| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.512406488408266, | |
| "eval_steps": 11, | |
| "global_step": 265, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.009480779201540626, | |
| "grad_norm": 2.265625, | |
| "learning_rate": 2e-05, | |
| "loss": 0.5339, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009480779201540626, | |
| "eval_loss": 0.5036121606826782, | |
| "eval_runtime": 36.0149, | |
| "eval_samples_per_second": 19.742, | |
| "eval_steps_per_second": 19.742, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.018961558403081252, | |
| "grad_norm": 2.1875, | |
| "learning_rate": 4e-05, | |
| "loss": 0.502, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02844233760462188, | |
| "grad_norm": 1.890625, | |
| "learning_rate": 6e-05, | |
| "loss": 0.4769, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.037923116806162505, | |
| "grad_norm": 1.0234375, | |
| "learning_rate": 8e-05, | |
| "loss": 0.2922, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04740389600770313, | |
| "grad_norm": 1.5234375, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2162, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05688467520924376, | |
| "grad_norm": 0.59375, | |
| "learning_rate": 0.00012, | |
| "loss": 0.1685, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.06636545441078438, | |
| "grad_norm": 0.359375, | |
| "learning_rate": 0.00014, | |
| "loss": 0.1208, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.07584623361232501, | |
| "grad_norm": 0.32421875, | |
| "learning_rate": 0.00016, | |
| "loss": 0.1147, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.08532701281386564, | |
| "grad_norm": 0.302734375, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0983, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.09480779201540626, | |
| "grad_norm": 0.25390625, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0827, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.10428857121694689, | |
| "grad_norm": 0.232421875, | |
| "learning_rate": 0.00019999469523400122, | |
| "loss": 0.0879, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.10428857121694689, | |
| "eval_loss": 0.08134982734918594, | |
| "eval_runtime": 35.8683, | |
| "eval_samples_per_second": 19.823, | |
| "eval_steps_per_second": 19.823, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.11376935041848751, | |
| "grad_norm": 0.2265625, | |
| "learning_rate": 0.00019997878149881574, | |
| "loss": 0.0831, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.12325012962002814, | |
| "grad_norm": 0.21875, | |
| "learning_rate": 0.0001999522604828164, | |
| "loss": 0.0756, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.13273090882156877, | |
| "grad_norm": 0.2255859375, | |
| "learning_rate": 0.00019991513499975882, | |
| "loss": 0.0835, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.1422116880231094, | |
| "grad_norm": 0.234375, | |
| "learning_rate": 0.00019986740898848306, | |
| "loss": 0.0732, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.15169246722465002, | |
| "grad_norm": 0.1650390625, | |
| "learning_rate": 0.00019980908751249555, | |
| "loss": 0.0739, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.16117324642619066, | |
| "grad_norm": 0.14453125, | |
| "learning_rate": 0.00019974017675943192, | |
| "loss": 0.0698, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.17065402562773127, | |
| "grad_norm": 0.1767578125, | |
| "learning_rate": 0.0001996606840404006, | |
| "loss": 0.072, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1801348048292719, | |
| "grad_norm": 0.1328125, | |
| "learning_rate": 0.00019957061778920701, | |
| "loss": 0.0556, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.18961558403081252, | |
| "grad_norm": 0.1455078125, | |
| "learning_rate": 0.0001994699875614589, | |
| "loss": 0.0685, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.19909636323235316, | |
| "grad_norm": 0.1455078125, | |
| "learning_rate": 0.00019935880403355253, | |
| "loss": 0.0598, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.20857714243389378, | |
| "grad_norm": 0.13671875, | |
| "learning_rate": 0.00019923707900153982, | |
| "loss": 0.0582, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.20857714243389378, | |
| "eval_loss": 0.06287878006696701, | |
| "eval_runtime": 35.7847, | |
| "eval_samples_per_second": 19.869, | |
| "eval_steps_per_second": 19.869, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.21805792163543442, | |
| "grad_norm": 0.15234375, | |
| "learning_rate": 0.00019910482537987702, | |
| "loss": 0.0644, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.22753870083697503, | |
| "grad_norm": 0.130859375, | |
| "learning_rate": 0.0001989620572000544, | |
| "loss": 0.0615, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.23701948003851567, | |
| "grad_norm": 0.13671875, | |
| "learning_rate": 0.00019880878960910772, | |
| "loss": 0.0686, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.24650025924005628, | |
| "grad_norm": 0.14453125, | |
| "learning_rate": 0.00019864503886801106, | |
| "loss": 0.068, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.2559810384415969, | |
| "grad_norm": 0.12353515625, | |
| "learning_rate": 0.00019847082234995171, | |
| "loss": 0.0525, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.26546181764313753, | |
| "grad_norm": 0.10791015625, | |
| "learning_rate": 0.00019828615853848688, | |
| "loss": 0.0541, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.27494259684467814, | |
| "grad_norm": 0.12060546875, | |
| "learning_rate": 0.00019809106702558277, | |
| "loss": 0.0522, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.2844233760462188, | |
| "grad_norm": 0.11669921875, | |
| "learning_rate": 0.0001978855685095358, | |
| "loss": 0.0526, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2939041552477594, | |
| "grad_norm": 0.140625, | |
| "learning_rate": 0.00019766968479277683, | |
| "loss": 0.0626, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.30338493444930004, | |
| "grad_norm": 0.134765625, | |
| "learning_rate": 0.00019744343877955788, | |
| "loss": 0.0598, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.3128657136508407, | |
| "grad_norm": 0.1220703125, | |
| "learning_rate": 0.00019720685447352209, | |
| "loss": 0.06, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.3128657136508407, | |
| "eval_loss": 0.05662544071674347, | |
| "eval_runtime": 35.8251, | |
