File size: 5,497 Bytes
2104588 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 |
{
"best_metric": 1.7296979427337646,
"best_model_checkpoint": "outputs/checkpoint-340",
"epoch": 9.74910394265233,
"eval_steps": 500,
"global_step": 340,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.5734767025089605,
"grad_norm": 0.8502072691917419,
"learning_rate": 2.0000000000000003e-06,
"loss": 2.925,
"step": 20
},
{
"epoch": 0.974910394265233,
"eval_loss": 2.817981243133545,
"eval_runtime": 11.5812,
"eval_samples_per_second": 32.121,
"eval_steps_per_second": 4.058,
"step": 34
},
{
"epoch": 1.146953405017921,
"grad_norm": 0.916117787361145,
"learning_rate": 4.000000000000001e-06,
"loss": 2.8937,
"step": 40
},
{
"epoch": 1.7204301075268817,
"grad_norm": 1.073569416999817,
"learning_rate": 6e-06,
"loss": 2.8277,
"step": 60
},
{
"epoch": 1.978494623655914,
"eval_loss": 2.588735342025757,
"eval_runtime": 11.5877,
"eval_samples_per_second": 32.103,
"eval_steps_per_second": 4.056,
"step": 69
},
{
"epoch": 2.293906810035842,
"grad_norm": 1.3921942710876465,
"learning_rate": 8.000000000000001e-06,
"loss": 2.6548,
"step": 80
},
{
"epoch": 2.867383512544803,
"grad_norm": 1.2179991006851196,
"learning_rate": 1e-05,
"loss": 2.2871,
"step": 100
},
{
"epoch": 2.982078853046595,
"eval_loss": 1.9897719621658325,
"eval_runtime": 11.5904,
"eval_samples_per_second": 32.096,
"eval_steps_per_second": 4.055,
"step": 104
},
{
"epoch": 3.4408602150537635,
"grad_norm": 0.5500979423522949,
"learning_rate": 9.829629131445342e-06,
"loss": 2.0042,
"step": 120
},
{
"epoch": 3.985663082437276,
"eval_loss": 1.8679059743881226,
"eval_runtime": 11.5852,
"eval_samples_per_second": 32.11,
"eval_steps_per_second": 4.057,
"step": 139
},
{
"epoch": 4.014336917562724,
"grad_norm": 0.46987271308898926,
"learning_rate": 9.330127018922195e-06,
"loss": 1.9362,
"step": 140
},
{
"epoch": 4.587813620071684,
"grad_norm": 0.44649583101272583,
"learning_rate": 8.535533905932739e-06,
"loss": 1.891,
"step": 160
},
{
"epoch": 4.989247311827957,
"eval_loss": 1.8080483675003052,
"eval_runtime": 11.5897,
"eval_samples_per_second": 32.097,
"eval_steps_per_second": 4.055,
"step": 174
},
{
"epoch": 5.161290322580645,
"grad_norm": 0.4501400589942932,
"learning_rate": 7.500000000000001e-06,
"loss": 1.8352,
"step": 180
},
{
"epoch": 5.734767025089606,
"grad_norm": 0.44334864616394043,
"learning_rate": 6.294095225512604e-06,
"loss": 1.8157,
"step": 200
},
{
"epoch": 5.992831541218638,
"eval_loss": 1.7702627182006836,
"eval_runtime": 11.5903,
"eval_samples_per_second": 32.096,
"eval_steps_per_second": 4.055,
"step": 209
},
{
"epoch": 6.308243727598566,
"grad_norm": 0.4709676504135132,
"learning_rate": 5e-06,
"loss": 1.769,
"step": 220
},
{
"epoch": 6.881720430107527,
"grad_norm": 0.45132553577423096,
"learning_rate": 3.705904774487396e-06,
"loss": 1.7697,
"step": 240
},
{
"epoch": 6.996415770609319,
"eval_loss": 1.7466135025024414,
"eval_runtime": 11.5882,
"eval_samples_per_second": 32.102,
"eval_steps_per_second": 4.056,
"step": 244
},
{
"epoch": 7.455197132616488,
"grad_norm": 0.4331286549568176,
"learning_rate": 2.5000000000000015e-06,
"loss": 1.7663,
"step": 260
},
{
"epoch": 8.0,
"eval_loss": 1.7342184782028198,
"eval_runtime": 11.5848,
"eval_samples_per_second": 32.111,
"eval_steps_per_second": 4.057,
"step": 279
},
{
"epoch": 8.028673835125447,
"grad_norm": 0.3883987069129944,
"learning_rate": 1.4644660940672628e-06,
"loss": 1.7284,
"step": 280
},
{
"epoch": 8.602150537634408,
"grad_norm": 0.47334837913513184,
"learning_rate": 6.698729810778065e-07,
"loss": 1.7424,
"step": 300
},
{
"epoch": 8.974910394265233,
"eval_loss": 1.7301242351531982,
"eval_runtime": 11.5834,
"eval_samples_per_second": 32.115,
"eval_steps_per_second": 4.058,
"step": 313
},
{
"epoch": 9.175627240143369,
"grad_norm": 0.4274068772792816,
"learning_rate": 1.7037086855465902e-07,
"loss": 1.7497,
"step": 320
},
{
"epoch": 9.74910394265233,
"grad_norm": 0.5189563632011414,
"learning_rate": 0.0,
"loss": 1.741,
"step": 340
},
{
"epoch": 9.74910394265233,
"eval_loss": 1.7296979427337646,
"eval_runtime": 11.5953,
"eval_samples_per_second": 32.082,
"eval_steps_per_second": 4.053,
"step": 340
}
],
"logging_steps": 20,
"max_steps": 340,
"num_input_tokens_seen": 0,
"num_train_epochs": 10,
"save_steps": 500,
"total_flos": 1.796114208104448e+16,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}
|