diegoale1248
commited on
Commit
·
0308401
1
Parent(s):
73ded0b
Model save
Browse files
README.md
CHANGED
@@ -1,4 +1,6 @@
|
|
1 |
---
|
|
|
|
|
2 |
tags:
|
3 |
- generated_from_trainer
|
4 |
metrics:
|
@@ -14,11 +16,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
14 |
|
15 |
# finetuned-bert-categories-estimation
|
16 |
|
17 |
-
This model
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Loss: 0.
|
20 |
-
- F1: 0.
|
21 |
-
- Accuracy: 0.
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -43,85 +45,47 @@ The following hyperparameters were used during training:
|
|
43 |
- seed: 42
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
- lr_scheduler_type: linear
|
46 |
-
- num_epochs:
|
47 |
|
48 |
### Training results
|
49 |
|
50 |
| Training Loss | Epoch | Step | Validation Loss | F1 | Accuracy |
|
51 |
|:-------------:|:-----:|:----:|:---------------:|:------:|:--------:|
|
52 |
-
|
|
53 |
-
|
|
54 |
-
|
|
55 |
-
|
|
56 |
-
|
|
57 |
-
|
|
58 |
-
|
|
59 |
-
| 0.
|
60 |
-
| 0.
|
61 |
-
| 0.
|
62 |
-
| 0.
|
63 |
-
| 0.
|
64 |
-
| 0.
|
65 |
-
| 0.
|
66 |
-
| 0.
|
67 |
-
| 0.
|
68 |
-
| 0.
|
69 |
-
| 0.
|
70 |
-
| 0.
|
71 |
-
| 0.
|
72 |
-
| 0.
|
73 |
-
| 0.
|
74 |
-
| 0.
|
75 |
-
| 0.
|
76 |
-
| 0.
|
77 |
-
| 0.
|
78 |
-
| 0.
|
79 |
-
| 0.
|
80 |
-
| 0.
|
81 |
-
| 0.
|
82 |
-
| 0.0572 | 4.55 | 3100 | 0.4091 | 0.9030 | 0.9282 |
|
83 |
-
| 0.0585 | 4.7 | 3200 | 0.4222 | 0.9003 | 0.9275 |
|
84 |
-
| 0.0615 | 4.85 | 3300 | 0.4134 | 0.9056 | 0.9311 |
|
85 |
-
| 0.0663 | 4.99 | 3400 | 0.4200 | 0.9046 | 0.9293 |
|
86 |
-
| 0.028 | 5.14 | 3500 | 0.4131 | 0.9057 | 0.9331 |
|
87 |
-
| 0.0196 | 5.29 | 3600 | 0.4436 | 0.9017 | 0.9293 |
|
88 |
-
| 0.0237 | 5.43 | 3700 | 0.4316 | 0.9054 | 0.9309 |
|
89 |
-
| 0.0278 | 5.58 | 3800 | 0.4364 | 0.9017 | 0.9280 |
|
90 |
-
| 0.0352 | 5.73 | 3900 | 0.4294 | 0.9021 | 0.9284 |
|
91 |
-
| 0.0547 | 5.87 | 4000 | 0.4202 | 0.9098 | 0.9320 |
|
92 |
-
| 0.0512 | 6.02 | 4100 | 0.4280 | 0.9083 | 0.9311 |
|
93 |
-
| 0.0201 | 6.17 | 4200 | 0.4336 | 0.9099 | 0.9311 |
|
94 |
-
| 0.0192 | 6.31 | 4300 | 0.4329 | 0.9078 | 0.9330 |
|
95 |
-
| 0.0167 | 6.46 | 4400 | 0.4318 | 0.9091 | 0.9331 |
|
96 |
-
| 0.0305 | 6.61 | 4500 | 0.4288 | 0.9085 | 0.9333 |
|
97 |
-
| 0.0178 | 6.75 | 4600 | 0.4269 | 0.9111 | 0.9337 |
|
98 |
-
| 0.0268 | 6.9 | 4700 | 0.4267 | 0.9114 | 0.9337 |
|
99 |
-
| 0.0207 | 7.05 | 4800 | 0.4281 | 0.9115 | 0.9344 |
|
100 |
-
| 0.0116 | 7.2 | 4900 | 0.4329 | 0.9111 | 0.9348 |
|
101 |
-
| 0.0104 | 7.34 | 5000 | 0.4445 | 0.9089 | 0.9335 |
|
102 |
-
| 0.0149 | 7.49 | 5100 | 0.4394 | 0.9114 | 0.9343 |
|
103 |
-
| 0.0084 | 7.64 | 5200 | 0.4367 | 0.9145 | 0.9350 |
|
104 |
-
| 0.0151 | 7.78 | 5300 | 0.4460 | 0.9087 | 0.9319 |
|
105 |
-
| 0.012 | 7.93 | 5400 | 0.4368 | 0.9130 | 0.9354 |
|
106 |
-
| 0.0083 | 8.08 | 5500 | 0.4354 | 0.9122 | 0.9350 |
|
107 |
-
| 0.0089 | 8.22 | 5600 | 0.4319 | 0.9120 | 0.9344 |
|
108 |
-
| 0.0063 | 8.37 | 5700 | 0.4304 | 0.9139 | 0.9359 |
|
109 |
-
| 0.0089 | 8.52 | 5800 | 0.4297 | 0.9136 | 0.9352 |
|
110 |
-
| 0.0081 | 8.66 | 5900 | 0.4348 | 0.9128 | 0.9348 |
|
111 |
-
| 0.0084 | 8.81 | 6000 | 0.4361 | 0.9126 | 0.9354 |
|
112 |
-
| 0.0051 | 8.96 | 6100 | 0.4373 | 0.9140 | 0.9366 |
|
113 |
-
| 0.0049 | 9.1 | 6200 | 0.4374 | 0.9167 | 0.9376 |
|
114 |
-
| 0.0049 | 9.25 | 6300 | 0.4349 | 0.9170 | 0.9377 |
|
115 |
-
| 0.004 | 9.4 | 6400 | 0.4358 | 0.9174 | 0.9385 |
|
116 |
-
| 0.0046 | 9.54 | 6500 | 0.4352 | 0.9175 | 0.9385 |
|
117 |
-
| 0.0108 | 9.69 | 6600 | 0.4355 | 0.9171 | 0.9381 |
|
118 |
-
| 0.0039 | 9.84 | 6700 | 0.4357 | 0.9168 | 0.9383 |
|
119 |
-
| 0.0053 | 9.99 | 6800 | 0.4354 | 0.9168 | 0.9383 |
|
120 |
|
121 |
|
122 |
### Framework versions
|
123 |
|
124 |
- Transformers 4.35.2
|
125 |
-
- Pytorch 2.1.0+
|
126 |
- Datasets 2.15.0
|
127 |
- Tokenizers 0.15.0
|
|
|
1 |
---
|
2 |
+
license: mit
|
3 |
+
base_model: neuralmind/bert-base-portuguese-cased
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
metrics:
|
|
|
16 |
|
17 |
# finetuned-bert-categories-estimation
|
18 |
|
19 |
+
This model is a fine-tuned version of [neuralmind/bert-base-portuguese-cased](https://huggingface.co/neuralmind/bert-base-portuguese-cased) on the None dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.3765
|
22 |
+
- F1: 0.8829
|
23 |
+
- Accuracy: 0.9185
|
24 |
|
25 |
## Model description
|
26 |
|
|
|
45 |
- seed: 42
|
46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
- lr_scheduler_type: linear
|
48 |
+
- num_epochs: 4
|
49 |
|
50 |
### Training results
|
51 |
|
52 |
| Training Loss | Epoch | Step | Validation Loss | F1 | Accuracy |
|
53 |
|:-------------:|:-----:|:----:|:---------------:|:------:|:--------:|
|
54 |
+
| 4.1819 | 0.13 | 100 | 3.4072 | 0.1568 | 0.4170 |
|
55 |
+
| 3.0332 | 0.27 | 200 | 2.4751 | 0.3097 | 0.5559 |
|
56 |
+
| 2.3356 | 0.4 | 300 | 1.9235 | 0.4379 | 0.6605 |
|
57 |
+
| 1.8533 | 0.53 | 400 | 1.5348 | 0.5528 | 0.7300 |
|
58 |
+
| 1.5404 | 0.66 | 500 | 1.2910 | 0.6279 | 0.7834 |
|
59 |
+
| 1.3375 | 0.8 | 600 | 1.0888 | 0.6428 | 0.7987 |
|
60 |
+
| 1.09 | 0.93 | 700 | 0.9613 | 0.6828 | 0.8233 |
|
61 |
+
| 0.9577 | 1.06 | 800 | 0.8399 | 0.7188 | 0.8387 |
|
62 |
+
| 0.7999 | 1.2 | 900 | 0.7625 | 0.7396 | 0.8510 |
|
63 |
+
| 0.7067 | 1.33 | 1000 | 0.7112 | 0.7534 | 0.8537 |
|
64 |
+
| 0.6479 | 1.46 | 1100 | 0.6395 | 0.7807 | 0.8695 |
|
65 |
+
| 0.6 | 1.6 | 1200 | 0.6111 | 0.8015 | 0.8781 |
|
66 |
+
| 0.5168 | 1.73 | 1300 | 0.5787 | 0.8070 | 0.8783 |
|
67 |
+
| 0.5635 | 1.86 | 1400 | 0.5333 | 0.8167 | 0.8873 |
|
68 |
+
| 0.5094 | 1.99 | 1500 | 0.5283 | 0.8217 | 0.8868 |
|
69 |
+
| 0.3862 | 2.13 | 1600 | 0.4973 | 0.8257 | 0.8908 |
|
70 |
+
| 0.3663 | 2.26 | 1700 | 0.4879 | 0.8281 | 0.8889 |
|
71 |
+
| 0.3584 | 2.39 | 1800 | 0.4619 | 0.8406 | 0.8973 |
|
72 |
+
| 0.3427 | 2.53 | 1900 | 0.4460 | 0.8555 | 0.9044 |
|
73 |
+
| 0.3334 | 2.66 | 2000 | 0.4386 | 0.8600 | 0.9056 |
|
74 |
+
| 0.3267 | 2.79 | 2100 | 0.4274 | 0.8638 | 0.9064 |
|
75 |
+
| 0.3045 | 2.93 | 2200 | 0.4154 | 0.8704 | 0.9094 |
|
76 |
+
| 0.3048 | 3.06 | 2300 | 0.4156 | 0.8703 | 0.9106 |
|
77 |
+
| 0.2329 | 3.19 | 2400 | 0.4068 | 0.8640 | 0.9097 |
|
78 |
+
| 0.2393 | 3.32 | 2500 | 0.3957 | 0.8766 | 0.9122 |
|
79 |
+
| 0.2335 | 3.46 | 2600 | 0.3923 | 0.8776 | 0.9159 |
|
80 |
+
| 0.201 | 3.59 | 2700 | 0.3840 | 0.8810 | 0.9175 |
|
81 |
+
| 0.2156 | 3.72 | 2800 | 0.3849 | 0.8817 | 0.9174 |
|
82 |
+
| 0.2135 | 3.86 | 2900 | 0.3777 | 0.8833 | 0.9190 |
|
83 |
+
| 0.2164 | 3.99 | 3000 | 0.3765 | 0.8829 | 0.9185 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
84 |
|
85 |
|
86 |
### Framework versions
|
87 |
|
88 |
- Transformers 4.35.2
|
89 |
+
- Pytorch 2.1.0+cu121
|
90 |
- Datasets 2.15.0
|
91 |
- Tokenizers 0.15.0
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 436155948
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f87aeb5f3d0c34a43a381487290b0df46caf8b0eefd271d81d32e2c7c6caff7
|
3 |
size 436155948
|
runs/Dec14_22-51-30_ee31911c34f9/events.out.tfevents.1702595652.ee31911c34f9.4052.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:85e29944ac45fc55b29b13ec9932891580cabec7a36b163e6c58932321a0e299
|
3 |
+
size 457
|