| "eval_samples_per_second": 19.846, | |
| "eval_steps_per_second": 19.846, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.3223464928523813, | |
| "grad_norm": 0.14453125, | |
| "learning_rate": 0.0001969599569751571, | |
| "loss": 0.0555, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.33182727205392193, | |
| "grad_norm": 0.12158203125, | |
| "learning_rate": 0.00019670277247913205, | |
| "loss": 0.0615, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.34130805125546254, | |
| "grad_norm": 0.11279296875, | |
| "learning_rate": 0.0001964353282715183, | |
| "loss": 0.0499, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.3507888304570032, | |
| "grad_norm": 0.12158203125, | |
| "learning_rate": 0.00019615765272689461, | |
| "loss": 0.0555, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.3602696096585438, | |
| "grad_norm": 0.11572265625, | |
| "learning_rate": 0.00019586977530533677, | |
| "loss": 0.0613, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.36975038886008443, | |
| "grad_norm": 0.1044921875, | |
| "learning_rate": 0.00019557172654929196, | |
| "loss": 0.0574, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.37923116806162505, | |
| "grad_norm": 0.1025390625, | |
| "learning_rate": 0.00019526353808033825, | |
| "loss": 0.0527, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3887119472631657, | |
| "grad_norm": 0.1298828125, | |
| "learning_rate": 0.00019494524259582992, | |
| "loss": 0.0561, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.3981927264647063, | |
| "grad_norm": 0.10302734375, | |
| "learning_rate": 0.00019461687386542826, | |
| "loss": 0.0487, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.40767350566624694, | |
| "grad_norm": 0.11279296875, | |
| "learning_rate": 0.00019427846672751873, | |
| "loss": 0.0476, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.41715428486778755, | |
| "grad_norm": 0.1240234375, | |
| "learning_rate": 0.00019393005708551498, | |
| "loss": 0.0593, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.41715428486778755, | |
| "eval_loss": 0.051377832889556885, | |
| "eval_runtime": 35.8632, | |
| "eval_samples_per_second": 19.825, | |
| "eval_steps_per_second": 19.825, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.4266350640693282, | |
| "grad_norm": 0.10888671875, | |
| "learning_rate": 0.00019357168190404936, | |
| "loss": 0.0498, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.43611584327086883, | |
| "grad_norm": 0.1171875, | |
| "learning_rate": 0.00019320337920505153, | |
| "loss": 0.0599, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.44559662247240944, | |
| "grad_norm": 0.11669921875, | |
| "learning_rate": 0.00019282518806371414, | |
| "loss": 0.0595, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.45507740167395005, | |
| "grad_norm": 0.123046875, | |
| "learning_rate": 0.0001924371486043473, | |
| "loss": 0.0648, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.4645581808754907, | |
| "grad_norm": 0.1025390625, | |
| "learning_rate": 0.0001920393019961217, | |
| "loss": 0.0506, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.47403896007703133, | |
| "grad_norm": 0.1171875, | |
| "learning_rate": 0.0001916316904487005, | |
| "loss": 0.0568, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.48351973927857195, | |
| "grad_norm": 0.09521484375, | |
| "learning_rate": 0.00019121435720776122, | |
| "loss": 0.0476, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.49300051848011256, | |
| "grad_norm": 0.11474609375, | |
| "learning_rate": 0.0001907873465504076, | |
| "loss": 0.0504, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.5024812976816532, | |
| "grad_norm": 0.11572265625, | |
| "learning_rate": 0.00019035070378047204, | |
| "loss": 0.0486, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.5119620768831938, | |
| "grad_norm": 0.10986328125, | |
| "learning_rate": 0.00018990447522370884, | |
| "loss": 0.0467, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.5214428560847345, | |
| "grad_norm": 0.12158203125, | |
| "learning_rate": 0.00018944870822287956, | |
| "loss": 0.054, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.5214428560847345, | |
| "eval_loss": 0.048270147293806076, | |
| "eval_runtime": 35.8252, | |
| "eval_samples_per_second": 19.846, | |
| "eval_steps_per_second": 19.846, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.5309236352862751, | |
| "grad_norm": 0.09912109375, | |
| "learning_rate": 0.00018898345113272998, | |
| "loss": 0.0442, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.5404044144878157, | |
| "grad_norm": 0.1005859375, | |
| "learning_rate": 0.00018850875331485995, | |
| "loss": 0.0415, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.5498851936893563, | |
| "grad_norm": 0.1142578125, | |
| "learning_rate": 0.00018802466513248632, | |
| "loss": 0.0474, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.559365972890897, | |
| "grad_norm": 0.1103515625, | |
| "learning_rate": 0.00018753123794509974, | |
| "loss": 0.0501, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.5688467520924376, | |
| "grad_norm": 0.10986328125, | |
| "learning_rate": 0.00018702852410301554, | |
| "loss": 0.0509, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.5783275312939782, | |
| "grad_norm": 0.119140625, | |
| "learning_rate": 0.0001865165769418196, | |
| "loss": 0.054, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.5878083104955188, | |
| "grad_norm": 0.12353515625, | |
| "learning_rate": 0.00018599545077670985, | |
| "loss": 0.0496, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.5972890896970595, | |
| "grad_norm": 0.09619140625, | |
| "learning_rate": 0.0001854652008967335, | |
| "loss": 0.0479, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.6067698688986001, | |
| "grad_norm": 0.1123046875, | |
| "learning_rate": 0.00018492588355892124, | |
| "loss": 0.0508, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.6162506481001407, | |
| "grad_norm": 0.125, | |
| "learning_rate": 0.00018437755598231856, | |
| "loss": 0.0499, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.6257314273016814, | |
| "grad_norm": 0.0986328125, | |
| "learning_rate": 0.00018382027634191524, | |
| "loss": 0.0459, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.6257314273016814, | |
| "eval_loss": 0.04686620458960533, | |
| "eval_runtime": 35.9226, | |
| "eval_samples_per_second": 19.793, | |
