End of training
Browse files- all_results.json +5 -5
- train_results.json +5 -5
- trainer_state.json +207 -87
all_results.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"train_loss":
|
| 4 |
-
"train_runtime":
|
| 5 |
-
"train_samples_per_second":
|
| 6 |
-
"train_steps_per_second": 0.
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 4.03,
|
| 3 |
+
"train_loss": 1.0273077850341796,
|
| 4 |
+
"train_runtime": 12431.9662,
|
| 5 |
+
"train_samples_per_second": 10.296,
|
| 6 |
+
"train_steps_per_second": 0.161
|
| 7 |
}
|
train_results.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"train_loss":
|
| 4 |
-
"train_runtime":
|
| 5 |
-
"train_samples_per_second":
|
| 6 |
-
"train_steps_per_second": 0.
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 4.03,
|
| 3 |
+
"train_loss": 1.0273077850341796,
|
| 4 |
+
"train_runtime": 12431.9662,
|
| 5 |
+
"train_samples_per_second": 10.296,
|
| 6 |
+
"train_steps_per_second": 0.161
|
| 7 |
}
|
trainer_state.json
CHANGED
|
@@ -1,145 +1,265 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
{
|
| 11 |
"epoch": 0.05,
|
| 12 |
-
"learning_rate":
|
| 13 |
-
"loss": 1.
|
| 14 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 0.1,
|
| 18 |
-
"learning_rate":
|
| 19 |
-
"loss": 1.
|
| 20 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
},
|
| 22 |
{
|
| 23 |
"epoch": 0.15,
|
| 24 |
-
"learning_rate":
|
| 25 |
-
"loss": 1.
|
| 26 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
},
|
| 28 |
{
|
| 29 |
"epoch": 0.2,
|
| 30 |
-
"learning_rate":
|
| 31 |
-
"loss": 1.
|
| 32 |
-
"step":
|
| 33 |
},
|
| 34 |
{
|
| 35 |
-
"epoch": 0.
|
| 36 |
-
"learning_rate":
|
| 37 |
-
"loss": 1.
|
| 38 |
-
"step":
|
| 39 |
},
|
| 40 |
{
|
| 41 |
-
"epoch":
|
| 42 |
-
"learning_rate":
|
| 43 |
-
"loss":
|
| 44 |
-
"step":
|
| 45 |
},
|
| 46 |
{
|
| 47 |
-
"epoch":
|
| 48 |
-
"learning_rate": 3.
|
| 49 |
-
"loss":
|
| 50 |
-
"step":
|
| 51 |
},
|
| 52 |
{
|
| 53 |
-
"epoch":
|
| 54 |
-
"learning_rate": 3.
|
| 55 |
-
"loss":
|
| 56 |
-
"step":
|
| 57 |
},
|
| 58 |
{
|
| 59 |
-
"epoch":
|
| 60 |
-
"learning_rate":
|
| 61 |
-
"loss":
|
| 62 |
-
"step":
|
| 63 |
},
|
| 64 |
{
|
| 65 |
-
"epoch":
|
| 66 |
-
"learning_rate":
|
| 67 |
-
"loss": 0.
|
| 68 |
-
"step":
|
| 69 |
},
|
| 70 |
{
|
| 71 |
-
"epoch":
|
| 72 |
-
"learning_rate":
|
| 73 |
-
"loss":
|
| 74 |
-
"step":
|
| 75 |
},
|
| 76 |
{
|
| 77 |
-
"epoch":
|
| 78 |
-
"learning_rate":
|
| 79 |
-
"loss": 0.
|
| 80 |
-
"step":
|
| 81 |
},
|
| 82 |
{
|
| 83 |
-
"epoch":
|
| 84 |
-
"learning_rate":
|
| 85 |
-
"loss": 0.
|
| 86 |
-
"step":
|
| 87 |
},
|
| 88 |
{
|
| 89 |
-
"epoch":
|
| 90 |
-
"learning_rate":
|
| 91 |
-
"loss": 0.
