Hugging Face's logo

Yova
/
baseline

Text2Text Generation
Transformers
TensorBoard
Safetensors
t5
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
Yova commited on
Commit
283bf6a
·
1 Parent(s): 9357137

End of training

Browse files
Files changed (3) hide show
  1. README.md +24 -28
  2. generation_config.json +0 -1
  3. model.safetensors +1 -1
README.md CHANGED
@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
13
 
14
  This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
15
  It achieves the following results on the evaluation set:
16
- - Loss: 2.4307
17
  - Exact Match: 0.0
18
 
19
  ## Model description
@@ -34,41 +34,37 @@ More information needed
34
 
35
  The following hyperparameters were used during training:
36
  - learning_rate: 0.001
37
- - train_batch_size: 100
38
  - eval_batch_size: 8
39
  - seed: 42
40
- - gradient_accumulation_steps: 4
41
- - total_train_batch_size: 400
42
- - optimizer: Adam with betas=(0.98,0.999) and epsilon=1e-08
43
- - lr_scheduler_type: inverse_sqrt
44
- - lr_scheduler_warmup_steps: 4000
45
  - num_epochs: 20
46
- - label_smoothing_factor: 0.1
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Exact Match |
51
  |:-------------:|:-----:|:----:|:---------------:|:-----------:|
52
- | 6.3427 | 1.0 | 25 | 5.7961 | 0.0 |
53
- | 5.7757 | 2.0 | 50 | 4.8370 | 0.0 |
54
- | 5.0702 | 3.0 | 75 | 4.3284 | 0.0 |
55
- | 4.6064 | 4.0 | 100 | 4.0447 | 0.0 |
56
- | 4.3415 | 5.0 | 125 | 3.8892 | 0.0 |
57
- | 4.1863 | 6.0 | 150 | 3.7803 | 0.0 |
58
- | 4.0684 | 7.0 | 175 | 3.6724 | 0.0 |
59
- | 3.9449 | 8.0 | 200 | 3.5356 | 0.0 |
60
- | 3.7922 | 9.0 | 225 | 3.3716 | 0.0 |
61
- | 3.6343 | 10.0 | 250 | 3.2232 | 0.0 |
62
- | 3.4833 | 11.0 | 275 | 3.0938 | 0.0 |
63
- | 3.3374 | 12.0 | 300 | 2.9880 | 0.0 |
64
- | 3.2006 | 13.0 | 325 | 2.8960 | 0.0 |
65
- | 3.0796 | 14.0 | 350 | 2.8199 | 0.0 |
66
- | 2.9739 | 15.0 | 375 | 2.7270 | 0.0 |
67
- | 2.8824 | 16.0 | 400 | 2.6369 | 0.0 |
68
- | 2.8 | 17.0 | 425 | 2.5811 | 0.0 |
69
- | 2.7323 | 18.0 | 450 | 2.5184 | 0.0 |
70
- | 2.6596 | 19.0 | 475 | 2.4946 | 0.0 |
71
- | 2.5931 | 20.0 | 500 | 2.4307 | 0.0 |
72
 
73
 
74
  ### Framework versions
 
13
 
14
  This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
15
  It achieves the following results on the evaluation set:
16
+ - Loss: 1.7391
17
  - Exact Match: 0.0
18
 
19
  ## Model description
 
34
 
35
  The following hyperparameters were used during training:
36
  - learning_rate: 0.001
37
+ - train_batch_size: 64
38
  - eval_batch_size: 8
39
  - seed: 42
40
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
+ - lr_scheduler_type: linear
 
 
 
42
  - num_epochs: 20
 
43
 
44
  ### Training results
45
 
46
  | Training Loss | Epoch | Step | Validation Loss | Exact Match |
47
  |:-------------:|:-----:|:----:|:---------------:|:-----------:|
48
+ | 2.0707 | 1.0 | 157 | 1.4872 | 0.003 |
49
+ | 1.0627 | 2.0 | 314 | 1.2868 | 0.007 |
50
+ | 0.8185 | 3.0 | 471 | 1.2750 | 0.0 |
51
+ | 0.6815 | 4.0 | 628 | 1.4788 | 0.0 |
52
+ | 0.6021 | 5.0 | 785 | 1.3314 | 0.003 |
53
+ | 0.5331 | 6.0 | 942 | 1.4174 | 0.0 |
54
+ | 0.481 | 7.0 | 1099 | 1.5780 | 0.0 |
55
+ | 0.442 | 8.0 | 1256 | 1.4797 | 0.0 |
56
+ | 0.4027 | 9.0 | 1413 | 1.5298 | 0.0 |
57
+ | 0.3629 | 10.0 | 1570 | 1.5906 | 0.0 |
58
+ | 0.3313 | 11.0 | 1727 | 1.6076 | 0.0 |
59
+ | 0.3031 | 12.0 | 1884 | 1.7169 | 0.0 |
60
+ | 0.269 | 13.0 | 2041 | 1.5874 | 0.0 |
61
+ | 0.2433 | 14.0 | 2198 | 1.7706 | 0.0 |
62
+ | 0.2079 | 15.0 | 2355 | 1.6666 | 0.0 |
63
+ | 0.1772 | 16.0 | 2512 | 1.6823 | 0.0 |
64
+ | 0.1549 | 17.0 | 2669 | 1.7645 | 0.0 |
65
+ | 0.1345 | 18.0 | 2826 | 1.7436 | 0.0 |
66
+ | 0.124 | 19.0 | 2983 | 1.7963 | 0.0 |
67
+ | 0.1166 | 20.0 | 3140 | 1.7391 | 0.0 |
68
 
69
 
70
  ### Framework versions
generation_config.json CHANGED
@@ -2,7 +2,6 @@
2
  "decoder_start_token_id": 259,
3
  "eos_token_id": 1,
4
  "max_new_tokens": 20,
5
- "num_beams": 5,
6
  "pad_token_id": 0,
7
  "transformers_version": "4.35.2"
8
  }
 
2
  "decoder_start_token_id": 259,
3
  "eos_token_id": 1,
4
  "max_new_tokens": 20,
 
5
  "pad_token_id": 0,
6
  "transformers_version": "4.35.2"
7
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f833b0041de4fd8abd5a25e09c5ab6b1f6d844090494de955b8ea1aa36cc8c2f
3
  size 20676648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d40e6ab7ebe39f319d71473c6cfb45f2201045e08ffd62fadc62b6f6b74a8f6
3
  size 20676648