| { | |
| "best_metric": 0.003461688058450818, | |
| "best_model_checkpoint": "autotrain-9t83i-0umcp/checkpoint-1372", | |
| "epoch": 7.0, | |
| "eval_steps": 500, | |
| "global_step": 1372, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04591836734693878, | |
| "grad_norm": 2.446383237838745, | |
| "learning_rate": 1.1479591836734695e-06, | |
| "loss": 0.1983, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.09183673469387756, | |
| "grad_norm": 3.9726994037628174, | |
| "learning_rate": 2.295918367346939e-06, | |
| "loss": 0.2526, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1377551020408163, | |
| "grad_norm": 4.180245399475098, | |
| "learning_rate": 3.443877551020408e-06, | |
| "loss": 0.1536, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.1836734693877551, | |
| "grad_norm": 3.1698622703552246, | |
| "learning_rate": 4.591836734693878e-06, | |
| "loss": 0.3117, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.22959183673469388, | |
| "grad_norm": 4.330101490020752, | |
| "learning_rate": 5.7397959183673475e-06, | |
| "loss": 0.2641, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.2755102040816326, | |
| "grad_norm": 2.323159694671631, | |
| "learning_rate": 6.887755102040816e-06, | |
| "loss": 0.4657, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.32142857142857145, | |
| "grad_norm": 5.427762508392334, | |
| "learning_rate": 8.035714285714286e-06, | |
| "loss": 0.3486, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.3673469387755102, | |
| "grad_norm": 4.673620223999023, | |
| "learning_rate": 9.183673469387756e-06, | |
| "loss": 0.3346, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.413265306122449, | |
| "grad_norm": 4.061607837677002, | |
| "learning_rate": 1.0331632653061225e-05, | |
| "loss": 0.1703, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.45918367346938777, | |
| "grad_norm": 2.6127052307128906, | |
| "learning_rate": 1.1479591836734695e-05, | |
| "loss": 0.4217, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.5051020408163265, | |
| "grad_norm": 4.84128475189209, | |
| "learning_rate": 1.2627551020408163e-05, | |
| "loss": 0.1865, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.5510204081632653, | |
| "grad_norm": 3.507438898086548, | |
| "learning_rate": 1.3775510204081633e-05, | |
| "loss": 0.3114, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.5969387755102041, | |
| "grad_norm": 1.1375735998153687, | |
| "learning_rate": 1.4923469387755104e-05, | |
| "loss": 0.3519, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.6428571428571429, | |
| "grad_norm": 3.5756773948669434, | |
| "learning_rate": 1.6071428571428572e-05, | |
| "loss": 0.2934, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.6887755102040817, | |
| "grad_norm": 3.714728593826294, | |
| "learning_rate": 1.7219387755102043e-05, | |
| "loss": 0.3112, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.7346938775510204, | |
| "grad_norm": 4.473227500915527, | |
| "learning_rate": 1.836734693877551e-05, | |
| "loss": 0.1897, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.7806122448979592, | |
| "grad_norm": 2.203939914703369, | |
| "learning_rate": 1.9515306122448983e-05, | |
| "loss": 0.2168, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.826530612244898, | |
| "grad_norm": 1.36044180393219, | |
| "learning_rate": 2.066326530612245e-05, | |
| "loss": 0.117, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.8724489795918368, | |
| "grad_norm": 1.2238707542419434, | |
| "learning_rate": 2.181122448979592e-05, | |
| "loss": 0.2936, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.9183673469387755, | |
| "grad_norm": 2.6794865131378174, | |
| "learning_rate": 2.295918367346939e-05, | |
