File size: 4,245 Bytes
742c7a4 |
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 |
{
"best_metric": 2.2569007873535156,
"best_model_checkpoint": "hBERTv2_new_pretrain_w_init_48_stsb/checkpoint-135",
"epoch": 8.0,
"global_step": 360,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"learning_rate": 3.9200000000000004e-05,
"loss": 2.3064,
"step": 45
},
{
"epoch": 1.0,
"eval_combined_score": 0.1462439839108577,
"eval_loss": 2.2783970832824707,
"eval_pearson": 0.14921550721008922,
"eval_runtime": 2.6216,
"eval_samples_per_second": 572.162,
"eval_spearmanr": 0.14327246061162616,
"eval_steps_per_second": 4.577,
"step": 45
},
{
"epoch": 2.0,
"learning_rate": 3.8400000000000005e-05,
"loss": 1.9454,
"step": 90
},
{
"epoch": 2.0,
"eval_combined_score": 0.26030447251939637,
"eval_loss": 2.2772936820983887,
"eval_pearson": 0.26598543333404057,
"eval_runtime": 2.6525,
"eval_samples_per_second": 565.495,
"eval_spearmanr": 0.2546235117047522,
"eval_steps_per_second": 4.524,
"step": 90
},
{
"epoch": 3.0,
"learning_rate": 3.76e-05,
"loss": 1.7733,
"step": 135
},
{
"epoch": 3.0,
"eval_combined_score": 0.24645036793946712,
"eval_loss": 2.2569007873535156,
"eval_pearson": 0.2426344717924136,
"eval_runtime": 2.6404,
"eval_samples_per_second": 568.092,
"eval_spearmanr": 0.25026626408652064,
"eval_steps_per_second": 4.545,
"step": 135
},
{
"epoch": 4.0,
"learning_rate": 3.680000000000001e-05,
"loss": 1.4752,
"step": 180
},
{
"epoch": 4.0,
"eval_combined_score": 0.29290243765316837,
"eval_loss": 2.3394598960876465,
"eval_pearson": 0.2832887660979118,
"eval_runtime": 2.6479,
"eval_samples_per_second": 566.491,
"eval_spearmanr": 0.30251610920842487,
"eval_steps_per_second": 4.532,
"step": 180
},
{
"epoch": 5.0,
"learning_rate": 3.6e-05,
"loss": 1.083,
"step": 225
},
{
"epoch": 5.0,
"eval_combined_score": 0.30418757127487117,
"eval_loss": 2.4139511585235596,
"eval_pearson": 0.30172563341382985,
"eval_runtime": 2.6618,
"eval_samples_per_second": 563.529,
"eval_spearmanr": 0.30664950913591255,
"eval_steps_per_second": 4.508,
"step": 225
},
{
"epoch": 6.0,
"learning_rate": 3.52e-05,
"loss": 0.8694,
"step": 270
},
{
"epoch": 6.0,
"eval_combined_score": 0.29075556065228314,
"eval_loss": 2.885422468185425,
"eval_pearson": 0.27900766009179806,
"eval_runtime": 2.6377,
"eval_samples_per_second": 568.667,
"eval_spearmanr": 0.30250346121276817,
"eval_steps_per_second": 4.549,
"step": 270
},
{
"epoch": 7.0,
"learning_rate": 3.44e-05,
"loss": 0.7272,
"step": 315
},
{
"epoch": 7.0,
"eval_combined_score": 0.30536562210653795,
"eval_loss": 2.890129566192627,
"eval_pearson": 0.30412357536912293,
"eval_runtime": 2.6421,
"eval_samples_per_second": 567.735,
"eval_spearmanr": 0.3066076688439529,
"eval_steps_per_second": 4.542,
"step": 315
},
{
"epoch": 8.0,
"learning_rate": 3.3600000000000004e-05,
"loss": 0.6008,
"step": 360
},
{
"epoch": 8.0,
"eval_combined_score": 0.283502287603587,
"eval_loss": 2.6252315044403076,
"eval_pearson": 0.283732546596965,
"eval_runtime": 2.6457,
"eval_samples_per_second": 566.952,
"eval_spearmanr": 0.283272028610209,
"eval_steps_per_second": 4.536,
"step": 360
},
{
"epoch": 8.0,
"step": 360,
"total_flos": 6730376961589248.0,
"train_loss": 1.3476022349463568,
"train_runtime": 308.5467,
"train_samples_per_second": 931.626,
"train_steps_per_second": 7.292
}
],
"max_steps": 2250,
"num_train_epochs": 50,
"total_flos": 6730376961589248.0,
"trial_name": null,
"trial_params": null
}
|