Hugging Face's logo

Mawiwawi
/
albert-base-spanish-finetuned-ner-finetuned-ner

Token Classification
Transformers
TensorBoard
Safetensors
albert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Mawiwawi commited on
Commit
5d07cdd
·
verified ·
1 Parent(s): 8ddeb3e

End of training

Browse files
Files changed (4) hide show
  1. README.md +25 -25
  2. config.json +3 -1
  3. model.safetensors +2 -2
  4. training_args.bin +1 -1
README.md CHANGED
@@ -19,11 +19,11 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  This model is a fine-tuned version of [dccuchile/albert-base-spanish-finetuned-ner](https://huggingface.co/dccuchile/albert-base-spanish-finetuned-ner) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.2545
23
- - Precision: 0.9038
24
- - Recall: 0.8624
25
- - F1: 0.8826
26
- - Accuracy: 0.9609
27
 
28
  ## Model description
29
 
@@ -54,26 +54,26 @@ The following hyperparameters were used during training:
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
56
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
57
- | No log | 1.0 | 13 | 1.8225 | 0.0 | 0.0 | 0.0 | 0.5668 |
58
- | No log | 2.0 | 26 | 1.3460 | 0.0 | 0.0 | 0.0 | 0.6676 |
59
- | No log | 3.0 | 39 | 1.0221 | 0.1910 | 0.1560 | 0.1717 | 0.7575 |
60
- | No log | 4.0 | 52 | 0.8052 | 0.2913 | 0.2752 | 0.2830 | 0.8138 |
61
- | No log | 5.0 | 65 | 0.6603 | 0.3832 | 0.3761 | 0.3796 | 0.8465 |
62
- | No log | 6.0 | 78 | 0.5510 | 0.4563 | 0.4312 | 0.4434 | 0.8810 |
63
- | No log | 7.0 | 91 | 0.4627 | 0.8350 | 0.7890 | 0.8113 | 0.9382 |
64
- | No log | 8.0 | 104 | 0.4011 | 0.8824 | 0.8257 | 0.8531 | 0.9401 |
65
- | No log | 9.0 | 117 | 0.3604 | 0.9109 | 0.8440 | 0.8762 | 0.9419 |
66
- | No log | 10.0 | 130 | 0.3323 | 0.9109 | 0.8440 | 0.8762 | 0.9437 |
67
- | No log | 11.0 | 143 | 0.3093 | 0.9020 | 0.8440 | 0.8720 | 0.9437 |
68
- | No log | 12.0 | 156 | 0.2946 | 0.9020 | 0.8440 | 0.8720 | 0.9482 |
69
- | No log | 13.0 | 169 | 0.2832 | 0.9020 | 0.8440 | 0.8720 | 0.9564 |
70
- | No log | 14.0 | 182 | 0.2733 | 0.8868 | 0.8624 | 0.8744 | 0.9609 |
71
- | No log | 15.0 | 195 | 0.2668 | 0.8868 | 0.8624 | 0.8744 | 0.9619 |
72
- | No log | 16.0 | 208 | 0.2616 | 0.8868 | 0.8624 | 0.8744 | 0.9609 |
73
- | No log | 17.0 | 221 | 0.2584 | 0.9216 | 0.8624 | 0.8910 | 0.9619 |
74
- | No log | 18.0 | 234 | 0.2557 | 0.9038 | 0.8624 | 0.8826 | 0.9619 |
75
- | No log | 19.0 | 247 | 0.2547 | 0.9038 | 0.8624 | 0.8826 | 0.9619 |
76
- | No log | 20.0 | 260 | 0.2545 | 0.9038 | 0.8624 | 0.8826 | 0.9609 |
77
 
78
 
79
  ### Framework versions
 
19
 
20
  This model is a fine-tuned version of [dccuchile/albert-base-spanish-finetuned-ner](https://huggingface.co/dccuchile/albert-base-spanish-finetuned-ner) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 0.2834
23
+ - Precision: 0.8857
24
+ - Recall: 0.8493
25
+ - F1: 0.8671
26
+ - Accuracy: 0.9550
27
 