| "loss": 0.1305, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.9642857142857143, | |
| "grad_norm": 3.089512825012207, | |
| "learning_rate": 2.4107142857142858e-05, | |
| "loss": 0.397, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_gen_len": 128.0, | |
| "eval_loss": 0.18853867053985596, | |
| "eval_rouge1": 89.2949, | |
| "eval_rouge2": 83.057, | |
| "eval_rougeL": 88.1848, | |
| "eval_rougeLsum": 88.7391, | |
| "eval_runtime": 38.0997, | |
| "eval_samples_per_second": 2.572, | |
| "eval_steps_per_second": 0.656, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 1.010204081632653, | |
| "grad_norm": 2.5835583209991455, | |
| "learning_rate": 2.5255102040816326e-05, | |
| "loss": 0.3554, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 1.0561224489795917, | |
| "grad_norm": 1.9029709100723267, | |
| "learning_rate": 2.6403061224489794e-05, | |
| "loss": 0.1324, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 1.1020408163265305, | |
| "grad_norm": 2.5668606758117676, | |
| "learning_rate": 2.7551020408163265e-05, | |
| "loss": 0.1243, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 1.1479591836734695, | |
| "grad_norm": 2.5577433109283447, | |
| "learning_rate": 2.869897959183674e-05, | |
| "loss": 0.0995, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 1.193877551020408, | |
| "grad_norm": 4.285234451293945, | |
| "learning_rate": 2.9846938775510208e-05, | |
| "loss": 0.2354, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 1.239795918367347, | |
| "grad_norm": 3.811396598815918, | |
| "learning_rate": 3.0994897959183676e-05, | |
| "loss": 0.181, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 1.2857142857142856, | |
| "grad_norm": 0.5611918568611145, | |
| "learning_rate": 3.2142857142857144e-05, | |
| "loss": 0.0721, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 1.3316326530612246, | |
| "grad_norm": 4.734651565551758, | |
| "learning_rate": 3.329081632653062e-05, | |
| "loss": 0.1276, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 1.3775510204081631, | |
| "grad_norm": 2.2007200717926025, | |
| "learning_rate": 3.443877551020409e-05, | |
| "loss": 0.0872, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.4234693877551021, | |
| "grad_norm": 1.3555959463119507, | |
| "learning_rate": 3.5586734693877555e-05, | |
| "loss": 0.2188, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 1.469387755102041, | |
| "grad_norm": 2.6970372200012207, | |
| "learning_rate": 3.673469387755102e-05, | |
| "loss": 0.2266, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 1.5153061224489797, | |
| "grad_norm": 10.701809883117676, | |
| "learning_rate": 3.788265306122449e-05, | |
| "loss": 0.157, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 1.5612244897959182, | |
| "grad_norm": 1.6892890930175781, | |
| "learning_rate": 3.9030612244897965e-05, | |
| "loss": 0.0885, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 1.6071428571428572, | |
| "grad_norm": 1.5699105262756348, | |
| "learning_rate": 4.017857142857143e-05, | |
| "loss": 0.1323, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 1.6530612244897958, | |
| "grad_norm": 4.3087639808654785, | |
| "learning_rate": 4.13265306122449e-05, | |
| "loss": 0.1482, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 1.6989795918367347, | |
| "grad_norm": 0.6790181994438171, | |
| "learning_rate": 4.247448979591837e-05, | |
| "loss": 0.1814, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 1.7448979591836735, | |
| "grad_norm": 2.1411118507385254, | |
| "learning_rate": 4.362244897959184e-05, | |
| "loss": 0.0834, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 1.7908163265306123, | |
| "grad_norm": 1.8243377208709717, | |
| "learning_rate": 4.477040816326531e-05, | |
