| { | |
| "best_metric": 0.5395539646127814, | |
| "best_model_checkpoint": "./runtime-text-classification/xtremedistil-l12-h384-uncased-CoLA/checkpoint-268", | |
| "epoch": 16.0, | |
| "global_step": 1072, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 9.090909090909091e-06, | |
| "loss": 0.6853, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.8181818181818182e-05, | |
| "loss": 0.6765, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 2.7272727272727273e-05, | |
| "loss": 0.6581, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 3.6363636363636364e-05, | |
| "loss": 0.6444, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 4.545454545454546e-05, | |
| "loss": 0.6218, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 5.4545454545454546e-05, | |
| "loss": 0.6467, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 6.363636363636364e-05, | |
| "loss": 0.594, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 7.272727272727273e-05, | |
| "loss": 0.6193, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 8.181818181818183e-05, | |
| "loss": 0.6009, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 9.090909090909092e-05, | |
| "loss": 0.5942, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.0001, | |
| "loss": 0.5839, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 9.999794293416862e-05, | |
| "loss": 0.5991, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 9.999177190593525e-05, | |
| "loss": 0.5808, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 9.998148742306837e-05, | |
| "loss": 0.5599, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 9.996709033180229e-05, | |
| "loss": 0.5859, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 9.99485818167676e-05, | |
| "loss": 0.5573, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 9.992596340089365e-05, | |
| "loss": 0.5645, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 9.989923694528327e-05, | |
| "loss": 0.513, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 9.986840464905958e-05, | |
| "loss": 0.5347, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 9.983346904918513e-05, | |
| "loss": 0.5333, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 9.979443302025305e-05, | |
| "loss": 0.5549, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 9.975129977425062e-05, | |
| "loss": 0.4822, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.5893396139144897, | |
| "eval_matthews_correlation": 0.26208039166807634, | |
| "eval_runtime": 1.0615, | |
| "eval_samples_per_second": 982.602, | |
| "eval_steps_per_second": 62.178, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 9.970407286029487e-05, | |
| "loss": 0.4866, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 9.965275616434067e-05, | |
| "loss": 0.4771, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 9.959735390886086e-05, | |
| "loss": 0.506, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 9.953787065249896e-05, | |
| "loss": 0.5117, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 9.947431128969387e-05, | |
| "loss": 0.4754, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 9.940668105027739e-05, | |
| "loss": 0.5221, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 9.933498549904368e-05, | |
| "loss": 0.4806, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 9.925923053529147e-05, | |
| "loss": 0.4426, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 9.917942239233871e-05, | |
| "loss": 0.5009, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 9.909556763700951e-05, | |
| "loss": 0.4601, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 9.900767316909396e-05, | |
| "loss": 0.4366, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 9.891574622078034e-05, | |
| "loss": 0.4403, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 9.881979435606003e-05, | |
| "loss": 0.3992, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 9.871982547010513e-05, | |
| "loss": 0.464, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 9.861584778861878e-05, | |
| "loss": 0.4349, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 9.850786986715846e-05, | |
| "loss": 0.4249, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 9.839590059043184e-05, | |
| "loss": 0.4344, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 9.827994917156587e-05, | |
| "loss": 0.4342, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 9.816002515134865e-05, | |
| "loss": 0.4304, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 9.80361383974443e-05, | |
| "loss": 0.4584, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 9.790829910358122e-05, | |
| "loss": 0.4151, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 9.777651778871309e-05, | |
| "loss": 0.4669, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.5811270475387573, | |
| "eval_matthews_correlation": 0.3721681506432673, | |
| "eval_runtime": 1.0734, | |
| "eval_samples_per_second": 971.718, | |
| "eval_steps_per_second": 61.489, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 9.764080529615351e-05, | |
| "loss": 0.4085, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 9.750117279268378e-05, | |
| "loss": 0.3755, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 9.735763176763394e-05, | |
| "loss": 0.3877, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 9.721019403193753e-05, | |
| "loss": 0.3769, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 9.705887171715966e-05, | |
| "loss": 0.3468, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 9.690367727449888e-05, | |
| "loss": 0.3736, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 9.674462347376259e-05, | |
| "loss": 0.3744, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 9.658172340231635e-05, | |
| "loss": 0.3203, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 9.6414990464007e-05, | |
