Hugging Face's logo

gechim
/
PhoBert_70KURL

Text Classification
Transformers
Safetensors
roberta
Generated from Trainer
Inference Endpoints
Model card Files Community
gechim commited on
Commit
5a9a7fa
•
1 Parent(s): 1b1a639

End of training

Browse files
Files changed (3) hide show
  1. README.md +46 -46
  2. config.json +2 -2
  3. model.safetensors +1 -1
README.md CHANGED
@@ -17,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [vinai/phobert-base-v2](https://huggingface.co/vinai/phobert-base-v2) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.0037
21
- - Accuracy: 0.9983
22
- - F1: 0.9983
23
 
24
  ## Model description
25
 
@@ -53,49 +53,49 @@ The following hyperparameters were used during training:
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
55
  |:-------------:|:-------:|:----:|:---------------:|:--------:|:------:|
56
- | No log | 0.4651 | 200 | 0.3962 | 0.8757 | 0.8704 |
57
- | No log | 0.9302 | 400 | 0.2125 | 0.9287 | 0.9284 |
58
- | No log | 1.3953 | 600 | 0.1637 | 0.9466 | 0.9466 |
59
- | No log | 1.8605 | 800 | 0.1432 | 0.9526 | 0.9530 |
60
- | 0.321 | 2.3256 | 1000 | 0.1220 | 0.9595 | 0.9597 |
61
- | 0.321 | 2.7907 | 1200 | 0.1084 | 0.9638 | 0.9640 |
62
- | 0.321 | 3.2558 | 1400 | 0.1034 | 0.9642 | 0.9644 |
63
- | 0.321 | 3.7209 | 1600 | 0.0905 | 0.9693 | 0.9695 |
64
- | 0.129 | 4.1860 | 1800 | 0.0813 | 0.9717 | 0.9717 |
65
- | 0.129 | 4.6512 | 2000 | 0.0762 | 0.9745 | 0.9746 |
66
- | 0.129 | 5.1163 | 2200 | 0.0693 | 0.9757 | 0.9758 |
67
- | 0.129 | 5.5814 | 2400 | 0.0633 | 0.9782 | 0.9783 |
68
- | 0.0951 | 6.0465 | 2600 | 0.0657 | 0.9781 | 0.9783 |
69
- | 0.0951 | 6.5116 | 2800 | 0.0500 | 0.9835 | 0.9836 |
70
- | 0.0951 | 6.9767 | 3000 | 0.0464 | 0.9842 | 0.9843 |
71
- | 0.0951 | 7.4419 | 3200 | 0.0429 | 0.9857 | 0.9858 |
72
- | 0.0951 | 7.9070 | 3400 | 0.0417 | 0.9861 | 0.9862 |
73
- | 0.068 | 8.3721 | 3600 | 0.0326 | 0.9890 | 0.9890 |
74
- | 0.068 | 8.8372 | 3800 | 0.0296 | 0.9907 | 0.9907 |
75
- | 0.068 | 9.3023 | 4000 | 0.0277 | 0.9905 | 0.9905 |
76
- | 0.068 | 9.7674 | 4200 | 0.0237 | 0.9916 | 0.9916 |
77
- | 0.0484 | 10.2326 | 4400 | 0.0205 | 0.9929 | 0.9929 |
78
- | 0.0484 | 10.6977 | 4600 | 0.0189 | 0.9933 | 0.9933 |
79
- | 0.0484 | 11.1628 | 4800 | 0.0157 | 0.9944 | 0.9944 |
80
- | 0.0484 | 11.6279 | 5000 | 0.0145 | 0.9955 | 0.9955 |
81
- | 0.0356 | 12.0930 | 5200 | 0.0185 | 0.9931 | 0.9931 |
82
- | 0.0356 | 12.5581 | 5400 | 0.0116 | 0.9962 | 0.9962 |
83
- | 0.0356 | 13.0233 | 5600 | 0.0099 | 0.9964 | 0.9964 |
84
- | 0.0356 | 13.4884 | 5800 | 0.0103 | 0.9962 | 0.9962 |
85
- | 0.0356 | 13.9535 | 6000 | 0.0076 | 0.9974 | 0.9974 |
86
- | 0.027 | 14.4186 | 6200 | 0.0080 | 0.9971 | 0.9971 |
87
- | 0.027 | 14.8837 | 6400 | 0.0071 | 0.9975 | 0.9975 |
88
- | 0.027 | 15.3488 | 6600 | 0.0057 | 0.9980 | 0.9980 |
89
- | 0.027 | 15.8140 | 6800 | 0.0058 | 0.9979 | 0.9979 |
90
- | 0.0193 | 16.2791 | 7000 | 0.0049 | 0.9981 | 0.9981 |
91
- | 0.0193 | 16.7442 | 7200 | 0.0076 | 0.9973 | 0.9973 |
92
- | 0.0193 | 17.2093 | 7400 | 0.0051 | 0.9982 | 0.9982 |
93
- | 0.0193 | 17.6744 | 7600 | 0.0044 | 0.9981 | 0.9981 |
94
- | 0.0148 | 18.1395 | 7800 | 0.0041 | 0.9984 | 0.9984 |
95
- | 0.0148 | 18.6047 | 8000 | 0.0038 | 0.9984 | 0.9984 |
96
- | 0.0148 | 19.0698 | 8200 | 0.0039 | 0.9983 | 0.9983 |
97
- | 0.0148 | 19.5349 | 8400 | 0.0038 | 0.9983 | 0.9983 |
98
- | 0.0115 | 20.0 | 8600 | 0.0037 | 0.9983 | 0.9983 |
99
 
