Santp98 commited on
Commit
7b52cd6
1 Parent(s): c6672b1

Model save

Browse files
Files changed (1) hide show
  1. README.md +21 -21
README.md CHANGED
@@ -1,20 +1,20 @@
1
  ---
2
- base_model: dccuchile/distilbert-base-spanish-uncased
3
  tags:
4
  - generated_from_trainer
5
  model-index:
6
- - name: distilbert-base-spanish-uncased-2023-11-13-18-01
7
  results: []
8
  ---
9
 
10
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
  should probably proofread and complete it, then remove this comment. -->
12
 
13
- # distilbert-base-spanish-uncased-2023-11-13-18-01
14
 
15
- This model is a fine-tuned version of [dccuchile/distilbert-base-spanish-uncased](https://huggingface.co/dccuchile/distilbert-base-spanish-uncased) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
- - Loss: 1.3884
18
 
19
  ## Model description
20
 
@@ -45,22 +45,22 @@ The following hyperparameters were used during training:
45
 
46
  | Training Loss | Epoch | Step | Validation Loss |
47
  |:-------------:|:-----:|:----:|:---------------:|
48
- | 2.5316 | 0.59 | 500 | 2.2591 |
49
- | 2.2197 | 1.19 | 1000 | 1.9800 |
50
- | 2.0108 | 1.78 | 1500 | 1.8304 |
51
- | 1.855 | 2.38 | 2000 | 1.7229 |
52
- | 1.7933 | 2.97 | 2500 | 1.6561 |
53
- | 1.7466 | 3.56 | 3000 | 1.6101 |
54
- | 1.6906 | 4.16 | 3500 | 1.5588 |
55
- | 1.6301 | 4.75 | 4000 | 1.5264 |
56
- | 1.6131 | 5.34 | 4500 | 1.4893 |
57
- | 1.5731 | 5.94 | 5000 | 1.4626 |
58
- | 1.5248 | 6.53 | 5500 | 1.4445 |
59
- | 1.509 | 7.13 | 6000 | 1.4274 |
60
- | 1.5083 | 7.72 | 6500 | 1.4109 |
61
- | 1.5277 | 8.31 | 7000 | 1.4051 |
62
- | 1.4884 | 8.91 | 7500 | 1.3872 |
63
- | 1.496 | 9.5 | 8000 | 1.3912 |
64
 
65
 
66
  ### Framework versions
 
1
  ---
2
+ base_model: dccuchile/albert-base-spanish
3
  tags:
4
  - generated_from_trainer
5
  model-index:
6
+ - name: albert-base-spanish-2023-11-13-19-24
7
  results: []
8
  ---
9
 
10
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
  should probably proofread and complete it, then remove this comment. -->
12
 
13
+ # albert-base-spanish-2023-11-13-19-24
14
 
15
+ This model is a fine-tuned version of [dccuchile/albert-base-spanish](https://huggingface.co/dccuchile/albert-base-spanish) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Loss: 1.4313
18
 
19
  ## Model description
20
 
 
45
 
46
  | Training Loss | Epoch | Step | Validation Loss |
47
  |:-------------:|:-----:|:----:|:---------------:|
48
+ | 1.9328 | 0.59 | 500 | 1.9145 |
49
+ | 1.863 | 1.19 | 1000 | 1.7882 |
50
+ | 1.7407 | 1.78 | 1500 | 1.7241 |
51
+ | 1.648 | 2.38 | 2000 | 1.6651 |
52
+ | 1.606 | 2.97 | 2500 | 1.6102 |
53
+ | 1.5833 | 3.56 | 3000 | 1.5912 |
54
+ | 1.5663 | 4.16 | 3500 | 1.5642 |
55
+ | 1.5104 | 4.75 | 4000 | 1.5390 |
56
+ | 1.5252 | 5.34 | 4500 | 1.5197 |
57
+ | 1.4676 | 5.94 | 5000 | 1.4950 |
58
+ | 1.4502 | 6.53 | 5500 | 1.4766 |
59
+ | 1.4336 | 7.13 | 6000 | 1.4694 |
60
+ | 1.4355 | 7.72 | 6500 | 1.4527 |
61
+ | 1.457 | 8.31 | 7000 | 1.4403 |
62
+ | 1.4219 | 8.91 | 7500 | 1.4380 |
63
+ | 1.4503 | 9.5 | 8000 | 1.4313 |
64
 
65
 
66
  ### Framework versions