| "loss": 0.3398, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 9.624443837805972e-05, | |
| "loss": 0.3255, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 9.607008117794928e-05, | |
| "loss": 0.349, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 9.589193321024524e-05, | |
| "loss": 0.4708, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 9.571000913343148e-05, | |
| "loss": 0.3565, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 9.552432391670009e-05, | |
| "loss": 0.3502, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 9.533489283871966e-05, | |
| "loss": 0.3605, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 9.51417314863781e-05, | |
| "loss": 0.4047, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 9.494485575350014e-05, | |
| "loss": 0.3681, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 9.474428183953951e-05, | |
| "loss": 0.4035, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 9.454002624824598e-05, | |
| "loss": 0.3704, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 9.433210578630749e-05, | |
| "loss": 0.3648, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 9.412053756196715e-05, | |
| "loss": 0.3498, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 9.390533898361555e-05, | |
| "loss": 0.3759, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 9.368652775835843e-05, | |
| "loss": 0.3077, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.615044891834259, | |
| "eval_matthews_correlation": 0.4382589402952836, | |
| "eval_runtime": 1.0332, | |
| "eval_samples_per_second": 1009.479, | |
| "eval_steps_per_second": 63.879, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 9.346412189055955e-05, | |
| "loss": 0.2746, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 9.323813968035936e-05, | |
| "loss": 0.242, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 9.300859972216924e-05, | |
| "loss": 0.2428, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 9.277552090314135e-05, | |
| "loss": 0.337, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 9.253892240161466e-05, | |
| "loss": 0.2882, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "learning_rate": 9.229882368553692e-05, | |
| "loss": 0.2743, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 9.205524451086274e-05, | |
| "loss": 0.2693, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 9.180820491992799e-05, | |
| "loss": 0.2557, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 9.155772523980075e-05, | |
| "loss": 0.296, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 9.130382608060868e-05, | |
| "loss": 0.2739, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "learning_rate": 9.104652833384317e-05, | |
| "loss": 0.2848, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "learning_rate": 9.078585317064036e-05, | |
| "loss": 0.2613, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 9.052182204003909e-05, | |
| "loss": 0.2775, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 3.63, | |
| "learning_rate": 9.025445666721608e-05, | |
| "loss": 0.2558, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 8.998377905169822e-05, | |
| "loss": 0.3344, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "learning_rate": 8.970981146555247e-05, | |
| "loss": 0.3003, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "learning_rate": 8.943257645155327e-05, | |
| "loss": 0.2598, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 8.91520968213276e-05, | |
| "loss": 0.2584, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "learning_rate": 8.886839565347797e-05, | |
| "loss": 0.2581, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "learning_rate": 8.858149629168357e-05, | |
| "loss": 0.3605, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "learning_rate": 8.829142234277936e-05, | |
| "loss": 0.3091, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "learning_rate": 8.79981976748137e-05, | |
| "loss": 0.2594, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.49737870693206787, | |
| "eval_matthews_correlation": 0.5395539646127814, | |
| "eval_runtime": 1.0788, | |
| "eval_samples_per_second": 966.811, | |
| "eval_steps_per_second": 61.179, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 8.770184641508439e-05, | |
| "loss": 0.2586, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "learning_rate": 8.740239294815345e-05, | |
| "loss": 0.2208, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "learning_rate": 8.70998619138407e-05, | |
| "loss": 0.1708, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "learning_rate": 8.679427820519625e-05, | |
| "loss": 0.2191, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "learning_rate": 8.648566696645233e-05, | |
| "loss": 0.2213, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 4.25, | |
| "learning_rate": 8.617405359095437e-05, | |
| "loss": 0.2575, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 4.3, | |
| "learning_rate": 8.585946371907138e-05, | |
| "loss": 0.2006, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 4.34, | |
| "learning_rate": 8.55419232360865e-05, | |
| "loss": 0.2023, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 4.39, | |
| "learning_rate": 8.522145827006675e-05, | |
| "loss": 0.1837, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 4.43, | |
| "learning_rate": 8.489809518971348e-05, | |
| "loss": 0.2486, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "learning_rate": 8.457186060219239e-05, | |
| "loss": 0.2044, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.52, | |
| "learning_rate": 8.42427813509444e-05, | |
| "loss": 0.1813, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "learning_rate": 8.391088451347688e-05, | |
| "loss": 0.2795, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 4.61, | |
| "learning_rate": 8.357619739913557e-05, | |
| "loss": 0.1769, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 4.66, | |
