Commit
•
9d2338f
1
Parent(s):
744a563
End of training
Browse files- all_results.json +14 -0
- eval_results.json +9 -0
- runs/Jun15_08-35-27_labgpu/events.out.tfevents.1655291370.labgpu.1906.2 +3 -0
- train_results.json +8 -0
- trainer_state.json +277 -0
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.9036697247706422,
|
| 4 |
+
"eval_loss": 1.1730189323425293,
|
| 5 |
+
"eval_runtime": 4.6464,
|
| 6 |
+
"eval_samples": 872,
|
| 7 |
+
"eval_samples_per_second": 187.674,
|
| 8 |
+
"eval_steps_per_second": 23.459,
|
| 9 |
+
"train_loss": 5265.971264971169,
|
| 10 |
+
"train_runtime": 8516.6719,
|
| 11 |
+
"train_samples": 67349,
|
| 12 |
+
"train_samples_per_second": 79.079,
|
| 13 |
+
"train_steps_per_second": 2.472
|
| 14 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.9036697247706422,
|
| 4 |
+
"eval_loss": 1.1730189323425293,
|
| 5 |
+
"eval_runtime": 4.6464,
|
| 6 |
+
"eval_samples": 872,
|
| 7 |
+
"eval_samples_per_second": 187.674,
|
| 8 |
+
"eval_steps_per_second": 23.459
|
| 9 |
+
}
|
runs/Jun15_08-35-27_labgpu/events.out.tfevents.1655291370.labgpu.1906.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4b552e6fadfe5cd5b476f182a20cdfe441fd9efe037a1a055088b65e266a7904
|
| 3 |
+
size 369
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"train_loss": 5265.971264971169,
|
| 4 |
+
"train_runtime": 8516.6719,
|
| 5 |
+
"train_samples": 67349,
|
| 6 |
+
"train_samples_per_second": 79.079,
|
| 7 |
+
"train_steps_per_second": 2.472
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,277 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"global_step": 21050,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.24,
|
| 12 |
+
"learning_rate": 9.7624703087886e-06,
|
| 13 |
+
"loss": 221692.304,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.48,
|
| 18 |
+
"learning_rate": 9.524940617577197e-06,
|
| 19 |
+
"loss": 0.2815,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.71,
|
| 24 |
+
"learning_rate": 9.287410926365797e-06,
|
| 25 |
+
"loss": 0.2438,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.95,
|
| 30 |
+
"learning_rate": 9.049881235154396e-06,
|
| 31 |
+
"loss": 0.2325,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 1.19,
|
| 36 |
+
"learning_rate": 8.812351543942995e-06,
|
| 37 |
+
"loss": 0.1994,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.43,
|
| 42 |
+
"learning_rate": 8.574821852731592e-06,
|
| 43 |
+
"loss": 0.1864,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.66,
|
| 48 |
+
"learning_rate": 8.337292161520191e-06,
|
| 49 |
+
"loss": 0.18,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 1.9,
|
| 54 |
+
"learning_rate": 8.099762470308789e-06,
|
| 55 |
+
"loss": 0.1788,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 2.14,
|
| 60 |
+
"learning_rate": 7.862232779097388e-06,
|
| 61 |
+
"loss": 0.1615,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 2.38,
|
| 66 |
+
"learning_rate": 7.624703087885986e-06,
|
| 67 |
+
"loss": 0.1516,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 2.61,
|
| 72 |
+
"learning_rate": 7.387173396674585e-06,
|
| 73 |
+
"loss": 0.1486,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 2.85,
|
| 78 |
+
"learning_rate": 7.149643705463184e-06,
|
| 79 |
+
"loss": 0.1462,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 3.09,
|
| 84 |
+
"learning_rate": 6.912114014251782e-06,
|
| 85 |
+
"loss": 0.134,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 3.33,
|
| 90 |
+
"learning_rate": 6.674584323040381e-06,
|
| 91 |
+
"loss": 0.1328,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 3.56,
|
| 96 |
+
"learning_rate": 6.437054631828979e-06,
|
| 97 |
+
"loss": 0.1229,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 3.8,
|
| 102 |
+
"learning_rate": 6.199524940617578e-06,
|
| 103 |
+
"loss": 0.1204,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 4.04,
|
| 108 |
+
"learning_rate": 5.961995249406176e-06,
|
| 109 |
+
"loss": 0.1323,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 4.28,
|
| 114 |
+
"learning_rate": 5.724465558194775e-06,
|
| 115 |
+
"loss": 0.1131,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 4.51,
|
| 120 |
+
