End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"eval_loss": 1.8519543409347534,
|
| 4 |
+
"eval_runtime": 89.6916,
|
| 5 |
+
"eval_samples": 30164,
|
| 6 |
+
"eval_samples_per_second": 336.308,
|
| 7 |
+
"eval_steps_per_second": 5.262,
|
| 8 |
+
"perplexity": 6.372260931650048,
|
| 9 |
+
"train_loss": 2.197303864837425,
|
| 10 |
+
"train_runtime": 7444.9411,
|
| 11 |
+
"train_samples": 573110,
|
| 12 |
+
"train_samples_per_second": 153.96,
|
| 13 |
+
"train_steps_per_second": 2.406
|
| 14 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"eval_loss": 1.8519543409347534,
|
| 4 |
+
"eval_runtime": 89.6916,
|
| 5 |
+
"eval_samples": 30164,
|
| 6 |
+
"eval_samples_per_second": 336.308,
|
| 7 |
+
"eval_steps_per_second": 5.262,
|
| 8 |
+
"perplexity": 6.372260931650048
|
| 9 |
+
}
|
runs/Oct21_16-00-14_2c937cb10a27/events.out.tfevents.1634832066.2c937cb10a27.5120.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ea9fe62e196f2fef0e0626f82159cd6b254f7631ea934a2016b9b3eaf661edd
|
| 3 |
+
size 9548
|
runs/Oct21_16-00-14_2c937cb10a27/events.out.tfevents.1634839605.2c937cb10a27.5120.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6c6beb2484d116840d6ba74f31893f914f3b8c475b075902b7cd521eb02f37ec
|
| 3 |
+
size 316
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"train_loss": 2.197303864837425,
|
| 4 |
+
"train_runtime": 7444.9411,
|
| 5 |
+
"train_samples": 573110,
|
| 6 |
+
"train_samples_per_second": 153.96,
|
| 7 |
+
"train_steps_per_second": 2.406
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,251 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"global_step": 17910,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.06,
|
| 12 |
+
"learning_rate": 1.944165270798437e-05,
|
| 13 |
+
"loss": 3.7464,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.11,
|
| 18 |
+
"learning_rate": 1.8883305415968732e-05,
|
| 19 |
+
"loss": 3.0711,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.17,
|
| 24 |
+
"learning_rate": 1.83249581239531e-05,
|
| 25 |
+
"loss": 2.8204,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.22,
|
| 30 |
+
"learning_rate": 1.7766610831937466e-05,
|
| 31 |
+
"loss": 2.6566,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.28,
|
| 36 |
+
"learning_rate": 1.720826353992183e-05,
|
| 37 |
+
"loss": 2.5476,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.34,
|
| 42 |
+
"learning_rate": 1.66499162479062e-05,
|
| 43 |
+
"loss": 2.4642,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.39,
|
| 48 |
+
"learning_rate": 1.6091568955890565e-05,
|
| 49 |
+
"loss": 2.3983,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.45,
|
| 54 |
+
"learning_rate": 1.553322166387493e-05,
|
| 55 |
+
"loss": 2.3347,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.5,
|
| 60 |
+
"learning_rate": 1.4974874371859299e-05,
|
| 61 |
+
"loss": 2.2982,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.56,
|
| 66 |
+
"learning_rate": 1.4416527079843662e-05,
|
| 67 |
+
"loss": 2.2627,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.61,
|
| 72 |
+
"learning_rate": 1.385817978782803e-05,
|
| 73 |
+
"loss": 2.2366,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.67,
|
| 78 |
+
"learning_rate": 1.3299832495812398e-05,
|
| 79 |
+
"loss": 2.1983,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.73,
|
| 84 |
+
"learning_rate": 1.2741485203796761e-05,
|
| 85 |
+
"loss": 2.1904,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.78,
|
| 90 |
+
"learning_rate": 1.2183137911781128e-05,
|
| 91 |
+
"loss": 2.1333,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.84,
|
| 96 |
+
"learning_rate": 1.1624790619765495e-05,
|
| 97 |
+
"loss": 2.1207,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.89,
|
| 102 |
+
"learning_rate": 1.106644332774986e-05,
|
| 103 |
+
"loss": 2.1035,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.95,
|
| 108 |
+
"learning_rate": 1.0508096035734227e-05,
|
| 109 |
+
"loss": 2.0814,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 1.0,
|
| 114 |
+
"eval_loss": 1.9788250923156738,
|
| 115 |
+
"eval_runtime": 99.7037,
|
| 116 |
+
"eval_samples_per_second": 302.537,
|
| 117 |
+
"eval_steps_per_second": 4.734,
|
| 118 |
+
"step": 8955
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 1.01,
|
| 122 |
+
"learning_rate": 9.949748743718594e-06,
|
| 123 |
+
"loss": 2.0605,
|
| 124 |
+
"step": 9000
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 1.06,
|
| 128 |
+
"learning_rate": 9.39140145170296e-06,
|
| 129 |
+
"loss": 2.0316,
|
| 130 |
+
"step": 9500
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 1.12,
|
| 134 |
+
"learning_rate": 8.833054159687326e-06,
|
| 135 |
+
"loss": 2.0237,
|
| 136 |
+
"step": 10000
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 1.17,
|
| 140 |
+
"learning_rate": 8.274706867671693e-06,
|
| 141 |
+
"loss": 2.0168,
|
| 142 |
+
"step": 10500
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 1.23,
|
| 146 |
+
"learning_rate": 7.716359575656058e-06,
|
| 147 |
+
"loss": 1.9817,
|
| 148 |
+
"step": 11000
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 1.28,
|
| 152 |
+
"learning_rate": 7.158012283640425e-06,
|
| 153 |
+
"loss": 1.9987,
|
| 154 |
+
"step": 11500
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 1.34,
|
| 158 |
+
"learning_rate": 6.599664991624791e-06,
|
| 159 |
+
"loss": 1.9769,
|
| 160 |
+
"step": 12000
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 1.4,
|
| 164 |
+
"learning_rate": 6.041317699609157e-06,
|
| 165 |
+
"loss": 1.9657,
|
| 166 |
+
"step": 12500
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 1.45,
|
| 170 |
+
"learning_rate": 5.482970407593524e-06,
|
| 171 |
+
"loss": 1.9676,
|
| 172 |
+
"step": 13000
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 1.51,
|
| 176 |
+
"learning_rate": 4.92462311557789e-06,
|
| 177 |
+
"loss": 1.9505,
|
| 178 |
+
"step": 13500
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 1.56,
|
| 182 |
+
"learning_rate": 4.366275823562256e-06,
|
| 183 |
+
"loss": 1.9629,
|
| 184 |
+
"step": 14000
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 1.62,
|
| 188 |
+
"learning_rate": 3.8079285315466224e-06,
|
| 189 |
+
"loss": 1.9709,
|
| 190 |
+
"step": 14500
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 1.68,
|
| 194 |
+
"learning_rate": 3.2495812395309884e-06,
|
| 195 |
+
"loss": 1.9377,
|
| 196 |
+
"step": 15000
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 1.73,
|
| 200 |
+
"learning_rate": 2.691233947515355e-06,
|
| 201 |
+
"loss": 1.9388,
|
| 202 |
+
"step": 15500
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 1.79,
|
| 206 |
+
"learning_rate": 2.132886655499721e-06,
|
| 207 |
+
"loss": 1.9248,
|
| 208 |
+
"step": 16000
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 1.84,
|
| 212 |
+
"learning_rate": 1.5745393634840873e-06,
|
| 213 |
+
"loss": 1.9169,
|
| 214 |
+
"step": 16500
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 1.9,
|
| 218 |
+
"learning_rate": 1.0161920714684535e-06,
|
| 219 |
+
"loss": 1.9248,
|
| 220 |
+
"step": 17000
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 1.95,
|
| 224 |
+
"learning_rate": 4.5784477945281974e-07,
|
| 225 |
+
"loss": 1.9237,
|
| 226 |
+
"step": 17500
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 2.0,
|
| 230 |
+
"eval_loss": 1.8554816246032715,
|
| 231 |
+
"eval_runtime": 89.1269,
|
| 232 |
+
"eval_samples_per_second": 338.439,
|
| 233 |
+
"eval_steps_per_second": 5.296,
|
| 234 |
+
"step": 17910
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 2.0,
|
| 238 |
+
"step": 17910,
|
| 239 |
+
"total_flos": 3.772502476406784e+16,
|
| 240 |
+
"train_loss": 2.197303864837425,
|
| 241 |
+
"train_runtime": 7444.9411,
|
| 242 |
+
"train_samples_per_second": 153.96,
|
| 243 |
+
"train_steps_per_second": 2.406
|
| 244 |
+
}
|
| 245 |
+
],
|
| 246 |
+
"max_steps": 17910,
|
| 247 |
+
"num_train_epochs": 2,
|
| 248 |
+
"total_flos": 3.772502476406784e+16,
|
| 249 |
+
"trial_name": null,
|
| 250 |
+
"trial_params": null
|
| 251 |
+
}
|