File size: 4,254 Bytes
84255d6 |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.061273571176912116,
"eval_steps": 500,
"global_step": 2000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.003063678558845606,
"grad_norm": 2.937537670135498,
"learning_rate": 4.000000000000001e-06,
"loss": 2.9979,
"step": 100
},
{
"epoch": 0.006127357117691212,
"grad_norm": 2.9786553382873535,
"learning_rate": 8.000000000000001e-06,
"loss": 2.9223,
"step": 200
},
{
"epoch": 0.009191035676536818,
"grad_norm": 2.899183750152588,
"learning_rate": 9.987820251299121e-06,
"loss": 2.9009,
"step": 300
},
{
"epoch": 0.012254714235382424,
"grad_norm": 2.9656615257263184,
"learning_rate": 9.890738003669029e-06,
"loss": 2.8884,
"step": 400
},
{
"epoch": 0.015318392794228029,
"grad_norm": 2.785738468170166,
"learning_rate": 9.698463103929542e-06,
"loss": 2.8738,
"step": 500
},
{
"epoch": 0.018382071353073636,
"grad_norm": 2.8539676666259766,
"learning_rate": 9.414737964294636e-06,
"loss": 2.8555,
"step": 600
},
{
"epoch": 0.02144574991191924,
"grad_norm": 2.6807861328125,
"learning_rate": 9.045084971874738e-06,
"loss": 2.8666,
"step": 700
},
{
"epoch": 0.024509428470764847,
"grad_norm": 2.81980037689209,
"learning_rate": 8.596699001693257e-06,
"loss": 2.8515,
"step": 800
},
{
"epoch": 0.027573107029610452,
"grad_norm": 2.636308193206787,
"learning_rate": 8.078307376628292e-06,
"loss": 2.8603,
"step": 900
},
{
"epoch": 0.030636785588456058,
"grad_norm": 2.5829219818115234,
"learning_rate": 7.500000000000001e-06,
"loss": 2.8555,
"step": 1000
},
{
"epoch": 0.03370046414730166,
"grad_norm": 2.622443914413452,
"learning_rate": 6.873032967079562e-06,
"loss": 2.8287,
"step": 1100
},
{
"epoch": 0.03676414270614727,
"grad_norm": 2.57558274269104,
"learning_rate": 6.209609477998339e-06,
"loss": 2.8294,
"step": 1200
},
{
"epoch": 0.039827821264992874,
"grad_norm": 2.6264266967773438,
"learning_rate": 5.522642316338268e-06,
"loss": 2.8315,
"step": 1300
},
{
"epoch": 0.04289149982383848,
"grad_norm": 2.575040578842163,
"learning_rate": 4.825502516487497e-06,
"loss": 2.8338,
"step": 1400
},
{
"epoch": 0.04595517838268409,
"grad_norm": 2.7474663257598877,
"learning_rate": 4.131759111665349e-06,
"loss": 2.8179,
"step": 1500
},
{
"epoch": 0.049018856941529694,
"grad_norm": 2.669630527496338,
"learning_rate": 3.4549150281252635e-06,
"loss": 2.8021,
"step": 1600
},
{
"epoch": 0.0520825355003753,
"grad_norm": 2.631849527359009,
"learning_rate": 2.8081442660546126e-06,
"loss": 2.8077,
"step": 1700
},
{
"epoch": 0.055146214059220905,
"grad_norm": 2.609309673309326,
"learning_rate": 2.204035482646267e-06,
"loss": 2.8177,
"step": 1800
},
{
"epoch": 0.058209892618066514,
"grad_norm": 2.68284273147583,
"learning_rate": 1.6543469682057105e-06,
"loss": 2.8051,
"step": 1900
},
{
"epoch": 0.061273571176912116,
"grad_norm": 2.7649335861206055,
"learning_rate": 1.1697777844051105e-06,
"loss": 2.8117,
"step": 2000
}
],
"logging_steps": 100,
"max_steps": 2500,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"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": 1.91328310788096e+17,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}
|