File size: 5,064 Bytes
f7d42aa |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.02120665889089174,
"eval_steps": 500,
"global_step": 25,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0008482663556356696,
"grad_norm": 14.401731491088867,
"learning_rate": 0.0001,
"loss": 6.023,
"step": 1
},
{
"epoch": 0.0016965327112713393,
"grad_norm": 12.187810897827148,
"learning_rate": 0.0002,
"loss": 5.9775,
"step": 2
},
{
"epoch": 0.002544799066907009,
"grad_norm": 12.369268417358398,
"learning_rate": 0.00019978589232386035,
"loss": 5.4492,
"step": 3
},
{
"epoch": 0.0033930654225426786,
"grad_norm": 11.223816871643066,
"learning_rate": 0.00019914448613738106,
"loss": 3.9348,
"step": 4
},
{
"epoch": 0.004241331778178348,
"grad_norm": 9.1347074508667,
"learning_rate": 0.00019807852804032305,
"loss": 2.3093,
"step": 5
},
{
"epoch": 0.005089598133814018,
"grad_norm": 6.055950164794922,
"learning_rate": 0.00019659258262890683,
"loss": 1.3156,
"step": 6
},
{
"epoch": 0.0059378644894496875,
"grad_norm": 3.676882743835449,
"learning_rate": 0.0001946930129495106,
"loss": 1.0411,
"step": 7
},
{
"epoch": 0.006786130845085357,
"grad_norm": 4.150704383850098,
"learning_rate": 0.0001923879532511287,
"loss": 0.8048,
"step": 8
},
{
"epoch": 0.007634397200721026,
"grad_norm": 3.6138298511505127,
"learning_rate": 0.00018968727415326884,
"loss": 0.7477,
"step": 9
},
{
"epoch": 0.008482663556356696,
"grad_norm": 2.753798484802246,
"learning_rate": 0.00018660254037844388,
"loss": 0.542,
"step": 10
},
{
"epoch": 0.009330929911992365,
"grad_norm": 4.54025411605835,
"learning_rate": 0.00018314696123025454,
"loss": 0.496,
"step": 11
},
{
"epoch": 0.010179196267628036,
"grad_norm": 13.51045036315918,
"learning_rate": 0.00017933533402912354,
"loss": 0.9441,
"step": 12
},
{
"epoch": 0.011027462623263705,
"grad_norm": 14.223007202148438,
"learning_rate": 0.00017518398074789775,
"loss": 1.0033,
"step": 13
},
{
"epoch": 0.011875728978899375,
"grad_norm": 2.892982006072998,
"learning_rate": 0.00017071067811865476,
"loss": 0.5323,
"step": 14
},
{
"epoch": 0.012723995334535044,
"grad_norm": 4.61104154586792,
"learning_rate": 0.00016593458151000688,
"loss": 0.4663,
"step": 15
},
{
"epoch": 0.013572261690170714,
"grad_norm": 2.2477262020111084,
"learning_rate": 0.00016087614290087208,
"loss": 0.4505,
"step": 16
},
{
"epoch": 0.014420528045806383,
"grad_norm": 4.4651899337768555,
"learning_rate": 0.00015555702330196023,
"loss": 0.6104,
"step": 17
},
{
"epoch": 0.015268794401442052,
"grad_norm": 2.236485004425049,
"learning_rate": 0.00015000000000000001,
"loss": 0.4329,
"step": 18
},
{
"epoch": 0.016117060757077722,
"grad_norm": 3.9798102378845215,
"learning_rate": 0.00014422886902190014,
"loss": 0.5202,
"step": 19
},
{
"epoch": 0.016965327112713393,
"grad_norm": 1.3175522089004517,
"learning_rate": 0.000138268343236509,
"loss": 0.4673,
"step": 20
},
{
"epoch": 0.01781359346834906,
"grad_norm": 1.3106902837753296,
"learning_rate": 0.00013214394653031616,
"loss": 0.4498,
"step": 21
},
{
"epoch": 0.01866185982398473,
"grad_norm": 1.7499768733978271,
"learning_rate": 0.00012588190451025207,
"loss": 0.4964,
"step": 22
},
{
"epoch": 0.0195101261796204,
"grad_norm": 2.9013662338256836,
"learning_rate": 0.00011950903220161285,
"loss": 0.5628,
"step": 23
},
{
"epoch": 0.02035839253525607,
"grad_norm": 0.665701687335968,
"learning_rate": 0.00011305261922200519,
"loss": 0.4783,
"step": 24
},
{
"epoch": 0.02120665889089174,
"grad_norm": 0.7912172675132751,
"learning_rate": 0.00010654031292301432,
"loss": 0.4836,
"step": 25
}
],
"logging_steps": 1,
"max_steps": 50,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 25,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 5146843860172800.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}
|