kairos-posicao-bert2
Browse files- IA-AzMina/modelos/checkpoint-408/config.json +41 -0
- IA-AzMina/modelos/checkpoint-408/model.safetensors +3 -0
- IA-AzMina/modelos/checkpoint-408/optimizer.pt +3 -0
- IA-AzMina/modelos/checkpoint-408/rng_state.pth +3 -0
- IA-AzMina/modelos/checkpoint-408/scheduler.pt +3 -0
- IA-AzMina/modelos/checkpoint-408/trainer_state.json +370 -0
- IA-AzMina/modelos/checkpoint-408/training_args.bin +3 -0
- IA-AzMina/modelos/checkpoint-612/config.json +41 -0
- IA-AzMina/modelos/checkpoint-612/model.safetensors +3 -0
- IA-AzMina/modelos/checkpoint-612/optimizer.pt +3 -0
- IA-AzMina/modelos/checkpoint-612/rng_state.pth +3 -0
- IA-AzMina/modelos/checkpoint-612/scheduler.pt +3 -0
- IA-AzMina/modelos/checkpoint-612/trainer_state.json +541 -0
- IA-AzMina/modelos/checkpoint-612/training_args.bin +3 -0
- README.md +71 -0
- config.json +41 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
IA-AzMina/modelos/checkpoint-408/config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "belisards/congretimbau",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.05,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"directionality": "bidi",
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.05,
|
| 11 |
+
"hidden_size": 1024,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "0",
|
| 14 |
+
"1": "1"
|
| 15 |
+
},
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 4096,
|
| 18 |
+
"label2id": {
|
| 19 |
+
"0": 0,
|
| 20 |
+
"1": 1
|
| 21 |
+
},
|
| 22 |
+
"layer_norm_eps": 1e-12,
|
| 23 |
+
"max_position_embeddings": 512,
|
| 24 |
+
"model_type": "bert",
|
| 25 |
+
"num_attention_heads": 16,
|
| 26 |
+
"num_hidden_layers": 24,
|
| 27 |
+
"output_past": true,
|
| 28 |
+
"pad_token_id": 0,
|
| 29 |
+
"pooler_fc_size": 768,
|
| 30 |
+
"pooler_num_attention_heads": 12,
|
| 31 |
+
"pooler_num_fc_layers": 3,
|
| 32 |
+
"pooler_size_per_head": 128,
|
| 33 |
+
"pooler_type": "first_token_transform",
|
| 34 |
+
"position_embedding_type": "absolute",
|
| 35 |
+
"problem_type": "single_label_classification",
|
| 36 |
+
"torch_dtype": "float32",
|
| 37 |
+
"transformers_version": "4.47.0",
|
| 38 |
+
"type_vocab_size": 2,
|
| 39 |
+
"use_cache": true,
|
| 40 |
+
"vocab_size": 29794
|
| 41 |
+
}
|
IA-AzMina/modelos/checkpoint-408/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a7a36797f549e03dff5cae7c929983a8e7224ea4d3b95202e65970178a1d732b
|
| 3 |
+
size 1337640872
|
IA-AzMina/modelos/checkpoint-408/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:19dc92698db5bfc83e45dc9a49707acaa3c52d7c03375d7c1a5de798221c3de7
|
| 3 |
+
size 2675516653
|
IA-AzMina/modelos/checkpoint-408/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4bc8c094d41b2386cecf147812ab95342108045e8b7e91f3e38d921a20eafd55
|
| 3 |
+
size 14244
|
IA-AzMina/modelos/checkpoint-408/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fcd49ea243f8cf14d88cbad39b61bde7ac8327c5a633b4fcbcc50f480aa5090d
|
| 3 |
+
size 1064
|
IA-AzMina/modelos/checkpoint-408/trainer_state.json
ADDED
|
@@ -0,0 +1,370 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.80479302832244,
|
| 3 |
+
"best_model_checkpoint": "/content/drive/MyDrive/IA-AzMina/modelos/checkpoint-306",
|
| 4 |
+
"epoch": 11.657142857142857,
|
| 5 |
+
"eval_steps": 102,
|
| 6 |
+
"global_step": 408,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.2857142857142857,
|
| 13 |
+
"grad_norm": 7.993121147155762,
|
| 14 |
+
"learning_rate": 6.666666666666667e-07,
|
| 15 |
+
"loss": 0.2403,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.5714285714285714,
|
| 20 |
+
"grad_norm": 3.0666286945343018,
|
| 21 |
+
"learning_rate": 1.3333333333333334e-06,
|
| 22 |
+
"loss": 0.1919,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.8571428571428571,
|
| 27 |
+
"grad_norm": 1.189735770225525,
|
| 28 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 29 |
+
"loss": 0.1434,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 1.1428571428571428,
|
| 34 |
+
"grad_norm": 5.863226413726807,
|
| 35 |
+
"learning_rate": 2.666666666666667e-06,
|
| 36 |
+
"loss": 0.1568,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 1.4285714285714286,
|
| 41 |
+
"grad_norm": 1.1394373178482056,
|
| 42 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 43 |
+
"loss": 0.1171,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.7142857142857144,
|
| 48 |
+
"grad_norm": 1.28859543800354,
|
| 49 |
+
"learning_rate": 4.000000000000001e-06,
|
| 50 |
+
"loss": 0.1281,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 2.0,
|
| 55 |
+
"grad_norm": 3.0536108016967773,
|
| 56 |
+
"learning_rate": 4.666666666666667e-06,
|
| 57 |
+
"loss": 0.1441,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 2.2857142857142856,
|
| 62 |
+
"grad_norm": 1.9521867036819458,
|
| 63 |
+
"learning_rate": 5.333333333333334e-06,
|
| 64 |
+
"loss": 0.1304,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 2.571428571428571,
|
| 69 |
+
