File size: 4,482 Bytes
f6c5562 |
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 |
{
"best_metric": 0.7449400424957275,
"best_model_checkpoint": "/content/drive/MyDrive/Colab Notebooks/models/t5-small-codesearchnet-python/checkpoint-3750",
"epoch": 10.0,
"global_step": 3750,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"eval_avg_length": 14.1472,
"eval_bleu": 0.0004,
"eval_loss": 0.966545581817627,
"eval_rouge1": 0.1696,
"eval_rouge2": 0.0384,
"eval_runtime": 148.9068,
"eval_samples_per_second": 33.578,
"eval_steps_per_second": 4.197,
"step": 375
},
{
"epoch": 1.33,
"learning_rate": 0.011612925678491592,
"loss": 2.0677,
"step": 500
},
{
"epoch": 2.0,
"eval_avg_length": 13.38,
"eval_bleu": 0.0004,
"eval_loss": 0.8739555478096008,
"eval_rouge1": 0.1758,
"eval_rouge2": 0.0428,
"eval_runtime": 148.3073,
"eval_samples_per_second": 33.714,
"eval_steps_per_second": 4.214,
"step": 750
},
{
"epoch": 2.67,
"learning_rate": 0.02327043004333973,
"loss": 0.8314,
"step": 1000
},
{
"epoch": 3.0,
"eval_avg_length": 14.8026,
"eval_bleu": 0.001,
"eval_loss": 0.8281144499778748,
"eval_rouge1": 0.1925,
"eval_rouge2": 0.0505,
"eval_runtime": 149.134,
"eval_samples_per_second": 33.527,
"eval_steps_per_second": 4.191,
"step": 1125
},
{
"epoch": 4.0,
"learning_rate": 0.03499961644411087,
"loss": 0.7563,
"step": 1500
},
{
"epoch": 4.0,
"eval_avg_length": 14.9606,
"eval_bleu": 0.0017,
"eval_loss": 0.7996220588684082,
"eval_rouge1": 0.2033,
"eval_rouge2": 0.0582,
"eval_runtime": 150.6141,
"eval_samples_per_second": 33.197,
"eval_steps_per_second": 4.15,
"step": 1500
},
{
"epoch": 5.0,
"eval_avg_length": 14.9434,
"eval_bleu": 0.0022,
"eval_loss": 0.7780128121376038,
"eval_rouge1": 0.2117,
"eval_rouge2": 0.0607,
"eval_runtime": 150.0628,
"eval_samples_per_second": 33.319,
"eval_steps_per_second": 4.165,
"step": 1875
},
{
"epoch": 5.33,
"learning_rate": 0.04683296009898186,
"loss": 0.6959,
"step": 2000
},
{
"epoch": 6.0,
"eval_avg_length": 14.6926,
"eval_bleu": 0.002,
"eval_loss": 0.7587344646453857,
"eval_rouge1": 0.2135,
"eval_rouge2": 0.0621,
"eval_runtime": 149.6348,
"eval_samples_per_second": 33.415,
"eval_steps_per_second": 4.177,
"step": 2250
},
{
"epoch": 6.67,
"learning_rate": 0.058812398463487625,
"loss": 0.6591,
"step": 2500
},
{
"epoch": 7.0,
"eval_avg_length": 15.2818,
"eval_bleu": 0.002,
"eval_loss": 0.7544705271720886,
"eval_rouge1": 0.2073,
"eval_rouge2": 0.0605,
"eval_runtime": 150.3492,
"eval_samples_per_second": 33.256,
"eval_steps_per_second": 4.157,
"step": 2625
},
{
"epoch": 8.0,
"learning_rate": 0.07098705321550369,
"loss": 0.6205,
"step": 3000
},
{
"epoch": 8.0,
"eval_avg_length": 15.051,
"eval_bleu": 0.0024,
"eval_loss": 0.7471866011619568,
"eval_rouge1": 0.2187,
"eval_rouge2": 0.0674,
"eval_runtime": 150.0125,
"eval_samples_per_second": 33.331,
"eval_steps_per_second": 4.166,
"step": 3000
},
{
"epoch": 9.0,
"eval_avg_length": 15.6286,
"eval_bleu": 0.0031,
"eval_loss": 0.7505583763122559,
"eval_rouge1": 0.2266,
"eval_rouge2": 0.0696,
"eval_runtime": 151.1802,
"eval_samples_per_second": 33.073,
"eval_steps_per_second": 4.134,
"step": 3375
},
{
"epoch": 9.33,
"learning_rate": 0.08336292207241058,
"loss": 0.5822,
"step": 3500
},
{
"epoch": 10.0,
"eval_avg_length": 13.1462,
"eval_bleu": 0.001,
"eval_loss": 0.7449400424957275,
"eval_rouge1": 0.206,
"eval_rouge2": 0.063,
"eval_runtime": 149.4965,
"eval_samples_per_second": 33.446,
"eval_steps_per_second": 4.181,
"step": 3750
}
],
"max_steps": 5625,
"num_train_epochs": 15,
"total_flos": 2.03012702208e+16,
"trial_name": null,
"trial_params": null
}
|