| "loss": 0.1124, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 1.836734693877551, | |
| "grad_norm": 1.9441792964935303, | |
| "learning_rate": 4.591836734693878e-05, | |
| "loss": 0.095, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.8826530612244898, | |
| "grad_norm": 3.742511034011841, | |
| "learning_rate": 4.706632653061225e-05, | |
| "loss": 0.0955, | |
| "step": 369 | |
| }, | |
| { | |
| "epoch": 1.9285714285714286, | |
| "grad_norm": 1.4945087432861328, | |
| "learning_rate": 4.8214285714285716e-05, | |
| "loss": 0.0543, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 1.9744897959183674, | |
| "grad_norm": 1.0501391887664795, | |
| "learning_rate": 4.9362244897959184e-05, | |
| "loss": 0.0861, | |
| "step": 387 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_gen_len": 128.0, | |
| "eval_loss": 0.05252710357308388, | |
| "eval_rouge1": 96.0027, | |
| "eval_rouge2": 93.3236, | |
| "eval_rougeL": 95.501, | |
| "eval_rougeLsum": 95.7994, | |
| "eval_runtime": 37.9097, | |
| "eval_samples_per_second": 2.585, | |
| "eval_steps_per_second": 0.659, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 2.020408163265306, | |
| "grad_norm": 2.9681637287139893, | |
| "learning_rate": 4.9943310657596374e-05, | |
| "loss": 0.0559, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 2.066326530612245, | |
| "grad_norm": 0.807901918888092, | |
| "learning_rate": 4.981575963718821e-05, | |
| "loss": 0.0334, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 2.1122448979591835, | |
| "grad_norm": 5.0659918785095215, | |
| "learning_rate": 4.968820861678005e-05, | |
| "loss": 0.1104, | |
| "step": 414 | |
| }, | |
| { | |
| "epoch": 2.1581632653061225, | |
| "grad_norm": 2.9605283737182617, | |
| "learning_rate": 4.956065759637189e-05, | |
| "loss": 0.0817, | |
| "step": 423 | |
| }, | |
| { | |
| "epoch": 2.204081632653061, | |
| "grad_norm": 2.554128408432007, | |
| "learning_rate": 4.9433106575963725e-05, | |
| "loss": 0.0524, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "grad_norm": 1.5891895294189453, | |
| "learning_rate": 4.930555555555556e-05, | |
| "loss": 0.0988, | |
| "step": 441 | |
| }, | |
| { | |
| "epoch": 2.295918367346939, | |
| "grad_norm": 3.2821803092956543, | |
| "learning_rate": 4.917800453514739e-05, | |
| "loss": 0.08, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.3418367346938775, | |
| "grad_norm": 1.6306498050689697, | |
| "learning_rate": 4.905045351473923e-05, | |
| "loss": 0.0339, | |
| "step": 459 | |
| }, | |
| { | |
| "epoch": 2.387755102040816, | |
| "grad_norm": 3.2567660808563232, | |
| "learning_rate": 4.892290249433107e-05, | |
| "loss": 0.0755, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 2.433673469387755, | |
| "grad_norm": 2.143312931060791, | |
| "learning_rate": 4.8795351473922906e-05, | |
| "loss": 0.0682, | |
| "step": 477 | |
| }, | |
| { | |
| "epoch": 2.479591836734694, | |
| "grad_norm": 1.9906742572784424, | |
| "learning_rate": 4.866780045351474e-05, | |
| "loss": 0.0747, | |
| "step": 486 | |
| }, | |
| { | |
| "epoch": 2.5255102040816326, | |
| "grad_norm": 6.981854438781738, | |
| "learning_rate": 4.8540249433106574e-05, | |
| "loss": 0.0533, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 2.571428571428571, | |
| "grad_norm": 1.767125129699707, | |
| "learning_rate": 4.841269841269841e-05, | |
| "loss": 0.0537, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 2.61734693877551, | |
| "grad_norm": 1.545177698135376, | |
| "learning_rate": 4.828514739229025e-05, | |
| "loss": 0.0535, | |
| "step": 513 | |
| }, | |
| { | |
| "epoch": 2.663265306122449, | |
| "grad_norm": 1.537906527519226, | |
| "learning_rate": 4.8157596371882094e-05, | |
| "loss": 0.0721, | |
| "step": 522 | |
| }, | |
| { | |
| "epoch": 2.7091836734693877, | |
| "grad_norm": 1.4103052616119385, | |
| "learning_rate": 4.8030045351473925e-05, | |
| "loss": 0.0515, | |
| "step": 531 | |
| }, | |
| { | |
| "epoch": 2.7551020408163263, | |
| "grad_norm": 1.9743316173553467, | |
| "learning_rate": 4.790249433106576e-05, | |
| "loss": 0.0606, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 2.8010204081632653, | |
| "grad_norm": 1.1865582466125488, | |
| "learning_rate": 4.77749433106576e-05, | |
| "loss": 0.0336, | |
| "step": 549 | |
| }, | |
| { | |
| "epoch": 2.8469387755102042, | |
| "grad_norm": 1.7514479160308838, | |
| "learning_rate": 4.764739229024944e-05, | |
| "loss": 0.0357, | |
| "step": 558 | |
| }, | |
| { | |
| "epoch": 2.892857142857143, | |
| "grad_norm": 3.3062944412231445, | |
| "learning_rate": 4.751984126984127e-05, | |
| "loss": 0.0613, | |
| "step": 567 | |
| }, | |
| { | |
| "epoch": 2.938775510204082, | |
| "grad_norm": 0.8094915151596069, | |
| "learning_rate": 4.7392290249433106e-05, | |
| "loss": 0.0449, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 2.9846938775510203, | |
| "grad_norm": 2.2876973152160645, | |
| "learning_rate": 4.7264739229024944e-05, | |
| "loss": 0.06, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_gen_len": 127.6939, | |
| "eval_loss": 0.025030160322785378, | |
| "eval_rouge1": 98.6655, | |
| "eval_rouge2": 97.5818, | |
| "eval_rougeL": 98.5529, | |
| "eval_rougeLsum": 98.5395, | |
| "eval_runtime": 37.9756, | |
| "eval_samples_per_second": 2.581, | |
| "eval_steps_per_second": 0.658, | |
| "step": 588 | |
| }, | |
| { | |
| "epoch": 3.0306122448979593, | |
| "grad_norm": 1.7782725095748901, | |
| "learning_rate": 4.713718820861678e-05, | |
| "loss": 0.0219, | |
| "step": 594 | |
| }, | |
| { | |
| "epoch": 3.076530612244898, | |
| "grad_norm": 0.317821741104126, | |
| "learning_rate": 4.700963718820862e-05, | |
| "loss": 0.037, | |
| "step": 603 | |
| }, | |
| { | |
| "epoch": 3.122448979591837, | |
| "grad_norm": 0.8859459757804871, | |
| "learning_rate": 4.688208616780046e-05, | |
| "loss": 0.0531, | |
| "step": 612 | |
| }, | |
| { | |
| "epoch": 3.1683673469387754, | |
| "grad_norm": 0.3588017225265503, | |
| "learning_rate": 4.67687074829932e-05, | |
| "loss": 0.0307, | |
| "step": 621 | |
| }, | |
| { | |
| "epoch": 3.2142857142857144, | |
| "grad_norm": 2.5311052799224854, | |
| "learning_rate": 4.664115646258503e-05, | |
| "loss": 0.0218, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 3.260204081632653, | |
| "grad_norm": 0.19862987101078033, | |
| "learning_rate": 4.651360544217687e-05, | |
| "loss": 0.0367, | |
| "step": 639 | |
| }, | |
| { | |
| "epoch": 3.306122448979592, | |
| "grad_norm": 0.6744495034217834, | |
| "learning_rate": 4.638605442176871e-05, | |
| "loss": 0.0369, | |
| "step": 648 | |
| }, | |
| { | |
| "epoch": 3.3520408163265305, | |
| "grad_norm": 2.8351736068725586, | |
| "learning_rate": 4.625850340136055e-05, | |
| "loss": 0.0465, | |
| "step": 657 | |
| }, | |
| { | |
| "epoch": 3.3979591836734695, | |
| "grad_norm": 3.43568754196167, | |
| "learning_rate": 4.613095238095239e-05, | |
| "loss": 0.0335, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 3.443877551020408, | |
| "grad_norm": 2.1830670833587646, | |
| "learning_rate": 4.600340136054422e-05, | |
| "loss": 0.0284, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 3.489795918367347, | |
| "grad_norm": 0.9732754826545715, | |
| "learning_rate": 4.587585034013606e-05, | |
| "loss": 0.0269, | |
| "step": 684 | |
| }, | |
| { | |
| "epoch": 3.5357142857142856, | |
| "grad_norm": 2.1796019077301025, | |
| "learning_rate": 4.5748299319727895e-05, | |
| "loss": 0.0362, | |
| "step": 693 | |