|
| 92 |
-
"step":
|
| 93 |
},
|
| 94 |
{
|
| 95 |
-
"epoch":
|
| 96 |
-
"learning_rate":
|
| 97 |
-
"loss": 0.
|
| 98 |
-
"step":
|
| 99 |
},
|
| 100 |
{
|
| 101 |
-
"epoch":
|
| 102 |
-
"learning_rate":
|
| 103 |
-
"loss":
|
| 104 |
-
"step":
|
| 105 |
},
|
| 106 |
{
|
| 107 |
-
"epoch":
|
| 108 |
-
"learning_rate":
|
| 109 |
-
"loss":
|
| 110 |
-
"step":
|
| 111 |
},
|
| 112 |
{
|
| 113 |
-
"epoch":
|
| 114 |
-
"learning_rate":
|
| 115 |
-
"loss":
|
| 116 |
-
"step":
|
| 117 |
},
|
| 118 |
{
|
| 119 |
-
"epoch":
|
| 120 |
-
"learning_rate": 2.
|
| 121 |
-
"loss":
|
| 122 |
-
"step":
|
| 123 |
},
|
| 124 |
{
|
| 125 |
-
"epoch":
|
| 126 |
-
"learning_rate":
|
| 127 |
-
"loss":
|
| 128 |
-
"step":
|
| 129 |
},
|
| 130 |
{
|
| 131 |
-
"epoch":
|
| 132 |
-
"
|
| 133 |
-
"
|
| 134 |
-
"
|
| 135 |
-
|
| 136 |
-
|
| 137 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 138 |
}
|
| 139 |
],
|
| 140 |
-
"max_steps":
|
| 141 |
"num_train_epochs": 9223372036854775807,
|
| 142 |
-
"total_flos":
|
| 143 |
"trial_name": null,
|
| 144 |
"trial_params": null
|
| 145 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 4.03,
|
| 5 |
+
"global_step": 2000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.03,
|
| 12 |
+
"learning_rate": 2.7416666666666667e-08,
|
| 13 |
+
"loss": 1.3507,
|
| 14 |
+
"step": 50
|
| 15 |
+
},
|
| 16 |
{
|
| 17 |
"epoch": 0.05,
|
| 18 |
+
"learning_rate": 5.658333333333333e-08,
|
| 19 |
+
"loss": 1.3311,
|
| 20 |
+
"step": 100
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.07,
|
| 24 |
+
"learning_rate": 8.575e-08,
|
| 25 |
+
"loss": 1.3252,
|
| 26 |
+
"step": 150
|
| 27 |
},
|
| 28 |
{
|
| 29 |
"epoch": 0.1,
|
| 30 |
+
"learning_rate": 1.1491666666666665e-07,
|
| 31 |
+
"loss": 1.2374,
|
| 32 |
+
"step": 200
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.12,
|
| 36 |
+
"learning_rate": 1.4408333333333332e-07,
|
| 37 |
+
"loss": 1.2842,
|
| 38 |
+
"step": 250
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 0.15,
|
| 42 |
+
"learning_rate": 1.7325e-07,
|
| 43 |
+
"loss": 1.1666,
|
| 44 |
+
"step": 300
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.17,
|
| 48 |
+
"learning_rate": 2.0241666666666666e-07,
|
| 49 |
+
"loss": 1.0935,
|
| 50 |
+
"step": 350
|
| 51 |
},
|
| 52 |
{
|
| 53 |
"epoch": 0.2,
|
| 54 |
+
"learning_rate": 2.315833333333333e-07,
|
| 55 |
+
"loss": 1.0436,
|
| 56 |
+
"step": 400
|
| 57 |
},
|
| 58 |
{
|
| 59 |
+
"epoch": 0.23,
|
| 60 |
+
"learning_rate": 2.6075e-07,
|
| 61 |
+
"loss": 1.0156,
|
| 62 |
+
"step": 450
|
| 63 |
},
|
| 64 |
{
|
| 65 |
+
"epoch": 1.01,
|
| 66 |
+
"learning_rate": 2.8991666666666667e-07,
|
| 67 |
+
"loss": 1.1327,
|
| 68 |
+
"step": 500
|
| 69 |
},
|
| 70 |
{
|
| 71 |
+
"epoch": 1.03,
|
| 72 |
+
"learning_rate": 3.190833333333333e-07,
|
| 73 |
+
"loss": 1.3554,
|
| 74 |
+
"step": 550
|
| 75 |
},
|
| 76 |
{
|
| 77 |
+
"epoch": 1.06,
|
| 78 |
+
"learning_rate": 3.4824999999999996e-07,
|
| 79 |
+
"loss": 1.2085,
|
| 80 |
+
"step": 600
|
| 81 |
},
|
| 82 |
{
|
| 83 |
+
"epoch": 1.08,
|
| 84 |
+
"learning_rate": 3.3825e-07,
|
| 85 |
+
"loss": 1.2987,
|
| 86 |
+
"step": 650
|
| 87 |
},
|
| 88 |
{
|
| 89 |
+
"epoch": 1.11,
|
| 90 |
+
"learning_rate": 3.2574999999999996e-07,
|
| 91 |
+
"loss": 0.9905,
|
| 92 |
+
"step": 700
|
| 93 |
},
|
| 94 |
{
|
| 95 |
+
"epoch": 1.13,
|
| 96 |
+
"learning_rate": 3.1325e-07,
|
| 97 |
+
"loss": 1.0011,
|
| 98 |
+
"step": 750
|
| 99 |
},
|
| 100 |
{
|
| 101 |
+
"epoch": 1.16,
|
| 102 |
+
"learning_rate": 3.0075e-07,
|
| 103 |
+
"loss": 0.9573,
|
| 104 |
+
"step": 800
|
| 105 |
},
|
| 106 |
{
|
| 107 |
+
"epoch": 1.18,
|
| 108 |
+
"learning_rate": 2.8825e-07,
|
| 109 |
+
"loss": 0.9946,
|
| 110 |
+
"step": 850
|
| 111 |
},
|
| 112 |
{
|
| 113 |
+
"epoch": 1.21,
|
| 114 |
+
"learning_rate": 2.7574999999999996e-07,
|
| 115 |
+
"loss": 0.9934,
|
| 116 |
+
"step": 900
|
| 117 |
},
|
| 118 |
{
|
| 119 |
+
"epoch": 1.23,
|
| 120 |
+
"learning_rate": 2.6325e-07,
|
| 121 |
+
"loss": 0.9519,
|
| 122 |
+
"step": 950
|
| 123 |
},
|
| 124 |
{
|
| 125 |
+
"epoch": 2.02,
|
| 126 |
+
"learning_rate": 2.5075e-07,
|
| 127 |
+
"loss": 1.042,
|
| 128 |
+
"step": 1000
|
| 129 |
},
|
| 130 |
{
|
| 131 |
+
"epoch": 2.04,
|
| 132 |
+
"learning_rate": 2.3824999999999998e-07,
|
| 133 |
+
"loss": 1.0339,
|
| 134 |
+
"step": 1050
|
| 135 |
},
|
| 136 |
{
|
| 137 |
+
"epoch": 2.06,
|
| 138 |
+
"learning_rate": 2.2575e-07,
|
| 139 |
+
"loss": 1.0101,
|
| 140 |
+
"step": 1100
|
| 141 |
},
|
| 142 |
{
|
| 143 |
+
"epoch": 2.09,
|
| 144 |
+
"learning_rate": 2.1325e-07,
|
| 145 |
+
"loss": 1.0805,
|
| 146 |
+
"step": 1150
|
| 147 |
},
|
| 148 |
{
|
| 149 |
+
"epoch": 2.12,
|
| 150 |
+
"learning_rate": 2.0075000000000002e-07,
|
| 151 |
+
"loss": 0.8829,
|
| 152 |
+
"step": 1200
|
| 153 |
},
|
| 154 |
{
|
| 155 |
+
"epoch": 2.14,
|
| 156 |
+
"learning_rate": 1.8824999999999998e-07,
|
| 157 |
+
"loss": 0.901,
|
| 158 |
+
"step": 1250
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 2.17,
|
| 162 |
+
"learning_rate": 1.7574999999999997e-07,
|
| 163 |
+
"loss": 0.8773,
|
| 164 |
+
"step": 1300
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 2.19,
|
| 168 |
+
"learning_rate": 1.6324999999999998e-07,
|
| 169 |
+
