File size: 5,135 Bytes
7fb6750 | 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": 2.13891863822937,
"best_model_checkpoint": "bert_base_km_50_v1_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": 14.298930168151855,
"learning_rate": 4.9e-05,
"loss": 2.8402,
"step": 23
},
{
"epoch": 1.0,
"eval_combined_score": 0.20431268932772875,
"eval_loss": 2.4772613048553467,
"eval_pearson": 0.20675580808289823,
"eval_runtime": 0.9909,
"eval_samples_per_second": 1513.804,
"eval_spearmanr": 0.20186957057255928,
"eval_steps_per_second": 6.055,
"step": 23
},
{
"epoch": 2.0,
"grad_norm": 7.726978302001953,
"learning_rate": 4.8e-05,
"loss": 2.0586,
"step": 46
},
{
"epoch": 2.0,
"eval_combined_score": 0.22702596907498984,
"eval_loss": 2.243328332901001,
"eval_pearson": 0.22765342410827677,
"eval_runtime": 1.0514,
"eval_samples_per_second": 1426.67,
"eval_spearmanr": 0.22639851404170291,
"eval_steps_per_second": 5.707,
"step": 46
},
{
"epoch": 3.0,
"grad_norm": 6.552237033843994,
"learning_rate": 4.7e-05,
"loss": 1.8469,
"step": 69
},
{
"epoch": 3.0,
"eval_combined_score": 0.27823015131617784,
"eval_loss": 2.13891863822937,
"eval_pearson": 0.27634819216922646,
"eval_runtime": 0.948,
"eval_samples_per_second": 1582.301,
"eval_spearmanr": 0.2801121104631292,
"eval_steps_per_second": 6.329,
"step": 69
},
{
"epoch": 4.0,
"grad_norm": 6.038108825683594,
"learning_rate": 4.600000000000001e-05,
"loss": 1.5476,
"step": 92
},
{
"epoch": 4.0,
"eval_combined_score": 0.2833951571023935,
"eval_loss": 2.307851791381836,
"eval_pearson": 0.28322316631141503,
"eval_runtime": 0.9719,
"eval_samples_per_second": 1543.433,
"eval_spearmanr": 0.28356714789337195,
"eval_steps_per_second": 6.174,
"step": 92
},
{
"epoch": 5.0,
"grad_norm": 9.0367431640625,
"learning_rate": 4.5e-05,
"loss": 1.1654,
"step": 115
},
{
"epoch": 5.0,
"eval_combined_score": 0.3019315552492974,
"eval_loss": 2.3807790279388428,
"eval_pearson": 0.3015344856746127,
"eval_runtime": 0.975,
"eval_samples_per_second": 1538.43,
"eval_spearmanr": 0.3023286248239821,
"eval_steps_per_second": 6.154,
"step": 115
},
{
"epoch": 6.0,
"grad_norm": 16.923473358154297,
"learning_rate": 4.4000000000000006e-05,
"loss": 0.8754,
"step": 138
},
{
"epoch": 6.0,
"eval_combined_score": 0.2759957313458622,
"eval_loss": 2.527632713317871,
"eval_pearson": 0.27689735430889173,
"eval_runtime": 0.9711,
"eval_samples_per_second": 1544.597,
"eval_spearmanr": 0.2750941083828327,
"eval_steps_per_second": 6.178,
"step": 138
},
{
"epoch": 7.0,
"grad_norm": 8.27717113494873,
"learning_rate": 4.3e-05,
"loss": 0.6215,
"step": 161
},
{
"epoch": 7.0,
"eval_combined_score": 0.2901122414894359,
"eval_loss": 2.4822278022766113,
"eval_pearson": 0.2906590318548305,
"eval_runtime": 1.0221,
"eval_samples_per_second": 1467.605,
"eval_spearmanr": 0.28956545112404125,
"eval_steps_per_second": 5.87,
"step": 161
},
{
"epoch": 8.0,
"grad_norm": 14.043330192565918,
"learning_rate": 4.2e-05,
"loss": 0.4911,
"step": 184
},
{
"epoch": 8.0,
"eval_combined_score": 0.3058001658608961,
"eval_loss": 2.5761725902557373,
"eval_pearson": 0.3055809401586476,
"eval_runtime": 0.9868,
"eval_samples_per_second": 1520.067,
"eval_spearmanr": 0.3060193915631446,
"eval_steps_per_second": 6.08,
"step": 184
},
{
"epoch": 8.0,
"step": 184,
"total_flos": 6050447504044032.0,
"train_loss": 1.4308352263077446,
"train_runtime": 100.0942,
"train_samples_per_second": 2871.795,
"train_steps_per_second": 11.489
}
],
"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": 6050447504044032.0,
"train_batch_size": 256,
"trial_name": null,
"trial_params": null
}
|