| "eval_steps_per_second": 19.793, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.635212206503222, | |
| "grad_norm": 0.12109375, | |
| "learning_rate": 0.00018325410376247294, | |
| "loss": 0.0473, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.6446929857047626, | |
| "grad_norm": 0.1103515625, | |
| "learning_rate": 0.0001826790983122527, | |
| "loss": 0.0443, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.6541737649063032, | |
| "grad_norm": 0.11279296875, | |
| "learning_rate": 0.00018209532099664174, | |
| "loss": 0.0508, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.6636545441078439, | |
| "grad_norm": 0.11083984375, | |
| "learning_rate": 0.00018150283375168114, | |
| "loss": 0.0485, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.6731353233093845, | |
| "grad_norm": 0.10693359375, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.0535, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.6826161025109251, | |
| "grad_norm": 0.10888671875, | |
| "learning_rate": 0.00018029198183161998, | |
| "loss": 0.0617, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.6920968817124658, | |
| "grad_norm": 0.09521484375, | |
| "learning_rate": 0.00017967374562224132, | |
| "loss": 0.0477, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.7015776609140064, | |
| "grad_norm": 0.0966796875, | |
| "learning_rate": 0.00017904705640132718, | |
| "loss": 0.0545, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.711058440115547, | |
| "grad_norm": 0.09423828125, | |
| "learning_rate": 0.00017841198065767107, | |
| "loss": 0.0396, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.7205392193170876, | |
| "grad_norm": 0.0947265625, | |
| "learning_rate": 0.00017776858576983712, | |
| "loss": 0.0483, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.7300199985186282, | |
| "grad_norm": 0.09326171875, | |
| "learning_rate": 0.0001771169399990119, | |
| "loss": 0.0397, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.7300199985186282, | |
| "eval_loss": 0.046032145619392395, | |
| "eval_runtime": 35.9702, | |
| "eval_samples_per_second": 19.766, | |
| "eval_steps_per_second": 19.766, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.7395007777201689, | |
| "grad_norm": 0.09423828125, | |
| "learning_rate": 0.00017645711248176195, | |
| "loss": 0.0414, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.7489815569217095, | |
| "grad_norm": 0.10107421875, | |
| "learning_rate": 0.00017578917322269886, | |
| "loss": 0.0447, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.7584623361232501, | |
| "grad_norm": 0.0966796875, | |
| "learning_rate": 0.00017511319308705198, | |
| "loss": 0.0404, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.7679431153247908, | |
| "grad_norm": 0.099609375, | |
| "learning_rate": 0.0001744292437931502, | |
| "loss": 0.0409, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.7774238945263314, | |
| "grad_norm": 0.12890625, | |
| "learning_rate": 0.00017373739790481262, | |
| "loss": 0.0482, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.786904673727872, | |
| "grad_norm": 0.09375, | |
| "learning_rate": 0.00017303772882365016, | |
| "loss": 0.0356, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.7963854529294127, | |
| "grad_norm": 0.1103515625, | |
| "learning_rate": 0.00017233031078127788, | |
| "loss": 0.0467, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.8058662321309532, | |
| "grad_norm": 0.11767578125, | |
| "learning_rate": 0.00017161521883143934, | |
| "loss": 0.0537, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.8153470113324939, | |
| "grad_norm": 0.095703125, | |
| "learning_rate": 0.00017089252884204377, | |
| "loss": 0.0477, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.8248277905340345, | |
| "grad_norm": 0.09521484375, | |
| "learning_rate": 0.0001701623174871168, | |
| "loss": 0.0466, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.8343085697355751, | |
| "grad_norm": 0.09326171875, | |
| "learning_rate": 0.0001694246622386658, | |
| "loss": 0.0453, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.8343085697355751, | |
| "eval_loss": 0.04489152505993843, | |
| "eval_runtime": 36.0012, | |
| "eval_samples_per_second": 19.749, | |
| "eval_steps_per_second": 19.749, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.8437893489371158, | |
| "grad_norm": 0.08349609375, | |
| "learning_rate": 0.00016867964135846043, | |
| "loss": 0.039, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.8532701281386564, | |
| "grad_norm": 0.10400390625, | |
| "learning_rate": 0.00016792733388972932, | |
| "loss": 0.0521, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.862750907340197, | |
| "grad_norm": 0.0849609375, | |
| "learning_rate": 0.0001671678196487741, | |
| "loss": 0.0481, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.8722316865417377, | |
| "grad_norm": 0.09814453125, | |
| "learning_rate": 0.00016640117921650117, | |
| "loss": 0.0509, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.8817124657432783, | |
| "grad_norm": 0.0927734375, | |
| "learning_rate": 0.00016562749392987254, | |
| "loss": 0.0413, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.8911932449448189, | |
| "grad_norm": 0.08740234375, | |
| "learning_rate": 0.0001648468458732762, | |
| "loss": 0.0405, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.9006740241463596, | |
| "grad_norm": 0.09228515625, | |
| "learning_rate": 0.00016405931786981755, | |
| "loss": 0.0458, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.9101548033479001, | |
| "grad_norm": 0.1005859375, | |
| "learning_rate": 0.00016326499347253207, | |
| "loss": 0.0457, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.9196355825494408, | |
| "grad_norm": 0.09619140625, | |
| "learning_rate": 0.00016246395695552085, | |
| "loss": 0.0439, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.9291163617509814, | |
| "grad_norm": 0.08740234375, | |
| "learning_rate": 0.00016165629330500952, | |
| "loss": 0.0389, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.938597140952522, | |
| "grad_norm": 0.08935546875, | |
| "learning_rate": 0.0001608420882103315, | |
| "loss": 0.04, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.938597140952522, | |
| "eval_loss": 0.04293662682175636, | |
| "eval_runtime": 36.2853, | |
| "eval_samples_per_second": 19.595, | |
| "eval_steps_per_second": 19.595, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.9480779201540627, | |
| "grad_norm": 0.09326171875, | |
| "learning_rate": 0.00016002142805483685, | |
| "loss": 0.0418, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.9575586993556033, | |
| "grad_norm": 0.0830078125, | |
| "learning_rate": 0.0001591943999067273, | |
| "loss": 0.0406, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.9670394785571439, | |
| "grad_norm": 0.09375, | |
| "learning_rate": 0.00015836109150981886, | |
| "loss": 0.0418, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.9765202577586846, | |
| "grad_norm": 0.09765625, | |
| "learning_rate": 0.00015752159127423263, | |
| "loss": 0.0395, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.9860010369602251, | |
| "grad_norm": 0.08154296875, | |
| "learning_rate": 0.0001566759882670146, | |
| "loss": 0.0375, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.9954818161617658, | |
| "grad_norm": 0.1005859375, | |
| "learning_rate": 0.00015582437220268647, | |
| "loss": 0.0463, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.0049625953633063, | |
| "grad_norm": 0.07666015625, | |
| "learning_rate": 0.0001549668334337271, | |
| "loss": 0.0346, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 1.0144433745648471, | |
| "grad_norm": 0.07763671875, | |
| "learning_rate": 0.0001541034629409865, | |
| "loss": 0.0322, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 1.0239241537663877, | |
| "grad_norm": 0.08154296875, | |
| "learning_rate": 0.00015323435232403337, | |
| "loss": 0.0328, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 1.0334049329679282, | |
| "grad_norm": 0.06591796875, | |
| "learning_rate": 0.00015235959379143678, | |
| "loss": 0.0299, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 1.042885712169469, | |
| "grad_norm": 0.08544921875, | |
| "learning_rate": 0.0001514792801509831, | |
| "loss": 0.0338, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.042885712169469, | |
| "eval_loss": 0.04179221764206886, | |
| "eval_runtime": 35.8658, | |
| "eval_samples_per_second": 19.824, | |
| "eval_steps_per_second": 19.824, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.0523664913710096, | |
| "grad_norm": 0.0830078125, | |
| "learning_rate": 0.00015059350479982965, | |
| "loss": 0.0281, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 1.0618472705725501, | |
| "grad_norm": 0.083984375, | |
| "learning_rate": 0.0001497023617145958, | |
| "loss": 0.03, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 1.071328049774091, | |
| "grad_norm": 0.0771484375, | |
| "learning_rate": 0.0001488059454413923, | |
| "loss": 0.0286, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 1.0808088289756315, | |
| "grad_norm": 0.0966796875, | |
| "learning_rate": 0.00014790435108579048, | |
| "loss": 0.0311, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 1.090289608177172, | |
| "grad_norm": 0.0869140625, | |
| "learning_rate": 0.000146997674302732, | |
| "loss": 0.0291, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.0997703873787126, | |
| "grad_norm": 0.08984375, | |
| "learning_rate": 0.00014608601128638027, | |
| "loss": 0.0281, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 1.1092511665802534, | |
| "grad_norm": 0.08837890625, | |
| "learning_rate": 0.00014516945875991472, | |
| "loss": 0.0322, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 1.118731945781794, | |
| "grad_norm": 0.083984375, | |
| "learning_rate": 0.00014424811396526892, | |
| "loss": 0.026, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 1.1282127249833347, | |
| "grad_norm": 0.08837890625, | |
| "learning_rate": 0.00014332207465281364, | |
| "loss": 0.0317, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 1.1376935041848752, | |
| "grad_norm": 0.09912109375, | |
| "learning_rate": 0.0001423914390709861, | |
| "loss": 0.0341, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.1471742833864158, | |
| "grad_norm": 0.095703125, | |
| "learning_rate": 0.00014145630595586607, | |
| "loss": 0.0322, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 1.1471742833864158, | |
| "eval_loss": 0.04224802553653717, | |
| "eval_runtime": 35.7541, | |
| "eval_samples_per_second": 19.886, | |
| "eval_steps_per_second": 19.886, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 1.1566550625879564, | |
| "grad_norm": 0.07763671875, | |
| "learning_rate": 0.00014051677452070065, | |
| "loss": 0.0279, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 1.1661358417894971, | |
| "grad_norm": 0.08837890625, | |
| "learning_rate": 0.00013957294444537808, | |
| "loss": 0.0276, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 1.1756166209910377, | |
| "grad_norm": 0.099609375, | |
| "learning_rate": 0.0001386249158658522, | |
| "loss": 0.0399, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 1.1850974001925783, | |
| "grad_norm": 0.0888671875, | |
| "learning_rate": 0.00013767278936351854, | |
| "loss": 0.0327, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.194578179394119, | |
| "grad_norm": 0.078125, | |
| "learning_rate": 0.00013671666595454295, | |
| "loss": 0.0257, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 1.2040589585956596, | |
| "grad_norm": 0.078125, | |
| "learning_rate": 0.00013575664707914448, | |
| "loss": 0.0268, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 1.2135397377972001, | |
| "grad_norm": 0.0966796875, | |
| "learning_rate": 0.0001347928345908329, | |
| "loss": 0.0368, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 1.223020516998741, | |
| "grad_norm": 0.076171875, | |
| "learning_rate": 0.00013382533074560255, | |
| "loss": 0.0286, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 1.2325012962002815, | |
| "grad_norm": 0.0888671875, | |
| "learning_rate": 0.0001328542381910835, | |
| "loss": 0.0304, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.241982075401822, | |
| "grad_norm": 0.087890625, | |
| "learning_rate": 0.00013187965995565098, | |
| "loss": 0.0304, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 1.2514628546033628, | |
| "grad_norm": 0.0732421875, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.0275, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 1.2514628546033628, | |
| "eval_loss": 0.04160289093852043, | |
| "eval_runtime": 35.8932, | |
| "eval_samples_per_second": 19.809, | |
| "eval_steps_per_second": 19.809, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 1.2609436338049034, | |
| "grad_norm": 0.08203125, | |
| "learning_rate": 0.00012992046039364893, | |
| "loss": 0.0293, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 1.270424413006444, | |
| "grad_norm": 0.087890625, | |
| "learning_rate": 0.0001289360469289838, | |
| "loss": 0.03, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 1.2799051922079845, | |
| "grad_norm": 0.08203125, | |
| "learning_rate": 0.00012794856348516095, | |
| "loss": 0.028, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.2893859714095253, | |
| "grad_norm": 0.0869140625, | |
| "learning_rate": 0.00012695811482955227, | |
| "loss": 0.0293, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 1.2988667506110658, | |
| "grad_norm": 0.09228515625, | |
| "learning_rate": 0.00012596480604412484, | |
| "loss": 0.0341, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 1.3083475298126066, | |
| "grad_norm": 0.07470703125, | |
| "learning_rate": 0.000124968742514292, | |
| "loss": 0.0259, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 1.3178283090141472, | |
| "grad_norm": 0.10009765625, | |
| "learning_rate": 0.00012397002991773275, | |
| "loss": 0.0298, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 1.3273090882156877, | |
| "grad_norm": 0.08837890625, | |
| "learning_rate": 0.0001229687742131796, | |
| "loss": 0.0285, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.3367898674172283, | |
| "grad_norm": 0.091796875, | |
| "learning_rate": 0.00012196508162917677, | |
| "loss": 0.034, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 1.346270646618769, | |
| "grad_norm": 0.0986328125, | |
| "learning_rate": 0.00012095905865281025, | |
| "loss": 0.0314, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 1.3557514258203096, | |
| "grad_norm": 0.0947265625, | |
| "learning_rate": 0.00011995081201840956, | |
| "loss": 0.0322, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 1.3557514258203096, | |
| "eval_loss": 0.041649721562862396, | |
| "eval_runtime": 35.8396, | |
| "eval_samples_per_second": 19.838, | |
| "eval_steps_per_second": 19.838, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 1.3652322050218502, | |
| "grad_norm": 0.083984375, | |
| "learning_rate": 0.00011894044869622403, | |
| "loss": 0.0303, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 1.374712984223391, | |
| "grad_norm": 0.07373046875, | |
| "learning_rate": 0.00011792807588107357, | |
| "loss": 0.0259, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.3841937634249315, | |
| "grad_norm": 0.08740234375, | |
| "learning_rate": 0.00011691380098097597, | |
| "loss": 0.0334, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 1.393674542626472, | |
| "grad_norm": 0.068359375, | |
| "learning_rate": 0.0001158977316057513, | |
| "loss": 0.0245, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 1.4031553218280126, | |
| "grad_norm": 0.09423828125, | |
| "learning_rate": 0.00011487997555560503, | |
| "loss": 0.0322, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 1.4126361010295534, | |
| "grad_norm": 0.0947265625, | |
| "learning_rate": 0.00011386064080969094, | |
| "loss": 0.0338, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 1.422116880231094, | |
| "grad_norm": 0.09326171875, | |
| "learning_rate": 0.00011283983551465511, | |
| "loss": 0.0278, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.4315976594326347, | |
| "grad_norm": 0.087890625, | |
| "learning_rate": 0.0001118176679731619, | |
| "loss": 0.0305, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 1.4410784386341753, | |
| "grad_norm": 0.083984375, | |
| "learning_rate": 0.00011079424663240372, | |
| "loss": 0.0311, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 1.4505592178357158, | |
| "grad_norm": 0.08154296875, | |
| "learning_rate": 0.00010976968007259519, | |
| "loss": 0.0298, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 1.4600399970372564, | |
| "grad_norm": 0.072265625, | |
| "learning_rate": 0.00010874407699545328, | |
| "loss": 0.0266, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 1.4600399970372564, | |
| "eval_loss": 0.04042724519968033, | |
| "eval_runtime": 36.0075, | |
| "eval_samples_per_second": 19.746, | |
| "eval_steps_per_second": 19.746, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 1.4695207762387972, | |
| "grad_norm": 0.083984375, | |
| "learning_rate": 0.00010771754621266466, | |
| "loss": 0.0335, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 1.4790015554403377, | |
| "grad_norm": 0.07470703125, | |
| "learning_rate": 0.00010669019663434117, | |
| "loss": 0.0268, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 1.4884823346418785, | |
| "grad_norm": 0.0849609375, | |
| "learning_rate": 0.00010566213725746506, | |
| "loss": 0.0334, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 1.497963113843419, | |
| "grad_norm": 0.0751953125, | |
| "learning_rate": 0.00010463347715432488, | |
| "loss": 0.0283, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 1.5074438930449596, | |
| "grad_norm": 0.07421875, | |
| "learning_rate": 0.00010360432546094341, | |
| "loss": 0.0284, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 1.5169246722465002, | |
| "grad_norm": 0.08154296875, | |
| "learning_rate": 0.00010257479136549889, | |
| "loss": 0.0306, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.5264054514480407, | |
| "grad_norm": 0.091796875, | |
| "learning_rate": 0.00010154498409674051, | |
| "loss": 0.0347, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 1.5358862306495815, | |
| "grad_norm": 0.087890625, | |
| "learning_rate": 0.00010051501291240008, | |
| "loss": 0.0343, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 1.5453670098511223, | |
| "grad_norm": 0.08544921875, | |
| "learning_rate": 9.948498708759993e-05, | |
| "loss": 0.0313, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 1.5548477890526629, | |
| "grad_norm": 0.0791015625, | |
| "learning_rate": 9.845501590325948e-05, | |
| "loss": 0.0284, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 1.5643285682542034, | |
| "grad_norm": 0.076171875, | |
| "learning_rate": 9.742520863450115e-05, | |
| "loss": 0.0249, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.5643285682542034, | |
| "eval_loss": 0.03973715007305145, | |
| "eval_runtime": 35.8478, | |
| "eval_samples_per_second": 19.834, | |
| "eval_steps_per_second": 19.834, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.573809347455744, | |
| "grad_norm": 0.076171875, | |
| "learning_rate": 9.639567453905661e-05, | |
| "loss": 0.0294, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 1.5832901266572845, | |
