Invalid JSON:Unexpected token 'I', ..."ad_norm": Infinity,
"... is not valid JSON
| { | |
| "best_global_step": 3000, | |
| "best_metric": 51.14, | |
| "best_model_checkpoint": "./bart-email-multitask-updated/checkpoint-3000", | |
| "epoch": 1.3807715543281263, | |
| "eval_steps": 500, | |
| "global_step": 4000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0172607232243031, | |
| "grad_norm": 3.8177006244659424, | |
| "learning_rate": 1.2250000000000001e-06, | |
| "loss": 0.4507, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0345214464486062, | |
| "grad_norm": Infinity, | |
| "learning_rate": 2.475e-06, | |
| "loss": 0.4331, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.051782169672909294, | |
| "grad_norm": 2.9417564868927, | |
| "learning_rate": 3.7250000000000003e-06, | |
| "loss": 0.4042, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.0690428928972124, | |
| "grad_norm": 2.8877062797546387, | |
| "learning_rate": 4.975000000000001e-06, | |
| "loss": 0.397, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.08630361612151549, | |
| "grad_norm": 3.343304395675659, | |
| "learning_rate": 4.956203074722918e-06, | |
| "loss": 0.3892, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.10356433934581859, | |
| "grad_norm": 3.0275661945343018, | |
| "learning_rate": 4.911512334644262e-06, | |
| "loss": 0.3891, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.12082506257012168, | |
| "grad_norm": 3.045884847640991, | |
| "learning_rate": 4.866821594565607e-06, | |
| "loss": 0.3656, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.1380857857944248, | |
| "grad_norm": 2.7904183864593506, | |
| "learning_rate": 4.82213085448695e-06, | |
| "loss": 0.365, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.15534650901872787, | |
| "grad_norm": 3.6787497997283936, | |
| "learning_rate": 4.777440114408295e-06, | |
| "loss": 0.3594, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.17260723224303098, | |
| "grad_norm": 3.1564106941223145, | |
| "learning_rate": 4.732749374329639e-06, | |
| "loss": 0.3719, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.17260723224303098, | |
| "eval_gen_len": 55.68621291448517, | |
| "eval_loss": 0.5641192197799683, | |
| "eval_rouge1": 49.82, | |
| "eval_rouge2": 35.56, | |
| "eval_rougeL": 43.37, | |
| "eval_rougeLsum": 43.9, | |
| "eval_runtime": 5387.3225, | |
| "eval_samples_per_second": 1.064, | |
| "eval_steps_per_second": 0.266, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.1898679554673341, | |
| "grad_norm": 3.0305216312408447, | |
| "learning_rate": 4.688058634250984e-06, | |
| "loss": 0.3849, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.20712867869163717, | |
| "grad_norm": 3.079951524734497, | |
| "learning_rate": 4.643367894172328e-06, | |
| "loss": 0.3802, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.22438940191594028, | |
| "grad_norm": 2.7168169021606445, | |
| "learning_rate": 4.598677154093672e-06, | |
| "loss": 0.3887, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.24165012514024337, | |
| "grad_norm": 2.76423716545105, | |
| "learning_rate": 4.553986414015016e-06, | |
| "loss": 0.3825, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.2589108483645465, | |
| "grad_norm": 4.16721248626709, | |
| "learning_rate": 4.509295673936361e-06, | |
| "loss": 0.3819, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.2761715715888496, | |
| "grad_norm": 2.646681785583496, | |
| "learning_rate": 4.464604933857705e-06, | |
| "loss": 0.3813, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.2934322948131527, | |
| "grad_norm": 3.4927141666412354, | |
| "learning_rate": 4.419914193779049e-06, | |
| "loss": 0.3793, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.31069301803745575, | |
| "grad_norm": 2.364363193511963, | |
| "learning_rate": 4.375223453700393e-06, | |
| "loss": 0.3815, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.32795374126175886, | |
| "grad_norm": 2.7475292682647705, | |
| "learning_rate": 4.330532713621738e-06, | |
| "loss": 0.3652, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.34521446448606197, | |
| "grad_norm": 3.994381904602051, | |
| "learning_rate": 4.285841973543082e-06, | |
| "loss": 0.39, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.34521446448606197, | |
| "eval_gen_len": 53.06160558464224, | |
| "eval_loss": 0.5498749613761902, | |
| "eval_rouge1": 50.66, | |
| "eval_rouge2": 36.17, | |
| "eval_rougeL": 44.07, | |
