diff --git "a/checkpoint-1755350/trainer_state.json" "b/checkpoint-1755350/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-1755350/trainer_state.json" @@ -0,0 +1,20777 @@ +{ + "best_metric": 3.890727996826172, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/pp-mod-subj/transformer/4/checkpoints/checkpoint-915830", + "epoch": 1.0250006060157382, + "eval_steps": 10, + "global_step": 1755350, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 4.999998362119627e-05, + "loss": 11.0005, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 6.849, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 6.1928, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 5.969, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 5.818, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 5.6938, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 5.6036, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 5.528, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 5.4669, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 5.3968, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 5.3531, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 5.3092, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989938500867749e-05, + "loss": 5.276, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989099906116697e-05, + "loss": 5.2132, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988261311365645e-05, + "loss": 5.1737, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.987422716614593e-05, + "loss": 5.1452, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986584121863541e-05, + "loss": 5.1033, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985745527112489e-05, + "loss": 5.0758, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984906932361437e-05, + "loss": 5.0546, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.0218, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983231380739706e-05, + "loss": 5.0072, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.9823927859886547e-05, + "loss": 4.9812, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.9815541912376026e-05, + "loss": 4.9481, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.9807155964865506e-05, + "loss": 4.9428, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 4.913, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790400448648195e-05, + "loss": 4.8886, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9782014501137675e-05, + "loss": 4.8751, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773628553627155e-05, + "loss": 4.866, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 4.8306, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756873037409844e-05, + "loss": 4.8223, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748487089899324e-05, + "loss": 4.7984, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.9740101142388804e-05, + "loss": 4.7886, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731715194878284e-05, + "loss": 4.79, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.97233456261715e-05, + "loss": 4.7668, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.971495967866098e-05, + "loss": 4.7559, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.970657373115046e-05, + "loss": 4.7431, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969818778363994e-05, + "loss": 4.7353, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968981821493315e-05, + "loss": 4.723, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.968143226742263e-05, + "loss": 4.708, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967304631991211e-05, + "loss": 4.6985, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966466037240159e-05, + "loss": 4.6794, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965627442489107e-05, + "loss": 4.6781, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964790485618428e-05, + "loss": 4.6498, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963951890867376e-05, + "loss": 4.6591, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.963113296116324e-05, + "loss": 4.6542, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962274701365272e-05, + "loss": 4.6418, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.9614377444945934e-05, + "loss": 4.6241, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.9605991497435414e-05, + "loss": 4.6233, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.9597605549924894e-05, + "loss": 4.618, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.9589219602414374e-05, + "loss": 4.6003, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958085003370758e-05, + "loss": 4.588, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957248046500079e-05, + "loss": 4.5828, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956409451749027e-05, + "loss": 4.5931, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.955570856997975e-05, + "loss": 4.5609, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.954732262246923e-05, + "loss": 4.5819, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.953893667495871e-05, + "loss": 4.5458, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.953055072744819e-05, + "loss": 4.5538, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.952216477993767e-05, + "loss": 4.5441, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951377883242715e-05, + "loss": 4.5404, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.950539288491663e-05, + "loss": 4.5321, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949702331620985e-05, + "loss": 4.526, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948863736869932e-05, + "loss": 4.5087, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.94802514211888e-05, + "loss": 4.5206, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947186547367828e-05, + "loss": 4.5004, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946349590497149e-05, + "loss": 4.5066, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945510995746097e-05, + "loss": 4.498, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944672400995045e-05, + "loss": 4.4885, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.943833806243993e-05, + "loss": 4.4713, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.9429968493733145e-05, + "loss": 4.4851, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.9421598925026354e-05, + "loss": 4.475, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.941321297751584e-05, + "loss": 4.4599, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.940482703000532e-05, + "loss": 4.466, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396441082494794e-05, + "loss": 4.4575, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388055134984274e-05, + "loss": 4.4561, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379669187473754e-05, + "loss": 4.4584, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371283239963234e-05, + "loss": 4.4502, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.936291367125644e-05, + "loss": 4.4416, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.935452772374592e-05, + "loss": 4.4269, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.93461417762354e-05, + "loss": 4.4338, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.933775582872488e-05, + "loss": 4.4308, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.932936988121436e-05, + "loss": 4.4331, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.932098393370384e-05, + "loss": 4.4258, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.931259798619332e-05, + "loss": 4.4131, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.930421203868281e-05, + "loss": 4.3969, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.929584246997602e-05, + "loss": 4.4015, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.92874565224655e-05, + "loss": 4.4024, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.927907057495498e-05, + "loss": 4.4031, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.927068462744446e-05, + "loss": 4.3985, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.926231505873767e-05, + "loss": 4.3939, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925392911122715e-05, + "loss": 4.3819, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.924555954252036e-05, + "loss": 4.3787, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923717359500984e-05, + "loss": 4.3765, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922878764749932e-05, + "loss": 4.3835, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.922041807879253e-05, + "loss": 4.3755, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921203213128201e-05, + "loss": 4.352, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920364618377149e-05, + "loss": 4.3571, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919526023626097e-05, + "loss": 4.3629, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918687428875045e-05, + "loss": 4.3642, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.917848834123993e-05, + "loss": 4.357, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.917010239372941e-05, + "loss": 4.3497, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.916171644621889e-05, + "loss": 4.3493, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.915333049870837e-05, + "loss": 4.3437, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.914494455119785e-05, + "loss": 4.3472, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.913657498249106e-05, + "loss": 4.3456, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.912818903498054e-05, + "loss": 4.3269, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.911980308747002e-05, + "loss": 4.3363, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.91114171399595e-05, + "loss": 4.314, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.910303119244898e-05, + "loss": 4.3246, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.909464524493846e-05, + "loss": 4.3239, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908625929742794e-05, + "loss": 4.3164, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907788972872115e-05, + "loss": 4.3199, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.906950378121063e-05, + "loss": 4.3052, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906111783370011e-05, + "loss": 4.3023, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.905273188618959e-05, + "loss": 4.3077, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.90443623174828e-05, + "loss": 4.3207, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903597636997228e-05, + "loss": 4.2925, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.902759042246176e-05, + "loss": 4.2872, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.901920447495124e-05, + "loss": 4.2898, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.9010834906244455e-05, + "loss": 4.3038, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.9002448958733935e-05, + "loss": 4.2917, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.899407939002715e-05, + "loss": 4.2946, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.8985693442516624e-05, + "loss": 4.288, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.8977307495006104e-05, + "loss": 4.2907, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968921547495584e-05, + "loss": 4.281, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.8960535599985064e-05, + "loss": 4.2814, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.8952149652474544e-05, + "loss": 4.2757, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.8943763704964024e-05, + "loss": 4.286, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.8935377757453504e-05, + "loss": 4.2639, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.892700818874671e-05, + "loss": 4.2767, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.891862224123619e-05, + "loss": 4.2724, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.891023629372567e-05, + "loss": 4.2598, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.890185034621515e-05, + "loss": 4.2711, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.889348077750837e-05, + "loss": 4.2657, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888509482999785e-05, + "loss": 4.2699, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.887670888248733e-05, + "loss": 4.2659, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886832293497681e-05, + "loss": 4.2481, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885993698746629e-05, + "loss": 4.2447, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.885155103995577e-05, + "loss": 4.2488, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884318147124898e-05, + "loss": 4.2588, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883479552373846e-05, + "loss": 4.2597, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882640957622794e-05, + "loss": 4.2515, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.881802362871742e-05, + "loss": 4.2403, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.88096376812069e-05, + "loss": 4.2414, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.8801268112500106e-05, + "loss": 4.2444, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.8792882164989586e-05, + "loss": 4.2404, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.878449621747907e-05, + "loss": 4.2354, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877611026996855e-05, + "loss": 4.2504, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.876774070126176e-05, + "loss": 4.2379, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875935475375124e-05, + "loss": 4.2296, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.875096880624072e-05, + "loss": 4.2271, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.243750095367432, + "eval_runtime": 568.7385, + "eval_samples_per_second": 670.943, + "eval_steps_per_second": 20.967, + "step": 76319 + }, + { + "epoch": 0.0, + "learning_rate": 4.87425828587302e-05, + "loss": 4.2337, + "step": 76800 + }, + { + "epoch": 0.0, + "learning_rate": 4.873419691121968e-05, + "loss": 4.2297, + "step": 77312 + }, + { + "epoch": 0.0, + "learning_rate": 4.872581096370916e-05, + "loss": 4.2167, + "step": 77824 + }, + { + "epoch": 0.0, + "learning_rate": 4.8717425016198635e-05, + "loss": 4.2169, + "step": 78336 + }, + { + "epoch": 0.0, + "learning_rate": 4.8709039068688115e-05, + "loss": 4.2103, + "step": 78848 + }, + { + "epoch": 0.0, + "learning_rate": 4.8700653121177595e-05, + "loss": 4.2082, + "step": 79360 + }, + { + "epoch": 0.0, + "learning_rate": 4.8692267173667075e-05, + "loss": 4.2012, + "step": 79872 + }, + { + "epoch": 0.0, + "learning_rate": 4.8683881226156555e-05, + "loss": 4.2031, + "step": 80384 + }, + { + "epoch": 0.0, + "learning_rate": 4.867549527864604e-05, + "loss": 4.2089, + "step": 80896 + }, + { + "epoch": 0.0, + "learning_rate": 4.866710933113552e-05, + "loss": 4.2071, + "step": 81408 + }, + { + "epoch": 0.0, + "learning_rate": 4.8658723383625e-05, + "loss": 4.2035, + "step": 81920 + }, + { + "epoch": 0.0, + "learning_rate": 4.865033743611448e-05, + "loss": 4.2064, + "step": 82432 + }, + { + "epoch": 0.0, + "learning_rate": 4.864196786740769e-05, + "loss": 4.1982, + "step": 82944 + }, + { + "epoch": 0.0, + "learning_rate": 4.863358191989717e-05, + "loss": 4.1931, + "step": 83456 + }, + { + "epoch": 0.0, + "learning_rate": 4.862519597238665e-05, + "loss": 4.1904, + "step": 83968 + }, + { + "epoch": 0.0, + "learning_rate": 4.861681002487613e-05, + "loss": 4.1642, + "step": 84480 + }, + { + "epoch": 0.0, + "learning_rate": 4.860844045616934e-05, + "loss": 4.1869, + "step": 84992 + }, + { + "epoch": 0.0, + "learning_rate": 4.860005450865882e-05, + "loss": 4.1843, + "step": 85504 + }, + { + "epoch": 0.0, + "learning_rate": 4.85916685611483e-05, + "loss": 4.1838, + "step": 86016 + }, + { + "epoch": 0.0, + "learning_rate": 4.858328261363778e-05, + "loss": 4.1949, + "step": 86528 + }, + { + "epoch": 0.0, + "learning_rate": 4.8574913044930995e-05, + "loss": 4.1788, + "step": 87040 + }, + { + "epoch": 0.0, + "learning_rate": 4.8566527097420475e-05, + "loss": 4.1812, + "step": 87552 + }, + { + "epoch": 0.0, + "learning_rate": 4.8558141149909955e-05, + "loss": 4.1798, + "step": 88064 + }, + { + "epoch": 0.0, + "learning_rate": 4.8549755202399435e-05, + "loss": 4.179, + "step": 88576 + }, + { + "epoch": 0.0, + "learning_rate": 4.8541385633692644e-05, + "loss": 4.1698, + "step": 89088 + }, + { + "epoch": 0.0, + "learning_rate": 4.8532999686182124e-05, + "loss": 4.1698, + "step": 89600 + }, + { + "epoch": 0.0, + "learning_rate": 4.8524613738671604e-05, + "loss": 4.1761, + "step": 90112 + }, + { + "epoch": 0.0, + "learning_rate": 4.8516227791161084e-05, + "loss": 4.1589, + "step": 90624 + }, + { + "epoch": 0.0, + "learning_rate": 4.850785822245429e-05, + "loss": 4.164, + "step": 91136 + }, + { + "epoch": 0.01, + "learning_rate": 4.849947227494377e-05, + "loss": 4.1519, + "step": 91648 + }, + { + "epoch": 0.01, + "learning_rate": 4.849108632743325e-05, + "loss": 4.1558, + "step": 92160 + }, + { + "epoch": 0.01, + "learning_rate": 4.848270037992273e-05, + "loss": 4.1671, + "step": 92672 + }, + { + "epoch": 0.01, + "learning_rate": 4.847433081121595e-05, + "loss": 4.1595, + "step": 93184 + }, + { + "epoch": 0.01, + "learning_rate": 4.846594486370543e-05, + "loss": 4.1597, + "step": 93696 + }, + { + "epoch": 0.01, + "learning_rate": 4.845755891619491e-05, + "loss": 4.158, + "step": 94208 + }, + { + "epoch": 0.01, + "learning_rate": 4.844917296868439e-05, + "loss": 4.1576, + "step": 94720 + }, + { + "epoch": 0.01, + "learning_rate": 4.84408033999776e-05, + "loss": 4.1567, + "step": 95232 + }, + { + "epoch": 0.01, + "learning_rate": 4.843241745246708e-05, + "loss": 4.1539, + "step": 95744 + }, + { + "epoch": 0.01, + "learning_rate": 4.842403150495656e-05, + "loss": 4.1513, + "step": 96256 + }, + { + "epoch": 0.01, + "learning_rate": 4.841564555744604e-05, + "loss": 4.1398, + "step": 96768 + }, + { + "epoch": 0.01, + "learning_rate": 4.840727598873925e-05, + "loss": 4.1477, + "step": 97280 + }, + { + "epoch": 0.01, + "learning_rate": 4.839889004122873e-05, + "loss": 4.1316, + "step": 97792 + }, + { + "epoch": 0.01, + "learning_rate": 4.839050409371821e-05, + "loss": 4.1432, + "step": 98304 + }, + { + "epoch": 0.01, + "learning_rate": 4.8382118146207687e-05, + "loss": 4.1481, + "step": 98816 + }, + { + "epoch": 0.01, + "learning_rate": 4.83737485775009e-05, + "loss": 4.1433, + "step": 99328 + }, + { + "epoch": 0.01, + "learning_rate": 4.836536262999038e-05, + "loss": 4.1356, + "step": 99840 + }, + { + "epoch": 0.01, + "learning_rate": 4.835697668247986e-05, + "loss": 4.1377, + "step": 100352 + }, + { + "epoch": 0.01, + "learning_rate": 4.834859073496934e-05, + "loss": 4.1425, + "step": 100864 + }, + { + "epoch": 0.01, + "learning_rate": 4.834022116626255e-05, + "loss": 4.1222, + "step": 101376 + }, + { + "epoch": 0.01, + "learning_rate": 4.833183521875203e-05, + "loss": 4.1254, + "step": 101888 + }, + { + "epoch": 0.01, + "learning_rate": 4.832344927124151e-05, + "loss": 4.1251, + "step": 102400 + }, + { + "epoch": 0.01, + "learning_rate": 4.831506332373099e-05, + "loss": 4.1396, + "step": 102912 + }, + { + "epoch": 0.01, + "learning_rate": 4.83066937550242e-05, + "loss": 4.1173, + "step": 103424 + }, + { + "epoch": 0.01, + "learning_rate": 4.829830780751368e-05, + "loss": 4.1383, + "step": 103936 + }, + { + "epoch": 0.01, + "learning_rate": 4.828992186000316e-05, + "loss": 4.1073, + "step": 104448 + }, + { + "epoch": 0.01, + "learning_rate": 4.828153591249264e-05, + "loss": 4.1229, + "step": 104960 + }, + { + "epoch": 0.01, + "learning_rate": 4.8273166343785856e-05, + "loss": 4.1215, + "step": 105472 + }, + { + "epoch": 0.01, + "learning_rate": 4.8264780396275336e-05, + "loss": 4.1249, + "step": 105984 + }, + { + "epoch": 0.01, + "learning_rate": 4.8256394448764816e-05, + "loss": 4.1156, + "step": 106496 + }, + { + "epoch": 0.01, + "learning_rate": 4.8248008501254296e-05, + "loss": 4.1191, + "step": 107008 + }, + { + "epoch": 0.01, + "learning_rate": 4.8239638932547505e-05, + "loss": 4.1065, + "step": 107520 + }, + { + "epoch": 0.01, + "learning_rate": 4.8231252985036985e-05, + "loss": 4.1168, + "step": 108032 + }, + { + "epoch": 0.01, + "learning_rate": 4.8222867037526465e-05, + "loss": 4.1083, + "step": 108544 + }, + { + "epoch": 0.01, + "learning_rate": 4.8214481090015945e-05, + "loss": 4.1133, + "step": 109056 + }, + { + "epoch": 0.01, + "learning_rate": 4.8206111521309154e-05, + "loss": 4.1083, + "step": 109568 + }, + { + "epoch": 0.01, + "learning_rate": 4.8197725573798634e-05, + "loss": 4.1046, + "step": 110080 + }, + { + "epoch": 0.01, + "learning_rate": 4.8189339626288114e-05, + "loss": 4.0879, + "step": 110592 + }, + { + "epoch": 0.01, + "learning_rate": 4.8180953678777594e-05, + "loss": 4.1127, + "step": 111104 + }, + { + "epoch": 0.01, + "learning_rate": 4.817258411007081e-05, + "loss": 4.1025, + "step": 111616 + }, + { + "epoch": 0.01, + "learning_rate": 4.816419816256029e-05, + "loss": 4.0941, + "step": 112128 + }, + { + "epoch": 0.01, + "learning_rate": 4.815581221504977e-05, + "loss": 4.1016, + "step": 112640 + }, + { + "epoch": 0.01, + "learning_rate": 4.814742626753924e-05, + "loss": 4.0982, + "step": 113152 + }, + { + "epoch": 0.01, + "learning_rate": 4.813905669883246e-05, + "loss": 4.0995, + "step": 113664 + }, + { + "epoch": 0.01, + "learning_rate": 4.813067075132194e-05, + "loss": 4.1085, + "step": 114176 + }, + { + "epoch": 0.01, + "learning_rate": 4.812228480381141e-05, + "loss": 4.1035, + "step": 114688 + }, + { + "epoch": 0.01, + "learning_rate": 4.811389885630089e-05, + "loss": 4.0942, + "step": 115200 + }, + { + "epoch": 0.01, + "learning_rate": 4.810552928759411e-05, + "loss": 4.0869, + "step": 115712 + }, + { + "epoch": 0.01, + "learning_rate": 4.809714334008359e-05, + "loss": 4.0926, + "step": 116224 + }, + { + "epoch": 0.01, + "learning_rate": 4.808875739257306e-05, + "loss": 4.095, + "step": 116736 + }, + { + "epoch": 0.01, + "learning_rate": 4.808037144506255e-05, + "loss": 4.1045, + "step": 117248 + }, + { + "epoch": 0.01, + "learning_rate": 4.807200187635576e-05, + "loss": 4.0934, + "step": 117760 + }, + { + "epoch": 0.01, + "learning_rate": 4.8063615928845243e-05, + "loss": 4.0882, + "step": 118272 + }, + { + "epoch": 0.01, + "learning_rate": 4.8055229981334717e-05, + "loss": 4.0731, + "step": 118784 + }, + { + "epoch": 0.01, + "learning_rate": 4.804686041262793e-05, + "loss": 4.0785, + "step": 119296 + }, + { + "epoch": 0.01, + "learning_rate": 4.803847446511741e-05, + "loss": 4.0815, + "step": 119808 + }, + { + "epoch": 0.01, + "learning_rate": 4.8030088517606886e-05, + "loss": 4.0834, + "step": 120320 + }, + { + "epoch": 0.01, + "learning_rate": 4.8021702570096366e-05, + "loss": 4.0908, + "step": 120832 + }, + { + "epoch": 0.01, + "learning_rate": 4.801333300138958e-05, + "loss": 4.0829, + "step": 121344 + }, + { + "epoch": 0.01, + "learning_rate": 4.800494705387906e-05, + "loss": 4.0749, + "step": 121856 + }, + { + "epoch": 0.02, + "learning_rate": 4.7996561106368535e-05, + "loss": 4.0793, + "step": 122368 + }, + { + "epoch": 0.02, + "learning_rate": 4.7988175158858015e-05, + "loss": 4.071, + "step": 122880 + }, + { + "epoch": 0.02, + "learning_rate": 4.797980559015123e-05, + "loss": 4.0805, + "step": 123392 + }, + { + "epoch": 0.02, + "learning_rate": 4.797141964264071e-05, + "loss": 4.0798, + "step": 123904 + }, + { + "epoch": 0.02, + "learning_rate": 4.796303369513019e-05, + "loss": 4.0608, + "step": 124416 + }, + { + "epoch": 0.02, + "learning_rate": 4.795464774761967e-05, + "loss": 4.0623, + "step": 124928 + }, + { + "epoch": 0.02, + "learning_rate": 4.7946278178912886e-05, + "loss": 4.0697, + "step": 125440 + }, + { + "epoch": 0.02, + "learning_rate": 4.793789223140236e-05, + "loss": 4.0802, + "step": 125952 + }, + { + "epoch": 0.02, + "learning_rate": 4.7929522662695575e-05, + "loss": 4.0656, + "step": 126464 + }, + { + "epoch": 0.02, + "learning_rate": 4.7921136715185055e-05, + "loss": 4.0741, + "step": 126976 + }, + { + "epoch": 0.02, + "learning_rate": 4.7912750767674535e-05, + "loss": 4.0662, + "step": 127488 + }, + { + "epoch": 0.02, + "learning_rate": 4.790436482016401e-05, + "loss": 4.0645, + "step": 128000 + }, + { + "epoch": 0.02, + "learning_rate": 4.789597887265349e-05, + "loss": 4.0701, + "step": 128512 + }, + { + "epoch": 0.02, + "learning_rate": 4.788759292514297e-05, + "loss": 4.069, + "step": 129024 + }, + { + "epoch": 0.02, + "learning_rate": 4.7879223356436184e-05, + "loss": 4.0562, + "step": 129536 + }, + { + "epoch": 0.02, + "learning_rate": 4.7870837408925664e-05, + "loss": 4.0683, + "step": 130048 + }, + { + "epoch": 0.02, + "learning_rate": 4.7862451461415144e-05, + "loss": 4.0479, + "step": 130560 + }, + { + "epoch": 0.02, + "learning_rate": 4.7854065513904624e-05, + "loss": 4.055, + "step": 131072 + }, + { + "epoch": 0.02, + "learning_rate": 4.7845679566394104e-05, + "loss": 4.0617, + "step": 131584 + }, + { + "epoch": 0.02, + "learning_rate": 4.7837293618883584e-05, + "loss": 4.0502, + "step": 132096 + }, + { + "epoch": 0.02, + "learning_rate": 4.7828907671373064e-05, + "loss": 4.0558, + "step": 132608 + }, + { + "epoch": 0.02, + "learning_rate": 4.7820521723862544e-05, + "loss": 4.0497, + "step": 133120 + }, + { + "epoch": 0.02, + "learning_rate": 4.781215215515575e-05, + "loss": 4.0453, + "step": 133632 + }, + { + "epoch": 0.02, + "learning_rate": 4.780378258644896e-05, + "loss": 4.0511, + "step": 134144 + }, + { + "epoch": 0.02, + "learning_rate": 4.779539663893844e-05, + "loss": 4.0662, + "step": 134656 + }, + { + "epoch": 0.02, + "learning_rate": 4.778701069142792e-05, + "loss": 4.0424, + "step": 135168 + }, + { + "epoch": 0.02, + "learning_rate": 4.77786247439174e-05, + "loss": 4.0417, + "step": 135680 + }, + { + "epoch": 0.02, + "learning_rate": 4.777023879640689e-05, + "loss": 4.0404, + "step": 136192 + }, + { + "epoch": 0.02, + "learning_rate": 4.776185284889637e-05, + "loss": 4.0507, + "step": 136704 + }, + { + "epoch": 0.02, + "learning_rate": 4.775346690138585e-05, + "loss": 4.0486, + "step": 137216 + }, + { + "epoch": 0.02, + "learning_rate": 4.774509733267906e-05, + "loss": 4.0463, + "step": 137728 + }, + { + "epoch": 0.02, + "learning_rate": 4.773671138516854e-05, + "loss": 4.0474, + "step": 138240 + }, + { + "epoch": 0.02, + "learning_rate": 4.772832543765802e-05, + "loss": 4.0481, + "step": 138752 + }, + { + "epoch": 0.02, + "learning_rate": 4.77199394901475e-05, + "loss": 4.0442, + "step": 139264 + }, + { + "epoch": 0.02, + "learning_rate": 4.771155354263698e-05, + "loss": 4.0392, + "step": 139776 + }, + { + "epoch": 0.02, + "learning_rate": 4.770316759512646e-05, + "loss": 4.0412, + "step": 140288 + }, + { + "epoch": 0.02, + "learning_rate": 4.769478164761594e-05, + "loss": 4.0511, + "step": 140800 + }, + { + "epoch": 0.02, + "learning_rate": 4.768639570010542e-05, + "loss": 4.0341, + "step": 141312 + }, + { + "epoch": 0.02, + "learning_rate": 4.7678026131398626e-05, + "loss": 4.0374, + "step": 141824 + }, + { + "epoch": 0.02, + "learning_rate": 4.7669640183888106e-05, + "loss": 4.0487, + "step": 142336 + }, + { + "epoch": 0.02, + "learning_rate": 4.7661254236377586e-05, + "loss": 4.0249, + "step": 142848 + }, + { + "epoch": 0.02, + "learning_rate": 4.765286828886707e-05, + "loss": 4.0421, + "step": 143360 + }, + { + "epoch": 0.02, + "learning_rate": 4.764451509896401e-05, + "loss": 4.0354, + "step": 143872 + }, + { + "epoch": 0.02, + "learning_rate": 4.763612915145349e-05, + "loss": 4.047, + "step": 144384 + }, + { + "epoch": 0.02, + "learning_rate": 4.762774320394297e-05, + "loss": 4.0394, + "step": 144896 + }, + { + "epoch": 0.02, + "learning_rate": 4.761935725643245e-05, + "loss": 4.0266, + "step": 145408 + }, + { + "epoch": 0.02, + "learning_rate": 4.761097130892193e-05, + "loss": 4.0248, + "step": 145920 + }, + { + "epoch": 0.02, + "learning_rate": 4.760258536141141e-05, + "loss": 4.0304, + "step": 146432 + }, + { + "epoch": 0.02, + "learning_rate": 4.759421579270462e-05, + "loss": 4.0399, + "step": 146944 + }, + { + "epoch": 0.02, + "learning_rate": 4.75858298451941e-05, + "loss": 4.0414, + "step": 147456 + }, + { + "epoch": 0.02, + "learning_rate": 4.757744389768358e-05, + "loss": 4.0377, + "step": 147968 + }, + { + "epoch": 0.02, + "learning_rate": 4.756905795017306e-05, + "loss": 4.0228, + "step": 148480 + }, + { + "epoch": 0.02, + "learning_rate": 4.756067200266254e-05, + "loss": 4.0271, + "step": 148992 + }, + { + "epoch": 0.02, + "learning_rate": 4.755228605515202e-05, + "loss": 4.0346, + "step": 149504 + }, + { + "epoch": 0.02, + "learning_rate": 4.75439001076415e-05, + "loss": 4.0287, + "step": 150016 + }, + { + "epoch": 0.02, + "learning_rate": 4.7535530538934716e-05, + "loss": 4.0246, + "step": 150528 + }, + { + "epoch": 0.02, + "learning_rate": 4.7527144591424196e-05, + "loss": 4.0425, + "step": 151040 + }, + { + "epoch": 0.02, + "learning_rate": 4.751875864391367e-05, + "loss": 4.0232, + "step": 151552 + }, + { + "epoch": 0.02, + "learning_rate": 4.751037269640315e-05, + "loss": 4.0267, + "step": 152064 + }, + { + "epoch": 0.02, + "learning_rate": 4.750198674889263e-05, + "loss": 4.0211, + "step": 152576 + }, + { + "epoch": 0.03, + "eval_loss": 4.073619365692139, + "eval_runtime": 572.2917, + "eval_samples_per_second": 666.777, + "eval_steps_per_second": 20.837, + "step": 152638 + }, + { + "epoch": 0.0, + "learning_rate": 4.7493617180185845e-05, + "loss": 4.0314, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.748523123267532e-05, + "loss": 4.027, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.74768452851648e-05, + "loss": 4.0185, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.746845933765428e-05, + "loss": 4.016, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.7460073390143764e-05, + "loss": 4.0105, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.7451687442633244e-05, + "loss": 4.0113, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.7443301495122724e-05, + "loss": 4.0091, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.7434915547612204e-05, + "loss": 4.0082, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.7426545978905413e-05, + "loss": 4.0131, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.741816003139489e-05, + "loss": 4.0143, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.740977408388437e-05, + "loss": 4.0136, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.740138813637385e-05, + "loss": 4.014, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.739301856766706e-05, + "loss": 4.0086, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.738463262015654e-05, + "loss": 4.0035, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.737624667264602e-05, + "loss": 4.0048, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.73678607251355e-05, + "loss": 3.9782, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.735947477762498e-05, + "loss": 4.0035, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.735108883011446e-05, + "loss": 4.0003, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.734270288260394e-05, + "loss": 3.9989, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.733433331389716e-05, + "loss": 4.0165, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.732594736638664e-05, + "loss": 3.9985, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.731756141887612e-05, + "loss": 4.004, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.73091754713656e-05, + "loss": 4.0009, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.730078952385508e-05, + "loss": 3.9989, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.729241995514829e-05, + "loss": 3.9932, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.728403400763777e-05, + "loss": 3.9925, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.727564806012725e-05, + "loss": 4.0005, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.726726211261673e-05, + "loss": 3.9855, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.725887616510621e-05, + "loss": 3.9913, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.725049021759568e-05, + "loss": 3.9783, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.7242120648888896e-05, + "loss": 3.9875, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.723373470137838e-05, + "loss": 3.9964, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.7225348753867856e-05, + "loss": 3.9858, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.7216962806357336e-05, + "loss": 3.9933, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.720859323765055e-05, + "loss": 3.9882, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.720020729014003e-05, + "loss": 3.9907, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.7191821342629505e-05, + "loss": 3.9938, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.7183435395118985e-05, + "loss": 3.9892, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.7175049447608465e-05, + "loss": 3.9855, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.716667987890168e-05, + "loss": 3.9746, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.7158293931391154e-05, + "loss": 3.9852, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.7149907983880634e-05, + "loss": 3.9711, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.714152203637012e-05, + "loss": 3.9873, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.71331360888596e-05, + "loss": 3.9839, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.712475014134908e-05, + "loss": 3.9855, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.711638057264229e-05, + "loss": 3.9764, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.710799462513177e-05, + "loss": 3.9774, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.709960867762125e-05, + "loss": 3.9849, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.709122273011073e-05, + "loss": 3.9654, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.708285316140394e-05, + "loss": 3.9712, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.707446721389342e-05, + "loss": 3.9664, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.70660812663829e-05, + "loss": 3.9847, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.705769531887238e-05, + "loss": 3.9653, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.704930937136186e-05, + "loss": 3.9848, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.7040939802655074e-05, + "loss": 3.9562, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.7032553855144554e-05, + "loss": 3.9683, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.7024167907634034e-05, + "loss": 3.9729, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.7015781960123514e-05, + "loss": 3.9714, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.700741239141672e-05, + "loss": 3.9675, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.69990264439062e-05, + "loss": 3.9809, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.699064049639568e-05, + "loss": 3.95, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.698225454888516e-05, + "loss": 3.9665, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.697386860137464e-05, + "loss": 3.9617, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.696549903266785e-05, + "loss": 3.9703, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.695711308515733e-05, + "loss": 3.9581, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694872713764681e-05, + "loss": 3.9615, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.694034119013629e-05, + "loss": 3.9449, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.693197162142951e-05, + "loss": 3.9678, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.692358567391899e-05, + "loss": 3.9583, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.691519972640847e-05, + "loss": 3.9551, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.690681377889795e-05, + "loss": 3.96, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.6898444210191157e-05, + "loss": 3.9585, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.6890058262680636e-05, + "loss": 3.9563, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.6881672315170116e-05, + "loss": 3.971, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.6873286367659596e-05, + "loss": 3.9653, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.6864916798952806e-05, + "loss": 3.9575, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.6856530851442285e-05, + "loss": 3.9497, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.6848144903931765e-05, + "loss": 3.9519, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.6839758956421245e-05, + "loss": 3.9594, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.6831373008910725e-05, + "loss": 3.9669, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.682300344020394e-05, + "loss": 3.9544, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.681461749269342e-05, + "loss": 3.9572, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.68062315451829e-05, + "loss": 3.9387, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.679784559767238e-05, + "loss": 3.9484, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.678945965016186e-05, + "loss": 3.9406, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.678109008145507e-05, + "loss": 3.9499, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.677270413394455e-05, + "loss": 3.9578, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.676431818643403e-05, + "loss": 3.9499, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.675593223892351e-05, + "loss": 3.9422, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.674756267021672e-05, + "loss": 3.948, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.67391767227062e-05, + "loss": 3.9404, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.673079077519568e-05, + "loss": 3.9511, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.672240482768516e-05, + "loss": 3.9478, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.6714035258978375e-05, + "loss": 3.9334, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.6705649311467855e-05, + "loss": 3.9339, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.6697263363957335e-05, + "loss": 3.9408, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.6688877416446815e-05, + "loss": 3.9506, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.668049146893629e-05, + "loss": 3.9399, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.6672121900229504e-05, + "loss": 3.9491, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.6663735952718984e-05, + "loss": 3.9375, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.665535000520846e-05, + "loss": 3.9383, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.664696405769794e-05, + "loss": 3.9432, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.663859448899115e-05, + "loss": 3.9436, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.663020854148063e-05, + "loss": 3.9319, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.662182259397011e-05, + "loss": 3.9479, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.661343664645959e-05, + "loss": 3.9241, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.660506707775281e-05, + "loss": 3.9281, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.659668113024229e-05, + "loss": 3.9403, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.658829518273176e-05, + "loss": 3.9251, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.657990923522124e-05, + "loss": 3.9378, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.657153966651446e-05, + "loss": 3.9273, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.656315371900393e-05, + "loss": 3.9222, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.655476777149341e-05, + "loss": 3.927, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.654638182398289e-05, + "loss": 3.9477, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.6538012255276106e-05, + "loss": 3.9236, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.6529626307765586e-05, + "loss": 3.9264, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.6521240360255066e-05, + "loss": 3.9186, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.6512854412744546e-05, + "loss": 3.9278, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.650448484403776e-05, + "loss": 3.9354, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.6496098896527235e-05, + "loss": 3.9288, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.6487712949016715e-05, + "loss": 3.9266, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.6479327001506195e-05, + "loss": 3.928, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.6470957432799404e-05, + "loss": 3.9269, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.6462571485288884e-05, + "loss": 3.9262, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.6454185537778364e-05, + "loss": 3.9242, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.6445799590267844e-05, + "loss": 3.9338, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.6437413642757324e-05, + "loss": 3.9209, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.642904407405054e-05, + "loss": 3.9204, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.642065812654002e-05, + "loss": 3.9352, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.64122721790295e-05, + "loss": 3.912, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.640388623151898e-05, + "loss": 3.9253, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.639551666281219e-05, + "loss": 3.9236, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.638713071530167e-05, + "loss": 3.934, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.637874476779115e-05, + "loss": 3.9249, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.637035882028063e-05, + "loss": 3.9197, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.636198925157384e-05, + "loss": 3.9108, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.635360330406332e-05, + "loss": 3.9162, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.63452173565528e-05, + "loss": 3.9275, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.633683140904228e-05, + "loss": 3.9305, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.6328461840335494e-05, + "loss": 3.9262, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.6320075892824974e-05, + "loss": 3.915, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.6311689945314454e-05, + "loss": 3.9144, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.6303303997803934e-05, + "loss": 3.9286, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.629493442909714e-05, + "loss": 3.9156, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.628654848158662e-05, + "loss": 3.9166, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.62781625340761e-05, + "loss": 3.9303, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.626977658656558e-05, + "loss": 3.9154, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.626140701785879e-05, + "loss": 3.9199, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.625302107034827e-05, + "loss": 3.9159, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 4.0001678466796875, + "eval_runtime": 585.2038, + "eval_samples_per_second": 652.065, + "eval_steps_per_second": 20.378, + "step": 228957 + }, + { + "epoch": 0.0, + "learning_rate": 4.624463512283775e-05, + "loss": 3.9246, + "step": 229376 + }, + { + "epoch": 0.0, + "learning_rate": 4.623624917532723e-05, + "loss": 3.9203, + "step": 229888 + }, + { + "epoch": 0.0, + "learning_rate": 4.622786322781671e-05, + "loss": 3.9119, + "step": 230400 + }, + { + "epoch": 0.0, + "learning_rate": 4.62194772803062e-05, + "loss": 3.9105, + "step": 230912 + }, + { + "epoch": 0.0, + "learning_rate": 4.621109133279568e-05, + "loss": 3.9081, + "step": 231424 + }, + { + "epoch": 0.0, + "learning_rate": 4.620270538528516e-05, + "loss": 3.9044, + "step": 231936 + }, + { + "epoch": 0.0, + "learning_rate": 4.619431943777464e-05, + "loss": 3.9074, + "step": 232448 + }, + { + "epoch": 0.0, + "learning_rate": 4.618593349026412e-05, + "loss": 