File size: 4,880 Bytes
d6ded99 | 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 | {
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 123,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0408997955010225,
"grad_norm": 7.998523235321045,
"learning_rate": 3.3333333333333333e-06,
"loss": 0.5733,
"step": 5
},
{
"epoch": 0.081799591002045,
"grad_norm": 9.153129577636719,
"learning_rate": 7.500000000000001e-06,
"loss": 0.5196,
"step": 10
},
{
"epoch": 0.12269938650306748,
"grad_norm": 8.34139347076416,
"learning_rate": 9.999225623611208e-06,
"loss": 0.5806,
"step": 15
},
{
"epoch": 0.16359918200409,
"grad_norm": 7.1141204833984375,
"learning_rate": 9.990516643685222e-06,
"loss": 0.4941,
"step": 20
},
{
"epoch": 0.20449897750511248,
"grad_norm": 8.44301700592041,
"learning_rate": 9.972147627352593e-06,
"loss": 0.6074,
"step": 25
},
{
"epoch": 0.24539877300613497,
"grad_norm": 6.837522029876709,
"learning_rate": 9.944154131125643e-06,
"loss": 0.6176,
"step": 30
},
{
"epoch": 0.28629856850715746,
"grad_norm": 6.722048282623291,
"learning_rate": 9.906590341416725e-06,
"loss": 0.6011,
"step": 35
},
{
"epoch": 0.32719836400818,
"grad_norm": 6.896355152130127,
"learning_rate": 9.859528969650739e-06,
"loss": 0.5717,
"step": 40
},
{
"epoch": 0.36809815950920244,
"grad_norm": 7.0612945556640625,
"learning_rate": 9.803061111519188e-06,
"loss": 0.5783,
"step": 45
},
{
"epoch": 0.40899795501022496,
"grad_norm": 6.113592147827148,
"learning_rate": 9.737296070648187e-06,
"loss": 0.6013,
"step": 50
},
{
"epoch": 0.4498977505112474,
"grad_norm": 6.054924488067627,
"learning_rate": 9.66236114702178e-06,
"loss": 0.612,
"step": 55
},
{
"epoch": 0.49079754601226994,
"grad_norm": 5.854165554046631,
"learning_rate": 9.57840139057007e-06,
"loss": 0.5835,
"step": 60
},
{
"epoch": 0.5316973415132924,
"grad_norm": 6.945219993591309,
"learning_rate": 9.485579320399184e-06,
"loss": 0.5709,
"step": 65
},
{
"epoch": 0.5725971370143149,
"grad_norm": 6.699445724487305,
"learning_rate": 9.384074610206495e-06,
"loss": 0.6038,
"step": 70
},
{
"epoch": 0.6134969325153374,
"grad_norm": 6.41201114654541,
"learning_rate": 9.274083740490097e-06,
"loss": 0.6221,
"step": 75
},
{
"epoch": 0.65439672801636,
"grad_norm": 5.748655796051025,
"learning_rate": 9.155819618225707e-06,
"loss": 0.6027,
"step": 80
},
{
"epoch": 0.6952965235173824,
"grad_norm": 6.205794334411621,
"learning_rate": 9.029511164747175e-06,
"loss": 0.5737,
"step": 85
},
{
"epoch": 0.7361963190184049,
"grad_norm": 6.745859622955322,
"learning_rate": 8.895402872628352e-06,
"loss": 0.6281,
"step": 90
},
{
"epoch": 0.7770961145194274,
"grad_norm": 5.8365302085876465,
"learning_rate": 8.753754332424047e-06,
"loss": 0.5721,
"step": 95
},
{
"epoch": 0.8179959100204499,
"grad_norm": 6.5638532638549805,
"learning_rate": 8.604839730186125e-06,
"loss": 0.6225,
"step": 100
},
{
"epoch": 0.8588957055214724,
"grad_norm": 9.908438682556152,
"learning_rate": 8.448947316727444e-06,
"loss": 0.6062,
"step": 105
},
{
"epoch": 0.8997955010224948,
"grad_norm": 7.083659648895264,
"learning_rate": 8.286378849660895e-06,
"loss": 0.5851,
"step": 110
},
{
"epoch": 0.9406952965235174,
"grad_norm": 5.502669811248779,
"learning_rate": 8.117449009293668e-06,
"loss": 0.5388,
"step": 115
},
{
"epoch": 0.9815950920245399,
"grad_norm": 5.813559055328369,
"learning_rate": 7.942484789507282e-06,
"loss": 0.6135,
"step": 120
}
],
"logging_steps": 5,
"max_steps": 369,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 3.8830705585474765e+17,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}
|