| "learning_rate": 8.323874754685755e-05, | |
| "loss": 0.1875, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 4.7, | |
| "learning_rate": 8.289856272290527e-05, | |
| "loss": 0.2291, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "learning_rate": 8.255567091858182e-05, | |
| "loss": 0.2097, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 4.79, | |
| "learning_rate": 8.22101003479278e-05, | |
| "loss": 0.2009, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 4.84, | |
| "learning_rate": 8.186187944539973e-05, | |
| "loss": 0.2932, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 4.88, | |
| "learning_rate": 8.151103686353042e-05, | |
| "loss": 0.2447, | |
| "step": 327 | |
| }, | |
| { | |
| "epoch": 4.93, | |
| "learning_rate": 8.115760147057138e-05, | |
| "loss": 0.202, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 4.97, | |
| "learning_rate": 8.080160234811742e-05, | |
| "loss": 0.21, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.5594205856323242, | |
| "eval_matthews_correlation": 0.5181917740456299, | |
| "eval_runtime": 1.065, | |
| "eval_samples_per_second": 979.357, | |
| "eval_steps_per_second": 61.973, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 8.044306878871375e-05, | |
| "loss": 0.2023, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 5.06, | |
| "learning_rate": 8.00820302934458e-05, | |
| "loss": 0.1664, | |
| "step": 339 | |
| }, | |
| { | |
| "epoch": 5.1, | |
| "learning_rate": 7.971851656951161e-05, | |
| "loss": 0.2118, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 5.15, | |
| "learning_rate": 7.935255752777764e-05, | |
| "loss": 0.1459, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 5.19, | |
| "learning_rate": 7.898418328031752e-05, | |
| "loss": 0.1239, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 5.24, | |
| "learning_rate": 7.861342413793433e-05, | |
| "loss": 0.2143, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 5.28, | |
| "learning_rate": 7.824031060766662e-05, | |
| "loss": 0.1456, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 5.33, | |
| "learning_rate": 7.786487339027815e-05, | |
| "loss": 0.1705, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 5.37, | |
| "learning_rate": 7.748714337773179e-05, | |
| "loss": 0.1135, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 5.42, | |
| "learning_rate": 7.710715165064765e-05, | |
| "loss": 0.2111, | |
| "step": 363 | |
| }, | |
| { | |
| "epoch": 5.46, | |
| "learning_rate": 7.672492947574566e-05, | |
| "loss": 0.2572, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 5.51, | |
| "learning_rate": 7.634050830327282e-05, | |
| "loss": 0.2522, | |
| "step": 369 | |
| }, | |
| { | |
| "epoch": 5.55, | |
| "learning_rate": 7.59539197644155e-05, | |
| "loss": 0.1322, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 5.6, | |
| "learning_rate": 7.556519566869666e-05, | |
| "loss": 0.224, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 5.64, | |
| "learning_rate": 7.517436800135853e-05, | |
| "loss": 0.1831, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 5.69, | |
| "learning_rate": 7.47814689207307e-05, | |
| "loss": 0.1731, | |
| "step": 381 | |
| }, | |
| { | |
| "epoch": 5.73, | |
| "learning_rate": 7.438653075558412e-05, | |
| "loss": 0.2192, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 5.78, | |
| "learning_rate": 7.398958600247103e-05, | |
| "loss": 0.1522, | |
| "step": 387 | |
| }, | |
| { | |
| "epoch": 5.82, | |
| "learning_rate": 7.359066732305095e-05, | |
| "loss": 0.2241, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 5.87, | |
| "learning_rate": 7.318980754140326e-05, | |
| "loss": 0.2172, | |
| "step": 393 | |
| }, | |
| { | |
| "epoch": 5.91, | |
| "learning_rate": 7.278703964132639e-05, | |
| "loss": 0.1706, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 5.96, | |
| "learning_rate": 7.238239676362372e-05, | |
| "loss": 0.1813, | |
| "step": 399 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 7.197591220337679e-05, | |
| "loss": 0.1526, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.5715296268463135, | |
| "eval_matthews_correlation": 0.5149844966342378, | |
| "eval_runtime": 1.0444, | |
| "eval_samples_per_second": 998.702, | |
| "eval_steps_per_second": 63.197, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 6.04, | |
| "learning_rate": 7.156761940720555e-05, | |
| "loss": 0.1491, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 6.09, | |
| "learning_rate": 7.115755197051645e-05, | |
| "loss": 0.1685, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 6.13, | |
| "learning_rate": 7.074574363473798e-05, | |
| "loss": 0.1871, | |
| "step": 411 | |
| }, | |
| { | |
| "epoch": 6.18, | |
| "learning_rate": 7.033222828454442e-05, | |
| "loss": 0.1312, | |
| "step": 414 | |
| }, | |
| { | |
| "epoch": 6.22, | |
| "learning_rate": 6.991703994506761e-05, | |
| "loss": 0.1746, | |
| "step": 417 | |
| }, | |
| { | |
| "epoch": 6.27, | |
| "learning_rate": 6.950021277909749e-05, | |
| "loss": 0.1484, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 6.31, | |
| "learning_rate": 6.908178108427088e-05, | |
| "loss": 0.1476, | |
| "step": 423 | |
| }, | |
| { | |
| "epoch": 6.36, | |
| "learning_rate": 6.866177929024945e-05, | |
| "loss": 0.1404, | |
| "step": 426 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 6.824024195588677e-05, | |
| "loss": 0.1335, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 6.45, | |
| "learning_rate": 6.781720376638477e-05, | |
| "loss": 0.1782, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 6.49, | |
| "learning_rate": 6.739269953043959e-05, | |
| "loss": 0.1941, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 6.54, | |
| "learning_rate": 6.696676417737764e-05, | |
| "loss": 0.1558, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 6.58, | |
