ulisesbravo
commited on
Upload folder using huggingface_hub
Browse files- README.md +36 -0
- checkpoint-768/config.json +48 -0
- checkpoint-768/model.safetensors +3 -0
- checkpoint-768/optimizer.pt +3 -0
- checkpoint-768/rng_state.pth +3 -0
- checkpoint-768/scheduler.pt +3 -0
- checkpoint-768/trainer_state.json +544 -0
- checkpoint-768/training_args.bin +3 -0
- config.json +48 -0
- model.safetensors +3 -0
- runs/Nov26_00-57-41_r-ulisesbravo-train-teste2-etn05s4x-fc8db-htf36/events.out.tfevents.1732582662.r-ulisesbravo-train-teste2-etn05s4x-fc8db-htf36.144.0 +2 -2
- runs/Nov26_00-57-41_r-ulisesbravo-train-teste2-etn05s4x-fc8db-htf36/events.out.tfevents.1732603239.r-ulisesbravo-train-teste2-etn05s4x-fc8db-htf36.144.1 +3 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +64 -0
- training_args.bin +3 -0
- training_params.json +30 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
---
|
3 |
+
tags:
|
4 |
+
- autotrain
|
5 |
+
- text-classification
|
6 |
+
base_model: ulisesbravo/autotrain-BERTimbau-DGS-0001
|
7 |
+
widget:
|
8 |
+
- text: "I love AutoTrain"
|
9 |
+
---
|
10 |
+
|
11 |
+
# Model Trained Using AutoTrain
|
12 |
+
|
13 |
+
- Problem type: Text Classification
|
14 |
+
|
15 |
+
## Validation Metrics
|
16 |
+
loss: 0.7617048025131226
|
17 |
+
|
18 |
+
f1_macro: 0.7457262796719101
|
19 |
+
|
20 |
+
f1_micro: 0.748046875
|
21 |
+
|
22 |
+
f1_weighted: 0.7458152229876283
|
23 |
+
|
24 |
+
precision_macro: 0.7510527252931124
|
25 |
+
|
26 |
+
precision_micro: 0.748046875
|
27 |
+
|
28 |
+
precision_weighted: 0.7510721957087751
|
29 |
+
|
30 |
+
recall_macro: 0.7478964401294499
|
31 |
+
|
32 |
+
recall_micro: 0.748046875
|
33 |
+
|
34 |
+
recall_weighted: 0.748046875
|
35 |
+
|
36 |
+
accuracy: 0.748046875
|
checkpoint-768/config.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "ulisesbravo/autotrain-BERTimbau-DGS-0001",
|
3 |
+
"_num_labels": 5,
|
4 |
+
"architectures": [
|
5 |
+
"BertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"directionality": "bidi",
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "1 - INTIMA\u00c7\u00c3O INICIAL",
|
15 |
+
"1": "2 - INTIMA\u00c7\u00c3O INSTRU\u00c7\u00c3O",
|
16 |
+
"2": "3 - INTIMA\u00c7\u00c3O RECURSAL",
|
17 |
+
"3": "4 - INTIMA\u00c7\u00c3O CUMPRIMENTO DE SENTEN\u00c7A",
|
18 |
+
"4": "5 - INTIMA\u00c7\u00c3O TR\u00c2NSITO"
|
19 |
+
},
|
20 |
+
"initializer_range": 0.02,
|
21 |
+
"intermediate_size": 3072,
|
22 |
+
"label2id": {
|
23 |
+
"1 - INTIMA\u00c7\u00c3O INICIAL": 0,
|
24 |
+
"2 - INTIMA\u00c7\u00c3O INSTRU\u00c7\u00c3O": 1,
|
25 |
+
"3 - INTIMA\u00c7\u00c3O RECURSAL": 2,
|
26 |
+
"4 - INTIMA\u00c7\u00c3O CUMPRIMENTO DE SENTEN\u00c7A": 3,
|
27 |
+
"5 - INTIMA\u00c7\u00c3O TR\u00c2NSITO": 4
|
28 |
+
},
|
29 |
+
"layer_norm_eps": 1e-12,
|
30 |
+
"max_position_embeddings": 512,
|
31 |
+
"model_type": "bert",
|
32 |
+
"num_attention_heads": 12,
|
33 |
+
"num_hidden_layers": 12,
|
34 |
+
"output_past": true,
|
35 |
+
"pad_token_id": 0,
|
36 |
+
"pooler_fc_size": 768,
|
37 |
+
"pooler_num_attention_heads": 12,
|
38 |
+
"pooler_num_fc_layers": 3,
|
39 |
+
"pooler_size_per_head": 128,
|
40 |
+
"pooler_type": "first_token_transform",
|
41 |
+
"position_embedding_type": "absolute",
|
42 |
+
"problem_type": "single_label_classification",
|
43 |
+
"torch_dtype": "float32",
|
44 |
+
"transformers_version": "4.46.2",
|
45 |
+
"type_vocab_size": 2,
|
46 |
+
"use_cache": true,
|
47 |
+
"vocab_size": 29794
|
48 |
+
}
|
checkpoint-768/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:51f8d08d02da34c510712efc366891b14d6bc355263f6ea4be2539dc7aef4b32
|
3 |
+
size 435731452
|
checkpoint-768/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c1811deda59694839c504bf51aadd15afb803ab2035583eb5bfcbef589f0c1b6
|
3 |
+
size 871578362
|
checkpoint-768/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:62e74b716758556f6ba31c1f5a2ccd12d8dd08fc7d5c9fa43acc5d86090e0175
|
3 |
+
size 13990
|
checkpoint-768/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:350c3c48766c7873590e96de15f51186910dbfc3a3758c08a47def3fc7ba5b33
|
3 |
+
size 1064
|
checkpoint-768/trainer_state.json
ADDED
@@ -0,0 +1,544 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.7617048025131226,
|
3 |
+
"best_model_checkpoint": "autotrain-BERTimbau-DGS-0002/checkpoint-768",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 768,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.046875,
|
13 |
+
"grad_norm": 16.356477737426758,
|
14 |
+
"learning_rate": 7.792207792207792e-06,
|
15 |
+
"loss": 0.9263,
|
16 |
+
"step": 12
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.09375,
|
20 |
+
"grad_norm": 16.417421340942383,
|
21 |
+
"learning_rate": 1.5584415584415583e-05,
|
22 |
+
"loss": 0.7481,
|
23 |
+
"step": 24
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.140625,
|
27 |
+
"grad_norm": 8.063264846801758,
|
28 |
+
"learning_rate": 2.3376623376623376e-05,
|
29 |
+
"loss": 0.6649,
|
30 |
+
"step": 36
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.1875,
|
34 |
+
"grad_norm": 20.237438201904297,
|
35 |
+
"learning_rate": 3.1168831168831166e-05,
|
36 |
+
"loss": 0.6951,
|
37 |
+
"step": 48
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.234375,
|
41 |
+
"grad_norm": 20.48522186279297,
|
42 |
+
"learning_rate": 3.8961038961038966e-05,
|
43 |
+
"loss": 0.7835,
|
44 |
+
"step": 60
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.28125,
|
48 |
+
"grad_norm": 18.863914489746094,
|
49 |
+
"learning_rate": 4.675324675324675e-05,
|
50 |
+
"loss": 0.8848,
|
51 |
+
"step": 72
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.328125,
|
55 |
+
"grad_norm": 44.188045501708984,
|
56 |
+
"learning_rate": 4.949348769898698e-05,
|
57 |
+
"loss": 0.7587,
|
58 |
+
"step": 84
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.375,
|
62 |
+
"grad_norm": 3.5654993057250977,
|
63 |
+
"learning_rate": 4.862518089725037e-05,
|
64 |
+
"loss": 0.8591,
|
65 |
+
"step": 96
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.421875,
|
69 |
+
"grad_norm": 14.715095520019531,
|
70 |
+
"learning_rate": 4.775687409551375e-05,
|
71 |
+
"loss": 1.0722,
|
72 |
+
"step": 108
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.46875,
|
76 |
+
"grad_norm": 24.525127410888672,
|
77 |
+
"learning_rate": 4.6888567293777135e-05,
|
78 |
+
"loss": 0.8705,
|
79 |
+
"step": 120
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.515625,
|
83 |
+
"grad_norm": 11.264841079711914,
|
84 |
+
"learning_rate": 4.6020260492040525e-05,
|
85 |
+
"loss": 0.725,
|
86 |
+
"step": 132
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.5625,
|
90 |
+
"grad_norm": 10.208191871643066,
|
91 |
+
"learning_rate": 4.515195369030391e-05,
|
92 |
+
"loss": 0.9423,
|
93 |
+
"step": 144
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.609375,
|
97 |
+
"grad_norm": 36.85372543334961,
|
98 |
+
"learning_rate": 4.42836468885673e-05,
|
99 |
+
"loss": 0.6916,
|
100 |
+
"step": 156
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.65625,
|
104 |
+
"grad_norm": 10.57655143737793,
|
105 |
+
"learning_rate": 4.341534008683068e-05,
|
106 |
+
"loss": 0.9208,
|
107 |
+
"step": 168
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.703125,
|
111 |
+
"grad_norm": 8.791451454162598,
|
112 |
+
"learning_rate": 4.2547033285094066e-05,
|
113 |
+
"loss": 0.7232,
|
114 |
+
"step": 180
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.75,
|
118 |
+
"grad_norm": 3.045738697052002,
|
119 |
+
"learning_rate": 4.1678726483357456e-05,
|
120 |
+
"loss": 0.8408,
|
121 |
+
"step": 192
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.796875,
|
125 |
+
"grad_norm": 10.673927307128906,
|
126 |
+
"learning_rate": 4.081041968162084e-05,
|
127 |
+
"loss": 0.8796,
|
128 |
+
"step": 204
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.84375,
|
132 |
+
"grad_norm": 25.335668563842773,
|
133 |
+
"learning_rate": 3.994211287988423e-05,
|
134 |
+
"loss": 0.6581,
|
135 |
+
"step": 216
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.890625,
|
139 |
+
"grad_norm": 14.630143165588379,
|
140 |
+
"learning_rate": 3.9073806078147614e-05,
|
141 |
+
"loss": 0.8087,
|
142 |
+
"step": 228
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.9375,
|
146 |
+
"grad_norm": 10.134491920471191,
|
147 |
+
"learning_rate": 3.8205499276411e-05,
|
148 |
+
"loss": 0.7872,
|
149 |
+
"step": 240
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.984375,
|
153 |
+
"grad_norm": 9.269867897033691,
|
154 |
+
"learning_rate": 3.733719247467439e-05,
|
155 |
+
"loss": 0.817,
|
156 |
+
"step": 252
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 1.0,
|
160 |
+
"eval_accuracy": 0.703125,
|
161 |
+
"eval_f1_macro": 0.695547181551088,
|
162 |
+
"eval_f1_micro": 0.703125,
|
163 |
+
"eval_f1_weighted": 0.6955464487515762,
|
164 |
+
"eval_loss": 0.8037577867507935,
|
165 |
+
"eval_precision_macro": 0.7208504141314569,
|
166 |
+
"eval_precision_micro": 0.703125,
|
167 |
+
"eval_precision_weighted": 0.721030433935127,
|
168 |
+
"eval_recall_macro": 0.7032362459546926,
|
169 |
+
"eval_recall_micro": 0.703125,
|
170 |
+
"eval_recall_weighted": 0.703125,
|
171 |
+
"eval_runtime": 433.339,
|
172 |
+
"eval_samples_per_second": 1.182,
|
173 |
+
"eval_steps_per_second": 0.074,
|
174 |
+
"step": 256
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 1.03125,
|
178 |
+
"grad_norm": 18.80913543701172,
|
179 |
+
"learning_rate": 3.646888567293778e-05,
|
180 |
+
"loss": 0.9221,
|
181 |
+
"step": 264
|
182 |
+
},
|
183 |
+
{
|
184 |
+
"epoch": 1.078125,
|
185 |
+
"grad_norm": 17.218036651611328,
|
186 |
+
"learning_rate": 3.5600578871201154e-05,
|
187 |
+
"loss": 0.6136,
|
188 |
+
"step": 276
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 1.125,
|
192 |
+
"grad_norm": 11.861041069030762,
|
193 |
+
"learning_rate": 3.4732272069464545e-05,
|
194 |
+
"loss": 0.691,
|
195 |
+
"step": 288
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 1.171875,
|
199 |
+
"grad_norm": 13.683526992797852,
|
200 |
+
"learning_rate": 3.3863965267727935e-05,
|
201 |
+
"loss": 0.633,
|
202 |
+
"step": 300
|
203 |
+
},
|
204 |
+
{
|
205 |
+
"epoch": 1.21875,
|
206 |
+
"grad_norm": 4.825338840484619,
|
207 |
+
"learning_rate": 3.299565846599132e-05,
|
208 |
+
"loss": 0.4653,
|
209 |
+
"step": 312
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 1.265625,
|
213 |
+
"grad_norm": 25.25005531311035,
|
214 |
+
"learning_rate": 3.212735166425471e-05,
|
215 |
+
"loss": 0.8424,
|
216 |
+
"step": 324
|
217 |
+
},
|
218 |
+
{
|
219 |
+
"epoch": 1.3125,
|
220 |
+
"grad_norm": 6.728404998779297,
|
221 |
+
"learning_rate": 3.1259044862518086e-05,
|
222 |
+
"loss": 0.5561,
|
223 |
+
"step": 336
|
224 |
+
},
|
225 |
+
{
|
226 |
+
"epoch": 1.359375,
|
227 |
+
"grad_norm": 25.705286026000977,
|
228 |
+
"learning_rate": 3.0390738060781476e-05,
|
229 |
+
"loss": 0.6089,
|
230 |
+
"step": 348
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 1.40625,
|
234 |
+
"grad_norm": 9.829946517944336,
|
235 |
+
"learning_rate": 2.9522431259044863e-05,
|
236 |
+
"loss": 0.7743,
|
237 |
+
"step": 360
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 1.453125,
|
241 |
+
"grad_norm": 18.433866500854492,
|
242 |
+
"learning_rate": 2.865412445730825e-05,
|
243 |
+
"loss": 0.6377,
|
244 |
+
"step": 372
|
245 |
+
},
|
246 |
+
{
|
247 |
+
"epoch": 1.5,
|
248 |
+
"grad_norm": 8.541472434997559,
|
249 |
+
"learning_rate": 2.778581765557164e-05,
|
250 |
+
"loss": 0.5226,
|
251 |
+
"step": 384
|
252 |
+
},
|
253 |
+
{
|
254 |
+
"epoch": 1.546875,
|
255 |
+
"grad_norm": 5.109964847564697,
|
256 |
+
"learning_rate": 2.691751085383502e-05,
|
257 |
+
"loss": 0.6857,
|
258 |
+
"step": 396
|
259 |
+
},
|
260 |
+
{
|
261 |
+
"epoch": 1.59375,
|
262 |
+
"grad_norm": 16.345888137817383,
|
263 |
+
"learning_rate": 2.6049204052098407e-05,
|
264 |
+
"loss": 0.7348,
|
265 |
+
"step": 408
|
266 |
+
},
|
267 |
+
{
|
268 |
+
"epoch": 1.640625,
|
269 |
+
"grad_norm": 2.8149545192718506,
|
270 |
+
"learning_rate": 2.5180897250361797e-05,
|
271 |
+
"loss": 0.5388,
|
272 |
+
"step": 420
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 1.6875,
|
276 |
+
"grad_norm": 25.609724044799805,
|
277 |
+
"learning_rate": 2.4312590448625184e-05,
|
278 |
+
"loss": 0.6311,
|
279 |
+
"step": 432
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 1.734375,
|
283 |
+
"grad_norm": 18.137908935546875,
|
284 |
+
"learning_rate": 2.3444283646888568e-05,
|
285 |
+
"loss": 0.5373,
|
286 |
+
"step": 444
|
287 |
+
},
|
288 |
+
{
|
289 |
+
"epoch": 1.78125,
|
290 |
+
"grad_norm": 20.912015914916992,
|
291 |
+
"learning_rate": 2.2575976845151954e-05,
|
292 |
+
"loss": 0.5749,
|
293 |
+
"step": 456
|
294 |
+
},
|
295 |
+
{
|
296 |
+
"epoch": 1.828125,
|
297 |
+
"grad_norm": 3.7946367263793945,
|
298 |
+
"learning_rate": 2.170767004341534e-05,
|
299 |
+
"loss": 0.4923,
|
300 |
+
"step": 468
|
301 |
+
},
|
302 |
+
{
|
303 |
+
"epoch": 1.875,
|
304 |
+
"grad_norm": 4.118808269500732,
|
305 |
+
"learning_rate": 2.0839363241678728e-05,
|
306 |
+
"loss": 0.5086,
|
307 |
+
"step": 480
|
308 |
+
},
|
309 |
+
{
|
310 |
+
"epoch": 1.921875,
|
311 |
+
"grad_norm": 24.049333572387695,
|
312 |
+
"learning_rate": 1.9971056439942115e-05,
|
313 |
+
"loss": 0.5282,
|
314 |
+
"step": 492
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 1.96875,
|
318 |
+
"grad_norm": 6.969969272613525,
|
319 |
+
"learning_rate": 1.91027496382055e-05,
|
320 |
+
"loss": 0.7777,
|
321 |
+
"step": 504
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 2.0,
|
325 |
+
"eval_accuracy": 0.73828125,
|
326 |
+
"eval_f1_macro": 0.7360418623759021,
|
327 |
+
"eval_f1_micro": 0.73828125,
|
328 |
+
"eval_f1_weighted": 0.7360378486320622,
|
329 |
+
"eval_loss": 0.7803243398666382,
|
330 |
+
"eval_precision_macro": 0.750415606846448,
|
331 |
+
"eval_precision_micro": 0.73828125,
|
332 |
+
"eval_precision_weighted": 0.7504776910198645,
|
333 |
+
"eval_recall_macro": 0.7383399961926519,
|
334 |
+
"eval_recall_micro": 0.73828125,
|
335 |
+
"eval_recall_weighted": 0.73828125,
|
336 |
+
"eval_runtime": 436.6228,
|
337 |
+
"eval_samples_per_second": 1.173,
|
338 |
+
"eval_steps_per_second": 0.073,
|
339 |
+
"step": 512
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 2.015625,
|
343 |
+
"grad_norm": 28.933380126953125,
|
344 |
+
"learning_rate": 1.823444283646889e-05,
|
345 |
+
"loss": 0.5839,
|
346 |
+
"step": 516
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"epoch": 2.0625,
|
350 |
+
"grad_norm": 2.4092745780944824,
|
351 |
+
"learning_rate": 1.7366136034732272e-05,
|
352 |
+
"loss": 0.3359,
|
353 |
+
"step": 528
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 2.109375,
|
357 |
+
"grad_norm": 9.090546607971191,
|
358 |
+
"learning_rate": 1.649782923299566e-05,
|
359 |
+
"loss": 0.4643,
|
360 |
+
"step": 540
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 2.15625,
|
364 |
+
"grad_norm": 21.722578048706055,
|
365 |
+
"learning_rate": 1.5629522431259043e-05,
|
366 |
+
"loss": 0.4644,
|
367 |
+
"step": 552
|
368 |
+
},
|
369 |
+
{
|
370 |
+
"epoch": 2.203125,
|
371 |
+
"grad_norm": 5.349146842956543,
|
372 |
+
"learning_rate": 1.4761215629522431e-05,
|
373 |
+
"loss": 0.5075,
|
374 |
+
"step": 564
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 2.25,
|
378 |
+
"grad_norm": 6.464962482452393,
|
379 |
+
"learning_rate": 1.389290882778582e-05,
|
380 |
+
"loss": 0.2939,
|
381 |
+
"step": 576
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 2.296875,
|
385 |
+
"grad_norm": 32.128089904785156,
|
386 |
+
"learning_rate": 1.3024602026049203e-05,
|
387 |
+
"loss": 0.4584,
|
388 |
+
"step": 588
|
389 |
+
},
|
390 |
+
{
|
391 |
+
"epoch": 2.34375,
|
392 |
+
"grad_norm": 6.097667694091797,
|
393 |
+
"learning_rate": 1.2156295224312592e-05,
|
394 |
+
"loss": 0.6406,
|
395 |
+
"step": 600
|
396 |
+
},
|
397 |
+
{
|
398 |
+
"epoch": 2.390625,
|
399 |
+
"grad_norm": 19.716564178466797,
|
400 |
+
"learning_rate": 1.1287988422575977e-05,
|
401 |
+
"loss": 0.4642,
|
402 |
+
"step": 612
|
403 |
+
},
|
404 |
+
{
|
405 |
+
"epoch": 2.4375,
|
406 |
+
"grad_norm": 29.19405174255371,
|
407 |
+
"learning_rate": 1.0419681620839364e-05,
|
408 |
+
"loss": 0.3899,
|
409 |
+
"step": 624
|
410 |
+
},
|
411 |
+
{
|
412 |
+
"epoch": 2.484375,
|
413 |
+
"grad_norm": 16.421785354614258,
|
414 |
+
"learning_rate": 9.55137481910275e-06,
|
415 |
+
"loss": 0.4938,
|
416 |
+
"step": 636
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 2.53125,
|
420 |
+
"grad_norm": 21.284482955932617,
|
421 |
+
"learning_rate": 8.683068017366136e-06,
|
422 |
+
"loss": 0.419,
|
423 |
+
"step": 648
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 2.578125,
|
427 |
+
"grad_norm": 38.47277069091797,
|
428 |
+
"learning_rate": 7.814761215629521e-06,
|
429 |
+
"loss": 0.4105,
|
430 |
+
"step": 660
|
431 |
+
},
|
432 |
+
{
|
433 |
+
"epoch": 2.625,
|
434 |
+
"grad_norm": 43.99268341064453,
|
435 |
+
"learning_rate": 6.94645441389291e-06,
|
436 |
+
"loss": 0.4791,
|
437 |
+
"step": 672
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 2.671875,
|
441 |
+
"grad_norm": 24.28075408935547,
|
442 |
+
"learning_rate": 6.078147612156296e-06,
|
443 |
+
"loss": 0.4125,
|
444 |
+
"step": 684
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 2.71875,
|
448 |
+
"grad_norm": 39.111759185791016,
|
449 |
+
"learning_rate": 5.209840810419682e-06,
|
450 |
+
"loss": 0.7284,
|
451 |
+
"step": 696
|
452 |
+
},
|
453 |
+
{
|
454 |
+
"epoch": 2.765625,
|
455 |
+
"grad_norm": 12.080262184143066,
|
456 |
+
"learning_rate": 4.341534008683068e-06,
|
457 |
+
"loss": 0.3698,
|
458 |
+
"step": 708
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 2.8125,
|
462 |
+
"grad_norm": 10.01552677154541,
|
463 |
+
"learning_rate": 3.473227206946455e-06,
|
464 |
+
"loss": 0.5005,
|
465 |
+
"step": 720
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 2.859375,
|
469 |
+
"grad_norm": 7.803253173828125,
|
470 |
+
"learning_rate": 2.604920405209841e-06,
|
471 |
+
"loss": 0.5321,
|
472 |
+
"step": 732
|
473 |
+
},
|
474 |
+
{
|
475 |
+
"epoch": 2.90625,
|
476 |
+
"grad_norm": 8.892068862915039,
|
477 |
+
"learning_rate": 1.7366136034732275e-06,
|
478 |
+
"loss": 0.6087,
|
479 |
+
"step": 744
|
480 |
+
},
|
481 |
+
{
|
482 |
+
"epoch": 2.953125,
|
483 |
+
"grad_norm": 1.938845157623291,
|
484 |
+
"learning_rate": 8.683068017366137e-07,
|
485 |
+
"loss": 0.535,
|
486 |
+
"step": 756
|
487 |
+
},
|
488 |
+
{
|
489 |
+
"epoch": 3.0,
|
490 |
+
"grad_norm": 4.535564422607422,
|
491 |
+
"learning_rate": 0.0,
|
492 |
+
"loss": 0.2496,
|
493 |
+
"step": 768
|
494 |
+
},
|
495 |
+
{
|
496 |
+
"epoch": 3.0,
|
497 |
+
"eval_accuracy": 0.748046875,
|
498 |
+
"eval_f1_macro": 0.7457262796719101,
|
499 |
+
"eval_f1_micro": 0.748046875,
|
500 |
+
"eval_f1_weighted": 0.7458152229876283,
|
501 |
+
"eval_loss": 0.7617048025131226,
|
502 |
+
"eval_precision_macro": 0.7510527252931124,
|
503 |
+
"eval_precision_micro": 0.748046875,
|
504 |
+
"eval_precision_weighted": 0.7510721957087751,
|
505 |
+
"eval_recall_macro": 0.7478964401294499,
|
506 |
+
"eval_recall_micro": 0.748046875,
|
507 |
+
"eval_recall_weighted": 0.748046875,
|
508 |
+
"eval_runtime": 444.9594,
|
509 |
+
"eval_samples_per_second": 1.151,
|
510 |
+
"eval_steps_per_second": 0.072,
|
511 |
+
"step": 768
|
512 |
+
}
|
513 |
+
],
|
514 |
+
"logging_steps": 12,
|
515 |
+
"max_steps": 768,
|
516 |
+
"num_input_tokens_seen": 0,
|
517 |
+
"num_train_epochs": 3,
|
518 |
+
"save_steps": 500,
|
519 |
+
"stateful_callbacks": {
|
520 |
+
"EarlyStoppingCallback": {
|
521 |
+
"args": {
|
522 |
+
"early_stopping_patience": 5,
|
523 |
+
"early_stopping_threshold": 0.01
|
524 |
+
},
|
525 |
+
"attributes": {
|
526 |
+
"early_stopping_patience_counter": 0
|
527 |
+
}
|
528 |
+
},
|
529 |
+
"TrainerControl": {
|
530 |
+
"args": {
|
531 |
+
"should_epoch_stop": false,
|
532 |
+
"should_evaluate": false,
|
533 |
+
"should_log": false,
|
534 |
+
"should_save": true,
|
535 |
+
"should_training_stop": true
|
536 |
+
},
|
537 |
+
"attributes": {}
|
538 |
+
}
|
539 |
+
},
|
540 |
+
"total_flos": 1616597867298816.0,
|
541 |
+
"train_batch_size": 8,
|
542 |
+
"trial_name": null,
|
543 |
+
"trial_params": null
|
544 |
+
}
|
checkpoint-768/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d006918cf2f8dc18dbdd7564d8e622357e45f4b2fe2cfe7a8e7fe12fa3640c98
|
3 |
+
size 5304
|
config.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "ulisesbravo/autotrain-BERTimbau-DGS-0001",
|
3 |
+
"_num_labels": 5,
|
4 |
+
"architectures": [
|
5 |
+
"BertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"directionality": "bidi",
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "1 - INTIMA\u00c7\u00c3O INICIAL",
|
15 |
+
"1": "2 - INTIMA\u00c7\u00c3O INSTRU\u00c7\u00c3O",
|
16 |
+
"2": "3 - INTIMA\u00c7\u00c3O RECURSAL",
|
17 |
+
"3": "4 - INTIMA\u00c7\u00c3O CUMPRIMENTO DE SENTEN\u00c7A",
|
18 |
+
"4": "5 - INTIMA\u00c7\u00c3O TR\u00c2NSITO"
|
19 |
+
},
|
20 |
+
"initializer_range": 0.02,
|
21 |
+
"intermediate_size": 3072,
|
22 |
+
"label2id": {
|
23 |
+
"1 - INTIMA\u00c7\u00c3O INICIAL": 0,
|
24 |
+
"2 - INTIMA\u00c7\u00c3O INSTRU\u00c7\u00c3O": 1,
|
25 |
+
"3 - INTIMA\u00c7\u00c3O RECURSAL": 2,
|
26 |
+
"4 - INTIMA\u00c7\u00c3O CUMPRIMENTO DE SENTEN\u00c7A": 3,
|
27 |
+
"5 - INTIMA\u00c7\u00c3O TR\u00c2NSITO": 4
|
28 |
+
},
|
29 |
+
"layer_norm_eps": 1e-12,
|
30 |
+
"max_position_embeddings": 512,
|
31 |
+
"model_type": "bert",
|
32 |
+
"num_attention_heads": 12,
|
33 |
+
"num_hidden_layers": 12,
|
34 |
+
"output_past": true,
|
35 |
+
"pad_token_id": 0,
|
36 |
+
"pooler_fc_size": 768,
|
37 |
+
"pooler_num_attention_heads": 12,
|
38 |
+
"pooler_num_fc_layers": 3,
|
39 |
+
"pooler_size_per_head": 128,
|
40 |
+
"pooler_type": "first_token_transform",
|
41 |
+
"position_embedding_type": "absolute",
|
42 |
+
"problem_type": "single_label_classification",
|
43 |
+
"torch_dtype": "float32",
|
44 |
+
"transformers_version": "4.46.2",
|
45 |
+
"type_vocab_size": 2,
|
46 |
+
"use_cache": true,
|
47 |
+
"vocab_size": 29794
|
48 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:51f8d08d02da34c510712efc366891b14d6bc355263f6ea4be2539dc7aef4b32
|
3 |
+
size 435731452
|
runs/Nov26_00-57-41_r-ulisesbravo-train-teste2-etn05s4x-fc8db-htf36/events.out.tfevents.1732582662.r-ulisesbravo-train-teste2-etn05s4x-fc8db-htf36.144.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c481768b97781055eea340ddbf7023627ce64d8b4f824983422642784c99673d
|
3 |
+
size 22282
|
runs/Nov26_00-57-41_r-ulisesbravo-train-teste2-etn05s4x-fc8db-htf36/events.out.tfevents.1732603239.r-ulisesbravo-train-teste2-etn05s4x-fc8db-htf36.144.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e91207b7e4b9c077d1a46728b1dfbde39bc118df59ed3dc224702ab9b3ee937
|
3 |
+
size 921
|
special_tokens_map.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": {
|
3 |
+
"content": "[CLS]",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"mask_token": {
|
10 |
+
"content": "[MASK]",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"sep_token": {
|
24 |
+
"content": "[SEP]",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"unk_token": {
|
31 |
+
"content": "[UNK]",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
}
|
37 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": false,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_basic_tokenize": true,
|
47 |
+
"do_lower_case": false,
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"max_length": 512,
|
50 |
+
"model_max_length": 1000000000000000019884624838656,
|
51 |
+
"never_split": null,
|
52 |
+
"pad_to_multiple_of": null,
|
53 |
+
"pad_token": "[PAD]",
|
54 |
+
"pad_token_type_id": 0,
|
55 |
+
"padding_side": "right",
|
56 |
+
"sep_token": "[SEP]",
|
57 |
+
"stride": 0,
|
58 |
+
"strip_accents": null,
|
59 |
+
"tokenize_chinese_chars": true,
|
60 |
+
"tokenizer_class": "BertTokenizer",
|
61 |
+
"truncation_side": "right",
|
62 |
+
"truncation_strategy": "longest_first",
|
63 |
+
"unk_token": "[UNK]"
|
64 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d006918cf2f8dc18dbdd7564d8e622357e45f4b2fe2cfe7a8e7fe12fa3640c98
|
3 |
+
size 5304
|
training_params.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"data_path": "autotrain-BERTimbau-DGS-0002/autotrain-data",
|
3 |
+
"model": "ulisesbravo/autotrain-BERTimbau-DGS-0001",
|
4 |
+
"lr": 5e-05,
|
5 |
+
"epochs": 3,
|
6 |
+
"max_seq_length": 512,
|
7 |
+
"batch_size": 8,
|
8 |
+
"warmup_ratio": 0.1,
|
9 |
+
"gradient_accumulation": 1,
|
10 |
+
"optimizer": "adamw_torch",
|
11 |
+
"scheduler": "linear",
|
12 |
+
"weight_decay": 0.0,
|
13 |
+
"max_grad_norm": 1.0,
|
14 |
+
"seed": 42,
|
15 |
+
"train_split": "train",
|
16 |
+
"valid_split": "validation",
|
17 |
+
"text_column": "autotrain_text",
|
18 |
+
"target_column": "autotrain_label",
|
19 |
+
"logging_steps": -1,
|
20 |
+
"project_name": "autotrain-BERTimbau-DGS-0002",
|
21 |
+
"auto_find_batch_size": false,
|
22 |
+
"mixed_precision": "fp16",
|
23 |
+
"save_total_limit": 1,
|
24 |
+
"push_to_hub": true,
|
25 |
+
"eval_strategy": "epoch",
|
26 |
+
"username": "ulisesbravo",
|
27 |
+
"log": "tensorboard",
|
28 |
+
"early_stopping_patience": 5,
|
29 |
+
"early_stopping_threshold": 0.01
|
30 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|