cleblainclb commited on
Commit
971f9bf
1 Parent(s): 16216ab

Training complete

Browse files
Files changed (3) hide show
  1. README.md +83 -0
  2. generation_config.json +6 -0
  3. pytorch_model.bin +1 -1
README.md ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: google/mt5-small
4
+ tags:
5
+ - summarization
6
+ - generated_from_trainer
7
+ datasets:
8
+ - mlsum
9
+ metrics:
10
+ - rouge
11
+ model-index:
12
+ - name: mt5-small-finetuned-mlsum
13
+ results:
14
+ - task:
15
+ name: Sequence-to-sequence Language Modeling
16
+ type: text2text-generation
17
+ dataset:
18
+ name: mlsum
19
+ type: mlsum
20
+ config: fr
21
+ split: validation
22
+ args: fr
23
+ metrics:
24
+ - name: Rouge1
25
+ type: rouge
26
+ value: 23.8523
27
+ ---
28
+
29
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
30
+ should probably proofread and complete it, then remove this comment. -->
31
+
32
+ # mt5-small-finetuned-mlsum
33
+
34
+ This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on the mlsum dataset.
35
+ It achieves the following results on the evaluation set:
36
+ - Loss: 2.1938
37
+ - Rouge1: 23.8523
38
+ - Rouge2: 11.7959
39
+ - Rougel: 21.1838
40
+ - Rougelsum: 21.2463
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: 5.6e-05
60
+ - train_batch_size: 8
61
+ - eval_batch_size: 8
62
+ - seed: 42
63
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
64
+ - lr_scheduler_type: linear
65
+ - num_epochs: 5
66
+
67
+ ### Training results
68
+
69
+ | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
70
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|
71
+ | 5.6087 | 1.0 | 1005 | 2.4269 | 29.6042 | 15.5378 | 25.5964 | 25.6503 |
72
+ | 3.4099 | 2.0 | 2010 | 2.2734 | 23.8963 | 12.2351 | 21.4806 | 21.4861 |
73
+ | 3.169 | 3.0 | 3015 | 2.2310 | 26.7408 | 13.7129 | 23.7543 | 23.8443 |
74
+ | 3.0327 | 4.0 | 4020 | 2.2084 | 23.2971 | 11.5675 | 20.911 | 21.0564 |
75
+ | 2.9777 | 5.0 | 5025 | 2.1938 | 23.8523 | 11.7959 | 21.1838 | 21.2463 |
76
+
77
+
78
+ ### Framework versions
79
+
80
+ - Transformers 4.34.0
81
+ - Pytorch 2.0.1+cu118
82
+ - Datasets 2.14.5
83
+ - Tokenizers 0.14.1
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "decoder_start_token_id": 0,
3
+ "eos_token_id": 1,
4
+ "pad_token_id": 0,
5
+ "transformers_version": "4.34.0"
6
+ }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c733b9954fe74d2e4345ef783f09ff3e186f724479659c2f655ad439efe087d0
3
  size 1200772613
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fb17b050d2637b51f646289063e1120ac0bc3a97d6468d193451e1462fcab85
3
  size 1200772613