"grad_norm": 1.1799356937408447,
|
| 70 |
+
"learning_rate": 6e-06,
|
| 71 |
+
"loss": 0.0976,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 2.857142857142857,
|
| 76 |
+
"grad_norm": 1.355656385421753,
|
| 77 |
+
"learning_rate": 6.666666666666667e-06,
|
| 78 |
+
"loss": 0.1206,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 2.914285714285714,
|
| 83 |
+
"eval_accuracy": 0.8392857142857143,
|
| 84 |
+
"eval_f1": 0.7613636363636364,
|
| 85 |
+
"eval_loss": 0.10990084707736969,
|
| 86 |
+
"eval_precision": 0.819468024900962,
|
| 87 |
+
"eval_recall": 0.7345243041130037,
|
| 88 |
+
"eval_runtime": 1.047,
|
| 89 |
+
"eval_samples_per_second": 106.971,
|
| 90 |
+
"eval_steps_per_second": 3.82,
|
| 91 |
+
"step": 102
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 3.142857142857143,
|
| 95 |
+
"grad_norm": 1.0178292989730835,
|
| 96 |
+
"learning_rate": 7.333333333333333e-06,
|
| 97 |
+
"loss": 0.1002,
|
| 98 |
+
"step": 110
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 3.4285714285714284,
|
| 102 |
+
"grad_norm": 3.186685800552368,
|
| 103 |
+
"learning_rate": 8.000000000000001e-06,
|
| 104 |
+
"loss": 0.1003,
|
| 105 |
+
"step": 120
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 3.7142857142857144,
|
| 109 |
+
"grad_norm": 3.820305347442627,
|
| 110 |
+
"learning_rate": 8.666666666666668e-06,
|
| 111 |
+
"loss": 0.1055,
|
| 112 |
+
"step": 130
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 4.0,
|
| 116 |
+
"grad_norm": 3.202270269393921,
|
| 117 |
+
"learning_rate": 9.333333333333334e-06,
|
| 118 |
+
"loss": 0.0954,
|
| 119 |
+
"step": 140
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 4.285714285714286,
|
| 123 |
+
"grad_norm": 1.2107843160629272,
|
| 124 |
+
"learning_rate": 1e-05,
|
| 125 |
+
"loss": 0.0792,
|
| 126 |
+
"step": 150
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 4.571428571428571,
|
| 130 |
+
"grad_norm": 0.7708235383033752,
|
| 131 |
+
"learning_rate": 9.920000000000002e-06,
|
| 132 |
+
"loss": 0.0687,
|
| 133 |
+
"step": 160
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 4.857142857142857,
|
| 137 |
+
"grad_norm": 2.158849000930786,
|
| 138 |
+
"learning_rate": 9.84e-06,
|
| 139 |
+
"loss": 0.0815,
|
| 140 |
+
"step": 170
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 5.142857142857143,
|
| 144 |
+
"grad_norm": 1.280442714691162,
|
| 145 |
+
"learning_rate": 9.760000000000001e-06,
|
| 146 |
+
"loss": 0.0729,
|
| 147 |
+
"step": 180
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 5.428571428571429,
|
| 151 |
+
"grad_norm": 0.9879515171051025,
|
| 152 |
+
"learning_rate": 9.68e-06,
|
| 153 |
+
"loss": 0.0534,
|
| 154 |
+
"step": 190
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 5.714285714285714,
|
| 158 |
+
"grad_norm": 2.0247597694396973,
|
| 159 |
+
"learning_rate": 9.600000000000001e-06,
|
| 160 |
+
"loss": 0.0448,
|
| 161 |
+
"step": 200
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 5.828571428571428,
|
| 165 |
+
"eval_accuracy": 0.8392857142857143,
|
| 166 |
+
"eval_f1": 0.7857142857142858,
|
| 167 |
+
"eval_loss": 0.11759153753519058,
|
| 168 |
+
"eval_precision": 0.7930283224400871,
|
| 169 |
+
"eval_recall": 0.7793934358122143,
|
| 170 |
+
"eval_runtime": 1.0356,
|
| 171 |
+
"eval_samples_per_second": 108.152,
|
| 172 |
+
"eval_steps_per_second": 3.863,
|
| 173 |
+
"step": 204
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 6.0,
|
| 177 |
+
"grad_norm": 1.6217639446258545,
|
| 178 |
+
"learning_rate": 9.52e-06,
|
| 179 |
+
"loss": 0.0439,
|
| 180 |
+
"step": 210
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 6.285714285714286,
|
| 184 |
+
"grad_norm": 0.7515562772750854,
|
| 185 |
+
"learning_rate": 9.440000000000001e-06,
|
| 186 |
+
"loss": 0.0227,
|
| 187 |
+
"step": 220
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 6.571428571428571,
|
| 191 |
+
"grad_norm": 0.7949752807617188,
|
| 192 |
+
"learning_rate": 9.360000000000002e-06,
|
| 193 |
+
"loss": 0.0236,
|
| 194 |
+
"step": 230
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 6.857142857142857,
|
| 198 |
+
"grad_norm": 1.0292161703109741,
|
| 199 |
+
"learning_rate": 9.280000000000001e-06,
|
| 200 |
+
"loss": 0.0309,
|
| 201 |
+
"step": 240
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 7.142857142857143,
|
| 205 |
+
"grad_norm": 1.0616097450256348,
|
| 206 |
+
"learning_rate": 9.200000000000002e-06,
|
| 207 |
+
"loss": 0.0199,
|
| 208 |
+
"step": 250
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 7.428571428571429,
|
| 212 |
+
"grad_norm": 0.13813751935958862,
|
| 213 |
+
"learning_rate": 9.12e-06,
|
| 214 |
+
"loss": 0.0112,
|
| 215 |
+
"step": 260
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 7.714285714285714,
|
| 219 |
+
"grad_norm": 0.5435482263565063,
|
| 220 |
+
"learning_rate": 9.040000000000002e-06,
|
| 221 |
+
"loss": 0.0088,
|
| 222 |
+
"step": 270
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 8.0,
|