| "learning_rate": 6.653943275428135e-05, | |
| "loss": 0.1311, | |
| "step": 441 | |
| }, | |
| { | |
| "epoch": 6.63, | |
| "learning_rate": 6.611074042310549e-05, | |
| "loss": 0.128, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "learning_rate": 6.568072245778394e-05, | |
| "loss": 0.1374, | |
| "step": 447 | |
| }, | |
| { | |
| "epoch": 6.72, | |
| "learning_rate": 6.524941424132719e-05, | |
| "loss": 0.1491, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 6.76, | |
| "learning_rate": 6.481685126291106e-05, | |
| "loss": 0.1242, | |
| "step": 453 | |
| }, | |
| { | |
| "epoch": 6.81, | |
| "learning_rate": 6.438306911495648e-05, | |
| "loss": 0.1379, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 6.85, | |
| "learning_rate": 6.394810349020083e-05, | |
| "loss": 0.168, | |
| "step": 459 | |
| }, | |
| { | |
| "epoch": 6.9, | |
| "learning_rate": 6.351199017876106e-05, | |
| "loss": 0.1601, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 6.94, | |
| "learning_rate": 6.30747650651889e-05, | |
| "loss": 0.1641, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "learning_rate": 6.263646412551794e-05, | |
| "loss": 0.1775, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 0.6637021899223328, | |
| "eval_matthews_correlation": 0.5019828461798207, | |
| "eval_runtime": 1.1986, | |
| "eval_samples_per_second": 870.206, | |
| "eval_steps_per_second": 55.066, | |
| "step": 469 | |
| }, | |
| { | |
| "epoch": 7.03, | |
| "learning_rate": 6.219712342430371e-05, | |
| "loss": 0.1263, | |
| "step": 471 | |
| }, | |
| { | |
| "epoch": 7.07, | |
| "learning_rate": 6.175677911165599e-05, | |
| "loss": 0.114, | |
| "step": 474 | |
| }, | |
| { | |
| "epoch": 7.12, | |
| "learning_rate": 6.131546742026438e-05, | |
| "loss": 0.0823, | |
| "step": 477 | |
| }, | |
| { | |
| "epoch": 7.16, | |
| "learning_rate": 6.0873224662416896e-05, | |
| "loss": 0.1068, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 7.21, | |
| "learning_rate": 6.04300872270122e-05, | |
| "loss": 0.1067, | |
| "step": 483 | |
| }, | |
| { | |
| "epoch": 7.25, | |
| "learning_rate": 5.998609157656539e-05, | |
| "loss": 0.1026, | |
| "step": 486 | |
| }, | |
| { | |
| "epoch": 7.3, | |
| "learning_rate": 5.954127424420773e-05, | |
| "loss": 0.1208, | |
| "step": 489 | |
| }, | |
| { | |
| "epoch": 7.34, | |
| "learning_rate": 5.9095671830680656e-05, | |
| "loss": 0.0778, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 7.39, | |
| "learning_rate": 5.864932100132411e-05, | |
| "loss": 0.1066, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 7.43, | |
| "learning_rate": 5.82022584830597e-05, | |
| "loss": 0.1086, | |
| "step": 498 | |
| }, | |
| { | |
| "epoch": 7.48, | |
| "learning_rate": 5.7754521061368684e-05, | |
| "loss": 0.1833, | |
| "step": 501 | |
| }, | |
| { | |
| "epoch": 7.52, | |
| "learning_rate": 5.730614557726509e-05, | |
| "loss": 0.1193, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 7.57, | |
| "learning_rate": 5.685716892426445e-05, | |
| "loss": 0.1628, | |
| "step": 507 | |
| }, | |
| { | |
| "epoch": 7.61, | |
| "learning_rate": 5.640762804534806e-05, | |
| "loss": 0.1774, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 7.66, | |
| "learning_rate": 5.595755992992317e-05, | |
| "loss": 0.1434, | |
| "step": 513 | |
| }, | |
| { | |
| "epoch": 7.7, | |
| "learning_rate": 5.550700161077945e-05, | |
| "loss": 0.0957, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 7.75, | |
| "learning_rate": 5.505599016104187e-05, | |
| "loss": 0.1219, | |
| "step": 519 | |
| }, | |
| { | |
| "epoch": 7.79, | |
| "learning_rate": 5.460456269112013e-05, | |
| "loss": 0.1562, | |
| "step": 522 | |
| }, | |
| { | |
| "epoch": 7.84, | |
| "learning_rate": 5.415275634565517e-05, | |
| "loss": 0.136, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 7.88, | |
| "learning_rate": 5.370060830046282e-05, | |
| "loss": 0.0868, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 7.93, | |
| "learning_rate": 5.3248155759474846e-05, | |
| "loss": 0.1028, | |
| "step": 531 | |
| }, | |
| { | |
| "epoch": 7.97, | |
| "learning_rate": 5.2795435951677785e-05, | |
| "loss": 0.1681, | |
| "step": 534 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 0.6957959532737732, | |
| "eval_matthews_correlation": 0.5131045571647604, | |
| "eval_runtime": 1.0682, | |
| "eval_samples_per_second": 976.38, | |
| "eval_steps_per_second": 61.784, | |
| "step": 536 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 5.234248612804952e-05, | |
| "loss": 0.1163, | |
| "step": 537 | |
| }, | |
| { | |
| "epoch": 8.06, | |
| "learning_rate": 5.1889343558494266e-05, | |
| "loss": 0.1022, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 8.1, | |
| "learning_rate": 5.14360455287759e-05, | |
| "loss": 0.0854, | |
| "step": 543 | |
| }, | |
| { | |
| "epoch": 8.15, | |
| "learning_rate": 5.098262933744994e-05, | |
| "loss": 0.112, | |
| "step": 546 | |
| }, | |
| { | |
| "epoch": 8.19, | |
| "learning_rate": 5.052913229279459e-05, | |
| "loss": 0.1067, | |
| "step": 549 | |
| }, | |
| { | |
| "epoch": 8.24, | |
| "learning_rate": 5.007559170974084e-05, | |
| "loss": 0.083, | |
| "step": 552 | |
| }, | |
| { | |
| "epoch": 8.28, | |
| "learning_rate": 4.962204490680216e-05, | |
| "loss": 0.085, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 8.33, | |
| "learning_rate": 4.9168529203003814e-05, | |
| "loss": 0.1075, | |
| "step": 558 | |
| }, | |
| { | |
| "epoch": 8.37, | |
| "learning_rate": 4.871508191481211e-05, | |
| "loss": 0.1416, | |
| "step": 561 | |
| }, | |
| { | |
| "epoch": 8.42, | |
| "learning_rate": 4.826174035306398e-05, | |
| "loss": 0.1248, | |
| "step": 564 | |
| }, | |
| { | |
| "epoch": 8.46, | |
| "learning_rate": 4.7808541819896885e-05, | |
| "loss": 0.0748, | |
| "step": 567 | |
| }, | |
| { | |
| "epoch": 8.51, | |
| "learning_rate": 4.735552360567952e-05, | |
| "loss": 0.0707, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 8.55, | |
| "learning_rate": 4.6902722985943444e-05, | |
| "loss": 0.0778, | |
| "step": 573 | |
| }, | |
| { | |
| "epoch": 8.6, | |
| "learning_rate": 4.645017721831602e-05, | |
| "loss": 0.1447, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 8.64, | |
| "learning_rate": 4.599792353945466e-05, | |
| "loss": 0.0839, | |
| "step": 579 | |
| }, | |
| { | |
| "epoch": 8.69, | |
| "learning_rate": 4.5545999161982953e-05, | |
| "loss": 0.1268, | |
| "step": 582 | |
| }, | |
| { | |
| "epoch": 8.73, | |
| "learning_rate": 4.509444127142871e-05, | |
| "loss": 0.0705, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 8.78, | |
| "learning_rate": 4.464328702316427e-05, | |
| "loss": 0.1196, | |
| "step": 588 | |
| }, | |
| { | |
| "epoch": 8.82, | |
| "learning_rate": 4.419257353934915e-05, | |
| "loss": 0.1071, | |
| "step": 591 | |
| }, | |
| { | |
| "epoch": 8.87, | |
| "learning_rate": 4.374233790587565e-05, | |
| "loss": 0.1177, | |
| "step": 594 | |
| }, | |
| { | |
| "epoch": 8.91, | |
| "learning_rate": 4.329261716931727e-05, | |
| "loss": 0.104, | |
| "step": 597 | |
| }, | |
| { | |
| "epoch": 8.96, | |
| "learning_rate": 4.284344833388047e-05, | |
| "loss": 0.0596, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 4.2394868358359774e-05, | |
| "loss": 0.124, | |
| "step": 603 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 0.7057417631149292, | |
| "eval_matthews_correlation": 0.5153742778418894, | |
| "eval_runtime": 1.2043, | |
| "eval_samples_per_second": 866.095, | |
| "eval_steps_per_second": 54.806, | |
| "step": 603 | |
| }, | |
| { | |
| "epoch": 9.04, | |
| "learning_rate": 4.1946914153096795e-05, | |
| "loss": 0.0838, | |
| "step": 606 | |
| }, | |
| { | |
| "epoch": 9.09, | |
| "learning_rate": 4.149962257694315e-05, | |
| "loss": 0.0915, | |
| "step": 609 | |
| }, | |
| { | |
| "epoch": 9.13, | |
| "learning_rate": 4.105303043422753e-05, | |
| "loss": 0.0818, | |
| "step": 612 | |
| }, | |
| { | |
| "epoch": 9.18, | |
| "learning_rate": 4.060717447172743e-05, | |
| "loss": 0.0508, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 9.22, | |
| "learning_rate": 4.0162091375645493e-05, | |
| "loss": 0.1156, | |
| "step": 618 | |
| }, | |
| { | |
| "epoch": 9.27, | |
| "learning_rate": 3.971781776859093e-05, | |
| "loss": 0.0697, | |
| "step": 621 | |
| }, | |
| { | |
| "epoch": 9.31, | |
| "learning_rate": 3.9274390206565956e-05, | |
| "loss": 0.0563, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 9.36, | |
| "learning_rate": 3.883184517595807e-05, | |
| "loss": 0.0993, | |
| "step": 627 | |
| }, | |
| { | |
| "epoch": 9.4, | |
| "learning_rate": 3.83902190905377e-05, | |
| "loss": 0.0621, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 9.45, | |
| "learning_rate": 3.794954828846208e-05, | |
| "loss": 0.0788, | |
| "step": 633 | |
| }, | |
| { | |
| "epoch": 9.49, | |
| "learning_rate": 3.7509869029285215e-05, | |
| "loss": 0.1224, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 9.54, | |
| "learning_rate": 3.707121749097431e-05, | |
| "loss": 0.0759, | |
| "step": 639 | |
| }, | |
| { | |
| "epoch": 9.58, | |
| "learning_rate": 3.663362976693304e-05, | |
| "loss": 0.0925, | |
| "step": 642 | |
| }, | |
| { | |
| "epoch": 9.63, | |
| "learning_rate": 3.619714186303162e-05, | |
| "loss": 0.0908, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 9.67, | |
| "learning_rate": 3.576178969464414e-05, | |
| "loss": 0.12, | |
| "step": 648 | |
| }, | |
| { | |
| "epoch": 9.72, | |
| "learning_rate": 3.532760908369344e-05, | |
| "loss": 0.0629, | |
| "step": 651 | |
| }, | |
| { | |
| "epoch": 9.76, | |
| "learning_rate": 3.489463575570349e-05, | |
| "loss": 0.0506, | |
| "step": 654 | |
| }, | |
| { | |
| "epoch": 9.81, | |
| "learning_rate": 3.446290533685984e-05, | |
| "loss": 0.0738, | |
| "step": 657 | |
| }, | |
| { | |
| "epoch": 9.85, | |
| "learning_rate": 3.403245335107822e-05, | |
| "loss": 0.0586, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 9.9, | |
| "learning_rate": 3.360331521708149e-05, | |
| "loss": 0.106, | |
| "step": 663 | |
| }, | |
| { | |
| "epoch": 9.94, | |
| "learning_rate": 3.3175526245485366e-05, | |
| "loss": 0.111, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 9.99, | |
| "learning_rate": 3.274912163589291e-05, | |
| "loss": 0.1111, | |
| "step": 669 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 0.8173357844352722, | |
| "eval_matthews_correlation": 0.5074384885743003, | |
| "eval_runtime": 1.0523, | |
| "eval_samples_per_second": 991.19, | |
| "eval_steps_per_second": 62.722, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 10.03, | |
| "learning_rate": 3.2324136473998204e-05, | |
| "loss": 0.0763, | |
| "step": 672 | |
| }, | |
| { | |
| "epoch": 10.07, | |
| "learning_rate": 3.190060572869948e-05, | |
| "loss": 0.07, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 10.12, | |
| "learning_rate": 3.147856424922174e-05, | |
| "loss": 0.051, | |
| "step": 678 | |
| }, | |
| { | |
| "epoch": 10.16, | |
| "learning_rate": 3.1058046762249224e-05, | |
| "loss": 0.0454, | |
| "step": 681 | |
| }, | |
| { | |
| "epoch": 10.21, | |
| "learning_rate": 3.063908786906812e-05, | |
| "loss": 0.0952, | |
| "step": 684 | |
| }, | |
| { | |
| "epoch": 10.25, | |
| "learning_rate": 3.022172204271938e-05, | |
| "loss": 0.0582, | |
| "step": 687 | |
| }, | |
| { | |
| "epoch": 10.3, | |
| "learning_rate": 2.9805983625162227e-05, | |
| "loss": 0.0653, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 10.34, | |
| "learning_rate": 2.93919068244484e-05, | |
| "loss": 0.0617, | |
| "step": 693 | |
| }, | |
| { | |
| "epoch": 10.39, | |
| "learning_rate": 2.897952571190743e-05, | |
| "loss": 0.0648, | |
| "step": 696 | |
| }, | |
| { | |
| "epoch": 10.43, | |
