HorikawaMegu commited on
Commit
1b8ba70
·
verified ·
1 Parent(s): a3fc1e9

HorikawaMegu/jfleg-mt5-small

Browse files
README.md ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ metrics:
5
+ - bleu
6
+ model-index:
7
+ - name: mt5-small
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # mt5-small
15
+
16
+ This model was trained from scratch on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 2.7308
19
+ - Bleu: 0.0181
20
+ - Gen Len: 27.656
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 2e-05
40
+ - train_batch_size: 8
41
+ - eval_batch_size: 8
42
+ - seed: 42
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - num_epochs: 6
46
+
47
+ ### Training results
48
+
49
+ | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
50
+ |:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|
51
+ | No log | 1.0 | 377 | 10.5974 | 0.0027 | 128.0 |
52
+ | 16.889 | 2.0 | 754 | 6.2000 | 0.0006 | 127.762 |
53
+ | 8.7035 | 3.0 | 1131 | 4.2664 | 0.0024 | 48.7383 |
54
+ | 5.0692 | 4.0 | 1508 | 3.3315 | 0.0103 | 30.2219 |
55
+ | 5.0692 | 5.0 | 1885 | 2.8775 | 0.0202 | 27.7363 |
56
+ | 3.7431 | 6.0 | 2262 | 2.7308 | 0.0181 | 27.656 |
57
+
58
+
59
+ ### Framework versions
60
+
61
+ - Transformers 4.40.0
62
+ - Pytorch 2.2.1+cu121
63
+ - Datasets 2.19.0
64
+ - Tokenizers 0.19.1
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.40.0"
7
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e5bdbc341cf66ff4cd6331d1f0ee69477488cb8d70ace266fd5e7d5c11fe0f25
3
  size 1200729512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e297ef68b556cf37b6c0d483168f4a268c1c72c5b47ae4af2c8a1c309aed9b34
3
  size 1200729512
runs/Apr22_19-16-16_89fd5c63729d/events.out.tfevents.1713813387.89fd5c63729d.2035.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e6ff9aeeee3ace9d7a770387713a6277fe681b2394853d6428f090690461452d
3
- size 7683
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91994bab6cf7899cdbc7dc08bd91263d2115e0d482a5143d4deff0d80a1badbf
3
+ size 8407