Commit
•
edbc511
1
Parent(s):
6f26459
End of training
Browse files- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +208 -0
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 1.2394252794231484,
|
| 4 |
+
"train_runtime": 3602.0389,
|
| 5 |
+
"train_samples": 128272,
|
| 6 |
+
"train_samples_per_second": 106.833,
|
| 7 |
+
"train_steps_per_second": 0.835
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 1.2394252794231484,
|
| 4 |
+
"train_runtime": 3602.0389,
|
| 5 |
+
"train_samples": 128272,
|
| 6 |
+
"train_samples_per_second": 106.833,
|
| 7 |
+
"train_steps_per_second": 0.835
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,208 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.9996257951852314,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 3006,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.1,
|
| 13 |
+
"learning_rate": 4.833666001330672e-05,
|
| 14 |
+
"loss": 1.4437,
|
| 15 |
+
"step": 100
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.2,
|
| 19 |
+
"learning_rate": 4.6673320026613444e-05,
|
| 20 |
+
"loss": 1.3823,
|
| 21 |
+
"step": 200
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.3,
|
| 25 |
+
"learning_rate": 4.5009980039920164e-05,
|
| 26 |
+
"loss": 1.3499,
|
| 27 |
+
"step": 300
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.4,
|
| 31 |
+
"learning_rate": 4.3346640053226885e-05,
|
| 32 |
+
"loss": 1.3187,
|
| 33 |
+
"step": 400
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.5,
|
| 37 |
+
"learning_rate": 4.1683300066533606e-05,
|
| 38 |
+
"loss": 1.3217,
|
| 39 |
+
"step": 500
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.6,
|
| 43 |
+
"learning_rate": 4.0019960079840326e-05,
|
| 44 |
+
"loss": 1.3004,
|
| 45 |
+
"step": 600
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.7,
|
| 49 |
+
"learning_rate": 3.835662009314704e-05,
|
| 50 |
+
"loss": 1.2892,
|
| 51 |
+
"step": 700
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.8,
|
| 55 |
+
"learning_rate": 3.669328010645376e-05,
|
| 56 |
+
"loss": 1.2834,
|
| 57 |
+
"step": 800
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.9,
|
| 61 |
+
"learning_rate": 3.502994011976048e-05,
|
| 62 |
+
"loss": 1.274,
|
| 63 |
+
"step": 900
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 1.0,
|
| 67 |
+
"learning_rate": 3.33666001330672e-05,
|
| 68 |
+
"loss": 1.2676,
|
| 69 |
+
"step": 1000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 1.1,
|
| 73 |
+
"learning_rate": 3.170326014637392e-05,
|
| 74 |
+
"loss": 1.2393,
|
| 75 |
+
"step": 1100
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 1.2,
|
| 79 |
+
"learning_rate": 3.003992015968064e-05,
|
| 80 |
+
"loss": 1.2381,
|
| 81 |
+
"step": 1200
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 1.3,
|
| 85 |
+
"learning_rate": 2.837658017298736e-05,
|
| 86 |
+
"loss": 1.2341,
|
| 87 |
+
"step": 1300
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 1.4,
|
| 91 |
+
"learning_rate": 2.671324018629408e-05,
|
| 92 |
+
"loss": 1.2248,
|
| 93 |
+
"step": 1400
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 1.5,
|
| 97 |
+
"learning_rate": 2.5049900199600802e-05,
|
| 98 |
+
"loss": 1.213,
|
| 99 |
+
"step": 1500
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 1.6,
|
| 103 |
+
"learning_rate": 2.338656021290752e-05,
|
| 104 |
+
"loss": 1.2051,
|
| 105 |
+
"step": 1600
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 1.7,
|
| 109 |
+
"learning_rate": 2.172322022621424e-05,
|
| 110 |
+
"loss": 1.2271,
|
| 111 |
+
"step": 1700
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 1.8,
|
| 115 |
+
"learning_rate": 2.0059880239520957e-05,
|
| 116 |
+
"loss": 1.2158,
|
| 117 |
+
"step": 1800
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 1.9,
|
| 121 |
+
"learning_rate": 1.8396540252827678e-05,
|
| 122 |
+
"loss": 1.2037,
|
| 123 |
+
"step": 1900
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 2.0,
|
| 127 |
+
"learning_rate": 1.67332002661344e-05,
|
| 128 |
+
"loss": 1.1981,
|
| 129 |
+
"step": 2000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 2.1,
|
| 133 |
+
"learning_rate": 1.506986027944112e-05,
|
| 134 |
+
"loss": 1.1968,
|
| 135 |
+
"step": 2100
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 2.2,
|
| 139 |
+
"learning_rate": 1.3406520292747837e-05,
|
| 140 |
+
"loss": 1.1906,
|
| 141 |
+
"step": 2200
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 2.3,
|
| 145 |
+
"learning_rate": 1.1743180306054557e-05,
|
| 146 |
+
"loss": 1.1746,
|
| 147 |
+
"step": 2300
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 2.39,
|
| 151 |
+
"learning_rate": 1.0079840319361278e-05,
|
| 152 |
+
"loss": 1.1874,
|
| 153 |
+
"step": 2400
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 2.49,
|
| 157 |
+
"learning_rate": 8.416500332667999e-06,
|
| 158 |
+
"loss": 1.1763,
|
| 159 |
+
"step": 2500
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 2.59,
|
| 163 |
+
"learning_rate": 6.753160345974717e-06,
|
| 164 |
+
"loss": 1.1672,
|
| 165 |
+
"step": 2600
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 2.69,
|
| 169 |
+
"learning_rate": 5.0898203592814375e-06,
|
| 170 |
+
"loss": 1.1709,
|
| 171 |
+
"step": 2700
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 2.79,
|
| 175 |
+
"learning_rate": 3.4264803725881573e-06,
|
| 176 |
+
"loss": 1.1677,
|
| 177 |
+
"step": 2800
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 2.89,
|
| 181 |
+
"learning_rate": 1.7631403858948771e-06,
|
| 182 |
+
"loss": 1.1616,
|
| 183 |
+
"step": 2900
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 2.99,
|
| 187 |
+
"learning_rate": 9.98003992015968e-08,
|
| 188 |
+
"loss": 1.1609,
|
| 189 |
+
"step": 3000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 3.0,
|
| 193 |
+
"step": 3006,
|
| 194 |
+
"total_flos": 5.378670905076864e+16,
|
| 195 |
+
"train_loss": 1.2394252794231484,
|
| 196 |
+
"train_runtime": 3602.0389,
|
| 197 |
+
"train_samples_per_second": 106.833,
|
| 198 |
+
"train_steps_per_second": 0.835
|
| 199 |
+
}
|
| 200 |
+
],
|
| 201 |
+
"logging_steps": 100,
|
| 202 |
+
"max_steps": 3006,
|
| 203 |
+
"num_train_epochs": 3,
|
| 204 |
+
"save_steps": 500,
|
| 205 |
+
"total_flos": 5.378670905076864e+16,
|
| 206 |
+
"trial_name": null,
|
| 207 |
+
"trial_params": null
|
| 208 |
+
}
|