File size: 5,631 Bytes
ae30720 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 | {
"best_global_step": 92,
"best_metric": 2.387584686279297,
"best_model_checkpoint": "tiny_bert_rand_5_v1_stsb/checkpoint-92",
"epoch": 9.0,
"eval_steps": 500,
"global_step": 207,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"grad_norm": 6.732455253601074,
"learning_rate": 4.9e-05,
"loss": 3.4897,
"step": 23
},
{
"epoch": 1.0,
"eval_combined_score": 0.06359102083043883,
"eval_loss": 2.4595422744750977,
"eval_pearson": 0.06898776371218468,
"eval_runtime": 0.4536,
"eval_samples_per_second": 3307.129,
"eval_spearmanr": 0.05819427794869299,
"eval_steps_per_second": 13.229,
"step": 23
},
{
"epoch": 2.0,
"grad_norm": 3.954559803009033,
"learning_rate": 4.8e-05,
"loss": 2.0096,
"step": 46
},
{
"epoch": 2.0,
"eval_combined_score": 0.11660029861389498,
"eval_loss": 2.6146180629730225,
"eval_pearson": 0.12482784591355002,
"eval_runtime": 0.5009,
"eval_samples_per_second": 2994.648,
"eval_spearmanr": 0.10837275131423994,
"eval_steps_per_second": 11.979,
"step": 46
},
{
"epoch": 3.0,
"grad_norm": 3.8552021980285645,
"learning_rate": 4.7e-05,
"loss": 1.8479,
"step": 69
},
{
"epoch": 3.0,
"eval_combined_score": 0.18696176467663445,
"eval_loss": 2.3950836658477783,
"eval_pearson": 0.19475826748422084,
"eval_runtime": 0.5063,
"eval_samples_per_second": 2962.428,
"eval_spearmanr": 0.17916526186904802,
"eval_steps_per_second": 11.85,
"step": 69
},
{
"epoch": 4.0,
"grad_norm": 8.263176918029785,
"learning_rate": 4.600000000000001e-05,
"loss": 1.6023,
"step": 92
},
{
"epoch": 4.0,
"eval_combined_score": 0.28932191146728636,
"eval_loss": 2.387584686279297,
"eval_pearson": 0.2931364205429543,
"eval_runtime": 0.4705,
"eval_samples_per_second": 3188.372,
"eval_spearmanr": 0.28550740239161837,
"eval_steps_per_second": 12.753,
"step": 92
},
{
"epoch": 5.0,
"grad_norm": 12.205520629882812,
"learning_rate": 4.5e-05,
"loss": 1.3085,
"step": 115
},
{
"epoch": 5.0,
"eval_combined_score": 0.27613789995817917,
"eval_loss": 2.4777557849884033,
"eval_pearson": 0.2810773671653918,
"eval_runtime": 0.4755,
"eval_samples_per_second": 3154.54,
"eval_spearmanr": 0.2711984327509666,
"eval_steps_per_second": 12.618,
"step": 115
},
{
"epoch": 6.0,
"grad_norm": 16.09912109375,
"learning_rate": 4.4000000000000006e-05,
"loss": 1.0396,
"step": 138
},
{
"epoch": 6.0,
"eval_combined_score": 0.31198315746046257,
"eval_loss": 2.449542999267578,
"eval_pearson": 0.3128501024896465,
"eval_runtime": 0.4966,
"eval_samples_per_second": 3020.566,
"eval_spearmanr": 0.3111162124312787,
"eval_steps_per_second": 12.082,
"step": 138
},
{
"epoch": 7.0,
"grad_norm": 16.89310646057129,
"learning_rate": 4.3e-05,
"loss": 0.8308,
"step": 161
},
{
"epoch": 7.0,
"eval_combined_score": 0.3389701896462223,
"eval_loss": 2.475055694580078,
"eval_pearson": 0.33859114529684625,
"eval_runtime": 0.4836,
"eval_samples_per_second": 3101.759,
"eval_spearmanr": 0.3393492339955983,
"eval_steps_per_second": 12.407,
"step": 161
},
{
"epoch": 8.0,
"grad_norm": 13.597253799438477,
"learning_rate": 4.2e-05,
"loss": 0.6749,
"step": 184
},
{
"epoch": 8.0,
"eval_combined_score": 0.3236788646982196,
"eval_loss": 2.54538631439209,
"eval_pearson": 0.32561739277468726,
"eval_runtime": 0.5142,
"eval_samples_per_second": 2917.382,
"eval_spearmanr": 0.32174033662175194,
"eval_steps_per_second": 11.67,
"step": 184
},
{
"epoch": 9.0,
"grad_norm": 8.104729652404785,
"learning_rate": 4.1e-05,
"loss": 0.574,
"step": 207
},
{
"epoch": 9.0,
"eval_combined_score": 0.3147812326804367,
"eval_loss": 2.6686761379241943,
"eval_pearson": 0.31714032142045084,
"eval_runtime": 0.4508,
"eval_samples_per_second": 3327.367,
"eval_spearmanr": 0.31242214394042245,
"eval_steps_per_second": 13.309,
"step": 207
},
{
"epoch": 9.0,
"step": 207,
"total_flos": 1356793384840704.0,
"train_loss": 1.486379623413086,
"train_runtime": 39.6567,
"train_samples_per_second": 7248.454,
"train_steps_per_second": 28.999
}
],
"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": 1356793384840704.0,
"train_batch_size": 256,
"trial_name": null,
"trial_params": null
}
|