File size: 5,456 Bytes
6067342 |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.07923930269413629,
"global_step": 200,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 3.846153846153847e-06,
"loss": 2.7796,
"theoretical_loss": 3.3518567762894107,
"tokens_seen": 2969305088
},
{
"epoch": 0.0,
"learning_rate": 3.846153846153846e-05,
"loss": 2.4642,
"theoretical_loss": 3.3517550749686795,
"tokens_seen": 2970484736
},
{
"epoch": 0.01,
"learning_rate": 7.692307692307693e-05,
"loss": 1.9063,
"theoretical_loss": 3.351642134115535,
"tokens_seen": 2971795456
},
{
"epoch": 0.01,
"learning_rate": 9.983987189751803e-05,
"loss": 1.4437,
"theoretical_loss": 3.351529257004948,
"tokens_seen": 2973106176
},
{
"epoch": 0.02,
"learning_rate": 9.943955164131305e-05,
"loss": 1.273,
"theoretical_loss": 3.3514164435728655,
"tokens_seen": 2974416896
},
{
"epoch": 0.02,
"learning_rate": 9.90392313851081e-05,
"loss": 1.2074,
"theoretical_loss": 3.3513036937553267,
"tokens_seen": 2975727616
},
{
"epoch": 0.02,
"learning_rate": 9.863891112890312e-05,
"loss": 1.2079,
"theoretical_loss": 3.3511910074884628,
"tokens_seen": 2977038336
},
{
"epoch": 0.02,
"objective/train/docs_used": 997783,
"objective/train/instantaneous_batch_size": 8,
"objective/train/instantaneous_microbatch_size": 8192,
"objective/train/original_loss": 0.9412798285484314,
"objective/train/theoretical_loss": 3.3511628458440637,
"objective/train/tokens_used": 28650976,
"theoretical_loss": 3.3511628458440637,
"tokens_seen": 2977366016
},
{
"epoch": 0.03,
"learning_rate": 9.823859087269817e-05,
"loss": 1.2032,
"theoretical_loss": 3.3510783847084977,
"tokens_seen": 2978349056
},
{
"epoch": 0.03,
"learning_rate": 9.78382706164932e-05,
"loss": 1.2178,
"theoretical_loss": 3.350965825351748,
"tokens_seen": 2979659776
},
{
"epoch": 0.04,
"learning_rate": 9.743795036028824e-05,
"loss": 1.189,
"theoretical_loss": 3.3508533293546208,
"tokens_seen": 2980970496
},
{
"epoch": 0.04,
"learning_rate": 9.703763010408326e-05,
"loss": 1.2086,
"theoretical_loss": 3.3507408966536154,
"tokens_seen": 2982281216
},
{
"epoch": 0.04,
"learning_rate": 9.663730984787832e-05,
"loss": 1.1797,
"theoretical_loss": 3.3506285271853233,
"tokens_seen": 2983591936
},
{
"epoch": 0.05,
"learning_rate": 9.623698959167334e-05,
"loss": 1.1709,
"theoretical_loss": 3.350516220886427,
"tokens_seen": 2984902656
},
{
"epoch": 0.05,
"objective/train/docs_used": 1000073,
"objective/train/instantaneous_batch_size": 8,
"objective/train/instantaneous_microbatch_size": 8192,
"objective/train/original_loss": 1.0221836566925049,
"objective/train/theoretical_loss": 3.3504600914057403,
"objective/train/tokens_used": 36842976,
"theoretical_loss": 3.3504600914057403,
"tokens_seen": 2985558016
},
{
"epoch": 0.05,
"learning_rate": 9.583666933546838e-05,
"loss": 1.1658,
"theoretical_loss": 3.3504039776936994,
"tokens_seen": 2986213376
},
{
"epoch": 0.06,
"learning_rate": 9.543634907926342e-05,
"loss": 1.1823,
"theoretical_loss": 3.350291797544005,
"tokens_seen": 2987524096
},
{
"epoch": 0.06,
"learning_rate": 9.503602882305846e-05,
"loss": 1.1859,
"theoretical_loss": 3.3501796803742994,
"tokens_seen": 2988834816
},
{
"epoch": 0.06,
"learning_rate": 9.463570856685348e-05,
"loss": 1.1906,
"theoretical_loss": 3.3500676261216285,
"tokens_seen": 2990145536
},
{
"epoch": 0.07,
"learning_rate": 9.423538831064852e-05,
"loss": 1.185,
"theoretical_loss": 3.3499556347231287,
"tokens_seen": 2991456256
},
{
"epoch": 0.07,
"learning_rate": 9.383506805444356e-05,
"loss": 1.2042,
"theoretical_loss": 3.349843706116027,
"tokens_seen": 2992766976
},
{
"epoch": 0.07,
"objective/train/docs_used": 1002769,
"objective/train/instantaneous_batch_size": 8,
"objective/train/instantaneous_microbatch_size": 8192,
"objective/train/original_loss": 1.227379560470581,
"objective/train/theoretical_loss": 3.349759800829844,
"objective/train/tokens_used": 45034976,
"theoretical_loss": 3.349759800829844,
"tokens_seen": 2993750016
},
{
"epoch": 0.08,
"learning_rate": 9.34347477982386e-05,
"loss": 1.1807,
"theoretical_loss": 3.3497318402376397,
"tokens_seen": 2994077696
},
{
"epoch": 0.08,
"learning_rate": 9.303442754203363e-05,
"loss": 1.1862,
"theoretical_loss": 3.349620037025374,
"tokens_seen": 2995388416
}
],
"max_steps": 2524,
"num_train_epochs": 9223372036854775807,
"total_flos": 1.33781520384e+16,
"trial_name": null,
"trial_params": null
}
|