| "learning_rate": 2.8568874219343155e-05, | |
| "loss": 0.0503, | |
| "step": 699 | |
| }, | |
| { | |
| "epoch": 10.48, | |
| "learning_rate": 2.8159986136241732e-05, | |
| "loss": 0.1065, | |
| "step": 702 | |
| }, | |
| { | |
| "epoch": 10.52, | |
| "learning_rate": 2.7752895106991384e-05, | |
| "loss": 0.1168, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 10.57, | |
| "learning_rate": 2.7347634628113916e-05, | |
| "loss": 0.0471, | |
| "step": 708 | |
| }, | |
| { | |
| "epoch": 10.61, | |
| "learning_rate": 2.6944238045508708e-05, | |
| "loss": 0.0782, | |
| "step": 711 | |
| }, | |
| { | |
| "epoch": 10.66, | |
| "learning_rate": 2.6542738551708828e-05, | |
| "loss": 0.0773, | |
| "step": 714 | |
| }, | |
| { | |
| "epoch": 10.7, | |
| "learning_rate": 2.6143169183149874e-05, | |
| "loss": 0.0629, | |
| "step": 717 | |
| }, | |
| { | |
| "epoch": 10.75, | |
| "learning_rate": 2.5745562817451686e-05, | |
| "loss": 0.0662, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 10.79, | |
| "learning_rate": 2.5349952170712977e-05, | |
| "loss": 0.0882, | |
| "step": 723 | |
| }, | |
| { | |
| "epoch": 10.84, | |
| "learning_rate": 2.4956369794819535e-05, | |
| "loss": 0.0508, | |
| "step": 726 | |
| }, | |
| { | |
| "epoch": 10.88, | |
| "learning_rate": 2.4564848074765674e-05, | |
| "loss": 0.0855, | |
| "step": 729 | |
| }, | |
| { | |
| "epoch": 10.93, | |
| "learning_rate": 2.417541922598945e-05, | |
| "loss": 0.0617, | |
| "step": 732 | |
| }, | |
| { | |
| "epoch": 10.97, | |
| "learning_rate": 2.378811529172203e-05, | |
| "loss": 0.1332, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 0.8252650499343872, | |
| "eval_matthews_correlation": 0.5260499940984096, | |
| "eval_runtime": 1.0581, | |
| "eval_samples_per_second": 985.733, | |
| "eval_steps_per_second": 62.376, | |
| "step": 737 | |
| }, | |
| { | |
| "epoch": 11.01, | |
| "learning_rate": 2.340296814035101e-05, | |
| "loss": 0.0843, | |
| "step": 738 | |
| }, | |
| { | |
| "epoch": 11.06, | |
| "learning_rate": 2.3020009462798163e-05, | |
| "loss": 0.0988, | |
| "step": 741 | |
| }, | |
| { | |
| "epoch": 11.1, | |
| "learning_rate": 2.263927076991193e-05, | |
| "loss": 0.0605, | |
| "step": 744 | |
| }, | |
| { | |
| "epoch": 11.15, | |
| "learning_rate": 2.226078338987453e-05, | |
| "loss": 0.0337, | |
| "step": 747 | |
| }, | |
| { | |
| "epoch": 11.19, | |
| "learning_rate": 2.1884578465624257e-05, | |
| "loss": 0.0412, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 11.24, | |
| "learning_rate": 2.1510686952292934e-05, | |
| "loss": 0.0611, | |
| "step": 753 | |
| }, | |
| { | |
| "epoch": 11.28, | |
| "learning_rate": 2.1139139614658798e-05, | |
| "loss": 0.0587, | |
| "step": 756 | |
| }, | |
| { | |
| "epoch": 11.33, | |
| "learning_rate": 2.0769967024615183e-05, | |
| "loss": 0.0204, | |
| "step": 759 | |
| }, | |
| { | |
| "epoch": 11.37, | |
| "learning_rate": 2.0403199558654945e-05, | |
| "loss": 0.1346, | |
| "step": 762 | |
| }, | |
| { | |
| "epoch": 11.42, | |
| "learning_rate": 2.0038867395370936e-05, | |
| "loss": 0.0577, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 11.46, | |
| "learning_rate": 1.967700051297295e-05, | |
| "loss": 0.0754, | |
| "step": 768 | |
| }, | |
| { | |
| "epoch": 11.51, | |
| "learning_rate": 1.931762868682098e-05, | |
| "loss": 0.0537, | |
| "step": 771 | |
| }, | |
| { | |
| "epoch": 11.55, | |
| "learning_rate": 1.8960781486975143e-05, | |
| "loss": 0.0334, | |
| "step": 774 | |
| }, | |
| { | |
| "epoch": 11.6, | |
| "learning_rate": 1.860648827576278e-05, | |
| "loss": 0.0651, | |
| "step": 777 | |
| }, | |
| { | |
| "epoch": 11.64, | |
| "learning_rate": 1.8254778205362206e-05, | |
| "loss": 0.0742, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 11.69, | |
| "learning_rate": 1.7905680215404174e-05, | |
| "loss": 0.1158, | |
| "step": 783 | |
| }, | |
| { | |
| "epoch": 11.73, | |
| "learning_rate": 1.7559223030590577e-05, | |
| "loss": 0.0916, | |
| "step": 786 | |
| }, | |
| { | |
| "epoch": 11.78, | |
| "learning_rate": 1.7215435158330855e-05, | |
| "loss": 0.0286, | |
| "step": 789 | |
| }, | |
| { | |
| "epoch": 11.82, | |
| "learning_rate": 1.6874344886396438e-05, | |
| "loss": 0.0687, | |
| "step": 792 | |
| }, | |
| { | |
| "epoch": 11.87, | |
| "learning_rate": 1.65359802805931e-05, | |
| "loss": 0.0705, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 11.91, | |
| "learning_rate": 1.6200369182451564e-05, | |
| "loss": 0.0717, | |
| "step": 798 | |
| }, | |
| { | |
| "epoch": 11.96, | |
| "learning_rate": 1.586753920693676e-05, | |
| "loss": 0.0445, | |
| "step": 801 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 1.553751774017551e-05, | |
| "loss": 0.0673, | |
| "step": 804 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 0.8085535764694214, | |
| "eval_matthews_correlation": 0.5179780196184617, | |
| "eval_runtime": 1.0516, | |
| "eval_samples_per_second": 991.801, | |
| "eval_steps_per_second": 62.76, | |
| "step": 804 | |
| }, | |
| { | |
| "epoch": 12.04, | |
| "learning_rate": 1.5210331937203088e-05, | |
| "loss": 0.094, | |
| "step": 807 | |
| }, | |
| { | |
| "epoch": 12.09, | |
| "learning_rate": 1.4886008719728989e-05, | |
| "loss": 0.0523, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 12.13, | |
| "learning_rate": 1.4564574773921514e-05, | |
| "loss": 0.0667, | |
| "step": 813 | |
| }, | |
| { | |
| "epoch": 12.18, | |
| "learning_rate": 1.4246056548212172e-05, | |
| "loss": 0.0533, | |
| "step": 816 | |
| }, | |
| { | |
| "epoch": 12.22, | |
| "learning_rate": 1.3930480251119321e-05, | |
| "loss": 0.0358, | |
| "step": 819 | |
| }, | |
| { | |
| "epoch": 12.27, | |
| "learning_rate": 1.3617871849091657e-05, | |
| "loss": 0.0532, | |
| "step": 822 | |
| }, | |
| { | |
| "epoch": 12.31, | |
| "learning_rate": 1.3308257064371677e-05, | |
| "loss": 0.0208, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 12.36, | |
| "learning_rate": 1.3001661372879192e-05, | |
| "loss": 0.0506, | |
| "step": 828 | |
| }, | |
| { | |
| "epoch": 12.4, | |
| "learning_rate": 1.2698110002115004e-05, | |
| "loss": 0.0827, | |
| "step": 831 | |
| }, | |
| { | |
| "epoch": 12.45, | |
| "learning_rate": 1.2397627929085248e-05, | |
| "loss": 0.0764, | |
| "step": 834 | |
| }, | |
| { | |
| "epoch": 12.49, | |
| "learning_rate": 1.2100239878246133e-05, | |
| "loss": 0.0863, | |
| "step": 837 | |
| }, | |
| { | |
| "epoch": 12.54, | |
| "learning_rate": 1.1805970319469589e-05, | |
| "loss": 0.0572, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 12.58, | |
| "learning_rate": 1.1514843466029807e-05, | |
| "loss": 0.103, | |
| "step": 843 | |
| }, | |
| { | |
| "epoch": 12.63, | |
| "learning_rate": 1.1226883272610877e-05, | |
| "loss": 0.0234, | |
| "step": 846 | |
| }, | |
| { | |
| "epoch": 12.67, | |
| "learning_rate": 1.0942113433335788e-05, | |
| "loss": 0.0521, | |
| "step": 849 | |
| }, | |
| { | |
| "epoch": 12.72, | |
| "learning_rate": 1.0660557379816816e-05, | |
| "loss": 0.0459, | |
| "step": 852 | |
| }, | |
| { | |
| "epoch": 12.76, | |
| "learning_rate": 1.0382238279227419e-05, | |
| "loss": 0.0695, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 12.81, | |
| "learning_rate": 1.0107179032396086e-05, | |
| "loss": 0.076, | |
| "step": 858 | |
| }, | |
| { | |
| "epoch": 12.85, | |
| "learning_rate": 9.835402271921974e-06, | |
| "loss": 0.0414, | |
| "step": 861 | |
| }, | |
| { | |
| "epoch": 12.9, | |
| "learning_rate": 9.56693036031256e-06, | |
| "loss": 0.0643, | |
| "step": 864 | |
| }, | |
| { | |
| "epoch": 12.94, | |
| "learning_rate": 9.301785388143697e-06, | |
| "loss": 0.0413, | |
| "step": 867 | |
| }, | |
| { | |
| "epoch": 12.99, | |
| "learning_rate": 9.039989172241886e-06, | |
| "loss": 0.0512, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 0.8409435749053955, | |
| "eval_matthews_correlation": 0.5127766293248668, | |
| "eval_runtime": 1.0686, | |
| "eval_samples_per_second": 976.072, | |
| "eval_steps_per_second": 61.765, | |
| "step": 871 | |
| }, | |
| { | |
| "epoch": 13.03, | |
| "learning_rate": 8.781563253889164e-06, | |
| "loss": 0.0642, | |
| "step": 873 | |
| }, | |
| { | |
| "epoch": 13.07, | |
| "learning_rate": 8.52652889705059e-06, | |
| "loss": 0.0699, | |
| "step": 876 | |
| }, | |
| { | |
| "epoch": 13.12, | |
| "learning_rate": 8.274907086624594e-06, | |
| "loss": 0.0431, | |
| "step": 879 | |
| }, | |
| { | |
| "epoch": 13.16, | |
| "learning_rate": 8.026718526716342e-06, | |
| "loss": 0.035, | |
| "step": 882 | |
| }, | |
| { | |
| "epoch": 13.21, | |
| "learning_rate": 7.781983638934092e-06, | |
| "loss": 0.0535, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 13.25, | |
| "learning_rate": 7.5407225607088405e-06, | |
| "loss": 0.0553, | |
| "step": 888 | |
| }, | |
| { | |
| "epoch": 13.3, | |
| "learning_rate": 7.302955143637419e-06, | |
| "loss": 0.0515, | |
| "step": 891 | |
| }, | |
| { | |
| "epoch": 13.34, | |
| "learning_rate": 7.068700951849011e-06, | |
| "loss": 0.047, | |
| "step": 894 | |
| }, | |
| { | |
| "epoch": 13.39, | |
| "learning_rate": 6.837979260395349e-06, | |
| "loss": 0.0787, | |
| "step": 897 | |
| }, | |
| { | |
| "epoch": 13.43, | |
| "learning_rate": 6.610809053664768e-06, | |
| "loss": 0.0559, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 13.48, | |
| "learning_rate": 6.387209023820073e-06, | |
| "loss": 0.0669, | |
| "step": 903 | |
| }, | |
| { | |
| "epoch": 13.52, | |
| "learning_rate": 6.1671975692605185e-06, | |
| "loss": 0.0828, | |
| "step": 906 | |
| }, | |
| { | |
| "epoch": 13.57, | |
| "learning_rate": 5.950792793107934e-06, | |
| "loss": 0.0373, | |
| "step": 909 | |
| }, | |
| { | |
| "epoch": 13.61, | |
| "learning_rate": 5.738012501717144e-06, | |
| "loss": 0.0586, | |
| "step": 912 | |
| }, | |
| { | |
| "epoch": 13.66, | |
| "learning_rate": 5.528874203210827e-06, | |
| "loss": 0.034, | |
| "step": 915 | |
| }, | |
| { | |
| "epoch": 13.7, | |
| "learning_rate": 5.323395106038909e-06, | |
| "loss": 0.0595, | |
| "step": 918 | |
| }, | |
| { | |
| "epoch": 13.75, | |
| "learning_rate": 5.121592117562573e-06, | |
| "loss": 0.0788, | |
| "step": 921 | |
| }, | |
| { | |
| "epoch": 13.79, | |
| "learning_rate": 4.923481842663114e-06, | |
| "loss": 0.0449, | |
| "step": 924 | |
| }, | |
| { | |
| "epoch": 13.84, | |
| "learning_rate": 4.729080582375633e-06, | |
| "loss": 0.0459, | |
| "step": 927 | |
| }, | |
| { | |
| "epoch": 13.88, | |
| "learning_rate": 4.538404332547719e-06, | |
| "loss": 0.0721, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 13.93, | |
| "learning_rate": 4.351468782523316e-06, | |
| "loss": 0.1029, | |
| "step": 933 | |
| }, | |
| { | |
| "epoch": 13.97, | |
| "learning_rate": 4.168289313851731e-06, | |
| "loss": 0.0457, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 0.8759517073631287, | |
| "eval_matthews_correlation": 0.4946640161033145, | |
| "eval_runtime": 1.079, | |
| "eval_samples_per_second": 966.594, | |
| "eval_steps_per_second": 61.165, | |
| "step": 938 | |
| }, | |
| { | |
| "epoch": 14.01, | |
| "learning_rate": 3.9888809990219985e-06, | |
| "loss": 0.0621, | |
| "step": 939 | |
| }, | |
| { | |
| "epoch": 14.06, | |
| "learning_rate": 3.8132586002227076e-06, | |
| "loss": 0.0333, | |
| "step": 942 | |
| }, | |
| { | |
| "epoch": 14.1, | |
| "learning_rate": 3.641436568127271e-06, | |
| "loss": 0.0461, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 14.15, | |
| "learning_rate": 3.4734290407049397e-06, | |
| "loss": 0.0532, | |
| "step": 948 | |
| }, | |
| { | |
| "epoch": 14.19, | |
| "learning_rate": 3.309249842057499e-06, | |
| "loss": 0.044, | |
| "step": 951 | |
| }, | |
| { | |
| "epoch": 14.24, | |
| "learning_rate": 3.148912481281713e-06, | |
| "loss": 0.0556, | |
| "step": 954 | |
