File size: 5,242 Bytes
33774b9 | 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": 0.8499380350112915,
"best_model_checkpoint": "tiny_bert_rand_5_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": 1.1199190616607666,
"learning_rate": 4.9e-05,
"loss": 0.9894,
"step": 1534
},
{
"epoch": 1.0,
"eval_accuracy": 0.5552725420275089,
"eval_loss": 0.9260166883468628,
"eval_runtime": 2.8587,
"eval_samples_per_second": 3433.368,
"eval_steps_per_second": 13.643,
"step": 1534
},
{
"epoch": 2.0,
"grad_norm": 1.4727002382278442,
"learning_rate": 4.8e-05,
"loss": 0.9044,
"step": 3068
},
{
"epoch": 2.0,
"eval_accuracy": 0.5842078451349975,
"eval_loss": 0.8912194967269897,
"eval_runtime": 2.8033,
"eval_samples_per_second": 3501.241,
"eval_steps_per_second": 13.912,
"step": 3068
},
{
"epoch": 3.0,
"grad_norm": 1.6097134351730347,
"learning_rate": 4.7e-05,
"loss": 0.8553,
"step": 4602
},
{
"epoch": 3.0,
"eval_accuracy": 0.5969434538970962,
"eval_loss": 0.8659091591835022,
"eval_runtime": 2.8097,
"eval_samples_per_second": 3493.315,
"eval_steps_per_second": 13.881,
"step": 4602
},
{
"epoch": 4.0,
"grad_norm": 1.6552950143814087,
"learning_rate": 4.600000000000001e-05,
"loss": 0.8096,
"step": 6136
},
{
"epoch": 4.0,
"eval_accuracy": 0.60825267447784,
"eval_loss": 0.8656396269798279,
"eval_runtime": 2.7768,
"eval_samples_per_second": 3534.651,
"eval_steps_per_second": 14.045,
"step": 6136
},
{
"epoch": 5.0,
"grad_norm": 1.7045304775238037,
"learning_rate": 4.5e-05,
"loss": 0.765,
"step": 7670
},
{
"epoch": 5.0,
"eval_accuracy": 0.6164034640855833,
"eval_loss": 0.8499380350112915,
"eval_runtime": 2.8047,
"eval_samples_per_second": 3499.494,
"eval_steps_per_second": 13.905,
"step": 7670
},
{
"epoch": 6.0,
"grad_norm": 2.182920217514038,
"learning_rate": 4.4000000000000006e-05,
"loss": 0.7195,
"step": 9204
},
{
"epoch": 6.0,
"eval_accuracy": 0.6299541518084565,
"eval_loss": 0.8635302186012268,
"eval_runtime": 2.7851,
"eval_samples_per_second": 3524.115,
"eval_steps_per_second": 14.003,
"step": 9204
},
{
"epoch": 7.0,
"grad_norm": 2.068575859069824,
"learning_rate": 4.3e-05,
"loss": 0.6754,
"step": 10738
},
{
"epoch": 7.0,
"eval_accuracy": 0.6362710137544575,
"eval_loss": 0.8769534230232239,
"eval_runtime": 2.8206,
"eval_samples_per_second": 3479.748,
"eval_steps_per_second": 13.827,
"step": 10738
},
{
"epoch": 8.0,
"grad_norm": 2.3491876125335693,
"learning_rate": 4.2e-05,
"loss": 0.6336,
"step": 12272
},
{
"epoch": 8.0,
"eval_accuracy": 0.6287315333672949,
"eval_loss": 0.914506733417511,
"eval_runtime": 2.8023,
"eval_samples_per_second": 3502.433,
"eval_steps_per_second": 13.917,
"step": 12272
},
{
"epoch": 9.0,
"grad_norm": 3.0106260776519775,
"learning_rate": 4.1e-05,
"loss": 0.5919,
"step": 13806
},
{
"epoch": 9.0,
"eval_accuracy": 0.6296484971981661,
"eval_loss": 0.9488242268562317,
"eval_runtime": 2.8102,
"eval_samples_per_second": 3492.655,
"eval_steps_per_second": 13.878,
"step": 13806
},
{
"epoch": 10.0,
"grad_norm": 3.469269275665283,
"learning_rate": 4e-05,
"loss": 0.5523,
"step": 15340
},
{
"epoch": 10.0,
"eval_accuracy": 0.6293428425878757,
"eval_loss": 0.9850627183914185,
"eval_runtime": 2.7995,
"eval_samples_per_second": 3506.037,
"eval_steps_per_second": 13.931,
"step": 15340
},
{
"epoch": 10.0,
"step": 15340,
"total_flos": 1.029836100834816e+17,
"train_loss": 0.7496284455022103,
"train_runtime": 2069.0979,
"train_samples_per_second": 9489.691,
"train_steps_per_second": 37.069
}
],
"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
}
|