| "grad_norm": 0.0703125, | |
| "learning_rate": 9.536652284567513e-05, | |
| "loss": 0.0248, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 1.5927709058588253, | |
| "grad_norm": 0.08251953125, | |
| "learning_rate": 9.433786274253495e-05, | |
| "loss": 0.03, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 1.6022516850603659, | |
| "grad_norm": 0.07373046875, | |
| "learning_rate": 9.330980336565887e-05, | |
| "loss": 0.0269, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 1.6117324642619066, | |
| "grad_norm": 0.10791015625, | |
| "learning_rate": 9.228245378733537e-05, | |
| "loss": 0.0323, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.6212132434634472, | |
| "grad_norm": 0.08837890625, | |
| "learning_rate": 9.125592300454676e-05, | |
| "loss": 0.0328, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 1.6306940226649878, | |
| "grad_norm": 0.076171875, | |
| "learning_rate": 9.023031992740488e-05, | |
| "loss": 0.0245, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 1.6401748018665283, | |
| "grad_norm": 0.0791015625, | |
| "learning_rate": 8.920575336759629e-05, | |
| "loss": 0.0291, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 1.6496555810680689, | |
| "grad_norm": 0.10107421875, | |
| "learning_rate": 8.818233202683814e-05, | |
| "loss": 0.0324, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 1.6591363602696096, | |
| "grad_norm": 0.0859375, | |
| "learning_rate": 8.71601644853449e-05, | |
| "loss": 0.0294, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.6686171394711504, | |
| "grad_norm": 0.0849609375, | |
| "learning_rate": 8.613935919030907e-05, | |
| "loss": 0.0292, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 1.6686171394711504, | |
| "eval_loss": 0.03933083638548851, | |
| "eval_runtime": 36.0124, | |
| "eval_samples_per_second": 19.743, | |
| "eval_steps_per_second": 19.743, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 1.678097918672691, | |
| "grad_norm": 0.07666015625, | |
| "learning_rate": 8.512002444439502e-05, | |
| "loss": 0.028, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 1.6875786978742315, | |
| "grad_norm": 0.08984375, | |
| "learning_rate": 8.410226839424871e-05, | |
| "loss": 0.0312, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 1.697059477075772, | |
| "grad_norm": 0.0732421875, | |
| "learning_rate": 8.308619901902406e-05, | |
| "loss": 0.0253, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 1.7065402562773127, | |
| "grad_norm": 0.083984375, | |
| "learning_rate": 8.207192411892646e-05, | |
| "loss": 0.0278, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.7160210354788534, | |
| "grad_norm": 0.08642578125, | |
| "learning_rate": 8.1059551303776e-05, | |
| "loss": 0.0275, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 1.7255018146803942, | |
| "grad_norm": 0.07568359375, | |
| "learning_rate": 8.004918798159045e-05, | |
| "loss": 0.0265, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 1.7349825938819348, | |
| "grad_norm": 0.076171875, | |
| "learning_rate": 7.904094134718976e-05, | |
| "loss": 0.0285, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 1.7444633730834753, | |
| "grad_norm": 0.09228515625, | |
| "learning_rate": 7.803491837082324e-05, | |
| "loss": 0.0349, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 1.7539441522850159, | |
| "grad_norm": 0.09521484375, | |
| "learning_rate": 7.703122578682046e-05, | |
| "loss": 0.0325, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 1.7634249314865564, | |
| "grad_norm": 0.0751953125, | |
| "learning_rate": 7.602997008226726e-05, | |
| "loss": 0.0283, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 1.7729057106880972, | |
| "grad_norm": 0.0869140625, | |
| "learning_rate": 7.5031257485708e-05, | |
| "loss": 0.031, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 1.7729057106880972, | |
| "eval_loss": 0.03848842531442642, | |
| "eval_runtime": 35.9251, | |
| "eval_samples_per_second": 19.791, | |
| "eval_steps_per_second": 19.791, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 1.7823864898896378, | |
| "grad_norm": 0.07861328125, | |
| "learning_rate": 7.403519395587521e-05, | |
| "loss": 0.03, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 1.7918672690911785, | |
| "grad_norm": 0.07177734375, | |
| "learning_rate": 7.304188517044774e-05, | |
| "loss": 0.0281, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 1.801348048292719, | |
| "grad_norm": 0.07568359375, | |
| "learning_rate": 7.205143651483906e-05, | |
| "loss": 0.0253, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.8108288274942597, | |
| "grad_norm": 0.06787109375, | |
| "learning_rate": 7.106395307101621e-05, | |
| "loss": 0.0264, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 1.8203096066958002, | |
| "grad_norm": 0.07177734375, | |
| "learning_rate": 7.007953960635109e-05, | |
| "loss": 0.0268, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 1.8297903858973408, | |
| "grad_norm": 0.08740234375, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 0.0308, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 1.8392711650988816, | |
| "grad_norm": 0.07275390625, | |
| "learning_rate": 6.812034004434903e-05, | |
| "loss": 0.0275, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 1.8487519443004223, | |
| "grad_norm": 0.07568359375, | |
| "learning_rate": 6.714576180891654e-05, | |
| "loss": 0.0253, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 1.858232723501963, | |
| "grad_norm": 0.07177734375, | |
| "learning_rate": 6.617466925439746e-05, | |
| "loss": 0.0262, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 1.8677135027035034, | |
| "grad_norm": 0.06787109375, | |
| "learning_rate": 6.520716540916709e-05, | |
| "loss": 0.0257, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 1.877194281905044, | |
| "grad_norm": 0.0751953125, | |
| "learning_rate": 6.424335292085553e-05, | |
| "loss": 0.0265, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 1.877194281905044, | |
| "eval_loss": 0.037521231919527054, | |
| "eval_runtime": 36.0213, | |
| "eval_samples_per_second": 19.738, | |
| "eval_steps_per_second": 19.738, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 1.8866750611065846, | |
| "grad_norm": 0.10107421875, | |
| "learning_rate": 6.32833340454571e-05, | |
| "loss": 0.0269, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 1.8961558403081253, | |
| "grad_norm": 0.0751953125, | |
| "learning_rate": 6.232721063648148e-05, | |
| "loss": 0.0279, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.905636619509666, | |
| "grad_norm": 0.0791015625, | |
| "learning_rate": 6.137508413414784e-05, | |
| "loss": 0.0301, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 1.9151173987112067, | |
| "grad_norm": 0.0791015625, | |
| "learning_rate": 6.0427055554621913e-05, | |
| "loss": 0.0289, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 1.9245981779127472, | |
| "grad_norm": 0.08349609375, | |
| "learning_rate": 5.948322547929939e-05, | |
| "loss": 0.0239, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 1.9340789571142878, | |
| "grad_norm": 0.07373046875, | |
| "learning_rate": 5.854369404413398e-05, | |
| "loss": 0.023, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 1.9435597363158283, | |
| "grad_norm": 0.080078125, | |
| "learning_rate": 5.7608560929013946e-05, | |
| "loss": 0.0274, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 1.9530405155173691, | |
| "grad_norm": 0.08447265625, | |
| "learning_rate": 5.667792534718639e-05, | |
| "loss": 0.0308, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 1.9625212947189097, | |
| "grad_norm": 0.0732421875, | |
| "learning_rate": 5.5751886034731115e-05, | |
| "loss": 0.0253, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 1.9720020739204505, | |
| "grad_norm": 0.0732421875, | |
| "learning_rate": 5.483054124008528e-05, | |
| "loss": 0.0261, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 1.981482853121991, | |
| "grad_norm": 0.07763671875, | |
| "learning_rate": 5.391398871361972e-05, | |
| "loss": 0.0273, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 1.981482853121991, | |
| "eval_loss": 0.037543829530477524, | |
| "eval_runtime": 36.1289, | |
| "eval_samples_per_second": 19.68, | |
| "eval_steps_per_second": 19.68, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 1.9909636323235316, | |
| "grad_norm": 0.07958984375, | |
| "learning_rate": 5.300232569726804e-05, | |
| "loss": 0.0284, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.000444411525072, | |
| "grad_norm": 0.08544921875, | |
| "learning_rate": 5.2095648914209525e-05, | |
| "loss": 0.0338, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 2.0099251907266127, | |
| "grad_norm": 0.06298828125, | |
| "learning_rate": 5.119405455860772e-05, | |
| "loss": 0.0198, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 2.0194059699281537, | |
| "grad_norm": 0.05810546875, | |
| "learning_rate": 5.029763828540419e-05, | |
| "loss": 0.0192, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 2.0288867491296942, | |
| "grad_norm": 0.059326171875, | |
| "learning_rate": 4.940649520017035e-05, | |
| "loss": 0.0202, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 2.038367528331235, | |
| "grad_norm": 0.060546875, | |
| "learning_rate": 4.852071984901696e-05, | |
| "loss": 0.0199, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 2.0478483075327754, | |
| "grad_norm": 0.05078125, | |
| "learning_rate": 4.7640406208563224e-05, | |
| "loss": 0.0169, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 2.057329086734316, | |
| "grad_norm": 0.058349609375, | |
| "learning_rate": 4.676564767596663e-05, | |
| "loss": 0.0193, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 2.0668098659358565, | |
| "grad_norm": 0.05712890625, | |
| "learning_rate": 4.5896537059013536e-05, | |
| "loss": 0.0175, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 2.076290645137397, | |
| "grad_norm": 0.056396484375, | |
| "learning_rate": 4.503316656627294e-05, | |
| "loss": 0.0193, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 2.085771424338938, | |
| "grad_norm": 0.06298828125, | |
| "learning_rate": 4.417562779731355e-05, | |
| "loss": 0.0175, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.085771424338938, | |
| "eval_loss": 0.03771064057946205, | |
| "eval_runtime": 36.0692, | |
| "eval_samples_per_second": 19.712, | |
| "eval_steps_per_second": 19.712, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.0952522035404786, | |
| "grad_norm": 0.0693359375, | |
| "learning_rate": 4.3324011732985433e-05, | |
| "loss": 0.0205, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 2.104732982742019, | |
| "grad_norm": 0.0693359375, | |
| "learning_rate": 4.247840872576739e-05, | |
| "loss": 0.0184, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 2.1142137619435597, | |
| "grad_norm": 0.0634765625, | |
| "learning_rate": 4.163890849018114e-05, | |
| "loss": 0.0191, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 2.1236945411451003, | |
| "grad_norm": 0.057373046875, | |
| "learning_rate": 4.0805600093272735e-05, | |
| "loss": 0.0157, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 2.133175320346641, | |
| "grad_norm": 0.06640625, | |
| "learning_rate": 3.997857194516319e-05, | |
| "loss": 0.019, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 2.142656099548182, | |
| "grad_norm": 0.06494140625, | |
| "learning_rate": 3.9157911789668525e-05, | |
| "loss": 0.0173, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 2.1521368787497224, | |
| "grad_norm": 0.064453125, | |
| "learning_rate": 3.8343706694990465e-05, | |
| "loss": 0.0169, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 2.161617657951263, | |
| "grad_norm": 0.06689453125, | |
| "learning_rate": 3.753604304447915e-05, | |
| "loss": 0.0166, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 2.1710984371528035, | |
| "grad_norm": 0.076171875, | |
| "learning_rate": 3.6735006527467965e-05, | |
| "loss": 0.0166, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 2.180579216354344, | |
| "grad_norm": 0.064453125, | |
| "learning_rate": 3.594068213018249e-05, | |
| "loss": 0.0172, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.1900599955558846, | |
| "grad_norm": 0.06884765625, | |
| "learning_rate": 3.515315412672384e-05, | |
| "loss": 0.0168, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 2.1900599955558846, | |
| "eval_loss": 0.03964013606309891, | |
| "eval_runtime": 36.2659, | |
| "eval_samples_per_second": 19.605, | |
| "eval_steps_per_second": 19.605, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 2.199540774757425, | |
| "grad_norm": 0.0751953125, | |
| "learning_rate": 3.437250607012748e-05, | |
| "loss": 0.0166, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 2.209021553958966, | |
| "grad_norm": 0.072265625, | |
| "learning_rate": 3.359882078349883e-05, | |
| "loss": 0.0181, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 2.2185023331605067, | |
| "grad_norm": 0.0673828125, | |
| "learning_rate": 3.283218035122592e-05, | |
| "loss": 0.0179, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 2.2279831123620473, | |
| "grad_norm": 0.09130859375, | |
| "learning_rate": 3.207266611027069e-05, | |
| "loss": 0.016, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 2.237463891563588, | |
| "grad_norm": 0.08447265625, | |
| "learning_rate": 3.132035864153958e-05, | |
| "loss": 0.0192, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 2.2469446707651284, | |
| "grad_norm": 0.08154296875, | |
| "learning_rate": 3.057533776133421e-05, | |
| "loss": 0.0183, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 2.2564254499666694, | |
| "grad_norm": 0.06640625, | |
| "learning_rate": 2.98376825128832e-05, | |
| "loss": 0.0146, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 2.26590622916821, | |
| "grad_norm": 0.07373046875, | |
| "learning_rate": 2.910747115795628e-05, | |
| "loss": 0.0171, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 2.2753870083697505, | |
| "grad_norm": 0.072265625, | |
| "learning_rate": 2.8384781168560693e-05, | |
| "loss": 0.0168, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.284867787571291, | |
| "grad_norm": 0.0859375, | |
| "learning_rate": 2.766968921872213e-05, | |
| "loss": 0.0166, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 2.2943485667728316, | |
| "grad_norm": 0.07470703125, | |
| "learning_rate": 2.6962271176349852e-05, | |
| "loss": 0.0182, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 2.2943485667728316, | |
| "eval_loss": 0.04028235375881195, | |
| "eval_runtime": 36.1866, | |
| "eval_samples_per_second": 19.648, | |
| "eval_steps_per_second": 19.648, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 2.303829345974372, | |
| "grad_norm": 0.06640625, | |
| "learning_rate": 2.626260209518737e-05, | |
| "loss": 0.0159, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 2.3133101251759127, | |
| "grad_norm": 0.06884765625, | |
| "learning_rate": 2.5570756206849832e-05, | |
| "loss": 0.0154, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 2.3227909043774533, | |
| "grad_norm": 0.064453125, | |
| "learning_rate": 2.4886806912948035e-05, | |
| "loss": 0.0148, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 2.3322716835789943, | |
| "grad_norm": 0.07080078125, | |
| "learning_rate": 2.4210826777301153e-05, | |
| "loss": 0.0175, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 2.341752462780535, | |
| "grad_norm": 0.06494140625, | |
| "learning_rate": 2.3542887518238056e-05, | |
| "loss": 0.0155, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 2.3512332419820754, | |
| "grad_norm": 0.078125, | |
| "learning_rate": 2.288306000098811e-05, | |
| "loss": 0.0166, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 2.360714021183616, | |
| "grad_norm": 0.083984375, | |
| "learning_rate": 2.2231414230162894e-05, | |
| "loss": 0.022, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 2.3701948003851565, | |
| "grad_norm": 0.09033203125, | |
| "learning_rate": 2.1588019342328968e-05, | |
| "loss": 0.0234, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.3796755795866975, | |
| "grad_norm": 0.07666015625, | |
| "learning_rate": 2.0952943598672846e-05, | |
| "loss": 0.0176, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 2.389156358788238, | |
| "grad_norm": 0.06982421875, | |
| "learning_rate": 2.0326254377758703e-05, | |
| "loss": 0.0189, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 2.3986371379897786, | |
| "grad_norm": 0.0751953125, | |
| "learning_rate": 1.9708018168380037e-05, | |
| "loss": 0.0201, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 2.3986371379897786, | |
| "eval_loss": 0.039680514484643936, | |
| "eval_runtime": 36.0607, | |
| "eval_samples_per_second": 19.717, | |
| "eval_steps_per_second": 19.717, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 2.408117917191319, | |
| "grad_norm": 0.06298828125, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 0.0147, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 2.4175986963928597, | |
| "grad_norm": 0.0634765625, | |
| "learning_rate": 1.8497166248318876e-05, | |
| "loss": 0.0172, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 2.4270794755944003, | |
| "grad_norm": 0.08349609375, | |
| "learning_rate": 1.7904679003358283e-05, | |
| "loss": 0.0173, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 2.436560254795941, | |
| "grad_norm": 0.07177734375, | |
| "learning_rate": 1.7320901687747292e-05, | |
| "loss": 0.0174, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 2.446041033997482, | |
| "grad_norm": 0.08203125, | |
| "learning_rate": 1.674589623752707e-05, | |
| "loss": 0.0184, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 2.4555218131990224, | |
| "grad_norm": 0.0947265625, | |
| "learning_rate": 1.617972365808481e-05, | |
| "loss": 0.0192, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 2.465002592400563, | |
| "grad_norm": 0.06005859375, | |
| "learning_rate": 1.562244401768144e-05, | |
| "loss": 0.0129, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.4744833716021035, | |
| "grad_norm": 0.0791015625, | |
| "learning_rate": 1.507411644107879e-05, | |
| "loss": 0.0215, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 2.483964150803644, | |
| "grad_norm": 0.078125, | |
| "learning_rate": 1.4534799103266505e-05, | |
| "loss": 0.0194, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 2.4934449300051846, | |
| "grad_norm": 0.07275390625, | |
| "learning_rate": 1.4004549223290164e-05, | |
| "loss": 0.0168, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 2.5029257092067256, | |
| "grad_norm": 0.05810546875, | |
| "learning_rate": 1.3483423058180421e-05, | |
| "loss": 0.0138, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 2.5029257092067256, | |
| "eval_loss": 0.039309222251176834, | |
| "eval_runtime": 36.2397, | |
| "eval_samples_per_second": 19.619, | |
| "eval_steps_per_second": 19.619, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 2.512406488408266, | |
| "grad_norm": 0.06787109375, | |
| "learning_rate": 1.2971475896984475e-05, | |
| "loss": 0.0157, | |
| "step": 265 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 315, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 53, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.742595805273129e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |