End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 18.0,
|
| 3 |
+
"eval_loss": 2.1134729385375977,
|
| 4 |
+
"eval_runtime": 45.3751,
|
| 5 |
+
"eval_samples": 2933,
|
| 6 |
+
"eval_samples_per_second": 64.639,
|
| 7 |
+
"eval_steps_per_second": 8.088,
|
| 8 |
+
"perplexity": 8.276936719550324,
|
| 9 |
+
"train_loss": 1.8265393278187887,
|
| 10 |
+
"train_runtime": 59534.5244,
|
| 11 |
+
"train_samples": 55736,
|
| 12 |
+
"train_samples_per_second": 16.852,
|
| 13 |
+
"train_steps_per_second": 0.263
|
| 14 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 18.0,
|
| 3 |
+
"eval_loss": 2.1134729385375977,
|
| 4 |
+
"eval_runtime": 45.3751,
|
| 5 |
+
"eval_samples": 2933,
|
| 6 |
+
"eval_samples_per_second": 64.639,
|
| 7 |
+
"eval_steps_per_second": 8.088,
|
| 8 |
+
"perplexity": 8.276936719550324
|
| 9 |
+
}
|
runs/Dec10_13-09-29_jbuhmann/events.out.tfevents.1639141792.jbuhmann.21311.0
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:cd70f0e097868fe56c01e3310b167870ad7bf9c22374a842111ca5cbf72f8354
|
| 3 |
+
size 13276
|
runs/Dec10_13-09-29_jbuhmann/events.out.tfevents.1639201373.jbuhmann.21311.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d0ce66d9e5b712678c79f3c5e878c5e20fd5a8bf3f0a2e48b96468e6e0a59662
|
| 3 |
+
size 311
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 18.0,
|
| 3 |
+
"train_loss": 1.8265393278187887,
|
| 4 |
+
"train_runtime": 59534.5244,
|
| 5 |
+
"train_samples": 55736,
|
| 6 |
+
"train_samples_per_second": 16.852,
|
| 7 |
+
"train_steps_per_second": 0.263
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,355 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 18.0,
|
| 5 |
+
"global_step": 15678,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.57,
|
| 12 |
+
"learning_rate": 9.68108177063401e-05,
|
| 13 |
+
"loss": 2.3589,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.0,
|
| 18 |
+
"eval_loss": 2.2804882526397705,
|
| 19 |
+
"eval_runtime": 46.5333,
|
| 20 |
+
"eval_samples_per_second": 63.03,
|
| 21 |
+
"eval_steps_per_second": 7.887,
|
| 22 |
+
"step": 871
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 1.15,
|
| 26 |
+
"learning_rate": 9.36216354126802e-05,
|
| 27 |
+
"loss": 2.3359,
|
| 28 |
+
"step": 1000
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 1.72,
|
| 32 |
+
"learning_rate": 9.043245311902028e-05,
|
| 33 |
+
"loss": 2.2563,
|
| 34 |
+
"step": 1500
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 2.0,
|
| 38 |
+
"eval_loss": 2.2500908374786377,
|
| 39 |
+
"eval_runtime": 46.4819,
|
| 40 |
+
"eval_samples_per_second": 63.1,
|
| 41 |
+
"eval_steps_per_second": 7.896,
|
| 42 |
+
"step": 1742
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 2.3,
|
| 46 |
+
"learning_rate": 8.724327082536038e-05,
|
| 47 |
+
"loss": 2.2043,
|
| 48 |
+
"step": 2000
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 2.87,
|
| 52 |
+
"learning_rate": 8.405408853170048e-05,
|
| 53 |
+
"loss": 2.1936,
|
| 54 |
+
"step": 2500
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 3.0,
|
| 58 |
+
"eval_loss": 2.2418746948242188,
|
| 59 |
+
"eval_runtime": 46.4009,
|
| 60 |
+
"eval_samples_per_second": 63.21,
|
| 61 |
+
"eval_steps_per_second": 7.909,
|
| 62 |
+
"step": 2613
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 3.44,
|
| 66 |
+
"learning_rate": 8.086490623804057e-05,
|
| 67 |
+
"loss": 2.11,
|
| 68 |
+
"step": 3000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 4.0,
|
| 72 |
+
"eval_loss": 2.230112314224243,
|
| 73 |
+
"eval_runtime": 46.3837,
|
| 74 |
+
"eval_samples_per_second": 63.233,
|
| 75 |
+
"eval_steps_per_second": 7.912,
|
| 76 |
+
"step": 3484
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 4.02,
|
| 80 |
+
"learning_rate": 7.767572394438066e-05,
|
| 81 |
+
"loss": 2.1018,
|
| 82 |
+
"step": 3500
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 4.59,
|
| 86 |
+
"learning_rate": 7.448654165072075e-05,
|
| 87 |
+
"loss": 2.0311,
|
| 88 |
+
"step": 4000
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 5.0,
|
| 92 |
+
"eval_loss": 2.231987476348877,
|
| 93 |
+
"eval_runtime": 46.4154,
|
| 94 |
+
"eval_samples_per_second": 63.19,
|
| 95 |
+
"eval_steps_per_second": 7.907,
|
| 96 |
+
"step": 4355
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 5.17,
|
| 100 |
+
"learning_rate": 7.129735935706085e-05,
|
| 101 |
+
"loss": 2.0174,
|
| 102 |
+
"step": 4500
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 5.74,
|
| 106 |
+
"learning_rate": 6.810817706340095e-05,
|
| 107 |
+
"loss": 1.969,
|
| 108 |
+
"step": 5000
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 6.0,
|
| 112 |
+
"eval_loss": 2.227581262588501,
|
| 113 |
+
"eval_runtime": 46.0273,
|
| 114 |
+
"eval_samples_per_second": 63.723,
|
| 115 |
+
"eval_steps_per_second": 7.974,
|
| 116 |
+
"step": 5226
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 6.31,
|
| 120 |
+
"learning_rate": 6.491899476974103e-05,
|
| 121 |
+
"loss": 1.9427,
|
| 122 |
+
"step": 5500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 6.89,
|
| 126 |
+
"learning_rate": 6.172981247608114e-05,
|
| 127 |
+
"loss": 1.9148,
|
| 128 |
+
"step": 6000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 7.0,
|
| 132 |
+
"eval_loss": 2.1621322631835938,
|
| 133 |
+
"eval_runtime": 45.9847,
|
| 134 |
+
"eval_samples_per_second": 63.782,
|
| 135 |
+
"eval_steps_per_second": 7.981,
|
| 136 |
+
"step": 6097
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 7.46,
|
| 140 |
+
"learning_rate": 5.854063018242123e-05,
|
| 141 |
+
"loss": 1.8569,
|
| 142 |
+
"step": 6500
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 8.0,
|
| 146 |
+
"eval_loss": 2.1876232624053955,
|
| 147 |
+
"eval_runtime": 45.9436,
|
| 148 |
+
"eval_samples_per_second": 63.839,
|
| 149 |
+
"eval_steps_per_second": 7.988,
|
| 150 |
+
"step": 6968
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 8.04,
|
| 154 |
+
"learning_rate": 5.535144788876132e-05,
|
| 155 |
+
"loss": 1.8523,
|
| 156 |
+
"step": 7000
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 8.61,
|
| 160 |
+
"learning_rate": 5.216226559510142e-05,
|
| 161 |
+
"loss": 1.7978,
|
| 162 |
+
"step": 7500
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 9.0,
|
| 166 |
+
"eval_loss": 2.201099395751953,
|
| 167 |
+
"eval_runtime": 45.9305,
|
| 168 |
+
"eval_samples_per_second": 63.857,
|
| 169 |
+
"eval_steps_per_second": 7.99,
|
| 170 |
+
"step": 7839
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 9.18,
|
| 174 |
+
"learning_rate": 4.897308330144152e-05,
|
| 175 |
+
"loss": 1.7922,
|
| 176 |
+
"step": 8000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 9.76,
|
| 180 |
+
"learning_rate": 4.578390100778161e-05,
|
| 181 |
+
"loss": 1.7602,
|
| 182 |
+
"step": 8500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 10.0,
|
| 186 |
+
"eval_loss": 2.1279566287994385,
|
| 187 |
+
"eval_runtime": 45.9065,
|
| 188 |
+
"eval_samples_per_second": 63.891,
|
| 189 |
+
"eval_steps_per_second": 7.995,
|
| 190 |
+
"step": 8710
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 10.33,
|
| 194 |
+
"learning_rate": 4.2594718714121704e-05,
|
| 195 |
+
"loss": 1.7371,
|
| 196 |
+
"step": 9000
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 10.91,
|
| 200 |
+
"learning_rate": 3.9405536420461794e-05,
|
| 201 |
+
"loss": 1.7166,
|
| 202 |
+
"step": 9500
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 11.0,
|
| 206 |
+
"eval_loss": 2.1643788814544678,
|
| 207 |
+
"eval_runtime": 45.9375,
|
| 208 |
+
"eval_samples_per_second": 63.848,
|
| 209 |
+
"eval_steps_per_second": 7.989,
|
| 210 |
+
"step": 9581
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 11.48,
|
| 214 |
+
"learning_rate": 3.621635412680189e-05,
|
| 215 |
+
"loss": 1.6651,
|
| 216 |
+
"step": 10000
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 12.0,
|
| 220 |
+
"eval_loss": 2.1245827674865723,
|
| 221 |
+
"eval_runtime": 45.9431,
|
| 222 |
+
"eval_samples_per_second": 63.84,
|
| 223 |
+
"eval_steps_per_second": 7.988,
|
| 224 |
+
"step": 10452
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 12.06,
|
| 228 |
+
"learning_rate": 3.302717183314198e-05,
|
| 229 |
+
"loss": 1.6508,
|
| 230 |
+
"step": 10500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 12.63,
|
| 234 |
+
"learning_rate": 2.9837989539482082e-05,
|
| 235 |
+
"loss": 1.6141,
|
| 236 |
+
"step": 11000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 13.0,
|
| 240 |
+
"eval_loss": 2.126392126083374,
|
| 241 |
+
"eval_runtime": 45.9202,
|
| 242 |
+
"eval_samples_per_second": 63.872,
|
| 243 |
+
"eval_steps_per_second": 7.992,
|
| 244 |
+
"step": 11323
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 13.2,
|
| 248 |
+
"learning_rate": 2.6648807245822172e-05,
|
| 249 |
+
"loss": 1.6312,
|
| 250 |
+
"step": 11500
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 13.78,
|
| 254 |
+
"learning_rate": 2.345962495216227e-05,
|
| 255 |
+
"loss": 1.5759,
|
| 256 |
+
"step": 12000
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 14.0,
|
| 260 |
+
"eval_loss": 2.114293098449707,
|
| 261 |
+
"eval_runtime": 45.9021,
|
| 262 |
+
"eval_samples_per_second": 63.897,
|
| 263 |
+
"eval_steps_per_second": 7.995,
|
| 264 |
+
"step": 12194
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 14.35,
|
| 268 |
+
"learning_rate": 2.0270442658502363e-05,
|
| 269 |
+
"loss": 1.572,
|
| 270 |
+
"step": 12500
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 14.93,
|
| 274 |
+
"learning_rate": 1.7081260364842456e-05,
|
| 275 |
+
"loss": 1.5478,
|
| 276 |
+
"step": 13000
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 15.0,
|
| 280 |
+
"eval_loss": 2.098154306411743,
|
| 281 |
+
"eval_runtime": 45.9315,
|
| 282 |
+
"eval_samples_per_second": 63.856,
|
| 283 |
+
"eval_steps_per_second": 7.99,
|
| 284 |
+
"step": 13065
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 15.5,
|
| 288 |
+
"learning_rate": 1.3892078071182548e-05,
|
| 289 |
+
"loss": 1.5311,
|
| 290 |
+
"step": 13500
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 16.0,
|
| 294 |
+
"eval_loss": 2.099287509918213,
|
| 295 |
+
"eval_runtime": 45.9245,
|
| 296 |
+
"eval_samples_per_second": 63.866,
|
| 297 |
+
"eval_steps_per_second": 7.991,
|
| 298 |
+
"step": 13936
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 16.07,
|
| 302 |
+
"learning_rate": 1.0702895777522644e-05,
|
| 303 |
+
"loss": 1.5187,
|
| 304 |
+
"step": 14000
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 16.65,
|
| 308 |
+
"learning_rate": 7.513713483862737e-06,
|
| 309 |
+
"loss": 1.5187,
|
| 310 |
+
"step": 14500
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 17.0,
|
| 314 |
+
"eval_loss": 2.0979349613189697,
|
| 315 |
+
"eval_runtime": 45.9022,
|
| 316 |
+
"eval_samples_per_second": 63.897,
|
| 317 |
+
"eval_steps_per_second": 7.995,
|
| 318 |
+
"step": 14807
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 17.22,
|
| 322 |
+
"learning_rate": 4.324531190202833e-06,
|
| 323 |
+
"loss": 1.4819,
|
| 324 |
+
"step": 15000
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 17.8,
|
| 328 |
+
"learning_rate": 1.1353488965429266e-06,
|
| 329 |
+
"loss": 1.4809,
|
| 330 |
+
"step": 15500
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 18.0,
|
| 334 |
+
"eval_loss": 2.0337767601013184,
|
| 335 |
+
"eval_runtime": 45.9061,
|
| 336 |
+
"eval_samples_per_second": 63.891,
|
| 337 |
+
"eval_steps_per_second": 7.995,
|
| 338 |
+
"step": 15678
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 18.0,
|
| 342 |
+
"step": 15678,
|
| 343 |
+
"total_flos": 2.6405831822391706e+17,
|
| 344 |
+
"train_loss": 1.8265393278187887,
|
| 345 |
+
"train_runtime": 59534.5244,
|
| 346 |
+
"train_samples_per_second": 16.852,
|
| 347 |
+
"train_steps_per_second": 0.263
|
| 348 |
+
}
|
| 349 |
+
],
|
| 350 |
+
"max_steps": 15678,
|
| 351 |
+
"num_train_epochs": 18,
|
| 352 |
+
"total_flos": 2.6405831822391706e+17,
|
| 353 |
+
"trial_name": null,
|
| 354 |
+
"trial_params": null
|
| 355 |
+
}
|