| }, | |
| { | |
| "epoch": 3.5816326530612246, | |
| "grad_norm": 1.1703124046325684, | |
| "learning_rate": 4.562074829931973e-05, | |
| "loss": 0.0229, | |
| "step": 702 | |
| }, | |
| { | |
| "epoch": 3.627551020408163, | |
| "grad_norm": 2.6701223850250244, | |
| "learning_rate": 4.549319727891156e-05, | |
| "loss": 0.0471, | |
| "step": 711 | |
| }, | |
| { | |
| "epoch": 3.673469387755102, | |
| "grad_norm": 1.3318531513214111, | |
| "learning_rate": 4.53656462585034e-05, | |
| "loss": 0.0327, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 3.7193877551020407, | |
| "grad_norm": 1.4701616764068604, | |
| "learning_rate": 4.523809523809524e-05, | |
| "loss": 0.0184, | |
| "step": 729 | |
| }, | |
| { | |
| "epoch": 3.7653061224489797, | |
| "grad_norm": 0.9515037536621094, | |
| "learning_rate": 4.5110544217687076e-05, | |
| "loss": 0.0308, | |
| "step": 738 | |
| }, | |
| { | |
| "epoch": 3.811224489795918, | |
| "grad_norm": 3.164966583251953, | |
| "learning_rate": 4.4982993197278914e-05, | |
| "loss": 0.0262, | |
| "step": 747 | |
| }, | |
| { | |
| "epoch": 3.857142857142857, | |
| "grad_norm": 0.8453909158706665, | |
| "learning_rate": 4.485544217687075e-05, | |
| "loss": 0.0327, | |
| "step": 756 | |
| }, | |
| { | |
| "epoch": 3.9030612244897958, | |
| "grad_norm": 2.3475284576416016, | |
| "learning_rate": 4.472789115646259e-05, | |
| "loss": 0.0222, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 3.9489795918367347, | |
| "grad_norm": 0.677014946937561, | |
| "learning_rate": 4.4600340136054427e-05, | |
| "loss": 0.0244, | |
| "step": 774 | |
| }, | |
| { | |
| "epoch": 3.9948979591836737, | |
| "grad_norm": 3.246267318725586, | |
| "learning_rate": 4.4472789115646264e-05, | |
| "loss": 0.0297, | |
| "step": 783 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_gen_len": 127.7143, | |
| "eval_loss": 0.010969710536301136, | |
| "eval_rouge1": 99.1634, | |
| "eval_rouge2": 98.7404, | |
| "eval_rougeL": 99.1194, | |
| "eval_rougeLsum": 99.1779, | |
| "eval_runtime": 37.9041, | |
| "eval_samples_per_second": 2.585, | |
| "eval_steps_per_second": 0.66, | |
| "step": 784 | |
| }, | |
| { | |
| "epoch": 4.040816326530612, | |
| "grad_norm": 0.39469975233078003, | |
| "learning_rate": 4.4345238095238095e-05, | |
| "loss": 0.0244, | |
| "step": 792 | |
| }, | |
| { | |
| "epoch": 4.086734693877551, | |
| "grad_norm": 2.384838581085205, | |
| "learning_rate": 4.421768707482993e-05, | |
| "loss": 0.0213, | |
| "step": 801 | |
| }, | |
| { | |
| "epoch": 4.13265306122449, | |
| "grad_norm": 3.5253398418426514, | |
| "learning_rate": 4.409013605442177e-05, | |
| "loss": 0.0089, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 4.178571428571429, | |
| "grad_norm": 2.1386358737945557, | |
| "learning_rate": 4.396258503401361e-05, | |
| "loss": 0.036, | |
| "step": 819 | |
| }, | |
| { | |
| "epoch": 4.224489795918367, | |
| "grad_norm": 0.44415947794914246, | |
| "learning_rate": 4.383503401360544e-05, | |
| "loss": 0.0147, | |
| "step": 828 | |
| }, | |
| { | |
| "epoch": 4.270408163265306, | |
| "grad_norm": 2.4095001220703125, | |
| "learning_rate": 4.3707482993197277e-05, | |
| "loss": 0.0321, | |
| "step": 837 | |
| }, | |
| { | |
| "epoch": 4.316326530612245, | |
| "grad_norm": 2.395909070968628, | |
| "learning_rate": 4.357993197278912e-05, | |
| "loss": 0.0296, | |
| "step": 846 | |
| }, | |
| { | |
| "epoch": 4.362244897959184, | |
| "grad_norm": 4.824786186218262, | |
| "learning_rate": 4.345238095238096e-05, | |
| "loss": 0.0233, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 4.408163265306122, | |
| "grad_norm": 2.400609254837036, | |
| "learning_rate": 4.3324829931972796e-05, | |
| "loss": 0.0389, | |
| "step": 864 | |
| }, | |
