File size: 5,143 Bytes
af5f4fe | 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 | {
"best_global_step": 69,
"best_metric": 2.2658326625823975,
"best_model_checkpoint": "distilbert_rand_5_v2_stsb/checkpoint-69",
"epoch": 8.0,
"eval_steps": 500,
"global_step": 184,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"grad_norm": 5.0608110427856445,
"learning_rate": 4.9e-05,
"loss": 2.6404,
"step": 23
},
{
"epoch": 1.0,
"eval_combined_score": 0.11699342039692526,
"eval_loss": 2.41465425491333,
"eval_pearson": 0.12565635781319812,
"eval_runtime": 0.6424,
"eval_samples_per_second": 2335.013,
"eval_spearmanr": 0.10833048298065238,
"eval_steps_per_second": 9.34,
"step": 23
},
{
"epoch": 2.0,
"grad_norm": 5.66240930557251,
"learning_rate": 4.8e-05,
"loss": 1.8953,
"step": 46
},
{
"epoch": 2.0,
"eval_combined_score": 0.1914796307307736,
"eval_loss": 2.4776315689086914,
"eval_pearson": 0.20277521257509618,
"eval_runtime": 0.6517,
"eval_samples_per_second": 2301.755,
"eval_spearmanr": 0.180184048886451,
"eval_steps_per_second": 9.207,
"step": 46
},
{
"epoch": 3.0,
"grad_norm": 7.03953218460083,
"learning_rate": 4.7e-05,
"loss": 1.6258,
"step": 69
},
{
"epoch": 3.0,
"eval_combined_score": 0.27922213217540587,
"eval_loss": 2.2658326625823975,
"eval_pearson": 0.28594795822205954,
"eval_runtime": 0.6249,
"eval_samples_per_second": 2400.384,
"eval_spearmanr": 0.2724963061287522,
"eval_steps_per_second": 9.602,
"step": 69
},
{
"epoch": 4.0,
"grad_norm": 9.639275550842285,
"learning_rate": 4.600000000000001e-05,
"loss": 1.3145,
"step": 92
},
{
"epoch": 4.0,
"eval_combined_score": 0.32255239461739416,
"eval_loss": 2.3222312927246094,
"eval_pearson": 0.3224380385194155,
"eval_runtime": 0.6167,
"eval_samples_per_second": 2432.496,
"eval_spearmanr": 0.3226667507153729,
"eval_steps_per_second": 9.73,
"step": 92
},
{
"epoch": 5.0,
"grad_norm": 10.404162406921387,
"learning_rate": 4.5e-05,
"loss": 0.9743,
"step": 115
},
{
"epoch": 5.0,
"eval_combined_score": 0.317422126291488,
"eval_loss": 2.4189276695251465,
"eval_pearson": 0.3225324801153353,
"eval_runtime": 0.6533,
"eval_samples_per_second": 2295.945,
"eval_spearmanr": 0.3123117724676408,
"eval_steps_per_second": 9.184,
"step": 115
},
{
"epoch": 6.0,
"grad_norm": 12.562041282653809,
"learning_rate": 4.4000000000000006e-05,
"loss": 0.7528,
"step": 138
},
{
"epoch": 6.0,
"eval_combined_score": 0.3305215504599094,
"eval_loss": 2.4691739082336426,
"eval_pearson": 0.33259118628799356,
"eval_runtime": 0.6654,
"eval_samples_per_second": 2254.382,
"eval_spearmanr": 0.3284519146318252,
"eval_steps_per_second": 9.018,
"step": 138
},
{
"epoch": 7.0,
"grad_norm": 9.112942695617676,
"learning_rate": 4.3e-05,
"loss": 0.5989,
"step": 161
},
{
"epoch": 7.0,
"eval_combined_score": 0.360745901774201,
"eval_loss": 2.382098436355591,
"eval_pearson": 0.36246744992255747,
"eval_runtime": 0.6361,
"eval_samples_per_second": 2358.195,
"eval_spearmanr": 0.35902435362584456,
"eval_steps_per_second": 9.433,
"step": 161
},
{
"epoch": 8.0,
"grad_norm": 23.918201446533203,
"learning_rate": 4.2e-05,
"loss": 0.4902,
"step": 184
},
{
"epoch": 8.0,
"eval_combined_score": 0.36350579676169986,
"eval_loss": 2.4664862155914307,
"eval_pearson": 0.36518619089227783,
"eval_runtime": 0.6496,
"eval_samples_per_second": 2309.002,
"eval_spearmanr": 0.3618254026311219,
"eval_steps_per_second": 9.236,
"step": 184
},
{
"epoch": 8.0,
"step": 184,
"total_flos": 3046165974478848.0,
"train_loss": 1.2865250680757605,
"train_runtime": 58.9398,
"train_samples_per_second": 4877.013,
"train_steps_per_second": 19.511
}
],
"logging_steps": 1,
"max_steps": 1150,
"num_input_tokens_seen": 0,
"num_train_epochs": 50,
"save_steps": 500,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 5,
"early_stopping_threshold": 0.0
},
"attributes": {
"early_stopping_patience_counter": 5
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 3046165974478848.0,
"train_batch_size": 256,
"trial_name": null,
"trial_params": null
}
|