.94 | 1600 | 1.7390 | 2.3582 | 0.4303 | 5.46 | 18.9993 |
|
68 |
+
| 1.805 | 12.69 | 1700 | 1.7340 | 2.3422 | 0.4261 | 5.4786 | 18.9996 |
|
69 |
+
| 1.7704 | 13.43 | 1800 | 1.7448 | 2.351 | 0.428 | 5.4723 | 18.9996 |
|
70 |
+
| 1.7868 | 14.18 | 1900 | 1.7367 | 2.3787 | 0.4303 | 5.5085 | 18.9996 |
|
71 |
+
| 1.7693 | 14.93 | 2000 | 1.7445 | 2.3526 | 0.4292 | 5.4647 | 18.9992 |
|
72 |
+
| 1.7541 | 15.67 | 2100 | 1.7391 | 2.3799 | 0.4314 | 5.5012 | 18.9996 |
|
73 |
+
| 1.7465 | 16.42 | 2200 | 1.7475 | 2.3556 | 0.4281 | 5.4835 | 18.9991 |
|
74 |
+
|
75 |
+
|
76 |
+
### Framework versions
|
77 |
+
|
78 |
+
- Transformers 4.18.0
|
79 |
+
- Pytorch 1.10.0+cu111
|
80 |
+
- Datasets 2.5.1
|
81 |
+
- Tokenizers 0.12.1
|