File size: 5,208 Bytes
90ab2a3 | 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 | {
"best_global_step": 100,
"best_metric": 0.5260673147136775,
"best_model_checkpoint": "output_checkpoints/graphcodebert-vanilla/checkpoint-100",
"epoch": 0.09784735812133072,
"eval_steps": 50,
"global_step": 100,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.004892367906066536,
"grad_norm": 33435.953125,
"learning_rate": 1.3071895424836603e-07,
"loss": 0.7006,
"step": 5
},
{
"epoch": 0.009784735812133072,
"grad_norm": 34831.7421875,
"learning_rate": 2.9411764705882356e-07,
"loss": 0.7023,
"step": 10
},
{
"epoch": 0.014677103718199608,
"grad_norm": 32986.62109375,
"learning_rate": 4.5751633986928105e-07,
"loss": 0.7019,
"step": 15
},
{
"epoch": 0.019569471624266144,
"grad_norm": 34257.4921875,
"learning_rate": 6.209150326797386e-07,
"loss": 0.7025,
"step": 20
},
{
"epoch": 0.02446183953033268,
"grad_norm": 35511.3359375,
"learning_rate": 7.843137254901962e-07,
"loss": 0.7032,
"step": 25
},
{
"epoch": 0.029354207436399216,
"grad_norm": 33043.3515625,
"learning_rate": 9.477124183006536e-07,
"loss": 0.6968,
"step": 30
},
{
"epoch": 0.03424657534246575,
"grad_norm": 38538.30078125,
"learning_rate": 1.111111111111111e-06,
"loss": 0.6992,
"step": 35
},
{
"epoch": 0.03913894324853229,
"grad_norm": 43255.37890625,
"learning_rate": 1.2745098039215686e-06,
"loss": 0.6991,
"step": 40
},
{
"epoch": 0.04403131115459882,
"grad_norm": 34170.8046875,
"learning_rate": 1.4379084967320261e-06,
"loss": 0.6996,
"step": 45
},
{
"epoch": 0.04892367906066536,
"grad_norm": 35399.70703125,
"learning_rate": 1.6013071895424837e-06,
"loss": 0.6937,
"step": 50
},
{
"epoch": 0.04892367906066536,
"eval_accuracy": 0.771,
"eval_loss": 0.6569265127182007,
"eval_macro_f1": 0.5082027063884254,
"eval_precision": 0.6109971743687904,
"eval_recall": 0.5281120325963375,
"eval_runtime": 17.5156,
"eval_samples_per_second": 57.092,
"eval_steps_per_second": 0.057,
"step": 50
},
{
"epoch": 0.053816046966731895,
"grad_norm": 34677.1796875,
"learning_rate": 1.7647058823529414e-06,
"loss": 0.6963,
"step": 55
},
{
"epoch": 0.05870841487279843,
"grad_norm": 31789.291015625,
"learning_rate": 1.928104575163399e-06,
"loss": 0.6971,
"step": 60
},
{
"epoch": 0.06360078277886497,
"grad_norm": 30762.345703125,
"learning_rate": 2.0915032679738565e-06,
"loss": 0.6946,
"step": 65
},
{
"epoch": 0.0684931506849315,
"grad_norm": 29590.083984375,
"learning_rate": 2.254901960784314e-06,
"loss": 0.693,
"step": 70
},
{
"epoch": 0.07338551859099804,
"grad_norm": 29346.84765625,
"learning_rate": 2.4183006535947716e-06,
"loss": 0.6905,
"step": 75
},
{
"epoch": 0.07827788649706457,
"grad_norm": 37289.77734375,
"learning_rate": 2.581699346405229e-06,
"loss": 0.6942,
"step": 80
},
{
"epoch": 0.08317025440313111,
"grad_norm": 33970.94140625,
"learning_rate": 2.7450980392156867e-06,
"loss": 0.69,
"step": 85
},
{
"epoch": 0.08806262230919765,
"grad_norm": 28671.583984375,
"learning_rate": 2.9084967320261443e-06,
"loss": 0.6889,
"step": 90
},
{
"epoch": 0.09295499021526418,
"grad_norm": 30156.005859375,
"learning_rate": 3.071895424836602e-06,
"loss": 0.6866,
"step": 95
},
{
"epoch": 0.09784735812133072,
"grad_norm": 33484.71484375,
"learning_rate": 3.2352941176470594e-06,
"loss": 0.6888,
"step": 100
},
{
"epoch": 0.09784735812133072,
"eval_accuracy": 0.767,
"eval_loss": 0.6559821367263794,
"eval_macro_f1": 0.5260673147136775,
"eval_precision": 0.6062366452991452,
"eval_recall": 0.5367285927824044,
"eval_runtime": 17.3972,
"eval_samples_per_second": 57.481,
"eval_steps_per_second": 0.057,
"step": 100
}
],
"logging_steps": 5,
"max_steps": 3066,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 100,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 3,
"early_stopping_threshold": 0.0
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1.3471286034432e+16,
"train_batch_size": 512,
"trial_name": null,
"trial_params": null
}
|