| "eval_rougeLsum": 44.56, | |
| "eval_runtime": 5246.3152, | |
| "eval_samples_per_second": 1.092, | |
| "eval_steps_per_second": 0.273, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.3624751877103651, | |
| "grad_norm": 4.5150227546691895, | |
| "learning_rate": 4.241151233464427e-06, | |
| "loss": 0.4227, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.3797359109346682, | |
| "grad_norm": 2.6075778007507324, | |
| "learning_rate": 4.19646049338577e-06, | |
| "loss": 0.4255, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.39699663415897124, | |
| "grad_norm": 3.93216609954834, | |
| "learning_rate": 4.151769753307115e-06, | |
| "loss": 0.4192, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.41425735738327435, | |
| "grad_norm": 3.318143606185913, | |
| "learning_rate": 4.107079013228459e-06, | |
| "loss": 0.3984, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.43151808060757746, | |
| "grad_norm": 3.0835282802581787, | |
| "learning_rate": 4.062388273149804e-06, | |
| "loss": 0.4086, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.44877880383188057, | |
| "grad_norm": 2.782550811767578, | |
| "learning_rate": 4.017697533071148e-06, | |
| "loss": 0.4114, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.4660395270561837, | |
| "grad_norm": 3.2588839530944824, | |
| "learning_rate": 3.973006792992492e-06, | |
| "loss": 0.4304, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.48330025028048673, | |
| "grad_norm": 3.4788544178009033, | |
| "learning_rate": 3.928316052913836e-06, | |
| "loss": 0.4047, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.5005609735047899, | |
| "grad_norm": 3.0864784717559814, | |
| "learning_rate": 3.883625312835181e-06, | |
| "loss": 0.4185, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.517821696729093, | |
| "grad_norm": 2.8312442302703857, | |
| "learning_rate": 3.838934572756525e-06, | |
| "loss": 0.4325, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.517821696729093, | |
| "eval_gen_len": 54.41937172774869, | |
| "eval_loss": 0.5411620736122131, | |
| "eval_rouge1": 50.59, | |
| "eval_rouge2": 36.52, | |
| "eval_rougeL": 44.19, | |
| "eval_rougeLsum": 44.63, | |
| "eval_runtime": 5226.6165, | |
| "eval_samples_per_second": 1.096, | |
| "eval_steps_per_second": 0.274, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.535082419953396, | |
| "grad_norm": 3.31876540184021, | |
| "learning_rate": 3.7942438326778697e-06, | |
| "loss": 0.4191, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.5523431431776992, | |
| "grad_norm": 3.1453733444213867, | |
| "learning_rate": 3.7495530925992137e-06, | |
| "loss": 0.4591, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.5696038664020022, | |
| "grad_norm": 3.1156108379364014, | |
| "learning_rate": 3.7048623525205578e-06, | |
| "loss": 0.4243, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.5868645896263054, | |
| "grad_norm": 3.0627033710479736, | |
| "learning_rate": 3.6601716124419022e-06, | |
| "loss": 0.4518, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.6041253128506084, | |
| "grad_norm": 3.0280168056488037, | |
| "learning_rate": 3.6154808723632467e-06, | |
| "loss": 0.4467, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.6213860360749115, | |
| "grad_norm": 3.178391456604004, | |
| "learning_rate": 3.570790132284591e-06, | |
| "loss": 0.4411, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.6386467592992147, | |
| "grad_norm": 3.445444345474243, | |
| "learning_rate": 3.526099392205935e-06, | |
| "loss": 0.425, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.6559074825235177, | |
| "grad_norm": 2.4380524158477783, | |
| "learning_rate": 3.4814086521272793e-06, | |
| "loss": 0.4237, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.6731682057478209, | |
| "grad_norm": 3.591120958328247, | |
| "learning_rate": 3.4367179120486237e-06, | |
| "loss": 0.4465, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.6904289289721239, | |
| "grad_norm": 2.699303388595581, | |
| "learning_rate": 3.3920271719699682e-06, | |
| "loss": 0.4328, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.6904289289721239, | |
| "eval_gen_len": 54.16980802792321, | |
| "eval_loss": 0.5556456446647644, | |
| "eval_rouge1": 50.8, | |
| "eval_rouge2": 36.6, | |
| "eval_rougeL": 44.19, | |
| "eval_rougeLsum": 44.7, | |
| "eval_runtime": 5233.7113, | |
| "eval_samples_per_second": 1.095, | |
| "eval_steps_per_second": 0.274, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.707689652196427, | |
| "grad_norm": 5.292072772979736, | |
| "learning_rate": 3.3473364318913127e-06, | |
| "loss": 0.4216, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 0.7249503754207302, | |
| "grad_norm": 2.9521191120147705, | |
| "learning_rate": 3.3026456918126563e-06, | |
| "loss": 0.4332, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.7422110986450332, | |
| "grad_norm": 4.375521183013916, | |
| "learning_rate": 3.2579549517340008e-06, | |
| "loss": 0.4392, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 0.7594718218693364, | |
| "grad_norm": 3.5504395961761475, | |
| "learning_rate": 3.2132642116553453e-06, | |
| "loss": 0.432, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.7767325450936394, | |
| "grad_norm": 3.7240469455718994, | |
| "learning_rate": 3.1685734715766897e-06, | |
| "loss": 0.4278, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.7939932683179425, | |
| "grad_norm": 2.717268943786621, | |
| "learning_rate": 3.123882731498034e-06, | |
| "loss": 0.4145, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.8112539915422456, | |
| "grad_norm": 2.7192165851593018, | |
| "learning_rate": 3.079191991419378e-06, | |
| "loss": 0.4454, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 0.8285147147665487, | |
| "grad_norm": 4.111413955688477, | |
| "learning_rate": 3.0345012513407223e-06, | |
| "loss": 0.4188, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.8457754379908519, | |
| "grad_norm": 3.396127223968506, | |
| "learning_rate": 2.9898105112620668e-06, | |
| "loss": 0.4349, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 0.8630361612151549, | |
| "grad_norm": 2.503493309020996, | |
| "learning_rate": 2.9451197711834112e-06, | |
| "loss": 0.4133, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.8630361612151549, | |
| "eval_gen_len": 54.88080279232112, | |
| "eval_loss": 0.5358440279960632, | |
| "eval_rouge1": 50.67, | |
| "eval_rouge2": 36.36, | |
| "eval_rougeL": 44.02, | |
| "eval_rougeLsum": 44.56, | |
| "eval_runtime": 5344.428, | |
| "eval_samples_per_second": 1.072, | |
| "eval_steps_per_second": 0.268, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.880296884439458, | |
| "grad_norm": 2.877305746078491, | |
| "learning_rate": 2.9004290311047557e-06, | |
| "loss": 0.4369, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 0.8975576076637611, | |
| "grad_norm": 2.5334177017211914, | |
| "learning_rate": 2.8557382910260993e-06, | |
| "loss": 0.4371, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.9148183308880642, | |
| "grad_norm": 2.780935049057007, | |
| "learning_rate": 2.811047550947444e-06, | |
| "loss": 0.3965, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 0.9320790541123674, | |
| "grad_norm": 3.019552707672119, | |
| "learning_rate": 2.7663568108687883e-06, | |
| "loss": 0.4191, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.9493397773366704, | |
| "grad_norm": 3.7161452770233154, | |
| "learning_rate": 2.7216660707901327e-06, | |
| "loss": 0.4164, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 0.9666005005609735, | |
| "grad_norm": 2.9958629608154297, | |
| "learning_rate": 2.6769753307114764e-06, | |
| "loss": 0.4069, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.9838612237852766, | |
| "grad_norm": 2.9618115425109863, | |
| "learning_rate": 2.632284590632821e-06, | |
| "loss": 0.4302, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 1.0010356433934582, | |
| "grad_norm": 2.9072768688201904, | |
| "learning_rate": 2.5875938505541653e-06, | |
| "loss": 0.426, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 1.0182963666177614, | |
| "grad_norm": 3.2817041873931885, | |
| "learning_rate": 2.5429031104755098e-06, | |
| "loss": 0.3912, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 1.0355570898420643, | |
| "grad_norm": 2.7742252349853516, | |
| "learning_rate": 2.498212370396854e-06, | |
| "loss": 0.3576, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.0355570898420643, | |
| "eval_gen_len": 53.4542757417103, | |
| "eval_loss": 0.5370803475379944, | |
| "eval_rouge1": 51.14, | |
| "eval_rouge2": 36.78, | |
| "eval_rougeL": 44.59, | |
| "eval_rougeLsum": 45.09, | |
| "eval_runtime": 5216.1975, | |
| "eval_samples_per_second": 1.099, | |
| "eval_steps_per_second": 0.275, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.0528178130663675, | |
| "grad_norm": 2.5936224460601807, | |
| "learning_rate": 2.4535216303181983e-06, | |
