File size: 5,149 Bytes
477368e | 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 | {
"best_global_step": 69,
"best_metric": 2.357128858566284,
"best_model_checkpoint": "tiny_bert_rand_100_v2_stsb/checkpoint-69",
"epoch": 8.0,
"eval_steps": 500,
"global_step": 184,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"grad_norm": 7.353635311126709,
"learning_rate": 4.9e-05,
"loss": 3.0934,
"step": 23
},
{
"epoch": 1.0,
"eval_combined_score": 0.1262982832568416,
"eval_loss": 2.4178946018218994,
"eval_pearson": 0.1274026693406406,
"eval_runtime": 0.4494,
"eval_samples_per_second": 3337.766,
"eval_spearmanr": 0.12519389717304258,
"eval_steps_per_second": 13.351,
"step": 23
},
{
"epoch": 2.0,
"grad_norm": 3.9686944484710693,
"learning_rate": 4.8e-05,
"loss": 2.0262,
"step": 46
},
{
"epoch": 2.0,
"eval_combined_score": 0.08032337810098913,
"eval_loss": 2.822695255279541,
"eval_pearson": 0.09062722453006844,
"eval_runtime": 0.483,
"eval_samples_per_second": 3105.343,
"eval_spearmanr": 0.07001953167190983,
"eval_steps_per_second": 12.421,
"step": 46
},
{
"epoch": 3.0,
"grad_norm": 4.415579319000244,
"learning_rate": 4.7e-05,
"loss": 1.8632,
"step": 69
},
{
"epoch": 3.0,
"eval_combined_score": 0.18249862203222653,
"eval_loss": 2.357128858566284,
"eval_pearson": 0.19035307550832772,
"eval_runtime": 0.4733,
"eval_samples_per_second": 3168.942,
"eval_spearmanr": 0.17464416855612533,
"eval_steps_per_second": 12.676,
"step": 69
},
{
"epoch": 4.0,
"grad_norm": 6.482253551483154,
"learning_rate": 4.600000000000001e-05,
"loss": 1.6504,
"step": 92
},
{
"epoch": 4.0,
"eval_combined_score": 0.23817120921581703,
"eval_loss": 2.4674251079559326,
"eval_pearson": 0.24049226357258544,
"eval_runtime": 0.4467,
"eval_samples_per_second": 3358.126,
"eval_spearmanr": 0.23585015485904862,
"eval_steps_per_second": 13.433,
"step": 92
},
{
"epoch": 5.0,
"grad_norm": 7.711766719818115,
"learning_rate": 4.5e-05,
"loss": 1.376,
"step": 115
},
{
"epoch": 5.0,
"eval_combined_score": 0.24243941396924645,
"eval_loss": 2.41092848777771,
"eval_pearson": 0.24433716723818158,
"eval_runtime": 0.4757,
"eval_samples_per_second": 3153.427,
"eval_spearmanr": 0.2405416607003113,
"eval_steps_per_second": 12.614,
"step": 115
},
{
"epoch": 6.0,
"grad_norm": 7.9283013343811035,
"learning_rate": 4.4000000000000006e-05,
"loss": 1.1686,
"step": 138
},
{
"epoch": 6.0,
"eval_combined_score": 0.2585957948418378,
"eval_loss": 2.5537660121917725,
"eval_pearson": 0.2572703578545987,
"eval_runtime": 0.46,
"eval_samples_per_second": 3260.655,
"eval_spearmanr": 0.2599212318290769,
"eval_steps_per_second": 13.043,
"step": 138
},
{
"epoch": 7.0,
"grad_norm": 8.92582893371582,
"learning_rate": 4.3e-05,
"loss": 0.9782,
"step": 161
},
{
"epoch": 7.0,
"eval_combined_score": 0.26390896222736915,
"eval_loss": 2.6227357387542725,
"eval_pearson": 0.2622185613208425,
"eval_runtime": 0.489,
"eval_samples_per_second": 3067.175,
"eval_spearmanr": 0.2655993631338958,
"eval_steps_per_second": 12.269,
"step": 161
},
{
"epoch": 8.0,
"grad_norm": 16.892637252807617,
"learning_rate": 4.2e-05,
"loss": 0.8135,
"step": 184
},
{
"epoch": 8.0,
"eval_combined_score": 0.234079183599613,
"eval_loss": 3.0192532539367676,
"eval_pearson": 0.2304551048967358,
"eval_runtime": 0.4608,
"eval_samples_per_second": 3255.012,
"eval_spearmanr": 0.23770326230249023,
"eval_steps_per_second": 13.02,
"step": 184
},
{
"epoch": 8.0,
"step": 184,
"total_flos": 1206038564302848.0,
"train_loss": 1.6211834264838176,
"train_runtime": 33.9359,
"train_samples_per_second": 8470.39,
"train_steps_per_second": 33.887
}
],
"logging_steps": 1,
"max_steps": 1150,
"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": 1206038564302848.0,
"train_batch_size": 256,
"trial_name": null,
"trial_params": null
}
|