Commit
·
6919853
1
Parent(s):
6a90420
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": 2.0527755599007507,
|
| 4 |
+
"train_runtime": 3751.6871,
|
| 5 |
+
"train_samples": 42367,
|
| 6 |
+
"train_samples_per_second": 56.464,
|
| 7 |
+
"train_steps_per_second": 0.882
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"train_loss": 2.0527755599007507,
|
| 4 |
+
"train_runtime": 3751.6871,
|
| 5 |
+
"train_samples": 42367,
|
| 6 |
+
"train_samples_per_second": 56.464,
|
| 7 |
+
"train_steps_per_second": 0.882
|
| 8 |
+
}
|
train_results.txt
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
epoch = 5.0
|
| 2 |
+
train_loss = 2.0527755599007507
|
| 3 |
+
train_runtime = 3751.6871
|
| 4 |
+
train_samples = 42367
|
| 5 |
+
train_samples_per_second = 56.464
|
| 6 |
+
train_steps_per_second = 0.882
|
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": 1.5105740181268882e-05,
|
| 13 |
+
"loss": 5.0514,
|
| 14 |
+
"step": 100
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.3,
|
| 18 |
+
"learning_rate": 3.0211480362537764e-05,
|
| 19 |
+
"loss": 2.6625,
|
| 20 |
+
"step": 200
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.45,
|
| 24 |
+
"learning_rate": 4.5317220543806646e-05,
|
| 25 |
+
"loss": 2.454,
|
| 26 |
+
"step": 300
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.6,
|
| 30 |
+
"learning_rate": 4.884189325276939e-05,
|
| 31 |
+
"loss": 2.3849,
|
| 32 |
+
"step": 400
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.76,
|
| 36 |
+
"learning_rate": 4.7163477677072846e-05,
|
| 37 |
+
"loss": 2.322,
|
| 38 |
+
"step": 500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.91,
|
| 42 |
+
"learning_rate": 4.5485062101376303e-05,
|
| 43 |
+
"loss": 2.2943,
|
| 44 |
+
"step": 600
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.06,
|
| 48 |
+
"learning_rate": 4.380664652567976e-05,
|
| 49 |
+
"loss": 2.1795,
|
| 50 |
+
"step": 700
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 1.21,
|
| 54 |
+
"learning_rate": 4.212823094998322e-05,
|
| 55 |
+
"loss": 2.1046,
|
| 56 |
+
"step": 800
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 1.36,
|
| 60 |
+
"learning_rate": 4.0449815374286676e-05,
|
| 61 |
+
"loss": 2.0928,
|
| 62 |
+
"step": 900
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 1.51,
|
| 66 |
+
"learning_rate": 3.877139979859013e-05,
|
| 67 |
+
"loss": 2.0994,
|
| 68 |
+
"step": 1000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.66,
|
| 72 |
+
"learning_rate": 3.709298422289359e-05,
|
| 73 |
+
"loss": 2.0772,
|
| 74 |
+
"step": 1100
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.81,
|
| 78 |
+
"learning_rate": 3.541456864719705e-05,
|
| 79 |
+
"loss": 2.0609,
|
| 80 |
+
"step": 1200
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.96,
|
| 84 |
+
"learning_rate": 3.3736153071500506e-05,
|
| 85 |
+
"loss": 2.0526,
|
| 86 |
+
"step": 1300
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 2.11,
|
| 90 |
+
"learning_rate": 3.2057737495803964e-05,
|
| 91 |
+
"loss": 1.9463,
|
| 92 |
+
"step": 1400
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 2.27,
|
| 96 |
+
"learning_rate": 3.0379321920107418e-05,
|
| 97 |
+
"loss": 1.906,
|
| 98 |
+
"step": 1500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 2.42,
|
| 102 |
+
"learning_rate": 2.870090634441088e-05,
|
| 103 |
+
"loss": 1.8914,
|
| 104 |
+
"step": 1600
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 2.57,
|
| 108 |
+
"learning_rate": 2.7022490768714336e-05,
|
| 109 |
+
"loss": 1.9058,
|
| 110 |
+
"step": 1700
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 2.72,
|
| 114 |
+
"learning_rate": 2.534407519301779e-05,
|
| 115 |
+
"loss": 1.9173,
|
| 116 |
+
"step": 1800
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 2.87,
|
| 120 |
+
"learning_rate": 2.366565961732125e-05,
|
| 121 |
+
"loss": 1.9018,
|
| 122 |
+
"step": 1900
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 3.02,
|
| 126 |
+
"learning_rate": 2.198724404162471e-05,
|
| 127 |
+
"loss": 1.8706,
|
| 128 |
+
"step": 2000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 3.17,
|
| 132 |
+
"learning_rate": 2.0308828465928163e-05,
|
| 133 |
+
"loss": 1.767,
|
| 134 |
+
"step": 2100
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 3.32,
|
| 138 |
+
"learning_rate": 1.863041289023162e-05,
|
| 139 |
+
"loss": 1.7729,
|
| 140 |
+
"step": 2200
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 3.47,
|
| 144 |
+
"learning_rate": 1.6951997314535078e-05,
|
| 145 |
+
"loss": 1.7836,
|
| 146 |
+
"step": 2300
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 3.63,
|
| 150 |
+
"learning_rate": 1.527358173883854e-05,
|
| 151 |
+
"loss": 1.7858,
|
| 152 |
+
"step": 2400
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 3.78,
|
| 156 |
+
"learning_rate": 1.3595166163141995e-05,
|
| 157 |
+
"loss": 1.7817,
|
| 158 |
+
"step": 2500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 3.93,
|
| 162 |
+
"learning_rate": 1.1916750587445452e-05,
|
| 163 |
+
"loss": 1.7874,
|
| 164 |
+
"step": 2600
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 4.08,
|
| 168 |
+
"learning_rate": 1.0238335011748908e-05,
|
| 169 |
+
"loss": 1.7385,
|
| 170 |
+
"step": 2700
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 4.23,
|
| 174 |
+
"learning_rate": 8.559919436052368e-06,
|
| 175 |
+
"loss": 1.6889,
|
| 176 |
+
"step": 2800
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 4.38,
|
| 180 |
+
"learning_rate": 6.881503860355824e-06,
|
| 181 |
+
"loss": 1.6939,
|
| 182 |
+
"step": 2900
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 4.53,
|
| 186 |
+
"learning_rate": 5.203088284659282e-06,
|
| 187 |
+
"loss": 1.6974,
|
| 188 |
+
"step": 3000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 4.68,
|
| 192 |
+
"learning_rate": 3.5246727089627398e-06,
|
| 193 |
+
"loss": 1.7041,
|
| 194 |
+
"step": 3100
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 4.83,
|
| 198 |
+
"learning_rate": 1.8462571332661969e-06,
|
| 199 |
+
"loss": 1.7036,
|
| 200 |
+
"step": 3200
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 4.98,
|
| 204 |
+
"learning_rate": 1.6784155756965426e-07,
|
| 205 |
+
"loss": 1.6982,
|
| 206 |
+
"step": 3300
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 5.0,
|
| 210 |
+
"step": 3310,
|
| 211 |
+
"total_flos": 5.435050739908608e+16,
|
| 212 |
+
"train_loss": 2.0527755599007507,
|
| 213 |
+
"train_runtime": 3751.6871,
|
| 214 |
+
"train_samples_per_second": 56.464,
|
| 215 |
+
"train_steps_per_second": 0.882
|
| 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 |
+
}
|