28
  ## Model description
29
 
 
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
56
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
57
+ | No log | 1.0 | 13 | 1.6810 | 0.0 | 0.0 | 0.0 | 0.6019 |
58
+ | No log | 2.0 | 26 | 1.2680 | 0.0246 | 0.0205 | 0.0224 | 0.6832 |
59
+ | No log | 3.0 | 39 | 0.9860 | 0.2439 | 0.2055 | 0.2230 | 0.7652 |
60
+ | No log | 4.0 | 52 | 0.8016 | 0.3876 | 0.3425 | 0.3636 | 0.8294 |
61
+ | No log | 5.0 | 65 | 0.6649 | 0.4806 | 0.4247 | 0.4509 | 0.8598 |
62
+ | No log | 6.0 | 78 | 0.5621 | 0.6319 | 0.6233 | 0.6276 | 0.8896 |
63
+ | No log | 7.0 | 91 | 0.4890 | 0.6986 | 0.6986 | 0.6986 | 0.9008 |
64
+ | No log | 8.0 | 104 | 0.4356 | 0.7114 | 0.7260 | 0.7186 | 0.9187 |
65
+ | No log | 9.0 | 117 | 0.3915 | 0.7877 | 0.7877 | 0.7877 | 0.9279 |
66
+ | No log | 10.0 | 130 | 0.3630 | 0.8125 | 0.8014 | 0.8069 | 0.9319 |
67
+ | No log | 11.0 | 143 | 0.3408 | 0.8310 | 0.8082 | 0.8194 | 0.9339 |
68
+ | No log | 12.0 | 156 | 0.3265 | 0.8777 | 0.8356 | 0.8561 | 0.9425 |
69
+ | No log | 13.0 | 169 | 0.3151 | 0.8921 | 0.8493 | 0.8702 | 0.9471 |
70
+ | No log | 14.0 | 182 | 0.3052 | 0.8857 | 0.8493 | 0.8671 | 0.9504 |
71
+ | No log | 15.0 | 195 | 0.2983 | 0.8857 | 0.8493 | 0.8671 | 0.9517 |
72
+ | No log | 16.0 | 208 | 0.2919 | 0.8857 | 0.8493 | 0.8671 | 0.9544 |
73
+ | No log | 17.0 | 221 | 0.2880 | 0.8857 | 0.8493 | 0.8671 | 0.9550 |
74
+ | No log | 18.0 | 234 | 0.2853 | 0.8857 | 0.8493 | 0.8671 | 0.9550 |
75
+ | No log | 19.0 | 247 | 0.2840 | 0.8857 | 0.8493 | 0.8671 | 0.9550 |
76
+ | No log | 20.0 | 260 | 0.2834 | 0.8857 | 0.8493 | 0.8671 | 0.9550 |
77
 
78
 
79
  ### Framework versions
config.json CHANGED
@@ -42,7 +42,8 @@
42
  "24": "LABEL_24",
43
  "25": "LABEL_25",
44
  "26": "LABEL_26",
45
- "27": "LABEL_27"
 
46
  },
47
  "initializer_range": 0.02,
48
  "inner_group_num": 1,
@@ -69,6 +70,7 @@
69
  "LABEL_25": 25,
70
  "LABEL_26": 26,
71
  "LABEL_27": 27,
 
72
  "LABEL_3": 3,
73
  "LABEL_4": 4,
74
  "LABEL_5": 5,
 
42
  "24": "LABEL_24",
43
  "25": "LABEL_25",
44
  "26": "LABEL_26",
45
+ "27": "LABEL_27",
46
+ "28": "LABEL_28"
47
  },
48
  "initializer_range": 0.02,
49
  "inner_group_num": 1,
 
70
  "LABEL_25": 25,
71
  "LABEL_26": 26,
72
  "LABEL_27": 27,
73
+ "LABEL_28": 28,
74
  "LABEL_3": 3,
75
  "LABEL_4": 4,
76
  "LABEL_5": 5,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a6f4c16f1d5347ba3642c414829abd8f0167a6f1de26851bbf1ad539b93c091
3
- size 44973344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2012a0352060e8040e8102522d07b1b8394d4e79b03a79e6ce4113159acf7072
3
+ size 44976420
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:05835657b57bd441e825bf345379dc66daebb8d59f84ffbf55db4cdf2457421d
3
  size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:496459f66584f6a232790e58056d7aa38589052c888dd11e3efe893e01062907
3
  size 5048