File size: 5,715 Bytes
f9495f4 | 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": 5688,
"best_metric": 0.30050283670425415,
"best_model_checkpoint": "tinybert_base_train_kd_qqp/checkpoint-5688",
"epoch": 9.0,
"eval_steps": 500,
"global_step": 12798,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"grad_norm": 2.605546474456787,
"learning_rate": 4.900070323488045e-05,
"loss": 0.4061,
"step": 1422
},
{
"epoch": 1.0,
"eval_accuracy": 0.8430373485035865,
"eval_combined_score": 0.8128542906901495,
"eval_f1": 0.7826712328767124,
"eval_loss": 0.34433236718177795,
"eval_runtime": 19.9883,
"eval_samples_per_second": 2022.682,
"eval_steps_per_second": 7.905,
"step": 1422
},
{
"epoch": 2.0,
"grad_norm": 3.7136270999908447,
"learning_rate": 4.800070323488045e-05,
"loss": 0.3179,
"step": 2844
},
{
"epoch": 2.0,
"eval_accuracy": 0.8611427158050953,
"eval_combined_score": 0.8380532300185661,
"eval_f1": 0.8149637442320369,
"eval_loss": 0.3137979209423065,
"eval_runtime": 20.1369,
"eval_samples_per_second": 2007.752,
"eval_steps_per_second": 7.846,
"step": 2844
},
{
"epoch": 3.0,
"grad_norm": 2.9198460578918457,
"learning_rate": 4.700070323488045e-05,
"loss": 0.269,
"step": 4266
},
{
"epoch": 3.0,
"eval_accuracy": 0.8663368785555281,
"eval_combined_score": 0.8460577293673894,
"eval_f1": 0.8257785801792508,
"eval_loss": 0.3077119290828705,
"eval_runtime": 20.3208,
"eval_samples_per_second": 1989.585,
"eval_steps_per_second": 7.775,
"step": 4266
},
{
"epoch": 4.0,
"grad_norm": 3.6862900257110596,
"learning_rate": 4.600070323488046e-05,
"loss": 0.2275,
"step": 5688
},
{
"epoch": 4.0,
"eval_accuracy": 0.8704922087558743,
"eval_combined_score": 0.8461257340075667,
"eval_f1": 0.8217592592592593,
"eval_loss": 0.30050283670425415,
"eval_runtime": 19.99,
"eval_samples_per_second": 2022.51,
"eval_steps_per_second": 7.904,
"step": 5688
},
{
"epoch": 5.0,
"grad_norm": 2.6690852642059326,
"learning_rate": 4.500070323488045e-05,
"loss": 0.1923,
"step": 7110
},
{
"epoch": 5.0,
"eval_accuracy": 0.8749690823645807,
"eval_combined_score": 0.8502059749334558,
"eval_f1": 0.8254428675023309,
"eval_loss": 0.3269473910331726,
"eval_runtime": 20.1113,
"eval_samples_per_second": 2010.309,
"eval_steps_per_second": 7.856,
"step": 7110
},
{
"epoch": 6.0,
"grad_norm": 2.443815231323242,
"learning_rate": 4.400070323488045e-05,
"loss": 0.1614,
"step": 8532
},
{
"epoch": 6.0,
"eval_accuracy": 0.8750432846895869,
"eval_combined_score": 0.8520798888608265,
"eval_f1": 0.829116493032066,
"eval_loss": 0.3224050998687744,
"eval_runtime": 20.1576,
"eval_samples_per_second": 2005.698,
"eval_steps_per_second": 7.838,
"step": 8532
},
{
"epoch": 7.0,
"grad_norm": 3.2654778957366943,
"learning_rate": 4.300070323488045e-05,
"loss": 0.1349,
"step": 9954
},
{
"epoch": 7.0,
"eval_accuracy": 0.8761068513480089,
"eval_combined_score": 0.857411380402407,
"eval_f1": 0.8387159094568052,
"eval_loss": 0.3559403121471405,
"eval_runtime": 20.0974,
"eval_samples_per_second": 2011.705,
"eval_steps_per_second": 7.862,
"step": 9954
},
{
"epoch": 8.0,
"grad_norm": 4.175635814666748,
"learning_rate": 4.200070323488045e-05,
"loss": 0.1132,
"step": 11376
},
{
"epoch": 8.0,
"eval_accuracy": 0.8775414296314618,
"eval_combined_score": 0.8549946141016627,
"eval_f1": 0.8324477985718637,
"eval_loss": 0.4348158538341522,
"eval_runtime": 19.998,
"eval_samples_per_second": 2021.701,
"eval_steps_per_second": 7.901,
"step": 11376
},
{
"epoch": 9.0,
"grad_norm": 3.47190523147583,
"learning_rate": 4.100070323488045e-05,
"loss": 0.0966,
"step": 12798
},
{
"epoch": 9.0,
"eval_accuracy": 0.8796438288399703,
"eval_combined_score": 0.8595354835857718,
"eval_f1": 0.8394271383315733,
"eval_loss": 0.435083270072937,
"eval_runtime": 20.1566,
"eval_samples_per_second": 2005.79,
"eval_steps_per_second": 7.839,
"step": 12798
},
{
"epoch": 9.0,
"step": 12798,
"total_flos": 2.168897990912594e+17,
"train_loss": 0.21321062558068765,
"train_runtime": 3308.4254,
"train_samples_per_second": 5498.779,
"train_steps_per_second": 21.491
}
],
"logging_steps": 1,
"max_steps": 71100,
"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": 2.168897990912594e+17,
"train_batch_size": 256,
"trial_name": null,
"trial_params": null
}
|