| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.9864454484852976, | |
| "eval_steps": 11, | |
| "global_step": 315, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.009480779201540626, | |
| "grad_norm": 0.38671875, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4197, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009480779201540626, | |
| "eval_loss": 0.41279804706573486, | |
| "eval_runtime": 34.6855, | |
| "eval_samples_per_second": 20.498, | |
| "eval_steps_per_second": 20.498, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.018961558403081252, | |
| "grad_norm": 0.359375, | |
| "learning_rate": 4e-05, | |
| "loss": 0.3966, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02844233760462188, | |
| "grad_norm": 0.388671875, | |
| "learning_rate": 6e-05, | |
| "loss": 0.4257, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.037923116806162505, | |
| "grad_norm": 0.408203125, | |
| "learning_rate": 8e-05, | |
| "loss": 0.4026, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04740389600770313, | |
| "grad_norm": 0.384765625, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3229, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05688467520924376, | |
| "grad_norm": 0.251953125, | |
| "learning_rate": 0.00012, | |
| "loss": 0.2408, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.06636545441078438, | |
| "grad_norm": 0.203125, | |
| "learning_rate": 0.00014, | |
| "loss": 0.1709, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.07584623361232501, | |
| "grad_norm": 0.150390625, | |
| "learning_rate": 0.00016, | |
| "loss": 0.1328, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.08532701281386564, | |
| "grad_norm": 0.1201171875, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0993, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.09480779201540626, | |
| "grad_norm": 0.10888671875, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0914, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.10428857121694689, | |
| "grad_norm": 0.119140625, | |
| "learning_rate": 0.00019999469523400122, | |
| "loss": 0.0885, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.10428857121694689, | |
| "eval_loss": 0.07809103280305862, | |
| "eval_runtime": 34.2892, | |
| "eval_samples_per_second": 20.735, | |
| "eval_steps_per_second": 20.735, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.11376935041848751, | |
| "grad_norm": 0.09228515625, | |
| "learning_rate": 0.00019997878149881574, | |
| "loss": 0.0761, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.12325012962002814, | |
| "grad_norm": 0.0703125, | |
| "learning_rate": 0.0001999522604828164, | |
| "loss": 0.0683, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.13273090882156877, | |
| "grad_norm": 0.059326171875, | |
| "learning_rate": 0.00019991513499975882, | |
| "loss": 0.0696, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.1422116880231094, | |
| "grad_norm": 0.044921875, | |
| "learning_rate": 0.00019986740898848306, | |
| "loss": 0.0615, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.15169246722465002, | |
| "grad_norm": 0.054443359375, | |
| "learning_rate": 0.00019980908751249555, | |
| "loss": 0.0625, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.16117324642619066, | |
| "grad_norm": 0.04736328125, | |
| "learning_rate": 0.00019974017675943192, | |
| "loss": 0.0598, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.17065402562773127, | |
| "grad_norm": 0.039306640625, | |
| "learning_rate": 0.0001996606840404006, | |
| "loss": 0.0573, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1801348048292719, | |
| "grad_norm": 0.036376953125, | |
| "learning_rate": 0.00019957061778920701, | |
| "loss": 0.0482, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.18961558403081252, | |
| "grad_norm": 0.039306640625, | |
| "learning_rate": 0.0001994699875614589, | |
| "loss": 0.0555, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.19909636323235316, | |
| "grad_norm": 0.0380859375, | |
| "learning_rate": 0.00019935880403355253, | |
| "loss": 0.0495, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.20857714243389378, | |
| "grad_norm": 0.038818359375, | |
| "learning_rate": 0.00019923707900153982, | |
| "loss": 0.0482, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.20857714243389378, | |
| "eval_loss": 0.05171125754714012, | |
| "eval_runtime": 34.4113, | |
| "eval_samples_per_second": 20.662, | |
| "eval_steps_per_second": 20.662, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.21805792163543442, | |
| "grad_norm": 0.038818359375, | |
| "learning_rate": 0.00019910482537987702, | |
| "loss": 0.0529, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.22753870083697503, | |
| "grad_norm": 0.031494140625, | |
| "learning_rate": 0.0001989620572000544, | |
| "loss": 0.0495, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.23701948003851567, | |
| "grad_norm": 0.0380859375, | |
| "learning_rate": 0.00019880878960910772, | |
| "loss": 0.059, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.24650025924005628, | |
| "grad_norm": 0.032470703125, | |
| "learning_rate": 0.00019864503886801106, | |
| "loss": 0.0545, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.2559810384415969, | |
| "grad_norm": 0.029296875, | |
| "learning_rate": 0.00019847082234995171, | |
| "loss": 0.0417, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.26546181764313753, | |
| "grad_norm": 0.037109375, | |
| "learning_rate": 0.00019828615853848688, | |
| "loss": 0.0459, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.27494259684467814, | |
| "grad_norm": 0.027099609375, | |
| "learning_rate": 0.00019809106702558277, | |
| "loss": 0.0412, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.2844233760462188, | |
| "grad_norm": 0.032470703125, | |
| "learning_rate": 0.0001978855685095358, | |
| "loss": 0.0403, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2939041552477594, | |
| "grad_norm": 0.0289306640625, | |
| "learning_rate": 0.00019766968479277683, | |
| "loss": 0.0463, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.30338493444930004, | |
| "grad_norm": 0.0301513671875, | |
| "learning_rate": 0.00019744343877955788, | |
| "loss": 0.041, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.3128657136508407, | |
| "grad_norm": 0.033447265625, | |
| "learning_rate": 0.00019720685447352209, | |
| "loss": 0.045, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.3128657136508407, | |
| "eval_loss": 0.04294149950146675, | |
| "eval_runtime": 34.2719, | |
| "eval_samples_per_second": 20.746, | |
| "eval_steps_per_second": 20.746, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.3223464928523813, | |
| "grad_norm": 0.028076171875, | |
| "learning_rate": 0.0001969599569751571, | |
| "loss": 0.0369, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.33182727205392193, | |
| "grad_norm": 0.029296875, | |
| "learning_rate": 0.00019670277247913205, | |
| "loss": 0.0465, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.34130805125546254, | |
| "grad_norm": 0.032958984375, | |
| "learning_rate": 0.0001964353282715183, | |
| "loss": 0.0382, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.3507888304570032, | |
| "grad_norm": 0.0299072265625, | |
| "learning_rate": 0.00019615765272689461, | |
| "loss": 0.0442, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.3602696096585438, | |
| "grad_norm": 0.0322265625, | |
| "learning_rate": 0.00019586977530533677, | |
| "loss": 0.0481, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.36975038886008443, | |
| "grad_norm": 0.028076171875, | |
| "learning_rate": 0.00019557172654929196, | |
| "loss": 0.0423, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.37923116806162505, | |
