File size: 5,081 Bytes
678d3db |
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 |
{
"best_metric": 0.002532488200813532,
"best_model_checkpoint": "wsd_embedding/checkpoint-280896",
"epoch": 11.0,
"eval_steps": 500,
"global_step": 280896,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"grad_norm": 0.013213178142905235,
"learning_rate": 9.800046992481203e-05,
"loss": 0.0078,
"step": 25536
},
{
"epoch": 1.0,
"eval_loss": 0.004399613011628389,
"eval_runtime": 113.9442,
"eval_samples_per_second": 94.362,
"eval_steps_per_second": 11.795,
"step": 25536
},
{
"epoch": 2.0,
"grad_norm": 0.008942891843616962,
"learning_rate": 9.600117481203008e-05,
"loss": 0.0056,
"step": 51072
},
{
"epoch": 2.0,
"eval_loss": 0.0036812573671340942,
"eval_runtime": 113.8113,
"eval_samples_per_second": 94.472,
"eval_steps_per_second": 11.809,
"step": 51072
},
{
"epoch": 3.0,
"grad_norm": 0.019620591774582863,
"learning_rate": 9.400180137844612e-05,
"loss": 0.0049,
"step": 76608
},
{
"epoch": 3.0,
"eval_loss": 0.003332871478050947,
"eval_runtime": 113.7743,
"eval_samples_per_second": 94.503,
"eval_steps_per_second": 11.813,
"step": 76608
},
{
"epoch": 4.0,
"grad_norm": 0.009495776146650314,
"learning_rate": 9.200250626566417e-05,
"loss": 0.0045,
"step": 102144
},
{
"epoch": 4.0,
"eval_loss": 0.0030836393125355244,
"eval_runtime": 113.745,
"eval_samples_per_second": 94.527,
"eval_steps_per_second": 11.816,
"step": 102144
},
{
"epoch": 5.0,
"grad_norm": 0.007638801820576191,
"learning_rate": 9.00031328320802e-05,
"loss": 0.0043,
"step": 127680
},
{
"epoch": 5.0,
"eval_loss": 0.002948065521195531,
"eval_runtime": 113.6579,
"eval_samples_per_second": 94.6,
"eval_steps_per_second": 11.825,
"step": 127680
},
{
"epoch": 6.0,
"grad_norm": 0.010788742452859879,
"learning_rate": 8.800407268170426e-05,
"loss": 0.0041,
"step": 153216
},
{
"epoch": 6.0,
"eval_loss": 0.0028368972707539797,
"eval_runtime": 114.0546,
"eval_samples_per_second": 94.271,
"eval_steps_per_second": 11.784,
"step": 153216
},
{
"epoch": 7.0,
"grad_norm": 0.017284151166677475,
"learning_rate": 8.600477756892231e-05,
"loss": 0.0039,
"step": 178752
},
{
"epoch": 7.0,
"eval_loss": 0.0027765275444835424,
"eval_runtime": 113.8381,
"eval_samples_per_second": 94.45,
"eval_steps_per_second": 11.806,
"step": 178752
},
{
"epoch": 8.0,
"grad_norm": 0.008209532126784325,
"learning_rate": 8.400540413533835e-05,
"loss": 0.0038,
"step": 204288
},
{
"epoch": 8.0,
"eval_loss": 0.002683098893612623,
"eval_runtime": 113.811,
"eval_samples_per_second": 94.472,
"eval_steps_per_second": 11.809,
"step": 204288
},
{
"epoch": 9.0,
"grad_norm": 0.01161679532378912,
"learning_rate": 8.20062656641604e-05,
"loss": 0.0037,
"step": 229824
},
{
"epoch": 9.0,
"eval_loss": 0.002616806188598275,
"eval_runtime": 113.6336,
"eval_samples_per_second": 94.62,
"eval_steps_per_second": 11.827,
"step": 229824
},
{
"epoch": 10.0,
"grad_norm": 0.005629376508295536,
"learning_rate": 8.000689223057644e-05,
"loss": 0.0036,
"step": 255360
},
{
"epoch": 10.0,
"eval_loss": 0.0025433956179767847,
"eval_runtime": 113.7133,
"eval_samples_per_second": 94.554,
"eval_steps_per_second": 11.819,
"step": 255360
},
{
"epoch": 11.0,
"grad_norm": 0.009585434570908546,
"learning_rate": 7.800767543859649e-05,
"loss": 0.0035,
"step": 280896
},
{
"epoch": 11.0,
"eval_loss": 0.002532488200813532,
"eval_runtime": 113.8464,
"eval_samples_per_second": 94.443,
"eval_steps_per_second": 11.805,
"step": 280896
}
],
"logging_steps": 500,
"max_steps": 1276800,
"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": 0
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 5.7262662954123264e+17,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}
|