Buseak commited on
Commit
e16bbb0
·
1 Parent(s): ca08054

End of training

Browse files
Files changed (2) hide show
  1. README.md +75 -0
  2. generation_config.json +6 -0
README.md ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: Buseak/md_mt5_0109
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - bleu
8
+ model-index:
9
+ - name: md_mt5_0109_v2
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # md_mt5_0109_v2
17
+
18
+ This model is a fine-tuned version of [Buseak/md_mt5_0109](https://huggingface.co/Buseak/md_mt5_0109) on the None dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.2368
21
+ - Bleu: 0.5272
22
+ - Gen Len: 18.9267
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: 4
43
+ - eval_batch_size: 4
44
+ - seed: 42
45
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
+ - lr_scheduler_type: linear
47
+ - num_epochs: 15
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
52
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|:-------:|
53
+ | 0.8133 | 1.0 | 975 | 0.4559 | 0.4502 | 18.9192 |
54
+ | 0.7386 | 2.0 | 1950 | 0.4087 | 0.4689 | 18.9203 |
55
+ | 0.6826 | 3.0 | 2925 | 0.3751 | 0.4854 | 18.9244 |
56
+ | 0.6321 | 4.0 | 3900 | 0.3450 | 0.4959 | 18.9221 |
57
+ | 0.6062 | 5.0 | 4875 | 0.3235 | 0.4977 | 18.9187 |
58
+ | 0.5634 | 6.0 | 5850 | 0.3027 | 0.5123 | 18.9172 |
59
+ | 0.5361 | 7.0 | 6825 | 0.2874 | 0.5146 | 18.9259 |
60
+ | 0.5152 | 8.0 | 7800 | 0.2719 | 0.5211 | 18.9295 |
61
+ | 0.503 | 9.0 | 8775 | 0.2661 | 0.5222 | 18.9292 |
62
+ | 0.4868 | 10.0 | 9750 | 0.2550 | 0.5258 | 18.9277 |
63
+ | 0.4691 | 11.0 | 10725 | 0.2485 | 0.5263 | 18.9251 |
64
+ | 0.4672 | 12.0 | 11700 | 0.2432 | 0.526 | 18.9238 |
65
+ | 0.4607 | 13.0 | 12675 | 0.2394 | 0.5268 | 18.9259 |
66
+ | 0.4536 | 14.0 | 13650 | 0.2369 | 0.5272 | 18.9267 |
67
+ | 0.4499 | 15.0 | 14625 | 0.2368 | 0.5272 | 18.9267 |
68
+
69
+
70
+ ### Framework versions
71
+
72
+ - Transformers 4.35.2
73
+ - Pytorch 2.1.0+cu121
74
+ - Datasets 2.16.1
75
+ - Tokenizers 0.15.0
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": "4.35.2"
6
+ }