update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
datasets:
|
5 |
+
- coco
|
6 |
+
metrics:
|
7 |
+
- rouge
|
8 |
+
- bleu
|
9 |
+
model-index:
|
10 |
+
- name: IC_ver6d_coco_swin_gpt2_50Bpc_1e
|
11 |
+
results: []
|
12 |
+
---
|
13 |
+
|
14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
+
should probably proofread and complete it, then remove this comment. -->
|
16 |
+
|
17 |
+
# IC_ver6d_coco_swin_gpt2_50Bpc_1e
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [VK246/IC_ver6c_coco_swin_gpt2_50Apc_1e](https://huggingface.co/VK246/IC_ver6c_coco_swin_gpt2_50Apc_1e) on the coco dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.7897
|
22 |
+
- Rouge1: 42.1846
|
23 |
+
- Rouge2: 16.6343
|
24 |
+
- Rougel: 38.2927
|
25 |
+
- Rougelsum: 38.2913
|
26 |
+
- Bleu: 10.4949
|
27 |
+
- Gen Len: 11.3063
|
28 |
+
|
29 |
+
## Model description
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Intended uses & limitations
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training and evaluation data
|
38 |
+
|
39 |
+
More information needed
|
40 |
+
|
41 |
+
## Training procedure
|
42 |
+
|
43 |
+
### Training hyperparameters
|
44 |
+
|
45 |
+
The following hyperparameters were used during training:
|
46 |
+
- learning_rate: 5e-05
|
47 |
+
- train_batch_size: 96
|
48 |
+
- eval_batch_size: 96
|
49 |
+
- seed: 42
|
50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
+
- lr_scheduler_type: linear
|
52 |
+
- num_epochs: 1
|
53 |
+
|
54 |
+
### Training results
|
55 |
+
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Bleu | Gen Len |
|
57 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|:-------:|
|
58 |
+
| 0.7741 | 0.17 | 500 | 0.8245 | 40.8216 | 15.539 | 37.1564 | 37.1436 | 9.6536 | 11.3063 |
|
59 |
+
| 0.7813 | 0.34 | 1000 | 0.8155 | 41.2707 | 15.9841 | 37.4357 | 37.4254 | 10.033 | 11.3063 |
|
60 |
+
| 0.782 | 0.51 | 1500 | 0.8061 | 41.6066 | 16.0222 | 37.802 | 37.8009 | 9.9619 | 11.3063 |
|
61 |
+
| 0.79 | 0.68 | 2000 | 0.7985 | 41.6881 | 16.2489 | 37.9303 | 37.9178 | 10.3074 | 11.3063 |
|
62 |
+
| 0.7888 | 0.85 | 2500 | 0.7929 | 42.1145 | 16.5388 | 38.2401 | 38.2324 | 10.3546 | 11.3063 |
|
63 |
+
|
64 |
+
|
65 |
+
### Framework versions
|
66 |
+
|
67 |
+
- Transformers 4.30.2
|
68 |
+
- Pytorch 2.0.1+cu118
|
69 |
+
- Datasets 2.13.1
|
70 |
+
- Tokenizers 0.13.3
|