Commit
·
d68f4da
1
Parent(s):
7f53205
End of training
Browse files- all_results.json +8 -0
- train_results.json +8 -0
- train_results.txt +6 -0
- trainer_state.json +223 -0
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"train_loss": 2.1781476905338715,
|
| 4 |
+
"train_runtime": 3749.3942,
|
| 5 |
+
"train_samples": 42367,
|
| 6 |
+
"train_samples_per_second": 56.498,
|
| 7 |
+
"train_steps_per_second": 0.883
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"train_loss": 2.1781476905338715,
|
| 4 |
+
"train_runtime": 3749.3942,
|
| 5 |
+
"train_samples": 42367,
|
| 6 |
+
"train_samples_per_second": 56.498,
|
| 7 |
+
"train_steps_per_second": 0.883
|
| 8 |
+
}
|
train_results.txt
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
epoch = 5.0
|
| 2 |
+
train_loss = 2.1781476905338715
|
| 3 |
+
train_runtime = 3749.3942
|
| 4 |
+
train_samples = 42367
|
| 5 |
+
train_samples_per_second = 56.498
|
| 6 |
+
train_steps_per_second = 0.883
|
trainer_state.json
ADDED
|
@@ -0,0 +1,223 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"global_step": 3310,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.15,
|
| 12 |
+
"learning_rate": 9.063444108761328e-06,
|
| 13 |
+
"loss": 5.5777,
|
| 14 |
+
"step": 100
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.3,
|
| 18 |
+
"learning_rate": 1.8126888217522657e-05,
|
| 19 |
+
"loss": 2.7803,
|
| 20 |
+
"step": 200
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.45,
|
| 24 |
+
"learning_rate": 2.719033232628399e-05,
|
| 25 |
+
"loss": 2.5334,
|
| 26 |
+
"step": 300
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.6,
|
| 30 |
+
"learning_rate": 2.9305135951661632e-05,
|
| 31 |
+
"loss": 2.4384,
|
| 32 |
+
"step": 400
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.76,
|
| 36 |
+
"learning_rate": 2.8298086606243708e-05,
|
| 37 |
+
"loss": 2.3651,
|
| 38 |
+
"step": 500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.91,
|
| 42 |
+
"learning_rate": 2.729103726082578e-05,
|
| 43 |
+
"loss": 2.3344,
|
| 44 |
+
"step": 600
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.06,
|
| 48 |
+
"learning_rate": 2.6283987915407858e-05,
|
| 49 |
+
"loss": 2.2344,
|
| 50 |
+
"step": 700
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 1.21,
|
| 54 |
+
"learning_rate": 2.527693856998993e-05,
|
| 55 |
+
"loss": 2.1806,
|
| 56 |
+
"step": 800
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 1.36,
|
| 60 |
+
"learning_rate": 2.4269889224572005e-05,
|
| 61 |
+
"loss": 2.1647,
|
| 62 |
+
"step": 900
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 1.51,
|
| 66 |
+
"learning_rate": 2.3262839879154077e-05,
|
| 67 |
+
"loss": 2.1694,
|
| 68 |
+
"step": 1000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.66,
|
| 72 |
+
"learning_rate": 2.2255790533736152e-05,
|
| 73 |
+
"loss": 2.1443,
|
| 74 |
+
"step": 1100
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.81,
|
| 78 |
+
"learning_rate": 2.124874118831823e-05,
|
| 79 |
+
"loss": 2.1277,
|
| 80 |
+
"step": 1200
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.96,
|
| 84 |
+
"learning_rate": 2.0241691842900302e-05,
|
| 85 |
+
"loss": 2.1174,
|
| 86 |
+
"step": 1300
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 2.11,
|
| 90 |
+
"learning_rate": 1.9234642497482378e-05,
|
| 91 |
+
"loss": 2.0509,
|
| 92 |
+
"step": 1400
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 2.27,
|
| 96 |
+
"learning_rate": 1.822759315206445e-05,
|
| 97 |
+
"loss": 2.0195,
|
| 98 |
+
"step": 1500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 2.42,
|
| 102 |
+
"learning_rate": 1.7220543806646525e-05,
|
| 103 |
+
"loss": 1.9997,
|
| 104 |
+
"step": 1600
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 2.57,
|
| 108 |
+
"learning_rate": 1.6213494461228603e-05,
|
| 109 |
+
"loss": 2.015,
|
| 110 |
+
"step": 1700
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 2.72,
|
| 114 |
+
"learning_rate": 1.5206445115810675e-05,
|
| 115 |
+
"loss": 2.024,
|
| 116 |
+
"step": 1800
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 2.87,
|
| 120 |
+
"learning_rate": 1.419939577039275e-05,
|
| 121 |
+
"loss": 2.0084,
|
| 122 |
+
"step": 1900
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 3.02,
|
| 126 |
+
"learning_rate": 1.3192346424974824e-05,
|
| 127 |
+
"loss": 1.9815,
|
| 128 |
+
"step": 2000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 3.17,
|
| 132 |
+
"learning_rate": 1.2185297079556899e-05,
|
| 133 |
+
"loss": 1.915,
|
| 134 |
+
"step": 2100
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 3.32,
|
| 138 |
+
"learning_rate": 1.1178247734138972e-05,
|
| 139 |
+
"loss": 1.9194,
|
| 140 |
+
"step": 2200
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 3.47,
|
| 144 |
+
"learning_rate": 1.0171198388721048e-05,
|
| 145 |
+
"loss": 1.9254,
|
| 146 |
+
"step": 2300
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 3.63,
|
| 150 |
+
"learning_rate": 9.164149043303123e-06,
|
| 151 |
+
"loss": 1.928,
|
| 152 |
+
"step": 2400
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 3.78,
|
| 156 |
+
"learning_rate": 8.157099697885196e-06,
|
| 157 |
+
"loss": 1.9235,
|
| 158 |
+
"step": 2500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 3.93,
|
| 162 |
+
"learning_rate": 7.1500503524672715e-06,
|
| 163 |
+
"loss": 1.9297,
|
| 164 |
+
"step": 2600
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 4.08,
|
| 168 |
+
"learning_rate": 6.143001007049345e-06,
|
| 169 |
+
"loss": 1.8951,
|
| 170 |
+
"step": 2700
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 4.23,
|
| 174 |
+
"learning_rate": 5.13595166163142e-06,
|
| 175 |
+
"loss": 1.8589,
|
| 176 |
+
"step": 2800
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 4.38,
|
| 180 |
+
"learning_rate": 4.1289023162134946e-06,
|
| 181 |
+
"loss": 1.8632,
|
| 182 |
+
"step": 2900
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 4.53,
|
| 186 |
+
"learning_rate": 3.121852970795569e-06,
|
| 187 |
+
"loss": 1.8684,
|
| 188 |
+
"step": 3000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 4.68,
|
| 192 |
+
"learning_rate": 2.1148036253776437e-06,
|
| 193 |
+
"loss": 1.8738,
|
| 194 |
+
"step": 3100
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 4.83,
|
| 198 |
+
"learning_rate": 1.107754279959718e-06,
|
| 199 |
+
"loss": 1.876,
|
| 200 |
+
"step": 3200
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 4.98,
|
| 204 |
+
"learning_rate": 1.0070493454179255e-07,
|
| 205 |
+
"loss": 1.8678,
|
| 206 |
+
"step": 3300
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 5.0,
|
| 210 |
+
"step": 3310,
|
| 211 |
+
"total_flos": 5.435050739908608e+16,
|
| 212 |
+
"train_loss": 2.1781476905338715,
|
| 213 |
+
"train_runtime": 3749.3942,
|
| 214 |
+
"train_samples_per_second": 56.498,
|
| 215 |
+
"train_steps_per_second": 0.883
|
| 216 |
+
}
|
| 217 |
+
],
|
| 218 |
+
"max_steps": 3310,
|
| 219 |
+
"num_train_epochs": 5,
|
| 220 |
+
"total_flos": 5.435050739908608e+16,
|
| 221 |
+
"trial_name": null,
|
| 222 |
+
"trial_params": null
|
| 223 |
+
}
|