| }, | |
| { | |
| "epoch": 14.28, | |
| "learning_rate": 2.99243015135785e-06, | |
| "loss": 0.0417, | |
| "step": 957 | |
| }, | |
| { | |
| "epoch": 14.33, | |
| "learning_rate": 2.839815728064077e-06, | |
| "loss": 0.0593, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 14.37, | |
| "learning_rate": 2.6910817689169922e-06, | |
| "loss": 0.0653, | |
| "step": 963 | |
| }, | |
| { | |
| "epoch": 14.42, | |
| "learning_rate": 2.5462405121384423e-06, | |
| "loss": 0.0558, | |
| "step": 966 | |
| }, | |
| { | |
| "epoch": 14.46, | |
| "learning_rate": 2.405303875648418e-06, | |
| "loss": 0.077, | |
| "step": 969 | |
| }, | |
| { | |
| "epoch": 14.51, | |
| "learning_rate": 2.268283456084491e-06, | |
| "loss": 0.0763, | |
| "step": 972 | |
| }, | |
| { | |
| "epoch": 14.55, | |
| "learning_rate": 2.135190527847608e-06, | |
| "loss": 0.075, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 14.6, | |
| "learning_rate": 2.0060360421743584e-06, | |
| "loss": 0.0172, | |
| "step": 978 | |
| }, | |
| { | |
| "epoch": 14.64, | |
| "learning_rate": 1.8808306262359243e-06, | |
| "loss": 0.034, | |
| "step": 981 | |
| }, | |
| { | |
| "epoch": 14.69, | |
| "learning_rate": 1.7595845822636293e-06, | |
| "loss": 0.0643, | |
| "step": 984 | |
| }, | |
| { | |
| "epoch": 14.73, | |
| "learning_rate": 1.6423078867012386e-06, | |
| "loss": 0.0568, | |
| "step": 987 | |
| }, | |
| { | |
| "epoch": 14.78, | |
| "learning_rate": 1.529010189384078e-06, | |
| "loss": 0.0609, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 14.82, | |
| "learning_rate": 1.419700812745045e-06, | |
| "loss": 0.0454, | |
| "step": 993 | |
| }, | |
| { | |
| "epoch": 14.87, | |
| "learning_rate": 1.3143887510474629e-06, | |
| "loss": 0.0688, | |
| "step": 996 | |
| }, | |
| { | |
| "epoch": 14.91, | |
| "learning_rate": 1.2130826696450992e-06, | |
| "loss": 0.0528, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 14.96, | |
| "learning_rate": 1.1157909042690928e-06, | |
| "loss": 0.0491, | |
| "step": 1002 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 1.0225214603420851e-06, | |
| "loss": 0.04, | |
| "step": 1005 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 0.8521906137466431, | |
| "eval_matthews_correlation": 0.5103199460790546, | |
| "eval_runtime": 1.1012, | |
| "eval_samples_per_second": 947.135, | |
| "eval_steps_per_second": 59.934, | |
| "step": 1005 | |
| }, | |
| { | |
| "epoch": 15.04, | |
| "learning_rate": 9.332820123195418e-07, | |
| "loss": 0.0588, | |
| "step": 1008 | |
| }, | |
| { | |
| "epoch": 15.09, | |
| "learning_rate": 8.480799030582187e-07, | |
| "loss": 0.0311, | |
| "step": 1011 | |
| }, | |
| { | |
| "epoch": 15.13, | |
| "learning_rate": 7.669221432120288e-07, | |
| "loss": 0.0655, | |
| "step": 1014 | |
| }, | |
| { | |
| "epoch": 15.18, | |
| "learning_rate": 6.898154106551702e-07, | |
| "loss": 0.0682, | |
| "step": 1017 | |
| }, | |
| { | |
| "epoch": 15.22, | |
| "learning_rate": 6.167660499326322e-07, | |
| "loss": 0.0736, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 15.27, | |
| "learning_rate": 5.477800717381687e-07, | |
| "loss": 0.0778, | |
| "step": 1023 | |
| }, | |
| { | |
| "epoch": 15.31, | |
| "learning_rate": 4.828631524197325e-07, | |
| "loss": 0.0917, | |
| "step": 1026 | |
| }, | |
| { | |
| "epoch": 15.36, | |
| "learning_rate": 4.2202063351238774e-07, | |
| "loss": 0.0468, | |
| "step": 1029 | |
| }, | |
| { | |
| "epoch": 15.4, | |
| "learning_rate": 3.652575212987952e-07, | |
| "loss": 0.0243, | |
| "step": 1032 | |
| }, | |
| { | |
| "epoch": 15.45, | |
| "learning_rate": 3.1257848639730803e-07, | |
| "loss": 0.0767, | |
| "step": 1035 | |
| }, | |
| { | |
| "epoch": 15.49, | |
| "learning_rate": 2.6398786337762936e-07, | |
| "loss": 0.0509, | |
| "step": 1038 | |
| }, | |
| { | |
| "epoch": 15.54, | |
| "learning_rate": 2.1948965040417547e-07, | |
| "loss": 0.0546, | |
| "step": 1041 | |
| }, | |
| { | |
| "epoch": 15.58, | |
| "learning_rate": 1.790875089070887e-07, | |
| "loss": 0.0451, | |
| "step": 1044 | |
| }, | |
| { | |
| "epoch": 15.63, | |
| "learning_rate": 1.427847632809509e-07, | |
| "loss": 0.0781, | |
| "step": 1047 | |
| }, | |
| { | |
| "epoch": 15.67, | |
| "learning_rate": 1.1058440061127439e-07, | |
| "loss": 0.0233, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 15.72, | |
| "learning_rate": 8.248907042868737e-08, | |
| "loss": 0.0393, | |
| "step": 1053 | |
| }, | |
| { | |
| "epoch": 15.76, | |
| "learning_rate": 5.850108449094727e-08, | |
| "loss": 0.0612, | |
| "step": 1056 | |
| }, | |
| { | |
| "epoch": 15.81, | |
| "learning_rate": 3.862241659269294e-08, | |
| "loss": 0.0476, | |
| "step": 1059 | |
| }, | |
| { | |
| "epoch": 15.85, | |
| "learning_rate": 2.2854702403068972e-08, | |
| "loss": 0.0283, | |
| "step": 1062 | |
| }, | |
| { | |
| "epoch": 15.9, | |
| "learning_rate": 1.1199239331122214e-08, | |
| "loss": 0.0482, | |
| "step": 1065 | |
| }, | |
| { | |
| "epoch": 15.94, | |
| "learning_rate": 3.6569864190427738e-09, | |
| "loss": 0.052, | |
| "step": 1068 | |
| }, | |
| { | |
| "epoch": 15.99, | |
| "learning_rate": 2.2856426326045565e-10, | |
| "loss": 0.0485, | |
| "step": 1071 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 0.8556408882141113, | |
| "eval_matthews_correlation": 0.5076423377649488, | |
| "eval_runtime": 1.1842, | |
| "eval_samples_per_second": 880.772, | |
| "eval_steps_per_second": 55.734, | |
| "step": 1072 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "step": 1072, | |
| "total_flos": 2253110839083008.0, | |
| "train_loss": 0.1824943411264763, | |
| "train_runtime": 434.1785, | |
| "train_samples_per_second": 315.115, | |
| "train_steps_per_second": 2.469 | |
| } | |
| ], | |
| "max_steps": 1072, | |
| "num_train_epochs": 16, | |
| "total_flos": 2253110839083008.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |