Upload trainer_state.json
Browse files- trainer_state.json +205 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,205 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 67.53246753246754,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 78000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 2.16,
|
| 13 |
+
"learning_rate": 9.892164502164502e-06,
|
| 14 |
+
"loss": 0.8489,
|
| 15 |
+
"step": 2500
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 4.33,
|
| 19 |
+
"learning_rate": 9.783982683982685e-06,
|
| 20 |
+
"loss": 0.6312,
|
| 21 |
+
"step": 5000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 6.49,
|
| 25 |
+
"learning_rate": 9.675757575757577e-06,
|
| 26 |
+
"loss": 0.5488,
|
| 27 |
+
"step": 7500
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 8.66,
|
| 31 |
+
"learning_rate": 9.56757575757576e-06,
|
| 32 |
+
"loss": 0.5403,
|
| 33 |
+
"step": 10000
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 10.82,
|
| 37 |
+
"learning_rate": 9.45939393939394e-06,
|
| 38 |
+
"loss": 0.5208,
|
| 39 |
+
"step": 12500
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 12.99,
|
| 43 |
+
"learning_rate": 9.351212121212121e-06,
|
| 44 |
+
"loss": 0.4982,
|
| 45 |
+
"step": 15000
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 15.15,
|
| 49 |
+
"learning_rate": 9.243030303030304e-06,
|
| 50 |
+
"loss": 0.4878,
|
| 51 |
+
"step": 17500
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 17.32,
|
| 55 |
+
"learning_rate": 9.134891774891776e-06,
|
| 56 |
+
"loss": 0.5034,
|
| 57 |
+
"step": 20000
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 19.48,
|
| 61 |
+
"learning_rate": 9.026666666666666e-06,
|
| 62 |
+
"loss": 0.4937,
|
| 63 |
+
"step": 22500
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 21.65,
|
| 67 |
+
"learning_rate": 8.91852813852814e-06,
|
| 68 |
+
"loss": 0.5369,
|
| 69 |
+
"step": 25000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 23.81,
|
| 73 |
+
"learning_rate": 8.810346320346321e-06,
|
| 74 |
+
"loss": 0.4645,
|
| 75 |
+
"step": 27500
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 25.97,
|
| 79 |
+
"learning_rate": 8.702121212121212e-06,
|
| 80 |
+
"loss": 0.4509,
|
| 81 |
+
"step": 30000
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 28.14,
|
| 85 |
+
"learning_rate": 8.593939393939395e-06,
|
| 86 |
+
"loss": 0.4499,
|
| 87 |
+
"step": 32500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 30.3,
|
| 91 |
+
"learning_rate": 8.485757575757576e-06,
|
| 92 |
+
"loss": 0.4875,
|
| 93 |
+
"step": 35000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 32.47,
|
| 97 |
+
"learning_rate": 8.377575757575759e-06,
|
| 98 |
+
"loss": 0.4544,
|
| 99 |
+
"step": 37500
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 34.63,
|
| 103 |
+
"learning_rate": 8.26939393939394e-06,
|
| 104 |
+
"loss": 0.4406,
|
| 105 |
+
"step": 40000
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 36.8,
|
| 109 |
+
"learning_rate": 8.161212121212123e-06,
|
| 110 |
+
"loss": 0.4369,
|
| 111 |
+
"step": 42500
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 38.96,
|
| 115 |
+
"learning_rate": 8.053030303030304e-06,
|
| 116 |
+
"loss": 0.4193,
|
| 117 |
+
"step": 45000
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 41.13,
|
| 121 |
+
"learning_rate": 7.944848484848485e-06,
|
| 122 |
+
"loss": 0.4057,
|
| 123 |
+
"step": 47500
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 43.29,
|
| 127 |
+
"learning_rate": 7.836666666666667e-06,
|
| 128 |
+
"loss": 0.3984,
|
| 129 |
+
"step": 50000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 45.45,
|
| 133 |
+
"learning_rate": 7.72848484848485e-06,
|
| 134 |
+
"loss": 0.3911,
|
| 135 |
+
"step": 52500
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 47.62,
|
| 139 |
+
"learning_rate": 7.620303030303031e-06,
|
| 140 |
+
"loss": 0.3861,
|
| 141 |
+
"step": 55000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 49.78,
|
| 145 |
+
"learning_rate": 7.512121212121213e-06,
|
| 146 |
+
"loss": 0.3833,
|
| 147 |
+
"step": 57500
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 51.95,
|
| 151 |
+
"learning_rate": 7.403939393939395e-06,
|
| 152 |
+
"loss": 0.3836,
|
| 153 |
+
"step": 60000
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 54.11,
|
| 157 |
+
"learning_rate": 7.295757575757576e-06,
|
| 158 |
+
"loss": 0.3706,
|
| 159 |
+
"step": 62500
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 56.28,
|
| 163 |
+
"learning_rate": 7.1875757575757576e-06,
|
| 164 |
+
"loss": 0.3625,
|
| 165 |
+
"step": 65000
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 58.44,
|
| 169 |
+
"learning_rate": 7.07939393939394e-06,
|
| 170 |
+
"loss": 0.3563,
|
| 171 |
+
"step": 67500
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 60.61,
|
| 175 |
+
"learning_rate": 6.971212121212122e-06,
|
| 176 |
+
"loss": 0.3522,
|
| 177 |
+
"step": 70000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 62.77,
|
| 181 |
+
"learning_rate": 6.863030303030304e-06,
|
| 182 |
+
"loss": 0.347,
|
| 183 |
+
"step": 72500
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 64.94,
|
| 187 |
+
"learning_rate": 6.754891774891775e-06,
|
| 188 |
+
"loss": 0.3413,
|
| 189 |
+
"step": 75000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 67.1,
|
| 193 |
+
"learning_rate": 6.646709956709957e-06,
|
| 194 |
+
"loss": 0.3355,
|
| 195 |
+
"step": 77500
|
| 196 |
+
}
|
| 197 |
+
],
|
| 198 |
+
"logging_steps": 2500,
|
| 199 |
+
"max_steps": 231000,
|
| 200 |
+
"num_train_epochs": 200,
|
| 201 |
+
"save_steps": 1000,
|
| 202 |
+
"total_flos": 1.863115306612301e+20,
|
| 203 |
+
"trial_name": null,
|
| 204 |
+
"trial_params": null
|
| 205 |
+
}
|