Hugging Face's logo

Samuael
/
geez_15k_sc_mt5

Transformers
TensorBoard
Safetensors
t5
text2text-generation
Generated from Trainer
text-generation-inference
Model card Files
xet
 Metrics Community
Samuael commited on
Commit
70c8e6f
·
verified ·
1 Parent(s): 53192ee

End of training

Browse files
Files changed (4) hide show
  1. README.md +45 -12
  2. model.safetensors +1 -1
  3. runs/Mar28_17-38-08_755793c9d493/events.out.tfevents.1711647547.755793c9d493.297.0 +3 -0
  4. training_args.bin +1 -1
README.md CHANGED
@@ -2,6 +2,9 @@
2
  base_model: Samuael/geez_15k_sc_mt5
3
  tags:
4
  - generated_from_trainer
 
 
 
5
  model-index:
6
  - name: geez_15k_sc_mt5
7
  results: []
@@ -14,15 +17,10 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [Samuael/geez_15k_sc_mt5](https://huggingface.co/Samuael/geez_15k_sc_mt5) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
- - eval_loss: 0.7308
18
- - eval_wer: 0.2779
19
- - eval_cer: 0.1107
20
- - eval_bleu: 63.3138
21
- - eval_runtime: 270.773
22
- - eval_samples_per_second: 4.399
23
- - eval_steps_per_second: 0.037
24
- - epoch: 30.0
25
- - step: 46620
26
 
27
  ## Model description
28
 
@@ -42,13 +40,48 @@ More information needed
42
 
43
  The following hyperparameters were used during training:
44
  - learning_rate: 0.0002
45
- - train_batch_size: 32
46
  - eval_batch_size: 128
47
  - seed: 42
48
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
  - lr_scheduler_type: linear
50
- - num_epochs: 60
51
- - mixed_precision_training: Native AMP
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
52
 
53
  ### Framework versions
54
 
 
2
  base_model: Samuael/geez_15k_sc_mt5
3
  tags:
4
  - generated_from_trainer
5
+ metrics:
6
+ - wer
7
+ - bleu
8
  model-index:
9
  - name: geez_15k_sc_mt5
10
  results: []
 
17
 
18
  This model is a fine-tuned version of [Samuael/geez_15k_sc_mt5](https://huggingface.co/Samuael/geez_15k_sc_mt5) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.8105
21
+ - Wer: 0.2849
22
+ - Cer: 0.1373
23
+ - Bleu: 57.6756
 
 
 
 
 
24
 
25
  ## Model description
26
 
 
40
 
41
  The following hyperparameters were used during training:
42
  - learning_rate: 0.0002
43
+ - train_batch_size: 128
44
  - eval_batch_size: 128
45
  - seed: 42
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
+ - num_epochs: 30
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss | Wer | Cer | Bleu |
53
+ |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:-------:|
54
+ | 0.9418 | 1.0 | 57 | 0.8984 | 0.4204 | 0.1872 | 42.5936 |
55
+ | 0.6386 | 2.0 | 114 | 0.6856 | 0.3535 | 0.1563 | 48.7013 |
56
+ | 0.6169 | 3.0 | 171 | 0.6101 | 0.3137 | 0.1256 | 52.0856 |
57
+ | 0.428 | 4.0 | 228 | 0.5921 | 0.3125 | 0.1365 | 53.1328 |
58
+ | 0.354 | 5.0 | 285 | 0.5692 | 0.2807 | 0.1096 | 55.5660 |
59
+ | 0.2604 | 6.0 | 342 | 0.5947 | 0.2818 | 0.1098 | 55.6749 |
60
+ | 0.2797 | 7.0 | 399 | 0.5874 | 0.2896 | 0.1203 | 55.5685 |
61
+ | 0.2372 | 8.0 | 456 | 0.5978 | 0.2829 | 0.1206 | 56.3162 |
62
+ | 0.1863 | 9.0 | 513 | 0.6046 | 0.2808 | 0.1188 | 56.7817 |
63
+ | 0.1595 | 10.0 | 570 | 0.6295 | 0.2615 | 0.1006 | 58.1387 |
64
+ | 0.1269 | 11.0 | 627 | 0.6548 | 0.2721 | 0.1157 | 57.4783 |
65
+ | 0.1421 | 12.0 | 684 | 0.6572 | 0.2734 | 0.1164 | 57.7264 |
66
+ | 0.1475 | 13.0 | 741 | 0.6673 | 0.2809 | 0.1204 | 57.1626 |
67
+ | 0.1201 | 14.0 | 798 | 0.6996 | 0.2835 | 0.1271 | 57.0274 |
68
+ | 0.0777 | 15.0 | 855 | 0.7227 | 0.2634 | 0.1071 | 58.3844 |
69
+ | 0.075 | 16.0 | 912 | 0.7295 | 0.2607 | 0.1050 | 58.7280 |
70
+ | 0.092 | 17.0 | 969 | 0.7404 | 0.2633 | 0.1062 | 58.7387 |
71
+ | 0.0795 | 18.0 | 1026 | 0.7437 | 0.2842 | 0.1297 | 57.4888 |
72
+ | 0.0933 | 19.0 | 1083 | 0.7513 | 0.2765 | 0.1207 | 57.8567 |
73
+ | 0.0794 | 20.0 | 1140 | 0.7620 | 0.2718 | 0.1165 | 58.1063 |
74
+ | 0.0559 | 21.0 | 1197 | 0.7543 | 0.2526 | 0.0999 | 59.4966 |
75
+ | 0.0616 | 22.0 | 1254 | 0.7885 | 0.2664 | 0.1126 | 58.7126 |
76
+ | 0.0666 | 23.0 | 1311 | 0.7734 | 0.2774 | 0.1215 | 57.7048 |
77
+ | 0.0746 | 24.0 | 1368 | 0.7832 | 0.2764 | 0.1225 | 58.0553 |
78
+ | 0.0644 | 25.0 | 1425 | 0.7872 | 0.2799 | 0.1273 | 57.9207 |
79
+ | 0.0596 | 26.0 | 1482 | 0.8184 | 0.2721 | 0.1197 | 58.1888 |
80
+ | 0.0507 | 27.0 | 1539 | 0.8053 | 0.2765 | 0.1226 | 58.1358 |
81
+ | 0.0585 | 28.0 | 1596 | 0.8091 | 0.2806 | 0.1293 | 57.9993 |
82
+ | 0.0595 | 29.0 | 1653 | 0.8147 | 0.2888 | 0.1416 | 57.4399 |
83
+ | 0.0469 | 30.0 | 1710 | 0.8105 | 0.2849 | 0.1373 | 57.6756 |
84
+
85
 
86
  ### Framework versions
87
 
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a652ff25a20812c0899dd3a16a78178f3d44631c413c042447863699852f690
3
  size 291090192
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b22914ac4c987d33a4938f5e835871d330d70e4fa3473056c56c376bed879441
3
  size 291090192
runs/Mar28_17-38-08_755793c9d493/events.out.tfevents.1711647547.755793c9d493.297.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49ef7d6601102cf6e82598be71bee4b1f21800505f5f9d05be94376d486026c3
3
+ size 377853
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:595b84e92896d7496ae2523258f15aff4c30b58338c110f2bf0620156fc16c16
3
  size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:180cf9a50e3f135a57f77e5beb852dababe2f91db2d7428a718fcbbb02f65d0b
3
  size 5048