| 226 |
+
"grad_norm": 0.13850395381450653,
|
| 227 |
+
"learning_rate": 8.96e-06,
|
| 228 |
+
"loss": 0.0101,
|
| 229 |
+
"step": 280
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 8.285714285714286,
|
| 233 |
+
"grad_norm": 0.21646977961063385,
|
| 234 |
+
"learning_rate": 8.880000000000001e-06,
|
| 235 |
+
"loss": 0.0043,
|
| 236 |
+
"step": 290
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 8.571428571428571,
|
| 240 |
+
"grad_norm": 0.4107956886291504,
|
| 241 |
+
"learning_rate": 8.8e-06,
|
| 242 |
+
"loss": 0.0069,
|
| 243 |
+
"step": 300
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 8.742857142857144,
|
| 247 |
+
"eval_accuracy": 0.8571428571428571,
|
| 248 |
+
"eval_f1": 0.80479302832244,
|
| 249 |
+
"eval_loss": 0.2356744110584259,
|
| 250 |
+
"eval_precision": 0.822528735632184,
|
| 251 |
+
"eval_recall": 0.7914416285832987,
|
| 252 |
+
"eval_runtime": 1.0345,
|
| 253 |
+
"eval_samples_per_second": 108.269,
|
| 254 |
+
"eval_steps_per_second": 3.867,
|
| 255 |
+
"step": 306
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 8.857142857142858,
|
| 259 |
+
"grad_norm": 0.3167528808116913,
|
| 260 |
+
"learning_rate": 8.720000000000001e-06,
|
| 261 |
+
"loss": 0.0023,
|
| 262 |
+
"step": 310
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 9.142857142857142,
|
| 266 |
+
"grad_norm": 0.12161283940076828,
|
| 267 |
+
"learning_rate": 8.64e-06,
|
| 268 |
+
"loss": 0.0041,
|
| 269 |
+
"step": 320
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 9.428571428571429,
|
| 273 |
+
"grad_norm": 0.2567730247974396,
|
| 274 |
+
"learning_rate": 8.560000000000001e-06,
|
| 275 |
+
"loss": 0.0012,
|
| 276 |
+
"step": 330
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 9.714285714285714,
|
| 280 |
+
"grad_norm": 0.05854232609272003,
|
| 281 |
+
"learning_rate": 8.48e-06,
|
| 282 |
+
"loss": 0.0049,
|
| 283 |
+
"step": 340
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 10.0,
|
| 287 |
+
"grad_norm": 0.032196223735809326,
|
| 288 |
+
"learning_rate": 8.400000000000001e-06,
|
| 289 |
+
"loss": 0.0045,
|
| 290 |
+
"step": 350
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 10.285714285714286,
|
| 294 |
+
"grad_norm": 0.06378399580717087,
|
| 295 |
+
"learning_rate": 8.32e-06,
|
| 296 |
+
"loss": 0.0016,
|
| 297 |
+
"step": 360
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 10.571428571428571,
|
| 301 |
+
"grad_norm": 0.08122693747282028,
|
| 302 |
+
"learning_rate": 8.24e-06,
|
| 303 |
+
"loss": 0.0015,
|
| 304 |
+
"step": 370
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 10.857142857142858,
|
| 308 |
+
"grad_norm": 0.11443732678890228,
|
| 309 |
+
"learning_rate": 8.16e-06,
|
| 310 |
+
"loss": 0.0024,
|
| 311 |
+
"step": 380
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 11.142857142857142,
|
| 315 |
+
"grad_norm": 0.11607003957033157,
|
| 316 |
+
"learning_rate": 8.08e-06,
|
| 317 |
+
"loss": 0.0024,
|
| 318 |
+
"step": 390
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 11.428571428571429,
|
| 322 |
+
"grad_norm": 0.045464884489774704,
|
| 323 |
+
"learning_rate": 8.000000000000001e-06,
|
| 324 |
+
"loss": 0.0009,
|
| 325 |
+
"step": 400
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 11.657142857142857,
|
| 329 |
+
"eval_accuracy": 0.8571428571428571,
|
| 330 |
+
"eval_f1": 0.80479302832244,
|
| 331 |
+
"eval_loss": 0.28746917843818665,
|
| 332 |
+
"eval_precision": 0.822528735632184,
|
| 333 |
+
"eval_recall": 0.7914416285832987,
|
| 334 |
+
"eval_runtime": 1.0337,
|
| 335 |
+
"eval_samples_per_second": 108.352,
|
| 336 |
+
"eval_steps_per_second": 3.87,
|
| 337 |
+
"step": 408
|
| 338 |
+
}
|
| 339 |
+
],
|
| 340 |
+
"logging_steps": 10,
|
| 341 |
+
"max_steps": 1400,
|
| 342 |
+
"num_input_tokens_seen": 0,
|
| 343 |
+
"num_train_epochs": 40,
|
| 344 |
+
"save_steps": 204,
|
| 345 |
+
"stateful_callbacks": {
|
| 346 |
+
"EarlyStoppingCallback": {
|
| 347 |
+
"args": {
|
| 348 |
+
"early_stopping_patience": 3,
|
| 349 |
+
"early_stopping_threshold": 0.0
|
| 350 |
+
},
|
| 351 |
+
"attributes": {
|
| 352 |
+
"early_stopping_patience_counter": 1
|
| 353 |
+
}
|
| 354 |
+
},
|
| 355 |
+
"TrainerControl": {
|
| 356 |
+
"args": {
|
| 357 |
+
"should_epoch_stop": false,
|
| 358 |
+
"should_evaluate": false,
|
| 359 |
+
"should_log": false,
|
| 360 |
+
"should_save": true,
|
| 361 |
+
"should_training_stop": false
|
| 362 |
+
},
|
| 363 |
+
"attributes": {}
|
| 364 |
+
}
|
| 365 |
+
},
|
| 366 |
+
"total_flos": 5223730116435600.0,
|
| 367 |
+
"train_batch_size": 32,
|
| 368 |
+
"trial_name": null,
|
| 369 |
+
"trial_params": null
|
| 370 |
+
}
|
IA-AzMina/modelos/checkpoint-408/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c556610c244fe3eab515697c5ad7e5a77de9be99acdc6711f4e42e2e85d0d4c7
|
| 3 |
+
size 5368
|
IA-AzMina/modelos/checkpoint-612/config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "belisards/congretimbau",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.05,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"directionality": "bidi",
