Upload folder using huggingface_hub
Browse files- README.md +27 -0
- checkpoint-60/config.json +38 -0
- checkpoint-60/model.safetensors +3 -0
- checkpoint-60/optimizer.pt +3 -0
- checkpoint-60/rng_state.pth +3 -0
- checkpoint-60/scheduler.pt +3 -0
- checkpoint-60/trainer_state.json +253 -0
- checkpoint-60/training_args.bin +3 -0
- config.json +38 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +58 -0
- training_args.bin +3 -0
- training_params.json +30 -0
- vocab.json +0 -0
README.md
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
---
|
| 3 |
+
tags:
|
| 4 |
+
- autotrain
|
| 5 |
+
- text-classification
|
| 6 |
+
widget:
|
| 7 |
+
- text: "I love AutoTrain"
|
| 8 |
+
datasets:
|
| 9 |
+
- autotrain-wewh0-x81n8/autotrain-data
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model Trained Using AutoTrain
|
| 13 |
+
|
| 14 |
+
- Problem type: Text Classification
|
| 15 |
+
|
| 16 |
+
## Validation Metrics
|
| 17 |
+
loss: 0.4244471490383148
|
| 18 |
+
|
| 19 |
+
f1: 0.0
|
| 20 |
+
|
| 21 |
+
precision: 0.0
|
| 22 |
+
|
| 23 |
+
recall: 0.0
|
| 24 |
+
|
| 25 |
+
auc: 0.7067708333333333
|
| 26 |
+
|
| 27 |
+
accuracy: 0.8275862068965517
|
checkpoint-60/config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "PlanTL-GOB-ES/roberta-base-bne",
|
| 3 |
+
"_num_labels": 2,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"RobertaForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_probs_dropout_prob": 0.0,
|
| 8 |
+
"bos_token_id": 0,
|
| 9 |
+
"classifier_dropout": null,
|
| 10 |
+
"eos_token_id": 2,
|
| 11 |
+
"gradient_checkpointing": false,
|
| 12 |
+
"hidden_act": "gelu",
|
| 13 |
+
"hidden_dropout_prob": 0.0,
|
| 14 |
+
"hidden_size": 768,
|
| 15 |
+
"id2label": {
|
| 16 |
+
"0": "alta",
|
| 17 |
+
"1": "ingreso"
|
| 18 |
+
},
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"intermediate_size": 3072,
|
| 21 |
+
"label2id": {
|
| 22 |
+
"alta": 0,
|
| 23 |
+
"ingreso": 1
|
| 24 |
+
},
|
| 25 |
+
"layer_norm_eps": 1e-05,
|
| 26 |
+
"max_position_embeddings": 514,
|
| 27 |
+
"model_type": "roberta",
|
| 28 |
+
"num_attention_heads": 12,
|
| 29 |
+
"num_hidden_layers": 12,
|
| 30 |
+
"pad_token_id": 1,
|
| 31 |
+
"position_embedding_type": "absolute",
|
| 32 |
+
"problem_type": "single_label_classification",
|
| 33 |
+
"torch_dtype": "float32",
|
| 34 |
+
"transformers_version": "4.37.0",
|
| 35 |
+
"type_vocab_size": 1,
|
| 36 |
+
"use_cache": true,
|
| 37 |
+
"vocab_size": 50262
|
| 38 |
+
}
|
checkpoint-60/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b63588e4695e2f703c018ffb78b8f623ea0909ffa0788b640c1f61e1dc111425
|
| 3 |
+
size 498603608
|
checkpoint-60/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c772e7809225c11356092d2b719d4479a3cf7b9851bf0d4b42240258166144fc
|
| 3 |
+
size 997327098
|
checkpoint-60/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e3e5d946241df2516b06d7074d8779088eae7607173ad780df56583910a9589b
|
| 3 |
+
size 14244
|
checkpoint-60/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e5004ebdf827539feee94a50499b60a54a4d8208e76ee616b3618fe350361f2e
|
| 3 |
+
size 1064
|
checkpoint-60/trainer_state.json
ADDED
|
@@ -0,0 +1,253 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.4244471490383148,
|
| 3 |
+
"best_model_checkpoint": "autotrain-wewh0-x81n8/checkpoint-60",
|
| 4 |
+
