Upload trainer_state.json
Browse files- trainer_state.json +214 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,214 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.946428571428571,
|
| 5 |
+
"global_step": 16500,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.09,
|
| 12 |
+
"learning_rate": 1.9956320789411338e-05,
|
| 13 |
+
"loss": 2.043,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.18,
|
| 18 |
+
"learning_rate": 1.9825664732332886e-05,
|
| 19 |
+
"loss": 2.0171,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.27,
|
| 24 |
+
"learning_rate": 1.9609173219450998e-05,
|
| 25 |
+
"loss": 1.9996,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.36,
|
| 30 |
+
"learning_rate": 1.9308737486442045e-05,
|
| 31 |
+
"loss": 2.0033,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.45,
|
| 36 |
+
"learning_rate": 1.8926982092436117e-05,
|
| 37 |
+
"loss": 1.9819,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.54,
|
| 42 |
+
"learning_rate": 1.8467241992282842e-05,
|
| 43 |
+
"loss": 1.9644,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.62,
|
| 48 |
+
"learning_rate": 1.7933533402912354e-05,
|
| 49 |
+
"loss": 1.9713,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.71,
|
| 54 |
+
"learning_rate": 1.7330518718298263e-05,
|
| 55 |
+
"loss": 1.9521,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.8,
|
| 60 |
+
"learning_rate": 1.6663465779520042e-05,
|
| 61 |
+
"loss": 1.9435,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.89,
|
| 66 |
+
"learning_rate": 1.5938201855735017e-05,
|
| 67 |
+
"loss": 1.9492,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.98,
|
| 72 |
+
"learning_rate": 1.5161062738075068e-05,
|
| 73 |
+
"loss": 1.9399,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.07,
|
| 78 |
+
"learning_rate": 1.4338837391175582e-05,
|
| 79 |
+
"loss": 1.9118,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.16,
|
| 84 |
+
"learning_rate": 1.3478708645852272e-05,
|
| 85 |
+
"loss": 1.9172,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.25,
|
| 90 |
+
"learning_rate": 1.2588190451025209e-05,
|
| 91 |
+
"loss": 1.8927,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 1.34,
|
| 96 |
+
"learning_rate": 1.1675062233047365e-05,
|
| 97 |
+
"loss": 1.8941,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.43,
|
| 102 |
+
"learning_rate": 1.0747300935864245e-05,
|
| 103 |
+
"loss": 1.8892,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.52,
|
| 108 |
+
"learning_rate": 9.81301133569098e-06,
|
| 109 |
+
"loss": 1.8915,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 1.61,
|
| 114 |
+
"learning_rate": 8.880355238966923e-06,
|
| 115 |
+
"loss": 1.8914,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.7,
|
| 120 |
+
"learning_rate": 7.957480182103198e-06,
|
| 121 |
+
"loss": 1.882,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 1.79,
|
| 126 |
+
"learning_rate": 7.052448255890958e-06,
|
| 127 |
+
"loss": 1.89,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.88,
|
| 132 |
+
"learning_rate": 6.173165676349103e-06,
|
| 133 |
+
"loss": 1.8947,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 1.96,
|
| 138 |
+
"learning_rate": 5.32731371726938e-06,
|
| 139 |
+
"loss": 1.8757,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 2.05,
|
| 144 |
+
"learning_rate": 4.522281607821288e-06,
|
| 145 |
+
"loss": 1.8693,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 2.14,
|
| 150 |
+
"learning_rate": 3.7651019814126656e-06,
|
| 151 |
+
"loss": 1.8495,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 2.23,
|
| 156 |
+
"learning_rate": 3.0623894397145837e-06,
|
| 157 |
+
"loss": 1.8522,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 2.32,
|
| 162 |
+
"learning_rate": 2.420282768545469e-06,
|
| 163 |
+
"loss": 1.8602,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 2.41,
|
| 168 |
+
"learning_rate": 1.8443913104073984e-06,
|
| 169 |
+
"loss": 1.8625,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 2.5,
|
| 174 |
+
"learning_rate": 1.339745962155613e-06,
|
| 175 |
+
"loss": 1.8574,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 2.59,
|
| 180 |
+
"learning_rate": 9.107552258778907e-07,
|
| 181 |
+
"loss": 1.8522,
|
| 182 |
+
"step": 14500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 2.68,
|
| 186 |
+
"learning_rate": 5.611666969163243e-07,
|
| 187 |
+
"loss": 1.8509,
|
| 188 |
+
"step": 15000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.77,
|
| 192 |
+
"learning_rate": 2.940343254660905e-07,
|
| 193 |
+
"loss": 1.8589,
|
| 194 |
+
"step": 15500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 2.86,
|
| 198 |
+
"learning_rate": 1.1169173774871478e-07,
|
| 199 |
+
"loss": 1.852,
|
| 200 |
+
"step": 16000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 2.95,
|
| 204 |
+
"learning_rate": 1.5731849821833955e-08,
|
| 205 |
+
"loss": 1.8588,
|
| 206 |
+
"step": 16500
|
| 207 |
+
}
|
| 208 |
+
],
|
| 209 |
+
"max_steps": 16800,
|
| 210 |
+
"num_train_epochs": 3,
|
| 211 |
+
"total_flos": 5.864707281361306e+16,
|
| 212 |
+
"trial_name": null,
|
| 213 |
+
"trial_params": null
|
| 214 |
+
}
|