version 1
Browse files
README.md
ADDED
@@ -0,0 +1,93 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: facebook/bart-large
|
4 |
+
tags:
|
5 |
+
- text2text-generation
|
6 |
+
- generated_from_trainer
|
7 |
+
metrics:
|
8 |
+
- sacrebleu
|
9 |
+
model-index:
|
10 |
+
- name: model_v3
|
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 |
+
# model_v3
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [facebook/bart-large](https://huggingface.co/facebook/bart-large) on the None dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 1.0664
|
22 |
+
- Sacrebleu: 66.6476
|
23 |
+
|
24 |
+
## Model description
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Intended uses & limitations
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training and evaluation data
|
33 |
+
|
34 |
+
More information needed
|
35 |
+
|
36 |
+
## Training procedure
|
37 |
+
|
38 |
+
### Training hyperparameters
|
39 |
+
|
40 |
+
The following hyperparameters were used during training:
|
41 |
+
- learning_rate: 2e-05
|
42 |
+
- train_batch_size: 16
|
43 |
+
- eval_batch_size: 16
|
44 |
+
- seed: 42
|
45 |
+
- gradient_accumulation_steps: 4
|
46 |
+
- total_train_batch_size: 64
|
47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
48 |
+
- lr_scheduler_type: linear
|
49 |
+
- num_epochs: 30
|
50 |
+
- mixed_precision_training: Native AMP
|
51 |
+
|
52 |
+
### Training results
|
53 |
+
|
54 |
+
| Training Loss | Epoch | Step | Validation Loss | Sacrebleu |
|
55 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|
|
56 |
+
| No log | 1.0 | 218 | 0.5750 | 66.6584 |
|
57 |
+
| No log | 2.0 | 437 | 0.5581 | 66.9419 |
|
58 |
+
| No log | 3.0 | 656 | 0.5662 | 66.8166 |
|
59 |
+
| No log | 4.0 | 875 | 0.6339 | 66.8911 |
|
60 |
+
| No log | 5.0 | 1093 | 0.6190 | 66.4260 |
|
61 |
+
| No log | 6.0 | 1312 | 0.6760 | 66.7698 |
|
62 |
+
| No log | 7.0 | 1531 | 0.6708 | 66.7328 |
|
63 |
+
| No log | 8.0 | 1750 | 0.7686 | 66.6153 |
|
64 |
+
| No log | 9.0 | 1968 | 0.7157 | 66.7670 |
|
65 |
+
| No log | 10.0 | 2187 | 0.7567 | 66.6510 |
|
66 |
+
| No log | 11.0 | 2406 | 0.7699 | 66.5710 |
|
67 |
+
| No log | 12.0 | 2625 | 0.8145 | 66.7658 |
|
68 |
+
| No log | 13.0 | 2843 | 0.8292 | 66.4557 |
|
69 |
+
| No log | 14.0 | 3062 | 0.8610 | 66.7477 |
|
70 |
+
| No log | 15.0 | 3281 | 0.8962 | 66.4487 |
|
71 |
+
| No log | 16.0 | 3500 | 0.9000 | 66.6798 |
|
72 |
+
| No log | 17.0 | 3718 | 0.9376 | 66.5672 |
|
73 |
+
| No log | 18.0 | 3937 | 0.8907 | 66.6538 |
|
74 |
+
| No log | 19.0 | 4156 | 0.8829 | 66.5278 |
|
75 |
+
| No log | 20.0 | 4375 | 0.9925 | 66.5495 |
|
76 |
+
| No log | 21.0 | 4593 | 0.9656 | 66.5410 |
|
77 |
+
| No log | 22.0 | 4812 | 0.9721 | 66.4741 |
|
78 |
+
| No log | 23.0 | 5031 | 0.9778 | 66.6736 |
|
79 |
+
| No log | 24.0 | 5250 | 1.0032 | 66.5801 |
|
80 |
+
| No log | 25.0 | 5468 | 1.0808 | 66.6122 |
|
81 |
+
| No log | 26.0 | 5687 | 1.0403 | 66.7292 |
|
82 |
+
| No log | 27.0 | 5906 | 1.0388 | 66.5946 |
|
83 |
+
| No log | 28.0 | 6125 | 1.0707 | 66.6240 |
|
84 |
+
| No log | 29.0 | 6343 | 1.0356 | 66.7184 |
|
85 |
+
| No log | 29.9 | 6540 | 1.0664 | 66.6476 |
|
86 |
+
|
87 |
+
|
88 |
+
### Framework versions
|
89 |
+
|
90 |
+
- Transformers 4.39.3
|
91 |
+
- Pytorch 2.1.2
|
92 |
+
- Datasets 2.18.0
|
93 |
+
- Tokenizers 0.15.2
|
generation_config.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 0,
|
3 |
+
"decoder_start_token_id": 2,
|
4 |
+
"early_stopping": true,
|
5 |
+
"eos_token_id": 2,
|
6 |
+
"forced_bos_token_id": 0,
|
7 |
+
"forced_eos_token_id": 2,
|
8 |
+
"no_repeat_ngram_size": 3,
|
9 |
+
"num_beams": 4,
|
10 |
+
"pad_token_id": 1,
|
11 |
+
"transformers_version": "4.39.3"
|
12 |
+
}
|
runs/May25_20-07-09_ed6880e0c837/events.out.tfevents.1716692349.ed6880e0c837.23.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f9d7813e52a66a2da0dcb748e639cd709f4f31ebab9dabe4c022b940d698ca3
|
3 |
+
size 412
|