100
 
101
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [vinai/phobert-base-v2](https://huggingface.co/vinai/phobert-base-v2) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.3781
21
+ - Accuracy: 0.9371
22
+ - F1: 0.9417
23
 
24
  ## Model description
25
 
 
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
55
  |:-------------:|:-------:|:----:|:---------------:|:--------:|:------:|
56
+ | No log | 0.4651 | 200 | 0.3374 | 0.9302 | 0.9233 |
57
+ | No log | 0.9302 | 400 | 0.1954 | 0.9353 | 0.9383 |
58
+ | No log | 1.3953 | 600 | 0.1273 | 0.9598 | 0.9609 |
59
+ | No log | 1.8605 | 800 | 0.1601 | 0.9423 | 0.9461 |
60
+ | 0.3263 | 2.3256 | 1000 | 0.1059 | 0.9666 | 0.9675 |
61
+ | 0.3263 | 2.7907 | 1200 | 0.0832 | 0.9742 | 0.9746 |
62
+ | 0.3263 | 3.2558 | 1400 | 0.1073 | 0.9621 | 0.9637 |
63
+ | 0.3263 | 3.7209 | 1600 | 0.1053 | 0.9644 | 0.9658 |
64
+ | 0.1315 | 4.1860 | 1800 | 0.0994 | 0.9653 | 0.9663 |
65
+ | 0.1315 | 4.6512 | 2000 | 0.1109 | 0.9617 | 0.9633 |
66
+ | 0.1315 | 5.1163 | 2200 | 0.1350 | 0.9491 | 0.9523 |
67
+ | 0.1315 | 5.5814 | 2400 | 0.1204 | 0.9543 | 0.9567 |
68
+ | 0.0959 | 6.0465 | 2600 | 0.2663 | 0.8906 | 0.9034 |
69
+ | 0.0959 | 6.5116 | 2800 | 0.1309 | 0.9510 | 0.9538 |
70
+ | 0.0959 | 6.9767 | 3000 | 0.2027 | 0.9279 | 0.9340 |
71
+ | 0.0959 | 7.4419 | 3200 | 0.1277 | 0.9509 | 0.9535 |
72
+ | 0.0959 | 7.9070 | 3400 | 0.1892 | 0.9473 | 0.9507 |
73
+ | 0.0689 | 8.3721 | 3600 | 0.2090 | 0.9350 | 0.9396 |
74
+ | 0.0689 | 8.8372 | 3800 | 0.1247 | 0.9579 | 0.9596 |
75
+ | 0.0689 | 9.3023 | 4000 | 0.2984 | 0.9132 | 0.9216 |
76
+ | 0.0689 | 9.7674 | 4200 | 0.2277 | 0.9352 | 0.9401 |
77
+ | 0.0483 | 10.2326 | 4400 | 0.2595 | 0.9266 | 0.9328 |
78
+ | 0.0483 | 10.6977 | 4600 | 0.2725 | 0.9249 | 0.9313 |
79
+ | 0.0483 | 11.1628 | 4800 | 0.2483 | 0.9341 | 0.9391 |
80
+ | 0.0483 | 11.6279 | 5000 | 0.2195 | 0.9442 | 0.9478 |
81
+ | 0.0379 | 12.0930 | 5200 | 0.7268 | 0.8450 | 0.8672 |
82
+ | 0.0379 | 12.5581 | 5400 | 0.2236 | 0.9503 | 0.9530 |
83
+ | 0.0379 | 13.0233 | 5600 | 0.2610 | 0.9438 | 0.9474 |
84