"loss": 0.921,
|
| 170 |
+
"step": 1350
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 2.21,
|
| 174 |
+
"learning_rate": 1.5075e-07,
|
| 175 |
+
"loss": 0.8838,
|
| 176 |
+
"step": 1400
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 2.24,
|
| 180 |
+
"learning_rate": 1.3825e-07,
|
| 181 |
+
"loss": 0.9622,
|
| 182 |
+
"step": 1450
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 3.02,
|
| 186 |
+
"learning_rate": 1.2575e-07,
|
| 187 |
+
"loss": 0.9518,
|
| 188 |
+
"step": 1500
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 3.05,
|
| 192 |
+
"learning_rate": 1.1325e-07,
|
| 193 |
+
"loss": 0.9739,
|
| 194 |
+
"step": 1550
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 3.07,
|
| 198 |
+
"learning_rate": 1.0075e-07,
|
| 199 |
+
"loss": 0.9918,
|
| 200 |
+
"step": 1600
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 3.1,
|
| 204 |
+
"learning_rate": 8.825e-08,
|
| 205 |
+
"loss": 0.9803,
|
| 206 |
+
"step": 1650
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 3.12,
|
| 210 |
+
"learning_rate": 7.575e-08,
|
| 211 |
+
"loss": 0.8518,
|
| 212 |
+
"step": 1700
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 3.15,
|
| 216 |
+
"learning_rate": 6.325e-08,
|
| 217 |
+
"loss": 0.8628,
|
| 218 |
+
"step": 1750
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 3.17,
|
| 222 |
+
"learning_rate": 5.0749999999999995e-08,
|
| 223 |
+
"loss": 0.864,
|
| 224 |
+
"step": 1800
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 3.2,
|
| 228 |
+
"learning_rate": 3.825e-08,
|
| 229 |
+
"loss": 0.9134,
|
| 230 |
+
"step": 1850
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 3.22,
|
| 234 |
+
"learning_rate": 2.5749999999999996e-08,
|
| 235 |
+
"loss": 0.828,
|
| 236 |
+
"step": 1900
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 4.0,
|
| 240 |
+
"learning_rate": 1.3250000000000001e-08,
|
| 241 |
+
"loss": 0.9324,
|
| 242 |
+
"step": 1950
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 4.03,
|
| 246 |
+
"learning_rate": 7.5e-10,
|
| 247 |
+
"loss": 0.6153,
|
| 248 |
+
"step": 2000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 4.03,
|
| 252 |
+
"step": 2000,
|
| 253 |
+
"total_flos": 3.15121729536e+18,
|
| 254 |
+
"train_loss": 1.0273077850341796,
|
| 255 |
+
"train_runtime": 12431.9662,
|
| 256 |
+
"train_samples_per_second": 10.296,
|
| 257 |
+
"train_steps_per_second": 0.161
|
| 258 |
}
|
| 259 |
],
|
| 260 |
+
"max_steps": 2000,
|
| 261 |
"num_train_epochs": 9223372036854775807,
|
| 262 |
+
"total_flos": 3.15121729536e+18,
|
| 263 |
"trial_name": null,
|
| 264 |
"trial_params": null
|
| 265 |
}
|