Hugging Face's logo

tlam25
/
bart_finetuned_clarify_aspects

Transformers
Safetensors
bart
text2text-generation
Generated from Trainer
Model card Files
xet
 Community
tlam25 commited on
Commit
6e7afd1
·
verified ·
1 Parent(s): 8965f00

End of training

Browse files
Files changed (3) hide show
  1. README.md +90 -0
  2. generation_config.json +12 -0
  3. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ - bleu
9
+ - rouge
10
+ model-index:
11
+ - name: bart_finetuned_clarify_aspects
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_finetuned_clarify_aspects
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: 0.0560
23
+ - Micro Precision: 0.2712
24
+ - Micro Recall: 0.0166
25
+ - Micro F1: 0.0314
26
+ - Macro Precision: 0.2494
27
+ - Macro Recall: 0.0151
28
+ - Macro F1: 0.0286
29
+ - Bleu: 0.8548
30
+ - Rouge1: 0.8182
31
+ - Rouge2: 0.5295
32
+
33
+ ## Model description
34
+
35
+ More information needed
36
+
37
+ ## Intended uses & limitations
38
+
39
+ More information needed
40
+
41
+ ## Training and evaluation data
42
+
43
+ More information needed
44
+
45
+ ## Training procedure
46
+
47
+ ### Training hyperparameters
48
+
49
+ The following hyperparameters were used during training:
50
+ - learning_rate: 2e-05
51
+ - train_batch_size: 16
52
+ - eval_batch_size: 16
53
+ - seed: 42
54
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
55
+ - lr_scheduler_type: linear
56
+ - num_epochs: 5
57
+ - mixed_precision_training: Native AMP
58
+
59
+ ### Training results
60
+
61
+ | Training Loss | Epoch | Step | Validation Loss | Micro Precision | Micro Recall | Micro F1 | Macro Precision | Macro Recall | Macro F1 | Bleu | Rouge1 | Rouge2 |
62
+ |:-------------:|:------:|:----:|:---------------:|:---------------:|:------------:|:--------:|:---------------:|:------------:|:--------:|:------:|:------:|:------:|
63
+ | 4.8047 | 0.2404 | 50 | 2.1142 | 0.1822 | 0.1342 | 0.1546 | 0.0875 | 0.1550 | 0.1119 | 0.6817 | 0.7401 | 0.4214 |
64
+ | 1.7947 | 0.4808 | 100 | 0.8958 | 0.1842 | 0.1384 | 0.1581 | 0.0894 | 0.1631 | 0.1155 | 0.6860 | 0.7497 | 0.4381 |
65
+ | 0.73 | 0.7212 | 150 | 0.2402 | 0.2192 | 0.0926 | 0.1302 | 0.1109 | 0.0917 | 0.1004 | 0.7091 | 0.7104 | 0.4484 |
66
+ | 0.2199 | 0.9615 | 200 | 0.0950 | 0.2541 | 0.0812 | 0.1230 | 0.3683 | 0.0905 | 0.1453 | 0.7935 | 0.7738 | 0.4546 |
67
+ | 0.1005 | 1.2019 | 250 | 0.0699 | 0.2076 | 0.1301 | 0.1599 | 0.3421 | 0.1252 | 0.1833 | 0.7582 | 0.7771 | 0.4545 |
68
+ | 0.0814 | 1.4423 | 300 | 0.0749 | 0.1780 | 0.0489 | 0.0767 | 0.1226 | 0.0424 | 0.0630 | 0.8222 | 0.7919 | 0.4567 |
69
+ | 0.075 | 1.6827 | 350 | 0.0682 | 0.2887 | 0.0583 | 0.0970 | 0.1443 | 0.0479 | 0.0719 | 0.8457 | 0.8202 | 0.4470 |
70
+ | 0.08 | 1.9231 | 400 | 0.0684 | 0.2475 | 0.1030 | 0.1455 | 0.2260 | 0.1003 | 0.1389 | 0.7753 | 0.7881 | 0.4973 |
71
+ | 0.0712 | 2.1635 | 450 | 0.0682 | 0.3091 | 0.0177 | 0.0335 | 0.2298 | 0.0155 | 0.0290 | 0.8510 | 0.7965 | 0.4711 |
72
+ | 0.0706 | 2.4038 | 500 | 0.0632 | 0.2785 | 0.0229 | 0.0423 | 0.2545 | 0.0202 | 0.0374 | 0.8552 | 0.8226 | 0.5135 |
73
+ | 0.0677 | 2.6442 | 550 | 0.0642 | 0.1935 | 0.0062 | 0.0121 | 0.1913 | 0.0055 | 0.0106 | 0.8513 | 0.8066 | 0.4972 |
74
+ | 0.0664 | 2.8846 | 600 | 0.0604 | 0.3846 | 0.0052 | 0.0103 | 0.4167 | 0.0050 | 0.0098 | 0.8547 | 0.8158 | 0.5237 |
75
+ | 0.0657 | 3.125 | 650 | 0.0613 | 0.3049 | 0.0260 | 0.0479 | 0.3263 | 0.0253 | 0.0470 | 0.8587 | 0.8306 | 0.5354 |
76
+ | 0.0634 | 3.3654 | 700 | 0.0608 | 0.2143 | 0.0062 | 0.0121 | 0.2210 | 0.0065 | 0.0127 | 0.8520 | 0.8096 | 0.5077 |
77
+ | 0.0627 | 3.6058 | 750 | 0.0568 | 0.36 | 0.0187 | 0.0356 | 0.3508 | 0.0166 | 0.0316 | 0.8467 | 0.8108 | 0.5133 |
78
+ | 0.0595 | 3.8462 | 800 | 0.0572 | 0.25 | 0.0010 | 0.0021 | 0.125 | 0.0007 | 0.0014 | 0.8508 | 0.8192 | 0.5214 |
79
+ | 0.0603 | 4.0865 | 850 | 0.0562 | 0.2462 | 0.0166 | 0.0312 | 0.2447 | 0.0160 | 0.0300 | 0.8530 | 0.8165 | 0.5251 |
80
+ | 0.0589 | 4.3269 | 900 | 0.0565 | 0.2222 | 0.0083 | 0.0160 | 0.3 | 0.0089 | 0.0172 | 0.8563 | 0.8184 | 0.5265 |
81
+ | 0.06 | 4.5673 | 950 | 0.0565 | 0.2807 | 0.0166 | 0.0314 | 0.2892 | 0.0160 | 0.0303 | 0.8561 | 0.8161 | 0.5287 |
82
+ | 0.0614 | 4.8077 | 1000 | 0.0560 | 0.2712 | 0.0166 | 0.0314 | 0.2494 | 0.0151 | 0.0286 | 0.8548 | 0.8182 | 0.5295 |
83
+
84
+
85
+ ### Framework versions
86
+
87
+ - Transformers 4.51.1
88
+ - Pytorch 2.5.1+cu124
89
+ - Datasets 3.5.0
90
+ - Tokenizers 0.21.0
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": "4.51.1"
12
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:02330601b5029481eef04affcff7cc7d2f006462d24cb64e5799488e6a677e3f
3
  size 557912620
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f90b756e8e87588bf3bc1df36f46665f0392482ce6e45068c78adf09ee25070d
3
  size 557912620