| "grad_norm": 0.0299072265625, | |
| "learning_rate": 0.00019526353808033825, | |
| "loss": 0.0384, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3887119472631657, | |
| "grad_norm": 0.027587890625, | |
| "learning_rate": 0.00019494524259582992, | |
| "loss": 0.0404, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.3981927264647063, | |
| "grad_norm": 0.0286865234375, | |
| "learning_rate": 0.00019461687386542826, | |
| "loss": 0.0394, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.40767350566624694, | |
| "grad_norm": 0.032958984375, | |
| "learning_rate": 0.00019427846672751873, | |
| "loss": 0.0351, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.41715428486778755, | |
| "grad_norm": 0.02783203125, | |
| "learning_rate": 0.00019393005708551498, | |
| "loss": 0.0425, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.41715428486778755, | |
| "eval_loss": 0.03996235132217407, | |
| "eval_runtime": 34.3007, | |
| "eval_samples_per_second": 20.728, | |
| "eval_steps_per_second": 20.728, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.4266350640693282, | |
| "grad_norm": 0.030517578125, | |
| "learning_rate": 0.00019357168190404936, | |
| "loss": 0.0365, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.43611584327086883, | |
| "grad_norm": 0.032958984375, | |
| "learning_rate": 0.00019320337920505153, | |
| "loss": 0.0438, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.44559662247240944, | |
| "grad_norm": 0.0306396484375, | |
| "learning_rate": 0.00019282518806371414, | |
| "loss": 0.044, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.45507740167395005, | |
| "grad_norm": 0.037841796875, | |
| "learning_rate": 0.0001924371486043473, | |
| "loss": 0.0496, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.4645581808754907, | |
| "grad_norm": 0.0284423828125, | |
| "learning_rate": 0.0001920393019961217, | |
| "loss": 0.0369, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.47403896007703133, | |
| "grad_norm": 0.0341796875, | |
| "learning_rate": 0.0001916316904487005, | |
| "loss": 0.0399, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.48351973927857195, | |
| "grad_norm": 0.0255126953125, | |
| "learning_rate": 0.00019121435720776122, | |
| "loss": 0.0363, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.49300051848011256, | |
| "grad_norm": 0.0311279296875, | |
| "learning_rate": 0.0001907873465504076, | |
| "loss": 0.0384, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.5024812976816532, | |
| "grad_norm": 0.03271484375, | |
| "learning_rate": 0.00019035070378047204, | |
| "loss": 0.0371, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.5119620768831938, | |
| "grad_norm": 0.0263671875, | |
| "learning_rate": 0.00018990447522370884, | |
| "loss": 0.0351, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.5214428560847345, | |
| "grad_norm": 0.033203125, | |
| "learning_rate": 0.00018944870822287956, | |
| "loss": 0.0411, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.5214428560847345, | |
| "eval_loss": 0.03788134828209877, | |
| "eval_runtime": 34.6048, | |
| "eval_samples_per_second": 20.546, | |
| "eval_steps_per_second": 20.546, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.5309236352862751, | |
| "grad_norm": 0.0272216796875, | |
| "learning_rate": 0.00018898345113272998, | |
| "loss": 0.0337, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.5404044144878157, | |
| "grad_norm": 0.0245361328125, | |
| "learning_rate": 0.00018850875331485995, | |
| "loss": 0.0309, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.5498851936893563, | |
| "grad_norm": 0.027587890625, | |
| "learning_rate": 0.00018802466513248632, | |
| "loss": 0.0329, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.559365972890897, | |
| "grad_norm": 0.0267333984375, | |
| "learning_rate": 0.00018753123794509974, | |
| "loss": 0.0365, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.5688467520924376, | |
| "grad_norm": 0.02734375, | |
| "learning_rate": 0.00018702852410301554, | |
| "loss": 0.0373, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.5783275312939782, | |
| "grad_norm": 0.025390625, | |
| "learning_rate": 0.0001865165769418196, | |
| "loss": 0.0375, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.5878083104955188, | |
| "grad_norm": 0.02978515625, | |
| "learning_rate": 0.00018599545077670985, | |
| "loss": 0.0376, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.5972890896970595, | |
| "grad_norm": 0.0242919921875, | |
| "learning_rate": 0.0001854652008967335, | |
| "loss": 0.0337, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.6067698688986001, | |
| "grad_norm": 0.02880859375, | |
| "learning_rate": 0.00018492588355892124, | |
| "loss": 0.0379, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.6162506481001407, | |
| "grad_norm": 0.0322265625, | |
| "learning_rate": 0.00018437755598231856, | |
| "loss": 0.0392, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.6257314273016814, | |
| "grad_norm": 0.0269775390625, | |
| "learning_rate": 0.00018382027634191524, | |
| "loss": 0.0348, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.6257314273016814, | |
| "eval_loss": 0.03594927862286568, | |
| "eval_runtime": 34.2756, | |
| "eval_samples_per_second": 20.744, | |
| "eval_steps_per_second": 20.744, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.635212206503222, | |
| "grad_norm": 0.03515625, | |
| "learning_rate": 0.00018325410376247294, | |
| "loss": 0.0379, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.6446929857047626, | |
| "grad_norm": 0.0301513671875, | |
| "learning_rate": 0.0001826790983122527, | |
| "loss": 0.0317, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.6541737649063032, | |
| "grad_norm": 0.0296630859375, | |
| "learning_rate": 0.00018209532099664174, | |
| "loss": 0.0366, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.6636545441078439, | |
| "grad_norm": 0.0272216796875, | |
| "learning_rate": 0.00018150283375168114, | |
| "loss": 0.0345, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.6731353233093845, | |
| "grad_norm": 0.03125, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.0368, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.6826161025109251, | |
| "grad_norm": 0.032470703125, | |
| "learning_rate": 0.00018029198183161998, | |
| "loss": 0.0455, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.6920968817124658, | |
| "grad_norm": 0.029296875, | |
| "learning_rate": 0.00017967374562224132, | |
| "loss": 0.0362, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.7015776609140064, | |
| "grad_norm": 0.0311279296875, | |
| "learning_rate": 0.00017904705640132718, | |
| "loss": 0.0388, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.711058440115547, | |
| "grad_norm": 0.02685546875, | |
| "learning_rate": 0.00017841198065767107, | |
| "loss": 0.0288, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.7205392193170876, | |
| "grad_norm": 0.0302734375, | |
| "learning_rate": 0.00017776858576983712, | |
| "loss": 0.0349, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.7300199985186282, | |
| "grad_norm": 0.026611328125, | |
| "learning_rate": 0.0001771169399990119, | |
| "loss": 0.0288, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.7300199985186282, | |
| "eval_loss": 0.03419337794184685, | |
| "eval_runtime": 34.3669, | |
| "eval_samples_per_second": 20.688, | |
| "eval_steps_per_second": 20.688, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.7395007777201689, | |
| "grad_norm": 0.0240478515625, | |
| "learning_rate": 0.00017645711248176195, | |
| "loss": 0.0285, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.7489815569217095, | |
| "grad_norm": 0.025390625, | |
| "learning_rate": 0.00017578917322269886, | |
| "loss": 0.0338, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.7584623361232501, | |
| "grad_norm": 0.0281982421875, | |
| "learning_rate": 0.00017511319308705198, | |
| "loss": 0.0316, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.7679431153247908, | |
| "grad_norm": 0.025146484375, | |
| "learning_rate": 0.0001744292437931502, | |
| "loss": 0.0306, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.7774238945263314, | |
| "grad_norm": 0.027099609375, | |
| "learning_rate": 0.00017373739790481262, | |
| "loss": 0.0335, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.786904673727872, | |
| "grad_norm": 0.0242919921875, | |
| "learning_rate": 0.00017303772882365016, | |
| "loss": 0.0271, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.7963854529294127, | |
| "grad_norm": 0.028564453125, | |
| "learning_rate": 0.00017233031078127788, | |
| "loss": 0.0334, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.8058662321309532, | |
| "grad_norm": 0.0299072265625, | |
| "learning_rate": 0.00017161521883143934, | |
| "loss": 0.0403, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.8153470113324939, | |
| "grad_norm": 0.0294189453125, | |
| "learning_rate": 0.00017089252884204377, | |
| "loss": 0.0368, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.8248277905340345, | |
| "grad_norm": 0.03369140625, | |
| "learning_rate": 0.0001701623174871168, | |
| "loss": 0.0335, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.8343085697355751, | |
| "grad_norm": 0.0277099609375, | |
| "learning_rate": 0.0001694246622386658, | |
| "loss": 0.0339, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.8343085697355751, | |
| "eval_loss": 0.033091045916080475, | |
| "eval_runtime": 34.4475, | |
| "eval_samples_per_second": 20.64, | |
| "eval_steps_per_second": 20.64, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.8437893489371158, | |
| "grad_norm": 0.02392578125, | |
| "learning_rate": 0.00016867964135846043, | |
| "loss": 0.0241, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.8532701281386564, | |
| "grad_norm": 0.0361328125, | |
| "learning_rate": 0.00016792733388972932, | |
| "loss": 0.0387, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.862750907340197, | |
| "grad_norm": 0.0260009765625, | |
| "learning_rate": 0.0001671678196487741, | |
| "loss": 0.0346, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.8722316865417377, | |
| "grad_norm": 0.0284423828125, | |
| "learning_rate": 0.00016640117921650117, | |
| "loss": 0.0378, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.8817124657432783, | |
| "grad_norm": 0.0279541015625, | |
| "learning_rate": 0.00016562749392987254, | |
| "loss": 0.0294, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.8911932449448189, | |
| "grad_norm": 0.0272216796875, | |
| "learning_rate": 0.0001648468458732762, | |
| "loss": 0.0308, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.9006740241463596, | |
| "grad_norm": 0.0242919921875, | |
| "learning_rate": 0.00016405931786981755, | |
| "loss": 0.0326, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.9101548033479001, | |
| "grad_norm": 0.0262451171875, | |
| "learning_rate": 0.00016326499347253207, | |
| "loss": 0.032, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.9196355825494408, | |
| "grad_norm": 0.0264892578125, | |
| "learning_rate": 0.00016246395695552085, | |
| "loss": 0.0321, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.9291163617509814, | |
| "grad_norm": 0.0244140625, | |
| "learning_rate": 0.00016165629330500952, | |
| "loss": 0.0301, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.938597140952522, | |
| "grad_norm": 0.029052734375, | |
| "learning_rate": 0.0001608420882103315, | |
| "loss": 0.0297, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.938597140952522, | |
| "eval_loss": 0.03182319179177284, | |
| "eval_runtime": 34.2304, | |
| "eval_samples_per_second": 20.771, | |
| "eval_steps_per_second": 20.771, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.9480779201540627, | |
| "grad_norm": 0.0302734375, | |
| "learning_rate": 0.00016002142805483685, | |
| "loss": 0.0327, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.9575586993556033, | |
| "grad_norm": 0.0260009765625, | |
| "learning_rate": 0.0001591943999067273, | |
| "loss": 0.0285, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.9670394785571439, | |
| "grad_norm": 0.032470703125, | |
| "learning_rate": 0.00015836109150981886, | |
| "loss": 0.0308, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.9765202577586846, | |
| "grad_norm": 0.0283203125, | |
| "learning_rate": 0.00015752159127423263, | |
| "loss": 0.0301, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.9860010369602251, | |
| "grad_norm": 0.027587890625, | |
| "learning_rate": 0.0001566759882670146, | |
| "loss": 0.0287, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.9954818161617658, | |
| "grad_norm": 0.025634765625, | |
| "learning_rate": 0.00015582437220268647, | |
| "loss": 0.031, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.0049625953633063, | |
| "grad_norm": 0.02490234375, | |
| "learning_rate": 0.0001549668334337271, | |
| "loss": 0.0275, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 1.0144433745648471, | |
| "grad_norm": 0.03369140625, | |
| "learning_rate": 0.0001541034629409865, | |
| "loss": 0.0302, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 1.0239241537663877, | |
| "grad_norm": 0.027099609375, | |
| "learning_rate": 0.00015323435232403337, | |
| "loss": 0.0308, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 1.0334049329679282, | |
| "grad_norm": 0.0240478515625, | |
| "learning_rate": 0.00015235959379143678, | |
| "loss": 0.0247, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 1.042885712169469, | |
| "grad_norm": 0.0255126953125, | |
| "learning_rate": 0.0001514792801509831, | |
| "loss": 0.0281, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.042885712169469, | |
| "eval_loss": 0.03116695210337639, | |
| "eval_runtime": 34.429, | |
| "eval_samples_per_second": 20.651, | |
| "eval_steps_per_second": 20.651, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.0523664913710096, | |
| "grad_norm": 0.0277099609375, | |
| "learning_rate": 0.00015059350479982965, | |
| "loss": 0.0243, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 1.0618472705725501, | |
| "grad_norm": 0.028564453125, | |
| "learning_rate": 0.0001497023617145958, | |
| "loss": 0.0274, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 1.071328049774091, | |
| "grad_norm": 0.0301513671875, | |
| "learning_rate": 0.0001488059454413923, | |
| "loss": 0.0265, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 1.0808088289756315, | |
| "grad_norm": 0.0296630859375, | |
| "learning_rate": 0.00014790435108579048, | |
| "loss": 0.0287, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 1.090289608177172, | |
| "grad_norm": 0.025390625, | |
| "learning_rate": 0.000146997674302732, | |
| "loss": 0.0255, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.0997703873787126, | |
| "grad_norm": 0.02685546875, | |
| "learning_rate": 0.00014608601128638027, | |
| "loss": 0.0258, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 1.1092511665802534, | |
| "grad_norm": 0.0277099609375, | |
| "learning_rate": 0.00014516945875991472, | |
| "loss": 0.0326, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 1.118731945781794, | |
| "grad_norm": 0.0260009765625, | |
| "learning_rate": 0.00014424811396526892, | |
| "loss": 0.0241, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 1.1282127249833347, | |
| "grad_norm": 0.0284423828125, | |
| "learning_rate": 0.00014332207465281364, | |
| "loss": 0.0276, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 1.1376935041848752, | |
| "grad_norm": 0.0306396484375, | |
| "learning_rate": 0.0001423914390709861, | |
| "loss": 0.0283, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.1471742833864158, | |
| "grad_norm": 0.0274658203125, | |
| "learning_rate": 0.00014145630595586607, | |
| "loss": 0.027, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 1.1471742833864158, | |
| "eval_loss": 0.030295666307210922, | |
| "eval_runtime": 34.4847, | |
| "eval_samples_per_second": 20.618, | |
| "eval_steps_per_second": 20.618, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 1.1566550625879564, | |
| "grad_norm": 0.0244140625, | |
| "learning_rate": 0.00014051677452070065, | |
| "loss": 0.0248, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 1.1661358417894971, | |
| "grad_norm": 0.023193359375, | |
| "learning_rate": 0.00013957294444537808, | |
| "loss": 0.0226, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 1.1756166209910377, | |
| "grad_norm": 0.02880859375, | |
| "learning_rate": 0.0001386249158658522, | |
| "loss": 0.0332, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 1.1850974001925783, | |
| "grad_norm": 0.028076171875, | |
| "learning_rate": 0.00013767278936351854, | |
| "loss": 0.0292, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.194578179394119, | |
| "grad_norm": 0.0264892578125, | |
| "learning_rate": 0.00013671666595454295, | |
| "loss": 0.0224, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 1.2040589585956596, | |
| "grad_norm": 0.027099609375, | |
| "learning_rate": 0.00013575664707914448, | |
| "loss": 0.0234, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 1.2135397377972001, | |
| "grad_norm": 0.03125, | |
| "learning_rate": 0.0001347928345908329, | |
| "loss": 0.029, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 1.223020516998741, | |
| "grad_norm": 0.0269775390625, | |
| "learning_rate": 0.00013382533074560255, | |
| "loss": 0.0249, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 1.2325012962002815, | |
| "grad_norm": 0.0291748046875, | |
| "learning_rate": 0.0001328542381910835, | |
| "loss": 0.026, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.241982075401822, | |
| "grad_norm": 0.0291748046875, | |
| "learning_rate": 0.00013187965995565098, | |
| "loss": 0.0252, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 1.2514628546033628, | |
| "grad_norm": 0.0279541015625, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.023, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 1.2514628546033628, | |
| "eval_loss": 0.029845552518963814, | |
| "eval_runtime": 34.1739, | |
| "eval_samples_per_second": 20.805, | |
| "eval_steps_per_second": 20.805, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 1.2609436338049034, | |
| "grad_norm": 0.02734375, | |
| "learning_rate": 0.00012992046039364893, | |
| "loss": 0.0259, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 1.270424413006444, | |
| "grad_norm": 0.0284423828125, | |
| "learning_rate": 0.0001289360469289838, | |
| "loss": 0.0244, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 1.2799051922079845, | |
| "grad_norm": 0.0286865234375, | |
| "learning_rate": 0.00012794856348516095, | |
| "loss": 0.0237, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.2893859714095253, | |
| "grad_norm": 0.0289306640625, | |
| "learning_rate": 0.00012695811482955227, | |
| "loss": 0.0248, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 1.2988667506110658, | |
| "grad_norm": 0.028076171875, | |
| "learning_rate": 0.00012596480604412484, | |
| "loss": 0.0283, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 1.3083475298126066, | |
| "grad_norm": 0.0260009765625, | |
| "learning_rate": 0.000124968742514292, | |
| "loss": 0.021, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 1.3178283090141472, | |
| "grad_norm": 0.0279541015625, | |
| "learning_rate": 0.00012397002991773275, | |
| "loss": 0.0249, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 1.3273090882156877, | |
| "grad_norm": 0.026611328125, | |
| "learning_rate": 0.0001229687742131796, | |
| "loss": 0.0231, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.3367898674172283, | |
| "grad_norm": 0.0274658203125, | |
| "learning_rate": 0.00012196508162917677, | |
| "loss": 0.0276, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 1.346270646618769, | |
| "grad_norm": 0.03173828125, | |
| "learning_rate": 0.00012095905865281025, | |
| "loss": 0.0268, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 1.3557514258203096, | |
| "grad_norm": 0.027587890625, | |
| "learning_rate": 0.00011995081201840956, | |
| "loss": 0.0259, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 1.3557514258203096, | |
| "eval_loss": 0.029736338183283806, | |
| "eval_runtime": 34.4542, | |
| "eval_samples_per_second": 20.636, | |
| "eval_steps_per_second": 20.636, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 1.3652322050218502, | |
| "grad_norm": 0.02734375, | |
| "learning_rate": 0.00011894044869622403, | |
| "loss": 0.025, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 1.374712984223391, | |
| "grad_norm": 0.0263671875, | |
| "learning_rate": 0.00011792807588107357, | |
| "loss": 0.0221, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.3841937634249315, | |
| "grad_norm": 0.031982421875, | |
| "learning_rate": 0.00011691380098097597, | |
| "loss": 0.0281, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 1.393674542626472, | |
| "grad_norm": 0.025146484375, | |
| "learning_rate": 0.0001158977316057513, | |
| "loss": 0.021, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 1.4031553218280126, | |
| "grad_norm": 0.032958984375, | |
| "learning_rate": 0.00011487997555560503, | |
| "loss": 0.0256, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 1.4126361010295534, | |
| "grad_norm": 0.0306396484375, | |
| "learning_rate": 0.00011386064080969094, | |
| "loss": 0.0267, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 1.422116880231094, | |
| "grad_norm": 0.0267333984375, | |
| "learning_rate": 0.00011283983551465511, | |
| "loss": 0.0211, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.4315976594326347, | |
| "grad_norm": 0.0291748046875, | |
| "learning_rate": 0.0001118176679731619, | |
| "loss": 0.025, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 1.4410784386341753, | |
| "grad_norm": 0.0296630859375, | |
| "learning_rate": 0.00011079424663240372, | |
| "loss": 0.0273, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 1.4505592178357158, | |
| "grad_norm": 0.0284423828125, | |
| "learning_rate": 0.00010976968007259519, | |
| "loss": 0.0243, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 1.4600399970372564, | |
| "grad_norm": 0.0272216796875, | |
| "learning_rate": 0.00010874407699545328, | |
| "loss": 0.0232, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 1.4600399970372564, | |
| "eval_loss": 0.029951849952340126, | |
| "eval_runtime": 34.3508, | |
| "eval_samples_per_second": 20.698, | |
| "eval_steps_per_second": 20.698, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 1.4695207762387972, | |
| "grad_norm": 0.03271484375, | |
| "learning_rate": 0.00010771754621266466, | |
| "loss": 0.0283, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 1.4790015554403377, | |
| "grad_norm": 0.024169921875, | |
| "learning_rate": 0.00010669019663434117, | |
| "loss": 0.0218, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 1.4884823346418785, | |
| "grad_norm": 0.029296875, | |
| "learning_rate": 0.00010566213725746506, | |
| "loss": 0.0273, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 1.497963113843419, | |
| "grad_norm": 0.0263671875, | |
| "learning_rate": 0.00010463347715432488, | |
| "loss": 0.0229, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 1.5074438930449596, | |
| "grad_norm": 0.02978515625, | |
| "learning_rate": 0.00010360432546094341, | |
| "loss": 0.0242, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 1.5169246722465002, | |
| "grad_norm": 0.031494140625, | |
| "learning_rate": 0.00010257479136549889, | |
| "loss": 0.0252, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.5264054514480407, | |
| "grad_norm": 0.0283203125, | |
| "learning_rate": 0.00010154498409674051, | |
| "loss": 0.0275, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 1.5358862306495815, | |
| "grad_norm": 0.035400390625, | |
| "learning_rate": 0.00010051501291240008, | |
| "loss": 0.0299, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 1.5453670098511223, | |
| "grad_norm": 0.031982421875, | |
| "learning_rate": 9.948498708759993e-05, | |
| "loss": 0.0264, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 1.5548477890526629, | |
| "grad_norm": 0.0302734375, | |
| "learning_rate": 9.845501590325948e-05, | |
| "loss": 0.025, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 1.5643285682542034, | |
| "grad_norm": 0.029296875, | |
| "learning_rate": 9.742520863450115e-05, | |
| "loss": 0.0203, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.5643285682542034, | |
| "eval_loss": 0.02908056415617466, | |
| "eval_runtime": 34.2083, | |
| "eval_samples_per_second": 20.784, | |
| "eval_steps_per_second": 20.784, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.573809347455744, | |
| "grad_norm": 0.0322265625, | |
| "learning_rate": 9.639567453905661e-05, | |
| "loss": 0.0262, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 1.5832901266572845, | |
| "grad_norm": 0.0245361328125, | |
| "learning_rate": 9.536652284567513e-05, | |
| "loss": 0.0213, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 1.5927709058588253, | |
| "grad_norm": 0.031005859375, | |
| "learning_rate": 9.433786274253495e-05, | |
| "loss": 0.0272, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 1.6022516850603659, | |
| "grad_norm": 0.0262451171875, | |
| "learning_rate": 9.330980336565887e-05, | |
| "loss": 0.0217, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 1.6117324642619066, | |
| "grad_norm": 0.0296630859375, | |
| "learning_rate": 9.228245378733537e-05, | |
| "loss": 0.0258, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.6212132434634472, | |
| "grad_norm": 0.03466796875, | |
| "learning_rate": 9.125592300454676e-05, | |
| "loss": 0.0278, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 1.6306940226649878, | |
| "grad_norm": 0.0284423828125, | |
| "learning_rate": 9.023031992740488e-05, | |
| "loss": 0.0234, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 1.6401748018665283, | |
| "grad_norm": 0.0301513671875, | |
| "learning_rate": 8.920575336759629e-05, | |
| "loss": 0.025, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 1.6496555810680689, | |
| "grad_norm": 0.03173828125, | |
| "learning_rate": 8.818233202683814e-05, | |
| "loss": 0.0268, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 1.6591363602696096, | |
| "grad_norm": 0.0260009765625, | |
| "learning_rate": 8.71601644853449e-05, | |
| "loss": 0.0241, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.6686171394711504, | |
| "grad_norm": 0.028564453125, | |
| "learning_rate": 8.613935919030907e-05, | |
| "loss": 0.0241, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 1.6686171394711504, | |
| "eval_loss": 0.02843022532761097, | |
| "eval_runtime": 34.2598, | |
| "eval_samples_per_second": 20.753, | |
| "eval_steps_per_second": 20.753, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 1.678097918672691, | |
| "grad_norm": 0.029052734375, | |
| "learning_rate": 8.512002444439502e-05, | |
| "loss": 0.0228, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 1.6875786978742315, | |
| "grad_norm": 0.02880859375, | |
| "learning_rate": 8.410226839424871e-05, | |
| "loss": 0.0272, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 1.697059477075772, | |
| "grad_norm": 0.0238037109375, | |
| "learning_rate": 8.308619901902406e-05, | |
| "loss": 0.0196, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 1.7065402562773127, | |
| "grad_norm": 0.02783203125, | |
| "learning_rate": 8.207192411892646e-05, | |
| "loss": 0.0218, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.7160210354788534, | |
| "grad_norm": 0.0277099609375, | |
| "learning_rate": 8.1059551303776e-05, | |
| "loss": 0.022, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 1.7255018146803942, | |
| "grad_norm": 0.0284423828125, | |
| "learning_rate": 8.004918798159045e-05, | |
| "loss": 0.0219, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 1.7349825938819348, | |
| "grad_norm": 0.02734375, | |
| "learning_rate": 7.904094134718976e-05, | |
| "loss": 0.0244, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 1.7444633730834753, | |
| "grad_norm": 0.036376953125, | |
| "learning_rate": 7.803491837082324e-05, | |
| "loss": 0.0301, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 1.7539441522850159, | |
| "grad_norm": 0.03125, | |
| "learning_rate": 7.703122578682046e-05, | |
| "loss": 0.0259, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 1.7634249314865564, | |
| "grad_norm": 0.025634765625, | |
| "learning_rate": 7.602997008226726e-05, | |
| "loss": 0.0216, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 1.7729057106880972, | |
| "grad_norm": 0.02783203125, | |
| "learning_rate": 7.5031257485708e-05, | |
| "loss": 0.0245, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 1.7729057106880972, | |
| "eval_loss": 0.028160251677036285, | |
| "eval_runtime": 34.3215, | |
| "eval_samples_per_second": 20.716, | |
| "eval_steps_per_second": 20.716, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 1.7823864898896378, | |
| "grad_norm": 0.024658203125, | |
| "learning_rate": 7.403519395587521e-05, | |
| "loss": 0.0221, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 1.7918672690911785, | |
| "grad_norm": 0.0263671875, | |
| "learning_rate": 7.304188517044774e-05, | |
| "loss": 0.0228, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 1.801348048292719, | |
| "grad_norm": 0.02587890625, | |
| "learning_rate": 7.205143651483906e-05, | |
| "loss": 0.0226, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.8108288274942597, | |
| "grad_norm": 0.028076171875, | |
| "learning_rate": 7.106395307101621e-05, | |
| "loss": 0.0213, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 1.8203096066958002, | |
| "grad_norm": 0.0299072265625, | |
| "learning_rate": 7.007953960635109e-05, | |
| "loss": 0.0247, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 1.8297903858973408, | |
| "grad_norm": 0.0341796875, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 0.0276, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 1.8392711650988816, | |
| "grad_norm": 0.031494140625, | |
| "learning_rate": 6.812034004434903e-05, | |
| "loss": 0.0233, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 1.8487519443004223, | |
| "grad_norm": 0.0269775390625, | |
| "learning_rate": 6.714576180891654e-05, | |
| "loss": 0.0213, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 1.858232723501963, | |
| "grad_norm": 0.0296630859375, | |
| "learning_rate": 6.617466925439746e-05, | |
| "loss": 0.0213, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 1.8677135027035034, | |
| "grad_norm": 0.02685546875, | |
| "learning_rate": 6.520716540916709e-05, | |
| "loss": 0.0227, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 1.877194281905044, | |
| "grad_norm": 0.02734375, | |
| "learning_rate": 6.424335292085553e-05, | |
| "loss": 0.0222, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 1.877194281905044, | |
| "eval_loss": 0.027654768899083138, | |
| "eval_runtime": 34.2048, | |
| "eval_samples_per_second": 20.787, | |
| "eval_steps_per_second": 20.787, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 1.8866750611065846, | |
| "grad_norm": 0.0255126953125, | |
| "learning_rate": 6.32833340454571e-05, | |
| "loss": 0.021, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 1.8961558403081253, | |
| "grad_norm": 0.02978515625, | |
| "learning_rate": 6.232721063648148e-05, | |
| "loss": 0.0249, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.905636619509666, | |
| "grad_norm": 0.029052734375, | |
| "learning_rate": 6.137508413414784e-05, | |
| "loss": 0.0238, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 1.9151173987112067, | |
| "grad_norm": 0.0294189453125, | |
| "learning_rate": 6.0427055554621913e-05, | |
| "loss": 0.0246, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 1.9245981779127472, | |
| "grad_norm": 0.0272216796875, | |
| "learning_rate": 5.948322547929939e-05, | |
| "loss": 0.0202, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 1.9340789571142878, | |
| "grad_norm": 0.024658203125, | |
| "learning_rate": 5.854369404413398e-05, | |
| "loss": 0.0165, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 1.9435597363158283, | |
| "grad_norm": 0.026611328125, | |
| "learning_rate": 5.7608560929013946e-05, | |
| "loss": 0.0226, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 1.9530405155173691, | |
| "grad_norm": 0.033203125, | |
| "learning_rate": 5.667792534718639e-05, | |
| "loss": 0.0265, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 1.9625212947189097, | |
| "grad_norm": 0.0269775390625, | |
| "learning_rate": 5.5751886034731115e-05, | |
| "loss": 0.0233, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 1.9720020739204505, | |
| "grad_norm": 0.02734375, | |
| "learning_rate": 5.483054124008528e-05, | |
| "loss": 0.0209, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 1.981482853121991, | |
| "grad_norm": 0.0286865234375, | |
| "learning_rate": 5.391398871361972e-05, | |
| "loss": 0.0231, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 1.981482853121991, | |
| "eval_loss": 0.027809714898467064, | |
| "eval_runtime": 34.3727, | |
| "eval_samples_per_second": 20.685, | |
| "eval_steps_per_second": 20.685, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 1.9909636323235316, | |
| "grad_norm": 0.03271484375, | |
| "learning_rate": 5.300232569726804e-05, | |
| "loss": 0.0246, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.000444411525072, | |
| "grad_norm": 0.032470703125, | |
| "learning_rate": 5.2095648914209525e-05, | |
| "loss": 0.0285, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 2.0099251907266127, | |
| "grad_norm": 0.026123046875, | |
| "learning_rate": 5.119405455860772e-05, | |
| "loss": 0.0201, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 2.0194059699281537, | |
| "grad_norm": 0.02490234375, | |
| "learning_rate": 5.029763828540419e-05, | |
| "loss": 0.0179, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 2.0288867491296942, | |
| "grad_norm": 0.0255126953125, | |
| "learning_rate": 4.940649520017035e-05, | |
| "loss": 0.0207, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 2.038367528331235, | |
| "grad_norm": 0.02587890625, | |
| "learning_rate": 4.852071984901696e-05, | |
| "loss": 0.0195, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 2.0478483075327754, | |
| "grad_norm": 0.02490234375, | |
| "learning_rate": 4.7640406208563224e-05, | |
| "loss": 0.0195, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 2.057329086734316, | |
| "grad_norm": 0.02490234375, | |
| "learning_rate": 4.676564767596663e-05, | |
| "loss": 0.0171, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 2.0668098659358565, | |
| "grad_norm": 0.027099609375, | |
| "learning_rate": 4.5896537059013536e-05, | |
| "loss": 0.0174, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 2.076290645137397, | |
| "grad_norm": 0.02392578125, | |
| "learning_rate": 4.503316656627294e-05, | |
| "loss": 0.0193, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 2.085771424338938, | |
| "grad_norm": 0.02490234375, | |
| "learning_rate": 4.417562779731355e-05, | |
| "loss": 0.0175, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.085771424338938, | |
| "eval_loss": 0.027570126578211784, | |
| "eval_runtime": 34.4181, | |
| "eval_samples_per_second": 20.658, | |
| "eval_steps_per_second": 20.658, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.0952522035404786, | |
| "grad_norm": 0.029296875, | |
| "learning_rate": 4.3324011732985433e-05, | |
| "loss": 0.0202, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 2.104732982742019, | |
| "grad_norm": 0.0283203125, | |
| "learning_rate": 4.247840872576739e-05, | |
| "loss": 0.0189, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 2.1142137619435597, | |
| "grad_norm": 0.0252685546875, | |
| "learning_rate": 4.163890849018114e-05, | |
| "loss": 0.0191, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 2.1236945411451003, | |
| "grad_norm": 0.0264892578125, | |
| "learning_rate": 4.0805600093272735e-05, | |
| "loss": 0.015, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 2.133175320346641, | |
| "grad_norm": 0.0264892578125, | |
| "learning_rate": 3.997857194516319e-05, | |
| "loss": 0.0191, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 2.142656099548182, | |
| "grad_norm": 0.0244140625, | |
| "learning_rate": 3.9157911789668525e-05, | |
| "loss": 0.0173, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 2.1521368787497224, | |
| "grad_norm": 0.0250244140625, | |
| "learning_rate": 3.8343706694990465e-05, | |
| "loss": 0.0168, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 2.161617657951263, | |
| "grad_norm": 0.0296630859375, | |
| "learning_rate": 3.753604304447915e-05, | |
| "loss": 0.0166, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 2.1710984371528035, | |
| "grad_norm": 0.0281982421875, | |
| "learning_rate": 3.6735006527467965e-05, | |
| "loss": 0.0167, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 2.180579216354344, | |
| "grad_norm": 0.0263671875, | |
| "learning_rate": 3.594068213018249e-05, | |
| "loss": 0.0167, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.1900599955558846, | |
| "grad_norm": 0.0262451171875, | |
| "learning_rate": 3.515315412672384e-05, | |
| "loss": 0.0165, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 2.1900599955558846, | |
| "eval_loss": 0.028142958879470825, | |
| "eval_runtime": 34.4859, | |
| "eval_samples_per_second": 20.617, | |
| "eval_steps_per_second": 20.617, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 2.199540774757425, | |
| "grad_norm": 0.029296875, | |
| "learning_rate": 3.437250607012748e-05, | |
| "loss": 0.0172, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 2.209021553958966, | |
| "grad_norm": 0.0299072265625, | |
| "learning_rate": 3.359882078349883e-05, | |
| "loss": 0.0187, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 2.2185023331605067, | |
| "grad_norm": 0.0277099609375, | |
| "learning_rate": 3.283218035122592e-05, | |
| "loss": 0.0182, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 2.2279831123620473, | |
| "grad_norm": 0.0311279296875, | |
| "learning_rate": 3.207266611027069e-05, | |
| "loss": 0.0169, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 2.237463891563588, | |
| "grad_norm": 0.030029296875, | |
| "learning_rate": 3.132035864153958e-05, | |
| "loss": 0.0192, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 2.2469446707651284, | |
| "grad_norm": 0.0303955078125, | |
| "learning_rate": 3.057533776133421e-05, | |
| "loss": 0.0157, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 2.2564254499666694, | |
| "grad_norm": 0.0262451171875, | |
| "learning_rate": 2.98376825128832e-05, | |
| "loss": 0.0149, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 2.26590622916821, | |
| "grad_norm": 0.031005859375, | |
| "learning_rate": 2.910747115795628e-05, | |
| "loss": 0.0177, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 2.2753870083697505, | |
| "grad_norm": 0.03173828125, | |
| "learning_rate": 2.8384781168560693e-05, | |
| "loss": 0.0193, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.284867787571291, | |
| "grad_norm": 0.0269775390625, | |
| "learning_rate": 2.766968921872213e-05, | |
| "loss": 0.0165, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 2.2943485667728316, | |
| "grad_norm": 0.032470703125, | |
| "learning_rate": 2.6962271176349852e-05, | |
| "loss": 0.0174, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 2.2943485667728316, | |
| "eval_loss": 0.028074759989976883, | |
| "eval_runtime": 34.4556, | |
| "eval_samples_per_second": 20.635, | |
| "eval_steps_per_second": 20.635, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 2.303829345974372, | |
| "grad_norm": 0.0283203125, | |
| "learning_rate": 2.626260209518737e-05, | |
| "loss": 0.0172, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 2.3133101251759127, | |
| "grad_norm": 0.0281982421875, | |
| "learning_rate": 2.5570756206849832e-05, | |
| "loss": 0.0158, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 2.3227909043774533, | |
| "grad_norm": 0.027587890625, | |
| "learning_rate": 2.4886806912948035e-05, | |
| "loss": 0.0159, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 2.3322716835789943, | |
| "grad_norm": 0.0274658203125, | |
| "learning_rate": 2.4210826777301153e-05, | |
| "loss": 0.0168, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 2.341752462780535, | |
| "grad_norm": 0.0269775390625, | |
| "learning_rate": 2.3542887518238056e-05, | |
| "loss": 0.0169, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 2.3512332419820754, | |
| "grad_norm": 0.028564453125, | |
| "learning_rate": 2.288306000098811e-05, | |
| "loss": 0.0174, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 2.360714021183616, | |
| "grad_norm": 0.0306396484375, | |
| "learning_rate": 2.2231414230162894e-05, | |
| "loss": 0.0219, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 2.3701948003851565, | |
| "grad_norm": 0.03466796875, | |
| "learning_rate": 2.1588019342328968e-05, | |
| "loss": 0.0234, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.3796755795866975, | |
| "grad_norm": 0.0294189453125, | |
| "learning_rate": 2.0952943598672846e-05, | |
| "loss": 0.0174, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 2.389156358788238, | |
| "grad_norm": 0.028076171875, | |
| "learning_rate": 2.0326254377758703e-05, | |
| "loss": 0.0194, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 2.3986371379897786, | |
| "grad_norm": 0.0296630859375, | |
| "learning_rate": 1.9708018168380037e-05, | |
| "loss": 0.021, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 2.3986371379897786, | |
| "eval_loss": 0.02788708359003067, | |
| "eval_runtime": 34.3192, | |
| "eval_samples_per_second": 20.717, | |
| "eval_steps_per_second": 20.717, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 2.408117917191319, | |
| "grad_norm": 0.02490234375, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 0.0155, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 2.4175986963928597, | |
| "grad_norm": 0.027587890625, | |
| "learning_rate": 1.8497166248318876e-05, | |
| "loss": 0.0176, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 2.4270794755944003, | |
| "grad_norm": 0.0302734375, | |
| "learning_rate": 1.7904679003358283e-05, | |
| "loss": 0.0176, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 2.436560254795941, | |
| "grad_norm": 0.0284423828125, | |
| "learning_rate": 1.7320901687747292e-05, | |
| "loss": 0.0172, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 2.446041033997482, | |
| "grad_norm": 0.0294189453125, | |
| "learning_rate": 1.674589623752707e-05, | |
| "loss": 0.0198, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 2.4555218131990224, | |
| "grad_norm": 0.0283203125, | |
| "learning_rate": 1.617972365808481e-05, | |
| "loss": 0.0187, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 2.465002592400563, | |
| "grad_norm": 0.0233154296875, | |
| "learning_rate": 1.562244401768144e-05, | |
| "loss": 0.0127, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.4744833716021035, | |
| "grad_norm": 0.03076171875, | |
| "learning_rate": 1.507411644107879e-05, | |
| "loss": 0.0228, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 2.483964150803644, | |
| "grad_norm": 0.031494140625, | |
| "learning_rate": 1.4534799103266505e-05, | |
| "loss": 0.0193, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 2.4934449300051846, | |
| "grad_norm": 0.0294189453125, | |
| "learning_rate": 1.4004549223290164e-05, | |
| "loss": 0.0194, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 2.5029257092067256, | |
| "grad_norm": 0.0238037109375, | |
| "learning_rate": 1.3483423058180421e-05, | |
| "loss": 0.0147, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 2.5029257092067256, | |
| "eval_loss": 0.027736255899071693, | |
| "eval_runtime": 34.4272, | |
| "eval_samples_per_second": 20.652, | |
| "eval_steps_per_second": 20.652, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 2.512406488408266, | |
| "grad_norm": 0.027099609375, | |
| "learning_rate": 1.2971475896984475e-05, | |
| "loss": 0.0163, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 2.5218872676098067, | |
| "grad_norm": 0.0322265625, | |
| "learning_rate": 1.2468762054900262e-05, | |
| "loss": 0.0197, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 2.5313680468113473, | |
| "grad_norm": 0.0303955078125, | |
| "learning_rate": 1.1975334867513687e-05, | |
| "loss": 0.017, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 2.540848826012888, | |
| "grad_norm": 0.02978515625, | |
| "learning_rate": 1.1491246685140077e-05, | |
| "loss": 0.0183, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 2.5503296052144284, | |
| "grad_norm": 0.030029296875, | |
| "learning_rate": 1.1016548867270038e-05, | |
| "loss": 0.0183, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 2.559810384415969, | |
| "grad_norm": 0.0272216796875, | |
| "learning_rate": 1.0551291777120464e-05, | |
| "loss": 0.0168, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.56929116361751, | |
| "grad_norm": 0.0302734375, | |
| "learning_rate": 1.0095524776291165e-05, | |
| "loss": 0.0187, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 2.5787719428190505, | |
| "grad_norm": 0.0272216796875, | |
| "learning_rate": 9.649296219527982e-06, | |
| "loss": 0.0179, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 2.588252722020591, | |
| "grad_norm": 0.030029296875, | |
| "learning_rate": 9.21265344959239e-06, | |
| "loss": 0.0189, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 2.5977335012221316, | |
| "grad_norm": 0.0294189453125, | |
| "learning_rate": 8.785642792238814e-06, | |
| "loss": 0.0182, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 2.607214280423672, | |
| "grad_norm": 0.027587890625, | |
| "learning_rate": 8.368309551299536e-06, | |
| "loss": 0.0162, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 2.607214280423672, | |
| "eval_loss": 0.027653872966766357, | |
| "eval_runtime": 34.1633, | |
| "eval_samples_per_second": 20.812, | |
| "eval_steps_per_second": 20.812, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 2.616695059625213, | |
| "grad_norm": 0.032958984375, | |
| "learning_rate": 7.960698003878309e-06, | |
| "loss": 0.0206, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 2.6261758388267538, | |
| "grad_norm": 0.02734375, | |
| "learning_rate": 7.562851395652692e-06, | |
| "loss": 0.0151, | |
| "step": 277 | |
| }, | |
| { | |
| "epoch": 2.6356566180282943, | |
| "grad_norm": 0.030517578125, | |
| "learning_rate": 7.174811936285886e-06, | |
| "loss": 0.0187, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 2.645137397229835, | |
| "grad_norm": 0.027099609375, | |
| "learning_rate": 6.796620794948483e-06, | |
| "loss": 0.0169, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 2.6546181764313754, | |
| "grad_norm": 0.02734375, | |
| "learning_rate": 6.428318095950647e-06, | |
| "loss": 0.0164, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.664098955632916, | |
| "grad_norm": 0.029296875, | |
| "learning_rate": 6.06994291448505e-06, | |
| "loss": 0.018, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 2.6735797348344565, | |
| "grad_norm": 0.030029296875, | |
| "learning_rate": 5.721533272481272e-06, | |
| "loss": 0.0201, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 2.683060514035997, | |
| "grad_norm": 0.02685546875, | |
| "learning_rate": 5.3831261345717476e-06, | |
| "loss": 0.0154, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 2.692541293237538, | |
| "grad_norm": 0.031005859375, | |
| "learning_rate": 5.054757404170074e-06, | |
| "loss": 0.0173, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 2.7020220724390787, | |
| "grad_norm": 0.0286865234375, | |
| "learning_rate": 4.7364619196617495e-06, | |
| "loss": 0.0189, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 2.711502851640619, | |
| "grad_norm": 0.031494140625, | |
| "learning_rate": 4.428273450708065e-06, | |
| "loss": 0.0206, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 2.711502851640619, | |
| "eval_loss": 0.02764257788658142, | |
| "eval_runtime": 34.4144, | |
| "eval_samples_per_second": 20.66, | |
| "eval_steps_per_second": 20.66, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 2.7209836308421598, | |
| "grad_norm": 0.035400390625, | |
| "learning_rate": 4.130224694663221e-06, | |
| "loss": 0.0197, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 2.7304644100437003, | |
| "grad_norm": 0.0269775390625, | |
| "learning_rate": 3.842347273105396e-06, | |
| "loss": 0.0173, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 2.7399451892452413, | |
| "grad_norm": 0.027099609375, | |
| "learning_rate": 3.564671728481739e-06, | |
| "loss": 0.0153, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 2.749425968446782, | |
| "grad_norm": 0.030029296875, | |
| "learning_rate": 3.2972275208679625e-06, | |
| "loss": 0.0189, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.7589067476483224, | |
| "grad_norm": 0.0303955078125, | |
| "learning_rate": 3.040043024842898e-06, | |
| "loss": 0.0185, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 2.768387526849863, | |
| "grad_norm": 0.03173828125, | |
| "learning_rate": 2.793145526477914e-06, | |
| "loss": 0.0194, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 2.7778683060514036, | |
| "grad_norm": 0.0286865234375, | |
| "learning_rate": 2.556561220442144e-06, | |
| "loss": 0.0191, | |
| "step": 293 | |
| }, | |
| { | |
| "epoch": 2.787349085252944, | |
| "grad_norm": 0.0322265625, | |
| "learning_rate": 2.3303152072231883e-06, | |
| "loss": 0.0187, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 2.7968298644544847, | |
| "grad_norm": 0.0289306640625, | |
| "learning_rate": 2.1144314904642195e-06, | |
| "loss": 0.0183, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 2.8063106436560252, | |
| "grad_norm": 0.0269775390625, | |
| "learning_rate": 1.908932974417266e-06, | |
| "loss": 0.0161, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 2.8157914228575662, | |
| "grad_norm": 0.03125, | |
| "learning_rate": 1.7138414615131327e-06, | |
| "loss": 0.0241, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 2.8157914228575662, | |
| "eval_loss": 0.027634525671601295, | |
| "eval_runtime": 34.429, | |
| "eval_samples_per_second": 20.651, | |
| "eval_steps_per_second": 20.651, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 2.825272202059107, | |
| "grad_norm": 0.0283203125, | |
| "learning_rate": 1.529177650048297e-06, | |
| "loss": 0.0179, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 2.8347529812606473, | |
| "grad_norm": 0.0262451171875, | |
| "learning_rate": 1.3549611319889521e-06, | |
| "loss": 0.0144, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 2.844233760462188, | |
| "grad_norm": 0.0283203125, | |
| "learning_rate": 1.1912103908922945e-06, | |
| "loss": 0.0169, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.8537145396637285, | |
| "grad_norm": 0.029541015625, | |
| "learning_rate": 1.0379427999456015e-06, | |
| "loss": 0.0191, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 2.8631953188652695, | |
| "grad_norm": 0.0284423828125, | |
| "learning_rate": 8.95174620122996e-07, | |
| "loss": 0.0174, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 2.87267609806681, | |
| "grad_norm": 0.028564453125, | |
| "learning_rate": 7.629209984601815e-07, | |
| "loss": 0.0172, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 2.8821568772683506, | |
| "grad_norm": 0.028076171875, | |
| "learning_rate": 6.411959664474831e-07, | |
| "loss": 0.0186, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 2.891637656469891, | |
| "grad_norm": 0.03173828125, | |
| "learning_rate": 5.300124385410943e-07, | |
| "loss": 0.0227, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 2.9011184356714317, | |
| "grad_norm": 0.0281982421875, | |
| "learning_rate": 4.2938221079300566e-07, | |
| "loss": 0.0159, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 2.9105992148729722, | |
| "grad_norm": 0.0267333984375, | |
| "learning_rate": 3.3931595959942886e-07, | |
| "loss": 0.0166, | |
| "step": 307 | |
| }, | |
| { | |
| "epoch": 2.920079994074513, | |
| "grad_norm": 0.027587890625, | |
| "learning_rate": 2.5982324056810225e-07, | |
| "loss": 0.0162, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 2.920079994074513, | |
| "eval_loss": 0.027648651972413063, | |
| "eval_runtime": 34.3412, | |
| "eval_samples_per_second": 20.704, | |
| "eval_steps_per_second": 20.704, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 2.9295607732760534, | |
| "grad_norm": 0.0269775390625, | |
| "learning_rate": 1.9091248750446876e-07, | |
| "loss": 0.018, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 2.9390415524775944, | |
| "grad_norm": 0.0262451171875, | |
| "learning_rate": 1.3259101151694708e-07, | |
| "loss": 0.0181, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.948522331679135, | |
| "grad_norm": 0.0247802734375, | |
| "learning_rate": 8.486500024118548e-08, | |
| "loss": 0.0146, | |
| "step": 311 | |
| }, | |
| { | |
| "epoch": 2.9580031108806755, | |
| "grad_norm": 0.0274658203125, | |
| "learning_rate": 4.7739517183620356e-08, | |
| "loss": 0.0153, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 2.967483890082216, | |
| "grad_norm": 0.0294189453125, | |
| "learning_rate": 2.1218501184261386e-08, | |
| "loss": 0.0189, | |
| "step": 313 | |
| }, | |
| { | |
| "epoch": 2.976964669283757, | |
| "grad_norm": 0.0299072265625, | |
| "learning_rate": 5.304765998781491e-09, | |
| "loss": 0.0181, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 2.9864454484852976, | |
| "grad_norm": 0.02685546875, | |
| "learning_rate": 0.0, | |
| "loss": 0.0152, | |
| "step": 315 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.251934498730803e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |