Model save
Browse files- README.md +140 -0
- config.json +36 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,140 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
metrics:
|
5 |
+
- accuracy
|
6 |
+
model-index:
|
7 |
+
- name: ServiModel
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# ServiModel
|
15 |
+
|
16 |
+
This model was trained from scratch on an unknown dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.9224
|
19 |
+
- Accuracy: 0.5437
|
20 |
+
|
21 |
+
## Model description
|
22 |
+
|
23 |
+
More information needed
|
24 |
+
|
25 |
+
## Intended uses & limitations
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Training and evaluation data
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training procedure
|
34 |
+
|
35 |
+
### Training hyperparameters
|
36 |
+
|
37 |
+
The following hyperparameters were used during training:
|
38 |
+
- learning_rate: 5e-05
|
39 |
+
- train_batch_size: 8
|
40 |
+
- eval_batch_size: 8
|
41 |
+
- seed: 42
|
42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
+
- lr_scheduler_type: linear
|
44 |
+
- num_epochs: 1
|
45 |
+
|
46 |
+
### Training results
|
47 |
+
|
48 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
49 |
+
|:-------------:|:------:|:----:|:---------------:|:--------:|
|
50 |
+
| 0.9203 | 0.0120 | 3 | 1.0271 | 0.5264 |
|
51 |
+
| 0.7804 | 0.0239 | 6 | 0.9705 | 0.5287 |
|
52 |
+
| 0.8766 | 0.0359 | 9 | 0.9562 | 0.5299 |
|
53 |
+
| 0.8149 | 0.0478 | 12 | 0.9631 | 0.5345 |
|
54 |
+
| 0.8701 | 0.0598 | 15 | 0.9796 | 0.5379 |
|
55 |
+
| 0.992 | 0.0717 | 18 | 0.9764 | 0.5276 |
|
56 |
+
| 0.6035 | 0.0837 | 21 | 0.9932 | 0.5356 |
|
57 |
+
| 0.7398 | 0.0956 | 24 | 1.0167 | 0.5368 |
|
58 |
+
| 1.1153 | 0.1076 | 27 | 1.0184 | 0.5322 |
|
59 |
+
| 1.0794 | 0.1195 | 30 | 0.9807 | 0.5471 |
|
60 |
+
| 0.9069 | 0.1315 | 33 | 0.9571 | 0.5368 |
|
61 |
+
| 1.0911 | 0.1434 | 36 | 0.9478 | 0.5356 |
|
62 |
+
| 0.856 | 0.1554 | 39 | 0.9417 | 0.5276 |
|
63 |
+
| 0.7464 | 0.1673 | 42 | 0.9329 | 0.5368 |
|
64 |
+
| 1.0068 | 0.1793 | 45 | 0.9318 | 0.5402 |
|
65 |
+
| 0.8869 | 0.1912 | 48 | 0.9383 | 0.5402 |
|
66 |
+
| 1.0068 | 0.2032 | 51 | 0.9451 | 0.5517 |
|
67 |
+
| 0.9831 | 0.2151 | 54 | 0.9459 | 0.5460 |
|
68 |
+
| 1.0295 | 0.2271 | 57 | 0.9345 | 0.5356 |
|
69 |
+
| 0.6741 | 0.2390 | 60 | 0.9517 | 0.5414 |
|
70 |
+
| 0.9761 | 0.2510 | 63 | 0.9543 | 0.5448 |
|
71 |
+
| 0.7699 | 0.2629 | 66 | 0.9568 | 0.5368 |
|
72 |
+
| 0.9349 | 0.2749 | 69 | 0.9716 | 0.5287 |
|
73 |
+
| 0.8818 | 0.2869 | 72 | 0.9599 | 0.5322 |
|
74 |
+
| 0.857 | 0.2988 | 75 | 0.9496 | 0.5345 |
|
75 |
+
| 0.8135 | 0.3108 | 78 | 0.9521 | 0.5310 |
|
76 |
+
| 0.727 | 0.3227 | 81 | 0.9635 | 0.5402 |
|
77 |
+
| 0.9652 | 0.3347 | 84 | 0.9609 | 0.5414 |
|
78 |
+
| 0.7455 | 0.3466 | 87 | 0.9702 | 0.5299 |
|
79 |
+
| 0.7711 | 0.3586 | 90 | 0.9836 | 0.5230 |
|
80 |
+
| 0.7348 | 0.3705 | 93 | 1.0026 | 0.5276 |
|
81 |
+
| 0.8274 | 0.3825 | 96 | 1.0305 | 0.5368 |
|
82 |
+
| 0.9674 | 0.3944 | 99 | 1.0415 | 0.5276 |
|
83 |
+
| 1.0927 | 0.4064 | 102 | 1.0280 | 0.5253 |
|
84 |
+
| 1.1576 | 0.4183 | 105 | 0.9987 | 0.5356 |
|
85 |
+
| 0.8832 | 0.4303 | 108 | 0.9807 | 0.5322 |
|
86 |
+
| 0.5615 | 0.4422 | 111 | 0.9751 | 0.5437 |
|
87 |
+
| 1.2028 | 0.4542 | 114 | 0.9600 | 0.5391 |
|
88 |
+
| 0.8733 | 0.4661 | 117 | 0.9601 | 0.5448 |
|
89 |
+
| 0.8855 | 0.4781 | 120 | 0.9657 | 0.5391 |
|
90 |
+
| 1.0181 | 0.4900 | 123 | 0.9632 | 0.5379 |
|
91 |
+
| 0.8833 | 0.5020 | 126 | 0.9461 | 0.5379 |
|
92 |
+
| 1.0474 | 0.5139 | 129 | 0.9384 | 0.5425 |
|
93 |
+
| 1.173 | 0.5259 | 132 | 0.9260 | 0.5529 |
|
94 |
+
| 1.0996 | 0.5378 | 135 | 0.9186 | 0.5552 |
|
95 |
+
| 0.6445 | 0.5498 | 138 | 0.9149 | 0.5586 |
|
96 |
+
| 0.7965 | 0.5618 | 141 | 0.9176 | 0.5540 |
|
97 |
+
| 1.0051 | 0.5737 | 144 | 0.9213 | 0.5517 |
|
98 |
+
| 0.8613 | 0.5857 | 147 | 0.9298 | 0.5506 |
|
99 |
+
| 0.8603 | 0.5976 | 150 | 0.9345 | 0.5460 |
|
100 |
+
| 0.8247 | 0.6096 | 153 | 0.9306 | 0.5506 |
|
101 |
+
| 0.8808 | 0.6215 | 156 | 0.9269 | 0.5506 |
|
102 |
+
| 1.0487 | 0.6335 | 159 | 0.9235 | 0.5529 |
|
103 |
+
| 0.9654 | 0.6454 | 162 | 0.9236 | 0.5529 |
|
104 |
+
| 0.9228 | 0.6574 | 165 | 0.9196 | 0.5598 |
|
105 |
+
| 0.8636 | 0.6693 | 168 | 0.9153 | 0.5586 |
|
106 |
+
| 0.7859 | 0.6813 | 171 | 0.9174 | 0.5609 |
|
107 |
+
| 0.7514 | 0.6932 | 174 | 0.9177 | 0.5598 |
|
108 |
+
| 0.7972 | 0.7052 | 177 | 0.9187 | 0.5655 |
|
109 |
+
| 0.8669 | 0.7171 | 180 | 0.9277 | 0.5471 |
|
110 |
+
| 0.8085 | 0.7291 | 183 | 0.9406 | 0.5437 |
|
111 |
+
| 0.9855 | 0.7410 | 186 | 0.9494 | 0.5391 |
|
112 |
+
| 0.9821 | 0.7530 | 189 | 0.9533 | 0.5437 |
|
113 |
+
| 0.8769 | 0.7649 | 192 | 0.9556 | 0.5448 |
|
114 |
+
| 0.7997 | 0.7769 | 195 | 0.9610 | 0.5448 |
|
115 |
+
| 0.9333 | 0.7888 | 198 | 0.9580 | 0.5471 |
|
116 |
+
| 0.9406 | 0.8008 | 201 | 0.9454 | 0.5437 |
|
117 |
+
| 0.7489 | 0.8127 | 204 | 0.9389 | 0.5425 |
|
118 |
+
| 0.7847 | 0.8247 | 207 | 0.9348 | 0.5414 |
|
119 |
+
| 0.7151 | 0.8367 | 210 | 0.9297 | 0.5425 |
|
120 |
+
| 0.8573 | 0.8486 | 213 | 0.9259 | 0.5483 |
|
121 |
+
| 0.88 | 0.8606 | 216 | 0.9238 | 0.5529 |
|
122 |
+
| 0.8127 | 0.8725 | 219 | 0.9221 | 0.5506 |
|
123 |
+
| 0.7742 | 0.8845 | 222 | 0.9203 | 0.5506 |
|
124 |
+
| 1.0872 | 0.8964 | 225 | 0.9198 | 0.5471 |
|
125 |
+
| 0.6082 | 0.9084 | 228 | 0.9196 | 0.5471 |
|
126 |
+
| 0.6126 | 0.9203 | 231 | 0.9206 | 0.5471 |
|
127 |
+
| 0.8127 | 0.9323 | 234 | 0.9217 | 0.5460 |
|
128 |
+
| 0.8886 | 0.9442 | 237 | 0.9221 | 0.5448 |
|
129 |
+
| 0.9518 | 0.9562 | 240 | 0.9222 | 0.5448 |
|
130 |
+
| 0.7686 | 0.9681 | 243 | 0.9223 | 0.5460 |
|
131 |
+
| 0.7965 | 0.9801 | 246 | 0.9224 | 0.5437 |
|
132 |
+
| 0.7674 | 0.9920 | 249 | 0.9224 | 0.5437 |
|
133 |
+
|
134 |
+
|
135 |
+
### Framework versions
|
136 |
+
|
137 |
+
- Transformers 4.40.1
|
138 |
+
- Pytorch 2.3.0+cu121
|
139 |
+
- Datasets 2.19.0
|
140 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "./modelo",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"hidden_dim": 3072,
|
11 |
+
"id2label": {
|
12 |
+
"0": "positive",
|
13 |
+
"1": "neutral",
|
14 |
+
"2": "negative"
|
15 |
+
},
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"label2id": {
|
18 |
+
"negative": 2,
|
19 |
+
"neutral": 1,
|
20 |
+
"positive": 0
|
21 |
+
},
|
22 |
+
"max_position_embeddings": 512,
|
23 |
+
"model_type": "distilbert",
|
24 |
+
"n_heads": 12,
|
25 |
+
"n_layers": 6,
|
26 |
+
"output_past": true,
|
27 |
+
"pad_token_id": 0,
|
28 |
+
"problem_type": "single_label_classification",
|
29 |
+
"qa_dropout": 0.1,
|
30 |
+
"seq_classif_dropout": 0.2,
|
31 |
+
"sinusoidal_pos_embds": false,
|
32 |
+
"tie_weights_": true,
|
33 |
+
"torch_dtype": "float32",
|
34 |
+
"transformers_version": "4.40.1",
|
35 |
+
"vocab_size": 119547
|
36 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:22fb1cd5e44cd27855910516f080880feaea9296eaa20d3358fe71fccc337a6b
|
3 |
+
size 541320452
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e4807236c915ce73177328640d185cfe341b3e4fc5a330f03576e8165512595
|
3 |
+
size 4984
|