"epoch": 4.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 60,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.13,
|
| 13 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 14 |
+
"loss": 0.6797,
|
| 15 |
+
"step": 2
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.27,
|
| 19 |
+
"learning_rate": 6.666666666666667e-06,
|
| 20 |
+
"loss": 0.6762,
|
| 21 |
+
"step": 4
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.4,
|
| 25 |
+
"learning_rate": 1e-05,
|
| 26 |
+
"loss": 0.6572,
|
| 27 |
+
"step": 6
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.53,
|
| 31 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 32 |
+
"loss": 0.631,
|
| 33 |
+
"step": 8
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.67,
|
| 37 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 38 |
+
"loss": 0.6555,
|
| 39 |
+
"step": 10
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.8,
|
| 43 |
+
"learning_rate": 2e-05,
|
| 44 |
+
"loss": 0.5082,
|
| 45 |
+
"step": 12
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.93,
|
| 49 |
+
"learning_rate": 2.3333333333333336e-05,
|
| 50 |
+
"loss": 0.525,
|
| 51 |
+
"step": 14
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 1.0,
|
| 55 |
+
"eval_accuracy": 0.8275862068965517,
|
| 56 |
+
"eval_auc": 0.5322916666666666,
|
| 57 |
+
"eval_f1": 0.0,
|
| 58 |
+
"eval_loss": 0.4591643214225769,
|
| 59 |
+
"eval_precision": 0.0,
|
| 60 |
+
"eval_recall": 0.0,
|
| 61 |
+
"eval_runtime": 0.3931,
|
| 62 |
+
"eval_samples_per_second": 295.124,
|
| 63 |
+
"eval_steps_per_second": 20.353,
|
| 64 |
+
"step": 15
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 1.07,
|
| 68 |
+
"learning_rate": 2.6666666666666667e-05,
|
| 69 |
+
"loss": 0.4126,
|
| 70 |
+
"step": 16
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 1.2,
|
| 74 |
+
"learning_rate": 3e-05,
|
| 75 |
+
"loss": 0.3881,
|
| 76 |
+
"step": 18
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 1.33,
|
| 80 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 81 |
+
"loss": 0.2395,
|
| 82 |
+
"step": 20
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 1.47,
|
| 86 |
+
"learning_rate": 3.6666666666666666e-05,
|
| 87 |
+
"loss": 0.7125,
|
| 88 |
+
"step": 22
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 1.6,
|
| 92 |
+
"learning_rate": 4e-05,
|
| 93 |
+
"loss": 0.3655,
|
| 94 |
+
"step": 24
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 1.73,
|
| 98 |
+
"learning_rate": 4.3333333333333334e-05,
|
| 99 |
+
"loss": 0.4883,
|
| 100 |
+
"step": 26
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 1.87,
|
| 104 |
+
"learning_rate": 4.666666666666667e-05,
|
| 105 |
+
"loss": 0.6153,
|
| 106 |
+
"step": 28
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 2.0,
|
| 110 |
+
"learning_rate": 5e-05,
|
| 111 |
+
"loss": 0.4142,
|
| 112 |
+
"step": 30
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 2.0,
|
| 116 |
+
"eval_accuracy": 0.8275862068965517,
|
| 117 |
+
"eval_auc": 0.6164062499999999,
|
| 118 |
+
"eval_f1": 0.0,
|
| 119 |
+
"eval_loss": 0.4668600261211395,
|
| 120 |
+
"eval_precision": 0.0,
|
| 121 |
+
"eval_recall": 0.0,
|
| 122 |
+
"eval_runtime": 0.4042,
|
| 123 |
+
"eval_samples_per_second": 286.979,
|
| 124 |
+
"eval_steps_per_second": 19.792,
|
| 125 |
+
"step": 30
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 2.13,
|
| 129 |
+
"learning_rate": 4.962962962962963e-05,
|
| 130 |
+
"loss": 0.533,
|
| 131 |
+
"step": 32
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 2.27,
|
| 135 |
+
"learning_rate": 4.925925925925926e-05,
|
| 136 |
+
"loss": 0.2934,
|
| 137 |
+
"step": 34
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 2.4,
|
| 141 |
+
"learning_rate": 4.888888888888889e-05,
|
| 142 |
+
"loss": 0.5174,
|
| 143 |
+
"step": 36
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 2.53,
|
| 147 |
+
"learning_rate": 4.851851851851852e-05,
|
| 148 |
+
"loss": 0.4464,
|
| 149 |
+
"step": 38
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 2.67,
|
| 153 |
+
"learning_rate": 4.814814814814815e-05,
|
| 154 |
+
"loss": 0.4544,
|
| 155 |
+
"step": 40
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 2.8,
|
| 159 |
+
"learning_rate": 4.796296296296296e-05,
|
| 160 |
+
"loss": 0.5618,
|
| 161 |
+
"step": 42
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 2.93,
|
| 165 |
+
"learning_rate": 4.759259259259259e-05,
|
| 166 |
+
"loss": 0.4412,
|
| 167 |
+
"step": 44
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 3.0,
|
| 171 |
+
"eval_accuracy": 0.8275862068965517,
|
| 172 |
+
"eval_auc": 0.6213541666666668,
|
| 173 |
+
"eval_f1": 0.0,
|
| 174 |
+
"eval_loss": 0.49061912298202515,
|
| 175 |
+
"eval_precision": 0.0,
|
| 176 |
+
"eval_recall": 0.0,
|
| 177 |
+
"eval_runtime": 0.385,
|
| 178 |
+
"eval_samples_per_second": 301.322,
|
| 179 |
+
"eval_steps_per_second": 20.781,
|
| 180 |
+
"step": 45
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 3.07,
|
| 184 |
+
"learning_rate": 4.722222222222222e-05,
|
| 185 |
+
"loss": 0.5116,
|
| 186 |
+
"step": 46
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 3.2,
|
| 190 |
+
"learning_rate": 4.685185185185185e-05,
|
| 191 |
+
"loss": 0.4371,
|
| 192 |
+
"step": 48
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 3.33,
|
| 196 |
+
"learning_rate": 4.648148148148148e-05,
|
| 197 |
+
"loss": 0.3013,
|
| 198 |
+
"step": 50
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 3.47,
|
| 202 |
+
"learning_rate": 4.6111111111111115e-05,
|
| 203 |
+
"loss": 0.1664,
|
| 204 |
+
"step": 52
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 3.6,
|
| 208 |
+
"learning_rate": 4.5740740740740745e-05,
|
| 209 |
+
"loss": 0.2152,
|
| 210 |
+
"step": 54
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 3.73,
|
| 214 |
+
"learning_rate": 4.5370370370370374e-05,
|
| 215 |
+
"loss": 0.8311,
|
| 216 |
+
"step": 56
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 3.87,
|
| 220 |
+
"learning_rate": 4.5e-05,
|
| 221 |
+
"loss": 0.3329,
|
| 222 |
+
"step": 58
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 4.0,
|
| 226 |
+
"learning_rate": 4.462962962962963e-05,
|
| 227 |
+
"loss": 0.1868,
|
| 228 |
+
"step": 60
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 4.0,
|
| 232 |
+
"eval_accuracy": 0.8275862068965517,
|
| 233 |
+
"eval_auc": 0.7067708333333333,
|
| 234 |
+
"eval_f1": 0.0,
|
| 235 |
+
"eval_loss": 0.4244471490383148,
|
| 236 |
+
"eval_precision": 0.0,
|
| 237 |
+
"eval_recall": 0.0,
|
| 238 |
+
"eval_runtime": 0.3986,
|
| 239 |
+
"eval_samples_per_second": 291.021,
|
| 240 |
+
"eval_steps_per_second": 20.07,
|
| 241 |
+
"step": 60
|
| 242 |
+
}
|
| 243 |
+
],
|
| 244 |
+
"logging_steps": 2,
|
| 245 |
+
"max_steps": 300,
|
| 246 |
+
"num_input_tokens_seen": 0,
|
| 247 |
+
"num_train_epochs": 20,
|
| 248 |
+
"save_steps": 500,
|
| 249 |
+
"total_flos": 30520882421760.0,
|
| 250 |
+
"train_batch_size": 8,
|
| 251 |
+
"trial_name": null,
|
| 252 |
+
"trial_params": null
|
| 253 |
+
}
|
checkpoint-60/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b488a97ce01e90b20f70dc687a2da9afa83f67cedcab115c0fb409b14b02c57a
|
| 3 |
+
size 4728
|
config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "PlanTL-GOB-ES/roberta-base-bne",
|
| 3 |
+
"_num_labels": 2,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"RobertaForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_probs_dropout_prob": 0.0,
|
| 8 |
+
"bos_token_id": 0,
|
| 9 |
+
"classifier_dropout": null,
|
| 10 |
+
"eos_token_id": 2,
|
| 11 |
+
"gradient_checkpointing": false,
|
| 12 |
+
"hidden_act": "gelu",
|
| 13 |
+
"hidden_dropout_prob": 0.0,
|
| 14 |
+
"hidden_size": 768,
|
| 15 |
+
"id2label": {
|
| 16 |
+
"0": "alta",
|
| 17 |
+
"1": "ingreso"
|
| 18 |
+
},
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"intermediate_size": 3072,
|
| 21 |
+
"label2id": {
|
| 22 |
+
"alta": 0,
|
| 23 |
+
"ingreso": 1
|
| 24 |
+
},
|
| 25 |
+
"layer_norm_eps": 1e-05,
|
| 26 |
+
"max_position_embeddings": 514,
|
| 27 |
+
"model_type": "roberta",
|
| 28 |
+
"num_attention_heads": 12,
|
| 29 |
+
"num_hidden_layers": 12,
|
| 30 |
+
"pad_token_id": 1,
|
| 31 |
+
"position_embedding_type": "absolute",
|
| 32 |
+
"problem_type": "single_label_classification",
|
| 33 |
+
"torch_dtype": "float32",
|
| 34 |
+
"transformers_version": "4.37.0",
|
| 35 |
+
"type_vocab_size": 1,
|
| 36 |
+
"use_cache": true,
|
| 37 |
+
"vocab_size": 50262
|
| 38 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b63588e4695e2f703c018ffb78b8f623ea0909ffa0788b640c1f61e1dc111425
|
| 3 |
+
size 498603608
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": true,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"4": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": true,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": true,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"mask_token": "<mask>",
|
| 51 |
+
"max_len": 512,
|
| 52 |
+
"model_max_length": 512,
|
| 53 |
+
"pad_token": "<pad>",
|
| 54 |
+
"sep_token": "</s>",
|
| 55 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 56 |
+
"trim_offsets": true,
|
| 57 |
+
"unk_token": "<unk>"
|
| 58 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b488a97ce01e90b20f70dc687a2da9afa83f67cedcab115c0fb409b14b02c57a
|
| 3 |
+
size 4728
|
training_params.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"data_path": "autotrain-wewh0-x81n8/autotrain-data",
|
| 3 |
+
"model": "PlanTL-GOB-ES/roberta-base-bne",
|
| 4 |
+
"lr": 5e-05,
|
| 5 |
+
"epochs": 20,
|
| 6 |
+
"max_seq_length": 128,
|
| 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-wewh0-x81n8",
|
| 21 |
+
"auto_find_batch_size": false,
|
| 22 |
+
"mixed_precision": "fp16",
|
| 23 |
+
"save_total_limit": 1,
|
| 24 |
+
"save_strategy": "epoch",
|
| 25 |
+
"push_to_hub": true,
|
| 26 |
+
"repo_id": "fecia/autotrain-wewh0-x81n8",
|
| 27 |
+
"evaluation_strategy": "epoch",
|
| 28 |
+
"username": "fecia",
|
| 29 |
+
"log": "none"
|
| 30 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|