| { | |
| "epoch": 4.454081632653061, | |
| "grad_norm": 1.0374516248703003, | |
| "learning_rate": 4.319727891156463e-05, | |
| "loss": 0.0307, | |
| "step": 873 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "grad_norm": 2.5744516849517822, | |
| "learning_rate": 4.3069727891156465e-05, | |
| "loss": 0.0234, | |
| "step": 882 | |
| }, | |
| { | |
| "epoch": 4.545918367346939, | |
| "grad_norm": 0.4013276696205139, | |
| "learning_rate": 4.29421768707483e-05, | |
| "loss": 0.0171, | |
| "step": 891 | |
| }, | |
| { | |
| "epoch": 4.591836734693878, | |
| "grad_norm": 1.4164782762527466, | |
| "learning_rate": 4.281462585034014e-05, | |
| "loss": 0.0217, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 4.637755102040816, | |
| "grad_norm": 0.2612836956977844, | |
| "learning_rate": 4.268707482993197e-05, | |
| "loss": 0.007, | |
| "step": 909 | |
| }, | |
| { | |
| "epoch": 4.683673469387755, | |
| "grad_norm": 0.537272036075592, | |
| "learning_rate": 4.255952380952381e-05, | |
| "loss": 0.034, | |
| "step": 918 | |
| }, | |
| { | |
| "epoch": 4.729591836734694, | |
| "grad_norm": 0.7186601758003235, | |
| "learning_rate": 4.2431972789115646e-05, | |
| "loss": 0.0173, | |
| "step": 927 | |
| }, | |
| { | |
| "epoch": 4.775510204081632, | |
| "grad_norm": 0.5405403971672058, | |
| "learning_rate": 4.2304421768707484e-05, | |
| "loss": 0.0175, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 4.821428571428571, | |
| "grad_norm": 0.49115684628486633, | |
| "learning_rate": 4.217687074829932e-05, | |
| "loss": 0.0115, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 4.86734693877551, | |
| "grad_norm": 0.08387177437543869, | |
| "learning_rate": 4.204931972789116e-05, | |
| "loss": 0.0159, | |
| "step": 954 | |
| }, | |
| { | |
| "epoch": 4.913265306122449, | |
| "grad_norm": 0.31179898977279663, | |
| "learning_rate": 4.1921768707483e-05, | |
| "loss": 0.0163, | |
| "step": 963 | |
| }, | |
| { | |
| "epoch": 4.959183673469388, | |
| "grad_norm": 1.2666131258010864, | |
| "learning_rate": 4.1794217687074834e-05, | |
| "loss": 0.0221, | |
| "step": 972 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_gen_len": 127.7143, | |
| "eval_loss": 0.00930405966937542, | |
| "eval_rouge1": 99.2277, | |
| "eval_rouge2": 98.8302, | |
| "eval_rougeL": 99.2299, | |
| "eval_rougeLsum": 99.2242, | |
| "eval_runtime": 37.8008, | |
| "eval_samples_per_second": 2.593, | |
| "eval_steps_per_second": 0.661, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 5.005102040816326, | |
| "grad_norm": 1.5087450742721558, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.0229, | |
| "step": 981 | |
| }, | |
| { | |
| "epoch": 5.051020408163265, | |
| "grad_norm": 0.1325344741344452, | |
| "learning_rate": 4.15391156462585e-05, | |
| "loss": 0.011, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 5.096938775510204, | |
| "grad_norm": 0.32866305112838745, | |
| "learning_rate": 4.141156462585034e-05, | |
| "loss": 0.0112, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 5.142857142857143, | |
| "grad_norm": 3.6175878047943115, | |
| "learning_rate": 4.128401360544218e-05, | |
| "loss": 0.0151, | |
| "step": 1008 | |
| }, | |
| { | |
| "epoch": 5.188775510204081, | |
| "grad_norm": 1.1477692127227783, | |
| "learning_rate": 4.1156462585034016e-05, | |
| "loss": 0.0093, | |
| "step": 1017 | |
| }, | |
| { | |
| "epoch": 5.23469387755102, | |
| "grad_norm": 0.1428331732749939, | |
| "learning_rate": 4.1028911564625853e-05, | |
| "loss": 0.0115, | |
| "step": 1026 | |
| }, | |
| { | |
| "epoch": 5.280612244897959, | |
| "grad_norm": 0.1712471842765808, | |
| "learning_rate": 4.0901360544217684e-05, | |
| "loss": 0.0219, | |
| "step": 1035 | |
| }, | |
| { | |
