Hugging Face's logo

MorcuendeA
/
profesion-tw-class

Text Classification
Transformers
Safetensors
Spanish
roberta
Generated from Trainer
Model card Files
xet
 Community
MorcuendeA commited on
Commit
7a10448
·
verified ·
1 Parent(s): f72e36e

profesion-tw-class

Browse files
Files changed (4) hide show
  1. README.md +25 -17
  2. config.json +1 -1
  3. model.safetensors +1 -1
  4. training_args.bin +1 -1
README.md CHANGED
@@ -18,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [PlanTL-GOB-ES/roberta-large-bne](https://huggingface.co/PlanTL-GOB-ES/roberta-large-bne) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.2291
22
- - Accuracy: 0.956
23
- - F1 Score: 0.9127
24
 
25
  ## Model description
26
 
@@ -42,7 +42,7 @@ The following hyperparameters were used during training:
42
  - learning_rate: 1e-05
43
  - train_batch_size: 8
44
  - eval_batch_size: 8
45
- - seed: 666
46
  - gradient_accumulation_steps: 2
47
  - total_train_batch_size: 16
48
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
@@ -53,19 +53,27 @@ The following hyperparameters were used during training:
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Score |
55
  |:-------------:|:------:|:----:|:---------------:|:--------:|:--------:|
56
- | 0.6858 | 0.2865 | 50 | 0.6501 | 0.622 | 0.5263 |
57
- | 0.595 | 0.5731 | 100 | 0.3948 | 0.848 | 0.6637 |
58
- | 0.3571 | 0.8596 | 150 | 0.1979 | 0.928 | 0.8605 |
59
- | 0.2677 | 1.1433 | 200 | 0.1686 | 0.956 | 0.9098 |
60
- | 0.2747 | 1.4298 | 250 | 0.1962 | 0.942 | 0.8880 |
61
- | 0.179 | 1.7163 | 300 | 0.1399 | 0.968 | 0.9344 |
62
- | 0.2171 | 2.0 | 350 | 0.1843 | 0.95 | 0.9020 |
63
- | 0.1014 | 2.2865 | 400 | 0.1766 | 0.968 | 0.9350 |
64
- | 0.1215 | 2.5731 | 450 | 0.2187 | 0.96 | 0.92 |
65
- | 0.2044 | 2.8596 | 500 | 0.1514 | 0.962 | 0.9212 |
66
- | 0.1196 | 3.1433 | 550 | 0.1951 | 0.96 | 0.92 |
67
- | 0.0968 | 3.4298 | 600 | 0.2465 | 0.954 | 0.9091 |
68
- | 0.0983 | 3.7163 | 650 | 0.2291 | 0.956 | 0.9127 |
 
 
 
 
 
 
 
 
69
 
70
 
71
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [PlanTL-GOB-ES/roberta-large-bne](https://huggingface.co/PlanTL-GOB-ES/roberta-large-bne) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.2443
22
+ - Accuracy: 0.9619
23
+ - F1 Score: 0.9224
24
 
25
  ## Model description
26
 
 
42
  - learning_rate: 1e-05
43
  - train_batch_size: 8
44
  - eval_batch_size: 8
45
+ - seed: 69
46
  - gradient_accumulation_steps: 2
47
  - total_train_batch_size: 16
48
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Score |
55
  |:-------------:|:------:|:----:|:---------------:|:--------:|:--------:|
56
+ | 0.5843 | 0.2865 | 50 | 0.3705 | 0.83 | 0.7231 |
57
+ | 0.2483 | 0.5731 | 100 | 0.1913 | 0.942 | 0.8872 |
58
+ | 0.2024 | 0.8596 | 150 | 0.1619 | 0.954 | 0.9091 |
59
+ | 0.1972 | 1.1433 | 200 | 0.2304 | 0.942 | 0.8872 |
60
+ | 0.1093 | 1.4298 | 250 | 0.2269 | 0.958 | 0.9157 |
61
+ | 0.0658 | 1.7163 | 300 | 0.2079 | 0.956 | 0.9098 |
62
+ | 0.0806 | 2.0 | 350 | 0.2081 | 0.954 | 0.9076 |
63
+ | 0.0194 | 2.2865 | 400 | 0.2177 | 0.956 | 0.9091 |
64
+ | 0.0165 | 2.5731 | 450 | 0.2319 | 0.962 | 0.9224 |
65
+ | 0.0507 | 2.8596 | 500 | 0.1857 | 0.956 | 0.9098 |
66
+ | 0.0393 | 3.1433 | 550 | 0.2356 | 0.954 | 0.9091 |
67
+ | 0.0057 | 3.4298 | 600 | 0.2623 | 0.952 | 0.9055 |
68
+ | 0.0114 | 3.7163 | 650 | 0.2037 | 0.962 | 0.9218 |
69
+ | 0.0011 | 4.0 | 700 | 0.2164 | 0.964 | 0.9268 |
70
+ | 0.0012 | 4.2865 | 750 | 0.2124 | 0.966 | 0.9289 |
71
+ | 0.0022 | 4.5731 | 800 | 0.2360 | 0.962 | 0.9237 |
72
+ | 0.0087 | 4.8596 | 850 | 0.2205 | 0.966 | 0.9306 |
73
+ | 0.0002 | 5.1433 | 900 | 0.2256 | 0.964 | 0.9268 |
74
+ | 0.0001 | 5.4298 | 950 | 0.2293 | 0.962 | 0.9231 |
75
+ | 0.0001 | 5.7163 | 1000 | 0.2312 | 0.962 | 0.9231 |
76
+ | 0.0001 | 6.0 | 1050 | 0.2318 | 0.962 | 0.9231 |
77
 
78
 
79
  ### Framework versions
config.json CHANGED
@@ -8,7 +8,7 @@
8
  "eos_token_id": 2,
9
  "gradient_checkpointing": false,
10
  "hidden_act": "gelu",
11
- "hidden_dropout_prob": 0.1,
12
  "hidden_size": 1024,
13
  "id2label": {
14
  "0": "NO_PROFESION",
 
8
  "eos_token_id": 2,
9
  "gradient_checkpointing": false,
10
  "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.0,
12
  "hidden_size": 1024,
13
  "id2label": {
14
  "0": "NO_PROFESION",
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6c5e26f13c378e38186b7e73d2044789e6a13326dbde0256911744390ebad1ee
3
  size 1421483128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6374cb9c0f51c46d26c598dff6bfd0fad814e278fd237cfa134e34c9c11590ca
3
  size 1421483128
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c1b25d672714ef5a6c594c221696add2efec031bc08c162fca0126c8b128ce2e
3
  size 5713
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:703853555f7209f647a33cd8da3208bcc5c656073dbed361041e71fe4f159f52
3
  size 5713