nandavikas16
commited on
Commit
•
7c22a1b
1
Parent(s):
c61bb12
Model save
Browse files
README.md
ADDED
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: google/pegasus-cnn_dailymail
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- rouge
|
7 |
+
model-index:
|
8 |
+
- name: pegasus-cnn_dailymail-finetuned-scope-summarization
|
9 |
+
results: []
|
10 |
+
---
|
11 |
+
|
12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
+
should probably proofread and complete it, then remove this comment. -->
|
14 |
+
|
15 |
+
# pegasus-cnn_dailymail-finetuned-scope-summarization
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [google/pegasus-cnn_dailymail](https://huggingface.co/google/pegasus-cnn_dailymail) on an unknown dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.1923
|
20 |
+
- Rouge1: 56.9116
|
21 |
+
- Rouge2: 45.4236
|
22 |
+
- Rougel: 49.8645
|
23 |
+
- Rougelsum: 49.71
|
24 |
+
|
25 |
+
## Model description
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Intended uses & limitations
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training and evaluation data
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training procedure
|
38 |
+
|
39 |
+
### Training hyperparameters
|
40 |
+
|
41 |
+
The following hyperparameters were used during training:
|
42 |
+
- learning_rate: 5.6e-05
|
43 |
+
- train_batch_size: 2
|
44 |
+
- eval_batch_size: 2
|
45 |
+
- seed: 42
|
46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
+
- lr_scheduler_type: linear
|
48 |
+
- num_epochs: 20
|
49 |
+
|
50 |
+
### Training results
|
51 |
+
|
52 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|
53 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|
|
54 |
+
| 0.5864 | 1.0 | 158 | 0.3056 | 41.1501 | 21.8098 | 34.2505 | 34.2057 |
|
55 |
+
| 0.3517 | 2.0 | 316 | 0.2787 | 45.9535 | 26.9084 | 37.7287 | 37.7213 |
|
56 |
+
| 0.2835 | 3.0 | 474 | 0.2655 | 49.4653 | 30.6584 | 40.5201 | 40.4494 |
|
57 |
+
| 0.2683 | 4.0 | 632 | 0.2528 | 50.2066 | 32.8862 | 40.4058 | 40.2244 |
|
58 |
+
| 0.2557 | 5.0 | 790 | 0.2469 | 50.3451 | 33.536 | 41.7433 | 41.6118 |
|
59 |
+
| 0.2493 | 6.0 | 948 | 0.2382 | 51.9053 | 36.1533 | 42.0343 | 41.8884 |
|
60 |
+
| 0.2406 | 7.0 | 1106 | 0.2330 | 53.2105 | 38.1 | 43.434 | 43.2194 |
|
61 |
+
| 0.235 | 8.0 | 1264 | 0.2267 | 51.9642 | 38.1903 | 44.4502 | 44.3851 |
|
62 |
+
| 0.2296 | 9.0 | 1422 | 0.2237 | 53.5609 | 38.9875 | 44.7145 | 44.6146 |
|
63 |
+
| 0.2246 | 10.0 | 1580 | 0.2195 | 54.6691 | 41.5464 | 45.7506 | 45.6856 |
|
64 |
+
| 0.221 | 11.0 | 1738 | 0.2141 | 54.4114 | 41.2748 | 45.9992 | 45.8182 |
|
65 |
+
| 0.2145 | 12.0 | 1896 | 0.2097 | 55.3852 | 42.9342 | 48.376 | 48.5267 |
|
66 |
+
| 0.2115 | 13.0 | 2054 | 0.2060 | 55.9251 | 43.4806 | 48.0303 | 47.9584 |
|
67 |
+
| 0.2081 | 14.0 | 2212 | 0.2017 | 55.8426 | 43.1239 | 47.8006 | 47.8356 |
|
68 |
+
| 0.2042 | 15.0 | 2370 | 0.1997 | 55.4631 | 42.78 | 47.307 | 47.3142 |
|
69 |
+
| 0.2031 | 16.0 | 2528 | 0.1970 | 57.0004 | 44.4252 | 49.6236 | 49.5213 |
|
70 |
+
| 0.1996 | 17.0 | 2686 | 0.1953 | 55.438 | 43.8797 | 48.536 | 48.3506 |
|
71 |
+
| 0.1991 | 18.0 | 2844 | 0.1939 | 56.1102 | 44.5176 | 48.5553 | 48.4163 |
|
72 |
+
| 0.1963 | 19.0 | 3002 | 0.1925 | 56.6366 | 45.3753 | 49.4421 | 49.3468 |
|
73 |
+
| 0.1955 | 20.0 | 3160 | 0.1923 | 56.9116 | 45.4236 | 49.8645 | 49.71 |
|
74 |
+
|
75 |
+
|
76 |
+
### Framework versions
|
77 |
+
|
78 |
+
- Transformers 4.40.1
|
79 |
+
- Pytorch 2.3.0+cu121
|
80 |
+
- Datasets 2.19.0
|
81 |
+
- Tokenizers 0.19.1
|
generation_config.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 0,
|
3 |
+
"decoder_start_token_id": 0,
|
4 |
+
"eos_token_id": 1,
|
5 |
+
"forced_eos_token_id": 1,
|
6 |
+
"length_penalty": 0.8,
|
7 |
+
"max_length": 128,
|
8 |
+
"min_length": 32,
|
9 |
+
"num_beams": 8,
|
10 |
+
"pad_token_id": 0,
|
11 |
+
"transformers_version": "4.40.1",
|
12 |
+
"use_cache": false
|
13 |
+
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2283652852
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ced80faae95b960ff680b35614a34c5071f710a802262f5856052a2f1402df6b
|
3 |
size 2283652852
|
runs/May01_18-59-09_n62771a8wg/events.out.tfevents.1714589956.n62771a8wg.607.0
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 sha256:36d359dd4a001a54b969e29d98982160716dac98676838f26f23cd3924c16365
|
3 |
+
size 19635
|
runs/May01_18-59-09_n62771a8wg/events.out.tfevents.1714597211.n62771a8wg.607.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b38c89adf34a5132ef1e39f82552c267d241f95b09fa2e0156e323568c3c3c7f
|
3 |
+
size 514
|