File size: 6,133 Bytes
a49562c |
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 |
{
"best_metric": 0.8271405492730209,
"best_model_checkpoint": "/scratch/mrahma45/pixel/finetuned_models/mbert/mbert-base-finetuned-masakhaner-kin/checkpoint-1000",
"epoch": 38.80597014925373,
"global_step": 2600,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 2.99,
"eval_accuracy_score": 0.9552972731336612,
"eval_f1": 0.8061538461538461,
"eval_loss": 0.14030461013317108,
"eval_precision": 0.7683284457478006,
"eval_recall": 0.8478964401294499,
"eval_runtime": 4.2191,
"eval_samples_per_second": 71.58,
"eval_steps_per_second": 9.007,
"step": 200
},
{
"epoch": 5.97,
"eval_accuracy_score": 0.9608106094471762,
"eval_f1": 0.8109375,
"eval_loss": 0.17163802683353424,
"eval_precision": 0.783987915407855,
"eval_recall": 0.8398058252427184,
"eval_runtime": 4.2278,
"eval_samples_per_second": 71.432,
"eval_steps_per_second": 8.988,
"step": 400
},
{
"epoch": 7.46,
"learning_rate": 4.865771812080537e-05,
"loss": 0.1428,
"step": 500
},
{
"epoch": 8.96,
"eval_accuracy_score": 0.9573834003874236,
"eval_f1": 0.7830940988835726,
"eval_loss": 0.2280413955450058,
"eval_precision": 0.7720125786163522,
"eval_recall": 0.7944983818770227,
"eval_runtime": 4.2189,
"eval_samples_per_second": 71.582,
"eval_steps_per_second": 9.007,
"step": 600
},
{
"epoch": 11.94,
"eval_accuracy_score": 0.9605125912680673,
"eval_f1": 0.8210862619808306,
"eval_loss": 0.22001390159130096,
"eval_precision": 0.8107255520504731,
"eval_recall": 0.8317152103559871,
"eval_runtime": 4.2196,
"eval_samples_per_second": 71.571,
"eval_steps_per_second": 9.006,
"step": 800
},
{
"epoch": 14.93,
"learning_rate": 4.697986577181208e-05,
"loss": 0.0075,
"step": 1000
},
{
"epoch": 14.93,
"eval_accuracy_score": 0.9640888094173745,
"eval_f1": 0.8271405492730209,
"eval_loss": 0.20800545811653137,
"eval_precision": 0.8258064516129032,
"eval_recall": 0.8284789644012945,
"eval_runtime": 4.2152,
"eval_samples_per_second": 71.645,
"eval_steps_per_second": 9.015,
"step": 1000
},
{
"epoch": 17.91,
"eval_accuracy_score": 0.9643868275964834,
"eval_f1": 0.8350764279967821,
"eval_loss": 0.2207585573196411,
"eval_precision": 0.8304,
"eval_recall": 0.8398058252427184,
"eval_runtime": 4.214,
"eval_samples_per_second": 71.666,
"eval_steps_per_second": 9.018,
"step": 1200
},
{
"epoch": 20.9,
"eval_accuracy_score": 0.9567873640292058,
"eval_f1": 0.8034455755677369,
"eval_loss": 0.24622981250286102,
"eval_precision": 0.7784522003034902,
"eval_recall": 0.8300970873786407,
"eval_runtime": 4.2176,
"eval_samples_per_second": 71.605,
"eval_steps_per_second": 9.01,
"step": 1400
},
{
"epoch": 22.39,
"learning_rate": 4.530201342281879e-05,
"loss": 0.004,
"step": 1500
},
{
"epoch": 23.88,
"eval_accuracy_score": 0.9658769184920281,
"eval_f1": 0.8436763550667713,
"eval_loss": 0.22536174952983856,
"eval_precision": 0.8198473282442749,
"eval_recall": 0.8689320388349514,
"eval_runtime": 4.214,
"eval_samples_per_second": 71.666,
"eval_steps_per_second": 9.018,
"step": 1600
},
{
"epoch": 26.87,
"eval_accuracy_score": 0.9646848457755923,
"eval_f1": 0.8192,
"eval_loss": 0.20931068062782288,
"eval_precision": 0.810126582278481,
"eval_recall": 0.8284789644012945,
"eval_runtime": 4.2136,
"eval_samples_per_second": 71.672,
"eval_steps_per_second": 9.018,
"step": 1800
},
{
"epoch": 29.85,
"learning_rate": 4.36241610738255e-05,
"loss": 0.0028,
"step": 2000
},
{
"epoch": 29.85,
"eval_accuracy_score": 0.9623007003427209,
"eval_f1": 0.822774659182037,
"eval_loss": 0.24018673598766327,
"eval_precision": 0.8155802861685215,
"eval_recall": 0.8300970873786407,
"eval_runtime": 4.2137,
"eval_samples_per_second": 71.671,
"eval_steps_per_second": 9.018,
"step": 2000
},
{
"epoch": 32.84,
"eval_accuracy_score": 0.9564893458500968,
"eval_f1": 0.8009630818619582,
"eval_loss": 0.26548677682876587,
"eval_precision": 0.7945859872611465,
"eval_recall": 0.8074433656957929,
"eval_runtime": 4.2161,
"eval_samples_per_second": 71.63,
"eval_steps_per_second": 9.013,
"step": 2200
},
{
"epoch": 35.82,
"eval_accuracy_score": 0.958128445835196,
"eval_f1": 0.8034727703235991,
"eval_loss": 0.2520817518234253,
"eval_precision": 0.7842835130970724,
"eval_recall": 0.8236245954692557,
"eval_runtime": 4.2073,
"eval_samples_per_second": 71.78,
"eval_steps_per_second": 9.032,
"step": 2400
},
{
"epoch": 37.31,
"learning_rate": 4.194630872483222e-05,
"loss": 0.0033,
"step": 2500
},
{
"epoch": 38.81,
"eval_accuracy_score": 0.9637907912382655,
"eval_f1": 0.8270313757039421,
"eval_loss": 0.2613898515701294,
"eval_precision": 0.8224,
"eval_recall": 0.8317152103559871,
"eval_runtime": 4.201,
"eval_samples_per_second": 71.887,
"eval_steps_per_second": 9.045,
"step": 2600
},
{
"epoch": 38.81,
"step": 2600,
"total_flos": 1.0731614329737216e+16,
"train_loss": 0.0309662873011369,
"train_runtime": 2918.4318,
"train_samples_per_second": 164.472,
"train_steps_per_second": 5.14
}
],
"max_steps": 15000,
"num_train_epochs": 224,
"total_flos": 1.0731614329737216e+16,
"trial_name": null,
"trial_params": null
}
|