roofdancer commited on
Commit
c41f2f0
1 Parent(s): 91f9d37

End of training

Browse files
Files changed (3) hide show
  1. README.md +82 -0
  2. generation_config.json +15 -0
  3. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: sshleifer/distilbart-cnn-6-6
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - wcep-10
8
+ metrics:
9
+ - rouge
10
+ model-index:
11
+ - name: thesis-bart-finetuned-on-original-wcep
12
+ results:
13
+ - task:
14
+ name: Sequence-to-sequence Language Modeling
15
+ type: text2text-generation
16
+ dataset:
17
+ name: wcep-10
18
+ type: wcep-10
19
+ config: roberta
20
+ split: validation
21
+ args: roberta
22
+ metrics:
23
+ - name: Rouge1
24
+ type: rouge
25
+ value: 37.1938
26
+ ---
27
+
28
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
+ should probably proofread and complete it, then remove this comment. -->
30
+
31
+ # thesis-bart-finetuned-on-original-wcep
32
+
33
+ This model is a fine-tuned version of [sshleifer/distilbart-cnn-6-6](https://huggingface.co/sshleifer/distilbart-cnn-6-6) on the wcep-10 dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 1.9981
36
+ - Rouge1: 37.1938
37
+ - Rouge2: 16.5385
38
+ - Rougel: 26.7997
39
+ - Rougelsum: 30.3278
40
+ - Gen Len: 67.5627
41
+
42
+ ## Model description
43
+
44
+ More information needed
45
+
46
+ ## Intended uses & limitations
47
+
48
+ More information needed
49
+
50
+ ## Training and evaluation data
51
+
52
+ More information needed
53
+
54
+ ## Training procedure
55
+
56
+ ### Training hyperparameters
57
+
58
+ The following hyperparameters were used during training:
59
+ - learning_rate: 2e-05
60
+ - train_batch_size: 16
61
+ - eval_batch_size: 16
62
+ - seed: 42
63
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
64
+ - lr_scheduler_type: linear
65
+ - num_epochs: 3
66
+ - mixed_precision_training: Native AMP
67
+
68
+ ### Training results
69
+
70
+ | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
71
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
72
+ | 2.0801 | 1.0 | 510 | 2.0119 | 36.476 | 16.0059 | 26.3489 | 29.7099 | 67.9882 |
73
+ | 1.7597 | 2.0 | 1020 | 1.9868 | 36.9333 | 16.3738 | 26.5067 | 30.1156 | 68.3961 |
74
+ | 1.5997 | 3.0 | 1530 | 1.9981 | 37.1938 | 16.5385 | 26.7997 | 30.3278 | 67.5627 |
75
+
76
+
77
+ ### Framework versions
78
+
79
+ - Transformers 4.39.3
80
+ - Pytorch 2.1.2
81
+ - Datasets 2.18.0
82
+ - Tokenizers 0.15.2
generation_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "length_penalty": 2.0,
9
+ "max_length": 142,
10
+ "min_length": 56,
11
+ "no_repeat_ngram_size": 3,
12
+ "num_beams": 4,
13
+ "pad_token_id": 1,
14
+ "transformers_version": "4.39.3"
15
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:74f3752a38b08d64407a6f2818c18f1887ec352984f6f065fdf212d6b947f5eb
3
  size 919963552
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f276edbf6e28e08c23dcb6f12c2ee8e40083f18f061b572154efc3a9d4dddb1e
3
  size 919963552