{ "best_metric": null, "best_model_checkpoint": null, "epoch": 3.7364014353249417, "eval_steps": 200, "global_step": 32800, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.02, "grad_norm": 0.1643640249967575, "learning_rate": 0.0001988891104338166, "loss": 1.7673, "step": 200 }, { "epoch": 0.02, "eval_bertscore": 0.7312520742416382, "eval_loss": 1.7944419384002686, "eval_rouge1": 0.645726048132668, "eval_rouge2": 0.342840307585653, "eval_rougeL": 0.5174784271125388, "eval_rougeLsum": 0.6359911842715976, "eval_runtime": 67.7968, "eval_samples_per_second": 0.147, "eval_steps_per_second": 0.074, "step": 200 }, { "epoch": 0.05, "grad_norm": 0.17238478362560272, "learning_rate": 0.00019774973651978238, "loss": 1.6985, "step": 400 }, { "epoch": 0.05, "eval_bertscore": 0.733666718006134, "eval_loss": 1.7791178226470947, "eval_rouge1": 0.6540909153028596, "eval_rouge2": 0.3548819059818129, "eval_rougeL": 0.527257232694246, "eval_rougeLsum": 0.6442799950994005, "eval_runtime": 15.1267, "eval_samples_per_second": 0.661, "eval_steps_per_second": 0.331, "step": 400 }, { "epoch": 0.07, "grad_norm": 0.19368696212768555, "learning_rate": 0.00019661036260574814, "loss": 1.6962, "step": 600 }, { "epoch": 0.07, "eval_bertscore": 0.7339462041854858, "eval_loss": 1.7609882354736328, "eval_rouge1": 0.6384337329686338, "eval_rouge2": 0.3415514270662107, "eval_rougeL": 0.51206080148464, "eval_rougeLsum": 0.6261968614666548, "eval_runtime": 15.2068, "eval_samples_per_second": 0.658, "eval_steps_per_second": 0.329, "step": 600 }, { "epoch": 0.09, "grad_norm": 0.18629203736782074, "learning_rate": 0.00019547098869171392, "loss": 1.6825, "step": 800 }, { "epoch": 0.09, "eval_bertscore": 0.7363594174385071, "eval_loss": 1.7610784769058228, "eval_rouge1": 0.6461624591922237, "eval_rouge2": 0.3477371388439609, "eval_rougeL": 0.5187429174752844, "eval_rougeLsum": 0.6361089823008282, "eval_runtime": 15.173, "eval_samples_per_second": 0.659, "eval_steps_per_second": 0.33, "step": 800 }, { "epoch": 0.11, "grad_norm": 0.1799013316631317, "learning_rate": 0.00019433161477767967, "loss": 1.6848, "step": 1000 }, { "epoch": 0.11, "eval_bertscore": 0.7334067225456238, "eval_loss": 1.7576347589492798, "eval_rouge1": 0.6345119236349537, "eval_rouge2": 0.3422519149071803, "eval_rougeL": 0.5111983101326238, "eval_rougeLsum": 0.6244653120436832, "eval_runtime": 15.2847, "eval_samples_per_second": 0.654, "eval_steps_per_second": 0.327, "step": 1000 }, { "epoch": 0.14, "grad_norm": 0.22036150097846985, "learning_rate": 0.00019319224086364545, "loss": 1.6714, "step": 1200 }, { "epoch": 0.14, "eval_bertscore": 0.7323788404464722, "eval_loss": 1.7521806955337524, "eval_rouge1": 0.6452540184557478, "eval_rouge2": 0.3465145726476423, "eval_rougeL": 0.516711757588783, "eval_rougeLsum": 0.6341049885677059, "eval_runtime": 15.1247, "eval_samples_per_second": 0.661, "eval_steps_per_second": 0.331, "step": 1200 }, { "epoch": 0.16, "grad_norm": 0.21381086111068726, "learning_rate": 0.0001920528669496112, "loss": 1.6669, "step": 1400 }, { "epoch": 0.16, "eval_bertscore": 0.7313202619552612, "eval_loss": 1.7520482540130615, "eval_rouge1": 0.6397526546254797, "eval_rouge2": 0.3452671288110514, "eval_rougeL": 0.5176580626678706, "eval_rougeLsum": 0.6296746647539768, "eval_runtime": 15.183, "eval_samples_per_second": 0.659, "eval_steps_per_second": 0.329, "step": 1400 }, { "epoch": 0.18, "grad_norm": 0.20332874357700348, "learning_rate": 0.00019091349303557696, "loss": 1.671, "step": 1600 }, { "epoch": 0.18, "eval_bertscore": 0.7349230647087097, "eval_loss": 1.7473630905151367, "eval_rouge1": 0.637439872504459, "eval_rouge2": 0.34307164454056094, "eval_rougeL": 0.5129717676228565, "eval_rougeLsum": 0.6272190896182391, "eval_runtime": 15.5672, "eval_samples_per_second": 0.642, "eval_steps_per_second": 0.321, "step": 1600 }, { "epoch": 0.21, "grad_norm": 0.2025599479675293, "learning_rate": 0.00018977411912154274, "loss": 1.6721, "step": 1800 }, { "epoch": 0.21, "eval_bertscore": 0.7357184290885925, "eval_loss": 1.7516342401504517, "eval_rouge1": 0.6387615819926658, "eval_rouge2": 0.34366787517105574, "eval_rougeL": 0.5129026911770751, "eval_rougeLsum": 0.6289314118258257, "eval_runtime": 15.9574, "eval_samples_per_second": 0.627, "eval_steps_per_second": 0.313, "step": 1800 }, { "epoch": 0.23, "grad_norm": 0.20457112789154053, "learning_rate": 0.0001886347452075085, "loss": 1.671, "step": 2000 }, { "epoch": 0.23, "eval_bertscore": 0.733718752861023, "eval_loss": 1.7501707077026367, "eval_rouge1": 0.6346207681220664, "eval_rouge2": 0.33748369437614106, "eval_rougeL": 0.5085159047705141, "eval_rougeLsum": 0.6239953154441167, "eval_runtime": 15.0863, "eval_samples_per_second": 0.663, "eval_steps_per_second": 0.331, "step": 2000 }, { "epoch": 0.25, "grad_norm": 0.22552740573883057, "learning_rate": 0.00018749537129347424, "loss": 1.6496, "step": 2200 }, { "epoch": 0.25, "eval_bertscore": 0.7368552684783936, "eval_loss": 1.7437107563018799, "eval_rouge1": 0.6490756387878311, "eval_rouge2": 0.3448817738175175, "eval_rougeL": 0.5235187045706321, "eval_rougeLsum": 0.6377780857890332, "eval_runtime": 15.07, "eval_samples_per_second": 0.664, "eval_steps_per_second": 0.332, "step": 2200 }, { "epoch": 0.27, "grad_norm": 0.22573673725128174, "learning_rate": 0.00018635599737944, "loss": 1.6629, "step": 2400 }, { "epoch": 0.27, "eval_bertscore": 0.7314499616622925, "eval_loss": 1.7462828159332275, "eval_rouge1": 0.6511482369678803, "eval_rouge2": 0.34632544827771805, "eval_rougeL": 0.5212417191003778, "eval_rougeLsum": 0.6415391907940229, "eval_runtime": 15.2078, "eval_samples_per_second": 0.658, "eval_steps_per_second": 0.329, "step": 2400 }, { "epoch": 0.3, "grad_norm": 0.26426687836647034, "learning_rate": 0.00018521662346540575, "loss": 1.6644, "step": 2600 }, { "epoch": 0.3, "eval_bertscore": 0.7363359928131104, "eval_loss": 1.7505037784576416, "eval_rouge1": 0.6498296552335481, "eval_rouge2": 0.34873833589761183, "eval_rougeL": 0.5194028620820592, "eval_rougeLsum": 0.6404603087578984, "eval_runtime": 14.8403, "eval_samples_per_second": 0.674, "eval_steps_per_second": 0.337, "step": 2600 }, { "epoch": 0.32, "grad_norm": 0.20142091810703278, "learning_rate": 0.00018407724955137153, "loss": 1.6535, "step": 2800 }, { "epoch": 0.32, "eval_bertscore": 0.7304679155349731, "eval_loss": 1.7511039972305298, "eval_rouge1": 0.6475130585388738, "eval_rouge2": 0.34648331046897884, "eval_rougeL": 0.5218042284020985, "eval_rougeLsum": 0.6382749834402862, "eval_runtime": 15.0162, "eval_samples_per_second": 0.666, "eval_steps_per_second": 0.333, "step": 2800 }, { "epoch": 0.34, "grad_norm": 0.23283220827579498, "learning_rate": 0.00018293787563733728, "loss": 1.6477, "step": 3000 }, { "epoch": 0.34, "eval_bertscore": 0.7327049374580383, "eval_loss": 1.7461665868759155, "eval_rouge1": 0.6309349586871908, "eval_rouge2": 0.3387882478990309, "eval_rougeL": 0.5042059192403674, "eval_rougeLsum": 0.6210432469674847, "eval_runtime": 15.463, "eval_samples_per_second": 0.647, "eval_steps_per_second": 0.323, "step": 3000 }, { "epoch": 0.36, "grad_norm": 0.21316750347614288, "learning_rate": 0.00018179850172330306, "loss": 1.6614, "step": 3200 }, { "epoch": 0.36, "eval_bertscore": 0.7314620018005371, "eval_loss": 1.7468239068984985, "eval_rouge1": 0.6480904534152265, "eval_rouge2": 0.3479530168963481, "eval_rougeL": 0.5193148273848067, "eval_rougeLsum": 0.6366010767207634, "eval_runtime": 15.0381, "eval_samples_per_second": 0.665, "eval_steps_per_second": 0.332, "step": 3200 }, { "epoch": 0.39, "grad_norm": 0.26080408692359924, "learning_rate": 0.00018065912780926882, "loss": 1.6591, "step": 3400 }, { "epoch": 0.39, "eval_bertscore": 0.7327477335929871, "eval_loss": 1.7442594766616821, "eval_rouge1": 0.6424613378037144, "eval_rouge2": 0.34731770322974903, "eval_rougeL": 0.5160705879794565, "eval_rougeLsum": 0.6327006420281607, "eval_runtime": 15.5373, "eval_samples_per_second": 0.644, "eval_steps_per_second": 0.322, "step": 3400 }, { "epoch": 0.41, "grad_norm": 0.23274216055870056, "learning_rate": 0.0001795197538952346, "loss": 1.6613, "step": 3600 }, { "epoch": 0.41, "eval_bertscore": 0.736956000328064, "eval_loss": 1.7429373264312744, "eval_rouge1": 0.6514574160666677, "eval_rouge2": 0.3556199242231646, "eval_rougeL": 0.5249726237675663, "eval_rougeLsum": 0.6406261097623661, "eval_runtime": 14.9415, "eval_samples_per_second": 0.669, "eval_steps_per_second": 0.335, "step": 3600 }, { "epoch": 0.43, "grad_norm": 0.23616766929626465, "learning_rate": 0.00017838037998120035, "loss": 1.6479, "step": 3800 }, { "epoch": 0.43, "eval_bertscore": 0.7349627614021301, "eval_loss": 1.7420669794082642, "eval_rouge1": 0.655851684949526, "eval_rouge2": 0.35254590691865084, "eval_rougeL": 0.5248980956621441, "eval_rougeLsum": 0.6449637270581419, "eval_runtime": 15.4178, "eval_samples_per_second": 0.649, "eval_steps_per_second": 0.324, "step": 3800 }, { "epoch": 0.46, "grad_norm": 0.23260319232940674, "learning_rate": 0.0001772410060671661, "loss": 1.6569, "step": 4000 }, { "epoch": 0.46, "eval_bertscore": 0.7332885265350342, "eval_loss": 1.7401313781738281, "eval_rouge1": 0.6669483634140105, "eval_rouge2": 0.35873988835161297, "eval_rougeL": 0.5343868725007427, "eval_rougeLsum": 0.6555353134690931, "eval_runtime": 15.0822, "eval_samples_per_second": 0.663, "eval_steps_per_second": 0.332, "step": 4000 }, { "epoch": 0.48, "grad_norm": 0.2366473525762558, "learning_rate": 0.00017610163215313186, "loss": 1.6599, "step": 4200 }, { "epoch": 0.48, "eval_bertscore": 0.7335314750671387, "eval_loss": 1.7385823726654053, "eval_rouge1": 0.6559297063578133, "eval_rouge2": 0.35483499789990636, "eval_rougeL": 0.5297939800986089, "eval_rougeLsum": 0.6454544372491222, "eval_runtime": 15.1029, "eval_samples_per_second": 0.662, "eval_steps_per_second": 0.331, "step": 4200 }, { "epoch": 0.5, "grad_norm": 0.20628753304481506, "learning_rate": 0.0001749622582390976, "loss": 1.6454, "step": 4400 }, { "epoch": 0.5, "eval_bertscore": 0.7342795133590698, "eval_loss": 1.7422058582305908, "eval_rouge1": 0.660746519614568, "eval_rouge2": 0.3633965895561597, "eval_rougeL": 0.5369036980876734, "eval_rougeLsum": 0.650338328328998, "eval_runtime": 15.4434, "eval_samples_per_second": 0.648, "eval_steps_per_second": 0.324, "step": 4400 }, { "epoch": 0.52, "grad_norm": 0.2239149957895279, "learning_rate": 0.0001738228843250634, "loss": 1.6594, "step": 4600 }, { "epoch": 0.52, "eval_bertscore": 0.7313543558120728, "eval_loss": 1.740854263305664, "eval_rouge1": 0.6591645132619427, "eval_rouge2": 0.35766117432431743, "eval_rougeL": 0.532710255034635, "eval_rougeLsum": 0.6479428185884644, "eval_runtime": 14.9436, "eval_samples_per_second": 0.669, "eval_steps_per_second": 0.335, "step": 4600 }, { "epoch": 0.55, "grad_norm": 0.24808338284492493, "learning_rate": 0.00017268351041102914, "loss": 1.6604, "step": 4800 }, { "epoch": 0.55, "eval_bertscore": 0.7333321571350098, "eval_loss": 1.7385585308074951, "eval_rouge1": 0.6532115808232871, "eval_rouge2": 0.35333788022501567, "eval_rougeL": 0.5284071547874328, "eval_rougeLsum": 0.6410472452797623, "eval_runtime": 15.0277, "eval_samples_per_second": 0.665, "eval_steps_per_second": 0.333, "step": 4800 }, { "epoch": 0.57, "grad_norm": 0.2555364966392517, "learning_rate": 0.0001715441364969949, "loss": 1.6493, "step": 5000 }, { "epoch": 0.57, "eval_bertscore": 0.7318152189254761, "eval_loss": 1.7357494831085205, "eval_rouge1": 0.6476755890502586, "eval_rouge2": 0.35312778275949164, "eval_rougeL": 0.5227601228049905, "eval_rougeLsum": 0.6371331138372852, "eval_runtime": 14.8807, "eval_samples_per_second": 0.672, "eval_steps_per_second": 0.336, "step": 5000 }, { "epoch": 0.59, "grad_norm": 0.21518155932426453, "learning_rate": 0.00017040476258296068, "loss": 1.644, "step": 5200 }, { "epoch": 0.59, "eval_bertscore": 0.734805703163147, "eval_loss": 1.74032723903656, "eval_rouge1": 0.6476813733451636, "eval_rouge2": 0.3509259728617576, "eval_rougeL": 0.5221334872800274, "eval_rougeLsum": 0.636892384667733, "eval_runtime": 15.1271, "eval_samples_per_second": 0.661, "eval_steps_per_second": 0.331, "step": 5200 }, { "epoch": 0.62, "grad_norm": 0.26086658239364624, "learning_rate": 0.00016926538866892643, "loss": 1.6449, "step": 5400 }, { "epoch": 0.62, "eval_bertscore": 0.7339995503425598, "eval_loss": 1.7338205575942993, "eval_rouge1": 0.6416889902864902, "eval_rouge2": 0.3479045880347737, "eval_rougeL": 0.5160577838468976, "eval_rougeLsum": 0.6317983411796093, "eval_runtime": 14.9992, "eval_samples_per_second": 0.667, "eval_steps_per_second": 0.333, "step": 5400 }, { "epoch": 0.64, "grad_norm": 0.25449469685554504, "learning_rate": 0.0001681260147548922, "loss": 1.6299, "step": 5600 }, { "epoch": 0.64, "eval_bertscore": 0.7306328415870667, "eval_loss": 1.7369228601455688, "eval_rouge1": 0.6390760905985684, "eval_rouge2": 0.3409328272828699, "eval_rougeL": 0.5111832543685331, "eval_rougeLsum": 0.6285753423407665, "eval_runtime": 15.483, "eval_samples_per_second": 0.646, "eval_steps_per_second": 0.323, "step": 5600 }, { "epoch": 0.66, "grad_norm": 0.24706102907657623, "learning_rate": 0.00016698664084085796, "loss": 1.6374, "step": 5800 }, { "epoch": 0.66, "eval_bertscore": 0.732075572013855, "eval_loss": 1.7343876361846924, "eval_rouge1": 0.6378821977913272, "eval_rouge2": 0.34619427775171585, "eval_rougeL": 0.5120186953041237, "eval_rougeLsum": 0.6284056323839109, "eval_runtime": 15.7341, "eval_samples_per_second": 0.636, "eval_steps_per_second": 0.318, "step": 5800 }, { "epoch": 0.68, "grad_norm": 0.24373260140419006, "learning_rate": 0.00016584726692682372, "loss": 1.6427, "step": 6000 }, { "epoch": 0.68, "eval_bertscore": 0.7350374460220337, "eval_loss": 1.729591965675354, "eval_rouge1": 0.6516545226356616, "eval_rouge2": 0.35485762033878543, "eval_rougeL": 0.5249054193354852, "eval_rougeLsum": 0.6411016821651583, "eval_runtime": 15.5199, "eval_samples_per_second": 0.644, "eval_steps_per_second": 0.322, "step": 6000 }, { "epoch": 0.71, "grad_norm": 0.24616578221321106, "learning_rate": 0.0001647078930127895, "loss": 1.6296, "step": 6200 }, { "epoch": 0.71, "eval_bertscore": 0.7335461378097534, "eval_loss": 1.7302274703979492, "eval_rouge1": 0.6531411706717427, "eval_rouge2": 0.35003053174601517, "eval_rougeL": 0.5212483686089053, "eval_rougeLsum": 0.6438454124825417, "eval_runtime": 15.3058, "eval_samples_per_second": 0.653, "eval_steps_per_second": 0.327, "step": 6200 }, { "epoch": 0.73, "grad_norm": 0.24500492215156555, "learning_rate": 0.00016356851909875522, "loss": 1.6251, "step": 6400 }, { "epoch": 0.73, "eval_bertscore": 0.7347471714019775, "eval_loss": 1.7292228937149048, "eval_rouge1": 0.6565322485502556, "eval_rouge2": 0.35887540291607073, "eval_rougeL": 0.5284326132878907, "eval_rougeLsum": 0.6469750895866724, "eval_runtime": 14.9708, "eval_samples_per_second": 0.668, "eval_steps_per_second": 0.334, "step": 6400 }, { "epoch": 0.75, "grad_norm": 0.26575228571891785, "learning_rate": 0.000162429145184721, "loss": 1.6389, "step": 6600 }, { "epoch": 0.75, "eval_bertscore": 0.7319897413253784, "eval_loss": 1.7287580966949463, "eval_rouge1": 0.6458608801881298, "eval_rouge2": 0.3503480901452204, "eval_rougeL": 0.519626708150005, "eval_rougeLsum": 0.6362405734928169, "eval_runtime": 15.3509, "eval_samples_per_second": 0.651, "eval_steps_per_second": 0.326, "step": 6600 }, { "epoch": 0.77, "grad_norm": 0.27144965529441833, "learning_rate": 0.00016128977127068676, "loss": 1.6476, "step": 6800 }, { "epoch": 0.77, "eval_bertscore": 0.7392772436141968, "eval_loss": 1.7257907390594482, "eval_rouge1": 0.6543238897579965, "eval_rouge2": 0.3606726049451984, "eval_rougeL": 0.5317585887753791, "eval_rougeLsum": 0.6452028420624081, "eval_runtime": 15.0268, "eval_samples_per_second": 0.665, "eval_steps_per_second": 0.333, "step": 6800 }, { "epoch": 0.8, "grad_norm": 0.2579711079597473, "learning_rate": 0.00016015039735665254, "loss": 1.6316, "step": 7000 }, { "epoch": 0.8, "eval_bertscore": 0.7375612854957581, "eval_loss": 1.7296981811523438, "eval_rouge1": 0.658906725408624, "eval_rouge2": 0.35825094165644866, "eval_rougeL": 0.5323299193377959, "eval_rougeLsum": 0.6500364347290426, "eval_runtime": 14.9244, "eval_samples_per_second": 0.67, "eval_steps_per_second": 0.335, "step": 7000 }, { "epoch": 0.82, "grad_norm": 0.2589207589626312, "learning_rate": 0.0001590110234426183, "loss": 1.6432, "step": 7200 }, { "epoch": 0.82, "eval_bertscore": 0.735145092010498, "eval_loss": 1.72720205783844, "eval_rouge1": 0.6678646250245518, "eval_rouge2": 0.36332843150846983, "eval_rougeL": 0.537576430733886, "eval_rougeLsum": 0.6579789388660506, "eval_runtime": 14.9067, "eval_samples_per_second": 0.671, "eval_steps_per_second": 0.335, "step": 7200 }, { "epoch": 0.84, "grad_norm": 0.26652559638023376, "learning_rate": 0.00015787164952858404, "loss": 1.6488, "step": 7400 }, { "epoch": 0.84, "eval_bertscore": 0.7320755124092102, "eval_loss": 1.7282931804656982, "eval_rouge1": 0.6325633297780734, "eval_rouge2": 0.34505856555703185, "eval_rougeL": 0.5100006743383693, "eval_rougeLsum": 0.6230385336341938, "eval_runtime": 14.9075, "eval_samples_per_second": 0.671, "eval_steps_per_second": 0.335, "step": 7400 }, { "epoch": 0.87, "grad_norm": 0.27353721857070923, "learning_rate": 0.00015673227561454982, "loss": 1.6486, "step": 7600 }, { "epoch": 0.87, "eval_bertscore": 0.7367390394210815, "eval_loss": 1.7290785312652588, "eval_rouge1": 0.639487116874423, "eval_rouge2": 0.3466574229736927, "eval_rougeL": 0.515038120249177, "eval_rougeLsum": 0.6301157215372983, "eval_runtime": 15.0876, "eval_samples_per_second": 0.663, "eval_steps_per_second": 0.331, "step": 7600 }, { "epoch": 0.89, "grad_norm": 0.24777938425540924, "learning_rate": 0.00015559290170051558, "loss": 1.6271, "step": 7800 }, { "epoch": 0.89, "eval_bertscore": 0.735866904258728, "eval_loss": 1.7264015674591064, "eval_rouge1": 0.64939597901302, "eval_rouge2": 0.3554282813944538, "eval_rougeL": 0.5247953329477759, "eval_rougeLsum": 0.6405524812915908, "eval_runtime": 14.8892, "eval_samples_per_second": 0.672, "eval_steps_per_second": 0.336, "step": 7800 }, { "epoch": 0.91, "grad_norm": 0.2703794538974762, "learning_rate": 0.00015445352778648136, "loss": 1.6415, "step": 8000 }, { "epoch": 0.91, "eval_bertscore": 0.7325771450996399, "eval_loss": 1.7271970510482788, "eval_rouge1": 0.6659432894288253, "eval_rouge2": 0.35962933912652617, "eval_rougeL": 0.5385420432813512, "eval_rougeLsum": 0.6557027031484046, "eval_runtime": 14.8319, "eval_samples_per_second": 0.674, "eval_steps_per_second": 0.337, "step": 8000 }, { "epoch": 0.93, "grad_norm": 0.28753793239593506, "learning_rate": 0.0001533141538724471, "loss": 1.6239, "step": 8200 }, { "epoch": 0.93, "eval_bertscore": 0.7350013852119446, "eval_loss": 1.7266199588775635, "eval_rouge1": 0.6549282561414593, "eval_rouge2": 0.35694530595734475, "eval_rougeL": 0.5301601006964574, "eval_rougeLsum": 0.6441779306137909, "eval_runtime": 14.9005, "eval_samples_per_second": 0.671, "eval_steps_per_second": 0.336, "step": 8200 }, { "epoch": 0.96, "grad_norm": 0.23870150744915009, "learning_rate": 0.00015217477995841286, "loss": 1.6293, "step": 8400 }, { "epoch": 0.96, "eval_bertscore": 0.7271261811256409, "eval_loss": 1.7256368398666382, "eval_rouge1": 0.6515513829901936, "eval_rouge2": 0.35217616104918836, "eval_rougeL": 0.5236553509227138, "eval_rougeLsum": 0.6411473505324752, "eval_runtime": 14.9938, "eval_samples_per_second": 0.667, "eval_steps_per_second": 0.333, "step": 8400 }, { "epoch": 0.98, "grad_norm": 0.28276997804641724, "learning_rate": 0.00015103540604437861, "loss": 1.6242, "step": 8600 }, { "epoch": 0.98, "eval_bertscore": 0.7347334027290344, "eval_loss": 1.717627763748169, "eval_rouge1": 0.6350112495847634, "eval_rouge2": 0.3477570751550898, "eval_rougeL": 0.5146616989899861, "eval_rougeLsum": 0.6246669376525157, "eval_runtime": 15.7032, "eval_samples_per_second": 0.637, "eval_steps_per_second": 0.318, "step": 8600 }, { "epoch": 1.0, "grad_norm": 0.24915842711925507, "learning_rate": 0.00014989603213034437, "loss": 1.6245, "step": 8800 }, { "epoch": 1.0, "eval_bertscore": 0.7313701510429382, "eval_loss": 1.7292964458465576, "eval_rouge1": 0.6479528105367669, "eval_rouge2": 0.35020983244262877, "eval_rougeL": 0.5200907337780047, "eval_rougeLsum": 0.6372896614836894, "eval_runtime": 15.0043, "eval_samples_per_second": 0.666, "eval_steps_per_second": 0.333, "step": 8800 }, { "epoch": 1.03, "grad_norm": 0.24036027491092682, "learning_rate": 0.00014875665821631015, "loss": 1.5364, "step": 9000 }, { "epoch": 1.03, "eval_bertscore": 0.7327737808227539, "eval_loss": 1.7339435815811157, "eval_rouge1": 0.6568524178922349, "eval_rouge2": 0.35560270713543163, "eval_rougeL": 0.5310443670833082, "eval_rougeLsum": 0.6480993679097387, "eval_runtime": 14.9303, "eval_samples_per_second": 0.67, "eval_steps_per_second": 0.335, "step": 9000 }, { "epoch": 1.05, "grad_norm": 0.2729027271270752, "learning_rate": 0.0001476172843022759, "loss": 1.5182, "step": 9200 }, { "epoch": 1.05, "eval_bertscore": 0.7334672212600708, "eval_loss": 1.739061713218689, "eval_rouge1": 0.6552962187824329, "eval_rouge2": 0.35210314124279196, "eval_rougeL": 0.5272039052368354, "eval_rougeLsum": 0.6437473533492806, "eval_runtime": 15.5418, "eval_samples_per_second": 0.643, "eval_steps_per_second": 0.322, "step": 9200 }, { "epoch": 1.07, "grad_norm": 0.2909716069698334, "learning_rate": 0.00014647791038824168, "loss": 1.5276, "step": 9400 }, { "epoch": 1.07, "eval_bertscore": 0.7288902997970581, "eval_loss": 1.736944556236267, "eval_rouge1": 0.6533271685598301, "eval_rouge2": 0.35279315321532184, "eval_rougeL": 0.5262688234671329, "eval_rougeLsum": 0.6424084937151033, "eval_runtime": 15.1115, "eval_samples_per_second": 0.662, "eval_steps_per_second": 0.331, "step": 9400 }, { "epoch": 1.09, "grad_norm": 0.3035859763622284, "learning_rate": 0.00014533853647420743, "loss": 1.5445, "step": 9600 }, { "epoch": 1.09, "eval_bertscore": 0.7308284044265747, "eval_loss": 1.737762689590454, "eval_rouge1": 0.6619725777891359, "eval_rouge2": 0.3611963714506864, "eval_rougeL": 0.5363802967084452, "eval_rougeLsum": 0.6516690557971352, "eval_runtime": 14.9932, "eval_samples_per_second": 0.667, "eval_steps_per_second": 0.333, "step": 9600 }, { "epoch": 1.12, "grad_norm": 0.26574915647506714, "learning_rate": 0.0001441991625601732, "loss": 1.5342, "step": 9800 }, { "epoch": 1.12, "eval_bertscore": 0.7328712344169617, "eval_loss": 1.7393991947174072, "eval_rouge1": 0.6856504003396884, "eval_rouge2": 0.3761098841062477, "eval_rougeL": 0.555477293163325, "eval_rougeLsum": 0.6757574283262289, "eval_runtime": 14.8121, "eval_samples_per_second": 0.675, "eval_steps_per_second": 0.338, "step": 9800 }, { "epoch": 1.14, "grad_norm": 0.315468430519104, "learning_rate": 0.00014305978864613897, "loss": 1.543, "step": 10000 }, { "epoch": 1.14, "eval_bertscore": 0.7349387407302856, "eval_loss": 1.7352710962295532, "eval_rouge1": 0.6749953128982036, "eval_rouge2": 0.3720385250530084, "eval_rougeL": 0.5472261566474382, "eval_rougeLsum": 0.6657643539219252, "eval_runtime": 14.909, "eval_samples_per_second": 0.671, "eval_steps_per_second": 0.335, "step": 10000 }, { "epoch": 1.16, "grad_norm": 0.29815027117729187, "learning_rate": 0.00014192041473210472, "loss": 1.5547, "step": 10200 }, { "epoch": 1.16, "eval_bertscore": 0.7359883189201355, "eval_loss": 1.7269136905670166, "eval_rouge1": 0.6561141614088863, "eval_rouge2": 0.3606175666303814, "eval_rougeL": 0.5302270771032793, "eval_rougeLsum": 0.6446912079521883, "eval_runtime": 14.9527, "eval_samples_per_second": 0.669, "eval_steps_per_second": 0.334, "step": 10200 }, { "epoch": 1.18, "grad_norm": 0.3595702350139618, "learning_rate": 0.00014078104081807047, "loss": 1.5567, "step": 10400 }, { "epoch": 1.18, "eval_bertscore": 0.7328116297721863, "eval_loss": 1.7341644763946533, "eval_rouge1": 0.6420332714823549, "eval_rouge2": 0.35094864549032, "eval_rougeL": 0.5179556761398367, "eval_rougeLsum": 0.631987397226809, "eval_runtime": 15.1438, "eval_samples_per_second": 0.66, "eval_steps_per_second": 0.33, "step": 10400 }, { "epoch": 1.21, "grad_norm": 0.2718666195869446, "learning_rate": 0.00013964166690403623, "loss": 1.5408, "step": 10600 }, { "epoch": 1.21, "eval_bertscore": 0.7337731122970581, "eval_loss": 1.7330901622772217, "eval_rouge1": 0.661681342484687, "eval_rouge2": 0.3626833509973693, "eval_rougeL": 0.5329424447373774, "eval_rougeLsum": 0.6519750177144633, "eval_runtime": 14.8142, "eval_samples_per_second": 0.675, "eval_steps_per_second": 0.338, "step": 10600 }, { "epoch": 1.23, "grad_norm": 0.29183274507522583, "learning_rate": 0.00013850229299000198, "loss": 1.5422, "step": 10800 }, { "epoch": 1.23, "eval_bertscore": 0.7331051230430603, "eval_loss": 1.7297636270523071, "eval_rouge1": 0.6655497978238063, "eval_rouge2": 0.3614235788441926, "eval_rougeL": 0.5327210061667442, "eval_rougeLsum": 0.6548836840483913, "eval_runtime": 15.1359, "eval_samples_per_second": 0.661, "eval_steps_per_second": 0.33, "step": 10800 }, { "epoch": 1.25, "grad_norm": 0.30979740619659424, "learning_rate": 0.00013736291907596776, "loss": 1.5372, "step": 11000 }, { "epoch": 1.25, "eval_bertscore": 0.7312799692153931, "eval_loss": 1.732444167137146, "eval_rouge1": 0.6568292865033993, "eval_rouge2": 0.35876682221562006, "eval_rougeL": 0.5300878844981931, "eval_rougeLsum": 0.6461751645858989, "eval_runtime": 14.819, "eval_samples_per_second": 0.675, "eval_steps_per_second": 0.337, "step": 11000 }, { "epoch": 1.28, "grad_norm": 0.31343138217926025, "learning_rate": 0.0001362235451619335, "loss": 1.5301, "step": 11200 }, { "epoch": 1.28, "eval_bertscore": 0.7317885160446167, "eval_loss": 1.7358499765396118, "eval_rouge1": 0.6548673097943329, "eval_rouge2": 0.3609116081432997, "eval_rougeL": 0.5279887650752133, "eval_rougeLsum": 0.6466232329097188, "eval_runtime": 14.8259, "eval_samples_per_second": 0.674, "eval_steps_per_second": 0.337, "step": 11200 }, { "epoch": 1.3, "grad_norm": 0.36181533336639404, "learning_rate": 0.0001350841712478993, "loss": 1.5421, "step": 11400 }, { "epoch": 1.3, "eval_bertscore": 0.7316756248474121, "eval_loss": 1.7282969951629639, "eval_rouge1": 0.6551882964480251, "eval_rouge2": 0.3580708921400697, "eval_rougeL": 0.5255367305995147, "eval_rougeLsum": 0.6449192953008009, "eval_runtime": 14.8816, "eval_samples_per_second": 0.672, "eval_steps_per_second": 0.336, "step": 11400 }, { "epoch": 1.32, "grad_norm": 0.30600836873054504, "learning_rate": 0.00013394479733386505, "loss": 1.5538, "step": 11600 }, { "epoch": 1.32, "eval_bertscore": 0.7311854362487793, "eval_loss": 1.7313562631607056, "eval_rouge1": 0.6592751199424156, "eval_rouge2": 0.35802855072854206, "eval_rougeL": 0.5297288176377084, "eval_rougeLsum": 0.6489455314962717, "eval_runtime": 15.0693, "eval_samples_per_second": 0.664, "eval_steps_per_second": 0.332, "step": 11600 }, { "epoch": 1.34, "grad_norm": 0.29904893040657043, "learning_rate": 0.0001328054234198308, "loss": 1.5328, "step": 11800 }, { "epoch": 1.34, "eval_bertscore": 0.7312635183334351, "eval_loss": 1.7318429946899414, "eval_rouge1": 0.6577169369077195, "eval_rouge2": 0.3582474830918887, "eval_rougeL": 0.5314990647771975, "eval_rougeLsum": 0.6454785220479866, "eval_runtime": 15.0235, "eval_samples_per_second": 0.666, "eval_steps_per_second": 0.333, "step": 11800 }, { "epoch": 1.37, "grad_norm": 0.3025416433811188, "learning_rate": 0.00013166604950579658, "loss": 1.5349, "step": 12000 }, { "epoch": 1.37, "eval_bertscore": 0.7325812578201294, "eval_loss": 1.7309118509292603, "eval_rouge1": 0.6629133074951261, "eval_rouge2": 0.3678158453940578, "eval_rougeL": 0.5380936907276155, "eval_rougeLsum": 0.654883061928214, "eval_runtime": 14.7666, "eval_samples_per_second": 0.677, "eval_steps_per_second": 0.339, "step": 12000 }, { "epoch": 1.39, "grad_norm": 0.34982389211654663, "learning_rate": 0.00013052667559176233, "loss": 1.5513, "step": 12200 }, { "epoch": 1.39, "eval_bertscore": 0.7340582609176636, "eval_loss": 1.7363474369049072, "eval_rouge1": 0.6555817937418287, "eval_rouge2": 0.35630500078358396, "eval_rougeL": 0.5272412353478366, "eval_rougeLsum": 0.6445837479327643, "eval_runtime": 14.9664, "eval_samples_per_second": 0.668, "eval_steps_per_second": 0.334, "step": 12200 }, { "epoch": 1.41, "grad_norm": 0.35809043049812317, "learning_rate": 0.0001293873016777281, "loss": 1.5444, "step": 12400 }, { "epoch": 1.41, "eval_bertscore": 0.7334069013595581, "eval_loss": 1.7328729629516602, "eval_rouge1": 0.6617971237669364, "eval_rouge2": 0.35951260376512423, "eval_rougeL": 0.5345512305507059, "eval_rougeLsum": 0.648363531132752, "eval_runtime": 15.2146, "eval_samples_per_second": 0.657, "eval_steps_per_second": 0.329, "step": 12400 }, { "epoch": 1.44, "grad_norm": 0.2954196631908417, "learning_rate": 0.00012824792776369387, "loss": 1.5406, "step": 12600 }, { "epoch": 1.44, "eval_bertscore": 0.7321678400039673, "eval_loss": 1.7335160970687866, "eval_rouge1": 0.6573625593086756, "eval_rouge2": 0.36210525247389347, "eval_rougeL": 0.5379361120230158, "eval_rougeLsum": 0.6459787883452857, "eval_runtime": 14.8942, "eval_samples_per_second": 0.671, "eval_steps_per_second": 0.336, "step": 12600 }, { "epoch": 1.46, "grad_norm": 0.32190588116645813, "learning_rate": 0.00012710855384965962, "loss": 1.5491, "step": 12800 }, { "epoch": 1.46, "eval_bertscore": 0.7346011400222778, "eval_loss": 1.7364966869354248, "eval_rouge1": 0.6481210247390559, "eval_rouge2": 0.3521173896017687, "eval_rougeL": 0.5240500581372636, "eval_rougeLsum": 0.63706442433335, "eval_runtime": 14.923, "eval_samples_per_second": 0.67, "eval_steps_per_second": 0.335, "step": 12800 }, { "epoch": 1.48, "grad_norm": 0.33323267102241516, "learning_rate": 0.00012596917993562537, "loss": 1.5596, "step": 13000 }, { "epoch": 1.48, "eval_bertscore": 0.7331587076187134, "eval_loss": 1.7332260608673096, "eval_rouge1": 0.6561257401878793, "eval_rouge2": 0.3548063723792664, "eval_rougeL": 0.527807776001489, "eval_rougeLsum": 0.6451911907984706, "eval_runtime": 15.4703, "eval_samples_per_second": 0.646, "eval_steps_per_second": 0.323, "step": 13000 }, { "epoch": 1.5, "grad_norm": 0.3564057946205139, "learning_rate": 0.00012482980602159113, "loss": 1.5261, "step": 13200 }, { "epoch": 1.5, "eval_bertscore": 0.7306063771247864, "eval_loss": 1.7368810176849365, "eval_rouge1": 0.637722723890071, "eval_rouge2": 0.3455358728458236, "eval_rougeL": 0.5136372690435154, "eval_rougeLsum": 0.6273570573595115, "eval_runtime": 15.3533, "eval_samples_per_second": 0.651, "eval_steps_per_second": 0.326, "step": 13200 }, { "epoch": 1.53, "grad_norm": 0.29219934344291687, "learning_rate": 0.0001236904321075569, "loss": 1.519, "step": 13400 }, { "epoch": 1.53, "eval_bertscore": 0.7338696122169495, "eval_loss": 1.734724998474121, "eval_rouge1": 0.6442107446420164, "eval_rouge2": 0.3494748457109431, "eval_rougeL": 0.5207483892007314, "eval_rougeLsum": 0.632886404907802, "eval_runtime": 15.3077, "eval_samples_per_second": 0.653, "eval_steps_per_second": 0.327, "step": 13400 }, { "epoch": 1.55, "grad_norm": 0.34681758284568787, "learning_rate": 0.00012255105819352266, "loss": 1.5419, "step": 13600 }, { "epoch": 1.55, "eval_bertscore": 0.7350045442581177, "eval_loss": 1.7329858541488647, "eval_rouge1": 0.6606839869796519, "eval_rouge2": 0.362188561160822, "eval_rougeL": 0.5342033818317451, "eval_rougeLsum": 0.6493340000068861, "eval_runtime": 15.44, "eval_samples_per_second": 0.648, "eval_steps_per_second": 0.324, "step": 13600 }, { "epoch": 1.57, "grad_norm": 0.3043666481971741, "learning_rate": 0.00012141168427948844, "loss": 1.5402, "step": 13800 }, { "epoch": 1.57, "eval_bertscore": 0.7363221645355225, "eval_loss": 1.7308530807495117, "eval_rouge1": 0.6638252384356028, "eval_rouge2": 0.3643237697892826, "eval_rougeL": 0.5403775887381331, "eval_rougeLsum": 0.6537260000827279, "eval_runtime": 14.7668, "eval_samples_per_second": 0.677, "eval_steps_per_second": 0.339, "step": 13800 }, { "epoch": 1.59, "grad_norm": 0.4073585867881775, "learning_rate": 0.00012027231036545419, "loss": 1.5256, "step": 14000 }, { "epoch": 1.59, "eval_bertscore": 0.7310279607772827, "eval_loss": 1.7326784133911133, "eval_rouge1": 0.6609594314120198, "eval_rouge2": 0.3601530714440473, "eval_rougeL": 0.5344452687135626, "eval_rougeLsum": 0.6480936554342305, "eval_runtime": 14.8565, "eval_samples_per_second": 0.673, "eval_steps_per_second": 0.337, "step": 14000 }, { "epoch": 1.62, "grad_norm": 0.3211813271045685, "learning_rate": 0.00011913293645141995, "loss": 1.5366, "step": 14200 }, { "epoch": 1.62, "eval_bertscore": 0.7356667518615723, "eval_loss": 1.7280094623565674, "eval_rouge1": 0.6519353227375031, "eval_rouge2": 0.3587025716186173, "eval_rougeL": 0.5306356200586075, "eval_rougeLsum": 0.6408870347994059, "eval_runtime": 14.9264, "eval_samples_per_second": 0.67, "eval_steps_per_second": 0.335, "step": 14200 }, { "epoch": 1.64, "grad_norm": 0.32776832580566406, "learning_rate": 0.00011799356253738571, "loss": 1.5504, "step": 14400 }, { "epoch": 1.64, "eval_bertscore": 0.7331353425979614, "eval_loss": 1.7308950424194336, "eval_rouge1": 0.6627702292814652, "eval_rouge2": 0.36117793957379707, "eval_rougeL": 0.5369305446079228, "eval_rougeLsum": 0.6516924083980089, "eval_runtime": 16.0138, "eval_samples_per_second": 0.624, "eval_steps_per_second": 0.312, "step": 14400 }, { "epoch": 1.66, "grad_norm": 0.3209726810455322, "learning_rate": 0.00011685418862335147, "loss": 1.5473, "step": 14600 }, { "epoch": 1.66, "eval_bertscore": 0.732498824596405, "eval_loss": 1.7328402996063232, "eval_rouge1": 0.6482679740803596, "eval_rouge2": 0.3538726087405498, "eval_rougeL": 0.5267677183598017, "eval_rougeLsum": 0.6366529460029322, "eval_runtime": 15.0195, "eval_samples_per_second": 0.666, "eval_steps_per_second": 0.333, "step": 14600 }, { "epoch": 1.69, "grad_norm": 0.3174591064453125, "learning_rate": 0.00011571481470931725, "loss": 1.5568, "step": 14800 }, { "epoch": 1.69, "eval_bertscore": 0.7335298657417297, "eval_loss": 1.7310253381729126, "eval_rouge1": 0.6560468577439627, "eval_rouge2": 0.36039371229175, "eval_rougeL": 0.5318708569729291, "eval_rougeLsum": 0.6444857558837042, "eval_runtime": 14.9774, "eval_samples_per_second": 0.668, "eval_steps_per_second": 0.334, "step": 14800 }, { "epoch": 1.71, "grad_norm": 0.2936408817768097, "learning_rate": 0.000114575440795283, "loss": 1.5345, "step": 15000 }, { "epoch": 1.71, "eval_bertscore": 0.7322725057601929, "eval_loss": 1.7270629405975342, "eval_rouge1": 0.6387060930656672, "eval_rouge2": 0.3480508127989137, "eval_rougeL": 0.5148670834213287, "eval_rougeLsum": 0.6273654952601909, "eval_runtime": 15.6687, "eval_samples_per_second": 0.638, "eval_steps_per_second": 0.319, "step": 15000 }, { "epoch": 1.73, "grad_norm": 0.32960689067840576, "learning_rate": 0.00011343606688124875, "loss": 1.5362, "step": 15200 }, { "epoch": 1.73, "eval_bertscore": 0.7337037920951843, "eval_loss": 1.7287395000457764, "eval_rouge1": 0.6476816970229771, "eval_rouge2": 0.3532248216683249, "eval_rougeL": 0.5253136618838716, "eval_rougeLsum": 0.6347493764394183, "eval_runtime": 15.0045, "eval_samples_per_second": 0.666, "eval_steps_per_second": 0.333, "step": 15200 }, { "epoch": 1.75, "grad_norm": 0.33265602588653564, "learning_rate": 0.00011229669296721452, "loss": 1.5215, "step": 15400 }, { "epoch": 1.75, "eval_bertscore": 0.7330806851387024, "eval_loss": 1.7265052795410156, "eval_rouge1": 0.6529393512177359, "eval_rouge2": 0.36182153145062224, "eval_rougeL": 0.5317061134915853, "eval_rougeLsum": 0.6413066299251913, "eval_runtime": 15.0256, "eval_samples_per_second": 0.666, "eval_steps_per_second": 0.333, "step": 15400 }, { "epoch": 1.78, "grad_norm": 0.3436201512813568, "learning_rate": 0.00011115731905318027, "loss": 1.539, "step": 15600 }, { "epoch": 1.78, "eval_bertscore": 0.7335551977157593, "eval_loss": 1.7254730463027954, "eval_rouge1": 0.6388518781767971, "eval_rouge2": 0.3501853846588857, "eval_rougeL": 0.5196828245794569, "eval_rougeLsum": 0.629333993884722, "eval_runtime": 15.2595, "eval_samples_per_second": 0.655, "eval_steps_per_second": 0.328, "step": 15600 }, { "epoch": 1.8, "grad_norm": 0.3428190350532532, "learning_rate": 0.00011001794513914605, "loss": 1.5273, "step": 15800 }, { "epoch": 1.8, "eval_bertscore": 0.7331770658493042, "eval_loss": 1.7286018133163452, "eval_rouge1": 0.6581941047310954, "eval_rouge2": 0.36277983926897583, "eval_rougeL": 0.5336464680120501, "eval_rougeLsum": 0.6489239720278894, "eval_runtime": 14.8252, "eval_samples_per_second": 0.675, "eval_steps_per_second": 0.337, "step": 15800 }, { "epoch": 1.82, "grad_norm": 0.363164484500885, "learning_rate": 0.0001088785712251118, "loss": 1.5445, "step": 16000 }, { "epoch": 1.82, "eval_bertscore": 0.7377282977104187, "eval_loss": 1.7363064289093018, "eval_rouge1": 0.6547011011872876, "eval_rouge2": 0.3553220826957326, "eval_rougeL": 0.5256073814411315, "eval_rougeLsum": 0.6420095316923398, "eval_runtime": 14.8599, "eval_samples_per_second": 0.673, "eval_steps_per_second": 0.336, "step": 16000 }, { "epoch": 1.85, "grad_norm": 0.3098333775997162, "learning_rate": 0.00010773919731107757, "loss": 1.5319, "step": 16200 }, { "epoch": 1.85, "eval_bertscore": 0.7324053645133972, "eval_loss": 1.7284066677093506, "eval_rouge1": 0.6477379941950916, "eval_rouge2": 0.3535918140554809, "eval_rougeL": 0.5226838544730126, "eval_rougeLsum": 0.6373271915355557, "eval_runtime": 14.9318, "eval_samples_per_second": 0.67, "eval_steps_per_second": 0.335, "step": 16200 }, { "epoch": 1.87, "grad_norm": 0.3637208938598633, "learning_rate": 0.00010659982339704332, "loss": 1.5442, "step": 16400 }, { "epoch": 1.87, "eval_bertscore": 0.7347462773323059, "eval_loss": 1.7252963781356812, "eval_rouge1": 0.6494449840449819, "eval_rouge2": 0.3586550050575282, "eval_rougeL": 0.5275675395159809, "eval_rougeLsum": 0.6396738714026391, "eval_runtime": 15.2218, "eval_samples_per_second": 0.657, "eval_steps_per_second": 0.328, "step": 16400 }, { "epoch": 1.89, "grad_norm": 0.35197457671165466, "learning_rate": 0.00010546044948300908, "loss": 1.5131, "step": 16600 }, { "epoch": 1.89, "eval_bertscore": 0.7329785227775574, "eval_loss": 1.7285687923431396, "eval_rouge1": 0.6582047811143328, "eval_rouge2": 0.3637700686094697, "eval_rougeL": 0.5355021948480279, "eval_rougeLsum": 0.6483245595148677, "eval_runtime": 14.8772, "eval_samples_per_second": 0.672, "eval_steps_per_second": 0.336, "step": 16600 }, { "epoch": 1.91, "grad_norm": 0.3406757116317749, "learning_rate": 0.00010432107556897486, "loss": 1.5394, "step": 16800 }, { "epoch": 1.91, "eval_bertscore": 0.7345961332321167, "eval_loss": 1.7324028015136719, "eval_rouge1": 0.6408293615351552, "eval_rouge2": 0.3520120690778129, "eval_rougeL": 0.5145218014745592, "eval_rougeLsum": 0.6297802607384266, "eval_runtime": 15.1044, "eval_samples_per_second": 0.662, "eval_steps_per_second": 0.331, "step": 16800 }, { "epoch": 1.94, "grad_norm": 0.3417683243751526, "learning_rate": 0.00010318170165494061, "loss": 1.526, "step": 17000 }, { "epoch": 1.94, "eval_bertscore": 0.735752522945404, "eval_loss": 1.7288110256195068, "eval_rouge1": 0.641158513352794, "eval_rouge2": 0.3544166440855814, "eval_rougeL": 0.5215201980495414, "eval_rougeLsum": 0.630550065494593, "eval_runtime": 15.0797, "eval_samples_per_second": 0.663, "eval_steps_per_second": 0.332, "step": 17000 }, { "epoch": 1.96, "grad_norm": 0.3256611227989197, "learning_rate": 0.00010204232774090639, "loss": 1.5484, "step": 17200 }, { "epoch": 1.96, "eval_bertscore": 0.7356327772140503, "eval_loss": 1.7305186986923218, "eval_rouge1": 0.6400269226515611, "eval_rouge2": 0.3502884634173268, "eval_rougeL": 0.517312321281175, "eval_rougeLsum": 0.6284556997614409, "eval_runtime": 15.4097, "eval_samples_per_second": 0.649, "eval_steps_per_second": 0.324, "step": 17200 }, { "epoch": 1.98, "grad_norm": 0.4035187363624573, "learning_rate": 0.00010090295382687213, "loss": 1.5261, "step": 17400 }, { "epoch": 1.98, "eval_bertscore": 0.7339992523193359, "eval_loss": 1.7282793521881104, "eval_rouge1": 0.6335770390416183, "eval_rouge2": 0.34592404578075897, "eval_rougeL": 0.5109045259792113, "eval_rougeLsum": 0.6218413683710426, "eval_runtime": 15.1959, "eval_samples_per_second": 0.658, "eval_steps_per_second": 0.329, "step": 17400 }, { "epoch": 2.0, "grad_norm": 0.34987062215805054, "learning_rate": 9.97635799128379e-05, "loss": 1.5199, "step": 17600 }, { "epoch": 2.0, "eval_bertscore": 0.7326329946517944, "eval_loss": 1.7544715404510498, "eval_rouge1": 0.6451558045750205, "eval_rouge2": 0.35565806935653943, "eval_rougeL": 0.5217034865840529, "eval_rougeLsum": 0.6329869715356753, "eval_runtime": 15.0351, "eval_samples_per_second": 0.665, "eval_steps_per_second": 0.333, "step": 17600 }, { "epoch": 2.03, "grad_norm": 0.37184038758277893, "learning_rate": 9.862420599880366e-05, "loss": 1.41, "step": 17800 }, { "epoch": 2.03, "eval_bertscore": 0.7315141558647156, "eval_loss": 1.7585878372192383, "eval_rouge1": 0.6469319193583706, "eval_rouge2": 0.3514447211469598, "eval_rougeL": 0.524755857688278, "eval_rougeLsum": 0.6350164781858667, "eval_runtime": 14.9583, "eval_samples_per_second": 0.669, "eval_steps_per_second": 0.334, "step": 17800 }, { "epoch": 2.05, "grad_norm": 0.3812776803970337, "learning_rate": 9.748483208476943e-05, "loss": 1.4132, "step": 18000 }, { "epoch": 2.05, "eval_bertscore": 0.7335561513900757, "eval_loss": 1.764611840248108, "eval_rouge1": 0.6381916780473581, "eval_rouge2": 0.3482510604092539, "eval_rougeL": 0.5162105225823392, "eval_rougeLsum": 0.627150245441782, "eval_runtime": 15.8515, "eval_samples_per_second": 0.631, "eval_steps_per_second": 0.315, "step": 18000 }, { "epoch": 2.07, "grad_norm": 0.45525220036506653, "learning_rate": 9.634545817073518e-05, "loss": 1.4, "step": 18200 }, { "epoch": 2.07, "eval_bertscore": 0.73627769947052, "eval_loss": 1.7585163116455078, "eval_rouge1": 0.6670097658027134, "eval_rouge2": 0.3658295359911405, "eval_rougeL": 0.5429667657900548, "eval_rougeLsum": 0.6543501745791419, "eval_runtime": 15.0301, "eval_samples_per_second": 0.665, "eval_steps_per_second": 0.333, "step": 18200 }, { "epoch": 2.1, "grad_norm": 0.37322184443473816, "learning_rate": 9.520608425670095e-05, "loss": 1.4293, "step": 18400 }, { "epoch": 2.1, "eval_bertscore": 0.730435848236084, "eval_loss": 1.764052391052246, "eval_rouge1": 0.6640215078213034, "eval_rouge2": 0.3625932287322054, "eval_rougeL": 0.5379978391335138, "eval_rougeLsum": 0.6542054656293199, "eval_runtime": 15.0762, "eval_samples_per_second": 0.663, "eval_steps_per_second": 0.332, "step": 18400 }, { "epoch": 2.12, "grad_norm": 0.4260891079902649, "learning_rate": 9.40667103426667e-05, "loss": 1.4077, "step": 18600 }, { "epoch": 2.12, "eval_bertscore": 0.7309869527816772, "eval_loss": 1.762108564376831, "eval_rouge1": 0.6571171081737958, "eval_rouge2": 0.35780421333141865, "eval_rougeL": 0.5320129270967632, "eval_rougeLsum": 0.64587787409523, "eval_runtime": 14.9004, "eval_samples_per_second": 0.671, "eval_steps_per_second": 0.336, "step": 18600 }, { "epoch": 2.14, "grad_norm": 0.39479926228523254, "learning_rate": 9.292733642863247e-05, "loss": 1.4165, "step": 18800 }, { "epoch": 2.14, "eval_bertscore": 0.7324444651603699, "eval_loss": 1.7607113122940063, "eval_rouge1": 0.6628398862884018, "eval_rouge2": 0.3627259806721216, "eval_rougeL": 0.5366106483832656, "eval_rougeLsum": 0.6528364858807157, "eval_runtime": 15.5766, "eval_samples_per_second": 0.642, "eval_steps_per_second": 0.321, "step": 18800 }, { "epoch": 2.16, "grad_norm": 0.39267703890800476, "learning_rate": 9.178796251459824e-05, "loss": 1.4123, "step": 19000 }, { "epoch": 2.16, "eval_bertscore": 0.7298994064331055, "eval_loss": 1.7668545246124268, "eval_rouge1": 0.6490850022857569, "eval_rouge2": 0.3532323419511264, "eval_rougeL": 0.5212823000193295, "eval_rougeLsum": 0.636442724466695, "eval_runtime": 14.9094, "eval_samples_per_second": 0.671, "eval_steps_per_second": 0.335, "step": 19000 }, { "epoch": 2.19, "grad_norm": 0.38221287727355957, "learning_rate": 9.0648588600564e-05, "loss": 1.401, "step": 19200 }, { "epoch": 2.19, "eval_bertscore": 0.7316875457763672, "eval_loss": 1.764147400856018, "eval_rouge1": 0.6490326710625849, "eval_rouge2": 0.3510351037900723, "eval_rougeL": 0.5239165028795836, "eval_rougeLsum": 0.6373687316421427, "eval_runtime": 15.1192, "eval_samples_per_second": 0.661, "eval_steps_per_second": 0.331, "step": 19200 }, { "epoch": 2.21, "grad_norm": 0.3653150200843811, "learning_rate": 8.950921468652976e-05, "loss": 1.4109, "step": 19400 }, { "epoch": 2.21, "eval_bertscore": 0.7348155975341797, "eval_loss": 1.7640550136566162, "eval_rouge1": 0.6462152873276823, "eval_rouge2": 0.3483599145461069, "eval_rougeL": 0.5193372430687719, "eval_rougeLsum": 0.6334254357511564, "eval_runtime": 14.9291, "eval_samples_per_second": 0.67, "eval_steps_per_second": 0.335, "step": 19400 }, { "epoch": 2.23, "grad_norm": 0.38049009442329407, "learning_rate": 8.836984077249551e-05, "loss": 1.4189, "step": 19600 }, { "epoch": 2.23, "eval_bertscore": 0.7357938885688782, "eval_loss": 1.7696326971054077, "eval_rouge1": 0.6377276221057538, "eval_rouge2": 0.3455397190390045, "eval_rougeL": 0.5118069428064842, "eval_rougeLsum": 0.6264501633078481, "eval_runtime": 14.8653, "eval_samples_per_second": 0.673, "eval_steps_per_second": 0.336, "step": 19600 }, { "epoch": 2.26, "grad_norm": 0.42111098766326904, "learning_rate": 8.723046685846128e-05, "loss": 1.4152, "step": 19800 }, { "epoch": 2.26, "eval_bertscore": 0.7339056134223938, "eval_loss": 1.7658218145370483, "eval_rouge1": 0.6494820372695989, "eval_rouge2": 0.34691658128805236, "eval_rougeL": 0.5193228965163086, "eval_rougeLsum": 0.6365347065687565, "eval_runtime": 15.3562, "eval_samples_per_second": 0.651, "eval_steps_per_second": 0.326, "step": 19800 }, { "epoch": 2.28, "grad_norm": 0.4452258050441742, "learning_rate": 8.609109294442704e-05, "loss": 1.4101, "step": 20000 }, { "epoch": 2.28, "eval_bertscore": 0.7296434640884399, "eval_loss": 1.7714240550994873, "eval_rouge1": 0.6565600824405751, "eval_rouge2": 0.3533618655201594, "eval_rougeL": 0.5263318202066467, "eval_rougeLsum": 0.6444964824298407, "eval_runtime": 14.8578, "eval_samples_per_second": 0.673, "eval_steps_per_second": 0.337, "step": 20000 }, { "epoch": 2.3, "grad_norm": 0.4030967652797699, "learning_rate": 8.495171903039281e-05, "loss": 1.4049, "step": 20200 }, { "epoch": 2.3, "eval_bertscore": 0.7307097315788269, "eval_loss": 1.774444580078125, "eval_rouge1": 0.6517204836155526, "eval_rouge2": 0.3521339653276223, "eval_rougeL": 0.5223211728244184, "eval_rougeLsum": 0.6398710531932736, "eval_runtime": 15.8543, "eval_samples_per_second": 0.631, "eval_steps_per_second": 0.315, "step": 20200 }, { "epoch": 2.32, "grad_norm": 0.33409813046455383, "learning_rate": 8.381234511635858e-05, "loss": 1.4243, "step": 20400 }, { "epoch": 2.32, "eval_bertscore": 0.7312101721763611, "eval_loss": 1.7654094696044922, "eval_rouge1": 0.6607249126293291, "eval_rouge2": 0.3545993249716188, "eval_rougeL": 0.5320161007986739, "eval_rougeLsum": 0.6503315335963733, "eval_runtime": 14.8739, "eval_samples_per_second": 0.672, "eval_steps_per_second": 0.336, "step": 20400 }, { "epoch": 2.35, "grad_norm": 0.4044789671897888, "learning_rate": 8.267297120232433e-05, "loss": 1.413, "step": 20600 }, { "epoch": 2.35, "eval_bertscore": 0.7342169880867004, "eval_loss": 1.769879937171936, "eval_rouge1": 0.6442777880355144, "eval_rouge2": 0.35006080708477183, "eval_rougeL": 0.5218799478770955, "eval_rougeLsum": 0.6332700294558067, "eval_runtime": 14.9089, "eval_samples_per_second": 0.671, "eval_steps_per_second": 0.335, "step": 20600 }, { "epoch": 2.37, "grad_norm": 0.39801183342933655, "learning_rate": 8.153359728829008e-05, "loss": 1.4177, "step": 20800 }, { "epoch": 2.37, "eval_bertscore": 0.7343758344650269, "eval_loss": 1.7737929821014404, "eval_rouge1": 0.6495678172205896, "eval_rouge2": 0.3505195734345703, "eval_rougeL": 0.5263025592812188, "eval_rougeLsum": 0.6390057749428748, "eval_runtime": 15.2148, "eval_samples_per_second": 0.657, "eval_steps_per_second": 0.329, "step": 20800 }, { "epoch": 2.39, "grad_norm": 0.36868759989738464, "learning_rate": 8.039422337425585e-05, "loss": 1.421, "step": 21000 }, { "epoch": 2.39, "eval_bertscore": 0.7333502173423767, "eval_loss": 1.7708820104599, "eval_rouge1": 0.656319412860679, "eval_rouge2": 0.3557406341135577, "eval_rougeL": 0.5293456110466322, "eval_rougeLsum": 0.6421819358163285, "eval_runtime": 14.9091, "eval_samples_per_second": 0.671, "eval_steps_per_second": 0.335, "step": 21000 }, { "epoch": 2.41, "grad_norm": 0.46111443638801575, "learning_rate": 7.925484946022162e-05, "loss": 1.4102, "step": 21200 }, { "epoch": 2.41, "eval_bertscore": 0.736262321472168, "eval_loss": 1.768972635269165, "eval_rouge1": 0.6582574071278393, "eval_rouge2": 0.3557625250443591, "eval_rougeL": 0.5322500342922363, "eval_rougeLsum": 0.646623827844921, "eval_runtime": 15.4088, "eval_samples_per_second": 0.649, "eval_steps_per_second": 0.324, "step": 21200 }, { "epoch": 2.44, "grad_norm": 0.41794517636299133, "learning_rate": 7.811547554618738e-05, "loss": 1.4231, "step": 21400 }, { "epoch": 2.44, "eval_bertscore": 0.7349900603294373, "eval_loss": 1.7673609256744385, "eval_rouge1": 0.6599777278993147, "eval_rouge2": 0.35744569380532043, "eval_rougeL": 0.5359850821835463, "eval_rougeLsum": 0.6469206354455653, "eval_runtime": 14.8837, "eval_samples_per_second": 0.672, "eval_steps_per_second": 0.336, "step": 21400 }, { "epoch": 2.46, "grad_norm": 0.3874039351940155, "learning_rate": 7.697610163215314e-05, "loss": 1.4158, "step": 21600 }, { "epoch": 2.46, "eval_bertscore": 0.7362676858901978, "eval_loss": 1.764347791671753, "eval_rouge1": 0.6576168971663054, "eval_rouge2": 0.36010190798950537, "eval_rougeL": 0.5365592740576962, "eval_rougeLsum": 0.6455601225938818, "eval_runtime": 15.4178, "eval_samples_per_second": 0.649, "eval_steps_per_second": 0.324, "step": 21600 }, { "epoch": 2.48, "grad_norm": 0.4013253450393677, "learning_rate": 7.583672771811889e-05, "loss": 1.418, "step": 21800 }, { "epoch": 2.48, "eval_bertscore": 0.7303592562675476, "eval_loss": 1.765144944190979, "eval_rouge1": 0.6610480012685163, "eval_rouge2": 0.36479831105715255, "eval_rougeL": 0.5375415216439376, "eval_rougeLsum": 0.6504955320897916, "eval_runtime": 15.0677, "eval_samples_per_second": 0.664, "eval_steps_per_second": 0.332, "step": 21800 }, { "epoch": 2.51, "grad_norm": 0.4189004898071289, "learning_rate": 7.469735380408466e-05, "loss": 1.4199, "step": 22000 }, { "epoch": 2.51, "eval_bertscore": 0.7319179773330688, "eval_loss": 1.7685811519622803, "eval_rouge1": 0.6589314825298751, "eval_rouge2": 0.36092809773515727, "eval_rougeL": 0.5359034256928837, "eval_rougeLsum": 0.647695652924998, "eval_runtime": 15.0325, "eval_samples_per_second": 0.665, "eval_steps_per_second": 0.333, "step": 22000 }, { "epoch": 2.53, "grad_norm": 0.39296436309814453, "learning_rate": 7.355797989005042e-05, "loss": 1.4353, "step": 22200 }, { "epoch": 2.53, "eval_bertscore": 0.734102725982666, "eval_loss": 1.7720457315444946, "eval_rouge1": 0.652136441919871, "eval_rouge2": 0.35394856883334874, "eval_rougeL": 0.5257845140699575, "eval_rougeLsum": 0.6411232244792167, "eval_runtime": 14.9943, "eval_samples_per_second": 0.667, "eval_steps_per_second": 0.333, "step": 22200 }, { "epoch": 2.55, "grad_norm": 0.3997296392917633, "learning_rate": 7.241860597601619e-05, "loss": 1.4224, "step": 22400 }, { "epoch": 2.55, "eval_bertscore": 0.7339878082275391, "eval_loss": 1.7666336297988892, "eval_rouge1": 0.6537340121878514, "eval_rouge2": 0.3570961026063757, "eval_rougeL": 0.529937130767685, "eval_rougeLsum": 0.6435060914147177, "eval_runtime": 15.0439, "eval_samples_per_second": 0.665, "eval_steps_per_second": 0.332, "step": 22400 }, { "epoch": 2.57, "grad_norm": 0.45447298884391785, "learning_rate": 7.127923206198196e-05, "loss": 1.4195, "step": 22600 }, { "epoch": 2.57, "eval_bertscore": 0.7328049540519714, "eval_loss": 1.767970085144043, "eval_rouge1": 0.6525615870662755, "eval_rouge2": 0.3548658659692201, "eval_rougeL": 0.5278612681579985, "eval_rougeLsum": 0.6426018669254849, "eval_runtime": 14.8509, "eval_samples_per_second": 0.673, "eval_steps_per_second": 0.337, "step": 22600 }, { "epoch": 2.6, "grad_norm": 0.37068402767181396, "learning_rate": 7.01398581479477e-05, "loss": 1.4174, "step": 22800 }, { "epoch": 2.6, "eval_bertscore": 0.7338019609451294, "eval_loss": 1.763349175453186, "eval_rouge1": 0.6536530437395975, "eval_rouge2": 0.3564778360043106, "eval_rougeL": 0.5285382022264695, "eval_rougeLsum": 0.6425723229746058, "eval_runtime": 14.8293, "eval_samples_per_second": 0.674, "eval_steps_per_second": 0.337, "step": 22800 }, { "epoch": 2.62, "grad_norm": 0.35103845596313477, "learning_rate": 6.900048423391346e-05, "loss": 1.4176, "step": 23000 }, { "epoch": 2.62, "eval_bertscore": 0.7325159311294556, "eval_loss": 1.7628978490829468, "eval_rouge1": 0.6623030759220351, "eval_rouge2": 0.3604109991839185, "eval_rougeL": 0.5322677462077166, "eval_rougeLsum": 0.6516312160764892, "eval_runtime": 14.923, "eval_samples_per_second": 0.67, "eval_steps_per_second": 0.335, "step": 23000 }, { "epoch": 2.64, "grad_norm": 0.39424487948417664, "learning_rate": 6.786111031987923e-05, "loss": 1.4141, "step": 23200 }, { "epoch": 2.64, "eval_bertscore": 0.7374362945556641, "eval_loss": 1.7650716304779053, "eval_rouge1": 0.6574628250156043, "eval_rouge2": 0.36049809448726045, "eval_rougeL": 0.5312753147070929, "eval_rougeLsum": 0.6452805224085838, "eval_runtime": 14.8888, "eval_samples_per_second": 0.672, "eval_steps_per_second": 0.336, "step": 23200 }, { "epoch": 2.67, "grad_norm": 0.43388617038726807, "learning_rate": 6.6721736405845e-05, "loss": 1.4162, "step": 23400 }, { "epoch": 2.67, "eval_bertscore": 0.7336270809173584, "eval_loss": 1.7658464908599854, "eval_rouge1": 0.6573821610105346, "eval_rouge2": 0.3554905858433707, "eval_rougeL": 0.5301171280694805, "eval_rougeLsum": 0.6452831484327366, "eval_runtime": 14.9065, "eval_samples_per_second": 0.671, "eval_steps_per_second": 0.335, "step": 23400 }, { "epoch": 2.69, "grad_norm": 0.41646161675453186, "learning_rate": 6.558236249181076e-05, "loss": 1.4199, "step": 23600 }, { "epoch": 2.69, "eval_bertscore": 0.7336153388023376, "eval_loss": 1.767188310623169, "eval_rouge1": 0.6571676655188523, "eval_rouge2": 0.3572385458490631, "eval_rougeL": 0.5296070447249894, "eval_rougeLsum": 0.6457403843177614, "eval_runtime": 14.7731, "eval_samples_per_second": 0.677, "eval_steps_per_second": 0.338, "step": 23600 }, { "epoch": 2.71, "grad_norm": 0.38818874955177307, "learning_rate": 6.444298857777651e-05, "loss": 1.416, "step": 23800 }, { "epoch": 2.71, "eval_bertscore": 0.7327283620834351, "eval_loss": 1.7616260051727295, "eval_rouge1": 0.656883853658625, "eval_rouge2": 0.3566053754349987, "eval_rougeL": 0.5314518531110131, "eval_rougeLsum": 0.6446071370588691, "eval_runtime": 15.1059, "eval_samples_per_second": 0.662, "eval_steps_per_second": 0.331, "step": 23800 }, { "epoch": 2.73, "grad_norm": 0.39458197355270386, "learning_rate": 6.330361466374227e-05, "loss": 1.4243, "step": 24000 }, { "epoch": 2.73, "eval_bertscore": 0.7317964434623718, "eval_loss": 1.7638084888458252, "eval_rouge1": 0.6571606334248314, "eval_rouge2": 0.3569373186268652, "eval_rougeL": 0.5293554693809414, "eval_rougeLsum": 0.645057709779701, "eval_runtime": 14.8582, "eval_samples_per_second": 0.673, "eval_steps_per_second": 0.337, "step": 24000 }, { "epoch": 2.76, "grad_norm": 0.38834938406944275, "learning_rate": 6.216424074970803e-05, "loss": 1.4131, "step": 24200 }, { "epoch": 2.76, "eval_bertscore": 0.7318626642227173, "eval_loss": 1.7657394409179688, "eval_rouge1": 0.6537968135786872, "eval_rouge2": 0.3558568019037358, "eval_rougeL": 0.528787979657496, "eval_rougeLsum": 0.643715855457879, "eval_runtime": 14.7776, "eval_samples_per_second": 0.677, "eval_steps_per_second": 0.338, "step": 24200 }, { "epoch": 2.78, "grad_norm": 0.37283340096473694, "learning_rate": 6.10248668356738e-05, "loss": 1.4203, "step": 24400 }, { "epoch": 2.78, "eval_bertscore": 0.7367373704910278, "eval_loss": 1.7650487422943115, "eval_rouge1": 0.6541794402701134, "eval_rouge2": 0.3544283778817331, "eval_rougeL": 0.5276595078021217, "eval_rougeLsum": 0.641985089875446, "eval_runtime": 15.2752, "eval_samples_per_second": 0.655, "eval_steps_per_second": 0.327, "step": 24400 }, { "epoch": 2.8, "grad_norm": 0.4221261441707611, "learning_rate": 5.988549292163956e-05, "loss": 1.4207, "step": 24600 }, { "epoch": 2.8, "eval_bertscore": 0.7366531491279602, "eval_loss": 1.7622770071029663, "eval_rouge1": 0.6593934034597051, "eval_rouge2": 0.359831500847421, "eval_rougeL": 0.5337810293575901, "eval_rougeLsum": 0.647676431170948, "eval_runtime": 16.3422, "eval_samples_per_second": 0.612, "eval_steps_per_second": 0.306, "step": 24600 }, { "epoch": 2.83, "grad_norm": 0.4765646457672119, "learning_rate": 5.874611900760533e-05, "loss": 1.4105, "step": 24800 }, { "epoch": 2.83, "eval_bertscore": 0.7325325012207031, "eval_loss": 1.7692537307739258, "eval_rouge1": 0.6507634466188938, "eval_rouge2": 0.3518723325059453, "eval_rougeL": 0.5245280386580646, "eval_rougeLsum": 0.6407163362773103, "eval_runtime": 15.8625, "eval_samples_per_second": 0.63, "eval_steps_per_second": 0.315, "step": 24800 }, { "epoch": 2.85, "grad_norm": 0.43420910835266113, "learning_rate": 5.760674509357109e-05, "loss": 1.4093, "step": 25000 }, { "epoch": 2.85, "eval_bertscore": 0.7350980043411255, "eval_loss": 1.765899896621704, "eval_rouge1": 0.654968133779226, "eval_rouge2": 0.35640798019371084, "eval_rougeL": 0.5293198154872452, "eval_rougeLsum": 0.6438911452718419, "eval_runtime": 14.9802, "eval_samples_per_second": 0.668, "eval_steps_per_second": 0.334, "step": 25000 }, { "epoch": 2.87, "grad_norm": 0.4037187993526459, "learning_rate": 5.646737117953684e-05, "loss": 1.4168, "step": 25200 }, { "epoch": 2.87, "eval_bertscore": 0.7334460020065308, "eval_loss": 1.7674219608306885, "eval_rouge1": 0.6449835105373629, "eval_rouge2": 0.3523964707950204, "eval_rougeL": 0.5229607326177911, "eval_rougeLsum": 0.6341183290076015, "eval_runtime": 15.1444, "eval_samples_per_second": 0.66, "eval_steps_per_second": 0.33, "step": 25200 }, { "epoch": 2.89, "grad_norm": 0.46987786889076233, "learning_rate": 5.532799726550261e-05, "loss": 1.4232, "step": 25400 }, { "epoch": 2.89, "eval_bertscore": 0.7338739037513733, "eval_loss": 1.766469955444336, "eval_rouge1": 0.652936115282645, "eval_rouge2": 0.35620333501115786, "eval_rougeL": 0.5268542487630437, "eval_rougeLsum": 0.6430711603020087, "eval_runtime": 15.1688, "eval_samples_per_second": 0.659, "eval_steps_per_second": 0.33, "step": 25400 }, { "epoch": 2.92, "grad_norm": 0.3969995081424713, "learning_rate": 5.418862335146837e-05, "loss": 1.4134, "step": 25600 }, { "epoch": 2.92, "eval_bertscore": 0.7372814416885376, "eval_loss": 1.7634046077728271, "eval_rouge1": 0.6612907782823452, "eval_rouge2": 0.3600341319079672, "eval_rougeL": 0.5358216104379979, "eval_rougeLsum": 0.6517186363306726, "eval_runtime": 15.3081, "eval_samples_per_second": 0.653, "eval_steps_per_second": 0.327, "step": 25600 }, { "epoch": 2.94, "grad_norm": 0.4024534821510315, "learning_rate": 5.3049249437434134e-05, "loss": 1.4101, "step": 25800 }, { "epoch": 2.94, "eval_bertscore": 0.7351590991020203, "eval_loss": 1.762956976890564, "eval_rouge1": 0.6564585752882299, "eval_rouge2": 0.35673018577153914, "eval_rougeL": 0.5313007749373967, "eval_rougeLsum": 0.6469154732294412, "eval_runtime": 15.373, "eval_samples_per_second": 0.65, "eval_steps_per_second": 0.325, "step": 25800 }, { "epoch": 2.96, "grad_norm": 0.3964459300041199, "learning_rate": 5.19098755233999e-05, "loss": 1.4238, "step": 26000 }, { "epoch": 2.96, "eval_bertscore": 0.7316532135009766, "eval_loss": 1.7618186473846436, "eval_rouge1": 0.654963067591155, "eval_rouge2": 0.3581644146516789, "eval_rougeL": 0.531393156301234, "eval_rougeLsum": 0.6434849921119885, "eval_runtime": 15.3495, "eval_samples_per_second": 0.651, "eval_steps_per_second": 0.326, "step": 26000 }, { "epoch": 2.98, "grad_norm": 0.4463755190372467, "learning_rate": 5.0770501609365654e-05, "loss": 1.4229, "step": 26200 }, { "epoch": 2.98, "eval_bertscore": 0.7320259213447571, "eval_loss": 1.7612769603729248, "eval_rouge1": 0.6614975676412205, "eval_rouge2": 0.3604125920722135, "eval_rougeL": 0.5363549802785277, "eval_rougeLsum": 0.6515851657527423, "eval_runtime": 14.8919, "eval_samples_per_second": 0.672, "eval_steps_per_second": 0.336, "step": 26200 }, { "epoch": 3.01, "grad_norm": 0.40796974301338196, "learning_rate": 4.963112769533142e-05, "loss": 1.3813, "step": 26400 }, { "epoch": 3.01, "eval_bertscore": 0.7295970320701599, "eval_loss": 1.811266303062439, "eval_rouge1": 0.6560490318552642, "eval_rouge2": 0.3557119399635176, "eval_rougeL": 0.5287962454708006, "eval_rougeLsum": 0.6446835859698083, "eval_runtime": 14.9171, "eval_samples_per_second": 0.67, "eval_steps_per_second": 0.335, "step": 26400 }, { "epoch": 3.03, "grad_norm": 0.46325549483299255, "learning_rate": 4.849175378129718e-05, "loss": 1.2736, "step": 26600 }, { "epoch": 3.03, "eval_bertscore": 0.7268515229225159, "eval_loss": 1.8191944360733032, "eval_rouge1": 0.6497892244364525, "eval_rouge2": 0.3506188166717437, "eval_rougeL": 0.5231517907924512, "eval_rougeLsum": 0.637288999184507, "eval_runtime": 15.1326, "eval_samples_per_second": 0.661, "eval_steps_per_second": 0.33, "step": 26600 }, { "epoch": 3.05, "grad_norm": 0.418163925409317, "learning_rate": 4.735237986726294e-05, "loss": 1.2907, "step": 26800 }, { "epoch": 3.05, "eval_bertscore": 0.7263709306716919, "eval_loss": 1.8185272216796875, "eval_rouge1": 0.6528251185371499, "eval_rouge2": 0.35135402870682864, "eval_rougeL": 0.5245953667859045, "eval_rougeLsum": 0.6409906452290423, "eval_runtime": 14.9485, "eval_samples_per_second": 0.669, "eval_steps_per_second": 0.334, "step": 26800 }, { "epoch": 3.08, "grad_norm": 0.4502899944782257, "learning_rate": 4.621300595322871e-05, "loss": 1.312, "step": 27000 }, { "epoch": 3.08, "eval_bertscore": 0.730769157409668, "eval_loss": 1.8249473571777344, "eval_rouge1": 0.6561686350412601, "eval_rouge2": 0.3569324008900834, "eval_rougeL": 0.5288774802109955, "eval_rougeLsum": 0.6442271954437371, "eval_runtime": 15.1193, "eval_samples_per_second": 0.661, "eval_steps_per_second": 0.331, "step": 27000 }, { "epoch": 3.1, "grad_norm": 0.5041025280952454, "learning_rate": 4.507363203919447e-05, "loss": 1.2901, "step": 27200 }, { "epoch": 3.1, "eval_bertscore": 0.7287546396255493, "eval_loss": 1.827923059463501, "eval_rouge1": 0.654431124870002, "eval_rouge2": 0.35368874998515576, "eval_rougeL": 0.5236566728859537, "eval_rougeLsum": 0.641190956348846, "eval_runtime": 15.038, "eval_samples_per_second": 0.665, "eval_steps_per_second": 0.332, "step": 27200 }, { "epoch": 3.12, "grad_norm": 0.49700435996055603, "learning_rate": 4.3934258125160227e-05, "loss": 1.3022, "step": 27400 }, { "epoch": 3.12, "eval_bertscore": 0.7300220727920532, "eval_loss": 1.8278529644012451, "eval_rouge1": 0.6495055712132203, "eval_rouge2": 0.35008948755256797, "eval_rougeL": 0.5213069893643358, "eval_rougeLsum": 0.6390055765751734, "eval_runtime": 15.0722, "eval_samples_per_second": 0.663, "eval_steps_per_second": 0.332, "step": 27400 }, { "epoch": 3.14, "grad_norm": 0.5290235280990601, "learning_rate": 4.279488421112599e-05, "loss": 1.294, "step": 27600 }, { "epoch": 3.14, "eval_bertscore": 0.729856014251709, "eval_loss": 1.8240941762924194, "eval_rouge1": 0.6470451896722034, "eval_rouge2": 0.3467642899944511, "eval_rougeL": 0.5174082021807023, "eval_rougeLsum": 0.6342977220765258, "eval_runtime": 15.0045, "eval_samples_per_second": 0.666, "eval_steps_per_second": 0.333, "step": 27600 }, { "epoch": 3.17, "grad_norm": 0.48079508543014526, "learning_rate": 4.1655510297091746e-05, "loss": 1.306, "step": 27800 }, { "epoch": 3.17, "eval_bertscore": 0.7321656346321106, "eval_loss": 1.825411081314087, "eval_rouge1": 0.6470417242893683, "eval_rouge2": 0.34887648488076, "eval_rougeL": 0.5195978025683929, "eval_rougeLsum": 0.6352241217746025, "eval_runtime": 15.2265, "eval_samples_per_second": 0.657, "eval_steps_per_second": 0.328, "step": 27800 }, { "epoch": 3.19, "grad_norm": 0.4453580379486084, "learning_rate": 4.051613638305751e-05, "loss": 1.2872, "step": 28000 }, { "epoch": 3.19, "eval_bertscore": 0.7312643527984619, "eval_loss": 1.8250818252563477, "eval_rouge1": 0.6529323387086918, "eval_rouge2": 0.35175299130000515, "eval_rougeL": 0.5236016220703108, "eval_rougeLsum": 0.641817087066691, "eval_runtime": 15.2328, "eval_samples_per_second": 0.656, "eval_steps_per_second": 0.328, "step": 28000 }, { "epoch": 3.21, "grad_norm": 0.5724875926971436, "learning_rate": 3.937676246902327e-05, "loss": 1.3023, "step": 28200 }, { "epoch": 3.21, "eval_bertscore": 0.7281081080436707, "eval_loss": 1.8279011249542236, "eval_rouge1": 0.6513629794596312, "eval_rouge2": 0.3514275809731242, "eval_rougeL": 0.5223236211798525, "eval_rougeLsum": 0.6403569684779228, "eval_runtime": 15.1002, "eval_samples_per_second": 0.662, "eval_steps_per_second": 0.331, "step": 28200 }, { "epoch": 3.24, "grad_norm": 0.5111600756645203, "learning_rate": 3.823738855498903e-05, "loss": 1.3147, "step": 28400 }, { "epoch": 3.24, "eval_bertscore": 0.7288422584533691, "eval_loss": 1.8290317058563232, "eval_rouge1": 0.6507807205572858, "eval_rouge2": 0.347161808566521, "eval_rougeL": 0.5183864656438575, "eval_rougeLsum": 0.6389967703327324, "eval_runtime": 15.1074, "eval_samples_per_second": 0.662, "eval_steps_per_second": 0.331, "step": 28400 }, { "epoch": 3.26, "grad_norm": 0.4945109486579895, "learning_rate": 3.70980146409548e-05, "loss": 1.2798, "step": 28600 }, { "epoch": 3.26, "eval_bertscore": 0.7282342910766602, "eval_loss": 1.8240516185760498, "eval_rouge1": 0.6466411393254512, "eval_rouge2": 0.3439998647318193, "eval_rougeL": 0.5156993049024075, "eval_rougeLsum": 0.6339007584931882, "eval_runtime": 15.1238, "eval_samples_per_second": 0.661, "eval_steps_per_second": 0.331, "step": 28600 }, { "epoch": 3.28, "grad_norm": 0.5064042806625366, "learning_rate": 3.595864072692056e-05, "loss": 1.2908, "step": 28800 }, { "epoch": 3.28, "eval_bertscore": 0.7303023934364319, "eval_loss": 1.8296499252319336, "eval_rouge1": 0.6422335462244783, "eval_rouge2": 0.3444891262545964, "eval_rougeL": 0.5139669252888657, "eval_rougeLsum": 0.6282864227941442, "eval_runtime": 15.1801, "eval_samples_per_second": 0.659, "eval_steps_per_second": 0.329, "step": 28800 }, { "epoch": 3.3, "grad_norm": 0.5009918808937073, "learning_rate": 3.481926681288632e-05, "loss": 1.2939, "step": 29000 }, { "epoch": 3.3, "eval_bertscore": 0.728093147277832, "eval_loss": 1.8265445232391357, "eval_rouge1": 0.644883485667703, "eval_rouge2": 0.3478659306090649, "eval_rougeL": 0.5177213919602106, "eval_rougeLsum": 0.6333667556178277, "eval_runtime": 15.6279, "eval_samples_per_second": 0.64, "eval_steps_per_second": 0.32, "step": 29000 }, { "epoch": 3.33, "grad_norm": 0.5137434005737305, "learning_rate": 3.3679892898852086e-05, "loss": 1.2859, "step": 29200 }, { "epoch": 3.33, "eval_bertscore": 0.7286854982376099, "eval_loss": 1.8274028301239014, "eval_rouge1": 0.6464900426605129, "eval_rouge2": 0.34794140309215504, "eval_rougeL": 0.5171376759249153, "eval_rougeLsum": 0.6350675668052526, "eval_runtime": 16.3341, "eval_samples_per_second": 0.612, "eval_steps_per_second": 0.306, "step": 29200 }, { "epoch": 3.35, "grad_norm": 0.5424513816833496, "learning_rate": 3.254051898481784e-05, "loss": 1.2982, "step": 29400 }, { "epoch": 3.35, "eval_bertscore": 0.7272428274154663, "eval_loss": 1.8286670446395874, "eval_rouge1": 0.6481295498889761, "eval_rouge2": 0.3477423613736981, "eval_rougeL": 0.5196844939850981, "eval_rougeLsum": 0.6363855713968847, "eval_runtime": 15.5655, "eval_samples_per_second": 0.642, "eval_steps_per_second": 0.321, "step": 29400 }, { "epoch": 3.37, "grad_norm": 0.444140762090683, "learning_rate": 3.1401145070783606e-05, "loss": 1.31, "step": 29600 }, { "epoch": 3.37, "eval_bertscore": 0.7301056981086731, "eval_loss": 1.8282674551010132, "eval_rouge1": 0.6540262039652377, "eval_rouge2": 0.3482307679056835, "eval_rougeL": 0.5226038858975284, "eval_rougeLsum": 0.6417997985279889, "eval_runtime": 15.2375, "eval_samples_per_second": 0.656, "eval_steps_per_second": 0.328, "step": 29600 }, { "epoch": 3.39, "grad_norm": 0.5904114842414856, "learning_rate": 3.026177115674937e-05, "loss": 1.294, "step": 29800 }, { "epoch": 3.39, "eval_bertscore": 0.7272050976753235, "eval_loss": 1.8291629552841187, "eval_rouge1": 0.6451593111208989, "eval_rouge2": 0.3441493766178606, "eval_rougeL": 0.5159603215943032, "eval_rougeLsum": 0.633764929096605, "eval_runtime": 15.414, "eval_samples_per_second": 0.649, "eval_steps_per_second": 0.324, "step": 29800 }, { "epoch": 3.42, "grad_norm": 0.4698268473148346, "learning_rate": 2.9122397242715125e-05, "loss": 1.302, "step": 30000 }, { "epoch": 3.42, "eval_bertscore": 0.727090060710907, "eval_loss": 1.826228141784668, "eval_rouge1": 0.6437945042471859, "eval_rouge2": 0.3459081721119077, "eval_rougeL": 0.516648955547528, "eval_rougeLsum": 0.6328083779823412, "eval_runtime": 15.0752, "eval_samples_per_second": 0.663, "eval_steps_per_second": 0.332, "step": 30000 }, { "epoch": 3.44, "grad_norm": 0.5351114869117737, "learning_rate": 2.7983023328680892e-05, "loss": 1.2971, "step": 30200 }, { "epoch": 3.44, "eval_bertscore": 0.7274346947669983, "eval_loss": 1.8284015655517578, "eval_rouge1": 0.6428862858184051, "eval_rouge2": 0.34402597597356294, "eval_rougeL": 0.5169219417216804, "eval_rougeLsum": 0.6311059754170927, "eval_runtime": 15.1782, "eval_samples_per_second": 0.659, "eval_steps_per_second": 0.329, "step": 30200 }, { "epoch": 3.46, "grad_norm": 0.4645843207836151, "learning_rate": 2.6843649414646655e-05, "loss": 1.3118, "step": 30400 }, { "epoch": 3.46, "eval_bertscore": 0.729422926902771, "eval_loss": 1.8232523202896118, "eval_rouge1": 0.6423334204787501, "eval_rouge2": 0.34656408059281585, "eval_rougeL": 0.5188486939610837, "eval_rougeLsum": 0.631364621415121, "eval_runtime": 15.069, "eval_samples_per_second": 0.664, "eval_steps_per_second": 0.332, "step": 30400 }, { "epoch": 3.49, "grad_norm": 0.47329181432724, "learning_rate": 2.5704275500612412e-05, "loss": 1.2988, "step": 30600 }, { "epoch": 3.49, "eval_bertscore": 0.7293562889099121, "eval_loss": 1.828523874282837, "eval_rouge1": 0.6415836961511305, "eval_rouge2": 0.3448380376898492, "eval_rougeL": 0.5160968947152185, "eval_rougeLsum": 0.6307043736862319, "eval_runtime": 15.0452, "eval_samples_per_second": 0.665, "eval_steps_per_second": 0.332, "step": 30600 }, { "epoch": 3.51, "grad_norm": 0.5455173850059509, "learning_rate": 2.4564901586578175e-05, "loss": 1.3047, "step": 30800 }, { "epoch": 3.51, "eval_bertscore": 0.7271963357925415, "eval_loss": 1.8309329748153687, "eval_rouge1": 0.6426011693074479, "eval_rouge2": 0.3431784961885528, "eval_rougeL": 0.5149548951072465, "eval_rougeLsum": 0.6316192615509898, "eval_runtime": 15.6627, "eval_samples_per_second": 0.638, "eval_steps_per_second": 0.319, "step": 30800 }, { "epoch": 3.53, "grad_norm": 0.5494771599769592, "learning_rate": 2.342552767254394e-05, "loss": 1.3024, "step": 31000 }, { "epoch": 3.53, "eval_bertscore": 0.7272982597351074, "eval_loss": 1.8302767276763916, "eval_rouge1": 0.6466094927962344, "eval_rouge2": 0.3471361046759306, "eval_rougeL": 0.5189286897798941, "eval_rougeLsum": 0.6353196842160578, "eval_runtime": 15.1338, "eval_samples_per_second": 0.661, "eval_steps_per_second": 0.33, "step": 31000 }, { "epoch": 3.55, "grad_norm": 0.5403386354446411, "learning_rate": 2.22861537585097e-05, "loss": 1.297, "step": 31200 }, { "epoch": 3.55, "eval_bertscore": 0.7270491123199463, "eval_loss": 1.8272756338119507, "eval_rouge1": 0.6403763553288392, "eval_rouge2": 0.34466660447048997, "eval_rougeL": 0.5148866492867579, "eval_rougeLsum": 0.6292478620902813, "eval_runtime": 14.964, "eval_samples_per_second": 0.668, "eval_steps_per_second": 0.334, "step": 31200 }, { "epoch": 3.58, "grad_norm": 0.503570020198822, "learning_rate": 2.114677984447546e-05, "loss": 1.2938, "step": 31400 }, { "epoch": 3.58, "eval_bertscore": 0.7284318804740906, "eval_loss": 1.829698920249939, "eval_rouge1": 0.645157270000772, "eval_rouge2": 0.3464589548126101, "eval_rougeL": 0.520190218446654, "eval_rougeLsum": 0.6339678909086379, "eval_runtime": 14.9783, "eval_samples_per_second": 0.668, "eval_steps_per_second": 0.334, "step": 31400 }, { "epoch": 3.6, "grad_norm": 0.4921557307243347, "learning_rate": 2.000740593044122e-05, "loss": 1.2976, "step": 31600 }, { "epoch": 3.6, "eval_bertscore": 0.7275441884994507, "eval_loss": 1.826766014099121, "eval_rouge1": 0.6448512195338201, "eval_rouge2": 0.34423006917554333, "eval_rougeL": 0.5158574771641147, "eval_rougeLsum": 0.6334922214996468, "eval_runtime": 15.0137, "eval_samples_per_second": 0.666, "eval_steps_per_second": 0.333, "step": 31600 }, { "epoch": 3.62, "grad_norm": 0.4597444534301758, "learning_rate": 1.8868032016406985e-05, "loss": 1.2984, "step": 31800 }, { "epoch": 3.62, "eval_bertscore": 0.7296847105026245, "eval_loss": 1.831121802330017, "eval_rouge1": 0.6418710105695564, "eval_rouge2": 0.34594102353175615, "eval_rougeL": 0.5177915012238398, "eval_rougeLsum": 0.6316847551673457, "eval_runtime": 15.411, "eval_samples_per_second": 0.649, "eval_steps_per_second": 0.324, "step": 31800 }, { "epoch": 3.65, "grad_norm": 0.47503286600112915, "learning_rate": 1.7728658102372748e-05, "loss": 1.3009, "step": 32000 }, { "epoch": 3.65, "eval_bertscore": 0.7298310995101929, "eval_loss": 1.8273332118988037, "eval_rouge1": 0.6417379366459213, "eval_rouge2": 0.34542487508092823, "eval_rougeL": 0.5158503557549705, "eval_rougeLsum": 0.6309833082960914, "eval_runtime": 14.9311, "eval_samples_per_second": 0.67, "eval_steps_per_second": 0.335, "step": 32000 }, { "epoch": 3.67, "grad_norm": 0.45725110173225403, "learning_rate": 1.6589284188338508e-05, "loss": 1.3042, "step": 32200 }, { "epoch": 3.67, "eval_bertscore": 0.7283689379692078, "eval_loss": 1.8278729915618896, "eval_rouge1": 0.6438134996619729, "eval_rouge2": 0.34631038919793855, "eval_rougeL": 0.5185962520496568, "eval_rougeLsum": 0.6335181171392547, "eval_runtime": 14.9577, "eval_samples_per_second": 0.669, "eval_steps_per_second": 0.334, "step": 32200 }, { "epoch": 3.69, "grad_norm": 0.527599036693573, "learning_rate": 1.544991027430427e-05, "loss": 1.3141, "step": 32400 }, { "epoch": 3.69, "eval_bertscore": 0.7283642292022705, "eval_loss": 1.828185796737671, "eval_rouge1": 0.6420673962616871, "eval_rouge2": 0.3428100609192179, "eval_rougeL": 0.5151424402980586, "eval_rougeLsum": 0.6312247707173357, "eval_runtime": 15.0727, "eval_samples_per_second": 0.663, "eval_steps_per_second": 0.332, "step": 32400 }, { "epoch": 3.71, "grad_norm": 0.4286324679851532, "learning_rate": 1.4310536360270033e-05, "loss": 1.2965, "step": 32600 }, { "epoch": 3.71, "eval_bertscore": 0.7269189953804016, "eval_loss": 1.827340841293335, "eval_rouge1": 0.6423441986765093, "eval_rouge2": 0.3444233896929453, "eval_rougeL": 0.515230719711361, "eval_rougeLsum": 0.6324502593091261, "eval_runtime": 15.762, "eval_samples_per_second": 0.634, "eval_steps_per_second": 0.317, "step": 32600 }, { "epoch": 3.74, "grad_norm": 0.45857399702072144, "learning_rate": 1.3171162446235794e-05, "loss": 1.3106, "step": 32800 }, { "epoch": 3.74, "eval_bertscore": 0.7266061305999756, "eval_loss": 1.8283151388168335, "eval_rouge1": 0.6411621669658236, "eval_rouge2": 0.3443038317384875, "eval_rougeL": 0.5144500926275494, "eval_rougeLsum": 0.6309220735111227, "eval_runtime": 15.7907, "eval_samples_per_second": 0.633, "eval_steps_per_second": 0.317, "step": 32800 } ], "logging_steps": 200, "max_steps": 35112, "num_input_tokens_seen": 0, "num_train_epochs": 4, "save_steps": 800, "total_flos": 3.3218338576266363e+18, "train_batch_size": 2, "trial_name": null, "trial_params": null }