File size: 5,347 Bytes
6ca15e8 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 5.0,
"eval_steps": 500,
"global_step": 12535,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.1994415636218588,
"grad_norm": 1.7483305931091309,
"learning_rate": 4.8005584363781416e-05,
"loss": 7.5177,
"step": 500
},
{
"epoch": 0.3988831272437176,
"grad_norm": 1.5902838706970215,
"learning_rate": 4.601116872756282e-05,
"loss": 6.6658,
"step": 1000
},
{
"epoch": 0.5983246908655764,
"grad_norm": 1.9109225273132324,
"learning_rate": 4.4016753091344236e-05,
"loss": 6.3093,
"step": 1500
},
{
"epoch": 0.7977662544874352,
"grad_norm": 1.8110615015029907,
"learning_rate": 4.202233745512565e-05,
"loss": 6.0429,
"step": 2000
},
{
"epoch": 0.9972078181092939,
"grad_norm": 2.1440045833587646,
"learning_rate": 4.002792181890706e-05,
"loss": 5.8564,
"step": 2500
},
{
"epoch": 1.1966493817311528,
"grad_norm": 2.1070995330810547,
"learning_rate": 3.803350618268847e-05,
"loss": 5.6429,
"step": 3000
},
{
"epoch": 1.3960909453530115,
"grad_norm": 2.0321288108825684,
"learning_rate": 3.6039090546469884e-05,
"loss": 5.5179,
"step": 3500
},
{
"epoch": 1.5955325089748702,
"grad_norm": 2.1192569732666016,
"learning_rate": 3.4044674910251304e-05,
"loss": 5.4088,
"step": 4000
},
{
"epoch": 1.7949740725967291,
"grad_norm": 2.2034354209899902,
"learning_rate": 3.205025927403271e-05,
"loss": 5.3574,
"step": 4500
},
{
"epoch": 1.994415636218588,
"grad_norm": 2.3862476348876953,
"learning_rate": 3.0055843637814124e-05,
"loss": 5.2802,
"step": 5000
},
{
"epoch": 2.193857199840447,
"grad_norm": 2.287271738052368,
"learning_rate": 2.8061428001595534e-05,
"loss": 5.1049,
"step": 5500
},
{
"epoch": 2.3932987634623055,
"grad_norm": 2.282344341278076,
"learning_rate": 2.6067012365376948e-05,
"loss": 5.0663,
"step": 6000
},
{
"epoch": 2.5927403270841642,
"grad_norm": 2.3689157962799072,
"learning_rate": 2.4072596729158358e-05,
"loss": 5.0354,
"step": 6500
},
{
"epoch": 2.792181890706023,
"grad_norm": 2.4090659618377686,
"learning_rate": 2.207818109293977e-05,
"loss": 4.9782,
"step": 7000
},
{
"epoch": 2.9916234543278817,
"grad_norm": 2.3092195987701416,
"learning_rate": 2.008376545672118e-05,
"loss": 4.9434,
"step": 7500
},
{
"epoch": 3.191065017949741,
"grad_norm": 2.460700273513794,
"learning_rate": 1.8089349820502595e-05,
"loss": 4.8539,
"step": 8000
},
{
"epoch": 3.3905065815715996,
"grad_norm": 2.6232993602752686,
"learning_rate": 1.6098923015556443e-05,
"loss": 4.8056,
"step": 8500
},
{
"epoch": 3.5899481451934583,
"grad_norm": 2.5114476680755615,
"learning_rate": 1.4104507379337855e-05,
"loss": 4.7642,
"step": 9000
},
{
"epoch": 3.789389708815317,
"grad_norm": 2.446881055831909,
"learning_rate": 1.2110091743119267e-05,
"loss": 4.7694,
"step": 9500
},
{
"epoch": 3.988831272437176,
"grad_norm": 2.586047410964966,
"learning_rate": 1.0115676106900679e-05,
"loss": 4.733,
"step": 10000
},
{
"epoch": 4.188272836059035,
"grad_norm": 2.6265206336975098,
"learning_rate": 8.125249301954529e-06,
"loss": 4.6612,
"step": 10500
},
{
"epoch": 4.387714399680894,
"grad_norm": 2.6361939907073975,
"learning_rate": 6.13083366573594e-06,
"loss": 4.6552,
"step": 11000
},
{
"epoch": 4.587155963302752,
"grad_norm": 2.643498182296753,
"learning_rate": 4.136418029517352e-06,
"loss": 4.6594,
"step": 11500
},
{
"epoch": 4.786597526924611,
"grad_norm": 2.601949453353882,
"learning_rate": 2.1420023932987634e-06,
"loss": 4.6318,
"step": 12000
},
{
"epoch": 4.98603909054647,
"grad_norm": 2.711338996887207,
"learning_rate": 1.515755883526127e-07,
"loss": 4.6389,
"step": 12500
},
{
"epoch": 5.0,
"step": 12535,
"total_flos": 1.310011259092992e+16,
"train_loss": 5.274392118328446,
"train_runtime": 3806.2907,
"train_samples_per_second": 52.686,
"train_steps_per_second": 3.293
}
],
"logging_steps": 500,
"max_steps": 12535,
"num_input_tokens_seen": 0,
"num_train_epochs": 5,
"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": 1.310011259092992e+16,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}
|