Hugging Face's logo

Samuael
/
geez_t5-15k

Text2Text Generation
Transformers
TensorBoard
Safetensors
t5
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
Samuael commited on
Commit
7f00c59
•
1 Parent(s): 45a1f6f

End of training

Browse files
Files changed (4) hide show
  1. README.md +19 -19
  2. config.json +1 -1
  3. model.safetensors +1 -1
  4. runs/Apr02_11-01-11_5154d18eb907/events.out.tfevents.1712055683.5154d18eb907.465.0 +2 -2
README.md CHANGED
@@ -1,10 +1,10 @@
1
  ---
 
2
  tags:
3
  - generated_from_trainer
4
  metrics:
5
  - wer
6
  - bleu
7
- base_model: Samuael/geez_t5-15k
8
  model-index:
9
  - name: geez_t5-15k
10
  results: []
@@ -17,10 +17,10 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [Samuael/geez_t5-15k](https://huggingface.co/Samuael/geez_t5-15k) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 1.1428
21
- - Wer: 0.2368
22
- - Cer: 0.0611
23
- - Bleu: 59.1856
24
 
25
  ## Model description
26
 
@@ -39,9 +39,9 @@ More information needed
39
  ### Training hyperparameters
40
 
41
  The following hyperparameters were used during training:
42
- - learning_rate: 0.0001
43
  - train_batch_size: 64
44
- - eval_batch_size: 64
45
  - seed: 42
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
@@ -50,18 +50,18 @@ The following hyperparameters were used during training:
50
 
51
  ### Training results
52
 
53
- | Training Loss | Epoch | Step | Validation Loss | Wer | Cer | Bleu |
54
- |:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:-------:|
55
- | 0.1721 | 1.0 | 1421 | 1.0128 | 0.2445 | 0.0640 | 58.5313 |
56
- | 0.3157 | 2.0 | 2842 | 0.9088 | 0.2409 | 0.0625 | 59.1274 |
57
- | 0.1958 | 3.0 | 4263 | 0.9950 | 0.2474 | 0.0617 | 58.7017 |
58
- | 0.2275 | 4.0 | 5684 | 1.0075 | 0.2522 | 0.0638 | 58.2146 |
59
- | 0.1139 | 5.0 | 7105 | 1.0297 | 0.2411 | 0.0607 | 59.7241 |
60
- | 0.1243 | 6.0 | 8526 | 1.0343 | 0.2360 | 0.0608 | 59.9537 |
61
- | 0.18 | 7.0 | 9947 | 1.0373 | 0.2423 | 0.0617 | 59.0538 |
62
- | 0.1281 | 8.0 | 11368 | 1.1003 | 0.2344 | 0.0605 | 59.8118 |
63
- | 0.1276 | 9.0 | 12789 | 1.1061 | 0.2385 | 0.0611 | 59.1765 |
64
- | 0.1128 | 10.0 | 14210 | 1.1428 | 0.2368 | 0.0611 | 59.1856 |
65
 
66
 
67
  ### Framework versions
 
1
  ---
2
+ base_model: Samuael/geez_t5-15k
3
  tags:
4
  - generated_from_trainer
5
  metrics:
6
  - wer
7
  - bleu
 
8
  model-index:
9
  - name: geez_t5-15k
10
  results: []
 
17
 
18
  This model is a fine-tuned version of [Samuael/geez_t5-15k](https://huggingface.co/Samuael/geez_t5-15k) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.4822
21
+ - Wer: 0.2284
22
+ - Cer: 0.0780
23
+ - Bleu: 67.0096
24
 
25
  ## Model description
26
 
 
39
  ### Training hyperparameters
40
 
41
  The following hyperparameters were used during training:
42
+ - learning_rate: 0.0002
43
  - train_batch_size: 64
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
 
50
 
51
  ### Training results
52
 
53
+ | Training Loss | Epoch | Step | Validation Loss | Wer | Cer | Bleu |
54
+ |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:-------:|
55
+ | 0.2496 | 1.0 | 313 | 0.3291 | 0.2456 | 0.1077 | 67.2734 |
56
+ | 0.2573 | 2.0 | 626 | 0.3445 | 0.2488 | 0.1114 | 67.1612 |
57
+ | 0.2368 | 3.0 | 939 | 0.3483 | 0.2075 | 0.0698 | 69.4248 |
58
+ | 0.1459 | 4.0 | 1252 | 0.3815 | 0.2212 | 0.0806 | 68.5281 |
59
+ | 0.1552 | 5.0 | 1565 | 0.4081 | 0.2372 | 0.0934 | 66.8604 |
60
+ | 0.1031 | 6.0 | 1878 | 0.4143 | 0.2084 | 0.0692 | 69.6668 |
61
+ | 0.1067 | 7.0 | 2191 | 0.4325 | 0.2305 | 0.0853 | 67.3479 |
62
+ | 0.1111 | 8.0 | 2504 | 0.4380 | 0.2070 | 0.0638 | 68.9579 |
63
+ | 0.0965 | 9.0 | 2817 | 0.4541 | 0.2195 | 0.0735 | 67.8519 |
64
+ | 0.0843 | 10.0 | 3130 | 0.4822 | 0.2284 | 0.0780 | 67.0096 |
65
 
66
 
67
  ### Framework versions
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "/content/geez_t5-15k/checkpoint-2000",
3
  "architectures": [
4
  "T5ForConditionalGeneration"
5
  ],
 
1
  {
2
+ "_name_or_path": "Samuael/geez_t5-15k",
3
  "architectures": [
4
  "T5ForConditionalGeneration"
5
  ],
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:737ad39bb4ea7aa37afbef96421b8d71b1640dc9f30eab7b140b5f4e1c402695
3
  size 240738368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a1ffedba9d014ac2f4f461e077b0aa47dfa97cebe91ab08ed4bd76a737dc69d
3
  size 240738368
runs/Apr02_11-01-11_5154d18eb907/events.out.tfevents.1712055683.5154d18eb907.465.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7e31421e1557eca66e3f6abeea11fd0ac78ce7d7f0ea4558eae7e69239be32a4
3
- size 322449
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcf98131e452cb4c71d46c7e4ae6177c441ea8be4af271ec785be86152dd99a6
3
+ size 669211