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.05,
|
| 11 |
+
"hidden_size": 1024,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "0",
|
| 14 |
+
"1": "1"
|
| 15 |
+
},
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 4096,
|
| 18 |
+
"label2id": {
|
| 19 |
+
"0": 0,
|
| 20 |
+
"1": 1
|
| 21 |
+
},
|
| 22 |
+
"layer_norm_eps": 1e-12,
|
| 23 |
+
"max_position_embeddings": 512,
|
| 24 |
+
"model_type": "bert",
|
| 25 |
+
"num_attention_heads": 16,
|
| 26 |
+
"num_hidden_layers": 24,
|
| 27 |
+
"output_past": true,
|
| 28 |
+
"pad_token_id": 0,
|
| 29 |
+
"pooler_fc_size": 768,
|
| 30 |
+
"pooler_num_attention_heads": 12,
|
| 31 |
+
"pooler_num_fc_layers": 3,
|
| 32 |
+
"pooler_size_per_head": 128,
|
| 33 |
+
"pooler_type": "first_token_transform",
|
| 34 |
+
"position_embedding_type": "absolute",
|
| 35 |
+
"problem_type": "single_label_classification",
|
| 36 |
+
"torch_dtype": "float32",
|
| 37 |
+
"transformers_version": "4.47.0",
|
| 38 |
+
"type_vocab_size": 2,
|
| 39 |
+
"use_cache": true,
|
| 40 |
+
"vocab_size": 29794
|
| 41 |
+
}
|
IA-AzMina/modelos/checkpoint-612/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2a12949bae3c6a0dc8741e3cb5df66d67500c579b47758491203a04e6aefa347
|
| 3 |
+
size 1337640872
|
IA-AzMina/modelos/checkpoint-612/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc69d74a232ec31240a45a5c24ca93b31d671cb43a2a38cc1643ca2977a5446e
|
| 3 |
+
size 2675516653
|
IA-AzMina/modelos/checkpoint-612/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eeb54e8e8abe2027bb41470139704f1b4ae8b9f5ba9e452c964b005706aed2b2
|
| 3 |
+
size 14244
|
IA-AzMina/modelos/checkpoint-612/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4c38b636cd1ea33d1b1f4ff4bbf0a94950d0334576f9fd4b3b6ca2001c0bc80b
|
| 3 |
+
size 1064
|
IA-AzMina/modelos/checkpoint-612/trainer_state.json
ADDED
|
@@ -0,0 +1,541 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.80479302832244,
|
| 3 |
+
"best_model_checkpoint": "/content/drive/MyDrive/IA-AzMina/modelos/checkpoint-306",
|
| 4 |
+
"epoch": 17.485714285714284,
|
| 5 |
+
"eval_steps": 102,
|
| 6 |
+
"global_step": 612,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.2857142857142857,
|
| 13 |
+
"grad_norm": 7.993121147155762,
|
| 14 |
+
"learning_rate": 6.666666666666667e-07,
|
| 15 |
+
"loss": 0.2403,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.5714285714285714,
|
| 20 |
+
"grad_norm": 3.0666286945343018,
|
| 21 |
+
"learning_rate": 1.3333333333333334e-06,
|
| 22 |
+
"loss": 0.1919,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.8571428571428571,
|
| 27 |
+
"grad_norm": 1.189735770225525,
|
| 28 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 29 |
+
"loss": 0.1434,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 1.1428571428571428,
|
| 34 |
+
"grad_norm": 5.863226413726807,
|
| 35 |
+
"learning_rate": 2.666666666666667e-06,
|
| 36 |
+
"loss": 0.1568,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 1.4285714285714286,
|
| 41 |
+
"grad_norm": 1.1394373178482056,
|
| 42 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 43 |
+
"loss": 0.1171,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.7142857142857144,
|
| 48 |
+
"grad_norm": 1.28859543800354,
|
| 49 |
+
"learning_rate": 4.000000000000001e-06,
|
| 50 |
+
"loss": 0.1281,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 2.0,
|
| 55 |
+
"grad_norm": 3.0536108016967773,
|
| 56 |
+
"learning_rate": 4.666666666666667e-06,
|
| 57 |
+
"loss": 0.1441,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 2.2857142857142856,
|
| 62 |
+
"grad_norm": 1.9521867036819458,
|
| 63 |
+
"learning_rate": 5.333333333333334e-06,
|
| 64 |
+
"loss": 0.1304,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 2.571428571428571,
|
| 69 |
+
"grad_norm": 1.1799356937408447,
|
| 70 |
+
"learning_rate": 6e-06,
|
| 71 |
+
"loss": 0.0976,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 2.857142857142857,
|
| 76 |
+
"grad_norm": 1.355656385421753,
|
| 77 |
+
"learning_rate": 6.666666666666667e-06,
|
| 78 |
+
"loss": 0.1206,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 2.914285714285714,
|
| 83 |
+
"eval_accuracy": 0.8392857142857143,
|
| 84 |
+
"eval_f1": 0.7613636363636364,
|
| 85 |
+
"eval_loss": 0.10990084707736969,
|
| 86 |
+
"eval_precision": 0.819468024900962,
|
| 87 |
+
"eval_recall": 0.7345243041130037,
|
| 88 |
+
"eval_runtime": 1.047,
|
| 89 |
+
"eval_samples_per_second": 106.971,
|
| 90 |
+
"eval_steps_per_second": 3.82,
|
| 91 |
+
"step": 102
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 3.142857142857143,
|
| 95 |
+
"grad_norm": 1.0178292989730835,
|
| 96 |
+
"learning_rate": 7.333333333333333e-06,
|
| 97 |
+
"loss": 0.1002,
|
| 98 |
+
"step": 110
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 3.4285714285714284,
|
| 102 |
+
"grad_norm": 3.186685800552368,
|
| 103 |
+
"learning_rate": 8.000000000000001e-06,
|
| 104 |
+
"loss": 0.1003,
|
| 105 |
+
"step": 120
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 3.7142857142857144,
|
| 109 |
+
"grad_norm": 3.820305347442627,
|
| 110 |
+
"learning_rate": 8.666666666666668e-06,
|
| 111 |
+
"loss": 0.1055,
|
| 112 |
+
"step": 130
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 4.0,
|
| 116 |
+
"grad_norm": 3.202270269393921,
|
| 117 |
+
"learning_rate": 9.333333333333334e-06,
|
| 118 |
+
"loss": 0.0954,
|
| 119 |
+
"step": 140
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 4.285714285714286,
|
| 123 |
+
"grad_norm": 1.2107843160629272,
|
| 124 |
+
"learning_rate": 1e-05,
|
| 125 |
+
"loss": 0.0792,
|
| 126 |
+
"step": 150
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 4.571428571428571,
|
| 130 |
+
"grad_norm": 0.7708235383033752,
|
| 131 |
+
"learning_rate": 9.920000000000002e-06,
|
| 132 |
+
"loss": 0.0687,
|
| 133 |
+
"step": 160
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 4.857142857142857,
|
| 137 |
+
"grad_norm": 2.158849000930786,
|
| 138 |
+
"learning_rate": 9.84e-06,
|
| 139 |
+
"loss": 0.0815,
|
| 140 |
+
"step": 170
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 5.142857142857143,
|
| 144 |
+
"grad_norm": 1.280442714691162,
|
| 145 |
+
"learning_rate": 9.760000000000001e-06,
|
| 146 |
+
"loss": 0.0729,
|
| 147 |
+
"step": 180
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 5.428571428571429,
|
| 151 |
+
"grad_norm": 0.9879515171051025,
|
| 152 |
+
"learning_rate": 9.68e-06,
|
| 153 |
+
"loss": 0.0534,
|
| 154 |
+
"step": 190
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 5.714285714285714,
|
| 158 |
+
"grad_norm": 2.0247597694396973,
|
| 159 |
+
"learning_rate": 9.600000000000001e-06,
|
| 160 |
+
"loss": 0.0448,
|
| 161 |
+
"step": 200
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 5.828571428571428,
|
| 165 |
+
"eval_accuracy": 0.8392857142857143,
|
| 166 |
+
"eval_f1": 0.7857142857142858,
|
| 167 |
+
"eval_loss": 0.11759153753519058,
|
| 168 |
+
"eval_precision": 0.7930283224400871,
|
| 169 |
+
"eval_recall": 0.7793934358122143,
|
| 170 |
+
"eval_runtime": 1.0356,
|
| 171 |
+
"eval_samples_per_second": 108.152,
|
| 172 |
+
"eval_steps_per_second": 3.863,
|
| 173 |
+
"step": 204
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 6.0,
|
| 177 |
+
"grad_norm": 1.6217639446258545,
|
| 178 |
+
"learning_rate": 9.52e-06,
|
| 179 |
+
"loss": 0.0439,
|
| 180 |
+
"step": 210
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 6.285714285714286,
|
| 184 |
+
"grad_norm": 0.7515562772750854,
|
| 185 |
+
"learning_rate": 9.440000000000001e-06,
|
| 186 |
+
"loss": 0.0227,
|
| 187 |
+
"step": 220
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 6.571428571428571,
|
| 191 |
+
"grad_norm": 0.7949752807617188,
|
| 192 |
+
"learning_rate": 9.360000000000002e-06,
|
| 193 |
+
"loss": 0.0236,
|
| 194 |
+
"step": 230
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 6.857142857142857,
|
| 198 |
+
"grad_norm": 1.0292161703109741,
|
| 199 |
+
"learning_rate": 9.280000000000001e-06,
|
| 200 |
+
"loss": 0.0309,
|
| 201 |
+
"step": 240
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 7.142857142857143,
|
| 205 |
+
"grad_norm": 1.0616097450256348,
|
| 206 |
+
"learning_rate": 9.200000000000002e-06,
|
| 207 |
+
"loss": 0.0199,
|
| 208 |
+
"step": 250
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 7.428571428571429,
|
| 212 |
+
"grad_norm": 0.13813751935958862,
|
| 213 |
+
"learning_rate": 9.12e-06,
|
| 214 |
+
"loss": 0.0112,
|
| 215 |
+
"step": 260
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 7.714285714285714,
|
| 219 |
+
"grad_norm": 0.5435482263565063,
|
| 220 |
+
"learning_rate": 9.040000000000002e-06,
|
| 221 |
+
"loss": 0.0088,
|
| 222 |
+
"step": 270
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 8.0,
|
| 226 |
+
"grad_norm": 0.13850395381450653,
|
| 227 |
+
"learning_rate": 8.96e-06,
|
| 228 |
+
"loss": 0.0101,
|
| 229 |
+
"step": 280
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 8.285714285714286,
|
| 233 |
+
"grad_norm": 0.21646977961063385,
|
| 234 |
+
"learning_rate": 8.880000000000001e-06,
|
| 235 |
+
"loss": 0.0043,
|
| 236 |
+
"step": 290
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 8.571428571428571,
|
| 240 |
+
"grad_norm": 0.4107956886291504,
|
| 241 |
+
"learning_rate": 8.8e-06,
|
| 242 |
+
"loss": 0.0069,
|
| 243 |
+
"step": 300
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 8.742857142857144,
|
| 247 |
+
"eval_accuracy": 0.8571428571428571,
|
| 248 |
+
"eval_f1": 0.80479302832244,
|
| 249 |
+
"eval_loss": 0.2356744110584259,
|
| 250 |
+
"eval_precision": 0.822528735632184,
|
| 251 |
+
"eval_recall": 0.7914416285832987,
|
| 252 |
+
"eval_runtime": 1.0345,
|
| 253 |
+
"eval_samples_per_second": 108.269,
|
| 254 |
+
"eval_steps_per_second": 3.867,
|
| 255 |
+
"step": 306
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 8.857142857142858,