| "loss": 0.3795, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 1.0700785362906706, | |
| "grad_norm": 2.727391481399536, | |
| "learning_rate": 2.4088308902395428e-06, | |
| "loss": 0.3797, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 1.0873392595149736, | |
| "grad_norm": 2.1693854331970215, | |
| "learning_rate": 2.364140150160887e-06, | |
| "loss": 0.3809, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 1.1045999827392767, | |
| "grad_norm": 3.9267098903656006, | |
| "learning_rate": 2.3194494100822313e-06, | |
| "loss": 0.3816, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 1.12186070596358, | |
| "grad_norm": 3.905186176300049, | |
| "learning_rate": 2.2747586700035753e-06, | |
| "loss": 0.3852, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 1.139121429187883, | |
| "grad_norm": 3.1914596557617188, | |
| "learning_rate": 2.23006792992492e-06, | |
| "loss": 0.3837, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 1.156382152412186, | |
| "grad_norm": 3.2150516510009766, | |
| "learning_rate": 2.185377189846264e-06, | |
| "loss": 0.3916, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 1.1736428756364892, | |
| "grad_norm": 3.4676005840301514, | |
| "learning_rate": 2.1406864497676083e-06, | |
| "loss": 0.3889, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 1.1909035988607923, | |
| "grad_norm": 3.015994071960449, | |
| "learning_rate": 2.095995709688953e-06, | |
| "loss": 0.3901, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 1.2081643220850953, | |
| "grad_norm": 3.504163980484009, | |
| "learning_rate": 2.051304969610297e-06, | |
| "loss": 0.3878, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.2081643220850953, | |
| "eval_gen_len": 54.42425828970332, | |
| "eval_loss": 0.5358798503875732, | |
| "eval_rouge1": 50.77, | |
| "eval_rouge2": 36.52, | |
| "eval_rougeL": 44.17, | |
| "eval_rougeLsum": 44.73, | |
| "eval_runtime": 5360.6563, | |
| "eval_samples_per_second": 1.069, | |
| "eval_steps_per_second": 0.267, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.2254250453093984, | |
| "grad_norm": 2.9530227184295654, | |
| "learning_rate": 2.0066142295316413e-06, | |
| "loss": 0.4127, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 1.2426857685337016, | |
| "grad_norm": 2.9822258949279785, | |
| "learning_rate": 1.9619234894529854e-06, | |
| "loss": 0.3785, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 1.2599464917580048, | |
| "grad_norm": 3.8967037200927734, | |
| "learning_rate": 1.91723274937433e-06, | |
| "loss": 0.4015, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 1.2772072149823077, | |
| "grad_norm": 2.652034044265747, | |
| "learning_rate": 1.872542009295674e-06, | |
| "loss": 0.3962, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 1.2944679382066109, | |
| "grad_norm": 2.3683066368103027, | |
| "learning_rate": 1.8278512692170184e-06, | |
| "loss": 0.3942, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 1.311728661430914, | |
| "grad_norm": 2.787900447845459, | |
| "learning_rate": 1.7831605291383628e-06, | |
| "loss": 0.3902, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 1.328989384655217, | |
| "grad_norm": 2.8084681034088135, | |
| "learning_rate": 1.7384697890597069e-06, | |
| "loss": 0.3971, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 1.3462501078795202, | |
| "grad_norm": 3.2413413524627686, | |
| "learning_rate": 1.6937790489810514e-06, | |
| "loss": 0.396, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 1.3635108311038233, | |
| "grad_norm": 2.3999781608581543, | |
| "learning_rate": 1.6490883089023956e-06, | |
| "loss": 0.3836, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 1.3807715543281263, | |
| "grad_norm": 3.1420865058898926, | |
| "learning_rate": 1.6043975688237399e-06, | |
| "loss": 0.3757, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.3807715543281263, | |
| "eval_gen_len": 54.231239092495635, | |
| "eval_loss": 0.5294080376625061, | |
| "eval_rouge1": 50.76, | |
| "eval_rouge2": 36.73, | |
| "eval_rougeL": 44.34, | |
| "eval_rougeLsum": 44.9, | |
| "eval_runtime": 5340.6521, | |
| "eval_samples_per_second": 1.073, | |
| "eval_steps_per_second": 0.268, | |
| "step": 4000 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 5794, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 2 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.373273785100206e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |