your_model_path
Browse files- README.md +74 -0
- generation_config.json +12 -0
README.md
ADDED
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
license: apache-2.0
|
4 |
+
base_model: facebook/bart-base
|
5 |
+
tags:
|
6 |
+
- generated_from_trainer
|
7 |
+
metrics:
|
8 |
+
- sacrebleu
|
9 |
+
- rouge
|
10 |
+
model-index:
|
11 |
+
- name: bart-base-finetuned-w-data-augm-4e-5
|
12 |
+
results: []
|
13 |
+
---
|
14 |
+
|
15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
16 |
+
should probably proofread and complete it, then remove this comment. -->
|
17 |
+
|
18 |
+
# bart-base-finetuned-w-data-augm-4e-5
|
19 |
+
|
20 |
+
This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the None dataset.
|
21 |
+
It achieves the following results on the evaluation set:
|
22 |
+
- Loss: 0.3985
|
23 |
+
- Sacrebleu: 89.8136
|
24 |
+
- Rouge1: 95.6369
|
25 |
+
- Rouge2: 91.8617
|
26 |
+
- Rougel: 94.6909
|
27 |
+
- Rougelsum: 94.6811
|
28 |
+
- Bertscore Precision: 0.9424
|
29 |
+
- Bertscore Recall: 0.9374
|
30 |
+
- Bertscore F1: 0.9399
|
31 |
+
|
32 |
+
## Model description
|
33 |
+
|
34 |
+
More information needed
|
35 |
+
|
36 |
+
## Intended uses & limitations
|
37 |
+
|
38 |
+
More information needed
|
39 |
+
|
40 |
+
## Training and evaluation data
|
41 |
+
|
42 |
+
More information needed
|
43 |
+
|
44 |
+
## Training procedure
|
45 |
+
|
46 |
+
### Training hyperparameters
|
47 |
+
|
48 |
+
The following hyperparameters were used during training:
|
49 |
+
- learning_rate: 4.4252514647201465e-05
|
50 |
+
- train_batch_size: 16
|
51 |
+
- eval_batch_size: 32
|
52 |
+
- seed: 42
|
53 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
54 |
+
- lr_scheduler_type: linear
|
55 |
+
- num_epochs: 5
|
56 |
+
- mixed_precision_training: Native AMP
|
57 |
+
|
58 |
+
### Training results
|
59 |
+
|
60 |
+
| Training Loss | Epoch | Step | Validation Loss | Sacrebleu | Rouge1 | Rouge2 | Rougel | Rougelsum | Bertscore Precision | Bertscore Recall | Bertscore F1 |
|
61 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:-------:|:-------:|:-------:|:---------:|:-------------------:|:----------------:|:------------:|
|
62 |
+
| 0.1107 | 1.0 | 761 | 0.2850 | 90.5237 | 96.15 | 92.6707 | 95.2684 | 95.2821 | 0.9487 | 0.9425 | 0.9456 |
|
63 |
+
| 0.0435 | 2.0 | 1522 | 0.2695 | 91.4933 | 96.4613 | 93.4149 | 95.6712 | 95.6642 | 0.9515 | 0.9522 | 0.9518 |
|
64 |
+
| 0.0421 | 3.0 | 2283 | 0.2579 | 91.4926 | 96.4713 | 93.2669 | 95.7036 | 95.7071 | 0.9522 | 0.9505 | 0.9513 |
|
65 |
+
| 0.0233 | 4.0 | 3044 | 0.2717 | 91.8243 | 96.6369 | 93.443 | 95.8509 | 95.8593 | 0.9537 | 0.9521 | 0.9529 |
|
66 |
+
| 0.0327 | 5.0 | 3805 | 0.2804 | 92.095 | 96.6849 | 93.7485 | 95.9279 | 95.9247 | 0.9551 | 0.9526 | 0.9538 |
|
67 |
+
|
68 |
+
|
69 |
+
### Framework versions
|
70 |
+
|
71 |
+
- Transformers 4.44.2
|
72 |
+
- Pytorch 2.4.0+cu121
|
73 |
+
- Datasets 2.21.0
|
74 |
+
- Tokenizers 0.19.1
|
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": "4.44.2"
|
12 |
+
}
|