File size: 5,189 Bytes
7ea4821 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.7540983606557377,
"eval_steps": 500,
"global_step": 21,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.13114754098360656,
"grad_norm": 39.05130772271081,
"learning_rate": 6.666666666666667e-06,
"loss": 2.4376,
"step": 1
},
{
"epoch": 0.26229508196721313,
"grad_norm": 39.015973031999486,
"learning_rate": 1.3333333333333333e-05,
"loss": 2.4339,
"step": 2
},
{
"epoch": 0.39344262295081966,
"grad_norm": 15.152312064538828,
"learning_rate": 2e-05,
"loss": 1.8888,
"step": 3
},
{
"epoch": 0.5245901639344263,
"grad_norm": 29.273723674546083,
"learning_rate": 1.9848077530122083e-05,
"loss": 1.8725,
"step": 4
},
{
"epoch": 0.6557377049180327,
"grad_norm": 11.667536919946288,
"learning_rate": 1.9396926207859085e-05,
"loss": 1.7797,
"step": 5
},
{
"epoch": 0.7868852459016393,
"grad_norm": 5.696635279505377,
"learning_rate": 1.866025403784439e-05,
"loss": 1.4526,
"step": 6
},
{
"epoch": 0.9180327868852459,
"grad_norm": 6.1474254223603655,
"learning_rate": 1.766044443118978e-05,
"loss": 1.3036,
"step": 7
},
{
"epoch": 0.9180327868852459,
"eval_loss": 1.2136186361312866,
"eval_runtime": 9.285,
"eval_samples_per_second": 20.678,
"eval_steps_per_second": 2.585,
"step": 7
},
{
"epoch": 1.0491803278688525,
"grad_norm": 3.8441152970886963,
"learning_rate": 1.6427876096865394e-05,
"loss": 1.193,
"step": 8
},
{
"epoch": 1.180327868852459,
"grad_norm": 3.216661811188678,
"learning_rate": 1.5000000000000002e-05,
"loss": 1.1161,
"step": 9
},
{
"epoch": 1.3114754098360657,
"grad_norm": 2.783161962423741,
"learning_rate": 1.342020143325669e-05,
"loss": 1.0656,
"step": 10
},
{
"epoch": 1.4426229508196722,
"grad_norm": 2.6684579204452517,
"learning_rate": 1.1736481776669307e-05,
"loss": 1.0333,
"step": 11
},
{
"epoch": 1.5737704918032787,
"grad_norm": 2.1293181551342286,
"learning_rate": 1e-05,
"loss": 1.0045,
"step": 12
},
{
"epoch": 1.7049180327868854,
"grad_norm": 1.7349053966220533,
"learning_rate": 8.263518223330698e-06,
"loss": 0.971,
"step": 13
},
{
"epoch": 1.8360655737704918,
"grad_norm": 1.708605250889302,
"learning_rate": 6.579798566743314e-06,
"loss": 0.9746,
"step": 14
},
{
"epoch": 1.9672131147540983,
"grad_norm": 1.565922544143404,
"learning_rate": 5.000000000000003e-06,
"loss": 0.9604,
"step": 15
},
{
"epoch": 1.9672131147540983,
"eval_loss": 0.9996973872184753,
"eval_runtime": 9.0907,
"eval_samples_per_second": 21.121,
"eval_steps_per_second": 2.64,
"step": 15
},
{
"epoch": 2.098360655737705,
"grad_norm": 1.4703758003535075,
"learning_rate": 3.5721239031346067e-06,
"loss": 0.9006,
"step": 16
},
{
"epoch": 2.2295081967213113,
"grad_norm": 1.4546503498400736,
"learning_rate": 2.339555568810221e-06,
"loss": 0.8672,
"step": 17
},
{
"epoch": 2.360655737704918,
"grad_norm": 1.333908386274604,
"learning_rate": 1.339745962155613e-06,
"loss": 0.8603,
"step": 18
},
{
"epoch": 2.4918032786885247,
"grad_norm": 1.2309918853415422,
"learning_rate": 6.030737921409169e-07,
"loss": 0.8533,
"step": 19
},
{
"epoch": 2.6229508196721314,
"grad_norm": 1.187570177680188,
"learning_rate": 1.519224698779198e-07,
"loss": 0.8482,
"step": 20
},
{
"epoch": 2.7540983606557377,
"grad_norm": 1.1796688649183953,
"learning_rate": 0.0,
"loss": 0.8292,
"step": 21
},
{
"epoch": 2.7540983606557377,
"eval_loss": 0.9841778874397278,
"eval_runtime": 9.0575,
"eval_samples_per_second": 21.198,
"eval_steps_per_second": 2.65,
"step": 21
},
{
"epoch": 2.7540983606557377,
"step": 21,
"total_flos": 3971544514560.0,
"train_loss": 1.268857215132032,
"train_runtime": 396.9611,
"train_samples_per_second": 3.673,
"train_steps_per_second": 0.053
}
],
"logging_steps": 1,
"max_steps": 21,
"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": true
},
"attributes": {}
}
},
"total_flos": 3971544514560.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}
|