|
| 259 |
+
"grad_norm": 0.3167528808116913,
|
| 260 |
+
"learning_rate": 8.720000000000001e-06,
|
| 261 |
+
"loss": 0.0023,
|
| 262 |
+
"step": 310
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 9.142857142857142,
|
| 266 |
+
"grad_norm": 0.12161283940076828,
|
| 267 |
+
"learning_rate": 8.64e-06,
|
| 268 |
+
"loss": 0.0041,
|
| 269 |
+
"step": 320
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 9.428571428571429,
|
| 273 |
+
"grad_norm": 0.2567730247974396,
|
| 274 |
+
"learning_rate": 8.560000000000001e-06,
|
| 275 |
+
"loss": 0.0012,
|
| 276 |
+
"step": 330
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 9.714285714285714,
|
| 280 |
+
"grad_norm": 0.05854232609272003,
|
| 281 |
+
"learning_rate": 8.48e-06,
|
| 282 |
+
"loss": 0.0049,
|
| 283 |
+
"step": 340
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 10.0,
|
| 287 |
+
"grad_norm": 0.032196223735809326,
|
| 288 |
+
"learning_rate": 8.400000000000001e-06,
|
| 289 |
+
"loss": 0.0045,
|
| 290 |
+
"step": 350
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 10.285714285714286,
|
| 294 |
+
"grad_norm": 0.06378399580717087,
|
| 295 |
+
"learning_rate": 8.32e-06,
|
| 296 |
+
"loss": 0.0016,
|
| 297 |
+
"step": 360
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 10.571428571428571,
|
| 301 |
+
"grad_norm": 0.08122693747282028,
|
| 302 |
+
"learning_rate": 8.24e-06,
|
| 303 |
+
"loss": 0.0015,
|
| 304 |
+
"step": 370
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 10.857142857142858,
|
| 308 |
+
"grad_norm": 0.11443732678890228,
|
| 309 |
+
"learning_rate": 8.16e-06,
|
| 310 |
+
"loss": 0.0024,
|
| 311 |
+
"step": 380
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 11.142857142857142,
|
| 315 |
+
"grad_norm": 0.11607003957033157,
|
| 316 |
+
"learning_rate": 8.08e-06,
|
| 317 |
+
"loss": 0.0024,
|
| 318 |
+
"step": 390
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 11.428571428571429,
|
| 322 |
+
"grad_norm": 0.045464884489774704,
|
| 323 |
+
"learning_rate": 8.000000000000001e-06,
|
| 324 |
+
"loss": 0.0009,
|
| 325 |
+
"step": 400
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 11.657142857142857,
|
| 329 |
+
"eval_accuracy": 0.8571428571428571,
|
| 330 |
+
"eval_f1": 0.80479302832244,
|
| 331 |
+
"eval_loss": 0.28746917843818665,
|
| 332 |
+
"eval_precision": 0.822528735632184,
|
| 333 |
+
"eval_recall": 0.7914416285832987,
|
| 334 |
+
"eval_runtime": 1.0337,
|
| 335 |
+
"eval_samples_per_second": 108.352,
|
| 336 |
+
"eval_steps_per_second": 3.87,
|
| 337 |
+
"step": 408
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 11.714285714285714,
|
| 341 |
+
"grad_norm": 0.6379269957542419,
|
| 342 |
+
"learning_rate": 7.92e-06,
|
| 343 |
+
"loss": 0.002,
|
| 344 |
+
"step": 410
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 12.0,
|
| 348 |
+
"grad_norm": 0.03601688891649246,
|
| 349 |
+
"learning_rate": 7.840000000000001e-06,
|
| 350 |
+
"loss": 0.0043,
|
| 351 |
+
"step": 420
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 12.285714285714286,
|
| 355 |
+
"grad_norm": 0.05463436618447304,
|
| 356 |
+
"learning_rate": 7.76e-06,
|
| 357 |
+
"loss": 0.0007,
|
| 358 |
+
"step": 430
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 12.571428571428571,
|
| 362 |
+
"grad_norm": 0.03801661357283592,
|
| 363 |
+
"learning_rate": 7.680000000000001e-06,
|
| 364 |
+
"loss": 0.0014,
|
| 365 |
+
"step": 440
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 12.857142857142858,
|
| 369 |
+
"grad_norm": 0.14569824934005737,
|
| 370 |
+
"learning_rate": 7.600000000000001e-06,
|
| 371 |
+
"loss": 0.0016,
|
| 372 |
+
"step": 450
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 13.142857142857142,
|
| 376 |
+
"grad_norm": 0.03199531510472298,
|
| 377 |
+
"learning_rate": 7.520000000000001e-06,
|
| 378 |
+
"loss": 0.001,
|
| 379 |
+
"step": 460
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 13.428571428571429,
|
| 383 |
+
"grad_norm": 0.046058498322963715,
|
| 384 |
+
"learning_rate": 7.440000000000001e-06,
|
| 385 |
+
"loss": 0.0005,
|
| 386 |
+
"step": 470
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 13.714285714285714,
|
| 390 |
+
"grad_norm": 0.7392578721046448,
|
| 391 |
+
"learning_rate": 7.360000000000001e-06,
|
| 392 |
+
"loss": 0.0026,
|
| 393 |
+
"step": 480
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 14.0,
|
| 397 |
+
"grad_norm": 0.05768726393580437,
|
| 398 |
+
"learning_rate": 7.280000000000001e-06,
|
| 399 |
+
"loss": 0.0004,
|
| 400 |
+
"step": 490
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 14.285714285714286,
|
| 404 |
+
"grad_norm": 0.029751360416412354,
|
| 405 |
+
"learning_rate": 7.2000000000000005e-06,
|
| 406 |
+
"loss": 0.0003,
|
| 407 |
+
"step": 500
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 14.571428571428571,
|
| 411 |
+
"grad_norm": 0.010745550505816936,
|
| 412 |
+
"learning_rate": 7.1200000000000004e-06,
|
