Commit
•
bb0a0bc
1
Parent(s):
d5f4b14
Upload 6 files
Browse files- merges.txt +0 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
- trainer_state.json +241 -0
- vocab.json +0 -0
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": {
|
| 6 |
+
"content": "<mask>",
|
| 7 |
+
"lstrip": true,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "</s>",
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"cls_token": "<s>",
|
| 5 |
+
"eos_token": "</s>",
|
| 6 |
+
"errors": "replace",
|
| 7 |
+
"mask_token": "<mask>",
|
| 8 |
+
"model_max_length": 512,
|
| 9 |
+
"name_or_path": "roberta-base",
|
| 10 |
+
"pad_token": "<pad>",
|
| 11 |
+
"sep_token": "</s>",
|
| 12 |
+
"special_tokens_map_file": null,
|
| 13 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 14 |
+
"trim_offsets": true,
|
| 15 |
+
"unk_token": "<unk>"
|
| 16 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,241 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.5862595419847328,
|
| 3 |
+
"best_model_checkpoint": "roberta-base-go_emotions/checkpoint-16281",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"global_step": 16281,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.09,
|
| 12 |
+
"learning_rate": 1.9815736134144095e-05,
|
| 13 |
+
"loss": 0.1826,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.18,
|
| 18 |
+
"learning_rate": 1.963147226828819e-05,
|
| 19 |
+
"loss": 0.1317,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.28,
|
| 24 |
+
"learning_rate": 1.9447208402432286e-05,
|
| 25 |
+
"loss": 0.1146,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.37,
|
| 30 |
+
"learning_rate": 1.9262944536576377e-05,
|
| 31 |
+
"loss": 0.1078,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.46,
|
| 36 |
+
"learning_rate": 1.9078680670720474e-05,
|
| 37 |
+
"loss": 0.1006,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.55,
|
| 42 |
+
"learning_rate": 1.8894416804864568e-05,
|
| 43 |
+
"loss": 0.0976,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.64,
|
| 48 |
+
"learning_rate": 1.871015293900866e-05,
|
| 49 |
+
"loss": 0.096,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.74,
|
| 54 |
+
"learning_rate": 1.8525889073152755e-05,
|
| 55 |
+
"loss": 0.0925,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.83,
|
| 60 |
+
"learning_rate": 1.8341625207296852e-05,
|
| 61 |
+
"loss": 0.0921,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.92,
|
| 66 |
+
"learning_rate": 1.8157361341440943e-05,
|
| 67 |
+
"loss": 0.0911,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.0,
|
| 72 |
+
"eval_accuracy": 0.40213785477331365,
|
| 73 |
+
"eval_f1": 0.5346146303196705,
|
| 74 |
+
"eval_loss": 0.08816272765398026,
|
| 75 |
+
"eval_roc_auc": 0.7098850238721621,
|
| 76 |
+
"eval_runtime": 11.8306,
|
| 77 |
+
"eval_samples_per_second": 458.641,
|
| 78 |
+
"eval_steps_per_second": 57.394,
|
| 79 |
+
"step": 5427
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 1.01,
|
| 83 |
+
"learning_rate": 1.797309747558504e-05,
|
| 84 |
+
"loss": 0.0897,
|
| 85 |
+
"step": 5500
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 1.11,
|
| 89 |
+
"learning_rate": 1.7788833609729134e-05,
|
| 90 |
+
"loss": 0.0856,
|
| 91 |
+
"step": 6000
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 1.2,
|
| 95 |
+
"learning_rate": 1.7604569743873227e-05,
|
| 96 |
+
"loss": 0.0816,
|
| 97 |
+
"step": 6500
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 1.29,
|
| 101 |
+
"learning_rate": 1.742030587801732e-05,
|
| 102 |
+
"loss": 0.0853,
|
| 103 |
+
"step": 7000
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 1.38,
|
| 107 |
+
"learning_rate": 1.7236042012161415e-05,
|
| 108 |
+
"loss": 0.0846,
|
| 109 |
+
"step": 7500
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 1.47,
|
| 113 |
+
"learning_rate": 1.7051778146305512e-05,
|
| 114 |
+
"loss": 0.0843,
|
| 115 |
+
"step": 8000
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 1.57,
|
| 119 |
+
"learning_rate": 1.6867514280449606e-05,
|
| 120 |
+
"loss": 0.0807,
|
| 121 |
+
"step": 8500
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 1.66,
|
| 125 |
+
"learning_rate": 1.66832504145937e-05,
|
| 126 |
+
"loss": 0.0796,
|
| 127 |
+
"step": 9000
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 1.75,
|
| 131 |
+
"learning_rate": 1.6498986548737793e-05,
|
| 132 |
+
"loss": 0.081,
|
| 133 |
+
"step": 9500
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 1.84,
|
| 137 |
+
"learning_rate": 1.6314722682881887e-05,
|
| 138 |
+
"loss": 0.0798,
|
| 139 |
+
"step": 10000
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 1.93,
|
| 143 |
+
"learning_rate": 1.613045881702598e-05,
|
| 144 |
+
"loss": 0.0821,
|
| 145 |
+
"step": 10500
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 2.0,
|
| 149 |
+
"eval_accuracy": 0.44010320678216,
|
| 150 |
+
"eval_f1": 0.5612426312342098,
|
| 151 |
+
"eval_loss": 0.08432479202747345,
|
| 152 |
+
"eval_roc_auc": 0.7305379849481191,
|
| 153 |
+
"eval_runtime": 11.8056,
|
| 154 |
+
"eval_samples_per_second": 459.613,
|
| 155 |
+
"eval_steps_per_second": 57.515,
|
| 156 |
+
"step": 10854
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 2.03,
|
| 160 |
+
"learning_rate": 1.5946194951170078e-05,
|
| 161 |
+
"loss": 0.0776,
|
| 162 |
+
"step": 11000
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 2.12,
|
| 166 |
+
"learning_rate": 1.5761931085314172e-05,
|
| 167 |
+
"loss": 0.0726,
|
| 168 |
+
"step": 11500
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 2.21,
|
| 172 |
+
"learning_rate": 1.5577667219458266e-05,
|
| 173 |
+
"loss": 0.0718,
|
| 174 |
+
"step": 12000
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 2.3,
|
| 178 |
+
"learning_rate": 1.539340335360236e-05,
|
| 179 |
+
"loss": 0.0735,
|
| 180 |
+
"step": 12500
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 2.4,
|
| 184 |
+
"learning_rate": 1.5209139487746453e-05,
|
| 185 |
+
"loss": 0.0735,
|
| 186 |
+
"step": 13000
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 2.49,
|
| 190 |
+
"learning_rate": 1.5024875621890549e-05,
|
| 191 |
+
"loss": 0.0721,
|
| 192 |
+
"step": 13500
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 2.58,
|
| 196 |
+
"learning_rate": 1.4840611756034643e-05,
|
| 197 |
+
"loss": 0.0722,
|
| 198 |
+
"step": 14000
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 2.67,
|
| 202 |
+
"learning_rate": 1.4656347890178736e-05,
|
| 203 |
+
"loss": 0.0751,
|
| 204 |
+
"step": 14500
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 2.76,
|
| 208 |
+
"learning_rate": 1.4472084024322832e-05,
|
| 209 |
+
"loss": 0.0727,
|
| 210 |
+
"step": 15000
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 2.86,
|
| 214 |
+
"learning_rate": 1.4287820158466926e-05,
|
| 215 |
+
"loss": 0.0735,
|
| 216 |
+
"step": 15500
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 2.95,
|
| 220 |
+
"learning_rate": 1.4103556292611021e-05,
|
| 221 |
+
"loss": 0.0714,
|
| 222 |
+
"step": 16000
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 3.0,
|
| 226 |
+
"eval_accuracy": 0.47475119793586434,
|
| 227 |
+
"eval_f1": 0.5862595419847328,
|
| 228 |
+
"eval_loss": 0.0838962271809578,
|
| 229 |
+
"eval_roc_auc": 0.7506773514396311,
|
| 230 |
+
"eval_runtime": 11.8261,
|
| 231 |
+
"eval_samples_per_second": 458.814,
|
| 232 |
+
"eval_steps_per_second": 57.415,
|
| 233 |
+
"step": 16281
|
| 234 |
+
}
|
| 235 |
+
],
|
| 236 |
+
"max_steps": 54270,
|
| 237 |
+
"num_train_epochs": 10,
|
| 238 |
+
"total_flos": 8568237917583360.0,
|
| 239 |
+
"trial_name": null,
|
| 240 |
+
"trial_params": null
|
| 241 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|