File size: 3,988 Bytes
6fe9314 |
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 |
{
"best_metric": 0.613650998068255,
"best_model_checkpoint": "/root/crosslingual-mining-for-domain-nli/output/pretraining/vihealthbert-w_dual-ViNLI/lr3e-5_wr0.1_wd0.0/checkpoint-8000",
"epoch": 125.0,
"eval_steps": 1000,
"global_step": 8000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.015625,
"grad_norm": 34.54078674316406,
"learning_rate": 1e-08,
"loss": 10.2871,
"step": 1
},
{
"epoch": 15.625,
"grad_norm": 5.461294174194336,
"learning_rate": 9.999999999999999e-06,
"loss": 5.8126,
"step": 1000
},
{
"epoch": 15.625,
"eval_accuracy": 0.44503311258278144,
"eval_loss": 3.546058177947998,
"eval_runtime": 0.7421,
"eval_samples_per_second": 312.643,
"eval_steps_per_second": 20.214,
"step": 1000
},
{
"epoch": 31.25,
"grad_norm": 4.604820728302002,
"learning_rate": 1.9999999999999998e-05,
"loss": 2.605,
"step": 2000
},
{
"epoch": 31.25,
"eval_accuracy": 0.540436456996149,
"eval_loss": 2.7789385318756104,
"eval_runtime": 0.799,
"eval_samples_per_second": 290.377,
"eval_steps_per_second": 18.774,
"step": 2000
},
{
"epoch": 46.875,
"grad_norm": 4.253050327301025,
"learning_rate": 3e-05,
"loss": 1.5924,
"step": 3000
},
{
"epoch": 46.875,
"eval_accuracy": 0.5809284818067754,
"eval_loss": 2.5431649684906006,
"eval_runtime": 0.7348,
"eval_samples_per_second": 315.742,
"eval_steps_per_second": 20.414,
"step": 3000
},
{
"epoch": 62.5,
"grad_norm": 4.554752349853516,
"learning_rate": 2.8888888888888888e-05,
"loss": 1.2233,
"step": 4000
},
{
"epoch": 62.5,
"eval_accuracy": 0.5567077122488658,
"eval_loss": 2.6662397384643555,
"eval_runtime": 0.7259,
"eval_samples_per_second": 319.609,
"eval_steps_per_second": 20.664,
"step": 4000
},
{
"epoch": 78.125,
"grad_norm": 3.5844781398773193,
"learning_rate": 2.777777777777778e-05,
"loss": 0.9236,
"step": 5000
},
{
"epoch": 78.125,
"eval_accuracy": 0.5927342256214149,
"eval_loss": 2.4690873622894287,
"eval_runtime": 0.7491,
"eval_samples_per_second": 309.699,
"eval_steps_per_second": 20.024,
"step": 5000
},
{
"epoch": 93.75,
"grad_norm": 5.544617176055908,
"learning_rate": 2.6666666666666667e-05,
"loss": 0.7193,
"step": 6000
},
{
"epoch": 93.75,
"eval_accuracy": 0.6027219701879456,
"eval_loss": 2.405272960662842,
"eval_runtime": 0.6998,
"eval_samples_per_second": 331.502,
"eval_steps_per_second": 21.433,
"step": 6000
},
{
"epoch": 109.375,
"grad_norm": 4.963156700134277,
"learning_rate": 2.5555555555555557e-05,
"loss": 0.6259,
"step": 7000
},
{
"epoch": 109.375,
"eval_accuracy": 0.5781748564135291,
"eval_loss": 2.5938053131103516,
"eval_runtime": 0.6966,
"eval_samples_per_second": 333.065,
"eval_steps_per_second": 21.534,
"step": 7000
},
{
"epoch": 125.0,
"grad_norm": 4.307164192199707,
"learning_rate": 2.4444444444444445e-05,
"loss": 0.5082,
"step": 8000
},
{
"epoch": 125.0,
"eval_accuracy": 0.613650998068255,
"eval_loss": 2.480868101119995,
"eval_runtime": 0.7149,
"eval_samples_per_second": 324.519,
"eval_steps_per_second": 20.982,
"step": 8000
}
],
"logging_steps": 1000,
"max_steps": 30000,
"num_input_tokens_seen": 0,
"num_train_epochs": 469,
"save_steps": 1000,
"total_flos": 0.0,
"train_batch_size": 32,
"trial_name": null,
"trial_params": null
}
|