File size: 5,239 Bytes
55c788c | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 | {
"best_global_step": 7670,
"best_metric": 0.8644183278083801,
"best_model_checkpoint": "tiny_bert_km_100_v2_mnli/checkpoint-7670",
"epoch": 10.0,
"eval_steps": 500,
"global_step": 15340,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"grad_norm": 0.9140164852142334,
"learning_rate": 4.9e-05,
"loss": 1.0063,
"step": 1534
},
{
"epoch": 1.0,
"eval_accuracy": 0.537238920020377,
"eval_loss": 0.947323739528656,
"eval_runtime": 2.8342,
"eval_samples_per_second": 3463.068,
"eval_steps_per_second": 13.761,
"step": 1534
},
{
"epoch": 2.0,
"grad_norm": 1.3851509094238281,
"learning_rate": 4.8e-05,
"loss": 0.916,
"step": 3068
},
{
"epoch": 2.0,
"eval_accuracy": 0.5816607233825777,
"eval_loss": 0.8941206336021423,
"eval_runtime": 2.7849,
"eval_samples_per_second": 3524.408,
"eval_steps_per_second": 14.004,
"step": 3068
},
{
"epoch": 3.0,
"grad_norm": 1.438253402709961,
"learning_rate": 4.7e-05,
"loss": 0.8629,
"step": 4602
},
{
"epoch": 3.0,
"eval_accuracy": 0.6017320427916455,
"eval_loss": 0.8664500117301941,
"eval_runtime": 2.7822,
"eval_samples_per_second": 3527.723,
"eval_steps_per_second": 14.017,
"step": 4602
},
{
"epoch": 4.0,
"grad_norm": 1.5567783117294312,
"learning_rate": 4.600000000000001e-05,
"loss": 0.8183,
"step": 6136
},
{
"epoch": 4.0,
"eval_accuracy": 0.6045848191543556,
"eval_loss": 0.8703648447990417,
"eval_runtime": 2.8078,
"eval_samples_per_second": 3495.602,
"eval_steps_per_second": 13.89,
"step": 6136
},
{
"epoch": 5.0,
"grad_norm": 1.7820237874984741,
"learning_rate": 4.5e-05,
"loss": 0.7746,
"step": 7670
},
{
"epoch": 5.0,
"eval_accuracy": 0.6161996943453897,
"eval_loss": 0.8644183278083801,
"eval_runtime": 2.8011,
"eval_samples_per_second": 3503.969,
"eval_steps_per_second": 13.923,
"step": 7670
},
{
"epoch": 6.0,
"grad_norm": 2.103147268295288,
"learning_rate": 4.4000000000000006e-05,
"loss": 0.7324,
"step": 9204
},
{
"epoch": 6.0,
"eval_accuracy": 0.6173204279164544,
"eval_loss": 0.8818243145942688,
"eval_runtime": 2.7802,
"eval_samples_per_second": 3530.372,
"eval_steps_per_second": 14.028,
"step": 9204
},
{
"epoch": 7.0,
"grad_norm": 1.9933719635009766,
"learning_rate": 4.3e-05,
"loss": 0.6902,
"step": 10738
},
{
"epoch": 7.0,
"eval_accuracy": 0.628222109016811,
"eval_loss": 0.8827255368232727,
"eval_runtime": 2.8175,
"eval_samples_per_second": 3483.629,
"eval_steps_per_second": 13.842,
"step": 10738
},
{
"epoch": 8.0,
"grad_norm": 2.3629040718078613,
"learning_rate": 4.2e-05,
"loss": 0.6478,
"step": 12272
},
{
"epoch": 8.0,
"eval_accuracy": 0.6206826286296485,
"eval_loss": 0.9343836307525635,
"eval_runtime": 2.8042,
"eval_samples_per_second": 3500.116,
"eval_steps_per_second": 13.908,
"step": 12272
},
{
"epoch": 9.0,
"grad_norm": 2.6676883697509766,
"learning_rate": 4.1e-05,
"loss": 0.6049,
"step": 13806
},
{
"epoch": 9.0,
"eval_accuracy": 0.6225165562913907,
"eval_loss": 0.9615498781204224,
"eval_runtime": 2.8505,
"eval_samples_per_second": 3443.197,
"eval_steps_per_second": 13.682,
"step": 13806
},
{
"epoch": 10.0,
"grad_norm": 2.945707082748413,
"learning_rate": 4e-05,
"loss": 0.5628,
"step": 15340
},
{
"epoch": 10.0,
"eval_accuracy": 0.6190524707080999,
"eval_loss": 0.9786139130592346,
"eval_runtime": 2.8978,
"eval_samples_per_second": 3387.031,
"eval_steps_per_second": 13.458,
"step": 15340
},
{
"epoch": 10.0,
"step": 15340,
"total_flos": 1.029836100834816e+17,
"train_loss": 0.761610681168259,
"train_runtime": 2062.3602,
"train_samples_per_second": 9520.694,
"train_steps_per_second": 37.19
}
],
"logging_steps": 1,
"max_steps": 76700,
"num_input_tokens_seen": 0,
"num_train_epochs": 50,
"save_steps": 500,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 5,
"early_stopping_threshold": 0.0
},
"attributes": {
"early_stopping_patience_counter": 5
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 1.029836100834816e+17,
"train_batch_size": 256,
"trial_name": null,
"trial_params": null
}
|