"learning_rate": 5.486935866983374e-06,
|
| 121 |
+
"loss": 0.122,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 4.75,
|
| 126 |
+
"learning_rate": 5.2494061757719716e-06,
|
| 127 |
+
"loss": 0.1081,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 4.99,
|
| 132 |
+
"learning_rate": 5.011876484560571e-06,
|
| 133 |
+
"loss": 0.1061,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 5.23,
|
| 138 |
+
"learning_rate": 4.774346793349169e-06,
|
| 139 |
+
"loss": 0.0975,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 5.46,
|
| 144 |
+
"learning_rate": 4.536817102137768e-06,
|
| 145 |
+
"loss": 0.094,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 5.7,
|
| 150 |
+
"learning_rate": 4.299287410926366e-06,
|
| 151 |
+
"loss": 0.1133,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 5.94,
|
| 156 |
+
"learning_rate": 4.061757719714965e-06,
|
| 157 |
+
"loss": 0.0999,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 6.18,
|
| 162 |
+
"learning_rate": 3.824228028503563e-06,
|
| 163 |
+
"loss": 0.0899,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 6.41,
|
| 168 |
+
"learning_rate": 3.5866983372921617e-06,
|
| 169 |
+
"loss": 0.0921,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 6.65,
|
| 174 |
+
"learning_rate": 3.3491686460807604e-06,
|
| 175 |
+
"loss": 0.083,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 6.89,
|
| 180 |
+
"learning_rate": 3.1116389548693587e-06,
|
| 181 |
+
"loss": 0.0909,
|
| 182 |
+
"step": 14500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 7.13,
|
| 186 |
+
"learning_rate": 2.874109263657958e-06,
|
| 187 |
+
"loss": 0.0772,
|
| 188 |
+
"step": 15000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 7.36,
|
| 192 |
+
"learning_rate": 2.636579572446556e-06,
|
| 193 |
+
"loss": 0.1717,
|
| 194 |
+
"step": 15500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 7.6,
|
| 198 |
+
"learning_rate": 2.3990498812351544e-06,
|
| 199 |
+
"loss": 0.0863,
|
| 200 |
+
"step": 16000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 7.84,
|
| 204 |
+
"learning_rate": 2.161520190023753e-06,
|
| 205 |
+
"loss": 0.0827,
|
| 206 |
+
"step": 16500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 8.08,
|
| 210 |
+
"learning_rate": 1.9239904988123518e-06,
|
| 211 |
+
"loss": 0.0726,
|
| 212 |
+
"step": 17000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 8.31,
|
| 216 |
+
"learning_rate": 1.6864608076009503e-06,
|
| 217 |
+
"loss": 0.081,
|
| 218 |
+
"step": 17500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 8.55,
|
| 222 |
+
"learning_rate": 1.448931116389549e-06,
|
| 223 |
+
"loss": 0.0779,
|
| 224 |
+
"step": 18000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 8.79,
|
| 228 |
+
"learning_rate": 1.2114014251781475e-06,
|
| 229 |
+
"loss": 0.077,
|
| 230 |
+
"step": 18500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 9.03,
|
| 234 |
+
"learning_rate": 9.73871733966746e-07,
|
| 235 |
+
"loss": 0.0747,
|
| 236 |
+
"step": 19000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 9.26,
|
| 240 |
+
"learning_rate": 7.363420427553445e-07,
|
| 241 |
+
"loss": 0.0676,
|
| 242 |
+
"step": 19500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 9.5,
|
| 246 |
+
"learning_rate": 4.988123515439431e-07,
|
| 247 |
+
"loss": 0.0989,
|
| 248 |
+
"step": 20000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 9.74,
|
| 252 |
+
"learning_rate": 2.6128266033254157e-07,
|
| 253 |
+
"loss": 0.0746,
|
| 254 |
+
"step": 20500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 9.98,
|
| 258 |
+
"learning_rate": 2.3752969121140145e-08,
|
| 259 |
+
"loss": 0.0738,
|
| 260 |
+
"step": 21000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 10.0,
|
| 264 |
+
"step": 21050,
|
| 265 |
+
"total_flos": 1.05583904453376e+16,
|
| 266 |
+
"train_loss": 5265.971264971169,
|
| 267 |
+
"train_runtime": 8516.6719,
|
| 268 |
+
"train_samples_per_second": 79.079,
|
| 269 |
+
"train_steps_per_second": 2.472
|
| 270 |
+
}
|
| 271 |
+
],
|
| 272 |
+
"max_steps": 21050,
|
| 273 |
+
"num_train_epochs": 10,
|
| 274 |
+
"total_flos": 1.05583904453376e+16,
|
| 275 |
+
"trial_name": null,
|
| 276 |
+
"trial_params": null
|
| 277 |
+
}
|