+ | 0.0379 | 13.4884 | 5800 | 0.3155 | 0.9366 | 0.9412 |
85
+ | 0.0379 | 13.9535 | 6000 | 0.3225 | 0.9374 | 0.9418 |
86
+ | 0.0284 | 14.4186 | 6200 | 0.4604 | 0.9158 | 0.9238 |
87
+ | 0.0284 | 14.8837 | 6400 | 0.3269 | 0.9372 | 0.9417 |
88
+ | 0.0284 | 15.3488 | 6600 | 0.3419 | 0.9401 | 0.9442 |
89
+ | 0.0284 | 15.8140 | 6800 | 0.2869 | 0.9465 | 0.9497 |
90
+ | 0.0213 | 16.2791 | 7000 | 0.3623 | 0.9364 | 0.9410 |
91
+ | 0.0213 | 16.7442 | 7200 | 0.2880 | 0.9433 | 0.9466 |
92
+ | 0.0213 | 17.2093 | 7400 | 0.3010 | 0.9454 | 0.9484 |
93
+ | 0.0213 | 17.6744 | 7600 | 0.3719 | 0.9344 | 0.9391 |
94
+ | 0.0165 | 18.1395 | 7800 | 0.3160 | 0.9448 | 0.9481 |
95
+ | 0.0165 | 18.6047 | 8000 | 0.3767 | 0.9388 | 0.9431 |
96
+ | 0.0165 | 19.0698 | 8200 | 0.3702 | 0.9383 | 0.9426 |
97
+ | 0.0165 | 19.5349 | 8400 | 0.3998 | 0.9343 | 0.9393 |
98
+ | 0.0121 | 20.0 | 8600 | 0.3781 | 0.9371 | 0.9417 |
99
 
100
 
101
  ### Framework versions
config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "_name_or_path": "vinai/phobert-base-v2",
3
  "architectures": [
4
- "XLMRobertaForSequenceClassification"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
7
  "bos_token_id": 0,
@@ -14,7 +14,7 @@
14
  "intermediate_size": 3072,
15
  "layer_norm_eps": 1e-05,
16
  "max_position_embeddings": 258,
17
- "model_type": "xlm-roberta",
18
  "num_attention_heads": 12,
19
  "num_hidden_layers": 12,
20
  "pad_token_id": 1,
 
1
  {
2
  "_name_or_path": "vinai/phobert-base-v2",
3
  "architectures": [
4
+ "RobertaForSequenceClassification"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
7
  "bos_token_id": 0,
 
14
  "intermediate_size": 3072,
15
  "layer_norm_eps": 1e-05,
16
  "max_position_embeddings": 258,
17
+ "model_type": "roberta",
18
  "num_attention_heads": 12,
19
  "num_hidden_layers": 12,
20
  "pad_token_id": 1,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ae657b75d56161a0b49b7fdc885134aad76b13c4d29ba0d9d0b36fe94cca4bd
3
  size 540023384
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:690613d9c1c5a7d18aef7d49c81c160d98408be96a80a27757731585f339315a
3
  size 540023384