3.9021, + "step": 232960 + }, + { + "epoch": 0.0, + "learning_rate": 4.617756392155733e-05, + "loss": 3.9096, + "step": 233472 + }, + { + "epoch": 0.0, + "learning_rate": 4.616917797404681e-05, + "loss": 3.9161, + "step": 233984 + }, + { + "epoch": 0.0, + "learning_rate": 4.616079202653629e-05, + "loss": 3.9076, + "step": 234496 + }, + { + "epoch": 0.0, + "learning_rate": 4.615240607902577e-05, + "loss": 3.9071, + "step": 235008 + }, + { + "epoch": 0.0, + "learning_rate": 4.6144036510318976e-05, + "loss": 3.9075, + "step": 235520 + }, + { + "epoch": 0.0, + "learning_rate": 4.6135650562808456e-05, + "loss": 3.9042, + "step": 236032 + }, + { + "epoch": 0.0, + "learning_rate": 4.6127264615297936e-05, + "loss": 3.901, + "step": 236544 + }, + { + "epoch": 0.0, + "learning_rate": 4.6118878667787416e-05, + "loss": 3.8802, + "step": 237056 + }, + { + "epoch": 0.0, + "learning_rate": 4.611050909908063e-05, + "loss": 3.8977, + "step": 237568 + }, + { + "epoch": 0.0, + "learning_rate": 4.610212315157011e-05, + "loss": 3.899, + "step": 238080 + }, + { + "epoch": 0.0, + "learning_rate": 4.609373720405959e-05, + "loss": 3.9005, + "step": 238592 + }, + { + "epoch": 0.0, + "learning_rate": 4.6085351256549065e-05, + "loss": 3.9142, + "step": 239104 + }, + { + "epoch": 0.0, + "learning_rate": 4.607698168784228e-05, + "loss": 3.8995, + "step": 239616 + }, + { + "epoch": 0.0, + "learning_rate": 4.606859574033176e-05, + "loss": 3.9076, + "step": 240128 + }, + { + "epoch": 0.0, + "learning_rate": 4.606020979282124e-05, + "loss": 3.8965, + "step": 240640 + }, + { + "epoch": 0.0, + "learning_rate": 4.605184022411445e-05, + "loss": 3.8974, + "step": 241152 + }, + { + "epoch": 0.0, + "learning_rate": 4.604345427660393e-05, + "loss": 3.896, + "step": 241664 + }, + { + "epoch": 0.0, + "learning_rate": 4.603506832909341e-05, + "loss": 3.8981, + "step": 242176 + }, + { + "epoch": 0.0, + "learning_rate": 4.602668238158289e-05, + "loss": 3.8992, + "step": 242688 + }, + { + "epoch": 0.0, + "learning_rate": 4.60183128128761e-05, + "loss": 3.8885, + "step": 243200 + }, + { + "epoch": 0.0, + "learning_rate": 4.6009926865365585e-05, + "loss": 3.8909, + "step": 243712 + }, + { + "epoch": 0.01, + "learning_rate": 4.6001540917855065e-05, + "loss": 3.8819, + "step": 244224 + }, + { + "epoch": 0.01, + "learning_rate": 4.599315497034454e-05, + "loss": 3.8913, + "step": 244736 + }, + { + "epoch": 0.01, + "learning_rate": 4.598476902283402e-05, + "loss": 3.899, + "step": 245248 + }, + { + "epoch": 0.01, + "learning_rate": 4.5976399454127234e-05, + "loss": 3.8937, + "step": 245760 + }, + { + "epoch": 0.01, + "learning_rate": 4.5968013506616714e-05, + "loss": 3.8955, + "step": 246272 + }, + { + "epoch": 0.01, + "learning_rate": 4.595962755910619e-05, + "loss": 3.8936, + "step": 246784 + }, + { + "epoch": 0.01, + "learning_rate": 4.5951257990399403e-05, + "loss": 3.8949, + "step": 247296 + }, + { + "epoch": 0.01, + "learning_rate": 4.594287204288888e-05, + "loss": 3.8959, + "step": 247808 + }, + { + "epoch": 0.01, + "learning_rate": 4.593448609537836e-05, + "loss": 3.8968, + "step": 248320 + }, + { + "epoch": 0.01, + "learning_rate": 4.5926100147867836e-05, + "loss": 3.8883, + "step": 248832 + }, + { + "epoch": 0.01, + "learning_rate": 4.591773057916105e-05, + "loss": 3.8805, + "step": 249344 + }, + { + "epoch": 0.01, + "learning_rate": 4.590934463165054e-05, + "loss": 3.8909, + "step": 249856 + }, + { + "epoch": 0.01, + "learning_rate": 4.590095868414001e-05, + "loss": 3.8738, + "step": 250368 + }, + { + "epoch": 0.01, + "learning_rate": 4.589257273662949e-05, + "loss": 3.8977, + "step": 250880 + }, + { + "epoch": 0.01, + "learning_rate": 4.588420316792271e-05, + "loss": 3.8916, + "step": 251392 + }, + { + "epoch": 0.01, + "learning_rate": 4.587581722041219e-05, + "loss": 3.8904, + "step": 251904 + }, + { + "epoch": 0.01, + "learning_rate": 4.586743127290166e-05, + "loss": 3.8835, + "step": 252416 + }, + { + "epoch": 0.01, + "learning_rate": 4.585904532539114e-05, + "loss": 3.8835, + "step": 252928 + }, + { + "epoch": 0.01, + "learning_rate": 4.585067575668436e-05, + "loss": 3.8957, + "step": 253440 + }, + { + "epoch": 0.01, + "learning_rate": 4.584228980917384e-05, + "loss": 3.8722, + "step": 253952 + }, + { + "epoch": 0.01, + "learning_rate": 4.583390386166331e-05, + "loss": 3.8779, + "step": 254464 + }, + { + "epoch": 0.01, + "learning_rate": 4.582551791415279e-05, + "loss": 3.8791, + "step": 254976 + }, + { + "epoch": 0.01, + "learning_rate": 4.5817148345446006e-05, + "loss": 3.8902, + "step": 255488 + }, + { + "epoch": 0.01, + "learning_rate": 4.5808762397935486e-05, + "loss": 3.8723, + "step": 256000 + }, + { + "epoch": 0.01, + "learning_rate": 4.5800376450424966e-05, + "loss": 3.8931, + "step": 256512 + }, + { + "epoch": 0.01, + "learning_rate": 4.5791990502914446e-05, + "loss": 3.8707, + "step": 257024 + }, + { + "epoch": 0.01, + "learning_rate": 4.578362093420766e-05, + "loss": 3.8716, + "step": 257536 + }, + { + "epoch": 0.01, + "learning_rate": 4.5775234986697135e-05, + "loss": 3.8867, + "step": 258048 + }, + { + "epoch": 0.01, + "learning_rate": 4.5766849039186615e-05, + "loss": 3.874, + "step": 258560 + }, + { + "epoch": 0.01, + "learning_rate": 4.5758463091676095e-05, + "loss": 3.8863, + "step": 259072 + }, + { + "epoch": 0.01, + "learning_rate": 4.575009352296931e-05, + "loss": 3.8918, + "step": 259584 + }, + { + "epoch": 0.01, + "learning_rate": 4.5741707575458784e-05, + "loss": 3.8653, + "step": 260096 + }, + { + "epoch": 0.01, + "learning_rate": 4.5733321627948264e-05, + "loss": 3.8725, + "step": 260608 + }, + { + "epoch": 0.01, + "learning_rate": 4.5724935680437744e-05, + "loss": 3.8754, + "step": 261120 + }, + { + "epoch": 0.01, + "learning_rate": 4.571656611173096e-05, + "loss": 3.8805, + "step": 261632 + }, + { + "epoch": 0.01, + "learning_rate": 4.570818016422044e-05, + "loss": 3.8697, + "step": 262144 + }, + { + "epoch": 0.01, + "learning_rate": 4.569979421670992e-05, + "loss": 3.8735, + "step": 262656 + }, + { + "epoch": 0.01, + "learning_rate": 4.56914082691994e-05, + "loss": 3.8568, + "step": 263168 + }, + { + "epoch": 0.01, + "learning_rate": 4.568303870049261e-05, + "loss": 3.8805, + "step": 263680 + }, + { + "epoch": 0.01, + "learning_rate": 4.567465275298209e-05, + "loss": 3.8711, + "step": 264192 + }, + { + "epoch": 0.01, + "learning_rate": 4.566626680547157e-05, + "loss": 3.8672, + "step": 264704 + }, + { + "epoch": 0.01, + "learning_rate": 4.565788085796105e-05, + "loss": 3.8717, + "step": 265216 + }, + { + "epoch": 0.01, + "learning_rate": 4.564951128925426e-05, + "loss": 3.8724, + "step": 265728 + }, + { + "epoch": 0.01, + "learning_rate": 4.564112534174374e-05, + "loss": 3.8714, + "step": 266240 + }, + { + "epoch": 0.01, + "learning_rate": 4.563273939423322e-05, + "loss": 3.8829, + "step": 266752 + }, + { + "epoch": 0.01, + "learning_rate": 4.56243534467227e-05, + "loss": 3.8802, + "step": 267264 + }, + { + "epoch": 0.01, + "learning_rate": 4.561598387801591e-05, + "loss": 3.874, + "step": 267776 + }, + { + "epoch": 0.01, + "learning_rate": 4.560759793050539e-05, + "loss": 3.867, + "step": 268288 + }, + { + "epoch": 0.01, + "learning_rate": 4.559921198299487e-05, + "loss": 3.8681, + "step": 268800 + }, + { + "epoch": 0.01, + "learning_rate": 4.559082603548435e-05, + "loss": 3.871, + "step": 269312 + }, + { + "epoch": 0.01, + "learning_rate": 4.558245646677756e-05, + "loss": 3.8833, + "step": 269824 + }, + { + "epoch": 0.01, + "learning_rate": 4.557407051926704e-05, + "loss": 3.8726, + "step": 270336 + }, + { + "epoch": 0.01, + "learning_rate": 4.556568457175652e-05, + "loss": 3.8659, + "step": 270848 + }, + { + "epoch": 0.01, + "learning_rate": 4.5557298624246e-05, + "loss": 3.86, + "step": 271360 + }, + { + "epoch": 0.01, + "learning_rate": 4.554892905553921e-05, + "loss": 3.8646, + "step": 271872 + }, + { + "epoch": 0.01, + "learning_rate": 4.554054310802869e-05, + "loss": 3.8588, + "step": 272384 + }, + { + "epoch": 0.01, + "learning_rate": 4.553215716051817e-05, + "loss": 3.8657, + "step": 272896 + }, + { + "epoch": 0.01, + "learning_rate": 4.552377121300765e-05, + "loss": 3.8681, + "step": 273408 + }, + { + "epoch": 0.01, + "learning_rate": 4.551540164430087e-05, + "loss": 3.8672, + "step": 273920 + }, + { + "epoch": 0.01, + "learning_rate": 4.550701569679035e-05, + "loss": 3.8613, + "step": 274432 + }, + { + "epoch": 0.02, + "learning_rate": 4.549862974927983e-05, + "loss": 3.8701, + "step": 274944 + }, + { + "epoch": 0.02, + "learning_rate": 4.549024380176931e-05, + "loss": 3.859, + "step": 275456 + }, + { + "epoch": 0.02, + "learning_rate": 4.5481874233062516e-05, + "loss": 3.8636, + "step": 275968 + }, + { + "epoch": 0.02, + "learning_rate": 4.5473488285551996e-05, + "loss": 3.8643, + "step": 276480 + }, + { + "epoch": 0.02, + "learning_rate": 4.5465102338041476e-05, + "loss": 3.8522, + "step": 276992 + }, + { + "epoch": 0.02, + "learning_rate": 4.5456716390530956e-05, + "loss": 3.8508, + "step": 277504 + }, + { + "epoch": 0.02, + "learning_rate": 4.5448346821824165e-05, + "loss": 3.8648, + "step": 278016 + }, + { + "epoch": 0.02, + "learning_rate": 4.5439960874313645e-05, + "loss": 3.862, + "step": 278528 + }, + { + "epoch": 0.02, + "learning_rate": 4.5431574926803125e-05, + "loss": 3.868, + "step": 279040 + }, + { + "epoch": 0.02, + "learning_rate": 4.5423188979292605e-05, + "loss": 3.8632, + "step": 279552 + }, + { + "epoch": 0.02, + "learning_rate": 4.541481941058582e-05, + "loss": 3.8568, + "step": 280064 + }, + { + "epoch": 0.02, + "learning_rate": 4.54064334630753e-05, + "loss": 3.8565, + "step": 280576 + }, + { + "epoch": 0.02, + "learning_rate": 4.539804751556478e-05, + "loss": 3.8654, + "step": 281088 + }, + { + "epoch": 0.02, + "learning_rate": 4.538966156805426e-05, + "loss": 3.8646, + "step": 281600 + }, + { + "epoch": 0.02, + "learning_rate": 4.538129199934747e-05, + "loss": 3.8516, + "step": 282112 + }, + { + "epoch": 0.02, + "learning_rate": 4.537290605183695e-05, + "loss": 3.869, + "step": 282624 + }, + { + "epoch": 0.02, + "learning_rate": 4.536452010432643e-05, + "loss": 3.8431, + "step": 283136 + }, + { + "epoch": 0.02, + "learning_rate": 4.535613415681591e-05, + "loss": 3.8524, + "step": 283648 + }, + { + "epoch": 0.02, + "learning_rate": 4.534776458810912e-05, + "loss": 3.8605, + "step": 284160 + }, + { + "epoch": 0.02, + "learning_rate": 4.53393786405986e-05, + "loss": 3.847, + "step": 284672 + }, + { + "epoch": 0.02, + "learning_rate": 4.533099269308808e-05, + "loss": 3.8602, + "step": 285184 + }, + { + "epoch": 0.02, + "learning_rate": 4.532260674557756e-05, + "loss": 3.8454, + "step": 285696 + }, + { + "epoch": 0.02, + "learning_rate": 4.5314237176870774e-05, + "loss": 3.8418, + "step": 286208 + }, + { + "epoch": 0.02, + "learning_rate": 4.5305851229360254e-05, + "loss": 3.8496, + "step": 286720 + }, + { + "epoch": 0.02, + "learning_rate": 4.5297465281849734e-05, + "loss": 3.8695, + "step": 287232 + }, + { + "epoch": 0.02, + "learning_rate": 4.5289079334339214e-05, + "loss": 3.8486, + "step": 287744 + }, + { + "epoch": 0.02, + "learning_rate": 4.528070976563242e-05, + "loss": 3.8484, + "step": 288256 + }, + { + "epoch": 0.02, + "learning_rate": 4.52723238181219e-05, + "loss": 3.8419, + "step": 288768 + }, + { + "epoch": 0.02, + "learning_rate": 4.526393787061138e-05, + "loss": 3.8506, + "step": 289280 + }, + { + "epoch": 0.02, + "learning_rate": 4.525555192310086e-05, + "loss": 3.857, + "step": 289792 + }, + { + "epoch": 0.02, + "learning_rate": 4.524718235439407e-05, + "loss": 3.8533, + "step": 290304 + }, + { + "epoch": 0.02, + "learning_rate": 4.523879640688355e-05, + "loss": 3.8446, + "step": 290816 + }, + { + "epoch": 0.02, + "learning_rate": 4.523041045937303e-05, + "loss": 3.8561, + "step": 291328 + }, + { + "epoch": 0.02, + "learning_rate": 4.522202451186251e-05, + "loss": 3.8503, + "step": 291840 + }, + { + "epoch": 0.02, + "learning_rate": 4.521365494315573e-05, + "loss": 3.851, + "step": 292352 + }, + { + "epoch": 0.02, + "learning_rate": 4.520526899564521e-05, + "loss": 3.8456, + "step": 292864 + }, + { + "epoch": 0.02, + "learning_rate": 4.519688304813469e-05, + "loss": 3.8576, + "step": 293376 + }, + { + "epoch": 0.02, + "learning_rate": 4.518849710062417e-05, + "loss": 3.8462, + "step": 293888 + }, + { + "epoch": 0.02, + "learning_rate": 4.518012753191738e-05, + "loss": 3.8458, + "step": 294400 + }, + { + "epoch": 0.02, + "learning_rate": 4.517174158440686e-05, + "loss": 3.8599, + "step": 294912 + }, + { + "epoch": 0.02, + "learning_rate": 4.516335563689634e-05, + "loss": 3.8362, + "step": 295424 + }, + { + "epoch": 0.02, + "learning_rate": 4.515496968938582e-05, + "loss": 3.8494, + "step": 295936 + }, + { + "epoch": 0.02, + "learning_rate": 4.5146600120679026e-05, + "loss": 3.8517, + "step": 296448 + }, + { + "epoch": 0.02, + "learning_rate": 4.5138214173168506e-05, + "loss": 3.8567, + "step": 296960 + }, + { + "epoch": 0.02, + "learning_rate": 4.5129828225657986e-05, + "loss": 3.849, + "step": 297472 + }, + { + "epoch": 0.02, + "learning_rate": 4.5121442278147466e-05, + "loss": 3.8474, + "step": 297984 + }, + { + "epoch": 0.02, + "learning_rate": 4.511307270944068e-05, + "loss": 3.8374, + "step": 298496 + }, + { + "epoch": 0.02, + "learning_rate": 4.510468676193016e-05, + "loss": 3.8415, + "step": 299008 + }, + { + "epoch": 0.02, + "learning_rate": 4.509630081441964e-05, + "loss": 3.8513, + "step": 299520 + }, + { + "epoch": 0.02, + "learning_rate": 4.508791486690912e-05, + "loss": 3.8564, + "step": 300032 + }, + { + "epoch": 0.02, + "learning_rate": 4.507954529820233e-05, + "loss": 3.8545, + "step": 300544 + }, + { + "epoch": 0.02, + "learning_rate": 4.507115935069181e-05, + "loss": 3.8439, + "step": 301056 + }, + { + "epoch": 0.02, + "learning_rate": 4.506277340318129e-05, + "loss": 3.8378, + "step": 301568 + }, + { + "epoch": 0.02, + "learning_rate": 4.505438745567077e-05, + "loss": 3.854, + "step": 302080 + }, + { + "epoch": 0.02, + "learning_rate": 4.504601788696398e-05, + "loss": 3.843, + "step": 302592 + }, + { + "epoch": 0.02, + "learning_rate": 4.503763193945346e-05, + "loss": 3.8447, + "step": 303104 + }, + { + "epoch": 0.02, + "learning_rate": 4.502924599194294e-05, + "loss": 3.8556, + "step": 303616 + }, + { + "epoch": 0.02, + "learning_rate": 4.5020876423236155e-05, + "loss": 3.8464, + "step": 304128 + }, + { + "epoch": 0.02, + "learning_rate": 4.5012490475725635e-05, + "loss": 3.8461, + "step": 304640 + }, + { + "epoch": 0.02, + "learning_rate": 4.5004104528215115e-05, + "loss": 3.8439, + "step": 305152 + }, + { + "epoch": 0.03, + "eval_loss": 3.9584410190582275, + "eval_runtime": 567.4578, + "eval_samples_per_second": 672.457, + "eval_steps_per_second": 21.015, + "step": 305276 + }, + { + "epoch": 0.0, + "learning_rate": 4.4995718580704595e-05, + "loss": 3.8527, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.4987332633194075e-05, + "loss": 3.8476, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.4978946685683555e-05, + "loss": 3.8394, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.4970560738173035e-05, + "loss": 3.8381, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.496217479066251e-05, + "loss": 3.838, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.495378884315199e-05, + "loss": 3.8335, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.494540289564147e-05, + "loss": 3.8376, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.493701694813095e-05, + "loss": 3.83, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.492864737942416e-05, + "loss": 3.8396, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.492027781071737e-05, + "loss": 3.8461, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.491189186320685e-05, + "loss": 3.8329, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.490350591569633e-05, + "loss": 3.8342, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.489513634698955e-05, + "loss": 3.8393, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.488675039947903e-05, + "loss": 3.835, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.487836445196851e-05, + "loss": 3.8332, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.486997850445798e-05, + "loss": 3.8105, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.486159255694746e-05, + "loss": 3.8275, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.485320660943694e-05, + "loss": 3.8306, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.484482066192642e-05, + "loss": 3.8311, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.48364347144159e-05, + "loss": 3.8493, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.482804876690538e-05, + "loss": 3.8264, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.481966281939486e-05, + "loss": 3.8397, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.481127687188434e-05, + "loss": 3.8257, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.480290730317756e-05, + "loss": 3.8324, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.479452135566704e-05, + "loss": 3.8238, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.478613540815652e-05, + "loss": 3.8305, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.4777749460646e-05, + "loss": 3.8314, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.4769379891939207e-05, + "loss": 3.8244, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.4760993944428687e-05, + "loss": 3.8225, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.4752607996918166e-05, + "loss": 3.8166, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.4744222049407646e-05, + "loss": 3.8183, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.4735852480700856e-05, + "loss": 3.8307, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.4727466533190335e-05, + "loss": 3.8272, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.4719080585679815e-05, + "loss": 3.8313, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.4710694638169295e-05, + "loss": 3.8261, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.470232506946251e-05, + "loss": 3.8296, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.469393912195199e-05, + "loss": 3.828, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.468555317444147e-05, + "loss": 3.8298, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.467716722693095e-05, + "loss": 3.8245, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.466879765822416e-05, + "loss": 3.8148, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.466041171071364e-05, + "loss": 3.8295, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.465202576320312e-05, + "loss": 3.8086, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.46436398156926e-05, + "loss": 3.8284, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.463527024698581e-05, + "loss": 3.8243, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.462688429947529e-05, + "loss": 3.8302, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.461849835196477e-05, + "loss": 3.8193, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.461011240445425e-05, + "loss": 3.8167, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.4601742835747465e-05, + "loss": 3.8301, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.4593356888236945e-05, + "loss": 3.811, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.4584970940726425e-05, + "loss": 3.8128, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.4576584993215905e-05, + "loss": 3.8157, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.4568215424509114e-05, + "loss": 3.8203, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.4559829476998594e-05, + "loss": 3.8119, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.4551443529488074e-05, + "loss": 3.8246, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.4543057581977554e-05, + "loss": 3.8073, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.453468801327076e-05, + "loss": 3.8109, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.452630206576024e-05, + "loss": 3.8213, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.451791611824972e-05, + "loss": 3.8071, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.45095301707392e-05, + "loss": 3.8261, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.450116060203242e-05, + "loss": 3.831, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.44927746545219e-05, + "loss": 3.7996, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.448438870701138e-05, + "loss": 3.8079, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.447600275950086e-05, + "loss": 3.8134, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.446763319079407e-05, + "loss": 3.8226, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.445924724328355e-05, + "loss": 3.8069, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.445086129577303e-05, + "loss": 3.8078, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.444247534826251e-05, + "loss": 3.7981, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.4434105779555717e-05, + "loss": 3.8145, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.4425719832045196e-05, + "loss": 3.8098, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.4417333884534676e-05, + "loss": 3.8025, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.4408947937024156e-05, + "loss": 3.8112, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.440057836831737e-05, + "loss": 3.8099, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.439219242080685e-05, + "loss": 3.8091, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.438380647329633e-05, + "loss": 3.8213, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.437543690458954e-05, + "loss": 3.8183, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.436705095707902e-05, + "loss": 3.8131, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.43586650095685e-05, + "loss": 3.8078, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.435027906205798e-05, + "loss": 3.8104, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.434190949335119e-05, + "loss": 3.805, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.433352354584067e-05, + "loss": 3.8279, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.432513759833015e-05, + "loss": 3.8094, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.431675165081963e-05, + "loss": 3.807, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.430838208211284e-05, + "loss": 3.7959, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.4300012513406055e-05, + "loss": 3.8106, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.4291626565895535e-05, + "loss": 3.7961, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.4283240618385015e-05, + "loss": 3.8083, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.4274854670874495e-05, + "loss": 3.8067, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.4266468723363975e-05, + "loss": 3.8056, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.4258082775853455e-05, + "loss": 3.8024, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.4249696828342935e-05, + "loss": 3.8116, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.4241327259636144e-05, + "loss": 3.7984, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.4232941312125624e-05, + "loss": 3.8047, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.4224555364615104e-05, + "loss": 3.8078, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.4216169417104584e-05, + "loss": 3.7899, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.420779984839779e-05, + "loss": 3.7936, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.419941390088728e-05, + "loss": 3.8082, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.419102795337676e-05, + "loss": 3.7993, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.418264200586624e-05, + "loss": 3.8147, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.417427243715945e-05, + "loss": 3.8011, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.416590286845266e-05, + "loss": 3.7934, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.415751692094214e-05, + "loss": 3.7991, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.414913097343162e-05, + "loss": 3.8052, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.41407450259211e-05, + "loss": 3.8063, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.413235907841058e-05, + "loss": 3.7956, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.412397313090006e-05, + "loss": 3.8089, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.411558718338953e-05, + "loss": 3.785, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.4107217614682747e-05, + "loss": 3.793, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.409883166717223e-05, + "loss": 3.804, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.409044571966171e-05, + "loss": 3.7861, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.4082059772151186e-05, + "loss": 3.8018, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.40736902034444e-05, + "loss": 3.7973, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.406532063473761e-05, + "loss": 3.7789, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.405693468722709e-05, + "loss": 3.7933, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.404854873971657e-05, + "loss": 3.8113, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.404016279220605e-05, + "loss": 3.7903, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.403177684469553e-05, + "loss": 3.7929, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.4023390897185004e-05, + "loss": 3.7864, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.4015004949674484e-05, + "loss": 3.7913, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.400661900216397e-05, + "loss": 3.8028, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.399824943345719e-05, + "loss": 3.7962, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.398986348594666e-05, + "loss": 3.7887, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.398147753843614e-05, + "loss": 3.7944, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.397309159092562e-05, + "loss": 3.7962, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.3964738401022565e-05, + "loss": 3.7932, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.3956352453512045e-05, + "loss": 3.7921, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.3947966506001525e-05, + "loss": 3.8002, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.3939580558491005e-05, + "loss": 3.7864, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.393119461098048e-05, + "loss": 3.795, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.392280866346996e-05, + "loss": 3.799, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.391442271595944e-05, + "loss": 3.7845, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.3906036768448925e-05, + "loss": 3.7901, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.3897667199742134e-05, + "loss": 3.7978, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.3889281252231614e-05, + "loss": 3.7978, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.3880895304721094e-05, + "loss": 3.7974, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.3872509357210574e-05, + "loss": 3.7909, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.386413978850378e-05, + "loss": 3.7821, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.385575384099326e-05, + "loss": 3.7864, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.384736789348274e-05, + "loss": 3.7941, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.383898194597222e-05, + "loss": 3.8014, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.383061237726543e-05, + "loss": 3.8019, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.382222642975491e-05, + "loss": 3.7914, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.381384048224439e-05, + "loss": 3.7805, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.380547091353761e-05, + "loss": 3.7986, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.379708496602709e-05, + "loss": 3.7855, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.378869901851657e-05, + "loss": 3.7909, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.378031307100605e-05, + "loss": 3.8031, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.377192712349553e-05, + "loss": 3.793, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.376354117598501e-05, + "loss": 3.7864, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.375515522847449e-05, + "loss": 3.7926, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 3.9340226650238037, + "eval_runtime": 557.6516, + "eval_samples_per_second": 684.282, + "eval_steps_per_second": 21.384, + "step": 381595 + }, + { + "epoch": 0.0, + "learning_rate": 4.374676928096397e-05, + "loss": 3.8003, + "step": 381952 + }, + { + "epoch": 0.0, + "learning_rate": 4.373838333345345e-05, + "loss": 3.7969, + "step": 382464 + }, + { + "epoch": 0.0, + "learning_rate": 4.372999738594293e-05, + "loss": 3.7822, + "step": 382976 + }, + { + "epoch": 0.0, + "learning_rate": 4.372161143843241e-05, + "loss": 3.7822, + "step": 383488 + }, + { + "epoch": 0.0, + "learning_rate": 4.3713241869725616e-05, + "loss": 3.7876, + "step": 384000 + }, + { + "epoch": 0.0, + "learning_rate": 4.3704855922215096e-05, + "loss": 3.7809, + "step": 384512 + }, + { + "epoch": 0.0, + "learning_rate": 4.3696469974704576e-05, + "loss": 3.7832, + "step": 385024 + }, + { + "epoch": 0.0, + "learning_rate": 4.368808402719406e-05, + "loss": 3.7703, + "step": 385536 + }, + { + "epoch": 0.0, + "learning_rate": 4.367969807968354e-05, + "loss": 3.7881, + "step": 386048 + }, + { + "epoch": 0.0, + "learning_rate": 4.367132851097675e-05, + "loss": 3.7967, + "step": 386560 + }, + { + "epoch": 0.0, + "learning_rate": 4.366294256346623e-05, + "loss": 3.7782, + "step": 387072 + }, + { + "epoch": 0.0, + "learning_rate": 4.365455661595571e-05, + "loss": 3.7794, + "step": 387584 + }, + { + "epoch": 0.0, + "learning_rate": 4.364618704724892e-05, + "loss": 3.7882, + "step": 388096 + }, + { + "epoch": 0.0, + "learning_rate": 4.36378010997384e-05, + "loss": 3.7807, + "step": 388608 + }, + { + "epoch": 0.0, + "learning_rate": 4.362941515222788e-05, + "loss": 3.7828, + "step": 389120 + }, + { + "epoch": 0.0, + "learning_rate": 4.362102920471736e-05, + "loss": 3.7584, + "step": 389632 + }, + { + "epoch": 0.0, + "learning_rate": 4.361264325720684e-05, + "loss": 3.7721, + "step": 390144 + }, + { + "epoch": 0.0, + "learning_rate": 4.3604257309696314e-05, + "loss": 3.7766, + "step": 390656 + }, + { + "epoch": 0.0, + "learning_rate": 4.35958713621858e-05, + "loss": 3.7786, + "step": 391168 + }, + { + "epoch": 0.0, + "learning_rate": 4.358748541467528e-05, + "loss": 3.7968, + "step": 391680 + }, + { + "epoch": 0.0, + "learning_rate": 4.357909946716476e-05, + "loss": 3.7764, + "step": 392192 + }, + { + "epoch": 0.0, + "learning_rate": 4.357071351965424e-05, + "loss": 3.7889, + "step": 392704 + }, + { + "epoch": 0.0, + "learning_rate": 4.356232757214372e-05, + "loss": 3.7749, + "step": 393216 + }, + { + "epoch": 0.0, + "learning_rate": 4.355395800343693e-05, + "loss": 3.7805, + "step": 393728 + }, + { + "epoch": 0.0, + "learning_rate": 4.354557205592641e-05, + "loss": 3.7697, + "step": 394240 + }, + { + "epoch": 0.0, + "learning_rate": 4.353718610841589e-05, + "loss": 3.7767, + "step": 394752 + }, + { + "epoch": 0.0, + "learning_rate": 4.352880016090537e-05, + "loss": 3.7796, + "step": 395264 + }, + { + "epoch": 0.0, + "learning_rate": 4.352041421339485e-05, + "loss": 3.7732, + "step": 395776 + }, + { + "epoch": 0.0, + "learning_rate": 4.351202826588433e-05, + "loss": 3.7698, + "step": 396288 + }, + { + "epoch": 0.0, + "learning_rate": 4.350365869717754e-05, + "loss": 3.7662, + "step": 396800 + }, + { + "epoch": 0.01, + "learning_rate": 4.349527274966702e-05, + "loss": 3.762, + "step": 397312 + }, + { + "epoch": 0.01, + "learning_rate": 4.34868868021565e-05, + "loss": 3.7814, + "step": 397824 + }, + { + "epoch": 0.01, + "learning_rate": 4.347850085464598e-05, + "loss": 3.7815, + "step": 398336 + }, + { + "epoch": 0.01, + "learning_rate": 4.3470114907135465e-05, + "loss": 3.7769, + "step": 398848 + }, + { + "epoch": 0.01, + "learning_rate": 4.3461728959624945e-05, + "loss": 3.7761, + "step": 399360 + }, + { + "epoch": 0.01, + "learning_rate": 4.3453343012114425e-05, + "loss": 3.7789, + "step": 399872 + }, + { + "epoch": 0.01, + "learning_rate": 4.3444973443407634e-05, + "loss": 3.7801, + "step": 400384 + }, + { + "epoch": 0.01, + "learning_rate": 4.3436587495897114e-05, + "loss": 3.7749, + "step": 400896 + }, + { + "epoch": 0.01, + "learning_rate": 4.342821792719032e-05, + "loss": 3.7767, + "step": 401408 + }, + { + "epoch": 0.01, + "learning_rate": 4.34198319796798e-05, + "loss": 3.7649, + "step": 401920 + }, + { + "epoch": 0.01, + "learning_rate": 4.341144603216928e-05, + "loss": 3.7773, + "step": 402432 + }, + { + "epoch": 0.01, + "learning_rate": 4.340306008465876e-05, + "loss": 3.7593, + "step": 402944 + }, + { + "epoch": 0.01, + "learning_rate": 4.339469051595197e-05, + "loss": 3.78, + "step": 403456 + }, + { + "epoch": 0.01, + "learning_rate": 4.338630456844145e-05, + "loss": 3.7716, + "step": 403968 + }, + { + "epoch": 0.01, + "learning_rate": 4.337791862093093e-05, + "loss": 3.7786, + "step": 404480 + }, + { + "epoch": 0.01, + "learning_rate": 4.336953267342042e-05, + "loss": 3.7693, + "step": 404992 + }, + { + "epoch": 0.01, + "learning_rate": 4.33611467259099e-05, + "loss": 3.7677, + "step": 405504 + }, + { + "epoch": 0.01, + "learning_rate": 4.335277715720311e-05, + "loss": 3.7837, + "step": 406016 + }, + { + "epoch": 0.01, + "learning_rate": 4.334439120969259e-05, + "loss": 3.7571, + "step": 406528 + }, + { + "epoch": 0.01, + "learning_rate": 4.333600526218207e-05, + "loss": 3.764, + "step": 407040 + }, + { + "epoch": 0.01, + "learning_rate": 4.332761931467155e-05, + "loss": 3.767, + "step": 407552 + }, + { + "epoch": 0.01, + "learning_rate": 4.331923336716103e-05, + "loss": 3.7694, + "step": 408064 + }, + { + "epoch": 0.01, + "learning_rate": 4.331086379845424e-05, + "loss": 3.765, + "step": 408576 + }, + { + "epoch": 0.01, + "learning_rate": 4.3302477850943717e-05, + "loss": 3.7715, + "step": 409088 + }, + { + "epoch": 0.01, + "learning_rate": 4.3294091903433197e-05, + "loss": 3.7625, + "step": 409600 + }, + { + "epoch": 0.01, + "learning_rate": 4.3285705955922677e-05, + "loss": 3.76, + "step": 410112 + }, + { + "epoch": 0.01, + "learning_rate": 4.3277320008412156e-05, + "loss": 3.7724, + "step": 410624 + }, + { + "epoch": 0.01, + "learning_rate": 4.326895043970537e-05, + "loss": 3.7613, + "step": 411136 + }, + { + "epoch": 0.01, + "learning_rate": 4.326056449219485e-05, + "loss": 3.7727, + "step": 411648 + }, + { + "epoch": 0.01, + "learning_rate": 4.3252178544684325e-05, + "loss": 3.7798, + "step": 412160 + }, + { + "epoch": 0.01, + "learning_rate": 4.3243792597173805e-05, + "loss": 3.7544, + "step": 412672 + }, + { + "epoch": 0.01, + "learning_rate": 4.3235406649663285e-05, + "loss": 3.7581, + "step": 413184 + }, + { + "epoch": 0.01, + "learning_rate": 4.3227020702152765e-05, + "loss": 3.7609, + "step": 413696 + }, + { + "epoch": 0.01, + "learning_rate": 4.3218634754642245e-05, + "loss": 3.7775, + "step": 414208 + }, + { + "epoch": 0.01, + "learning_rate": 4.3210248807131725e-05, + "loss": 3.7595, + "step": 414720 + }, + { + "epoch": 0.01, + "learning_rate": 4.3201879238424934e-05, + "loss": 3.7617, + "step": 415232 + }, + { + "epoch": 0.01, + "learning_rate": 4.3193493290914414e-05, + "loss": 3.749, + "step": 415744 + }, + { + "epoch": 0.01, + "learning_rate": 4.3185107343403894e-05, + "loss": 3.7681, + "step": 416256 + }, + { + "epoch": 0.01, + "learning_rate": 4.3176721395893374e-05, + "loss": 3.7582, + "step": 416768 + }, + { + "epoch": 0.01, + "learning_rate": 4.3168335448382854e-05, + "loss": 3.7554, + "step": 417280 + }, + { + "epoch": 0.01, + "learning_rate": 4.315996587967607e-05, + "loss": 3.7619, + "step": 417792 + }, + { + "epoch": 0.01, + "learning_rate": 4.315157993216555e-05, + "loss": 3.7634, + "step": 418304 + }, + { + "epoch": 0.01, + "learning_rate": 4.314319398465503e-05, + "loss": 3.7608, + "step": 418816 + }, + { + "epoch": 0.01, + "learning_rate": 4.313480803714451e-05, + "loss": 3.7722, + "step": 419328 + }, + { + "epoch": 0.01, + "learning_rate": 4.312642208963399e-05, + "loss": 3.771, + "step": 419840 + }, + { + "epoch": 0.01, + "learning_rate": 4.31180525209272e-05, + "loss": 3.7646, + "step": 420352 + }, + { + "epoch": 0.01, + "learning_rate": 4.310966657341668e-05, + "loss": 3.76, + "step": 420864 + }, + { + "epoch": 0.01, + "learning_rate": 4.310128062590616e-05, + "loss": 3.7646, + "step": 421376 + }, + { + "epoch": 0.01, + "learning_rate": 4.309289467839564e-05, + "loss": 3.7534, + "step": 421888 + }, + { + "epoch": 0.01, + "learning_rate": 4.308450873088512e-05, + "loss": 3.776, + "step": 422400 + }, + { + "epoch": 0.01, + "learning_rate": 4.30761227833746e-05, + "loss": 3.7606, + "step": 422912 + }, + { + "epoch": 0.01, + "learning_rate": 4.306775321466781e-05, + "loss": 3.7629, + "step": 423424 + }, + { + "epoch": 0.01, + "learning_rate": 4.305936726715729e-05, + "loss": 3.7494, + "step": 423936 + }, + { + "epoch": 0.01, + "learning_rate": 4.3050981319646775e-05, + "loss": 3.7631, + "step": 424448 + }, + { + "epoch": 0.01, + "learning_rate": 4.3042595372136254e-05, + "loss": 3.7462, + "step": 424960 + }, + { + "epoch": 0.01, + "learning_rate": 4.3034225803429464e-05, + "loss": 3.7624, + "step": 425472 + }, + { + "epoch": 0.01, + "learning_rate": 4.3025839855918944e-05, + "loss": 3.7598, + "step": 425984 + }, + { + "epoch": 0.01, + "learning_rate": 4.3017453908408424e-05, + "loss": 3.7581, + "step": 426496 + }, + { + "epoch": 0.01, + "learning_rate": 4.3009067960897903e-05, + "loss": 3.7588, + "step": 427008 + }, + { + "epoch": 0.02, + "learning_rate": 4.300069839219111e-05, + "loss": 3.7677, + "step": 427520 + }, + { + "epoch": 0.02, + "learning_rate": 4.299231244468059e-05, + "loss": 3.7459, + "step": 428032 + }, + { + "epoch": 0.02, + "learning_rate": 4.298392649717007e-05, + "loss": 3.7554, + "step": 428544 + }, + { + "epoch": 0.02, + "learning_rate": 4.297554054965955e-05, + "loss": 3.7627, + "step": 429056 + }, + { + "epoch": 0.02, + "learning_rate": 4.296715460214903e-05, + "loss": 3.7443, + "step": 429568 + }, + { + "epoch": 0.02, + "learning_rate": 4.295876865463851e-05, + "loss": 3.7478, + "step": 430080 + }, + { + "epoch": 0.02, + "learning_rate": 4.295039908593173e-05, + "loss": 3.7611, + "step": 430592 + }, + { + "epoch": 0.02, + "learning_rate": 4.294201313842121e-05, + "loss": 3.7494, + "step": 431104 + }, + { + "epoch": 0.02, + "learning_rate": 4.293362719091069e-05, + "loss": 3.7728, + "step": 431616 + }, + { + "epoch": 0.02, + "learning_rate": 4.292524124340016e-05, + "loss": 3.7558, + "step": 432128 + }, + { + "epoch": 0.02, + "learning_rate": 4.291685529588964e-05, + "loss": 3.7469, + "step": 432640 + }, + { + "epoch": 0.02, + "learning_rate": 4.290846934837912e-05, + "loss": 3.751, + "step": 433152 + }, + { + "epoch": 0.02, + "learning_rate": 4.29000834008686e-05, + "loss": 3.7602, + "step": 433664 + }, + { + "epoch": 0.02, + "learning_rate": 4.289169745335808e-05, + "loss": 3.7617, + "step": 434176 + }, + { + "epoch": 0.02, + "learning_rate": 4.288332788465129e-05, + "loss": 3.7472, + "step": 434688 + }, + { + "epoch": 0.02, + "learning_rate": 4.2874958315944506e-05, + "loss": 3.7623, + "step": 435200 + }, + { + "epoch": 0.02, + "learning_rate": 4.286657236843398e-05, + "loss": 3.739, + "step": 435712 + }, + { + "epoch": 0.02, + "learning_rate": 4.2858186420923466e-05, + "loss": 3.7457, + "step": 436224 + }, + { + "epoch": 0.02, + "learning_rate": 4.2849800473412946e-05, + "loss": 3.7575, + "step": 436736 + }, + { + "epoch": 0.02, + "learning_rate": 4.284143090470616e-05, + "loss": 3.7443, + "step": 437248 + }, + { + "epoch": 0.02, + "learning_rate": 4.2833044957195635e-05, + "loss": 3.7542, + "step": 437760 + }, + { + "epoch": 0.02, + "learning_rate": 4.2824659009685115e-05, + "loss": 3.7568, + "step": 438272 + }, + { + "epoch": 0.02, + "learning_rate": 4.2816273062174595e-05, + "loss": 3.7299, + "step": 438784 + }, + { + "epoch": 0.02, + "learning_rate": 4.2807887114664075e-05, + "loss": 3.7498, + "step": 439296 + }, + { + "epoch": 0.02, + "learning_rate": 4.2799517545957284e-05, + "loss": 3.764, + "step": 439808 + }, + { + "epoch": 0.02, + "learning_rate": 4.2791131598446764e-05, + "loss": 3.7503, + "step": 440320 + }, + { + "epoch": 0.02, + "learning_rate": 4.2782745650936244e-05, + "loss": 3.7433, + "step": 440832 + }, + { + "epoch": 0.02, + "learning_rate": 4.2774359703425724e-05, + "loss": 3.7418, + "step": 441344 + }, + { + "epoch": 0.02, + "learning_rate": 4.2765973755915204e-05, + "loss": 3.7459, + "step": 441856 + }, + { + "epoch": 0.02, + "learning_rate": 4.275760418720842e-05, + "loss": 3.7572, + "step": 442368 + }, + { + "epoch": 0.02, + "learning_rate": 4.27492182396979e-05, + "loss": 3.7536, + "step": 442880 + }, + { + "epoch": 0.02, + "learning_rate": 4.274083229218738e-05, + "loss": 3.7415, + "step": 443392 + }, + { + "epoch": 0.02, + "learning_rate": 4.273244634467686e-05, + "loss": 3.7491, + "step": 443904 + }, + { + "epoch": 0.02, + "learning_rate": 4.272407677597007e-05, + "loss": 3.7498, + "step": 444416 + }, + { + "epoch": 0.02, + "learning_rate": 4.271569082845955e-05, + "loss": 3.7523, + "step": 444928 + }, + { + "epoch": 0.02, + "learning_rate": 4.270730488094903e-05, + "loss": 3.7452, + "step": 445440 + }, + { + "epoch": 0.02, + "learning_rate": 4.269891893343851e-05, + "loss": 3.7543, + "step": 445952 + }, + { + "epoch": 0.02, + "learning_rate": 4.269054936473172e-05, + "loss": 3.746, + "step": 446464 + }, + { + "epoch": 0.02, + "learning_rate": 4.26821634172212e-05, + "loss": 3.7496, + "step": 446976 + }, + { + "epoch": 0.02, + "learning_rate": 4.267377746971068e-05, + "loss": 3.7544, + "step": 447488 + }, + { + "epoch": 0.02, + "learning_rate": 4.266539152220016e-05, + "loss": 3.7386, + "step": 448000 + }, + { + "epoch": 0.02, + "learning_rate": 4.265702195349337e-05, + "loss": 3.7462, + "step": 448512 + }, + { + "epoch": 0.02, + "learning_rate": 4.264863600598285e-05, + "loss": 3.7556, + "step": 449024 + }, + { + "epoch": 0.02, + "learning_rate": 4.264025005847233e-05, + "loss": 3.7519, + "step": 449536 + }, + { + "epoch": 0.02, + "learning_rate": 4.263186411096181e-05, + "loss": 3.7525, + "step": 450048 + }, + { + "epoch": 0.02, + "learning_rate": 4.262347816345129e-05, + "loss": 3.7478, + "step": 450560 + }, + { + "epoch": 0.02, + "learning_rate": 4.26151085947445e-05, + "loss": 3.7348, + "step": 451072 + }, + { + "epoch": 0.02, + "learning_rate": 4.260672264723398e-05, + "loss": 3.7421, + "step": 451584 + }, + { + "epoch": 0.02, + "learning_rate": 4.259833669972346e-05, + "loss": 3.749, + "step": 452096 + }, + { + "epoch": 0.02, + "learning_rate": 4.258995075221294e-05, + "loss": 3.7639, + "step": 452608 + }, + { + "epoch": 0.02, + "learning_rate": 4.258156480470242e-05, + "loss": 3.7548, + "step": 453120 + }, + { + "epoch": 0.02, + "learning_rate": 4.25731788571919e-05, + "loss": 3.7446, + "step": 453632 + }, + { + "epoch": 0.02, + "learning_rate": 4.256480928848511e-05, + "loss": 3.7444, + "step": 454144 + }, + { + "epoch": 0.02, + "learning_rate": 4.255642334097459e-05, + "loss": 3.7504, + "step": 454656 + }, + { + "epoch": 0.02, + "learning_rate": 4.254803739346407e-05, + "loss": 3.7437, + "step": 455168 + }, + { + "epoch": 0.02, + "learning_rate": 4.253965144595356e-05, + "loss": 3.7437, + "step": 455680 + }, + { + "epoch": 0.02, + "learning_rate": 4.253128187724677e-05, + "loss": 3.762, + "step": 456192 + }, + { + "epoch": 0.02, + "learning_rate": 4.252289592973625e-05, + "loss": 3.7486, + "step": 456704 + }, + { + "epoch": 0.02, + "learning_rate": 4.251450998222573e-05, + "loss": 3.7418, + "step": 457216 + }, + { + "epoch": 0.02, + "learning_rate": 4.250612403471521e-05, + "loss": 3.7493, + "step": 457728 + }, + { + "epoch": 0.03, + "eval_loss": 3.918626546859741, + "eval_runtime": 569.637, + "eval_samples_per_second": 669.884, + "eval_steps_per_second": 20.934, + "step": 457914 + }, + { + "epoch": 0.0, + "learning_rate": 4.249773808720469e-05, + "loss": 3.7555, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.248935213969417e-05, + "loss": 3.7508, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.248096619218364e-05, + "loss": 3.7427, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.247258024467312e-05, + "loss": 3.7431, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.2464210675966336e-05, + "loss": 3.7416, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.2455824728455816e-05, + "loss": 3.7362, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.2447438780945296e-05, + "loss": 3.741, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.2439052833434776e-05, + "loss": 3.7294, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.243068326472799e-05, + "loss": 3.743, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.242229731721747e-05, + "loss": 3.7561, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.2413911369706945e-05, + "loss": 3.737, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.2405525422196424e-05, + "loss": 3.7361, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.2397139474685904e-05, + "loss": 3.7456, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.2388769905979114e-05, + "loss": 3.7376, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.2380383958468593e-05, + "loss": 3.7439, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.2371998010958073e-05, + "loss": 3.7161, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.2363612063447553e-05, + "loss": 3.7259, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.235524249474076e-05, + "loss": 3.7337, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.234685654723025e-05, + "loss": 3.7337, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.233847059971973e-05, + "loss": 3.7588, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.233008465220921e-05, + "loss": 3.7338, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.232169870469869e-05, + "loss": 3.7491, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.23133291359919e-05, + "loss": 3.7287, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.230494318848138e-05, + "loss": 3.7379, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.229655724097086e-05, + "loss": 3.7287, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.228817129346034e-05, + "loss": 3.7367, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.227980172475355e-05, + "loss": 3.7381, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.227141577724303e-05, + "loss": 3.7299, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.226302982973251e-05, + "loss": 3.7348, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.225464388222199e-05, + "loss": 3.7242, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.2246274313515196e-05, + "loss": 3.7187, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.223788836600468e-05, + "loss": 3.7397, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.222950241849416e-05, + "loss": 3.7379, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.222111647098364e-05, + "loss": 3.7398, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.221274690227685e-05, + "loss": 3.7309, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.220436095476633e-05, + "loss": 3.7402, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.219597500725581e-05, + "loss": 3.7346, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.218758905974529e-05, + "loss": 3.7365, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.21792194910385e-05, + "loss": 3.7321, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.217083354352798e-05, + "loss": 3.7259, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.216244759601746e-05, + "loss": 3.738, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.215406164850694e-05, + "loss": 3.7165, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.214569207980015e-05, + "loss": 3.7393, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.2137306132289637e-05, + "loss": 3.7331, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.2128920184779116e-05, + "loss": 3.737, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.2120534237268596e-05, + "loss": 3.7307, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.2112148289758076e-05, + "loss": 3.726, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.2103778721051285e-05, + "loss": 3.7417, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.2095392773540765e-05, + "loss": 3.7203, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.2087006826030245e-05, + "loss": 3.7237, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.2078620878519725e-05, + "loss": 3.7262, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.2070251309812934e-05, + "loss": 3.7266, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.2061865362302414e-05, + "loss": 3.7268, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.2053479414791894e-05, + "loss": 3.7279, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.2045093467281374e-05, + "loss": 3.7224, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.203672389857459e-05, + "loss": 3.7249, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.202833795106407e-05, + "loss": 3.73, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.201995200355355e-05, + "loss": 3.7235, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.201156605604303e-05, + "loss": 3.7329, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.200319648733624e-05, + "loss": 3.739, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.199481053982572e-05, + "loss": 3.716, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.19864245923152e-05, + "loss": 3.7175, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.197803864480468e-05, + "loss": 3.7175, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.196965269729416e-05, + "loss": 3.7401, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.196128312858737e-05, + "loss": 3.722, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.195289718107685e-05, + "loss": 3.7204, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.194451123356633e-05, + "loss": 3.7118, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.193612528605581e-05, + "loss": 3.7224, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.1927755717349024e-05, + "loss": 3.7203, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.1919369769838504e-05, + "loss": 3.7168, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.1910983822327984e-05, + "loss": 3.724, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.1902597874817464e-05, + "loss": 3.7233, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.189422830611067e-05, + "loss": 3.7246, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.188584235860015e-05, + "loss": 3.7316, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.187745641108963e-05, + "loss": 3.7324, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.186907046357911e-05, + "loss": 3.7271, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.186070089487232e-05, + "loss": 3.7217, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.18523149473618e-05, + "loss": 3.7234, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.184392899985128e-05, + "loss": 3.7167, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.183554305234076e-05, + "loss": 3.7386, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.182717348363398e-05, + "loss": 3.7225, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.181878753612346e-05, + "loss": 3.7273, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.181040158861294e-05, + "loss": 3.7083, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.180201564110242e-05, + "loss": 3.7274, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.1793646072395626e-05, + "loss": 3.7047, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.1785260124885106e-05, + "loss": 3.7236, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.1776874177374586e-05, + "loss": 3.7218, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.1768488229864066e-05, + "loss": 3.7223, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.1760102282353546e-05, + "loss": 3.7187, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.1751732713646755e-05, + "loss": 3.7278, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.1743346766136235e-05, + "loss": 3.7123, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.1734960818625715e-05, + "loss": 3.7172, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.1726574871115195e-05, + "loss": 3.7231, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.171820530240841e-05, + "loss": 3.708, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.170981935489789e-05, + "loss": 3.7098, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.170143340738737e-05, + "loss": 3.7198, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.1693047459876844e-05, + "loss": 3.7127, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.168467789117006e-05, + "loss": 3.7349, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.167629194365954e-05, + "loss": 3.7158, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.166790599614902e-05, + "loss": 3.7127, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.165952004863849e-05, + "loss": 3.7141, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.165115047993171e-05, + "loss": 3.7218, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.164276453242119e-05, + "loss": 3.727, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.163437858491067e-05, + "loss": 3.7115, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.162599263740015e-05, + "loss": 3.723, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.1617623068693365e-05, + "loss": 3.7054, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.1609237121182845e-05, + "loss": 3.7055, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.160085117367232e-05, + "loss": 3.7189, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.15924652261618e-05, + "loss": 3.7095, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.158407927865128e-05, + "loss": 3.7139, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.1575709709944494e-05, + "loss": 3.7178, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.156732376243397e-05, + "loss": 3.6948, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.155893781492345e-05, + "loss": 3.7115, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.155055186741293e-05, + "loss": 3.7299, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.154218229870614e-05, + "loss": 3.7167, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.153379635119562e-05, + "loss": 3.703, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.15254104036851e-05, + "loss": 3.7053, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.151702445617458e-05, + "loss": 3.7095, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.150863850866406e-05, + "loss": 3.7198, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.150026893995727e-05, + "loss": 3.7162, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.149188299244675e-05, + "loss": 3.706, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.148349704493623e-05, + "loss": 3.7106, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.147511109742571e-05, + "loss": 3.7138, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.146674152871892e-05, + "loss": 3.7133, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.14583555812084e-05, + "loss": 3.708, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.144996963369788e-05, + "loss": 3.7157, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.144158368618736e-05, + "loss": 3.7112, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.1433214117480576e-05, + "loss": 3.7148, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.1424828169970056e-05, + "loss": 3.715, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.1416442222459536e-05, + "loss": 3.6998, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.1408056274949016e-05, + "loss": 3.711, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.1399686706242225e-05, + "loss": 3.7164, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.1391300758731705e-05, + "loss": 3.718, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.1382914811221185e-05, + "loss": 3.7151, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.1374528863710665e-05, + "loss": 3.7141, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.1366142916200145e-05, + "loss": 3.7015, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.1357773347493354e-05, + "loss": 3.701, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.1349387399982834e-05, + "loss": 3.7122, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.1341001452472314e-05, + "loss": 3.7263, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.1332615504961794e-05, + "loss": 3.7188, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.132424593625501e-05, + "loss": 3.7088, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.131585998874449e-05, + "loss": 3.7044, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.130747404123397e-05, + "loss": 3.7164, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.129908809372345e-05, + "loss": 3.7087, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.129071852501666e-05, + "loss": 3.7085, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.128233257750614e-05, + "loss": 3.7261, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.127394662999562e-05, + "loss": 3.7133, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.12655606824851e-05, + "loss": 3.7061, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.125717473497458e-05, + "loss": 3.7135, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 3.908137559890747, + "eval_runtime": 567.1197, + "eval_samples_per_second": 672.858, + "eval_steps_per_second": 21.027, + "step": 534233 + }, + { + "epoch": 0.0, + "learning_rate": 4.124880516626779e-05, + "loss": 3.7188, + "step": 534528 + }, + { + "epoch": 0.0, + "learning_rate": 4.124041921875727e-05, + "loss": 3.7168, + "step": 535040 + }, + { + "epoch": 0.0, + "learning_rate": 4.123203327124675e-05, + "loss": 3.7096, + "step": 535552 + }, + { + "epoch": 0.0, + "learning_rate": 4.122364732373623e-05, + "loss": 3.7064, + "step": 536064 + }, + { + "epoch": 0.0, + "learning_rate": 4.1215277755029444e-05, + "loss": 3.7042, + "step": 536576 + }, + { + "epoch": 0.0, + "learning_rate": 4.1206891807518923e-05, + "loss": 3.7054, + "step": 537088 + }, + { + "epoch": 0.0, + "learning_rate": 4.1198505860008403e-05, + "loss": 3.705, + "step": 537600 + }, + { + "epoch": 0.0, + "learning_rate": 4.119011991249788e-05, + "loss": 3.6957, + "step": 538112 + }, + { + "epoch": 0.0, + "learning_rate": 4.118175034379109e-05, + "loss": 3.7055, + "step": 538624 + }, + { + "epoch": 0.0, + "learning_rate": 4.117336439628057e-05, + "loss": 3.7173, + "step": 539136 + }, + { + "epoch": 0.0, + "learning_rate": 4.116497844877005e-05, + "loss": 3.7008, + "step": 539648 + }, + { + "epoch": 0.0, + "learning_rate": 4.115659250125953e-05, + "loss": 3.6999, + "step": 540160 + }, + { + "epoch": 0.0, + "learning_rate": 4.114820655374901e-05, + "loss": 3.713, + "step": 540672 + }, + { + "epoch": 0.0, + "learning_rate": 4.113983698504222e-05, + "loss": 3.6993, + "step": 541184 + }, + { + "epoch": 0.0, + "learning_rate": 4.11314510375317e-05, + "loss": 3.7112, + "step": 541696 + }, + { + "epoch": 0.0, + "learning_rate": 4.112306509002118e-05, + "loss": 3.6832, + "step": 542208 + }, + { + "epoch": 0.0, + "learning_rate": 4.111467914251067e-05, + "loss": 3.6847, + "step": 542720 + }, + { + "epoch": 0.0, + "learning_rate": 4.110630957380388e-05, + "loss": 3.7024, + "step": 543232 + }, + { + "epoch": 0.0, + "learning_rate": 4.109792362629336e-05, + "loss": 3.6968, + "step": 543744 + }, + { + "epoch": 0.0, + "learning_rate": 4.108953767878284e-05, + "loss": 3.7213, + "step": 544256 + }, + { + "epoch": 0.0, + "learning_rate": 4.108115173127232e-05, + "loss": 3.7023, + "step": 544768 + }, + { + "epoch": 0.0, + "learning_rate": 4.1072782162565526e-05, + "loss": 3.7093, + "step": 545280 + }, + { + "epoch": 0.0, + "learning_rate": 4.1064396215055006e-05, + "loss": 3.6959, + "step": 545792 + }, + { + "epoch": 0.0, + "learning_rate": 4.1056010267544486e-05, + "loss": 3.7055, + "step": 546304 + }, + { + "epoch": 0.0, + "learning_rate": 4.1047624320033966e-05, + "loss": 3.6908, + "step": 546816 + }, + { + "epoch": 0.0, + "learning_rate": 4.1039254751327175e-05, + "loss": 3.7022, + "step": 547328 + }, + { + "epoch": 0.0, + "learning_rate": 4.1030868803816655e-05, + "loss": 3.7063, + "step": 547840 + }, + { + "epoch": 0.0, + "learning_rate": 4.1022482856306135e-05, + "loss": 3.7008, + "step": 548352 + }, + { + "epoch": 0.0, + "learning_rate": 4.101409690879562e-05, + "loss": 3.6925, + "step": 548864 + }, + { + "epoch": 0.0, + "learning_rate": 4.100572734008883e-05, + "loss": 3.6927, + "step": 549376 + }, + { + "epoch": 0.01, + "learning_rate": 4.099734139257831e-05, + "loss": 3.6831, + "step": 549888 + }, + { + "epoch": 0.01, + "learning_rate": 4.098895544506779e-05, + "loss": 3.7051, + "step": 550400 + }, + { + "epoch": 0.01, + "learning_rate": 4.098056949755727e-05, + "loss": 3.7019, + "step": 550912 + }, + { + "epoch": 0.01, + "learning_rate": 4.097219992885048e-05, + "loss": 3.7018, + "step": 551424 + }, + { + "epoch": 0.01, + "learning_rate": 4.096381398133996e-05, + "loss": 3.701, + "step": 551936 + }, + { + "epoch": 0.01, + "learning_rate": 4.095542803382944e-05, + "loss": 3.7078, + "step": 552448 + }, + { + "epoch": 0.01, + "learning_rate": 4.094704208631892e-05, + "loss": 3.6997, + "step": 552960 + }, + { + "epoch": 0.01, + "learning_rate": 4.093867251761213e-05, + "loss": 3.6982, + "step": 553472 + }, + { + "epoch": 0.01, + "learning_rate": 4.093028657010161e-05, + "loss": 3.698, + "step": 553984 + }, + { + "epoch": 0.01, + "learning_rate": 4.092190062259109e-05, + "loss": 3.6977, + "step": 554496 + }, + { + "epoch": 0.01, + "learning_rate": 4.0913514675080575e-05, + "loss": 3.6977, + "step": 555008 + }, + { + "epoch": 0.01, + "learning_rate": 4.0905145106373784e-05, + "loss": 3.6836, + "step": 555520 + }, + { + "epoch": 0.01, + "learning_rate": 4.0896759158863264e-05, + "loss": 3.7079, + "step": 556032 + }, + { + "epoch": 0.01, + "learning_rate": 4.0888373211352744e-05, + "loss": 3.6969, + "step": 556544 + }, + { + "epoch": 0.01, + "learning_rate": 4.087998726384222e-05, + "loss": 3.7048, + "step": 557056 + }, + { + "epoch": 0.01, + "learning_rate": 4.0871617695135433e-05, + "loss": 3.6983, + "step": 557568 + }, + { + "epoch": 0.01, + "learning_rate": 4.0863231747624913e-05, + "loss": 3.6891, + "step": 558080 + }, + { + "epoch": 0.01, + "learning_rate": 4.085484580011439e-05, + "loss": 3.7089, + "step": 558592 + }, + { + "epoch": 0.01, + "learning_rate": 4.0846459852603867e-05, + "loss": 3.6848, + "step": 559104 + }, + { + "epoch": 0.01, + "learning_rate": 4.083809028389708e-05, + "loss": 3.6924, + "step": 559616 + }, + { + "epoch": 0.01, + "learning_rate": 4.082970433638656e-05, + "loss": 3.6873, + "step": 560128 + }, + { + "epoch": 0.01, + "learning_rate": 4.082131838887604e-05, + "loss": 3.6976, + "step": 560640 + }, + { + "epoch": 0.01, + "learning_rate": 4.081293244136552e-05, + "loss": 3.6929, + "step": 561152 + }, + { + "epoch": 0.01, + "learning_rate": 4.080456287265874e-05, + "loss": 3.6941, + "step": 561664 + }, + { + "epoch": 0.01, + "learning_rate": 4.079617692514822e-05, + "loss": 3.6915, + "step": 562176 + }, + { + "epoch": 0.01, + "learning_rate": 4.078779097763769e-05, + "loss": 3.6898, + "step": 562688 + }, + { + "epoch": 0.01, + "learning_rate": 4.077940503012717e-05, + "loss": 3.6951, + "step": 563200 + }, + { + "epoch": 0.01, + "learning_rate": 4.077103546142039e-05, + "loss": 3.6907, + "step": 563712 + }, + { + "epoch": 0.01, + "learning_rate": 4.076264951390987e-05, + "loss": 3.7007, + "step": 564224 + }, + { + "epoch": 0.01, + "learning_rate": 4.075426356639934e-05, + "loss": 3.7005, + "step": 564736 + }, + { + "epoch": 0.01, + "learning_rate": 4.074587761888882e-05, + "loss": 3.6867, + "step": 565248 + }, + { + "epoch": 0.01, + "learning_rate": 4.0737508050182036e-05, + "loss": 3.6799, + "step": 565760 + }, + { + "epoch": 0.01, + "learning_rate": 4.0729122102671516e-05, + "loss": 3.6867, + "step": 566272 + }, + { + "epoch": 0.01, + "learning_rate": 4.0720736155160996e-05, + "loss": 3.7034, + "step": 566784 + }, + { + "epoch": 0.01, + "learning_rate": 4.0712350207650476e-05, + "loss": 3.6915, + "step": 567296 + }, + { + "epoch": 0.01, + "learning_rate": 4.0703964260139956e-05, + "loss": 3.6844, + "step": 567808 + }, + { + "epoch": 0.01, + "learning_rate": 4.0695594691433165e-05, + "loss": 3.6832, + "step": 568320 + }, + { + "epoch": 0.01, + "learning_rate": 4.0687208743922645e-05, + "loss": 3.6902, + "step": 568832 + }, + { + "epoch": 0.01, + "learning_rate": 4.0678822796412125e-05, + "loss": 3.6831, + "step": 569344 + }, + { + "epoch": 0.01, + "learning_rate": 4.0670436848901605e-05, + "loss": 3.6878, + "step": 569856 + }, + { + "epoch": 0.01, + "learning_rate": 4.0662067280194814e-05, + "loss": 3.6891, + "step": 570368 + }, + { + "epoch": 0.01, + "learning_rate": 4.0653681332684294e-05, + "loss": 3.6859, + "step": 570880 + }, + { + "epoch": 0.01, + "learning_rate": 4.0645295385173774e-05, + "loss": 3.6926, + "step": 571392 + }, + { + "epoch": 0.01, + "learning_rate": 4.0636909437663254e-05, + "loss": 3.6994, + "step": 571904 + }, + { + "epoch": 0.01, + "learning_rate": 4.062853986895647e-05, + "loss": 3.6983, + "step": 572416 + }, + { + "epoch": 0.01, + "learning_rate": 4.062015392144595e-05, + "loss": 3.6911, + "step": 572928 + }, + { + "epoch": 0.01, + "learning_rate": 4.061176797393543e-05, + "loss": 3.6898, + "step": 573440 + }, + { + "epoch": 0.01, + "learning_rate": 4.060338202642491e-05, + "loss": 3.6914, + "step": 573952 + }, + { + "epoch": 0.01, + "learning_rate": 4.059501245771812e-05, + "loss": 3.6849, + "step": 574464 + }, + { + "epoch": 0.01, + "learning_rate": 4.05866265102076e-05, + "loss": 3.7025, + "step": 574976 + }, + { + "epoch": 0.01, + "learning_rate": 4.057824056269708e-05, + "loss": 3.6953, + "step": 575488 + }, + { + "epoch": 0.01, + "learning_rate": 4.056985461518656e-05, + "loss": 3.6943, + "step": 576000 + }, + { + "epoch": 0.01, + "learning_rate": 4.056148504647977e-05, + "loss": 3.6747, + "step": 576512 + }, + { + "epoch": 0.01, + "learning_rate": 4.055309909896925e-05, + "loss": 3.6901, + "step": 577024 + }, + { + "epoch": 0.01, + "learning_rate": 4.054471315145873e-05, + "loss": 3.6754, + "step": 577536 + }, + { + "epoch": 0.01, + "learning_rate": 4.053632720394821e-05, + "loss": 3.6882, + "step": 578048 + }, + { + "epoch": 0.01, + "learning_rate": 4.052795763524142e-05, + "loss": 3.6902, + "step": 578560 + }, + { + "epoch": 0.01, + "learning_rate": 4.05195716877309e-05, + "loss": 3.6868, + "step": 579072 + }, + { + "epoch": 0.01, + "learning_rate": 4.051118574022038e-05, + "loss": 3.6896, + "step": 579584 + }, + { + "epoch": 0.02, + "learning_rate": 4.050279979270986e-05, + "loss": 3.6904, + "step": 580096 + }, + { + "epoch": 0.02, + "learning_rate": 4.049441384519934e-05, + "loss": 3.6806, + "step": 580608 + }, + { + "epoch": 0.02, + "learning_rate": 4.048604427649255e-05, + "loss": 3.6856, + "step": 581120 + }, + { + "epoch": 0.02, + "learning_rate": 4.047765832898203e-05, + "loss": 3.6905, + "step": 581632 + }, + { + "epoch": 0.02, + "learning_rate": 4.046927238147151e-05, + "loss": 3.6776, + "step": 582144 + }, + { + "epoch": 0.02, + "learning_rate": 4.046088643396099e-05, + "loss": 3.6796, + "step": 582656 + }, + { + "epoch": 0.02, + "learning_rate": 4.04525168652542e-05, + "loss": 3.6794, + "step": 583168 + }, + { + "epoch": 0.02, + "learning_rate": 4.044413091774368e-05, + "loss": 3.6871, + "step": 583680 + }, + { + "epoch": 0.02, + "learning_rate": 4.043574497023316e-05, + "loss": 3.7023, + "step": 584192 + }, + { + "epoch": 0.02, + "learning_rate": 4.042737540152638e-05, + "loss": 3.6809, + "step": 584704 + }, + { + "epoch": 0.02, + "learning_rate": 4.041898945401586e-05, + "loss": 3.6843, + "step": 585216 + }, + { + "epoch": 0.02, + "learning_rate": 4.041060350650534e-05, + "loss": 3.681, + "step": 585728 + }, + { + "epoch": 0.02, + "learning_rate": 4.040221755899482e-05, + "loss": 3.6926, + "step": 586240 + }, + { + "epoch": 0.02, + "learning_rate": 4.0393847990288026e-05, + "loss": 3.6898, + "step": 586752 + }, + { + "epoch": 0.02, + "learning_rate": 4.0385462042777506e-05, + "loss": 3.6788, + "step": 587264 + }, + { + "epoch": 0.02, + "learning_rate": 4.0377076095266986e-05, + "loss": 3.6924, + "step": 587776 + }, + { + "epoch": 0.02, + "learning_rate": 4.0368690147756466e-05, + "loss": 3.6709, + "step": 588288 + }, + { + "epoch": 0.02, + "learning_rate": 4.0360304200245946e-05, + "loss": 3.6728, + "step": 588800 + }, + { + "epoch": 0.02, + "learning_rate": 4.0351934631539155e-05, + "loss": 3.6866, + "step": 589312 + }, + { + "epoch": 0.02, + "learning_rate": 4.0343548684028635e-05, + "loss": 3.6796, + "step": 589824 + }, + { + "epoch": 0.02, + "learning_rate": 4.0335162736518115e-05, + "loss": 3.6839, + "step": 590336 + }, + { + "epoch": 0.02, + "learning_rate": 4.0326776789007595e-05, + "loss": 3.6849, + "step": 590848 + }, + { + "epoch": 0.02, + "learning_rate": 4.031840722030081e-05, + "loss": 3.6605, + "step": 591360 + }, + { + "epoch": 0.02, + "learning_rate": 4.031002127279029e-05, + "loss": 3.6829, + "step": 591872 + }, + { + "epoch": 0.02, + "learning_rate": 4.030163532527977e-05, + "loss": 3.6956, + "step": 592384 + }, + { + "epoch": 0.02, + "learning_rate": 4.029324937776925e-05, + "loss": 3.6837, + "step": 592896 + }, + { + "epoch": 0.02, + "learning_rate": 4.028487980906246e-05, + "loss": 3.6729, + "step": 593408 + }, + { + "epoch": 0.02, + "learning_rate": 4.027649386155194e-05, + "loss": 3.6734, + "step": 593920 + }, + { + "epoch": 0.02, + "learning_rate": 4.026810791404142e-05, + "loss": 3.6748, + "step": 594432 + }, + { + "epoch": 0.02, + "learning_rate": 4.02597219665309e-05, + "loss": 3.6875, + "step": 594944 + }, + { + "epoch": 0.02, + "learning_rate": 4.025135239782411e-05, + "loss": 3.6861, + "step": 595456 + }, + { + "epoch": 0.02, + "learning_rate": 4.024296645031359e-05, + "loss": 3.6736, + "step": 595968 + }, + { + "epoch": 0.02, + "learning_rate": 4.023458050280307e-05, + "loss": 3.6763, + "step": 596480 + }, + { + "epoch": 0.02, + "learning_rate": 4.022619455529255e-05, + "loss": 3.6889, + "step": 596992 + }, + { + "epoch": 0.02, + "learning_rate": 4.0217824986585764e-05, + "loss": 3.6821, + "step": 597504 + }, + { + "epoch": 0.02, + "learning_rate": 4.0209439039075244e-05, + "loss": 3.673, + "step": 598016 + }, + { + "epoch": 0.02, + "learning_rate": 4.0201053091564724e-05, + "loss": 3.6871, + "step": 598528 + }, + { + "epoch": 0.02, + "learning_rate": 4.0192667144054204e-05, + "loss": 3.6796, + "step": 599040 + }, + { + "epoch": 0.02, + "learning_rate": 4.018429757534741e-05, + "loss": 3.6788, + "step": 599552 + }, + { + "epoch": 0.02, + "learning_rate": 4.017591162783689e-05, + "loss": 3.6897, + "step": 600064 + }, + { + "epoch": 0.02, + "learning_rate": 4.016752568032637e-05, + "loss": 3.6664, + "step": 600576 + }, + { + "epoch": 0.02, + "learning_rate": 4.015913973281585e-05, + "loss": 3.679, + "step": 601088 + }, + { + "epoch": 0.02, + "learning_rate": 4.015077016410906e-05, + "loss": 3.6876, + "step": 601600 + }, + { + "epoch": 0.02, + "learning_rate": 4.014238421659854e-05, + "loss": 3.6835, + "step": 602112 + }, + { + "epoch": 0.02, + "learning_rate": 4.013399826908802e-05, + "loss": 3.6812, + "step": 602624 + }, + { + "epoch": 0.02, + "learning_rate": 4.01256123215775e-05, + "loss": 3.6853, + "step": 603136 + }, + { + "epoch": 0.02, + "learning_rate": 4.011724275287072e-05, + "loss": 3.6724, + "step": 603648 + }, + { + "epoch": 0.02, + "learning_rate": 4.01088568053602e-05, + "loss": 3.6704, + "step": 604160 + }, + { + "epoch": 0.02, + "learning_rate": 4.010047085784968e-05, + "loss": 3.6821, + "step": 604672 + }, + { + "epoch": 0.02, + "learning_rate": 4.009208491033916e-05, + "loss": 3.6899, + "step": 605184 + }, + { + "epoch": 0.02, + "learning_rate": 4.008371534163237e-05, + "loss": 3.6901, + "step": 605696 + }, + { + "epoch": 0.02, + "learning_rate": 4.007532939412185e-05, + "loss": 3.6769, + "step": 606208 + }, + { + "epoch": 0.02, + "learning_rate": 4.006694344661133e-05, + "loss": 3.6738, + "step": 606720 + }, + { + "epoch": 0.02, + "learning_rate": 4.005855749910081e-05, + "loss": 3.6854, + "step": 607232 + }, + { + "epoch": 0.02, + "learning_rate": 4.0050187930394016e-05, + "loss": 3.6753, + "step": 607744 + }, + { + "epoch": 0.02, + "learning_rate": 4.0041801982883496e-05, + "loss": 3.6801, + "step": 608256 + }, + { + "epoch": 0.02, + "learning_rate": 4.0033416035372976e-05, + "loss": 3.691, + "step": 608768 + }, + { + "epoch": 0.02, + "learning_rate": 4.0025030087862456e-05, + "loss": 3.688, + "step": 609280 + }, + { + "epoch": 0.02, + "learning_rate": 4.001666051915567e-05, + "loss": 3.6735, + "step": 609792 + }, + { + "epoch": 0.02, + "learning_rate": 4.000827457164515e-05, + "loss": 3.6846, + "step": 610304 + }, + { + "epoch": 0.03, + "eval_loss": 3.9025914669036865, + "eval_runtime": 586.0986, + "eval_samples_per_second": 651.07, + "eval_steps_per_second": 20.346, + "step": 610552 + }, + { + "epoch": 0.0, + "learning_rate": 3.999988862413463e-05, + "loss": 3.6834, + "step": 610816 + }, + { + "epoch": 0.0, + "learning_rate": 3.999150267662411e-05, + "loss": 3.6901, + "step": 611328 + }, + { + "epoch": 0.0, + "learning_rate": 3.998311672911359e-05, + "loss": 3.6763, + "step": 611840 + }, + { + "epoch": 0.0, + "learning_rate": 3.9974730781603065e-05, + "loss": 3.6787, + "step": 612352 + }, + { + "epoch": 0.0, + "learning_rate": 3.996636121289628e-05, + "loss": 3.6713, + "step": 612864 + }, + { + "epoch": 0.0, + "learning_rate": 3.995797526538576e-05, + "loss": 3.6764, + "step": 613376 + }, + { + "epoch": 0.0, + "learning_rate": 3.994958931787524e-05, + "loss": 3.6795, + "step": 613888 + }, + { + "epoch": 0.0, + "learning_rate": 3.9941203370364714e-05, + "loss": 3.6604, + "step": 614400 + }, + { + "epoch": 0.0, + "learning_rate": 3.993283380165793e-05, + "loss": 3.6737, + "step": 614912 + }, + { + "epoch": 0.0, + "learning_rate": 3.992444785414741e-05, + "loss": 3.6868, + "step": 615424 + }, + { + "epoch": 0.0, + "learning_rate": 3.991606190663689e-05, + "loss": 3.6722, + "step": 615936 + }, + { + "epoch": 0.0, + "learning_rate": 3.990767595912637e-05, + "loss": 3.6679, + "step": 616448 + }, + { + "epoch": 0.0, + "learning_rate": 3.9899306390419585e-05, + "loss": 3.6827, + "step": 616960 + }, + { + "epoch": 0.0, + "learning_rate": 3.9890920442909065e-05, + "loss": 3.67, + "step": 617472 + }, + { + "epoch": 0.0, + "learning_rate": 3.988253449539854e-05, + "loss": 3.6789, + "step": 617984 + }, + { + "epoch": 0.0, + "learning_rate": 3.987414854788802e-05, + "loss": 3.6548, + "step": 618496 + }, + { + "epoch": 0.0, + "learning_rate": 3.9865778979181234e-05, + "loss": 3.653, + "step": 619008 + }, + { + "epoch": 0.0, + "learning_rate": 3.9857393031670714e-05, + "loss": 3.6743, + "step": 619520 + }, + { + "epoch": 0.0, + "learning_rate": 3.984900708416019e-05, + "loss": 3.6653, + "step": 620032 + }, + { + "epoch": 0.0, + "learning_rate": 3.984062113664967e-05, + "loss": 3.6917, + "step": 620544 + }, + { + "epoch": 0.0, + "learning_rate": 3.983225156794288e-05, + "loss": 3.6733, + "step": 621056 + }, + { + "epoch": 0.0, + "learning_rate": 3.982386562043236e-05, + "loss": 3.6795, + "step": 621568 + }, + { + "epoch": 0.0, + "learning_rate": 3.981547967292184e-05, + "loss": 3.6655, + "step": 622080 + }, + { + "epoch": 0.0, + "learning_rate": 3.980709372541132e-05, + "loss": 3.6779, + "step": 622592 + }, + { + "epoch": 0.0, + "learning_rate": 3.979872415670454e-05, + "loss": 3.6642, + "step": 623104 + }, + { + "epoch": 0.0, + "learning_rate": 3.979033820919401e-05, + "loss": 3.6721, + "step": 623616 + }, + { + "epoch": 0.0, + "learning_rate": 3.978195226168349e-05, + "loss": 3.6683, + "step": 624128 + }, + { + "epoch": 0.0, + "learning_rate": 3.977356631417297e-05, + "loss": 3.6753, + "step": 624640 + }, + { + "epoch": 0.0, + "learning_rate": 3.976519674546619e-05, + "loss": 3.6668, + "step": 625152 + }, + { + "epoch": 0.0, + "learning_rate": 3.975681079795566e-05, + "loss": 3.6601, + "step": 625664 + }, + { + "epoch": 0.01, + "learning_rate": 3.974842485044514e-05, + "loss": 3.6553, + "step": 626176 + }, + { + "epoch": 0.01, + "learning_rate": 3.974003890293462e-05, + "loss": 3.6725, + "step": 626688 + }, + { + "epoch": 0.01, + "learning_rate": 3.973166933422784e-05, + "loss": 3.6734, + "step": 627200 + }, + { + "epoch": 0.01, + "learning_rate": 3.972328338671732e-05, + "loss": 3.6716, + "step": 627712 + }, + { + "epoch": 0.01, + "learning_rate": 3.97148974392068e-05, + "loss": 3.6708, + "step": 628224 + }, + { + "epoch": 0.01, + "learning_rate": 3.970651149169628e-05, + "loss": 3.6751, + "step": 628736 + }, + { + "epoch": 0.01, + "learning_rate": 3.9698141922989486e-05, + "loss": 3.6708, + "step": 629248 + }, + { + "epoch": 0.01, + "learning_rate": 3.9689755975478966e-05, + "loss": 3.6701, + "step": 629760 + }, + { + "epoch": 0.01, + "learning_rate": 3.9681370027968446e-05, + "loss": 3.6675, + "step": 630272 + }, + { + "epoch": 0.01, + "learning_rate": 3.967300045926166e-05, + "loss": 3.6665, + "step": 630784 + }, + { + "epoch": 0.01, + "learning_rate": 3.9664614511751135e-05, + "loss": 3.6707, + "step": 631296 + }, + { + "epoch": 0.01, + "learning_rate": 3.9656228564240615e-05, + "loss": 3.6554, + "step": 631808 + }, + { + "epoch": 0.01, + "learning_rate": 3.9647842616730095e-05, + "loss": 3.6725, + "step": 632320 + }, + { + "epoch": 0.01, + "learning_rate": 3.963947304802331e-05, + "loss": 3.6728, + "step": 632832 + }, + { + "epoch": 0.01, + "learning_rate": 3.9631087100512784e-05, + "loss": 3.6726, + "step": 633344 + }, + { + "epoch": 0.01, + "learning_rate": 3.962270115300227e-05, + "loss": 3.672, + "step": 633856 + }, + { + "epoch": 0.01, + "learning_rate": 3.961431520549175e-05, + "loss": 3.6567, + "step": 634368 + }, + { + "epoch": 0.01, + "learning_rate": 3.960594563678496e-05, + "loss": 3.6795, + "step": 634880 + }, + { + "epoch": 0.01, + "learning_rate": 3.959755968927444e-05, + "loss": 3.658, + "step": 635392 + }, + { + "epoch": 0.01, + "learning_rate": 3.958917374176392e-05, + "loss": 3.6641, + "step": 635904 + }, + { + "epoch": 0.01, + "learning_rate": 3.95807877942534e-05, + "loss": 3.6566, + "step": 636416 + }, + { + "epoch": 0.01, + "learning_rate": 3.957241822554661e-05, + "loss": 3.6643, + "step": 636928 + }, + { + "epoch": 0.01, + "learning_rate": 3.956403227803609e-05, + "loss": 3.6699, + "step": 637440 + }, + { + "epoch": 0.01, + "learning_rate": 3.955564633052557e-05, + "loss": 3.6574, + "step": 637952 + }, + { + "epoch": 0.01, + "learning_rate": 3.954726038301505e-05, + "loss": 3.666, + "step": 638464 + }, + { + "epoch": 0.01, + "learning_rate": 3.953889081430826e-05, + "loss": 3.6578, + "step": 638976 + }, + { + "epoch": 0.01, + "learning_rate": 3.953050486679774e-05, + "loss": 3.6701, + "step": 639488 + }, + { + "epoch": 0.01, + "learning_rate": 3.9522118919287224e-05, + "loss": 3.66, + "step": 640000 + }, + { + "epoch": 0.01, + "learning_rate": 3.9513732971776704e-05, + "loss": 3.6732, + "step": 640512 + }, + { + "epoch": 0.01, + "learning_rate": 3.950536340306991e-05, + "loss": 3.6674, + "step": 641024 + }, + { + "epoch": 0.01, + "learning_rate": 3.949697745555939e-05, + "loss": 3.6599, + "step": 641536 + }, + { + "epoch": 0.01, + "learning_rate": 3.948859150804887e-05, + "loss": 3.6545, + "step": 642048 + }, + { + "epoch": 0.01, + "learning_rate": 3.948020556053835e-05, + "loss": 3.659, + "step": 642560 + }, + { + "epoch": 0.01, + "learning_rate": 3.947183599183156e-05, + "loss": 3.6695, + "step": 643072 + }, + { + "epoch": 0.01, + "learning_rate": 3.946345004432104e-05, + "loss": 3.6617, + "step": 643584 + }, + { + "epoch": 0.01, + "learning_rate": 3.945506409681052e-05, + "loss": 3.6592, + "step": 644096 + }, + { + "epoch": 0.01, + "learning_rate": 3.94466781493e-05, + "loss": 3.6564, + "step": 644608 + }, + { + "epoch": 0.01, + "learning_rate": 3.943829220178948e-05, + "loss": 3.6582, + "step": 645120 + }, + { + "epoch": 0.01, + "learning_rate": 3.942992263308269e-05, + "loss": 3.6567, + "step": 645632 + }, + { + "epoch": 0.01, + "learning_rate": 3.942153668557218e-05, + "loss": 3.6591, + "step": 646144 + }, + { + "epoch": 0.01, + "learning_rate": 3.941315073806166e-05, + "loss": 3.658, + "step": 646656 + }, + { + "epoch": 0.01, + "learning_rate": 3.940476479055114e-05, + "loss": 3.6591, + "step": 647168 + }, + { + "epoch": 0.01, + "learning_rate": 3.939639522184435e-05, + "loss": 3.6616, + "step": 647680 + }, + { + "epoch": 0.01, + "learning_rate": 3.938800927433383e-05, + "loss": 3.675, + "step": 648192 + }, + { + "epoch": 0.01, + "learning_rate": 3.937962332682331e-05, + "loss": 3.666, + "step": 648704 + }, + { + "epoch": 0.01, + "learning_rate": 3.937123737931279e-05, + "loss": 3.6612, + "step": 649216 + }, + { + "epoch": 0.01, + "learning_rate": 3.9362867810605996e-05, + "loss": 3.6625, + "step": 649728 + }, + { + "epoch": 0.01, + "learning_rate": 3.9354481863095476e-05, + "loss": 3.6616, + "step": 650240 + }, + { + "epoch": 0.01, + "learning_rate": 3.9346095915584956e-05, + "loss": 3.6533, + "step": 650752 + }, + { + "epoch": 0.01, + "learning_rate": 3.9337709968074436e-05, + "loss": 3.6714, + "step": 651264 + }, + { + "epoch": 0.01, + "learning_rate": 3.9329340399367645e-05, + "loss": 3.6679, + "step": 651776 + }, + { + "epoch": 0.01, + "learning_rate": 3.932095445185713e-05, + "loss": 3.6663, + "step": 652288 + }, + { + "epoch": 0.01, + "learning_rate": 3.931256850434661e-05, + "loss": 3.6478, + "step": 652800 + }, + { + "epoch": 0.01, + "learning_rate": 3.930419893563982e-05, + "loss": 3.6601, + "step": 653312 + }, + { + "epoch": 0.01, + "learning_rate": 3.92958129881293e-05, + "loss": 3.6465, + "step": 653824 + }, + { + "epoch": 0.01, + "learning_rate": 3.928742704061878e-05, + "loss": 3.6646, + "step": 654336 + }, + { + "epoch": 0.01, + "learning_rate": 3.927904109310826e-05, + "loss": 3.6624, + "step": 654848 + }, + { + "epoch": 0.01, + "learning_rate": 3.927067152440147e-05, + "loss": 3.6556, + "step": 655360 + }, + { + "epoch": 0.01, + "learning_rate": 3.926228557689095e-05, + "loss": 3.6619, + "step": 655872 + }, + { + "epoch": 0.02, + "learning_rate": 3.925389962938043e-05, + "loss": 3.6627, + "step": 656384 + }, + { + "epoch": 0.02, + "learning_rate": 3.924551368186991e-05, + "loss": 3.6539, + "step": 656896 + }, + { + "epoch": 0.02, + "learning_rate": 3.923714411316312e-05, + "loss": 3.6558, + "step": 657408 + }, + { + "epoch": 0.02, + "learning_rate": 3.92287581656526e-05, + "loss": 3.6623, + "step": 657920 + }, + { + "epoch": 0.02, + "learning_rate": 3.9220372218142085e-05, + "loss": 3.6501, + "step": 658432 + }, + { + "epoch": 0.02, + "learning_rate": 3.9211986270631565e-05, + "loss": 3.6543, + "step": 658944 + }, + { + "epoch": 0.02, + "learning_rate": 3.9203616701924774e-05, + "loss": 3.6501, + "step": 659456 + }, + { + "epoch": 0.02, + "learning_rate": 3.9195230754414254e-05, + "loss": 3.6578, + "step": 659968 + }, + { + "epoch": 0.02, + "learning_rate": 3.9186844806903734e-05, + "loss": 3.6722, + "step": 660480 + }, + { + "epoch": 0.02, + "learning_rate": 3.9178458859393214e-05, + "loss": 3.655, + "step": 660992 + }, + { + "epoch": 0.02, + "learning_rate": 3.917008929068642e-05, + "loss": 3.6556, + "step": 661504 + }, + { + "epoch": 0.02, + "learning_rate": 3.91617033431759e-05, + "loss": 3.6549, + "step": 662016 + }, + { + "epoch": 0.02, + "learning_rate": 3.915331739566538e-05, + "loss": 3.6619, + "step": 662528 + }, + { + "epoch": 0.02, + "learning_rate": 3.914493144815486e-05, + "loss": 3.6617, + "step": 663040 + }, + { + "epoch": 0.02, + "learning_rate": 3.913656187944807e-05, + "loss": 3.651, + "step": 663552 + }, + { + "epoch": 0.02, + "learning_rate": 3.912817593193755e-05, + "loss": 3.6648, + "step": 664064 + }, + { + "epoch": 0.02, + "learning_rate": 3.911978998442704e-05, + "loss": 3.6426, + "step": 664576 + }, + { + "epoch": 0.02, + "learning_rate": 3.911140403691652e-05, + "loss": 3.6479, + "step": 665088 + }, + { + "epoch": 0.02, + "learning_rate": 3.910303446820973e-05, + "loss": 3.6596, + "step": 665600 + }, + { + "epoch": 0.02, + "learning_rate": 3.909464852069921e-05, + "loss": 3.6557, + "step": 666112 + }, + { + "epoch": 0.02, + "learning_rate": 3.908626257318869e-05, + "loss": 3.6514, + "step": 666624 + }, + { + "epoch": 0.02, + "learning_rate": 3.907787662567817e-05, + "loss": 3.6577, + "step": 667136 + }, + { + "epoch": 0.02, + "learning_rate": 3.906950705697138e-05, + "loss": 3.6332, + "step": 667648 + }, + { + "epoch": 0.02, + "learning_rate": 3.906112110946086e-05, + "loss": 3.6577, + "step": 668160 + }, + { + "epoch": 0.02, + "learning_rate": 3.905273516195034e-05, + "loss": 3.6636, + "step": 668672 + }, + { + "epoch": 0.02, + "learning_rate": 3.904434921443982e-05, + "loss": 3.657, + "step": 669184 + }, + { + "epoch": 0.02, + "learning_rate": 3.9035979645733026e-05, + "loss": 3.6453, + "step": 669696 + }, + { + "epoch": 0.02, + "learning_rate": 3.9027593698222506e-05, + "loss": 3.6507, + "step": 670208 + }, + { + "epoch": 0.02, + "learning_rate": 3.901920775071199e-05, + "loss": 3.6437, + "step": 670720 + }, + { + "epoch": 0.02, + "learning_rate": 3.901082180320147e-05, + "loss": 3.6611, + "step": 671232 + }, + { + "epoch": 0.02, + "learning_rate": 3.900245223449468e-05, + "loss": 3.6553, + "step": 671744 + }, + { + "epoch": 0.02, + "learning_rate": 3.899406628698416e-05, + "loss": 3.6498, + "step": 672256 + }, + { + "epoch": 0.02, + "learning_rate": 3.898568033947364e-05, + "loss": 3.6485, + "step": 672768 + }, + { + "epoch": 0.02, + "learning_rate": 3.897729439196312e-05, + "loss": 3.6606, + "step": 673280 + }, + { + "epoch": 0.02, + "learning_rate": 3.896892482325633e-05, + "loss": 3.6545, + "step": 673792 + }, + { + "epoch": 0.02, + "learning_rate": 3.896053887574581e-05, + "loss": 3.6476, + "step": 674304 + }, + { + "epoch": 0.02, + "learning_rate": 3.895215292823529e-05, + "loss": 3.6523, + "step": 674816 + }, + { + "epoch": 0.02, + "learning_rate": 3.894376698072477e-05, + "loss": 3.6548, + "step": 675328 + }, + { + "epoch": 0.02, + "learning_rate": 3.893539741201798e-05, + "loss": 3.6516, + "step": 675840 + }, + { + "epoch": 0.02, + "learning_rate": 3.892701146450746e-05, + "loss": 3.6587, + "step": 676352 + }, + { + "epoch": 0.02, + "learning_rate": 3.891862551699694e-05, + "loss": 3.6424, + "step": 676864 + }, + { + "epoch": 0.02, + "learning_rate": 3.8910239569486426e-05, + "loss": 3.6517, + "step": 677376 + }, + { + "epoch": 0.02, + "learning_rate": 3.8901870000779635e-05, + "loss": 3.6611, + "step": 677888 + }, + { + "epoch": 0.02, + "learning_rate": 3.8893484053269115e-05, + "loss": 3.6536, + "step": 678400 + }, + { + "epoch": 0.02, + "learning_rate": 3.8885098105758595e-05, + "loss": 3.6545, + "step": 678912 + }, + { + "epoch": 0.02, + "learning_rate": 3.8876712158248075e-05, + "loss": 3.6551, + "step": 679424 + }, + { + "epoch": 0.02, + "learning_rate": 3.8868342589541284e-05, + "loss": 3.6485, + "step": 679936 + }, + { + "epoch": 0.02, + "learning_rate": 3.8859956642030764e-05, + "loss": 3.6434, + "step": 680448 + }, + { + "epoch": 0.02, + "learning_rate": 3.8851570694520244e-05, + "loss": 3.6514, + "step": 680960 + }, + { + "epoch": 0.02, + "learning_rate": 3.8843184747009724e-05, + "loss": 3.6667, + "step": 681472 + }, + { + "epoch": 0.02, + "learning_rate": 3.883481517830293e-05, + "loss": 3.6617, + "step": 681984 + }, + { + "epoch": 0.02, + "learning_rate": 3.882642923079241e-05, + "loss": 3.6493, + "step": 682496 + }, + { + "epoch": 0.02, + "learning_rate": 3.881804328328189e-05, + "loss": 3.6511, + "step": 683008 + }, + { + "epoch": 0.02, + "learning_rate": 3.880965733577138e-05, + "loss": 3.6541, + "step": 683520 + }, + { + "epoch": 0.02, + "learning_rate": 3.880128776706459e-05, + "loss": 3.6502, + "step": 684032 + }, + { + "epoch": 0.02, + "learning_rate": 3.879290181955407e-05, + "loss": 3.6542, + "step": 684544 + }, + { + "epoch": 0.02, + "learning_rate": 3.878451587204355e-05, + "loss": 3.6598, + "step": 685056 + }, + { + "epoch": 0.02, + "learning_rate": 3.877612992453303e-05, + "loss": 3.6605, + "step": 685568 + }, + { + "epoch": 0.02, + "learning_rate": 3.876774397702251e-05, + "loss": 3.6474, + "step": 686080 + }, + { + "epoch": 0.02, + "learning_rate": 3.875935802951198e-05, + "loss": 3.6569, + "step": 686592 + }, + { + "epoch": 0.03, + "eval_loss": 3.899163246154785, + "eval_runtime": 326.7628, + "eval_samples_per_second": 1167.792, + "eval_steps_per_second": 36.494, + "step": 686871 + }, + { + "epoch": 1.0, + "learning_rate": 3.875097208200146e-05, + "loss": 3.6499, + "step": 687104 + }, + { + "epoch": 1.0, + "learning_rate": 3.874260251329468e-05, + "loss": 3.6632, + "step": 687616 + }, + { + "epoch": 1.0, + "learning_rate": 3.873421656578416e-05, + "loss": 3.6515, + "step": 688128 + }, + { + "epoch": 1.0, + "learning_rate": 3.872583061827363e-05, + "loss": 3.6497, + "step": 688640 + }, + { + "epoch": 1.0, + "learning_rate": 3.871744467076312e-05, + "loss": 3.6459, + "step": 689152 + }, + { + "epoch": 1.0, + "learning_rate": 3.8709075102056333e-05, + "loss": 3.6476, + "step": 689664 + }, + { + "epoch": 1.0, + "learning_rate": 3.870068915454581e-05, + "loss": 3.6516, + "step": 690176 + }, + { + "epoch": 1.0, + "learning_rate": 3.8692303207035287e-05, + "loss": 3.6366, + "step": 690688 + }, + { + "epoch": 1.0, + "learning_rate": 3.8683917259524766e-05, + "loss": 3.6433, + "step": 691200 + }, + { + "epoch": 1.0, + "learning_rate": 3.867554769081798e-05, + "loss": 3.6615, + "step": 691712 + }, + { + "epoch": 1.0, + "learning_rate": 3.8667161743307456e-05, + "loss": 3.6437, + "step": 692224 + }, + { + "epoch": 1.0, + "learning_rate": 3.8658775795796935e-05, + "loss": 3.6393, + "step": 692736 + }, + { + "epoch": 1.0, + "learning_rate": 3.8650389848286415e-05, + "loss": 3.6592, + "step": 693248 + }, + { + "epoch": 1.0, + "learning_rate": 3.864202027957963e-05, + "loss": 3.643, + "step": 693760 + }, + { + "epoch": 1.0, + "learning_rate": 3.8633634332069105e-05, + "loss": 3.6522, + "step": 694272 + }, + { + "epoch": 1.0, + "learning_rate": 3.8625248384558584e-05, + "loss": 3.6296, + "step": 694784 + }, + { + "epoch": 1.0, + "learning_rate": 3.861686243704807e-05, + "loss": 3.6274, + "step": 695296 + }, + { + "epoch": 1.0, + "learning_rate": 3.860849286834128e-05, + "loss": 3.6474, + "step": 695808 + }, + { + "epoch": 1.0, + "learning_rate": 3.860010692083076e-05, + "loss": 3.639, + "step": 696320 + }, + { + "epoch": 1.0, + "learning_rate": 3.859172097332024e-05, + "loss": 3.6637, + "step": 696832 + }, + { + "epoch": 1.0, + "learning_rate": 3.858333502580972e-05, + "loss": 3.6456, + "step": 697344 + }, + { + "epoch": 1.0, + "learning_rate": 3.857496545710293e-05, + "loss": 3.6581, + "step": 697856 + }, + { + "epoch": 1.0, + "learning_rate": 3.856657950959241e-05, + "loss": 3.6395, + "step": 698368 + }, + { + "epoch": 1.0, + "learning_rate": 3.855819356208189e-05, + "loss": 3.6465, + "step": 698880 + }, + { + "epoch": 1.0, + "learning_rate": 3.8549823993375105e-05, + "loss": 3.6364, + "step": 699392 + }, + { + "epoch": 1.0, + "learning_rate": 3.854143804586458e-05, + "loss": 3.6465, + "step": 699904 + }, + { + "epoch": 1.0, + "learning_rate": 3.853305209835406e-05, + "loss": 3.6445, + "step": 700416 + }, + { + "epoch": 1.0, + "learning_rate": 3.852466615084354e-05, + "loss": 3.6492, + "step": 700928 + }, + { + "epoch": 1.0, + "learning_rate": 3.8516280203333025e-05, + "loss": 3.6404, + "step": 701440 + }, + { + "epoch": 1.0, + "learning_rate": 3.8507894255822505e-05, + "loss": 3.6338, + "step": 701952 + }, + { + "epoch": 1.01, + "learning_rate": 3.8499508308311985e-05, + "loss": 3.6281, + "step": 702464 + }, + { + "epoch": 1.01, + "learning_rate": 3.8491122360801465e-05, + "loss": 3.6473, + "step": 702976 + }, + { + "epoch": 1.01, + "learning_rate": 3.8482752792094674e-05, + "loss": 3.6446, + "step": 703488 + }, + { + "epoch": 1.01, + "learning_rate": 3.8474366844584154e-05, + "loss": 3.6456, + "step": 704000 + }, + { + "epoch": 1.01, + "learning_rate": 3.8465980897073634e-05, + "loss": 3.646, + "step": 704512 + }, + { + "epoch": 1.01, + "learning_rate": 3.8457594949563114e-05, + "loss": 3.6501, + "step": 705024 + }, + { + "epoch": 1.01, + "learning_rate": 3.844922538085632e-05, + "loss": 3.6445, + "step": 705536 + }, + { + "epoch": 1.01, + "learning_rate": 3.84408394333458e-05, + "loss": 3.6428, + "step": 706048 + }, + { + "epoch": 1.01, + "learning_rate": 3.843245348583528e-05, + "loss": 3.6454, + "step": 706560 + }, + { + "epoch": 1.01, + "learning_rate": 3.842406753832476e-05, + "loss": 3.6422, + "step": 707072 + }, + { + "epoch": 1.01, + "learning_rate": 3.841569796961798e-05, + "loss": 3.6416, + "step": 707584 + }, + { + "epoch": 1.01, + "learning_rate": 3.840731202210746e-05, + "loss": 3.6359, + "step": 708096 + }, + { + "epoch": 1.01, + "learning_rate": 3.839892607459694e-05, + "loss": 3.6423, + "step": 708608 + }, + { + "epoch": 1.01, + "learning_rate": 3.839054012708642e-05, + "loss": 3.6491, + "step": 709120 + }, + { + "epoch": 1.01, + "learning_rate": 3.838217055837963e-05, + "loss": 3.645, + "step": 709632 + }, + { + "epoch": 1.01, + "learning_rate": 3.837378461086911e-05, + "loss": 3.645, + "step": 710144 + }, + { + "epoch": 1.01, + "learning_rate": 3.836539866335859e-05, + "loss": 3.6306, + "step": 710656 + }, + { + "epoch": 1.01, + "learning_rate": 3.835701271584807e-05, + "loss": 3.6516, + "step": 711168 + }, + { + "epoch": 1.01, + "learning_rate": 3.8348643147141276e-05, + "loss": 3.6341, + "step": 711680 + }, + { + "epoch": 1.01, + "learning_rate": 3.8340257199630756e-05, + "loss": 3.6381, + "step": 712192 + }, + { + "epoch": 1.01, + "learning_rate": 3.8331871252120236e-05, + "loss": 3.6327, + "step": 712704 + }, + { + "epoch": 1.01, + "learning_rate": 3.8323485304609716e-05, + "loss": 3.6337, + "step": 713216 + }, + { + "epoch": 1.01, + "learning_rate": 3.831511573590293e-05, + "loss": 3.6498, + "step": 713728 + }, + { + "epoch": 1.01, + "learning_rate": 3.830672978839241e-05, + "loss": 3.6314, + "step": 714240 + }, + { + "epoch": 1.01, + "learning_rate": 3.829834384088189e-05, + "loss": 3.6425, + "step": 714752 + }, + { + "epoch": 1.01, + "learning_rate": 3.828995789337137e-05, + "loss": 3.6274, + "step": 715264 + }, + { + "epoch": 1.01, + "learning_rate": 3.828158832466458e-05, + "loss": 3.6436, + "step": 715776 + }, + { + "epoch": 1.01, + "learning_rate": 3.827320237715406e-05, + "loss": 3.6352, + "step": 716288 + }, + { + "epoch": 1.01, + "learning_rate": 3.826481642964354e-05, + "loss": 3.6476, + "step": 716800 + }, + { + "epoch": 1.01, + "learning_rate": 3.825643048213302e-05, + "loss": 3.6458, + "step": 717312 + }, + { + "epoch": 1.01, + "learning_rate": 3.824806091342623e-05, + "loss": 3.6331, + "step": 717824 + }, + { + "epoch": 1.01, + "learning_rate": 3.823967496591571e-05, + "loss": 3.63, + "step": 718336 + }, + { + "epoch": 1.01, + "learning_rate": 3.823128901840519e-05, + "loss": 3.6316, + "step": 718848 + }, + { + "epoch": 1.01, + "learning_rate": 3.822290307089467e-05, + "loss": 3.639, + "step": 719360 + }, + { + "epoch": 1.01, + "learning_rate": 3.8214533502187886e-05, + "loss": 3.6409, + "step": 719872 + }, + { + "epoch": 1.01, + "learning_rate": 3.8206147554677366e-05, + "loss": 3.6337, + "step": 720384 + }, + { + "epoch": 1.01, + "learning_rate": 3.8197761607166846e-05, + "loss": 3.6313, + "step": 720896 + }, + { + "epoch": 1.01, + "learning_rate": 3.8189375659656326e-05, + "loss": 3.6341, + "step": 721408 + }, + { + "epoch": 1.01, + "learning_rate": 3.8181006090949535e-05, + "loss": 3.6277, + "step": 721920 + }, + { + "epoch": 1.01, + "learning_rate": 3.8172620143439015e-05, + "loss": 3.6346, + "step": 722432 + }, + { + "epoch": 1.01, + "learning_rate": 3.8164234195928495e-05, + "loss": 3.6323, + "step": 722944 + }, + { + "epoch": 1.01, + "learning_rate": 3.8155848248417975e-05, + "loss": 3.6311, + "step": 723456 + }, + { + "epoch": 1.01, + "learning_rate": 3.8147478679711184e-05, + "loss": 3.641, + "step": 723968 + }, + { + "epoch": 1.01, + "learning_rate": 3.8139092732200664e-05, + "loss": 3.6485, + "step": 724480 + }, + { + "epoch": 1.01, + "learning_rate": 3.8130706784690144e-05, + "loss": 3.6402, + "step": 724992 + }, + { + "epoch": 1.01, + "learning_rate": 3.8122320837179624e-05, + "loss": 3.6393, + "step": 725504 + }, + { + "epoch": 1.01, + "learning_rate": 3.811395126847284e-05, + "loss": 3.6345, + "step": 726016 + }, + { + "epoch": 1.01, + "learning_rate": 3.810556532096232e-05, + "loss": 3.6427, + "step": 726528 + }, + { + "epoch": 1.01, + "learning_rate": 3.80971793734518e-05, + "loss": 3.6275, + "step": 727040 + }, + { + "epoch": 1.01, + "learning_rate": 3.808879342594128e-05, + "loss": 3.6432, + "step": 727552 + }, + { + "epoch": 1.01, + "learning_rate": 3.808042385723449e-05, + "loss": 3.6452, + "step": 728064 + }, + { + "epoch": 1.01, + "learning_rate": 3.807203790972397e-05, + "loss": 3.642, + "step": 728576 + }, + { + "epoch": 1.01, + "learning_rate": 3.806365196221345e-05, + "loss": 3.6254, + "step": 729088 + }, + { + "epoch": 1.01, + "learning_rate": 3.805526601470293e-05, + "loss": 3.631, + "step": 729600 + }, + { + "epoch": 1.01, + "learning_rate": 3.804689644599614e-05, + "loss": 3.6198, + "step": 730112 + }, + { + "epoch": 1.01, + "learning_rate": 3.803851049848562e-05, + "loss": 3.6416, + "step": 730624 + }, + { + "epoch": 1.01, + "learning_rate": 3.80301245509751e-05, + "loss": 3.6365, + "step": 731136 + }, + { + "epoch": 1.01, + "learning_rate": 3.802173860346458e-05, + "loss": 3.6343, + "step": 731648 + }, + { + "epoch": 1.01, + "learning_rate": 3.8013369034757786e-05, + "loss": 3.6364, + "step": 732160 + }, + { + "epoch": 1.02, + "learning_rate": 3.800498308724727e-05, + "loss": 3.6378, + "step": 732672 + }, + { + "epoch": 1.02, + "learning_rate": 3.799659713973675e-05, + "loss": 3.6277, + "step": 733184 + }, + { + "epoch": 1.02, + "learning_rate": 3.798821119222623e-05, + "loss": 3.6299, + "step": 733696 + }, + { + "epoch": 1.02, + "learning_rate": 3.797984162351944e-05, + "loss": 3.6409, + "step": 734208 + }, + { + "epoch": 1.02, + "learning_rate": 3.797145567600892e-05, + "loss": 3.6225, + "step": 734720 + }, + { + "epoch": 1.02, + "learning_rate": 3.79630697284984e-05, + "loss": 3.6283, + "step": 735232 + }, + { + "epoch": 1.02, + "learning_rate": 3.795468378098788e-05, + "loss": 3.6269, + "step": 735744 + }, + { + "epoch": 1.02, + "learning_rate": 3.794631421228109e-05, + "loss": 3.6338, + "step": 736256 + }, + { + "epoch": 1.02, + "learning_rate": 3.793792826477057e-05, + "loss": 3.6461, + "step": 736768 + }, + { + "epoch": 1.02, + "learning_rate": 3.792954231726005e-05, + "loss": 3.6278, + "step": 737280 + }, + { + "epoch": 1.02, + "learning_rate": 3.792115636974953e-05, + "loss": 3.6336, + "step": 737792 + }, + { + "epoch": 1.02, + "learning_rate": 3.791278680104274e-05, + "loss": 3.6314, + "step": 738304 + }, + { + "epoch": 1.02, + "learning_rate": 3.790440085353223e-05, + "loss": 3.6373, + "step": 738816 + }, + { + "epoch": 1.02, + "learning_rate": 3.789601490602171e-05, + "loss": 3.6348, + "step": 739328 + }, + { + "epoch": 1.02, + "learning_rate": 3.788762895851119e-05, + "loss": 3.6296, + "step": 739840 + }, + { + "epoch": 1.02, + "learning_rate": 3.7879259389804396e-05, + "loss": 3.6347, + "step": 740352 + }, + { + "epoch": 1.02, + "learning_rate": 3.7870873442293876e-05, + "loss": 3.621, + "step": 740864 + }, + { + "epoch": 1.02, + "learning_rate": 3.7862487494783356e-05, + "loss": 3.6239, + "step": 741376 + }, + { + "epoch": 1.02, + "learning_rate": 3.785410154727283e-05, + "loss": 3.6342, + "step": 741888 + }, + { + "epoch": 1.02, + "learning_rate": 3.7845731978566045e-05, + "loss": 3.6306, + "step": 742400 + }, + { + "epoch": 1.02, + "learning_rate": 3.7837346031055525e-05, + "loss": 3.6264, + "step": 742912 + }, + { + "epoch": 1.02, + "learning_rate": 3.7828960083545005e-05, + "loss": 3.6336, + "step": 743424 + }, + { + "epoch": 1.02, + "learning_rate": 3.782057413603448e-05, + "loss": 3.6125, + "step": 743936 + }, + { + "epoch": 1.02, + "learning_rate": 3.7812204567327694e-05, + "loss": 3.6302, + "step": 744448 + }, + { + "epoch": 1.02, + "learning_rate": 3.780381861981718e-05, + "loss": 3.6377, + "step": 744960 + }, + { + "epoch": 1.02, + "learning_rate": 3.779543267230666e-05, + "loss": 3.6331, + "step": 745472 + }, + { + "epoch": 1.02, + "learning_rate": 3.7787046724796134e-05, + "loss": 3.6225, + "step": 745984 + }, + { + "epoch": 1.02, + "learning_rate": 3.777867715608935e-05, + "loss": 3.6238, + "step": 746496 + }, + { + "epoch": 1.02, + "learning_rate": 3.777029120857883e-05, + "loss": 3.6197, + "step": 747008 + }, + { + "epoch": 1.02, + "learning_rate": 3.77619052610683e-05, + "loss": 3.6311, + "step": 747520 + }, + { + "epoch": 1.02, + "learning_rate": 3.775351931355778e-05, + "loss": 3.6311, + "step": 748032 + }, + { + "epoch": 1.02, + "learning_rate": 3.7745149744851e-05, + "loss": 3.6308, + "step": 748544 + }, + { + "epoch": 1.02, + "learning_rate": 3.773676379734048e-05, + "loss": 3.6176, + "step": 749056 + }, + { + "epoch": 1.02, + "learning_rate": 3.772837784982995e-05, + "loss": 3.6398, + "step": 749568 + }, + { + "epoch": 1.02, + "learning_rate": 3.771999190231943e-05, + "loss": 3.626, + "step": 750080 + }, + { + "epoch": 1.02, + "learning_rate": 3.771162233361265e-05, + "loss": 3.6258, + "step": 750592 + }, + { + "epoch": 1.02, + "learning_rate": 3.7703236386102134e-05, + "loss": 3.6247, + "step": 751104 + }, + { + "epoch": 1.02, + "learning_rate": 3.769485043859161e-05, + "loss": 3.632, + "step": 751616 + }, + { + "epoch": 1.02, + "learning_rate": 3.768648086988482e-05, + "loss": 3.6273, + "step": 752128 + }, + { + "epoch": 1.02, + "learning_rate": 3.76780949223743e-05, + "loss": 3.6319, + "step": 752640 + }, + { + "epoch": 1.02, + "learning_rate": 3.7669708974863776e-05, + "loss": 3.6204, + "step": 753152 + }, + { + "epoch": 1.02, + "learning_rate": 3.7661323027353256e-05, + "loss": 3.6279, + "step": 753664 + }, + { + "epoch": 1.02, + "learning_rate": 3.765295345864647e-05, + "loss": 3.6394, + "step": 754176 + }, + { + "epoch": 1.02, + "learning_rate": 3.764456751113595e-05, + "loss": 3.6255, + "step": 754688 + }, + { + "epoch": 1.02, + "learning_rate": 3.7636181563625425e-05, + "loss": 3.6282, + "step": 755200 + }, + { + "epoch": 1.02, + "learning_rate": 3.7627795616114905e-05, + "loss": 3.635, + "step": 755712 + }, + { + "epoch": 1.02, + "learning_rate": 3.761942604740812e-05, + "loss": 3.6236, + "step": 756224 + }, + { + "epoch": 1.02, + "learning_rate": 3.76110400998976e-05, + "loss": 3.6227, + "step": 756736 + }, + { + "epoch": 1.02, + "learning_rate": 3.760265415238708e-05, + "loss": 3.6278, + "step": 757248 + }, + { + "epoch": 1.02, + "learning_rate": 3.759426820487656e-05, + "loss": 3.6344, + "step": 757760 + }, + { + "epoch": 1.02, + "learning_rate": 3.758589863616978e-05, + "loss": 3.6406, + "step": 758272 + }, + { + "epoch": 1.02, + "learning_rate": 3.757751268865925e-05, + "loss": 3.6246, + "step": 758784 + }, + { + "epoch": 1.02, + "learning_rate": 3.756912674114873e-05, + "loss": 3.6293, + "step": 759296 + }, + { + "epoch": 1.02, + "learning_rate": 3.756074079363821e-05, + "loss": 3.6266, + "step": 759808 + }, + { + "epoch": 1.02, + "learning_rate": 3.7552371224931426e-05, + "loss": 3.627, + "step": 760320 + }, + { + "epoch": 1.02, + "learning_rate": 3.75439852774209e-05, + "loss": 3.6309, + "step": 760832 + }, + { + "epoch": 1.02, + "learning_rate": 3.753559932991038e-05, + "loss": 3.6346, + "step": 761344 + }, + { + "epoch": 1.02, + "learning_rate": 3.752721338239986e-05, + "loss": 3.6362, + "step": 761856 + }, + { + "epoch": 1.02, + "learning_rate": 3.751882743488934e-05, + "loss": 3.6235, + "step": 762368 + }, + { + "epoch": 1.02, + "learning_rate": 3.7510441487378826e-05, + "loss": 3.6319, + "step": 762880 + }, + { + "epoch": 1.03, + "eval_loss": 3.897075891494751, + "eval_runtime": 324.3395, + "eval_samples_per_second": 1176.517, + "eval_steps_per_second": 36.767, + "step": 763190 + }, + { + "epoch": 0.0, + "learning_rate": 3.7502055539868306e-05, + "loss": 3.6296, + "step": 763392 + }, + { + "epoch": 0.0, + "learning_rate": 3.7493669592357786e-05, + "loss": 3.6305, + "step": 763904 + }, + { + "epoch": 0.0, + "learning_rate": 3.7485283644847265e-05, + "loss": 3.6331, + "step": 764416 + }, + { + "epoch": 0.0, + "learning_rate": 3.7476897697336745e-05, + "loss": 3.6335, + "step": 764928 + }, + { + "epoch": 0.0, + "learning_rate": 3.7468528128629955e-05, + "loss": 3.6385, + "step": 765440 + }, + { + "epoch": 0.0, + "learning_rate": 3.7460142181119434e-05, + "loss": 3.6288, + "step": 765952 + }, + { + "epoch": 0.0, + "learning_rate": 3.7451756233608914e-05, + "loss": 3.6295, + "step": 766464 + }, + { + "epoch": 0.0, + "learning_rate": 3.7443370286098394e-05, + "loss": 3.626, + "step": 766976 + }, + { + "epoch": 0.0, + "learning_rate": 3.7435000717391603e-05, + "loss": 3.6261, + "step": 767488 + }, + { + "epoch": 0.0, + "learning_rate": 3.7426614769881083e-05, + "loss": 3.6359, + "step": 768000 + }, + { + "epoch": 0.0, + "learning_rate": 3.7418228822370563e-05, + "loss": 3.631, + "step": 768512 + }, + { + "epoch": 0.0, + "learning_rate": 3.740984287486004e-05, + "loss": 3.6272, + "step": 769024 + }, + { + "epoch": 0.0, + "learning_rate": 3.740147330615326e-05, + "loss": 3.6336, + "step": 769536 + }, + { + "epoch": 0.0, + "learning_rate": 3.739308735864274e-05, + "loss": 3.619, + "step": 770048 + }, + { + "epoch": 0.0, + "learning_rate": 3.738470141113222e-05, + "loss": 3.6295, + "step": 770560 + }, + { + "epoch": 0.0, + "learning_rate": 3.73763154636217e-05, + "loss": 3.6145, + "step": 771072 + }, + { + "epoch": 0.0, + "learning_rate": 3.736794589491491e-05, + "loss": 3.621, + "step": 771584 + }, + { + "epoch": 0.0, + "learning_rate": 3.735955994740439e-05, + "loss": 3.6238, + "step": 772096 + }, + { + "epoch": 0.0, + "learning_rate": 3.735117399989387e-05, + "loss": 3.6189, + "step": 772608 + }, + { + "epoch": 0.0, + "learning_rate": 3.734278805238335e-05, + "loss": 3.6434, + "step": 773120 + }, + { + "epoch": 0.0, + "learning_rate": 3.733441848367656e-05, + "loss": 3.6337, + "step": 773632 + }, + { + "epoch": 0.0, + "learning_rate": 3.732603253616604e-05, + "loss": 3.6283, + "step": 774144 + }, + { + "epoch": 0.0, + "learning_rate": 3.731764658865552e-05, + "loss": 3.6282, + "step": 774656 + }, + { + "epoch": 0.0, + "learning_rate": 3.7309260641145e-05, + "loss": 3.6312, + "step": 775168 + }, + { + "epoch": 0.0, + "learning_rate": 3.730089107243821e-05, + "loss": 3.6166, + "step": 775680 + }, + { + "epoch": 0.0, + "learning_rate": 3.729250512492769e-05, + "loss": 3.6314, + "step": 776192 + }, + { + "epoch": 0.0, + "learning_rate": 3.728411917741717e-05, + "loss": 3.6299, + "step": 776704 + }, + { + "epoch": 0.0, + "learning_rate": 3.727573322990665e-05, + "loss": 3.6103, + "step": 777216 + }, + { + "epoch": 0.0, + "learning_rate": 3.726736366119986e-05, + "loss": 3.6202, + "step": 777728 + }, + { + "epoch": 0.0, + "learning_rate": 3.725897771368934e-05, + "loss": 3.619, + "step": 778240 + }, + { + "epoch": 0.01, + "learning_rate": 3.725059176617882e-05, + "loss": 3.6293, + "step": 778752 + }, + { + "epoch": 0.01, + "learning_rate": 3.72422058186683e-05, + "loss": 3.6247, + "step": 779264 + }, + { + "epoch": 0.01, + "learning_rate": 3.723383624996151e-05, + "loss": 3.6234, + "step": 779776 + }, + { + "epoch": 0.01, + "learning_rate": 3.722545030245099e-05, + "loss": 3.6331, + "step": 780288 + }, + { + "epoch": 0.01, + "learning_rate": 3.721706435494047e-05, + "loss": 3.6223, + "step": 780800 + }, + { + "epoch": 0.01, + "learning_rate": 3.720869478623368e-05, + "loss": 3.6288, + "step": 781312 + }, + { + "epoch": 0.01, + "learning_rate": 3.7200308838723167e-05, + "loss": 3.6315, + "step": 781824 + }, + { + "epoch": 0.01, + "learning_rate": 3.7191922891212647e-05, + "loss": 3.6182, + "step": 782336 + }, + { + "epoch": 0.01, + "learning_rate": 3.7183536943702126e-05, + "loss": 3.6194, + "step": 782848 + }, + { + "epoch": 0.01, + "learning_rate": 3.7175167374995336e-05, + "loss": 3.6226, + "step": 783360 + }, + { + "epoch": 0.01, + "learning_rate": 3.7166781427484816e-05, + "loss": 3.6147, + "step": 783872 + }, + { + "epoch": 0.01, + "learning_rate": 3.7158411858778025e-05, + "loss": 3.6311, + "step": 784384 + }, + { + "epoch": 0.01, + "learning_rate": 3.7150025911267505e-05, + "loss": 3.6277, + "step": 784896 + }, + { + "epoch": 0.01, + "learning_rate": 3.7141639963756985e-05, + "loss": 3.6272, + "step": 785408 + }, + { + "epoch": 0.01, + "learning_rate": 3.7133254016246464e-05, + "loss": 3.6236, + "step": 785920 + }, + { + "epoch": 0.01, + "learning_rate": 3.7124868068735944e-05, + "loss": 3.6233, + "step": 786432 + }, + { + "epoch": 0.01, + "learning_rate": 3.7116482121225424e-05, + "loss": 3.6246, + "step": 786944 + }, + { + "epoch": 0.01, + "learning_rate": 3.7108096173714904e-05, + "loss": 3.6276, + "step": 787456 + }, + { + "epoch": 0.01, + "learning_rate": 3.709972660500812e-05, + "loss": 3.5949, + "step": 787968 + }, + { + "epoch": 0.01, + "learning_rate": 3.70913406574976e-05, + "loss": 3.6358, + "step": 788480 + }, + { + "epoch": 0.01, + "learning_rate": 3.708297108879081e-05, + "loss": 3.6203, + "step": 788992 + }, + { + "epoch": 0.01, + "learning_rate": 3.707458514128029e-05, + "loss": 3.6285, + "step": 789504 + }, + { + "epoch": 0.01, + "learning_rate": 3.706619919376977e-05, + "loss": 3.626, + "step": 790016 + }, + { + "epoch": 0.01, + "learning_rate": 3.705781324625925e-05, + "loss": 3.6201, + "step": 790528 + }, + { + "epoch": 0.01, + "learning_rate": 3.704942729874873e-05, + "loss": 3.6078, + "step": 791040 + }, + { + "epoch": 0.01, + "learning_rate": 3.704104135123821e-05, + "loss": 3.6217, + "step": 791552 + }, + { + "epoch": 0.01, + "learning_rate": 3.703265540372768e-05, + "loss": 3.6299, + "step": 792064 + }, + { + "epoch": 0.01, + "learning_rate": 3.70242858350209e-05, + "loss": 3.6267, + "step": 792576 + }, + { + "epoch": 0.01, + "learning_rate": 3.701589988751038e-05, + "loss": 3.6367, + "step": 793088 + }, + { + "epoch": 0.01, + "learning_rate": 3.700751393999986e-05, + "loss": 3.6173, + "step": 793600 + }, + { + "epoch": 0.01, + "learning_rate": 3.699912799248934e-05, + "loss": 3.601, + "step": 794112 + }, + { + "epoch": 0.01, + "learning_rate": 3.699077480258628e-05, + "loss": 3.6369, + "step": 794624 + }, + { + "epoch": 0.01, + "learning_rate": 3.698238885507576e-05, + "loss": 3.6137, + "step": 795136 + }, + { + "epoch": 0.01, + "learning_rate": 3.697400290756524e-05, + "loss": 3.6075, + "step": 795648 + }, + { + "epoch": 0.01, + "learning_rate": 3.696561696005472e-05, + "loss": 3.6217, + "step": 796160 + }, + { + "epoch": 0.01, + "learning_rate": 3.69572310125442e-05, + "loss": 3.6208, + "step": 796672 + }, + { + "epoch": 0.01, + "learning_rate": 3.694884506503368e-05, + "loss": 3.6123, + "step": 797184 + }, + { + "epoch": 0.01, + "learning_rate": 3.6940459117523156e-05, + "loss": 3.6102, + "step": 797696 + }, + { + "epoch": 0.01, + "learning_rate": 3.6932073170012636e-05, + "loss": 3.6082, + "step": 798208 + }, + { + "epoch": 0.01, + "learning_rate": 3.692370360130585e-05, + "loss": 3.6061, + "step": 798720 + }, + { + "epoch": 0.01, + "learning_rate": 3.6915317653795325e-05, + "loss": 3.6309, + "step": 799232 + }, + { + "epoch": 0.01, + "learning_rate": 3.690693170628481e-05, + "loss": 3.6218, + "step": 799744 + }, + { + "epoch": 0.01, + "learning_rate": 3.689854575877429e-05, + "loss": 3.6193, + "step": 800256 + }, + { + "epoch": 0.01, + "learning_rate": 3.689017619006751e-05, + "loss": 3.6154, + "step": 800768 + }, + { + "epoch": 0.01, + "learning_rate": 3.688179024255698e-05, + "loss": 3.6308, + "step": 801280 + }, + { + "epoch": 0.01, + "learning_rate": 3.687340429504646e-05, + "loss": 3.6164, + "step": 801792 + }, + { + "epoch": 0.01, + "learning_rate": 3.686501834753594e-05, + "loss": 3.6278, + "step": 802304 + }, + { + "epoch": 0.01, + "learning_rate": 3.685663240002542e-05, + "loss": 3.6131, + "step": 802816 + }, + { + "epoch": 0.01, + "learning_rate": 3.68482464525149e-05, + "loss": 3.613, + "step": 803328 + }, + { + "epoch": 0.01, + "learning_rate": 3.683987688380811e-05, + "loss": 3.6236, + "step": 803840 + }, + { + "epoch": 0.01, + "learning_rate": 3.683149093629759e-05, + "loss": 3.6292, + "step": 804352 + }, + { + "epoch": 0.01, + "learning_rate": 3.682310498878707e-05, + "loss": 3.6154, + "step": 804864 + }, + { + "epoch": 0.01, + "learning_rate": 3.681471904127655e-05, + "loss": 3.6244, + "step": 805376 + }, + { + "epoch": 0.01, + "learning_rate": 3.680633309376603e-05, + "loss": 3.608, + "step": 805888 + }, + { + "epoch": 0.01, + "learning_rate": 3.679794714625551e-05, + "loss": 3.6129, + "step": 806400 + }, + { + "epoch": 0.01, + "learning_rate": 3.6789561198744996e-05, + "loss": 3.6206, + "step": 806912 + }, + { + "epoch": 0.01, + "learning_rate": 3.6781175251234476e-05, + "loss": 3.6213, + "step": 807424 + }, + { + "epoch": 0.01, + "learning_rate": 3.6772805682527685e-05, + "loss": 3.611, + "step": 807936 + }, + { + "epoch": 0.01, + "learning_rate": 3.6764419735017165e-05, + "loss": 3.6112, + "step": 808448 + }, + { + "epoch": 0.01, + "learning_rate": 3.6756033787506645e-05, + "loss": 3.6166, + "step": 808960 + }, + { + "epoch": 0.02, + "learning_rate": 3.6747647839996125e-05, + "loss": 3.6166, + "step": 809472 + }, + { + "epoch": 0.02, + "learning_rate": 3.673929465009306e-05, + "loss": 3.6198, + "step": 809984 + }, + { + "epoch": 0.02, + "learning_rate": 3.673090870258254e-05, + "loss": 3.6046, + "step": 810496 + }, + { + "epoch": 0.02, + "learning_rate": 3.672252275507202e-05, + "loss": 3.6203, + "step": 811008 + }, + { + "epoch": 0.02, + "learning_rate": 3.67141368075615e-05, + "loss": 3.6258, + "step": 811520 + }, + { + "epoch": 0.02, + "learning_rate": 3.670575086005098e-05, + "loss": 3.6207, + "step": 812032 + }, + { + "epoch": 0.02, + "learning_rate": 3.669736491254046e-05, + "loss": 3.5929, + "step": 812544 + }, + { + "epoch": 0.02, + "learning_rate": 3.668897896502995e-05, + "loss": 3.6126, + "step": 813056 + }, + { + "epoch": 0.02, + "learning_rate": 3.668060939632316e-05, + "loss": 3.6131, + "step": 813568 + }, + { + "epoch": 0.02, + "learning_rate": 3.667222344881264e-05, + "loss": 3.624, + "step": 814080 + }, + { + "epoch": 0.02, + "learning_rate": 3.666383750130212e-05, + "loss": 3.6198, + "step": 814592 + }, + { + "epoch": 0.02, + "learning_rate": 3.66554515537916e-05, + "loss": 3.6175, + "step": 815104 + }, + { + "epoch": 0.02, + "learning_rate": 3.664708198508481e-05, + "loss": 3.607, + "step": 815616 + }, + { + "epoch": 0.02, + "learning_rate": 3.663869603757429e-05, + "loss": 3.6164, + "step": 816128 + }, + { + "epoch": 0.02, + "learning_rate": 3.663031009006377e-05, + "loss": 3.6069, + "step": 816640 + }, + { + "epoch": 0.02, + "learning_rate": 3.662192414255325e-05, + "loss": 3.6122, + "step": 817152 + }, + { + "epoch": 0.02, + "learning_rate": 3.661355457384646e-05, + "loss": 3.6048, + "step": 817664 + }, + { + "epoch": 0.02, + "learning_rate": 3.660516862633594e-05, + "loss": 3.6195, + "step": 818176 + }, + { + "epoch": 0.02, + "learning_rate": 3.659678267882542e-05, + "loss": 3.6065, + "step": 818688 + }, + { + "epoch": 0.02, + "learning_rate": 3.6588396731314903e-05, + "loss": 3.603, + "step": 819200 + }, + { + "epoch": 0.02, + "learning_rate": 3.658002716260811e-05, + "loss": 3.6024, + "step": 819712 + }, + { + "epoch": 0.02, + "learning_rate": 3.657164121509759e-05, + "loss": 3.6089, + "step": 820224 + }, + { + "epoch": 0.02, + "learning_rate": 3.656325526758707e-05, + "loss": 3.617, + "step": 820736 + }, + { + "epoch": 0.02, + "learning_rate": 3.655486932007655e-05, + "loss": 3.6071, + "step": 821248 + }, + { + "epoch": 0.02, + "learning_rate": 3.654649975136976e-05, + "loss": 3.6143, + "step": 821760 + }, + { + "epoch": 0.02, + "learning_rate": 3.653811380385924e-05, + "loss": 3.6186, + "step": 822272 + }, + { + "epoch": 0.02, + "learning_rate": 3.652972785634872e-05, + "loss": 3.6047, + "step": 822784 + }, + { + "epoch": 0.02, + "learning_rate": 3.65213419088382e-05, + "loss": 3.6157, + "step": 823296 + }, + { + "epoch": 0.02, + "learning_rate": 3.651297234013141e-05, + "loss": 3.613, + "step": 823808 + }, + { + "epoch": 0.02, + "learning_rate": 3.650458639262089e-05, + "loss": 3.6121, + "step": 824320 + }, + { + "epoch": 0.02, + "learning_rate": 3.649620044511037e-05, + "loss": 3.6096, + "step": 824832 + }, + { + "epoch": 0.02, + "learning_rate": 3.648781449759985e-05, + "loss": 3.602, + "step": 825344 + }, + { + "epoch": 0.02, + "learning_rate": 3.6479444928893066e-05, + "loss": 3.615, + "step": 825856 + }, + { + "epoch": 0.02, + "learning_rate": 3.6471058981382546e-05, + "loss": 3.608, + "step": 826368 + }, + { + "epoch": 0.02, + "learning_rate": 3.6462673033872026e-05, + "loss": 3.6143, + "step": 826880 + }, + { + "epoch": 0.02, + "learning_rate": 3.6454287086361506e-05, + "loss": 3.6128, + "step": 827392 + }, + { + "epoch": 0.02, + "learning_rate": 3.6445917517654715e-05, + "loss": 3.6094, + "step": 827904 + }, + { + "epoch": 0.02, + "learning_rate": 3.6437531570144195e-05, + "loss": 3.6117, + "step": 828416 + }, + { + "epoch": 0.02, + "learning_rate": 3.6429162001437404e-05, + "loss": 3.5955, + "step": 828928 + }, + { + "epoch": 0.02, + "learning_rate": 3.6420776053926884e-05, + "loss": 3.6206, + "step": 829440 + }, + { + "epoch": 0.02, + "learning_rate": 3.6412390106416364e-05, + "loss": 3.6027, + "step": 829952 + }, + { + "epoch": 0.02, + "learning_rate": 3.6404004158905844e-05, + "loss": 3.6266, + "step": 830464 + }, + { + "epoch": 0.02, + "learning_rate": 3.6395618211395324e-05, + "loss": 3.6034, + "step": 830976 + }, + { + "epoch": 0.02, + "learning_rate": 3.638724864268854e-05, + "loss": 3.6161, + "step": 831488 + }, + { + "epoch": 0.02, + "learning_rate": 3.637886269517802e-05, + "loss": 3.6169, + "step": 832000 + }, + { + "epoch": 0.02, + "learning_rate": 3.63704767476675e-05, + "loss": 3.6035, + "step": 832512 + }, + { + "epoch": 0.02, + "learning_rate": 3.636209080015698e-05, + "loss": 3.6114, + "step": 833024 + }, + { + "epoch": 0.02, + "learning_rate": 3.635370485264646e-05, + "loss": 3.6061, + "step": 833536 + }, + { + "epoch": 0.02, + "learning_rate": 3.634531890513593e-05, + "loss": 3.6182, + "step": 834048 + }, + { + "epoch": 0.02, + "learning_rate": 3.633693295762541e-05, + "loss": 3.6185, + "step": 834560 + }, + { + "epoch": 0.02, + "learning_rate": 3.632854701011489e-05, + "loss": 3.6073, + "step": 835072 + }, + { + "epoch": 0.02, + "learning_rate": 3.632017744140811e-05, + "loss": 3.6141, + "step": 835584 + }, + { + "epoch": 0.02, + "learning_rate": 3.631179149389758e-05, + "loss": 3.6068, + "step": 836096 + }, + { + "epoch": 0.02, + "learning_rate": 3.63034219251908e-05, + "loss": 3.6174, + "step": 836608 + }, + { + "epoch": 0.02, + "learning_rate": 3.629503597768028e-05, + "loss": 3.6031, + "step": 837120 + }, + { + "epoch": 0.02, + "learning_rate": 3.628665003016976e-05, + "loss": 3.6228, + "step": 837632 + }, + { + "epoch": 0.02, + "learning_rate": 3.627826408265924e-05, + "loss": 3.6047, + "step": 838144 + }, + { + "epoch": 0.02, + "learning_rate": 3.626987813514872e-05, + "loss": 3.6168, + "step": 838656 + }, + { + "epoch": 0.02, + "learning_rate": 3.62614921876382e-05, + "loss": 3.6103, + "step": 839168 + }, + { + "epoch": 0.03, + "eval_loss": 3.891366958618164, + "eval_runtime": 326.6234, + "eval_samples_per_second": 1168.291, + "eval_steps_per_second": 36.51, + "step": 839510 + }, + { + "epoch": 1.0, + "learning_rate": 3.625310624012768e-05, + "loss": 3.6065, + "step": 839680 + }, + { + "epoch": 1.0, + "learning_rate": 3.624472029261716e-05, + "loss": 3.6064, + "step": 840192 + }, + { + "epoch": 1.0, + "learning_rate": 3.6236350723910367e-05, + "loss": 3.6089, + "step": 840704 + }, + { + "epoch": 1.0, + "learning_rate": 3.6227964776399847e-05, + "loss": 3.612, + "step": 841216 + }, + { + "epoch": 1.0, + "learning_rate": 3.6219578828889326e-05, + "loss": 3.6186, + "step": 841728 + }, + { + "epoch": 1.0, + "learning_rate": 3.6211192881378806e-05, + "loss": 3.6037, + "step": 842240 + }, + { + "epoch": 1.0, + "learning_rate": 3.6202823312672016e-05, + "loss": 3.6061, + "step": 842752 + }, + { + "epoch": 1.0, + "learning_rate": 3.6194437365161495e-05, + "loss": 3.6023, + "step": 843264 + }, + { + "epoch": 1.0, + "learning_rate": 3.618605141765098e-05, + "loss": 3.6072, + "step": 843776 + }, + { + "epoch": 1.0, + "learning_rate": 3.617766547014046e-05, + "loss": 3.6112, + "step": 844288 + }, + { + "epoch": 1.0, + "learning_rate": 3.616929590143367e-05, + "loss": 3.6039, + "step": 844800 + }, + { + "epoch": 1.0, + "learning_rate": 3.616090995392315e-05, + "loss": 3.6061, + "step": 845312 + }, + { + "epoch": 1.0, + "learning_rate": 3.615252400641263e-05, + "loss": 3.6127, + "step": 845824 + }, + { + "epoch": 1.0, + "learning_rate": 3.614413805890211e-05, + "loss": 3.5937, + "step": 846336 + }, + { + "epoch": 1.0, + "learning_rate": 3.613576849019532e-05, + "loss": 3.603, + "step": 846848 + }, + { + "epoch": 1.0, + "learning_rate": 3.61273825426848e-05, + "loss": 3.5938, + "step": 847360 + }, + { + "epoch": 1.0, + "learning_rate": 3.611899659517428e-05, + "loss": 3.5969, + "step": 847872 + }, + { + "epoch": 1.0, + "learning_rate": 3.611061064766376e-05, + "loss": 3.6021, + "step": 848384 + }, + { + "epoch": 1.0, + "learning_rate": 3.610224107895697e-05, + "loss": 3.5933, + "step": 848896 + }, + { + "epoch": 1.0, + "learning_rate": 3.609385513144645e-05, + "loss": 3.6169, + "step": 849408 + }, + { + "epoch": 1.0, + "learning_rate": 3.6085469183935936e-05, + "loss": 3.6114, + "step": 849920 + }, + { + "epoch": 1.0, + "learning_rate": 3.6077083236425416e-05, + "loss": 3.6035, + "step": 850432 + }, + { + "epoch": 1.0, + "learning_rate": 3.6068697288914896e-05, + "loss": 3.6065, + "step": 850944 + }, + { + "epoch": 1.0, + "learning_rate": 3.6060311341404376e-05, + "loss": 3.6047, + "step": 851456 + }, + { + "epoch": 1.0, + "learning_rate": 3.6051925393893856e-05, + "loss": 3.5934, + "step": 851968 + }, + { + "epoch": 1.0, + "learning_rate": 3.6043555825187065e-05, + "loss": 3.6075, + "step": 852480 + }, + { + "epoch": 1.0, + "learning_rate": 3.6035169877676545e-05, + "loss": 3.6038, + "step": 852992 + }, + { + "epoch": 1.0, + "learning_rate": 3.6026783930166025e-05, + "loss": 3.5898, + "step": 853504 + }, + { + "epoch": 1.0, + "learning_rate": 3.6018397982655505e-05, + "loss": 3.5958, + "step": 854016 + }, + { + "epoch": 1.0, + "learning_rate": 3.6010028413948714e-05, + "loss": 3.5978, + "step": 854528 + }, + { + "epoch": 1.01, + "learning_rate": 3.6001642466438194e-05, + "loss": 3.6054, + "step": 855040 + }, + { + "epoch": 1.01, + "learning_rate": 3.5993256518927674e-05, + "loss": 3.5999, + "step": 855552 + }, + { + "epoch": 1.01, + "learning_rate": 3.5984870571417154e-05, + "loss": 3.6029, + "step": 856064 + }, + { + "epoch": 1.01, + "learning_rate": 3.597650100271037e-05, + "loss": 3.6077, + "step": 856576 + }, + { + "epoch": 1.01, + "learning_rate": 3.596811505519985e-05, + "loss": 3.5959, + "step": 857088 + }, + { + "epoch": 1.01, + "learning_rate": 3.595972910768933e-05, + "loss": 3.6101, + "step": 857600 + }, + { + "epoch": 1.01, + "learning_rate": 3.595134316017881e-05, + "loss": 3.6091, + "step": 858112 + }, + { + "epoch": 1.01, + "learning_rate": 3.594297359147202e-05, + "loss": 3.593, + "step": 858624 + }, + { + "epoch": 1.01, + "learning_rate": 3.59345876439615e-05, + "loss": 3.5978, + "step": 859136 + }, + { + "epoch": 1.01, + "learning_rate": 3.592620169645098e-05, + "loss": 3.5975, + "step": 859648 + }, + { + "epoch": 1.01, + "learning_rate": 3.591781574894046e-05, + "loss": 3.5926, + "step": 860160 + }, + { + "epoch": 1.01, + "learning_rate": 3.590944618023367e-05, + "loss": 3.6049, + "step": 860672 + }, + { + "epoch": 1.01, + "learning_rate": 3.590106023272315e-05, + "loss": 3.6028, + "step": 861184 + }, + { + "epoch": 1.01, + "learning_rate": 3.589267428521263e-05, + "loss": 3.607, + "step": 861696 + }, + { + "epoch": 1.01, + "learning_rate": 3.588428833770211e-05, + "loss": 3.6005, + "step": 862208 + }, + { + "epoch": 1.01, + "learning_rate": 3.587590239019159e-05, + "loss": 3.6019, + "step": 862720 + }, + { + "epoch": 1.01, + "learning_rate": 3.586751644268107e-05, + "loss": 3.5993, + "step": 863232 + }, + { + "epoch": 1.01, + "learning_rate": 3.585913049517055e-05, + "loss": 3.602, + "step": 863744 + }, + { + "epoch": 1.01, + "learning_rate": 3.585076092646376e-05, + "loss": 3.5761, + "step": 864256 + }, + { + "epoch": 1.01, + "learning_rate": 3.584237497895324e-05, + "loss": 3.612, + "step": 864768 + }, + { + "epoch": 1.01, + "learning_rate": 3.583400541024645e-05, + "loss": 3.5946, + "step": 865280 + }, + { + "epoch": 1.01, + "learning_rate": 3.582561946273593e-05, + "loss": 3.6064, + "step": 865792 + }, + { + "epoch": 1.01, + "learning_rate": 3.581723351522541e-05, + "loss": 3.6031, + "step": 866304 + }, + { + "epoch": 1.01, + "learning_rate": 3.580884756771489e-05, + "loss": 3.5942, + "step": 866816 + }, + { + "epoch": 1.01, + "learning_rate": 3.5800461620204365e-05, + "loss": 3.5865, + "step": 867328 + }, + { + "epoch": 1.01, + "learning_rate": 3.5792075672693845e-05, + "loss": 3.5958, + "step": 867840 + }, + { + "epoch": 1.01, + "learning_rate": 3.5783689725183325e-05, + "loss": 3.6133, + "step": 868352 + }, + { + "epoch": 1.01, + "learning_rate": 3.5775303777672805e-05, + "loss": 3.597, + "step": 868864 + }, + { + "epoch": 1.01, + "learning_rate": 3.576693420896602e-05, + "loss": 3.6138, + "step": 869376 + }, + { + "epoch": 1.01, + "learning_rate": 3.57585482614555e-05, + "loss": 3.5971, + "step": 869888 + }, + { + "epoch": 1.01, + "learning_rate": 3.575016231394498e-05, + "loss": 3.5761, + "step": 870400 + }, + { + "epoch": 1.01, + "learning_rate": 3.574179274523819e-05, + "loss": 3.6135, + "step": 870912 + }, + { + "epoch": 1.01, + "learning_rate": 3.5733423176531406e-05, + "loss": 3.5941, + "step": 871424 + }, + { + "epoch": 1.01, + "learning_rate": 3.5725037229020886e-05, + "loss": 3.5849, + "step": 871936 + }, + { + "epoch": 1.01, + "learning_rate": 3.5716651281510366e-05, + "loss": 3.5986, + "step": 872448 + }, + { + "epoch": 1.01, + "learning_rate": 3.570826533399984e-05, + "loss": 3.5983, + "step": 872960 + }, + { + "epoch": 1.01, + "learning_rate": 3.569987938648932e-05, + "loss": 3.586, + "step": 873472 + }, + { + "epoch": 1.01, + "learning_rate": 3.56914934389788e-05, + "loss": 3.5908, + "step": 873984 + }, + { + "epoch": 1.01, + "learning_rate": 3.568310749146828e-05, + "loss": 3.5831, + "step": 874496 + }, + { + "epoch": 1.01, + "learning_rate": 3.5674737922761495e-05, + "loss": 3.5889, + "step": 875008 + }, + { + "epoch": 1.01, + "learning_rate": 3.5666351975250975e-05, + "loss": 3.6028, + "step": 875520 + }, + { + "epoch": 1.01, + "learning_rate": 3.5657966027740454e-05, + "loss": 3.5971, + "step": 876032 + }, + { + "epoch": 1.01, + "learning_rate": 3.5649580080229934e-05, + "loss": 3.5974, + "step": 876544 + }, + { + "epoch": 1.01, + "learning_rate": 3.5641210511523144e-05, + "loss": 3.5898, + "step": 877056 + }, + { + "epoch": 1.01, + "learning_rate": 3.5632824564012624e-05, + "loss": 3.6049, + "step": 877568 + }, + { + "epoch": 1.01, + "learning_rate": 3.5624438616502103e-05, + "loss": 3.5966, + "step": 878080 + }, + { + "epoch": 1.01, + "learning_rate": 3.5616052668991583e-05, + "loss": 3.6051, + "step": 878592 + }, + { + "epoch": 1.01, + "learning_rate": 3.560766672148106e-05, + "loss": 3.5896, + "step": 879104 + }, + { + "epoch": 1.01, + "learning_rate": 3.559928077397054e-05, + "loss": 3.5883, + "step": 879616 + }, + { + "epoch": 1.01, + "learning_rate": 3.559091120526375e-05, + "loss": 3.6001, + "step": 880128 + }, + { + "epoch": 1.01, + "learning_rate": 3.558252525775323e-05, + "loss": 3.6083, + "step": 880640 + }, + { + "epoch": 1.01, + "learning_rate": 3.557413931024271e-05, + "loss": 3.595, + "step": 881152 + }, + { + "epoch": 1.01, + "learning_rate": 3.55657533627322e-05, + "loss": 3.6028, + "step": 881664 + }, + { + "epoch": 1.01, + "learning_rate": 3.555736741522168e-05, + "loss": 3.585, + "step": 882176 + }, + { + "epoch": 1.01, + "learning_rate": 3.554898146771116e-05, + "loss": 3.5898, + "step": 882688 + }, + { + "epoch": 1.01, + "learning_rate": 3.554059552020064e-05, + "loss": 3.5973, + "step": 883200 + }, + { + "epoch": 1.01, + "learning_rate": 3.553220957269012e-05, + "loss": 3.604, + "step": 883712 + }, + { + "epoch": 1.01, + "learning_rate": 3.552384000398333e-05, + "loss": 3.5866, + "step": 884224 + }, + { + "epoch": 1.01, + "learning_rate": 3.551545405647281e-05, + "loss": 3.5909, + "step": 884736 + }, + { + "epoch": 1.01, + "learning_rate": 3.550706810896229e-05, + "loss": 3.5956, + "step": 885248 + }, + { + "epoch": 1.02, + "learning_rate": 3.549868216145177e-05, + "loss": 3.594, + "step": 885760 + }, + { + "epoch": 1.02, + "learning_rate": 3.5490328971548706e-05, + "loss": 3.5973, + "step": 886272 + }, + { + "epoch": 1.02, + "learning_rate": 3.5481943024038186e-05, + "loss": 3.5817, + "step": 886784 + }, + { + "epoch": 1.02, + "learning_rate": 3.5473557076527666e-05, + "loss": 3.5962, + "step": 887296 + }, + { + "epoch": 1.02, + "learning_rate": 3.546517112901715e-05, + "loss": 3.607, + "step": 887808 + }, + { + "epoch": 1.02, + "learning_rate": 3.545678518150663e-05, + "loss": 3.5996, + "step": 888320 + }, + { + "epoch": 1.02, + "learning_rate": 3.544839923399611e-05, + "loss": 3.5765, + "step": 888832 + }, + { + "epoch": 1.02, + "learning_rate": 3.544001328648559e-05, + "loss": 3.5862, + "step": 889344 + }, + { + "epoch": 1.02, + "learning_rate": 3.543162733897507e-05, + "loss": 3.5886, + "step": 889856 + }, + { + "epoch": 1.02, + "learning_rate": 3.542325777026828e-05, + "loss": 3.6026, + "step": 890368 + }, + { + "epoch": 1.02, + "learning_rate": 3.541487182275776e-05, + "loss": 3.601, + "step": 890880 + }, + { + "epoch": 1.02, + "learning_rate": 3.540648587524724e-05, + "loss": 3.5935, + "step": 891392 + }, + { + "epoch": 1.02, + "learning_rate": 3.539811630654045e-05, + "loss": 3.5853, + "step": 891904 + }, + { + "epoch": 1.02, + "learning_rate": 3.538973035902993e-05, + "loss": 3.5966, + "step": 892416 + }, + { + "epoch": 1.02, + "learning_rate": 3.538134441151941e-05, + "loss": 3.5827, + "step": 892928 + }, + { + "epoch": 1.02, + "learning_rate": 3.537295846400889e-05, + "loss": 3.5916, + "step": 893440 + }, + { + "epoch": 1.02, + "learning_rate": 3.5364588895302106e-05, + "loss": 3.5873, + "step": 893952 + }, + { + "epoch": 1.02, + "learning_rate": 3.5356202947791586e-05, + "loss": 3.5931, + "step": 894464 + }, + { + "epoch": 1.02, + "learning_rate": 3.5347817000281066e-05, + "loss": 3.5882, + "step": 894976 + }, + { + "epoch": 1.02, + "learning_rate": 3.5339431052770546e-05, + "loss": 3.5786, + "step": 895488 + }, + { + "epoch": 1.02, + "learning_rate": 3.5331061484063755e-05, + "loss": 3.5841, + "step": 896000 + }, + { + "epoch": 1.02, + "learning_rate": 3.5322675536553235e-05, + "loss": 3.5817, + "step": 896512 + }, + { + "epoch": 1.02, + "learning_rate": 3.5314289589042715e-05, + "loss": 3.5981, + "step": 897024 + }, + { + "epoch": 1.02, + "learning_rate": 3.5305903641532195e-05, + "loss": 3.5851, + "step": 897536 + }, + { + "epoch": 1.02, + "learning_rate": 3.5297534072825404e-05, + "loss": 3.5926, + "step": 898048 + }, + { + "epoch": 1.02, + "learning_rate": 3.5289148125314884e-05, + "loss": 3.5925, + "step": 898560 + }, + { + "epoch": 1.02, + "learning_rate": 3.5280762177804364e-05, + "loss": 3.5856, + "step": 899072 + }, + { + "epoch": 1.02, + "learning_rate": 3.527239260909757e-05, + "loss": 3.5968, + "step": 899584 + }, + { + "epoch": 1.02, + "learning_rate": 3.526400666158706e-05, + "loss": 3.5895, + "step": 900096 + }, + { + "epoch": 1.02, + "learning_rate": 3.525562071407654e-05, + "loss": 3.5913, + "step": 900608 + }, + { + "epoch": 1.02, + "learning_rate": 3.524723476656602e-05, + "loss": 3.5846, + "step": 901120 + }, + { + "epoch": 1.02, + "learning_rate": 3.523886519785923e-05, + "loss": 3.5806, + "step": 901632 + }, + { + "epoch": 1.02, + "learning_rate": 3.523047925034871e-05, + "loss": 3.5941, + "step": 902144 + }, + { + "epoch": 1.02, + "learning_rate": 3.522209330283819e-05, + "loss": 3.5868, + "step": 902656 + }, + { + "epoch": 1.02, + "learning_rate": 3.521370735532767e-05, + "loss": 3.5938, + "step": 903168 + }, + { + "epoch": 1.02, + "learning_rate": 3.520532140781714e-05, + "loss": 3.5916, + "step": 903680 + }, + { + "epoch": 1.02, + "learning_rate": 3.519693546030662e-05, + "loss": 3.5882, + "step": 904192 + }, + { + "epoch": 1.02, + "learning_rate": 3.51885495127961e-05, + "loss": 3.5851, + "step": 904704 + }, + { + "epoch": 1.02, + "learning_rate": 3.518017994408932e-05, + "loss": 3.5785, + "step": 905216 + }, + { + "epoch": 1.02, + "learning_rate": 3.51717939965788e-05, + "loss": 3.596, + "step": 905728 + }, + { + "epoch": 1.02, + "learning_rate": 3.516340804906828e-05, + "loss": 3.5836, + "step": 906240 + }, + { + "epoch": 1.02, + "learning_rate": 3.515502210155776e-05, + "loss": 3.6017, + "step": 906752 + }, + { + "epoch": 1.02, + "learning_rate": 3.514663615404724e-05, + "loss": 3.5825, + "step": 907264 + }, + { + "epoch": 1.02, + "learning_rate": 3.513826658534045e-05, + "loss": 3.5943, + "step": 907776 + }, + { + "epoch": 1.02, + "learning_rate": 3.512988063782993e-05, + "loss": 3.5947, + "step": 908288 + }, + { + "epoch": 1.02, + "learning_rate": 3.512149469031941e-05, + "loss": 3.5831, + "step": 908800 + }, + { + "epoch": 1.02, + "learning_rate": 3.511310874280889e-05, + "loss": 3.5895, + "step": 909312 + }, + { + "epoch": 1.02, + "learning_rate": 3.5104739174102096e-05, + "loss": 3.5854, + "step": 909824 + }, + { + "epoch": 1.02, + "learning_rate": 3.5096353226591576e-05, + "loss": 3.5978, + "step": 910336 + }, + { + "epoch": 1.02, + "learning_rate": 3.5087967279081056e-05, + "loss": 3.5976, + "step": 910848 + }, + { + "epoch": 1.02, + "learning_rate": 3.5079581331570536e-05, + "loss": 3.5854, + "step": 911360 + }, + { + "epoch": 1.02, + "learning_rate": 3.5071195384060016e-05, + "loss": 3.5859, + "step": 911872 + }, + { + "epoch": 1.02, + "learning_rate": 3.5062809436549496e-05, + "loss": 3.5891, + "step": 912384 + }, + { + "epoch": 1.02, + "learning_rate": 3.505443986784271e-05, + "loss": 3.5955, + "step": 912896 + }, + { + "epoch": 1.02, + "learning_rate": 3.504605392033219e-05, + "loss": 3.5806, + "step": 913408 + }, + { + "epoch": 1.02, + "learning_rate": 3.503766797282167e-05, + "loss": 3.6023, + "step": 913920 + }, + { + "epoch": 1.02, + "learning_rate": 3.502928202531115e-05, + "loss": 3.5855, + "step": 914432 + }, + { + "epoch": 1.02, + "learning_rate": 3.502089607780063e-05, + "loss": 3.593, + "step": 914944 + }, + { + "epoch": 1.02, + "learning_rate": 3.501251013029011e-05, + "loss": 3.5908, + "step": 915456 + }, + { + "epoch": 1.03, + "eval_loss": 3.890727996826172, + "eval_runtime": 333.8747, + "eval_samples_per_second": 1142.917, + "eval_steps_per_second": 35.717, + "step": 915830 + }, + { + "epoch": 0.0, + "learning_rate": 3.500412418277959e-05, + "loss": 3.59, + "step": 915968 + }, + { + "epoch": 0.0, + "learning_rate": 3.499573823526907e-05, + "loss": 3.5838, + "step": 916480 + }, + { + "epoch": 0.0, + "learning_rate": 3.498735228775855e-05, + "loss": 3.5894, + "step": 916992 + }, + { + "epoch": 0.0, + "learning_rate": 3.497896634024803e-05, + "loss": 3.5915, + "step": 917504 + }, + { + "epoch": 0.0, + "learning_rate": 3.497059677154124e-05, + "loss": 3.5961, + "step": 918016 + }, + { + "epoch": 0.0, + "learning_rate": 3.496222720283445e-05, + "loss": 3.5855, + "step": 918528 + }, + { + "epoch": 0.0, + "learning_rate": 3.495384125532393e-05, + "loss": 3.586, + "step": 919040 + }, + { + "epoch": 0.0, + "learning_rate": 3.4945455307813416e-05, + "loss": 3.5844, + "step": 919552 + }, + { + "epoch": 0.0, + "learning_rate": 3.4937069360302896e-05, + "loss": 3.5837, + "step": 920064 + }, + { + "epoch": 0.0, + "learning_rate": 3.4928683412792376e-05, + "loss": 3.5843, + "step": 920576 + }, + { + "epoch": 0.0, + "learning_rate": 3.4920297465281856e-05, + "loss": 3.5881, + "step": 921088 + }, + { + "epoch": 0.0, + "learning_rate": 3.4911911517771336e-05, + "loss": 3.5876, + "step": 921600 + }, + { + "epoch": 0.0, + "learning_rate": 3.490352557026081e-05, + "loss": 3.5928, + "step": 922112 + }, + { + "epoch": 0.0, + "learning_rate": 3.4895156001554025e-05, + "loss": 3.5745, + "step": 922624 + }, + { + "epoch": 0.0, + "learning_rate": 3.4886770054043505e-05, + "loss": 3.5809, + "step": 923136 + }, + { + "epoch": 0.0, + "learning_rate": 3.487838410653298e-05, + "loss": 3.572, + "step": 923648 + }, + { + "epoch": 0.0, + "learning_rate": 3.486999815902246e-05, + "loss": 3.5743, + "step": 924160 + }, + { + "epoch": 0.0, + "learning_rate": 3.4861628590315674e-05, + "loss": 3.5819, + "step": 924672 + }, + { + "epoch": 0.0, + "learning_rate": 3.485325902160888e-05, + "loss": 3.5728, + "step": 925184 + }, + { + "epoch": 0.0, + "learning_rate": 3.484487307409837e-05, + "loss": 3.5951, + "step": 925696 + }, + { + "epoch": 0.0, + "learning_rate": 3.483648712658785e-05, + "loss": 3.5928, + "step": 926208 + }, + { + "epoch": 0.0, + "learning_rate": 3.482810117907733e-05, + "loss": 3.5825, + "step": 926720 + }, + { + "epoch": 0.0, + "learning_rate": 3.48197152315668e-05, + "loss": 3.5832, + "step": 927232 + }, + { + "epoch": 0.0, + "learning_rate": 3.481132928405628e-05, + "loss": 3.5858, + "step": 927744 + }, + { + "epoch": 0.0, + "learning_rate": 3.480294333654576e-05, + "loss": 3.5688, + "step": 928256 + }, + { + "epoch": 0.0, + "learning_rate": 3.479457376783898e-05, + "loss": 3.5933, + "step": 928768 + }, + { + "epoch": 0.0, + "learning_rate": 3.478618782032845e-05, + "loss": 3.5804, + "step": 929280 + }, + { + "epoch": 0.0, + "learning_rate": 3.477780187281793e-05, + "loss": 3.5677, + "step": 929792 + }, + { + "epoch": 0.0, + "learning_rate": 3.476941592530741e-05, + "loss": 3.5783, + "step": 930304 + }, + { + "epoch": 0.0, + "learning_rate": 3.476104635660063e-05, + "loss": 3.5771, + "step": 930816 + }, + { + "epoch": 0.01, + "learning_rate": 3.475266040909011e-05, + "loss": 3.5808, + "step": 931328 + }, + { + "epoch": 0.01, + "learning_rate": 3.474427446157959e-05, + "loss": 3.5785, + "step": 931840 + }, + { + "epoch": 0.01, + "learning_rate": 3.473588851406907e-05, + "loss": 3.5878, + "step": 932352 + }, + { + "epoch": 0.01, + "learning_rate": 3.4727518945362276e-05, + "loss": 3.5814, + "step": 932864 + }, + { + "epoch": 0.01, + "learning_rate": 3.4719132997851756e-05, + "loss": 3.5776, + "step": 933376 + }, + { + "epoch": 0.01, + "learning_rate": 3.4710747050341236e-05, + "loss": 3.5882, + "step": 933888 + }, + { + "epoch": 0.01, + "learning_rate": 3.4702361102830716e-05, + "loss": 3.5878, + "step": 934400 + }, + { + "epoch": 0.01, + "learning_rate": 3.4693991534123925e-05, + "loss": 3.5762, + "step": 934912 + }, + { + "epoch": 0.01, + "learning_rate": 3.4685605586613405e-05, + "loss": 3.5763, + "step": 935424 + }, + { + "epoch": 0.01, + "learning_rate": 3.4677219639102885e-05, + "loss": 3.5764, + "step": 935936 + }, + { + "epoch": 0.01, + "learning_rate": 3.4668833691592365e-05, + "loss": 3.5724, + "step": 936448 + }, + { + "epoch": 0.01, + "learning_rate": 3.4660464122885574e-05, + "loss": 3.5858, + "step": 936960 + }, + { + "epoch": 0.01, + "learning_rate": 3.465207817537506e-05, + "loss": 3.5843, + "step": 937472 + }, + { + "epoch": 0.01, + "learning_rate": 3.464369222786454e-05, + "loss": 3.5865, + "step": 937984 + }, + { + "epoch": 0.01, + "learning_rate": 3.463530628035402e-05, + "loss": 3.5792, + "step": 938496 + }, + { + "epoch": 0.01, + "learning_rate": 3.46269203328435e-05, + "loss": 3.5796, + "step": 939008 + }, + { + "epoch": 0.01, + "learning_rate": 3.461853438533298e-05, + "loss": 3.5835, + "step": 939520 + }, + { + "epoch": 0.01, + "learning_rate": 3.461014843782246e-05, + "loss": 3.5825, + "step": 940032 + }, + { + "epoch": 0.01, + "learning_rate": 3.460176249031194e-05, + "loss": 3.558, + "step": 940544 + }, + { + "epoch": 0.01, + "learning_rate": 3.459339292160515e-05, + "loss": 3.5898, + "step": 941056 + }, + { + "epoch": 0.01, + "learning_rate": 3.458502335289836e-05, + "loss": 3.5766, + "step": 941568 + }, + { + "epoch": 0.01, + "learning_rate": 3.457663740538784e-05, + "loss": 3.5853, + "step": 942080 + }, + { + "epoch": 0.01, + "learning_rate": 3.456825145787732e-05, + "loss": 3.5829, + "step": 942592 + }, + { + "epoch": 0.01, + "learning_rate": 3.45598655103668e-05, + "loss": 3.5777, + "step": 943104 + }, + { + "epoch": 0.01, + "learning_rate": 3.4551495941660015e-05, + "loss": 3.5641, + "step": 943616 + }, + { + "epoch": 0.01, + "learning_rate": 3.4543109994149495e-05, + "loss": 3.5742, + "step": 944128 + }, + { + "epoch": 0.01, + "learning_rate": 3.4534724046638975e-05, + "loss": 3.5956, + "step": 944640 + }, + { + "epoch": 0.01, + "learning_rate": 3.4526338099128455e-05, + "loss": 3.5809, + "step": 945152 + }, + { + "epoch": 0.01, + "learning_rate": 3.4517952151617935e-05, + "loss": 3.5887, + "step": 945664 + }, + { + "epoch": 0.01, + "learning_rate": 3.4509566204107414e-05, + "loss": 3.5773, + "step": 946176 + }, + { + "epoch": 0.01, + "learning_rate": 3.4501180256596894e-05, + "loss": 3.5546, + "step": 946688 + }, + { + "epoch": 0.01, + "learning_rate": 3.4492794309086374e-05, + "loss": 3.595, + "step": 947200 + }, + { + "epoch": 0.01, + "learning_rate": 3.4484424740379583e-05, + "loss": 3.5731, + "step": 947712 + }, + { + "epoch": 0.01, + "learning_rate": 3.4476038792869063e-05, + "loss": 3.5678, + "step": 948224 + }, + { + "epoch": 0.01, + "learning_rate": 3.4467652845358543e-05, + "loss": 3.5791, + "step": 948736 + }, + { + "epoch": 0.01, + "learning_rate": 3.445926689784802e-05, + "loss": 3.5737, + "step": 949248 + }, + { + "epoch": 0.01, + "learning_rate": 3.44508809503375e-05, + "loss": 3.5692, + "step": 949760 + }, + { + "epoch": 0.01, + "learning_rate": 3.444249500282698e-05, + "loss": 3.5708, + "step": 950272 + }, + { + "epoch": 0.01, + "learning_rate": 3.443410905531646e-05, + "loss": 3.5659, + "step": 950784 + }, + { + "epoch": 0.01, + "learning_rate": 3.442573948660968e-05, + "loss": 3.5699, + "step": 951296 + }, + { + "epoch": 0.01, + "learning_rate": 3.441735353909916e-05, + "loss": 3.5838, + "step": 951808 + }, + { + "epoch": 0.01, + "learning_rate": 3.440896759158864e-05, + "loss": 3.5774, + "step": 952320 + }, + { + "epoch": 0.01, + "learning_rate": 3.440058164407811e-05, + "loss": 3.5802, + "step": 952832 + }, + { + "epoch": 0.01, + "learning_rate": 3.439221207537133e-05, + "loss": 3.5682, + "step": 953344 + }, + { + "epoch": 0.01, + "learning_rate": 3.438382612786081e-05, + "loss": 3.5863, + "step": 953856 + }, + { + "epoch": 0.01, + "learning_rate": 3.437544018035029e-05, + "loss": 3.577, + "step": 954368 + }, + { + "epoch": 0.01, + "learning_rate": 3.436705423283976e-05, + "loss": 3.5858, + "step": 954880 + }, + { + "epoch": 0.01, + "learning_rate": 3.435866828532924e-05, + "loss": 3.5699, + "step": 955392 + }, + { + "epoch": 0.01, + "learning_rate": 3.435028233781872e-05, + "loss": 3.5723, + "step": 955904 + }, + { + "epoch": 0.01, + "learning_rate": 3.434191276911194e-05, + "loss": 3.584, + "step": 956416 + }, + { + "epoch": 0.01, + "learning_rate": 3.433352682160142e-05, + "loss": 3.5813, + "step": 956928 + }, + { + "epoch": 0.01, + "learning_rate": 3.43251408740909e-05, + "loss": 3.5761, + "step": 957440 + }, + { + "epoch": 0.01, + "learning_rate": 3.431675492658038e-05, + "loss": 3.5844, + "step": 957952 + }, + { + "epoch": 0.01, + "learning_rate": 3.430836897906986e-05, + "loss": 3.566, + "step": 958464 + }, + { + "epoch": 0.01, + "learning_rate": 3.429998303155934e-05, + "loss": 3.5697, + "step": 958976 + }, + { + "epoch": 0.01, + "learning_rate": 3.429159708404882e-05, + "loss": 3.5766, + "step": 959488 + }, + { + "epoch": 0.01, + "learning_rate": 3.42832111365383e-05, + "loss": 3.5839, + "step": 960000 + }, + { + "epoch": 0.01, + "learning_rate": 3.4274841567831506e-05, + "loss": 3.5655, + "step": 960512 + }, + { + "epoch": 0.01, + "learning_rate": 3.4266455620320986e-05, + "loss": 3.5754, + "step": 961024 + }, + { + "epoch": 0.01, + "learning_rate": 3.4258069672810466e-05, + "loss": 3.5744, + "step": 961536 + }, + { + "epoch": 0.02, + "learning_rate": 3.4249683725299946e-05, + "loss": 3.5741, + "step": 962048 + }, + { + "epoch": 0.02, + "learning_rate": 3.4241330535396884e-05, + "loss": 3.5756, + "step": 962560 + }, + { + "epoch": 0.02, + "learning_rate": 3.423294458788637e-05, + "loss": 3.5668, + "step": 963072 + }, + { + "epoch": 0.02, + "learning_rate": 3.422455864037585e-05, + "loss": 3.574, + "step": 963584 + }, + { + "epoch": 0.02, + "learning_rate": 3.421617269286533e-05, + "loss": 3.5847, + "step": 964096 + }, + { + "epoch": 0.02, + "learning_rate": 3.420778674535481e-05, + "loss": 3.5842, + "step": 964608 + }, + { + "epoch": 0.02, + "learning_rate": 3.419941717664802e-05, + "loss": 3.5507, + "step": 965120 + }, + { + "epoch": 0.02, + "learning_rate": 3.41910312291375e-05, + "loss": 3.5685, + "step": 965632 + }, + { + "epoch": 0.02, + "learning_rate": 3.418264528162698e-05, + "loss": 3.5658, + "step": 966144 + }, + { + "epoch": 0.02, + "learning_rate": 3.417425933411646e-05, + "loss": 3.5819, + "step": 966656 + }, + { + "epoch": 0.02, + "learning_rate": 3.416587338660594e-05, + "loss": 3.5832, + "step": 967168 + }, + { + "epoch": 0.02, + "learning_rate": 3.415748743909542e-05, + "loss": 3.5731, + "step": 967680 + }, + { + "epoch": 0.02, + "learning_rate": 3.41491014915849e-05, + "loss": 3.566, + "step": 968192 + }, + { + "epoch": 0.02, + "learning_rate": 3.414071554407438e-05, + "loss": 3.5746, + "step": 968704 + }, + { + "epoch": 0.02, + "learning_rate": 3.413234597536759e-05, + "loss": 3.5691, + "step": 969216 + }, + { + "epoch": 0.02, + "learning_rate": 3.412396002785707e-05, + "loss": 3.571, + "step": 969728 + }, + { + "epoch": 0.02, + "learning_rate": 3.4115574080346555e-05, + "loss": 3.5662, + "step": 970240 + }, + { + "epoch": 0.02, + "learning_rate": 3.4107188132836035e-05, + "loss": 3.5744, + "step": 970752 + }, + { + "epoch": 0.02, + "learning_rate": 3.4098818564129244e-05, + "loss": 3.5703, + "step": 971264 + }, + { + "epoch": 0.02, + "learning_rate": 3.4090432616618724e-05, + "loss": 3.5597, + "step": 971776 + }, + { + "epoch": 0.02, + "learning_rate": 3.4082046669108204e-05, + "loss": 3.5629, + "step": 972288 + }, + { + "epoch": 0.02, + "learning_rate": 3.4073660721597684e-05, + "loss": 3.5655, + "step": 972800 + }, + { + "epoch": 0.02, + "learning_rate": 3.406529115289089e-05, + "loss": 3.5757, + "step": 973312 + }, + { + "epoch": 0.02, + "learning_rate": 3.405690520538037e-05, + "loss": 3.5642, + "step": 973824 + }, + { + "epoch": 0.02, + "learning_rate": 3.404851925786985e-05, + "loss": 3.5751, + "step": 974336 + }, + { + "epoch": 0.02, + "learning_rate": 3.404013331035933e-05, + "loss": 3.5707, + "step": 974848 + }, + { + "epoch": 0.02, + "learning_rate": 3.403176374165254e-05, + "loss": 3.5703, + "step": 975360 + }, + { + "epoch": 0.02, + "learning_rate": 3.402339417294576e-05, + "loss": 3.5718, + "step": 975872 + }, + { + "epoch": 0.02, + "learning_rate": 3.401500822543524e-05, + "loss": 3.5739, + "step": 976384 + }, + { + "epoch": 0.02, + "learning_rate": 3.400662227792472e-05, + "loss": 3.5729, + "step": 976896 + }, + { + "epoch": 0.02, + "learning_rate": 3.39982363304142e-05, + "loss": 3.5627, + "step": 977408 + }, + { + "epoch": 0.02, + "learning_rate": 3.398985038290368e-05, + "loss": 3.5607, + "step": 977920 + }, + { + "epoch": 0.02, + "learning_rate": 3.398148081419689e-05, + "loss": 3.5754, + "step": 978432 + }, + { + "epoch": 0.02, + "learning_rate": 3.397309486668637e-05, + "loss": 3.5694, + "step": 978944 + }, + { + "epoch": 0.02, + "learning_rate": 3.396470891917585e-05, + "loss": 3.5717, + "step": 979456 + }, + { + "epoch": 0.02, + "learning_rate": 3.395632297166533e-05, + "loss": 3.5705, + "step": 979968 + }, + { + "epoch": 0.02, + "learning_rate": 3.3947937024154807e-05, + "loss": 3.5689, + "step": 980480 + }, + { + "epoch": 0.02, + "learning_rate": 3.3939551076644287e-05, + "loss": 3.5709, + "step": 980992 + }, + { + "epoch": 0.02, + "learning_rate": 3.3931181507937496e-05, + "loss": 3.5619, + "step": 981504 + }, + { + "epoch": 0.02, + "learning_rate": 3.3922795560426976e-05, + "loss": 3.5723, + "step": 982016 + }, + { + "epoch": 0.02, + "learning_rate": 3.391440961291646e-05, + "loss": 3.5698, + "step": 982528 + }, + { + "epoch": 0.02, + "learning_rate": 3.390602366540594e-05, + "loss": 3.586, + "step": 983040 + }, + { + "epoch": 0.02, + "learning_rate": 3.389763771789542e-05, + "loss": 3.5615, + "step": 983552 + }, + { + "epoch": 0.02, + "learning_rate": 3.388926814918863e-05, + "loss": 3.5723, + "step": 984064 + }, + { + "epoch": 0.02, + "learning_rate": 3.388088220167811e-05, + "loss": 3.5776, + "step": 984576 + }, + { + "epoch": 0.02, + "learning_rate": 3.387249625416759e-05, + "loss": 3.5638, + "step": 985088 + }, + { + "epoch": 0.02, + "learning_rate": 3.386411030665707e-05, + "loss": 3.5679, + "step": 985600 + }, + { + "epoch": 0.02, + "learning_rate": 3.385574073795028e-05, + "loss": 3.5688, + "step": 986112 + }, + { + "epoch": 0.02, + "learning_rate": 3.384735479043976e-05, + "loss": 3.5777, + "step": 986624 + }, + { + "epoch": 0.02, + "learning_rate": 3.383896884292924e-05, + "loss": 3.5792, + "step": 987136 + }, + { + "epoch": 0.02, + "learning_rate": 3.3830582895418713e-05, + "loss": 3.5714, + "step": 987648 + }, + { + "epoch": 0.02, + "learning_rate": 3.38221969479082e-05, + "loss": 3.566, + "step": 988160 + }, + { + "epoch": 0.02, + "learning_rate": 3.381381100039768e-05, + "loss": 3.5692, + "step": 988672 + }, + { + "epoch": 0.02, + "learning_rate": 3.3805441431690896e-05, + "loss": 3.5764, + "step": 989184 + }, + { + "epoch": 0.02, + "learning_rate": 3.379705548418037e-05, + "loss": 3.5604, + "step": 989696 + }, + { + "epoch": 0.02, + "learning_rate": 3.378866953666985e-05, + "loss": 3.585, + "step": 990208 + }, + { + "epoch": 0.02, + "learning_rate": 3.378028358915933e-05, + "loss": 3.5642, + "step": 990720 + }, + { + "epoch": 0.02, + "learning_rate": 3.377189764164881e-05, + "loss": 3.5759, + "step": 991232 + }, + { + "epoch": 0.02, + "learning_rate": 3.376351169413829e-05, + "loss": 3.5721, + "step": 991744 + }, + { + "epoch": 0.03, + "eval_loss": 3.8927314281463623, + "eval_runtime": 307.5721, + "eval_samples_per_second": 1240.655, + "eval_steps_per_second": 38.771, + "step": 992150 + }, + { + "epoch": 1.0, + "learning_rate": 3.375512574662777e-05, + "loss": 3.5714, + "step": 992256 + }, + { + "epoch": 1.0, + "learning_rate": 3.374673979911725e-05, + "loss": 3.566, + "step": 992768 + }, + { + "epoch": 1.0, + "learning_rate": 3.373837023041046e-05, + "loss": 3.5678, + "step": 993280 + }, + { + "epoch": 1.0, + "learning_rate": 3.373000066170367e-05, + "loss": 3.5743, + "step": 993792 + }, + { + "epoch": 1.0, + "learning_rate": 3.3721614714193154e-05, + "loss": 3.5743, + "step": 994304 + }, + { + "epoch": 1.0, + "learning_rate": 3.3713228766682634e-05, + "loss": 3.5681, + "step": 994816 + }, + { + "epoch": 1.0, + "learning_rate": 3.3704842819172114e-05, + "loss": 3.568, + "step": 995328 + }, + { + "epoch": 1.0, + "learning_rate": 3.3696456871661594e-05, + "loss": 3.5618, + "step": 995840 + }, + { + "epoch": 1.0, + "learning_rate": 3.3688070924151074e-05, + "loss": 3.5656, + "step": 996352 + }, + { + "epoch": 1.0, + "learning_rate": 3.3679684976640554e-05, + "loss": 3.5682, + "step": 996864 + }, + { + "epoch": 1.0, + "learning_rate": 3.3671299029130034e-05, + "loss": 3.5696, + "step": 997376 + }, + { + "epoch": 1.0, + "learning_rate": 3.366292946042324e-05, + "loss": 3.5735, + "step": 997888 + }, + { + "epoch": 1.0, + "learning_rate": 3.365454351291272e-05, + "loss": 3.571, + "step": 998400 + }, + { + "epoch": 1.0, + "learning_rate": 3.36461575654022e-05, + "loss": 3.5551, + "step": 998912 + }, + { + "epoch": 1.0, + "learning_rate": 3.363778799669541e-05, + "loss": 3.5639, + "step": 999424 + }, + { + "epoch": 1.0, + "learning_rate": 3.362940204918489e-05, + "loss": 3.5552, + "step": 999936 + }, + { + "epoch": 1.0, + "learning_rate": 3.362101610167437e-05, + "loss": 3.5527, + "step": 1000448 + }, + { + "epoch": 1.0, + "learning_rate": 3.361263015416385e-05, + "loss": 3.5672, + "step": 1000960 + }, + { + "epoch": 1.0, + "learning_rate": 3.360426058545707e-05, + "loss": 3.5557, + "step": 1001472 + }, + { + "epoch": 1.0, + "learning_rate": 3.359587463794655e-05, + "loss": 3.5718, + "step": 1001984 + }, + { + "epoch": 1.0, + "learning_rate": 3.358748869043603e-05, + "loss": 3.5768, + "step": 1002496 + }, + { + "epoch": 1.0, + "learning_rate": 3.357910274292551e-05, + "loss": 3.5637, + "step": 1003008 + }, + { + "epoch": 1.0, + "learning_rate": 3.357071679541499e-05, + "loss": 3.5673, + "step": 1003520 + }, + { + "epoch": 1.0, + "learning_rate": 3.356233084790447e-05, + "loss": 3.5664, + "step": 1004032 + }, + { + "epoch": 1.0, + "learning_rate": 3.3553961279197676e-05, + "loss": 3.5508, + "step": 1004544 + }, + { + "epoch": 1.0, + "learning_rate": 3.3545575331687156e-05, + "loss": 3.5749, + "step": 1005056 + }, + { + "epoch": 1.0, + "learning_rate": 3.3537189384176636e-05, + "loss": 3.5618, + "step": 1005568 + }, + { + "epoch": 1.0, + "learning_rate": 3.3528803436666116e-05, + "loss": 3.5564, + "step": 1006080 + }, + { + "epoch": 1.0, + "learning_rate": 3.3520417489155596e-05, + "loss": 3.5574, + "step": 1006592 + }, + { + "epoch": 1.0, + "learning_rate": 3.3512031541645076e-05, + "loss": 3.5551, + "step": 1007104 + }, + { + "epoch": 1.01, + "learning_rate": 3.3503645594134556e-05, + "loss": 3.5628, + "step": 1007616 + }, + { + "epoch": 1.01, + "learning_rate": 3.3495259646624036e-05, + "loss": 3.5616, + "step": 1008128 + }, + { + "epoch": 1.01, + "learning_rate": 3.348689007791725e-05, + "loss": 3.5694, + "step": 1008640 + }, + { + "epoch": 1.01, + "learning_rate": 3.347850413040673e-05, + "loss": 3.5613, + "step": 1009152 + }, + { + "epoch": 1.01, + "learning_rate": 3.3470118182896205e-05, + "loss": 3.5594, + "step": 1009664 + }, + { + "epoch": 1.01, + "learning_rate": 3.3461732235385685e-05, + "loss": 3.5622, + "step": 1010176 + }, + { + "epoch": 1.01, + "learning_rate": 3.34533626666789e-05, + "loss": 3.5734, + "step": 1010688 + }, + { + "epoch": 1.01, + "learning_rate": 3.3444976719168374e-05, + "loss": 3.5581, + "step": 1011200 + }, + { + "epoch": 1.01, + "learning_rate": 3.343660715046159e-05, + "loss": 3.5586, + "step": 1011712 + }, + { + "epoch": 1.01, + "learning_rate": 3.342822120295107e-05, + "loss": 3.5583, + "step": 1012224 + }, + { + "epoch": 1.01, + "learning_rate": 3.341983525544055e-05, + "loss": 3.5587, + "step": 1012736 + }, + { + "epoch": 1.01, + "learning_rate": 3.341144930793002e-05, + "loss": 3.5611, + "step": 1013248 + }, + { + "epoch": 1.01, + "learning_rate": 3.340306336041951e-05, + "loss": 3.567, + "step": 1013760 + }, + { + "epoch": 1.01, + "learning_rate": 3.339467741290899e-05, + "loss": 3.5702, + "step": 1014272 + }, + { + "epoch": 1.01, + "learning_rate": 3.338629146539847e-05, + "loss": 3.5607, + "step": 1014784 + }, + { + "epoch": 1.01, + "learning_rate": 3.337792189669168e-05, + "loss": 3.563, + "step": 1015296 + }, + { + "epoch": 1.01, + "learning_rate": 3.336953594918116e-05, + "loss": 3.5609, + "step": 1015808 + }, + { + "epoch": 1.01, + "learning_rate": 3.336115000167064e-05, + "loss": 3.5656, + "step": 1016320 + }, + { + "epoch": 1.01, + "learning_rate": 3.335278043296385e-05, + "loss": 3.5405, + "step": 1016832 + }, + { + "epoch": 1.01, + "learning_rate": 3.334439448545333e-05, + "loss": 3.5685, + "step": 1017344 + }, + { + "epoch": 1.01, + "learning_rate": 3.333600853794281e-05, + "loss": 3.5587, + "step": 1017856 + }, + { + "epoch": 1.01, + "learning_rate": 3.332762259043229e-05, + "loss": 3.5644, + "step": 1018368 + }, + { + "epoch": 1.01, + "learning_rate": 3.331923664292177e-05, + "loss": 3.5633, + "step": 1018880 + }, + { + "epoch": 1.01, + "learning_rate": 3.331085069541125e-05, + "loss": 3.5577, + "step": 1019392 + }, + { + "epoch": 1.01, + "learning_rate": 3.330248112670446e-05, + "loss": 3.5546, + "step": 1019904 + }, + { + "epoch": 1.01, + "learning_rate": 3.329409517919394e-05, + "loss": 3.5522, + "step": 1020416 + }, + { + "epoch": 1.01, + "learning_rate": 3.328570923168342e-05, + "loss": 3.5743, + "step": 1020928 + }, + { + "epoch": 1.01, + "learning_rate": 3.32773232841729e-05, + "loss": 3.5595, + "step": 1021440 + }, + { + "epoch": 1.01, + "learning_rate": 3.326893733666238e-05, + "loss": 3.5769, + "step": 1021952 + }, + { + "epoch": 1.01, + "learning_rate": 3.326055138915186e-05, + "loss": 3.5587, + "step": 1022464 + }, + { + "epoch": 1.01, + "learning_rate": 3.325216544164134e-05, + "loss": 3.5435, + "step": 1022976 + }, + { + "epoch": 1.01, + "learning_rate": 3.324377949413082e-05, + "loss": 3.5748, + "step": 1023488 + }, + { + "epoch": 1.01, + "learning_rate": 3.323540992542403e-05, + "loss": 3.5592, + "step": 1024000 + }, + { + "epoch": 1.01, + "learning_rate": 3.322702397791351e-05, + "loss": 3.5462, + "step": 1024512 + }, + { + "epoch": 1.01, + "learning_rate": 3.321863803040299e-05, + "loss": 3.5558, + "step": 1025024 + }, + { + "epoch": 1.01, + "learning_rate": 3.321025208289247e-05, + "loss": 3.5611, + "step": 1025536 + }, + { + "epoch": 1.01, + "learning_rate": 3.320186613538195e-05, + "loss": 3.5485, + "step": 1026048 + }, + { + "epoch": 1.01, + "learning_rate": 3.319348018787143e-05, + "loss": 3.5544, + "step": 1026560 + }, + { + "epoch": 1.01, + "learning_rate": 3.318509424036091e-05, + "loss": 3.5484, + "step": 1027072 + }, + { + "epoch": 1.01, + "learning_rate": 3.317672467165413e-05, + "loss": 3.5476, + "step": 1027584 + }, + { + "epoch": 1.01, + "learning_rate": 3.316835510294734e-05, + "loss": 3.5663, + "step": 1028096 + }, + { + "epoch": 1.01, + "learning_rate": 3.315996915543682e-05, + "loss": 3.5613, + "step": 1028608 + }, + { + "epoch": 1.01, + "learning_rate": 3.31515832079263e-05, + "loss": 3.5584, + "step": 1029120 + }, + { + "epoch": 1.01, + "learning_rate": 3.314319726041578e-05, + "loss": 3.552, + "step": 1029632 + }, + { + "epoch": 1.01, + "learning_rate": 3.313481131290526e-05, + "loss": 3.5664, + "step": 1030144 + }, + { + "epoch": 1.01, + "learning_rate": 3.3126425365394737e-05, + "loss": 3.5589, + "step": 1030656 + }, + { + "epoch": 1.01, + "learning_rate": 3.311803941788421e-05, + "loss": 3.5699, + "step": 1031168 + }, + { + "epoch": 1.01, + "learning_rate": 3.3109669849177426e-05, + "loss": 3.5509, + "step": 1031680 + }, + { + "epoch": 1.01, + "learning_rate": 3.3101283901666906e-05, + "loss": 3.5554, + "step": 1032192 + }, + { + "epoch": 1.01, + "learning_rate": 3.3092897954156386e-05, + "loss": 3.563, + "step": 1032704 + }, + { + "epoch": 1.01, + "learning_rate": 3.3084512006645866e-05, + "loss": 3.5632, + "step": 1033216 + }, + { + "epoch": 1.01, + "learning_rate": 3.307614243793908e-05, + "loss": 3.5591, + "step": 1033728 + }, + { + "epoch": 1.01, + "learning_rate": 3.306775649042856e-05, + "loss": 3.5655, + "step": 1034240 + }, + { + "epoch": 1.01, + "learning_rate": 3.305937054291804e-05, + "loss": 3.5517, + "step": 1034752 + }, + { + "epoch": 1.01, + "learning_rate": 3.3050984595407514e-05, + "loss": 3.5488, + "step": 1035264 + }, + { + "epoch": 1.01, + "learning_rate": 3.3042598647896994e-05, + "loss": 3.5601, + "step": 1035776 + }, + { + "epoch": 1.01, + "learning_rate": 3.3034212700386474e-05, + "loss": 3.5633, + "step": 1036288 + }, + { + "epoch": 1.01, + "learning_rate": 3.3025826752875954e-05, + "loss": 3.5543, + "step": 1036800 + }, + { + "epoch": 1.01, + "learning_rate": 3.3017440805365434e-05, + "loss": 3.5543, + "step": 1037312 + }, + { + "epoch": 1.01, + "learning_rate": 3.300907123665864e-05, + "loss": 3.5558, + "step": 1037824 + }, + { + "epoch": 1.02, + "learning_rate": 3.300068528914812e-05, + "loss": 3.5567, + "step": 1038336 + }, + { + "epoch": 1.02, + "learning_rate": 3.299231572044133e-05, + "loss": 3.554, + "step": 1038848 + }, + { + "epoch": 1.02, + "learning_rate": 3.298392977293082e-05, + "loss": 3.5534, + "step": 1039360 + }, + { + "epoch": 1.02, + "learning_rate": 3.29755438254203e-05, + "loss": 3.5541, + "step": 1039872 + }, + { + "epoch": 1.02, + "learning_rate": 3.296715787790978e-05, + "loss": 3.5664, + "step": 1040384 + }, + { + "epoch": 1.02, + "learning_rate": 3.295877193039926e-05, + "loss": 3.5658, + "step": 1040896 + }, + { + "epoch": 1.02, + "learning_rate": 3.295038598288874e-05, + "loss": 3.5367, + "step": 1041408 + }, + { + "epoch": 1.02, + "learning_rate": 3.294200003537822e-05, + "loss": 3.5513, + "step": 1041920 + }, + { + "epoch": 1.02, + "learning_rate": 3.29336140878677e-05, + "loss": 3.5479, + "step": 1042432 + }, + { + "epoch": 1.02, + "learning_rate": 3.292524451916091e-05, + "loss": 3.5652, + "step": 1042944 + }, + { + "epoch": 1.02, + "learning_rate": 3.291685857165039e-05, + "loss": 3.5621, + "step": 1043456 + }, + { + "epoch": 1.02, + "learning_rate": 3.290847262413987e-05, + "loss": 3.5596, + "step": 1043968 + }, + { + "epoch": 1.02, + "learning_rate": 3.290008667662935e-05, + "loss": 3.5467, + "step": 1044480 + }, + { + "epoch": 1.02, + "learning_rate": 3.289171710792256e-05, + "loss": 3.5595, + "step": 1044992 + }, + { + "epoch": 1.02, + "learning_rate": 3.288333116041204e-05, + "loss": 3.5515, + "step": 1045504 + }, + { + "epoch": 1.02, + "learning_rate": 3.287494521290152e-05, + "loss": 3.5525, + "step": 1046016 + }, + { + "epoch": 1.02, + "learning_rate": 3.2866559265391004e-05, + "loss": 3.5467, + "step": 1046528 + }, + { + "epoch": 1.02, + "learning_rate": 3.285818969668421e-05, + "loss": 3.5556, + "step": 1047040 + }, + { + "epoch": 1.02, + "learning_rate": 3.284980374917369e-05, + "loss": 3.5558, + "step": 1047552 + }, + { + "epoch": 1.02, + "learning_rate": 3.284141780166317e-05, + "loss": 3.5394, + "step": 1048064 + }, + { + "epoch": 1.02, + "learning_rate": 3.283304823295638e-05, + "loss": 3.5514, + "step": 1048576 + }, + { + "epoch": 1.02, + "learning_rate": 3.282466228544586e-05, + "loss": 3.5407, + "step": 1049088 + }, + { + "epoch": 1.02, + "learning_rate": 3.281627633793534e-05, + "loss": 3.5585, + "step": 1049600 + }, + { + "epoch": 1.02, + "learning_rate": 3.280789039042482e-05, + "loss": 3.5508, + "step": 1050112 + }, + { + "epoch": 1.02, + "learning_rate": 3.279952082171803e-05, + "loss": 3.5535, + "step": 1050624 + }, + { + "epoch": 1.02, + "learning_rate": 3.279113487420751e-05, + "loss": 3.5543, + "step": 1051136 + }, + { + "epoch": 1.02, + "learning_rate": 3.278274892669699e-05, + "loss": 3.5539, + "step": 1051648 + }, + { + "epoch": 1.02, + "learning_rate": 3.2774379357990206e-05, + "loss": 3.5528, + "step": 1052160 + }, + { + "epoch": 1.02, + "learning_rate": 3.2765993410479686e-05, + "loss": 3.5543, + "step": 1052672 + }, + { + "epoch": 1.02, + "learning_rate": 3.2757607462969166e-05, + "loss": 3.5566, + "step": 1053184 + }, + { + "epoch": 1.02, + "learning_rate": 3.2749221515458646e-05, + "loss": 3.546, + "step": 1053696 + }, + { + "epoch": 1.02, + "learning_rate": 3.2740835567948126e-05, + "loss": 3.5416, + "step": 1054208 + }, + { + "epoch": 1.02, + "learning_rate": 3.2732465999241335e-05, + "loss": 3.5581, + "step": 1054720 + }, + { + "epoch": 1.02, + "learning_rate": 3.2724080051730815e-05, + "loss": 3.5531, + "step": 1055232 + }, + { + "epoch": 1.02, + "learning_rate": 3.2715694104220295e-05, + "loss": 3.5535, + "step": 1055744 + }, + { + "epoch": 1.02, + "learning_rate": 3.2707308156709775e-05, + "loss": 3.5482, + "step": 1056256 + }, + { + "epoch": 1.02, + "learning_rate": 3.2698938588002984e-05, + "loss": 3.5557, + "step": 1056768 + }, + { + "epoch": 1.02, + "learning_rate": 3.2690552640492464e-05, + "loss": 3.5551, + "step": 1057280 + }, + { + "epoch": 1.02, + "learning_rate": 3.2682166692981944e-05, + "loss": 3.5433, + "step": 1057792 + }, + { + "epoch": 1.02, + "learning_rate": 3.2673780745471424e-05, + "loss": 3.5477, + "step": 1058304 + }, + { + "epoch": 1.02, + "learning_rate": 3.266539479796091e-05, + "loss": 3.5558, + "step": 1058816 + }, + { + "epoch": 1.02, + "learning_rate": 3.265702522925412e-05, + "loss": 3.5678, + "step": 1059328 + }, + { + "epoch": 1.02, + "learning_rate": 3.26486392817436e-05, + "loss": 3.5445, + "step": 1059840 + }, + { + "epoch": 1.02, + "learning_rate": 3.264025333423308e-05, + "loss": 3.5477, + "step": 1060352 + }, + { + "epoch": 1.02, + "learning_rate": 3.263186738672256e-05, + "loss": 3.5629, + "step": 1060864 + }, + { + "epoch": 1.02, + "learning_rate": 3.262348143921204e-05, + "loss": 3.5491, + "step": 1061376 + }, + { + "epoch": 1.02, + "learning_rate": 3.261509549170152e-05, + "loss": 3.5493, + "step": 1061888 + }, + { + "epoch": 1.02, + "learning_rate": 3.260672592299473e-05, + "loss": 3.5501, + "step": 1062400 + }, + { + "epoch": 1.02, + "learning_rate": 3.259833997548421e-05, + "loss": 3.5619, + "step": 1062912 + }, + { + "epoch": 1.02, + "learning_rate": 3.258995402797369e-05, + "loss": 3.5636, + "step": 1063424 + }, + { + "epoch": 1.02, + "learning_rate": 3.258156808046317e-05, + "loss": 3.5537, + "step": 1063936 + }, + { + "epoch": 1.02, + "learning_rate": 3.257318213295265e-05, + "loss": 3.5474, + "step": 1064448 + }, + { + "epoch": 1.02, + "learning_rate": 3.256479618544213e-05, + "loss": 3.5522, + "step": 1064960 + }, + { + "epoch": 1.02, + "learning_rate": 3.2556426616735345e-05, + "loss": 3.5553, + "step": 1065472 + }, + { + "epoch": 1.02, + "learning_rate": 3.254804066922482e-05, + "loss": 3.5437, + "step": 1065984 + }, + { + "epoch": 1.02, + "learning_rate": 3.25396547217143e-05, + "loss": 3.5695, + "step": 1066496 + }, + { + "epoch": 1.02, + "learning_rate": 3.253126877420378e-05, + "loss": 3.5479, + "step": 1067008 + }, + { + "epoch": 1.02, + "learning_rate": 3.252288282669326e-05, + "loss": 3.5577, + "step": 1067520 + }, + { + "epoch": 1.02, + "learning_rate": 3.251449687918274e-05, + "loss": 3.5536, + "step": 1068032 + }, + { + "epoch": 1.03, + "eval_loss": 3.8927876949310303, + "eval_runtime": 305.0378, + "eval_samples_per_second": 1250.963, + "eval_steps_per_second": 39.094, + "step": 1068470 + }, + { + "epoch": 0.0, + "learning_rate": 3.250611093167222e-05, + "loss": 3.5785, + "step": 1068544 + }, + { + "epoch": 0.0, + "learning_rate": 3.249774136296543e-05, + "loss": 3.547, + "step": 1069056 + }, + { + "epoch": 0.0, + "learning_rate": 3.2489355415454907e-05, + "loss": 3.5512, + "step": 1069568 + }, + { + "epoch": 0.0, + "learning_rate": 3.2480969467944387e-05, + "loss": 3.5586, + "step": 1070080 + }, + { + "epoch": 0.0, + "learning_rate": 3.2472583520433866e-05, + "loss": 3.5547, + "step": 1070592 + }, + { + "epoch": 0.0, + "learning_rate": 3.2464197572923346e-05, + "loss": 3.5543, + "step": 1071104 + }, + { + "epoch": 0.0, + "learning_rate": 3.245582800421656e-05, + "loss": 3.5518, + "step": 1071616 + }, + { + "epoch": 0.0, + "learning_rate": 3.244744205670604e-05, + "loss": 3.5459, + "step": 1072128 + }, + { + "epoch": 0.0, + "learning_rate": 3.243905610919552e-05, + "loss": 3.547, + "step": 1072640 + }, + { + "epoch": 0.0, + "learning_rate": 3.2430670161685e-05, + "loss": 3.5541, + "step": 1073152 + }, + { + "epoch": 0.0, + "learning_rate": 3.242228421417448e-05, + "loss": 3.5497, + "step": 1073664 + }, + { + "epoch": 0.0, + "learning_rate": 3.241389826666396e-05, + "loss": 3.5559, + "step": 1074176 + }, + { + "epoch": 0.0, + "learning_rate": 3.240551231915344e-05, + "loss": 3.5552, + "step": 1074688 + }, + { + "epoch": 0.0, + "learning_rate": 3.239714275044665e-05, + "loss": 3.537, + "step": 1075200 + }, + { + "epoch": 0.0, + "learning_rate": 3.238877318173986e-05, + "loss": 3.5486, + "step": 1075712 + }, + { + "epoch": 0.0, + "learning_rate": 3.238038723422934e-05, + "loss": 3.5348, + "step": 1076224 + }, + { + "epoch": 0.0, + "learning_rate": 3.237200128671882e-05, + "loss": 3.5346, + "step": 1076736 + }, + { + "epoch": 0.0, + "learning_rate": 3.23636153392083e-05, + "loss": 3.5506, + "step": 1077248 + }, + { + "epoch": 0.0, + "learning_rate": 3.235522939169778e-05, + "loss": 3.5368, + "step": 1077760 + }, + { + "epoch": 0.0, + "learning_rate": 3.234684344418727e-05, + "loss": 3.5567, + "step": 1078272 + }, + { + "epoch": 0.0, + "learning_rate": 3.233845749667675e-05, + "loss": 3.5624, + "step": 1078784 + }, + { + "epoch": 0.0, + "learning_rate": 3.233007154916623e-05, + "loss": 3.5435, + "step": 1079296 + }, + { + "epoch": 0.0, + "learning_rate": 3.2321701980459436e-05, + "loss": 3.5515, + "step": 1079808 + }, + { + "epoch": 0.0, + "learning_rate": 3.2313316032948916e-05, + "loss": 3.553, + "step": 1080320 + }, + { + "epoch": 0.0, + "learning_rate": 3.2304946464242125e-05, + "loss": 3.5338, + "step": 1080832 + }, + { + "epoch": 0.0, + "learning_rate": 3.2296560516731605e-05, + "loss": 3.5536, + "step": 1081344 + }, + { + "epoch": 0.0, + "learning_rate": 3.2288174569221085e-05, + "loss": 3.5433, + "step": 1081856 + }, + { + "epoch": 0.0, + "learning_rate": 3.2279788621710565e-05, + "loss": 3.5431, + "step": 1082368 + }, + { + "epoch": 0.0, + "learning_rate": 3.2271402674200045e-05, + "loss": 3.5418, + "step": 1082880 + }, + { + "epoch": 0.0, + "learning_rate": 3.2263016726689525e-05, + "loss": 3.538, + "step": 1083392 + }, + { + "epoch": 0.01, + "learning_rate": 3.2254630779179005e-05, + "loss": 3.542, + "step": 1083904 + }, + { + "epoch": 0.01, + "learning_rate": 3.2246244831668485e-05, + "loss": 3.5482, + "step": 1084416 + }, + { + "epoch": 0.01, + "learning_rate": 3.22378752629617e-05, + "loss": 3.5521, + "step": 1084928 + }, + { + "epoch": 0.01, + "learning_rate": 3.222948931545118e-05, + "loss": 3.5421, + "step": 1085440 + }, + { + "epoch": 0.01, + "learning_rate": 3.2221103367940654e-05, + "loss": 3.5437, + "step": 1085952 + }, + { + "epoch": 0.01, + "learning_rate": 3.2212717420430134e-05, + "loss": 3.5462, + "step": 1086464 + }, + { + "epoch": 0.01, + "learning_rate": 3.220434785172335e-05, + "loss": 3.561, + "step": 1086976 + }, + { + "epoch": 0.01, + "learning_rate": 3.219596190421283e-05, + "loss": 3.5378, + "step": 1087488 + }, + { + "epoch": 0.01, + "learning_rate": 3.218759233550604e-05, + "loss": 3.5422, + "step": 1088000 + }, + { + "epoch": 0.01, + "learning_rate": 3.217920638799552e-05, + "loss": 3.5433, + "step": 1088512 + }, + { + "epoch": 0.01, + "learning_rate": 3.2170820440485e-05, + "loss": 3.5378, + "step": 1089024 + }, + { + "epoch": 0.01, + "learning_rate": 3.216243449297447e-05, + "loss": 3.5442, + "step": 1089536 + }, + { + "epoch": 0.01, + "learning_rate": 3.215404854546396e-05, + "loss": 3.5509, + "step": 1090048 + }, + { + "epoch": 0.01, + "learning_rate": 3.214566259795344e-05, + "loss": 3.5564, + "step": 1090560 + }, + { + "epoch": 0.01, + "learning_rate": 3.213727665044292e-05, + "loss": 3.5435, + "step": 1091072 + }, + { + "epoch": 0.01, + "learning_rate": 3.21288907029324e-05, + "loss": 3.5434, + "step": 1091584 + }, + { + "epoch": 0.01, + "learning_rate": 3.212052113422561e-05, + "loss": 3.5424, + "step": 1092096 + }, + { + "epoch": 0.01, + "learning_rate": 3.211213518671509e-05, + "loss": 3.5516, + "step": 1092608 + }, + { + "epoch": 0.01, + "learning_rate": 3.210374923920457e-05, + "loss": 3.5234, + "step": 1093120 + }, + { + "epoch": 0.01, + "learning_rate": 3.209536329169405e-05, + "loss": 3.5497, + "step": 1093632 + }, + { + "epoch": 0.01, + "learning_rate": 3.208701010179099e-05, + "loss": 3.5448, + "step": 1094144 + }, + { + "epoch": 0.01, + "learning_rate": 3.207862415428047e-05, + "loss": 3.5514, + "step": 1094656 + }, + { + "epoch": 0.01, + "learning_rate": 3.2070238206769945e-05, + "loss": 3.5422, + "step": 1095168 + }, + { + "epoch": 0.01, + "learning_rate": 3.2061852259259425e-05, + "loss": 3.5395, + "step": 1095680 + }, + { + "epoch": 0.01, + "learning_rate": 3.205348269055264e-05, + "loss": 3.5392, + "step": 1096192 + }, + { + "epoch": 0.01, + "learning_rate": 3.204509674304213e-05, + "loss": 3.5361, + "step": 1096704 + }, + { + "epoch": 0.01, + "learning_rate": 3.20367107955316e-05, + "loss": 3.557, + "step": 1097216 + }, + { + "epoch": 0.01, + "learning_rate": 3.202832484802108e-05, + "loss": 3.5462, + "step": 1097728 + }, + { + "epoch": 0.01, + "learning_rate": 3.201993890051056e-05, + "loss": 3.5596, + "step": 1098240 + }, + { + "epoch": 0.01, + "learning_rate": 3.201155295300004e-05, + "loss": 3.5394, + "step": 1098752 + }, + { + "epoch": 0.01, + "learning_rate": 3.200316700548952e-05, + "loss": 3.5265, + "step": 1099264 + }, + { + "epoch": 0.01, + "learning_rate": 3.1994781057979e-05, + "loss": 3.5604, + "step": 1099776 + }, + { + "epoch": 0.01, + "learning_rate": 3.198641148927221e-05, + "loss": 3.5384, + "step": 1100288 + }, + { + "epoch": 0.01, + "learning_rate": 3.197802554176169e-05, + "loss": 3.5313, + "step": 1100800 + }, + { + "epoch": 0.01, + "learning_rate": 3.196963959425117e-05, + "loss": 3.5416, + "step": 1101312 + }, + { + "epoch": 0.01, + "learning_rate": 3.196125364674065e-05, + "loss": 3.5442, + "step": 1101824 + }, + { + "epoch": 0.01, + "learning_rate": 3.195286769923013e-05, + "loss": 3.5311, + "step": 1102336 + }, + { + "epoch": 0.01, + "learning_rate": 3.194448175171961e-05, + "loss": 3.5394, + "step": 1102848 + }, + { + "epoch": 0.01, + "learning_rate": 3.1936095804209096e-05, + "loss": 3.5316, + "step": 1103360 + }, + { + "epoch": 0.01, + "learning_rate": 3.1927709856698576e-05, + "loss": 3.531, + "step": 1103872 + }, + { + "epoch": 0.01, + "learning_rate": 3.1919356666795515e-05, + "loss": 3.5492, + "step": 1104384 + }, + { + "epoch": 0.01, + "learning_rate": 3.1910970719284995e-05, + "loss": 3.5471, + "step": 1104896 + }, + { + "epoch": 0.01, + "learning_rate": 3.1902584771774474e-05, + "loss": 3.5409, + "step": 1105408 + }, + { + "epoch": 0.01, + "learning_rate": 3.1894198824263954e-05, + "loss": 3.5353, + "step": 1105920 + }, + { + "epoch": 0.01, + "learning_rate": 3.1885812876753434e-05, + "loss": 3.5505, + "step": 1106432 + }, + { + "epoch": 0.01, + "learning_rate": 3.1877426929242914e-05, + "loss": 3.541, + "step": 1106944 + }, + { + "epoch": 0.01, + "learning_rate": 3.1869040981732394e-05, + "loss": 3.551, + "step": 1107456 + }, + { + "epoch": 0.01, + "learning_rate": 3.18606714130256e-05, + "loss": 3.5377, + "step": 1107968 + }, + { + "epoch": 0.01, + "learning_rate": 3.185228546551508e-05, + "loss": 3.5395, + "step": 1108480 + }, + { + "epoch": 0.01, + "learning_rate": 3.184389951800456e-05, + "loss": 3.5443, + "step": 1108992 + }, + { + "epoch": 0.01, + "learning_rate": 3.183551357049404e-05, + "loss": 3.546, + "step": 1109504 + }, + { + "epoch": 0.01, + "learning_rate": 3.182714400178726e-05, + "loss": 3.5441, + "step": 1110016 + }, + { + "epoch": 0.01, + "learning_rate": 3.181875805427674e-05, + "loss": 3.5498, + "step": 1110528 + }, + { + "epoch": 0.01, + "learning_rate": 3.181037210676622e-05, + "loss": 3.5403, + "step": 1111040 + }, + { + "epoch": 0.01, + "learning_rate": 3.18019861592557e-05, + "loss": 3.5304, + "step": 1111552 + }, + { + "epoch": 0.01, + "learning_rate": 3.179360021174518e-05, + "loss": 3.5424, + "step": 1112064 + }, + { + "epoch": 0.01, + "learning_rate": 3.178521426423466e-05, + "loss": 3.5484, + "step": 1112576 + }, + { + "epoch": 0.01, + "learning_rate": 3.177682831672413e-05, + "loss": 3.5352, + "step": 1113088 + }, + { + "epoch": 0.01, + "learning_rate": 3.176844236921361e-05, + "loss": 3.5384, + "step": 1113600 + }, + { + "epoch": 0.01, + "learning_rate": 3.176007280050683e-05, + "loss": 3.5383, + "step": 1114112 + }, + { + "epoch": 0.02, + "learning_rate": 3.175168685299631e-05, + "loss": 3.5394, + "step": 1114624 + }, + { + "epoch": 0.02, + "learning_rate": 3.174331728428952e-05, + "loss": 3.5372, + "step": 1115136 + }, + { + "epoch": 0.02, + "learning_rate": 3.1734931336779e-05, + "loss": 3.5385, + "step": 1115648 + }, + { + "epoch": 0.02, + "learning_rate": 3.1726545389268484e-05, + "loss": 3.5436, + "step": 1116160 + }, + { + "epoch": 0.02, + "learning_rate": 3.1718159441757964e-05, + "loss": 3.5452, + "step": 1116672 + }, + { + "epoch": 0.02, + "learning_rate": 3.170977349424744e-05, + "loss": 3.5545, + "step": 1117184 + }, + { + "epoch": 0.02, + "learning_rate": 3.170138754673692e-05, + "loss": 3.5158, + "step": 1117696 + }, + { + "epoch": 0.02, + "learning_rate": 3.16930015992264e-05, + "loss": 3.5377, + "step": 1118208 + }, + { + "epoch": 0.02, + "learning_rate": 3.168461565171588e-05, + "loss": 3.5331, + "step": 1118720 + }, + { + "epoch": 0.02, + "learning_rate": 3.1676246083009086e-05, + "loss": 3.5477, + "step": 1119232 + }, + { + "epoch": 0.02, + "learning_rate": 3.1667860135498566e-05, + "loss": 3.5463, + "step": 1119744 + }, + { + "epoch": 0.02, + "learning_rate": 3.1659474187988046e-05, + "loss": 3.5397, + "step": 1120256 + }, + { + "epoch": 0.02, + "learning_rate": 3.1651088240477526e-05, + "loss": 3.5302, + "step": 1120768 + }, + { + "epoch": 0.02, + "learning_rate": 3.1642718671770735e-05, + "loss": 3.5426, + "step": 1121280 + }, + { + "epoch": 0.02, + "learning_rate": 3.163433272426022e-05, + "loss": 3.5372, + "step": 1121792 + }, + { + "epoch": 0.02, + "learning_rate": 3.16259467767497e-05, + "loss": 3.5341, + "step": 1122304 + }, + { + "epoch": 0.02, + "learning_rate": 3.161756082923918e-05, + "loss": 3.5299, + "step": 1122816 + }, + { + "epoch": 0.02, + "learning_rate": 3.160919126053239e-05, + "loss": 3.5359, + "step": 1123328 + }, + { + "epoch": 0.02, + "learning_rate": 3.160080531302187e-05, + "loss": 3.5423, + "step": 1123840 + }, + { + "epoch": 0.02, + "learning_rate": 3.159241936551135e-05, + "loss": 3.5282, + "step": 1124352 + }, + { + "epoch": 0.02, + "learning_rate": 3.158404979680456e-05, + "loss": 3.5353, + "step": 1124864 + }, + { + "epoch": 0.02, + "learning_rate": 3.157566384929404e-05, + "loss": 3.5221, + "step": 1125376 + }, + { + "epoch": 0.02, + "learning_rate": 3.156727790178352e-05, + "loss": 3.5448, + "step": 1125888 + }, + { + "epoch": 0.02, + "learning_rate": 3.1558891954273e-05, + "loss": 3.5302, + "step": 1126400 + }, + { + "epoch": 0.02, + "learning_rate": 3.155050600676248e-05, + "loss": 3.5348, + "step": 1126912 + }, + { + "epoch": 0.02, + "learning_rate": 3.154212005925196e-05, + "loss": 3.5399, + "step": 1127424 + }, + { + "epoch": 0.02, + "learning_rate": 3.153373411174144e-05, + "loss": 3.5415, + "step": 1127936 + }, + { + "epoch": 0.02, + "learning_rate": 3.1525364543034655e-05, + "loss": 3.5313, + "step": 1128448 + }, + { + "epoch": 0.02, + "learning_rate": 3.1516978595524135e-05, + "loss": 3.5419, + "step": 1128960 + }, + { + "epoch": 0.02, + "learning_rate": 3.1508592648013615e-05, + "loss": 3.541, + "step": 1129472 + }, + { + "epoch": 0.02, + "learning_rate": 3.1500206700503095e-05, + "loss": 3.5247, + "step": 1129984 + }, + { + "epoch": 0.02, + "learning_rate": 3.1491820752992575e-05, + "loss": 3.5233, + "step": 1130496 + }, + { + "epoch": 0.02, + "learning_rate": 3.1483451184285784e-05, + "loss": 3.5444, + "step": 1131008 + }, + { + "epoch": 0.02, + "learning_rate": 3.1475065236775264e-05, + "loss": 3.5384, + "step": 1131520 + }, + { + "epoch": 0.02, + "learning_rate": 3.1466679289264744e-05, + "loss": 3.5373, + "step": 1132032 + }, + { + "epoch": 0.02, + "learning_rate": 3.1458293341754224e-05, + "loss": 3.5353, + "step": 1132544 + }, + { + "epoch": 0.02, + "learning_rate": 3.144992377304743e-05, + "loss": 3.5374, + "step": 1133056 + }, + { + "epoch": 0.02, + "learning_rate": 3.144153782553691e-05, + "loss": 3.5378, + "step": 1133568 + }, + { + "epoch": 0.02, + "learning_rate": 3.143315187802639e-05, + "loss": 3.5279, + "step": 1134080 + }, + { + "epoch": 0.02, + "learning_rate": 3.142476593051587e-05, + "loss": 3.527, + "step": 1134592 + }, + { + "epoch": 0.02, + "learning_rate": 3.141637998300536e-05, + "loss": 3.5428, + "step": 1135104 + }, + { + "epoch": 0.02, + "learning_rate": 3.140801041429857e-05, + "loss": 3.5497, + "step": 1135616 + }, + { + "epoch": 0.02, + "learning_rate": 3.139962446678805e-05, + "loss": 3.5301, + "step": 1136128 + }, + { + "epoch": 0.02, + "learning_rate": 3.139123851927753e-05, + "loss": 3.5314, + "step": 1136640 + }, + { + "epoch": 0.02, + "learning_rate": 3.138285257176701e-05, + "loss": 3.5429, + "step": 1137152 + }, + { + "epoch": 0.02, + "learning_rate": 3.137446662425649e-05, + "loss": 3.5326, + "step": 1137664 + }, + { + "epoch": 0.02, + "learning_rate": 3.136608067674597e-05, + "loss": 3.5345, + "step": 1138176 + }, + { + "epoch": 0.02, + "learning_rate": 3.135771110803918e-05, + "loss": 3.5354, + "step": 1138688 + }, + { + "epoch": 0.02, + "learning_rate": 3.134932516052866e-05, + "loss": 3.5475, + "step": 1139200 + }, + { + "epoch": 0.02, + "learning_rate": 3.134093921301814e-05, + "loss": 3.5417, + "step": 1139712 + }, + { + "epoch": 0.02, + "learning_rate": 3.133255326550762e-05, + "loss": 3.5374, + "step": 1140224 + }, + { + "epoch": 0.02, + "learning_rate": 3.13241673179971e-05, + "loss": 3.5298, + "step": 1140736 + }, + { + "epoch": 0.02, + "learning_rate": 3.131578137048658e-05, + "loss": 3.5393, + "step": 1141248 + }, + { + "epoch": 0.02, + "learning_rate": 3.130741180177979e-05, + "loss": 3.5379, + "step": 1141760 + }, + { + "epoch": 0.02, + "learning_rate": 3.129902585426927e-05, + "loss": 3.5255, + "step": 1142272 + }, + { + "epoch": 0.02, + "learning_rate": 3.1290639906758746e-05, + "loss": 3.5528, + "step": 1142784 + }, + { + "epoch": 0.02, + "learning_rate": 3.1282253959248226e-05, + "loss": 3.5315, + "step": 1143296 + }, + { + "epoch": 0.02, + "learning_rate": 3.1273868011737706e-05, + "loss": 3.543, + "step": 1143808 + }, + { + "epoch": 0.02, + "learning_rate": 3.1265482064227186e-05, + "loss": 3.5359, + "step": 1144320 + }, + { + "epoch": 0.03, + "eval_loss": 3.895263195037842, + "eval_runtime": 306.8242, + "eval_samples_per_second": 1243.679, + "eval_steps_per_second": 38.866, + "step": 1144790 + }, + { + "epoch": 1.0, + "learning_rate": 3.1257096116716666e-05, + "loss": 3.5382, + "step": 1144832 + }, + { + "epoch": 1.0, + "learning_rate": 3.1248726548009875e-05, + "loss": 3.5299, + "step": 1145344 + }, + { + "epoch": 1.0, + "learning_rate": 3.1240340600499355e-05, + "loss": 3.538, + "step": 1145856 + }, + { + "epoch": 1.0, + "learning_rate": 3.1231954652988835e-05, + "loss": 3.5435, + "step": 1146368 + }, + { + "epoch": 1.0, + "learning_rate": 3.1223568705478315e-05, + "loss": 3.5391, + "step": 1146880 + }, + { + "epoch": 1.0, + "learning_rate": 3.1215182757967795e-05, + "loss": 3.5365, + "step": 1147392 + }, + { + "epoch": 1.0, + "learning_rate": 3.120681318926101e-05, + "loss": 3.5341, + "step": 1147904 + }, + { + "epoch": 1.0, + "learning_rate": 3.119842724175049e-05, + "loss": 3.5316, + "step": 1148416 + }, + { + "epoch": 1.0, + "learning_rate": 3.119004129423997e-05, + "loss": 3.5312, + "step": 1148928 + }, + { + "epoch": 1.0, + "learning_rate": 3.118165534672945e-05, + "loss": 3.5358, + "step": 1149440 + }, + { + "epoch": 1.0, + "learning_rate": 3.117326939921893e-05, + "loss": 3.533, + "step": 1149952 + }, + { + "epoch": 1.0, + "learning_rate": 3.116488345170841e-05, + "loss": 3.5367, + "step": 1150464 + }, + { + "epoch": 1.0, + "learning_rate": 3.115649750419789e-05, + "loss": 3.5416, + "step": 1150976 + }, + { + "epoch": 1.0, + "learning_rate": 3.11481279354911e-05, + "loss": 3.5216, + "step": 1151488 + }, + { + "epoch": 1.0, + "learning_rate": 3.113974198798058e-05, + "loss": 3.5329, + "step": 1152000 + }, + { + "epoch": 1.0, + "learning_rate": 3.113135604047006e-05, + "loss": 3.5183, + "step": 1152512 + }, + { + "epoch": 1.0, + "learning_rate": 3.112297009295954e-05, + "loss": 3.5225, + "step": 1153024 + }, + { + "epoch": 1.0, + "learning_rate": 3.111460052425275e-05, + "loss": 3.5324, + "step": 1153536 + }, + { + "epoch": 1.0, + "learning_rate": 3.1106230955545965e-05, + "loss": 3.5229, + "step": 1154048 + }, + { + "epoch": 1.0, + "learning_rate": 3.1097845008035445e-05, + "loss": 3.5341, + "step": 1154560 + }, + { + "epoch": 1.0, + "learning_rate": 3.1089459060524924e-05, + "loss": 3.5455, + "step": 1155072 + }, + { + "epoch": 1.0, + "learning_rate": 3.1081073113014404e-05, + "loss": 3.5301, + "step": 1155584 + }, + { + "epoch": 1.0, + "learning_rate": 3.1072687165503884e-05, + "loss": 3.5348, + "step": 1156096 + }, + { + "epoch": 1.0, + "learning_rate": 3.1064301217993364e-05, + "loss": 3.5367, + "step": 1156608 + }, + { + "epoch": 1.0, + "learning_rate": 3.1055931649286573e-05, + "loss": 3.5251, + "step": 1157120 + }, + { + "epoch": 1.0, + "learning_rate": 3.1047545701776053e-05, + "loss": 3.5366, + "step": 1157632 + }, + { + "epoch": 1.0, + "learning_rate": 3.103915975426553e-05, + "loss": 3.5228, + "step": 1158144 + }, + { + "epoch": 1.0, + "learning_rate": 3.103077380675501e-05, + "loss": 3.5342, + "step": 1158656 + }, + { + "epoch": 1.0, + "learning_rate": 3.102238785924449e-05, + "loss": 3.5227, + "step": 1159168 + }, + { + "epoch": 1.0, + "learning_rate": 3.101400191173397e-05, + "loss": 3.5226, + "step": 1159680 + }, + { + "epoch": 1.01, + "learning_rate": 3.100561596422345e-05, + "loss": 3.5296, + "step": 1160192 + }, + { + "epoch": 1.01, + "learning_rate": 3.099723001671293e-05, + "loss": 3.5262, + "step": 1160704 + }, + { + "epoch": 1.01, + "learning_rate": 3.098886044800615e-05, + "loss": 3.5386, + "step": 1161216 + }, + { + "epoch": 1.01, + "learning_rate": 3.098047450049563e-05, + "loss": 3.5323, + "step": 1161728 + }, + { + "epoch": 1.01, + "learning_rate": 3.09720885529851e-05, + "loss": 3.5252, + "step": 1162240 + }, + { + "epoch": 1.01, + "learning_rate": 3.096370260547458e-05, + "loss": 3.5274, + "step": 1162752 + }, + { + "epoch": 1.01, + "learning_rate": 3.09553330367678e-05, + "loss": 3.5463, + "step": 1163264 + }, + { + "epoch": 1.01, + "learning_rate": 3.094694708925728e-05, + "loss": 3.5232, + "step": 1163776 + }, + { + "epoch": 1.01, + "learning_rate": 3.093857752055049e-05, + "loss": 3.5272, + "step": 1164288 + }, + { + "epoch": 1.01, + "learning_rate": 3.093019157303997e-05, + "loss": 3.525, + "step": 1164800 + }, + { + "epoch": 1.01, + "learning_rate": 3.092180562552945e-05, + "loss": 3.5216, + "step": 1165312 + }, + { + "epoch": 1.01, + "learning_rate": 3.091341967801893e-05, + "loss": 3.5259, + "step": 1165824 + }, + { + "epoch": 1.01, + "learning_rate": 3.090503373050841e-05, + "loss": 3.5403, + "step": 1166336 + }, + { + "epoch": 1.01, + "learning_rate": 3.089664778299789e-05, + "loss": 3.5376, + "step": 1166848 + }, + { + "epoch": 1.01, + "learning_rate": 3.08882782142911e-05, + "loss": 3.5303, + "step": 1167360 + }, + { + "epoch": 1.01, + "learning_rate": 3.0879892266780576e-05, + "loss": 3.5297, + "step": 1167872 + }, + { + "epoch": 1.01, + "learning_rate": 3.0871506319270056e-05, + "loss": 3.5236, + "step": 1168384 + }, + { + "epoch": 1.01, + "learning_rate": 3.0863120371759536e-05, + "loss": 3.5375, + "step": 1168896 + }, + { + "epoch": 1.01, + "learning_rate": 3.085475080305275e-05, + "loss": 3.5076, + "step": 1169408 + }, + { + "epoch": 1.01, + "learning_rate": 3.0846364855542225e-05, + "loss": 3.5316, + "step": 1169920 + }, + { + "epoch": 1.01, + "learning_rate": 3.0837978908031705e-05, + "loss": 3.5307, + "step": 1170432 + }, + { + "epoch": 1.01, + "learning_rate": 3.0829592960521185e-05, + "loss": 3.5374, + "step": 1170944 + }, + { + "epoch": 1.01, + "learning_rate": 3.0821207013010665e-05, + "loss": 3.5283, + "step": 1171456 + }, + { + "epoch": 1.01, + "learning_rate": 3.0812821065500145e-05, + "loss": 3.518, + "step": 1171968 + }, + { + "epoch": 1.01, + "learning_rate": 3.080445149679336e-05, + "loss": 3.53, + "step": 1172480 + }, + { + "epoch": 1.01, + "learning_rate": 3.079606554928284e-05, + "loss": 3.5153, + "step": 1172992 + }, + { + "epoch": 1.01, + "learning_rate": 3.078767960177232e-05, + "loss": 3.5458, + "step": 1173504 + }, + { + "epoch": 1.01, + "learning_rate": 3.07792936542618e-05, + "loss": 3.5288, + "step": 1174016 + }, + { + "epoch": 1.01, + "learning_rate": 3.077090770675128e-05, + "loss": 3.5469, + "step": 1174528 + }, + { + "epoch": 1.01, + "learning_rate": 3.076252175924076e-05, + "loss": 3.5224, + "step": 1175040 + }, + { + "epoch": 1.01, + "learning_rate": 3.075413581173024e-05, + "loss": 3.5145, + "step": 1175552 + }, + { + "epoch": 1.01, + "learning_rate": 3.074574986421972e-05, + "loss": 3.5374, + "step": 1176064 + }, + { + "epoch": 1.01, + "learning_rate": 3.073738029551293e-05, + "loss": 3.5223, + "step": 1176576 + }, + { + "epoch": 1.01, + "learning_rate": 3.072899434800241e-05, + "loss": 3.5221, + "step": 1177088 + }, + { + "epoch": 1.01, + "learning_rate": 3.072060840049189e-05, + "loss": 3.5218, + "step": 1177600 + }, + { + "epoch": 1.01, + "learning_rate": 3.071222245298137e-05, + "loss": 3.5321, + "step": 1178112 + }, + { + "epoch": 1.01, + "learning_rate": 3.070383650547085e-05, + "loss": 3.5159, + "step": 1178624 + }, + { + "epoch": 1.01, + "learning_rate": 3.069546693676406e-05, + "loss": 3.5221, + "step": 1179136 + }, + { + "epoch": 1.01, + "learning_rate": 3.0687080989253545e-05, + "loss": 3.5164, + "step": 1179648 + }, + { + "epoch": 1.01, + "learning_rate": 3.0678695041743025e-05, + "loss": 3.5157, + "step": 1180160 + }, + { + "epoch": 1.01, + "learning_rate": 3.0670309094232505e-05, + "loss": 3.5354, + "step": 1180672 + }, + { + "epoch": 1.01, + "learning_rate": 3.0661923146721985e-05, + "loss": 3.531, + "step": 1181184 + }, + { + "epoch": 1.01, + "learning_rate": 3.0653537199211465e-05, + "loss": 3.523, + "step": 1181696 + }, + { + "epoch": 1.01, + "learning_rate": 3.0645167630504674e-05, + "loss": 3.5224, + "step": 1182208 + }, + { + "epoch": 1.01, + "learning_rate": 3.0636781682994154e-05, + "loss": 3.5338, + "step": 1182720 + }, + { + "epoch": 1.01, + "learning_rate": 3.0628395735483634e-05, + "loss": 3.5246, + "step": 1183232 + }, + { + "epoch": 1.01, + "learning_rate": 3.0620009787973114e-05, + "loss": 3.5313, + "step": 1183744 + }, + { + "epoch": 1.01, + "learning_rate": 3.061164021926632e-05, + "loss": 3.5255, + "step": 1184256 + }, + { + "epoch": 1.01, + "learning_rate": 3.06032542717558e-05, + "loss": 3.5228, + "step": 1184768 + }, + { + "epoch": 1.01, + "learning_rate": 3.059486832424528e-05, + "loss": 3.5308, + "step": 1185280 + }, + { + "epoch": 1.01, + "learning_rate": 3.058648237673476e-05, + "loss": 3.5313, + "step": 1185792 + }, + { + "epoch": 1.01, + "learning_rate": 3.057811280802798e-05, + "loss": 3.5293, + "step": 1186304 + }, + { + "epoch": 1.01, + "learning_rate": 3.056972686051746e-05, + "loss": 3.5346, + "step": 1186816 + }, + { + "epoch": 1.01, + "learning_rate": 3.056134091300694e-05, + "loss": 3.5283, + "step": 1187328 + }, + { + "epoch": 1.01, + "learning_rate": 3.055295496549641e-05, + "loss": 3.5077, + "step": 1187840 + }, + { + "epoch": 1.01, + "learning_rate": 3.054456901798589e-05, + "loss": 3.5286, + "step": 1188352 + }, + { + "epoch": 1.01, + "learning_rate": 3.053619944927911e-05, + "loss": 3.5298, + "step": 1188864 + }, + { + "epoch": 1.01, + "learning_rate": 3.052781350176859e-05, + "loss": 3.5241, + "step": 1189376 + }, + { + "epoch": 1.01, + "learning_rate": 3.051942755425806e-05, + "loss": 3.5207, + "step": 1189888 + }, + { + "epoch": 1.01, + "learning_rate": 3.0511041606747544e-05, + "loss": 3.5227, + "step": 1190400 + }, + { + "epoch": 1.02, + "learning_rate": 3.0502655659237024e-05, + "loss": 3.5241, + "step": 1190912 + }, + { + "epoch": 1.02, + "learning_rate": 3.0494286090530233e-05, + "loss": 3.5196, + "step": 1191424 + }, + { + "epoch": 1.02, + "learning_rate": 3.0485900143019713e-05, + "loss": 3.5242, + "step": 1191936 + }, + { + "epoch": 1.02, + "learning_rate": 3.0477514195509193e-05, + "loss": 3.5253, + "step": 1192448 + }, + { + "epoch": 1.02, + "learning_rate": 3.0469128247998673e-05, + "loss": 3.5273, + "step": 1192960 + }, + { + "epoch": 1.02, + "learning_rate": 3.0460742300488153e-05, + "loss": 3.5412, + "step": 1193472 + }, + { + "epoch": 1.02, + "learning_rate": 3.0452372731781365e-05, + "loss": 3.5053, + "step": 1193984 + }, + { + "epoch": 1.02, + "learning_rate": 3.0443986784270845e-05, + "loss": 3.5197, + "step": 1194496 + }, + { + "epoch": 1.02, + "learning_rate": 3.0435600836760325e-05, + "loss": 3.5199, + "step": 1195008 + }, + { + "epoch": 1.02, + "learning_rate": 3.0427214889249805e-05, + "loss": 3.5305, + "step": 1195520 + }, + { + "epoch": 1.02, + "learning_rate": 3.0418828941739285e-05, + "loss": 3.5315, + "step": 1196032 + }, + { + "epoch": 1.02, + "learning_rate": 3.0410442994228765e-05, + "loss": 3.5257, + "step": 1196544 + }, + { + "epoch": 1.02, + "learning_rate": 3.0402057046718245e-05, + "loss": 3.514, + "step": 1197056 + }, + { + "epoch": 1.02, + "learning_rate": 3.0393671099207725e-05, + "loss": 3.5231, + "step": 1197568 + }, + { + "epoch": 1.02, + "learning_rate": 3.0385301530500938e-05, + "loss": 3.5271, + "step": 1198080 + }, + { + "epoch": 1.02, + "learning_rate": 3.0376915582990417e-05, + "loss": 3.517, + "step": 1198592 + }, + { + "epoch": 1.02, + "learning_rate": 3.0368529635479897e-05, + "loss": 3.5144, + "step": 1199104 + }, + { + "epoch": 1.02, + "learning_rate": 3.0360143687969377e-05, + "loss": 3.5227, + "step": 1199616 + }, + { + "epoch": 1.02, + "learning_rate": 3.035177411926259e-05, + "loss": 3.5276, + "step": 1200128 + }, + { + "epoch": 1.02, + "learning_rate": 3.03434045505558e-05, + "loss": 3.5102, + "step": 1200640 + }, + { + "epoch": 1.02, + "learning_rate": 3.033501860304528e-05, + "loss": 3.5224, + "step": 1201152 + }, + { + "epoch": 1.02, + "learning_rate": 3.032663265553476e-05, + "loss": 3.5067, + "step": 1201664 + }, + { + "epoch": 1.02, + "learning_rate": 3.031824670802424e-05, + "loss": 3.5282, + "step": 1202176 + }, + { + "epoch": 1.02, + "learning_rate": 3.030986076051372e-05, + "loss": 3.5183, + "step": 1202688 + }, + { + "epoch": 1.02, + "learning_rate": 3.03014748130032e-05, + "loss": 3.5191, + "step": 1203200 + }, + { + "epoch": 1.02, + "learning_rate": 3.029308886549268e-05, + "loss": 3.5238, + "step": 1203712 + }, + { + "epoch": 1.02, + "learning_rate": 3.0284702917982162e-05, + "loss": 3.5231, + "step": 1204224 + }, + { + "epoch": 1.02, + "learning_rate": 3.027633334927537e-05, + "loss": 3.52, + "step": 1204736 + }, + { + "epoch": 1.02, + "learning_rate": 3.026794740176485e-05, + "loss": 3.5248, + "step": 1205248 + }, + { + "epoch": 1.02, + "learning_rate": 3.025956145425433e-05, + "loss": 3.5267, + "step": 1205760 + }, + { + "epoch": 1.02, + "learning_rate": 3.025117550674381e-05, + "loss": 3.5108, + "step": 1206272 + }, + { + "epoch": 1.02, + "learning_rate": 3.024278955923329e-05, + "loss": 3.5109, + "step": 1206784 + }, + { + "epoch": 1.02, + "learning_rate": 3.0234419990526503e-05, + "loss": 3.5277, + "step": 1207296 + }, + { + "epoch": 1.02, + "learning_rate": 3.0226034043015983e-05, + "loss": 3.5219, + "step": 1207808 + }, + { + "epoch": 1.02, + "learning_rate": 3.0217648095505463e-05, + "loss": 3.524, + "step": 1208320 + }, + { + "epoch": 1.02, + "learning_rate": 3.0209262147994943e-05, + "loss": 3.5164, + "step": 1208832 + }, + { + "epoch": 1.02, + "learning_rate": 3.0200892579288152e-05, + "loss": 3.5244, + "step": 1209344 + }, + { + "epoch": 1.02, + "learning_rate": 3.0192506631777632e-05, + "loss": 3.5232, + "step": 1209856 + }, + { + "epoch": 1.02, + "learning_rate": 3.0184120684267116e-05, + "loss": 3.514, + "step": 1210368 + }, + { + "epoch": 1.02, + "learning_rate": 3.0175734736756596e-05, + "loss": 3.5088, + "step": 1210880 + }, + { + "epoch": 1.02, + "learning_rate": 3.016734878924607e-05, + "loss": 3.528, + "step": 1211392 + }, + { + "epoch": 1.02, + "learning_rate": 3.0158979220539285e-05, + "loss": 3.5349, + "step": 1211904 + }, + { + "epoch": 1.02, + "learning_rate": 3.0150593273028765e-05, + "loss": 3.5187, + "step": 1212416 + }, + { + "epoch": 1.02, + "learning_rate": 3.0142207325518245e-05, + "loss": 3.5149, + "step": 1212928 + }, + { + "epoch": 1.02, + "learning_rate": 3.013382137800772e-05, + "loss": 3.5248, + "step": 1213440 + }, + { + "epoch": 1.02, + "learning_rate": 3.01254354304972e-05, + "loss": 3.519, + "step": 1213952 + }, + { + "epoch": 1.02, + "learning_rate": 3.011704948298668e-05, + "loss": 3.5188, + "step": 1214464 + }, + { + "epoch": 1.02, + "learning_rate": 3.0108679914279897e-05, + "loss": 3.5227, + "step": 1214976 + }, + { + "epoch": 1.02, + "learning_rate": 3.010029396676937e-05, + "loss": 3.5327, + "step": 1215488 + }, + { + "epoch": 1.02, + "learning_rate": 3.0091908019258853e-05, + "loss": 3.5255, + "step": 1216000 + }, + { + "epoch": 1.02, + "learning_rate": 3.0083522071748333e-05, + "loss": 3.5226, + "step": 1216512 + }, + { + "epoch": 1.02, + "learning_rate": 3.0075136124237813e-05, + "loss": 3.5157, + "step": 1217024 + }, + { + "epoch": 1.02, + "learning_rate": 3.0066750176727293e-05, + "loss": 3.5244, + "step": 1217536 + }, + { + "epoch": 1.02, + "learning_rate": 3.0058380608020502e-05, + "loss": 3.5229, + "step": 1218048 + }, + { + "epoch": 1.02, + "learning_rate": 3.0049994660509982e-05, + "loss": 3.5096, + "step": 1218560 + }, + { + "epoch": 1.02, + "learning_rate": 3.0041608712999462e-05, + "loss": 3.5394, + "step": 1219072 + }, + { + "epoch": 1.02, + "learning_rate": 3.0033222765488946e-05, + "loss": 3.5164, + "step": 1219584 + }, + { + "epoch": 1.02, + "learning_rate": 3.0024836817978426e-05, + "loss": 3.5278, + "step": 1220096 + }, + { + "epoch": 1.02, + "learning_rate": 3.0016450870467906e-05, + "loss": 3.5224, + "step": 1220608 + }, + { + "epoch": 1.03, + "eval_loss": 3.897325277328491, + "eval_runtime": 303.4997, + "eval_samples_per_second": 1257.303, + "eval_steps_per_second": 39.292, + "step": 1221110 + }, + { + "epoch": 0.0, + "learning_rate": 3.0008064922957386e-05, + "loss": 3.472, + "step": 1221120 + }, + { + "epoch": 0.0, + "learning_rate": 2.9999695354250595e-05, + "loss": 3.5179, + "step": 1221632 + }, + { + "epoch": 0.0, + "learning_rate": 2.9991309406740075e-05, + "loss": 3.521, + "step": 1222144 + }, + { + "epoch": 0.0, + "learning_rate": 2.9982923459229555e-05, + "loss": 3.5311, + "step": 1222656 + }, + { + "epoch": 0.0, + "learning_rate": 2.9974537511719038e-05, + "loss": 3.5241, + "step": 1223168 + }, + { + "epoch": 0.0, + "learning_rate": 2.9966167943012247e-05, + "loss": 3.5252, + "step": 1223680 + }, + { + "epoch": 0.0, + "learning_rate": 2.9957781995501727e-05, + "loss": 3.5186, + "step": 1224192 + }, + { + "epoch": 0.0, + "learning_rate": 2.9949396047991207e-05, + "loss": 3.5174, + "step": 1224704 + }, + { + "epoch": 0.0, + "learning_rate": 2.9941010100480687e-05, + "loss": 3.5125, + "step": 1225216 + }, + { + "epoch": 0.0, + "learning_rate": 2.9932624152970167e-05, + "loss": 3.5227, + "step": 1225728 + }, + { + "epoch": 0.0, + "learning_rate": 2.9924238205459647e-05, + "loss": 3.5167, + "step": 1226240 + }, + { + "epoch": 0.0, + "learning_rate": 2.991585225794913e-05, + "loss": 3.5232, + "step": 1226752 + }, + { + "epoch": 0.0, + "learning_rate": 2.990746631043861e-05, + "loss": 3.5262, + "step": 1227264 + }, + { + "epoch": 0.0, + "learning_rate": 2.989909674173182e-05, + "loss": 3.5083, + "step": 1227776 + }, + { + "epoch": 0.0, + "learning_rate": 2.98907107942213e-05, + "loss": 3.5136, + "step": 1228288 + }, + { + "epoch": 0.0, + "learning_rate": 2.9882341225514508e-05, + "loss": 3.5063, + "step": 1228800 + }, + { + "epoch": 0.0, + "learning_rate": 2.987395527800399e-05, + "loss": 3.5061, + "step": 1229312 + }, + { + "epoch": 0.0, + "learning_rate": 2.986556933049347e-05, + "loss": 3.5165, + "step": 1229824 + }, + { + "epoch": 0.0, + "learning_rate": 2.985718338298295e-05, + "loss": 3.5132, + "step": 1230336 + }, + { + "epoch": 0.0, + "learning_rate": 2.984881381427616e-05, + "loss": 3.5159, + "step": 1230848 + }, + { + "epoch": 0.0, + "learning_rate": 2.984042786676564e-05, + "loss": 3.5331, + "step": 1231360 + }, + { + "epoch": 0.0, + "learning_rate": 2.983204191925512e-05, + "loss": 3.5166, + "step": 1231872 + }, + { + "epoch": 0.0, + "learning_rate": 2.98236559717446e-05, + "loss": 3.5204, + "step": 1232384 + }, + { + "epoch": 0.0, + "learning_rate": 2.981527002423408e-05, + "loss": 3.5159, + "step": 1232896 + }, + { + "epoch": 0.0, + "learning_rate": 2.9806900455527293e-05, + "loss": 3.5161, + "step": 1233408 + }, + { + "epoch": 0.0, + "learning_rate": 2.9798514508016773e-05, + "loss": 3.5191, + "step": 1233920 + }, + { + "epoch": 0.0, + "learning_rate": 2.9790128560506253e-05, + "loss": 3.5076, + "step": 1234432 + }, + { + "epoch": 0.0, + "learning_rate": 2.978174261299573e-05, + "loss": 3.5163, + "step": 1234944 + }, + { + "epoch": 0.0, + "learning_rate": 2.977335666548521e-05, + "loss": 3.5107, + "step": 1235456 + }, + { + "epoch": 0.0, + "learning_rate": 2.976497071797469e-05, + "loss": 3.5053, + "step": 1235968 + }, + { + "epoch": 0.01, + "learning_rate": 2.975658477046417e-05, + "loss": 3.5168, + "step": 1236480 + }, + { + "epoch": 0.01, + "learning_rate": 2.974819882295365e-05, + "loss": 3.5114, + "step": 1236992 + }, + { + "epoch": 0.01, + "learning_rate": 2.973982925424686e-05, + "loss": 3.5186, + "step": 1237504 + }, + { + "epoch": 0.01, + "learning_rate": 2.9731443306736338e-05, + "loss": 3.5189, + "step": 1238016 + }, + { + "epoch": 0.01, + "learning_rate": 2.9723057359225818e-05, + "loss": 3.51, + "step": 1238528 + }, + { + "epoch": 0.01, + "learning_rate": 2.97146714117153e-05, + "loss": 3.5133, + "step": 1239040 + }, + { + "epoch": 0.01, + "learning_rate": 2.970630184300851e-05, + "loss": 3.5292, + "step": 1239552 + }, + { + "epoch": 0.01, + "learning_rate": 2.969791589549799e-05, + "loss": 3.5062, + "step": 1240064 + }, + { + "epoch": 0.01, + "learning_rate": 2.96895463267912e-05, + "loss": 3.5126, + "step": 1240576 + }, + { + "epoch": 0.01, + "learning_rate": 2.9681160379280683e-05, + "loss": 3.5132, + "step": 1241088 + }, + { + "epoch": 0.01, + "learning_rate": 2.9672774431770163e-05, + "loss": 3.5023, + "step": 1241600 + }, + { + "epoch": 0.01, + "learning_rate": 2.9664388484259643e-05, + "loss": 3.5129, + "step": 1242112 + }, + { + "epoch": 0.01, + "learning_rate": 2.9656002536749123e-05, + "loss": 3.5288, + "step": 1242624 + }, + { + "epoch": 0.01, + "learning_rate": 2.9647616589238603e-05, + "loss": 3.5224, + "step": 1243136 + }, + { + "epoch": 0.01, + "learning_rate": 2.9639230641728083e-05, + "loss": 3.5101, + "step": 1243648 + }, + { + "epoch": 0.01, + "learning_rate": 2.9630844694217563e-05, + "loss": 3.5204, + "step": 1244160 + }, + { + "epoch": 0.01, + "learning_rate": 2.9622475125510772e-05, + "loss": 3.5094, + "step": 1244672 + }, + { + "epoch": 0.01, + "learning_rate": 2.9614089178000255e-05, + "loss": 3.5192, + "step": 1245184 + }, + { + "epoch": 0.01, + "learning_rate": 2.9605719609293464e-05, + "loss": 3.4932, + "step": 1245696 + }, + { + "epoch": 0.01, + "learning_rate": 2.9597333661782944e-05, + "loss": 3.5152, + "step": 1246208 + }, + { + "epoch": 0.01, + "learning_rate": 2.9588947714272424e-05, + "loss": 3.5225, + "step": 1246720 + }, + { + "epoch": 0.01, + "learning_rate": 2.9580561766761904e-05, + "loss": 3.5166, + "step": 1247232 + }, + { + "epoch": 0.01, + "learning_rate": 2.9572175819251384e-05, + "loss": 3.5165, + "step": 1247744 + }, + { + "epoch": 0.01, + "learning_rate": 2.9563789871740864e-05, + "loss": 3.5026, + "step": 1248256 + }, + { + "epoch": 0.01, + "learning_rate": 2.9555420303034077e-05, + "loss": 3.5161, + "step": 1248768 + }, + { + "epoch": 0.01, + "learning_rate": 2.9547034355523557e-05, + "loss": 3.4987, + "step": 1249280 + }, + { + "epoch": 0.01, + "learning_rate": 2.9538648408013037e-05, + "loss": 3.534, + "step": 1249792 + }, + { + "epoch": 0.01, + "learning_rate": 2.9530262460502516e-05, + "loss": 3.5139, + "step": 1250304 + }, + { + "epoch": 0.01, + "learning_rate": 2.9521876512991996e-05, + "loss": 3.5292, + "step": 1250816 + }, + { + "epoch": 0.01, + "learning_rate": 2.951350694428521e-05, + "loss": 3.5076, + "step": 1251328 + }, + { + "epoch": 0.01, + "learning_rate": 2.950512099677469e-05, + "loss": 3.5043, + "step": 1251840 + }, + { + "epoch": 0.01, + "learning_rate": 2.949673504926417e-05, + "loss": 3.5172, + "step": 1252352 + }, + { + "epoch": 0.01, + "learning_rate": 2.948834910175365e-05, + "loss": 3.5083, + "step": 1252864 + }, + { + "epoch": 0.01, + "learning_rate": 2.947996315424313e-05, + "loss": 3.509, + "step": 1253376 + }, + { + "epoch": 0.01, + "learning_rate": 2.947157720673261e-05, + "loss": 3.5069, + "step": 1253888 + }, + { + "epoch": 0.01, + "learning_rate": 2.9463207638025818e-05, + "loss": 3.515, + "step": 1254400 + }, + { + "epoch": 0.01, + "learning_rate": 2.94548216905153e-05, + "loss": 3.5026, + "step": 1254912 + }, + { + "epoch": 0.01, + "learning_rate": 2.944643574300478e-05, + "loss": 3.5086, + "step": 1255424 + }, + { + "epoch": 0.01, + "learning_rate": 2.943804979549426e-05, + "loss": 3.498, + "step": 1255936 + }, + { + "epoch": 0.01, + "learning_rate": 2.942966384798374e-05, + "loss": 3.5002, + "step": 1256448 + }, + { + "epoch": 0.01, + "learning_rate": 2.942129427927695e-05, + "loss": 3.5181, + "step": 1256960 + }, + { + "epoch": 0.01, + "learning_rate": 2.941290833176643e-05, + "loss": 3.5196, + "step": 1257472 + }, + { + "epoch": 0.01, + "learning_rate": 2.940452238425591e-05, + "loss": 3.5082, + "step": 1257984 + }, + { + "epoch": 0.01, + "learning_rate": 2.9396136436745387e-05, + "loss": 3.5087, + "step": 1258496 + }, + { + "epoch": 0.01, + "learning_rate": 2.9387750489234867e-05, + "loss": 3.5151, + "step": 1259008 + }, + { + "epoch": 0.01, + "learning_rate": 2.9379364541724346e-05, + "loss": 3.5142, + "step": 1259520 + }, + { + "epoch": 0.01, + "learning_rate": 2.9370978594213826e-05, + "loss": 3.5123, + "step": 1260032 + }, + { + "epoch": 0.01, + "learning_rate": 2.936260902550704e-05, + "loss": 3.5156, + "step": 1260544 + }, + { + "epoch": 0.01, + "learning_rate": 2.935422307799652e-05, + "loss": 3.5088, + "step": 1261056 + }, + { + "epoch": 0.01, + "learning_rate": 2.9345837130486e-05, + "loss": 3.5153, + "step": 1261568 + }, + { + "epoch": 0.01, + "learning_rate": 2.933745118297548e-05, + "loss": 3.5172, + "step": 1262080 + }, + { + "epoch": 0.01, + "learning_rate": 2.9329081614268688e-05, + "loss": 3.517, + "step": 1262592 + }, + { + "epoch": 0.01, + "learning_rate": 2.9320695666758168e-05, + "loss": 3.5199, + "step": 1263104 + }, + { + "epoch": 0.01, + "learning_rate": 2.9312309719247648e-05, + "loss": 3.5128, + "step": 1263616 + }, + { + "epoch": 0.01, + "learning_rate": 2.930392377173713e-05, + "loss": 3.4941, + "step": 1264128 + }, + { + "epoch": 0.01, + "learning_rate": 2.929553782422661e-05, + "loss": 3.5151, + "step": 1264640 + }, + { + "epoch": 0.01, + "learning_rate": 2.928716825551982e-05, + "loss": 3.5137, + "step": 1265152 + }, + { + "epoch": 0.01, + "learning_rate": 2.92787823080093e-05, + "loss": 3.5108, + "step": 1265664 + }, + { + "epoch": 0.01, + "learning_rate": 2.927039636049878e-05, + "loss": 3.5102, + "step": 1266176 + }, + { + "epoch": 0.01, + "learning_rate": 2.926201041298826e-05, + "loss": 3.5057, + "step": 1266688 + }, + { + "epoch": 0.02, + "learning_rate": 2.925362446547774e-05, + "loss": 3.5175, + "step": 1267200 + }, + { + "epoch": 0.02, + "learning_rate": 2.9245254896770952e-05, + "loss": 3.5053, + "step": 1267712 + }, + { + "epoch": 0.02, + "learning_rate": 2.9236868949260432e-05, + "loss": 3.5078, + "step": 1268224 + }, + { + "epoch": 0.02, + "learning_rate": 2.9228483001749912e-05, + "loss": 3.5096, + "step": 1268736 + }, + { + "epoch": 0.02, + "learning_rate": 2.9220097054239392e-05, + "loss": 3.5102, + "step": 1269248 + }, + { + "epoch": 0.02, + "learning_rate": 2.9211711106728872e-05, + "loss": 3.5258, + "step": 1269760 + }, + { + "epoch": 0.02, + "learning_rate": 2.9203325159218352e-05, + "loss": 3.4979, + "step": 1270272 + }, + { + "epoch": 0.02, + "learning_rate": 2.9194955590511565e-05, + "loss": 3.4995, + "step": 1270784 + }, + { + "epoch": 0.02, + "learning_rate": 2.9186569643001045e-05, + "loss": 3.5084, + "step": 1271296 + }, + { + "epoch": 0.02, + "learning_rate": 2.9178183695490525e-05, + "loss": 3.5141, + "step": 1271808 + }, + { + "epoch": 0.02, + "learning_rate": 2.9169797747980005e-05, + "loss": 3.5166, + "step": 1272320 + }, + { + "epoch": 0.02, + "learning_rate": 2.9161411800469485e-05, + "loss": 3.5118, + "step": 1272832 + }, + { + "epoch": 0.02, + "learning_rate": 2.9153025852958965e-05, + "loss": 3.4993, + "step": 1273344 + }, + { + "epoch": 0.02, + "learning_rate": 2.9144639905448444e-05, + "loss": 3.5085, + "step": 1273856 + }, + { + "epoch": 0.02, + "learning_rate": 2.9136270336741657e-05, + "loss": 3.5143, + "step": 1274368 + }, + { + "epoch": 0.02, + "learning_rate": 2.9127884389231137e-05, + "loss": 3.4989, + "step": 1274880 + }, + { + "epoch": 0.02, + "learning_rate": 2.9119498441720617e-05, + "loss": 3.4983, + "step": 1275392 + }, + { + "epoch": 0.02, + "learning_rate": 2.9111112494210097e-05, + "loss": 3.5115, + "step": 1275904 + }, + { + "epoch": 0.02, + "learning_rate": 2.9102742925503306e-05, + "loss": 3.5155, + "step": 1276416 + }, + { + "epoch": 0.02, + "learning_rate": 2.909437335679652e-05, + "loss": 3.4964, + "step": 1276928 + }, + { + "epoch": 0.02, + "learning_rate": 2.9085987409286e-05, + "loss": 3.5019, + "step": 1277440 + }, + { + "epoch": 0.02, + "learning_rate": 2.907760146177548e-05, + "loss": 3.4966, + "step": 1277952 + }, + { + "epoch": 0.02, + "learning_rate": 2.9069215514264958e-05, + "loss": 3.5135, + "step": 1278464 + }, + { + "epoch": 0.02, + "learning_rate": 2.9060829566754438e-05, + "loss": 3.5036, + "step": 1278976 + }, + { + "epoch": 0.02, + "learning_rate": 2.9052443619243918e-05, + "loss": 3.5028, + "step": 1279488 + }, + { + "epoch": 0.02, + "learning_rate": 2.9044057671733398e-05, + "loss": 3.5117, + "step": 1280000 + }, + { + "epoch": 0.02, + "learning_rate": 2.9035671724222875e-05, + "loss": 3.5117, + "step": 1280512 + }, + { + "epoch": 0.02, + "learning_rate": 2.902730215551609e-05, + "loss": 3.5019, + "step": 1281024 + }, + { + "epoch": 0.02, + "learning_rate": 2.901891620800557e-05, + "loss": 3.513, + "step": 1281536 + }, + { + "epoch": 0.02, + "learning_rate": 2.901053026049505e-05, + "loss": 3.5102, + "step": 1282048 + }, + { + "epoch": 0.02, + "learning_rate": 2.9002144312984524e-05, + "loss": 3.5029, + "step": 1282560 + }, + { + "epoch": 0.02, + "learning_rate": 2.8993758365474004e-05, + "loss": 3.4908, + "step": 1283072 + }, + { + "epoch": 0.02, + "learning_rate": 2.898538879676722e-05, + "loss": 3.5102, + "step": 1283584 + }, + { + "epoch": 0.02, + "learning_rate": 2.8977002849256696e-05, + "loss": 3.5068, + "step": 1284096 + }, + { + "epoch": 0.02, + "learning_rate": 2.8968616901746176e-05, + "loss": 3.5116, + "step": 1284608 + }, + { + "epoch": 0.02, + "learning_rate": 2.8960230954235656e-05, + "loss": 3.5013, + "step": 1285120 + }, + { + "epoch": 0.02, + "learning_rate": 2.8951861385528872e-05, + "loss": 3.5114, + "step": 1285632 + }, + { + "epoch": 0.02, + "learning_rate": 2.894347543801835e-05, + "loss": 3.5064, + "step": 1286144 + }, + { + "epoch": 0.02, + "learning_rate": 2.893508949050783e-05, + "loss": 3.4999, + "step": 1286656 + }, + { + "epoch": 0.02, + "learning_rate": 2.892670354299731e-05, + "loss": 3.4935, + "step": 1287168 + }, + { + "epoch": 0.02, + "learning_rate": 2.8918317595486788e-05, + "loss": 3.5147, + "step": 1287680 + }, + { + "epoch": 0.02, + "learning_rate": 2.8909948026779997e-05, + "loss": 3.5197, + "step": 1288192 + }, + { + "epoch": 0.02, + "learning_rate": 2.8901562079269477e-05, + "loss": 3.5066, + "step": 1288704 + }, + { + "epoch": 0.02, + "learning_rate": 2.8893176131758957e-05, + "loss": 3.4956, + "step": 1289216 + }, + { + "epoch": 0.02, + "learning_rate": 2.888479018424844e-05, + "loss": 3.5134, + "step": 1289728 + }, + { + "epoch": 0.02, + "learning_rate": 2.887640423673792e-05, + "loss": 3.5031, + "step": 1290240 + }, + { + "epoch": 0.02, + "learning_rate": 2.88680182892274e-05, + "loss": 3.5068, + "step": 1290752 + }, + { + "epoch": 0.02, + "learning_rate": 2.885964872052061e-05, + "loss": 3.5074, + "step": 1291264 + }, + { + "epoch": 0.02, + "learning_rate": 2.885126277301009e-05, + "loss": 3.5155, + "step": 1291776 + }, + { + "epoch": 0.02, + "learning_rate": 2.884287682549957e-05, + "loss": 3.5072, + "step": 1292288 + }, + { + "epoch": 0.02, + "learning_rate": 2.883449087798905e-05, + "loss": 3.5115, + "step": 1292800 + }, + { + "epoch": 0.02, + "learning_rate": 2.8826104930478533e-05, + "loss": 3.5021, + "step": 1293312 + }, + { + "epoch": 0.02, + "learning_rate": 2.8817718982968013e-05, + "loss": 3.5089, + "step": 1293824 + }, + { + "epoch": 0.02, + "learning_rate": 2.8809333035457493e-05, + "loss": 3.5083, + "step": 1294336 + }, + { + "epoch": 0.02, + "learning_rate": 2.8800963466750702e-05, + "loss": 3.4983, + "step": 1294848 + }, + { + "epoch": 0.02, + "learning_rate": 2.8792577519240182e-05, + "loss": 3.5264, + "step": 1295360 + }, + { + "epoch": 0.02, + "learning_rate": 2.8784191571729662e-05, + "loss": 3.504, + "step": 1295872 + }, + { + "epoch": 0.02, + "learning_rate": 2.8775805624219142e-05, + "loss": 3.5108, + "step": 1296384 + }, + { + "epoch": 0.02, + "learning_rate": 2.8767419676708625e-05, + "loss": 3.5083, + "step": 1296896 + }, + { + "epoch": 0.02, + "learning_rate": 2.8759033729198105e-05, + "loss": 3.5034, + "step": 1297408 + }, + { + "epoch": 0.03, + "eval_loss": 3.898564338684082, + "eval_runtime": 305.374, + "eval_samples_per_second": 1249.586, + "eval_steps_per_second": 39.05, + "step": 1297430 + }, + { + "epoch": 0.0, + "learning_rate": 2.8750664160491314e-05, + "loss": 3.5009, + "step": 1297920 + }, + { + "epoch": 0.0, + "learning_rate": 2.8742278212980794e-05, + "loss": 3.5077, + "step": 1298432 + }, + { + "epoch": 0.0, + "learning_rate": 2.8733892265470274e-05, + "loss": 3.5149, + "step": 1298944 + }, + { + "epoch": 0.0, + "learning_rate": 2.8725506317959754e-05, + "loss": 3.5042, + "step": 1299456 + }, + { + "epoch": 0.0, + "learning_rate": 2.8717120370449234e-05, + "loss": 3.5136, + "step": 1299968 + }, + { + "epoch": 0.0, + "learning_rate": 2.8708750801742446e-05, + "loss": 3.5015, + "step": 1300480 + }, + { + "epoch": 0.0, + "learning_rate": 2.8700364854231926e-05, + "loss": 3.5024, + "step": 1300992 + }, + { + "epoch": 0.0, + "learning_rate": 2.8691978906721406e-05, + "loss": 3.4981, + "step": 1301504 + }, + { + "epoch": 0.0, + "learning_rate": 2.868359295921088e-05, + "loss": 3.5118, + "step": 1302016 + }, + { + "epoch": 0.0, + "learning_rate": 2.8675207011700363e-05, + "loss": 3.4993, + "step": 1302528 + }, + { + "epoch": 0.0, + "learning_rate": 2.8666821064189843e-05, + "loss": 3.5125, + "step": 1303040 + }, + { + "epoch": 0.0, + "learning_rate": 2.8658435116679323e-05, + "loss": 3.5107, + "step": 1303552 + }, + { + "epoch": 0.0, + "learning_rate": 2.8650049169168803e-05, + "loss": 3.4977, + "step": 1304064 + }, + { + "epoch": 0.0, + "learning_rate": 2.8641679600462012e-05, + "loss": 3.4991, + "step": 1304576 + }, + { + "epoch": 0.0, + "learning_rate": 2.8633293652951492e-05, + "loss": 3.4901, + "step": 1305088 + }, + { + "epoch": 0.0, + "learning_rate": 2.8624907705440972e-05, + "loss": 3.4977, + "step": 1305600 + }, + { + "epoch": 0.0, + "learning_rate": 2.8616521757930455e-05, + "loss": 3.499, + "step": 1306112 + }, + { + "epoch": 0.0, + "learning_rate": 2.86081685680274e-05, + "loss": 3.4992, + "step": 1306624 + }, + { + "epoch": 0.0, + "learning_rate": 2.859978262051688e-05, + "loss": 3.5011, + "step": 1307136 + }, + { + "epoch": 0.0, + "learning_rate": 2.8591396673006353e-05, + "loss": 3.5197, + "step": 1307648 + }, + { + "epoch": 0.0, + "learning_rate": 2.8583010725495833e-05, + "loss": 3.4984, + "step": 1308160 + }, + { + "epoch": 0.0, + "learning_rate": 2.8574624777985317e-05, + "loss": 3.5054, + "step": 1308672 + }, + { + "epoch": 0.0, + "learning_rate": 2.8566238830474796e-05, + "loss": 3.5041, + "step": 1309184 + }, + { + "epoch": 0.0, + "learning_rate": 2.8557869261768006e-05, + "loss": 3.5018, + "step": 1309696 + }, + { + "epoch": 0.0, + "learning_rate": 2.8549483314257486e-05, + "loss": 3.501, + "step": 1310208 + }, + { + "epoch": 0.0, + "learning_rate": 2.8541097366746966e-05, + "loss": 3.4943, + "step": 1310720 + }, + { + "epoch": 0.0, + "learning_rate": 2.8532711419236445e-05, + "loss": 3.5042, + "step": 1311232 + }, + { + "epoch": 0.0, + "learning_rate": 2.8524325471725925e-05, + "loss": 3.4973, + "step": 1311744 + }, + { + "epoch": 0.0, + "learning_rate": 2.8515939524215405e-05, + "loss": 3.4858, + "step": 1312256 + }, + { + "epoch": 0.01, + "learning_rate": 2.850755357670489e-05, + "loss": 3.505, + "step": 1312768 + }, + { + "epoch": 0.01, + "learning_rate": 2.8499184007998098e-05, + "loss": 3.4978, + "step": 1313280 + }, + { + "epoch": 0.01, + "learning_rate": 2.8490798060487578e-05, + "loss": 3.5047, + "step": 1313792 + }, + { + "epoch": 0.01, + "learning_rate": 2.8482412112977058e-05, + "loss": 3.5044, + "step": 1314304 + }, + { + "epoch": 0.01, + "learning_rate": 2.8474026165466538e-05, + "loss": 3.494, + "step": 1314816 + }, + { + "epoch": 0.01, + "learning_rate": 2.8465640217956018e-05, + "loss": 3.5049, + "step": 1315328 + }, + { + "epoch": 0.01, + "learning_rate": 2.8457254270445498e-05, + "loss": 3.5152, + "step": 1315840 + }, + { + "epoch": 0.01, + "learning_rate": 2.844886832293498e-05, + "loss": 3.4894, + "step": 1316352 + }, + { + "epoch": 0.01, + "learning_rate": 2.844049875422819e-05, + "loss": 3.5023, + "step": 1316864 + }, + { + "epoch": 0.01, + "learning_rate": 2.843211280671767e-05, + "loss": 3.496, + "step": 1317376 + }, + { + "epoch": 0.01, + "learning_rate": 2.842372685920715e-05, + "loss": 3.4915, + "step": 1317888 + }, + { + "epoch": 0.01, + "learning_rate": 2.841534091169663e-05, + "loss": 3.4988, + "step": 1318400 + }, + { + "epoch": 0.01, + "learning_rate": 2.840695496418611e-05, + "loss": 3.5115, + "step": 1318912 + }, + { + "epoch": 0.01, + "learning_rate": 2.839856901667559e-05, + "loss": 3.5061, + "step": 1319424 + }, + { + "epoch": 0.01, + "learning_rate": 2.8390199447968802e-05, + "loss": 3.496, + "step": 1319936 + }, + { + "epoch": 0.01, + "learning_rate": 2.8381813500458282e-05, + "loss": 3.5071, + "step": 1320448 + }, + { + "epoch": 0.01, + "learning_rate": 2.8373427552947762e-05, + "loss": 3.4976, + "step": 1320960 + }, + { + "epoch": 0.01, + "learning_rate": 2.8365041605437242e-05, + "loss": 3.5035, + "step": 1321472 + }, + { + "epoch": 0.01, + "learning_rate": 2.835665565792672e-05, + "loss": 3.4844, + "step": 1321984 + }, + { + "epoch": 0.01, + "learning_rate": 2.8348286089219935e-05, + "loss": 3.4977, + "step": 1322496 + }, + { + "epoch": 0.01, + "learning_rate": 2.8339900141709415e-05, + "loss": 3.5058, + "step": 1323008 + }, + { + "epoch": 0.01, + "learning_rate": 2.8331514194198895e-05, + "loss": 3.5045, + "step": 1323520 + }, + { + "epoch": 0.01, + "learning_rate": 2.8323128246688368e-05, + "loss": 3.5001, + "step": 1324032 + }, + { + "epoch": 0.01, + "learning_rate": 2.8314742299177848e-05, + "loss": 3.491, + "step": 1324544 + }, + { + "epoch": 0.01, + "learning_rate": 2.8306372730471064e-05, + "loss": 3.5044, + "step": 1325056 + }, + { + "epoch": 0.01, + "learning_rate": 2.8297986782960543e-05, + "loss": 3.4853, + "step": 1325568 + }, + { + "epoch": 0.01, + "learning_rate": 2.828960083545002e-05, + "loss": 3.513, + "step": 1326080 + }, + { + "epoch": 0.01, + "learning_rate": 2.82812148879395e-05, + "loss": 3.4996, + "step": 1326592 + }, + { + "epoch": 0.01, + "learning_rate": 2.827282894042898e-05, + "loss": 3.5151, + "step": 1327104 + }, + { + "epoch": 0.01, + "learning_rate": 2.826444299291846e-05, + "loss": 3.4938, + "step": 1327616 + }, + { + "epoch": 0.01, + "learning_rate": 2.825605704540794e-05, + "loss": 3.4938, + "step": 1328128 + }, + { + "epoch": 0.01, + "learning_rate": 2.824767109789742e-05, + "loss": 3.4971, + "step": 1328640 + }, + { + "epoch": 0.01, + "learning_rate": 2.8239301529190632e-05, + "loss": 3.5014, + "step": 1329152 + }, + { + "epoch": 0.01, + "learning_rate": 2.8230915581680112e-05, + "loss": 3.492, + "step": 1329664 + }, + { + "epoch": 0.01, + "learning_rate": 2.8222529634169592e-05, + "loss": 3.4904, + "step": 1330176 + }, + { + "epoch": 0.01, + "learning_rate": 2.8214143686659072e-05, + "loss": 3.5033, + "step": 1330688 + }, + { + "epoch": 0.01, + "learning_rate": 2.820577411795228e-05, + "loss": 3.4898, + "step": 1331200 + }, + { + "epoch": 0.01, + "learning_rate": 2.8197388170441765e-05, + "loss": 3.4901, + "step": 1331712 + }, + { + "epoch": 0.01, + "learning_rate": 2.8189002222931245e-05, + "loss": 3.4887, + "step": 1332224 + }, + { + "epoch": 0.01, + "learning_rate": 2.8180616275420725e-05, + "loss": 3.49, + "step": 1332736 + }, + { + "epoch": 0.01, + "learning_rate": 2.8172246706713934e-05, + "loss": 3.5031, + "step": 1333248 + }, + { + "epoch": 0.01, + "learning_rate": 2.8163860759203414e-05, + "loss": 3.508, + "step": 1333760 + }, + { + "epoch": 0.01, + "learning_rate": 2.8155474811692894e-05, + "loss": 3.4943, + "step": 1334272 + }, + { + "epoch": 0.01, + "learning_rate": 2.8147088864182373e-05, + "loss": 3.4933, + "step": 1334784 + }, + { + "epoch": 0.01, + "learning_rate": 2.8138702916671857e-05, + "loss": 3.4999, + "step": 1335296 + }, + { + "epoch": 0.01, + "learning_rate": 2.8130316969161337e-05, + "loss": 3.4987, + "step": 1335808 + }, + { + "epoch": 0.01, + "learning_rate": 2.8121931021650817e-05, + "loss": 3.4975, + "step": 1336320 + }, + { + "epoch": 0.01, + "learning_rate": 2.8113561452944026e-05, + "loss": 3.5019, + "step": 1336832 + }, + { + "epoch": 0.01, + "learning_rate": 2.8105175505433506e-05, + "loss": 3.4969, + "step": 1337344 + }, + { + "epoch": 0.01, + "learning_rate": 2.8096789557922986e-05, + "loss": 3.503, + "step": 1337856 + }, + { + "epoch": 0.01, + "learning_rate": 2.8088403610412466e-05, + "loss": 3.499, + "step": 1338368 + }, + { + "epoch": 0.01, + "learning_rate": 2.8080017662901946e-05, + "loss": 3.5045, + "step": 1338880 + }, + { + "epoch": 0.01, + "learning_rate": 2.8071648094195158e-05, + "loss": 3.5015, + "step": 1339392 + }, + { + "epoch": 0.01, + "learning_rate": 2.8063262146684638e-05, + "loss": 3.4984, + "step": 1339904 + }, + { + "epoch": 0.01, + "learning_rate": 2.8054876199174118e-05, + "loss": 3.4802, + "step": 1340416 + }, + { + "epoch": 0.01, + "learning_rate": 2.8046490251663598e-05, + "loss": 3.5025, + "step": 1340928 + }, + { + "epoch": 0.01, + "learning_rate": 2.803812068295681e-05, + "loss": 3.4986, + "step": 1341440 + }, + { + "epoch": 0.01, + "learning_rate": 2.802973473544629e-05, + "loss": 3.4993, + "step": 1341952 + }, + { + "epoch": 0.01, + "learning_rate": 2.802134878793577e-05, + "loss": 3.496, + "step": 1342464 + }, + { + "epoch": 0.01, + "learning_rate": 2.801296284042525e-05, + "loss": 3.4924, + "step": 1342976 + }, + { + "epoch": 0.02, + "learning_rate": 2.800457689291473e-05, + "loss": 3.4992, + "step": 1343488 + }, + { + "epoch": 0.02, + "learning_rate": 2.799620732420794e-05, + "loss": 3.4911, + "step": 1344000 + }, + { + "epoch": 0.02, + "learning_rate": 2.798782137669742e-05, + "loss": 3.4966, + "step": 1344512 + }, + { + "epoch": 0.02, + "learning_rate": 2.79794354291869e-05, + "loss": 3.4922, + "step": 1345024 + }, + { + "epoch": 0.02, + "learning_rate": 2.7971049481676376e-05, + "loss": 3.4979, + "step": 1345536 + }, + { + "epoch": 0.02, + "learning_rate": 2.7962663534165856e-05, + "loss": 3.5074, + "step": 1346048 + }, + { + "epoch": 0.02, + "learning_rate": 2.7954277586655336e-05, + "loss": 3.4924, + "step": 1346560 + }, + { + "epoch": 0.02, + "learning_rate": 2.794590801794855e-05, + "loss": 3.4796, + "step": 1347072 + }, + { + "epoch": 0.02, + "learning_rate": 2.7937522070438028e-05, + "loss": 3.4969, + "step": 1347584 + }, + { + "epoch": 0.02, + "learning_rate": 2.7929136122927508e-05, + "loss": 3.5006, + "step": 1348096 + }, + { + "epoch": 0.02, + "learning_rate": 2.7920750175416988e-05, + "loss": 3.5036, + "step": 1348608 + }, + { + "epoch": 0.02, + "learning_rate": 2.7912364227906468e-05, + "loss": 3.4956, + "step": 1349120 + }, + { + "epoch": 0.02, + "learning_rate": 2.7903978280395948e-05, + "loss": 3.4897, + "step": 1349632 + }, + { + "epoch": 0.02, + "learning_rate": 2.7895592332885428e-05, + "loss": 3.49, + "step": 1350144 + }, + { + "epoch": 0.02, + "learning_rate": 2.7887222764178637e-05, + "loss": 3.5038, + "step": 1350656 + }, + { + "epoch": 0.02, + "learning_rate": 2.787883681666812e-05, + "loss": 3.4843, + "step": 1351168 + }, + { + "epoch": 0.02, + "learning_rate": 2.78704508691576e-05, + "loss": 3.4863, + "step": 1351680 + }, + { + "epoch": 0.02, + "learning_rate": 2.786206492164708e-05, + "loss": 3.4969, + "step": 1352192 + }, + { + "epoch": 0.02, + "learning_rate": 2.785369535294029e-05, + "loss": 3.5016, + "step": 1352704 + }, + { + "epoch": 0.02, + "learning_rate": 2.784530940542977e-05, + "loss": 3.4789, + "step": 1353216 + }, + { + "epoch": 0.02, + "learning_rate": 2.7836939836722982e-05, + "loss": 3.49, + "step": 1353728 + }, + { + "epoch": 0.02, + "learning_rate": 2.7828553889212462e-05, + "loss": 3.4827, + "step": 1354240 + }, + { + "epoch": 0.02, + "learning_rate": 2.7820167941701942e-05, + "loss": 3.4984, + "step": 1354752 + }, + { + "epoch": 0.02, + "learning_rate": 2.7811781994191422e-05, + "loss": 3.4931, + "step": 1355264 + }, + { + "epoch": 0.02, + "learning_rate": 2.7803396046680902e-05, + "loss": 3.484, + "step": 1355776 + }, + { + "epoch": 0.02, + "learning_rate": 2.779501009917038e-05, + "loss": 3.5022, + "step": 1356288 + }, + { + "epoch": 0.02, + "learning_rate": 2.778662415165986e-05, + "loss": 3.4951, + "step": 1356800 + }, + { + "epoch": 0.02, + "learning_rate": 2.7778254582953074e-05, + "loss": 3.4877, + "step": 1357312 + }, + { + "epoch": 0.02, + "learning_rate": 2.7769868635442554e-05, + "loss": 3.4973, + "step": 1357824 + }, + { + "epoch": 0.02, + "learning_rate": 2.7761482687932034e-05, + "loss": 3.4961, + "step": 1358336 + }, + { + "epoch": 0.02, + "learning_rate": 2.7753096740421514e-05, + "loss": 3.4899, + "step": 1358848 + }, + { + "epoch": 0.02, + "learning_rate": 2.7744710792910994e-05, + "loss": 3.4773, + "step": 1359360 + }, + { + "epoch": 0.02, + "learning_rate": 2.7736341224204203e-05, + "loss": 3.4989, + "step": 1359872 + }, + { + "epoch": 0.02, + "learning_rate": 2.7727955276693683e-05, + "loss": 3.4919, + "step": 1360384 + }, + { + "epoch": 0.02, + "learning_rate": 2.7719569329183166e-05, + "loss": 3.4974, + "step": 1360896 + }, + { + "epoch": 0.02, + "learning_rate": 2.7711183381672646e-05, + "loss": 3.4872, + "step": 1361408 + }, + { + "epoch": 0.02, + "learning_rate": 2.7702813812965855e-05, + "loss": 3.4958, + "step": 1361920 + }, + { + "epoch": 0.02, + "learning_rate": 2.7694427865455335e-05, + "loss": 3.4964, + "step": 1362432 + }, + { + "epoch": 0.02, + "learning_rate": 2.7686041917944815e-05, + "loss": 3.486, + "step": 1362944 + }, + { + "epoch": 0.02, + "learning_rate": 2.7677655970434295e-05, + "loss": 3.4753, + "step": 1363456 + }, + { + "epoch": 0.02, + "learning_rate": 2.7669270022923775e-05, + "loss": 3.5036, + "step": 1363968 + }, + { + "epoch": 0.02, + "learning_rate": 2.7660900454216988e-05, + "loss": 3.5058, + "step": 1364480 + }, + { + "epoch": 0.02, + "learning_rate": 2.7652514506706468e-05, + "loss": 3.4915, + "step": 1364992 + }, + { + "epoch": 0.02, + "learning_rate": 2.7644128559195948e-05, + "loss": 3.4827, + "step": 1365504 + }, + { + "epoch": 0.02, + "learning_rate": 2.7635742611685428e-05, + "loss": 3.503, + "step": 1366016 + }, + { + "epoch": 0.02, + "learning_rate": 2.7627356664174908e-05, + "loss": 3.4904, + "step": 1366528 + }, + { + "epoch": 0.02, + "learning_rate": 2.7618970716664387e-05, + "loss": 3.4918, + "step": 1367040 + }, + { + "epoch": 0.02, + "learning_rate": 2.76106011479576e-05, + "loss": 3.4931, + "step": 1367552 + }, + { + "epoch": 0.02, + "learning_rate": 2.760221520044708e-05, + "loss": 3.502, + "step": 1368064 + }, + { + "epoch": 0.02, + "learning_rate": 2.759382925293656e-05, + "loss": 3.4944, + "step": 1368576 + }, + { + "epoch": 0.02, + "learning_rate": 2.7585443305426033e-05, + "loss": 3.4996, + "step": 1369088 + }, + { + "epoch": 0.02, + "learning_rate": 2.7577057357915513e-05, + "loss": 3.4874, + "step": 1369600 + }, + { + "epoch": 0.02, + "learning_rate": 2.7568671410404996e-05, + "loss": 3.4964, + "step": 1370112 + }, + { + "epoch": 0.02, + "learning_rate": 2.7560285462894476e-05, + "loss": 3.4916, + "step": 1370624 + }, + { + "epoch": 0.02, + "learning_rate": 2.7551915894187685e-05, + "loss": 3.4887, + "step": 1371136 + }, + { + "epoch": 0.02, + "learning_rate": 2.7543529946677165e-05, + "loss": 3.51, + "step": 1371648 + }, + { + "epoch": 0.02, + "learning_rate": 2.7535143999166645e-05, + "loss": 3.4916, + "step": 1372160 + }, + { + "epoch": 0.02, + "learning_rate": 2.7526758051656125e-05, + "loss": 3.4941, + "step": 1372672 + }, + { + "epoch": 0.02, + "learning_rate": 2.7518372104145605e-05, + "loss": 3.4926, + "step": 1373184 + }, + { + "epoch": 0.02, + "learning_rate": 2.750998615663509e-05, + "loss": 3.491, + "step": 1373696 + }, + { + "epoch": 0.03, + "eval_loss": 3.9005258083343506, + "eval_runtime": 317.1296, + "eval_samples_per_second": 1203.265, + "eval_steps_per_second": 37.603, + "step": 1373750 + }, + { + "epoch": 1.0, + "learning_rate": 2.7501616587928298e-05, + "loss": 3.4884, + "step": 1374208 + }, + { + "epoch": 1.0, + "learning_rate": 2.7493230640417778e-05, + "loss": 3.496, + "step": 1374720 + }, + { + "epoch": 1.0, + "learning_rate": 2.7484844692907258e-05, + "loss": 3.4997, + "step": 1375232 + }, + { + "epoch": 1.0, + "learning_rate": 2.7476458745396738e-05, + "loss": 3.4952, + "step": 1375744 + }, + { + "epoch": 1.0, + "learning_rate": 2.7468072797886217e-05, + "loss": 3.5041, + "step": 1376256 + }, + { + "epoch": 1.0, + "learning_rate": 2.745970322917943e-05, + "loss": 3.4841, + "step": 1376768 + }, + { + "epoch": 1.0, + "learning_rate": 2.745131728166891e-05, + "loss": 3.4909, + "step": 1377280 + }, + { + "epoch": 1.0, + "learning_rate": 2.744293133415839e-05, + "loss": 3.4864, + "step": 1377792 + }, + { + "epoch": 1.0, + "learning_rate": 2.743454538664787e-05, + "loss": 3.4947, + "step": 1378304 + }, + { + "epoch": 1.0, + "learning_rate": 2.742615943913735e-05, + "loss": 3.4914, + "step": 1378816 + }, + { + "epoch": 1.0, + "learning_rate": 2.741777349162683e-05, + "loss": 3.4968, + "step": 1379328 + }, + { + "epoch": 1.0, + "learning_rate": 2.740938754411631e-05, + "loss": 3.497, + "step": 1379840 + }, + { + "epoch": 1.0, + "learning_rate": 2.740100159660579e-05, + "loss": 3.4796, + "step": 1380352 + }, + { + "epoch": 1.0, + "learning_rate": 2.7392632027899002e-05, + "loss": 3.4878, + "step": 1380864 + }, + { + "epoch": 1.0, + "learning_rate": 2.738426245919221e-05, + "loss": 3.4762, + "step": 1381376 + }, + { + "epoch": 1.0, + "learning_rate": 2.737587651168169e-05, + "loss": 3.4825, + "step": 1381888 + }, + { + "epoch": 1.0, + "learning_rate": 2.736749056417117e-05, + "loss": 3.4845, + "step": 1382400 + }, + { + "epoch": 1.0, + "learning_rate": 2.735910461666065e-05, + "loss": 3.4871, + "step": 1382912 + }, + { + "epoch": 1.0, + "learning_rate": 2.7350735047953864e-05, + "loss": 3.4856, + "step": 1383424 + }, + { + "epoch": 1.0, + "learning_rate": 2.7342349100443344e-05, + "loss": 3.5084, + "step": 1383936 + }, + { + "epoch": 1.0, + "learning_rate": 2.7333963152932824e-05, + "loss": 3.4884, + "step": 1384448 + }, + { + "epoch": 1.0, + "learning_rate": 2.7325577205422303e-05, + "loss": 3.4865, + "step": 1384960 + }, + { + "epoch": 1.0, + "learning_rate": 2.7317191257911783e-05, + "loss": 3.4943, + "step": 1385472 + }, + { + "epoch": 1.0, + "learning_rate": 2.7308821689204993e-05, + "loss": 3.4899, + "step": 1385984 + }, + { + "epoch": 1.0, + "learning_rate": 2.7300435741694476e-05, + "loss": 3.4851, + "step": 1386496 + }, + { + "epoch": 1.0, + "learning_rate": 2.7292049794183956e-05, + "loss": 3.4827, + "step": 1387008 + }, + { + "epoch": 1.0, + "learning_rate": 2.7283663846673436e-05, + "loss": 3.4913, + "step": 1387520 + }, + { + "epoch": 1.0, + "learning_rate": 2.7275277899162916e-05, + "loss": 3.4815, + "step": 1388032 + }, + { + "epoch": 1.0, + "learning_rate": 2.7266908330456125e-05, + "loss": 3.4753, + "step": 1388544 + }, + { + "epoch": 1.01, + "learning_rate": 2.7258522382945605e-05, + "loss": 3.4916, + "step": 1389056 + }, + { + "epoch": 1.01, + "learning_rate": 2.7250136435435085e-05, + "loss": 3.4825, + "step": 1389568 + }, + { + "epoch": 1.01, + "learning_rate": 2.7241750487924568e-05, + "loss": 3.4924, + "step": 1390080 + }, + { + "epoch": 1.01, + "learning_rate": 2.7233364540414048e-05, + "loss": 3.4889, + "step": 1390592 + }, + { + "epoch": 1.01, + "learning_rate": 2.722497859290352e-05, + "loss": 3.4812, + "step": 1391104 + }, + { + "epoch": 1.01, + "learning_rate": 2.7216592645393e-05, + "loss": 3.49, + "step": 1391616 + }, + { + "epoch": 1.01, + "learning_rate": 2.720820669788248e-05, + "loss": 3.5032, + "step": 1392128 + }, + { + "epoch": 1.01, + "learning_rate": 2.7199837129175697e-05, + "loss": 3.4765, + "step": 1392640 + }, + { + "epoch": 1.01, + "learning_rate": 2.719146756046891e-05, + "loss": 3.4903, + "step": 1393152 + }, + { + "epoch": 1.01, + "learning_rate": 2.718308161295839e-05, + "loss": 3.4791, + "step": 1393664 + }, + { + "epoch": 1.01, + "learning_rate": 2.717469566544787e-05, + "loss": 3.4793, + "step": 1394176 + }, + { + "epoch": 1.01, + "learning_rate": 2.7166309717937343e-05, + "loss": 3.4837, + "step": 1394688 + }, + { + "epoch": 1.01, + "learning_rate": 2.7157923770426823e-05, + "loss": 3.4998, + "step": 1395200 + }, + { + "epoch": 1.01, + "learning_rate": 2.7149537822916306e-05, + "loss": 3.4932, + "step": 1395712 + }, + { + "epoch": 1.01, + "learning_rate": 2.7141168254209522e-05, + "loss": 3.4852, + "step": 1396224 + }, + { + "epoch": 1.01, + "learning_rate": 2.7132782306698995e-05, + "loss": 3.4936, + "step": 1396736 + }, + { + "epoch": 1.01, + "learning_rate": 2.7124396359188475e-05, + "loss": 3.4811, + "step": 1397248 + }, + { + "epoch": 1.01, + "learning_rate": 2.7116010411677955e-05, + "loss": 3.4907, + "step": 1397760 + }, + { + "epoch": 1.01, + "learning_rate": 2.7107624464167435e-05, + "loss": 3.476, + "step": 1398272 + }, + { + "epoch": 1.01, + "learning_rate": 2.7099254895460647e-05, + "loss": 3.4801, + "step": 1398784 + }, + { + "epoch": 1.01, + "learning_rate": 2.7090868947950127e-05, + "loss": 3.4968, + "step": 1399296 + }, + { + "epoch": 1.01, + "learning_rate": 2.7082483000439607e-05, + "loss": 3.4899, + "step": 1399808 + }, + { + "epoch": 1.01, + "learning_rate": 2.7074097052929087e-05, + "loss": 3.4842, + "step": 1400320 + }, + { + "epoch": 1.01, + "learning_rate": 2.7065711105418567e-05, + "loss": 3.4802, + "step": 1400832 + }, + { + "epoch": 1.01, + "learning_rate": 2.7057341536711776e-05, + "loss": 3.4928, + "step": 1401344 + }, + { + "epoch": 1.01, + "learning_rate": 2.704895558920126e-05, + "loss": 3.4712, + "step": 1401856 + }, + { + "epoch": 1.01, + "learning_rate": 2.704056964169074e-05, + "loss": 3.4962, + "step": 1402368 + }, + { + "epoch": 1.01, + "learning_rate": 2.703218369418022e-05, + "loss": 3.4891, + "step": 1402880 + }, + { + "epoch": 1.01, + "learning_rate": 2.70237977466697e-05, + "loss": 3.4998, + "step": 1403392 + }, + { + "epoch": 1.01, + "learning_rate": 2.701541179915918e-05, + "loss": 3.4854, + "step": 1403904 + }, + { + "epoch": 1.01, + "learning_rate": 2.700702585164866e-05, + "loss": 3.4784, + "step": 1404416 + }, + { + "epoch": 1.01, + "learning_rate": 2.699863990413814e-05, + "loss": 3.4835, + "step": 1404928 + }, + { + "epoch": 1.01, + "learning_rate": 2.6990270335431352e-05, + "loss": 3.4897, + "step": 1405440 + }, + { + "epoch": 1.01, + "learning_rate": 2.6981884387920832e-05, + "loss": 3.4777, + "step": 1405952 + }, + { + "epoch": 1.01, + "learning_rate": 2.697349844041031e-05, + "loss": 3.4757, + "step": 1406464 + }, + { + "epoch": 1.01, + "learning_rate": 2.696511249289979e-05, + "loss": 3.4872, + "step": 1406976 + }, + { + "epoch": 1.01, + "learning_rate": 2.6956742924193e-05, + "loss": 3.4798, + "step": 1407488 + }, + { + "epoch": 1.01, + "learning_rate": 2.694835697668248e-05, + "loss": 3.4739, + "step": 1408000 + }, + { + "epoch": 1.01, + "learning_rate": 2.693997102917196e-05, + "loss": 3.4798, + "step": 1408512 + }, + { + "epoch": 1.01, + "learning_rate": 2.6931585081661444e-05, + "loss": 3.4732, + "step": 1409024 + }, + { + "epoch": 1.01, + "learning_rate": 2.6923215512954653e-05, + "loss": 3.4882, + "step": 1409536 + }, + { + "epoch": 1.01, + "learning_rate": 2.6914829565444133e-05, + "loss": 3.4952, + "step": 1410048 + }, + { + "epoch": 1.01, + "learning_rate": 2.6906443617933613e-05, + "loss": 3.4803, + "step": 1410560 + }, + { + "epoch": 1.01, + "learning_rate": 2.6898057670423093e-05, + "loss": 3.4833, + "step": 1411072 + }, + { + "epoch": 1.01, + "learning_rate": 2.6889688101716305e-05, + "loss": 3.484, + "step": 1411584 + }, + { + "epoch": 1.01, + "learning_rate": 2.6881302154205785e-05, + "loss": 3.4874, + "step": 1412096 + }, + { + "epoch": 1.01, + "learning_rate": 2.6872916206695265e-05, + "loss": 3.4845, + "step": 1412608 + }, + { + "epoch": 1.01, + "learning_rate": 2.6864530259184745e-05, + "loss": 3.4903, + "step": 1413120 + }, + { + "epoch": 1.01, + "learning_rate": 2.6856160690477954e-05, + "loss": 3.4846, + "step": 1413632 + }, + { + "epoch": 1.01, + "learning_rate": 2.6847774742967434e-05, + "loss": 3.4883, + "step": 1414144 + }, + { + "epoch": 1.01, + "learning_rate": 2.6839388795456914e-05, + "loss": 3.4858, + "step": 1414656 + }, + { + "epoch": 1.01, + "learning_rate": 2.6831002847946398e-05, + "loss": 3.4892, + "step": 1415168 + }, + { + "epoch": 1.01, + "learning_rate": 2.6822616900435878e-05, + "loss": 3.4881, + "step": 1415680 + }, + { + "epoch": 1.01, + "learning_rate": 2.6814230952925358e-05, + "loss": 3.4892, + "step": 1416192 + }, + { + "epoch": 1.01, + "learning_rate": 2.680584500541483e-05, + "loss": 3.4709, + "step": 1416704 + }, + { + "epoch": 1.01, + "learning_rate": 2.6797475436708047e-05, + "loss": 3.4859, + "step": 1417216 + }, + { + "epoch": 1.01, + "learning_rate": 2.6789089489197527e-05, + "loss": 3.4837, + "step": 1417728 + }, + { + "epoch": 1.01, + "learning_rate": 2.6780703541687003e-05, + "loss": 3.4842, + "step": 1418240 + }, + { + "epoch": 1.01, + "learning_rate": 2.6772317594176483e-05, + "loss": 3.4842, + "step": 1418752 + }, + { + "epoch": 1.01, + "learning_rate": 2.6763931646665963e-05, + "loss": 3.473, + "step": 1419264 + }, + { + "epoch": 1.02, + "learning_rate": 2.6755545699155443e-05, + "loss": 3.4866, + "step": 1419776 + }, + { + "epoch": 1.02, + "learning_rate": 2.6747176130448652e-05, + "loss": 3.4794, + "step": 1420288 + }, + { + "epoch": 1.02, + "learning_rate": 2.6738790182938135e-05, + "loss": 3.4847, + "step": 1420800 + }, + { + "epoch": 1.02, + "learning_rate": 2.6730404235427615e-05, + "loss": 3.4712, + "step": 1421312 + }, + { + "epoch": 1.02, + "learning_rate": 2.6722018287917095e-05, + "loss": 3.4862, + "step": 1421824 + }, + { + "epoch": 1.02, + "learning_rate": 2.6713632340406575e-05, + "loss": 3.497, + "step": 1422336 + }, + { + "epoch": 1.02, + "learning_rate": 2.6705246392896055e-05, + "loss": 3.4812, + "step": 1422848 + }, + { + "epoch": 1.02, + "learning_rate": 2.6696876824189264e-05, + "loss": 3.4664, + "step": 1423360 + }, + { + "epoch": 1.02, + "learning_rate": 2.6688490876678744e-05, + "loss": 3.4834, + "step": 1423872 + }, + { + "epoch": 1.02, + "learning_rate": 2.6680104929168224e-05, + "loss": 3.4867, + "step": 1424384 + }, + { + "epoch": 1.02, + "learning_rate": 2.6671718981657708e-05, + "loss": 3.4865, + "step": 1424896 + }, + { + "epoch": 1.02, + "learning_rate": 2.6663333034147188e-05, + "loss": 3.4845, + "step": 1425408 + }, + { + "epoch": 1.02, + "learning_rate": 2.6654947086636668e-05, + "loss": 3.477, + "step": 1425920 + }, + { + "epoch": 1.02, + "learning_rate": 2.6646561139126147e-05, + "loss": 3.4778, + "step": 1426432 + }, + { + "epoch": 1.02, + "learning_rate": 2.6638191570419357e-05, + "loss": 3.4906, + "step": 1426944 + }, + { + "epoch": 1.02, + "learning_rate": 2.6629805622908837e-05, + "loss": 3.4705, + "step": 1427456 + }, + { + "epoch": 1.02, + "learning_rate": 2.6621419675398316e-05, + "loss": 3.4744, + "step": 1427968 + }, + { + "epoch": 1.02, + "learning_rate": 2.66130337278878e-05, + "loss": 3.4828, + "step": 1428480 + }, + { + "epoch": 1.02, + "learning_rate": 2.660466415918101e-05, + "loss": 3.4907, + "step": 1428992 + }, + { + "epoch": 1.02, + "learning_rate": 2.659627821167049e-05, + "loss": 3.4641, + "step": 1429504 + }, + { + "epoch": 1.02, + "learning_rate": 2.6587908642963698e-05, + "loss": 3.4808, + "step": 1430016 + }, + { + "epoch": 1.02, + "learning_rate": 2.6579522695453178e-05, + "loss": 3.4661, + "step": 1430528 + }, + { + "epoch": 1.02, + "learning_rate": 2.657113674794266e-05, + "loss": 3.4827, + "step": 1431040 + }, + { + "epoch": 1.02, + "learning_rate": 2.656275080043214e-05, + "loss": 3.4816, + "step": 1431552 + }, + { + "epoch": 1.02, + "learning_rate": 2.655436485292162e-05, + "loss": 3.4717, + "step": 1432064 + }, + { + "epoch": 1.02, + "learning_rate": 2.654599528421483e-05, + "loss": 3.4876, + "step": 1432576 + }, + { + "epoch": 1.02, + "learning_rate": 2.653760933670431e-05, + "loss": 3.4849, + "step": 1433088 + }, + { + "epoch": 1.02, + "learning_rate": 2.652922338919379e-05, + "loss": 3.4733, + "step": 1433600 + }, + { + "epoch": 1.02, + "learning_rate": 2.652083744168327e-05, + "loss": 3.4861, + "step": 1434112 + }, + { + "epoch": 1.02, + "learning_rate": 2.6512467872976483e-05, + "loss": 3.4792, + "step": 1434624 + }, + { + "epoch": 1.02, + "learning_rate": 2.6504081925465963e-05, + "loss": 3.4784, + "step": 1435136 + }, + { + "epoch": 1.02, + "learning_rate": 2.6495695977955443e-05, + "loss": 3.4619, + "step": 1435648 + }, + { + "epoch": 1.02, + "learning_rate": 2.6487310030444923e-05, + "loss": 3.4875, + "step": 1436160 + }, + { + "epoch": 1.02, + "learning_rate": 2.6478924082934402e-05, + "loss": 3.4794, + "step": 1436672 + }, + { + "epoch": 1.02, + "learning_rate": 2.6470554514227615e-05, + "loss": 3.483, + "step": 1437184 + }, + { + "epoch": 1.02, + "learning_rate": 2.6462168566717095e-05, + "loss": 3.4775, + "step": 1437696 + }, + { + "epoch": 1.02, + "learning_rate": 2.6453782619206575e-05, + "loss": 3.4835, + "step": 1438208 + }, + { + "epoch": 1.02, + "learning_rate": 2.6445396671696055e-05, + "loss": 3.4753, + "step": 1438720 + }, + { + "epoch": 1.02, + "learning_rate": 2.6437010724185535e-05, + "loss": 3.4717, + "step": 1439232 + }, + { + "epoch": 1.02, + "learning_rate": 2.6428641155478744e-05, + "loss": 3.466, + "step": 1439744 + }, + { + "epoch": 1.02, + "learning_rate": 2.6420255207968224e-05, + "loss": 3.4903, + "step": 1440256 + }, + { + "epoch": 1.02, + "learning_rate": 2.6411869260457707e-05, + "loss": 3.487, + "step": 1440768 + }, + { + "epoch": 1.02, + "learning_rate": 2.6403483312947187e-05, + "loss": 3.4831, + "step": 1441280 + }, + { + "epoch": 1.02, + "learning_rate": 2.6395113744240396e-05, + "loss": 3.4713, + "step": 1441792 + }, + { + "epoch": 1.02, + "learning_rate": 2.6386727796729876e-05, + "loss": 3.4848, + "step": 1442304 + }, + { + "epoch": 1.02, + "learning_rate": 2.6378341849219356e-05, + "loss": 3.4817, + "step": 1442816 + }, + { + "epoch": 1.02, + "learning_rate": 2.6369955901708836e-05, + "loss": 3.4759, + "step": 1443328 + }, + { + "epoch": 1.02, + "learning_rate": 2.636158633300205e-05, + "loss": 3.4795, + "step": 1443840 + }, + { + "epoch": 1.02, + "learning_rate": 2.635320038549153e-05, + "loss": 3.4842, + "step": 1444352 + }, + { + "epoch": 1.02, + "learning_rate": 2.634481443798101e-05, + "loss": 3.4829, + "step": 1444864 + }, + { + "epoch": 1.02, + "learning_rate": 2.633642849047049e-05, + "loss": 3.4873, + "step": 1445376 + }, + { + "epoch": 1.02, + "learning_rate": 2.632804254295996e-05, + "loss": 3.473, + "step": 1445888 + }, + { + "epoch": 1.02, + "learning_rate": 2.6319672974253177e-05, + "loss": 3.4831, + "step": 1446400 + }, + { + "epoch": 1.02, + "learning_rate": 2.631128702674266e-05, + "loss": 3.4803, + "step": 1446912 + }, + { + "epoch": 1.02, + "learning_rate": 2.6302901079232134e-05, + "loss": 3.4721, + "step": 1447424 + }, + { + "epoch": 1.02, + "learning_rate": 2.6294515131721614e-05, + "loss": 3.4949, + "step": 1447936 + }, + { + "epoch": 1.02, + "learning_rate": 2.6286129184211094e-05, + "loss": 3.4783, + "step": 1448448 + }, + { + "epoch": 1.02, + "learning_rate": 2.627775961550431e-05, + "loss": 3.4834, + "step": 1448960 + }, + { + "epoch": 1.02, + "learning_rate": 2.6269373667993786e-05, + "loss": 3.477, + "step": 1449472 + }, + { + "epoch": 1.02, + "learning_rate": 2.6260987720483266e-05, + "loss": 3.4799, + "step": 1449984 + }, + { + "epoch": 1.03, + "eval_loss": 3.9022610187530518, + "eval_runtime": 316.864, + "eval_samples_per_second": 1204.274, + "eval_steps_per_second": 37.634, + "step": 1450070 + }, + { + "epoch": 0.0, + "learning_rate": 2.6252618151776482e-05, + "loss": 3.4736, + "step": 1450496 + }, + { + "epoch": 0.0, + "learning_rate": 2.6244232204265962e-05, + "loss": 3.4838, + "step": 1451008 + }, + { + "epoch": 0.0, + "learning_rate": 2.6235846256755435e-05, + "loss": 3.4828, + "step": 1451520 + }, + { + "epoch": 0.0, + "learning_rate": 2.6227460309244915e-05, + "loss": 3.4811, + "step": 1452032 + }, + { + "epoch": 0.0, + "learning_rate": 2.621909074053813e-05, + "loss": 3.4883, + "step": 1452544 + }, + { + "epoch": 0.0, + "learning_rate": 2.6210704793027608e-05, + "loss": 3.4736, + "step": 1453056 + }, + { + "epoch": 0.0, + "learning_rate": 2.6202318845517088e-05, + "loss": 3.4768, + "step": 1453568 + }, + { + "epoch": 0.0, + "learning_rate": 2.6193932898006568e-05, + "loss": 3.468, + "step": 1454080 + }, + { + "epoch": 0.0, + "learning_rate": 2.6185546950496048e-05, + "loss": 3.485, + "step": 1454592 + }, + { + "epoch": 0.0, + "learning_rate": 2.6177161002985528e-05, + "loss": 3.4749, + "step": 1455104 + }, + { + "epoch": 0.0, + "learning_rate": 2.6168775055475008e-05, + "loss": 3.4829, + "step": 1455616 + }, + { + "epoch": 0.0, + "learning_rate": 2.616038910796449e-05, + "loss": 3.4843, + "step": 1456128 + }, + { + "epoch": 0.0, + "learning_rate": 2.6152035918061436e-05, + "loss": 3.4706, + "step": 1456640 + }, + { + "epoch": 0.0, + "learning_rate": 2.614364997055091e-05, + "loss": 3.4713, + "step": 1457152 + }, + { + "epoch": 0.0, + "learning_rate": 2.613526402304039e-05, + "loss": 3.468, + "step": 1457664 + }, + { + "epoch": 0.0, + "learning_rate": 2.612687807552987e-05, + "loss": 3.4667, + "step": 1458176 + }, + { + "epoch": 0.0, + "learning_rate": 2.611850850682308e-05, + "loss": 3.4745, + "step": 1458688 + }, + { + "epoch": 0.0, + "learning_rate": 2.611012255931256e-05, + "loss": 3.4705, + "step": 1459200 + }, + { + "epoch": 0.0, + "learning_rate": 2.610173661180204e-05, + "loss": 3.4734, + "step": 1459712 + }, + { + "epoch": 0.0, + "learning_rate": 2.609335066429152e-05, + "loss": 3.4925, + "step": 1460224 + }, + { + "epoch": 0.0, + "learning_rate": 2.6084964716781e-05, + "loss": 3.4786, + "step": 1460736 + }, + { + "epoch": 0.0, + "learning_rate": 2.6076595148074214e-05, + "loss": 3.4743, + "step": 1461248 + }, + { + "epoch": 0.0, + "learning_rate": 2.6068209200563694e-05, + "loss": 3.4795, + "step": 1461760 + }, + { + "epoch": 0.0, + "learning_rate": 2.6059823253053174e-05, + "loss": 3.4789, + "step": 1462272 + }, + { + "epoch": 0.0, + "learning_rate": 2.6051437305542654e-05, + "loss": 3.4706, + "step": 1462784 + }, + { + "epoch": 0.0, + "learning_rate": 2.6043067736835863e-05, + "loss": 3.4685, + "step": 1463296 + }, + { + "epoch": 0.0, + "learning_rate": 2.6034681789325343e-05, + "loss": 3.4848, + "step": 1463808 + }, + { + "epoch": 0.0, + "learning_rate": 2.6026295841814823e-05, + "loss": 3.4629, + "step": 1464320 + }, + { + "epoch": 0.0, + "learning_rate": 2.6017909894304303e-05, + "loss": 3.4683, + "step": 1464832 + }, + { + "epoch": 0.01, + "learning_rate": 2.6009540325597515e-05, + "loss": 3.4749, + "step": 1465344 + }, + { + "epoch": 0.01, + "learning_rate": 2.6001154378086995e-05, + "loss": 3.4732, + "step": 1465856 + }, + { + "epoch": 0.01, + "learning_rate": 2.5992768430576475e-05, + "loss": 3.4743, + "step": 1466368 + }, + { + "epoch": 0.01, + "learning_rate": 2.5984382483065955e-05, + "loss": 3.476, + "step": 1466880 + }, + { + "epoch": 0.01, + "learning_rate": 2.5975996535555435e-05, + "loss": 3.469, + "step": 1467392 + }, + { + "epoch": 0.01, + "learning_rate": 2.5967626966848647e-05, + "loss": 3.4779, + "step": 1467904 + }, + { + "epoch": 0.01, + "learning_rate": 2.5959241019338127e-05, + "loss": 3.4888, + "step": 1468416 + }, + { + "epoch": 0.01, + "learning_rate": 2.5950855071827607e-05, + "loss": 3.4634, + "step": 1468928 + }, + { + "epoch": 0.01, + "learning_rate": 2.5942469124317087e-05, + "loss": 3.481, + "step": 1469440 + }, + { + "epoch": 0.01, + "learning_rate": 2.5934099555610296e-05, + "loss": 3.4636, + "step": 1469952 + }, + { + "epoch": 0.01, + "learning_rate": 2.5925713608099776e-05, + "loss": 3.4716, + "step": 1470464 + }, + { + "epoch": 0.01, + "learning_rate": 2.5917327660589256e-05, + "loss": 3.4675, + "step": 1470976 + }, + { + "epoch": 0.01, + "learning_rate": 2.590894171307874e-05, + "loss": 3.4877, + "step": 1471488 + }, + { + "epoch": 0.01, + "learning_rate": 2.590055576556822e-05, + "loss": 3.476, + "step": 1472000 + }, + { + "epoch": 0.01, + "learning_rate": 2.589218619686143e-05, + "loss": 3.4758, + "step": 1472512 + }, + { + "epoch": 0.01, + "learning_rate": 2.588380024935091e-05, + "loss": 3.4778, + "step": 1473024 + }, + { + "epoch": 0.01, + "learning_rate": 2.587541430184039e-05, + "loss": 3.4706, + "step": 1473536 + }, + { + "epoch": 0.01, + "learning_rate": 2.586702835432987e-05, + "loss": 3.4778, + "step": 1474048 + }, + { + "epoch": 0.01, + "learning_rate": 2.585864240681935e-05, + "loss": 3.4636, + "step": 1474560 + }, + { + "epoch": 0.01, + "learning_rate": 2.585027283811256e-05, + "loss": 3.467, + "step": 1475072 + }, + { + "epoch": 0.01, + "learning_rate": 2.584188689060204e-05, + "loss": 3.4807, + "step": 1475584 + }, + { + "epoch": 0.01, + "learning_rate": 2.583350094309152e-05, + "loss": 3.4745, + "step": 1476096 + }, + { + "epoch": 0.01, + "learning_rate": 2.5825114995581e-05, + "loss": 3.4737, + "step": 1476608 + }, + { + "epoch": 0.01, + "learning_rate": 2.581672904807048e-05, + "loss": 3.4655, + "step": 1477120 + }, + { + "epoch": 0.01, + "learning_rate": 2.580834310055996e-05, + "loss": 3.4744, + "step": 1477632 + }, + { + "epoch": 0.01, + "learning_rate": 2.5799973531853173e-05, + "loss": 3.4614, + "step": 1478144 + }, + { + "epoch": 0.01, + "learning_rate": 2.5791587584342653e-05, + "loss": 3.479, + "step": 1478656 + }, + { + "epoch": 0.01, + "learning_rate": 2.5783201636832133e-05, + "loss": 3.4802, + "step": 1479168 + }, + { + "epoch": 0.01, + "learning_rate": 2.5774815689321613e-05, + "loss": 3.4849, + "step": 1479680 + }, + { + "epoch": 0.01, + "learning_rate": 2.5766446120614822e-05, + "loss": 3.473, + "step": 1480192 + }, + { + "epoch": 0.01, + "learning_rate": 2.5758060173104302e-05, + "loss": 3.4708, + "step": 1480704 + }, + { + "epoch": 0.01, + "learning_rate": 2.5749674225593785e-05, + "loss": 3.4656, + "step": 1481216 + }, + { + "epoch": 0.01, + "learning_rate": 2.5741288278083265e-05, + "loss": 3.4794, + "step": 1481728 + }, + { + "epoch": 0.01, + "learning_rate": 2.573290233057274e-05, + "loss": 3.4643, + "step": 1482240 + }, + { + "epoch": 0.01, + "learning_rate": 2.5724532761865954e-05, + "loss": 3.4654, + "step": 1482752 + }, + { + "epoch": 0.01, + "learning_rate": 2.5716146814355434e-05, + "loss": 3.4706, + "step": 1483264 + }, + { + "epoch": 0.01, + "learning_rate": 2.5707760866844914e-05, + "loss": 3.4712, + "step": 1483776 + }, + { + "epoch": 0.01, + "learning_rate": 2.569937491933439e-05, + "loss": 3.4603, + "step": 1484288 + }, + { + "epoch": 0.01, + "learning_rate": 2.5691005350627607e-05, + "loss": 3.4623, + "step": 1484800 + }, + { + "epoch": 0.01, + "learning_rate": 2.5682619403117087e-05, + "loss": 3.4626, + "step": 1485312 + }, + { + "epoch": 0.01, + "learning_rate": 2.5674233455606567e-05, + "loss": 3.4778, + "step": 1485824 + }, + { + "epoch": 0.01, + "learning_rate": 2.566584750809604e-05, + "loss": 3.4785, + "step": 1486336 + }, + { + "epoch": 0.01, + "learning_rate": 2.5657461560585523e-05, + "loss": 3.4674, + "step": 1486848 + }, + { + "epoch": 0.01, + "learning_rate": 2.564909199187874e-05, + "loss": 3.4742, + "step": 1487360 + }, + { + "epoch": 0.01, + "learning_rate": 2.5640706044368212e-05, + "loss": 3.4691, + "step": 1487872 + }, + { + "epoch": 0.01, + "learning_rate": 2.5632320096857692e-05, + "loss": 3.4811, + "step": 1488384 + }, + { + "epoch": 0.01, + "learning_rate": 2.5623934149347172e-05, + "loss": 3.4641, + "step": 1488896 + }, + { + "epoch": 0.01, + "learning_rate": 2.5615548201836652e-05, + "loss": 3.482, + "step": 1489408 + }, + { + "epoch": 0.01, + "learning_rate": 2.5607178633129865e-05, + "loss": 3.4682, + "step": 1489920 + }, + { + "epoch": 0.01, + "learning_rate": 2.5598792685619345e-05, + "loss": 3.4748, + "step": 1490432 + }, + { + "epoch": 0.01, + "learning_rate": 2.5590406738108825e-05, + "loss": 3.4738, + "step": 1490944 + }, + { + "epoch": 0.01, + "learning_rate": 2.5582020790598305e-05, + "loss": 3.4719, + "step": 1491456 + }, + { + "epoch": 0.01, + "learning_rate": 2.5573651221891514e-05, + "loss": 3.4801, + "step": 1491968 + }, + { + "epoch": 0.01, + "learning_rate": 2.5565265274380994e-05, + "loss": 3.4718, + "step": 1492480 + }, + { + "epoch": 0.01, + "learning_rate": 2.5556879326870477e-05, + "loss": 3.4604, + "step": 1492992 + }, + { + "epoch": 0.01, + "learning_rate": 2.5548493379359957e-05, + "loss": 3.4711, + "step": 1493504 + }, + { + "epoch": 0.01, + "learning_rate": 2.5540123810653166e-05, + "loss": 3.4697, + "step": 1494016 + }, + { + "epoch": 0.01, + "learning_rate": 2.5531737863142646e-05, + "loss": 3.4771, + "step": 1494528 + }, + { + "epoch": 0.01, + "learning_rate": 2.5523351915632126e-05, + "loss": 3.4699, + "step": 1495040 + }, + { + "epoch": 0.01, + "learning_rate": 2.5514965968121606e-05, + "loss": 3.4637, + "step": 1495552 + }, + { + "epoch": 0.02, + "learning_rate": 2.5506580020611086e-05, + "loss": 3.472, + "step": 1496064 + }, + { + "epoch": 0.02, + "learning_rate": 2.5498210451904298e-05, + "loss": 3.4641, + "step": 1496576 + }, + { + "epoch": 0.02, + "learning_rate": 2.5489824504393778e-05, + "loss": 3.4727, + "step": 1497088 + }, + { + "epoch": 0.02, + "learning_rate": 2.5481438556883258e-05, + "loss": 3.4586, + "step": 1497600 + }, + { + "epoch": 0.02, + "learning_rate": 2.5473052609372738e-05, + "loss": 3.4745, + "step": 1498112 + }, + { + "epoch": 0.02, + "learning_rate": 2.5464666661862218e-05, + "loss": 3.4842, + "step": 1498624 + }, + { + "epoch": 0.02, + "learning_rate": 2.545629709315543e-05, + "loss": 3.4663, + "step": 1499136 + }, + { + "epoch": 0.02, + "learning_rate": 2.544791114564491e-05, + "loss": 3.4545, + "step": 1499648 + }, + { + "epoch": 0.02, + "learning_rate": 2.543952519813439e-05, + "loss": 3.469, + "step": 1500160 + }, + { + "epoch": 0.02, + "learning_rate": 2.543113925062387e-05, + "loss": 3.4721, + "step": 1500672 + }, + { + "epoch": 0.02, + "learning_rate": 2.542276968191708e-05, + "loss": 3.4772, + "step": 1501184 + }, + { + "epoch": 0.02, + "learning_rate": 2.541438373440656e-05, + "loss": 3.4731, + "step": 1501696 + }, + { + "epoch": 0.02, + "learning_rate": 2.540599778689604e-05, + "loss": 3.4631, + "step": 1502208 + }, + { + "epoch": 0.02, + "learning_rate": 2.5397611839385523e-05, + "loss": 3.4656, + "step": 1502720 + }, + { + "epoch": 0.02, + "learning_rate": 2.5389242270678732e-05, + "loss": 3.476, + "step": 1503232 + }, + { + "epoch": 0.02, + "learning_rate": 2.5380856323168212e-05, + "loss": 3.4568, + "step": 1503744 + }, + { + "epoch": 0.02, + "learning_rate": 2.5372470375657692e-05, + "loss": 3.4652, + "step": 1504256 + }, + { + "epoch": 0.02, + "learning_rate": 2.5364084428147172e-05, + "loss": 3.4674, + "step": 1504768 + }, + { + "epoch": 0.02, + "learning_rate": 2.5355714859440384e-05, + "loss": 3.4771, + "step": 1505280 + }, + { + "epoch": 0.02, + "learning_rate": 2.5347328911929864e-05, + "loss": 3.4507, + "step": 1505792 + }, + { + "epoch": 0.02, + "learning_rate": 2.5338942964419344e-05, + "loss": 3.4674, + "step": 1506304 + }, + { + "epoch": 0.02, + "learning_rate": 2.5330557016908824e-05, + "loss": 3.4601, + "step": 1506816 + }, + { + "epoch": 0.02, + "learning_rate": 2.5322171069398304e-05, + "loss": 3.4659, + "step": 1507328 + }, + { + "epoch": 0.02, + "learning_rate": 2.5313801500691513e-05, + "loss": 3.4695, + "step": 1507840 + }, + { + "epoch": 0.02, + "learning_rate": 2.5305415553180993e-05, + "loss": 3.4596, + "step": 1508352 + }, + { + "epoch": 0.02, + "learning_rate": 2.5297029605670473e-05, + "loss": 3.4778, + "step": 1508864 + }, + { + "epoch": 0.02, + "learning_rate": 2.5288643658159956e-05, + "loss": 3.4696, + "step": 1509376 + }, + { + "epoch": 0.02, + "learning_rate": 2.5280274089453166e-05, + "loss": 3.4611, + "step": 1509888 + }, + { + "epoch": 0.02, + "learning_rate": 2.5271888141942645e-05, + "loss": 3.4724, + "step": 1510400 + }, + { + "epoch": 0.02, + "learning_rate": 2.5263502194432125e-05, + "loss": 3.4691, + "step": 1510912 + }, + { + "epoch": 0.02, + "learning_rate": 2.5255116246921605e-05, + "loss": 3.4654, + "step": 1511424 + }, + { + "epoch": 0.02, + "learning_rate": 2.5246730299411085e-05, + "loss": 3.4465, + "step": 1511936 + }, + { + "epoch": 0.02, + "learning_rate": 2.5238360730704298e-05, + "loss": 3.4751, + "step": 1512448 + }, + { + "epoch": 0.02, + "learning_rate": 2.5229974783193778e-05, + "loss": 3.4663, + "step": 1512960 + }, + { + "epoch": 0.02, + "learning_rate": 2.5221588835683258e-05, + "loss": 3.4686, + "step": 1513472 + }, + { + "epoch": 0.02, + "learning_rate": 2.5213202888172738e-05, + "loss": 3.4648, + "step": 1513984 + }, + { + "epoch": 0.02, + "learning_rate": 2.5204833319465947e-05, + "loss": 3.4756, + "step": 1514496 + }, + { + "epoch": 0.02, + "learning_rate": 2.5196447371955427e-05, + "loss": 3.463, + "step": 1515008 + }, + { + "epoch": 0.02, + "learning_rate": 2.518806142444491e-05, + "loss": 3.4601, + "step": 1515520 + }, + { + "epoch": 0.02, + "learning_rate": 2.517967547693439e-05, + "loss": 3.4555, + "step": 1516032 + }, + { + "epoch": 0.02, + "learning_rate": 2.517128952942387e-05, + "loss": 3.4732, + "step": 1516544 + }, + { + "epoch": 0.02, + "learning_rate": 2.516291996071708e-05, + "loss": 3.4737, + "step": 1517056 + }, + { + "epoch": 0.02, + "learning_rate": 2.515453401320656e-05, + "loss": 3.4707, + "step": 1517568 + }, + { + "epoch": 0.02, + "learning_rate": 2.514614806569604e-05, + "loss": 3.4602, + "step": 1518080 + }, + { + "epoch": 0.02, + "learning_rate": 2.513776211818552e-05, + "loss": 3.474, + "step": 1518592 + }, + { + "epoch": 0.02, + "learning_rate": 2.512939254947873e-05, + "loss": 3.4702, + "step": 1519104 + }, + { + "epoch": 0.02, + "learning_rate": 2.512100660196821e-05, + "loss": 3.4602, + "step": 1519616 + }, + { + "epoch": 0.02, + "learning_rate": 2.511262065445769e-05, + "loss": 3.4693, + "step": 1520128 + }, + { + "epoch": 0.02, + "learning_rate": 2.510423470694717e-05, + "loss": 3.4676, + "step": 1520640 + }, + { + "epoch": 0.02, + "learning_rate": 2.5095848759436648e-05, + "loss": 3.4733, + "step": 1521152 + }, + { + "epoch": 0.02, + "learning_rate": 2.5087479190729864e-05, + "loss": 3.4752, + "step": 1521664 + }, + { + "epoch": 0.02, + "learning_rate": 2.5079093243219344e-05, + "loss": 3.4606, + "step": 1522176 + }, + { + "epoch": 0.02, + "learning_rate": 2.5070707295708817e-05, + "loss": 3.4692, + "step": 1522688 + }, + { + "epoch": 0.02, + "learning_rate": 2.5062321348198297e-05, + "loss": 3.4666, + "step": 1523200 + }, + { + "epoch": 0.02, + "learning_rate": 2.5053951779491513e-05, + "loss": 3.4606, + "step": 1523712 + }, + { + "epoch": 0.02, + "learning_rate": 2.5045565831980993e-05, + "loss": 3.4819, + "step": 1524224 + }, + { + "epoch": 0.02, + "learning_rate": 2.503717988447047e-05, + "loss": 3.4694, + "step": 1524736 + }, + { + "epoch": 0.02, + "learning_rate": 2.502879393695995e-05, + "loss": 3.4702, + "step": 1525248 + }, + { + "epoch": 0.02, + "learning_rate": 2.502040798944943e-05, + "loss": 3.463, + "step": 1525760 + }, + { + "epoch": 0.02, + "learning_rate": 2.5012038420742645e-05, + "loss": 3.4689, + "step": 1526272 + }, + { + "epoch": 0.03, + "eval_loss": 3.904942750930786, + "eval_runtime": 309.8417, + "eval_samples_per_second": 1231.568, + "eval_steps_per_second": 38.487, + "step": 1526390 + }, + { + "epoch": 1.0, + "learning_rate": 2.5003652473232118e-05, + "loss": 3.464, + "step": 1526784 + }, + { + "epoch": 1.0, + "learning_rate": 2.49952665257216e-05, + "loss": 3.471, + "step": 1527296 + }, + { + "epoch": 1.0, + "learning_rate": 2.498688057821108e-05, + "loss": 3.4715, + "step": 1527808 + }, + { + "epoch": 1.0, + "learning_rate": 2.4978511009504294e-05, + "loss": 3.4704, + "step": 1528320 + }, + { + "epoch": 1.0, + "learning_rate": 2.4970125061993774e-05, + "loss": 3.4791, + "step": 1528832 + }, + { + "epoch": 1.0, + "learning_rate": 2.4961739114483254e-05, + "loss": 3.4602, + "step": 1529344 + }, + { + "epoch": 1.0, + "learning_rate": 2.4953353166972734e-05, + "loss": 3.4667, + "step": 1529856 + }, + { + "epoch": 1.0, + "learning_rate": 2.494496721946221e-05, + "loss": 3.4541, + "step": 1530368 + }, + { + "epoch": 1.0, + "learning_rate": 2.4936597650755426e-05, + "loss": 3.4738, + "step": 1530880 + }, + { + "epoch": 1.0, + "learning_rate": 2.4928211703244906e-05, + "loss": 3.4641, + "step": 1531392 + }, + { + "epoch": 1.0, + "learning_rate": 2.4919825755734383e-05, + "loss": 3.4704, + "step": 1531904 + }, + { + "epoch": 1.0, + "learning_rate": 2.4911439808223863e-05, + "loss": 3.4677, + "step": 1532416 + }, + { + "epoch": 1.0, + "learning_rate": 2.4903070239517075e-05, + "loss": 3.4624, + "step": 1532928 + }, + { + "epoch": 1.0, + "learning_rate": 2.4894684292006555e-05, + "loss": 3.4539, + "step": 1533440 + }, + { + "epoch": 1.0, + "learning_rate": 2.4886298344496035e-05, + "loss": 3.4595, + "step": 1533952 + }, + { + "epoch": 1.0, + "learning_rate": 2.4877912396985515e-05, + "loss": 3.454, + "step": 1534464 + }, + { + "epoch": 1.0, + "learning_rate": 2.4869526449474995e-05, + "loss": 3.4621, + "step": 1534976 + }, + { + "epoch": 1.0, + "learning_rate": 2.4861156880768208e-05, + "loss": 3.464, + "step": 1535488 + }, + { + "epoch": 1.0, + "learning_rate": 2.4852770933257684e-05, + "loss": 3.4561, + "step": 1536000 + }, + { + "epoch": 1.0, + "learning_rate": 2.4844384985747164e-05, + "loss": 3.4865, + "step": 1536512 + }, + { + "epoch": 1.0, + "learning_rate": 2.4835999038236647e-05, + "loss": 3.4637, + "step": 1537024 + }, + { + "epoch": 1.0, + "learning_rate": 2.4827629469529857e-05, + "loss": 3.462, + "step": 1537536 + }, + { + "epoch": 1.0, + "learning_rate": 2.4819243522019337e-05, + "loss": 3.4691, + "step": 1538048 + }, + { + "epoch": 1.0, + "learning_rate": 2.4810857574508816e-05, + "loss": 3.4649, + "step": 1538560 + }, + { + "epoch": 1.0, + "learning_rate": 2.4802471626998296e-05, + "loss": 3.4601, + "step": 1539072 + }, + { + "epoch": 1.0, + "learning_rate": 2.479410205829151e-05, + "loss": 3.4575, + "step": 1539584 + }, + { + "epoch": 1.0, + "learning_rate": 2.478571611078099e-05, + "loss": 3.4706, + "step": 1540096 + }, + { + "epoch": 1.0, + "learning_rate": 2.477733016327047e-05, + "loss": 3.4449, + "step": 1540608 + }, + { + "epoch": 1.0, + "learning_rate": 2.476894421575995e-05, + "loss": 3.4584, + "step": 1541120 + }, + { + "epoch": 1.0, + "learning_rate": 2.476055826824943e-05, + "loss": 3.46, + "step": 1541632 + }, + { + "epoch": 1.01, + "learning_rate": 2.475217232073891e-05, + "loss": 3.4613, + "step": 1542144 + }, + { + "epoch": 1.01, + "learning_rate": 2.4743802752032118e-05, + "loss": 3.4656, + "step": 1542656 + }, + { + "epoch": 1.01, + "learning_rate": 2.47354168045216e-05, + "loss": 3.4607, + "step": 1543168 + }, + { + "epoch": 1.01, + "learning_rate": 2.472703085701108e-05, + "loss": 3.4586, + "step": 1543680 + }, + { + "epoch": 1.01, + "learning_rate": 2.471864490950056e-05, + "loss": 3.465, + "step": 1544192 + }, + { + "epoch": 1.01, + "learning_rate": 2.4710258961990038e-05, + "loss": 3.4758, + "step": 1544704 + }, + { + "epoch": 1.01, + "learning_rate": 2.4701873014479518e-05, + "loss": 3.4519, + "step": 1545216 + }, + { + "epoch": 1.01, + "learning_rate": 2.469350344577273e-05, + "loss": 3.4673, + "step": 1545728 + }, + { + "epoch": 1.01, + "learning_rate": 2.468511749826221e-05, + "loss": 3.4515, + "step": 1546240 + }, + { + "epoch": 1.01, + "learning_rate": 2.467673155075169e-05, + "loss": 3.4639, + "step": 1546752 + }, + { + "epoch": 1.01, + "learning_rate": 2.466834560324117e-05, + "loss": 3.4511, + "step": 1547264 + }, + { + "epoch": 1.01, + "learning_rate": 2.465995965573065e-05, + "loss": 3.4757, + "step": 1547776 + }, + { + "epoch": 1.01, + "learning_rate": 2.465157370822013e-05, + "loss": 3.4662, + "step": 1548288 + }, + { + "epoch": 1.01, + "learning_rate": 2.464320413951334e-05, + "loss": 3.4609, + "step": 1548800 + }, + { + "epoch": 1.01, + "learning_rate": 2.463481819200282e-05, + "loss": 3.468, + "step": 1549312 + }, + { + "epoch": 1.01, + "learning_rate": 2.4626432244492302e-05, + "loss": 3.4575, + "step": 1549824 + }, + { + "epoch": 1.01, + "learning_rate": 2.4618046296981782e-05, + "loss": 3.4649, + "step": 1550336 + }, + { + "epoch": 1.01, + "learning_rate": 2.4609660349471262e-05, + "loss": 3.4515, + "step": 1550848 + }, + { + "epoch": 1.01, + "learning_rate": 2.460129078076447e-05, + "loss": 3.4524, + "step": 1551360 + }, + { + "epoch": 1.01, + "learning_rate": 2.459290483325395e-05, + "loss": 3.4734, + "step": 1551872 + }, + { + "epoch": 1.01, + "learning_rate": 2.458451888574343e-05, + "loss": 3.4584, + "step": 1552384 + }, + { + "epoch": 1.01, + "learning_rate": 2.457613293823291e-05, + "loss": 3.4649, + "step": 1552896 + }, + { + "epoch": 1.01, + "learning_rate": 2.4567763369526124e-05, + "loss": 3.4526, + "step": 1553408 + }, + { + "epoch": 1.01, + "learning_rate": 2.4559377422015604e-05, + "loss": 3.4641, + "step": 1553920 + }, + { + "epoch": 1.01, + "learning_rate": 2.4550991474505083e-05, + "loss": 3.4513, + "step": 1554432 + }, + { + "epoch": 1.01, + "learning_rate": 2.4542605526994563e-05, + "loss": 3.466, + "step": 1554944 + }, + { + "epoch": 1.01, + "learning_rate": 2.4534219579484043e-05, + "loss": 3.4643, + "step": 1555456 + }, + { + "epoch": 1.01, + "learning_rate": 2.4525850010777256e-05, + "loss": 3.4738, + "step": 1555968 + }, + { + "epoch": 1.01, + "learning_rate": 2.4517464063266736e-05, + "loss": 3.4624, + "step": 1556480 + }, + { + "epoch": 1.01, + "learning_rate": 2.4509078115756216e-05, + "loss": 3.4562, + "step": 1556992 + }, + { + "epoch": 1.01, + "learning_rate": 2.4500692168245692e-05, + "loss": 3.4545, + "step": 1557504 + }, + { + "epoch": 1.01, + "learning_rate": 2.4492322599538905e-05, + "loss": 3.4659, + "step": 1558016 + }, + { + "epoch": 1.01, + "learning_rate": 2.4483936652028385e-05, + "loss": 3.4528, + "step": 1558528 + }, + { + "epoch": 1.01, + "learning_rate": 2.4475550704517865e-05, + "loss": 3.4561, + "step": 1559040 + }, + { + "epoch": 1.01, + "learning_rate": 2.4467164757007345e-05, + "loss": 3.4568, + "step": 1559552 + }, + { + "epoch": 1.01, + "learning_rate": 2.4458795188300557e-05, + "loss": 3.4616, + "step": 1560064 + }, + { + "epoch": 1.01, + "learning_rate": 2.4450409240790037e-05, + "loss": 3.445, + "step": 1560576 + }, + { + "epoch": 1.01, + "learning_rate": 2.4442023293279514e-05, + "loss": 3.4537, + "step": 1561088 + }, + { + "epoch": 1.01, + "learning_rate": 2.4433637345768994e-05, + "loss": 3.4486, + "step": 1561600 + }, + { + "epoch": 1.01, + "learning_rate": 2.442526777706221e-05, + "loss": 3.4641, + "step": 1562112 + }, + { + "epoch": 1.01, + "learning_rate": 2.441688182955169e-05, + "loss": 3.4633, + "step": 1562624 + }, + { + "epoch": 1.01, + "learning_rate": 2.4408495882041166e-05, + "loss": 3.4577, + "step": 1563136 + }, + { + "epoch": 1.01, + "learning_rate": 2.4400109934530646e-05, + "loss": 3.4593, + "step": 1563648 + }, + { + "epoch": 1.01, + "learning_rate": 2.439174036582386e-05, + "loss": 3.4576, + "step": 1564160 + }, + { + "epoch": 1.01, + "learning_rate": 2.438335441831334e-05, + "loss": 3.4727, + "step": 1564672 + }, + { + "epoch": 1.01, + "learning_rate": 2.437496847080282e-05, + "loss": 3.4501, + "step": 1565184 + }, + { + "epoch": 1.01, + "learning_rate": 2.43665825232923e-05, + "loss": 3.4648, + "step": 1565696 + }, + { + "epoch": 1.01, + "learning_rate": 2.435819657578178e-05, + "loss": 3.4623, + "step": 1566208 + }, + { + "epoch": 1.01, + "learning_rate": 2.4349827007074987e-05, + "loss": 3.4576, + "step": 1566720 + }, + { + "epoch": 1.01, + "learning_rate": 2.4341441059564467e-05, + "loss": 3.4654, + "step": 1567232 + }, + { + "epoch": 1.01, + "learning_rate": 2.4333055112053947e-05, + "loss": 3.4604, + "step": 1567744 + }, + { + "epoch": 1.01, + "learning_rate": 2.4324669164543427e-05, + "loss": 3.4667, + "step": 1568256 + }, + { + "epoch": 1.01, + "learning_rate": 2.431628321703291e-05, + "loss": 3.4614, + "step": 1568768 + }, + { + "epoch": 1.01, + "learning_rate": 2.430789726952239e-05, + "loss": 3.4459, + "step": 1569280 + }, + { + "epoch": 1.01, + "learning_rate": 2.42995277008156e-05, + "loss": 3.4605, + "step": 1569792 + }, + { + "epoch": 1.01, + "learning_rate": 2.429114175330508e-05, + "loss": 3.4549, + "step": 1570304 + }, + { + "epoch": 1.01, + "learning_rate": 2.428275580579456e-05, + "loss": 3.4637, + "step": 1570816 + }, + { + "epoch": 1.01, + "learning_rate": 2.427436985828404e-05, + "loss": 3.4576, + "step": 1571328 + }, + { + "epoch": 1.01, + "learning_rate": 2.426598391077352e-05, + "loss": 3.4503, + "step": 1571840 + }, + { + "epoch": 1.02, + "learning_rate": 2.4257597963263e-05, + "loss": 3.4596, + "step": 1572352 + }, + { + "epoch": 1.02, + "learning_rate": 2.4249228394556212e-05, + "loss": 3.457, + "step": 1572864 + }, + { + "epoch": 1.02, + "learning_rate": 2.4240842447045692e-05, + "loss": 3.4605, + "step": 1573376 + }, + { + "epoch": 1.02, + "learning_rate": 2.423245649953517e-05, + "loss": 3.446, + "step": 1573888 + }, + { + "epoch": 1.02, + "learning_rate": 2.422407055202465e-05, + "loss": 3.4637, + "step": 1574400 + }, + { + "epoch": 1.02, + "learning_rate": 2.421568460451413e-05, + "loss": 3.4727, + "step": 1574912 + }, + { + "epoch": 1.02, + "learning_rate": 2.4207298657003612e-05, + "loss": 3.4548, + "step": 1575424 + }, + { + "epoch": 1.02, + "learning_rate": 2.419892908829682e-05, + "loss": 3.4406, + "step": 1575936 + }, + { + "epoch": 1.02, + "learning_rate": 2.41905431407863e-05, + "loss": 3.4563, + "step": 1576448 + }, + { + "epoch": 1.02, + "learning_rate": 2.418215719327578e-05, + "loss": 3.4565, + "step": 1576960 + }, + { + "epoch": 1.02, + "learning_rate": 2.417377124576526e-05, + "loss": 3.4651, + "step": 1577472 + }, + { + "epoch": 1.02, + "learning_rate": 2.416538529825474e-05, + "loss": 3.461, + "step": 1577984 + }, + { + "epoch": 1.02, + "learning_rate": 2.415699935074422e-05, + "loss": 3.4519, + "step": 1578496 + }, + { + "epoch": 1.02, + "learning_rate": 2.4148613403233704e-05, + "loss": 3.4517, + "step": 1579008 + }, + { + "epoch": 1.02, + "learning_rate": 2.4140243834526913e-05, + "loss": 3.4652, + "step": 1579520 + }, + { + "epoch": 1.02, + "learning_rate": 2.4131857887016393e-05, + "loss": 3.4459, + "step": 1580032 + }, + { + "epoch": 1.02, + "learning_rate": 2.4123471939505873e-05, + "loss": 3.4517, + "step": 1580544 + }, + { + "epoch": 1.02, + "learning_rate": 2.411508599199535e-05, + "loss": 3.4532, + "step": 1581056 + }, + { + "epoch": 1.02, + "learning_rate": 2.4106700044484833e-05, + "loss": 3.4647, + "step": 1581568 + }, + { + "epoch": 1.02, + "learning_rate": 2.4098330475778045e-05, + "loss": 3.4393, + "step": 1582080 + }, + { + "epoch": 1.02, + "learning_rate": 2.4089944528267525e-05, + "loss": 3.4597, + "step": 1582592 + }, + { + "epoch": 1.02, + "learning_rate": 2.4081558580757002e-05, + "loss": 3.4453, + "step": 1583104 + }, + { + "epoch": 1.02, + "learning_rate": 2.4073172633246482e-05, + "loss": 3.456, + "step": 1583616 + }, + { + "epoch": 1.02, + "learning_rate": 2.4064803064539694e-05, + "loss": 3.4556, + "step": 1584128 + }, + { + "epoch": 1.02, + "learning_rate": 2.4056417117029174e-05, + "loss": 3.4475, + "step": 1584640 + }, + { + "epoch": 1.02, + "learning_rate": 2.4048031169518654e-05, + "loss": 3.4628, + "step": 1585152 + }, + { + "epoch": 1.02, + "learning_rate": 2.4039645222008134e-05, + "loss": 3.4614, + "step": 1585664 + }, + { + "epoch": 1.02, + "learning_rate": 2.4031275653301347e-05, + "loss": 3.4474, + "step": 1586176 + }, + { + "epoch": 1.02, + "learning_rate": 2.4022889705790823e-05, + "loss": 3.4603, + "step": 1586688 + }, + { + "epoch": 1.02, + "learning_rate": 2.4014503758280303e-05, + "loss": 3.4551, + "step": 1587200 + }, + { + "epoch": 1.02, + "learning_rate": 2.4006117810769783e-05, + "loss": 3.4568, + "step": 1587712 + }, + { + "epoch": 1.02, + "learning_rate": 2.3997731863259266e-05, + "loss": 3.4378, + "step": 1588224 + }, + { + "epoch": 1.02, + "learning_rate": 2.3989362294552476e-05, + "loss": 3.4642, + "step": 1588736 + }, + { + "epoch": 1.02, + "learning_rate": 2.3980976347041956e-05, + "loss": 3.4488, + "step": 1589248 + }, + { + "epoch": 1.02, + "learning_rate": 2.3972590399531435e-05, + "loss": 3.4578, + "step": 1589760 + }, + { + "epoch": 1.02, + "learning_rate": 2.3964204452020915e-05, + "loss": 3.4501, + "step": 1590272 + }, + { + "epoch": 1.02, + "learning_rate": 2.3955834883314128e-05, + "loss": 3.4644, + "step": 1590784 + }, + { + "epoch": 1.02, + "learning_rate": 2.3947448935803608e-05, + "loss": 3.4581, + "step": 1591296 + }, + { + "epoch": 1.02, + "learning_rate": 2.3939062988293088e-05, + "loss": 3.4468, + "step": 1591808 + }, + { + "epoch": 1.02, + "learning_rate": 2.3930677040782568e-05, + "loss": 3.4438, + "step": 1592320 + }, + { + "epoch": 1.02, + "learning_rate": 2.3922291093272048e-05, + "loss": 3.4612, + "step": 1592832 + }, + { + "epoch": 1.02, + "learning_rate": 2.3913921524565257e-05, + "loss": 3.4588, + "step": 1593344 + }, + { + "epoch": 1.02, + "learning_rate": 2.3905535577054737e-05, + "loss": 3.4596, + "step": 1593856 + }, + { + "epoch": 1.02, + "learning_rate": 2.389714962954422e-05, + "loss": 3.4486, + "step": 1594368 + }, + { + "epoch": 1.02, + "learning_rate": 2.38887636820337e-05, + "loss": 3.4581, + "step": 1594880 + }, + { + "epoch": 1.02, + "learning_rate": 2.388037773452318e-05, + "loss": 3.4599, + "step": 1595392 + }, + { + "epoch": 1.02, + "learning_rate": 2.3871991787012657e-05, + "loss": 3.4486, + "step": 1595904 + }, + { + "epoch": 1.02, + "learning_rate": 2.386362221830587e-05, + "loss": 3.4562, + "step": 1596416 + }, + { + "epoch": 1.02, + "learning_rate": 2.385523627079535e-05, + "loss": 3.4584, + "step": 1596928 + }, + { + "epoch": 1.02, + "learning_rate": 2.384685032328483e-05, + "loss": 3.4588, + "step": 1597440 + }, + { + "epoch": 1.02, + "learning_rate": 2.383846437577431e-05, + "loss": 3.4662, + "step": 1597952 + }, + { + "epoch": 1.02, + "learning_rate": 2.383007842826379e-05, + "loss": 3.4486, + "step": 1598464 + }, + { + "epoch": 1.02, + "learning_rate": 2.3821708859557e-05, + "loss": 3.4577, + "step": 1598976 + }, + { + "epoch": 1.02, + "learning_rate": 2.3813322912046478e-05, + "loss": 3.4529, + "step": 1599488 + }, + { + "epoch": 1.02, + "learning_rate": 2.3804936964535958e-05, + "loss": 3.4524, + "step": 1600000 + }, + { + "epoch": 1.02, + "learning_rate": 2.379655101702544e-05, + "loss": 3.4653, + "step": 1600512 + }, + { + "epoch": 1.02, + "learning_rate": 2.378816506951492e-05, + "loss": 3.4526, + "step": 1601024 + }, + { + "epoch": 1.02, + "learning_rate": 2.37797791220044e-05, + "loss": 3.461, + "step": 1601536 + }, + { + "epoch": 1.02, + "learning_rate": 2.377140955329761e-05, + "loss": 3.4447, + "step": 1602048 + }, + { + "epoch": 1.02, + "learning_rate": 2.376302360578709e-05, + "loss": 3.4616, + "step": 1602560 + }, + { + "epoch": 1.03, + "eval_loss": 3.9053592681884766, + "eval_runtime": 317.6552, + "eval_samples_per_second": 1201.274, + "eval_steps_per_second": 37.541, + "step": 1602710 + }, + { + "epoch": 0.0, + "learning_rate": 2.3754654037080303e-05, + "loss": 3.4489, + "step": 1603072 + }, + { + "epoch": 0.0, + "learning_rate": 2.3746268089569783e-05, + "loss": 3.4588, + "step": 1603584 + }, + { + "epoch": 0.0, + "learning_rate": 2.3737882142059263e-05, + "loss": 3.461, + "step": 1604096 + }, + { + "epoch": 0.0, + "learning_rate": 2.3729496194548743e-05, + "loss": 3.4546, + "step": 1604608 + }, + { + "epoch": 0.0, + "learning_rate": 2.3721126625841952e-05, + "loss": 3.4636, + "step": 1605120 + }, + { + "epoch": 0.0, + "learning_rate": 2.371274067833143e-05, + "loss": 3.4537, + "step": 1605632 + }, + { + "epoch": 0.0, + "learning_rate": 2.370435473082091e-05, + "loss": 3.4495, + "step": 1606144 + }, + { + "epoch": 0.0, + "learning_rate": 2.3695968783310395e-05, + "loss": 3.4444, + "step": 1606656 + }, + { + "epoch": 0.0, + "learning_rate": 2.3687582835799875e-05, + "loss": 3.4584, + "step": 1607168 + }, + { + "epoch": 0.0, + "learning_rate": 2.3679196888289355e-05, + "loss": 3.4585, + "step": 1607680 + }, + { + "epoch": 0.0, + "learning_rate": 2.3670810940778835e-05, + "loss": 3.4533, + "step": 1608192 + }, + { + "epoch": 0.0, + "learning_rate": 2.366242499326831e-05, + "loss": 3.4535, + "step": 1608704 + }, + { + "epoch": 0.0, + "learning_rate": 2.3654071803365256e-05, + "loss": 3.4473, + "step": 1609216 + }, + { + "epoch": 0.0, + "learning_rate": 2.3645685855854736e-05, + "loss": 3.4441, + "step": 1609728 + }, + { + "epoch": 0.0, + "learning_rate": 2.3637299908344216e-05, + "loss": 3.4522, + "step": 1610240 + }, + { + "epoch": 0.0, + "learning_rate": 2.3628913960833696e-05, + "loss": 3.4364, + "step": 1610752 + }, + { + "epoch": 0.0, + "learning_rate": 2.3620528013323176e-05, + "loss": 3.4496, + "step": 1611264 + }, + { + "epoch": 0.0, + "learning_rate": 2.3612158444616385e-05, + "loss": 3.4502, + "step": 1611776 + }, + { + "epoch": 0.0, + "learning_rate": 2.3603772497105865e-05, + "loss": 3.4429, + "step": 1612288 + }, + { + "epoch": 0.0, + "learning_rate": 2.3595386549595345e-05, + "loss": 3.4779, + "step": 1612800 + }, + { + "epoch": 0.0, + "learning_rate": 2.358700060208483e-05, + "loss": 3.4491, + "step": 1613312 + }, + { + "epoch": 0.0, + "learning_rate": 2.3578631033378038e-05, + "loss": 3.4549, + "step": 1613824 + }, + { + "epoch": 0.0, + "learning_rate": 2.3570245085867518e-05, + "loss": 3.4532, + "step": 1614336 + }, + { + "epoch": 0.0, + "learning_rate": 2.3561859138356998e-05, + "loss": 3.4553, + "step": 1614848 + }, + { + "epoch": 0.0, + "learning_rate": 2.3553473190846478e-05, + "loss": 3.443, + "step": 1615360 + }, + { + "epoch": 0.0, + "learning_rate": 2.354510362213969e-05, + "loss": 3.4512, + "step": 1615872 + }, + { + "epoch": 0.0, + "learning_rate": 2.353671767462917e-05, + "loss": 3.4565, + "step": 1616384 + }, + { + "epoch": 0.0, + "learning_rate": 2.352833172711865e-05, + "loss": 3.4347, + "step": 1616896 + }, + { + "epoch": 0.0, + "learning_rate": 2.351994577960813e-05, + "loss": 3.4457, + "step": 1617408 + }, + { + "epoch": 0.0, + "learning_rate": 2.351157621090134e-05, + "loss": 3.4424, + "step": 1617920 + }, + { + "epoch": 0.01, + "learning_rate": 2.350319026339082e-05, + "loss": 3.4496, + "step": 1618432 + }, + { + "epoch": 0.01, + "learning_rate": 2.34948043158803e-05, + "loss": 3.4516, + "step": 1618944 + }, + { + "epoch": 0.01, + "learning_rate": 2.3486418368369782e-05, + "loss": 3.4512, + "step": 1619456 + }, + { + "epoch": 0.01, + "learning_rate": 2.347803242085926e-05, + "loss": 3.4533, + "step": 1619968 + }, + { + "epoch": 0.01, + "learning_rate": 2.346966285215247e-05, + "loss": 3.4525, + "step": 1620480 + }, + { + "epoch": 0.01, + "learning_rate": 2.346127690464195e-05, + "loss": 3.4573, + "step": 1620992 + }, + { + "epoch": 0.01, + "learning_rate": 2.3452890957131428e-05, + "loss": 3.4429, + "step": 1621504 + }, + { + "epoch": 0.01, + "learning_rate": 2.344450500962091e-05, + "loss": 3.4563, + "step": 1622016 + }, + { + "epoch": 0.01, + "learning_rate": 2.343611906211039e-05, + "loss": 3.4385, + "step": 1622528 + }, + { + "epoch": 0.01, + "learning_rate": 2.3427749493403604e-05, + "loss": 3.4508, + "step": 1623040 + }, + { + "epoch": 0.01, + "learning_rate": 2.341936354589308e-05, + "loss": 3.4367, + "step": 1623552 + }, + { + "epoch": 0.01, + "learning_rate": 2.341097759838256e-05, + "loss": 3.4656, + "step": 1624064 + }, + { + "epoch": 0.01, + "learning_rate": 2.340259165087204e-05, + "loss": 3.4563, + "step": 1624576 + }, + { + "epoch": 0.01, + "learning_rate": 2.3394222082165253e-05, + "loss": 3.4474, + "step": 1625088 + }, + { + "epoch": 0.01, + "learning_rate": 2.3385836134654733e-05, + "loss": 3.4555, + "step": 1625600 + }, + { + "epoch": 0.01, + "learning_rate": 2.3377450187144212e-05, + "loss": 3.4523, + "step": 1626112 + }, + { + "epoch": 0.01, + "learning_rate": 2.3369064239633692e-05, + "loss": 3.4516, + "step": 1626624 + }, + { + "epoch": 0.01, + "learning_rate": 2.33606946709269e-05, + "loss": 3.4364, + "step": 1627136 + }, + { + "epoch": 0.01, + "learning_rate": 2.335230872341638e-05, + "loss": 3.4381, + "step": 1627648 + }, + { + "epoch": 0.01, + "learning_rate": 2.3343922775905865e-05, + "loss": 3.4636, + "step": 1628160 + }, + { + "epoch": 0.01, + "learning_rate": 2.3335536828395345e-05, + "loss": 3.4476, + "step": 1628672 + }, + { + "epoch": 0.01, + "learning_rate": 2.3327167259688554e-05, + "loss": 3.4541, + "step": 1629184 + }, + { + "epoch": 0.01, + "learning_rate": 2.3318781312178034e-05, + "loss": 3.4451, + "step": 1629696 + }, + { + "epoch": 0.01, + "learning_rate": 2.3310395364667514e-05, + "loss": 3.446, + "step": 1630208 + }, + { + "epoch": 0.01, + "learning_rate": 2.3302009417156994e-05, + "loss": 3.4418, + "step": 1630720 + }, + { + "epoch": 0.01, + "learning_rate": 2.3293639848450206e-05, + "loss": 3.4507, + "step": 1631232 + }, + { + "epoch": 0.01, + "learning_rate": 2.3285253900939686e-05, + "loss": 3.4513, + "step": 1631744 + }, + { + "epoch": 0.01, + "learning_rate": 2.3276867953429166e-05, + "loss": 3.4624, + "step": 1632256 + }, + { + "epoch": 0.01, + "learning_rate": 2.3268482005918646e-05, + "loss": 3.4512, + "step": 1632768 + }, + { + "epoch": 0.01, + "learning_rate": 2.3260096058408126e-05, + "loss": 3.4419, + "step": 1633280 + }, + { + "epoch": 0.01, + "learning_rate": 2.3251726489701335e-05, + "loss": 3.4417, + "step": 1633792 + }, + { + "epoch": 0.01, + "learning_rate": 2.3243340542190815e-05, + "loss": 3.4549, + "step": 1634304 + }, + { + "epoch": 0.01, + "learning_rate": 2.32349545946803e-05, + "loss": 3.4404, + "step": 1634816 + }, + { + "epoch": 0.01, + "learning_rate": 2.322656864716978e-05, + "loss": 3.4443, + "step": 1635328 + }, + { + "epoch": 0.01, + "learning_rate": 2.321818269965926e-05, + "loss": 3.4464, + "step": 1635840 + }, + { + "epoch": 0.01, + "learning_rate": 2.3209813130952467e-05, + "loss": 3.4503, + "step": 1636352 + }, + { + "epoch": 0.01, + "learning_rate": 2.3201427183441947e-05, + "loss": 3.4338, + "step": 1636864 + }, + { + "epoch": 0.01, + "learning_rate": 2.3193041235931427e-05, + "loss": 3.4422, + "step": 1637376 + }, + { + "epoch": 0.01, + "learning_rate": 2.3184655288420907e-05, + "loss": 3.4347, + "step": 1637888 + }, + { + "epoch": 0.01, + "learning_rate": 2.317628571971412e-05, + "loss": 3.4537, + "step": 1638400 + }, + { + "epoch": 0.01, + "learning_rate": 2.31678997722036e-05, + "loss": 3.4502, + "step": 1638912 + }, + { + "epoch": 0.01, + "learning_rate": 2.315951382469308e-05, + "loss": 3.4467, + "step": 1639424 + }, + { + "epoch": 0.01, + "learning_rate": 2.3151127877182556e-05, + "loss": 3.4492, + "step": 1639936 + }, + { + "epoch": 0.01, + "learning_rate": 2.314275830847577e-05, + "loss": 3.4438, + "step": 1640448 + }, + { + "epoch": 0.01, + "learning_rate": 2.3134372360965252e-05, + "loss": 3.4599, + "step": 1640960 + }, + { + "epoch": 0.01, + "learning_rate": 2.3125986413454732e-05, + "loss": 3.4382, + "step": 1641472 + }, + { + "epoch": 0.01, + "learning_rate": 2.311760046594421e-05, + "loss": 3.4556, + "step": 1641984 + }, + { + "epoch": 0.01, + "learning_rate": 2.310921451843369e-05, + "loss": 3.4466, + "step": 1642496 + }, + { + "epoch": 0.01, + "learning_rate": 2.31008449497269e-05, + "loss": 3.4479, + "step": 1643008 + }, + { + "epoch": 0.01, + "learning_rate": 2.309245900221638e-05, + "loss": 3.456, + "step": 1643520 + }, + { + "epoch": 0.01, + "learning_rate": 2.308407305470586e-05, + "loss": 3.4469, + "step": 1644032 + }, + { + "epoch": 0.01, + "learning_rate": 2.307568710719534e-05, + "loss": 3.4522, + "step": 1644544 + }, + { + "epoch": 0.01, + "learning_rate": 2.306730115968482e-05, + "loss": 3.4496, + "step": 1645056 + }, + { + "epoch": 0.01, + "learning_rate": 2.305893159097803e-05, + "loss": 3.4327, + "step": 1645568 + }, + { + "epoch": 0.01, + "learning_rate": 2.305054564346751e-05, + "loss": 3.4503, + "step": 1646080 + }, + { + "epoch": 0.01, + "learning_rate": 2.304215969595699e-05, + "loss": 3.4454, + "step": 1646592 + }, + { + "epoch": 0.01, + "learning_rate": 2.3033773748446473e-05, + "loss": 3.4512, + "step": 1647104 + }, + { + "epoch": 0.01, + "learning_rate": 2.3025404179739682e-05, + "loss": 3.4467, + "step": 1647616 + }, + { + "epoch": 0.01, + "learning_rate": 2.3017018232229162e-05, + "loss": 3.4357, + "step": 1648128 + }, + { + "epoch": 0.02, + "learning_rate": 2.3008632284718642e-05, + "loss": 3.4483, + "step": 1648640 + }, + { + "epoch": 0.02, + "learning_rate": 2.3000246337208122e-05, + "loss": 3.4491, + "step": 1649152 + }, + { + "epoch": 0.02, + "learning_rate": 2.2991860389697602e-05, + "loss": 3.4463, + "step": 1649664 + }, + { + "epoch": 0.02, + "learning_rate": 2.2983490820990815e-05, + "loss": 3.4341, + "step": 1650176 + }, + { + "epoch": 0.02, + "learning_rate": 2.2975104873480295e-05, + "loss": 3.4528, + "step": 1650688 + }, + { + "epoch": 0.02, + "learning_rate": 2.2966718925969775e-05, + "loss": 3.4601, + "step": 1651200 + }, + { + "epoch": 0.02, + "learning_rate": 2.2958332978459255e-05, + "loss": 3.4459, + "step": 1651712 + }, + { + "epoch": 0.02, + "learning_rate": 2.2949963409752464e-05, + "loss": 3.4312, + "step": 1652224 + }, + { + "epoch": 0.02, + "learning_rate": 2.2941577462241944e-05, + "loss": 3.4443, + "step": 1652736 + }, + { + "epoch": 0.02, + "learning_rate": 2.2933191514731427e-05, + "loss": 3.4455, + "step": 1653248 + }, + { + "epoch": 0.02, + "learning_rate": 2.2924805567220907e-05, + "loss": 3.4524, + "step": 1653760 + }, + { + "epoch": 0.02, + "learning_rate": 2.2916435998514116e-05, + "loss": 3.4501, + "step": 1654272 + }, + { + "epoch": 0.02, + "learning_rate": 2.2908050051003596e-05, + "loss": 3.4397, + "step": 1654784 + }, + { + "epoch": 0.02, + "learning_rate": 2.2899664103493076e-05, + "loss": 3.4437, + "step": 1655296 + }, + { + "epoch": 0.02, + "learning_rate": 2.2891278155982556e-05, + "loss": 3.4494, + "step": 1655808 + }, + { + "epoch": 0.02, + "learning_rate": 2.2882892208472036e-05, + "loss": 3.4339, + "step": 1656320 + }, + { + "epoch": 0.02, + "learning_rate": 2.2874506260961516e-05, + "loss": 3.4411, + "step": 1656832 + }, + { + "epoch": 0.02, + "learning_rate": 2.2866136692254728e-05, + "loss": 3.4404, + "step": 1657344 + }, + { + "epoch": 0.02, + "learning_rate": 2.2857750744744208e-05, + "loss": 3.4521, + "step": 1657856 + }, + { + "epoch": 0.02, + "learning_rate": 2.2849364797233685e-05, + "loss": 3.4283, + "step": 1658368 + }, + { + "epoch": 0.02, + "learning_rate": 2.2840978849723165e-05, + "loss": 3.4436, + "step": 1658880 + }, + { + "epoch": 0.02, + "learning_rate": 2.2832609281016377e-05, + "loss": 3.4371, + "step": 1659392 + }, + { + "epoch": 0.02, + "learning_rate": 2.282422333350586e-05, + "loss": 3.4434, + "step": 1659904 + }, + { + "epoch": 0.02, + "learning_rate": 2.2815837385995337e-05, + "loss": 3.4445, + "step": 1660416 + }, + { + "epoch": 0.02, + "learning_rate": 2.2807451438484817e-05, + "loss": 3.4342, + "step": 1660928 + }, + { + "epoch": 0.02, + "learning_rate": 2.2799065490974297e-05, + "loss": 3.4493, + "step": 1661440 + }, + { + "epoch": 0.02, + "learning_rate": 2.2790679543463777e-05, + "loss": 3.4486, + "step": 1661952 + }, + { + "epoch": 0.02, + "learning_rate": 2.2782293595953257e-05, + "loss": 3.435, + "step": 1662464 + }, + { + "epoch": 0.02, + "learning_rate": 2.277392402724647e-05, + "loss": 3.4517, + "step": 1662976 + }, + { + "epoch": 0.02, + "learning_rate": 2.276553807973595e-05, + "loss": 3.4409, + "step": 1663488 + }, + { + "epoch": 0.02, + "learning_rate": 2.275715213222543e-05, + "loss": 3.4496, + "step": 1664000 + }, + { + "epoch": 0.02, + "learning_rate": 2.274876618471491e-05, + "loss": 3.4289, + "step": 1664512 + }, + { + "epoch": 0.02, + "learning_rate": 2.274039661600812e-05, + "loss": 3.4478, + "step": 1665024 + }, + { + "epoch": 0.02, + "learning_rate": 2.27320106684976e-05, + "loss": 3.4362, + "step": 1665536 + }, + { + "epoch": 0.02, + "learning_rate": 2.272362472098708e-05, + "loss": 3.4472, + "step": 1666048 + }, + { + "epoch": 0.02, + "learning_rate": 2.271523877347656e-05, + "loss": 3.4369, + "step": 1666560 + }, + { + "epoch": 0.02, + "learning_rate": 2.270686920476977e-05, + "loss": 3.4526, + "step": 1667072 + }, + { + "epoch": 0.02, + "learning_rate": 2.269848325725925e-05, + "loss": 3.4458, + "step": 1667584 + }, + { + "epoch": 0.02, + "learning_rate": 2.269009730974873e-05, + "loss": 3.4407, + "step": 1668096 + }, + { + "epoch": 0.02, + "learning_rate": 2.268171136223821e-05, + "loss": 3.4243, + "step": 1668608 + }, + { + "epoch": 0.02, + "learning_rate": 2.267332541472769e-05, + "loss": 3.4549, + "step": 1669120 + }, + { + "epoch": 0.02, + "learning_rate": 2.2664955846020903e-05, + "loss": 3.4438, + "step": 1669632 + }, + { + "epoch": 0.02, + "learning_rate": 2.2656569898510383e-05, + "loss": 3.4495, + "step": 1670144 + }, + { + "epoch": 0.02, + "learning_rate": 2.2648183950999863e-05, + "loss": 3.4374, + "step": 1670656 + }, + { + "epoch": 0.02, + "learning_rate": 2.263979800348934e-05, + "loss": 3.4484, + "step": 1671168 + }, + { + "epoch": 0.02, + "learning_rate": 2.2631428434782552e-05, + "loss": 3.4457, + "step": 1671680 + }, + { + "epoch": 0.02, + "learning_rate": 2.2623042487272035e-05, + "loss": 3.4401, + "step": 1672192 + }, + { + "epoch": 0.02, + "learning_rate": 2.2614656539761512e-05, + "loss": 3.4421, + "step": 1672704 + }, + { + "epoch": 0.02, + "learning_rate": 2.2606270592250992e-05, + "loss": 3.4469, + "step": 1673216 + }, + { + "epoch": 0.02, + "learning_rate": 2.2597884644740472e-05, + "loss": 3.4455, + "step": 1673728 + }, + { + "epoch": 0.02, + "learning_rate": 2.2589515076033684e-05, + "loss": 3.4595, + "step": 1674240 + }, + { + "epoch": 0.02, + "learning_rate": 2.258112912852316e-05, + "loss": 3.4325, + "step": 1674752 + }, + { + "epoch": 0.02, + "learning_rate": 2.2572743181012644e-05, + "loss": 3.4491, + "step": 1675264 + }, + { + "epoch": 0.02, + "learning_rate": 2.2564357233502124e-05, + "loss": 3.4389, + "step": 1675776 + }, + { + "epoch": 0.02, + "learning_rate": 2.2555971285991604e-05, + "loss": 3.4452, + "step": 1676288 + }, + { + "epoch": 0.02, + "learning_rate": 2.2547601717284813e-05, + "loss": 3.4494, + "step": 1676800 + }, + { + "epoch": 0.02, + "learning_rate": 2.2539215769774293e-05, + "loss": 3.4378, + "step": 1677312 + }, + { + "epoch": 0.02, + "learning_rate": 2.2530829822263773e-05, + "loss": 3.451, + "step": 1677824 + }, + { + "epoch": 0.02, + "learning_rate": 2.2522443874753253e-05, + "loss": 3.4395, + "step": 1678336 + }, + { + "epoch": 0.02, + "learning_rate": 2.2514074306046466e-05, + "loss": 3.4481, + "step": 1678848 + }, + { + "epoch": 0.03, + "eval_loss": 3.909003496170044, + "eval_runtime": 306.0127, + "eval_samples_per_second": 1246.978, + "eval_steps_per_second": 38.969, + "step": 1679030 + }, + { + "epoch": 1.0, + "learning_rate": 2.2505688358535946e-05, + "loss": 3.4362, + "step": 1679360 + }, + { + "epoch": 1.0, + "learning_rate": 2.2497302411025426e-05, + "loss": 3.4486, + "step": 1679872 + }, + { + "epoch": 1.0, + "learning_rate": 2.2488916463514905e-05, + "loss": 3.4466, + "step": 1680384 + }, + { + "epoch": 1.0, + "learning_rate": 2.2480546894808115e-05, + "loss": 3.4445, + "step": 1680896 + }, + { + "epoch": 1.0, + "learning_rate": 2.2472160947297598e-05, + "loss": 3.453, + "step": 1681408 + }, + { + "epoch": 1.0, + "learning_rate": 2.2463774999787078e-05, + "loss": 3.4432, + "step": 1681920 + }, + { + "epoch": 1.0, + "learning_rate": 2.2455389052276558e-05, + "loss": 3.4349, + "step": 1682432 + }, + { + "epoch": 1.0, + "learning_rate": 2.2447019483569767e-05, + "loss": 3.4353, + "step": 1682944 + }, + { + "epoch": 1.0, + "learning_rate": 2.2438633536059247e-05, + "loss": 3.4454, + "step": 1683456 + }, + { + "epoch": 1.0, + "learning_rate": 2.2430247588548727e-05, + "loss": 3.4485, + "step": 1683968 + }, + { + "epoch": 1.0, + "learning_rate": 2.2421861641038207e-05, + "loss": 3.4398, + "step": 1684480 + }, + { + "epoch": 1.0, + "learning_rate": 2.241349207233142e-05, + "loss": 3.4469, + "step": 1684992 + }, + { + "epoch": 1.0, + "learning_rate": 2.24051061248209e-05, + "loss": 3.4291, + "step": 1685504 + }, + { + "epoch": 1.0, + "learning_rate": 2.239672017731038e-05, + "loss": 3.4363, + "step": 1686016 + }, + { + "epoch": 1.0, + "learning_rate": 2.238833422979986e-05, + "loss": 3.4405, + "step": 1686528 + }, + { + "epoch": 1.0, + "learning_rate": 2.237994828228934e-05, + "loss": 3.4266, + "step": 1687040 + }, + { + "epoch": 1.0, + "learning_rate": 2.237157871358255e-05, + "loss": 3.4403, + "step": 1687552 + }, + { + "epoch": 1.0, + "learning_rate": 2.236319276607203e-05, + "loss": 3.4329, + "step": 1688064 + }, + { + "epoch": 1.0, + "learning_rate": 2.235480681856151e-05, + "loss": 3.4344, + "step": 1688576 + }, + { + "epoch": 1.0, + "learning_rate": 2.234642087105099e-05, + "loss": 3.4671, + "step": 1689088 + }, + { + "epoch": 1.0, + "learning_rate": 2.2338034923540468e-05, + "loss": 3.4386, + "step": 1689600 + }, + { + "epoch": 1.0, + "learning_rate": 2.232966535483368e-05, + "loss": 3.4384, + "step": 1690112 + }, + { + "epoch": 1.0, + "learning_rate": 2.232127940732316e-05, + "loss": 3.4425, + "step": 1690624 + }, + { + "epoch": 1.0, + "learning_rate": 2.231289345981264e-05, + "loss": 3.4449, + "step": 1691136 + }, + { + "epoch": 1.0, + "learning_rate": 2.230450751230212e-05, + "loss": 3.427, + "step": 1691648 + }, + { + "epoch": 1.0, + "learning_rate": 2.2296137943595333e-05, + "loss": 3.442, + "step": 1692160 + }, + { + "epoch": 1.0, + "learning_rate": 2.2287751996084813e-05, + "loss": 3.4402, + "step": 1692672 + }, + { + "epoch": 1.0, + "learning_rate": 2.227936604857429e-05, + "loss": 3.4246, + "step": 1693184 + }, + { + "epoch": 1.0, + "learning_rate": 2.227098010106377e-05, + "loss": 3.4347, + "step": 1693696 + }, + { + "epoch": 1.0, + "learning_rate": 2.2262594153553253e-05, + "loss": 3.4314, + "step": 1694208 + }, + { + "epoch": 1.01, + "learning_rate": 2.2254208206042733e-05, + "loss": 3.4422, + "step": 1694720 + }, + { + "epoch": 1.01, + "learning_rate": 2.2245838637335942e-05, + "loss": 3.4418, + "step": 1695232 + }, + { + "epoch": 1.01, + "learning_rate": 2.223745268982542e-05, + "loss": 3.4364, + "step": 1695744 + }, + { + "epoch": 1.01, + "learning_rate": 2.22290667423149e-05, + "loss": 3.4409, + "step": 1696256 + }, + { + "epoch": 1.01, + "learning_rate": 2.222068079480438e-05, + "loss": 3.4401, + "step": 1696768 + }, + { + "epoch": 1.01, + "learning_rate": 2.221229484729386e-05, + "loss": 3.4437, + "step": 1697280 + }, + { + "epoch": 1.01, + "learning_rate": 2.2203908899783345e-05, + "loss": 3.4304, + "step": 1697792 + }, + { + "epoch": 1.01, + "learning_rate": 2.2195539331076554e-05, + "loss": 3.4469, + "step": 1698304 + }, + { + "epoch": 1.01, + "learning_rate": 2.2187153383566034e-05, + "loss": 3.4242, + "step": 1698816 + }, + { + "epoch": 1.01, + "learning_rate": 2.2178767436055514e-05, + "loss": 3.4434, + "step": 1699328 + }, + { + "epoch": 1.01, + "learning_rate": 2.2170381488544994e-05, + "loss": 3.4215, + "step": 1699840 + }, + { + "epoch": 1.01, + "learning_rate": 2.216199554103447e-05, + "loss": 3.4566, + "step": 1700352 + }, + { + "epoch": 1.01, + "learning_rate": 2.2153625972327686e-05, + "loss": 3.4411, + "step": 1700864 + }, + { + "epoch": 1.01, + "learning_rate": 2.2145240024817166e-05, + "loss": 3.4416, + "step": 1701376 + }, + { + "epoch": 1.01, + "learning_rate": 2.2136854077306646e-05, + "loss": 3.439, + "step": 1701888 + }, + { + "epoch": 1.01, + "learning_rate": 2.2128468129796123e-05, + "loss": 3.4406, + "step": 1702400 + }, + { + "epoch": 1.01, + "learning_rate": 2.2120098561089335e-05, + "loss": 3.4387, + "step": 1702912 + }, + { + "epoch": 1.01, + "learning_rate": 2.2111712613578815e-05, + "loss": 3.432, + "step": 1703424 + }, + { + "epoch": 1.01, + "learning_rate": 2.2103326666068295e-05, + "loss": 3.4194, + "step": 1703936 + }, + { + "epoch": 1.01, + "learning_rate": 2.2094940718557775e-05, + "loss": 3.4526, + "step": 1704448 + }, + { + "epoch": 1.01, + "learning_rate": 2.2086554771047255e-05, + "loss": 3.4373, + "step": 1704960 + }, + { + "epoch": 1.01, + "learning_rate": 2.2078185202340468e-05, + "loss": 3.4476, + "step": 1705472 + }, + { + "epoch": 1.01, + "learning_rate": 2.2069799254829944e-05, + "loss": 3.432, + "step": 1705984 + }, + { + "epoch": 1.01, + "learning_rate": 2.2061413307319424e-05, + "loss": 3.4365, + "step": 1706496 + }, + { + "epoch": 1.01, + "learning_rate": 2.2053027359808907e-05, + "loss": 3.4251, + "step": 1707008 + }, + { + "epoch": 1.01, + "learning_rate": 2.204465779110212e-05, + "loss": 3.4436, + "step": 1707520 + }, + { + "epoch": 1.01, + "learning_rate": 2.2036271843591596e-05, + "loss": 3.4399, + "step": 1708032 + }, + { + "epoch": 1.01, + "learning_rate": 2.2027885896081076e-05, + "loss": 3.4497, + "step": 1708544 + }, + { + "epoch": 1.01, + "learning_rate": 2.2019499948570556e-05, + "loss": 3.4426, + "step": 1709056 + }, + { + "epoch": 1.01, + "learning_rate": 2.2011114001060036e-05, + "loss": 3.4262, + "step": 1709568 + }, + { + "epoch": 1.01, + "learning_rate": 2.200274443235325e-05, + "loss": 3.4316, + "step": 1710080 + }, + { + "epoch": 1.01, + "learning_rate": 2.199435848484273e-05, + "loss": 3.4428, + "step": 1710592 + }, + { + "epoch": 1.01, + "learning_rate": 2.198597253733221e-05, + "loss": 3.429, + "step": 1711104 + }, + { + "epoch": 1.01, + "learning_rate": 2.197758658982169e-05, + "loss": 3.4319, + "step": 1711616 + }, + { + "epoch": 1.01, + "learning_rate": 2.1969217021114898e-05, + "loss": 3.4339, + "step": 1712128 + }, + { + "epoch": 1.01, + "learning_rate": 2.1960831073604378e-05, + "loss": 3.4422, + "step": 1712640 + }, + { + "epoch": 1.01, + "learning_rate": 2.195244512609386e-05, + "loss": 3.4195, + "step": 1713152 + }, + { + "epoch": 1.01, + "learning_rate": 2.194405917858334e-05, + "loss": 3.4295, + "step": 1713664 + }, + { + "epoch": 1.01, + "learning_rate": 2.193568960987655e-05, + "loss": 3.4275, + "step": 1714176 + }, + { + "epoch": 1.01, + "learning_rate": 2.192730366236603e-05, + "loss": 3.4338, + "step": 1714688 + }, + { + "epoch": 1.01, + "learning_rate": 2.191891771485551e-05, + "loss": 3.4407, + "step": 1715200 + }, + { + "epoch": 1.01, + "learning_rate": 2.191053176734499e-05, + "loss": 3.436, + "step": 1715712 + }, + { + "epoch": 1.01, + "learning_rate": 2.190214581983447e-05, + "loss": 3.4384, + "step": 1716224 + }, + { + "epoch": 1.01, + "learning_rate": 2.1893776251127682e-05, + "loss": 3.428, + "step": 1716736 + }, + { + "epoch": 1.01, + "learning_rate": 2.1885390303617162e-05, + "loss": 3.4538, + "step": 1717248 + }, + { + "epoch": 1.01, + "learning_rate": 2.1877004356106642e-05, + "loss": 3.4268, + "step": 1717760 + }, + { + "epoch": 1.01, + "learning_rate": 2.1868618408596122e-05, + "loss": 3.4436, + "step": 1718272 + }, + { + "epoch": 1.01, + "learning_rate": 2.186024883988933e-05, + "loss": 3.4343, + "step": 1718784 + }, + { + "epoch": 1.01, + "learning_rate": 2.1851862892378815e-05, + "loss": 3.4375, + "step": 1719296 + }, + { + "epoch": 1.01, + "learning_rate": 2.1843476944868295e-05, + "loss": 3.4451, + "step": 1719808 + }, + { + "epoch": 1.01, + "learning_rate": 2.183509099735777e-05, + "loss": 3.439, + "step": 1720320 + }, + { + "epoch": 1.01, + "learning_rate": 2.1826721428650984e-05, + "loss": 3.4356, + "step": 1720832 + }, + { + "epoch": 1.01, + "learning_rate": 2.1818335481140464e-05, + "loss": 3.4409, + "step": 1721344 + }, + { + "epoch": 1.01, + "learning_rate": 2.1809949533629944e-05, + "loss": 3.4234, + "step": 1721856 + }, + { + "epoch": 1.01, + "learning_rate": 2.1801563586119424e-05, + "loss": 3.4364, + "step": 1722368 + }, + { + "epoch": 1.01, + "learning_rate": 2.1793194017412636e-05, + "loss": 3.4341, + "step": 1722880 + }, + { + "epoch": 1.01, + "learning_rate": 2.1784808069902116e-05, + "loss": 3.4418, + "step": 1723392 + }, + { + "epoch": 1.01, + "learning_rate": 2.1776422122391596e-05, + "loss": 3.4316, + "step": 1723904 + }, + { + "epoch": 1.01, + "learning_rate": 2.1768036174881073e-05, + "loss": 3.4286, + "step": 1724416 + }, + { + "epoch": 1.02, + "learning_rate": 2.1759650227370553e-05, + "loss": 3.4337, + "step": 1724928 + }, + { + "epoch": 1.02, + "learning_rate": 2.175128065866377e-05, + "loss": 3.4417, + "step": 1725440 + }, + { + "epoch": 1.02, + "learning_rate": 2.1742894711153245e-05, + "loss": 3.4343, + "step": 1725952 + }, + { + "epoch": 1.02, + "learning_rate": 2.1734508763642725e-05, + "loss": 3.4237, + "step": 1726464 + }, + { + "epoch": 1.02, + "learning_rate": 2.1726122816132205e-05, + "loss": 3.4369, + "step": 1726976 + }, + { + "epoch": 1.02, + "learning_rate": 2.1717753247425417e-05, + "loss": 3.4513, + "step": 1727488 + }, + { + "epoch": 1.02, + "learning_rate": 2.1709367299914894e-05, + "loss": 3.4329, + "step": 1728000 + }, + { + "epoch": 1.02, + "learning_rate": 2.1700981352404377e-05, + "loss": 3.4162, + "step": 1728512 + }, + { + "epoch": 1.02, + "learning_rate": 2.1692595404893857e-05, + "loss": 3.4344, + "step": 1729024 + }, + { + "epoch": 1.02, + "learning_rate": 2.168422583618707e-05, + "loss": 3.4318, + "step": 1729536 + }, + { + "epoch": 1.02, + "learning_rate": 2.1675839888676546e-05, + "loss": 3.44, + "step": 1730048 + }, + { + "epoch": 1.02, + "learning_rate": 2.1667453941166026e-05, + "loss": 3.4424, + "step": 1730560 + }, + { + "epoch": 1.02, + "learning_rate": 2.1659067993655506e-05, + "loss": 3.4296, + "step": 1731072 + }, + { + "epoch": 1.02, + "learning_rate": 2.165069842494872e-05, + "loss": 3.4287, + "step": 1731584 + }, + { + "epoch": 1.02, + "learning_rate": 2.16423124774382e-05, + "loss": 3.4402, + "step": 1732096 + }, + { + "epoch": 1.02, + "learning_rate": 2.163392652992768e-05, + "loss": 3.4221, + "step": 1732608 + }, + { + "epoch": 1.02, + "learning_rate": 2.162554058241716e-05, + "loss": 3.4307, + "step": 1733120 + }, + { + "epoch": 1.02, + "learning_rate": 2.161715463490664e-05, + "loss": 3.4284, + "step": 1733632 + }, + { + "epoch": 1.02, + "learning_rate": 2.160876868739612e-05, + "loss": 3.4438, + "step": 1734144 + }, + { + "epoch": 1.02, + "learning_rate": 2.160039911868933e-05, + "loss": 3.42, + "step": 1734656 + }, + { + "epoch": 1.02, + "learning_rate": 2.159201317117881e-05, + "loss": 3.4286, + "step": 1735168 + }, + { + "epoch": 1.02, + "learning_rate": 2.158362722366829e-05, + "loss": 3.4241, + "step": 1735680 + }, + { + "epoch": 1.02, + "learning_rate": 2.157524127615777e-05, + "loss": 3.4346, + "step": 1736192 + }, + { + "epoch": 1.02, + "learning_rate": 2.156685532864725e-05, + "loss": 3.4311, + "step": 1736704 + }, + { + "epoch": 1.02, + "learning_rate": 2.155848575994046e-05, + "loss": 3.4255, + "step": 1737216 + }, + { + "epoch": 1.02, + "learning_rate": 2.155009981242994e-05, + "loss": 3.4375, + "step": 1737728 + }, + { + "epoch": 1.02, + "learning_rate": 2.1541713864919423e-05, + "loss": 3.438, + "step": 1738240 + }, + { + "epoch": 1.02, + "learning_rate": 2.15333279174089e-05, + "loss": 3.423, + "step": 1738752 + }, + { + "epoch": 1.02, + "learning_rate": 2.1524958348702112e-05, + "loss": 3.444, + "step": 1739264 + }, + { + "epoch": 1.02, + "learning_rate": 2.1516572401191592e-05, + "loss": 3.4295, + "step": 1739776 + }, + { + "epoch": 1.02, + "learning_rate": 2.1508186453681072e-05, + "loss": 3.4345, + "step": 1740288 + }, + { + "epoch": 1.02, + "learning_rate": 2.1499800506170552e-05, + "loss": 3.4223, + "step": 1740800 + }, + { + "epoch": 1.02, + "learning_rate": 2.1491430937463765e-05, + "loss": 3.4323, + "step": 1741312 + }, + { + "epoch": 1.02, + "learning_rate": 2.1483044989953245e-05, + "loss": 3.4261, + "step": 1741824 + }, + { + "epoch": 1.02, + "learning_rate": 2.1474659042442724e-05, + "loss": 3.4333, + "step": 1742336 + }, + { + "epoch": 1.02, + "learning_rate": 2.14662730949322e-05, + "loss": 3.4338, + "step": 1742848 + }, + { + "epoch": 1.02, + "learning_rate": 2.1457903526225414e-05, + "loss": 3.4325, + "step": 1743360 + }, + { + "epoch": 1.02, + "learning_rate": 2.1449517578714894e-05, + "loss": 3.4325, + "step": 1743872 + }, + { + "epoch": 1.02, + "learning_rate": 2.1441131631204373e-05, + "loss": 3.4292, + "step": 1744384 + }, + { + "epoch": 1.02, + "learning_rate": 2.1432745683693853e-05, + "loss": 3.419, + "step": 1744896 + }, + { + "epoch": 1.02, + "learning_rate": 2.1424376114987066e-05, + "loss": 3.4396, + "step": 1745408 + }, + { + "epoch": 1.02, + "learning_rate": 2.1415990167476546e-05, + "loss": 3.4319, + "step": 1745920 + }, + { + "epoch": 1.02, + "learning_rate": 2.1407604219966022e-05, + "loss": 3.4379, + "step": 1746432 + }, + { + "epoch": 1.02, + "learning_rate": 2.1399218272455502e-05, + "loss": 3.4259, + "step": 1746944 + }, + { + "epoch": 1.02, + "learning_rate": 2.1390832324944986e-05, + "loss": 3.4392, + "step": 1747456 + }, + { + "epoch": 1.02, + "learning_rate": 2.1382462756238195e-05, + "loss": 3.4315, + "step": 1747968 + }, + { + "epoch": 1.02, + "learning_rate": 2.1374076808727675e-05, + "loss": 3.4284, + "step": 1748480 + }, + { + "epoch": 1.02, + "learning_rate": 2.1365690861217155e-05, + "loss": 3.4306, + "step": 1748992 + }, + { + "epoch": 1.02, + "learning_rate": 2.1357304913706635e-05, + "loss": 3.4332, + "step": 1749504 + }, + { + "epoch": 1.02, + "learning_rate": 2.1348918966196115e-05, + "loss": 3.4348, + "step": 1750016 + }, + { + "epoch": 1.02, + "learning_rate": 2.1340549397489327e-05, + "loss": 3.45, + "step": 1750528 + }, + { + "epoch": 1.02, + "learning_rate": 2.1332163449978807e-05, + "loss": 3.4194, + "step": 1751040 + }, + { + "epoch": 1.02, + "learning_rate": 2.1323777502468287e-05, + "loss": 3.4379, + "step": 1751552 + }, + { + "epoch": 1.02, + "learning_rate": 2.1315391554957767e-05, + "loss": 3.4253, + "step": 1752064 + }, + { + "epoch": 1.02, + "learning_rate": 2.1307005607447247e-05, + "loss": 3.434, + "step": 1752576 + }, + { + "epoch": 1.02, + "learning_rate": 2.1298636038740456e-05, + "loss": 3.4327, + "step": 1753088 + }, + { + "epoch": 1.02, + "learning_rate": 2.129025009122994e-05, + "loss": 3.4263, + "step": 1753600 + }, + { + "epoch": 1.02, + "learning_rate": 2.128186414371942e-05, + "loss": 3.4433, + "step": 1754112 + }, + { + "epoch": 1.02, + "learning_rate": 2.12734781962089e-05, + "loss": 3.4258, + "step": 1754624 + }, + { + "epoch": 1.02, + "learning_rate": 2.126510862750211e-05, + "loss": 3.4351, + "step": 1755136 + }, + { + "epoch": 1.03, + "eval_loss": 3.9107778072357178, + "eval_runtime": 306.3468, + "eval_samples_per_second": 1245.618, + "eval_steps_per_second": 38.926, + "step": 1755350 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 1.1384826034353408e+18, + "trial_name": null, + "trial_params": null +}