| 413 |
+
"loss": 0.0003,
|
| 414 |
+
"step": 510
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 14.571428571428571,
|
| 418 |
+
"eval_accuracy": 0.8482142857142857,
|
| 419 |
+
"eval_f1": 0.7951586874663799,
|
| 420 |
+
"eval_loss": 0.3132219910621643,
|
| 421 |
+
"eval_precision": 0.8072450805008944,
|
| 422 |
+
"eval_recall": 0.7854175321977566,
|
| 423 |
+
"eval_runtime": 1.0368,
|
| 424 |
+
"eval_samples_per_second": 108.023,
|
| 425 |
+
"eval_steps_per_second": 3.858,
|
| 426 |
+
"step": 510
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 14.857142857142858,
|
| 430 |
+
"grad_norm": 1.0502158403396606,
|
| 431 |
+
"learning_rate": 7.04e-06,
|
| 432 |
+
"loss": 0.0011,
|
| 433 |
+
"step": 520
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 15.142857142857142,
|
| 437 |
+
"grad_norm": 0.10267035663127899,
|
| 438 |
+
"learning_rate": 6.96e-06,
|
| 439 |
+
"loss": 0.0005,
|
| 440 |
+
"step": 530
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 15.428571428571429,
|
| 444 |
+
"grad_norm": 0.011969078332185745,
|
| 445 |
+
"learning_rate": 6.88e-06,
|
| 446 |
+
"loss": 0.0002,
|
| 447 |
+
"step": 540
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 15.714285714285714,
|
| 451 |
+
"grad_norm": 0.012641573324799538,
|
| 452 |
+
"learning_rate": 6.800000000000001e-06,
|
| 453 |
+
"loss": 0.0002,
|
| 454 |
+
"step": 550
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 16.0,
|
| 458 |
+
"grad_norm": 0.06238975375890732,
|
| 459 |
+
"learning_rate": 6.720000000000001e-06,
|
| 460 |
+
"loss": 0.0002,
|
| 461 |
+
"step": 560
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 16.285714285714285,
|
| 465 |
+
"grad_norm": 0.48989102244377136,
|
| 466 |
+
"learning_rate": 6.640000000000001e-06,
|
| 467 |
+
"loss": 0.0003,
|
| 468 |
+
"step": 570
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 16.571428571428573,
|
| 472 |
+
"grad_norm": 0.020364921540021896,
|
| 473 |
+
"learning_rate": 6.560000000000001e-06,
|
| 474 |
+
"loss": 0.0002,
|
| 475 |
+
"step": 580
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 16.857142857142858,
|
| 479 |
+
"grad_norm": 0.0456659160554409,
|
| 480 |
+
"learning_rate": 6.480000000000001e-06,
|
| 481 |
+
"loss": 0.0002,
|
| 482 |
+
"step": 590
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 17.142857142857142,
|
| 486 |
+
"grad_norm": 0.010210112668573856,
|
| 487 |
+
"learning_rate": 6.4000000000000006e-06,
|
| 488 |
+
"loss": 0.0004,
|
| 489 |
+
"step": 600
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 17.428571428571427,
|
| 493 |
+
"grad_norm": 0.008525541983544827,
|
| 494 |
+
"learning_rate": 6.3200000000000005e-06,
|
| 495 |
+
"loss": 0.0002,
|
| 496 |
+
"step": 610
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 17.485714285714284,
|
| 500 |
+
"eval_accuracy": 0.8125,
|
| 501 |
+
"eval_f1": 0.7583975346687211,
|
| 502 |
+
"eval_loss": 0.32605651021003723,
|
| 503 |
+
"eval_precision": 0.755691056910569,
|
| 504 |
+
"eval_recall": 0.7613211466555878,
|
| 505 |
+
"eval_runtime": 1.0368,
|
| 506 |
+
"eval_samples_per_second": 108.022,
|
| 507 |
+
"eval_steps_per_second": 3.858,
|
| 508 |
+
"step": 612
|
| 509 |
+
}
|
| 510 |
+
],
|
| 511 |
+
"logging_steps": 10,
|
| 512 |
+
"max_steps": 1400,
|
| 513 |
+
"num_input_tokens_seen": 0,
|
| 514 |
+
"num_train_epochs": 40,
|
| 515 |
+
"save_steps": 204,
|
| 516 |
+
"stateful_callbacks": {
|
| 517 |
+
"EarlyStoppingCallback": {
|
| 518 |
+
"args": {
|
| 519 |
+
"early_stopping_patience": 3,
|
| 520 |
+
"early_stopping_threshold": 0.0
|
| 521 |
+
},
|
| 522 |
+
"attributes": {
|
| 523 |
+
"early_stopping_patience_counter": 3
|
| 524 |
+
}
|
| 525 |
+
},
|
| 526 |
+
"TrainerControl": {
|
| 527 |
+
"args": {
|
| 528 |
+
"should_epoch_stop": false,
|
| 529 |
+
"should_evaluate": false,
|
| 530 |
+
"should_log": false,
|
| 531 |
+
"should_save": true,
|
| 532 |
+
"should_training_stop": true
|
| 533 |
+
},
|
| 534 |
+
"attributes": {}
|
| 535 |
+
}
|
| 536 |
+
},
|
| 537 |
+
"total_flos": 7835394955024560.0,
|
| 538 |
+
"train_batch_size": 32,
|
| 539 |
+
"trial_name": null,
|
| 540 |
+
"trial_params": null
|
| 541 |
+
}
|
IA-AzMina/modelos/checkpoint-612/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c556610c244fe3eab515697c5ad7e5a77de9be99acdc6711f4e42e2e85d0d4c7
|
| 3 |
+
size 5368
|
README.md
ADDED
|
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: mit
|
| 4 |
+
base_model: belisards/congretimbau
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
- f1
|
| 10 |
+
- recall
|
| 11 |
+
- precision
|
| 12 |
+
model-index:
|
| 13 |
+
- name: MyDrive
|
| 14 |
+
results: []
|
| 15 |
+
---
|
| 16 |
+
|
| 17 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 18 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 19 |
+
|
| 20 |
+
# MyDrive
|
| 21 |
+
|
| 22 |
+
This model is a fine-tuned version of [belisards/congretimbau](https://huggingface.co/belisards/congretimbau) on the None dataset.
|
| 23 |
+
It achieves the following results on the evaluation set:
|
| 24 |
+
- Loss: 0.1271
|
| 25 |
+
- Accuracy: 0.8367
|
| 26 |
+
- F1: 0.7603
|
| 27 |
+
- Recall: 0.7548
|
| 28 |
+
- Precision: 0.7665
|
| 29 |
+
|
| 30 |
+
## Model description
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Intended uses & limitations
|
| 35 |
+
|
| 36 |
+
More information needed
|
| 37 |
+
|
| 38 |
+
## Training and evaluation data
|
| 39 |
+
|
| 40 |
+
More information needed
|
| 41 |
+
|
| 42 |
+
## Training procedure
|
| 43 |
+
|
| 44 |
+
### Training hyperparameters
|
| 45 |
+
|
| 46 |
+
The following hyperparameters were used during training:
|
| 47 |
+
- learning_rate: 1e-05
|
| 48 |
+
- train_batch_size: 64
|
| 49 |
+
- eval_batch_size: 64
|
| 50 |
+
- seed: 5151
|
| 51 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 52 |
+
- lr_scheduler_type: linear
|
| 53 |
+
- lr_scheduler_warmup_steps: 150
|
| 54 |
+
- num_epochs: 14
|
| 55 |
+
|
| 56 |
+
### Training results
|
| 57 |
+
|
| 58 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Recall | Precision |
|
| 59 |
+
|:-------------:|:-------:|:----:|:---------------:|:--------:|:------:|:------:|:---------:|
|
| 60 |
+
| 0.1299 | 2.8333 | 51 | 0.1261 | 0.75 | 0.5739 | 0.5733 | 0.6589 |
|
| 61 |
+
| 0.1037 | 5.6667 | 102 | 0.1088 | 0.8214 | 0.7172 | 0.6888 | 0.8124 |
|
| 62 |
+
| 0.0511 | 8.5 | 153 | 0.1180 | 0.8304 | 0.7652 | 0.7509 | 0.7860 |
|
| 63 |
+
| 0.0138 | 11.3333 | 204 | 0.1670 | 0.8304 | 0.7711 | 0.7622 | 0.7822 |
|
| 64 |
+
|
| 65 |
+
|
| 66 |
+
### Framework versions
|
| 67 |
+
|
| 68 |
+
- Transformers 4.47.0
|
| 69 |
+
- Pytorch 2.5.1+cu121
|
| 70 |
+
- Datasets 3.2.0
|
| 71 |
+
- Tokenizers 0.21.0
|
config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "belisards/congretimbau",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.05,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"directionality": "bidi",
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.05,
|
| 11 |
+
"hidden_size": 1024,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "0",
|
| 14 |
+
"1": "1"
|
| 15 |
+
},
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 4096,
|
| 18 |
+
"label2id": {
|
| 19 |
+
"0": 0,
|
| 20 |
+
"1": 1
|
| 21 |
+
},
|
| 22 |
+
"layer_norm_eps": 1e-12,
|
| 23 |
+
"max_position_embeddings": 512,
|
| 24 |
+
"model_type": "bert",
|
| 25 |
+
"num_attention_heads": 16,
|
| 26 |
+
"num_hidden_layers": 24,
|
| 27 |
+
"output_past": true,
|
| 28 |
+
"pad_token_id": 0,
|
| 29 |
+
"pooler_fc_size": 768,
|
| 30 |
+
"pooler_num_attention_heads": 12,
|
| 31 |
+
"pooler_num_fc_layers": 3,
|
| 32 |
+
"pooler_size_per_head": 128,
|
| 33 |
+
"pooler_type": "first_token_transform",
|
| 34 |
+
"position_embedding_type": "absolute",
|
| 35 |
+
"problem_type": "single_label_classification",
|
| 36 |
+
"torch_dtype": "float32",
|
| 37 |
+
"transformers_version": "4.47.0",
|
| 38 |
+
"type_vocab_size": 2,
|
| 39 |
+
"use_cache": true,
|
| 40 |
+
"vocab_size": 29794
|
| 41 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d33ddadd8d5a9d4cb954d875040a9063becee11c17d1fd92db7ce4292ea42b5a
|
| 3 |
+
size 1337640872
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a13489cbcc2e2be266ed1c5dc167ddbcb7b517347fefd4b42dddf09a3fb8f769
|
| 3 |
+
size 5368
|