File size: 5,241 Bytes
8f496b1 | 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": 0.8496004343032837,
"best_model_checkpoint": "tiny_bert_rand_20_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": 1.1339234113693237,
"learning_rate": 4.9e-05,
"loss": 0.9926,
"step": 1534
},
{
"epoch": 1.0,
"eval_accuracy": 0.5506877228731534,
"eval_loss": 0.9313808679580688,
"eval_runtime": 3.0,
"eval_samples_per_second": 3271.614,
"eval_steps_per_second": 13.0,
"step": 1534
},
{
"epoch": 2.0,
"grad_norm": 1.3619678020477295,
"learning_rate": 4.8e-05,
"loss": 0.9032,
"step": 3068
},
{
"epoch": 2.0,
"eval_accuracy": 0.5823739174732552,
"eval_loss": 0.8910712599754333,
"eval_runtime": 2.8007,
"eval_samples_per_second": 3504.45,
"eval_steps_per_second": 13.925,
"step": 3068
},
{
"epoch": 3.0,
"grad_norm": 1.7281922101974487,
"learning_rate": 4.7e-05,
"loss": 0.8523,
"step": 4602
},
{
"epoch": 3.0,
"eval_accuracy": 0.6031584309730005,
"eval_loss": 0.8651266098022461,
"eval_runtime": 2.8129,
"eval_samples_per_second": 3489.278,
"eval_steps_per_second": 13.865,
"step": 4602
},
{
"epoch": 4.0,
"grad_norm": 1.9255449771881104,
"learning_rate": 4.600000000000001e-05,
"loss": 0.8089,
"step": 6136
},
{
"epoch": 4.0,
"eval_accuracy": 0.6095771777890984,
"eval_loss": 0.8570564985275269,
"eval_runtime": 2.9455,
"eval_samples_per_second": 3332.204,
"eval_steps_per_second": 13.241,
"step": 6136
},
{
"epoch": 5.0,
"grad_norm": 1.6890971660614014,
"learning_rate": 4.5e-05,
"loss": 0.7665,
"step": 7670
},
{
"epoch": 5.0,
"eval_accuracy": 0.6182373917473255,
"eval_loss": 0.8496004343032837,
"eval_runtime": 2.7913,
"eval_samples_per_second": 3516.255,
"eval_steps_per_second": 13.972,
"step": 7670
},
{
"epoch": 6.0,
"grad_norm": 1.9976463317871094,
"learning_rate": 4.4000000000000006e-05,
"loss": 0.7234,
"step": 9204
},
{
"epoch": 6.0,
"eval_accuracy": 0.624350483953133,
"eval_loss": 0.8671989440917969,
"eval_runtime": 2.8098,
"eval_samples_per_second": 3493.092,
"eval_steps_per_second": 13.88,
"step": 9204
},
{
"epoch": 7.0,
"grad_norm": 2.1107654571533203,
"learning_rate": 4.3e-05,
"loss": 0.6827,
"step": 10738
},
{
"epoch": 7.0,
"eval_accuracy": 0.6287315333672949,
"eval_loss": 0.8687392473220825,
"eval_runtime": 2.9761,
"eval_samples_per_second": 3297.938,
"eval_steps_per_second": 13.104,
"step": 10738
},
{
"epoch": 8.0,
"grad_norm": 2.3106932640075684,
"learning_rate": 4.2e-05,
"loss": 0.6402,
"step": 12272
},
{
"epoch": 8.0,
"eval_accuracy": 0.6142638818135507,
"eval_loss": 0.9203874468803406,
"eval_runtime": 2.8068,
"eval_samples_per_second": 3496.895,
"eval_steps_per_second": 13.895,
"step": 12272
},
{
"epoch": 9.0,
"grad_norm": 3.1391849517822266,
"learning_rate": 4.1e-05,
"loss": 0.6004,
"step": 13806
},
{
"epoch": 9.0,
"eval_accuracy": 0.6229240957717779,
"eval_loss": 0.9506785869598389,
"eval_runtime": 2.9969,
"eval_samples_per_second": 3275.072,
"eval_steps_per_second": 13.014,
"step": 13806
},
{
"epoch": 10.0,
"grad_norm": 3.063190221786499,
"learning_rate": 4e-05,
"loss": 0.5621,
"step": 15340
},
{
"epoch": 10.0,
"eval_accuracy": 0.6297503820682628,
"eval_loss": 0.9863426685333252,
"eval_runtime": 2.7969,
"eval_samples_per_second": 3509.228,
"eval_steps_per_second": 13.944,
"step": 15340
},
{
"epoch": 10.0,
"step": 15340,
"total_flos": 1.029836100834816e+17,
"train_loss": 0.7532363434036832,
"train_runtime": 2078.1752,
"train_samples_per_second": 9448.241,
"train_steps_per_second": 36.907
}
],
"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
}
|