End of training
Browse files- README.md +8 -31
- model.safetensors +1 -1
README.md
CHANGED
@@ -2,8 +2,6 @@
|
|
2 |
base_model: dccuchile/bert-base-spanish-wwm-cased
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
-
metrics:
|
6 |
-
- accuracy
|
7 |
model-index:
|
8 |
- name: Prototipo_1_EMI
|
9 |
results: []
|
@@ -16,8 +14,13 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
This model is a fine-tuned version of [dccuchile/bert-base-spanish-wwm-cased](https://huggingface.co/dccuchile/bert-base-spanish-wwm-cased) on an unknown dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
-
|
20 |
-
-
|
|
|
|
|
|
|
|
|
|
|
21 |
|
22 |
## Model description
|
23 |
|
@@ -36,7 +39,7 @@ More information needed
|
|
36 |
### Training hyperparameters
|
37 |
|
38 |
The following hyperparameters were used during training:
|
39 |
-
- learning_rate:
|
40 |
- train_batch_size: 25
|
41 |
- eval_batch_size: 25
|
42 |
- seed: 42
|
@@ -46,32 +49,6 @@ The following hyperparameters were used during training:
|
|
46 |
- num_epochs: 5
|
47 |
- mixed_precision_training: Native AMP
|
48 |
|
49 |
-
### Training results
|
50 |
-
|
51 |
-
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
52 |
-
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
53 |
-
| 1.0936 | 0.25 | 500 | 1.0491 | 0.527 |
|
54 |
-
| 0.9889 | 0.5 | 1000 | 0.9982 | 0.5478 |
|
55 |
-
| 0.9964 | 0.75 | 1500 | 0.9847 | 0.5624 |
|
56 |
-
| 1.012 | 1.0 | 2000 | 0.9651 | 0.5744 |
|
57 |
-
| 0.8354 | 1.25 | 2500 | 0.9694 | 0.5748 |
|
58 |
-
| 0.9153 | 1.5 | 3000 | 0.9953 | 0.5636 |
|
59 |
-
| 0.8969 | 1.75 | 3500 | 0.9661 | 0.5682 |
|
60 |
-
| 0.9201 | 2.0 | 4000 | 0.9527 | 0.5816 |
|
61 |
-
| 0.8482 | 2.25 | 4500 | 0.9854 | 0.576 |
|
62 |
-
| 0.8222 | 2.5 | 5000 | 0.9788 | 0.5764 |
|
63 |
-
| 0.774 | 2.75 | 5500 | 0.9925 | 0.5784 |
|
64 |
-
| 0.8086 | 3.0 | 6000 | 0.9864 | 0.5788 |
|
65 |
-
| 0.7053 | 3.25 | 6500 | 1.0250 | 0.5752 |
|
66 |
-
| 0.704 | 3.5 | 7000 | 1.0330 | 0.5702 |
|
67 |
-
| 0.7205 | 3.75 | 7500 | 1.0258 | 0.5762 |
|
68 |
-
| 0.6891 | 4.0 | 8000 | 1.0314 | 0.5746 |
|
69 |
-
| 0.6354 | 4.25 | 8500 | 1.0445 | 0.5746 |
|
70 |
-
| 0.6902 | 4.5 | 9000 | 1.0502 | 0.5714 |
|
71 |
-
| 0.6682 | 4.75 | 9500 | 1.0516 | 0.5718 |
|
72 |
-
| 0.6791 | 5.0 | 10000 | 1.0522 | 0.5728 |
|
73 |
-
|
74 |
-
|
75 |
### Framework versions
|
76 |
|
77 |
- Transformers 4.40.1
|
|
|
2 |
base_model: dccuchile/bert-base-spanish-wwm-cased
|
3 |
tags:
|
4 |
- generated_from_trainer
|
|
|
|
|
5 |
model-index:
|
6 |
- name: Prototipo_1_EMI
|
7 |
results: []
|
|
|
14 |
|
15 |
This model is a fine-tuned version of [dccuchile/bert-base-spanish-wwm-cased](https://huggingface.co/dccuchile/bert-base-spanish-wwm-cased) on an unknown dataset.
|
16 |
It achieves the following results on the evaluation set:
|
17 |
+
- eval_loss: 1.0198
|
18 |
+
- eval_accuracy: 0.5826
|
19 |
+
- eval_runtime: 23.4219
|
20 |
+
- eval_samples_per_second: 213.475
|
21 |
+
- eval_steps_per_second: 8.539
|
22 |
+
- epoch: 2.3333
|
23 |
+
- step: 7000
|
24 |
|
25 |
## Model description
|
26 |
|
|
|
39 |
### Training hyperparameters
|
40 |
|
41 |
The following hyperparameters were used during training:
|
42 |
+
- learning_rate: 3e-05
|
43 |
- train_batch_size: 25
|
44 |
- eval_batch_size: 25
|
45 |
- seed: 42
|
|
|
49 |
- num_epochs: 5
|
50 |
- mixed_precision_training: Native AMP
|
51 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
52 |
### Framework versions
|
53 |
|
54 |
- Transformers 4.40.1
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 439442436
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c316663b4593fe9d303b69f4ffea6beff7f67e49a273509096d95920d6e7bcf
|
3 |
size 439442436
|