| "epoch": 5.326530612244898, | |
| "grad_norm": 0.21103200316429138, | |
| "learning_rate": 4.077380952380952e-05, | |
| "loss": 0.0121, | |
| "step": 1044 | |
| }, | |
| { | |
| "epoch": 5.372448979591836, | |
| "grad_norm": 0.15935823321342468, | |
| "learning_rate": 4.0646258503401366e-05, | |
| "loss": 0.0074, | |
| "step": 1053 | |
| }, | |
| { | |
| "epoch": 5.418367346938775, | |
| "grad_norm": 0.7716410756111145, | |
| "learning_rate": 4.0518707482993204e-05, | |
| "loss": 0.0314, | |
| "step": 1062 | |
| }, | |
| { | |
| "epoch": 5.464285714285714, | |
| "grad_norm": 0.5172207951545715, | |
| "learning_rate": 4.0391156462585035e-05, | |
| "loss": 0.0101, | |
| "step": 1071 | |
| }, | |
| { | |
| "epoch": 5.510204081632653, | |
| "grad_norm": 1.6434773206710815, | |
| "learning_rate": 4.026360544217687e-05, | |
| "loss": 0.0176, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 5.5561224489795915, | |
| "grad_norm": 0.2688583731651306, | |
| "learning_rate": 4.013605442176871e-05, | |
| "loss": 0.0136, | |
| "step": 1089 | |
| }, | |
| { | |
| "epoch": 5.6020408163265305, | |
| "grad_norm": 0.7320523858070374, | |
| "learning_rate": 4.000850340136055e-05, | |
| "loss": 0.0132, | |
| "step": 1098 | |
| }, | |
| { | |
| "epoch": 5.6479591836734695, | |
| "grad_norm": 0.7341743111610413, | |
| "learning_rate": 3.9880952380952386e-05, | |
| "loss": 0.0064, | |
| "step": 1107 | |
| }, | |
| { | |
| "epoch": 5.6938775510204085, | |
| "grad_norm": 1.0884281396865845, | |
| "learning_rate": 3.9753401360544216e-05, | |
| "loss": 0.0192, | |
| "step": 1116 | |
| }, | |
| { | |
| "epoch": 5.739795918367347, | |
| "grad_norm": 0.36947500705718994, | |
| "learning_rate": 3.9625850340136054e-05, | |
| "loss": 0.0128, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 5.785714285714286, | |
| "grad_norm": 0.5507375597953796, | |
| "learning_rate": 3.949829931972789e-05, | |
| "loss": 0.005, | |
| "step": 1134 | |
| }, | |
| { | |
| "epoch": 5.831632653061225, | |
| "grad_norm": 2.703362226486206, | |
| "learning_rate": 3.937074829931973e-05, | |
| "loss": 0.0336, | |
| "step": 1143 | |
| }, | |
| { | |
| "epoch": 5.877551020408164, | |
| "grad_norm": 0.28341037034988403, | |
| "learning_rate": 3.924319727891157e-05, | |
| "loss": 0.0085, | |
| "step": 1152 | |
| }, | |
| { | |
| "epoch": 5.923469387755102, | |
| "grad_norm": 0.5502461194992065, | |
| "learning_rate": 3.9115646258503405e-05, | |
| "loss": 0.0197, | |
| "step": 1161 | |
| }, | |
| { | |
| "epoch": 5.969387755102041, | |
| "grad_norm": 0.14302176237106323, | |
| "learning_rate": 3.898809523809524e-05, | |
| "loss": 0.0085, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_gen_len": 127.0408, | |
| "eval_loss": 0.005346208810806274, | |
| "eval_rouge1": 99.1155, | |
| "eval_rouge2": 98.9388, | |
| "eval_rougeL": 99.0647, | |
| "eval_rougeLsum": 99.1173, | |
| "eval_runtime": 37.8929, | |
| "eval_samples_per_second": 2.586, | |
| "eval_steps_per_second": 0.66, | |
| "step": 1176 | |
| }, | |
| { | |
| "epoch": 6.01530612244898, | |
| "grad_norm": 3.993354558944702, | |
| "learning_rate": 3.886054421768708e-05, | |
| "loss": 0.0131, | |
| "step": 1179 | |
| }, | |
| { | |
| "epoch": 6.061224489795919, | |
| "grad_norm": 1.2994415760040283, | |
| "learning_rate": 3.873299319727892e-05, | |
| "loss": 0.0164, | |
| "step": 1188 | |
| }, | |
| { | |
| "epoch": 6.107142857142857, | |
| "grad_norm": 1.7750136852264404, | |
| "learning_rate": 3.860544217687075e-05, | |
| "loss": 0.0049, | |
| "step": 1197 | |
| }, | |
| { | |
| "epoch": 6.153061224489796, | |
| "grad_norm": 1.9320180416107178, | |
| "learning_rate": 3.8477891156462586e-05, | |
| "loss": 0.0039, | |
| "step": 1206 | |
| }, | |
| { | |
| "epoch": 6.198979591836735, | |
| "grad_norm": 0.19184532761573792, | |
| "learning_rate": 3.8350340136054424e-05, | |
| "loss": 0.0045, | |
| "step": 1215 | |
| }, | |
| { | |
| "epoch": 6.244897959183674, | |
| "grad_norm": 0.7971787452697754, | |
| "learning_rate": 3.822278911564626e-05, | |
| "loss": 0.0063, | |
| "step": 1224 | |
| }, | |
| { | |
| "epoch": 6.290816326530612, | |
| "grad_norm": 0.3261989951133728, | |
| "learning_rate": 3.809523809523809e-05, | |
| "loss": 0.0166, | |
| "step": 1233 | |
| }, | |
| { | |
| "epoch": 6.336734693877551, | |
| "grad_norm": 3.3873021602630615, | |
| "learning_rate": 3.796768707482993e-05, | |
| "loss": 0.0074, | |
| "step": 1242 | |
| }, | |
| { | |
| "epoch": 6.38265306122449, | |
| "grad_norm": 2.5156352519989014, | |
| "learning_rate": 3.784013605442177e-05, | |
| "loss": 0.0132, | |
| "step": 1251 | |
| }, | |
| { | |
| "epoch": 6.428571428571429, | |
| "grad_norm": 4.740504264831543, | |
| "learning_rate": 3.771258503401361e-05, | |
| "loss": 0.0197, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 6.474489795918368, | |
| "grad_norm": 0.14355747401714325, | |
| "learning_rate": 3.758503401360544e-05, | |
| "loss": 0.005, | |
| "step": 1269 | |
| }, | |
| { | |
| "epoch": 6.520408163265306, | |
| "grad_norm": 1.1807011365890503, | |
| "learning_rate": 3.745748299319728e-05, | |
| "loss": 0.0073, | |
| "step": 1278 | |
| }, | |
| { | |
| "epoch": 6.566326530612245, | |
| "grad_norm": 0.22915400564670563, | |
| "learning_rate": 3.732993197278912e-05, | |
| "loss": 0.006, | |
| "step": 1287 | |
| }, | |
| { | |
| "epoch": 6.612244897959184, | |
| "grad_norm": 0.3873462975025177, | |
| "learning_rate": 3.7202380952380956e-05, | |
| "loss": 0.0113, | |
| "step": 1296 | |
| }, | |
| { | |
| "epoch": 6.658163265306122, | |
| "grad_norm": 1.502334475517273, | |
| "learning_rate": 3.707482993197279e-05, | |
| "loss": 0.0145, | |
| "step": 1305 | |
| }, | |
| { | |
| "epoch": 6.704081632653061, | |
| "grad_norm": 1.4580602645874023, | |
| "learning_rate": 3.6947278911564624e-05, | |
| "loss": 0.0115, | |
| "step": 1314 | |
| }, | |
| { | |
| "epoch": 6.75, | |
| "grad_norm": 0.14768829941749573, | |
| "learning_rate": 3.681972789115646e-05, | |
| "loss": 0.0057, | |
| "step": 1323 | |
| }, | |
| { | |
| "epoch": 6.795918367346939, | |
| "grad_norm": 0.10615669190883636, | |
| "learning_rate": 3.66921768707483e-05, | |
| "loss": 0.0113, | |
| "step": 1332 | |
| }, | |
| { | |
| "epoch": 6.841836734693878, | |
| "grad_norm": 0.17342956364154816, | |
| "learning_rate": 3.656462585034014e-05, | |
| "loss": 0.0077, | |
| "step": 1341 | |
| }, | |
| { | |
| "epoch": 6.887755102040816, | |
| "grad_norm": 1.031613826751709, | |
| "learning_rate": 3.6437074829931975e-05, | |
| "loss": 0.0061, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 6.933673469387755, | |
| "grad_norm": 0.5434854030609131, | |
| "learning_rate": 3.630952380952381e-05, | |
| "loss": 0.0046, | |
| "step": 1359 | |
| }, | |
| { | |
| "epoch": 6.979591836734694, | |
| "grad_norm": 2.6706666946411133, | |
| "learning_rate": 3.618197278911565e-05, | |
| "loss": 0.008, | |
| "step": 1368 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_gen_len": 127.7143, | |
| "eval_loss": 0.003461688058450818, | |
| "eval_rouge1": 99.738, | |
| "eval_rouge2": 99.6362, | |
| "eval_rougeL": 99.7372, | |
| "eval_rougeLsum": 99.739, | |
| "eval_runtime": 37.7713, | |
| "eval_samples_per_second": 2.595, | |
| "eval_steps_per_second": 0.662, | |
| "step": 1372 | |
| } | |
| ], | |
| "logging_steps": 9, | |
| "max_steps": 3920, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 20, | |
| "save_steps": 500, | |
| "total_flos": 93017113362432.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |