diff --git "a/checkpoint-2823840/trainer_state.json" "b/checkpoint-2823840/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-2823840/trainer_state.json" @@ -0,0 +1,33411 @@ +{ + "best_metric": 3.842043876647949, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/npi-sim-ques/transformer/3/checkpoints/checkpoint-992160", + "epoch": 0.025000606015738065, + "eval_steps": 10, + "global_step": 2823840, + "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": 11.017, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 6.8258, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 6.2024, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 5.9812, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 5.812, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 5.7064, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 5.595, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 5.5237, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 5.4424, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 5.3939, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 5.3316, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 5.3101, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989938500867749e-05, + "loss": 5.2571, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989099906116697e-05, + "loss": 5.1918, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988261311365645e-05, + "loss": 5.1639, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.987422716614593e-05, + "loss": 5.1214, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986584121863541e-05, + "loss": 5.1038, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985745527112489e-05, + "loss": 5.06, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984906932361437e-05, + "loss": 5.0316, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.0076, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 4.9891, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.9823927859886547e-05, + "loss": 4.9663, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.9815541912376026e-05, + "loss": 4.9455, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.9807155964865506e-05, + "loss": 4.9271, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 4.9063, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790400448648195e-05, + "loss": 4.884, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9782014501137675e-05, + "loss": 4.8572, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773628553627155e-05, + "loss": 4.842, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 4.8209, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756873037409844e-05, + "loss": 4.8138, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748487089899324e-05, + "loss": 4.7963, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.9740101142388804e-05, + "loss": 4.7798, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731715194878284e-05, + "loss": 4.772, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.97233456261715e-05, + "loss": 4.7526, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.971495967866098e-05, + "loss": 4.7482, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.970657373115046e-05, + "loss": 4.7436, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969818778363994e-05, + "loss": 4.7239, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968980183612942e-05, + "loss": 4.6899, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.96814158886189e-05, + "loss": 4.701, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967302994110837e-05, + "loss": 4.6717, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966466037240159e-05, + "loss": 4.6672, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965627442489107e-05, + "loss": 4.6654, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964788847738054e-05, + "loss": 4.6575, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963950252987002e-05, + "loss": 4.6407, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.96311165823595e-05, + "loss": 4.6428, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962274701365272e-05, + "loss": 4.6341, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.96143610661422e-05, + "loss": 4.6237, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960597511863168e-05, + "loss": 4.6151, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.959758917112116e-05, + "loss": 4.5926, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.95892359812181e-05, + "loss": 4.5885, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958085003370758e-05, + "loss": 4.5936, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957246408619706e-05, + "loss": 4.578, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956407813868654e-05, + "loss": 4.5651, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.9555692191176016e-05, + "loss": 4.552, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.9547306243665496e-05, + "loss": 4.5559, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.9538920296154976e-05, + "loss": 4.5399, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.9530534348644456e-05, + "loss": 4.5554, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.952216477993767e-05, + "loss": 4.5274, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951377883242715e-05, + "loss": 4.534, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.950539288491663e-05, + "loss": 4.5266, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949700693740611e-05, + "loss": 4.5026, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948863736869932e-05, + "loss": 4.5129, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.94802514211888e-05, + "loss": 4.4983, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947186547367828e-05, + "loss": 4.4888, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946347952616776e-05, + "loss": 4.4864, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945510995746097e-05, + "loss": 4.5013, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944672400995045e-05, + "loss": 4.4795, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.943833806243993e-05, + "loss": 4.4674, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942995211492941e-05, + "loss": 4.4551, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.9421582546222625e-05, + "loss": 4.4559, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.9413196598712105e-05, + "loss": 4.4718, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.9404810651201585e-05, + "loss": 4.4695, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396424703691065e-05, + "loss": 4.4438, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388055134984274e-05, + "loss": 4.4624, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379669187473754e-05, + "loss": 4.4554, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371283239963234e-05, + "loss": 4.4414, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.936291367125644e-05, + "loss": 4.428, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.935452772374592e-05, + "loss": 4.4326, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.93461417762354e-05, + "loss": 4.4215, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.933775582872488e-05, + "loss": 4.4163, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.932936988121436e-05, + "loss": 4.4164, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.932098393370384e-05, + "loss": 4.4129, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.931259798619332e-05, + "loss": 4.4138, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.930421203868281e-05, + "loss": 4.4104, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.929584246997602e-05, + "loss": 4.3922, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.928747290126923e-05, + "loss": 4.3962, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.927908695375871e-05, + "loss": 4.3973, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.927070100624819e-05, + "loss": 4.3879, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.926231505873767e-05, + "loss": 4.3838, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925394549003088e-05, + "loss": 4.381, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.924555954252036e-05, + "loss": 4.3813, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923717359500984e-05, + "loss": 4.3689, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922878764749932e-05, + "loss": 4.3706, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.92204016999888e-05, + "loss": 4.3645, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921201575247828e-05, + "loss": 4.3687, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920362980496776e-05, + "loss": 4.3638, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919524385745724e-05, + "loss": 4.3582, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918687428875045e-05, + "loss": 4.3408, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.917848834123993e-05, + "loss": 4.3462, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.917010239372941e-05, + "loss": 4.3497, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.916173282502262e-05, + "loss": 4.3563, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.91533468775121e-05, + "loss": 4.3408, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.914496093000158e-05, + "loss": 4.3309, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.913657498249106e-05, + "loss": 4.3274, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.912818903498054e-05, + "loss": 4.3347, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.911980308747002e-05, + "loss": 4.3063, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.911143351876323e-05, + "loss": 4.3141, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.910304757125272e-05, + "loss": 4.317, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.90946616237422e-05, + "loss": 4.3155, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908627567623168e-05, + "loss": 4.3078, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907788972872115e-05, + "loss": 4.3157, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.906950378121063e-05, + "loss": 4.2964, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906111783370011e-05, + "loss": 4.323, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.9052748264993326e-05, + "loss": 4.3014, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.90443623174828e-05, + "loss": 4.3048, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903597636997228e-05, + "loss": 4.3082, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.902759042246176e-05, + "loss": 4.317, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.9019237232558704e-05, + "loss": 4.294, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.9010851285048184e-05, + "loss": 4.2885, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.900246533753767e-05, + "loss": 4.293, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.899407939002715e-05, + "loss": 4.2822, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.8985693442516624e-05, + "loss": 4.2895, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.8977307495006104e-05, + "loss": 4.2863, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968921547495584e-05, + "loss": 4.2743, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.8960535599985064e-05, + "loss": 4.2925, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.8952149652474544e-05, + "loss": 4.2733, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.8943763704964024e-05, + "loss": 4.2692, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.8935377757453504e-05, + "loss": 4.268, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.892700818874671e-05, + "loss": 4.2723, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.891862224123619e-05, + "loss": 4.2586, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.891023629372567e-05, + "loss": 4.2757, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.890185034621515e-05, + "loss": 4.2688, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.889346439870464e-05, + "loss": 4.2569, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888507845119412e-05, + "loss": 4.2482, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.88766925036836e-05, + "loss": 4.2593, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886830655617308e-05, + "loss": 4.254, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885993698746629e-05, + "loss": 4.259, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.88515674187595e-05, + "loss": 4.2538, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884318147124898e-05, + "loss": 4.2536, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883479552373846e-05, + "loss": 4.2515, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882640957622794e-05, + "loss": 4.2459, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.8818040007521146e-05, + "loss": 4.2378, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.8809654060010626e-05, + "loss": 4.2358, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.8801268112500106e-05, + "loss": 4.2426, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.8792882164989586e-05, + "loss": 4.2214, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.878449621747907e-05, + "loss": 4.2425, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877611026996855e-05, + "loss": 4.2374, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.876774070126176e-05, + "loss": 4.2293, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875935475375124e-05, + "loss": 4.2304, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.875096880624072e-05, + "loss": 4.2287, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.191126823425293, + "eval_runtime": 302.1611, + "eval_samples_per_second": 1262.872, + "eval_steps_per_second": 39.466, + "step": 76320 + }, + { + "epoch": 1.0, + "learning_rate": 4.87425828587302e-05, + "loss": 4.2053, + "step": 76800 + }, + { + "epoch": 1.0, + "learning_rate": 4.873421329002341e-05, + "loss": 4.2138, + "step": 77312 + }, + { + "epoch": 1.0, + "learning_rate": 4.872582734251289e-05, + "loss": 4.2239, + "step": 77824 + }, + { + "epoch": 1.0, + "learning_rate": 4.871744139500237e-05, + "loss": 4.2113, + "step": 78336 + }, + { + "epoch": 1.0, + "learning_rate": 4.870905544749185e-05, + "loss": 4.2159, + "step": 78848 + }, + { + "epoch": 1.0, + "learning_rate": 4.870066949998133e-05, + "loss": 4.2058, + "step": 79360 + }, + { + "epoch": 1.0, + "learning_rate": 4.869229993127454e-05, + "loss": 4.2033, + "step": 79872 + }, + { + "epoch": 1.0, + "learning_rate": 4.8683913983764027e-05, + "loss": 4.1972, + "step": 80384 + }, + { + "epoch": 1.0, + "learning_rate": 4.8675528036253507e-05, + "loss": 4.2062, + "step": 80896 + }, + { + "epoch": 1.0, + "learning_rate": 4.8667142088742986e-05, + "loss": 4.1942, + "step": 81408 + }, + { + "epoch": 1.0, + "learning_rate": 4.8658772520036196e-05, + "loss": 4.2148, + "step": 81920 + }, + { + "epoch": 1.0, + "learning_rate": 4.8650386572525676e-05, + "loss": 4.2074, + "step": 82432 + }, + { + "epoch": 1.0, + "learning_rate": 4.8642017003818885e-05, + "loss": 4.1903, + "step": 82944 + }, + { + "epoch": 1.0, + "learning_rate": 4.8633631056308365e-05, + "loss": 4.1855, + "step": 83456 + }, + { + "epoch": 1.0, + "learning_rate": 4.8625245108797845e-05, + "loss": 4.1851, + "step": 83968 + }, + { + "epoch": 1.0, + "learning_rate": 4.8616859161287324e-05, + "loss": 4.1839, + "step": 84480 + }, + { + "epoch": 1.0, + "learning_rate": 4.8608473213776804e-05, + "loss": 4.1793, + "step": 84992 + }, + { + "epoch": 1.0, + "learning_rate": 4.860008726626628e-05, + "loss": 4.1798, + "step": 85504 + }, + { + "epoch": 1.0, + "learning_rate": 4.8591701318755764e-05, + "loss": 4.1743, + "step": 86016 + }, + { + "epoch": 1.0, + "learning_rate": 4.8583315371245244e-05, + "loss": 4.1893, + "step": 86528 + }, + { + "epoch": 1.0, + "learning_rate": 4.857494580253846e-05, + "loss": 4.1785, + "step": 87040 + }, + { + "epoch": 1.0, + "learning_rate": 4.856655985502793e-05, + "loss": 4.1823, + "step": 87552 + }, + { + "epoch": 1.0, + "learning_rate": 4.855817390751741e-05, + "loss": 4.1787, + "step": 88064 + }, + { + "epoch": 1.0, + "learning_rate": 4.854978796000689e-05, + "loss": 4.1866, + "step": 88576 + }, + { + "epoch": 1.0, + "learning_rate": 4.854141839130011e-05, + "loss": 4.1622, + "step": 89088 + }, + { + "epoch": 1.0, + "learning_rate": 4.853303244378958e-05, + "loss": 4.1643, + "step": 89600 + }, + { + "epoch": 1.0, + "learning_rate": 4.852464649627906e-05, + "loss": 4.1603, + "step": 90112 + }, + { + "epoch": 1.0, + "learning_rate": 4.851626054876854e-05, + "loss": 4.1606, + "step": 90624 + }, + { + "epoch": 1.0, + "learning_rate": 4.850789098006175e-05, + "loss": 4.1606, + "step": 91136 + }, + { + "epoch": 1.01, + "learning_rate": 4.849950503255123e-05, + "loss": 4.1585, + "step": 91648 + }, + { + "epoch": 1.01, + "learning_rate": 4.849111908504072e-05, + "loss": 4.161, + "step": 92160 + }, + { + "epoch": 1.01, + "learning_rate": 4.84827331375302e-05, + "loss": 4.1628, + "step": 92672 + }, + { + "epoch": 1.01, + "learning_rate": 4.847436356882341e-05, + "loss": 4.1502, + "step": 93184 + }, + { + "epoch": 1.01, + "learning_rate": 4.846597762131289e-05, + "loss": 4.1583, + "step": 93696 + }, + { + "epoch": 1.01, + "learning_rate": 4.845759167380237e-05, + "loss": 4.1648, + "step": 94208 + }, + { + "epoch": 1.01, + "learning_rate": 4.844920572629185e-05, + "loss": 4.151, + "step": 94720 + }, + { + "epoch": 1.01, + "learning_rate": 4.8440836157585056e-05, + "loss": 4.1369, + "step": 95232 + }, + { + "epoch": 1.01, + "learning_rate": 4.8432450210074536e-05, + "loss": 4.1486, + "step": 95744 + }, + { + "epoch": 1.01, + "learning_rate": 4.8424064262564016e-05, + "loss": 4.1298, + "step": 96256 + }, + { + "epoch": 1.01, + "learning_rate": 4.8415678315053496e-05, + "loss": 4.1388, + "step": 96768 + }, + { + "epoch": 1.01, + "learning_rate": 4.8407308746346705e-05, + "loss": 4.1377, + "step": 97280 + }, + { + "epoch": 1.01, + "learning_rate": 4.8398922798836185e-05, + "loss": 4.1466, + "step": 97792 + }, + { + "epoch": 1.01, + "learning_rate": 4.839053685132567e-05, + "loss": 4.133, + "step": 98304 + }, + { + "epoch": 1.01, + "learning_rate": 4.838215090381515e-05, + "loss": 4.1399, + "step": 98816 + }, + { + "epoch": 1.01, + "learning_rate": 4.837378133510836e-05, + "loss": 4.1448, + "step": 99328 + }, + { + "epoch": 1.01, + "learning_rate": 4.836539538759784e-05, + "loss": 4.1364, + "step": 99840 + }, + { + "epoch": 1.01, + "learning_rate": 4.835700944008732e-05, + "loss": 4.1367, + "step": 100352 + }, + { + "epoch": 1.01, + "learning_rate": 4.83486234925768e-05, + "loss": 4.1188, + "step": 100864 + }, + { + "epoch": 1.01, + "learning_rate": 4.834023754506628e-05, + "loss": 4.1264, + "step": 101376 + }, + { + "epoch": 1.01, + "learning_rate": 4.833185159755576e-05, + "loss": 4.1331, + "step": 101888 + }, + { + "epoch": 1.01, + "learning_rate": 4.832348202884897e-05, + "loss": 4.1251, + "step": 102400 + }, + { + "epoch": 1.01, + "learning_rate": 4.831509608133845e-05, + "loss": 4.1195, + "step": 102912 + }, + { + "epoch": 1.01, + "learning_rate": 4.830671013382793e-05, + "loss": 4.1058, + "step": 103424 + }, + { + "epoch": 1.01, + "learning_rate": 4.829832418631741e-05, + "loss": 4.1181, + "step": 103936 + }, + { + "epoch": 1.01, + "learning_rate": 4.8289954617610625e-05, + "loss": 4.108, + "step": 104448 + }, + { + "epoch": 1.01, + "learning_rate": 4.8281568670100105e-05, + "loss": 4.1229, + "step": 104960 + }, + { + "epoch": 1.01, + "learning_rate": 4.8273182722589585e-05, + "loss": 4.1095, + "step": 105472 + }, + { + "epoch": 1.01, + "learning_rate": 4.8264796775079065e-05, + "loss": 4.1197, + "step": 105984 + }, + { + "epoch": 1.01, + "learning_rate": 4.8256427206372274e-05, + "loss": 4.1199, + "step": 106496 + }, + { + "epoch": 1.01, + "learning_rate": 4.8248041258861754e-05, + "loss": 4.0944, + "step": 107008 + }, + { + "epoch": 1.01, + "learning_rate": 4.8239655311351234e-05, + "loss": 4.1095, + "step": 107520 + }, + { + "epoch": 1.01, + "learning_rate": 4.8231269363840714e-05, + "loss": 4.1064, + "step": 108032 + }, + { + "epoch": 1.01, + "learning_rate": 4.8222883416330194e-05, + "loss": 4.096, + "step": 108544 + }, + { + "epoch": 1.01, + "learning_rate": 4.82145138476234e-05, + "loss": 4.0985, + "step": 109056 + }, + { + "epoch": 1.01, + "learning_rate": 4.820612790011288e-05, + "loss": 4.1162, + "step": 109568 + }, + { + "epoch": 1.01, + "learning_rate": 4.819774195260236e-05, + "loss": 4.1032, + "step": 110080 + }, + { + "epoch": 1.01, + "learning_rate": 4.818935600509184e-05, + "loss": 4.0924, + "step": 110592 + }, + { + "epoch": 1.01, + "learning_rate": 4.818098643638506e-05, + "loss": 4.0838, + "step": 111104 + }, + { + "epoch": 1.01, + "learning_rate": 4.817260048887454e-05, + "loss": 4.0921, + "step": 111616 + }, + { + "epoch": 1.01, + "learning_rate": 4.816421454136402e-05, + "loss": 4.1058, + "step": 112128 + }, + { + "epoch": 1.01, + "learning_rate": 4.81558285938535e-05, + "loss": 4.1083, + "step": 112640 + }, + { + "epoch": 1.01, + "learning_rate": 4.814745902514671e-05, + "loss": 4.0939, + "step": 113152 + }, + { + "epoch": 1.01, + "learning_rate": 4.813907307763619e-05, + "loss": 4.1062, + "step": 113664 + }, + { + "epoch": 1.01, + "learning_rate": 4.813068713012567e-05, + "loss": 4.1019, + "step": 114176 + }, + { + "epoch": 1.01, + "learning_rate": 4.812230118261515e-05, + "loss": 4.0956, + "step": 114688 + }, + { + "epoch": 1.01, + "learning_rate": 4.811393161390836e-05, + "loss": 4.0821, + "step": 115200 + }, + { + "epoch": 1.01, + "learning_rate": 4.810554566639784e-05, + "loss": 4.0975, + "step": 115712 + }, + { + "epoch": 1.01, + "learning_rate": 4.809715971888732e-05, + "loss": 4.0856, + "step": 116224 + }, + { + "epoch": 1.01, + "learning_rate": 4.80887737713768e-05, + "loss": 4.0822, + "step": 116736 + }, + { + "epoch": 1.01, + "learning_rate": 4.808040420267001e-05, + "loss": 4.0867, + "step": 117248 + }, + { + "epoch": 1.01, + "learning_rate": 4.807201825515949e-05, + "loss": 4.0838, + "step": 117760 + }, + { + "epoch": 1.01, + "learning_rate": 4.806363230764897e-05, + "loss": 4.0966, + "step": 118272 + }, + { + "epoch": 1.01, + "learning_rate": 4.805524636013845e-05, + "loss": 4.0832, + "step": 118784 + }, + { + "epoch": 1.01, + "learning_rate": 4.804687679143166e-05, + "loss": 4.0765, + "step": 119296 + }, + { + "epoch": 1.01, + "learning_rate": 4.803849084392114e-05, + "loss": 4.0806, + "step": 119808 + }, + { + "epoch": 1.01, + "learning_rate": 4.803010489641062e-05, + "loss": 4.0834, + "step": 120320 + }, + { + "epoch": 1.01, + "learning_rate": 4.80217189489001e-05, + "loss": 4.079, + "step": 120832 + }, + { + "epoch": 1.01, + "learning_rate": 4.801334938019331e-05, + "loss": 4.0768, + "step": 121344 + }, + { + "epoch": 1.01, + "learning_rate": 4.800497981148652e-05, + "loss": 4.0704, + "step": 121856 + }, + { + "epoch": 1.02, + "learning_rate": 4.7996593863976e-05, + "loss": 4.0841, + "step": 122368 + }, + { + "epoch": 1.02, + "learning_rate": 4.7988207916465486e-05, + "loss": 4.0681, + "step": 122880 + }, + { + "epoch": 1.02, + "learning_rate": 4.7979821968954966e-05, + "loss": 4.0723, + "step": 123392 + }, + { + "epoch": 1.02, + "learning_rate": 4.7971436021444446e-05, + "loss": 4.0669, + "step": 123904 + }, + { + "epoch": 1.02, + "learning_rate": 4.7963050073933926e-05, + "loss": 4.0789, + "step": 124416 + }, + { + "epoch": 1.02, + "learning_rate": 4.7954664126423406e-05, + "loss": 4.0765, + "step": 124928 + }, + { + "epoch": 1.02, + "learning_rate": 4.7946278178912886e-05, + "loss": 4.0682, + "step": 125440 + }, + { + "epoch": 1.02, + "learning_rate": 4.7937908610206095e-05, + "loss": 4.0562, + "step": 125952 + }, + { + "epoch": 1.02, + "learning_rate": 4.7929522662695575e-05, + "loss": 4.0648, + "step": 126464 + }, + { + "epoch": 1.02, + "learning_rate": 4.7921136715185055e-05, + "loss": 4.0676, + "step": 126976 + }, + { + "epoch": 1.02, + "learning_rate": 4.7912750767674535e-05, + "loss": 4.0761, + "step": 127488 + }, + { + "epoch": 1.02, + "learning_rate": 4.7904381198967744e-05, + "loss": 4.0648, + "step": 128000 + }, + { + "epoch": 1.02, + "learning_rate": 4.7895995251457224e-05, + "loss": 4.0586, + "step": 128512 + }, + { + "epoch": 1.02, + "learning_rate": 4.7887609303946704e-05, + "loss": 4.0507, + "step": 129024 + }, + { + "epoch": 1.02, + "learning_rate": 4.7879223356436184e-05, + "loss": 4.0658, + "step": 129536 + }, + { + "epoch": 1.02, + "learning_rate": 4.78708537877294e-05, + "loss": 4.0351, + "step": 130048 + }, + { + "epoch": 1.02, + "learning_rate": 4.786248421902261e-05, + "loss": 4.0508, + "step": 130560 + }, + { + "epoch": 1.02, + "learning_rate": 4.785409827151209e-05, + "loss": 4.0549, + "step": 131072 + }, + { + "epoch": 1.02, + "learning_rate": 4.784571232400157e-05, + "loss": 4.0545, + "step": 131584 + }, + { + "epoch": 1.02, + "learning_rate": 4.783732637649105e-05, + "loss": 4.0432, + "step": 132096 + }, + { + "epoch": 1.02, + "learning_rate": 4.782894042898053e-05, + "loss": 4.0532, + "step": 132608 + }, + { + "epoch": 1.02, + "learning_rate": 4.782055448147001e-05, + "loss": 4.045, + "step": 133120 + }, + { + "epoch": 1.02, + "learning_rate": 4.781216853395948e-05, + "loss": 4.0632, + "step": 133632 + }, + { + "epoch": 1.02, + "learning_rate": 4.780378258644896e-05, + "loss": 4.0494, + "step": 134144 + }, + { + "epoch": 1.02, + "learning_rate": 4.779541301774218e-05, + "loss": 4.0479, + "step": 134656 + }, + { + "epoch": 1.02, + "learning_rate": 4.778702707023166e-05, + "loss": 4.0637, + "step": 135168 + }, + { + "epoch": 1.02, + "learning_rate": 4.777864112272114e-05, + "loss": 4.0664, + "step": 135680 + }, + { + "epoch": 1.02, + "learning_rate": 4.7770271554014354e-05, + "loss": 4.0471, + "step": 136192 + }, + { + "epoch": 1.02, + "learning_rate": 4.7761885606503834e-05, + "loss": 4.0423, + "step": 136704 + }, + { + "epoch": 1.02, + "learning_rate": 4.775349965899331e-05, + "loss": 4.0498, + "step": 137216 + }, + { + "epoch": 1.02, + "learning_rate": 4.774511371148279e-05, + "loss": 4.0402, + "step": 137728 + }, + { + "epoch": 1.02, + "learning_rate": 4.773672776397227e-05, + "loss": 4.0435, + "step": 138240 + }, + { + "epoch": 1.02, + "learning_rate": 4.7728341816461747e-05, + "loss": 4.0502, + "step": 138752 + }, + { + "epoch": 1.02, + "learning_rate": 4.7719955868951227e-05, + "loss": 4.0356, + "step": 139264 + }, + { + "epoch": 1.02, + "learning_rate": 4.7711586300244436e-05, + "loss": 4.0565, + "step": 139776 + }, + { + "epoch": 1.02, + "learning_rate": 4.7703200352733916e-05, + "loss": 4.0385, + "step": 140288 + }, + { + "epoch": 1.02, + "learning_rate": 4.7694814405223396e-05, + "loss": 4.0396, + "step": 140800 + }, + { + "epoch": 1.02, + "learning_rate": 4.7686428457712876e-05, + "loss": 4.0333, + "step": 141312 + }, + { + "epoch": 1.02, + "learning_rate": 4.767805888900609e-05, + "loss": 4.04, + "step": 141824 + }, + { + "epoch": 1.02, + "learning_rate": 4.766967294149557e-05, + "loss": 4.0312, + "step": 142336 + }, + { + "epoch": 1.02, + "learning_rate": 4.766128699398505e-05, + "loss": 4.047, + "step": 142848 + }, + { + "epoch": 1.02, + "learning_rate": 4.765290104647453e-05, + "loss": 4.0441, + "step": 143360 + }, + { + "epoch": 1.02, + "learning_rate": 4.764453147776774e-05, + "loss": 4.0349, + "step": 143872 + }, + { + "epoch": 1.02, + "learning_rate": 4.763614553025722e-05, + "loss": 4.0177, + "step": 144384 + }, + { + "epoch": 1.02, + "learning_rate": 4.76277595827467e-05, + "loss": 4.0427, + "step": 144896 + }, + { + "epoch": 1.02, + "learning_rate": 4.761937363523618e-05, + "loss": 4.0325, + "step": 145408 + }, + { + "epoch": 1.02, + "learning_rate": 4.761100406652939e-05, + "loss": 4.039, + "step": 145920 + }, + { + "epoch": 1.02, + "learning_rate": 4.760261811901887e-05, + "loss": 4.0353, + "step": 146432 + }, + { + "epoch": 1.02, + "learning_rate": 4.759423217150835e-05, + "loss": 4.0345, + "step": 146944 + }, + { + "epoch": 1.02, + "learning_rate": 4.758584622399783e-05, + "loss": 4.0344, + "step": 147456 + }, + { + "epoch": 1.02, + "learning_rate": 4.7577476655291045e-05, + "loss": 4.0362, + "step": 147968 + }, + { + "epoch": 1.02, + "learning_rate": 4.7569090707780525e-05, + "loss": 4.0239, + "step": 148480 + }, + { + "epoch": 1.02, + "learning_rate": 4.7560704760270005e-05, + "loss": 4.0217, + "step": 148992 + }, + { + "epoch": 1.02, + "learning_rate": 4.7552318812759485e-05, + "loss": 4.0315, + "step": 149504 + }, + { + "epoch": 1.02, + "learning_rate": 4.7543949244052694e-05, + "loss": 4.0128, + "step": 150016 + }, + { + "epoch": 1.02, + "learning_rate": 4.7535563296542174e-05, + "loss": 4.0286, + "step": 150528 + }, + { + "epoch": 1.02, + "learning_rate": 4.7527177349031654e-05, + "loss": 4.0349, + "step": 151040 + }, + { + "epoch": 1.02, + "learning_rate": 4.7518791401521134e-05, + "loss": 4.022, + "step": 151552 + }, + { + "epoch": 1.02, + "learning_rate": 4.751042183281434e-05, + "loss": 4.0207, + "step": 152064 + }, + { + "epoch": 1.02, + "learning_rate": 4.750203588530382e-05, + "loss": 4.0243, + "step": 152576 + }, + { + "epoch": 1.03, + "eval_loss": 4.023052215576172, + "eval_runtime": 302.5541, + "eval_samples_per_second": 1261.232, + "eval_steps_per_second": 39.414, + "step": 152640 + }, + { + "epoch": 0.0, + "learning_rate": 4.74936499377933e-05, + "loss": 4.0037, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.748526399028278e-05, + "loss": 4.0126, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.747687804277226e-05, + "loss": 4.0224, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.746849209526175e-05, + "loss": 4.0168, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.746010614775123e-05, + "loss": 4.022, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.745172020024071e-05, + "loss": 4.0048, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.744333425273019e-05, + "loss": 4.016, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.743494830521967e-05, + "loss": 3.9994, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.742656235770914e-05, + "loss": 4.0135, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.741817641019862e-05, + "loss": 4.0079, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.74097904626881e-05, + "loss": 4.0175, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.740142089398132e-05, + "loss": 4.0191, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.739305132527453e-05, + "loss": 4.001, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.738466537776401e-05, + "loss": 4.0023, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.737627943025349e-05, + "loss": 4.0029, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.736789348274297e-05, + "loss": 3.9984, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.735950753523245e-05, + "loss": 3.9955, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.735112158772193e-05, + "loss": 3.9972, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.734273564021141e-05, + "loss": 3.9926, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.7334366071504616e-05, + "loss": 4.0151, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.7325980123994096e-05, + "loss": 3.9928, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.7317594176483576e-05, + "loss": 4.0083, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.7309208228973056e-05, + "loss": 4.0024, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.7300838660266265e-05, + "loss": 4.0085, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.7292452712755745e-05, + "loss": 3.9822, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.7284066765245225e-05, + "loss": 3.9944, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.7275680817734705e-05, + "loss": 3.9849, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.726731124902792e-05, + "loss": 3.9933, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.72589253015174e-05, + "loss": 3.985, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.725053935400688e-05, + "loss": 3.9874, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.724215340649636e-05, + "loss": 3.9944, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.723378383778957e-05, + "loss": 3.9936, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.722539789027905e-05, + "loss": 3.9793, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.721701194276853e-05, + "loss": 3.9946, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.720864237406174e-05, + "loss": 3.9896, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.720025642655122e-05, + "loss": 3.9864, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.71918704790407e-05, + "loss": 3.9756, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.718348453153018e-05, + "loss": 3.9843, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.717509858401966e-05, + "loss": 3.9676, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.716671263650914e-05, + "loss": 3.9816, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.715832668899862e-05, + "loss": 3.9757, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.7149940741488105e-05, + "loss": 3.9852, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.7141571172781314e-05, + "loss": 3.9776, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.7133185225270794e-05, + "loss": 3.9803, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.7124799277760274e-05, + "loss": 3.9871, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.7116413330249754e-05, + "loss": 3.9819, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.7108043761542963e-05, + "loss": 3.9788, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.7099657814032443e-05, + "loss": 3.9637, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.709127186652192e-05, + "loss": 3.9696, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.70828859190114e-05, + "loss": 3.9805, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.707451635030461e-05, + "loss": 3.9716, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.706613040279409e-05, + "loss": 3.9664, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.705774445528357e-05, + "loss": 3.9577, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.704935850777306e-05, + "loss": 3.969, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.704098893906627e-05, + "loss": 3.9538, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.703260299155575e-05, + "loss": 3.9722, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.702421704404523e-05, + "loss": 3.9605, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.701583109653471e-05, + "loss": 3.9746, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.700746152782792e-05, + "loss": 3.9692, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.69990755803174e-05, + "loss": 3.9509, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.699068963280688e-05, + "loss": 3.9598, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.698230368529636e-05, + "loss": 3.9602, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.6973934116589566e-05, + "loss": 3.9515, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.6965548169079046e-05, + "loss": 3.9575, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.6957162221568526e-05, + "loss": 3.966, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694877627405801e-05, + "loss": 3.9618, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.694040670535122e-05, + "loss": 3.9517, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.69320207578407e-05, + "loss": 3.9418, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.692363481033018e-05, + "loss": 3.9498, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.691524886281966e-05, + "loss": 3.9626, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.690687929411287e-05, + "loss": 3.97, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.689849334660235e-05, + "loss": 3.9534, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.689012377789556e-05, + "loss": 3.9658, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.688173783038504e-05, + "loss": 3.9623, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.687335188287452e-05, + "loss": 3.9627, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.6864965935364e-05, + "loss": 3.9394, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.685657998785348e-05, + "loss": 3.9632, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.6848194040342966e-05, + "loss": 3.9524, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.6839808092832446e-05, + "loss": 3.9462, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.6831422145321926e-05, + "loss": 3.9545, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.6823052576615135e-05, + "loss": 3.9482, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.6814666629104615e-05, + "loss": 3.9613, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.6806297060397824e-05, + "loss": 3.9529, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.6797911112887304e-05, + "loss": 3.941, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.6789525165376784e-05, + "loss": 3.9483, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.6781139217866264e-05, + "loss": 3.9476, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.6772753270355744e-05, + "loss": 3.9497, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.676436732284522e-05, + "loss": 3.9457, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.675599775413843e-05, + "loss": 3.9406, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.674761180662792e-05, + "loss": 3.9511, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.67392258591174e-05, + "loss": 3.9385, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.673083991160687e-05, + "loss": 3.943, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.672245396409635e-05, + "loss": 3.9369, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.671406801658583e-05, + "loss": 3.952, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.670568206907531e-05, + "loss": 3.9499, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.669729612156479e-05, + "loss": 3.9413, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.668894293166174e-05, + "loss": 3.9337, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.668055698415122e-05, + "loss": 3.9422, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.667217103664069e-05, + "loss": 3.9359, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.666378508913017e-05, + "loss": 3.9538, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.665539914161966e-05, + "loss": 3.9385, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.664701319410914e-05, + "loss": 3.9348, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.663862724659862e-05, + "loss": 3.9271, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.66302412990881e-05, + "loss": 3.9406, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.662187173038131e-05, + "loss": 3.9162, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.6613502161674516e-05, + "loss": 3.9315, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.6605116214163996e-05, + "loss": 3.9332, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.6596730266653476e-05, + "loss": 3.9324, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.6588344319142956e-05, + "loss": 3.9188, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.6579958371632436e-05, + "loss": 3.9363, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.6571572424121916e-05, + "loss": 3.921, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.6563186476611396e-05, + "loss": 3.9439, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.655481690790461e-05, + "loss": 3.9302, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.654643096039409e-05, + "loss": 3.9267, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.653804501288357e-05, + "loss": 3.9448, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.652965906537305e-05, + "loss": 3.9505, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.652128949666626e-05, + "loss": 3.9306, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.651290354915574e-05, + "loss": 3.9219, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.650451760164522e-05, + "loss": 3.9316, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.64961316541347e-05, + "loss": 3.9244, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.648774570662418e-05, + "loss": 3.9253, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.647935975911366e-05, + "loss": 3.937, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.647097381160314e-05, + "loss": 3.9174, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.646260424289635e-05, + "loss": 3.9402, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.645421829538583e-05, + "loss": 3.9255, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.644583234787531e-05, + "loss": 3.9253, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.643744640036479e-05, + "loss": 3.918, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.6429076831658005e-05, + "loss": 3.9275, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.6420690884147485e-05, + "loss": 3.9142, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.6412304936636965e-05, + "loss": 3.9356, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.6403918989126445e-05, + "loss": 3.9273, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.6395533041615925e-05, + "loss": 3.9241, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.6387147094105405e-05, + "loss": 3.9062, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.637876114659488e-05, + "loss": 3.9293, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.637037519908436e-05, + "loss": 3.9246, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.6362005630377574e-05, + "loss": 3.9218, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.6353619682867054e-05, + "loss": 3.9216, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.634523373535653e-05, + "loss": 3.9298, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.6336847787846014e-05, + "loss": 3.9258, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.6328461840335494e-05, + "loss": 3.9299, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.632009227162871e-05, + "loss": 3.9127, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.631170632411818e-05, + "loss": 3.9137, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.630332037660766e-05, + "loss": 3.9199, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.629493442909714e-05, + "loss": 3.9044, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.628654848158662e-05, + "loss": 3.9208, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.62781625340761e-05, + "loss": 3.9262, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.626977658656558e-05, + "loss": 3.9149, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.626139063905506e-05, + "loss": 3.9123, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.625302107034827e-05, + "loss": 3.9212, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 3.9499285221099854, + "eval_runtime": 304.4414, + "eval_samples_per_second": 1253.414, + "eval_steps_per_second": 39.17, + "step": 228960 + }, + { + "epoch": 1.0, + "learning_rate": 4.624463512283775e-05, + "loss": 3.9076, + "step": 229376 + }, + { + "epoch": 1.0, + "learning_rate": 4.623624917532723e-05, + "loss": 3.907, + "step": 229888 + }, + { + "epoch": 1.0, + "learning_rate": 4.622786322781671e-05, + "loss": 3.9166, + "step": 230400 + }, + { + "epoch": 1.0, + "learning_rate": 4.62194772803062e-05, + "loss": 3.9068, + "step": 230912 + }, + { + "epoch": 1.0, + "learning_rate": 4.621110771159941e-05, + "loss": 3.9214, + "step": 231424 + }, + { + "epoch": 1.0, + "learning_rate": 4.620272176408889e-05, + "loss": 3.899, + "step": 231936 + }, + { + "epoch": 1.0, + "learning_rate": 4.619433581657837e-05, + "loss": 3.9144, + "step": 232448 + }, + { + "epoch": 1.0, + "learning_rate": 4.618594986906785e-05, + "loss": 3.8961, + "step": 232960 + }, + { + "epoch": 1.0, + "learning_rate": 4.617756392155733e-05, + "loss": 3.91, + "step": 233472 + }, + { + "epoch": 1.0, + "learning_rate": 4.616917797404681e-05, + "loss": 3.9024, + "step": 233984 + }, + { + "epoch": 1.0, + "learning_rate": 4.616079202653629e-05, + "loss": 3.9145, + "step": 234496 + }, + { + "epoch": 1.0, + "learning_rate": 4.615240607902577e-05, + "loss": 3.9152, + "step": 235008 + }, + { + "epoch": 1.0, + "learning_rate": 4.6144036510318976e-05, + "loss": 3.8997, + "step": 235520 + }, + { + "epoch": 1.0, + "learning_rate": 4.6135650562808456e-05, + "loss": 3.9018, + "step": 236032 + }, + { + "epoch": 1.0, + "learning_rate": 4.6127264615297936e-05, + "loss": 3.8991, + "step": 236544 + }, + { + "epoch": 1.0, + "learning_rate": 4.6118878667787416e-05, + "loss": 3.8995, + "step": 237056 + }, + { + "epoch": 1.0, + "learning_rate": 4.6110492720276896e-05, + "loss": 3.8936, + "step": 237568 + }, + { + "epoch": 1.0, + "learning_rate": 4.6102106772766376e-05, + "loss": 3.8966, + "step": 238080 + }, + { + "epoch": 1.0, + "learning_rate": 4.6093720825255856e-05, + "loss": 3.8928, + "step": 238592 + }, + { + "epoch": 1.0, + "learning_rate": 4.6085351256549065e-05, + "loss": 3.9198, + "step": 239104 + }, + { + "epoch": 1.0, + "learning_rate": 4.607698168784228e-05, + "loss": 3.8953, + "step": 239616 + }, + { + "epoch": 1.0, + "learning_rate": 4.606859574033176e-05, + "loss": 3.9041, + "step": 240128 + }, + { + "epoch": 1.0, + "learning_rate": 4.606020979282124e-05, + "loss": 3.9093, + "step": 240640 + }, + { + "epoch": 1.0, + "learning_rate": 4.6051823845310714e-05, + "loss": 3.9071, + "step": 241152 + }, + { + "epoch": 1.0, + "learning_rate": 4.6043437897800194e-05, + "loss": 3.8863, + "step": 241664 + }, + { + "epoch": 1.0, + "learning_rate": 4.6035051950289674e-05, + "loss": 3.8964, + "step": 242176 + }, + { + "epoch": 1.0, + "learning_rate": 4.6026666002779154e-05, + "loss": 3.8899, + "step": 242688 + }, + { + "epoch": 1.0, + "learning_rate": 4.601829643407237e-05, + "loss": 3.8969, + "step": 243200 + }, + { + "epoch": 1.0, + "learning_rate": 4.600991048656185e-05, + "loss": 3.8863, + "step": 243712 + }, + { + "epoch": 1.01, + "learning_rate": 4.600152453905133e-05, + "loss": 3.8896, + "step": 244224 + }, + { + "epoch": 1.01, + "learning_rate": 4.599313859154081e-05, + "loss": 3.8985, + "step": 244736 + }, + { + "epoch": 1.01, + "learning_rate": 4.598476902283402e-05, + "loss": 3.8982, + "step": 245248 + }, + { + "epoch": 1.01, + "learning_rate": 4.59763830753235e-05, + "loss": 3.8897, + "step": 245760 + }, + { + "epoch": 1.01, + "learning_rate": 4.596799712781298e-05, + "loss": 3.8979, + "step": 246272 + }, + { + "epoch": 1.01, + "learning_rate": 4.595961118030246e-05, + "loss": 3.8971, + "step": 246784 + }, + { + "epoch": 1.01, + "learning_rate": 4.595122523279194e-05, + "loss": 3.8904, + "step": 247296 + }, + { + "epoch": 1.01, + "learning_rate": 4.594285566408515e-05, + "loss": 3.8788, + "step": 247808 + }, + { + "epoch": 1.01, + "learning_rate": 4.593446971657463e-05, + "loss": 3.8944, + "step": 248320 + }, + { + "epoch": 1.01, + "learning_rate": 4.592608376906411e-05, + "loss": 3.8713, + "step": 248832 + }, + { + "epoch": 1.01, + "learning_rate": 4.591769782155359e-05, + "loss": 3.8879, + "step": 249344 + }, + { + "epoch": 1.01, + "learning_rate": 4.59093282528468e-05, + "loss": 3.8809, + "step": 249856 + }, + { + "epoch": 1.01, + "learning_rate": 4.590094230533628e-05, + "loss": 3.8935, + "step": 250368 + }, + { + "epoch": 1.01, + "learning_rate": 4.589255635782576e-05, + "loss": 3.8917, + "step": 250880 + }, + { + "epoch": 1.01, + "learning_rate": 4.588417041031524e-05, + "loss": 3.884, + "step": 251392 + }, + { + "epoch": 1.01, + "learning_rate": 4.587580084160845e-05, + "loss": 3.893, + "step": 251904 + }, + { + "epoch": 1.01, + "learning_rate": 4.586741489409793e-05, + "loss": 3.8929, + "step": 252416 + }, + { + "epoch": 1.01, + "learning_rate": 4.585902894658741e-05, + "loss": 3.889, + "step": 252928 + }, + { + "epoch": 1.01, + "learning_rate": 4.585064299907689e-05, + "loss": 3.8729, + "step": 253440 + }, + { + "epoch": 1.01, + "learning_rate": 4.584225705156637e-05, + "loss": 3.8775, + "step": 253952 + }, + { + "epoch": 1.01, + "learning_rate": 4.583387110405585e-05, + "loss": 3.8915, + "step": 254464 + }, + { + "epoch": 1.01, + "learning_rate": 4.582550153534906e-05, + "loss": 3.8778, + "step": 254976 + }, + { + "epoch": 1.01, + "learning_rate": 4.581711558783854e-05, + "loss": 3.8732, + "step": 255488 + }, + { + "epoch": 1.01, + "learning_rate": 4.580872964032802e-05, + "loss": 3.8709, + "step": 256000 + }, + { + "epoch": 1.01, + "learning_rate": 4.580034369281751e-05, + "loss": 3.8809, + "step": 256512 + }, + { + "epoch": 1.01, + "learning_rate": 4.579195774530699e-05, + "loss": 3.8659, + "step": 257024 + }, + { + "epoch": 1.01, + "learning_rate": 4.57835881766002e-05, + "loss": 3.8789, + "step": 257536 + }, + { + "epoch": 1.01, + "learning_rate": 4.577520222908968e-05, + "loss": 3.8751, + "step": 258048 + }, + { + "epoch": 1.01, + "learning_rate": 4.576681628157916e-05, + "loss": 3.8806, + "step": 258560 + }, + { + "epoch": 1.01, + "learning_rate": 4.5758430334068637e-05, + "loss": 3.8808, + "step": 259072 + }, + { + "epoch": 1.01, + "learning_rate": 4.5750044386558117e-05, + "loss": 3.8658, + "step": 259584 + }, + { + "epoch": 1.01, + "learning_rate": 4.5741658439047596e-05, + "loss": 3.8671, + "step": 260096 + }, + { + "epoch": 1.01, + "learning_rate": 4.5733288870340806e-05, + "loss": 3.8798, + "step": 260608 + }, + { + "epoch": 1.01, + "learning_rate": 4.5724902922830286e-05, + "loss": 3.8612, + "step": 261120 + }, + { + "epoch": 1.01, + "learning_rate": 4.5716516975319765e-05, + "loss": 3.8693, + "step": 261632 + }, + { + "epoch": 1.01, + "learning_rate": 4.5708131027809245e-05, + "loss": 3.8796, + "step": 262144 + }, + { + "epoch": 1.01, + "learning_rate": 4.569976145910246e-05, + "loss": 3.8795, + "step": 262656 + }, + { + "epoch": 1.01, + "learning_rate": 4.569137551159194e-05, + "loss": 3.8637, + "step": 263168 + }, + { + "epoch": 1.01, + "learning_rate": 4.568298956408142e-05, + "loss": 3.8587, + "step": 263680 + }, + { + "epoch": 1.01, + "learning_rate": 4.56746036165709e-05, + "loss": 3.8612, + "step": 264192 + }, + { + "epoch": 1.01, + "learning_rate": 4.5666217669060374e-05, + "loss": 3.8743, + "step": 264704 + }, + { + "epoch": 1.01, + "learning_rate": 4.5657831721549854e-05, + "loss": 3.8819, + "step": 265216 + }, + { + "epoch": 1.01, + "learning_rate": 4.564946215284307e-05, + "loss": 3.8694, + "step": 265728 + }, + { + "epoch": 1.01, + "learning_rate": 4.564107620533255e-05, + "loss": 3.8796, + "step": 266240 + }, + { + "epoch": 1.01, + "learning_rate": 4.563269025782202e-05, + "loss": 3.8794, + "step": 266752 + }, + { + "epoch": 1.01, + "learning_rate": 4.56243043103115e-05, + "loss": 3.8781, + "step": 267264 + }, + { + "epoch": 1.01, + "learning_rate": 4.561593474160472e-05, + "loss": 3.8579, + "step": 267776 + }, + { + "epoch": 1.01, + "learning_rate": 4.56075487940942e-05, + "loss": 3.8758, + "step": 268288 + }, + { + "epoch": 1.01, + "learning_rate": 4.559916284658368e-05, + "loss": 3.8691, + "step": 268800 + }, + { + "epoch": 1.01, + "learning_rate": 4.559077689907316e-05, + "loss": 3.8632, + "step": 269312 + }, + { + "epoch": 1.01, + "learning_rate": 4.558239095156264e-05, + "loss": 3.8679, + "step": 269824 + }, + { + "epoch": 1.01, + "learning_rate": 4.557402138285585e-05, + "loss": 3.8687, + "step": 270336 + }, + { + "epoch": 1.01, + "learning_rate": 4.556563543534533e-05, + "loss": 3.8727, + "step": 270848 + }, + { + "epoch": 1.01, + "learning_rate": 4.555724948783481e-05, + "loss": 3.8698, + "step": 271360 + }, + { + "epoch": 1.01, + "learning_rate": 4.554886354032429e-05, + "loss": 3.8606, + "step": 271872 + }, + { + "epoch": 1.01, + "learning_rate": 4.55404939716175e-05, + "loss": 3.8676, + "step": 272384 + }, + { + "epoch": 1.01, + "learning_rate": 4.553210802410698e-05, + "loss": 3.8629, + "step": 272896 + }, + { + "epoch": 1.01, + "learning_rate": 4.552372207659646e-05, + "loss": 3.8677, + "step": 273408 + }, + { + "epoch": 1.01, + "learning_rate": 4.551533612908594e-05, + "loss": 3.8638, + "step": 273920 + }, + { + "epoch": 1.01, + "learning_rate": 4.550695018157542e-05, + "loss": 3.8553, + "step": 274432 + }, + { + "epoch": 1.02, + "learning_rate": 4.549858061286863e-05, + "loss": 3.8699, + "step": 274944 + }, + { + "epoch": 1.02, + "learning_rate": 4.549019466535811e-05, + "loss": 3.8628, + "step": 275456 + }, + { + "epoch": 1.02, + "learning_rate": 4.548180871784759e-05, + "loss": 3.8568, + "step": 275968 + }, + { + "epoch": 1.02, + "learning_rate": 4.547342277033707e-05, + "loss": 3.8574, + "step": 276480 + }, + { + "epoch": 1.02, + "learning_rate": 4.546503682282655e-05, + "loss": 3.8746, + "step": 276992 + }, + { + "epoch": 1.02, + "learning_rate": 4.545666725411976e-05, + "loss": 3.8686, + "step": 277504 + }, + { + "epoch": 1.02, + "learning_rate": 4.544828130660924e-05, + "loss": 3.8594, + "step": 278016 + }, + { + "epoch": 1.02, + "learning_rate": 4.543989535909872e-05, + "loss": 3.8511, + "step": 278528 + }, + { + "epoch": 1.02, + "learning_rate": 4.54315094115882e-05, + "loss": 3.8602, + "step": 279040 + }, + { + "epoch": 1.02, + "learning_rate": 4.542313984288141e-05, + "loss": 3.8549, + "step": 279552 + }, + { + "epoch": 1.02, + "learning_rate": 4.541475389537089e-05, + "loss": 3.8752, + "step": 280064 + }, + { + "epoch": 1.02, + "learning_rate": 4.540636794786037e-05, + "loss": 3.8605, + "step": 280576 + }, + { + "epoch": 1.02, + "learning_rate": 4.539798200034985e-05, + "loss": 3.8569, + "step": 281088 + }, + { + "epoch": 1.02, + "learning_rate": 4.538959605283933e-05, + "loss": 3.8498, + "step": 281600 + }, + { + "epoch": 1.02, + "learning_rate": 4.5381226484132546e-05, + "loss": 3.863, + "step": 282112 + }, + { + "epoch": 1.02, + "learning_rate": 4.5372840536622026e-05, + "loss": 3.8356, + "step": 282624 + }, + { + "epoch": 1.02, + "learning_rate": 4.5364454589111506e-05, + "loss": 3.8529, + "step": 283136 + }, + { + "epoch": 1.02, + "learning_rate": 4.5356068641600986e-05, + "loss": 3.8541, + "step": 283648 + }, + { + "epoch": 1.02, + "learning_rate": 4.5347682694090466e-05, + "loss": 3.8557, + "step": 284160 + }, + { + "epoch": 1.02, + "learning_rate": 4.5339313125383675e-05, + "loss": 3.8418, + "step": 284672 + }, + { + "epoch": 1.02, + "learning_rate": 4.5330927177873155e-05, + "loss": 3.859, + "step": 285184 + }, + { + "epoch": 1.02, + "learning_rate": 4.5322541230362635e-05, + "loss": 3.8447, + "step": 285696 + }, + { + "epoch": 1.02, + "learning_rate": 4.5314155282852115e-05, + "loss": 3.862, + "step": 286208 + }, + { + "epoch": 1.02, + "learning_rate": 4.5305769335341595e-05, + "loss": 3.8559, + "step": 286720 + }, + { + "epoch": 1.02, + "learning_rate": 4.5297399766634804e-05, + "loss": 3.8491, + "step": 287232 + }, + { + "epoch": 1.02, + "learning_rate": 4.5289013819124284e-05, + "loss": 3.8674, + "step": 287744 + }, + { + "epoch": 1.02, + "learning_rate": 4.528062787161377e-05, + "loss": 3.8711, + "step": 288256 + }, + { + "epoch": 1.02, + "learning_rate": 4.527225830290698e-05, + "loss": 3.8554, + "step": 288768 + }, + { + "epoch": 1.02, + "learning_rate": 4.526387235539646e-05, + "loss": 3.8475, + "step": 289280 + }, + { + "epoch": 1.02, + "learning_rate": 4.525548640788594e-05, + "loss": 3.8548, + "step": 289792 + }, + { + "epoch": 1.02, + "learning_rate": 4.524710046037542e-05, + "loss": 3.8466, + "step": 290304 + }, + { + "epoch": 1.02, + "learning_rate": 4.52387145128649e-05, + "loss": 3.8484, + "step": 290816 + }, + { + "epoch": 1.02, + "learning_rate": 4.523032856535438e-05, + "loss": 3.8609, + "step": 291328 + }, + { + "epoch": 1.02, + "learning_rate": 4.522194261784386e-05, + "loss": 3.8444, + "step": 291840 + }, + { + "epoch": 1.02, + "learning_rate": 4.521355667033333e-05, + "loss": 3.8619, + "step": 292352 + }, + { + "epoch": 1.02, + "learning_rate": 4.520518710162655e-05, + "loss": 3.8515, + "step": 292864 + }, + { + "epoch": 1.02, + "learning_rate": 4.519680115411603e-05, + "loss": 3.8539, + "step": 293376 + }, + { + "epoch": 1.02, + "learning_rate": 4.518841520660551e-05, + "loss": 3.8386, + "step": 293888 + }, + { + "epoch": 1.02, + "learning_rate": 4.518002925909499e-05, + "loss": 3.8543, + "step": 294400 + }, + { + "epoch": 1.02, + "learning_rate": 4.5171659690388204e-05, + "loss": 3.8401, + "step": 294912 + }, + { + "epoch": 1.02, + "learning_rate": 4.5163273742877684e-05, + "loss": 3.8592, + "step": 295424 + }, + { + "epoch": 1.02, + "learning_rate": 4.515488779536716e-05, + "loss": 3.8496, + "step": 295936 + }, + { + "epoch": 1.02, + "learning_rate": 4.514650184785664e-05, + "loss": 3.8552, + "step": 296448 + }, + { + "epoch": 1.02, + "learning_rate": 4.513811590034612e-05, + "loss": 3.8328, + "step": 296960 + }, + { + "epoch": 1.02, + "learning_rate": 4.5129746331639333e-05, + "loss": 3.8586, + "step": 297472 + }, + { + "epoch": 1.02, + "learning_rate": 4.5121360384128807e-05, + "loss": 3.8463, + "step": 297984 + }, + { + "epoch": 1.02, + "learning_rate": 4.5112974436618287e-05, + "loss": 3.8478, + "step": 298496 + }, + { + "epoch": 1.02, + "learning_rate": 4.5104588489107766e-05, + "loss": 3.8471, + "step": 299008 + }, + { + "epoch": 1.02, + "learning_rate": 4.5096218920400976e-05, + "loss": 3.8561, + "step": 299520 + }, + { + "epoch": 1.02, + "learning_rate": 4.508783297289046e-05, + "loss": 3.854, + "step": 300032 + }, + { + "epoch": 1.02, + "learning_rate": 4.507944702537994e-05, + "loss": 3.8533, + "step": 300544 + }, + { + "epoch": 1.02, + "learning_rate": 4.507106107786942e-05, + "loss": 3.8403, + "step": 301056 + }, + { + "epoch": 1.02, + "learning_rate": 4.50626751303589e-05, + "loss": 3.8427, + "step": 301568 + }, + { + "epoch": 1.02, + "learning_rate": 4.505430556165211e-05, + "loss": 3.8448, + "step": 302080 + }, + { + "epoch": 1.02, + "learning_rate": 4.504591961414159e-05, + "loss": 3.8353, + "step": 302592 + }, + { + "epoch": 1.02, + "learning_rate": 4.503753366663107e-05, + "loss": 3.8484, + "step": 303104 + }, + { + "epoch": 1.02, + "learning_rate": 4.502914771912055e-05, + "loss": 3.8531, + "step": 303616 + }, + { + "epoch": 1.02, + "learning_rate": 4.502077815041376e-05, + "loss": 3.8437, + "step": 304128 + }, + { + "epoch": 1.02, + "learning_rate": 4.501239220290324e-05, + "loss": 3.8379, + "step": 304640 + }, + { + "epoch": 1.02, + "learning_rate": 4.500400625539272e-05, + "loss": 3.8501, + "step": 305152 + }, + { + "epoch": 1.03, + "eval_loss": 3.9095025062561035, + "eval_runtime": 305.1679, + "eval_samples_per_second": 1250.43, + "eval_steps_per_second": 39.077, + "step": 305280 + }, + { + "epoch": 0.0, + "learning_rate": 4.49956203078822e-05, + "loss": 3.8285, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.498723436037168e-05, + "loss": 3.8361, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.497884841286116e-05, + "loss": 3.8438, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.497046246535065e-05, + "loss": 3.8392, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.496207651784013e-05, + "loss": 3.8523, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.495369057032961e-05, + "loss": 3.8314, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.4945304622819087e-05, + "loss": 3.8398, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.4936918675308567e-05, + "loss": 3.8263, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.4928549106601776e-05, + "loss": 3.8424, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.4920163159091256e-05, + "loss": 3.8326, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.4911777211580736e-05, + "loss": 3.8386, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.4903391264070216e-05, + "loss": 3.8468, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.4895038074167154e-05, + "loss": 3.8256, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.4886652126656634e-05, + "loss": 3.8377, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.4878266179146114e-05, + "loss": 3.8299, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.48698802316356e-05, + "loss": 3.831, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.486149428412508e-05, + "loss": 3.8237, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.485310833661456e-05, + "loss": 3.8294, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.484472238910404e-05, + "loss": 3.8276, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.483633644159352e-05, + "loss": 3.8476, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.482796687288673e-05, + "loss": 3.8269, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.481958092537621e-05, + "loss": 3.8372, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.481119497786569e-05, + "loss": 3.8402, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.480280903035516e-05, + "loss": 3.8412, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.479442308284464e-05, + "loss": 3.818, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.478605351413786e-05, + "loss": 3.8322, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.477766756662734e-05, + "loss": 3.8194, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.476928161911682e-05, + "loss": 3.8293, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.47608956716063e-05, + "loss": 3.8173, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.4752526102899514e-05, + "loss": 3.8246, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.4744140155388994e-05, + "loss": 3.8312, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.473575420787847e-05, + "loss": 3.8322, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.472736826036795e-05, + "loss": 3.8221, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.471898231285743e-05, + "loss": 3.8337, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.4710612744150636e-05, + "loss": 3.8253, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.4702226796640116e-05, + "loss": 3.8296, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.4693840849129596e-05, + "loss": 3.8134, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.4685454901619076e-05, + "loss": 3.8257, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.4677085332912285e-05, + "loss": 3.8129, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.466869938540177e-05, + "loss": 3.8185, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.466031343789125e-05, + "loss": 3.8149, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.465192749038073e-05, + "loss": 3.8283, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.464355792167394e-05, + "loss": 3.8256, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.463517197416342e-05, + "loss": 3.8245, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.46267860266529e-05, + "loss": 3.8274, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.461840007914238e-05, + "loss": 3.8299, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.461001413163186e-05, + "loss": 3.8208, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.460164456292507e-05, + "loss": 3.8141, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.459325861541455e-05, + "loss": 3.8059, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.458487266790403e-05, + "loss": 3.8282, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.457648672039351e-05, + "loss": 3.8167, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.4568117151686725e-05, + "loss": 3.8104, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.4559731204176205e-05, + "loss": 3.8102, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.4551345256665685e-05, + "loss": 3.8192, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.4542959309155165e-05, + "loss": 3.8038, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.4534589740448374e-05, + "loss": 3.8113, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.4526203792937854e-05, + "loss": 3.8103, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.4517817845427334e-05, + "loss": 3.8137, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.4509431897916814e-05, + "loss": 3.8235, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.4501045950406294e-05, + "loss": 3.8043, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.44926763816995e-05, + "loss": 3.8052, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.448429043418898e-05, + "loss": 3.8183, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.447590448667846e-05, + "loss": 3.8028, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.446751853916794e-05, + "loss": 3.8054, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.445914897046116e-05, + "loss": 3.8173, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.445076302295064e-05, + "loss": 3.8158, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.444237707544012e-05, + "loss": 3.8043, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.44339911279296e-05, + "loss": 3.795, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.442560518041908e-05, + "loss": 3.7956, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.441721923290856e-05, + "loss": 3.8102, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.440884966420177e-05, + "loss": 3.8221, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.440046371669125e-05, + "loss": 3.8067, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.439207776918073e-05, + "loss": 3.8194, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.438369182167021e-05, + "loss": 3.8172, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.437532225296342e-05, + "loss": 3.821, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.43669363054529e-05, + "loss": 3.7992, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.435855035794238e-05, + "loss": 3.8142, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.4350164410431864e-05, + "loss": 3.8069, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.434179484172507e-05, + "loss": 3.8013, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.433340889421455e-05, + "loss": 3.8117, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.432502294670403e-05, + "loss": 3.8072, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.431663699919351e-05, + "loss": 3.8072, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.430825105168299e-05, + "loss": 3.8092, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.42998814829762e-05, + "loss": 3.8055, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.429149553546568e-05, + "loss": 3.8082, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.428310958795516e-05, + "loss": 3.8005, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.427472364044464e-05, + "loss": 3.8095, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.426635407173785e-05, + "loss": 3.8001, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.425796812422733e-05, + "loss": 3.7995, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.424958217671682e-05, + "loss": 3.8089, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.42411962292063e-05, + "loss": 3.8053, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.4232826660499506e-05, + "loss": 3.797, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.4224440712988986e-05, + "loss": 3.7983, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.4216054765478466e-05, + "loss": 3.8155, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.4207668817967946e-05, + "loss": 3.8092, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.4199299249261155e-05, + "loss": 3.8038, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.4190913301750635e-05, + "loss": 3.7933, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.4182527354240115e-05, + "loss": 3.7998, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.4174141406729595e-05, + "loss": 3.7974, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.416575545921907e-05, + "loss": 3.8105, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.4157385890512284e-05, + "loss": 3.8075, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.414899994300177e-05, + "loss": 3.7987, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.4140613995491244e-05, + "loss": 3.7915, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.4132228047980724e-05, + "loss": 3.8066, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.412385847927394e-05, + "loss": 3.7745, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.411547253176342e-05, + "loss": 3.8004, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.410708658425289e-05, + "loss": 3.7918, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.409870063674237e-05, + "loss": 3.7985, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.409033106803559e-05, + "loss": 3.7863, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.408194512052507e-05, + "loss": 3.8022, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.407355917301454e-05, + "loss": 3.793, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.406517322550402e-05, + "loss": 3.7992, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.405680365679724e-05, + "loss": 3.8027, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.404841770928672e-05, + "loss": 3.7898, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.40400317617762e-05, + "loss": 3.8111, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.403164581426568e-05, + "loss": 3.8158, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.4023276245558894e-05, + "loss": 3.7999, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.401489029804837e-05, + "loss": 3.7893, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.400650435053785e-05, + "loss": 3.8022, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.399811840302733e-05, + "loss": 3.7926, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.398974883432054e-05, + "loss": 3.7887, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.3981362886810016e-05, + "loss": 3.8047, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.3972976939299496e-05, + "loss": 3.7875, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.3964590991788976e-05, + "loss": 3.8025, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.395622142308219e-05, + "loss": 3.7974, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.394783547557167e-05, + "loss": 3.7987, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.393944952806115e-05, + "loss": 3.7889, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.393106358055063e-05, + "loss": 3.7931, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.392269401184384e-05, + "loss": 3.7901, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.391430806433332e-05, + "loss": 3.8043, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.39059221168228e-05, + "loss": 3.7935, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.389753616931228e-05, + "loss": 3.799, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.388916660060549e-05, + "loss": 3.7775, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.388078065309497e-05, + "loss": 3.8034, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.387239470558445e-05, + "loss": 3.7934, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.386400875807393e-05, + "loss": 3.7974, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.3855639189367145e-05, + "loss": 3.7901, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.3847253241856625e-05, + "loss": 3.8012, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.3838867294346105e-05, + "loss": 3.7979, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.3830481346835585e-05, + "loss": 3.8041, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.3822111778128794e-05, + "loss": 3.7816, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.3813725830618274e-05, + "loss": 3.7918, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.3805339883107754e-05, + "loss": 3.7909, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.3796953935597234e-05, + "loss": 3.7811, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.378858436689044e-05, + "loss": 3.796, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.378019841937992e-05, + "loss": 3.7963, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.37718124718694e-05, + "loss": 3.7962, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.376342652435888e-05, + "loss": 3.7786, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.37550569556521e-05, + "loss": 3.7982, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 3.884186029434204, + "eval_runtime": 308.3906, + "eval_samples_per_second": 1237.362, + "eval_steps_per_second": 38.668, + "step": 381600 + }, + { + "epoch": 1.0, + "learning_rate": 4.374667100814158e-05, + "loss": 3.7858, + "step": 381952 + }, + { + "epoch": 1.0, + "learning_rate": 4.373828506063106e-05, + "loss": 3.7784, + "step": 382464 + }, + { + "epoch": 1.0, + "learning_rate": 4.372989911312054e-05, + "loss": 3.7934, + "step": 382976 + }, + { + "epoch": 1.0, + "learning_rate": 4.372152954441375e-05, + "loss": 3.7872, + "step": 383488 + }, + { + "epoch": 1.0, + "learning_rate": 4.371314359690323e-05, + "loss": 3.7925, + "step": 384000 + }, + { + "epoch": 1.0, + "learning_rate": 4.370475764939271e-05, + "loss": 3.781, + "step": 384512 + }, + { + "epoch": 1.0, + "learning_rate": 4.369637170188219e-05, + "loss": 3.7847, + "step": 385024 + }, + { + "epoch": 1.0, + "learning_rate": 4.36880021331754e-05, + "loss": 3.7737, + "step": 385536 + }, + { + "epoch": 1.0, + "learning_rate": 4.367961618566488e-05, + "loss": 3.7881, + "step": 386048 + }, + { + "epoch": 1.0, + "learning_rate": 4.367123023815436e-05, + "loss": 3.7831, + "step": 386560 + }, + { + "epoch": 1.0, + "learning_rate": 4.366284429064384e-05, + "loss": 3.7854, + "step": 387072 + }, + { + "epoch": 1.0, + "learning_rate": 4.365447472193705e-05, + "loss": 3.7948, + "step": 387584 + }, + { + "epoch": 1.0, + "learning_rate": 4.364610515323026e-05, + "loss": 3.7755, + "step": 388096 + }, + { + "epoch": 1.0, + "learning_rate": 4.363771920571974e-05, + "loss": 3.7859, + "step": 388608 + }, + { + "epoch": 1.0, + "learning_rate": 4.362933325820922e-05, + "loss": 3.7782, + "step": 389120 + }, + { + "epoch": 1.0, + "learning_rate": 4.36209473106987e-05, + "loss": 3.7773, + "step": 389632 + }, + { + "epoch": 1.0, + "learning_rate": 4.361256136318818e-05, + "loss": 3.7703, + "step": 390144 + }, + { + "epoch": 1.0, + "learning_rate": 4.360417541567766e-05, + "loss": 3.778, + "step": 390656 + }, + { + "epoch": 1.0, + "learning_rate": 4.359578946816714e-05, + "loss": 3.7726, + "step": 391168 + }, + { + "epoch": 1.0, + "learning_rate": 4.358740352065662e-05, + "loss": 3.7933, + "step": 391680 + }, + { + "epoch": 1.0, + "learning_rate": 4.357903395194983e-05, + "loss": 3.781, + "step": 392192 + }, + { + "epoch": 1.0, + "learning_rate": 4.357064800443931e-05, + "loss": 3.7846, + "step": 392704 + }, + { + "epoch": 1.0, + "learning_rate": 4.356226205692879e-05, + "loss": 3.7916, + "step": 393216 + }, + { + "epoch": 1.0, + "learning_rate": 4.355387610941827e-05, + "loss": 3.7891, + "step": 393728 + }, + { + "epoch": 1.0, + "learning_rate": 4.3545506540711486e-05, + "loss": 3.7643, + "step": 394240 + }, + { + "epoch": 1.0, + "learning_rate": 4.3537120593200966e-05, + "loss": 3.7806, + "step": 394752 + }, + { + "epoch": 1.0, + "learning_rate": 4.3528734645690446e-05, + "loss": 3.7725, + "step": 395264 + }, + { + "epoch": 1.0, + "learning_rate": 4.3520348698179926e-05, + "loss": 3.7776, + "step": 395776 + }, + { + "epoch": 1.0, + "learning_rate": 4.3511979129473135e-05, + "loss": 3.7693, + "step": 396288 + }, + { + "epoch": 1.0, + "learning_rate": 4.3503593181962615e-05, + "loss": 3.7733, + "step": 396800 + }, + { + "epoch": 1.01, + "learning_rate": 4.3495207234452095e-05, + "loss": 3.7813, + "step": 397312 + }, + { + "epoch": 1.01, + "learning_rate": 4.3486821286941575e-05, + "loss": 3.779, + "step": 397824 + }, + { + "epoch": 1.01, + "learning_rate": 4.3478451718234784e-05, + "loss": 3.7742, + "step": 398336 + }, + { + "epoch": 1.01, + "learning_rate": 4.3470065770724264e-05, + "loss": 3.7792, + "step": 398848 + }, + { + "epoch": 1.01, + "learning_rate": 4.3461679823213744e-05, + "loss": 3.7773, + "step": 399360 + }, + { + "epoch": 1.01, + "learning_rate": 4.3453293875703224e-05, + "loss": 3.7785, + "step": 399872 + }, + { + "epoch": 1.01, + "learning_rate": 4.344492430699644e-05, + "loss": 3.7687, + "step": 400384 + }, + { + "epoch": 1.01, + "learning_rate": 4.343653835948592e-05, + "loss": 3.7682, + "step": 400896 + }, + { + "epoch": 1.01, + "learning_rate": 4.34281524119754e-05, + "loss": 3.7681, + "step": 401408 + }, + { + "epoch": 1.01, + "learning_rate": 4.341976646446488e-05, + "loss": 3.7666, + "step": 401920 + }, + { + "epoch": 1.01, + "learning_rate": 4.341139689575809e-05, + "loss": 3.7663, + "step": 402432 + }, + { + "epoch": 1.01, + "learning_rate": 4.340301094824757e-05, + "loss": 3.7773, + "step": 402944 + }, + { + "epoch": 1.01, + "learning_rate": 4.339462500073705e-05, + "loss": 3.777, + "step": 403456 + }, + { + "epoch": 1.01, + "learning_rate": 4.338623905322653e-05, + "loss": 3.7754, + "step": 403968 + }, + { + "epoch": 1.01, + "learning_rate": 4.337786948451974e-05, + "loss": 3.7819, + "step": 404480 + }, + { + "epoch": 1.01, + "learning_rate": 4.336948353700922e-05, + "loss": 3.7725, + "step": 404992 + }, + { + "epoch": 1.01, + "learning_rate": 4.33610975894987e-05, + "loss": 3.7752, + "step": 405504 + }, + { + "epoch": 1.01, + "learning_rate": 4.335271164198818e-05, + "loss": 3.7646, + "step": 406016 + }, + { + "epoch": 1.01, + "learning_rate": 4.3344325694477664e-05, + "loss": 3.7537, + "step": 406528 + }, + { + "epoch": 1.01, + "learning_rate": 4.3335956125770873e-05, + "loss": 3.7803, + "step": 407040 + }, + { + "epoch": 1.01, + "learning_rate": 4.3327570178260353e-05, + "loss": 3.7662, + "step": 407552 + }, + { + "epoch": 1.01, + "learning_rate": 4.331918423074983e-05, + "loss": 3.7649, + "step": 408064 + }, + { + "epoch": 1.01, + "learning_rate": 4.331079828323931e-05, + "loss": 3.7617, + "step": 408576 + }, + { + "epoch": 1.01, + "learning_rate": 4.330242871453252e-05, + "loss": 3.7668, + "step": 409088 + }, + { + "epoch": 1.01, + "learning_rate": 4.3294042767022e-05, + "loss": 3.7558, + "step": 409600 + }, + { + "epoch": 1.01, + "learning_rate": 4.328565681951148e-05, + "loss": 3.7631, + "step": 410112 + }, + { + "epoch": 1.01, + "learning_rate": 4.327727087200096e-05, + "loss": 3.7651, + "step": 410624 + }, + { + "epoch": 1.01, + "learning_rate": 4.326890130329417e-05, + "loss": 3.763, + "step": 411136 + }, + { + "epoch": 1.01, + "learning_rate": 4.326051535578365e-05, + "loss": 3.7755, + "step": 411648 + }, + { + "epoch": 1.01, + "learning_rate": 4.325212940827313e-05, + "loss": 3.755, + "step": 412160 + }, + { + "epoch": 1.01, + "learning_rate": 4.324374346076261e-05, + "loss": 3.7589, + "step": 412672 + }, + { + "epoch": 1.01, + "learning_rate": 4.323537389205583e-05, + "loss": 3.7737, + "step": 413184 + }, + { + "epoch": 1.01, + "learning_rate": 4.322698794454531e-05, + "loss": 3.7535, + "step": 413696 + }, + { + "epoch": 1.01, + "learning_rate": 4.321860199703479e-05, + "loss": 3.7576, + "step": 414208 + }, + { + "epoch": 1.01, + "learning_rate": 4.321021604952427e-05, + "loss": 3.7657, + "step": 414720 + }, + { + "epoch": 1.01, + "learning_rate": 4.3201846480817476e-05, + "loss": 3.7698, + "step": 415232 + }, + { + "epoch": 1.01, + "learning_rate": 4.3193460533306956e-05, + "loss": 3.756, + "step": 415744 + }, + { + "epoch": 1.01, + "learning_rate": 4.3185074585796436e-05, + "loss": 3.7527, + "step": 416256 + }, + { + "epoch": 1.01, + "learning_rate": 4.3176688638285916e-05, + "loss": 3.7453, + "step": 416768 + }, + { + "epoch": 1.01, + "learning_rate": 4.3168319069579125e-05, + "loss": 3.7632, + "step": 417280 + }, + { + "epoch": 1.01, + "learning_rate": 4.3159933122068605e-05, + "loss": 3.774, + "step": 417792 + }, + { + "epoch": 1.01, + "learning_rate": 4.3151547174558085e-05, + "loss": 3.7613, + "step": 418304 + }, + { + "epoch": 1.01, + "learning_rate": 4.3143161227047565e-05, + "loss": 3.768, + "step": 418816 + }, + { + "epoch": 1.01, + "learning_rate": 4.313479165834078e-05, + "loss": 3.769, + "step": 419328 + }, + { + "epoch": 1.01, + "learning_rate": 4.312640571083026e-05, + "loss": 3.7765, + "step": 419840 + }, + { + "epoch": 1.01, + "learning_rate": 4.311801976331974e-05, + "loss": 3.7531, + "step": 420352 + }, + { + "epoch": 1.01, + "learning_rate": 4.3109633815809214e-05, + "loss": 3.7668, + "step": 420864 + }, + { + "epoch": 1.01, + "learning_rate": 4.310126424710243e-05, + "loss": 3.7616, + "step": 421376 + }, + { + "epoch": 1.01, + "learning_rate": 4.309287829959191e-05, + "loss": 3.7512, + "step": 421888 + }, + { + "epoch": 1.01, + "learning_rate": 4.308449235208139e-05, + "loss": 3.7661, + "step": 422400 + }, + { + "epoch": 1.01, + "learning_rate": 4.307610640457086e-05, + "loss": 3.7645, + "step": 422912 + }, + { + "epoch": 1.01, + "learning_rate": 4.306773683586408e-05, + "loss": 3.7622, + "step": 423424 + }, + { + "epoch": 1.01, + "learning_rate": 4.305935088835356e-05, + "loss": 3.7644, + "step": 423936 + }, + { + "epoch": 1.01, + "learning_rate": 4.305096494084304e-05, + "loss": 3.7584, + "step": 424448 + }, + { + "epoch": 1.01, + "learning_rate": 4.304257899333252e-05, + "loss": 3.7535, + "step": 424960 + }, + { + "epoch": 1.01, + "learning_rate": 4.3034209424625734e-05, + "loss": 3.7585, + "step": 425472 + }, + { + "epoch": 1.01, + "learning_rate": 4.3025823477115214e-05, + "loss": 3.7654, + "step": 425984 + }, + { + "epoch": 1.01, + "learning_rate": 4.301743752960469e-05, + "loss": 3.7509, + "step": 426496 + }, + { + "epoch": 1.01, + "learning_rate": 4.300905158209417e-05, + "loss": 3.7543, + "step": 427008 + }, + { + "epoch": 1.02, + "learning_rate": 4.3000682013387383e-05, + "loss": 3.7643, + "step": 427520 + }, + { + "epoch": 1.02, + "learning_rate": 4.299229606587686e-05, + "loss": 3.7601, + "step": 428032 + }, + { + "epoch": 1.02, + "learning_rate": 4.2983910118366337e-05, + "loss": 3.751, + "step": 428544 + }, + { + "epoch": 1.02, + "learning_rate": 4.2975524170855817e-05, + "loss": 3.7532, + "step": 429056 + }, + { + "epoch": 1.02, + "learning_rate": 4.296715460214903e-05, + "loss": 3.77, + "step": 429568 + }, + { + "epoch": 1.02, + "learning_rate": 4.295876865463851e-05, + "loss": 3.7648, + "step": 430080 + }, + { + "epoch": 1.02, + "learning_rate": 4.295038270712799e-05, + "loss": 3.7617, + "step": 430592 + }, + { + "epoch": 1.02, + "learning_rate": 4.294199675961747e-05, + "loss": 3.7432, + "step": 431104 + }, + { + "epoch": 1.02, + "learning_rate": 4.293362719091069e-05, + "loss": 3.756, + "step": 431616 + }, + { + "epoch": 1.02, + "learning_rate": 4.292524124340016e-05, + "loss": 3.7529, + "step": 432128 + }, + { + "epoch": 1.02, + "learning_rate": 4.291685529588964e-05, + "loss": 3.7637, + "step": 432640 + }, + { + "epoch": 1.02, + "learning_rate": 4.290846934837912e-05, + "loss": 3.7644, + "step": 433152 + }, + { + "epoch": 1.02, + "learning_rate": 4.290009977967234e-05, + "loss": 3.7528, + "step": 433664 + }, + { + "epoch": 1.02, + "learning_rate": 4.289171383216181e-05, + "loss": 3.7462, + "step": 434176 + }, + { + "epoch": 1.02, + "learning_rate": 4.288332788465129e-05, + "loss": 3.7607, + "step": 434688 + }, + { + "epoch": 1.02, + "learning_rate": 4.287494193714077e-05, + "loss": 3.7321, + "step": 435200 + }, + { + "epoch": 1.02, + "learning_rate": 4.286657236843398e-05, + "loss": 3.7535, + "step": 435712 + }, + { + "epoch": 1.02, + "learning_rate": 4.2858186420923466e-05, + "loss": 3.7447, + "step": 436224 + }, + { + "epoch": 1.02, + "learning_rate": 4.2849800473412946e-05, + "loss": 3.758, + "step": 436736 + }, + { + "epoch": 1.02, + "learning_rate": 4.284143090470616e-05, + "loss": 3.7405, + "step": 437248 + }, + { + "epoch": 1.02, + "learning_rate": 4.2833044957195635e-05, + "loss": 3.7571, + "step": 437760 + }, + { + "epoch": 1.02, + "learning_rate": 4.2824659009685115e-05, + "loss": 3.7471, + "step": 438272 + }, + { + "epoch": 1.02, + "learning_rate": 4.2816273062174595e-05, + "loss": 3.7553, + "step": 438784 + }, + { + "epoch": 1.02, + "learning_rate": 4.2807887114664075e-05, + "loss": 3.7599, + "step": 439296 + }, + { + "epoch": 1.02, + "learning_rate": 4.2799501167153555e-05, + "loss": 3.7503, + "step": 439808 + }, + { + "epoch": 1.02, + "learning_rate": 4.2791115219643035e-05, + "loss": 3.7627, + "step": 440320 + }, + { + "epoch": 1.02, + "learning_rate": 4.2782729272132515e-05, + "loss": 3.7697, + "step": 440832 + }, + { + "epoch": 1.02, + "learning_rate": 4.277437608222945e-05, + "loss": 3.7575, + "step": 441344 + }, + { + "epoch": 1.02, + "learning_rate": 4.276599013471893e-05, + "loss": 3.7471, + "step": 441856 + }, + { + "epoch": 1.02, + "learning_rate": 4.275760418720842e-05, + "loss": 3.7508, + "step": 442368 + }, + { + "epoch": 1.02, + "learning_rate": 4.27492182396979e-05, + "loss": 3.7524, + "step": 442880 + }, + { + "epoch": 1.02, + "learning_rate": 4.274083229218738e-05, + "loss": 3.7411, + "step": 443392 + }, + { + "epoch": 1.02, + "learning_rate": 4.273244634467686e-05, + "loss": 3.7653, + "step": 443904 + }, + { + "epoch": 1.02, + "learning_rate": 4.272406039716634e-05, + "loss": 3.7393, + "step": 444416 + }, + { + "epoch": 1.02, + "learning_rate": 4.271567444965582e-05, + "loss": 3.7603, + "step": 444928 + }, + { + "epoch": 1.02, + "learning_rate": 4.270730488094903e-05, + "loss": 3.7532, + "step": 445440 + }, + { + "epoch": 1.02, + "learning_rate": 4.269891893343851e-05, + "loss": 3.7533, + "step": 445952 + }, + { + "epoch": 1.02, + "learning_rate": 4.269053298592799e-05, + "loss": 3.7459, + "step": 446464 + }, + { + "epoch": 1.02, + "learning_rate": 4.268214703841747e-05, + "loss": 3.7517, + "step": 446976 + }, + { + "epoch": 1.02, + "learning_rate": 4.267377746971068e-05, + "loss": 3.743, + "step": 447488 + }, + { + "epoch": 1.02, + "learning_rate": 4.266539152220016e-05, + "loss": 3.7609, + "step": 448000 + }, + { + "epoch": 1.02, + "learning_rate": 4.265700557468964e-05, + "loss": 3.7495, + "step": 448512 + }, + { + "epoch": 1.02, + "learning_rate": 4.264861962717912e-05, + "loss": 3.7558, + "step": 449024 + }, + { + "epoch": 1.02, + "learning_rate": 4.264025005847233e-05, + "loss": 3.736, + "step": 449536 + }, + { + "epoch": 1.02, + "learning_rate": 4.263186411096181e-05, + "loss": 3.76, + "step": 450048 + }, + { + "epoch": 1.02, + "learning_rate": 4.262347816345129e-05, + "loss": 3.7471, + "step": 450560 + }, + { + "epoch": 1.02, + "learning_rate": 4.261509221594077e-05, + "loss": 3.7531, + "step": 451072 + }, + { + "epoch": 1.02, + "learning_rate": 4.260672264723398e-05, + "loss": 3.7483, + "step": 451584 + }, + { + "epoch": 1.02, + "learning_rate": 4.259833669972346e-05, + "loss": 3.7564, + "step": 452096 + }, + { + "epoch": 1.02, + "learning_rate": 4.258995075221294e-05, + "loss": 3.7529, + "step": 452608 + }, + { + "epoch": 1.02, + "learning_rate": 4.258156480470242e-05, + "loss": 3.7655, + "step": 453120 + }, + { + "epoch": 1.02, + "learning_rate": 4.257319523599563e-05, + "loss": 3.7374, + "step": 453632 + }, + { + "epoch": 1.02, + "learning_rate": 4.256480928848511e-05, + "loss": 3.7496, + "step": 454144 + }, + { + "epoch": 1.02, + "learning_rate": 4.255642334097459e-05, + "loss": 3.7471, + "step": 454656 + }, + { + "epoch": 1.02, + "learning_rate": 4.254803739346407e-05, + "loss": 3.7445, + "step": 455168 + }, + { + "epoch": 1.02, + "learning_rate": 4.253966782475729e-05, + "loss": 3.7472, + "step": 455680 + }, + { + "epoch": 1.02, + "learning_rate": 4.253128187724677e-05, + "loss": 3.7555, + "step": 456192 + }, + { + "epoch": 1.02, + "learning_rate": 4.252289592973625e-05, + "loss": 3.7541, + "step": 456704 + }, + { + "epoch": 1.02, + "learning_rate": 4.251450998222573e-05, + "loss": 3.7357, + "step": 457216 + }, + { + "epoch": 1.02, + "learning_rate": 4.2506140413518936e-05, + "loss": 3.7556, + "step": 457728 + }, + { + "epoch": 1.03, + "eval_loss": 3.8682146072387695, + "eval_runtime": 305.7468, + "eval_samples_per_second": 1248.062, + "eval_steps_per_second": 39.003, + "step": 457920 + }, + { + "epoch": 0.0, + "learning_rate": 4.2497754466008416e-05, + "loss": 3.7433, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.2489368518497896e-05, + "loss": 3.7326, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.2480982570987376e-05, + "loss": 3.7516, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.2472596623476856e-05, + "loss": 3.7445, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.2464210675966336e-05, + "loss": 3.751, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.2455824728455816e-05, + "loss": 3.7383, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.2447438780945296e-05, + "loss": 3.7386, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.2439052833434776e-05, + "loss": 3.7365, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.243068326472799e-05, + "loss": 3.7458, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.242229731721747e-05, + "loss": 3.7398, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.2413911369706945e-05, + "loss": 3.7465, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.2405525422196424e-05, + "loss": 3.7497, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.239717223229337e-05, + "loss": 3.7379, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.238878628478285e-05, + "loss": 3.74, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.238040033727233e-05, + "loss": 3.7413, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.237201438976181e-05, + "loss": 3.7344, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.236362844225129e-05, + "loss": 3.727, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.235524249474076e-05, + "loss": 3.7354, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.234685654723025e-05, + "loss": 3.7354, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.233847059971973e-05, + "loss": 3.7495, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.2330101031012945e-05, + "loss": 3.7413, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.232171508350242e-05, + "loss": 3.7439, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.23133291359919e-05, + "loss": 3.7476, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.230494318848138e-05, + "loss": 3.7451, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.229657361977459e-05, + "loss": 3.7268, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.228818767226407e-05, + "loss": 3.7415, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.227980172475355e-05, + "loss": 3.7268, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.227141577724303e-05, + "loss": 3.7355, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.2263046208536236e-05, + "loss": 3.7334, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.2254660261025716e-05, + "loss": 3.7312, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.2246274313515196e-05, + "loss": 3.7417, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.223788836600468e-05, + "loss": 3.7376, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.222951879729789e-05, + "loss": 3.7352, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.222113284978737e-05, + "loss": 3.7386, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.221274690227685e-05, + "loss": 3.7361, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.220437733357006e-05, + "loss": 3.7411, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.219599138605954e-05, + "loss": 3.729, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.218760543854902e-05, + "loss": 3.7274, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.21792194910385e-05, + "loss": 3.7255, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.217084992233171e-05, + "loss": 3.7263, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.216246397482119e-05, + "loss": 3.7284, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.215407802731067e-05, + "loss": 3.7369, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.214569207980015e-05, + "loss": 3.7363, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.2137322511093366e-05, + "loss": 3.7362, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.2128936563582846e-05, + "loss": 3.7413, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.2120550616072326e-05, + "loss": 3.7366, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.2112164668561806e-05, + "loss": 3.7351, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.2103795099855015e-05, + "loss": 3.7232, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.2095409152344495e-05, + "loss": 3.7135, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.2087023204833975e-05, + "loss": 3.7436, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.2078637257323454e-05, + "loss": 3.7285, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.2070267688616664e-05, + "loss": 3.7211, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.2061881741106144e-05, + "loss": 3.7276, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.2053495793595623e-05, + "loss": 3.7225, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.2045109846085103e-05, + "loss": 3.7216, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.203674027737832e-05, + "loss": 3.7213, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.20283543298678e-05, + "loss": 3.7264, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.201996838235728e-05, + "loss": 3.7244, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.201158243484676e-05, + "loss": 3.7377, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.200321286613997e-05, + "loss": 3.7168, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.199482691862945e-05, + "loss": 3.7171, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.198644097111893e-05, + "loss": 3.7389, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.197805502360841e-05, + "loss": 3.7109, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.196968545490162e-05, + "loss": 3.7173, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.19612995073911e-05, + "loss": 3.7283, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.195291355988058e-05, + "loss": 3.7357, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.194452761237006e-05, + "loss": 3.7146, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.193615804366327e-05, + "loss": 3.7152, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.192777209615275e-05, + "loss": 3.7067, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.191938614864223e-05, + "loss": 3.7242, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.191100020113171e-05, + "loss": 3.737, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.190263063242492e-05, + "loss": 3.7248, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.18942446849144e-05, + "loss": 3.7255, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.188585873740388e-05, + "loss": 3.7338, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.187747278989336e-05, + "loss": 3.7369, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.186910322118657e-05, + "loss": 3.7166, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.186071727367605e-05, + "loss": 3.7281, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.185233132616553e-05, + "loss": 3.7241, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.184394537865501e-05, + "loss": 3.7111, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.183557580994823e-05, + "loss": 3.7253, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.182718986243771e-05, + "loss": 3.7276, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.1818803914927187e-05, + "loss": 3.726, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.1810417967416667e-05, + "loss": 3.7237, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.1802048398709876e-05, + "loss": 3.7227, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.1793662451199356e-05, + "loss": 3.7139, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.1785276503688836e-05, + "loss": 3.7249, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.1776890556178315e-05, + "loss": 3.7248, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.1768520987471525e-05, + "loss": 3.7177, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.1760135039961005e-05, + "loss": 3.7181, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.1751749092450484e-05, + "loss": 3.7199, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.1743363144939964e-05, + "loss": 3.7276, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.173499357623318e-05, + "loss": 3.7162, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.172660762872266e-05, + "loss": 3.7135, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.171822168121214e-05, + "loss": 3.7319, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.170983573370162e-05, + "loss": 3.7247, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.170146616499483e-05, + "loss": 3.7241, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.169308021748431e-05, + "loss": 3.7062, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.168469426997379e-05, + "loss": 3.7231, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.167630832246327e-05, + "loss": 3.713, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.166793875375648e-05, + "loss": 3.7235, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.165955280624596e-05, + "loss": 3.7294, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.165116685873544e-05, + "loss": 3.7138, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.164278091122492e-05, + "loss": 3.7117, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.1634411342518134e-05, + "loss": 3.72, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.1626025395007614e-05, + "loss": 3.6958, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.1617639447497094e-05, + "loss": 3.7211, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.1609253499986574e-05, + "loss": 3.7033, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.160088393127978e-05, + "loss": 3.7222, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.159251436257299e-05, + "loss": 3.7062, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.158412841506247e-05, + "loss": 3.7185, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.157574246755195e-05, + "loss": 3.7128, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.156735652004143e-05, + "loss": 3.7142, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.155897057253091e-05, + "loss": 3.7268, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.155058462502039e-05, + "loss": 3.7103, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.154219867750987e-05, + "loss": 3.7259, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.153381272999936e-05, + "loss": 3.7312, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.15254595400963e-05, + "loss": 3.7191, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.151707359258578e-05, + "loss": 3.7178, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.150868764507526e-05, + "loss": 3.7097, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.150030169756474e-05, + "loss": 3.7155, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.1491915750054217e-05, + "loss": 3.7103, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.1483529802543697e-05, + "loss": 3.7266, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.1475143855033176e-05, + "loss": 3.7007, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.1466757907522656e-05, + "loss": 3.7246, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.1458388338815866e-05, + "loss": 3.72, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.1450002391305345e-05, + "loss": 3.7168, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.1441616443794825e-05, + "loss": 3.7063, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.1433230496284305e-05, + "loss": 3.7184, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.142484454877379e-05, + "loss": 3.705, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.1416458601263265e-05, + "loss": 3.7287, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.1408072653752745e-05, + "loss": 3.7116, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.139970308504596e-05, + "loss": 3.7228, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.139131713753544e-05, + "loss": 3.6982, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.1382931190024914e-05, + "loss": 3.7254, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.1374545242514394e-05, + "loss": 3.7132, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.136617567380761e-05, + "loss": 3.7189, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.135780610510082e-05, + "loss": 3.7121, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.13494201575903e-05, + "loss": 3.7133, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.134103421007978e-05, + "loss": 3.7194, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.133264826256926e-05, + "loss": 3.7335, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.132426231505874e-05, + "loss": 3.6992, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.131587636754822e-05, + "loss": 3.7143, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.13074904200377e-05, + "loss": 3.7106, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.129910447252718e-05, + "loss": 3.712, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.129073490382039e-05, + "loss": 3.7087, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.128234895630987e-05, + "loss": 3.719, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.127396300879935e-05, + "loss": 3.7171, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.126557706128883e-05, + "loss": 3.7033, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.125720749258204e-05, + "loss": 3.7228, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 3.857759952545166, + "eval_runtime": 304.9483, + "eval_samples_per_second": 1251.33, + "eval_steps_per_second": 39.105, + "step": 534240 + }, + { + "epoch": 1.0, + "learning_rate": 4.124882154507152e-05, + "loss": 3.7077, + "step": 534528 + }, + { + "epoch": 1.0, + "learning_rate": 4.1240435597561e-05, + "loss": 3.6984, + "step": 535040 + }, + { + "epoch": 1.0, + "learning_rate": 4.1232049650050484e-05, + "loss": 3.7174, + "step": 535552 + }, + { + "epoch": 1.0, + "learning_rate": 4.122368008134369e-05, + "loss": 3.7064, + "step": 536064 + }, + { + "epoch": 1.0, + "learning_rate": 4.121529413383317e-05, + "loss": 3.7156, + "step": 536576 + }, + { + "epoch": 1.0, + "learning_rate": 4.120690818632265e-05, + "loss": 3.7044, + "step": 537088 + }, + { + "epoch": 1.0, + "learning_rate": 4.119852223881213e-05, + "loss": 3.7068, + "step": 537600 + }, + { + "epoch": 1.0, + "learning_rate": 4.119015267010534e-05, + "loss": 3.701, + "step": 538112 + }, + { + "epoch": 1.0, + "learning_rate": 4.118176672259482e-05, + "loss": 3.712, + "step": 538624 + }, + { + "epoch": 1.0, + "learning_rate": 4.11733807750843e-05, + "loss": 3.7023, + "step": 539136 + }, + { + "epoch": 1.0, + "learning_rate": 4.116499482757378e-05, + "loss": 3.7116, + "step": 539648 + }, + { + "epoch": 1.0, + "learning_rate": 4.115662525886699e-05, + "loss": 3.7136, + "step": 540160 + }, + { + "epoch": 1.0, + "learning_rate": 4.1148255690160207e-05, + "loss": 3.7082, + "step": 540672 + }, + { + "epoch": 1.0, + "learning_rate": 4.1139869742649686e-05, + "loss": 3.7059, + "step": 541184 + }, + { + "epoch": 1.0, + "learning_rate": 4.1131483795139166e-05, + "loss": 3.7041, + "step": 541696 + }, + { + "epoch": 1.0, + "learning_rate": 4.1123097847628646e-05, + "loss": 3.6971, + "step": 542208 + }, + { + "epoch": 1.0, + "learning_rate": 4.1114711900118126e-05, + "loss": 3.6946, + "step": 542720 + }, + { + "epoch": 1.0, + "learning_rate": 4.1106325952607606e-05, + "loss": 3.7015, + "step": 543232 + }, + { + "epoch": 1.0, + "learning_rate": 4.1097940005097086e-05, + "loss": 3.7015, + "step": 543744 + }, + { + "epoch": 1.0, + "learning_rate": 4.1089554057586566e-05, + "loss": 3.7106, + "step": 544256 + }, + { + "epoch": 1.0, + "learning_rate": 4.1081184488879775e-05, + "loss": 3.7116, + "step": 544768 + }, + { + "epoch": 1.0, + "learning_rate": 4.1072798541369255e-05, + "loss": 3.7076, + "step": 545280 + }, + { + "epoch": 1.0, + "learning_rate": 4.1064412593858735e-05, + "loss": 3.7121, + "step": 545792 + }, + { + "epoch": 1.0, + "learning_rate": 4.1056026646348215e-05, + "loss": 3.7094, + "step": 546304 + }, + { + "epoch": 1.0, + "learning_rate": 4.1047657077641424e-05, + "loss": 3.6902, + "step": 546816 + }, + { + "epoch": 1.0, + "learning_rate": 4.1039271130130904e-05, + "loss": 3.7109, + "step": 547328 + }, + { + "epoch": 1.0, + "learning_rate": 4.103088518262039e-05, + "loss": 3.6965, + "step": 547840 + }, + { + "epoch": 1.0, + "learning_rate": 4.102249923510987e-05, + "loss": 3.6997, + "step": 548352 + }, + { + "epoch": 1.0, + "learning_rate": 4.101412966640308e-05, + "loss": 3.6965, + "step": 548864 + }, + { + "epoch": 1.0, + "learning_rate": 4.100574371889256e-05, + "loss": 3.7003, + "step": 549376 + }, + { + "epoch": 1.01, + "learning_rate": 4.099735777138204e-05, + "loss": 3.7031, + "step": 549888 + }, + { + "epoch": 1.01, + "learning_rate": 4.098897182387152e-05, + "loss": 3.7062, + "step": 550400 + }, + { + "epoch": 1.01, + "learning_rate": 4.098060225516473e-05, + "loss": 3.7039, + "step": 550912 + }, + { + "epoch": 1.01, + "learning_rate": 4.097221630765421e-05, + "loss": 3.7051, + "step": 551424 + }, + { + "epoch": 1.01, + "learning_rate": 4.096383036014369e-05, + "loss": 3.6962, + "step": 551936 + }, + { + "epoch": 1.01, + "learning_rate": 4.09554607914369e-05, + "loss": 3.7074, + "step": 552448 + }, + { + "epoch": 1.01, + "learning_rate": 4.094707484392638e-05, + "loss": 3.7016, + "step": 552960 + }, + { + "epoch": 1.01, + "learning_rate": 4.093868889641586e-05, + "loss": 3.688, + "step": 553472 + }, + { + "epoch": 1.01, + "learning_rate": 4.0930302948905345e-05, + "loss": 3.6913, + "step": 553984 + }, + { + "epoch": 1.01, + "learning_rate": 4.0921933380198554e-05, + "loss": 3.6931, + "step": 554496 + }, + { + "epoch": 1.01, + "learning_rate": 4.0913547432688034e-05, + "loss": 3.6995, + "step": 555008 + }, + { + "epoch": 1.01, + "learning_rate": 4.0905161485177514e-05, + "loss": 3.7015, + "step": 555520 + }, + { + "epoch": 1.01, + "learning_rate": 4.0896775537666994e-05, + "loss": 3.7041, + "step": 556032 + }, + { + "epoch": 1.01, + "learning_rate": 4.08884059689602e-05, + "loss": 3.6992, + "step": 556544 + }, + { + "epoch": 1.01, + "learning_rate": 4.088002002144968e-05, + "loss": 3.7114, + "step": 557056 + }, + { + "epoch": 1.01, + "learning_rate": 4.087163407393916e-05, + "loss": 3.702, + "step": 557568 + }, + { + "epoch": 1.01, + "learning_rate": 4.086324812642864e-05, + "loss": 3.7041, + "step": 558080 + }, + { + "epoch": 1.01, + "learning_rate": 4.085487855772185e-05, + "loss": 3.6937, + "step": 558592 + }, + { + "epoch": 1.01, + "learning_rate": 4.084649261021133e-05, + "loss": 3.6739, + "step": 559104 + }, + { + "epoch": 1.01, + "learning_rate": 4.083810666270081e-05, + "loss": 3.7101, + "step": 559616 + }, + { + "epoch": 1.01, + "learning_rate": 4.08297207151903e-05, + "loss": 3.696, + "step": 560128 + }, + { + "epoch": 1.01, + "learning_rate": 4.082135114648351e-05, + "loss": 3.6938, + "step": 560640 + }, + { + "epoch": 1.01, + "learning_rate": 4.081296519897299e-05, + "loss": 3.6921, + "step": 561152 + }, + { + "epoch": 1.01, + "learning_rate": 4.080457925146247e-05, + "loss": 3.6925, + "step": 561664 + }, + { + "epoch": 1.01, + "learning_rate": 4.079619330395195e-05, + "loss": 3.6891, + "step": 562176 + }, + { + "epoch": 1.01, + "learning_rate": 4.0787823735245156e-05, + "loss": 3.6865, + "step": 562688 + }, + { + "epoch": 1.01, + "learning_rate": 4.0779437787734636e-05, + "loss": 3.6917, + "step": 563200 + }, + { + "epoch": 1.01, + "learning_rate": 4.0771051840224116e-05, + "loss": 3.6893, + "step": 563712 + }, + { + "epoch": 1.01, + "learning_rate": 4.0762665892713596e-05, + "loss": 3.7052, + "step": 564224 + }, + { + "epoch": 1.01, + "learning_rate": 4.0754296324006805e-05, + "loss": 3.6841, + "step": 564736 + }, + { + "epoch": 1.01, + "learning_rate": 4.0745910376496285e-05, + "loss": 3.6828, + "step": 565248 + }, + { + "epoch": 1.01, + "learning_rate": 4.0737524428985765e-05, + "loss": 3.7066, + "step": 565760 + }, + { + "epoch": 1.01, + "learning_rate": 4.072913848147525e-05, + "loss": 3.6775, + "step": 566272 + }, + { + "epoch": 1.01, + "learning_rate": 4.072076891276846e-05, + "loss": 3.6854, + "step": 566784 + }, + { + "epoch": 1.01, + "learning_rate": 4.071238296525794e-05, + "loss": 3.6964, + "step": 567296 + }, + { + "epoch": 1.01, + "learning_rate": 4.070399701774742e-05, + "loss": 3.7021, + "step": 567808 + }, + { + "epoch": 1.01, + "learning_rate": 4.06956110702369e-05, + "loss": 3.6843, + "step": 568320 + }, + { + "epoch": 1.01, + "learning_rate": 4.068724150153011e-05, + "loss": 3.682, + "step": 568832 + }, + { + "epoch": 1.01, + "learning_rate": 4.067885555401959e-05, + "loss": 3.677, + "step": 569344 + }, + { + "epoch": 1.01, + "learning_rate": 4.067046960650907e-05, + "loss": 3.6899, + "step": 569856 + }, + { + "epoch": 1.01, + "learning_rate": 4.066208365899855e-05, + "loss": 3.7032, + "step": 570368 + }, + { + "epoch": 1.01, + "learning_rate": 4.065371409029176e-05, + "loss": 3.691, + "step": 570880 + }, + { + "epoch": 1.01, + "learning_rate": 4.064532814278124e-05, + "loss": 3.6911, + "step": 571392 + }, + { + "epoch": 1.01, + "learning_rate": 4.063694219527072e-05, + "loss": 3.7023, + "step": 571904 + }, + { + "epoch": 1.01, + "learning_rate": 4.06285562477602e-05, + "loss": 3.7041, + "step": 572416 + }, + { + "epoch": 1.01, + "learning_rate": 4.0620186679053415e-05, + "loss": 3.6832, + "step": 572928 + }, + { + "epoch": 1.01, + "learning_rate": 4.0611800731542895e-05, + "loss": 3.6991, + "step": 573440 + }, + { + "epoch": 1.01, + "learning_rate": 4.0603414784032375e-05, + "loss": 3.687, + "step": 573952 + }, + { + "epoch": 1.01, + "learning_rate": 4.0595028836521855e-05, + "loss": 3.6864, + "step": 574464 + }, + { + "epoch": 1.01, + "learning_rate": 4.0586659267815064e-05, + "loss": 3.6898, + "step": 574976 + }, + { + "epoch": 1.01, + "learning_rate": 4.0578273320304544e-05, + "loss": 3.6996, + "step": 575488 + }, + { + "epoch": 1.01, + "learning_rate": 4.0569887372794024e-05, + "loss": 3.6915, + "step": 576000 + }, + { + "epoch": 1.01, + "learning_rate": 4.0561501425283504e-05, + "loss": 3.6969, + "step": 576512 + }, + { + "epoch": 1.01, + "learning_rate": 4.055313185657671e-05, + "loss": 3.688, + "step": 577024 + }, + { + "epoch": 1.01, + "learning_rate": 4.054474590906619e-05, + "loss": 3.6793, + "step": 577536 + }, + { + "epoch": 1.01, + "learning_rate": 4.053635996155567e-05, + "loss": 3.6922, + "step": 578048 + }, + { + "epoch": 1.01, + "learning_rate": 4.052797401404515e-05, + "loss": 3.6911, + "step": 578560 + }, + { + "epoch": 1.01, + "learning_rate": 4.051960444533837e-05, + "loss": 3.6855, + "step": 579072 + }, + { + "epoch": 1.01, + "learning_rate": 4.051121849782785e-05, + "loss": 3.6866, + "step": 579584 + }, + { + "epoch": 1.02, + "learning_rate": 4.050283255031733e-05, + "loss": 3.6897, + "step": 580096 + }, + { + "epoch": 1.02, + "learning_rate": 4.049444660280681e-05, + "loss": 3.6947, + "step": 580608 + }, + { + "epoch": 1.02, + "learning_rate": 4.048607703410002e-05, + "loss": 3.6852, + "step": 581120 + }, + { + "epoch": 1.02, + "learning_rate": 4.04776910865895e-05, + "loss": 3.6812, + "step": 581632 + }, + { + "epoch": 1.02, + "learning_rate": 4.046930513907898e-05, + "loss": 3.6982, + "step": 582144 + }, + { + "epoch": 1.02, + "learning_rate": 4.0460935570372186e-05, + "loss": 3.6965, + "step": 582656 + }, + { + "epoch": 1.02, + "learning_rate": 4.0452549622861666e-05, + "loss": 3.6913, + "step": 583168 + }, + { + "epoch": 1.02, + "learning_rate": 4.0444163675351146e-05, + "loss": 3.679, + "step": 583680 + }, + { + "epoch": 1.02, + "learning_rate": 4.0435777727840626e-05, + "loss": 3.687, + "step": 584192 + }, + { + "epoch": 1.02, + "learning_rate": 4.042740815913384e-05, + "loss": 3.6804, + "step": 584704 + }, + { + "epoch": 1.02, + "learning_rate": 4.041902221162332e-05, + "loss": 3.6915, + "step": 585216 + }, + { + "epoch": 1.02, + "learning_rate": 4.04106362641128e-05, + "loss": 3.6983, + "step": 585728 + }, + { + "epoch": 1.02, + "learning_rate": 4.040225031660228e-05, + "loss": 3.6856, + "step": 586240 + }, + { + "epoch": 1.02, + "learning_rate": 4.039388074789549e-05, + "loss": 3.6803, + "step": 586752 + }, + { + "epoch": 1.02, + "learning_rate": 4.038549480038497e-05, + "loss": 3.6838, + "step": 587264 + }, + { + "epoch": 1.02, + "learning_rate": 4.037710885287445e-05, + "loss": 3.6693, + "step": 587776 + }, + { + "epoch": 1.02, + "learning_rate": 4.036872290536393e-05, + "loss": 3.6842, + "step": 588288 + }, + { + "epoch": 1.02, + "learning_rate": 4.036035333665714e-05, + "loss": 3.6761, + "step": 588800 + }, + { + "epoch": 1.02, + "learning_rate": 4.035196738914662e-05, + "loss": 3.6926, + "step": 589312 + }, + { + "epoch": 1.02, + "learning_rate": 4.034359782043983e-05, + "loss": 3.6753, + "step": 589824 + }, + { + "epoch": 1.02, + "learning_rate": 4.0335211872929316e-05, + "loss": 3.6847, + "step": 590336 + }, + { + "epoch": 1.02, + "learning_rate": 4.0326825925418796e-05, + "loss": 3.6803, + "step": 590848 + }, + { + "epoch": 1.02, + "learning_rate": 4.0318439977908276e-05, + "loss": 3.6876, + "step": 591360 + }, + { + "epoch": 1.02, + "learning_rate": 4.0310054030397756e-05, + "loss": 3.6917, + "step": 591872 + }, + { + "epoch": 1.02, + "learning_rate": 4.0301668082887236e-05, + "loss": 3.6802, + "step": 592384 + }, + { + "epoch": 1.02, + "learning_rate": 4.029328213537671e-05, + "loss": 3.696, + "step": 592896 + }, + { + "epoch": 1.02, + "learning_rate": 4.028489618786619e-05, + "loss": 3.6989, + "step": 593408 + }, + { + "epoch": 1.02, + "learning_rate": 4.0276542997963134e-05, + "loss": 3.6874, + "step": 593920 + }, + { + "epoch": 1.02, + "learning_rate": 4.0268157050452614e-05, + "loss": 3.6909, + "step": 594432 + }, + { + "epoch": 1.02, + "learning_rate": 4.0259771102942094e-05, + "loss": 3.6779, + "step": 594944 + }, + { + "epoch": 1.02, + "learning_rate": 4.0251385155431574e-05, + "loss": 3.6845, + "step": 595456 + }, + { + "epoch": 1.02, + "learning_rate": 4.0242999207921054e-05, + "loss": 3.6849, + "step": 595968 + }, + { + "epoch": 1.02, + "learning_rate": 4.0234613260410534e-05, + "loss": 3.689, + "step": 596480 + }, + { + "epoch": 1.02, + "learning_rate": 4.0226227312900013e-05, + "loss": 3.6726, + "step": 596992 + }, + { + "epoch": 1.02, + "learning_rate": 4.0217841365389493e-05, + "loss": 3.6926, + "step": 597504 + }, + { + "epoch": 1.02, + "learning_rate": 4.020947179668271e-05, + "loss": 3.6913, + "step": 598016 + }, + { + "epoch": 1.02, + "learning_rate": 4.020108584917218e-05, + "loss": 3.6864, + "step": 598528 + }, + { + "epoch": 1.02, + "learning_rate": 4.019269990166166e-05, + "loss": 3.6753, + "step": 599040 + }, + { + "epoch": 1.02, + "learning_rate": 4.018431395415114e-05, + "loss": 3.6872, + "step": 599552 + }, + { + "epoch": 1.02, + "learning_rate": 4.017592800664062e-05, + "loss": 3.6764, + "step": 600064 + }, + { + "epoch": 1.02, + "learning_rate": 4.01675420591301e-05, + "loss": 3.6923, + "step": 600576 + }, + { + "epoch": 1.02, + "learning_rate": 4.015915611161958e-05, + "loss": 3.6856, + "step": 601088 + }, + { + "epoch": 1.02, + "learning_rate": 4.015078654291279e-05, + "loss": 3.6889, + "step": 601600 + }, + { + "epoch": 1.02, + "learning_rate": 4.014240059540227e-05, + "loss": 3.6663, + "step": 602112 + }, + { + "epoch": 1.02, + "learning_rate": 4.013401464789175e-05, + "loss": 3.6996, + "step": 602624 + }, + { + "epoch": 1.02, + "learning_rate": 4.012562870038124e-05, + "loss": 3.6784, + "step": 603136 + }, + { + "epoch": 1.02, + "learning_rate": 4.011725913167445e-05, + "loss": 3.6872, + "step": 603648 + }, + { + "epoch": 1.02, + "learning_rate": 4.0108889562967656e-05, + "loss": 3.682, + "step": 604160 + }, + { + "epoch": 1.02, + "learning_rate": 4.0100503615457136e-05, + "loss": 3.6808, + "step": 604672 + }, + { + "epoch": 1.02, + "learning_rate": 4.0092117667946616e-05, + "loss": 3.6913, + "step": 605184 + }, + { + "epoch": 1.02, + "learning_rate": 4.0083731720436096e-05, + "loss": 3.7005, + "step": 605696 + }, + { + "epoch": 1.02, + "learning_rate": 4.0075345772925576e-05, + "loss": 3.6711, + "step": 606208 + }, + { + "epoch": 1.02, + "learning_rate": 4.0066959825415056e-05, + "loss": 3.6861, + "step": 606720 + }, + { + "epoch": 1.02, + "learning_rate": 4.0058573877904536e-05, + "loss": 3.6808, + "step": 607232 + }, + { + "epoch": 1.02, + "learning_rate": 4.0050187930394016e-05, + "loss": 3.6795, + "step": 607744 + }, + { + "epoch": 1.02, + "learning_rate": 4.0041818361687225e-05, + "loss": 3.6796, + "step": 608256 + }, + { + "epoch": 1.02, + "learning_rate": 4.0033432414176705e-05, + "loss": 3.6879, + "step": 608768 + }, + { + "epoch": 1.02, + "learning_rate": 4.002504646666619e-05, + "loss": 3.6889, + "step": 609280 + }, + { + "epoch": 1.02, + "learning_rate": 4.001666051915567e-05, + "loss": 3.671, + "step": 609792 + }, + { + "epoch": 1.02, + "learning_rate": 4.000829095044888e-05, + "loss": 3.6904, + "step": 610304 + }, + { + "epoch": 1.03, + "eval_loss": 3.8511815071105957, + "eval_runtime": 307.5416, + "eval_samples_per_second": 1240.779, + "eval_steps_per_second": 38.775, + "step": 610560 + }, + { + "epoch": 0.0, + "learning_rate": 3.999990500293836e-05, + "loss": 3.6755, + "step": 610816 + }, + { + "epoch": 0.0, + "learning_rate": 3.999151905542784e-05, + "loss": 3.671, + "step": 611328 + }, + { + "epoch": 0.0, + "learning_rate": 3.998313310791732e-05, + "loss": 3.6822, + "step": 611840 + }, + { + "epoch": 0.0, + "learning_rate": 3.99747471604068e-05, + "loss": 3.6742, + "step": 612352 + }, + { + "epoch": 0.0, + "learning_rate": 3.996636121289628e-05, + "loss": 3.6868, + "step": 612864 + }, + { + "epoch": 0.0, + "learning_rate": 3.995797526538576e-05, + "loss": 3.6684, + "step": 613376 + }, + { + "epoch": 0.0, + "learning_rate": 3.994958931787524e-05, + "loss": 3.6829, + "step": 613888 + }, + { + "epoch": 0.0, + "learning_rate": 3.9941203370364714e-05, + "loss": 3.6705, + "step": 614400 + }, + { + "epoch": 0.0, + "learning_rate": 3.993283380165793e-05, + "loss": 3.682, + "step": 614912 + }, + { + "epoch": 0.0, + "learning_rate": 3.992444785414741e-05, + "loss": 3.674, + "step": 615424 + }, + { + "epoch": 0.0, + "learning_rate": 3.991606190663689e-05, + "loss": 3.6783, + "step": 615936 + }, + { + "epoch": 0.0, + "learning_rate": 3.990767595912637e-05, + "loss": 3.6861, + "step": 616448 + }, + { + "epoch": 0.0, + "learning_rate": 3.9899322769223314e-05, + "loss": 3.6765, + "step": 616960 + }, + { + "epoch": 0.0, + "learning_rate": 3.9890936821712794e-05, + "loss": 3.6769, + "step": 617472 + }, + { + "epoch": 0.0, + "learning_rate": 3.9882550874202274e-05, + "loss": 3.6765, + "step": 617984 + }, + { + "epoch": 0.0, + "learning_rate": 3.9874164926691754e-05, + "loss": 3.6659, + "step": 618496 + }, + { + "epoch": 0.0, + "learning_rate": 3.9865778979181234e-05, + "loss": 3.666, + "step": 619008 + }, + { + "epoch": 0.0, + "learning_rate": 3.9857393031670714e-05, + "loss": 3.6736, + "step": 619520 + }, + { + "epoch": 0.0, + "learning_rate": 3.984900708416019e-05, + "loss": 3.674, + "step": 620032 + }, + { + "epoch": 0.0, + "learning_rate": 3.984062113664967e-05, + "loss": 3.6753, + "step": 620544 + }, + { + "epoch": 0.0, + "learning_rate": 3.983225156794288e-05, + "loss": 3.6844, + "step": 621056 + }, + { + "epoch": 0.0, + "learning_rate": 3.982386562043236e-05, + "loss": 3.6784, + "step": 621568 + }, + { + "epoch": 0.0, + "learning_rate": 3.981547967292184e-05, + "loss": 3.6836, + "step": 622080 + }, + { + "epoch": 0.0, + "learning_rate": 3.980709372541132e-05, + "loss": 3.6794, + "step": 622592 + }, + { + "epoch": 0.0, + "learning_rate": 3.979872415670454e-05, + "loss": 3.666, + "step": 623104 + }, + { + "epoch": 0.0, + "learning_rate": 3.979033820919401e-05, + "loss": 3.681, + "step": 623616 + }, + { + "epoch": 0.0, + "learning_rate": 3.978195226168349e-05, + "loss": 3.6662, + "step": 624128 + }, + { + "epoch": 0.0, + "learning_rate": 3.977356631417297e-05, + "loss": 3.6733, + "step": 624640 + }, + { + "epoch": 0.0, + "learning_rate": 3.976519674546619e-05, + "loss": 3.6701, + "step": 625152 + }, + { + "epoch": 0.0, + "learning_rate": 3.975681079795566e-05, + "loss": 3.6683, + "step": 625664 + }, + { + "epoch": 0.01, + "learning_rate": 3.974842485044514e-05, + "loss": 3.6729, + "step": 626176 + }, + { + "epoch": 0.01, + "learning_rate": 3.974003890293462e-05, + "loss": 3.6769, + "step": 626688 + }, + { + "epoch": 0.01, + "learning_rate": 3.973166933422784e-05, + "loss": 3.6723, + "step": 627200 + }, + { + "epoch": 0.01, + "learning_rate": 3.972328338671732e-05, + "loss": 3.6775, + "step": 627712 + }, + { + "epoch": 0.01, + "learning_rate": 3.97148974392068e-05, + "loss": 3.6677, + "step": 628224 + }, + { + "epoch": 0.01, + "learning_rate": 3.970651149169628e-05, + "loss": 3.6786, + "step": 628736 + }, + { + "epoch": 0.01, + "learning_rate": 3.9698141922989486e-05, + "loss": 3.6716, + "step": 629248 + }, + { + "epoch": 0.01, + "learning_rate": 3.9689755975478966e-05, + "loss": 3.6605, + "step": 629760 + }, + { + "epoch": 0.01, + "learning_rate": 3.9681370027968446e-05, + "loss": 3.6671, + "step": 630272 + }, + { + "epoch": 0.01, + "learning_rate": 3.9672984080457926e-05, + "loss": 3.6621, + "step": 630784 + }, + { + "epoch": 0.01, + "learning_rate": 3.9664614511751135e-05, + "loss": 3.6695, + "step": 631296 + }, + { + "epoch": 0.01, + "learning_rate": 3.9656228564240615e-05, + "loss": 3.6721, + "step": 631808 + }, + { + "epoch": 0.01, + "learning_rate": 3.9647842616730095e-05, + "loss": 3.6725, + "step": 632320 + }, + { + "epoch": 0.01, + "learning_rate": 3.963947304802331e-05, + "loss": 3.6726, + "step": 632832 + }, + { + "epoch": 0.01, + "learning_rate": 3.9631087100512784e-05, + "loss": 3.6791, + "step": 633344 + }, + { + "epoch": 0.01, + "learning_rate": 3.962270115300227e-05, + "loss": 3.6735, + "step": 633856 + }, + { + "epoch": 0.01, + "learning_rate": 3.961431520549175e-05, + "loss": 3.6762, + "step": 634368 + }, + { + "epoch": 0.01, + "learning_rate": 3.960594563678496e-05, + "loss": 3.6676, + "step": 634880 + }, + { + "epoch": 0.01, + "learning_rate": 3.959755968927444e-05, + "loss": 3.6399, + "step": 635392 + }, + { + "epoch": 0.01, + "learning_rate": 3.958917374176392e-05, + "loss": 3.689, + "step": 635904 + }, + { + "epoch": 0.01, + "learning_rate": 3.95807877942534e-05, + "loss": 3.6638, + "step": 636416 + }, + { + "epoch": 0.01, + "learning_rate": 3.957241822554661e-05, + "loss": 3.6675, + "step": 636928 + }, + { + "epoch": 0.01, + "learning_rate": 3.956403227803609e-05, + "loss": 3.6648, + "step": 637440 + }, + { + "epoch": 0.01, + "learning_rate": 3.955564633052557e-05, + "loss": 3.6641, + "step": 637952 + }, + { + "epoch": 0.01, + "learning_rate": 3.954726038301505e-05, + "loss": 3.6553, + "step": 638464 + }, + { + "epoch": 0.01, + "learning_rate": 3.953889081430826e-05, + "loss": 3.6561, + "step": 638976 + }, + { + "epoch": 0.01, + "learning_rate": 3.953050486679774e-05, + "loss": 3.6665, + "step": 639488 + }, + { + "epoch": 0.01, + "learning_rate": 3.9522118919287224e-05, + "loss": 3.6602, + "step": 640000 + }, + { + "epoch": 0.01, + "learning_rate": 3.9513732971776704e-05, + "loss": 3.6798, + "step": 640512 + }, + { + "epoch": 0.01, + "learning_rate": 3.950536340306991e-05, + "loss": 3.6591, + "step": 641024 + }, + { + "epoch": 0.01, + "learning_rate": 3.949697745555939e-05, + "loss": 3.6534, + "step": 641536 + }, + { + "epoch": 0.01, + "learning_rate": 3.948859150804887e-05, + "loss": 3.6763, + "step": 642048 + }, + { + "epoch": 0.01, + "learning_rate": 3.948020556053835e-05, + "loss": 3.6521, + "step": 642560 + }, + { + "epoch": 0.01, + "learning_rate": 3.947183599183156e-05, + "loss": 3.6557, + "step": 643072 + }, + { + "epoch": 0.01, + "learning_rate": 3.946345004432104e-05, + "loss": 3.6694, + "step": 643584 + }, + { + "epoch": 0.01, + "learning_rate": 3.945506409681052e-05, + "loss": 3.673, + "step": 644096 + }, + { + "epoch": 0.01, + "learning_rate": 3.944669452810373e-05, + "loss": 3.656, + "step": 644608 + }, + { + "epoch": 0.01, + "learning_rate": 3.943830858059321e-05, + "loss": 3.6553, + "step": 645120 + }, + { + "epoch": 0.01, + "learning_rate": 3.942992263308269e-05, + "loss": 3.6484, + "step": 645632 + }, + { + "epoch": 0.01, + "learning_rate": 3.942153668557218e-05, + "loss": 3.662, + "step": 646144 + }, + { + "epoch": 0.01, + "learning_rate": 3.941315073806166e-05, + "loss": 3.6749, + "step": 646656 + }, + { + "epoch": 0.01, + "learning_rate": 3.940476479055114e-05, + "loss": 3.6623, + "step": 647168 + }, + { + "epoch": 0.01, + "learning_rate": 3.939637884304062e-05, + "loss": 3.6658, + "step": 647680 + }, + { + "epoch": 0.01, + "learning_rate": 3.93879928955301e-05, + "loss": 3.67, + "step": 648192 + }, + { + "epoch": 0.01, + "learning_rate": 3.937962332682331e-05, + "loss": 3.6755, + "step": 648704 + }, + { + "epoch": 0.01, + "learning_rate": 3.937123737931279e-05, + "loss": 3.6572, + "step": 649216 + }, + { + "epoch": 0.01, + "learning_rate": 3.9362851431802267e-05, + "loss": 3.6705, + "step": 649728 + }, + { + "epoch": 0.01, + "learning_rate": 3.9354465484291747e-05, + "loss": 3.6593, + "step": 650240 + }, + { + "epoch": 0.01, + "learning_rate": 3.9346095915584956e-05, + "loss": 3.6611, + "step": 650752 + }, + { + "epoch": 0.01, + "learning_rate": 3.9337709968074436e-05, + "loss": 3.66, + "step": 651264 + }, + { + "epoch": 0.01, + "learning_rate": 3.9329324020563916e-05, + "loss": 3.6688, + "step": 651776 + }, + { + "epoch": 0.01, + "learning_rate": 3.9320938073053396e-05, + "loss": 3.663, + "step": 652288 + }, + { + "epoch": 0.01, + "learning_rate": 3.931256850434661e-05, + "loss": 3.6717, + "step": 652800 + }, + { + "epoch": 0.01, + "learning_rate": 3.930418255683609e-05, + "loss": 3.655, + "step": 653312 + }, + { + "epoch": 0.01, + "learning_rate": 3.929579660932557e-05, + "loss": 3.6546, + "step": 653824 + }, + { + "epoch": 0.01, + "learning_rate": 3.928741066181505e-05, + "loss": 3.6667, + "step": 654336 + }, + { + "epoch": 0.01, + "learning_rate": 3.927904109310826e-05, + "loss": 3.6634, + "step": 654848 + }, + { + "epoch": 0.01, + "learning_rate": 3.927065514559774e-05, + "loss": 3.6537, + "step": 655360 + }, + { + "epoch": 0.01, + "learning_rate": 3.926226919808722e-05, + "loss": 3.6612, + "step": 655872 + }, + { + "epoch": 0.02, + "learning_rate": 3.92538832505767e-05, + "loss": 3.6639, + "step": 656384 + }, + { + "epoch": 0.02, + "learning_rate": 3.924551368186991e-05, + "loss": 3.6694, + "step": 656896 + }, + { + "epoch": 0.02, + "learning_rate": 3.923712773435939e-05, + "loss": 3.656, + "step": 657408 + }, + { + "epoch": 0.02, + "learning_rate": 3.922874178684887e-05, + "loss": 3.6543, + "step": 657920 + }, + { + "epoch": 0.02, + "learning_rate": 3.922035583933835e-05, + "loss": 3.6722, + "step": 658432 + }, + { + "epoch": 0.02, + "learning_rate": 3.9211986270631565e-05, + "loss": 3.6683, + "step": 658944 + }, + { + "epoch": 0.02, + "learning_rate": 3.9203600323121045e-05, + "loss": 3.6635, + "step": 659456 + }, + { + "epoch": 0.02, + "learning_rate": 3.9195214375610525e-05, + "loss": 3.6537, + "step": 659968 + }, + { + "epoch": 0.02, + "learning_rate": 3.9186828428100005e-05, + "loss": 3.658, + "step": 660480 + }, + { + "epoch": 0.02, + "learning_rate": 3.9178442480589485e-05, + "loss": 3.6537, + "step": 660992 + }, + { + "epoch": 0.02, + "learning_rate": 3.9170056533078965e-05, + "loss": 3.6662, + "step": 661504 + }, + { + "epoch": 0.02, + "learning_rate": 3.9161670585568445e-05, + "loss": 3.669, + "step": 662016 + }, + { + "epoch": 0.02, + "learning_rate": 3.9153301016861654e-05, + "loss": 3.6608, + "step": 662528 + }, + { + "epoch": 0.02, + "learning_rate": 3.9144915069351134e-05, + "loss": 3.6537, + "step": 663040 + }, + { + "epoch": 0.02, + "learning_rate": 3.9136529121840614e-05, + "loss": 3.6505, + "step": 663552 + }, + { + "epoch": 0.02, + "learning_rate": 3.912814317433009e-05, + "loss": 3.6513, + "step": 664064 + }, + { + "epoch": 0.02, + "learning_rate": 3.91197736056233e-05, + "loss": 3.6552, + "step": 664576 + }, + { + "epoch": 0.02, + "learning_rate": 3.911138765811278e-05, + "loss": 3.6491, + "step": 665088 + }, + { + "epoch": 0.02, + "learning_rate": 3.910300171060226e-05, + "loss": 3.6671, + "step": 665600 + }, + { + "epoch": 0.02, + "learning_rate": 3.909463214189548e-05, + "loss": 3.6498, + "step": 666112 + }, + { + "epoch": 0.02, + "learning_rate": 3.908624619438496e-05, + "loss": 3.6551, + "step": 666624 + }, + { + "epoch": 0.02, + "learning_rate": 3.907786024687444e-05, + "loss": 3.6515, + "step": 667136 + }, + { + "epoch": 0.02, + "learning_rate": 3.906947429936392e-05, + "loss": 3.6617, + "step": 667648 + }, + { + "epoch": 0.02, + "learning_rate": 3.906108835185339e-05, + "loss": 3.6646, + "step": 668160 + }, + { + "epoch": 0.02, + "learning_rate": 3.905270240434287e-05, + "loss": 3.653, + "step": 668672 + }, + { + "epoch": 0.02, + "learning_rate": 3.904431645683235e-05, + "loss": 3.6712, + "step": 669184 + }, + { + "epoch": 0.02, + "learning_rate": 3.903593050932183e-05, + "loss": 3.6728, + "step": 669696 + }, + { + "epoch": 0.02, + "learning_rate": 3.902756094061504e-05, + "loss": 3.6616, + "step": 670208 + }, + { + "epoch": 0.02, + "learning_rate": 3.901917499310452e-05, + "loss": 3.6627, + "step": 670720 + }, + { + "epoch": 0.02, + "learning_rate": 3.9010789045594e-05, + "loss": 3.6518, + "step": 671232 + }, + { + "epoch": 0.02, + "learning_rate": 3.900240309808349e-05, + "loss": 3.6526, + "step": 671744 + }, + { + "epoch": 0.02, + "learning_rate": 3.899401715057297e-05, + "loss": 3.6642, + "step": 672256 + }, + { + "epoch": 0.02, + "learning_rate": 3.898563120306245e-05, + "loss": 3.6588, + "step": 672768 + }, + { + "epoch": 0.02, + "learning_rate": 3.897724525555193e-05, + "loss": 3.6486, + "step": 673280 + }, + { + "epoch": 0.02, + "learning_rate": 3.896885930804141e-05, + "loss": 3.6657, + "step": 673792 + }, + { + "epoch": 0.02, + "learning_rate": 3.8960489739334616e-05, + "loss": 3.6658, + "step": 674304 + }, + { + "epoch": 0.02, + "learning_rate": 3.8952103791824096e-05, + "loss": 3.6588, + "step": 674816 + }, + { + "epoch": 0.02, + "learning_rate": 3.8943717844313576e-05, + "loss": 3.651, + "step": 675328 + }, + { + "epoch": 0.02, + "learning_rate": 3.8935331896803056e-05, + "loss": 3.6585, + "step": 675840 + }, + { + "epoch": 0.02, + "learning_rate": 3.8926945949292536e-05, + "loss": 3.6518, + "step": 676352 + }, + { + "epoch": 0.02, + "learning_rate": 3.8918560001782016e-05, + "loss": 3.6675, + "step": 676864 + }, + { + "epoch": 0.02, + "learning_rate": 3.8910174054271496e-05, + "loss": 3.6564, + "step": 677376 + }, + { + "epoch": 0.02, + "learning_rate": 3.8901788106760976e-05, + "loss": 3.6637, + "step": 677888 + }, + { + "epoch": 0.02, + "learning_rate": 3.8893418538054185e-05, + "loss": 3.6421, + "step": 678400 + }, + { + "epoch": 0.02, + "learning_rate": 3.888503259054367e-05, + "loss": 3.67, + "step": 678912 + }, + { + "epoch": 0.02, + "learning_rate": 3.887664664303315e-05, + "loss": 3.6488, + "step": 679424 + }, + { + "epoch": 0.02, + "learning_rate": 3.886827707432636e-05, + "loss": 3.664, + "step": 679936 + }, + { + "epoch": 0.02, + "learning_rate": 3.885989112681584e-05, + "loss": 3.6588, + "step": 680448 + }, + { + "epoch": 0.02, + "learning_rate": 3.885150517930532e-05, + "loss": 3.6506, + "step": 680960 + }, + { + "epoch": 0.02, + "learning_rate": 3.88431192317948e-05, + "loss": 3.6644, + "step": 681472 + }, + { + "epoch": 0.02, + "learning_rate": 3.883474966308801e-05, + "loss": 3.6751, + "step": 681984 + }, + { + "epoch": 0.02, + "learning_rate": 3.882636371557749e-05, + "loss": 3.6433, + "step": 682496 + }, + { + "epoch": 0.02, + "learning_rate": 3.881797776806697e-05, + "loss": 3.664, + "step": 683008 + }, + { + "epoch": 0.02, + "learning_rate": 3.880960819936018e-05, + "loss": 3.6533, + "step": 683520 + }, + { + "epoch": 0.02, + "learning_rate": 3.880122225184966e-05, + "loss": 3.6513, + "step": 684032 + }, + { + "epoch": 0.02, + "learning_rate": 3.879283630433914e-05, + "loss": 3.6539, + "step": 684544 + }, + { + "epoch": 0.02, + "learning_rate": 3.8784450356828625e-05, + "loss": 3.661, + "step": 685056 + }, + { + "epoch": 0.02, + "learning_rate": 3.8776064409318105e-05, + "loss": 3.6614, + "step": 685568 + }, + { + "epoch": 0.02, + "learning_rate": 3.876767846180758e-05, + "loss": 3.6508, + "step": 686080 + }, + { + "epoch": 0.02, + "learning_rate": 3.875929251429706e-05, + "loss": 3.6617, + "step": 686592 + }, + { + "epoch": 0.03, + "eval_loss": 3.8471453189849854, + "eval_runtime": 307.3194, + "eval_samples_per_second": 1241.675, + "eval_steps_per_second": 38.803, + "step": 686880 + }, + { + "epoch": 1.0, + "learning_rate": 3.875090656678654e-05, + "loss": 3.6484, + "step": 687104 + }, + { + "epoch": 1.0, + "learning_rate": 3.8742536998079754e-05, + "loss": 3.6455, + "step": 687616 + }, + { + "epoch": 1.0, + "learning_rate": 3.873415105056923e-05, + "loss": 3.6574, + "step": 688128 + }, + { + "epoch": 1.0, + "learning_rate": 3.872576510305871e-05, + "loss": 3.6524, + "step": 688640 + }, + { + "epoch": 1.0, + "learning_rate": 3.871737915554819e-05, + "loss": 3.6612, + "step": 689152 + }, + { + "epoch": 1.0, + "learning_rate": 3.8709009586841397e-05, + "loss": 3.6453, + "step": 689664 + }, + { + "epoch": 1.0, + "learning_rate": 3.8700623639330876e-05, + "loss": 3.6565, + "step": 690176 + }, + { + "epoch": 1.0, + "learning_rate": 3.869223769182036e-05, + "loss": 3.6483, + "step": 690688 + }, + { + "epoch": 1.0, + "learning_rate": 3.868386812311358e-05, + "loss": 3.6506, + "step": 691200 + }, + { + "epoch": 1.0, + "learning_rate": 3.867548217560305e-05, + "loss": 3.653, + "step": 691712 + }, + { + "epoch": 1.0, + "learning_rate": 3.866709622809253e-05, + "loss": 3.6504, + "step": 692224 + }, + { + "epoch": 1.0, + "learning_rate": 3.865871028058201e-05, + "loss": 3.6565, + "step": 692736 + }, + { + "epoch": 1.0, + "learning_rate": 3.865034071187522e-05, + "loss": 3.6617, + "step": 693248 + }, + { + "epoch": 1.0, + "learning_rate": 3.86419547643647e-05, + "loss": 3.644, + "step": 693760 + }, + { + "epoch": 1.0, + "learning_rate": 3.863356881685418e-05, + "loss": 3.649, + "step": 694272 + }, + { + "epoch": 1.0, + "learning_rate": 3.862518286934366e-05, + "loss": 3.6422, + "step": 694784 + }, + { + "epoch": 1.0, + "learning_rate": 3.861679692183314e-05, + "loss": 3.6378, + "step": 695296 + }, + { + "epoch": 1.0, + "learning_rate": 3.860841097432262e-05, + "loss": 3.6488, + "step": 695808 + }, + { + "epoch": 1.0, + "learning_rate": 3.86000250268121e-05, + "loss": 3.6423, + "step": 696320 + }, + { + "epoch": 1.0, + "learning_rate": 3.859163907930158e-05, + "loss": 3.6505, + "step": 696832 + }, + { + "epoch": 1.0, + "learning_rate": 3.85832695105948e-05, + "loss": 3.6602, + "step": 697344 + }, + { + "epoch": 1.0, + "learning_rate": 3.857488356308428e-05, + "loss": 3.6561, + "step": 697856 + }, + { + "epoch": 1.0, + "learning_rate": 3.856649761557376e-05, + "loss": 3.66, + "step": 698368 + }, + { + "epoch": 1.0, + "learning_rate": 3.855811166806324e-05, + "loss": 3.6528, + "step": 698880 + }, + { + "epoch": 1.0, + "learning_rate": 3.8549742099356446e-05, + "loss": 3.6391, + "step": 699392 + }, + { + "epoch": 1.0, + "learning_rate": 3.8541356151845926e-05, + "loss": 3.6545, + "step": 699904 + }, + { + "epoch": 1.0, + "learning_rate": 3.8532970204335406e-05, + "loss": 3.6408, + "step": 700416 + }, + { + "epoch": 1.0, + "learning_rate": 3.8524584256824886e-05, + "loss": 3.6519, + "step": 700928 + }, + { + "epoch": 1.0, + "learning_rate": 3.8516214688118095e-05, + "loss": 3.6417, + "step": 701440 + }, + { + "epoch": 1.0, + "learning_rate": 3.8507828740607575e-05, + "loss": 3.6441, + "step": 701952 + }, + { + "epoch": 1.01, + "learning_rate": 3.8499442793097055e-05, + "loss": 3.6437, + "step": 702464 + }, + { + "epoch": 1.01, + "learning_rate": 3.8491056845586535e-05, + "loss": 3.6514, + "step": 702976 + }, + { + "epoch": 1.01, + "learning_rate": 3.848268727687975e-05, + "loss": 3.6503, + "step": 703488 + }, + { + "epoch": 1.01, + "learning_rate": 3.847430132936923e-05, + "loss": 3.6487, + "step": 704000 + }, + { + "epoch": 1.01, + "learning_rate": 3.846591538185871e-05, + "loss": 3.6435, + "step": 704512 + }, + { + "epoch": 1.01, + "learning_rate": 3.845752943434819e-05, + "loss": 3.6519, + "step": 705024 + }, + { + "epoch": 1.01, + "learning_rate": 3.84491598656414e-05, + "loss": 3.6512, + "step": 705536 + }, + { + "epoch": 1.01, + "learning_rate": 3.844077391813088e-05, + "loss": 3.6363, + "step": 706048 + }, + { + "epoch": 1.01, + "learning_rate": 3.843238797062036e-05, + "loss": 3.6416, + "step": 706560 + }, + { + "epoch": 1.01, + "learning_rate": 3.842401840191357e-05, + "loss": 3.6364, + "step": 707072 + }, + { + "epoch": 1.01, + "learning_rate": 3.841563245440305e-05, + "loss": 3.6408, + "step": 707584 + }, + { + "epoch": 1.01, + "learning_rate": 3.840724650689253e-05, + "loss": 3.6467, + "step": 708096 + }, + { + "epoch": 1.01, + "learning_rate": 3.839886055938201e-05, + "loss": 3.649, + "step": 708608 + }, + { + "epoch": 1.01, + "learning_rate": 3.8390490990675224e-05, + "loss": 3.6486, + "step": 709120 + }, + { + "epoch": 1.01, + "learning_rate": 3.8382105043164704e-05, + "loss": 3.6507, + "step": 709632 + }, + { + "epoch": 1.01, + "learning_rate": 3.8373719095654184e-05, + "loss": 3.6522, + "step": 710144 + }, + { + "epoch": 1.01, + "learning_rate": 3.8365333148143664e-05, + "loss": 3.6479, + "step": 710656 + }, + { + "epoch": 1.01, + "learning_rate": 3.835696357943687e-05, + "loss": 3.6429, + "step": 711168 + }, + { + "epoch": 1.01, + "learning_rate": 3.834857763192635e-05, + "loss": 3.6167, + "step": 711680 + }, + { + "epoch": 1.01, + "learning_rate": 3.834019168441583e-05, + "loss": 3.6593, + "step": 712192 + }, + { + "epoch": 1.01, + "learning_rate": 3.833182211570904e-05, + "loss": 3.6388, + "step": 712704 + }, + { + "epoch": 1.01, + "learning_rate": 3.832343616819852e-05, + "loss": 3.6426, + "step": 713216 + }, + { + "epoch": 1.01, + "learning_rate": 3.8315050220688e-05, + "loss": 3.6438, + "step": 713728 + }, + { + "epoch": 1.01, + "learning_rate": 3.830666427317748e-05, + "loss": 3.6372, + "step": 714240 + }, + { + "epoch": 1.01, + "learning_rate": 3.829827832566696e-05, + "loss": 3.6299, + "step": 714752 + }, + { + "epoch": 1.01, + "learning_rate": 3.828990875696017e-05, + "loss": 3.6328, + "step": 715264 + }, + { + "epoch": 1.01, + "learning_rate": 3.828152280944966e-05, + "loss": 3.6432, + "step": 715776 + }, + { + "epoch": 1.01, + "learning_rate": 3.827313686193914e-05, + "loss": 3.6343, + "step": 716288 + }, + { + "epoch": 1.01, + "learning_rate": 3.826475091442862e-05, + "loss": 3.6534, + "step": 716800 + }, + { + "epoch": 1.01, + "learning_rate": 3.82563649669181e-05, + "loss": 3.6363, + "step": 717312 + }, + { + "epoch": 1.01, + "learning_rate": 3.824797901940758e-05, + "loss": 3.6253, + "step": 717824 + }, + { + "epoch": 1.01, + "learning_rate": 3.823959307189706e-05, + "loss": 3.6534, + "step": 718336 + }, + { + "epoch": 1.01, + "learning_rate": 3.823120712438653e-05, + "loss": 3.6318, + "step": 718848 + }, + { + "epoch": 1.01, + "learning_rate": 3.822283755567975e-05, + "loss": 3.6308, + "step": 719360 + }, + { + "epoch": 1.01, + "learning_rate": 3.8214451608169227e-05, + "loss": 3.6431, + "step": 719872 + }, + { + "epoch": 1.01, + "learning_rate": 3.8206065660658707e-05, + "loss": 3.6492, + "step": 720384 + }, + { + "epoch": 1.01, + "learning_rate": 3.8197696091951916e-05, + "loss": 3.6304, + "step": 720896 + }, + { + "epoch": 1.01, + "learning_rate": 3.8189310144441396e-05, + "loss": 3.6296, + "step": 721408 + }, + { + "epoch": 1.01, + "learning_rate": 3.8180924196930876e-05, + "loss": 3.6259, + "step": 721920 + }, + { + "epoch": 1.01, + "learning_rate": 3.8172538249420356e-05, + "loss": 3.6389, + "step": 722432 + }, + { + "epoch": 1.01, + "learning_rate": 3.8164152301909835e-05, + "loss": 3.6492, + "step": 722944 + }, + { + "epoch": 1.01, + "learning_rate": 3.8155766354399315e-05, + "loss": 3.6401, + "step": 723456 + }, + { + "epoch": 1.01, + "learning_rate": 3.8147380406888795e-05, + "loss": 3.6437, + "step": 723968 + }, + { + "epoch": 1.01, + "learning_rate": 3.8138994459378275e-05, + "loss": 3.6417, + "step": 724480 + }, + { + "epoch": 1.01, + "learning_rate": 3.8130624890671484e-05, + "loss": 3.6504, + "step": 724992 + }, + { + "epoch": 1.01, + "learning_rate": 3.8122238943160964e-05, + "loss": 3.6358, + "step": 725504 + }, + { + "epoch": 1.01, + "learning_rate": 3.8113852995650444e-05, + "loss": 3.6496, + "step": 726016 + }, + { + "epoch": 1.01, + "learning_rate": 3.8105467048139924e-05, + "loss": 3.6303, + "step": 726528 + }, + { + "epoch": 1.01, + "learning_rate": 3.8097097479433133e-05, + "loss": 3.6363, + "step": 727040 + }, + { + "epoch": 1.01, + "learning_rate": 3.808871153192261e-05, + "loss": 3.6381, + "step": 727552 + }, + { + "epoch": 1.01, + "learning_rate": 3.808034196321583e-05, + "loss": 3.6429, + "step": 728064 + }, + { + "epoch": 1.01, + "learning_rate": 3.807195601570531e-05, + "loss": 3.6415, + "step": 728576 + }, + { + "epoch": 1.01, + "learning_rate": 3.806357006819479e-05, + "loss": 3.6468, + "step": 729088 + }, + { + "epoch": 1.01, + "learning_rate": 3.805518412068427e-05, + "loss": 3.6322, + "step": 729600 + }, + { + "epoch": 1.01, + "learning_rate": 3.804681455197748e-05, + "loss": 3.6314, + "step": 730112 + }, + { + "epoch": 1.01, + "learning_rate": 3.803842860446696e-05, + "loss": 3.6396, + "step": 730624 + }, + { + "epoch": 1.01, + "learning_rate": 3.803004265695644e-05, + "loss": 3.6443, + "step": 731136 + }, + { + "epoch": 1.01, + "learning_rate": 3.802165670944592e-05, + "loss": 3.6284, + "step": 731648 + }, + { + "epoch": 1.01, + "learning_rate": 3.80132707619354e-05, + "loss": 3.6364, + "step": 732160 + }, + { + "epoch": 1.02, + "learning_rate": 3.800488481442488e-05, + "loss": 3.6408, + "step": 732672 + }, + { + "epoch": 1.02, + "learning_rate": 3.799649886691436e-05, + "loss": 3.6395, + "step": 733184 + }, + { + "epoch": 1.02, + "learning_rate": 3.798811291940384e-05, + "loss": 3.6351, + "step": 733696 + }, + { + "epoch": 1.02, + "learning_rate": 3.797974335069705e-05, + "loss": 3.6295, + "step": 734208 + }, + { + "epoch": 1.02, + "learning_rate": 3.7971357403186534e-05, + "loss": 3.6441, + "step": 734720 + }, + { + "epoch": 1.02, + "learning_rate": 3.796298783447974e-05, + "loss": 3.6458, + "step": 735232 + }, + { + "epoch": 1.02, + "learning_rate": 3.795460188696922e-05, + "loss": 3.64, + "step": 735744 + }, + { + "epoch": 1.02, + "learning_rate": 3.79462159394587e-05, + "loss": 3.6305, + "step": 736256 + }, + { + "epoch": 1.02, + "learning_rate": 3.793782999194818e-05, + "loss": 3.6349, + "step": 736768 + }, + { + "epoch": 1.02, + "learning_rate": 3.792944404443766e-05, + "loss": 3.6278, + "step": 737280 + }, + { + "epoch": 1.02, + "learning_rate": 3.792105809692714e-05, + "loss": 3.6436, + "step": 737792 + }, + { + "epoch": 1.02, + "learning_rate": 3.791267214941662e-05, + "loss": 3.6414, + "step": 738304 + }, + { + "epoch": 1.02, + "learning_rate": 3.790430258070983e-05, + "loss": 3.6341, + "step": 738816 + }, + { + "epoch": 1.02, + "learning_rate": 3.789591663319931e-05, + "loss": 3.6344, + "step": 739328 + }, + { + "epoch": 1.02, + "learning_rate": 3.788753068568879e-05, + "loss": 3.6267, + "step": 739840 + }, + { + "epoch": 1.02, + "learning_rate": 3.787914473817827e-05, + "loss": 3.6302, + "step": 740352 + }, + { + "epoch": 1.02, + "learning_rate": 3.787077516947149e-05, + "loss": 3.6285, + "step": 740864 + }, + { + "epoch": 1.02, + "learning_rate": 3.786238922196097e-05, + "loss": 3.6281, + "step": 741376 + }, + { + "epoch": 1.02, + "learning_rate": 3.785400327445045e-05, + "loss": 3.6385, + "step": 741888 + }, + { + "epoch": 1.02, + "learning_rate": 3.7845633705743656e-05, + "loss": 3.6276, + "step": 742400 + }, + { + "epoch": 1.02, + "learning_rate": 3.7837247758233136e-05, + "loss": 3.6298, + "step": 742912 + }, + { + "epoch": 1.02, + "learning_rate": 3.7828861810722616e-05, + "loss": 3.632, + "step": 743424 + }, + { + "epoch": 1.02, + "learning_rate": 3.7820475863212096e-05, + "loss": 3.6315, + "step": 743936 + }, + { + "epoch": 1.02, + "learning_rate": 3.7812089915701576e-05, + "loss": 3.6437, + "step": 744448 + }, + { + "epoch": 1.02, + "learning_rate": 3.7803703968191056e-05, + "loss": 3.6298, + "step": 744960 + }, + { + "epoch": 1.02, + "learning_rate": 3.7795318020680536e-05, + "loss": 3.6462, + "step": 745472 + }, + { + "epoch": 1.02, + "learning_rate": 3.7786932073170016e-05, + "loss": 3.6495, + "step": 745984 + }, + { + "epoch": 1.02, + "learning_rate": 3.7778562504463225e-05, + "loss": 3.6381, + "step": 746496 + }, + { + "epoch": 1.02, + "learning_rate": 3.777019293575644e-05, + "loss": 3.6349, + "step": 747008 + }, + { + "epoch": 1.02, + "learning_rate": 3.776180698824592e-05, + "loss": 3.6309, + "step": 747520 + }, + { + "epoch": 1.02, + "learning_rate": 3.77534210407354e-05, + "loss": 3.6328, + "step": 748032 + }, + { + "epoch": 1.02, + "learning_rate": 3.774503509322488e-05, + "loss": 3.6397, + "step": 748544 + }, + { + "epoch": 1.02, + "learning_rate": 3.773664914571436e-05, + "loss": 3.6334, + "step": 749056 + }, + { + "epoch": 1.02, + "learning_rate": 3.772826319820384e-05, + "loss": 3.6255, + "step": 749568 + }, + { + "epoch": 1.02, + "learning_rate": 3.7719877250693314e-05, + "loss": 3.6433, + "step": 750080 + }, + { + "epoch": 1.02, + "learning_rate": 3.771150768198653e-05, + "loss": 3.6448, + "step": 750592 + }, + { + "epoch": 1.02, + "learning_rate": 3.770313811327974e-05, + "loss": 3.6301, + "step": 751104 + }, + { + "epoch": 1.02, + "learning_rate": 3.769475216576922e-05, + "loss": 3.6286, + "step": 751616 + }, + { + "epoch": 1.02, + "learning_rate": 3.76863662182587e-05, + "loss": 3.6379, + "step": 752128 + }, + { + "epoch": 1.02, + "learning_rate": 3.767798027074818e-05, + "loss": 3.6243, + "step": 752640 + }, + { + "epoch": 1.02, + "learning_rate": 3.766959432323766e-05, + "loss": 3.6448, + "step": 753152 + }, + { + "epoch": 1.02, + "learning_rate": 3.766120837572714e-05, + "loss": 3.6307, + "step": 753664 + }, + { + "epoch": 1.02, + "learning_rate": 3.765282242821662e-05, + "loss": 3.6427, + "step": 754176 + }, + { + "epoch": 1.02, + "learning_rate": 3.76444364807061e-05, + "loss": 3.618, + "step": 754688 + }, + { + "epoch": 1.02, + "learning_rate": 3.7636066911999315e-05, + "loss": 3.6418, + "step": 755200 + }, + { + "epoch": 1.02, + "learning_rate": 3.762768096448879e-05, + "loss": 3.6338, + "step": 755712 + }, + { + "epoch": 1.02, + "learning_rate": 3.761929501697827e-05, + "loss": 3.6348, + "step": 756224 + }, + { + "epoch": 1.02, + "learning_rate": 3.761090906946775e-05, + "loss": 3.6362, + "step": 756736 + }, + { + "epoch": 1.02, + "learning_rate": 3.7602539500760963e-05, + "loss": 3.6279, + "step": 757248 + }, + { + "epoch": 1.02, + "learning_rate": 3.759415355325044e-05, + "loss": 3.6399, + "step": 757760 + }, + { + "epoch": 1.02, + "learning_rate": 3.758576760573992e-05, + "loss": 3.6572, + "step": 758272 + }, + { + "epoch": 1.02, + "learning_rate": 3.7577381658229397e-05, + "loss": 3.6193, + "step": 758784 + }, + { + "epoch": 1.02, + "learning_rate": 3.756901208952261e-05, + "loss": 3.6407, + "step": 759296 + }, + { + "epoch": 1.02, + "learning_rate": 3.756064252081583e-05, + "loss": 3.6306, + "step": 759808 + }, + { + "epoch": 1.02, + "learning_rate": 3.755225657330531e-05, + "loss": 3.6248, + "step": 760320 + }, + { + "epoch": 1.02, + "learning_rate": 3.754387062579479e-05, + "loss": 3.6318, + "step": 760832 + }, + { + "epoch": 1.02, + "learning_rate": 3.753548467828426e-05, + "loss": 3.6355, + "step": 761344 + }, + { + "epoch": 1.02, + "learning_rate": 3.752709873077374e-05, + "loss": 3.6382, + "step": 761856 + }, + { + "epoch": 1.02, + "learning_rate": 3.751872916206696e-05, + "loss": 3.6322, + "step": 762368 + }, + { + "epoch": 1.02, + "learning_rate": 3.751034321455644e-05, + "loss": 3.6355, + "step": 762880 + }, + { + "epoch": 1.03, + "eval_loss": 3.8439886569976807, + "eval_runtime": 307.4311, + "eval_samples_per_second": 1241.224, + "eval_steps_per_second": 38.789, + "step": 763200 + }, + { + "epoch": 0.0, + "learning_rate": 3.750195726704591e-05, + "loss": 3.619, + "step": 763392 + }, + { + "epoch": 0.0, + "learning_rate": 3.749357131953539e-05, + "loss": 3.622, + "step": 763904 + }, + { + "epoch": 0.0, + "learning_rate": 3.748518537202487e-05, + "loss": 3.631, + "step": 764416 + }, + { + "epoch": 0.0, + "learning_rate": 3.747679942451435e-05, + "loss": 3.6308, + "step": 764928 + }, + { + "epoch": 0.0, + "learning_rate": 3.746841347700383e-05, + "loss": 3.6401, + "step": 765440 + }, + { + "epoch": 0.0, + "learning_rate": 3.746002752949331e-05, + "loss": 3.624, + "step": 765952 + }, + { + "epoch": 0.0, + "learning_rate": 3.74516415819828e-05, + "loss": 3.634, + "step": 766464 + }, + { + "epoch": 0.0, + "learning_rate": 3.744325563447228e-05, + "loss": 3.6223, + "step": 766976 + }, + { + "epoch": 0.0, + "learning_rate": 3.7434886065765486e-05, + "loss": 3.6304, + "step": 767488 + }, + { + "epoch": 0.0, + "learning_rate": 3.7426500118254966e-05, + "loss": 3.6282, + "step": 768000 + }, + { + "epoch": 0.0, + "learning_rate": 3.7418114170744446e-05, + "loss": 3.6242, + "step": 768512 + }, + { + "epoch": 0.0, + "learning_rate": 3.7409728223233926e-05, + "loss": 3.6358, + "step": 769024 + }, + { + "epoch": 0.0, + "learning_rate": 3.7401375033330864e-05, + "loss": 3.6422, + "step": 769536 + }, + { + "epoch": 0.0, + "learning_rate": 3.7392989085820344e-05, + "loss": 3.6201, + "step": 770048 + }, + { + "epoch": 0.0, + "learning_rate": 3.7384603138309824e-05, + "loss": 3.628, + "step": 770560 + }, + { + "epoch": 0.0, + "learning_rate": 3.7376217190799304e-05, + "loss": 3.6152, + "step": 771072 + }, + { + "epoch": 0.0, + "learning_rate": 3.7367831243288784e-05, + "loss": 3.6175, + "step": 771584 + }, + { + "epoch": 0.0, + "learning_rate": 3.7359461674582e-05, + "loss": 3.625, + "step": 772096 + }, + { + "epoch": 0.0, + "learning_rate": 3.735107572707148e-05, + "loss": 3.6186, + "step": 772608 + }, + { + "epoch": 0.0, + "learning_rate": 3.734268977956096e-05, + "loss": 3.6293, + "step": 773120 + }, + { + "epoch": 0.0, + "learning_rate": 3.733430383205044e-05, + "loss": 3.6365, + "step": 773632 + }, + { + "epoch": 0.0, + "learning_rate": 3.732591788453992e-05, + "loss": 3.6314, + "step": 774144 + }, + { + "epoch": 0.0, + "learning_rate": 3.73175319370294e-05, + "loss": 3.6354, + "step": 774656 + }, + { + "epoch": 0.0, + "learning_rate": 3.730914598951888e-05, + "loss": 3.6289, + "step": 775168 + }, + { + "epoch": 0.0, + "learning_rate": 3.730076004200836e-05, + "loss": 3.6215, + "step": 775680 + }, + { + "epoch": 0.0, + "learning_rate": 3.729239047330157e-05, + "loss": 3.6286, + "step": 776192 + }, + { + "epoch": 0.0, + "learning_rate": 3.728402090459478e-05, + "loss": 3.6213, + "step": 776704 + }, + { + "epoch": 0.0, + "learning_rate": 3.727563495708426e-05, + "loss": 3.6303, + "step": 777216 + }, + { + "epoch": 0.0, + "learning_rate": 3.726724900957374e-05, + "loss": 3.6173, + "step": 777728 + }, + { + "epoch": 0.0, + "learning_rate": 3.725886306206322e-05, + "loss": 3.6234, + "step": 778240 + }, + { + "epoch": 0.01, + "learning_rate": 3.7250477114552704e-05, + "loss": 3.6224, + "step": 778752 + }, + { + "epoch": 0.01, + "learning_rate": 3.7242091167042184e-05, + "loss": 3.6291, + "step": 779264 + }, + { + "epoch": 0.01, + "learning_rate": 3.7233705219531664e-05, + "loss": 3.6295, + "step": 779776 + }, + { + "epoch": 0.01, + "learning_rate": 3.7225319272021144e-05, + "loss": 3.6246, + "step": 780288 + }, + { + "epoch": 0.01, + "learning_rate": 3.721694970331435e-05, + "loss": 3.6219, + "step": 780800 + }, + { + "epoch": 0.01, + "learning_rate": 3.720856375580383e-05, + "loss": 3.6264, + "step": 781312 + }, + { + "epoch": 0.01, + "learning_rate": 3.720017780829331e-05, + "loss": 3.6285, + "step": 781824 + }, + { + "epoch": 0.01, + "learning_rate": 3.719179186078279e-05, + "loss": 3.6153, + "step": 782336 + }, + { + "epoch": 0.01, + "learning_rate": 3.7183422292076e-05, + "loss": 3.6178, + "step": 782848 + }, + { + "epoch": 0.01, + "learning_rate": 3.717503634456548e-05, + "loss": 3.6149, + "step": 783360 + }, + { + "epoch": 0.01, + "learning_rate": 3.716665039705496e-05, + "loss": 3.6175, + "step": 783872 + }, + { + "epoch": 0.01, + "learning_rate": 3.715826444954444e-05, + "loss": 3.622, + "step": 784384 + }, + { + "epoch": 0.01, + "learning_rate": 3.714989488083766e-05, + "loss": 3.6296, + "step": 784896 + }, + { + "epoch": 0.01, + "learning_rate": 3.714150893332714e-05, + "loss": 3.6272, + "step": 785408 + }, + { + "epoch": 0.01, + "learning_rate": 3.713312298581662e-05, + "loss": 3.6275, + "step": 785920 + }, + { + "epoch": 0.01, + "learning_rate": 3.712475341710983e-05, + "loss": 3.6288, + "step": 786432 + }, + { + "epoch": 0.01, + "learning_rate": 3.711636746959931e-05, + "loss": 3.6269, + "step": 786944 + }, + { + "epoch": 0.01, + "learning_rate": 3.710798152208879e-05, + "loss": 3.6213, + "step": 787456 + }, + { + "epoch": 0.01, + "learning_rate": 3.709959557457827e-05, + "loss": 3.5956, + "step": 787968 + }, + { + "epoch": 0.01, + "learning_rate": 3.7091226005871476e-05, + "loss": 3.6362, + "step": 788480 + }, + { + "epoch": 0.01, + "learning_rate": 3.7082856437164685e-05, + "loss": 3.6149, + "step": 788992 + }, + { + "epoch": 0.01, + "learning_rate": 3.7074470489654165e-05, + "loss": 3.6217, + "step": 789504 + }, + { + "epoch": 0.01, + "learning_rate": 3.7066084542143645e-05, + "loss": 3.6221, + "step": 790016 + }, + { + "epoch": 0.01, + "learning_rate": 3.7057698594633125e-05, + "loss": 3.6116, + "step": 790528 + }, + { + "epoch": 0.01, + "learning_rate": 3.704931264712261e-05, + "loss": 3.6141, + "step": 791040 + }, + { + "epoch": 0.01, + "learning_rate": 3.704094307841582e-05, + "loss": 3.6094, + "step": 791552 + }, + { + "epoch": 0.01, + "learning_rate": 3.70325571309053e-05, + "loss": 3.6222, + "step": 792064 + }, + { + "epoch": 0.01, + "learning_rate": 3.702417118339478e-05, + "loss": 3.6087, + "step": 792576 + }, + { + "epoch": 0.01, + "learning_rate": 3.701578523588426e-05, + "loss": 3.6309, + "step": 793088 + }, + { + "epoch": 0.01, + "learning_rate": 3.700739928837374e-05, + "loss": 3.6149, + "step": 793600 + }, + { + "epoch": 0.01, + "learning_rate": 3.699902971966695e-05, + "loss": 3.6015, + "step": 794112 + }, + { + "epoch": 0.01, + "learning_rate": 3.699064377215643e-05, + "loss": 3.6346, + "step": 794624 + }, + { + "epoch": 0.01, + "learning_rate": 3.698225782464591e-05, + "loss": 3.6096, + "step": 795136 + }, + { + "epoch": 0.01, + "learning_rate": 3.697387187713539e-05, + "loss": 3.6067, + "step": 795648 + }, + { + "epoch": 0.01, + "learning_rate": 3.69655023084286e-05, + "loss": 3.6229, + "step": 796160 + }, + { + "epoch": 0.01, + "learning_rate": 3.695711636091808e-05, + "loss": 3.6271, + "step": 796672 + }, + { + "epoch": 0.01, + "learning_rate": 3.694873041340756e-05, + "loss": 3.6072, + "step": 797184 + }, + { + "epoch": 0.01, + "learning_rate": 3.6940344465897045e-05, + "loss": 3.6092, + "step": 797696 + }, + { + "epoch": 0.01, + "learning_rate": 3.693195851838652e-05, + "loss": 3.6036, + "step": 798208 + }, + { + "epoch": 0.01, + "learning_rate": 3.6923572570876e-05, + "loss": 3.6132, + "step": 798720 + }, + { + "epoch": 0.01, + "learning_rate": 3.691518662336548e-05, + "loss": 3.6258, + "step": 799232 + }, + { + "epoch": 0.01, + "learning_rate": 3.690680067585496e-05, + "loss": 3.6212, + "step": 799744 + }, + { + "epoch": 0.01, + "learning_rate": 3.689843110714817e-05, + "loss": 3.6221, + "step": 800256 + }, + { + "epoch": 0.01, + "learning_rate": 3.689006153844138e-05, + "loss": 3.6188, + "step": 800768 + }, + { + "epoch": 0.01, + "learning_rate": 3.688167559093086e-05, + "loss": 3.6266, + "step": 801280 + }, + { + "epoch": 0.01, + "learning_rate": 3.6873289643420336e-05, + "loss": 3.6181, + "step": 801792 + }, + { + "epoch": 0.01, + "learning_rate": 3.6864903695909816e-05, + "loss": 3.6255, + "step": 802304 + }, + { + "epoch": 0.01, + "learning_rate": 3.6856517748399296e-05, + "loss": 3.6073, + "step": 802816 + }, + { + "epoch": 0.01, + "learning_rate": 3.684813180088878e-05, + "loss": 3.6143, + "step": 803328 + }, + { + "epoch": 0.01, + "learning_rate": 3.683976223218199e-05, + "loss": 3.6169, + "step": 803840 + }, + { + "epoch": 0.01, + "learning_rate": 3.683137628467147e-05, + "loss": 3.6182, + "step": 804352 + }, + { + "epoch": 0.01, + "learning_rate": 3.682299033716095e-05, + "loss": 3.6218, + "step": 804864 + }, + { + "epoch": 0.01, + "learning_rate": 3.681460438965043e-05, + "loss": 3.6252, + "step": 805376 + }, + { + "epoch": 0.01, + "learning_rate": 3.680621844213991e-05, + "loss": 3.6111, + "step": 805888 + }, + { + "epoch": 0.01, + "learning_rate": 3.679784887343312e-05, + "loss": 3.6063, + "step": 806400 + }, + { + "epoch": 0.01, + "learning_rate": 3.67894629259226e-05, + "loss": 3.6184, + "step": 806912 + }, + { + "epoch": 0.01, + "learning_rate": 3.678107697841208e-05, + "loss": 3.6216, + "step": 807424 + }, + { + "epoch": 0.01, + "learning_rate": 3.677269103090156e-05, + "loss": 3.6075, + "step": 807936 + }, + { + "epoch": 0.01, + "learning_rate": 3.676432146219477e-05, + "loss": 3.6133, + "step": 808448 + }, + { + "epoch": 0.01, + "learning_rate": 3.675593551468425e-05, + "loss": 3.6233, + "step": 808960 + }, + { + "epoch": 0.02, + "learning_rate": 3.674754956717374e-05, + "loss": 3.616, + "step": 809472 + }, + { + "epoch": 0.02, + "learning_rate": 3.6739163619663217e-05, + "loss": 3.6137, + "step": 809984 + }, + { + "epoch": 0.02, + "learning_rate": 3.6730777672152697e-05, + "loss": 3.6097, + "step": 810496 + }, + { + "epoch": 0.02, + "learning_rate": 3.6722408103445906e-05, + "loss": 3.6214, + "step": 811008 + }, + { + "epoch": 0.02, + "learning_rate": 3.6714022155935386e-05, + "loss": 3.6269, + "step": 811520 + }, + { + "epoch": 0.02, + "learning_rate": 3.6705636208424866e-05, + "loss": 3.6183, + "step": 812032 + }, + { + "epoch": 0.02, + "learning_rate": 3.6697250260914346e-05, + "loss": 3.6089, + "step": 812544 + }, + { + "epoch": 0.02, + "learning_rate": 3.6688880692207555e-05, + "loss": 3.6132, + "step": 813056 + }, + { + "epoch": 0.02, + "learning_rate": 3.6680494744697035e-05, + "loss": 3.6074, + "step": 813568 + }, + { + "epoch": 0.02, + "learning_rate": 3.6672108797186515e-05, + "loss": 3.621, + "step": 814080 + }, + { + "epoch": 0.02, + "learning_rate": 3.6663722849675994e-05, + "loss": 3.6213, + "step": 814592 + }, + { + "epoch": 0.02, + "learning_rate": 3.6655353280969204e-05, + "loss": 3.6115, + "step": 815104 + }, + { + "epoch": 0.02, + "learning_rate": 3.664696733345869e-05, + "loss": 3.6095, + "step": 815616 + }, + { + "epoch": 0.02, + "learning_rate": 3.663858138594817e-05, + "loss": 3.609, + "step": 816128 + }, + { + "epoch": 0.02, + "learning_rate": 3.663019543843765e-05, + "loss": 3.6059, + "step": 816640 + }, + { + "epoch": 0.02, + "learning_rate": 3.662180949092713e-05, + "loss": 3.6096, + "step": 817152 + }, + { + "epoch": 0.02, + "learning_rate": 3.661342354341661e-05, + "loss": 3.6076, + "step": 817664 + }, + { + "epoch": 0.02, + "learning_rate": 3.660505397470982e-05, + "loss": 3.611, + "step": 818176 + }, + { + "epoch": 0.02, + "learning_rate": 3.65966680271993e-05, + "loss": 3.6094, + "step": 818688 + }, + { + "epoch": 0.02, + "learning_rate": 3.658828207968878e-05, + "loss": 3.6073, + "step": 819200 + }, + { + "epoch": 0.02, + "learning_rate": 3.657989613217826e-05, + "loss": 3.6118, + "step": 819712 + }, + { + "epoch": 0.02, + "learning_rate": 3.657151018466774e-05, + "loss": 3.6082, + "step": 820224 + }, + { + "epoch": 0.02, + "learning_rate": 3.656314061596095e-05, + "loss": 3.6235, + "step": 820736 + }, + { + "epoch": 0.02, + "learning_rate": 3.655475466845043e-05, + "loss": 3.6057, + "step": 821248 + }, + { + "epoch": 0.02, + "learning_rate": 3.654636872093991e-05, + "loss": 3.6267, + "step": 821760 + }, + { + "epoch": 0.02, + "learning_rate": 3.653798277342939e-05, + "loss": 3.6285, + "step": 822272 + }, + { + "epoch": 0.02, + "learning_rate": 3.6529596825918875e-05, + "loss": 3.6192, + "step": 822784 + }, + { + "epoch": 0.02, + "learning_rate": 3.6521227257212084e-05, + "loss": 3.6123, + "step": 823296 + }, + { + "epoch": 0.02, + "learning_rate": 3.6512841309701564e-05, + "loss": 3.6104, + "step": 823808 + }, + { + "epoch": 0.02, + "learning_rate": 3.6504455362191044e-05, + "loss": 3.6118, + "step": 824320 + }, + { + "epoch": 0.02, + "learning_rate": 3.6496069414680524e-05, + "loss": 3.6206, + "step": 824832 + }, + { + "epoch": 0.02, + "learning_rate": 3.648768346717e-05, + "loss": 3.6125, + "step": 825344 + }, + { + "epoch": 0.02, + "learning_rate": 3.647931389846321e-05, + "loss": 3.6056, + "step": 825856 + }, + { + "epoch": 0.02, + "learning_rate": 3.647092795095269e-05, + "loss": 3.6176, + "step": 826368 + }, + { + "epoch": 0.02, + "learning_rate": 3.646254200344217e-05, + "loss": 3.6253, + "step": 826880 + }, + { + "epoch": 0.02, + "learning_rate": 3.6454156055931646e-05, + "loss": 3.6082, + "step": 827392 + }, + { + "epoch": 0.02, + "learning_rate": 3.6445770108421126e-05, + "loss": 3.6078, + "step": 827904 + }, + { + "epoch": 0.02, + "learning_rate": 3.643740053971434e-05, + "loss": 3.6158, + "step": 828416 + }, + { + "epoch": 0.02, + "learning_rate": 3.642901459220382e-05, + "loss": 3.6036, + "step": 828928 + }, + { + "epoch": 0.02, + "learning_rate": 3.64206286446933e-05, + "loss": 3.6253, + "step": 829440 + }, + { + "epoch": 0.02, + "learning_rate": 3.641224269718278e-05, + "loss": 3.6081, + "step": 829952 + }, + { + "epoch": 0.02, + "learning_rate": 3.6403873128476e-05, + "loss": 3.6221, + "step": 830464 + }, + { + "epoch": 0.02, + "learning_rate": 3.639548718096547e-05, + "loss": 3.5968, + "step": 830976 + }, + { + "epoch": 0.02, + "learning_rate": 3.638710123345495e-05, + "loss": 3.6185, + "step": 831488 + }, + { + "epoch": 0.02, + "learning_rate": 3.637871528594443e-05, + "loss": 3.612, + "step": 832000 + }, + { + "epoch": 0.02, + "learning_rate": 3.6370345717237646e-05, + "loss": 3.6141, + "step": 832512 + }, + { + "epoch": 0.02, + "learning_rate": 3.636195976972712e-05, + "loss": 3.6147, + "step": 833024 + }, + { + "epoch": 0.02, + "learning_rate": 3.63535738222166e-05, + "loss": 3.6058, + "step": 833536 + }, + { + "epoch": 0.02, + "learning_rate": 3.634518787470608e-05, + "loss": 3.6213, + "step": 834048 + }, + { + "epoch": 0.02, + "learning_rate": 3.6336801927195566e-05, + "loss": 3.633, + "step": 834560 + }, + { + "epoch": 0.02, + "learning_rate": 3.6328415979685046e-05, + "loss": 3.6017, + "step": 835072 + }, + { + "epoch": 0.02, + "learning_rate": 3.6320046410978255e-05, + "loss": 3.6154, + "step": 835584 + }, + { + "epoch": 0.02, + "learning_rate": 3.6311660463467735e-05, + "loss": 3.6129, + "step": 836096 + }, + { + "epoch": 0.02, + "learning_rate": 3.6303274515957215e-05, + "loss": 3.606, + "step": 836608 + }, + { + "epoch": 0.02, + "learning_rate": 3.6294888568446695e-05, + "loss": 3.6103, + "step": 837120 + }, + { + "epoch": 0.02, + "learning_rate": 3.6286502620936175e-05, + "loss": 3.6142, + "step": 837632 + }, + { + "epoch": 0.02, + "learning_rate": 3.6278116673425655e-05, + "loss": 3.6155, + "step": 838144 + }, + { + "epoch": 0.02, + "learning_rate": 3.6269747104718864e-05, + "loss": 3.6135, + "step": 838656 + }, + { + "epoch": 0.02, + "learning_rate": 3.6261361157208344e-05, + "loss": 3.6132, + "step": 839168 + }, + { + "epoch": 0.03, + "eval_loss": 3.8428730964660645, + "eval_runtime": 304.678, + "eval_samples_per_second": 1252.44, + "eval_steps_per_second": 39.14, + "step": 839520 + }, + { + "epoch": 1.0, + "learning_rate": 3.6252975209697824e-05, + "loss": 3.6059, + "step": 839680 + }, + { + "epoch": 1.0, + "learning_rate": 3.6244589262187304e-05, + "loss": 3.6002, + "step": 840192 + }, + { + "epoch": 1.0, + "learning_rate": 3.623621969348051e-05, + "loss": 3.6146, + "step": 840704 + }, + { + "epoch": 1.0, + "learning_rate": 3.622783374597e-05, + "loss": 3.6071, + "step": 841216 + }, + { + "epoch": 1.0, + "learning_rate": 3.621944779845948e-05, + "loss": 3.6182, + "step": 841728 + }, + { + "epoch": 1.0, + "learning_rate": 3.621106185094896e-05, + "loss": 3.6032, + "step": 842240 + }, + { + "epoch": 1.0, + "learning_rate": 3.620269228224217e-05, + "loss": 3.611, + "step": 842752 + }, + { + "epoch": 1.0, + "learning_rate": 3.619430633473165e-05, + "loss": 3.6075, + "step": 843264 + }, + { + "epoch": 1.0, + "learning_rate": 3.618592038722113e-05, + "loss": 3.6102, + "step": 843776 + }, + { + "epoch": 1.0, + "learning_rate": 3.617753443971061e-05, + "loss": 3.6018, + "step": 844288 + }, + { + "epoch": 1.0, + "learning_rate": 3.616914849220009e-05, + "loss": 3.6056, + "step": 844800 + }, + { + "epoch": 1.0, + "learning_rate": 3.61607789234933e-05, + "loss": 3.6197, + "step": 845312 + }, + { + "epoch": 1.0, + "learning_rate": 3.615240935478651e-05, + "loss": 3.6159, + "step": 845824 + }, + { + "epoch": 1.0, + "learning_rate": 3.614402340727599e-05, + "loss": 3.5998, + "step": 846336 + }, + { + "epoch": 1.0, + "learning_rate": 3.613563745976547e-05, + "loss": 3.6068, + "step": 846848 + }, + { + "epoch": 1.0, + "learning_rate": 3.6127251512254953e-05, + "loss": 3.5951, + "step": 847360 + }, + { + "epoch": 1.0, + "learning_rate": 3.6118865564744433e-05, + "loss": 3.5983, + "step": 847872 + }, + { + "epoch": 1.0, + "learning_rate": 3.6110479617233913e-05, + "loss": 3.6081, + "step": 848384 + }, + { + "epoch": 1.0, + "learning_rate": 3.610209366972339e-05, + "loss": 3.5972, + "step": 848896 + }, + { + "epoch": 1.0, + "learning_rate": 3.609370772221287e-05, + "loss": 3.6074, + "step": 849408 + }, + { + "epoch": 1.0, + "learning_rate": 3.608532177470235e-05, + "loss": 3.6128, + "step": 849920 + }, + { + "epoch": 1.0, + "learning_rate": 3.607693582719183e-05, + "loss": 3.6088, + "step": 850432 + }, + { + "epoch": 1.0, + "learning_rate": 3.606856625848504e-05, + "loss": 3.6183, + "step": 850944 + }, + { + "epoch": 1.0, + "learning_rate": 3.606018031097452e-05, + "loss": 3.6087, + "step": 851456 + }, + { + "epoch": 1.0, + "learning_rate": 3.6051794363464e-05, + "loss": 3.6016, + "step": 851968 + }, + { + "epoch": 1.0, + "learning_rate": 3.6043408415953475e-05, + "loss": 3.6057, + "step": 852480 + }, + { + "epoch": 1.0, + "learning_rate": 3.6035022468442955e-05, + "loss": 3.5997, + "step": 852992 + }, + { + "epoch": 1.0, + "learning_rate": 3.602665289973617e-05, + "loss": 3.6098, + "step": 853504 + }, + { + "epoch": 1.0, + "learning_rate": 3.601826695222565e-05, + "loss": 3.5979, + "step": 854016 + }, + { + "epoch": 1.0, + "learning_rate": 3.600988100471513e-05, + "loss": 3.6052, + "step": 854528 + }, + { + "epoch": 1.01, + "learning_rate": 3.600149505720461e-05, + "loss": 3.604, + "step": 855040 + }, + { + "epoch": 1.01, + "learning_rate": 3.599312548849783e-05, + "loss": 3.6038, + "step": 855552 + }, + { + "epoch": 1.01, + "learning_rate": 3.598473954098731e-05, + "loss": 3.6075, + "step": 856064 + }, + { + "epoch": 1.01, + "learning_rate": 3.597635359347678e-05, + "loss": 3.606, + "step": 856576 + }, + { + "epoch": 1.01, + "learning_rate": 3.596796764596626e-05, + "loss": 3.6012, + "step": 857088 + }, + { + "epoch": 1.01, + "learning_rate": 3.5959598077259476e-05, + "loss": 3.6065, + "step": 857600 + }, + { + "epoch": 1.01, + "learning_rate": 3.595121212974895e-05, + "loss": 3.6115, + "step": 858112 + }, + { + "epoch": 1.01, + "learning_rate": 3.594282618223843e-05, + "loss": 3.5928, + "step": 858624 + }, + { + "epoch": 1.01, + "learning_rate": 3.593444023472791e-05, + "loss": 3.5963, + "step": 859136 + }, + { + "epoch": 1.01, + "learning_rate": 3.592605428721739e-05, + "loss": 3.596, + "step": 859648 + }, + { + "epoch": 1.01, + "learning_rate": 3.5917684718510605e-05, + "loss": 3.5941, + "step": 860160 + }, + { + "epoch": 1.01, + "learning_rate": 3.5909298771000085e-05, + "loss": 3.6038, + "step": 860672 + }, + { + "epoch": 1.01, + "learning_rate": 3.5900912823489565e-05, + "loss": 3.6057, + "step": 861184 + }, + { + "epoch": 1.01, + "learning_rate": 3.5892526875979045e-05, + "loss": 3.6102, + "step": 861696 + }, + { + "epoch": 1.01, + "learning_rate": 3.5884157307272254e-05, + "loss": 3.6061, + "step": 862208 + }, + { + "epoch": 1.01, + "learning_rate": 3.5875771359761734e-05, + "loss": 3.6077, + "step": 862720 + }, + { + "epoch": 1.01, + "learning_rate": 3.5867385412251214e-05, + "loss": 3.605, + "step": 863232 + }, + { + "epoch": 1.01, + "learning_rate": 3.5858999464740694e-05, + "loss": 3.6032, + "step": 863744 + }, + { + "epoch": 1.01, + "learning_rate": 3.58506298960339e-05, + "loss": 3.5784, + "step": 864256 + }, + { + "epoch": 1.01, + "learning_rate": 3.584224394852338e-05, + "loss": 3.6139, + "step": 864768 + }, + { + "epoch": 1.01, + "learning_rate": 3.583385800101286e-05, + "loss": 3.5958, + "step": 865280 + }, + { + "epoch": 1.01, + "learning_rate": 3.582547205350234e-05, + "loss": 3.6031, + "step": 865792 + }, + { + "epoch": 1.01, + "learning_rate": 3.581708610599183e-05, + "loss": 3.5964, + "step": 866304 + }, + { + "epoch": 1.01, + "learning_rate": 3.580871653728504e-05, + "loss": 3.5922, + "step": 866816 + }, + { + "epoch": 1.01, + "learning_rate": 3.580033058977452e-05, + "loss": 3.5945, + "step": 867328 + }, + { + "epoch": 1.01, + "learning_rate": 3.5791944642264e-05, + "loss": 3.5912, + "step": 867840 + }, + { + "epoch": 1.01, + "learning_rate": 3.578355869475348e-05, + "loss": 3.6053, + "step": 868352 + }, + { + "epoch": 1.01, + "learning_rate": 3.577518912604669e-05, + "loss": 3.5876, + "step": 868864 + }, + { + "epoch": 1.01, + "learning_rate": 3.576680317853617e-05, + "loss": 3.6134, + "step": 869376 + }, + { + "epoch": 1.01, + "learning_rate": 3.575841723102565e-05, + "loss": 3.599, + "step": 869888 + }, + { + "epoch": 1.01, + "learning_rate": 3.575003128351513e-05, + "loss": 3.5764, + "step": 870400 + }, + { + "epoch": 1.01, + "learning_rate": 3.5741661714808336e-05, + "loss": 3.6136, + "step": 870912 + }, + { + "epoch": 1.01, + "learning_rate": 3.5733275767297816e-05, + "loss": 3.5885, + "step": 871424 + }, + { + "epoch": 1.01, + "learning_rate": 3.5724889819787296e-05, + "loss": 3.59, + "step": 871936 + }, + { + "epoch": 1.01, + "learning_rate": 3.571650387227678e-05, + "loss": 3.6001, + "step": 872448 + }, + { + "epoch": 1.01, + "learning_rate": 3.570813430356999e-05, + "loss": 3.6079, + "step": 872960 + }, + { + "epoch": 1.01, + "learning_rate": 3.569974835605947e-05, + "loss": 3.5865, + "step": 873472 + }, + { + "epoch": 1.01, + "learning_rate": 3.569136240854895e-05, + "loss": 3.5955, + "step": 873984 + }, + { + "epoch": 1.01, + "learning_rate": 3.568297646103843e-05, + "loss": 3.5816, + "step": 874496 + }, + { + "epoch": 1.01, + "learning_rate": 3.567460689233164e-05, + "loss": 3.5934, + "step": 875008 + }, + { + "epoch": 1.01, + "learning_rate": 3.566622094482112e-05, + "loss": 3.6087, + "step": 875520 + }, + { + "epoch": 1.01, + "learning_rate": 3.56578349973106e-05, + "loss": 3.5985, + "step": 876032 + }, + { + "epoch": 1.01, + "learning_rate": 3.564944904980008e-05, + "loss": 3.6021, + "step": 876544 + }, + { + "epoch": 1.01, + "learning_rate": 3.564107948109329e-05, + "loss": 3.5992, + "step": 877056 + }, + { + "epoch": 1.01, + "learning_rate": 3.563269353358277e-05, + "loss": 3.6082, + "step": 877568 + }, + { + "epoch": 1.01, + "learning_rate": 3.562430758607225e-05, + "loss": 3.5988, + "step": 878080 + }, + { + "epoch": 1.01, + "learning_rate": 3.561592163856174e-05, + "loss": 3.6039, + "step": 878592 + }, + { + "epoch": 1.01, + "learning_rate": 3.5607552069854946e-05, + "loss": 3.59, + "step": 879104 + }, + { + "epoch": 1.01, + "learning_rate": 3.5599166122344426e-05, + "loss": 3.594, + "step": 879616 + }, + { + "epoch": 1.01, + "learning_rate": 3.5590780174833906e-05, + "loss": 3.597, + "step": 880128 + }, + { + "epoch": 1.01, + "learning_rate": 3.5582394227323386e-05, + "loss": 3.5974, + "step": 880640 + }, + { + "epoch": 1.01, + "learning_rate": 3.5574024658616595e-05, + "loss": 3.5993, + "step": 881152 + }, + { + "epoch": 1.01, + "learning_rate": 3.5565638711106075e-05, + "loss": 3.6064, + "step": 881664 + }, + { + "epoch": 1.01, + "learning_rate": 3.5557252763595555e-05, + "loss": 3.5979, + "step": 882176 + }, + { + "epoch": 1.01, + "learning_rate": 3.5548866816085035e-05, + "loss": 3.5845, + "step": 882688 + }, + { + "epoch": 1.01, + "learning_rate": 3.5540497247378244e-05, + "loss": 3.5987, + "step": 883200 + }, + { + "epoch": 1.01, + "learning_rate": 3.5532111299867724e-05, + "loss": 3.6012, + "step": 883712 + }, + { + "epoch": 1.01, + "learning_rate": 3.5523725352357204e-05, + "loss": 3.5877, + "step": 884224 + }, + { + "epoch": 1.01, + "learning_rate": 3.5515339404846684e-05, + "loss": 3.5942, + "step": 884736 + }, + { + "epoch": 1.01, + "learning_rate": 3.55069698361399e-05, + "loss": 3.6027, + "step": 885248 + }, + { + "epoch": 1.02, + "learning_rate": 3.549858388862938e-05, + "loss": 3.5942, + "step": 885760 + }, + { + "epoch": 1.02, + "learning_rate": 3.549019794111886e-05, + "loss": 3.5978, + "step": 886272 + }, + { + "epoch": 1.02, + "learning_rate": 3.548181199360834e-05, + "loss": 3.5904, + "step": 886784 + }, + { + "epoch": 1.02, + "learning_rate": 3.547342604609782e-05, + "loss": 3.6019, + "step": 887296 + }, + { + "epoch": 1.02, + "learning_rate": 3.546505647739103e-05, + "loss": 3.6021, + "step": 887808 + }, + { + "epoch": 1.02, + "learning_rate": 3.545667052988051e-05, + "loss": 3.6042, + "step": 888320 + }, + { + "epoch": 1.02, + "learning_rate": 3.544828458236999e-05, + "loss": 3.5824, + "step": 888832 + }, + { + "epoch": 1.02, + "learning_rate": 3.54399150136632e-05, + "loss": 3.599, + "step": 889344 + }, + { + "epoch": 1.02, + "learning_rate": 3.543152906615268e-05, + "loss": 3.5865, + "step": 889856 + }, + { + "epoch": 1.02, + "learning_rate": 3.542314311864216e-05, + "loss": 3.6014, + "step": 890368 + }, + { + "epoch": 1.02, + "learning_rate": 3.541475717113164e-05, + "loss": 3.6049, + "step": 890880 + }, + { + "epoch": 1.02, + "learning_rate": 3.540638760242485e-05, + "loss": 3.5895, + "step": 891392 + }, + { + "epoch": 1.02, + "learning_rate": 3.539800165491433e-05, + "loss": 3.592, + "step": 891904 + }, + { + "epoch": 1.02, + "learning_rate": 3.538961570740381e-05, + "loss": 3.5888, + "step": 892416 + }, + { + "epoch": 1.02, + "learning_rate": 3.538122975989329e-05, + "loss": 3.5877, + "step": 892928 + }, + { + "epoch": 1.02, + "learning_rate": 3.53728601911865e-05, + "loss": 3.5903, + "step": 893440 + }, + { + "epoch": 1.02, + "learning_rate": 3.536447424367598e-05, + "loss": 3.5901, + "step": 893952 + }, + { + "epoch": 1.02, + "learning_rate": 3.535608829616546e-05, + "loss": 3.5941, + "step": 894464 + }, + { + "epoch": 1.02, + "learning_rate": 3.534770234865494e-05, + "loss": 3.5917, + "step": 894976 + }, + { + "epoch": 1.02, + "learning_rate": 3.533933277994815e-05, + "loss": 3.5856, + "step": 895488 + }, + { + "epoch": 1.02, + "learning_rate": 3.533094683243763e-05, + "loss": 3.5877, + "step": 896000 + }, + { + "epoch": 1.02, + "learning_rate": 3.532256088492711e-05, + "loss": 3.5891, + "step": 896512 + }, + { + "epoch": 1.02, + "learning_rate": 3.531417493741659e-05, + "loss": 3.6059, + "step": 897024 + }, + { + "epoch": 1.02, + "learning_rate": 3.530578898990608e-05, + "loss": 3.5886, + "step": 897536 + }, + { + "epoch": 1.02, + "learning_rate": 3.529740304239556e-05, + "loss": 3.604, + "step": 898048 + }, + { + "epoch": 1.02, + "learning_rate": 3.528901709488503e-05, + "loss": 3.6035, + "step": 898560 + }, + { + "epoch": 1.02, + "learning_rate": 3.528063114737451e-05, + "loss": 3.6087, + "step": 899072 + }, + { + "epoch": 1.02, + "learning_rate": 3.527226157866773e-05, + "loss": 3.5907, + "step": 899584 + }, + { + "epoch": 1.02, + "learning_rate": 3.5263875631157207e-05, + "loss": 3.5907, + "step": 900096 + }, + { + "epoch": 1.02, + "learning_rate": 3.525548968364668e-05, + "loss": 3.5941, + "step": 900608 + }, + { + "epoch": 1.02, + "learning_rate": 3.524710373613616e-05, + "loss": 3.5977, + "step": 901120 + }, + { + "epoch": 1.02, + "learning_rate": 3.5238734167429376e-05, + "loss": 3.5958, + "step": 901632 + }, + { + "epoch": 1.02, + "learning_rate": 3.5230348219918856e-05, + "loss": 3.5889, + "step": 902144 + }, + { + "epoch": 1.02, + "learning_rate": 3.522196227240833e-05, + "loss": 3.5939, + "step": 902656 + }, + { + "epoch": 1.02, + "learning_rate": 3.5213576324897815e-05, + "loss": 3.6049, + "step": 903168 + }, + { + "epoch": 1.02, + "learning_rate": 3.520520675619103e-05, + "loss": 3.5962, + "step": 903680 + }, + { + "epoch": 1.02, + "learning_rate": 3.5196820808680505e-05, + "loss": 3.5852, + "step": 904192 + }, + { + "epoch": 1.02, + "learning_rate": 3.5188434861169984e-05, + "loss": 3.5957, + "step": 904704 + }, + { + "epoch": 1.02, + "learning_rate": 3.5180048913659464e-05, + "loss": 3.5849, + "step": 905216 + }, + { + "epoch": 1.02, + "learning_rate": 3.517167934495268e-05, + "loss": 3.604, + "step": 905728 + }, + { + "epoch": 1.02, + "learning_rate": 3.5163293397442153e-05, + "loss": 3.5912, + "step": 906240 + }, + { + "epoch": 1.02, + "learning_rate": 3.5154907449931633e-05, + "loss": 3.604, + "step": 906752 + }, + { + "epoch": 1.02, + "learning_rate": 3.5146521502421113e-05, + "loss": 3.5802, + "step": 907264 + }, + { + "epoch": 1.02, + "learning_rate": 3.513815193371433e-05, + "loss": 3.6002, + "step": 907776 + }, + { + "epoch": 1.02, + "learning_rate": 3.51297659862038e-05, + "loss": 3.5948, + "step": 908288 + }, + { + "epoch": 1.02, + "learning_rate": 3.512138003869328e-05, + "loss": 3.5951, + "step": 908800 + }, + { + "epoch": 1.02, + "learning_rate": 3.511299409118277e-05, + "loss": 3.5968, + "step": 909312 + }, + { + "epoch": 1.02, + "learning_rate": 3.510462452247598e-05, + "loss": 3.5866, + "step": 909824 + }, + { + "epoch": 1.02, + "learning_rate": 3.509623857496546e-05, + "loss": 3.6029, + "step": 910336 + }, + { + "epoch": 1.02, + "learning_rate": 3.508785262745494e-05, + "loss": 3.6137, + "step": 910848 + }, + { + "epoch": 1.02, + "learning_rate": 3.507946667994442e-05, + "loss": 3.5832, + "step": 911360 + }, + { + "epoch": 1.02, + "learning_rate": 3.507109711123763e-05, + "loss": 3.5953, + "step": 911872 + }, + { + "epoch": 1.02, + "learning_rate": 3.506271116372711e-05, + "loss": 3.5954, + "step": 912384 + }, + { + "epoch": 1.02, + "learning_rate": 3.505432521621659e-05, + "loss": 3.5893, + "step": 912896 + }, + { + "epoch": 1.02, + "learning_rate": 3.504593926870607e-05, + "loss": 3.5879, + "step": 913408 + }, + { + "epoch": 1.02, + "learning_rate": 3.5037569699999276e-05, + "loss": 3.6016, + "step": 913920 + }, + { + "epoch": 1.02, + "learning_rate": 3.5029183752488756e-05, + "loss": 3.5922, + "step": 914432 + }, + { + "epoch": 1.02, + "learning_rate": 3.5020797804978236e-05, + "loss": 3.5948, + "step": 914944 + }, + { + "epoch": 1.02, + "learning_rate": 3.501241185746772e-05, + "loss": 3.5978, + "step": 915456 + }, + { + "epoch": 1.03, + "eval_loss": 3.842829465866089, + "eval_runtime": 306.6744, + "eval_samples_per_second": 1244.287, + "eval_steps_per_second": 38.885, + "step": 915840 + }, + { + "epoch": 0.0, + "learning_rate": 3.500404228876093e-05, + "loss": 3.5837, + "step": 915968 + }, + { + "epoch": 0.0, + "learning_rate": 3.499565634125041e-05, + "loss": 3.5762, + "step": 916480 + }, + { + "epoch": 0.0, + "learning_rate": 3.498727039373989e-05, + "loss": 3.5957, + "step": 916992 + }, + { + "epoch": 0.0, + "learning_rate": 3.497888444622937e-05, + "loss": 3.5903, + "step": 917504 + }, + { + "epoch": 0.0, + "learning_rate": 3.497051487752258e-05, + "loss": 3.5961, + "step": 918016 + }, + { + "epoch": 0.0, + "learning_rate": 3.496212893001206e-05, + "loss": 3.5841, + "step": 918528 + }, + { + "epoch": 0.0, + "learning_rate": 3.495374298250154e-05, + "loss": 3.5957, + "step": 919040 + }, + { + "epoch": 0.0, + "learning_rate": 3.494535703499102e-05, + "loss": 3.5868, + "step": 919552 + }, + { + "epoch": 0.0, + "learning_rate": 3.49369710874805e-05, + "loss": 3.5893, + "step": 920064 + }, + { + "epoch": 0.0, + "learning_rate": 3.492860151877371e-05, + "loss": 3.5825, + "step": 920576 + }, + { + "epoch": 0.0, + "learning_rate": 3.492021557126319e-05, + "loss": 3.5898, + "step": 921088 + }, + { + "epoch": 0.0, + "learning_rate": 3.4911829623752676e-05, + "loss": 3.5966, + "step": 921600 + }, + { + "epoch": 0.0, + "learning_rate": 3.4903460055045886e-05, + "loss": 3.6008, + "step": 922112 + }, + { + "epoch": 0.0, + "learning_rate": 3.4895074107535366e-05, + "loss": 3.5792, + "step": 922624 + }, + { + "epoch": 0.0, + "learning_rate": 3.4886688160024845e-05, + "loss": 3.5896, + "step": 923136 + }, + { + "epoch": 0.0, + "learning_rate": 3.4878302212514325e-05, + "loss": 3.574, + "step": 923648 + }, + { + "epoch": 0.0, + "learning_rate": 3.4869916265003805e-05, + "loss": 3.5835, + "step": 924160 + }, + { + "epoch": 0.0, + "learning_rate": 3.4861530317493285e-05, + "loss": 3.5856, + "step": 924672 + }, + { + "epoch": 0.0, + "learning_rate": 3.4853144369982765e-05, + "loss": 3.5796, + "step": 925184 + }, + { + "epoch": 0.0, + "learning_rate": 3.4844758422472245e-05, + "loss": 3.5875, + "step": 925696 + }, + { + "epoch": 0.0, + "learning_rate": 3.4836388853765454e-05, + "loss": 3.5943, + "step": 926208 + }, + { + "epoch": 0.0, + "learning_rate": 3.4828002906254934e-05, + "loss": 3.5874, + "step": 926720 + }, + { + "epoch": 0.0, + "learning_rate": 3.4819616958744414e-05, + "loss": 3.6002, + "step": 927232 + }, + { + "epoch": 0.0, + "learning_rate": 3.4811231011233894e-05, + "loss": 3.5927, + "step": 927744 + }, + { + "epoch": 0.0, + "learning_rate": 3.480286144252711e-05, + "loss": 3.5814, + "step": 928256 + }, + { + "epoch": 0.0, + "learning_rate": 3.479447549501659e-05, + "loss": 3.5906, + "step": 928768 + }, + { + "epoch": 0.0, + "learning_rate": 3.478608954750607e-05, + "loss": 3.581, + "step": 929280 + }, + { + "epoch": 0.0, + "learning_rate": 3.477770359999555e-05, + "loss": 3.5864, + "step": 929792 + }, + { + "epoch": 0.0, + "learning_rate": 3.476933403128876e-05, + "loss": 3.5792, + "step": 930304 + }, + { + "epoch": 0.0, + "learning_rate": 3.476094808377824e-05, + "loss": 3.5838, + "step": 930816 + }, + { + "epoch": 0.01, + "learning_rate": 3.475256213626772e-05, + "loss": 3.5877, + "step": 931328 + }, + { + "epoch": 0.01, + "learning_rate": 3.47441761887572e-05, + "loss": 3.5861, + "step": 931840 + }, + { + "epoch": 0.01, + "learning_rate": 3.473580662005041e-05, + "loss": 3.5834, + "step": 932352 + }, + { + "epoch": 0.01, + "learning_rate": 3.472742067253989e-05, + "loss": 3.5917, + "step": 932864 + }, + { + "epoch": 0.01, + "learning_rate": 3.471903472502937e-05, + "loss": 3.5821, + "step": 933376 + }, + { + "epoch": 0.01, + "learning_rate": 3.471064877751885e-05, + "loss": 3.5862, + "step": 933888 + }, + { + "epoch": 0.01, + "learning_rate": 3.4702279208812064e-05, + "loss": 3.593, + "step": 934400 + }, + { + "epoch": 0.01, + "learning_rate": 3.4693893261301544e-05, + "loss": 3.5724, + "step": 934912 + }, + { + "epoch": 0.01, + "learning_rate": 3.4685507313791024e-05, + "loss": 3.5827, + "step": 935424 + }, + { + "epoch": 0.01, + "learning_rate": 3.4677121366280504e-05, + "loss": 3.58, + "step": 935936 + }, + { + "epoch": 0.01, + "learning_rate": 3.466875179757371e-05, + "loss": 3.5762, + "step": 936448 + }, + { + "epoch": 0.01, + "learning_rate": 3.466036585006319e-05, + "loss": 3.5835, + "step": 936960 + }, + { + "epoch": 0.01, + "learning_rate": 3.465197990255267e-05, + "loss": 3.5877, + "step": 937472 + }, + { + "epoch": 0.01, + "learning_rate": 3.464359395504215e-05, + "loss": 3.5925, + "step": 937984 + }, + { + "epoch": 0.01, + "learning_rate": 3.463522438633536e-05, + "loss": 3.5878, + "step": 938496 + }, + { + "epoch": 0.01, + "learning_rate": 3.462683843882484e-05, + "loss": 3.5902, + "step": 939008 + }, + { + "epoch": 0.01, + "learning_rate": 3.461845249131432e-05, + "loss": 3.5893, + "step": 939520 + }, + { + "epoch": 0.01, + "learning_rate": 3.46100665438038e-05, + "loss": 3.5834, + "step": 940032 + }, + { + "epoch": 0.01, + "learning_rate": 3.460169697509702e-05, + "loss": 3.5636, + "step": 940544 + }, + { + "epoch": 0.01, + "learning_rate": 3.45933110275865e-05, + "loss": 3.5912, + "step": 941056 + }, + { + "epoch": 0.01, + "learning_rate": 3.458492508007598e-05, + "loss": 3.5786, + "step": 941568 + }, + { + "epoch": 0.01, + "learning_rate": 3.457653913256546e-05, + "loss": 3.5826, + "step": 942080 + }, + { + "epoch": 0.01, + "learning_rate": 3.4568169563858666e-05, + "loss": 3.5806, + "step": 942592 + }, + { + "epoch": 0.01, + "learning_rate": 3.4559783616348146e-05, + "loss": 3.5746, + "step": 943104 + }, + { + "epoch": 0.01, + "learning_rate": 3.4551397668837626e-05, + "loss": 3.5768, + "step": 943616 + }, + { + "epoch": 0.01, + "learning_rate": 3.4543011721327106e-05, + "loss": 3.5723, + "step": 944128 + }, + { + "epoch": 0.01, + "learning_rate": 3.4534642152620315e-05, + "loss": 3.5862, + "step": 944640 + }, + { + "epoch": 0.01, + "learning_rate": 3.4526256205109795e-05, + "loss": 3.5644, + "step": 945152 + }, + { + "epoch": 0.01, + "learning_rate": 3.4517870257599275e-05, + "loss": 3.5964, + "step": 945664 + }, + { + "epoch": 0.01, + "learning_rate": 3.4509484310088755e-05, + "loss": 3.5826, + "step": 946176 + }, + { + "epoch": 0.01, + "learning_rate": 3.450111474138197e-05, + "loss": 3.5615, + "step": 946688 + }, + { + "epoch": 0.01, + "learning_rate": 3.449272879387145e-05, + "loss": 3.5925, + "step": 947200 + }, + { + "epoch": 0.01, + "learning_rate": 3.448434284636093e-05, + "loss": 3.5686, + "step": 947712 + }, + { + "epoch": 0.01, + "learning_rate": 3.447595689885041e-05, + "loss": 3.5749, + "step": 948224 + }, + { + "epoch": 0.01, + "learning_rate": 3.446758733014362e-05, + "loss": 3.5789, + "step": 948736 + }, + { + "epoch": 0.01, + "learning_rate": 3.44592013826331e-05, + "loss": 3.5885, + "step": 949248 + }, + { + "epoch": 0.01, + "learning_rate": 3.445081543512258e-05, + "loss": 3.5702, + "step": 949760 + }, + { + "epoch": 0.01, + "learning_rate": 3.444242948761205e-05, + "loss": 3.5763, + "step": 950272 + }, + { + "epoch": 0.01, + "learning_rate": 3.443404354010153e-05, + "loss": 3.5591, + "step": 950784 + }, + { + "epoch": 0.01, + "learning_rate": 3.442567397139475e-05, + "loss": 3.5791, + "step": 951296 + }, + { + "epoch": 0.01, + "learning_rate": 3.441728802388423e-05, + "loss": 3.5854, + "step": 951808 + }, + { + "epoch": 0.01, + "learning_rate": 3.440890207637371e-05, + "loss": 3.5838, + "step": 952320 + }, + { + "epoch": 0.01, + "learning_rate": 3.4400532507666925e-05, + "loss": 3.5834, + "step": 952832 + }, + { + "epoch": 0.01, + "learning_rate": 3.4392146560156405e-05, + "loss": 3.582, + "step": 953344 + }, + { + "epoch": 0.01, + "learning_rate": 3.4383760612645885e-05, + "loss": 3.5929, + "step": 953856 + }, + { + "epoch": 0.01, + "learning_rate": 3.437537466513536e-05, + "loss": 3.5808, + "step": 954368 + }, + { + "epoch": 0.01, + "learning_rate": 3.4367005096428574e-05, + "loss": 3.5859, + "step": 954880 + }, + { + "epoch": 0.01, + "learning_rate": 3.4358619148918054e-05, + "loss": 3.5737, + "step": 955392 + }, + { + "epoch": 0.01, + "learning_rate": 3.435023320140753e-05, + "loss": 3.5776, + "step": 955904 + }, + { + "epoch": 0.01, + "learning_rate": 3.434184725389701e-05, + "loss": 3.579, + "step": 956416 + }, + { + "epoch": 0.01, + "learning_rate": 3.433347768519022e-05, + "loss": 3.5736, + "step": 956928 + }, + { + "epoch": 0.01, + "learning_rate": 3.43250917376797e-05, + "loss": 3.5859, + "step": 957440 + }, + { + "epoch": 0.01, + "learning_rate": 3.4316705790169176e-05, + "loss": 3.5849, + "step": 957952 + }, + { + "epoch": 0.01, + "learning_rate": 3.430831984265866e-05, + "loss": 3.5853, + "step": 958464 + }, + { + "epoch": 0.01, + "learning_rate": 3.429995027395188e-05, + "loss": 3.5655, + "step": 958976 + }, + { + "epoch": 0.01, + "learning_rate": 3.429156432644136e-05, + "loss": 3.5786, + "step": 959488 + }, + { + "epoch": 0.01, + "learning_rate": 3.428317837893083e-05, + "loss": 3.5821, + "step": 960000 + }, + { + "epoch": 0.01, + "learning_rate": 3.427479243142031e-05, + "loss": 3.5728, + "step": 960512 + }, + { + "epoch": 0.01, + "learning_rate": 3.426642286271353e-05, + "loss": 3.5725, + "step": 961024 + }, + { + "epoch": 0.01, + "learning_rate": 3.4258036915203e-05, + "loss": 3.5846, + "step": 961536 + }, + { + "epoch": 0.02, + "learning_rate": 3.424965096769248e-05, + "loss": 3.5795, + "step": 962048 + }, + { + "epoch": 0.02, + "learning_rate": 3.424126502018196e-05, + "loss": 3.5761, + "step": 962560 + }, + { + "epoch": 0.02, + "learning_rate": 3.4232895451475176e-05, + "loss": 3.5736, + "step": 963072 + }, + { + "epoch": 0.02, + "learning_rate": 3.422450950396465e-05, + "loss": 3.5807, + "step": 963584 + }, + { + "epoch": 0.02, + "learning_rate": 3.421612355645413e-05, + "loss": 3.5891, + "step": 964096 + }, + { + "epoch": 0.02, + "learning_rate": 3.4207737608943616e-05, + "loss": 3.5834, + "step": 964608 + }, + { + "epoch": 0.02, + "learning_rate": 3.4199368040236825e-05, + "loss": 3.5663, + "step": 965120 + }, + { + "epoch": 0.02, + "learning_rate": 3.4190982092726305e-05, + "loss": 3.5791, + "step": 965632 + }, + { + "epoch": 0.02, + "learning_rate": 3.4182596145215785e-05, + "loss": 3.5673, + "step": 966144 + }, + { + "epoch": 0.02, + "learning_rate": 3.4174210197705265e-05, + "loss": 3.5829, + "step": 966656 + }, + { + "epoch": 0.02, + "learning_rate": 3.4165840628998474e-05, + "loss": 3.5886, + "step": 967168 + }, + { + "epoch": 0.02, + "learning_rate": 3.4157454681487954e-05, + "loss": 3.574, + "step": 967680 + }, + { + "epoch": 0.02, + "learning_rate": 3.4149068733977434e-05, + "loss": 3.5705, + "step": 968192 + }, + { + "epoch": 0.02, + "learning_rate": 3.4140682786466914e-05, + "loss": 3.574, + "step": 968704 + }, + { + "epoch": 0.02, + "learning_rate": 3.413231321776012e-05, + "loss": 3.5708, + "step": 969216 + }, + { + "epoch": 0.02, + "learning_rate": 3.41239272702496e-05, + "loss": 3.5677, + "step": 969728 + }, + { + "epoch": 0.02, + "learning_rate": 3.411554132273908e-05, + "loss": 3.5751, + "step": 970240 + }, + { + "epoch": 0.02, + "learning_rate": 3.410715537522857e-05, + "loss": 3.575, + "step": 970752 + }, + { + "epoch": 0.02, + "learning_rate": 3.409878580652178e-05, + "loss": 3.5761, + "step": 971264 + }, + { + "epoch": 0.02, + "learning_rate": 3.4090416237814995e-05, + "loss": 3.5656, + "step": 971776 + }, + { + "epoch": 0.02, + "learning_rate": 3.4082030290304475e-05, + "loss": 3.5714, + "step": 972288 + }, + { + "epoch": 0.02, + "learning_rate": 3.407364434279395e-05, + "loss": 3.5679, + "step": 972800 + }, + { + "epoch": 0.02, + "learning_rate": 3.406525839528343e-05, + "loss": 3.5877, + "step": 973312 + }, + { + "epoch": 0.02, + "learning_rate": 3.405687244777291e-05, + "loss": 3.5694, + "step": 973824 + }, + { + "epoch": 0.02, + "learning_rate": 3.404848650026239e-05, + "loss": 3.5855, + "step": 974336 + }, + { + "epoch": 0.02, + "learning_rate": 3.404010055275187e-05, + "loss": 3.5827, + "step": 974848 + }, + { + "epoch": 0.02, + "learning_rate": 3.403171460524135e-05, + "loss": 3.593, + "step": 975360 + }, + { + "epoch": 0.02, + "learning_rate": 3.402334503653456e-05, + "loss": 3.5759, + "step": 975872 + }, + { + "epoch": 0.02, + "learning_rate": 3.401495908902404e-05, + "loss": 3.5734, + "step": 976384 + }, + { + "epoch": 0.02, + "learning_rate": 3.4006573141513524e-05, + "loss": 3.5762, + "step": 976896 + }, + { + "epoch": 0.02, + "learning_rate": 3.3998187194003004e-05, + "loss": 3.5793, + "step": 977408 + }, + { + "epoch": 0.02, + "learning_rate": 3.398981762529621e-05, + "loss": 3.5741, + "step": 977920 + }, + { + "epoch": 0.02, + "learning_rate": 3.398143167778569e-05, + "loss": 3.5759, + "step": 978432 + }, + { + "epoch": 0.02, + "learning_rate": 3.397304573027517e-05, + "loss": 3.5735, + "step": 978944 + }, + { + "epoch": 0.02, + "learning_rate": 3.396467616156838e-05, + "loss": 3.5881, + "step": 979456 + }, + { + "epoch": 0.02, + "learning_rate": 3.395629021405786e-05, + "loss": 3.5746, + "step": 979968 + }, + { + "epoch": 0.02, + "learning_rate": 3.394790426654734e-05, + "loss": 3.571, + "step": 980480 + }, + { + "epoch": 0.02, + "learning_rate": 3.393951831903682e-05, + "loss": 3.5765, + "step": 980992 + }, + { + "epoch": 0.02, + "learning_rate": 3.393114875033003e-05, + "loss": 3.573, + "step": 981504 + }, + { + "epoch": 0.02, + "learning_rate": 3.392276280281951e-05, + "loss": 3.5855, + "step": 982016 + }, + { + "epoch": 0.02, + "learning_rate": 3.391437685530899e-05, + "loss": 3.5728, + "step": 982528 + }, + { + "epoch": 0.02, + "learning_rate": 3.390599090779848e-05, + "loss": 3.5855, + "step": 983040 + }, + { + "epoch": 0.02, + "learning_rate": 3.3897621339091686e-05, + "loss": 3.5668, + "step": 983552 + }, + { + "epoch": 0.02, + "learning_rate": 3.3889235391581166e-05, + "loss": 3.5788, + "step": 984064 + }, + { + "epoch": 0.02, + "learning_rate": 3.3880849444070646e-05, + "loss": 3.5755, + "step": 984576 + }, + { + "epoch": 0.02, + "learning_rate": 3.3872463496560126e-05, + "loss": 3.579, + "step": 985088 + }, + { + "epoch": 0.02, + "learning_rate": 3.3864093927853335e-05, + "loss": 3.5704, + "step": 985600 + }, + { + "epoch": 0.02, + "learning_rate": 3.3855707980342815e-05, + "loss": 3.5754, + "step": 986112 + }, + { + "epoch": 0.02, + "learning_rate": 3.3847322032832295e-05, + "loss": 3.5847, + "step": 986624 + }, + { + "epoch": 0.02, + "learning_rate": 3.3838936085321775e-05, + "loss": 3.594, + "step": 987136 + }, + { + "epoch": 0.02, + "learning_rate": 3.3830566516614984e-05, + "loss": 3.5693, + "step": 987648 + }, + { + "epoch": 0.02, + "learning_rate": 3.3822180569104464e-05, + "loss": 3.5749, + "step": 988160 + }, + { + "epoch": 0.02, + "learning_rate": 3.3813794621593944e-05, + "loss": 3.5773, + "step": 988672 + }, + { + "epoch": 0.02, + "learning_rate": 3.3805408674083424e-05, + "loss": 3.5718, + "step": 989184 + }, + { + "epoch": 0.02, + "learning_rate": 3.379703910537664e-05, + "loss": 3.567, + "step": 989696 + }, + { + "epoch": 0.02, + "learning_rate": 3.378865315786612e-05, + "loss": 3.5855, + "step": 990208 + }, + { + "epoch": 0.02, + "learning_rate": 3.37802672103556e-05, + "loss": 3.5732, + "step": 990720 + }, + { + "epoch": 0.02, + "learning_rate": 3.377188126284508e-05, + "loss": 3.5815, + "step": 991232 + }, + { + "epoch": 0.02, + "learning_rate": 3.376351169413829e-05, + "loss": 3.5714, + "step": 991744 + }, + { + "epoch": 0.03, + "eval_loss": 3.842043876647949, + "eval_runtime": 307.0087, + "eval_samples_per_second": 1242.932, + "eval_steps_per_second": 38.843, + "step": 992160 + }, + { + "epoch": 1.0, + "learning_rate": 3.375512574662777e-05, + "loss": 3.5762, + "step": 992256 + }, + { + "epoch": 1.0, + "learning_rate": 3.374673979911725e-05, + "loss": 3.5586, + "step": 992768 + }, + { + "epoch": 1.0, + "learning_rate": 3.373835385160673e-05, + "loss": 3.5768, + "step": 993280 + }, + { + "epoch": 1.0, + "learning_rate": 3.372998428289994e-05, + "loss": 3.5757, + "step": 993792 + }, + { + "epoch": 1.0, + "learning_rate": 3.372159833538942e-05, + "loss": 3.5774, + "step": 994304 + }, + { + "epoch": 1.0, + "learning_rate": 3.37132123878789e-05, + "loss": 3.5703, + "step": 994816 + }, + { + "epoch": 1.0, + "learning_rate": 3.370482644036838e-05, + "loss": 3.574, + "step": 995328 + }, + { + "epoch": 1.0, + "learning_rate": 3.3696456871661594e-05, + "loss": 3.5708, + "step": 995840 + }, + { + "epoch": 1.0, + "learning_rate": 3.3688070924151074e-05, + "loss": 3.5689, + "step": 996352 + }, + { + "epoch": 1.0, + "learning_rate": 3.3679684976640554e-05, + "loss": 3.5708, + "step": 996864 + }, + { + "epoch": 1.0, + "learning_rate": 3.3671299029130034e-05, + "loss": 3.5697, + "step": 997376 + }, + { + "epoch": 1.0, + "learning_rate": 3.366292946042324e-05, + "loss": 3.5779, + "step": 997888 + }, + { + "epoch": 1.0, + "learning_rate": 3.365455989171645e-05, + "loss": 3.5877, + "step": 998400 + }, + { + "epoch": 1.0, + "learning_rate": 3.364617394420593e-05, + "loss": 3.5611, + "step": 998912 + }, + { + "epoch": 1.0, + "learning_rate": 3.363778799669541e-05, + "loss": 3.566, + "step": 999424 + }, + { + "epoch": 1.0, + "learning_rate": 3.362940204918489e-05, + "loss": 3.5619, + "step": 999936 + }, + { + "epoch": 1.0, + "learning_rate": 3.362101610167437e-05, + "loss": 3.566, + "step": 1000448 + }, + { + "epoch": 1.0, + "learning_rate": 3.361263015416385e-05, + "loss": 3.5696, + "step": 1000960 + }, + { + "epoch": 1.0, + "learning_rate": 3.360424420665333e-05, + "loss": 3.5602, + "step": 1001472 + }, + { + "epoch": 1.0, + "learning_rate": 3.359585825914282e-05, + "loss": 3.5681, + "step": 1001984 + }, + { + "epoch": 1.0, + "learning_rate": 3.358748869043603e-05, + "loss": 3.5819, + "step": 1002496 + }, + { + "epoch": 1.0, + "learning_rate": 3.357910274292551e-05, + "loss": 3.5692, + "step": 1003008 + }, + { + "epoch": 1.0, + "learning_rate": 3.357071679541499e-05, + "loss": 3.5789, + "step": 1003520 + }, + { + "epoch": 1.0, + "learning_rate": 3.356233084790447e-05, + "loss": 3.5783, + "step": 1004032 + }, + { + "epoch": 1.0, + "learning_rate": 3.3553961279197676e-05, + "loss": 3.5661, + "step": 1004544 + }, + { + "epoch": 1.0, + "learning_rate": 3.3545575331687156e-05, + "loss": 3.5735, + "step": 1005056 + }, + { + "epoch": 1.0, + "learning_rate": 3.3537189384176636e-05, + "loss": 3.5619, + "step": 1005568 + }, + { + "epoch": 1.0, + "learning_rate": 3.3528803436666116e-05, + "loss": 3.5712, + "step": 1006080 + }, + { + "epoch": 1.0, + "learning_rate": 3.3520433867959325e-05, + "loss": 3.5638, + "step": 1006592 + }, + { + "epoch": 1.0, + "learning_rate": 3.3512047920448805e-05, + "loss": 3.5638, + "step": 1007104 + }, + { + "epoch": 1.01, + "learning_rate": 3.3503661972938285e-05, + "loss": 3.5734, + "step": 1007616 + }, + { + "epoch": 1.01, + "learning_rate": 3.349527602542777e-05, + "loss": 3.5667, + "step": 1008128 + }, + { + "epoch": 1.01, + "learning_rate": 3.348690645672098e-05, + "loss": 3.5737, + "step": 1008640 + }, + { + "epoch": 1.01, + "learning_rate": 3.347852050921046e-05, + "loss": 3.5678, + "step": 1009152 + }, + { + "epoch": 1.01, + "learning_rate": 3.347013456169994e-05, + "loss": 3.5668, + "step": 1009664 + }, + { + "epoch": 1.01, + "learning_rate": 3.346174861418942e-05, + "loss": 3.5724, + "step": 1010176 + }, + { + "epoch": 1.01, + "learning_rate": 3.345337904548263e-05, + "loss": 3.577, + "step": 1010688 + }, + { + "epoch": 1.01, + "learning_rate": 3.344499309797211e-05, + "loss": 3.5494, + "step": 1011200 + }, + { + "epoch": 1.01, + "learning_rate": 3.343660715046159e-05, + "loss": 3.569, + "step": 1011712 + }, + { + "epoch": 1.01, + "learning_rate": 3.342822120295107e-05, + "loss": 3.564, + "step": 1012224 + }, + { + "epoch": 1.01, + "learning_rate": 3.341985163424428e-05, + "loss": 3.5554, + "step": 1012736 + }, + { + "epoch": 1.01, + "learning_rate": 3.341146568673376e-05, + "loss": 3.5643, + "step": 1013248 + }, + { + "epoch": 1.01, + "learning_rate": 3.340307973922324e-05, + "loss": 3.5749, + "step": 1013760 + }, + { + "epoch": 1.01, + "learning_rate": 3.3394693791712726e-05, + "loss": 3.5728, + "step": 1014272 + }, + { + "epoch": 1.01, + "learning_rate": 3.3386324223005935e-05, + "loss": 3.5714, + "step": 1014784 + }, + { + "epoch": 1.01, + "learning_rate": 3.3377938275495415e-05, + "loss": 3.5713, + "step": 1015296 + }, + { + "epoch": 1.01, + "learning_rate": 3.3369552327984895e-05, + "loss": 3.5713, + "step": 1015808 + }, + { + "epoch": 1.01, + "learning_rate": 3.3361166380474374e-05, + "loss": 3.5648, + "step": 1016320 + }, + { + "epoch": 1.01, + "learning_rate": 3.3352796811767584e-05, + "loss": 3.547, + "step": 1016832 + }, + { + "epoch": 1.01, + "learning_rate": 3.3344410864257064e-05, + "loss": 3.5757, + "step": 1017344 + }, + { + "epoch": 1.01, + "learning_rate": 3.3336024916746543e-05, + "loss": 3.5635, + "step": 1017856 + }, + { + "epoch": 1.01, + "learning_rate": 3.3327638969236023e-05, + "loss": 3.5682, + "step": 1018368 + }, + { + "epoch": 1.01, + "learning_rate": 3.331926940052923e-05, + "loss": 3.5623, + "step": 1018880 + }, + { + "epoch": 1.01, + "learning_rate": 3.331088345301871e-05, + "loss": 3.5585, + "step": 1019392 + }, + { + "epoch": 1.01, + "learning_rate": 3.330249750550819e-05, + "loss": 3.5576, + "step": 1019904 + }, + { + "epoch": 1.01, + "learning_rate": 3.329411155799768e-05, + "loss": 3.5519, + "step": 1020416 + }, + { + "epoch": 1.01, + "learning_rate": 3.328574198929089e-05, + "loss": 3.5715, + "step": 1020928 + }, + { + "epoch": 1.01, + "learning_rate": 3.327735604178037e-05, + "loss": 3.5521, + "step": 1021440 + }, + { + "epoch": 1.01, + "learning_rate": 3.326897009426985e-05, + "loss": 3.5748, + "step": 1021952 + }, + { + "epoch": 1.01, + "learning_rate": 3.326058414675932e-05, + "loss": 3.5666, + "step": 1022464 + }, + { + "epoch": 1.01, + "learning_rate": 3.325221457805254e-05, + "loss": 3.547, + "step": 1022976 + }, + { + "epoch": 1.01, + "learning_rate": 3.324382863054202e-05, + "loss": 3.573, + "step": 1023488 + }, + { + "epoch": 1.01, + "learning_rate": 3.32354426830315e-05, + "loss": 3.5524, + "step": 1024000 + }, + { + "epoch": 1.01, + "learning_rate": 3.322705673552097e-05, + "loss": 3.5598, + "step": 1024512 + }, + { + "epoch": 1.01, + "learning_rate": 3.3218687166814186e-05, + "loss": 3.5582, + "step": 1025024 + }, + { + "epoch": 1.01, + "learning_rate": 3.3210301219303666e-05, + "loss": 3.5736, + "step": 1025536 + }, + { + "epoch": 1.01, + "learning_rate": 3.3201915271793146e-05, + "loss": 3.5577, + "step": 1026048 + }, + { + "epoch": 1.01, + "learning_rate": 3.3193529324282626e-05, + "loss": 3.5565, + "step": 1026560 + }, + { + "epoch": 1.01, + "learning_rate": 3.318515975557584e-05, + "loss": 3.5419, + "step": 1027072 + }, + { + "epoch": 1.01, + "learning_rate": 3.317677380806532e-05, + "loss": 3.5618, + "step": 1027584 + }, + { + "epoch": 1.01, + "learning_rate": 3.3168387860554795e-05, + "loss": 3.5704, + "step": 1028096 + }, + { + "epoch": 1.01, + "learning_rate": 3.3160001913044275e-05, + "loss": 3.5723, + "step": 1028608 + }, + { + "epoch": 1.01, + "learning_rate": 3.315163234433749e-05, + "loss": 3.5638, + "step": 1029120 + }, + { + "epoch": 1.01, + "learning_rate": 3.314324639682697e-05, + "loss": 3.5681, + "step": 1029632 + }, + { + "epoch": 1.01, + "learning_rate": 3.3134860449316444e-05, + "loss": 3.5749, + "step": 1030144 + }, + { + "epoch": 1.01, + "learning_rate": 3.312649088060966e-05, + "loss": 3.5586, + "step": 1030656 + }, + { + "epoch": 1.01, + "learning_rate": 3.311810493309914e-05, + "loss": 3.5661, + "step": 1031168 + }, + { + "epoch": 1.01, + "learning_rate": 3.310971898558862e-05, + "loss": 3.5633, + "step": 1031680 + }, + { + "epoch": 1.01, + "learning_rate": 3.31013330380781e-05, + "loss": 3.5602, + "step": 1032192 + }, + { + "epoch": 1.01, + "learning_rate": 3.3092963469371316e-05, + "loss": 3.5599, + "step": 1032704 + }, + { + "epoch": 1.01, + "learning_rate": 3.3084577521860796e-05, + "loss": 3.5605, + "step": 1033216 + }, + { + "epoch": 1.01, + "learning_rate": 3.307619157435027e-05, + "loss": 3.5682, + "step": 1033728 + }, + { + "epoch": 1.01, + "learning_rate": 3.306780562683975e-05, + "loss": 3.5701, + "step": 1034240 + }, + { + "epoch": 1.01, + "learning_rate": 3.3059436058132965e-05, + "loss": 3.5685, + "step": 1034752 + }, + { + "epoch": 1.01, + "learning_rate": 3.3051050110622445e-05, + "loss": 3.5489, + "step": 1035264 + }, + { + "epoch": 1.01, + "learning_rate": 3.304266416311192e-05, + "loss": 3.5641, + "step": 1035776 + }, + { + "epoch": 1.01, + "learning_rate": 3.30342782156014e-05, + "loss": 3.5631, + "step": 1036288 + }, + { + "epoch": 1.01, + "learning_rate": 3.3025908646894614e-05, + "loss": 3.557, + "step": 1036800 + }, + { + "epoch": 1.01, + "learning_rate": 3.3017522699384094e-05, + "loss": 3.5558, + "step": 1037312 + }, + { + "epoch": 1.01, + "learning_rate": 3.3009136751873574e-05, + "loss": 3.5669, + "step": 1037824 + }, + { + "epoch": 1.02, + "learning_rate": 3.3000750804363053e-05, + "loss": 3.5602, + "step": 1038336 + }, + { + "epoch": 1.02, + "learning_rate": 3.299238123565627e-05, + "loss": 3.5594, + "step": 1038848 + }, + { + "epoch": 1.02, + "learning_rate": 3.298399528814574e-05, + "loss": 3.5571, + "step": 1039360 + }, + { + "epoch": 1.02, + "learning_rate": 3.297560934063522e-05, + "loss": 3.566, + "step": 1039872 + }, + { + "epoch": 1.02, + "learning_rate": 3.29672233931247e-05, + "loss": 3.5705, + "step": 1040384 + }, + { + "epoch": 1.02, + "learning_rate": 3.295885382441792e-05, + "loss": 3.5672, + "step": 1040896 + }, + { + "epoch": 1.02, + "learning_rate": 3.295046787690739e-05, + "loss": 3.5454, + "step": 1041408 + }, + { + "epoch": 1.02, + "learning_rate": 3.294208192939687e-05, + "loss": 3.5632, + "step": 1041920 + }, + { + "epoch": 1.02, + "learning_rate": 3.293369598188635e-05, + "loss": 3.5568, + "step": 1042432 + }, + { + "epoch": 1.02, + "learning_rate": 3.292532641317956e-05, + "loss": 3.5635, + "step": 1042944 + }, + { + "epoch": 1.02, + "learning_rate": 3.291694046566905e-05, + "loss": 3.5717, + "step": 1043456 + }, + { + "epoch": 1.02, + "learning_rate": 3.290855451815853e-05, + "loss": 3.5559, + "step": 1043968 + }, + { + "epoch": 1.02, + "learning_rate": 3.290016857064801e-05, + "loss": 3.555, + "step": 1044480 + }, + { + "epoch": 1.02, + "learning_rate": 3.2891799001941216e-05, + "loss": 3.5544, + "step": 1044992 + }, + { + "epoch": 1.02, + "learning_rate": 3.2883413054430696e-05, + "loss": 3.559, + "step": 1045504 + }, + { + "epoch": 1.02, + "learning_rate": 3.2875027106920176e-05, + "loss": 3.5508, + "step": 1046016 + }, + { + "epoch": 1.02, + "learning_rate": 3.2866641159409656e-05, + "loss": 3.5566, + "step": 1046528 + }, + { + "epoch": 1.02, + "learning_rate": 3.2858271590702865e-05, + "loss": 3.5591, + "step": 1047040 + }, + { + "epoch": 1.02, + "learning_rate": 3.2849885643192345e-05, + "loss": 3.5575, + "step": 1047552 + }, + { + "epoch": 1.02, + "learning_rate": 3.284151607448556e-05, + "loss": 3.5501, + "step": 1048064 + }, + { + "epoch": 1.02, + "learning_rate": 3.2833130126975034e-05, + "loss": 3.5546, + "step": 1048576 + }, + { + "epoch": 1.02, + "learning_rate": 3.2824744179464514e-05, + "loss": 3.5508, + "step": 1049088 + }, + { + "epoch": 1.02, + "learning_rate": 3.2816358231954e-05, + "loss": 3.571, + "step": 1049600 + }, + { + "epoch": 1.02, + "learning_rate": 3.280797228444348e-05, + "loss": 3.5565, + "step": 1050112 + }, + { + "epoch": 1.02, + "learning_rate": 3.279958633693296e-05, + "loss": 3.5663, + "step": 1050624 + }, + { + "epoch": 1.02, + "learning_rate": 3.279120038942244e-05, + "loss": 3.5674, + "step": 1051136 + }, + { + "epoch": 1.02, + "learning_rate": 3.278281444191192e-05, + "loss": 3.5785, + "step": 1051648 + }, + { + "epoch": 1.02, + "learning_rate": 3.277444487320513e-05, + "loss": 3.5584, + "step": 1052160 + }, + { + "epoch": 1.02, + "learning_rate": 3.276605892569461e-05, + "loss": 3.5578, + "step": 1052672 + }, + { + "epoch": 1.02, + "learning_rate": 3.275767297818409e-05, + "loss": 3.5617, + "step": 1053184 + }, + { + "epoch": 1.02, + "learning_rate": 3.274928703067357e-05, + "loss": 3.5618, + "step": 1053696 + }, + { + "epoch": 1.02, + "learning_rate": 3.274091746196678e-05, + "loss": 3.5569, + "step": 1054208 + }, + { + "epoch": 1.02, + "learning_rate": 3.273253151445626e-05, + "loss": 3.5599, + "step": 1054720 + }, + { + "epoch": 1.02, + "learning_rate": 3.272414556694574e-05, + "loss": 3.5569, + "step": 1055232 + }, + { + "epoch": 1.02, + "learning_rate": 3.271577599823895e-05, + "loss": 3.5685, + "step": 1055744 + }, + { + "epoch": 1.02, + "learning_rate": 3.2707406429532164e-05, + "loss": 3.5584, + "step": 1056256 + }, + { + "epoch": 1.02, + "learning_rate": 3.2699020482021644e-05, + "loss": 3.5539, + "step": 1056768 + }, + { + "epoch": 1.02, + "learning_rate": 3.2690634534511124e-05, + "loss": 3.561, + "step": 1057280 + }, + { + "epoch": 1.02, + "learning_rate": 3.2682248587000604e-05, + "loss": 3.5579, + "step": 1057792 + }, + { + "epoch": 1.02, + "learning_rate": 3.2673862639490083e-05, + "loss": 3.5636, + "step": 1058304 + }, + { + "epoch": 1.02, + "learning_rate": 3.2665476691979563e-05, + "loss": 3.5596, + "step": 1058816 + }, + { + "epoch": 1.02, + "learning_rate": 3.265709074446904e-05, + "loss": 3.564, + "step": 1059328 + }, + { + "epoch": 1.02, + "learning_rate": 3.264870479695852e-05, + "loss": 3.5527, + "step": 1059840 + }, + { + "epoch": 1.02, + "learning_rate": 3.264033522825173e-05, + "loss": 3.559, + "step": 1060352 + }, + { + "epoch": 1.02, + "learning_rate": 3.263194928074121e-05, + "loss": 3.5632, + "step": 1060864 + }, + { + "epoch": 1.02, + "learning_rate": 3.262356333323069e-05, + "loss": 3.5585, + "step": 1061376 + }, + { + "epoch": 1.02, + "learning_rate": 3.261517738572017e-05, + "loss": 3.5579, + "step": 1061888 + }, + { + "epoch": 1.02, + "learning_rate": 3.260680781701339e-05, + "loss": 3.5588, + "step": 1062400 + }, + { + "epoch": 1.02, + "learning_rate": 3.259842186950287e-05, + "loss": 3.5686, + "step": 1062912 + }, + { + "epoch": 1.02, + "learning_rate": 3.259003592199235e-05, + "loss": 3.5773, + "step": 1063424 + }, + { + "epoch": 1.02, + "learning_rate": 3.258164997448183e-05, + "loss": 3.554, + "step": 1063936 + }, + { + "epoch": 1.02, + "learning_rate": 3.257328040577504e-05, + "loss": 3.557, + "step": 1064448 + }, + { + "epoch": 1.02, + "learning_rate": 3.256489445826452e-05, + "loss": 3.5576, + "step": 1064960 + }, + { + "epoch": 1.02, + "learning_rate": 3.2556508510754e-05, + "loss": 3.5582, + "step": 1065472 + }, + { + "epoch": 1.02, + "learning_rate": 3.254812256324348e-05, + "loss": 3.5485, + "step": 1065984 + }, + { + "epoch": 1.02, + "learning_rate": 3.2539752994536686e-05, + "loss": 3.5696, + "step": 1066496 + }, + { + "epoch": 1.02, + "learning_rate": 3.2531367047026166e-05, + "loss": 3.5585, + "step": 1067008 + }, + { + "epoch": 1.02, + "learning_rate": 3.2522981099515646e-05, + "loss": 3.5676, + "step": 1067520 + }, + { + "epoch": 1.02, + "learning_rate": 3.2514595152005126e-05, + "loss": 3.5492, + "step": 1068032 + }, + { + "epoch": 1.03, + "eval_loss": 3.842775821685791, + "eval_runtime": 308.3348, + "eval_samples_per_second": 1237.587, + "eval_steps_per_second": 38.675, + "step": 1068480 + }, + { + "epoch": 0.0, + "learning_rate": 3.250622558329834e-05, + "loss": 3.5434, + "step": 1068544 + }, + { + "epoch": 0.0, + "learning_rate": 3.249783963578782e-05, + "loss": 3.5464, + "step": 1069056 + }, + { + "epoch": 0.0, + "learning_rate": 3.24894536882773e-05, + "loss": 3.5575, + "step": 1069568 + }, + { + "epoch": 0.0, + "learning_rate": 3.248106774076678e-05, + "loss": 3.5596, + "step": 1070080 + }, + { + "epoch": 0.0, + "learning_rate": 3.247269817205999e-05, + "loss": 3.5644, + "step": 1070592 + }, + { + "epoch": 0.0, + "learning_rate": 3.246431222454947e-05, + "loss": 3.5546, + "step": 1071104 + }, + { + "epoch": 0.0, + "learning_rate": 3.245592627703895e-05, + "loss": 3.5535, + "step": 1071616 + }, + { + "epoch": 0.0, + "learning_rate": 3.244754032952843e-05, + "loss": 3.5559, + "step": 1072128 + }, + { + "epoch": 0.0, + "learning_rate": 3.243917076082164e-05, + "loss": 3.5535, + "step": 1072640 + }, + { + "epoch": 0.0, + "learning_rate": 3.243078481331112e-05, + "loss": 3.5559, + "step": 1073152 + }, + { + "epoch": 0.0, + "learning_rate": 3.24223988658006e-05, + "loss": 3.5522, + "step": 1073664 + }, + { + "epoch": 0.0, + "learning_rate": 3.241401291829008e-05, + "loss": 3.5645, + "step": 1074176 + }, + { + "epoch": 0.0, + "learning_rate": 3.2405659728387025e-05, + "loss": 3.5701, + "step": 1074688 + }, + { + "epoch": 0.0, + "learning_rate": 3.2397273780876505e-05, + "loss": 3.5433, + "step": 1075200 + }, + { + "epoch": 0.0, + "learning_rate": 3.2388887833365985e-05, + "loss": 3.5532, + "step": 1075712 + }, + { + "epoch": 0.0, + "learning_rate": 3.2380501885855465e-05, + "loss": 3.543, + "step": 1076224 + }, + { + "epoch": 0.0, + "learning_rate": 3.2372115938344944e-05, + "loss": 3.553, + "step": 1076736 + }, + { + "epoch": 0.0, + "learning_rate": 3.2363729990834424e-05, + "loss": 3.5478, + "step": 1077248 + }, + { + "epoch": 0.0, + "learning_rate": 3.2355344043323904e-05, + "loss": 3.5499, + "step": 1077760 + }, + { + "epoch": 0.0, + "learning_rate": 3.2346958095813384e-05, + "loss": 3.548, + "step": 1078272 + }, + { + "epoch": 0.0, + "learning_rate": 3.2338588527106593e-05, + "loss": 3.5689, + "step": 1078784 + }, + { + "epoch": 0.0, + "learning_rate": 3.2330202579596073e-05, + "loss": 3.5548, + "step": 1079296 + }, + { + "epoch": 0.0, + "learning_rate": 3.232181663208555e-05, + "loss": 3.5617, + "step": 1079808 + }, + { + "epoch": 0.0, + "learning_rate": 3.231343068457503e-05, + "loss": 3.5586, + "step": 1080320 + }, + { + "epoch": 0.0, + "learning_rate": 3.230506111586825e-05, + "loss": 3.5579, + "step": 1080832 + }, + { + "epoch": 0.0, + "learning_rate": 3.229667516835773e-05, + "loss": 3.5528, + "step": 1081344 + }, + { + "epoch": 0.0, + "learning_rate": 3.228828922084721e-05, + "loss": 3.5464, + "step": 1081856 + }, + { + "epoch": 0.0, + "learning_rate": 3.227990327333669e-05, + "loss": 3.5551, + "step": 1082368 + }, + { + "epoch": 0.0, + "learning_rate": 3.22715337046299e-05, + "loss": 3.5485, + "step": 1082880 + }, + { + "epoch": 0.0, + "learning_rate": 3.226314775711938e-05, + "loss": 3.5483, + "step": 1083392 + }, + { + "epoch": 0.01, + "learning_rate": 3.225476180960886e-05, + "loss": 3.5554, + "step": 1083904 + }, + { + "epoch": 0.01, + "learning_rate": 3.224637586209834e-05, + "loss": 3.5478, + "step": 1084416 + }, + { + "epoch": 0.01, + "learning_rate": 3.223800629339155e-05, + "loss": 3.5594, + "step": 1084928 + }, + { + "epoch": 0.01, + "learning_rate": 3.222962034588103e-05, + "loss": 3.5496, + "step": 1085440 + }, + { + "epoch": 0.01, + "learning_rate": 3.222123439837051e-05, + "loss": 3.5509, + "step": 1085952 + }, + { + "epoch": 0.01, + "learning_rate": 3.221284845085999e-05, + "loss": 3.5622, + "step": 1086464 + }, + { + "epoch": 0.01, + "learning_rate": 3.22044788821532e-05, + "loss": 3.5583, + "step": 1086976 + }, + { + "epoch": 0.01, + "learning_rate": 3.219609293464268e-05, + "loss": 3.5353, + "step": 1087488 + }, + { + "epoch": 0.01, + "learning_rate": 3.218770698713216e-05, + "loss": 3.5526, + "step": 1088000 + }, + { + "epoch": 0.01, + "learning_rate": 3.217932103962164e-05, + "loss": 3.5489, + "step": 1088512 + }, + { + "epoch": 0.01, + "learning_rate": 3.217095147091485e-05, + "loss": 3.5387, + "step": 1089024 + }, + { + "epoch": 0.01, + "learning_rate": 3.216256552340433e-05, + "loss": 3.5516, + "step": 1089536 + }, + { + "epoch": 0.01, + "learning_rate": 3.215417957589381e-05, + "loss": 3.5615, + "step": 1090048 + }, + { + "epoch": 0.01, + "learning_rate": 3.214579362838329e-05, + "loss": 3.5529, + "step": 1090560 + }, + { + "epoch": 0.01, + "learning_rate": 3.21374240596765e-05, + "loss": 3.557, + "step": 1091072 + }, + { + "epoch": 0.01, + "learning_rate": 3.212903811216598e-05, + "loss": 3.5567, + "step": 1091584 + }, + { + "epoch": 0.01, + "learning_rate": 3.212065216465546e-05, + "loss": 3.5547, + "step": 1092096 + }, + { + "epoch": 0.01, + "learning_rate": 3.211226621714494e-05, + "loss": 3.55, + "step": 1092608 + }, + { + "epoch": 0.01, + "learning_rate": 3.2103896648438157e-05, + "loss": 3.5341, + "step": 1093120 + }, + { + "epoch": 0.01, + "learning_rate": 3.2095510700927636e-05, + "loss": 3.555, + "step": 1093632 + }, + { + "epoch": 0.01, + "learning_rate": 3.2087124753417116e-05, + "loss": 3.5487, + "step": 1094144 + }, + { + "epoch": 0.01, + "learning_rate": 3.207873880590659e-05, + "loss": 3.5505, + "step": 1094656 + }, + { + "epoch": 0.01, + "learning_rate": 3.2070369237199805e-05, + "loss": 3.546, + "step": 1095168 + }, + { + "epoch": 0.01, + "learning_rate": 3.2061983289689285e-05, + "loss": 3.5437, + "step": 1095680 + }, + { + "epoch": 0.01, + "learning_rate": 3.2053597342178765e-05, + "loss": 3.5373, + "step": 1096192 + }, + { + "epoch": 0.01, + "learning_rate": 3.204521139466824e-05, + "loss": 3.5381, + "step": 1096704 + }, + { + "epoch": 0.01, + "learning_rate": 3.2036841825961454e-05, + "loss": 3.5586, + "step": 1097216 + }, + { + "epoch": 0.01, + "learning_rate": 3.2028455878450934e-05, + "loss": 3.533, + "step": 1097728 + }, + { + "epoch": 0.01, + "learning_rate": 3.2020069930940414e-05, + "loss": 3.5561, + "step": 1098240 + }, + { + "epoch": 0.01, + "learning_rate": 3.2011683983429894e-05, + "loss": 3.5497, + "step": 1098752 + }, + { + "epoch": 0.01, + "learning_rate": 3.2003314414723103e-05, + "loss": 3.5349, + "step": 1099264 + }, + { + "epoch": 0.01, + "learning_rate": 3.199492846721259e-05, + "loss": 3.5511, + "step": 1099776 + }, + { + "epoch": 0.01, + "learning_rate": 3.198654251970206e-05, + "loss": 3.5441, + "step": 1100288 + }, + { + "epoch": 0.01, + "learning_rate": 3.197817295099528e-05, + "loss": 3.5452, + "step": 1100800 + }, + { + "epoch": 0.01, + "learning_rate": 3.196978700348476e-05, + "loss": 3.5391, + "step": 1101312 + }, + { + "epoch": 0.01, + "learning_rate": 3.196140105597424e-05, + "loss": 3.559, + "step": 1101824 + }, + { + "epoch": 0.01, + "learning_rate": 3.195301510846371e-05, + "loss": 3.5452, + "step": 1102336 + }, + { + "epoch": 0.01, + "learning_rate": 3.194464553975693e-05, + "loss": 3.5375, + "step": 1102848 + }, + { + "epoch": 0.01, + "learning_rate": 3.193625959224641e-05, + "loss": 3.5294, + "step": 1103360 + }, + { + "epoch": 0.01, + "learning_rate": 3.192787364473589e-05, + "loss": 3.5452, + "step": 1103872 + }, + { + "epoch": 0.01, + "learning_rate": 3.191948769722536e-05, + "loss": 3.5512, + "step": 1104384 + }, + { + "epoch": 0.01, + "learning_rate": 3.191111812851858e-05, + "loss": 3.5612, + "step": 1104896 + }, + { + "epoch": 0.01, + "learning_rate": 3.190273218100806e-05, + "loss": 3.5458, + "step": 1105408 + }, + { + "epoch": 0.01, + "learning_rate": 3.189434623349754e-05, + "loss": 3.5569, + "step": 1105920 + }, + { + "epoch": 0.01, + "learning_rate": 3.188596028598702e-05, + "loss": 3.555, + "step": 1106432 + }, + { + "epoch": 0.01, + "learning_rate": 3.187759071728023e-05, + "loss": 3.5477, + "step": 1106944 + }, + { + "epoch": 0.01, + "learning_rate": 3.186920476976971e-05, + "loss": 3.5461, + "step": 1107456 + }, + { + "epoch": 0.01, + "learning_rate": 3.1860818822259186e-05, + "loss": 3.5476, + "step": 1107968 + }, + { + "epoch": 0.01, + "learning_rate": 3.1852432874748666e-05, + "loss": 3.5455, + "step": 1108480 + }, + { + "epoch": 0.01, + "learning_rate": 3.184406330604188e-05, + "loss": 3.5431, + "step": 1108992 + }, + { + "epoch": 0.01, + "learning_rate": 3.183567735853136e-05, + "loss": 3.5448, + "step": 1109504 + }, + { + "epoch": 0.01, + "learning_rate": 3.1827291411020835e-05, + "loss": 3.5552, + "step": 1110016 + }, + { + "epoch": 0.01, + "learning_rate": 3.1818905463510315e-05, + "loss": 3.5557, + "step": 1110528 + }, + { + "epoch": 0.01, + "learning_rate": 3.181053589480353e-05, + "loss": 3.5483, + "step": 1111040 + }, + { + "epoch": 0.01, + "learning_rate": 3.180214994729301e-05, + "loss": 3.533, + "step": 1111552 + }, + { + "epoch": 0.01, + "learning_rate": 3.179376399978249e-05, + "loss": 3.5471, + "step": 1112064 + }, + { + "epoch": 0.01, + "learning_rate": 3.178537805227197e-05, + "loss": 3.5476, + "step": 1112576 + }, + { + "epoch": 0.01, + "learning_rate": 3.1777008483565187e-05, + "loss": 3.5464, + "step": 1113088 + }, + { + "epoch": 0.01, + "learning_rate": 3.176862253605466e-05, + "loss": 3.5416, + "step": 1113600 + }, + { + "epoch": 0.01, + "learning_rate": 3.176023658854414e-05, + "loss": 3.5478, + "step": 1114112 + }, + { + "epoch": 0.02, + "learning_rate": 3.175185064103362e-05, + "loss": 3.5507, + "step": 1114624 + }, + { + "epoch": 0.02, + "learning_rate": 3.1743481072326835e-05, + "loss": 3.5398, + "step": 1115136 + }, + { + "epoch": 0.02, + "learning_rate": 3.173509512481631e-05, + "loss": 3.5439, + "step": 1115648 + }, + { + "epoch": 0.02, + "learning_rate": 3.172670917730579e-05, + "loss": 3.5484, + "step": 1116160 + }, + { + "epoch": 0.02, + "learning_rate": 3.171832322979527e-05, + "loss": 3.5511, + "step": 1116672 + }, + { + "epoch": 0.02, + "learning_rate": 3.1709953661088484e-05, + "loss": 3.556, + "step": 1117184 + }, + { + "epoch": 0.02, + "learning_rate": 3.1701567713577964e-05, + "loss": 3.5324, + "step": 1117696 + }, + { + "epoch": 0.02, + "learning_rate": 3.1693181766067444e-05, + "loss": 3.5482, + "step": 1118208 + }, + { + "epoch": 0.02, + "learning_rate": 3.1684795818556924e-05, + "loss": 3.5459, + "step": 1118720 + }, + { + "epoch": 0.02, + "learning_rate": 3.1676426249850133e-05, + "loss": 3.5434, + "step": 1119232 + }, + { + "epoch": 0.02, + "learning_rate": 3.166804030233961e-05, + "loss": 3.5595, + "step": 1119744 + }, + { + "epoch": 0.02, + "learning_rate": 3.165965435482909e-05, + "loss": 3.5439, + "step": 1120256 + }, + { + "epoch": 0.02, + "learning_rate": 3.165126840731857e-05, + "loss": 3.5347, + "step": 1120768 + }, + { + "epoch": 0.02, + "learning_rate": 3.164289883861178e-05, + "loss": 3.5421, + "step": 1121280 + }, + { + "epoch": 0.02, + "learning_rate": 3.163451289110126e-05, + "loss": 3.5431, + "step": 1121792 + }, + { + "epoch": 0.02, + "learning_rate": 3.162612694359074e-05, + "loss": 3.5324, + "step": 1122304 + }, + { + "epoch": 0.02, + "learning_rate": 3.161774099608022e-05, + "loss": 3.5413, + "step": 1122816 + }, + { + "epoch": 0.02, + "learning_rate": 3.160937142737344e-05, + "loss": 3.5447, + "step": 1123328 + }, + { + "epoch": 0.02, + "learning_rate": 3.160098547986292e-05, + "loss": 3.5397, + "step": 1123840 + }, + { + "epoch": 0.02, + "learning_rate": 3.1592615911156134e-05, + "loss": 3.5346, + "step": 1124352 + }, + { + "epoch": 0.02, + "learning_rate": 3.158422996364561e-05, + "loss": 3.5451, + "step": 1124864 + }, + { + "epoch": 0.02, + "learning_rate": 3.157584401613509e-05, + "loss": 3.5322, + "step": 1125376 + }, + { + "epoch": 0.02, + "learning_rate": 3.156745806862457e-05, + "loss": 3.5543, + "step": 1125888 + }, + { + "epoch": 0.02, + "learning_rate": 3.155907212111405e-05, + "loss": 3.5405, + "step": 1126400 + }, + { + "epoch": 0.02, + "learning_rate": 3.155068617360353e-05, + "loss": 3.5488, + "step": 1126912 + }, + { + "epoch": 0.02, + "learning_rate": 3.154230022609301e-05, + "loss": 3.5524, + "step": 1127424 + }, + { + "epoch": 0.02, + "learning_rate": 3.1533930657386216e-05, + "loss": 3.5666, + "step": 1127936 + }, + { + "epoch": 0.02, + "learning_rate": 3.1525544709875696e-05, + "loss": 3.5439, + "step": 1128448 + }, + { + "epoch": 0.02, + "learning_rate": 3.1517158762365176e-05, + "loss": 3.5389, + "step": 1128960 + }, + { + "epoch": 0.02, + "learning_rate": 3.1508772814854656e-05, + "loss": 3.5478, + "step": 1129472 + }, + { + "epoch": 0.02, + "learning_rate": 3.150038686734414e-05, + "loss": 3.5407, + "step": 1129984 + }, + { + "epoch": 0.02, + "learning_rate": 3.149200091983362e-05, + "loss": 3.5427, + "step": 1130496 + }, + { + "epoch": 0.02, + "learning_rate": 3.14836149723231e-05, + "loss": 3.5453, + "step": 1131008 + }, + { + "epoch": 0.02, + "learning_rate": 3.147524540361631e-05, + "loss": 3.5443, + "step": 1131520 + }, + { + "epoch": 0.02, + "learning_rate": 3.146685945610579e-05, + "loss": 3.5539, + "step": 1132032 + }, + { + "epoch": 0.02, + "learning_rate": 3.145847350859527e-05, + "loss": 3.5444, + "step": 1132544 + }, + { + "epoch": 0.02, + "learning_rate": 3.145010393988848e-05, + "loss": 3.54, + "step": 1133056 + }, + { + "epoch": 0.02, + "learning_rate": 3.144171799237796e-05, + "loss": 3.5421, + "step": 1133568 + }, + { + "epoch": 0.02, + "learning_rate": 3.143333204486744e-05, + "loss": 3.5495, + "step": 1134080 + }, + { + "epoch": 0.02, + "learning_rate": 3.142494609735692e-05, + "loss": 3.5417, + "step": 1134592 + }, + { + "epoch": 0.02, + "learning_rate": 3.14165601498464e-05, + "loss": 3.5464, + "step": 1135104 + }, + { + "epoch": 0.02, + "learning_rate": 3.140817420233588e-05, + "loss": 3.5499, + "step": 1135616 + }, + { + "epoch": 0.02, + "learning_rate": 3.139978825482536e-05, + "loss": 3.5379, + "step": 1136128 + }, + { + "epoch": 0.02, + "learning_rate": 3.1391418686118576e-05, + "loss": 3.5427, + "step": 1136640 + }, + { + "epoch": 0.02, + "learning_rate": 3.1383049117411785e-05, + "loss": 3.5452, + "step": 1137152 + }, + { + "epoch": 0.02, + "learning_rate": 3.1374663169901265e-05, + "loss": 3.5482, + "step": 1137664 + }, + { + "epoch": 0.02, + "learning_rate": 3.1366277222390745e-05, + "loss": 3.538, + "step": 1138176 + }, + { + "epoch": 0.02, + "learning_rate": 3.1357891274880225e-05, + "loss": 3.5446, + "step": 1138688 + }, + { + "epoch": 0.02, + "learning_rate": 3.1349505327369705e-05, + "loss": 3.5536, + "step": 1139200 + }, + { + "epoch": 0.02, + "learning_rate": 3.1341119379859185e-05, + "loss": 3.5555, + "step": 1139712 + }, + { + "epoch": 0.02, + "learning_rate": 3.1332733432348665e-05, + "loss": 3.5432, + "step": 1140224 + }, + { + "epoch": 0.02, + "learning_rate": 3.132434748483814e-05, + "loss": 3.5446, + "step": 1140736 + }, + { + "epoch": 0.02, + "learning_rate": 3.1315977916131354e-05, + "loss": 3.5395, + "step": 1141248 + }, + { + "epoch": 0.02, + "learning_rate": 3.1307591968620834e-05, + "loss": 3.5457, + "step": 1141760 + }, + { + "epoch": 0.02, + "learning_rate": 3.1299206021110314e-05, + "loss": 3.5322, + "step": 1142272 + }, + { + "epoch": 0.02, + "learning_rate": 3.1290820073599794e-05, + "loss": 3.5552, + "step": 1142784 + }, + { + "epoch": 0.02, + "learning_rate": 3.128245050489301e-05, + "loss": 3.543, + "step": 1143296 + }, + { + "epoch": 0.02, + "learning_rate": 3.127406455738249e-05, + "loss": 3.5494, + "step": 1143808 + }, + { + "epoch": 0.02, + "learning_rate": 3.126567860987197e-05, + "loss": 3.5363, + "step": 1144320 + }, + { + "epoch": 0.03, + "eval_loss": 3.8431458473205566, + "eval_runtime": 306.0361, + "eval_samples_per_second": 1246.882, + "eval_steps_per_second": 38.966, + "step": 1144800 + }, + { + "epoch": 1.0, + "learning_rate": 3.125729266236144e-05, + "loss": 3.5427, + "step": 1144832 + }, + { + "epoch": 1.0, + "learning_rate": 3.124892309365466e-05, + "loss": 3.5323, + "step": 1145344 + }, + { + "epoch": 1.0, + "learning_rate": 3.124053714614414e-05, + "loss": 3.5441, + "step": 1145856 + }, + { + "epoch": 1.0, + "learning_rate": 3.123215119863361e-05, + "loss": 3.5447, + "step": 1146368 + }, + { + "epoch": 1.0, + "learning_rate": 3.122378162992683e-05, + "loss": 3.5445, + "step": 1146880 + }, + { + "epoch": 1.0, + "learning_rate": 3.121539568241631e-05, + "loss": 3.5447, + "step": 1147392 + }, + { + "epoch": 1.0, + "learning_rate": 3.120700973490579e-05, + "loss": 3.5376, + "step": 1147904 + }, + { + "epoch": 1.0, + "learning_rate": 3.119862378739527e-05, + "loss": 3.5385, + "step": 1148416 + }, + { + "epoch": 1.0, + "learning_rate": 3.1190254218688484e-05, + "loss": 3.5414, + "step": 1148928 + }, + { + "epoch": 1.0, + "learning_rate": 3.1181868271177964e-05, + "loss": 3.5405, + "step": 1149440 + }, + { + "epoch": 1.0, + "learning_rate": 3.1173482323667443e-05, + "loss": 3.5383, + "step": 1149952 + }, + { + "epoch": 1.0, + "learning_rate": 3.116509637615692e-05, + "loss": 3.5485, + "step": 1150464 + }, + { + "epoch": 1.0, + "learning_rate": 3.115674318625386e-05, + "loss": 3.5528, + "step": 1150976 + }, + { + "epoch": 1.0, + "learning_rate": 3.114835723874334e-05, + "loss": 3.5325, + "step": 1151488 + }, + { + "epoch": 1.0, + "learning_rate": 3.113997129123282e-05, + "loss": 3.5388, + "step": 1152000 + }, + { + "epoch": 1.0, + "learning_rate": 3.11315853437223e-05, + "loss": 3.5298, + "step": 1152512 + }, + { + "epoch": 1.0, + "learning_rate": 3.112319939621178e-05, + "loss": 3.5419, + "step": 1153024 + }, + { + "epoch": 1.0, + "learning_rate": 3.111481344870126e-05, + "loss": 3.5282, + "step": 1153536 + }, + { + "epoch": 1.0, + "learning_rate": 3.110642750119074e-05, + "loss": 3.5366, + "step": 1154048 + }, + { + "epoch": 1.0, + "learning_rate": 3.109804155368022e-05, + "loss": 3.537, + "step": 1154560 + }, + { + "epoch": 1.0, + "learning_rate": 3.108967198497344e-05, + "loss": 3.5485, + "step": 1155072 + }, + { + "epoch": 1.0, + "learning_rate": 3.108128603746292e-05, + "loss": 3.5391, + "step": 1155584 + }, + { + "epoch": 1.0, + "learning_rate": 3.107290008995239e-05, + "loss": 3.541, + "step": 1156096 + }, + { + "epoch": 1.0, + "learning_rate": 3.106451414244187e-05, + "loss": 3.5454, + "step": 1156608 + }, + { + "epoch": 1.0, + "learning_rate": 3.1056144573735086e-05, + "loss": 3.5436, + "step": 1157120 + }, + { + "epoch": 1.0, + "learning_rate": 3.104775862622456e-05, + "loss": 3.5356, + "step": 1157632 + }, + { + "epoch": 1.0, + "learning_rate": 3.103937267871404e-05, + "loss": 3.5316, + "step": 1158144 + }, + { + "epoch": 1.0, + "learning_rate": 3.103098673120352e-05, + "loss": 3.5398, + "step": 1158656 + }, + { + "epoch": 1.0, + "learning_rate": 3.1022617162496735e-05, + "loss": 3.5308, + "step": 1159168 + }, + { + "epoch": 1.0, + "learning_rate": 3.101423121498621e-05, + "loss": 3.533, + "step": 1159680 + }, + { + "epoch": 1.01, + "learning_rate": 3.1005861646279424e-05, + "loss": 3.5382, + "step": 1160192 + }, + { + "epoch": 1.01, + "learning_rate": 3.0997475698768904e-05, + "loss": 3.5343, + "step": 1160704 + }, + { + "epoch": 1.01, + "learning_rate": 3.0989089751258384e-05, + "loss": 3.5435, + "step": 1161216 + }, + { + "epoch": 1.01, + "learning_rate": 3.0980703803747864e-05, + "loss": 3.5353, + "step": 1161728 + }, + { + "epoch": 1.01, + "learning_rate": 3.0972317856237344e-05, + "loss": 3.5381, + "step": 1162240 + }, + { + "epoch": 1.01, + "learning_rate": 3.0963931908726824e-05, + "loss": 3.5464, + "step": 1162752 + }, + { + "epoch": 1.01, + "learning_rate": 3.0955545961216304e-05, + "loss": 3.5394, + "step": 1163264 + }, + { + "epoch": 1.01, + "learning_rate": 3.094717639250951e-05, + "loss": 3.5194, + "step": 1163776 + }, + { + "epoch": 1.01, + "learning_rate": 3.093879044499899e-05, + "loss": 3.5424, + "step": 1164288 + }, + { + "epoch": 1.01, + "learning_rate": 3.093040449748847e-05, + "loss": 3.5293, + "step": 1164800 + }, + { + "epoch": 1.01, + "learning_rate": 3.092201854997795e-05, + "loss": 3.5229, + "step": 1165312 + }, + { + "epoch": 1.01, + "learning_rate": 3.091364898127116e-05, + "loss": 3.5376, + "step": 1165824 + }, + { + "epoch": 1.01, + "learning_rate": 3.090526303376064e-05, + "loss": 3.548, + "step": 1166336 + }, + { + "epoch": 1.01, + "learning_rate": 3.089687708625013e-05, + "loss": 3.5373, + "step": 1166848 + }, + { + "epoch": 1.01, + "learning_rate": 3.088849113873961e-05, + "loss": 3.5407, + "step": 1167360 + }, + { + "epoch": 1.01, + "learning_rate": 3.088012157003282e-05, + "loss": 3.5439, + "step": 1167872 + }, + { + "epoch": 1.01, + "learning_rate": 3.08717356225223e-05, + "loss": 3.5407, + "step": 1168384 + }, + { + "epoch": 1.01, + "learning_rate": 3.086334967501178e-05, + "loss": 3.5361, + "step": 1168896 + }, + { + "epoch": 1.01, + "learning_rate": 3.085496372750126e-05, + "loss": 3.5188, + "step": 1169408 + }, + { + "epoch": 1.01, + "learning_rate": 3.084659415879447e-05, + "loss": 3.5382, + "step": 1169920 + }, + { + "epoch": 1.01, + "learning_rate": 3.083820821128395e-05, + "loss": 3.539, + "step": 1170432 + }, + { + "epoch": 1.01, + "learning_rate": 3.0829822263773427e-05, + "loss": 3.5337, + "step": 1170944 + }, + { + "epoch": 1.01, + "learning_rate": 3.0821436316262907e-05, + "loss": 3.53, + "step": 1171456 + }, + { + "epoch": 1.01, + "learning_rate": 3.0813066747556116e-05, + "loss": 3.5273, + "step": 1171968 + }, + { + "epoch": 1.01, + "learning_rate": 3.0804680800045596e-05, + "loss": 3.5273, + "step": 1172480 + }, + { + "epoch": 1.01, + "learning_rate": 3.079629485253508e-05, + "loss": 3.5205, + "step": 1172992 + }, + { + "epoch": 1.01, + "learning_rate": 3.078792528382829e-05, + "loss": 3.5453, + "step": 1173504 + }, + { + "epoch": 1.01, + "learning_rate": 3.077953933631777e-05, + "loss": 3.5204, + "step": 1174016 + }, + { + "epoch": 1.01, + "learning_rate": 3.077115338880725e-05, + "loss": 3.5404, + "step": 1174528 + }, + { + "epoch": 1.01, + "learning_rate": 3.076276744129673e-05, + "loss": 3.5338, + "step": 1175040 + }, + { + "epoch": 1.01, + "learning_rate": 3.075438149378621e-05, + "loss": 3.5204, + "step": 1175552 + }, + { + "epoch": 1.01, + "learning_rate": 3.074599554627569e-05, + "loss": 3.5344, + "step": 1176064 + }, + { + "epoch": 1.01, + "learning_rate": 3.073760959876517e-05, + "loss": 3.5293, + "step": 1176576 + }, + { + "epoch": 1.01, + "learning_rate": 3.072924003005838e-05, + "loss": 3.5271, + "step": 1177088 + }, + { + "epoch": 1.01, + "learning_rate": 3.072085408254786e-05, + "loss": 3.521, + "step": 1177600 + }, + { + "epoch": 1.01, + "learning_rate": 3.071246813503734e-05, + "loss": 3.549, + "step": 1178112 + }, + { + "epoch": 1.01, + "learning_rate": 3.070408218752682e-05, + "loss": 3.5289, + "step": 1178624 + }, + { + "epoch": 1.01, + "learning_rate": 3.06956962400163e-05, + "loss": 3.525, + "step": 1179136 + }, + { + "epoch": 1.01, + "learning_rate": 3.068731029250578e-05, + "loss": 3.5139, + "step": 1179648 + }, + { + "epoch": 1.01, + "learning_rate": 3.067892434499527e-05, + "loss": 3.5293, + "step": 1180160 + }, + { + "epoch": 1.01, + "learning_rate": 3.067053839748475e-05, + "loss": 3.5364, + "step": 1180672 + }, + { + "epoch": 1.01, + "learning_rate": 3.0662168828777956e-05, + "loss": 3.544, + "step": 1181184 + }, + { + "epoch": 1.01, + "learning_rate": 3.0653782881267436e-05, + "loss": 3.5308, + "step": 1181696 + }, + { + "epoch": 1.01, + "learning_rate": 3.0645413312560645e-05, + "loss": 3.5396, + "step": 1182208 + }, + { + "epoch": 1.01, + "learning_rate": 3.0637027365050125e-05, + "loss": 3.5405, + "step": 1182720 + }, + { + "epoch": 1.01, + "learning_rate": 3.0628641417539605e-05, + "loss": 3.5328, + "step": 1183232 + }, + { + "epoch": 1.01, + "learning_rate": 3.0620255470029085e-05, + "loss": 3.5321, + "step": 1183744 + }, + { + "epoch": 1.01, + "learning_rate": 3.0611869522518565e-05, + "loss": 3.5341, + "step": 1184256 + }, + { + "epoch": 1.01, + "learning_rate": 3.0603483575008045e-05, + "loss": 3.5316, + "step": 1184768 + }, + { + "epoch": 1.01, + "learning_rate": 3.059509762749752e-05, + "loss": 3.5306, + "step": 1185280 + }, + { + "epoch": 1.01, + "learning_rate": 3.0586711679987005e-05, + "loss": 3.5283, + "step": 1185792 + }, + { + "epoch": 1.01, + "learning_rate": 3.057834211128022e-05, + "loss": 3.5397, + "step": 1186304 + }, + { + "epoch": 1.01, + "learning_rate": 3.0569956163769694e-05, + "loss": 3.5376, + "step": 1186816 + }, + { + "epoch": 1.01, + "learning_rate": 3.0561570216259174e-05, + "loss": 3.5346, + "step": 1187328 + }, + { + "epoch": 1.01, + "learning_rate": 3.0553184268748654e-05, + "loss": 3.5198, + "step": 1187840 + }, + { + "epoch": 1.01, + "learning_rate": 3.054481470004187e-05, + "loss": 3.5302, + "step": 1188352 + }, + { + "epoch": 1.01, + "learning_rate": 3.053642875253134e-05, + "loss": 3.5361, + "step": 1188864 + }, + { + "epoch": 1.01, + "learning_rate": 3.052804280502082e-05, + "loss": 3.5332, + "step": 1189376 + }, + { + "epoch": 1.01, + "learning_rate": 3.05196568575103e-05, + "loss": 3.5266, + "step": 1189888 + }, + { + "epoch": 1.01, + "learning_rate": 3.051128728880352e-05, + "loss": 3.5324, + "step": 1190400 + }, + { + "epoch": 1.02, + "learning_rate": 3.0502901341292995e-05, + "loss": 3.5376, + "step": 1190912 + }, + { + "epoch": 1.02, + "learning_rate": 3.0494515393782475e-05, + "loss": 3.522, + "step": 1191424 + }, + { + "epoch": 1.02, + "learning_rate": 3.0486129446271955e-05, + "loss": 3.5305, + "step": 1191936 + }, + { + "epoch": 1.02, + "learning_rate": 3.0477759877565164e-05, + "loss": 3.5338, + "step": 1192448 + }, + { + "epoch": 1.02, + "learning_rate": 3.0469373930054644e-05, + "loss": 3.534, + "step": 1192960 + }, + { + "epoch": 1.02, + "learning_rate": 3.0460987982544127e-05, + "loss": 3.5399, + "step": 1193472 + }, + { + "epoch": 1.02, + "learning_rate": 3.0452602035033607e-05, + "loss": 3.5251, + "step": 1193984 + }, + { + "epoch": 1.02, + "learning_rate": 3.0444216087523087e-05, + "loss": 3.5281, + "step": 1194496 + }, + { + "epoch": 1.02, + "learning_rate": 3.0435830140012567e-05, + "loss": 3.5311, + "step": 1195008 + }, + { + "epoch": 1.02, + "learning_rate": 3.0427444192502047e-05, + "loss": 3.5322, + "step": 1195520 + }, + { + "epoch": 1.02, + "learning_rate": 3.0419058244991527e-05, + "loss": 3.5408, + "step": 1196032 + }, + { + "epoch": 1.02, + "learning_rate": 3.0410688676284736e-05, + "loss": 3.5323, + "step": 1196544 + }, + { + "epoch": 1.02, + "learning_rate": 3.040230272877422e-05, + "loss": 3.5201, + "step": 1197056 + }, + { + "epoch": 1.02, + "learning_rate": 3.03939167812637e-05, + "loss": 3.5247, + "step": 1197568 + }, + { + "epoch": 1.02, + "learning_rate": 3.038553083375318e-05, + "loss": 3.5348, + "step": 1198080 + }, + { + "epoch": 1.02, + "learning_rate": 3.037716126504639e-05, + "loss": 3.5094, + "step": 1198592 + }, + { + "epoch": 1.02, + "learning_rate": 3.036877531753587e-05, + "loss": 3.5276, + "step": 1199104 + }, + { + "epoch": 1.02, + "learning_rate": 3.036038937002535e-05, + "loss": 3.535, + "step": 1199616 + }, + { + "epoch": 1.02, + "learning_rate": 3.035200342251483e-05, + "loss": 3.522, + "step": 1200128 + }, + { + "epoch": 1.02, + "learning_rate": 3.034365023261177e-05, + "loss": 3.5215, + "step": 1200640 + }, + { + "epoch": 1.02, + "learning_rate": 3.033526428510125e-05, + "loss": 3.533, + "step": 1201152 + }, + { + "epoch": 1.02, + "learning_rate": 3.032687833759073e-05, + "loss": 3.517, + "step": 1201664 + }, + { + "epoch": 1.02, + "learning_rate": 3.031849239008021e-05, + "loss": 3.5404, + "step": 1202176 + }, + { + "epoch": 1.02, + "learning_rate": 3.031010644256969e-05, + "loss": 3.5246, + "step": 1202688 + }, + { + "epoch": 1.02, + "learning_rate": 3.0301720495059173e-05, + "loss": 3.5327, + "step": 1203200 + }, + { + "epoch": 1.02, + "learning_rate": 3.0293334547548653e-05, + "loss": 3.539, + "step": 1203712 + }, + { + "epoch": 1.02, + "learning_rate": 3.0284948600038133e-05, + "loss": 3.5513, + "step": 1204224 + }, + { + "epoch": 1.02, + "learning_rate": 3.0276579031331342e-05, + "loss": 3.5318, + "step": 1204736 + }, + { + "epoch": 1.02, + "learning_rate": 3.0268193083820822e-05, + "loss": 3.5223, + "step": 1205248 + }, + { + "epoch": 1.02, + "learning_rate": 3.0259807136310302e-05, + "loss": 3.5349, + "step": 1205760 + }, + { + "epoch": 1.02, + "learning_rate": 3.0251437567603515e-05, + "loss": 3.5259, + "step": 1206272 + }, + { + "epoch": 1.02, + "learning_rate": 3.0243051620092994e-05, + "loss": 3.5269, + "step": 1206784 + }, + { + "epoch": 1.02, + "learning_rate": 3.0234665672582474e-05, + "loss": 3.5297, + "step": 1207296 + }, + { + "epoch": 1.02, + "learning_rate": 3.0226279725071954e-05, + "loss": 3.5296, + "step": 1207808 + }, + { + "epoch": 1.02, + "learning_rate": 3.0217893777561434e-05, + "loss": 3.5402, + "step": 1208320 + }, + { + "epoch": 1.02, + "learning_rate": 3.0209507830050914e-05, + "loss": 3.53, + "step": 1208832 + }, + { + "epoch": 1.02, + "learning_rate": 3.0201138261344127e-05, + "loss": 3.5253, + "step": 1209344 + }, + { + "epoch": 1.02, + "learning_rate": 3.0192752313833607e-05, + "loss": 3.5284, + "step": 1209856 + }, + { + "epoch": 1.02, + "learning_rate": 3.0184366366323087e-05, + "loss": 3.531, + "step": 1210368 + }, + { + "epoch": 1.02, + "learning_rate": 3.0175980418812567e-05, + "loss": 3.5273, + "step": 1210880 + }, + { + "epoch": 1.02, + "learning_rate": 3.0167594471302047e-05, + "loss": 3.5324, + "step": 1211392 + }, + { + "epoch": 1.02, + "learning_rate": 3.0159208523791527e-05, + "loss": 3.5366, + "step": 1211904 + }, + { + "epoch": 1.02, + "learning_rate": 3.0150822576281003e-05, + "loss": 3.5261, + "step": 1212416 + }, + { + "epoch": 1.02, + "learning_rate": 3.0142453007574216e-05, + "loss": 3.5218, + "step": 1212928 + }, + { + "epoch": 1.02, + "learning_rate": 3.01340670600637e-05, + "loss": 3.5346, + "step": 1213440 + }, + { + "epoch": 1.02, + "learning_rate": 3.012568111255318e-05, + "loss": 3.5311, + "step": 1213952 + }, + { + "epoch": 1.02, + "learning_rate": 3.0117295165042652e-05, + "loss": 3.5284, + "step": 1214464 + }, + { + "epoch": 1.02, + "learning_rate": 3.0108925596335868e-05, + "loss": 3.5306, + "step": 1214976 + }, + { + "epoch": 1.02, + "learning_rate": 3.010055602762908e-05, + "loss": 3.5421, + "step": 1215488 + }, + { + "epoch": 1.02, + "learning_rate": 3.009217008011856e-05, + "loss": 3.5394, + "step": 1216000 + }, + { + "epoch": 1.02, + "learning_rate": 3.008378413260804e-05, + "loss": 3.5293, + "step": 1216512 + }, + { + "epoch": 1.02, + "learning_rate": 3.007539818509752e-05, + "loss": 3.5278, + "step": 1217024 + }, + { + "epoch": 1.02, + "learning_rate": 3.0067012237587e-05, + "loss": 3.5274, + "step": 1217536 + }, + { + "epoch": 1.02, + "learning_rate": 3.005864266888021e-05, + "loss": 3.5322, + "step": 1218048 + }, + { + "epoch": 1.02, + "learning_rate": 3.005025672136969e-05, + "loss": 3.5156, + "step": 1218560 + }, + { + "epoch": 1.02, + "learning_rate": 3.004187077385917e-05, + "loss": 3.5397, + "step": 1219072 + }, + { + "epoch": 1.02, + "learning_rate": 3.0033484826348653e-05, + "loss": 3.5362, + "step": 1219584 + }, + { + "epoch": 1.02, + "learning_rate": 3.0025098878838126e-05, + "loss": 3.5325, + "step": 1220096 + }, + { + "epoch": 1.02, + "learning_rate": 3.0016712931327606e-05, + "loss": 3.5205, + "step": 1220608 + }, + { + "epoch": 1.03, + "learning_rate": 3.0008326983817086e-05, + "loss": 3.5302, + "step": 1221120 + }, + { + "epoch": 1.03, + "eval_loss": 3.8464837074279785, + "eval_runtime": 304.6007, + "eval_samples_per_second": 1252.758, + "eval_steps_per_second": 39.15, + "step": 1221120 + }, + { + "epoch": 0.0, + "learning_rate": 2.9999941036306566e-05, + "loss": 3.5167, + "step": 1221632 + }, + { + "epoch": 0.0, + "learning_rate": 2.9991555088796046e-05, + "loss": 3.526, + "step": 1222144 + }, + { + "epoch": 0.0, + "learning_rate": 2.998316914128553e-05, + "loss": 3.5315, + "step": 1222656 + }, + { + "epoch": 0.0, + "learning_rate": 2.9974799572578738e-05, + "loss": 3.5313, + "step": 1223168 + }, + { + "epoch": 0.0, + "learning_rate": 2.9966413625068218e-05, + "loss": 3.5322, + "step": 1223680 + }, + { + "epoch": 0.0, + "learning_rate": 2.9958027677557698e-05, + "loss": 3.5213, + "step": 1224192 + }, + { + "epoch": 0.0, + "learning_rate": 2.9949641730047178e-05, + "loss": 3.5265, + "step": 1224704 + }, + { + "epoch": 0.0, + "learning_rate": 2.994127216134039e-05, + "loss": 3.5211, + "step": 1225216 + }, + { + "epoch": 0.0, + "learning_rate": 2.99329025926336e-05, + "loss": 3.5321, + "step": 1225728 + }, + { + "epoch": 0.0, + "learning_rate": 2.992451664512308e-05, + "loss": 3.5174, + "step": 1226240 + }, + { + "epoch": 0.0, + "learning_rate": 2.991613069761256e-05, + "loss": 3.5373, + "step": 1226752 + }, + { + "epoch": 0.0, + "learning_rate": 2.990774475010204e-05, + "loss": 3.5428, + "step": 1227264 + }, + { + "epoch": 0.0, + "learning_rate": 2.989935880259152e-05, + "loss": 3.517, + "step": 1227776 + }, + { + "epoch": 0.0, + "learning_rate": 2.9890972855081e-05, + "loss": 3.5209, + "step": 1228288 + }, + { + "epoch": 0.0, + "learning_rate": 2.9882586907570483e-05, + "loss": 3.5152, + "step": 1228800 + }, + { + "epoch": 0.0, + "learning_rate": 2.9874200960059963e-05, + "loss": 3.525, + "step": 1229312 + }, + { + "epoch": 0.0, + "learning_rate": 2.9865831391353172e-05, + "loss": 3.5181, + "step": 1229824 + }, + { + "epoch": 0.0, + "learning_rate": 2.985744544384265e-05, + "loss": 3.5221, + "step": 1230336 + }, + { + "epoch": 0.0, + "learning_rate": 2.984905949633213e-05, + "loss": 3.5206, + "step": 1230848 + }, + { + "epoch": 0.0, + "learning_rate": 2.984067354882161e-05, + "loss": 3.5326, + "step": 1231360 + }, + { + "epoch": 0.0, + "learning_rate": 2.9832303980114824e-05, + "loss": 3.5252, + "step": 1231872 + }, + { + "epoch": 0.0, + "learning_rate": 2.9823918032604304e-05, + "loss": 3.5282, + "step": 1232384 + }, + { + "epoch": 0.0, + "learning_rate": 2.9815532085093784e-05, + "loss": 3.5297, + "step": 1232896 + }, + { + "epoch": 0.0, + "learning_rate": 2.9807146137583264e-05, + "loss": 3.5345, + "step": 1233408 + }, + { + "epoch": 0.0, + "learning_rate": 2.9798776568876473e-05, + "loss": 3.5189, + "step": 1233920 + }, + { + "epoch": 0.0, + "learning_rate": 2.9790390621365953e-05, + "loss": 3.5186, + "step": 1234432 + }, + { + "epoch": 0.0, + "learning_rate": 2.9782004673855436e-05, + "loss": 3.5261, + "step": 1234944 + }, + { + "epoch": 0.0, + "learning_rate": 2.9773618726344916e-05, + "loss": 3.5176, + "step": 1235456 + }, + { + "epoch": 0.0, + "learning_rate": 2.9765249157638125e-05, + "loss": 3.5199, + "step": 1235968 + }, + { + "epoch": 0.01, + "learning_rate": 2.9756879588931334e-05, + "loss": 3.519, + "step": 1236480 + }, + { + "epoch": 0.01, + "learning_rate": 2.9748493641420814e-05, + "loss": 3.5261, + "step": 1236992 + }, + { + "epoch": 0.01, + "learning_rate": 2.9740107693910298e-05, + "loss": 3.5298, + "step": 1237504 + }, + { + "epoch": 0.01, + "learning_rate": 2.9731721746399778e-05, + "loss": 3.52, + "step": 1238016 + }, + { + "epoch": 0.01, + "learning_rate": 2.9723335798889258e-05, + "loss": 3.5237, + "step": 1238528 + }, + { + "epoch": 0.01, + "learning_rate": 2.9714949851378738e-05, + "loss": 3.5341, + "step": 1239040 + }, + { + "epoch": 0.01, + "learning_rate": 2.9706563903868218e-05, + "loss": 3.524, + "step": 1239552 + }, + { + "epoch": 0.01, + "learning_rate": 2.9698194335161427e-05, + "loss": 3.5089, + "step": 1240064 + }, + { + "epoch": 0.01, + "learning_rate": 2.9689808387650907e-05, + "loss": 3.5277, + "step": 1240576 + }, + { + "epoch": 0.01, + "learning_rate": 2.968142244014039e-05, + "loss": 3.5127, + "step": 1241088 + }, + { + "epoch": 0.01, + "learning_rate": 2.967303649262987e-05, + "loss": 3.515, + "step": 1241600 + }, + { + "epoch": 0.01, + "learning_rate": 2.966466692392308e-05, + "loss": 3.5211, + "step": 1242112 + }, + { + "epoch": 0.01, + "learning_rate": 2.965628097641256e-05, + "loss": 3.5293, + "step": 1242624 + }, + { + "epoch": 0.01, + "learning_rate": 2.964789502890204e-05, + "loss": 3.5255, + "step": 1243136 + }, + { + "epoch": 0.01, + "learning_rate": 2.963950908139152e-05, + "loss": 3.5258, + "step": 1243648 + }, + { + "epoch": 0.01, + "learning_rate": 2.963113951268473e-05, + "loss": 3.5299, + "step": 1244160 + }, + { + "epoch": 0.01, + "learning_rate": 2.962275356517421e-05, + "loss": 3.5255, + "step": 1244672 + }, + { + "epoch": 0.01, + "learning_rate": 2.961436761766369e-05, + "loss": 3.5231, + "step": 1245184 + }, + { + "epoch": 0.01, + "learning_rate": 2.960598167015317e-05, + "loss": 3.5036, + "step": 1245696 + }, + { + "epoch": 0.01, + "learning_rate": 2.959761210144638e-05, + "loss": 3.5218, + "step": 1246208 + }, + { + "epoch": 0.01, + "learning_rate": 2.958922615393586e-05, + "loss": 3.5253, + "step": 1246720 + }, + { + "epoch": 0.01, + "learning_rate": 2.9580840206425344e-05, + "loss": 3.5191, + "step": 1247232 + }, + { + "epoch": 0.01, + "learning_rate": 2.9572454258914824e-05, + "loss": 3.5138, + "step": 1247744 + }, + { + "epoch": 0.01, + "learning_rate": 2.9564084690208033e-05, + "loss": 3.5125, + "step": 1248256 + }, + { + "epoch": 0.01, + "learning_rate": 2.9555698742697513e-05, + "loss": 3.5166, + "step": 1248768 + }, + { + "epoch": 0.01, + "learning_rate": 2.9547312795186993e-05, + "loss": 3.5051, + "step": 1249280 + }, + { + "epoch": 0.01, + "learning_rate": 2.9538943226480205e-05, + "loss": 3.5292, + "step": 1249792 + }, + { + "epoch": 0.01, + "learning_rate": 2.9530557278969685e-05, + "loss": 3.5105, + "step": 1250304 + }, + { + "epoch": 0.01, + "learning_rate": 2.9522171331459165e-05, + "loss": 3.5278, + "step": 1250816 + }, + { + "epoch": 0.01, + "learning_rate": 2.9513785383948645e-05, + "loss": 3.5196, + "step": 1251328 + }, + { + "epoch": 0.01, + "learning_rate": 2.9505399436438125e-05, + "loss": 3.5043, + "step": 1251840 + }, + { + "epoch": 0.01, + "learning_rate": 2.9497013488927605e-05, + "loss": 3.5245, + "step": 1252352 + }, + { + "epoch": 0.01, + "learning_rate": 2.948862754141708e-05, + "loss": 3.517, + "step": 1252864 + }, + { + "epoch": 0.01, + "learning_rate": 2.9480257972710297e-05, + "loss": 3.5119, + "step": 1253376 + }, + { + "epoch": 0.01, + "learning_rate": 2.9471872025199777e-05, + "loss": 3.5071, + "step": 1253888 + }, + { + "epoch": 0.01, + "learning_rate": 2.9463486077689257e-05, + "loss": 3.5299, + "step": 1254400 + }, + { + "epoch": 0.01, + "learning_rate": 2.945510013017873e-05, + "loss": 3.5178, + "step": 1254912 + }, + { + "epoch": 0.01, + "learning_rate": 2.944671418266821e-05, + "loss": 3.5108, + "step": 1255424 + }, + { + "epoch": 0.01, + "learning_rate": 2.943832823515769e-05, + "loss": 3.5019, + "step": 1255936 + }, + { + "epoch": 0.01, + "learning_rate": 2.9429942287647174e-05, + "loss": 3.5144, + "step": 1256448 + }, + { + "epoch": 0.01, + "learning_rate": 2.9421556340136654e-05, + "loss": 3.5219, + "step": 1256960 + }, + { + "epoch": 0.01, + "learning_rate": 2.9413186771429863e-05, + "loss": 3.5309, + "step": 1257472 + }, + { + "epoch": 0.01, + "learning_rate": 2.9404800823919343e-05, + "loss": 3.5154, + "step": 1257984 + }, + { + "epoch": 0.01, + "learning_rate": 2.9396414876408823e-05, + "loss": 3.5294, + "step": 1258496 + }, + { + "epoch": 0.01, + "learning_rate": 2.9388028928898303e-05, + "loss": 3.5267, + "step": 1259008 + }, + { + "epoch": 0.01, + "learning_rate": 2.9379659360191515e-05, + "loss": 3.5206, + "step": 1259520 + }, + { + "epoch": 0.01, + "learning_rate": 2.937128979148473e-05, + "loss": 3.5152, + "step": 1260032 + }, + { + "epoch": 0.01, + "learning_rate": 2.9362903843974204e-05, + "loss": 3.5215, + "step": 1260544 + }, + { + "epoch": 0.01, + "learning_rate": 2.9354517896463684e-05, + "loss": 3.5176, + "step": 1261056 + }, + { + "epoch": 0.01, + "learning_rate": 2.9346131948953164e-05, + "loss": 3.5165, + "step": 1261568 + }, + { + "epoch": 0.01, + "learning_rate": 2.9337746001442644e-05, + "loss": 3.5164, + "step": 1262080 + }, + { + "epoch": 0.01, + "learning_rate": 2.9329360053932124e-05, + "loss": 3.5215, + "step": 1262592 + }, + { + "epoch": 0.01, + "learning_rate": 2.9320974106421607e-05, + "loss": 3.5263, + "step": 1263104 + }, + { + "epoch": 0.01, + "learning_rate": 2.9312588158911087e-05, + "loss": 3.5215, + "step": 1263616 + }, + { + "epoch": 0.01, + "learning_rate": 2.9304218590204296e-05, + "loss": 3.5113, + "step": 1264128 + }, + { + "epoch": 0.01, + "learning_rate": 2.9295832642693776e-05, + "loss": 3.5132, + "step": 1264640 + }, + { + "epoch": 0.01, + "learning_rate": 2.9287446695183256e-05, + "loss": 3.5235, + "step": 1265152 + }, + { + "epoch": 0.01, + "learning_rate": 2.9279060747672736e-05, + "loss": 3.518, + "step": 1265664 + }, + { + "epoch": 0.01, + "learning_rate": 2.927069117896595e-05, + "loss": 3.5137, + "step": 1266176 + }, + { + "epoch": 0.01, + "learning_rate": 2.926230523145543e-05, + "loss": 3.5174, + "step": 1266688 + }, + { + "epoch": 0.02, + "learning_rate": 2.925391928394491e-05, + "loss": 3.5248, + "step": 1267200 + }, + { + "epoch": 0.02, + "learning_rate": 2.924553333643439e-05, + "loss": 3.5093, + "step": 1267712 + }, + { + "epoch": 0.02, + "learning_rate": 2.9237163767727598e-05, + "loss": 3.5171, + "step": 1268224 + }, + { + "epoch": 0.02, + "learning_rate": 2.9228777820217078e-05, + "loss": 3.5133, + "step": 1268736 + }, + { + "epoch": 0.02, + "learning_rate": 2.922039187270656e-05, + "loss": 3.5254, + "step": 1269248 + }, + { + "epoch": 0.02, + "learning_rate": 2.921200592519604e-05, + "loss": 3.521, + "step": 1269760 + }, + { + "epoch": 0.02, + "learning_rate": 2.920361997768552e-05, + "loss": 3.5186, + "step": 1270272 + }, + { + "epoch": 0.02, + "learning_rate": 2.9195234030175e-05, + "loss": 3.509, + "step": 1270784 + }, + { + "epoch": 0.02, + "learning_rate": 2.918684808266448e-05, + "loss": 3.5152, + "step": 1271296 + }, + { + "epoch": 0.02, + "learning_rate": 2.917846213515396e-05, + "loss": 3.5177, + "step": 1271808 + }, + { + "epoch": 0.02, + "learning_rate": 2.917009256644717e-05, + "loss": 3.5268, + "step": 1272320 + }, + { + "epoch": 0.02, + "learning_rate": 2.9161706618936653e-05, + "loss": 3.5196, + "step": 1272832 + }, + { + "epoch": 0.02, + "learning_rate": 2.9153320671426133e-05, + "loss": 3.5085, + "step": 1273344 + }, + { + "epoch": 0.02, + "learning_rate": 2.9144934723915613e-05, + "loss": 3.5097, + "step": 1273856 + }, + { + "epoch": 0.02, + "learning_rate": 2.9136565155208822e-05, + "loss": 3.5234, + "step": 1274368 + }, + { + "epoch": 0.02, + "learning_rate": 2.912819558650203e-05, + "loss": 3.4978, + "step": 1274880 + }, + { + "epoch": 0.02, + "learning_rate": 2.9119809638991515e-05, + "loss": 3.5107, + "step": 1275392 + }, + { + "epoch": 0.02, + "learning_rate": 2.9111423691480995e-05, + "loss": 3.5181, + "step": 1275904 + }, + { + "epoch": 0.02, + "learning_rate": 2.9103037743970475e-05, + "loss": 3.5149, + "step": 1276416 + }, + { + "epoch": 0.02, + "learning_rate": 2.9094651796459954e-05, + "loss": 3.5032, + "step": 1276928 + }, + { + "epoch": 0.02, + "learning_rate": 2.9086282227753164e-05, + "loss": 3.5198, + "step": 1277440 + }, + { + "epoch": 0.02, + "learning_rate": 2.9077896280242644e-05, + "loss": 3.5024, + "step": 1277952 + }, + { + "epoch": 0.02, + "learning_rate": 2.9069510332732123e-05, + "loss": 3.5263, + "step": 1278464 + }, + { + "epoch": 0.02, + "learning_rate": 2.9061124385221607e-05, + "loss": 3.5114, + "step": 1278976 + }, + { + "epoch": 0.02, + "learning_rate": 2.9052738437711087e-05, + "loss": 3.521, + "step": 1279488 + }, + { + "epoch": 0.02, + "learning_rate": 2.904435249020056e-05, + "loss": 3.5226, + "step": 1280000 + }, + { + "epoch": 0.02, + "learning_rate": 2.9035982921493776e-05, + "loss": 3.5391, + "step": 1280512 + }, + { + "epoch": 0.02, + "learning_rate": 2.9027596973983256e-05, + "loss": 3.5149, + "step": 1281024 + }, + { + "epoch": 0.02, + "learning_rate": 2.9019211026472736e-05, + "loss": 3.5138, + "step": 1281536 + }, + { + "epoch": 0.02, + "learning_rate": 2.9010825078962212e-05, + "loss": 3.5202, + "step": 1282048 + }, + { + "epoch": 0.02, + "learning_rate": 2.9002455510255428e-05, + "loss": 3.5088, + "step": 1282560 + }, + { + "epoch": 0.02, + "learning_rate": 2.8994069562744908e-05, + "loss": 3.518, + "step": 1283072 + }, + { + "epoch": 0.02, + "learning_rate": 2.8985683615234388e-05, + "loss": 3.5151, + "step": 1283584 + }, + { + "epoch": 0.02, + "learning_rate": 2.897729766772386e-05, + "loss": 3.5094, + "step": 1284096 + }, + { + "epoch": 0.02, + "learning_rate": 2.8968911720213345e-05, + "loss": 3.5322, + "step": 1284608 + }, + { + "epoch": 0.02, + "learning_rate": 2.8960525772702825e-05, + "loss": 3.5155, + "step": 1285120 + }, + { + "epoch": 0.02, + "learning_rate": 2.8952156203996034e-05, + "loss": 3.5129, + "step": 1285632 + }, + { + "epoch": 0.02, + "learning_rate": 2.8943770256485514e-05, + "loss": 3.5133, + "step": 1286144 + }, + { + "epoch": 0.02, + "learning_rate": 2.8935384308974994e-05, + "loss": 3.5183, + "step": 1286656 + }, + { + "epoch": 0.02, + "learning_rate": 2.8926998361464474e-05, + "loss": 3.5129, + "step": 1287168 + }, + { + "epoch": 0.02, + "learning_rate": 2.8918612413953954e-05, + "loss": 3.5229, + "step": 1287680 + }, + { + "epoch": 0.02, + "learning_rate": 2.8910226466443437e-05, + "loss": 3.5242, + "step": 1288192 + }, + { + "epoch": 0.02, + "learning_rate": 2.8901840518932917e-05, + "loss": 3.5123, + "step": 1288704 + }, + { + "epoch": 0.02, + "learning_rate": 2.8893470950226126e-05, + "loss": 3.5073, + "step": 1289216 + }, + { + "epoch": 0.02, + "learning_rate": 2.8885101381519335e-05, + "loss": 3.5178, + "step": 1289728 + }, + { + "epoch": 0.02, + "learning_rate": 2.8876715434008815e-05, + "loss": 3.5176, + "step": 1290240 + }, + { + "epoch": 0.02, + "learning_rate": 2.8868329486498298e-05, + "loss": 3.5187, + "step": 1290752 + }, + { + "epoch": 0.02, + "learning_rate": 2.8859943538987778e-05, + "loss": 3.5161, + "step": 1291264 + }, + { + "epoch": 0.02, + "learning_rate": 2.8851557591477258e-05, + "loss": 3.529, + "step": 1291776 + }, + { + "epoch": 0.02, + "learning_rate": 2.8843171643966738e-05, + "loss": 3.5201, + "step": 1292288 + }, + { + "epoch": 0.02, + "learning_rate": 2.8834785696456218e-05, + "loss": 3.5178, + "step": 1292800 + }, + { + "epoch": 0.02, + "learning_rate": 2.8826399748945698e-05, + "loss": 3.5168, + "step": 1293312 + }, + { + "epoch": 0.02, + "learning_rate": 2.8818030180238907e-05, + "loss": 3.5125, + "step": 1293824 + }, + { + "epoch": 0.02, + "learning_rate": 2.880964423272839e-05, + "loss": 3.5198, + "step": 1294336 + }, + { + "epoch": 0.02, + "learning_rate": 2.880125828521787e-05, + "loss": 3.4981, + "step": 1294848 + }, + { + "epoch": 0.02, + "learning_rate": 2.879287233770735e-05, + "loss": 3.5265, + "step": 1295360 + }, + { + "epoch": 0.02, + "learning_rate": 2.878450276900056e-05, + "loss": 3.5238, + "step": 1295872 + }, + { + "epoch": 0.02, + "learning_rate": 2.877611682149004e-05, + "loss": 3.519, + "step": 1296384 + }, + { + "epoch": 0.02, + "learning_rate": 2.876773087397952e-05, + "loss": 3.5096, + "step": 1296896 + }, + { + "epoch": 0.02, + "learning_rate": 2.8759344926469e-05, + "loss": 3.5177, + "step": 1297408 + }, + { + "epoch": 0.03, + "eval_loss": 3.845597982406616, + "eval_runtime": 325.2527, + "eval_samples_per_second": 1173.214, + "eval_steps_per_second": 36.664, + "step": 1297440 + }, + { + "epoch": 1.0, + "learning_rate": 2.8750975357762212e-05, + "loss": 3.5015, + "step": 1297920 + }, + { + "epoch": 1.0, + "learning_rate": 2.8742589410251692e-05, + "loss": 3.5133, + "step": 1298432 + }, + { + "epoch": 1.0, + "learning_rate": 2.8734203462741172e-05, + "loss": 3.5204, + "step": 1298944 + }, + { + "epoch": 1.0, + "learning_rate": 2.8725817515230652e-05, + "loss": 3.5133, + "step": 1299456 + }, + { + "epoch": 1.0, + "learning_rate": 2.871744794652386e-05, + "loss": 3.5192, + "step": 1299968 + }, + { + "epoch": 1.0, + "learning_rate": 2.870906199901334e-05, + "loss": 3.5098, + "step": 1300480 + }, + { + "epoch": 1.0, + "learning_rate": 2.8700676051502824e-05, + "loss": 3.5109, + "step": 1300992 + }, + { + "epoch": 1.0, + "learning_rate": 2.8692306482796033e-05, + "loss": 3.5083, + "step": 1301504 + }, + { + "epoch": 1.0, + "learning_rate": 2.8683936914089242e-05, + "loss": 3.5164, + "step": 1302016 + }, + { + "epoch": 1.0, + "learning_rate": 2.8675550966578722e-05, + "loss": 3.5064, + "step": 1302528 + }, + { + "epoch": 1.0, + "learning_rate": 2.8667165019068206e-05, + "loss": 3.5236, + "step": 1303040 + }, + { + "epoch": 1.0, + "learning_rate": 2.8658779071557686e-05, + "loss": 3.5223, + "step": 1303552 + }, + { + "epoch": 1.0, + "learning_rate": 2.8650393124047166e-05, + "loss": 3.5095, + "step": 1304064 + }, + { + "epoch": 1.0, + "learning_rate": 2.8642007176536645e-05, + "loss": 3.5039, + "step": 1304576 + }, + { + "epoch": 1.0, + "learning_rate": 2.8633621229026125e-05, + "loss": 3.5095, + "step": 1305088 + }, + { + "epoch": 1.0, + "learning_rate": 2.8625235281515605e-05, + "loss": 3.5079, + "step": 1305600 + }, + { + "epoch": 1.0, + "learning_rate": 2.8616865712808815e-05, + "loss": 3.5042, + "step": 1306112 + }, + { + "epoch": 1.0, + "learning_rate": 2.8608479765298294e-05, + "loss": 3.5105, + "step": 1306624 + }, + { + "epoch": 1.0, + "learning_rate": 2.8600093817787778e-05, + "loss": 3.5055, + "step": 1307136 + }, + { + "epoch": 1.0, + "learning_rate": 2.8591707870277258e-05, + "loss": 3.5228, + "step": 1307648 + }, + { + "epoch": 1.0, + "learning_rate": 2.8583338301570467e-05, + "loss": 3.5118, + "step": 1308160 + }, + { + "epoch": 1.0, + "learning_rate": 2.8574952354059947e-05, + "loss": 3.5165, + "step": 1308672 + }, + { + "epoch": 1.0, + "learning_rate": 2.8566566406549427e-05, + "loss": 3.5169, + "step": 1309184 + }, + { + "epoch": 1.0, + "learning_rate": 2.8558180459038907e-05, + "loss": 3.5227, + "step": 1309696 + }, + { + "epoch": 1.0, + "learning_rate": 2.854981089033212e-05, + "loss": 3.5003, + "step": 1310208 + }, + { + "epoch": 1.0, + "learning_rate": 2.85414249428216e-05, + "loss": 3.5097, + "step": 1310720 + }, + { + "epoch": 1.0, + "learning_rate": 2.853303899531108e-05, + "loss": 3.5062, + "step": 1311232 + }, + { + "epoch": 1.0, + "learning_rate": 2.852465304780056e-05, + "loss": 3.5072, + "step": 1311744 + }, + { + "epoch": 1.0, + "learning_rate": 2.8516283479093768e-05, + "loss": 3.5056, + "step": 1312256 + }, + { + "epoch": 1.01, + "learning_rate": 2.850791391038698e-05, + "loss": 3.5067, + "step": 1312768 + }, + { + "epoch": 1.01, + "learning_rate": 2.849952796287646e-05, + "loss": 3.5152, + "step": 1313280 + }, + { + "epoch": 1.01, + "learning_rate": 2.849114201536594e-05, + "loss": 3.5124, + "step": 1313792 + }, + { + "epoch": 1.01, + "learning_rate": 2.848275606785542e-05, + "loss": 3.5017, + "step": 1314304 + }, + { + "epoch": 1.01, + "learning_rate": 2.84743701203449e-05, + "loss": 3.5145, + "step": 1314816 + }, + { + "epoch": 1.01, + "learning_rate": 2.846598417283438e-05, + "loss": 3.5205, + "step": 1315328 + }, + { + "epoch": 1.01, + "learning_rate": 2.845759822532386e-05, + "loss": 3.5082, + "step": 1315840 + }, + { + "epoch": 1.01, + "learning_rate": 2.8449228656617073e-05, + "loss": 3.4956, + "step": 1316352 + }, + { + "epoch": 1.01, + "learning_rate": 2.8440842709106553e-05, + "loss": 3.5122, + "step": 1316864 + }, + { + "epoch": 1.01, + "learning_rate": 2.8432473140399762e-05, + "loss": 3.4977, + "step": 1317376 + }, + { + "epoch": 1.01, + "learning_rate": 2.8424087192889242e-05, + "loss": 3.5051, + "step": 1317888 + }, + { + "epoch": 1.01, + "learning_rate": 2.8415701245378722e-05, + "loss": 3.5063, + "step": 1318400 + }, + { + "epoch": 1.01, + "learning_rate": 2.8407315297868202e-05, + "loss": 3.5192, + "step": 1318912 + }, + { + "epoch": 1.01, + "learning_rate": 2.8398929350357685e-05, + "loss": 3.5095, + "step": 1319424 + }, + { + "epoch": 1.01, + "learning_rate": 2.8390543402847165e-05, + "loss": 3.5119, + "step": 1319936 + }, + { + "epoch": 1.01, + "learning_rate": 2.8382157455336638e-05, + "loss": 3.5189, + "step": 1320448 + }, + { + "epoch": 1.01, + "learning_rate": 2.8373787886629854e-05, + "loss": 3.5107, + "step": 1320960 + }, + { + "epoch": 1.01, + "learning_rate": 2.8365401939119334e-05, + "loss": 3.5102, + "step": 1321472 + }, + { + "epoch": 1.01, + "learning_rate": 2.8357015991608814e-05, + "loss": 3.4911, + "step": 1321984 + }, + { + "epoch": 1.01, + "learning_rate": 2.834863004409829e-05, + "loss": 3.507, + "step": 1322496 + }, + { + "epoch": 1.01, + "learning_rate": 2.834024409658777e-05, + "loss": 3.5109, + "step": 1323008 + }, + { + "epoch": 1.01, + "learning_rate": 2.833185814907725e-05, + "loss": 3.5072, + "step": 1323520 + }, + { + "epoch": 1.01, + "learning_rate": 2.832347220156673e-05, + "loss": 3.5031, + "step": 1324032 + }, + { + "epoch": 1.01, + "learning_rate": 2.831508625405621e-05, + "loss": 3.4945, + "step": 1324544 + }, + { + "epoch": 1.01, + "learning_rate": 2.8306716685349423e-05, + "loss": 3.5053, + "step": 1325056 + }, + { + "epoch": 1.01, + "learning_rate": 2.8298330737838903e-05, + "loss": 3.4918, + "step": 1325568 + }, + { + "epoch": 1.01, + "learning_rate": 2.8289961169132112e-05, + "loss": 3.511, + "step": 1326080 + }, + { + "epoch": 1.01, + "learning_rate": 2.8281575221621592e-05, + "loss": 3.4988, + "step": 1326592 + }, + { + "epoch": 1.01, + "learning_rate": 2.8273189274111072e-05, + "loss": 3.5114, + "step": 1327104 + }, + { + "epoch": 1.01, + "learning_rate": 2.8264803326600552e-05, + "loss": 3.511, + "step": 1327616 + }, + { + "epoch": 1.01, + "learning_rate": 2.8256417379090032e-05, + "loss": 3.4904, + "step": 1328128 + }, + { + "epoch": 1.01, + "learning_rate": 2.8248031431579515e-05, + "loss": 3.5072, + "step": 1328640 + }, + { + "epoch": 1.01, + "learning_rate": 2.8239645484068995e-05, + "loss": 3.5059, + "step": 1329152 + }, + { + "epoch": 1.01, + "learning_rate": 2.8231275915362204e-05, + "loss": 3.4963, + "step": 1329664 + }, + { + "epoch": 1.01, + "learning_rate": 2.8222889967851684e-05, + "loss": 3.4961, + "step": 1330176 + }, + { + "epoch": 1.01, + "learning_rate": 2.8214504020341164e-05, + "loss": 3.5149, + "step": 1330688 + }, + { + "epoch": 1.01, + "learning_rate": 2.8206118072830644e-05, + "loss": 3.5071, + "step": 1331200 + }, + { + "epoch": 1.01, + "learning_rate": 2.8197732125320124e-05, + "loss": 3.4961, + "step": 1331712 + }, + { + "epoch": 1.01, + "learning_rate": 2.8189346177809607e-05, + "loss": 3.4887, + "step": 1332224 + }, + { + "epoch": 1.01, + "learning_rate": 2.8180960230299087e-05, + "loss": 3.4999, + "step": 1332736 + }, + { + "epoch": 1.01, + "learning_rate": 2.8172574282788567e-05, + "loss": 3.5071, + "step": 1333248 + }, + { + "epoch": 1.01, + "learning_rate": 2.8164204714081776e-05, + "loss": 3.5153, + "step": 1333760 + }, + { + "epoch": 1.01, + "learning_rate": 2.8155818766571256e-05, + "loss": 3.5039, + "step": 1334272 + }, + { + "epoch": 1.01, + "learning_rate": 2.8147432819060736e-05, + "loss": 3.5166, + "step": 1334784 + }, + { + "epoch": 1.01, + "learning_rate": 2.8139046871550216e-05, + "loss": 3.5112, + "step": 1335296 + }, + { + "epoch": 1.01, + "learning_rate": 2.813067730284343e-05, + "loss": 3.5093, + "step": 1335808 + }, + { + "epoch": 1.01, + "learning_rate": 2.8122307734136638e-05, + "loss": 3.4975, + "step": 1336320 + }, + { + "epoch": 1.01, + "learning_rate": 2.8113921786626118e-05, + "loss": 3.5121, + "step": 1336832 + }, + { + "epoch": 1.01, + "learning_rate": 2.8105535839115598e-05, + "loss": 3.5061, + "step": 1337344 + }, + { + "epoch": 1.01, + "learning_rate": 2.8097149891605078e-05, + "loss": 3.5014, + "step": 1337856 + }, + { + "epoch": 1.01, + "learning_rate": 2.808876394409456e-05, + "loss": 3.5034, + "step": 1338368 + }, + { + "epoch": 1.01, + "learning_rate": 2.808039437538777e-05, + "loss": 3.5035, + "step": 1338880 + }, + { + "epoch": 1.01, + "learning_rate": 2.807200842787725e-05, + "loss": 3.5171, + "step": 1339392 + }, + { + "epoch": 1.01, + "learning_rate": 2.806362248036673e-05, + "loss": 3.5033, + "step": 1339904 + }, + { + "epoch": 1.01, + "learning_rate": 2.805523653285621e-05, + "loss": 3.4994, + "step": 1340416 + }, + { + "epoch": 1.01, + "learning_rate": 2.804685058534569e-05, + "loss": 3.5026, + "step": 1340928 + }, + { + "epoch": 1.01, + "learning_rate": 2.803846463783517e-05, + "loss": 3.5084, + "step": 1341440 + }, + { + "epoch": 1.01, + "learning_rate": 2.803007869032465e-05, + "loss": 3.5044, + "step": 1341952 + }, + { + "epoch": 1.01, + "learning_rate": 2.8021709121617862e-05, + "loss": 3.5038, + "step": 1342464 + }, + { + "epoch": 1.01, + "learning_rate": 2.8013323174107342e-05, + "loss": 3.4999, + "step": 1342976 + }, + { + "epoch": 1.02, + "learning_rate": 2.8004937226596822e-05, + "loss": 3.5124, + "step": 1343488 + }, + { + "epoch": 1.02, + "learning_rate": 2.7996551279086302e-05, + "loss": 3.4955, + "step": 1344000 + }, + { + "epoch": 1.02, + "learning_rate": 2.798818171037951e-05, + "loss": 3.5007, + "step": 1344512 + }, + { + "epoch": 1.02, + "learning_rate": 2.7979795762868995e-05, + "loss": 3.4967, + "step": 1345024 + }, + { + "epoch": 1.02, + "learning_rate": 2.7971409815358475e-05, + "loss": 3.5111, + "step": 1345536 + }, + { + "epoch": 1.02, + "learning_rate": 2.7963023867847948e-05, + "loss": 3.5115, + "step": 1346048 + }, + { + "epoch": 1.02, + "learning_rate": 2.7954654299141164e-05, + "loss": 3.5063, + "step": 1346560 + }, + { + "epoch": 1.02, + "learning_rate": 2.7946268351630644e-05, + "loss": 3.4935, + "step": 1347072 + }, + { + "epoch": 1.02, + "learning_rate": 2.7937882404120124e-05, + "loss": 3.5043, + "step": 1347584 + }, + { + "epoch": 1.02, + "learning_rate": 2.79294964566096e-05, + "loss": 3.505, + "step": 1348096 + }, + { + "epoch": 1.02, + "learning_rate": 2.792111050909908e-05, + "loss": 3.5139, + "step": 1348608 + }, + { + "epoch": 1.02, + "learning_rate": 2.791272456158856e-05, + "loss": 3.5066, + "step": 1349120 + }, + { + "epoch": 1.02, + "learning_rate": 2.790433861407804e-05, + "loss": 3.4971, + "step": 1349632 + }, + { + "epoch": 1.02, + "learning_rate": 2.789595266656752e-05, + "loss": 3.4942, + "step": 1350144 + }, + { + "epoch": 1.02, + "learning_rate": 2.7887583097860732e-05, + "loss": 3.5091, + "step": 1350656 + }, + { + "epoch": 1.02, + "learning_rate": 2.7879197150350212e-05, + "loss": 3.4822, + "step": 1351168 + }, + { + "epoch": 1.02, + "learning_rate": 2.7870811202839692e-05, + "loss": 3.5012, + "step": 1351680 + }, + { + "epoch": 1.02, + "learning_rate": 2.78624416341329e-05, + "loss": 3.5039, + "step": 1352192 + }, + { + "epoch": 1.02, + "learning_rate": 2.785405568662238e-05, + "loss": 3.5006, + "step": 1352704 + }, + { + "epoch": 1.02, + "learning_rate": 2.784566973911186e-05, + "loss": 3.4904, + "step": 1353216 + }, + { + "epoch": 1.02, + "learning_rate": 2.783728379160134e-05, + "loss": 3.5049, + "step": 1353728 + }, + { + "epoch": 1.02, + "learning_rate": 2.7828897844090825e-05, + "loss": 3.4941, + "step": 1354240 + }, + { + "epoch": 1.02, + "learning_rate": 2.7820511896580305e-05, + "loss": 3.5093, + "step": 1354752 + }, + { + "epoch": 1.02, + "learning_rate": 2.7812125949069785e-05, + "loss": 3.5004, + "step": 1355264 + }, + { + "epoch": 1.02, + "learning_rate": 2.7803740001559265e-05, + "loss": 3.4999, + "step": 1355776 + }, + { + "epoch": 1.02, + "learning_rate": 2.7795370432852474e-05, + "loss": 3.5161, + "step": 1356288 + }, + { + "epoch": 1.02, + "learning_rate": 2.7787000864145686e-05, + "loss": 3.5239, + "step": 1356800 + }, + { + "epoch": 1.02, + "learning_rate": 2.7778614916635166e-05, + "loss": 3.4996, + "step": 1357312 + }, + { + "epoch": 1.02, + "learning_rate": 2.7770228969124646e-05, + "loss": 3.4979, + "step": 1357824 + }, + { + "epoch": 1.02, + "learning_rate": 2.7761843021614126e-05, + "loss": 3.5093, + "step": 1358336 + }, + { + "epoch": 1.02, + "learning_rate": 2.7753457074103606e-05, + "loss": 3.4968, + "step": 1358848 + }, + { + "epoch": 1.02, + "learning_rate": 2.7745071126593086e-05, + "loss": 3.5007, + "step": 1359360 + }, + { + "epoch": 1.02, + "learning_rate": 2.7736685179082566e-05, + "loss": 3.5044, + "step": 1359872 + }, + { + "epoch": 1.02, + "learning_rate": 2.7728299231572046e-05, + "loss": 3.497, + "step": 1360384 + }, + { + "epoch": 1.02, + "learning_rate": 2.7719929662865258e-05, + "loss": 3.5157, + "step": 1360896 + }, + { + "epoch": 1.02, + "learning_rate": 2.7711543715354738e-05, + "loss": 3.4996, + "step": 1361408 + }, + { + "epoch": 1.02, + "learning_rate": 2.7703174146647947e-05, + "loss": 3.5021, + "step": 1361920 + }, + { + "epoch": 1.02, + "learning_rate": 2.7694788199137427e-05, + "loss": 3.4966, + "step": 1362432 + }, + { + "epoch": 1.02, + "learning_rate": 2.7686402251626907e-05, + "loss": 3.5038, + "step": 1362944 + }, + { + "epoch": 1.02, + "learning_rate": 2.7678016304116387e-05, + "loss": 3.4987, + "step": 1363456 + }, + { + "epoch": 1.02, + "learning_rate": 2.766963035660587e-05, + "loss": 3.5099, + "step": 1363968 + }, + { + "epoch": 1.02, + "learning_rate": 2.766126078789908e-05, + "loss": 3.5121, + "step": 1364480 + }, + { + "epoch": 1.02, + "learning_rate": 2.765287484038856e-05, + "loss": 3.5021, + "step": 1364992 + }, + { + "epoch": 1.02, + "learning_rate": 2.764448889287804e-05, + "loss": 3.4884, + "step": 1365504 + }, + { + "epoch": 1.02, + "learning_rate": 2.763610294536752e-05, + "loss": 3.5079, + "step": 1366016 + }, + { + "epoch": 1.02, + "learning_rate": 2.7627716997857e-05, + "loss": 3.5019, + "step": 1366528 + }, + { + "epoch": 1.02, + "learning_rate": 2.761933105034648e-05, + "loss": 3.5073, + "step": 1367040 + }, + { + "epoch": 1.02, + "learning_rate": 2.7610961481639692e-05, + "loss": 3.5023, + "step": 1367552 + }, + { + "epoch": 1.02, + "learning_rate": 2.7602575534129172e-05, + "loss": 3.51, + "step": 1368064 + }, + { + "epoch": 1.02, + "learning_rate": 2.7594189586618652e-05, + "loss": 3.5074, + "step": 1368576 + }, + { + "epoch": 1.02, + "learning_rate": 2.7585803639108132e-05, + "loss": 3.5093, + "step": 1369088 + }, + { + "epoch": 1.02, + "learning_rate": 2.757741769159761e-05, + "loss": 3.5022, + "step": 1369600 + }, + { + "epoch": 1.02, + "learning_rate": 2.7569031744087088e-05, + "loss": 3.4995, + "step": 1370112 + }, + { + "epoch": 1.02, + "learning_rate": 2.7560662175380304e-05, + "loss": 3.5075, + "step": 1370624 + }, + { + "epoch": 1.02, + "learning_rate": 2.7552276227869784e-05, + "loss": 3.4898, + "step": 1371136 + }, + { + "epoch": 1.02, + "learning_rate": 2.7543890280359257e-05, + "loss": 3.5103, + "step": 1371648 + }, + { + "epoch": 1.02, + "learning_rate": 2.7535504332848737e-05, + "loss": 3.5148, + "step": 1372160 + }, + { + "epoch": 1.02, + "learning_rate": 2.7527118385338217e-05, + "loss": 3.5041, + "step": 1372672 + }, + { + "epoch": 1.02, + "learning_rate": 2.75187324378277e-05, + "loss": 3.4932, + "step": 1373184 + }, + { + "epoch": 1.02, + "learning_rate": 2.751034649031718e-05, + "loss": 3.5018, + "step": 1373696 + }, + { + "epoch": 1.03, + "eval_loss": 3.847632646560669, + "eval_runtime": 326.3744, + "eval_samples_per_second": 1169.182, + "eval_steps_per_second": 36.538, + "step": 1373760 + }, + { + "epoch": 0.0, + "learning_rate": 2.750196054280666e-05, + "loss": 3.4902, + "step": 1374208 + }, + { + "epoch": 0.0, + "learning_rate": 2.749357459529614e-05, + "loss": 3.5, + "step": 1374720 + }, + { + "epoch": 0.0, + "learning_rate": 2.748518864778562e-05, + "loss": 3.5054, + "step": 1375232 + }, + { + "epoch": 0.0, + "learning_rate": 2.74768027002751e-05, + "loss": 3.501, + "step": 1375744 + }, + { + "epoch": 0.0, + "learning_rate": 2.746843313156831e-05, + "loss": 3.5058, + "step": 1376256 + }, + { + "epoch": 0.0, + "learning_rate": 2.746004718405779e-05, + "loss": 3.495, + "step": 1376768 + }, + { + "epoch": 0.0, + "learning_rate": 2.7451661236547273e-05, + "loss": 3.5039, + "step": 1377280 + }, + { + "epoch": 0.0, + "learning_rate": 2.7443291667840482e-05, + "loss": 3.4914, + "step": 1377792 + }, + { + "epoch": 0.0, + "learning_rate": 2.743492209913369e-05, + "loss": 3.5014, + "step": 1378304 + }, + { + "epoch": 0.0, + "learning_rate": 2.742653615162317e-05, + "loss": 3.4988, + "step": 1378816 + }, + { + "epoch": 0.0, + "learning_rate": 2.7418150204112654e-05, + "loss": 3.5014, + "step": 1379328 + }, + { + "epoch": 0.0, + "learning_rate": 2.7409764256602134e-05, + "loss": 3.5107, + "step": 1379840 + }, + { + "epoch": 0.0, + "learning_rate": 2.7401378309091614e-05, + "loss": 3.4959, + "step": 1380352 + }, + { + "epoch": 0.0, + "learning_rate": 2.7392992361581094e-05, + "loss": 3.4953, + "step": 1380864 + }, + { + "epoch": 0.0, + "learning_rate": 2.7384606414070574e-05, + "loss": 3.4967, + "step": 1381376 + }, + { + "epoch": 0.0, + "learning_rate": 2.7376220466560054e-05, + "loss": 3.4925, + "step": 1381888 + }, + { + "epoch": 0.0, + "learning_rate": 2.7367850897853263e-05, + "loss": 3.49, + "step": 1382400 + }, + { + "epoch": 0.0, + "learning_rate": 2.7359464950342743e-05, + "loss": 3.4977, + "step": 1382912 + }, + { + "epoch": 0.0, + "learning_rate": 2.7351079002832226e-05, + "loss": 3.4882, + "step": 1383424 + }, + { + "epoch": 0.0, + "learning_rate": 2.7342693055321706e-05, + "loss": 3.5151, + "step": 1383936 + }, + { + "epoch": 0.0, + "learning_rate": 2.7334323486614915e-05, + "loss": 3.4922, + "step": 1384448 + }, + { + "epoch": 0.0, + "learning_rate": 2.7325937539104395e-05, + "loss": 3.5071, + "step": 1384960 + }, + { + "epoch": 0.0, + "learning_rate": 2.7317551591593875e-05, + "loss": 3.5048, + "step": 1385472 + }, + { + "epoch": 0.0, + "learning_rate": 2.7309165644083355e-05, + "loss": 3.5079, + "step": 1385984 + }, + { + "epoch": 0.0, + "learning_rate": 2.7300796075376568e-05, + "loss": 3.4841, + "step": 1386496 + }, + { + "epoch": 0.0, + "learning_rate": 2.7292410127866048e-05, + "loss": 3.4991, + "step": 1387008 + }, + { + "epoch": 0.0, + "learning_rate": 2.7284024180355528e-05, + "loss": 3.4914, + "step": 1387520 + }, + { + "epoch": 0.0, + "learning_rate": 2.7275654611648737e-05, + "loss": 3.4971, + "step": 1388032 + }, + { + "epoch": 0.0, + "learning_rate": 2.7267268664138217e-05, + "loss": 3.4923, + "step": 1388544 + }, + { + "epoch": 0.01, + "learning_rate": 2.7258882716627697e-05, + "loss": 3.4918, + "step": 1389056 + }, + { + "epoch": 0.01, + "learning_rate": 2.725049676911718e-05, + "loss": 3.5039, + "step": 1389568 + }, + { + "epoch": 0.01, + "learning_rate": 2.724211082160666e-05, + "loss": 3.4988, + "step": 1390080 + }, + { + "epoch": 0.01, + "learning_rate": 2.723372487409614e-05, + "loss": 3.488, + "step": 1390592 + }, + { + "epoch": 0.01, + "learning_rate": 2.722533892658562e-05, + "loss": 3.5039, + "step": 1391104 + }, + { + "epoch": 0.01, + "learning_rate": 2.7216952979075093e-05, + "loss": 3.5011, + "step": 1391616 + }, + { + "epoch": 0.01, + "learning_rate": 2.720858341036831e-05, + "loss": 3.4945, + "step": 1392128 + }, + { + "epoch": 0.01, + "learning_rate": 2.720019746285779e-05, + "loss": 3.4847, + "step": 1392640 + }, + { + "epoch": 0.01, + "learning_rate": 2.7191811515347266e-05, + "loss": 3.4995, + "step": 1393152 + }, + { + "epoch": 0.01, + "learning_rate": 2.7183425567836745e-05, + "loss": 3.4837, + "step": 1393664 + }, + { + "epoch": 0.01, + "learning_rate": 2.7175039620326225e-05, + "loss": 3.4938, + "step": 1394176 + }, + { + "epoch": 0.01, + "learning_rate": 2.7166653672815705e-05, + "loss": 3.4926, + "step": 1394688 + }, + { + "epoch": 0.01, + "learning_rate": 2.7158267725305185e-05, + "loss": 3.5043, + "step": 1395200 + }, + { + "epoch": 0.01, + "learning_rate": 2.7149881777794665e-05, + "loss": 3.4958, + "step": 1395712 + }, + { + "epoch": 0.01, + "learning_rate": 2.7141512209087878e-05, + "loss": 3.4996, + "step": 1396224 + }, + { + "epoch": 0.01, + "learning_rate": 2.7133126261577358e-05, + "loss": 3.5056, + "step": 1396736 + }, + { + "epoch": 0.01, + "learning_rate": 2.7124740314066838e-05, + "loss": 3.4997, + "step": 1397248 + }, + { + "epoch": 0.01, + "learning_rate": 2.7116370745360047e-05, + "loss": 3.4977, + "step": 1397760 + }, + { + "epoch": 0.01, + "learning_rate": 2.7107984797849527e-05, + "loss": 3.4798, + "step": 1398272 + }, + { + "epoch": 0.01, + "learning_rate": 2.709959885033901e-05, + "loss": 3.4894, + "step": 1398784 + }, + { + "epoch": 0.01, + "learning_rate": 2.709121290282849e-05, + "loss": 3.5014, + "step": 1399296 + }, + { + "epoch": 0.01, + "learning_rate": 2.70828433341217e-05, + "loss": 3.4933, + "step": 1399808 + }, + { + "epoch": 0.01, + "learning_rate": 2.707445738661118e-05, + "loss": 3.4912, + "step": 1400320 + }, + { + "epoch": 0.01, + "learning_rate": 2.706607143910066e-05, + "loss": 3.4841, + "step": 1400832 + }, + { + "epoch": 0.01, + "learning_rate": 2.705768549159014e-05, + "loss": 3.4913, + "step": 1401344 + }, + { + "epoch": 0.01, + "learning_rate": 2.704931592288335e-05, + "loss": 3.4762, + "step": 1401856 + }, + { + "epoch": 0.01, + "learning_rate": 2.7040946354176567e-05, + "loss": 3.4957, + "step": 1402368 + }, + { + "epoch": 0.01, + "learning_rate": 2.703256040666604e-05, + "loss": 3.4866, + "step": 1402880 + }, + { + "epoch": 0.01, + "learning_rate": 2.702417445915552e-05, + "loss": 3.5012, + "step": 1403392 + }, + { + "epoch": 0.01, + "learning_rate": 2.7015788511645e-05, + "loss": 3.4942, + "step": 1403904 + }, + { + "epoch": 0.01, + "learning_rate": 2.700740256413448e-05, + "loss": 3.4799, + "step": 1404416 + }, + { + "epoch": 0.01, + "learning_rate": 2.6999016616623964e-05, + "loss": 3.4911, + "step": 1404928 + }, + { + "epoch": 0.01, + "learning_rate": 2.6990630669113444e-05, + "loss": 3.4952, + "step": 1405440 + }, + { + "epoch": 0.01, + "learning_rate": 2.6982261100406653e-05, + "loss": 3.4815, + "step": 1405952 + }, + { + "epoch": 0.01, + "learning_rate": 2.6973875152896133e-05, + "loss": 3.4904, + "step": 1406464 + }, + { + "epoch": 0.01, + "learning_rate": 2.6965489205385613e-05, + "loss": 3.4962, + "step": 1406976 + }, + { + "epoch": 0.01, + "learning_rate": 2.6957103257875093e-05, + "loss": 3.4951, + "step": 1407488 + }, + { + "epoch": 0.01, + "learning_rate": 2.6948717310364573e-05, + "loss": 3.4848, + "step": 1408000 + }, + { + "epoch": 0.01, + "learning_rate": 2.6940331362854056e-05, + "loss": 3.4766, + "step": 1408512 + }, + { + "epoch": 0.01, + "learning_rate": 2.6931945415343536e-05, + "loss": 3.4865, + "step": 1409024 + }, + { + "epoch": 0.01, + "learning_rate": 2.6923559467833016e-05, + "loss": 3.4958, + "step": 1409536 + }, + { + "epoch": 0.01, + "learning_rate": 2.6915189899126225e-05, + "loss": 3.5038, + "step": 1410048 + }, + { + "epoch": 0.01, + "learning_rate": 2.6906803951615705e-05, + "loss": 3.4902, + "step": 1410560 + }, + { + "epoch": 0.01, + "learning_rate": 2.6898418004105185e-05, + "loss": 3.5035, + "step": 1411072 + }, + { + "epoch": 0.01, + "learning_rate": 2.6890048435398397e-05, + "loss": 3.5007, + "step": 1411584 + }, + { + "epoch": 0.01, + "learning_rate": 2.6881662487887877e-05, + "loss": 3.5005, + "step": 1412096 + }, + { + "epoch": 0.01, + "learning_rate": 2.6873276540377357e-05, + "loss": 3.4813, + "step": 1412608 + }, + { + "epoch": 0.01, + "learning_rate": 2.6864890592866837e-05, + "loss": 3.4998, + "step": 1413120 + }, + { + "epoch": 0.01, + "learning_rate": 2.6856504645356317e-05, + "loss": 3.4946, + "step": 1413632 + }, + { + "epoch": 0.01, + "learning_rate": 2.6848135076649526e-05, + "loss": 3.4863, + "step": 1414144 + }, + { + "epoch": 0.01, + "learning_rate": 2.683974912913901e-05, + "loss": 3.4941, + "step": 1414656 + }, + { + "epoch": 0.01, + "learning_rate": 2.683136318162849e-05, + "loss": 3.4909, + "step": 1415168 + }, + { + "epoch": 0.01, + "learning_rate": 2.682297723411797e-05, + "loss": 3.5011, + "step": 1415680 + }, + { + "epoch": 0.01, + "learning_rate": 2.681459128660745e-05, + "loss": 3.4937, + "step": 1416192 + }, + { + "epoch": 0.01, + "learning_rate": 2.680620533909693e-05, + "loss": 3.483, + "step": 1416704 + }, + { + "epoch": 0.01, + "learning_rate": 2.6797819391586403e-05, + "loss": 3.4894, + "step": 1417216 + }, + { + "epoch": 0.01, + "learning_rate": 2.6789433444075886e-05, + "loss": 3.4931, + "step": 1417728 + }, + { + "epoch": 0.01, + "learning_rate": 2.67810638753691e-05, + "loss": 3.4929, + "step": 1418240 + }, + { + "epoch": 0.01, + "learning_rate": 2.677269430666231e-05, + "loss": 3.4889, + "step": 1418752 + }, + { + "epoch": 0.01, + "learning_rate": 2.676430835915179e-05, + "loss": 3.4889, + "step": 1419264 + }, + { + "epoch": 0.02, + "learning_rate": 2.675592241164127e-05, + "loss": 3.4963, + "step": 1419776 + }, + { + "epoch": 0.02, + "learning_rate": 2.674753646413075e-05, + "loss": 3.4837, + "step": 1420288 + }, + { + "epoch": 0.02, + "learning_rate": 2.6739150516620227e-05, + "loss": 3.4904, + "step": 1420800 + }, + { + "epoch": 0.02, + "learning_rate": 2.6730780947913443e-05, + "loss": 3.4847, + "step": 1421312 + }, + { + "epoch": 0.02, + "learning_rate": 2.6722395000402923e-05, + "loss": 3.5027, + "step": 1421824 + }, + { + "epoch": 0.02, + "learning_rate": 2.6714009052892403e-05, + "loss": 3.4967, + "step": 1422336 + }, + { + "epoch": 0.02, + "learning_rate": 2.6705623105381876e-05, + "loss": 3.4928, + "step": 1422848 + }, + { + "epoch": 0.02, + "learning_rate": 2.6697237157871356e-05, + "loss": 3.4831, + "step": 1423360 + }, + { + "epoch": 0.02, + "learning_rate": 2.6688851210360836e-05, + "loss": 3.495, + "step": 1423872 + }, + { + "epoch": 0.02, + "learning_rate": 2.668046526285032e-05, + "loss": 3.4835, + "step": 1424384 + }, + { + "epoch": 0.02, + "learning_rate": 2.66720793153398e-05, + "loss": 3.5042, + "step": 1424896 + }, + { + "epoch": 0.02, + "learning_rate": 2.666370974663301e-05, + "loss": 3.4894, + "step": 1425408 + }, + { + "epoch": 0.02, + "learning_rate": 2.665532379912249e-05, + "loss": 3.487, + "step": 1425920 + }, + { + "epoch": 0.02, + "learning_rate": 2.664693785161197e-05, + "loss": 3.4831, + "step": 1426432 + }, + { + "epoch": 0.02, + "learning_rate": 2.663855190410145e-05, + "loss": 3.4937, + "step": 1426944 + }, + { + "epoch": 0.02, + "learning_rate": 2.663018233539466e-05, + "loss": 3.4744, + "step": 1427456 + }, + { + "epoch": 0.02, + "learning_rate": 2.662179638788414e-05, + "loss": 3.4891, + "step": 1427968 + }, + { + "epoch": 0.02, + "learning_rate": 2.661342681917735e-05, + "loss": 3.4891, + "step": 1428480 + }, + { + "epoch": 0.02, + "learning_rate": 2.660504087166683e-05, + "loss": 3.4881, + "step": 1428992 + }, + { + "epoch": 0.02, + "learning_rate": 2.659665492415631e-05, + "loss": 3.4738, + "step": 1429504 + }, + { + "epoch": 0.02, + "learning_rate": 2.658826897664579e-05, + "loss": 3.4946, + "step": 1430016 + }, + { + "epoch": 0.02, + "learning_rate": 2.6579883029135273e-05, + "loss": 3.4782, + "step": 1430528 + }, + { + "epoch": 0.02, + "learning_rate": 2.6571513460428482e-05, + "loss": 3.4989, + "step": 1431040 + }, + { + "epoch": 0.02, + "learning_rate": 2.6563127512917962e-05, + "loss": 3.4884, + "step": 1431552 + }, + { + "epoch": 0.02, + "learning_rate": 2.6554741565407442e-05, + "loss": 3.4855, + "step": 1432064 + }, + { + "epoch": 0.02, + "learning_rate": 2.6546355617896922e-05, + "loss": 3.5032, + "step": 1432576 + }, + { + "epoch": 0.02, + "learning_rate": 2.6537969670386402e-05, + "loss": 3.5135, + "step": 1433088 + }, + { + "epoch": 0.02, + "learning_rate": 2.6529583722875882e-05, + "loss": 3.4884, + "step": 1433600 + }, + { + "epoch": 0.02, + "learning_rate": 2.6521197775365365e-05, + "loss": 3.4817, + "step": 1434112 + }, + { + "epoch": 0.02, + "learning_rate": 2.6512811827854845e-05, + "loss": 3.4968, + "step": 1434624 + }, + { + "epoch": 0.02, + "learning_rate": 2.6504458637951784e-05, + "loss": 3.486, + "step": 1435136 + }, + { + "epoch": 0.02, + "learning_rate": 2.6496072690441264e-05, + "loss": 3.4879, + "step": 1435648 + }, + { + "epoch": 0.02, + "learning_rate": 2.6487686742930744e-05, + "loss": 3.4969, + "step": 1436160 + }, + { + "epoch": 0.02, + "learning_rate": 2.6479300795420227e-05, + "loss": 3.4804, + "step": 1436672 + }, + { + "epoch": 0.02, + "learning_rate": 2.6470914847909707e-05, + "loss": 3.502, + "step": 1437184 + }, + { + "epoch": 0.02, + "learning_rate": 2.6462528900399187e-05, + "loss": 3.491, + "step": 1437696 + }, + { + "epoch": 0.02, + "learning_rate": 2.6454159331692396e-05, + "loss": 3.4894, + "step": 1438208 + }, + { + "epoch": 0.02, + "learning_rate": 2.6445773384181876e-05, + "loss": 3.483, + "step": 1438720 + }, + { + "epoch": 0.02, + "learning_rate": 2.6437387436671356e-05, + "loss": 3.492, + "step": 1439232 + }, + { + "epoch": 0.02, + "learning_rate": 2.6429001489160836e-05, + "loss": 3.4847, + "step": 1439744 + }, + { + "epoch": 0.02, + "learning_rate": 2.642061554165032e-05, + "loss": 3.4991, + "step": 1440256 + }, + { + "epoch": 0.02, + "learning_rate": 2.6412245972943528e-05, + "loss": 3.4953, + "step": 1440768 + }, + { + "epoch": 0.02, + "learning_rate": 2.6403860025433008e-05, + "loss": 3.4913, + "step": 1441280 + }, + { + "epoch": 0.02, + "learning_rate": 2.6395474077922488e-05, + "loss": 3.4772, + "step": 1441792 + }, + { + "epoch": 0.02, + "learning_rate": 2.6387088130411968e-05, + "loss": 3.4974, + "step": 1442304 + }, + { + "epoch": 0.02, + "learning_rate": 2.6378702182901448e-05, + "loss": 3.4909, + "step": 1442816 + }, + { + "epoch": 0.02, + "learning_rate": 2.6370316235390928e-05, + "loss": 3.4907, + "step": 1443328 + }, + { + "epoch": 0.02, + "learning_rate": 2.636194666668414e-05, + "loss": 3.4886, + "step": 1443840 + }, + { + "epoch": 0.02, + "learning_rate": 2.635356071917362e-05, + "loss": 3.4993, + "step": 1444352 + }, + { + "epoch": 0.02, + "learning_rate": 2.63451747716631e-05, + "loss": 3.4965, + "step": 1444864 + }, + { + "epoch": 0.02, + "learning_rate": 2.633678882415258e-05, + "loss": 3.499, + "step": 1445376 + }, + { + "epoch": 0.02, + "learning_rate": 2.632840287664206e-05, + "loss": 3.4866, + "step": 1445888 + }, + { + "epoch": 0.02, + "learning_rate": 2.6320016929131537e-05, + "loss": 3.4874, + "step": 1446400 + }, + { + "epoch": 0.02, + "learning_rate": 2.6311647360424753e-05, + "loss": 3.4951, + "step": 1446912 + }, + { + "epoch": 0.02, + "learning_rate": 2.6303261412914233e-05, + "loss": 3.4769, + "step": 1447424 + }, + { + "epoch": 0.02, + "learning_rate": 2.6294875465403706e-05, + "loss": 3.4947, + "step": 1447936 + }, + { + "epoch": 0.02, + "learning_rate": 2.6286489517893186e-05, + "loss": 3.5026, + "step": 1448448 + }, + { + "epoch": 0.02, + "learning_rate": 2.6278103570382666e-05, + "loss": 3.4918, + "step": 1448960 + }, + { + "epoch": 0.02, + "learning_rate": 2.626971762287215e-05, + "loss": 3.4801, + "step": 1449472 + }, + { + "epoch": 0.02, + "learning_rate": 2.626133167536163e-05, + "loss": 3.4902, + "step": 1449984 + }, + { + "epoch": 0.03, + "eval_loss": 3.8493411540985107, + "eval_runtime": 306.0097, + "eval_samples_per_second": 1246.99, + "eval_steps_per_second": 38.969, + "step": 1450080 + }, + { + "epoch": 1.0, + "learning_rate": 2.625294572785111e-05, + "loss": 3.4818, + "step": 1450496 + }, + { + "epoch": 1.0, + "learning_rate": 2.6244576159144318e-05, + "loss": 3.4851, + "step": 1451008 + }, + { + "epoch": 1.0, + "learning_rate": 2.6236206590437534e-05, + "loss": 3.4936, + "step": 1451520 + }, + { + "epoch": 1.0, + "learning_rate": 2.622782064292701e-05, + "loss": 3.4851, + "step": 1452032 + }, + { + "epoch": 1.0, + "learning_rate": 2.621943469541649e-05, + "loss": 3.4978, + "step": 1452544 + }, + { + "epoch": 1.0, + "learning_rate": 2.621104874790597e-05, + "loss": 3.4786, + "step": 1453056 + }, + { + "epoch": 1.0, + "learning_rate": 2.620266280039545e-05, + "loss": 3.4928, + "step": 1453568 + }, + { + "epoch": 1.0, + "learning_rate": 2.619427685288493e-05, + "loss": 3.4772, + "step": 1454080 + }, + { + "epoch": 1.0, + "learning_rate": 2.618590728417814e-05, + "loss": 3.4892, + "step": 1454592 + }, + { + "epoch": 1.0, + "learning_rate": 2.617752133666762e-05, + "loss": 3.4829, + "step": 1455104 + }, + { + "epoch": 1.0, + "learning_rate": 2.6169135389157103e-05, + "loss": 3.4907, + "step": 1455616 + }, + { + "epoch": 1.0, + "learning_rate": 2.6160749441646583e-05, + "loss": 3.4968, + "step": 1456128 + }, + { + "epoch": 1.0, + "learning_rate": 2.6152379872939792e-05, + "loss": 3.4835, + "step": 1456640 + }, + { + "epoch": 1.0, + "learning_rate": 2.6143993925429272e-05, + "loss": 3.4838, + "step": 1457152 + }, + { + "epoch": 1.0, + "learning_rate": 2.6135607977918752e-05, + "loss": 3.4828, + "step": 1457664 + }, + { + "epoch": 1.0, + "learning_rate": 2.6127222030408232e-05, + "loss": 3.4829, + "step": 1458176 + }, + { + "epoch": 1.0, + "learning_rate": 2.6118836082897712e-05, + "loss": 3.4764, + "step": 1458688 + }, + { + "epoch": 1.0, + "learning_rate": 2.611045013538719e-05, + "loss": 3.4822, + "step": 1459200 + }, + { + "epoch": 1.0, + "learning_rate": 2.6102064187876675e-05, + "loss": 3.4778, + "step": 1459712 + }, + { + "epoch": 1.0, + "learning_rate": 2.6093678240366155e-05, + "loss": 3.5046, + "step": 1460224 + }, + { + "epoch": 1.0, + "learning_rate": 2.6085308671659364e-05, + "loss": 3.4817, + "step": 1460736 + }, + { + "epoch": 1.0, + "learning_rate": 2.6076922724148844e-05, + "loss": 3.489, + "step": 1461248 + }, + { + "epoch": 1.0, + "learning_rate": 2.6068536776638324e-05, + "loss": 3.4974, + "step": 1461760 + }, + { + "epoch": 1.0, + "learning_rate": 2.6060150829127804e-05, + "loss": 3.4927, + "step": 1462272 + }, + { + "epoch": 1.0, + "learning_rate": 2.6051781260421016e-05, + "loss": 3.4747, + "step": 1462784 + }, + { + "epoch": 1.0, + "learning_rate": 2.6043395312910496e-05, + "loss": 3.4847, + "step": 1463296 + }, + { + "epoch": 1.0, + "learning_rate": 2.6035025744203705e-05, + "loss": 3.481, + "step": 1463808 + }, + { + "epoch": 1.0, + "learning_rate": 2.6026639796693185e-05, + "loss": 3.4854, + "step": 1464320 + }, + { + "epoch": 1.0, + "learning_rate": 2.6018253849182665e-05, + "loss": 3.477, + "step": 1464832 + }, + { + "epoch": 1.01, + "learning_rate": 2.6009867901672145e-05, + "loss": 3.4803, + "step": 1465344 + }, + { + "epoch": 1.01, + "learning_rate": 2.600148195416163e-05, + "loss": 3.4923, + "step": 1465856 + }, + { + "epoch": 1.01, + "learning_rate": 2.5993112385454838e-05, + "loss": 3.4869, + "step": 1466368 + }, + { + "epoch": 1.01, + "learning_rate": 2.5984726437944318e-05, + "loss": 3.4822, + "step": 1466880 + }, + { + "epoch": 1.01, + "learning_rate": 2.5976340490433798e-05, + "loss": 3.49, + "step": 1467392 + }, + { + "epoch": 1.01, + "learning_rate": 2.5967954542923278e-05, + "loss": 3.4879, + "step": 1467904 + }, + { + "epoch": 1.01, + "learning_rate": 2.595958497421649e-05, + "loss": 3.4819, + "step": 1468416 + }, + { + "epoch": 1.01, + "learning_rate": 2.595119902670597e-05, + "loss": 3.4718, + "step": 1468928 + }, + { + "epoch": 1.01, + "learning_rate": 2.594281307919545e-05, + "loss": 3.4887, + "step": 1469440 + }, + { + "epoch": 1.01, + "learning_rate": 2.593442713168493e-05, + "loss": 3.4684, + "step": 1469952 + }, + { + "epoch": 1.01, + "learning_rate": 2.592604118417441e-05, + "loss": 3.483, + "step": 1470464 + }, + { + "epoch": 1.01, + "learning_rate": 2.591765523666389e-05, + "loss": 3.4774, + "step": 1470976 + }, + { + "epoch": 1.01, + "learning_rate": 2.5909269289153366e-05, + "loss": 3.494, + "step": 1471488 + }, + { + "epoch": 1.01, + "learning_rate": 2.5900883341642846e-05, + "loss": 3.4895, + "step": 1472000 + }, + { + "epoch": 1.01, + "learning_rate": 2.5892513772936062e-05, + "loss": 3.4822, + "step": 1472512 + }, + { + "epoch": 1.01, + "learning_rate": 2.5884127825425542e-05, + "loss": 3.4908, + "step": 1473024 + }, + { + "epoch": 1.01, + "learning_rate": 2.587575825671875e-05, + "loss": 3.4905, + "step": 1473536 + }, + { + "epoch": 1.01, + "learning_rate": 2.586737230920823e-05, + "loss": 3.4839, + "step": 1474048 + }, + { + "epoch": 1.01, + "learning_rate": 2.585898636169771e-05, + "loss": 3.4715, + "step": 1474560 + }, + { + "epoch": 1.01, + "learning_rate": 2.585060041418719e-05, + "loss": 3.4746, + "step": 1475072 + }, + { + "epoch": 1.01, + "learning_rate": 2.5842214466676668e-05, + "loss": 3.4913, + "step": 1475584 + }, + { + "epoch": 1.01, + "learning_rate": 2.5833844897969884e-05, + "loss": 3.4775, + "step": 1476096 + }, + { + "epoch": 1.01, + "learning_rate": 2.5825458950459364e-05, + "loss": 3.4758, + "step": 1476608 + }, + { + "epoch": 1.01, + "learning_rate": 2.5817073002948837e-05, + "loss": 3.4732, + "step": 1477120 + }, + { + "epoch": 1.01, + "learning_rate": 2.580868705543832e-05, + "loss": 3.482, + "step": 1477632 + }, + { + "epoch": 1.01, + "learning_rate": 2.58003011079278e-05, + "loss": 3.4669, + "step": 1478144 + }, + { + "epoch": 1.01, + "learning_rate": 2.579191516041728e-05, + "loss": 3.4803, + "step": 1478656 + }, + { + "epoch": 1.01, + "learning_rate": 2.578352921290676e-05, + "loss": 3.4783, + "step": 1479168 + }, + { + "epoch": 1.01, + "learning_rate": 2.577514326539624e-05, + "loss": 3.485, + "step": 1479680 + }, + { + "epoch": 1.01, + "learning_rate": 2.576677369668945e-05, + "loss": 3.4852, + "step": 1480192 + }, + { + "epoch": 1.01, + "learning_rate": 2.575838774917893e-05, + "loss": 3.4714, + "step": 1480704 + }, + { + "epoch": 1.01, + "learning_rate": 2.5750001801668412e-05, + "loss": 3.4737, + "step": 1481216 + }, + { + "epoch": 1.01, + "learning_rate": 2.5741615854157892e-05, + "loss": 3.4868, + "step": 1481728 + }, + { + "epoch": 1.01, + "learning_rate": 2.5733262664254837e-05, + "loss": 3.4667, + "step": 1482240 + }, + { + "epoch": 1.01, + "learning_rate": 2.572487671674431e-05, + "loss": 3.477, + "step": 1482752 + }, + { + "epoch": 1.01, + "learning_rate": 2.571649076923379e-05, + "loss": 3.4836, + "step": 1483264 + }, + { + "epoch": 1.01, + "learning_rate": 2.5708104821723274e-05, + "loss": 3.4871, + "step": 1483776 + }, + { + "epoch": 1.01, + "learning_rate": 2.5699718874212754e-05, + "loss": 3.4705, + "step": 1484288 + }, + { + "epoch": 1.01, + "learning_rate": 2.5691332926702234e-05, + "loss": 3.4654, + "step": 1484800 + }, + { + "epoch": 1.01, + "learning_rate": 2.5682946979191714e-05, + "loss": 3.472, + "step": 1485312 + }, + { + "epoch": 1.01, + "learning_rate": 2.5674561031681194e-05, + "loss": 3.4828, + "step": 1485824 + }, + { + "epoch": 1.01, + "learning_rate": 2.5666191462974403e-05, + "loss": 3.4893, + "step": 1486336 + }, + { + "epoch": 1.01, + "learning_rate": 2.5657821894267615e-05, + "loss": 3.4789, + "step": 1486848 + }, + { + "epoch": 1.01, + "learning_rate": 2.5649435946757095e-05, + "loss": 3.491, + "step": 1487360 + }, + { + "epoch": 1.01, + "learning_rate": 2.5641049999246575e-05, + "loss": 3.4879, + "step": 1487872 + }, + { + "epoch": 1.01, + "learning_rate": 2.5632664051736055e-05, + "loss": 3.4881, + "step": 1488384 + }, + { + "epoch": 1.01, + "learning_rate": 2.5624294483029264e-05, + "loss": 3.4697, + "step": 1488896 + }, + { + "epoch": 1.01, + "learning_rate": 2.5615908535518744e-05, + "loss": 3.4867, + "step": 1489408 + }, + { + "epoch": 1.01, + "learning_rate": 2.5607522588008227e-05, + "loss": 3.4829, + "step": 1489920 + }, + { + "epoch": 1.01, + "learning_rate": 2.5599136640497707e-05, + "loss": 3.475, + "step": 1490432 + }, + { + "epoch": 1.01, + "learning_rate": 2.5590750692987187e-05, + "loss": 3.4807, + "step": 1490944 + }, + { + "epoch": 1.01, + "learning_rate": 2.5582381124280396e-05, + "loss": 3.4818, + "step": 1491456 + }, + { + "epoch": 1.01, + "learning_rate": 2.5573995176769876e-05, + "loss": 3.4866, + "step": 1491968 + }, + { + "epoch": 1.01, + "learning_rate": 2.5565609229259356e-05, + "loss": 3.4823, + "step": 1492480 + }, + { + "epoch": 1.01, + "learning_rate": 2.5557223281748836e-05, + "loss": 3.4722, + "step": 1492992 + }, + { + "epoch": 1.01, + "learning_rate": 2.554883733423832e-05, + "loss": 3.4809, + "step": 1493504 + }, + { + "epoch": 1.01, + "learning_rate": 2.55404513867278e-05, + "loss": 3.4775, + "step": 1494016 + }, + { + "epoch": 1.01, + "learning_rate": 2.553206543921728e-05, + "loss": 3.4826, + "step": 1494528 + }, + { + "epoch": 1.01, + "learning_rate": 2.552367949170676e-05, + "loss": 3.4783, + "step": 1495040 + }, + { + "epoch": 1.01, + "learning_rate": 2.551530992299997e-05, + "loss": 3.4742, + "step": 1495552 + }, + { + "epoch": 1.02, + "learning_rate": 2.550692397548945e-05, + "loss": 3.4857, + "step": 1496064 + }, + { + "epoch": 1.02, + "learning_rate": 2.549853802797893e-05, + "loss": 3.4751, + "step": 1496576 + }, + { + "epoch": 1.02, + "learning_rate": 2.549016845927214e-05, + "loss": 3.4739, + "step": 1497088 + }, + { + "epoch": 1.02, + "learning_rate": 2.548178251176162e-05, + "loss": 3.4703, + "step": 1497600 + }, + { + "epoch": 1.02, + "learning_rate": 2.54733965642511e-05, + "loss": 3.4936, + "step": 1498112 + }, + { + "epoch": 1.02, + "learning_rate": 2.546501061674058e-05, + "loss": 3.4865, + "step": 1498624 + }, + { + "epoch": 1.02, + "learning_rate": 2.545662466923006e-05, + "loss": 3.4789, + "step": 1499136 + }, + { + "epoch": 1.02, + "learning_rate": 2.544823872171954e-05, + "loss": 3.4711, + "step": 1499648 + }, + { + "epoch": 1.02, + "learning_rate": 2.543985277420902e-05, + "loss": 3.4809, + "step": 1500160 + }, + { + "epoch": 1.02, + "learning_rate": 2.5431466826698497e-05, + "loss": 3.4714, + "step": 1500672 + }, + { + "epoch": 1.02, + "learning_rate": 2.5423097257991713e-05, + "loss": 3.4946, + "step": 1501184 + }, + { + "epoch": 1.02, + "learning_rate": 2.5414711310481193e-05, + "loss": 3.4779, + "step": 1501696 + }, + { + "epoch": 1.02, + "learning_rate": 2.5406325362970673e-05, + "loss": 3.476, + "step": 1502208 + }, + { + "epoch": 1.02, + "learning_rate": 2.5397939415460146e-05, + "loss": 3.4717, + "step": 1502720 + }, + { + "epoch": 1.02, + "learning_rate": 2.538955346794963e-05, + "loss": 3.4826, + "step": 1503232 + }, + { + "epoch": 1.02, + "learning_rate": 2.538116752043911e-05, + "loss": 3.4573, + "step": 1503744 + }, + { + "epoch": 1.02, + "learning_rate": 2.537278157292859e-05, + "loss": 3.4765, + "step": 1504256 + }, + { + "epoch": 1.02, + "learning_rate": 2.53644120042218e-05, + "loss": 3.4737, + "step": 1504768 + }, + { + "epoch": 1.02, + "learning_rate": 2.5356042435515015e-05, + "loss": 3.4773, + "step": 1505280 + }, + { + "epoch": 1.02, + "learning_rate": 2.5347656488004494e-05, + "loss": 3.4601, + "step": 1505792 + }, + { + "epoch": 1.02, + "learning_rate": 2.533927054049397e-05, + "loss": 3.4855, + "step": 1506304 + }, + { + "epoch": 1.02, + "learning_rate": 2.533088459298345e-05, + "loss": 3.4681, + "step": 1506816 + }, + { + "epoch": 1.02, + "learning_rate": 2.532249864547293e-05, + "loss": 3.482, + "step": 1507328 + }, + { + "epoch": 1.02, + "learning_rate": 2.531411269796241e-05, + "loss": 3.476, + "step": 1507840 + }, + { + "epoch": 1.02, + "learning_rate": 2.530572675045189e-05, + "loss": 3.4714, + "step": 1508352 + }, + { + "epoch": 1.02, + "learning_rate": 2.52973571817451e-05, + "loss": 3.49, + "step": 1508864 + }, + { + "epoch": 1.02, + "learning_rate": 2.5288987613038316e-05, + "loss": 3.4999, + "step": 1509376 + }, + { + "epoch": 1.02, + "learning_rate": 2.52806016655278e-05, + "loss": 3.481, + "step": 1509888 + }, + { + "epoch": 1.02, + "learning_rate": 2.5272215718017272e-05, + "loss": 3.4705, + "step": 1510400 + }, + { + "epoch": 1.02, + "learning_rate": 2.5263829770506752e-05, + "loss": 3.4827, + "step": 1510912 + }, + { + "epoch": 1.02, + "learning_rate": 2.5255443822996232e-05, + "loss": 3.4746, + "step": 1511424 + }, + { + "epoch": 1.02, + "learning_rate": 2.5247074254289445e-05, + "loss": 3.4745, + "step": 1511936 + }, + { + "epoch": 1.02, + "learning_rate": 2.5238688306778925e-05, + "loss": 3.4856, + "step": 1512448 + }, + { + "epoch": 1.02, + "learning_rate": 2.5230302359268405e-05, + "loss": 3.4714, + "step": 1512960 + }, + { + "epoch": 1.02, + "learning_rate": 2.5221916411757885e-05, + "loss": 3.4882, + "step": 1513472 + }, + { + "epoch": 1.02, + "learning_rate": 2.5213530464247365e-05, + "loss": 3.4808, + "step": 1513984 + }, + { + "epoch": 1.02, + "learning_rate": 2.5205160895540574e-05, + "loss": 3.4809, + "step": 1514496 + }, + { + "epoch": 1.02, + "learning_rate": 2.5196774948030054e-05, + "loss": 3.4666, + "step": 1515008 + }, + { + "epoch": 1.02, + "learning_rate": 2.5188389000519537e-05, + "loss": 3.4806, + "step": 1515520 + }, + { + "epoch": 1.02, + "learning_rate": 2.5180003053009017e-05, + "loss": 3.4722, + "step": 1516032 + }, + { + "epoch": 1.02, + "learning_rate": 2.5171617105498497e-05, + "loss": 3.4854, + "step": 1516544 + }, + { + "epoch": 1.02, + "learning_rate": 2.5163247536791706e-05, + "loss": 3.4809, + "step": 1517056 + }, + { + "epoch": 1.02, + "learning_rate": 2.5154861589281186e-05, + "loss": 3.4847, + "step": 1517568 + }, + { + "epoch": 1.02, + "learning_rate": 2.5146475641770666e-05, + "loss": 3.4625, + "step": 1518080 + }, + { + "epoch": 1.02, + "learning_rate": 2.5138089694260146e-05, + "loss": 3.4874, + "step": 1518592 + }, + { + "epoch": 1.02, + "learning_rate": 2.512970374674963e-05, + "loss": 3.4758, + "step": 1519104 + }, + { + "epoch": 1.02, + "learning_rate": 2.512131779923911e-05, + "loss": 3.4782, + "step": 1519616 + }, + { + "epoch": 1.02, + "learning_rate": 2.511293185172859e-05, + "loss": 3.4765, + "step": 1520128 + }, + { + "epoch": 1.02, + "learning_rate": 2.510454590421807e-05, + "loss": 3.4858, + "step": 1520640 + }, + { + "epoch": 1.02, + "learning_rate": 2.5096176335511278e-05, + "loss": 3.4844, + "step": 1521152 + }, + { + "epoch": 1.02, + "learning_rate": 2.5087790388000758e-05, + "loss": 3.4852, + "step": 1521664 + }, + { + "epoch": 1.02, + "learning_rate": 2.507942081929397e-05, + "loss": 3.4729, + "step": 1522176 + }, + { + "epoch": 1.02, + "learning_rate": 2.507103487178345e-05, + "loss": 3.4782, + "step": 1522688 + }, + { + "epoch": 1.02, + "learning_rate": 2.506264892427293e-05, + "loss": 3.476, + "step": 1523200 + }, + { + "epoch": 1.02, + "learning_rate": 2.505426297676241e-05, + "loss": 3.4698, + "step": 1523712 + }, + { + "epoch": 1.02, + "learning_rate": 2.504587702925189e-05, + "loss": 3.4803, + "step": 1524224 + }, + { + "epoch": 1.02, + "learning_rate": 2.503749108174137e-05, + "loss": 3.4904, + "step": 1524736 + }, + { + "epoch": 1.02, + "learning_rate": 2.5029121513034583e-05, + "loss": 3.4797, + "step": 1525248 + }, + { + "epoch": 1.02, + "learning_rate": 2.5020735565524063e-05, + "loss": 3.4677, + "step": 1525760 + }, + { + "epoch": 1.02, + "learning_rate": 2.5012349618013543e-05, + "loss": 3.4786, + "step": 1526272 + }, + { + "epoch": 1.03, + "eval_loss": 3.849599838256836, + "eval_runtime": 305.5078, + "eval_samples_per_second": 1249.038, + "eval_steps_per_second": 39.033, + "step": 1526400 + }, + { + "epoch": 0.0, + "learning_rate": 2.5003963670503023e-05, + "loss": 3.4662, + "step": 1526784 + }, + { + "epoch": 0.0, + "learning_rate": 2.49955777229925e-05, + "loss": 3.4723, + "step": 1527296 + }, + { + "epoch": 0.0, + "learning_rate": 2.498719177548198e-05, + "loss": 3.4785, + "step": 1527808 + }, + { + "epoch": 0.0, + "learning_rate": 2.497880582797146e-05, + "loss": 3.4765, + "step": 1528320 + }, + { + "epoch": 0.0, + "learning_rate": 2.4970436259264672e-05, + "loss": 3.4874, + "step": 1528832 + }, + { + "epoch": 0.0, + "learning_rate": 2.496205031175415e-05, + "loss": 3.4673, + "step": 1529344 + }, + { + "epoch": 0.0, + "learning_rate": 2.495366436424363e-05, + "loss": 3.4781, + "step": 1529856 + }, + { + "epoch": 0.0, + "learning_rate": 2.494527841673311e-05, + "loss": 3.4648, + "step": 1530368 + }, + { + "epoch": 0.0, + "learning_rate": 2.4936925226830053e-05, + "loss": 3.4812, + "step": 1530880 + }, + { + "epoch": 0.0, + "learning_rate": 2.4928539279319537e-05, + "loss": 3.4722, + "step": 1531392 + }, + { + "epoch": 0.0, + "learning_rate": 2.4920153331809016e-05, + "loss": 3.4709, + "step": 1531904 + }, + { + "epoch": 0.0, + "learning_rate": 2.4911767384298493e-05, + "loss": 3.4868, + "step": 1532416 + }, + { + "epoch": 0.0, + "learning_rate": 2.4903381436787973e-05, + "loss": 3.4656, + "step": 1532928 + }, + { + "epoch": 0.0, + "learning_rate": 2.4895011868081186e-05, + "loss": 3.4774, + "step": 1533440 + }, + { + "epoch": 0.0, + "learning_rate": 2.4886625920570662e-05, + "loss": 3.4719, + "step": 1533952 + }, + { + "epoch": 0.0, + "learning_rate": 2.4878239973060145e-05, + "loss": 3.4723, + "step": 1534464 + }, + { + "epoch": 0.0, + "learning_rate": 2.4869854025549625e-05, + "loss": 3.4641, + "step": 1534976 + }, + { + "epoch": 0.0, + "learning_rate": 2.4861468078039105e-05, + "loss": 3.4701, + "step": 1535488 + }, + { + "epoch": 0.0, + "learning_rate": 2.4853082130528585e-05, + "loss": 3.4688, + "step": 1536000 + }, + { + "epoch": 0.0, + "learning_rate": 2.4844696183018065e-05, + "loss": 3.488, + "step": 1536512 + }, + { + "epoch": 0.0, + "learning_rate": 2.4836326614311274e-05, + "loss": 3.4714, + "step": 1537024 + }, + { + "epoch": 0.0, + "learning_rate": 2.4827940666800754e-05, + "loss": 3.4771, + "step": 1537536 + }, + { + "epoch": 0.0, + "learning_rate": 2.4819554719290238e-05, + "loss": 3.4831, + "step": 1538048 + }, + { + "epoch": 0.0, + "learning_rate": 2.4811168771779718e-05, + "loss": 3.4816, + "step": 1538560 + }, + { + "epoch": 0.0, + "learning_rate": 2.4802799203072927e-05, + "loss": 3.4609, + "step": 1539072 + }, + { + "epoch": 0.0, + "learning_rate": 2.4794413255562407e-05, + "loss": 3.4765, + "step": 1539584 + }, + { + "epoch": 0.0, + "learning_rate": 2.4786027308051887e-05, + "loss": 3.467, + "step": 1540096 + }, + { + "epoch": 0.0, + "learning_rate": 2.4777641360541367e-05, + "loss": 3.4743, + "step": 1540608 + }, + { + "epoch": 0.0, + "learning_rate": 2.476927179183458e-05, + "loss": 3.461, + "step": 1541120 + }, + { + "epoch": 0.0, + "learning_rate": 2.4760902223127788e-05, + "loss": 3.4701, + "step": 1541632 + }, + { + "epoch": 0.01, + "learning_rate": 2.4752516275617268e-05, + "loss": 3.4781, + "step": 1542144 + }, + { + "epoch": 0.01, + "learning_rate": 2.4744130328106748e-05, + "loss": 3.4747, + "step": 1542656 + }, + { + "epoch": 0.01, + "learning_rate": 2.4735744380596228e-05, + "loss": 3.4695, + "step": 1543168 + }, + { + "epoch": 0.01, + "learning_rate": 2.4727358433085708e-05, + "loss": 3.4797, + "step": 1543680 + }, + { + "epoch": 0.01, + "learning_rate": 2.471898886437892e-05, + "loss": 3.4701, + "step": 1544192 + }, + { + "epoch": 0.01, + "learning_rate": 2.47106029168684e-05, + "loss": 3.4763, + "step": 1544704 + }, + { + "epoch": 0.01, + "learning_rate": 2.470221696935788e-05, + "loss": 3.4595, + "step": 1545216 + }, + { + "epoch": 0.01, + "learning_rate": 2.469383102184736e-05, + "loss": 3.4759, + "step": 1545728 + }, + { + "epoch": 0.01, + "learning_rate": 2.468546145314057e-05, + "loss": 3.462, + "step": 1546240 + }, + { + "epoch": 0.01, + "learning_rate": 2.4677075505630053e-05, + "loss": 3.466, + "step": 1546752 + }, + { + "epoch": 0.01, + "learning_rate": 2.4668689558119533e-05, + "loss": 3.4639, + "step": 1547264 + }, + { + "epoch": 0.01, + "learning_rate": 2.4660303610609013e-05, + "loss": 3.4806, + "step": 1547776 + }, + { + "epoch": 0.01, + "learning_rate": 2.4651934041902222e-05, + "loss": 3.4774, + "step": 1548288 + }, + { + "epoch": 0.01, + "learning_rate": 2.4643548094391702e-05, + "loss": 3.4736, + "step": 1548800 + }, + { + "epoch": 0.01, + "learning_rate": 2.463516214688118e-05, + "loss": 3.4782, + "step": 1549312 + }, + { + "epoch": 0.01, + "learning_rate": 2.462677619937066e-05, + "loss": 3.4788, + "step": 1549824 + }, + { + "epoch": 0.01, + "learning_rate": 2.461839025186014e-05, + "loss": 3.4702, + "step": 1550336 + }, + { + "epoch": 0.01, + "learning_rate": 2.461000430434962e-05, + "loss": 3.4652, + "step": 1550848 + }, + { + "epoch": 0.01, + "learning_rate": 2.46016183568391e-05, + "loss": 3.4555, + "step": 1551360 + }, + { + "epoch": 0.01, + "learning_rate": 2.459323240932858e-05, + "loss": 3.4813, + "step": 1551872 + }, + { + "epoch": 0.01, + "learning_rate": 2.458486284062179e-05, + "loss": 3.466, + "step": 1552384 + }, + { + "epoch": 0.01, + "learning_rate": 2.457647689311127e-05, + "loss": 3.4625, + "step": 1552896 + }, + { + "epoch": 0.01, + "learning_rate": 2.4568090945600754e-05, + "loss": 3.4644, + "step": 1553408 + }, + { + "epoch": 0.01, + "learning_rate": 2.4559704998090234e-05, + "loss": 3.4683, + "step": 1553920 + }, + { + "epoch": 0.01, + "learning_rate": 2.4551319050579714e-05, + "loss": 3.4561, + "step": 1554432 + }, + { + "epoch": 0.01, + "learning_rate": 2.4542933103069194e-05, + "loss": 3.4628, + "step": 1554944 + }, + { + "epoch": 0.01, + "learning_rate": 2.4534547155558674e-05, + "loss": 3.4661, + "step": 1555456 + }, + { + "epoch": 0.01, + "learning_rate": 2.452616120804815e-05, + "loss": 3.468, + "step": 1555968 + }, + { + "epoch": 0.01, + "learning_rate": 2.4517808018145095e-05, + "loss": 3.4776, + "step": 1556480 + }, + { + "epoch": 0.01, + "learning_rate": 2.4509422070634575e-05, + "loss": 3.4591, + "step": 1556992 + }, + { + "epoch": 0.01, + "learning_rate": 2.4501036123124055e-05, + "loss": 3.4613, + "step": 1557504 + }, + { + "epoch": 0.01, + "learning_rate": 2.4492650175613535e-05, + "loss": 3.4743, + "step": 1558016 + }, + { + "epoch": 0.01, + "learning_rate": 2.4484264228103015e-05, + "loss": 3.4584, + "step": 1558528 + }, + { + "epoch": 0.01, + "learning_rate": 2.4475878280592495e-05, + "loss": 3.4634, + "step": 1559040 + }, + { + "epoch": 0.01, + "learning_rate": 2.4467492333081975e-05, + "loss": 3.4718, + "step": 1559552 + }, + { + "epoch": 0.01, + "learning_rate": 2.4459106385571455e-05, + "loss": 3.4736, + "step": 1560064 + }, + { + "epoch": 0.01, + "learning_rate": 2.4450736816864667e-05, + "loss": 3.4621, + "step": 1560576 + }, + { + "epoch": 0.01, + "learning_rate": 2.4442350869354147e-05, + "loss": 3.4535, + "step": 1561088 + }, + { + "epoch": 0.01, + "learning_rate": 2.4433964921843624e-05, + "loss": 3.4585, + "step": 1561600 + }, + { + "epoch": 0.01, + "learning_rate": 2.4425578974333104e-05, + "loss": 3.4689, + "step": 1562112 + }, + { + "epoch": 0.01, + "learning_rate": 2.4417209405626316e-05, + "loss": 3.477, + "step": 1562624 + }, + { + "epoch": 0.01, + "learning_rate": 2.4408823458115796e-05, + "loss": 3.4645, + "step": 1563136 + }, + { + "epoch": 0.01, + "learning_rate": 2.4400437510605276e-05, + "loss": 3.4787, + "step": 1563648 + }, + { + "epoch": 0.01, + "learning_rate": 2.439206794189849e-05, + "loss": 3.4756, + "step": 1564160 + }, + { + "epoch": 0.01, + "learning_rate": 2.438368199438797e-05, + "loss": 3.4803, + "step": 1564672 + }, + { + "epoch": 0.01, + "learning_rate": 2.4375296046877445e-05, + "loss": 3.4604, + "step": 1565184 + }, + { + "epoch": 0.01, + "learning_rate": 2.4366910099366925e-05, + "loss": 3.4748, + "step": 1565696 + }, + { + "epoch": 0.01, + "learning_rate": 2.435852415185641e-05, + "loss": 3.47, + "step": 1566208 + }, + { + "epoch": 0.01, + "learning_rate": 2.435015458314962e-05, + "loss": 3.4624, + "step": 1566720 + }, + { + "epoch": 0.01, + "learning_rate": 2.4341768635639098e-05, + "loss": 3.4743, + "step": 1567232 + }, + { + "epoch": 0.01, + "learning_rate": 2.4333382688128578e-05, + "loss": 3.4697, + "step": 1567744 + }, + { + "epoch": 0.01, + "learning_rate": 2.4324996740618058e-05, + "loss": 3.4698, + "step": 1568256 + }, + { + "epoch": 0.01, + "learning_rate": 2.4316610793107538e-05, + "loss": 3.4698, + "step": 1568768 + }, + { + "epoch": 0.01, + "learning_rate": 2.430824122440075e-05, + "loss": 3.4645, + "step": 1569280 + }, + { + "epoch": 0.01, + "learning_rate": 2.429985527689023e-05, + "loss": 3.4711, + "step": 1569792 + }, + { + "epoch": 0.01, + "learning_rate": 2.429146932937971e-05, + "loss": 3.4629, + "step": 1570304 + }, + { + "epoch": 0.01, + "learning_rate": 2.428308338186919e-05, + "loss": 3.4701, + "step": 1570816 + }, + { + "epoch": 0.01, + "learning_rate": 2.42747138131624e-05, + "loss": 3.4633, + "step": 1571328 + }, + { + "epoch": 0.01, + "learning_rate": 2.426632786565188e-05, + "loss": 3.4657, + "step": 1571840 + }, + { + "epoch": 0.02, + "learning_rate": 2.4257941918141362e-05, + "loss": 3.4724, + "step": 1572352 + }, + { + "epoch": 0.02, + "learning_rate": 2.4249555970630842e-05, + "loss": 3.4676, + "step": 1572864 + }, + { + "epoch": 0.02, + "learning_rate": 2.4241170023120322e-05, + "loss": 3.4598, + "step": 1573376 + }, + { + "epoch": 0.02, + "learning_rate": 2.423280045441353e-05, + "loss": 3.4612, + "step": 1573888 + }, + { + "epoch": 0.02, + "learning_rate": 2.422441450690301e-05, + "loss": 3.4798, + "step": 1574400 + }, + { + "epoch": 0.02, + "learning_rate": 2.421602855939249e-05, + "loss": 3.4738, + "step": 1574912 + }, + { + "epoch": 0.02, + "learning_rate": 2.420764261188197e-05, + "loss": 3.4707, + "step": 1575424 + }, + { + "epoch": 0.02, + "learning_rate": 2.419925666437145e-05, + "loss": 3.4591, + "step": 1575936 + }, + { + "epoch": 0.02, + "learning_rate": 2.4190887095664664e-05, + "loss": 3.4687, + "step": 1576448 + }, + { + "epoch": 0.02, + "learning_rate": 2.4182501148154144e-05, + "loss": 3.4597, + "step": 1576960 + }, + { + "epoch": 0.02, + "learning_rate": 2.4174115200643623e-05, + "loss": 3.4765, + "step": 1577472 + }, + { + "epoch": 0.02, + "learning_rate": 2.41657292531331e-05, + "loss": 3.4721, + "step": 1577984 + }, + { + "epoch": 0.02, + "learning_rate": 2.4157343305622583e-05, + "loss": 3.4635, + "step": 1578496 + }, + { + "epoch": 0.02, + "learning_rate": 2.4148957358112063e-05, + "loss": 3.4597, + "step": 1579008 + }, + { + "epoch": 0.02, + "learning_rate": 2.4140571410601543e-05, + "loss": 3.4712, + "step": 1579520 + }, + { + "epoch": 0.02, + "learning_rate": 2.4132185463091023e-05, + "loss": 3.444, + "step": 1580032 + }, + { + "epoch": 0.02, + "learning_rate": 2.4123815894384232e-05, + "loss": 3.4678, + "step": 1580544 + }, + { + "epoch": 0.02, + "learning_rate": 2.4115429946873712e-05, + "loss": 3.4612, + "step": 1581056 + }, + { + "epoch": 0.02, + "learning_rate": 2.4107043999363192e-05, + "loss": 3.4665, + "step": 1581568 + }, + { + "epoch": 0.02, + "learning_rate": 2.4098658051852672e-05, + "loss": 3.4525, + "step": 1582080 + }, + { + "epoch": 0.02, + "learning_rate": 2.4090272104342156e-05, + "loss": 3.4706, + "step": 1582592 + }, + { + "epoch": 0.02, + "learning_rate": 2.4081886156831632e-05, + "loss": 3.4609, + "step": 1583104 + }, + { + "epoch": 0.02, + "learning_rate": 2.4073516588124845e-05, + "loss": 3.4652, + "step": 1583616 + }, + { + "epoch": 0.02, + "learning_rate": 2.4065130640614325e-05, + "loss": 3.4694, + "step": 1584128 + }, + { + "epoch": 0.02, + "learning_rate": 2.4056744693103805e-05, + "loss": 3.4578, + "step": 1584640 + }, + { + "epoch": 0.02, + "learning_rate": 2.4048358745593284e-05, + "loss": 3.4795, + "step": 1585152 + }, + { + "epoch": 0.02, + "learning_rate": 2.4039972798082764e-05, + "loss": 3.4891, + "step": 1585664 + }, + { + "epoch": 0.02, + "learning_rate": 2.4031586850572244e-05, + "loss": 3.4688, + "step": 1586176 + }, + { + "epoch": 0.02, + "learning_rate": 2.4023217281865454e-05, + "loss": 3.4575, + "step": 1586688 + }, + { + "epoch": 0.02, + "learning_rate": 2.4014831334354933e-05, + "loss": 3.472, + "step": 1587200 + }, + { + "epoch": 0.02, + "learning_rate": 2.4006445386844413e-05, + "loss": 3.4641, + "step": 1587712 + }, + { + "epoch": 0.02, + "learning_rate": 2.3998059439333893e-05, + "loss": 3.46, + "step": 1588224 + }, + { + "epoch": 0.02, + "learning_rate": 2.3989689870627106e-05, + "loss": 3.4762, + "step": 1588736 + }, + { + "epoch": 0.02, + "learning_rate": 2.3981303923116586e-05, + "loss": 3.4577, + "step": 1589248 + }, + { + "epoch": 0.02, + "learning_rate": 2.3972917975606066e-05, + "loss": 3.474, + "step": 1589760 + }, + { + "epoch": 0.02, + "learning_rate": 2.3964532028095546e-05, + "loss": 3.468, + "step": 1590272 + }, + { + "epoch": 0.02, + "learning_rate": 2.3956146080585026e-05, + "loss": 3.4692, + "step": 1590784 + }, + { + "epoch": 0.02, + "learning_rate": 2.3947760133074506e-05, + "loss": 3.4607, + "step": 1591296 + }, + { + "epoch": 0.02, + "learning_rate": 2.3939374185563986e-05, + "loss": 3.4663, + "step": 1591808 + }, + { + "epoch": 0.02, + "learning_rate": 2.3930988238053466e-05, + "loss": 3.465, + "step": 1592320 + }, + { + "epoch": 0.02, + "learning_rate": 2.3922618669346678e-05, + "loss": 3.4727, + "step": 1592832 + }, + { + "epoch": 0.02, + "learning_rate": 2.3914249100639887e-05, + "loss": 3.4673, + "step": 1593344 + }, + { + "epoch": 0.02, + "learning_rate": 2.3905863153129367e-05, + "loss": 3.471, + "step": 1593856 + }, + { + "epoch": 0.02, + "learning_rate": 2.3897477205618847e-05, + "loss": 3.4536, + "step": 1594368 + }, + { + "epoch": 0.02, + "learning_rate": 2.388909125810833e-05, + "loss": 3.4758, + "step": 1594880 + }, + { + "epoch": 0.02, + "learning_rate": 2.388070531059781e-05, + "loss": 3.4639, + "step": 1595392 + }, + { + "epoch": 0.02, + "learning_rate": 2.3872319363087287e-05, + "loss": 3.4719, + "step": 1595904 + }, + { + "epoch": 0.02, + "learning_rate": 2.3863933415576767e-05, + "loss": 3.4625, + "step": 1596416 + }, + { + "epoch": 0.02, + "learning_rate": 2.385556384686998e-05, + "loss": 3.4754, + "step": 1596928 + }, + { + "epoch": 0.02, + "learning_rate": 2.384717789935946e-05, + "loss": 3.471, + "step": 1597440 + }, + { + "epoch": 0.02, + "learning_rate": 2.383879195184894e-05, + "loss": 3.478, + "step": 1597952 + }, + { + "epoch": 0.02, + "learning_rate": 2.383040600433842e-05, + "loss": 3.4573, + "step": 1598464 + }, + { + "epoch": 0.02, + "learning_rate": 2.38220200568279e-05, + "loss": 3.4692, + "step": 1598976 + }, + { + "epoch": 0.02, + "learning_rate": 2.3813650488121108e-05, + "loss": 3.4658, + "step": 1599488 + }, + { + "epoch": 0.02, + "learning_rate": 2.3805264540610588e-05, + "loss": 3.4595, + "step": 1600000 + }, + { + "epoch": 0.02, + "learning_rate": 2.3796878593100068e-05, + "loss": 3.4699, + "step": 1600512 + }, + { + "epoch": 0.02, + "learning_rate": 2.3788492645589548e-05, + "loss": 3.4756, + "step": 1601024 + }, + { + "epoch": 0.02, + "learning_rate": 2.378010669807903e-05, + "loss": 3.4747, + "step": 1601536 + }, + { + "epoch": 0.02, + "learning_rate": 2.377172075056851e-05, + "loss": 3.4508, + "step": 1602048 + }, + { + "epoch": 0.02, + "learning_rate": 2.376333480305799e-05, + "loss": 3.4687, + "step": 1602560 + }, + { + "epoch": 0.03, + "eval_loss": 3.8518857955932617, + "eval_runtime": 303.5477, + "eval_samples_per_second": 1257.104, + "eval_steps_per_second": 39.285, + "step": 1602720 + }, + { + "epoch": 0.0, + "learning_rate": 2.3754948855547468e-05, + "loss": 3.4583, + "step": 1603072 + }, + { + "epoch": 0.0, + "learning_rate": 2.3746562908036948e-05, + "loss": 3.4581, + "step": 1603584 + }, + { + "epoch": 0.0, + "learning_rate": 2.373819333933016e-05, + "loss": 3.4692, + "step": 1604096 + }, + { + "epoch": 0.0, + "learning_rate": 2.372980739181964e-05, + "loss": 3.4664, + "step": 1604608 + }, + { + "epoch": 0.0, + "learning_rate": 2.372142144430912e-05, + "loss": 3.4691, + "step": 1605120 + }, + { + "epoch": 0.0, + "learning_rate": 2.37130354967986e-05, + "loss": 3.4608, + "step": 1605632 + }, + { + "epoch": 0.0, + "learning_rate": 2.370464954928808e-05, + "loss": 3.4659, + "step": 1606144 + }, + { + "epoch": 0.0, + "learning_rate": 2.369627998058129e-05, + "loss": 3.4552, + "step": 1606656 + }, + { + "epoch": 0.0, + "learning_rate": 2.368789403307077e-05, + "loss": 3.4689, + "step": 1607168 + }, + { + "epoch": 0.0, + "learning_rate": 2.367950808556025e-05, + "loss": 3.4635, + "step": 1607680 + }, + { + "epoch": 0.0, + "learning_rate": 2.3671122138049733e-05, + "loss": 3.4609, + "step": 1608192 + }, + { + "epoch": 0.0, + "learning_rate": 2.366275256934294e-05, + "loss": 3.475, + "step": 1608704 + }, + { + "epoch": 0.0, + "learning_rate": 2.365436662183242e-05, + "loss": 3.4556, + "step": 1609216 + }, + { + "epoch": 0.0, + "learning_rate": 2.36459806743219e-05, + "loss": 3.4655, + "step": 1609728 + }, + { + "epoch": 0.0, + "learning_rate": 2.363759472681138e-05, + "loss": 3.4605, + "step": 1610240 + }, + { + "epoch": 0.0, + "learning_rate": 2.362920877930086e-05, + "loss": 3.4582, + "step": 1610752 + }, + { + "epoch": 0.0, + "learning_rate": 2.362082283179034e-05, + "loss": 3.4501, + "step": 1611264 + }, + { + "epoch": 0.0, + "learning_rate": 2.361243688427982e-05, + "loss": 3.4606, + "step": 1611776 + }, + { + "epoch": 0.0, + "learning_rate": 2.3604067315573034e-05, + "loss": 3.4544, + "step": 1612288 + }, + { + "epoch": 0.0, + "learning_rate": 2.3595681368062514e-05, + "loss": 3.475, + "step": 1612800 + }, + { + "epoch": 0.0, + "learning_rate": 2.3587295420551994e-05, + "loss": 3.463, + "step": 1613312 + }, + { + "epoch": 0.0, + "learning_rate": 2.357890947304147e-05, + "loss": 3.4645, + "step": 1613824 + }, + { + "epoch": 0.0, + "learning_rate": 2.357052352553095e-05, + "loss": 3.4731, + "step": 1614336 + }, + { + "epoch": 0.0, + "learning_rate": 2.3562137578020434e-05, + "loss": 3.4686, + "step": 1614848 + }, + { + "epoch": 0.0, + "learning_rate": 2.3553751630509914e-05, + "loss": 3.4503, + "step": 1615360 + }, + { + "epoch": 0.0, + "learning_rate": 2.3545365682999394e-05, + "loss": 3.4652, + "step": 1615872 + }, + { + "epoch": 0.0, + "learning_rate": 2.3536996114292603e-05, + "loss": 3.4576, + "step": 1616384 + }, + { + "epoch": 0.0, + "learning_rate": 2.3528610166782083e-05, + "loss": 3.4611, + "step": 1616896 + }, + { + "epoch": 0.0, + "learning_rate": 2.3520224219271563e-05, + "loss": 3.4503, + "step": 1617408 + }, + { + "epoch": 0.0, + "learning_rate": 2.3511854650564775e-05, + "loss": 3.4597, + "step": 1617920 + }, + { + "epoch": 0.01, + "learning_rate": 2.3503468703054255e-05, + "loss": 3.4675, + "step": 1618432 + }, + { + "epoch": 0.01, + "learning_rate": 2.3495082755543735e-05, + "loss": 3.4614, + "step": 1618944 + }, + { + "epoch": 0.01, + "learning_rate": 2.3486696808033215e-05, + "loss": 3.4593, + "step": 1619456 + }, + { + "epoch": 0.01, + "learning_rate": 2.3478310860522695e-05, + "loss": 3.4652, + "step": 1619968 + }, + { + "epoch": 0.01, + "learning_rate": 2.3469924913012175e-05, + "loss": 3.4601, + "step": 1620480 + }, + { + "epoch": 0.01, + "learning_rate": 2.3461555344305387e-05, + "loss": 3.4629, + "step": 1620992 + }, + { + "epoch": 0.01, + "learning_rate": 2.3453169396794867e-05, + "loss": 3.4525, + "step": 1621504 + }, + { + "epoch": 0.01, + "learning_rate": 2.3444783449284347e-05, + "loss": 3.4557, + "step": 1622016 + }, + { + "epoch": 0.01, + "learning_rate": 2.3436397501773827e-05, + "loss": 3.4564, + "step": 1622528 + }, + { + "epoch": 0.01, + "learning_rate": 2.3428011554263304e-05, + "loss": 3.4541, + "step": 1623040 + }, + { + "epoch": 0.01, + "learning_rate": 2.3419625606752784e-05, + "loss": 3.4544, + "step": 1623552 + }, + { + "epoch": 0.01, + "learning_rate": 2.3411239659242264e-05, + "loss": 3.4673, + "step": 1624064 + }, + { + "epoch": 0.01, + "learning_rate": 2.3402870090535476e-05, + "loss": 3.4645, + "step": 1624576 + }, + { + "epoch": 0.01, + "learning_rate": 2.3394484143024956e-05, + "loss": 3.4641, + "step": 1625088 + }, + { + "epoch": 0.01, + "learning_rate": 2.3386098195514436e-05, + "loss": 3.4715, + "step": 1625600 + }, + { + "epoch": 0.01, + "learning_rate": 2.3377712248003916e-05, + "loss": 3.4622, + "step": 1626112 + }, + { + "epoch": 0.01, + "learning_rate": 2.3369326300493396e-05, + "loss": 3.4619, + "step": 1626624 + }, + { + "epoch": 0.01, + "learning_rate": 2.336095673178661e-05, + "loss": 3.4533, + "step": 1627136 + }, + { + "epoch": 0.01, + "learning_rate": 2.335257078427609e-05, + "loss": 3.441, + "step": 1627648 + }, + { + "epoch": 0.01, + "learning_rate": 2.334418483676557e-05, + "loss": 3.4715, + "step": 1628160 + }, + { + "epoch": 0.01, + "learning_rate": 2.333579888925505e-05, + "loss": 3.4558, + "step": 1628672 + }, + { + "epoch": 0.01, + "learning_rate": 2.3327412941744528e-05, + "loss": 3.4546, + "step": 1629184 + }, + { + "epoch": 0.01, + "learning_rate": 2.3319026994234008e-05, + "loss": 3.4523, + "step": 1629696 + }, + { + "epoch": 0.01, + "learning_rate": 2.3310641046723485e-05, + "loss": 3.4556, + "step": 1630208 + }, + { + "epoch": 0.01, + "learning_rate": 2.3302255099212965e-05, + "loss": 3.4468, + "step": 1630720 + }, + { + "epoch": 0.01, + "learning_rate": 2.329390190930991e-05, + "loss": 3.4539, + "step": 1631232 + }, + { + "epoch": 0.01, + "learning_rate": 2.328551596179939e-05, + "loss": 3.4561, + "step": 1631744 + }, + { + "epoch": 0.01, + "learning_rate": 2.327713001428887e-05, + "loss": 3.4547, + "step": 1632256 + }, + { + "epoch": 0.01, + "learning_rate": 2.326874406677835e-05, + "loss": 3.464, + "step": 1632768 + }, + { + "epoch": 0.01, + "learning_rate": 2.326035811926783e-05, + "loss": 3.4467, + "step": 1633280 + }, + { + "epoch": 0.01, + "learning_rate": 2.325197217175731e-05, + "loss": 3.4509, + "step": 1633792 + }, + { + "epoch": 0.01, + "learning_rate": 2.3243602603050522e-05, + "loss": 3.4641, + "step": 1634304 + }, + { + "epoch": 0.01, + "learning_rate": 2.3235216655540002e-05, + "loss": 3.4475, + "step": 1634816 + }, + { + "epoch": 0.01, + "learning_rate": 2.3226830708029482e-05, + "loss": 3.4489, + "step": 1635328 + }, + { + "epoch": 0.01, + "learning_rate": 2.321844476051896e-05, + "loss": 3.4572, + "step": 1635840 + }, + { + "epoch": 0.01, + "learning_rate": 2.321005881300844e-05, + "loss": 3.4624, + "step": 1636352 + }, + { + "epoch": 0.01, + "learning_rate": 2.320167286549792e-05, + "loss": 3.4486, + "step": 1636864 + }, + { + "epoch": 0.01, + "learning_rate": 2.3193286917987402e-05, + "loss": 3.4473, + "step": 1637376 + }, + { + "epoch": 0.01, + "learning_rate": 2.3184900970476882e-05, + "loss": 3.4397, + "step": 1637888 + }, + { + "epoch": 0.01, + "learning_rate": 2.317653140177009e-05, + "loss": 3.4584, + "step": 1638400 + }, + { + "epoch": 0.01, + "learning_rate": 2.316814545425957e-05, + "loss": 3.4672, + "step": 1638912 + }, + { + "epoch": 0.01, + "learning_rate": 2.315975950674905e-05, + "loss": 3.4554, + "step": 1639424 + }, + { + "epoch": 0.01, + "learning_rate": 2.315137355923853e-05, + "loss": 3.4634, + "step": 1639936 + }, + { + "epoch": 0.01, + "learning_rate": 2.3143020369335476e-05, + "loss": 3.4636, + "step": 1640448 + }, + { + "epoch": 0.01, + "learning_rate": 2.3134634421824956e-05, + "loss": 3.4721, + "step": 1640960 + }, + { + "epoch": 0.01, + "learning_rate": 2.3126248474314432e-05, + "loss": 3.4486, + "step": 1641472 + }, + { + "epoch": 0.01, + "learning_rate": 2.3117862526803912e-05, + "loss": 3.4635, + "step": 1641984 + }, + { + "epoch": 0.01, + "learning_rate": 2.3109476579293392e-05, + "loss": 3.4573, + "step": 1642496 + }, + { + "epoch": 0.01, + "learning_rate": 2.3101090631782872e-05, + "loss": 3.4485, + "step": 1643008 + }, + { + "epoch": 0.01, + "learning_rate": 2.3092704684272355e-05, + "loss": 3.462, + "step": 1643520 + }, + { + "epoch": 0.01, + "learning_rate": 2.3084335115565565e-05, + "loss": 3.4601, + "step": 1644032 + }, + { + "epoch": 0.01, + "learning_rate": 2.3075949168055044e-05, + "loss": 3.4586, + "step": 1644544 + }, + { + "epoch": 0.01, + "learning_rate": 2.3067563220544524e-05, + "loss": 3.461, + "step": 1645056 + }, + { + "epoch": 0.01, + "learning_rate": 2.3059177273034004e-05, + "loss": 3.4536, + "step": 1645568 + }, + { + "epoch": 0.01, + "learning_rate": 2.3050791325523484e-05, + "loss": 3.4499, + "step": 1646080 + }, + { + "epoch": 0.01, + "learning_rate": 2.3042405378012964e-05, + "loss": 3.4539, + "step": 1646592 + }, + { + "epoch": 0.01, + "learning_rate": 2.3034019430502444e-05, + "loss": 3.4622, + "step": 1647104 + }, + { + "epoch": 0.01, + "learning_rate": 2.3025633482991924e-05, + "loss": 3.4467, + "step": 1647616 + }, + { + "epoch": 0.01, + "learning_rate": 2.3017263914285133e-05, + "loss": 3.4555, + "step": 1648128 + }, + { + "epoch": 0.02, + "learning_rate": 2.3008877966774613e-05, + "loss": 3.4615, + "step": 1648640 + }, + { + "epoch": 0.02, + "learning_rate": 2.3000492019264093e-05, + "loss": 3.4552, + "step": 1649152 + }, + { + "epoch": 0.02, + "learning_rate": 2.2992106071753573e-05, + "loss": 3.4475, + "step": 1649664 + }, + { + "epoch": 0.02, + "learning_rate": 2.2983736503046786e-05, + "loss": 3.4505, + "step": 1650176 + }, + { + "epoch": 0.02, + "learning_rate": 2.2975350555536266e-05, + "loss": 3.466, + "step": 1650688 + }, + { + "epoch": 0.02, + "learning_rate": 2.2966964608025746e-05, + "loss": 3.4627, + "step": 1651200 + }, + { + "epoch": 0.02, + "learning_rate": 2.2958578660515226e-05, + "loss": 3.4598, + "step": 1651712 + }, + { + "epoch": 0.02, + "learning_rate": 2.2950209091808435e-05, + "loss": 3.4437, + "step": 1652224 + }, + { + "epoch": 0.02, + "learning_rate": 2.2941823144297918e-05, + "loss": 3.4568, + "step": 1652736 + }, + { + "epoch": 0.02, + "learning_rate": 2.2933437196787398e-05, + "loss": 3.4525, + "step": 1653248 + }, + { + "epoch": 0.02, + "learning_rate": 2.2925051249276878e-05, + "loss": 3.4632, + "step": 1653760 + }, + { + "epoch": 0.02, + "learning_rate": 2.2916665301766358e-05, + "loss": 3.4608, + "step": 1654272 + }, + { + "epoch": 0.02, + "learning_rate": 2.2908279354255838e-05, + "loss": 3.4533, + "step": 1654784 + }, + { + "epoch": 0.02, + "learning_rate": 2.2899893406745314e-05, + "loss": 3.447, + "step": 1655296 + }, + { + "epoch": 0.02, + "learning_rate": 2.2891507459234794e-05, + "loss": 3.4584, + "step": 1655808 + }, + { + "epoch": 0.02, + "learning_rate": 2.288313789052801e-05, + "loss": 3.4349, + "step": 1656320 + }, + { + "epoch": 0.02, + "learning_rate": 2.287475194301749e-05, + "loss": 3.4542, + "step": 1656832 + }, + { + "epoch": 0.02, + "learning_rate": 2.2866365995506967e-05, + "loss": 3.4439, + "step": 1657344 + }, + { + "epoch": 0.02, + "learning_rate": 2.2857980047996447e-05, + "loss": 3.4585, + "step": 1657856 + }, + { + "epoch": 0.02, + "learning_rate": 2.2849594100485927e-05, + "loss": 3.4413, + "step": 1658368 + }, + { + "epoch": 0.02, + "learning_rate": 2.284122453177914e-05, + "loss": 3.4603, + "step": 1658880 + }, + { + "epoch": 0.02, + "learning_rate": 2.283283858426862e-05, + "loss": 3.4486, + "step": 1659392 + }, + { + "epoch": 0.02, + "learning_rate": 2.28244526367581e-05, + "loss": 3.4552, + "step": 1659904 + }, + { + "epoch": 0.02, + "learning_rate": 2.281606668924758e-05, + "loss": 3.4594, + "step": 1660416 + }, + { + "epoch": 0.02, + "learning_rate": 2.280768074173706e-05, + "loss": 3.4523, + "step": 1660928 + }, + { + "epoch": 0.02, + "learning_rate": 2.2799311173030268e-05, + "loss": 3.466, + "step": 1661440 + }, + { + "epoch": 0.02, + "learning_rate": 2.2790925225519748e-05, + "loss": 3.4735, + "step": 1661952 + }, + { + "epoch": 0.02, + "learning_rate": 2.2782539278009228e-05, + "loss": 3.4587, + "step": 1662464 + }, + { + "epoch": 0.02, + "learning_rate": 2.277415333049871e-05, + "loss": 3.4483, + "step": 1662976 + }, + { + "epoch": 0.02, + "learning_rate": 2.276578376179192e-05, + "loss": 3.4555, + "step": 1663488 + }, + { + "epoch": 0.02, + "learning_rate": 2.27573978142814e-05, + "loss": 3.4548, + "step": 1664000 + }, + { + "epoch": 0.02, + "learning_rate": 2.274901186677088e-05, + "loss": 3.4444, + "step": 1664512 + }, + { + "epoch": 0.02, + "learning_rate": 2.274062591926036e-05, + "loss": 3.4673, + "step": 1665024 + }, + { + "epoch": 0.02, + "learning_rate": 2.273223997174984e-05, + "loss": 3.4434, + "step": 1665536 + }, + { + "epoch": 0.02, + "learning_rate": 2.272385402423932e-05, + "loss": 3.4646, + "step": 1666048 + }, + { + "epoch": 0.02, + "learning_rate": 2.27154680767288e-05, + "loss": 3.4571, + "step": 1666560 + }, + { + "epoch": 0.02, + "learning_rate": 2.2707098508022013e-05, + "loss": 3.4574, + "step": 1667072 + }, + { + "epoch": 0.02, + "learning_rate": 2.2698712560511493e-05, + "loss": 3.448, + "step": 1667584 + }, + { + "epoch": 0.02, + "learning_rate": 2.269032661300097e-05, + "loss": 3.457, + "step": 1668096 + }, + { + "epoch": 0.02, + "learning_rate": 2.268194066549045e-05, + "loss": 3.4505, + "step": 1668608 + }, + { + "epoch": 0.02, + "learning_rate": 2.267355471797993e-05, + "loss": 3.4622, + "step": 1669120 + }, + { + "epoch": 0.02, + "learning_rate": 2.2665185149273145e-05, + "loss": 3.4558, + "step": 1669632 + }, + { + "epoch": 0.02, + "learning_rate": 2.265679920176262e-05, + "loss": 3.4627, + "step": 1670144 + }, + { + "epoch": 0.02, + "learning_rate": 2.26484132542521e-05, + "loss": 3.4414, + "step": 1670656 + }, + { + "epoch": 0.02, + "learning_rate": 2.264002730674158e-05, + "loss": 3.4669, + "step": 1671168 + }, + { + "epoch": 0.02, + "learning_rate": 2.263164135923106e-05, + "loss": 3.4511, + "step": 1671680 + }, + { + "epoch": 0.02, + "learning_rate": 2.262325541172054e-05, + "loss": 3.458, + "step": 1672192 + }, + { + "epoch": 0.02, + "learning_rate": 2.2614885843013754e-05, + "loss": 3.4522, + "step": 1672704 + }, + { + "epoch": 0.02, + "learning_rate": 2.2606499895503234e-05, + "loss": 3.4595, + "step": 1673216 + }, + { + "epoch": 0.02, + "learning_rate": 2.2598113947992714e-05, + "loss": 3.459, + "step": 1673728 + }, + { + "epoch": 0.02, + "learning_rate": 2.2589728000482194e-05, + "loss": 3.4722, + "step": 1674240 + }, + { + "epoch": 0.02, + "learning_rate": 2.2581342052971674e-05, + "loss": 3.4448, + "step": 1674752 + }, + { + "epoch": 0.02, + "learning_rate": 2.257295610546115e-05, + "loss": 3.4567, + "step": 1675264 + }, + { + "epoch": 0.02, + "learning_rate": 2.2564570157950634e-05, + "loss": 3.4529, + "step": 1675776 + }, + { + "epoch": 0.02, + "learning_rate": 2.2556200589243846e-05, + "loss": 3.4509, + "step": 1676288 + }, + { + "epoch": 0.02, + "learning_rate": 2.2547814641733326e-05, + "loss": 3.4526, + "step": 1676800 + }, + { + "epoch": 0.02, + "learning_rate": 2.2539428694222803e-05, + "loss": 3.4652, + "step": 1677312 + }, + { + "epoch": 0.02, + "learning_rate": 2.2531042746712282e-05, + "loss": 3.4634, + "step": 1677824 + }, + { + "epoch": 0.02, + "learning_rate": 2.2522656799201762e-05, + "loss": 3.4404, + "step": 1678336 + }, + { + "epoch": 0.02, + "learning_rate": 2.2514270851691242e-05, + "loss": 3.4584, + "step": 1678848 + }, + { + "epoch": 0.03, + "eval_loss": 3.852686643600464, + "eval_runtime": 302.9735, + "eval_samples_per_second": 1259.486, + "eval_steps_per_second": 39.36, + "step": 1679040 + }, + { + "epoch": 1.0, + "learning_rate": 2.2505884904180722e-05, + "loss": 3.4511, + "step": 1679360 + }, + { + "epoch": 1.0, + "learning_rate": 2.2497515335473935e-05, + "loss": 3.4417, + "step": 1679872 + }, + { + "epoch": 1.0, + "learning_rate": 2.2489129387963415e-05, + "loss": 3.4589, + "step": 1680384 + }, + { + "epoch": 1.0, + "learning_rate": 2.2480743440452895e-05, + "loss": 3.4539, + "step": 1680896 + }, + { + "epoch": 1.0, + "learning_rate": 2.2472373871746104e-05, + "loss": 3.46, + "step": 1681408 + }, + { + "epoch": 1.0, + "learning_rate": 2.2463987924235587e-05, + "loss": 3.4487, + "step": 1681920 + }, + { + "epoch": 1.0, + "learning_rate": 2.2455601976725067e-05, + "loss": 3.4487, + "step": 1682432 + }, + { + "epoch": 1.0, + "learning_rate": 2.2447216029214547e-05, + "loss": 3.447, + "step": 1682944 + }, + { + "epoch": 1.0, + "learning_rate": 2.2438846460507756e-05, + "loss": 3.4554, + "step": 1683456 + }, + { + "epoch": 1.0, + "learning_rate": 2.2430460512997236e-05, + "loss": 3.4512, + "step": 1683968 + }, + { + "epoch": 1.0, + "learning_rate": 2.2422074565486716e-05, + "loss": 3.453, + "step": 1684480 + }, + { + "epoch": 1.0, + "learning_rate": 2.2413688617976196e-05, + "loss": 3.4615, + "step": 1684992 + }, + { + "epoch": 1.0, + "learning_rate": 2.2405302670465676e-05, + "loss": 3.4472, + "step": 1685504 + }, + { + "epoch": 1.0, + "learning_rate": 2.2396916722955156e-05, + "loss": 3.4514, + "step": 1686016 + }, + { + "epoch": 1.0, + "learning_rate": 2.2388530775444636e-05, + "loss": 3.4526, + "step": 1686528 + }, + { + "epoch": 1.0, + "learning_rate": 2.2380144827934116e-05, + "loss": 3.4468, + "step": 1687040 + }, + { + "epoch": 1.0, + "learning_rate": 2.237177525922733e-05, + "loss": 3.4397, + "step": 1687552 + }, + { + "epoch": 1.0, + "learning_rate": 2.2363389311716805e-05, + "loss": 3.4484, + "step": 1688064 + }, + { + "epoch": 1.0, + "learning_rate": 2.2355003364206288e-05, + "loss": 3.4462, + "step": 1688576 + }, + { + "epoch": 1.0, + "learning_rate": 2.2346617416695768e-05, + "loss": 3.4602, + "step": 1689088 + }, + { + "epoch": 1.0, + "learning_rate": 2.233824784798898e-05, + "loss": 3.4524, + "step": 1689600 + }, + { + "epoch": 1.0, + "learning_rate": 2.2329861900478457e-05, + "loss": 3.455, + "step": 1690112 + }, + { + "epoch": 1.0, + "learning_rate": 2.2321475952967937e-05, + "loss": 3.4589, + "step": 1690624 + }, + { + "epoch": 1.0, + "learning_rate": 2.2313090005457417e-05, + "loss": 3.4558, + "step": 1691136 + }, + { + "epoch": 1.0, + "learning_rate": 2.230472043675063e-05, + "loss": 3.4399, + "step": 1691648 + }, + { + "epoch": 1.0, + "learning_rate": 2.229633448924011e-05, + "loss": 3.4556, + "step": 1692160 + }, + { + "epoch": 1.0, + "learning_rate": 2.228794854172959e-05, + "loss": 3.442, + "step": 1692672 + }, + { + "epoch": 1.0, + "learning_rate": 2.2279578973022802e-05, + "loss": 3.4483, + "step": 1693184 + }, + { + "epoch": 1.0, + "learning_rate": 2.227119302551228e-05, + "loss": 3.4443, + "step": 1693696 + }, + { + "epoch": 1.0, + "learning_rate": 2.226280707800176e-05, + "loss": 3.4446, + "step": 1694208 + }, + { + "epoch": 1.01, + "learning_rate": 2.2254421130491242e-05, + "loss": 3.4572, + "step": 1694720 + }, + { + "epoch": 1.01, + "learning_rate": 2.2246051561784454e-05, + "loss": 3.4494, + "step": 1695232 + }, + { + "epoch": 1.01, + "learning_rate": 2.223766561427393e-05, + "loss": 3.4486, + "step": 1695744 + }, + { + "epoch": 1.01, + "learning_rate": 2.222927966676341e-05, + "loss": 3.4536, + "step": 1696256 + }, + { + "epoch": 1.01, + "learning_rate": 2.222089371925289e-05, + "loss": 3.4485, + "step": 1696768 + }, + { + "epoch": 1.01, + "learning_rate": 2.2212524150546103e-05, + "loss": 3.4535, + "step": 1697280 + }, + { + "epoch": 1.01, + "learning_rate": 2.2204138203035583e-05, + "loss": 3.4427, + "step": 1697792 + }, + { + "epoch": 1.01, + "learning_rate": 2.2195752255525063e-05, + "loss": 3.445, + "step": 1698304 + }, + { + "epoch": 1.01, + "learning_rate": 2.2187366308014543e-05, + "loss": 3.4416, + "step": 1698816 + }, + { + "epoch": 1.01, + "learning_rate": 2.2178980360504023e-05, + "loss": 3.4407, + "step": 1699328 + }, + { + "epoch": 1.01, + "learning_rate": 2.2170594412993503e-05, + "loss": 3.4437, + "step": 1699840 + }, + { + "epoch": 1.01, + "learning_rate": 2.2162208465482983e-05, + "loss": 3.4543, + "step": 1700352 + }, + { + "epoch": 1.01, + "learning_rate": 2.215382251797246e-05, + "loss": 3.4525, + "step": 1700864 + }, + { + "epoch": 1.01, + "learning_rate": 2.2145452949265676e-05, + "loss": 3.4525, + "step": 1701376 + }, + { + "epoch": 1.01, + "learning_rate": 2.2137083380558885e-05, + "loss": 3.4605, + "step": 1701888 + }, + { + "epoch": 1.01, + "learning_rate": 2.2128697433048365e-05, + "loss": 3.4541, + "step": 1702400 + }, + { + "epoch": 1.01, + "learning_rate": 2.2120311485537845e-05, + "loss": 3.4508, + "step": 1702912 + }, + { + "epoch": 1.01, + "learning_rate": 2.2111925538027325e-05, + "loss": 3.4426, + "step": 1703424 + }, + { + "epoch": 1.01, + "learning_rate": 2.2103539590516804e-05, + "loss": 3.4269, + "step": 1703936 + }, + { + "epoch": 1.01, + "learning_rate": 2.2095170021810017e-05, + "loss": 3.4616, + "step": 1704448 + }, + { + "epoch": 1.01, + "learning_rate": 2.2086784074299497e-05, + "loss": 3.4467, + "step": 1704960 + }, + { + "epoch": 1.01, + "learning_rate": 2.2078398126788977e-05, + "loss": 3.4399, + "step": 1705472 + }, + { + "epoch": 1.01, + "learning_rate": 2.2070012179278457e-05, + "loss": 3.4467, + "step": 1705984 + }, + { + "epoch": 1.01, + "learning_rate": 2.2061642610571666e-05, + "loss": 3.4396, + "step": 1706496 + }, + { + "epoch": 1.01, + "learning_rate": 2.2053256663061146e-05, + "loss": 3.4391, + "step": 1707008 + }, + { + "epoch": 1.01, + "learning_rate": 2.204487071555063e-05, + "loss": 3.4375, + "step": 1707520 + }, + { + "epoch": 1.01, + "learning_rate": 2.203648476804011e-05, + "loss": 3.4449, + "step": 1708032 + }, + { + "epoch": 1.01, + "learning_rate": 2.2028098820529586e-05, + "loss": 3.4455, + "step": 1708544 + }, + { + "epoch": 1.01, + "learning_rate": 2.2019712873019066e-05, + "loss": 3.456, + "step": 1709056 + }, + { + "epoch": 1.01, + "learning_rate": 2.2011326925508546e-05, + "loss": 3.4371, + "step": 1709568 + }, + { + "epoch": 1.01, + "learning_rate": 2.2002940977998026e-05, + "loss": 3.4386, + "step": 1710080 + }, + { + "epoch": 1.01, + "learning_rate": 2.199458778809497e-05, + "loss": 3.4603, + "step": 1710592 + }, + { + "epoch": 1.01, + "learning_rate": 2.198620184058445e-05, + "loss": 3.4312, + "step": 1711104 + }, + { + "epoch": 1.01, + "learning_rate": 2.197781589307393e-05, + "loss": 3.4391, + "step": 1711616 + }, + { + "epoch": 1.01, + "learning_rate": 2.1969429945563407e-05, + "loss": 3.4457, + "step": 1712128 + }, + { + "epoch": 1.01, + "learning_rate": 2.1961043998052887e-05, + "loss": 3.4545, + "step": 1712640 + }, + { + "epoch": 1.01, + "learning_rate": 2.1952658050542367e-05, + "loss": 3.4368, + "step": 1713152 + }, + { + "epoch": 1.01, + "learning_rate": 2.194427210303185e-05, + "loss": 3.4354, + "step": 1713664 + }, + { + "epoch": 1.01, + "learning_rate": 2.193588615552133e-05, + "loss": 3.4279, + "step": 1714176 + }, + { + "epoch": 1.01, + "learning_rate": 2.1927532965618272e-05, + "loss": 3.4455, + "step": 1714688 + }, + { + "epoch": 1.01, + "learning_rate": 2.1919147018107752e-05, + "loss": 3.4584, + "step": 1715200 + }, + { + "epoch": 1.01, + "learning_rate": 2.191076107059723e-05, + "loss": 3.4465, + "step": 1715712 + }, + { + "epoch": 1.01, + "learning_rate": 2.1902375123086712e-05, + "loss": 3.4472, + "step": 1716224 + }, + { + "epoch": 1.01, + "learning_rate": 2.1893989175576192e-05, + "loss": 3.4534, + "step": 1716736 + }, + { + "epoch": 1.01, + "learning_rate": 2.1885603228065672e-05, + "loss": 3.4592, + "step": 1717248 + }, + { + "epoch": 1.01, + "learning_rate": 2.187721728055515e-05, + "loss": 3.4397, + "step": 1717760 + }, + { + "epoch": 1.01, + "learning_rate": 2.186884771184836e-05, + "loss": 3.4509, + "step": 1718272 + }, + { + "epoch": 1.01, + "learning_rate": 2.186046176433784e-05, + "loss": 3.4466, + "step": 1718784 + }, + { + "epoch": 1.01, + "learning_rate": 2.185207581682732e-05, + "loss": 3.4362, + "step": 1719296 + }, + { + "epoch": 1.01, + "learning_rate": 2.1843689869316804e-05, + "loss": 3.4494, + "step": 1719808 + }, + { + "epoch": 1.01, + "learning_rate": 2.1835320300610013e-05, + "loss": 3.4509, + "step": 1720320 + }, + { + "epoch": 1.01, + "learning_rate": 2.1826934353099493e-05, + "loss": 3.4492, + "step": 1720832 + }, + { + "epoch": 1.01, + "learning_rate": 2.1818548405588973e-05, + "loss": 3.4459, + "step": 1721344 + }, + { + "epoch": 1.01, + "learning_rate": 2.1810162458078453e-05, + "loss": 3.4455, + "step": 1721856 + }, + { + "epoch": 1.01, + "learning_rate": 2.1801792889371665e-05, + "loss": 3.438, + "step": 1722368 + }, + { + "epoch": 1.01, + "learning_rate": 2.1793406941861145e-05, + "loss": 3.4466, + "step": 1722880 + }, + { + "epoch": 1.01, + "learning_rate": 2.1785020994350625e-05, + "loss": 3.449, + "step": 1723392 + }, + { + "epoch": 1.01, + "learning_rate": 2.1776635046840105e-05, + "loss": 3.4403, + "step": 1723904 + }, + { + "epoch": 1.01, + "learning_rate": 2.1768249099329585e-05, + "loss": 3.4443, + "step": 1724416 + }, + { + "epoch": 1.02, + "learning_rate": 2.1759863151819062e-05, + "loss": 3.4438, + "step": 1724928 + }, + { + "epoch": 1.02, + "learning_rate": 2.1751477204308542e-05, + "loss": 3.4473, + "step": 1725440 + }, + { + "epoch": 1.02, + "learning_rate": 2.1743107635601754e-05, + "loss": 3.4407, + "step": 1725952 + }, + { + "epoch": 1.02, + "learning_rate": 2.1734721688091234e-05, + "loss": 3.4379, + "step": 1726464 + }, + { + "epoch": 1.02, + "learning_rate": 2.1726335740580714e-05, + "loss": 3.4582, + "step": 1726976 + }, + { + "epoch": 1.02, + "learning_rate": 2.1717949793070194e-05, + "loss": 3.4485, + "step": 1727488 + }, + { + "epoch": 1.02, + "learning_rate": 2.1709563845559674e-05, + "loss": 3.4497, + "step": 1728000 + }, + { + "epoch": 1.02, + "learning_rate": 2.1701177898049154e-05, + "loss": 3.4343, + "step": 1728512 + }, + { + "epoch": 1.02, + "learning_rate": 2.1692808329342367e-05, + "loss": 3.4489, + "step": 1729024 + }, + { + "epoch": 1.02, + "learning_rate": 2.1684422381831847e-05, + "loss": 3.4407, + "step": 1729536 + }, + { + "epoch": 1.02, + "learning_rate": 2.1676036434321326e-05, + "loss": 3.4498, + "step": 1730048 + }, + { + "epoch": 1.02, + "learning_rate": 2.1667650486810806e-05, + "loss": 3.4524, + "step": 1730560 + }, + { + "epoch": 1.02, + "learning_rate": 2.1659264539300286e-05, + "loss": 3.4419, + "step": 1731072 + }, + { + "epoch": 1.02, + "learning_rate": 2.1650878591789766e-05, + "loss": 3.4383, + "step": 1731584 + }, + { + "epoch": 1.02, + "learning_rate": 2.1642492644279243e-05, + "loss": 3.445, + "step": 1732096 + }, + { + "epoch": 1.02, + "learning_rate": 2.1634106696768723e-05, + "loss": 3.4241, + "step": 1732608 + }, + { + "epoch": 1.02, + "learning_rate": 2.162573712806194e-05, + "loss": 3.4474, + "step": 1733120 + }, + { + "epoch": 1.02, + "learning_rate": 2.1617351180551415e-05, + "loss": 3.4317, + "step": 1733632 + }, + { + "epoch": 1.02, + "learning_rate": 2.1608981611844628e-05, + "loss": 3.4484, + "step": 1734144 + }, + { + "epoch": 1.02, + "learning_rate": 2.1600595664334108e-05, + "loss": 3.4309, + "step": 1734656 + }, + { + "epoch": 1.02, + "learning_rate": 2.1592209716823588e-05, + "loss": 3.4455, + "step": 1735168 + }, + { + "epoch": 1.02, + "learning_rate": 2.1583823769313068e-05, + "loss": 3.4391, + "step": 1735680 + }, + { + "epoch": 1.02, + "learning_rate": 2.1575437821802548e-05, + "loss": 3.4418, + "step": 1736192 + }, + { + "epoch": 1.02, + "learning_rate": 2.1567051874292028e-05, + "loss": 3.452, + "step": 1736704 + }, + { + "epoch": 1.02, + "learning_rate": 2.1558665926781508e-05, + "loss": 3.4385, + "step": 1737216 + }, + { + "epoch": 1.02, + "learning_rate": 2.1550296358074717e-05, + "loss": 3.4532, + "step": 1737728 + }, + { + "epoch": 1.02, + "learning_rate": 2.1541910410564197e-05, + "loss": 3.4637, + "step": 1738240 + }, + { + "epoch": 1.02, + "learning_rate": 2.1533524463053677e-05, + "loss": 3.4465, + "step": 1738752 + }, + { + "epoch": 1.02, + "learning_rate": 2.152513851554316e-05, + "loss": 3.4424, + "step": 1739264 + }, + { + "epoch": 1.02, + "learning_rate": 2.151675256803264e-05, + "loss": 3.4385, + "step": 1739776 + }, + { + "epoch": 1.02, + "learning_rate": 2.150836662052212e-05, + "loss": 3.4451, + "step": 1740288 + }, + { + "epoch": 1.02, + "learning_rate": 2.149999705181533e-05, + "loss": 3.4406, + "step": 1740800 + }, + { + "epoch": 1.02, + "learning_rate": 2.149161110430481e-05, + "loss": 3.4547, + "step": 1741312 + }, + { + "epoch": 1.02, + "learning_rate": 2.148322515679429e-05, + "loss": 3.4293, + "step": 1741824 + }, + { + "epoch": 1.02, + "learning_rate": 2.147483920928377e-05, + "loss": 3.4526, + "step": 1742336 + }, + { + "epoch": 1.02, + "learning_rate": 2.146645326177325e-05, + "loss": 3.4486, + "step": 1742848 + }, + { + "epoch": 1.02, + "learning_rate": 2.145808369306646e-05, + "loss": 3.4469, + "step": 1743360 + }, + { + "epoch": 1.02, + "learning_rate": 2.144969774555594e-05, + "loss": 3.4351, + "step": 1743872 + }, + { + "epoch": 1.02, + "learning_rate": 2.144131179804542e-05, + "loss": 3.4465, + "step": 1744384 + }, + { + "epoch": 1.02, + "learning_rate": 2.1432925850534898e-05, + "loss": 3.4376, + "step": 1744896 + }, + { + "epoch": 1.02, + "learning_rate": 2.1424539903024378e-05, + "loss": 3.4536, + "step": 1745408 + }, + { + "epoch": 1.02, + "learning_rate": 2.1416170334317594e-05, + "loss": 3.441, + "step": 1745920 + }, + { + "epoch": 1.02, + "learning_rate": 2.140778438680707e-05, + "loss": 3.4537, + "step": 1746432 + }, + { + "epoch": 1.02, + "learning_rate": 2.139939843929655e-05, + "loss": 3.4303, + "step": 1746944 + }, + { + "epoch": 1.02, + "learning_rate": 2.139101249178603e-05, + "loss": 3.4571, + "step": 1747456 + }, + { + "epoch": 1.02, + "learning_rate": 2.138262654427551e-05, + "loss": 3.4405, + "step": 1747968 + }, + { + "epoch": 1.02, + "learning_rate": 2.137424059676499e-05, + "loss": 3.4475, + "step": 1748480 + }, + { + "epoch": 1.02, + "learning_rate": 2.136585464925447e-05, + "loss": 3.4416, + "step": 1748992 + }, + { + "epoch": 1.02, + "learning_rate": 2.1357468701743953e-05, + "loss": 3.4426, + "step": 1749504 + }, + { + "epoch": 1.02, + "learning_rate": 2.1349099133037162e-05, + "loss": 3.4517, + "step": 1750016 + }, + { + "epoch": 1.02, + "learning_rate": 2.1340713185526642e-05, + "loss": 3.4634, + "step": 1750528 + }, + { + "epoch": 1.02, + "learning_rate": 2.1332327238016122e-05, + "loss": 3.4321, + "step": 1751040 + }, + { + "epoch": 1.02, + "learning_rate": 2.1323941290505602e-05, + "loss": 3.4469, + "step": 1751552 + }, + { + "epoch": 1.02, + "learning_rate": 2.1315571721798815e-05, + "loss": 3.4411, + "step": 1752064 + }, + { + "epoch": 1.02, + "learning_rate": 2.1307185774288295e-05, + "loss": 3.4469, + "step": 1752576 + }, + { + "epoch": 1.02, + "learning_rate": 2.1298799826777775e-05, + "loss": 3.4384, + "step": 1753088 + }, + { + "epoch": 1.02, + "learning_rate": 2.129041387926725e-05, + "loss": 3.4511, + "step": 1753600 + }, + { + "epoch": 1.02, + "learning_rate": 2.1282044310560464e-05, + "loss": 3.451, + "step": 1754112 + }, + { + "epoch": 1.02, + "learning_rate": 2.1273658363049944e-05, + "loss": 3.4326, + "step": 1754624 + }, + { + "epoch": 1.02, + "learning_rate": 2.1265272415539424e-05, + "loss": 3.4511, + "step": 1755136 + }, + { + "epoch": 1.03, + "eval_loss": 3.8543224334716797, + "eval_runtime": 302.9651, + "eval_samples_per_second": 1259.521, + "eval_steps_per_second": 39.361, + "step": 1755360 + }, + { + "epoch": 0.0, + "learning_rate": 2.1256886468028903e-05, + "loss": 3.439, + "step": 1755648 + }, + { + "epoch": 0.0, + "learning_rate": 2.1248500520518383e-05, + "loss": 3.4335, + "step": 1756160 + }, + { + "epoch": 0.0, + "learning_rate": 2.1240114573007863e-05, + "loss": 3.4462, + "step": 1756672 + }, + { + "epoch": 0.0, + "learning_rate": 2.1231745004301072e-05, + "loss": 3.4405, + "step": 1757184 + }, + { + "epoch": 0.0, + "learning_rate": 2.1223359056790552e-05, + "loss": 3.4505, + "step": 1757696 + }, + { + "epoch": 0.0, + "learning_rate": 2.1214973109280036e-05, + "loss": 3.4381, + "step": 1758208 + }, + { + "epoch": 0.0, + "learning_rate": 2.1206587161769516e-05, + "loss": 3.4421, + "step": 1758720 + }, + { + "epoch": 0.0, + "learning_rate": 2.1198201214258996e-05, + "loss": 3.4342, + "step": 1759232 + }, + { + "epoch": 0.0, + "learning_rate": 2.1189831645552205e-05, + "loss": 3.4462, + "step": 1759744 + }, + { + "epoch": 0.0, + "learning_rate": 2.1181445698041685e-05, + "loss": 3.4362, + "step": 1760256 + }, + { + "epoch": 0.0, + "learning_rate": 2.1173059750531165e-05, + "loss": 3.4408, + "step": 1760768 + }, + { + "epoch": 0.0, + "learning_rate": 2.1164673803020645e-05, + "loss": 3.4489, + "step": 1761280 + }, + { + "epoch": 0.0, + "learning_rate": 2.1156287855510125e-05, + "loss": 3.4416, + "step": 1761792 + }, + { + "epoch": 0.0, + "learning_rate": 2.1147918286803337e-05, + "loss": 3.4401, + "step": 1762304 + }, + { + "epoch": 0.0, + "learning_rate": 2.1139532339292817e-05, + "loss": 3.4401, + "step": 1762816 + }, + { + "epoch": 0.0, + "learning_rate": 2.1131146391782297e-05, + "loss": 3.4328, + "step": 1763328 + }, + { + "epoch": 0.0, + "learning_rate": 2.1122760444271777e-05, + "loss": 3.4305, + "step": 1763840 + }, + { + "epoch": 0.0, + "learning_rate": 2.1114374496761254e-05, + "loss": 3.4384, + "step": 1764352 + }, + { + "epoch": 0.0, + "learning_rate": 2.1105988549250737e-05, + "loss": 3.4354, + "step": 1764864 + }, + { + "epoch": 0.0, + "learning_rate": 2.1097602601740217e-05, + "loss": 3.4456, + "step": 1765376 + }, + { + "epoch": 0.0, + "learning_rate": 2.1089216654229697e-05, + "loss": 3.4466, + "step": 1765888 + }, + { + "epoch": 0.0, + "learning_rate": 2.1080847085522906e-05, + "loss": 3.4427, + "step": 1766400 + }, + { + "epoch": 0.0, + "learning_rate": 2.1072461138012386e-05, + "loss": 3.4481, + "step": 1766912 + }, + { + "epoch": 0.0, + "learning_rate": 2.1064075190501866e-05, + "loss": 3.4463, + "step": 1767424 + }, + { + "epoch": 0.0, + "learning_rate": 2.1055705621795078e-05, + "loss": 3.4302, + "step": 1767936 + }, + { + "epoch": 0.0, + "learning_rate": 2.1047319674284558e-05, + "loss": 3.4464, + "step": 1768448 + }, + { + "epoch": 0.0, + "learning_rate": 2.1038933726774038e-05, + "loss": 3.4335, + "step": 1768960 + }, + { + "epoch": 0.0, + "learning_rate": 2.1030547779263518e-05, + "loss": 3.4356, + "step": 1769472 + }, + { + "epoch": 0.0, + "learning_rate": 2.1022178210556727e-05, + "loss": 3.4327, + "step": 1769984 + }, + { + "epoch": 0.0, + "learning_rate": 2.101380864184994e-05, + "loss": 3.437, + "step": 1770496 + }, + { + "epoch": 0.01, + "learning_rate": 2.1005422694339423e-05, + "loss": 3.4407, + "step": 1771008 + }, + { + "epoch": 0.01, + "learning_rate": 2.0997036746828903e-05, + "loss": 3.4423, + "step": 1771520 + }, + { + "epoch": 0.01, + "learning_rate": 2.098865079931838e-05, + "loss": 3.4403, + "step": 1772032 + }, + { + "epoch": 0.01, + "learning_rate": 2.098026485180786e-05, + "loss": 3.4444, + "step": 1772544 + }, + { + "epoch": 0.01, + "learning_rate": 2.097187890429734e-05, + "loss": 3.4319, + "step": 1773056 + }, + { + "epoch": 0.01, + "learning_rate": 2.0963509335590552e-05, + "loss": 3.4446, + "step": 1773568 + }, + { + "epoch": 0.01, + "learning_rate": 2.0955123388080032e-05, + "loss": 3.4376, + "step": 1774080 + }, + { + "epoch": 0.01, + "learning_rate": 2.0946737440569512e-05, + "loss": 3.4265, + "step": 1774592 + }, + { + "epoch": 0.01, + "learning_rate": 2.0938351493058992e-05, + "loss": 3.4319, + "step": 1775104 + }, + { + "epoch": 0.01, + "learning_rate": 2.0929965545548472e-05, + "loss": 3.4322, + "step": 1775616 + }, + { + "epoch": 0.01, + "learning_rate": 2.0921579598037952e-05, + "loss": 3.4377, + "step": 1776128 + }, + { + "epoch": 0.01, + "learning_rate": 2.0913193650527432e-05, + "loss": 3.4415, + "step": 1776640 + }, + { + "epoch": 0.01, + "learning_rate": 2.0904807703016908e-05, + "loss": 3.4427, + "step": 1777152 + }, + { + "epoch": 0.01, + "learning_rate": 2.0896438134310124e-05, + "loss": 3.4387, + "step": 1777664 + }, + { + "epoch": 0.01, + "learning_rate": 2.0888052186799604e-05, + "loss": 3.4505, + "step": 1778176 + }, + { + "epoch": 0.01, + "learning_rate": 2.0879666239289084e-05, + "loss": 3.4407, + "step": 1778688 + }, + { + "epoch": 0.01, + "learning_rate": 2.087128029177856e-05, + "loss": 3.4435, + "step": 1779200 + }, + { + "epoch": 0.01, + "learning_rate": 2.086289434426804e-05, + "loss": 3.4319, + "step": 1779712 + }, + { + "epoch": 0.01, + "learning_rate": 2.085450839675752e-05, + "loss": 3.4129, + "step": 1780224 + }, + { + "epoch": 0.01, + "learning_rate": 2.0846122449247e-05, + "loss": 3.454, + "step": 1780736 + }, + { + "epoch": 0.01, + "learning_rate": 2.0837752880540213e-05, + "loss": 3.4355, + "step": 1781248 + }, + { + "epoch": 0.01, + "learning_rate": 2.0829366933029693e-05, + "loss": 3.4346, + "step": 1781760 + }, + { + "epoch": 0.01, + "learning_rate": 2.0820980985519173e-05, + "loss": 3.4341, + "step": 1782272 + }, + { + "epoch": 0.01, + "learning_rate": 2.0812595038008653e-05, + "loss": 3.4302, + "step": 1782784 + }, + { + "epoch": 0.01, + "learning_rate": 2.0804225469301862e-05, + "loss": 3.4283, + "step": 1783296 + }, + { + "epoch": 0.01, + "learning_rate": 2.0795839521791345e-05, + "loss": 3.4239, + "step": 1783808 + }, + { + "epoch": 0.01, + "learning_rate": 2.0787453574280825e-05, + "loss": 3.4363, + "step": 1784320 + }, + { + "epoch": 0.01, + "learning_rate": 2.0779067626770305e-05, + "loss": 3.4315, + "step": 1784832 + }, + { + "epoch": 0.01, + "learning_rate": 2.0770681679259785e-05, + "loss": 3.4467, + "step": 1785344 + }, + { + "epoch": 0.01, + "learning_rate": 2.0762295731749265e-05, + "loss": 3.4266, + "step": 1785856 + }, + { + "epoch": 0.01, + "learning_rate": 2.0753909784238742e-05, + "loss": 3.4254, + "step": 1786368 + }, + { + "epoch": 0.01, + "learning_rate": 2.0745540215531954e-05, + "loss": 3.4469, + "step": 1786880 + }, + { + "epoch": 0.01, + "learning_rate": 2.0737154268021438e-05, + "loss": 3.4219, + "step": 1787392 + }, + { + "epoch": 0.01, + "learning_rate": 2.0728768320510917e-05, + "loss": 3.4272, + "step": 1787904 + }, + { + "epoch": 0.01, + "learning_rate": 2.0720382373000394e-05, + "loss": 3.4383, + "step": 1788416 + }, + { + "epoch": 0.01, + "learning_rate": 2.0711996425489874e-05, + "loss": 3.4426, + "step": 1788928 + }, + { + "epoch": 0.01, + "learning_rate": 2.0703610477979354e-05, + "loss": 3.4263, + "step": 1789440 + }, + { + "epoch": 0.01, + "learning_rate": 2.0695224530468834e-05, + "loss": 3.426, + "step": 1789952 + }, + { + "epoch": 0.01, + "learning_rate": 2.0686838582958314e-05, + "loss": 3.4193, + "step": 1790464 + }, + { + "epoch": 0.01, + "learning_rate": 2.067848539305526e-05, + "loss": 3.4324, + "step": 1790976 + }, + { + "epoch": 0.01, + "learning_rate": 2.067009944554474e-05, + "loss": 3.4475, + "step": 1791488 + }, + { + "epoch": 0.01, + "learning_rate": 2.0661713498034215e-05, + "loss": 3.4333, + "step": 1792000 + }, + { + "epoch": 0.01, + "learning_rate": 2.0653327550523695e-05, + "loss": 3.4372, + "step": 1792512 + }, + { + "epoch": 0.01, + "learning_rate": 2.0644941603013175e-05, + "loss": 3.4454, + "step": 1793024 + }, + { + "epoch": 0.01, + "learning_rate": 2.0636555655502655e-05, + "loss": 3.448, + "step": 1793536 + }, + { + "epoch": 0.01, + "learning_rate": 2.062816970799214e-05, + "loss": 3.4279, + "step": 1794048 + }, + { + "epoch": 0.01, + "learning_rate": 2.0619800139285348e-05, + "loss": 3.4432, + "step": 1794560 + }, + { + "epoch": 0.01, + "learning_rate": 2.0611414191774828e-05, + "loss": 3.4308, + "step": 1795072 + }, + { + "epoch": 0.01, + "learning_rate": 2.0603028244264308e-05, + "loss": 3.4321, + "step": 1795584 + }, + { + "epoch": 0.01, + "learning_rate": 2.0594642296753788e-05, + "loss": 3.4351, + "step": 1796096 + }, + { + "epoch": 0.01, + "learning_rate": 2.0586272728047e-05, + "loss": 3.4437, + "step": 1796608 + }, + { + "epoch": 0.01, + "learning_rate": 2.057788678053648e-05, + "loss": 3.4354, + "step": 1797120 + }, + { + "epoch": 0.01, + "learning_rate": 2.056950083302596e-05, + "loss": 3.4406, + "step": 1797632 + }, + { + "epoch": 0.01, + "learning_rate": 2.056111488551544e-05, + "loss": 3.4317, + "step": 1798144 + }, + { + "epoch": 0.01, + "learning_rate": 2.055274531680865e-05, + "loss": 3.4266, + "step": 1798656 + }, + { + "epoch": 0.01, + "learning_rate": 2.054435936929813e-05, + "loss": 3.4365, + "step": 1799168 + }, + { + "epoch": 0.01, + "learning_rate": 2.053597342178761e-05, + "loss": 3.4366, + "step": 1799680 + }, + { + "epoch": 0.01, + "learning_rate": 2.0527587474277092e-05, + "loss": 3.4307, + "step": 1800192 + }, + { + "epoch": 0.01, + "learning_rate": 2.051920152676657e-05, + "loss": 3.4329, + "step": 1800704 + }, + { + "epoch": 0.02, + "learning_rate": 2.051081557925605e-05, + "loss": 3.436, + "step": 1801216 + }, + { + "epoch": 0.02, + "learning_rate": 2.050244601054926e-05, + "loss": 3.4398, + "step": 1801728 + }, + { + "epoch": 0.02, + "learning_rate": 2.049406006303874e-05, + "loss": 3.4295, + "step": 1802240 + }, + { + "epoch": 0.02, + "learning_rate": 2.0485674115528218e-05, + "loss": 3.4258, + "step": 1802752 + }, + { + "epoch": 0.02, + "learning_rate": 2.04772881680177e-05, + "loss": 3.4431, + "step": 1803264 + }, + { + "epoch": 0.02, + "learning_rate": 2.046890222050718e-05, + "loss": 3.4394, + "step": 1803776 + }, + { + "epoch": 0.02, + "learning_rate": 2.046051627299666e-05, + "loss": 3.4386, + "step": 1804288 + }, + { + "epoch": 0.02, + "learning_rate": 2.045213032548614e-05, + "loss": 3.4261, + "step": 1804800 + }, + { + "epoch": 0.02, + "learning_rate": 2.044376075677935e-05, + "loss": 3.4358, + "step": 1805312 + }, + { + "epoch": 0.02, + "learning_rate": 2.043537480926883e-05, + "loss": 3.4278, + "step": 1805824 + }, + { + "epoch": 0.02, + "learning_rate": 2.042698886175831e-05, + "loss": 3.4379, + "step": 1806336 + }, + { + "epoch": 0.02, + "learning_rate": 2.0418602914247793e-05, + "loss": 3.4401, + "step": 1806848 + }, + { + "epoch": 0.02, + "learning_rate": 2.0410216966737273e-05, + "loss": 3.4342, + "step": 1807360 + }, + { + "epoch": 0.02, + "learning_rate": 2.040183101922675e-05, + "loss": 3.4296, + "step": 1807872 + }, + { + "epoch": 0.02, + "learning_rate": 2.039344507171623e-05, + "loss": 3.4284, + "step": 1808384 + }, + { + "epoch": 0.02, + "learning_rate": 2.0385075503009442e-05, + "loss": 3.4198, + "step": 1808896 + }, + { + "epoch": 0.02, + "learning_rate": 2.0376689555498922e-05, + "loss": 3.4315, + "step": 1809408 + }, + { + "epoch": 0.02, + "learning_rate": 2.0368303607988402e-05, + "loss": 3.4232, + "step": 1809920 + }, + { + "epoch": 0.02, + "learning_rate": 2.0359917660477882e-05, + "loss": 3.4405, + "step": 1810432 + }, + { + "epoch": 0.02, + "learning_rate": 2.0351531712967362e-05, + "loss": 3.4201, + "step": 1810944 + }, + { + "epoch": 0.02, + "learning_rate": 2.0343162144260575e-05, + "loss": 3.4326, + "step": 1811456 + }, + { + "epoch": 0.02, + "learning_rate": 2.033477619675005e-05, + "loss": 3.4277, + "step": 1811968 + }, + { + "epoch": 0.02, + "learning_rate": 2.032639024923953e-05, + "loss": 3.4348, + "step": 1812480 + }, + { + "epoch": 0.02, + "learning_rate": 2.031800430172901e-05, + "loss": 3.4382, + "step": 1812992 + }, + { + "epoch": 0.02, + "learning_rate": 2.0309618354218494e-05, + "loss": 3.4288, + "step": 1813504 + }, + { + "epoch": 0.02, + "learning_rate": 2.0301248785511704e-05, + "loss": 3.4433, + "step": 1814016 + }, + { + "epoch": 0.02, + "learning_rate": 2.0292862838001184e-05, + "loss": 3.4469, + "step": 1814528 + }, + { + "epoch": 0.02, + "learning_rate": 2.0284476890490663e-05, + "loss": 3.4347, + "step": 1815040 + }, + { + "epoch": 0.02, + "learning_rate": 2.0276090942980143e-05, + "loss": 3.436, + "step": 1815552 + }, + { + "epoch": 0.02, + "learning_rate": 2.0267704995469623e-05, + "loss": 3.4275, + "step": 1816064 + }, + { + "epoch": 0.02, + "learning_rate": 2.0259335426762836e-05, + "loss": 3.4321, + "step": 1816576 + }, + { + "epoch": 0.02, + "learning_rate": 2.0250949479252316e-05, + "loss": 3.4336, + "step": 1817088 + }, + { + "epoch": 0.02, + "learning_rate": 2.0242563531741796e-05, + "loss": 3.4384, + "step": 1817600 + }, + { + "epoch": 0.02, + "learning_rate": 2.0234177584231276e-05, + "loss": 3.4239, + "step": 1818112 + }, + { + "epoch": 0.02, + "learning_rate": 2.0225791636720756e-05, + "loss": 3.4399, + "step": 1818624 + }, + { + "epoch": 0.02, + "learning_rate": 2.0217405689210232e-05, + "loss": 3.4396, + "step": 1819136 + }, + { + "epoch": 0.02, + "learning_rate": 2.0209036120503448e-05, + "loss": 3.4359, + "step": 1819648 + }, + { + "epoch": 0.02, + "learning_rate": 2.0200650172992928e-05, + "loss": 3.4218, + "step": 1820160 + }, + { + "epoch": 0.02, + "learning_rate": 2.0192264225482405e-05, + "loss": 3.4364, + "step": 1820672 + }, + { + "epoch": 0.02, + "learning_rate": 2.0183878277971885e-05, + "loss": 3.4286, + "step": 1821184 + }, + { + "epoch": 0.02, + "learning_rate": 2.0175492330461365e-05, + "loss": 3.441, + "step": 1821696 + }, + { + "epoch": 0.02, + "learning_rate": 2.0167122761754577e-05, + "loss": 3.4356, + "step": 1822208 + }, + { + "epoch": 0.02, + "learning_rate": 2.0158736814244057e-05, + "loss": 3.4387, + "step": 1822720 + }, + { + "epoch": 0.02, + "learning_rate": 2.0150350866733537e-05, + "loss": 3.417, + "step": 1823232 + }, + { + "epoch": 0.02, + "learning_rate": 2.0141964919223017e-05, + "loss": 3.4491, + "step": 1823744 + }, + { + "epoch": 0.02, + "learning_rate": 2.0133578971712497e-05, + "loss": 3.4258, + "step": 1824256 + }, + { + "epoch": 0.02, + "learning_rate": 2.0125193024201977e-05, + "loss": 3.4371, + "step": 1824768 + }, + { + "epoch": 0.02, + "learning_rate": 2.0116807076691457e-05, + "loss": 3.4321, + "step": 1825280 + }, + { + "epoch": 0.02, + "learning_rate": 2.0108421129180937e-05, + "loss": 3.4302, + "step": 1825792 + }, + { + "epoch": 0.02, + "learning_rate": 2.010005156047415e-05, + "loss": 3.4418, + "step": 1826304 + }, + { + "epoch": 0.02, + "learning_rate": 2.009166561296363e-05, + "loss": 3.4495, + "step": 1826816 + }, + { + "epoch": 0.02, + "learning_rate": 2.008327966545311e-05, + "loss": 3.4225, + "step": 1827328 + }, + { + "epoch": 0.02, + "learning_rate": 2.0074893717942586e-05, + "loss": 3.4358, + "step": 1827840 + }, + { + "epoch": 0.02, + "learning_rate": 2.0066524149235798e-05, + "loss": 3.4314, + "step": 1828352 + }, + { + "epoch": 0.02, + "learning_rate": 2.0058138201725278e-05, + "loss": 3.4335, + "step": 1828864 + }, + { + "epoch": 0.02, + "learning_rate": 2.0049752254214758e-05, + "loss": 3.4293, + "step": 1829376 + }, + { + "epoch": 0.02, + "learning_rate": 2.0041366306704238e-05, + "loss": 3.4411, + "step": 1829888 + }, + { + "epoch": 0.02, + "learning_rate": 2.0032980359193718e-05, + "loss": 3.4435, + "step": 1830400 + }, + { + "epoch": 0.02, + "learning_rate": 2.0024594411683198e-05, + "loss": 3.4203, + "step": 1830912 + }, + { + "epoch": 0.02, + "learning_rate": 2.0016208464172678e-05, + "loss": 3.438, + "step": 1831424 + }, + { + "epoch": 0.03, + "eval_loss": 3.855004072189331, + "eval_runtime": 307.7829, + "eval_samples_per_second": 1239.806, + "eval_steps_per_second": 38.745, + "step": 1831680 + }, + { + "epoch": 1.0, + "learning_rate": 2.0007822516662158e-05, + "loss": 3.428, + "step": 1831936 + }, + { + "epoch": 1.0, + "learning_rate": 1.999945294795537e-05, + "loss": 3.4258, + "step": 1832448 + }, + { + "epoch": 1.0, + "learning_rate": 1.999106700044485e-05, + "loss": 3.4332, + "step": 1832960 + }, + { + "epoch": 1.0, + "learning_rate": 1.998268105293433e-05, + "loss": 3.4295, + "step": 1833472 + }, + { + "epoch": 1.0, + "learning_rate": 1.997431148422754e-05, + "loss": 3.4399, + "step": 1833984 + }, + { + "epoch": 1.0, + "learning_rate": 1.996592553671702e-05, + "loss": 3.422, + "step": 1834496 + }, + { + "epoch": 1.0, + "learning_rate": 1.99575395892065e-05, + "loss": 3.437, + "step": 1835008 + }, + { + "epoch": 1.0, + "learning_rate": 1.994915364169598e-05, + "loss": 3.4242, + "step": 1835520 + }, + { + "epoch": 1.0, + "learning_rate": 1.9940784072989192e-05, + "loss": 3.434, + "step": 1836032 + }, + { + "epoch": 1.0, + "learning_rate": 1.993239812547867e-05, + "loss": 3.429, + "step": 1836544 + }, + { + "epoch": 1.0, + "learning_rate": 1.992401217796815e-05, + "loss": 3.4268, + "step": 1837056 + }, + { + "epoch": 1.0, + "learning_rate": 1.991562623045763e-05, + "loss": 3.4377, + "step": 1837568 + }, + { + "epoch": 1.0, + "learning_rate": 1.990724028294711e-05, + "loss": 3.4297, + "step": 1838080 + }, + { + "epoch": 1.0, + "learning_rate": 1.9898870714240324e-05, + "loss": 3.4289, + "step": 1838592 + }, + { + "epoch": 1.0, + "learning_rate": 1.9890484766729804e-05, + "loss": 3.4342, + "step": 1839104 + }, + { + "epoch": 1.0, + "learning_rate": 1.9882098819219284e-05, + "loss": 3.4197, + "step": 1839616 + }, + { + "epoch": 1.0, + "learning_rate": 1.9873712871708764e-05, + "loss": 3.4211, + "step": 1840128 + }, + { + "epoch": 1.0, + "learning_rate": 1.986532692419824e-05, + "loss": 3.4278, + "step": 1840640 + }, + { + "epoch": 1.0, + "learning_rate": 1.985694097668772e-05, + "loss": 3.426, + "step": 1841152 + }, + { + "epoch": 1.0, + "learning_rate": 1.98485550291772e-05, + "loss": 3.4281, + "step": 1841664 + }, + { + "epoch": 1.0, + "learning_rate": 1.9840185460470416e-05, + "loss": 3.4357, + "step": 1842176 + }, + { + "epoch": 1.0, + "learning_rate": 1.9831799512959893e-05, + "loss": 3.4332, + "step": 1842688 + }, + { + "epoch": 1.0, + "learning_rate": 1.9823413565449373e-05, + "loss": 3.4353, + "step": 1843200 + }, + { + "epoch": 1.0, + "learning_rate": 1.9815027617938853e-05, + "loss": 3.434, + "step": 1843712 + }, + { + "epoch": 1.0, + "learning_rate": 1.9806641670428333e-05, + "loss": 3.4218, + "step": 1844224 + }, + { + "epoch": 1.0, + "learning_rate": 1.9798255722917813e-05, + "loss": 3.435, + "step": 1844736 + }, + { + "epoch": 1.0, + "learning_rate": 1.9789869775407293e-05, + "loss": 3.4216, + "step": 1845248 + }, + { + "epoch": 1.0, + "learning_rate": 1.9781500206700505e-05, + "loss": 3.4271, + "step": 1845760 + }, + { + "epoch": 1.0, + "learning_rate": 1.9773114259189985e-05, + "loss": 3.4262, + "step": 1846272 + }, + { + "epoch": 1.0, + "learning_rate": 1.9764728311679465e-05, + "loss": 3.4246, + "step": 1846784 + }, + { + "epoch": 1.01, + "learning_rate": 1.9756342364168945e-05, + "loss": 3.4277, + "step": 1847296 + }, + { + "epoch": 1.01, + "learning_rate": 1.9747972795462154e-05, + "loss": 3.4324, + "step": 1847808 + }, + { + "epoch": 1.01, + "learning_rate": 1.9739586847951634e-05, + "loss": 3.4288, + "step": 1848320 + }, + { + "epoch": 1.01, + "learning_rate": 1.9731200900441117e-05, + "loss": 3.4324, + "step": 1848832 + }, + { + "epoch": 1.01, + "learning_rate": 1.9722814952930597e-05, + "loss": 3.4229, + "step": 1849344 + }, + { + "epoch": 1.01, + "learning_rate": 1.9714445384223806e-05, + "loss": 3.4352, + "step": 1849856 + }, + { + "epoch": 1.01, + "learning_rate": 1.9706059436713286e-05, + "loss": 3.4255, + "step": 1850368 + }, + { + "epoch": 1.01, + "learning_rate": 1.9697673489202766e-05, + "loss": 3.4175, + "step": 1850880 + }, + { + "epoch": 1.01, + "learning_rate": 1.9689287541692243e-05, + "loss": 3.4242, + "step": 1851392 + }, + { + "epoch": 1.01, + "learning_rate": 1.9680901594181726e-05, + "loss": 3.4179, + "step": 1851904 + }, + { + "epoch": 1.01, + "learning_rate": 1.9672515646671206e-05, + "loss": 3.4272, + "step": 1852416 + }, + { + "epoch": 1.01, + "learning_rate": 1.9664129699160686e-05, + "loss": 3.431, + "step": 1852928 + }, + { + "epoch": 1.01, + "learning_rate": 1.9655743751650166e-05, + "loss": 3.4312, + "step": 1853440 + }, + { + "epoch": 1.01, + "learning_rate": 1.9647374182943375e-05, + "loss": 3.4313, + "step": 1853952 + }, + { + "epoch": 1.01, + "learning_rate": 1.9638988235432855e-05, + "loss": 3.4365, + "step": 1854464 + }, + { + "epoch": 1.01, + "learning_rate": 1.9630602287922335e-05, + "loss": 3.4319, + "step": 1854976 + }, + { + "epoch": 1.01, + "learning_rate": 1.962221634041182e-05, + "loss": 3.431, + "step": 1855488 + }, + { + "epoch": 1.01, + "learning_rate": 1.9613846771705028e-05, + "loss": 3.4246, + "step": 1856000 + }, + { + "epoch": 1.01, + "learning_rate": 1.9605460824194507e-05, + "loss": 3.3976, + "step": 1856512 + }, + { + "epoch": 1.01, + "learning_rate": 1.9597074876683987e-05, + "loss": 3.4486, + "step": 1857024 + }, + { + "epoch": 1.01, + "learning_rate": 1.9588688929173467e-05, + "loss": 3.4225, + "step": 1857536 + }, + { + "epoch": 1.01, + "learning_rate": 1.958031936046668e-05, + "loss": 3.4249, + "step": 1858048 + }, + { + "epoch": 1.01, + "learning_rate": 1.957193341295616e-05, + "loss": 3.4242, + "step": 1858560 + }, + { + "epoch": 1.01, + "learning_rate": 1.956354746544564e-05, + "loss": 3.4194, + "step": 1859072 + }, + { + "epoch": 1.01, + "learning_rate": 1.955516151793512e-05, + "loss": 3.4133, + "step": 1859584 + }, + { + "epoch": 1.01, + "learning_rate": 1.95467755704246e-05, + "loss": 3.413, + "step": 1860096 + }, + { + "epoch": 1.01, + "learning_rate": 1.9538389622914076e-05, + "loss": 3.4249, + "step": 1860608 + }, + { + "epoch": 1.01, + "learning_rate": 1.9530003675403556e-05, + "loss": 3.4192, + "step": 1861120 + }, + { + "epoch": 1.01, + "learning_rate": 1.952161772789304e-05, + "loss": 3.4366, + "step": 1861632 + }, + { + "epoch": 1.01, + "learning_rate": 1.9513248159186252e-05, + "loss": 3.4199, + "step": 1862144 + }, + { + "epoch": 1.01, + "learning_rate": 1.950486221167573e-05, + "loss": 3.4133, + "step": 1862656 + }, + { + "epoch": 1.01, + "learning_rate": 1.949647626416521e-05, + "loss": 3.4344, + "step": 1863168 + }, + { + "epoch": 1.01, + "learning_rate": 1.948809031665469e-05, + "loss": 3.4136, + "step": 1863680 + }, + { + "epoch": 1.01, + "learning_rate": 1.947970436914417e-05, + "loss": 3.4158, + "step": 1864192 + }, + { + "epoch": 1.01, + "learning_rate": 1.947131842163365e-05, + "loss": 3.4286, + "step": 1864704 + }, + { + "epoch": 1.01, + "learning_rate": 1.946293247412313e-05, + "loss": 3.4306, + "step": 1865216 + }, + { + "epoch": 1.01, + "learning_rate": 1.945456290541634e-05, + "loss": 3.4168, + "step": 1865728 + }, + { + "epoch": 1.01, + "learning_rate": 1.944617695790582e-05, + "loss": 3.414, + "step": 1866240 + }, + { + "epoch": 1.01, + "learning_rate": 1.943780738919903e-05, + "loss": 3.41, + "step": 1866752 + }, + { + "epoch": 1.01, + "learning_rate": 1.942942144168851e-05, + "loss": 3.4226, + "step": 1867264 + }, + { + "epoch": 1.01, + "learning_rate": 1.942103549417799e-05, + "loss": 3.4374, + "step": 1867776 + }, + { + "epoch": 1.01, + "learning_rate": 1.9412649546667473e-05, + "loss": 3.4233, + "step": 1868288 + }, + { + "epoch": 1.01, + "learning_rate": 1.9404263599156953e-05, + "loss": 3.4282, + "step": 1868800 + }, + { + "epoch": 1.01, + "learning_rate": 1.9395894030450162e-05, + "loss": 3.429, + "step": 1869312 + }, + { + "epoch": 1.01, + "learning_rate": 1.9387508082939642e-05, + "loss": 3.4365, + "step": 1869824 + }, + { + "epoch": 1.01, + "learning_rate": 1.9379122135429122e-05, + "loss": 3.4175, + "step": 1870336 + }, + { + "epoch": 1.01, + "learning_rate": 1.9370736187918602e-05, + "loss": 3.4337, + "step": 1870848 + }, + { + "epoch": 1.01, + "learning_rate": 1.9362350240408082e-05, + "loss": 3.4185, + "step": 1871360 + }, + { + "epoch": 1.01, + "learning_rate": 1.9353980671701295e-05, + "loss": 3.4235, + "step": 1871872 + }, + { + "epoch": 1.01, + "learning_rate": 1.9345594724190775e-05, + "loss": 3.4243, + "step": 1872384 + }, + { + "epoch": 1.01, + "learning_rate": 1.9337208776680254e-05, + "loss": 3.4308, + "step": 1872896 + }, + { + "epoch": 1.01, + "learning_rate": 1.932882282916973e-05, + "loss": 3.4245, + "step": 1873408 + }, + { + "epoch": 1.01, + "learning_rate": 1.932043688165921e-05, + "loss": 3.4333, + "step": 1873920 + }, + { + "epoch": 1.01, + "learning_rate": 1.9312050934148694e-05, + "loss": 3.4164, + "step": 1874432 + }, + { + "epoch": 1.01, + "learning_rate": 1.9303664986638174e-05, + "loss": 3.4177, + "step": 1874944 + }, + { + "epoch": 1.01, + "learning_rate": 1.9295279039127654e-05, + "loss": 3.4282, + "step": 1875456 + }, + { + "epoch": 1.01, + "learning_rate": 1.9286909470420863e-05, + "loss": 3.4254, + "step": 1875968 + }, + { + "epoch": 1.01, + "learning_rate": 1.9278523522910343e-05, + "loss": 3.4172, + "step": 1876480 + }, + { + "epoch": 1.01, + "learning_rate": 1.9270153954203556e-05, + "loss": 3.4238, + "step": 1876992 + }, + { + "epoch": 1.02, + "learning_rate": 1.9261768006693036e-05, + "loss": 3.4254, + "step": 1877504 + }, + { + "epoch": 1.02, + "learning_rate": 1.9253382059182516e-05, + "loss": 3.4314, + "step": 1878016 + }, + { + "epoch": 1.02, + "learning_rate": 1.9244996111671996e-05, + "loss": 3.4178, + "step": 1878528 + }, + { + "epoch": 1.02, + "learning_rate": 1.9236626542965205e-05, + "loss": 3.4159, + "step": 1879040 + }, + { + "epoch": 1.02, + "learning_rate": 1.9228240595454685e-05, + "loss": 3.433, + "step": 1879552 + }, + { + "epoch": 1.02, + "learning_rate": 1.9219854647944165e-05, + "loss": 3.4277, + "step": 1880064 + }, + { + "epoch": 1.02, + "learning_rate": 1.9211468700433648e-05, + "loss": 3.4286, + "step": 1880576 + }, + { + "epoch": 1.02, + "learning_rate": 1.9203099131726857e-05, + "loss": 3.4155, + "step": 1881088 + }, + { + "epoch": 1.02, + "learning_rate": 1.9194713184216337e-05, + "loss": 3.4237, + "step": 1881600 + }, + { + "epoch": 1.02, + "learning_rate": 1.9186327236705817e-05, + "loss": 3.4169, + "step": 1882112 + }, + { + "epoch": 1.02, + "learning_rate": 1.9177941289195297e-05, + "loss": 3.4278, + "step": 1882624 + }, + { + "epoch": 1.02, + "learning_rate": 1.9169555341684777e-05, + "loss": 3.4296, + "step": 1883136 + }, + { + "epoch": 1.02, + "learning_rate": 1.9161169394174257e-05, + "loss": 3.4266, + "step": 1883648 + }, + { + "epoch": 1.02, + "learning_rate": 1.9152783446663737e-05, + "loss": 3.4164, + "step": 1884160 + }, + { + "epoch": 1.02, + "learning_rate": 1.914441387795695e-05, + "loss": 3.414, + "step": 1884672 + }, + { + "epoch": 1.02, + "learning_rate": 1.913602793044643e-05, + "loss": 3.4156, + "step": 1885184 + }, + { + "epoch": 1.02, + "learning_rate": 1.912764198293591e-05, + "loss": 3.4186, + "step": 1885696 + }, + { + "epoch": 1.02, + "learning_rate": 1.9119256035425386e-05, + "loss": 3.4118, + "step": 1886208 + }, + { + "epoch": 1.02, + "learning_rate": 1.9110886466718598e-05, + "loss": 3.4293, + "step": 1886720 + }, + { + "epoch": 1.02, + "learning_rate": 1.910250051920808e-05, + "loss": 3.412, + "step": 1887232 + }, + { + "epoch": 1.02, + "learning_rate": 1.9094114571697558e-05, + "loss": 3.4199, + "step": 1887744 + }, + { + "epoch": 1.02, + "learning_rate": 1.9085728624187038e-05, + "loss": 3.4137, + "step": 1888256 + }, + { + "epoch": 1.02, + "learning_rate": 1.9077342676676518e-05, + "loss": 3.4252, + "step": 1888768 + }, + { + "epoch": 1.02, + "learning_rate": 1.9068956729165998e-05, + "loss": 3.4281, + "step": 1889280 + }, + { + "epoch": 1.02, + "learning_rate": 1.9060570781655478e-05, + "loss": 3.4161, + "step": 1889792 + }, + { + "epoch": 1.02, + "learning_rate": 1.905220121294869e-05, + "loss": 3.4359, + "step": 1890304 + }, + { + "epoch": 1.02, + "learning_rate": 1.904381526543817e-05, + "loss": 3.4395, + "step": 1890816 + }, + { + "epoch": 1.02, + "learning_rate": 1.903542931792765e-05, + "loss": 3.4246, + "step": 1891328 + }, + { + "epoch": 1.02, + "learning_rate": 1.902704337041713e-05, + "loss": 3.4229, + "step": 1891840 + }, + { + "epoch": 1.02, + "learning_rate": 1.901865742290661e-05, + "loss": 3.4158, + "step": 1892352 + }, + { + "epoch": 1.02, + "learning_rate": 1.901028785419982e-05, + "loss": 3.4196, + "step": 1892864 + }, + { + "epoch": 1.02, + "learning_rate": 1.9001901906689303e-05, + "loss": 3.4292, + "step": 1893376 + }, + { + "epoch": 1.02, + "learning_rate": 1.8993515959178783e-05, + "loss": 3.4241, + "step": 1893888 + }, + { + "epoch": 1.02, + "learning_rate": 1.8985130011668263e-05, + "loss": 3.4124, + "step": 1894400 + }, + { + "epoch": 1.02, + "learning_rate": 1.897674406415774e-05, + "loss": 3.4296, + "step": 1894912 + }, + { + "epoch": 1.02, + "learning_rate": 1.896835811664722e-05, + "loss": 3.4314, + "step": 1895424 + }, + { + "epoch": 1.02, + "learning_rate": 1.895998854794043e-05, + "loss": 3.4242, + "step": 1895936 + }, + { + "epoch": 1.02, + "learning_rate": 1.895160260042991e-05, + "loss": 3.4158, + "step": 1896448 + }, + { + "epoch": 1.02, + "learning_rate": 1.894321665291939e-05, + "loss": 3.4209, + "step": 1896960 + }, + { + "epoch": 1.02, + "learning_rate": 1.893483070540887e-05, + "loss": 3.4179, + "step": 1897472 + }, + { + "epoch": 1.02, + "learning_rate": 1.892644475789835e-05, + "loss": 3.4295, + "step": 1897984 + }, + { + "epoch": 1.02, + "learning_rate": 1.8918075189191564e-05, + "loss": 3.4228, + "step": 1898496 + }, + { + "epoch": 1.02, + "learning_rate": 1.890968924168104e-05, + "loss": 3.4318, + "step": 1899008 + }, + { + "epoch": 1.02, + "learning_rate": 1.890130329417052e-05, + "loss": 3.4088, + "step": 1899520 + }, + { + "epoch": 1.02, + "learning_rate": 1.8892933725463736e-05, + "loss": 3.4382, + "step": 1900032 + }, + { + "epoch": 1.02, + "learning_rate": 1.8884547777953213e-05, + "loss": 3.4148, + "step": 1900544 + }, + { + "epoch": 1.02, + "learning_rate": 1.8876161830442693e-05, + "loss": 3.4307, + "step": 1901056 + }, + { + "epoch": 1.02, + "learning_rate": 1.8867775882932173e-05, + "loss": 3.423, + "step": 1901568 + }, + { + "epoch": 1.02, + "learning_rate": 1.8859389935421653e-05, + "loss": 3.4165, + "step": 1902080 + }, + { + "epoch": 1.02, + "learning_rate": 1.8851020366714865e-05, + "loss": 3.4314, + "step": 1902592 + }, + { + "epoch": 1.02, + "learning_rate": 1.8842634419204345e-05, + "loss": 3.4398, + "step": 1903104 + }, + { + "epoch": 1.02, + "learning_rate": 1.8834248471693825e-05, + "loss": 3.4106, + "step": 1903616 + }, + { + "epoch": 1.02, + "learning_rate": 1.8825862524183305e-05, + "loss": 3.4301, + "step": 1904128 + }, + { + "epoch": 1.02, + "learning_rate": 1.8817492955476514e-05, + "loss": 3.4206, + "step": 1904640 + }, + { + "epoch": 1.02, + "learning_rate": 1.8809107007965994e-05, + "loss": 3.42, + "step": 1905152 + }, + { + "epoch": 1.02, + "learning_rate": 1.8800721060455474e-05, + "loss": 3.4206, + "step": 1905664 + }, + { + "epoch": 1.02, + "learning_rate": 1.8792335112944958e-05, + "loss": 3.4297, + "step": 1906176 + }, + { + "epoch": 1.02, + "learning_rate": 1.8783949165434437e-05, + "loss": 3.4321, + "step": 1906688 + }, + { + "epoch": 1.02, + "learning_rate": 1.8775563217923917e-05, + "loss": 3.418, + "step": 1907200 + }, + { + "epoch": 1.02, + "learning_rate": 1.8767193649217127e-05, + "loss": 3.4252, + "step": 1907712 + }, + { + "epoch": 1.03, + "eval_loss": 3.855289936065674, + "eval_runtime": 306.5121, + "eval_samples_per_second": 1244.946, + "eval_steps_per_second": 38.905, + "step": 1908000 + }, + { + "epoch": 0.0, + "learning_rate": 1.8758807701706606e-05, + "loss": 3.4177, + "step": 1908224 + }, + { + "epoch": 0.0, + "learning_rate": 1.8750421754196086e-05, + "loss": 3.4133, + "step": 1908736 + }, + { + "epoch": 0.0, + "learning_rate": 1.8742035806685566e-05, + "loss": 3.4248, + "step": 1909248 + }, + { + "epoch": 0.0, + "learning_rate": 1.873366623797878e-05, + "loss": 3.4211, + "step": 1909760 + }, + { + "epoch": 0.0, + "learning_rate": 1.872528029046826e-05, + "loss": 3.4292, + "step": 1910272 + }, + { + "epoch": 0.0, + "learning_rate": 1.871689434295774e-05, + "loss": 3.4124, + "step": 1910784 + }, + { + "epoch": 0.0, + "learning_rate": 1.8708508395447215e-05, + "loss": 3.4233, + "step": 1911296 + }, + { + "epoch": 0.0, + "learning_rate": 1.8700138826740428e-05, + "loss": 3.4159, + "step": 1911808 + }, + { + "epoch": 0.0, + "learning_rate": 1.869175287922991e-05, + "loss": 3.4186, + "step": 1912320 + }, + { + "epoch": 0.0, + "learning_rate": 1.868336693171939e-05, + "loss": 3.421, + "step": 1912832 + }, + { + "epoch": 0.0, + "learning_rate": 1.8674980984208868e-05, + "loss": 3.4174, + "step": 1913344 + }, + { + "epoch": 0.0, + "learning_rate": 1.866661141550208e-05, + "loss": 3.4258, + "step": 1913856 + }, + { + "epoch": 0.0, + "learning_rate": 1.865822546799156e-05, + "loss": 3.4293, + "step": 1914368 + }, + { + "epoch": 0.0, + "learning_rate": 1.864983952048104e-05, + "loss": 3.4131, + "step": 1914880 + }, + { + "epoch": 0.0, + "learning_rate": 1.864145357297052e-05, + "loss": 3.4186, + "step": 1915392 + }, + { + "epoch": 0.0, + "learning_rate": 1.863306762546e-05, + "loss": 3.411, + "step": 1915904 + }, + { + "epoch": 0.0, + "learning_rate": 1.8624698056753213e-05, + "loss": 3.4087, + "step": 1916416 + }, + { + "epoch": 0.0, + "learning_rate": 1.861631210924269e-05, + "loss": 3.4191, + "step": 1916928 + }, + { + "epoch": 0.0, + "learning_rate": 1.860792616173217e-05, + "loss": 3.4123, + "step": 1917440 + }, + { + "epoch": 0.0, + "learning_rate": 1.859954021422165e-05, + "loss": 3.4205, + "step": 1917952 + }, + { + "epoch": 0.0, + "learning_rate": 1.859115426671113e-05, + "loss": 3.4267, + "step": 1918464 + }, + { + "epoch": 0.0, + "learning_rate": 1.8582768319200612e-05, + "loss": 3.4254, + "step": 1918976 + }, + { + "epoch": 0.0, + "learning_rate": 1.8574382371690092e-05, + "loss": 3.4265, + "step": 1919488 + }, + { + "epoch": 0.0, + "learning_rate": 1.8565996424179572e-05, + "loss": 3.4233, + "step": 1920000 + }, + { + "epoch": 0.0, + "learning_rate": 1.855762685547278e-05, + "loss": 3.4103, + "step": 1920512 + }, + { + "epoch": 0.0, + "learning_rate": 1.854924090796226e-05, + "loss": 3.4241, + "step": 1921024 + }, + { + "epoch": 0.0, + "learning_rate": 1.854085496045174e-05, + "loss": 3.4117, + "step": 1921536 + }, + { + "epoch": 0.0, + "learning_rate": 1.853246901294122e-05, + "loss": 3.4214, + "step": 1922048 + }, + { + "epoch": 0.0, + "learning_rate": 1.8524099444234434e-05, + "loss": 3.411, + "step": 1922560 + }, + { + "epoch": 0.0, + "learning_rate": 1.8515729875527643e-05, + "loss": 3.4143, + "step": 1923072 + }, + { + "epoch": 0.01, + "learning_rate": 1.8507343928017123e-05, + "loss": 3.4143, + "step": 1923584 + }, + { + "epoch": 0.01, + "learning_rate": 1.8498957980506603e-05, + "loss": 3.4216, + "step": 1924096 + }, + { + "epoch": 0.01, + "learning_rate": 1.8490572032996083e-05, + "loss": 3.4192, + "step": 1924608 + }, + { + "epoch": 0.01, + "learning_rate": 1.8482186085485566e-05, + "loss": 3.4187, + "step": 1925120 + }, + { + "epoch": 0.01, + "learning_rate": 1.8473800137975046e-05, + "loss": 3.4134, + "step": 1925632 + }, + { + "epoch": 0.01, + "learning_rate": 1.8465430569268255e-05, + "loss": 3.4215, + "step": 1926144 + }, + { + "epoch": 0.01, + "learning_rate": 1.8457044621757735e-05, + "loss": 3.4199, + "step": 1926656 + }, + { + "epoch": 0.01, + "learning_rate": 1.8448658674247215e-05, + "loss": 3.4086, + "step": 1927168 + }, + { + "epoch": 0.01, + "learning_rate": 1.8440272726736695e-05, + "loss": 3.4146, + "step": 1927680 + }, + { + "epoch": 0.01, + "learning_rate": 1.8431886779226175e-05, + "loss": 3.4068, + "step": 1928192 + }, + { + "epoch": 0.01, + "learning_rate": 1.8423500831715655e-05, + "loss": 3.4116, + "step": 1928704 + }, + { + "epoch": 0.01, + "learning_rate": 1.8415114884205135e-05, + "loss": 3.4192, + "step": 1929216 + }, + { + "epoch": 0.01, + "learning_rate": 1.8406728936694615e-05, + "loss": 3.4249, + "step": 1929728 + }, + { + "epoch": 0.01, + "learning_rate": 1.8398359367987824e-05, + "loss": 3.4204, + "step": 1930240 + }, + { + "epoch": 0.01, + "learning_rate": 1.8389973420477304e-05, + "loss": 3.4207, + "step": 1930752 + }, + { + "epoch": 0.01, + "learning_rate": 1.8381587472966784e-05, + "loss": 3.426, + "step": 1931264 + }, + { + "epoch": 0.01, + "learning_rate": 1.8373201525456267e-05, + "loss": 3.4191, + "step": 1931776 + }, + { + "epoch": 0.01, + "learning_rate": 1.8364831956749476e-05, + "loss": 3.4131, + "step": 1932288 + }, + { + "epoch": 0.01, + "learning_rate": 1.8356446009238956e-05, + "loss": 3.391, + "step": 1932800 + }, + { + "epoch": 0.01, + "learning_rate": 1.8348060061728436e-05, + "loss": 3.4353, + "step": 1933312 + }, + { + "epoch": 0.01, + "learning_rate": 1.8339674114217916e-05, + "loss": 3.4102, + "step": 1933824 + }, + { + "epoch": 0.01, + "learning_rate": 1.8331288166707396e-05, + "loss": 3.4147, + "step": 1934336 + }, + { + "epoch": 0.01, + "learning_rate": 1.8322902219196876e-05, + "loss": 3.4159, + "step": 1934848 + }, + { + "epoch": 0.01, + "learning_rate": 1.8314516271686356e-05, + "loss": 3.4065, + "step": 1935360 + }, + { + "epoch": 0.01, + "learning_rate": 1.8306130324175836e-05, + "loss": 3.4053, + "step": 1935872 + }, + { + "epoch": 0.01, + "learning_rate": 1.8297777134272777e-05, + "loss": 3.4028, + "step": 1936384 + }, + { + "epoch": 0.01, + "learning_rate": 1.8289391186762257e-05, + "loss": 3.4157, + "step": 1936896 + }, + { + "epoch": 0.01, + "learning_rate": 1.8281005239251737e-05, + "loss": 3.407, + "step": 1937408 + }, + { + "epoch": 0.01, + "learning_rate": 1.827261929174122e-05, + "loss": 3.4278, + "step": 1937920 + }, + { + "epoch": 0.01, + "learning_rate": 1.82642333442307e-05, + "loss": 3.4128, + "step": 1938432 + }, + { + "epoch": 0.01, + "learning_rate": 1.825586377552391e-05, + "loss": 3.3992, + "step": 1938944 + }, + { + "epoch": 0.01, + "learning_rate": 1.824747782801339e-05, + "loss": 3.4254, + "step": 1939456 + }, + { + "epoch": 0.01, + "learning_rate": 1.823909188050287e-05, + "loss": 3.4067, + "step": 1939968 + }, + { + "epoch": 0.01, + "learning_rate": 1.823070593299235e-05, + "loss": 3.403, + "step": 1940480 + }, + { + "epoch": 0.01, + "learning_rate": 1.822231998548183e-05, + "loss": 3.419, + "step": 1940992 + }, + { + "epoch": 0.01, + "learning_rate": 1.821393403797131e-05, + "loss": 3.4232, + "step": 1941504 + }, + { + "epoch": 0.01, + "learning_rate": 1.820554809046079e-05, + "loss": 3.4039, + "step": 1942016 + }, + { + "epoch": 0.01, + "learning_rate": 1.819716214295027e-05, + "loss": 3.4059, + "step": 1942528 + }, + { + "epoch": 0.01, + "learning_rate": 1.818879257424348e-05, + "loss": 3.4002, + "step": 1943040 + }, + { + "epoch": 0.01, + "learning_rate": 1.818040662673296e-05, + "loss": 3.4132, + "step": 1943552 + }, + { + "epoch": 0.01, + "learning_rate": 1.817202067922244e-05, + "loss": 3.4235, + "step": 1944064 + }, + { + "epoch": 0.01, + "learning_rate": 1.8163634731711922e-05, + "loss": 3.4165, + "step": 1944576 + }, + { + "epoch": 0.01, + "learning_rate": 1.815526516300513e-05, + "loss": 3.4177, + "step": 1945088 + }, + { + "epoch": 0.01, + "learning_rate": 1.8146895594298343e-05, + "loss": 3.4173, + "step": 1945600 + }, + { + "epoch": 0.01, + "learning_rate": 1.813850964678782e-05, + "loss": 3.4233, + "step": 1946112 + }, + { + "epoch": 0.01, + "learning_rate": 1.81301236992773e-05, + "loss": 3.4117, + "step": 1946624 + }, + { + "epoch": 0.01, + "learning_rate": 1.8121737751766783e-05, + "loss": 3.4257, + "step": 1947136 + }, + { + "epoch": 0.01, + "learning_rate": 1.8113351804256263e-05, + "loss": 3.4056, + "step": 1947648 + }, + { + "epoch": 0.01, + "learning_rate": 1.8104982235549472e-05, + "loss": 3.4128, + "step": 1948160 + }, + { + "epoch": 0.01, + "learning_rate": 1.8096596288038952e-05, + "loss": 3.4152, + "step": 1948672 + }, + { + "epoch": 0.01, + "learning_rate": 1.8088210340528432e-05, + "loss": 3.4188, + "step": 1949184 + }, + { + "epoch": 0.01, + "learning_rate": 1.8079824393017912e-05, + "loss": 3.4177, + "step": 1949696 + }, + { + "epoch": 0.01, + "learning_rate": 1.8071438445507392e-05, + "loss": 3.4229, + "step": 1950208 + }, + { + "epoch": 0.01, + "learning_rate": 1.8063052497996875e-05, + "loss": 3.4064, + "step": 1950720 + }, + { + "epoch": 0.01, + "learning_rate": 1.8054666550486355e-05, + "loss": 3.4075, + "step": 1951232 + }, + { + "epoch": 0.01, + "learning_rate": 1.8046280602975832e-05, + "loss": 3.4155, + "step": 1951744 + }, + { + "epoch": 0.01, + "learning_rate": 1.8037911034269044e-05, + "loss": 3.4199, + "step": 1952256 + }, + { + "epoch": 0.01, + "learning_rate": 1.8029525086758524e-05, + "loss": 3.4049, + "step": 1952768 + }, + { + "epoch": 0.01, + "learning_rate": 1.8021155518051737e-05, + "loss": 3.4105, + "step": 1953280 + }, + { + "epoch": 0.02, + "learning_rate": 1.8012769570541217e-05, + "loss": 3.4153, + "step": 1953792 + }, + { + "epoch": 0.02, + "learning_rate": 1.8004383623030697e-05, + "loss": 3.4156, + "step": 1954304 + }, + { + "epoch": 0.02, + "learning_rate": 1.7995997675520177e-05, + "loss": 3.4116, + "step": 1954816 + }, + { + "epoch": 0.02, + "learning_rate": 1.7987611728009653e-05, + "loss": 3.4048, + "step": 1955328 + }, + { + "epoch": 0.02, + "learning_rate": 1.7979242159302866e-05, + "loss": 3.4196, + "step": 1955840 + }, + { + "epoch": 0.02, + "learning_rate": 1.7970856211792346e-05, + "loss": 3.4193, + "step": 1956352 + }, + { + "epoch": 0.02, + "learning_rate": 1.796247026428183e-05, + "loss": 3.4168, + "step": 1956864 + }, + { + "epoch": 0.02, + "learning_rate": 1.7954084316771306e-05, + "loss": 3.4046, + "step": 1957376 + }, + { + "epoch": 0.02, + "learning_rate": 1.7945714748064518e-05, + "loss": 3.4153, + "step": 1957888 + }, + { + "epoch": 0.02, + "learning_rate": 1.7937328800553998e-05, + "loss": 3.4066, + "step": 1958400 + }, + { + "epoch": 0.02, + "learning_rate": 1.7928942853043475e-05, + "loss": 3.4213, + "step": 1958912 + }, + { + "epoch": 0.02, + "learning_rate": 1.7920556905532958e-05, + "loss": 3.4173, + "step": 1959424 + }, + { + "epoch": 0.02, + "learning_rate": 1.7912170958022438e-05, + "loss": 3.4146, + "step": 1959936 + }, + { + "epoch": 0.02, + "learning_rate": 1.7903785010511918e-05, + "loss": 3.4109, + "step": 1960448 + }, + { + "epoch": 0.02, + "learning_rate": 1.7895415441805127e-05, + "loss": 3.4023, + "step": 1960960 + }, + { + "epoch": 0.02, + "learning_rate": 1.7887029494294607e-05, + "loss": 3.4068, + "step": 1961472 + }, + { + "epoch": 0.02, + "learning_rate": 1.7878643546784087e-05, + "loss": 3.4049, + "step": 1961984 + }, + { + "epoch": 0.02, + "learning_rate": 1.7870257599273567e-05, + "loss": 3.4037, + "step": 1962496 + }, + { + "epoch": 0.02, + "learning_rate": 1.7861871651763047e-05, + "loss": 3.4149, + "step": 1963008 + }, + { + "epoch": 0.02, + "learning_rate": 1.785348570425253e-05, + "loss": 3.4019, + "step": 1963520 + }, + { + "epoch": 0.02, + "learning_rate": 1.784509975674201e-05, + "loss": 3.4082, + "step": 1964032 + }, + { + "epoch": 0.02, + "learning_rate": 1.783673018803522e-05, + "loss": 3.4093, + "step": 1964544 + }, + { + "epoch": 0.02, + "learning_rate": 1.78283442405247e-05, + "loss": 3.4054, + "step": 1965056 + }, + { + "epoch": 0.02, + "learning_rate": 1.781995829301418e-05, + "loss": 3.4201, + "step": 1965568 + }, + { + "epoch": 0.02, + "learning_rate": 1.781157234550366e-05, + "loss": 3.4048, + "step": 1966080 + }, + { + "epoch": 0.02, + "learning_rate": 1.780318639799314e-05, + "loss": 3.4245, + "step": 1966592 + }, + { + "epoch": 0.02, + "learning_rate": 1.779481682928635e-05, + "loss": 3.4304, + "step": 1967104 + }, + { + "epoch": 0.02, + "learning_rate": 1.778643088177583e-05, + "loss": 3.4165, + "step": 1967616 + }, + { + "epoch": 0.02, + "learning_rate": 1.7778044934265308e-05, + "loss": 3.4098, + "step": 1968128 + }, + { + "epoch": 0.02, + "learning_rate": 1.7769658986754788e-05, + "loss": 3.4071, + "step": 1968640 + }, + { + "epoch": 0.02, + "learning_rate": 1.7761273039244268e-05, + "loss": 3.4113, + "step": 1969152 + }, + { + "epoch": 0.02, + "learning_rate": 1.7752903470537484e-05, + "loss": 3.4179, + "step": 1969664 + }, + { + "epoch": 0.02, + "learning_rate": 1.774451752302696e-05, + "loss": 3.4125, + "step": 1970176 + }, + { + "epoch": 0.02, + "learning_rate": 1.773613157551644e-05, + "loss": 3.4018, + "step": 1970688 + }, + { + "epoch": 0.02, + "learning_rate": 1.772774562800592e-05, + "loss": 3.4206, + "step": 1971200 + }, + { + "epoch": 0.02, + "learning_rate": 1.77193596804954e-05, + "loss": 3.4223, + "step": 1971712 + }, + { + "epoch": 0.02, + "learning_rate": 1.7710990111788613e-05, + "loss": 3.4084, + "step": 1972224 + }, + { + "epoch": 0.02, + "learning_rate": 1.7702604164278093e-05, + "loss": 3.4057, + "step": 1972736 + }, + { + "epoch": 0.02, + "learning_rate": 1.7694218216767573e-05, + "loss": 3.4158, + "step": 1973248 + }, + { + "epoch": 0.02, + "learning_rate": 1.7685832269257053e-05, + "loss": 3.405, + "step": 1973760 + }, + { + "epoch": 0.02, + "learning_rate": 1.7677446321746533e-05, + "loss": 3.4224, + "step": 1974272 + }, + { + "epoch": 0.02, + "learning_rate": 1.7669060374236013e-05, + "loss": 3.4095, + "step": 1974784 + }, + { + "epoch": 0.02, + "learning_rate": 1.766069080552922e-05, + "loss": 3.4225, + "step": 1975296 + }, + { + "epoch": 0.02, + "learning_rate": 1.7652304858018705e-05, + "loss": 3.3981, + "step": 1975808 + }, + { + "epoch": 0.02, + "learning_rate": 1.7643918910508185e-05, + "loss": 3.4202, + "step": 1976320 + }, + { + "epoch": 0.02, + "learning_rate": 1.763553296299766e-05, + "loss": 3.4144, + "step": 1976832 + }, + { + "epoch": 0.02, + "learning_rate": 1.762714701548714e-05, + "loss": 3.4138, + "step": 1977344 + }, + { + "epoch": 0.02, + "learning_rate": 1.761876106797662e-05, + "loss": 3.4141, + "step": 1977856 + }, + { + "epoch": 0.02, + "learning_rate": 1.76103751204661e-05, + "loss": 3.404, + "step": 1978368 + }, + { + "epoch": 0.02, + "learning_rate": 1.7602005551759314e-05, + "loss": 3.4207, + "step": 1978880 + }, + { + "epoch": 0.02, + "learning_rate": 1.7593619604248794e-05, + "loss": 3.4355, + "step": 1979392 + }, + { + "epoch": 0.02, + "learning_rate": 1.7585233656738274e-05, + "loss": 3.4007, + "step": 1979904 + }, + { + "epoch": 0.02, + "learning_rate": 1.7576847709227754e-05, + "loss": 3.4207, + "step": 1980416 + }, + { + "epoch": 0.02, + "learning_rate": 1.7568478140520963e-05, + "loss": 3.4124, + "step": 1980928 + }, + { + "epoch": 0.02, + "learning_rate": 1.7560092193010443e-05, + "loss": 3.4065, + "step": 1981440 + }, + { + "epoch": 0.02, + "learning_rate": 1.7551706245499923e-05, + "loss": 3.4118, + "step": 1981952 + }, + { + "epoch": 0.02, + "learning_rate": 1.7543320297989406e-05, + "loss": 3.417, + "step": 1982464 + }, + { + "epoch": 0.02, + "learning_rate": 1.7534934350478886e-05, + "loss": 3.4184, + "step": 1982976 + }, + { + "epoch": 0.02, + "learning_rate": 1.7526564781772095e-05, + "loss": 3.4117, + "step": 1983488 + }, + { + "epoch": 0.02, + "learning_rate": 1.7518178834261575e-05, + "loss": 3.4141, + "step": 1984000 + }, + { + "epoch": 0.03, + "eval_loss": 3.858607053756714, + "eval_runtime": 306.4869, + "eval_samples_per_second": 1245.048, + "eval_steps_per_second": 38.909, + "step": 1984320 + }, + { + "epoch": 1.0, + "learning_rate": 1.7509792886751055e-05, + "loss": 3.4037, + "step": 1984512 + }, + { + "epoch": 1.0, + "learning_rate": 1.7501406939240535e-05, + "loss": 3.4036, + "step": 1985024 + }, + { + "epoch": 1.0, + "learning_rate": 1.7493020991730015e-05, + "loss": 3.4124, + "step": 1985536 + }, + { + "epoch": 1.0, + "learning_rate": 1.7484651423023227e-05, + "loss": 3.4107, + "step": 1986048 + }, + { + "epoch": 1.0, + "learning_rate": 1.7476265475512707e-05, + "loss": 3.4194, + "step": 1986560 + }, + { + "epoch": 1.0, + "learning_rate": 1.7467879528002187e-05, + "loss": 3.4038, + "step": 1987072 + }, + { + "epoch": 1.0, + "learning_rate": 1.7459493580491667e-05, + "loss": 3.4138, + "step": 1987584 + }, + { + "epoch": 1.0, + "learning_rate": 1.7451107632981144e-05, + "loss": 3.4039, + "step": 1988096 + }, + { + "epoch": 1.0, + "learning_rate": 1.7442721685470624e-05, + "loss": 3.4106, + "step": 1988608 + }, + { + "epoch": 1.0, + "learning_rate": 1.743435211676384e-05, + "loss": 3.411, + "step": 1989120 + }, + { + "epoch": 1.0, + "learning_rate": 1.7425966169253316e-05, + "loss": 3.4031, + "step": 1989632 + }, + { + "epoch": 1.0, + "learning_rate": 1.7417580221742796e-05, + "loss": 3.4156, + "step": 1990144 + }, + { + "epoch": 1.0, + "learning_rate": 1.7409194274232276e-05, + "loss": 3.4215, + "step": 1990656 + }, + { + "epoch": 1.0, + "learning_rate": 1.7400808326721756e-05, + "loss": 3.4011, + "step": 1991168 + }, + { + "epoch": 1.0, + "learning_rate": 1.7392422379211236e-05, + "loss": 3.4112, + "step": 1991680 + }, + { + "epoch": 1.0, + "learning_rate": 1.7384036431700716e-05, + "loss": 3.3977, + "step": 1992192 + }, + { + "epoch": 1.0, + "learning_rate": 1.737566686299393e-05, + "loss": 3.4003, + "step": 1992704 + }, + { + "epoch": 1.0, + "learning_rate": 1.736728091548341e-05, + "loss": 3.4067, + "step": 1993216 + }, + { + "epoch": 1.0, + "learning_rate": 1.735889496797289e-05, + "loss": 3.4009, + "step": 1993728 + }, + { + "epoch": 1.0, + "learning_rate": 1.735050902046237e-05, + "loss": 3.4108, + "step": 1994240 + }, + { + "epoch": 1.0, + "learning_rate": 1.7342139451755578e-05, + "loss": 3.4146, + "step": 1994752 + }, + { + "epoch": 1.0, + "learning_rate": 1.733375350424506e-05, + "loss": 3.4122, + "step": 1995264 + }, + { + "epoch": 1.0, + "learning_rate": 1.732536755673454e-05, + "loss": 3.4148, + "step": 1995776 + }, + { + "epoch": 1.0, + "learning_rate": 1.731698160922402e-05, + "loss": 3.4113, + "step": 1996288 + }, + { + "epoch": 1.0, + "learning_rate": 1.7308595661713497e-05, + "loss": 3.4044, + "step": 1996800 + }, + { + "epoch": 1.0, + "learning_rate": 1.7300209714202977e-05, + "loss": 3.4107, + "step": 1997312 + }, + { + "epoch": 1.0, + "learning_rate": 1.7291823766692457e-05, + "loss": 3.404, + "step": 1997824 + }, + { + "epoch": 1.0, + "learning_rate": 1.7283437819181937e-05, + "loss": 3.4124, + "step": 1998336 + }, + { + "epoch": 1.0, + "learning_rate": 1.7275084629278882e-05, + "loss": 3.4005, + "step": 1998848 + }, + { + "epoch": 1.0, + "learning_rate": 1.7266698681768362e-05, + "loss": 3.4047, + "step": 1999360 + }, + { + "epoch": 1.01, + "learning_rate": 1.7258312734257842e-05, + "loss": 3.4048, + "step": 1999872 + }, + { + "epoch": 1.01, + "learning_rate": 1.7249926786747322e-05, + "loss": 3.4103, + "step": 2000384 + }, + { + "epoch": 1.01, + "learning_rate": 1.72415408392368e-05, + "loss": 3.4133, + "step": 2000896 + }, + { + "epoch": 1.01, + "learning_rate": 1.723315489172628e-05, + "loss": 3.4073, + "step": 2001408 + }, + { + "epoch": 1.01, + "learning_rate": 1.7224768944215762e-05, + "loss": 3.4047, + "step": 2001920 + }, + { + "epoch": 1.01, + "learning_rate": 1.721639937550897e-05, + "loss": 3.4059, + "step": 2002432 + }, + { + "epoch": 1.01, + "learning_rate": 1.720801342799845e-05, + "loss": 3.4105, + "step": 2002944 + }, + { + "epoch": 1.01, + "learning_rate": 1.719962748048793e-05, + "loss": 3.3977, + "step": 2003456 + }, + { + "epoch": 1.01, + "learning_rate": 1.719124153297741e-05, + "loss": 3.4033, + "step": 2003968 + }, + { + "epoch": 1.01, + "learning_rate": 1.718285558546689e-05, + "loss": 3.3985, + "step": 2004480 + }, + { + "epoch": 1.01, + "learning_rate": 1.717446963795637e-05, + "loss": 3.4003, + "step": 2004992 + }, + { + "epoch": 1.01, + "learning_rate": 1.7166083690445854e-05, + "loss": 3.4052, + "step": 2005504 + }, + { + "epoch": 1.01, + "learning_rate": 1.715769774293533e-05, + "loss": 3.4157, + "step": 2006016 + }, + { + "epoch": 1.01, + "learning_rate": 1.7149328174228543e-05, + "loss": 3.4099, + "step": 2006528 + }, + { + "epoch": 1.01, + "learning_rate": 1.7140958605521752e-05, + "loss": 3.4125, + "step": 2007040 + }, + { + "epoch": 1.01, + "learning_rate": 1.7132572658011232e-05, + "loss": 3.4133, + "step": 2007552 + }, + { + "epoch": 1.01, + "learning_rate": 1.7124186710500716e-05, + "loss": 3.4088, + "step": 2008064 + }, + { + "epoch": 1.01, + "learning_rate": 1.7115800762990196e-05, + "loss": 3.4067, + "step": 2008576 + }, + { + "epoch": 1.01, + "learning_rate": 1.7107414815479676e-05, + "loss": 3.379, + "step": 2009088 + }, + { + "epoch": 1.01, + "learning_rate": 1.7099028867969152e-05, + "loss": 3.4205, + "step": 2009600 + }, + { + "epoch": 1.01, + "learning_rate": 1.7090659299262365e-05, + "loss": 3.4009, + "step": 2010112 + }, + { + "epoch": 1.01, + "learning_rate": 1.7082273351751845e-05, + "loss": 3.4065, + "step": 2010624 + }, + { + "epoch": 1.01, + "learning_rate": 1.7073887404241325e-05, + "loss": 3.404, + "step": 2011136 + }, + { + "epoch": 1.01, + "learning_rate": 1.7065501456730804e-05, + "loss": 3.3953, + "step": 2011648 + }, + { + "epoch": 1.01, + "learning_rate": 1.7057115509220284e-05, + "loss": 3.3982, + "step": 2012160 + }, + { + "epoch": 1.01, + "learning_rate": 1.7048745940513497e-05, + "loss": 3.3939, + "step": 2012672 + }, + { + "epoch": 1.01, + "learning_rate": 1.7040359993002973e-05, + "loss": 3.4091, + "step": 2013184 + }, + { + "epoch": 1.01, + "learning_rate": 1.7031974045492453e-05, + "loss": 3.3966, + "step": 2013696 + }, + { + "epoch": 1.01, + "learning_rate": 1.7023588097981937e-05, + "loss": 3.4156, + "step": 2014208 + }, + { + "epoch": 1.01, + "learning_rate": 1.7015202150471417e-05, + "loss": 3.4022, + "step": 2014720 + }, + { + "epoch": 1.01, + "learning_rate": 1.7006816202960897e-05, + "loss": 3.3887, + "step": 2015232 + }, + { + "epoch": 1.01, + "learning_rate": 1.6998446634254106e-05, + "loss": 3.4176, + "step": 2015744 + }, + { + "epoch": 1.01, + "learning_rate": 1.6990060686743586e-05, + "loss": 3.3953, + "step": 2016256 + }, + { + "epoch": 1.01, + "learning_rate": 1.6981674739233066e-05, + "loss": 3.3925, + "step": 2016768 + }, + { + "epoch": 1.01, + "learning_rate": 1.6973288791722546e-05, + "loss": 3.4063, + "step": 2017280 + }, + { + "epoch": 1.01, + "learning_rate": 1.6964902844212026e-05, + "loss": 3.4131, + "step": 2017792 + }, + { + "epoch": 1.01, + "learning_rate": 1.695651689670151e-05, + "loss": 3.3941, + "step": 2018304 + }, + { + "epoch": 1.01, + "learning_rate": 1.6948130949190986e-05, + "loss": 3.3946, + "step": 2018816 + }, + { + "epoch": 1.01, + "learning_rate": 1.6939745001680465e-05, + "loss": 3.3905, + "step": 2019328 + }, + { + "epoch": 1.01, + "learning_rate": 1.6931375432973678e-05, + "loss": 3.3994, + "step": 2019840 + }, + { + "epoch": 1.01, + "learning_rate": 1.6922989485463155e-05, + "loss": 3.4122, + "step": 2020352 + }, + { + "epoch": 1.01, + "learning_rate": 1.691461991675637e-05, + "loss": 3.4068, + "step": 2020864 + }, + { + "epoch": 1.01, + "learning_rate": 1.690623396924585e-05, + "loss": 3.4068, + "step": 2021376 + }, + { + "epoch": 1.01, + "learning_rate": 1.689784802173533e-05, + "loss": 3.4058, + "step": 2021888 + }, + { + "epoch": 1.01, + "learning_rate": 1.6889462074224807e-05, + "loss": 3.4132, + "step": 2022400 + }, + { + "epoch": 1.01, + "learning_rate": 1.688109250551802e-05, + "loss": 3.4045, + "step": 2022912 + }, + { + "epoch": 1.01, + "learning_rate": 1.68727065580075e-05, + "loss": 3.414, + "step": 2023424 + }, + { + "epoch": 1.01, + "learning_rate": 1.686432061049698e-05, + "loss": 3.3954, + "step": 2023936 + }, + { + "epoch": 1.01, + "learning_rate": 1.685593466298646e-05, + "loss": 3.4014, + "step": 2024448 + }, + { + "epoch": 1.01, + "learning_rate": 1.684754871547594e-05, + "loss": 3.4056, + "step": 2024960 + }, + { + "epoch": 1.01, + "learning_rate": 1.683917914676915e-05, + "loss": 3.4073, + "step": 2025472 + }, + { + "epoch": 1.01, + "learning_rate": 1.6830793199258628e-05, + "loss": 3.4085, + "step": 2025984 + }, + { + "epoch": 1.01, + "learning_rate": 1.6822407251748108e-05, + "loss": 3.4114, + "step": 2026496 + }, + { + "epoch": 1.01, + "learning_rate": 1.681402130423759e-05, + "loss": 3.3991, + "step": 2027008 + }, + { + "epoch": 1.01, + "learning_rate": 1.680563535672707e-05, + "loss": 3.3967, + "step": 2027520 + }, + { + "epoch": 1.01, + "learning_rate": 1.679724940921655e-05, + "loss": 3.4035, + "step": 2028032 + }, + { + "epoch": 1.01, + "learning_rate": 1.678886346170603e-05, + "loss": 3.4096, + "step": 2028544 + }, + { + "epoch": 1.01, + "learning_rate": 1.678047751419551e-05, + "loss": 3.3961, + "step": 2029056 + }, + { + "epoch": 1.01, + "learning_rate": 1.677210794548872e-05, + "loss": 3.4023, + "step": 2029568 + }, + { + "epoch": 1.01, + "learning_rate": 1.67637219979782e-05, + "loss": 3.4114, + "step": 2030080 + }, + { + "epoch": 1.02, + "learning_rate": 1.6755336050467684e-05, + "loss": 3.4004, + "step": 2030592 + }, + { + "epoch": 1.02, + "learning_rate": 1.6746950102957164e-05, + "loss": 3.3991, + "step": 2031104 + }, + { + "epoch": 1.02, + "learning_rate": 1.673856415544664e-05, + "loss": 3.3973, + "step": 2031616 + }, + { + "epoch": 1.02, + "learning_rate": 1.6730194586739853e-05, + "loss": 3.4071, + "step": 2032128 + }, + { + "epoch": 1.02, + "learning_rate": 1.6721808639229333e-05, + "loss": 3.4114, + "step": 2032640 + }, + { + "epoch": 1.02, + "learning_rate": 1.671342269171881e-05, + "loss": 3.4056, + "step": 2033152 + }, + { + "epoch": 1.02, + "learning_rate": 1.6705036744208293e-05, + "loss": 3.3971, + "step": 2033664 + }, + { + "epoch": 1.02, + "learning_rate": 1.6696667175501505e-05, + "loss": 3.4018, + "step": 2034176 + }, + { + "epoch": 1.02, + "learning_rate": 1.6688281227990985e-05, + "loss": 3.3975, + "step": 2034688 + }, + { + "epoch": 1.02, + "learning_rate": 1.667989528048046e-05, + "loss": 3.4091, + "step": 2035200 + }, + { + "epoch": 1.02, + "learning_rate": 1.667150933296994e-05, + "loss": 3.4074, + "step": 2035712 + }, + { + "epoch": 1.02, + "learning_rate": 1.666312338545942e-05, + "loss": 3.4014, + "step": 2036224 + }, + { + "epoch": 1.02, + "learning_rate": 1.66547374379489e-05, + "loss": 3.3978, + "step": 2036736 + }, + { + "epoch": 1.02, + "learning_rate": 1.6646351490438385e-05, + "loss": 3.3981, + "step": 2037248 + }, + { + "epoch": 1.02, + "learning_rate": 1.6637981921731594e-05, + "loss": 3.3935, + "step": 2037760 + }, + { + "epoch": 1.02, + "learning_rate": 1.6629595974221074e-05, + "loss": 3.397, + "step": 2038272 + }, + { + "epoch": 1.02, + "learning_rate": 1.6621210026710554e-05, + "loss": 3.3953, + "step": 2038784 + }, + { + "epoch": 1.02, + "learning_rate": 1.6612824079200034e-05, + "loss": 3.3978, + "step": 2039296 + }, + { + "epoch": 1.02, + "learning_rate": 1.6604438131689514e-05, + "loss": 3.3981, + "step": 2039808 + }, + { + "epoch": 1.02, + "learning_rate": 1.6596052184178994e-05, + "loss": 3.3949, + "step": 2040320 + }, + { + "epoch": 1.02, + "learning_rate": 1.6587666236668474e-05, + "loss": 3.4003, + "step": 2040832 + }, + { + "epoch": 1.02, + "learning_rate": 1.6579280289157954e-05, + "loss": 3.3939, + "step": 2041344 + }, + { + "epoch": 1.02, + "learning_rate": 1.6570910720451166e-05, + "loss": 3.4111, + "step": 2041856 + }, + { + "epoch": 1.02, + "learning_rate": 1.6562524772940643e-05, + "loss": 3.3941, + "step": 2042368 + }, + { + "epoch": 1.02, + "learning_rate": 1.6554155204233855e-05, + "loss": 3.4152, + "step": 2042880 + }, + { + "epoch": 1.02, + "learning_rate": 1.654576925672334e-05, + "loss": 3.4184, + "step": 2043392 + }, + { + "epoch": 1.02, + "learning_rate": 1.653738330921282e-05, + "loss": 3.4094, + "step": 2043904 + }, + { + "epoch": 1.02, + "learning_rate": 1.6528997361702295e-05, + "loss": 3.3983, + "step": 2044416 + }, + { + "epoch": 1.02, + "learning_rate": 1.6520611414191775e-05, + "loss": 3.3988, + "step": 2044928 + }, + { + "epoch": 1.02, + "learning_rate": 1.6512241845484987e-05, + "loss": 3.401, + "step": 2045440 + }, + { + "epoch": 1.02, + "learning_rate": 1.6503855897974464e-05, + "loss": 3.4085, + "step": 2045952 + }, + { + "epoch": 1.02, + "learning_rate": 1.6495469950463947e-05, + "loss": 3.4019, + "step": 2046464 + }, + { + "epoch": 1.02, + "learning_rate": 1.6487084002953427e-05, + "loss": 3.3955, + "step": 2046976 + }, + { + "epoch": 1.02, + "learning_rate": 1.6478698055442907e-05, + "loss": 3.4067, + "step": 2047488 + }, + { + "epoch": 1.02, + "learning_rate": 1.6470312107932387e-05, + "loss": 3.4165, + "step": 2048000 + }, + { + "epoch": 1.02, + "learning_rate": 1.6461942539225596e-05, + "loss": 3.397, + "step": 2048512 + }, + { + "epoch": 1.02, + "learning_rate": 1.6453556591715076e-05, + "loss": 3.3951, + "step": 2049024 + }, + { + "epoch": 1.02, + "learning_rate": 1.6445170644204556e-05, + "loss": 3.4022, + "step": 2049536 + }, + { + "epoch": 1.02, + "learning_rate": 1.643678469669404e-05, + "loss": 3.3925, + "step": 2050048 + }, + { + "epoch": 1.02, + "learning_rate": 1.642839874918352e-05, + "loss": 3.4144, + "step": 2050560 + }, + { + "epoch": 1.02, + "learning_rate": 1.6420012801672996e-05, + "loss": 3.3973, + "step": 2051072 + }, + { + "epoch": 1.02, + "learning_rate": 1.641164323296621e-05, + "loss": 3.4171, + "step": 2051584 + }, + { + "epoch": 1.02, + "learning_rate": 1.640325728545569e-05, + "loss": 3.3896, + "step": 2052096 + }, + { + "epoch": 1.02, + "learning_rate": 1.639487133794517e-05, + "loss": 3.4091, + "step": 2052608 + }, + { + "epoch": 1.02, + "learning_rate": 1.638648539043465e-05, + "loss": 3.4013, + "step": 2053120 + }, + { + "epoch": 1.02, + "learning_rate": 1.637809944292413e-05, + "loss": 3.4044, + "step": 2053632 + }, + { + "epoch": 1.02, + "learning_rate": 1.636972987421734e-05, + "loss": 3.4037, + "step": 2054144 + }, + { + "epoch": 1.02, + "learning_rate": 1.636134392670682e-05, + "loss": 3.3949, + "step": 2054656 + }, + { + "epoch": 1.02, + "learning_rate": 1.6352957979196297e-05, + "loss": 3.4116, + "step": 2055168 + }, + { + "epoch": 1.02, + "learning_rate": 1.6344572031685777e-05, + "loss": 3.4233, + "step": 2055680 + }, + { + "epoch": 1.02, + "learning_rate": 1.6336186084175257e-05, + "loss": 3.3928, + "step": 2056192 + }, + { + "epoch": 1.02, + "learning_rate": 1.632780013666474e-05, + "loss": 3.4045, + "step": 2056704 + }, + { + "epoch": 1.02, + "learning_rate": 1.631943056795795e-05, + "loss": 3.4051, + "step": 2057216 + }, + { + "epoch": 1.02, + "learning_rate": 1.631104462044743e-05, + "loss": 3.3986, + "step": 2057728 + }, + { + "epoch": 1.02, + "learning_rate": 1.630265867293691e-05, + "loss": 3.4006, + "step": 2058240 + }, + { + "epoch": 1.02, + "learning_rate": 1.629427272542639e-05, + "loss": 3.407, + "step": 2058752 + }, + { + "epoch": 1.02, + "learning_rate": 1.628588677791587e-05, + "loss": 3.4054, + "step": 2059264 + }, + { + "epoch": 1.02, + "learning_rate": 1.627750083040535e-05, + "loss": 3.4037, + "step": 2059776 + }, + { + "epoch": 1.02, + "learning_rate": 1.626911488289483e-05, + "loss": 3.4015, + "step": 2060288 + }, + { + "epoch": 1.03, + "eval_loss": 3.859443426132202, + "eval_runtime": 306.4113, + "eval_samples_per_second": 1245.355, + "eval_steps_per_second": 38.918, + "step": 2060640 + }, + { + "epoch": 0.0, + "learning_rate": 1.626072893538431e-05, + "loss": 3.3854, + "step": 2060800 + }, + { + "epoch": 0.0, + "learning_rate": 1.625234298787379e-05, + "loss": 3.3902, + "step": 2061312 + }, + { + "epoch": 0.0, + "learning_rate": 1.624395704036327e-05, + "loss": 3.4058, + "step": 2061824 + }, + { + "epoch": 0.0, + "learning_rate": 1.623558747165648e-05, + "loss": 3.3987, + "step": 2062336 + }, + { + "epoch": 0.0, + "learning_rate": 1.6227201524145962e-05, + "loss": 3.412, + "step": 2062848 + }, + { + "epoch": 0.0, + "learning_rate": 1.6218815576635442e-05, + "loss": 3.3927, + "step": 2063360 + }, + { + "epoch": 0.0, + "learning_rate": 1.6210429629124922e-05, + "loss": 3.4015, + "step": 2063872 + }, + { + "epoch": 0.0, + "learning_rate": 1.620206006041813e-05, + "loss": 3.3969, + "step": 2064384 + }, + { + "epoch": 0.0, + "learning_rate": 1.619367411290761e-05, + "loss": 3.4029, + "step": 2064896 + }, + { + "epoch": 0.0, + "learning_rate": 1.618528816539709e-05, + "loss": 3.3949, + "step": 2065408 + }, + { + "epoch": 0.0, + "learning_rate": 1.617690221788657e-05, + "loss": 3.3938, + "step": 2065920 + }, + { + "epoch": 0.0, + "learning_rate": 1.6168532649179783e-05, + "loss": 3.4125, + "step": 2066432 + }, + { + "epoch": 0.0, + "learning_rate": 1.6160146701669263e-05, + "loss": 3.4068, + "step": 2066944 + }, + { + "epoch": 0.0, + "learning_rate": 1.6151760754158743e-05, + "loss": 3.3926, + "step": 2067456 + }, + { + "epoch": 0.0, + "learning_rate": 1.6143374806648223e-05, + "loss": 3.4018, + "step": 2067968 + }, + { + "epoch": 0.0, + "learning_rate": 1.6134988859137703e-05, + "loss": 3.3864, + "step": 2068480 + }, + { + "epoch": 0.0, + "learning_rate": 1.6126602911627183e-05, + "loss": 3.3927, + "step": 2068992 + }, + { + "epoch": 0.0, + "learning_rate": 1.6118216964116663e-05, + "loss": 3.4014, + "step": 2069504 + }, + { + "epoch": 0.0, + "learning_rate": 1.6109831016606143e-05, + "loss": 3.3897, + "step": 2070016 + }, + { + "epoch": 0.0, + "learning_rate": 1.6101461447899355e-05, + "loss": 3.4003, + "step": 2070528 + }, + { + "epoch": 0.0, + "learning_rate": 1.6093075500388832e-05, + "loss": 3.4041, + "step": 2071040 + }, + { + "epoch": 0.0, + "learning_rate": 1.6084689552878312e-05, + "loss": 3.4015, + "step": 2071552 + }, + { + "epoch": 0.0, + "learning_rate": 1.6076303605367792e-05, + "loss": 3.409, + "step": 2072064 + }, + { + "epoch": 0.0, + "learning_rate": 1.6067934036661004e-05, + "loss": 3.402, + "step": 2072576 + }, + { + "epoch": 0.0, + "learning_rate": 1.6059548089150484e-05, + "loss": 3.3946, + "step": 2073088 + }, + { + "epoch": 0.0, + "learning_rate": 1.6051162141639964e-05, + "loss": 3.3979, + "step": 2073600 + }, + { + "epoch": 0.0, + "learning_rate": 1.6042776194129444e-05, + "loss": 3.3931, + "step": 2074112 + }, + { + "epoch": 0.0, + "learning_rate": 1.6034406625422657e-05, + "loss": 3.4013, + "step": 2074624 + }, + { + "epoch": 0.0, + "learning_rate": 1.6026037056715866e-05, + "loss": 3.3905, + "step": 2075136 + }, + { + "epoch": 0.0, + "learning_rate": 1.601765110920535e-05, + "loss": 3.3975, + "step": 2075648 + }, + { + "epoch": 0.01, + "learning_rate": 1.600926516169483e-05, + "loss": 3.3961, + "step": 2076160 + }, + { + "epoch": 0.01, + "learning_rate": 1.6000879214184306e-05, + "loss": 3.3964, + "step": 2076672 + }, + { + "epoch": 0.01, + "learning_rate": 1.5992493266673786e-05, + "loss": 3.3986, + "step": 2077184 + }, + { + "epoch": 0.01, + "learning_rate": 1.5984123697966998e-05, + "loss": 3.4013, + "step": 2077696 + }, + { + "epoch": 0.01, + "learning_rate": 1.5975737750456478e-05, + "loss": 3.3947, + "step": 2078208 + }, + { + "epoch": 0.01, + "learning_rate": 1.5967351802945958e-05, + "loss": 3.3998, + "step": 2078720 + }, + { + "epoch": 0.01, + "learning_rate": 1.5958965855435438e-05, + "loss": 3.4025, + "step": 2079232 + }, + { + "epoch": 0.01, + "learning_rate": 1.595059628672865e-05, + "loss": 3.3882, + "step": 2079744 + }, + { + "epoch": 0.01, + "learning_rate": 1.594221033921813e-05, + "loss": 3.39, + "step": 2080256 + }, + { + "epoch": 0.01, + "learning_rate": 1.5933824391707607e-05, + "loss": 3.3908, + "step": 2080768 + }, + { + "epoch": 0.01, + "learning_rate": 1.5925438444197087e-05, + "loss": 3.3881, + "step": 2081280 + }, + { + "epoch": 0.01, + "learning_rate": 1.591705249668657e-05, + "loss": 3.397, + "step": 2081792 + }, + { + "epoch": 0.01, + "learning_rate": 1.590866654917605e-05, + "loss": 3.4006, + "step": 2082304 + }, + { + "epoch": 0.01, + "learning_rate": 1.590028060166553e-05, + "loss": 3.4047, + "step": 2082816 + }, + { + "epoch": 0.01, + "learning_rate": 1.589191103295874e-05, + "loss": 3.3999, + "step": 2083328 + }, + { + "epoch": 0.01, + "learning_rate": 1.588352508544822e-05, + "loss": 3.405, + "step": 2083840 + }, + { + "epoch": 0.01, + "learning_rate": 1.58751391379377e-05, + "loss": 3.3985, + "step": 2084352 + }, + { + "epoch": 0.01, + "learning_rate": 1.586675319042718e-05, + "loss": 3.3972, + "step": 2084864 + }, + { + "epoch": 0.01, + "learning_rate": 1.585836724291666e-05, + "loss": 3.3699, + "step": 2085376 + }, + { + "epoch": 0.01, + "learning_rate": 1.584998129540614e-05, + "loss": 3.4087, + "step": 2085888 + }, + { + "epoch": 0.01, + "learning_rate": 1.584161172669935e-05, + "loss": 3.3919, + "step": 2086400 + }, + { + "epoch": 0.01, + "learning_rate": 1.583322577918883e-05, + "loss": 3.3954, + "step": 2086912 + }, + { + "epoch": 0.01, + "learning_rate": 1.5824839831678308e-05, + "loss": 3.3902, + "step": 2087424 + }, + { + "epoch": 0.01, + "learning_rate": 1.5816453884167788e-05, + "loss": 3.3866, + "step": 2087936 + }, + { + "epoch": 0.01, + "learning_rate": 1.580806793665727e-05, + "loss": 3.3893, + "step": 2088448 + }, + { + "epoch": 0.01, + "learning_rate": 1.5799698367950484e-05, + "loss": 3.3846, + "step": 2088960 + }, + { + "epoch": 0.01, + "learning_rate": 1.579131242043996e-05, + "loss": 3.4, + "step": 2089472 + }, + { + "epoch": 0.01, + "learning_rate": 1.578292647292944e-05, + "loss": 3.3831, + "step": 2089984 + }, + { + "epoch": 0.01, + "learning_rate": 1.577454052541892e-05, + "loss": 3.4088, + "step": 2090496 + }, + { + "epoch": 0.01, + "learning_rate": 1.57661545779084e-05, + "loss": 3.3959, + "step": 2091008 + }, + { + "epoch": 0.01, + "learning_rate": 1.575776863039788e-05, + "loss": 3.372, + "step": 2091520 + }, + { + "epoch": 0.01, + "learning_rate": 1.5749399061691093e-05, + "loss": 3.4045, + "step": 2092032 + }, + { + "epoch": 0.01, + "learning_rate": 1.5741013114180573e-05, + "loss": 3.3857, + "step": 2092544 + }, + { + "epoch": 0.01, + "learning_rate": 1.5732627166670053e-05, + "loss": 3.3842, + "step": 2093056 + }, + { + "epoch": 0.01, + "learning_rate": 1.5724241219159533e-05, + "loss": 3.3936, + "step": 2093568 + }, + { + "epoch": 0.01, + "learning_rate": 1.5715855271649013e-05, + "loss": 3.4029, + "step": 2094080 + }, + { + "epoch": 0.01, + "learning_rate": 1.570746932413849e-05, + "loss": 3.3841, + "step": 2094592 + }, + { + "epoch": 0.01, + "learning_rate": 1.5699083376627972e-05, + "loss": 3.3914, + "step": 2095104 + }, + { + "epoch": 0.01, + "learning_rate": 1.5690697429117452e-05, + "loss": 3.3779, + "step": 2095616 + }, + { + "epoch": 0.01, + "learning_rate": 1.5682344239214394e-05, + "loss": 3.3893, + "step": 2096128 + }, + { + "epoch": 0.01, + "learning_rate": 1.5673958291703874e-05, + "loss": 3.4041, + "step": 2096640 + }, + { + "epoch": 0.01, + "learning_rate": 1.5665572344193354e-05, + "loss": 3.3949, + "step": 2097152 + }, + { + "epoch": 0.01, + "learning_rate": 1.5657186396682834e-05, + "loss": 3.3977, + "step": 2097664 + }, + { + "epoch": 0.01, + "learning_rate": 1.5648800449172317e-05, + "loss": 3.3966, + "step": 2098176 + }, + { + "epoch": 0.01, + "learning_rate": 1.5640414501661794e-05, + "loss": 3.4046, + "step": 2098688 + }, + { + "epoch": 0.01, + "learning_rate": 1.5632028554151274e-05, + "loss": 3.3954, + "step": 2099200 + }, + { + "epoch": 0.01, + "learning_rate": 1.5623658985444486e-05, + "loss": 3.4014, + "step": 2099712 + }, + { + "epoch": 0.01, + "learning_rate": 1.5615273037933963e-05, + "loss": 3.3867, + "step": 2100224 + }, + { + "epoch": 0.01, + "learning_rate": 1.5606887090423443e-05, + "loss": 3.3911, + "step": 2100736 + }, + { + "epoch": 0.01, + "learning_rate": 1.5598501142912926e-05, + "loss": 3.3942, + "step": 2101248 + }, + { + "epoch": 0.01, + "learning_rate": 1.559013157420614e-05, + "loss": 3.3935, + "step": 2101760 + }, + { + "epoch": 0.01, + "learning_rate": 1.5581745626695615e-05, + "loss": 3.397, + "step": 2102272 + }, + { + "epoch": 0.01, + "learning_rate": 1.5573359679185095e-05, + "loss": 3.4036, + "step": 2102784 + }, + { + "epoch": 0.01, + "learning_rate": 1.5564973731674575e-05, + "loss": 3.3954, + "step": 2103296 + }, + { + "epoch": 0.01, + "learning_rate": 1.5556604162967788e-05, + "loss": 3.3827, + "step": 2103808 + }, + { + "epoch": 0.01, + "learning_rate": 1.5548218215457268e-05, + "loss": 3.3954, + "step": 2104320 + }, + { + "epoch": 0.01, + "learning_rate": 1.5539832267946747e-05, + "loss": 3.3972, + "step": 2104832 + }, + { + "epoch": 0.01, + "learning_rate": 1.5531446320436227e-05, + "loss": 3.3865, + "step": 2105344 + }, + { + "epoch": 0.01, + "learning_rate": 1.5523060372925707e-05, + "loss": 3.3908, + "step": 2105856 + }, + { + "epoch": 0.01, + "learning_rate": 1.5514674425415187e-05, + "loss": 3.4007, + "step": 2106368 + }, + { + "epoch": 0.02, + "learning_rate": 1.5506304856708396e-05, + "loss": 3.3922, + "step": 2106880 + }, + { + "epoch": 0.02, + "learning_rate": 1.549791890919788e-05, + "loss": 3.3927, + "step": 2107392 + }, + { + "epoch": 0.02, + "learning_rate": 1.548953296168736e-05, + "loss": 3.3851, + "step": 2107904 + }, + { + "epoch": 0.02, + "learning_rate": 1.548114701417684e-05, + "loss": 3.3972, + "step": 2108416 + }, + { + "epoch": 0.02, + "learning_rate": 1.547276106666632e-05, + "loss": 3.3977, + "step": 2108928 + }, + { + "epoch": 0.02, + "learning_rate": 1.546439149795953e-05, + "loss": 3.4008, + "step": 2109440 + }, + { + "epoch": 0.02, + "learning_rate": 1.545600555044901e-05, + "loss": 3.3798, + "step": 2109952 + }, + { + "epoch": 0.02, + "learning_rate": 1.544761960293849e-05, + "loss": 3.3973, + "step": 2110464 + }, + { + "epoch": 0.02, + "learning_rate": 1.5439233655427972e-05, + "loss": 3.3859, + "step": 2110976 + }, + { + "epoch": 0.02, + "learning_rate": 1.543084770791745e-05, + "loss": 3.3993, + "step": 2111488 + }, + { + "epoch": 0.02, + "learning_rate": 1.542246176040693e-05, + "loss": 3.4009, + "step": 2112000 + }, + { + "epoch": 0.02, + "learning_rate": 1.541409219170014e-05, + "loss": 3.389, + "step": 2112512 + }, + { + "epoch": 0.02, + "learning_rate": 1.5405706244189618e-05, + "loss": 3.3905, + "step": 2113024 + }, + { + "epoch": 0.02, + "learning_rate": 1.5397320296679098e-05, + "loss": 3.3855, + "step": 2113536 + }, + { + "epoch": 0.02, + "learning_rate": 1.538893434916858e-05, + "loss": 3.3857, + "step": 2114048 + }, + { + "epoch": 0.02, + "learning_rate": 1.5380564780461793e-05, + "loss": 3.387, + "step": 2114560 + }, + { + "epoch": 0.02, + "learning_rate": 1.537217883295127e-05, + "loss": 3.387, + "step": 2115072 + }, + { + "epoch": 0.02, + "learning_rate": 1.536379288544075e-05, + "loss": 3.3891, + "step": 2115584 + }, + { + "epoch": 0.02, + "learning_rate": 1.535540693793023e-05, + "loss": 3.3878, + "step": 2116096 + }, + { + "epoch": 0.02, + "learning_rate": 1.534702099041971e-05, + "loss": 3.385, + "step": 2116608 + }, + { + "epoch": 0.02, + "learning_rate": 1.5338651421712922e-05, + "loss": 3.3849, + "step": 2117120 + }, + { + "epoch": 0.02, + "learning_rate": 1.5330265474202402e-05, + "loss": 3.3857, + "step": 2117632 + }, + { + "epoch": 0.02, + "learning_rate": 1.5321879526691882e-05, + "loss": 3.4032, + "step": 2118144 + }, + { + "epoch": 0.02, + "learning_rate": 1.5313493579181362e-05, + "loss": 3.3863, + "step": 2118656 + }, + { + "epoch": 0.02, + "learning_rate": 1.530512401047457e-05, + "loss": 3.4003, + "step": 2119168 + }, + { + "epoch": 0.02, + "learning_rate": 1.529673806296405e-05, + "loss": 3.402, + "step": 2119680 + }, + { + "epoch": 0.02, + "learning_rate": 1.5288352115453535e-05, + "loss": 3.4055, + "step": 2120192 + }, + { + "epoch": 0.02, + "learning_rate": 1.5279966167943014e-05, + "loss": 3.3863, + "step": 2120704 + }, + { + "epoch": 0.02, + "learning_rate": 1.5271580220432494e-05, + "loss": 3.3888, + "step": 2121216 + }, + { + "epoch": 0.02, + "learning_rate": 1.5263194272921974e-05, + "loss": 3.3922, + "step": 2121728 + }, + { + "epoch": 0.02, + "learning_rate": 1.5254808325411451e-05, + "loss": 3.3982, + "step": 2122240 + }, + { + "epoch": 0.02, + "learning_rate": 1.5246422377900933e-05, + "loss": 3.3948, + "step": 2122752 + }, + { + "epoch": 0.02, + "learning_rate": 1.5238052809194145e-05, + "loss": 3.3857, + "step": 2123264 + }, + { + "epoch": 0.02, + "learning_rate": 1.5229666861683622e-05, + "loss": 3.3894, + "step": 2123776 + }, + { + "epoch": 0.02, + "learning_rate": 1.5221280914173103e-05, + "loss": 3.4042, + "step": 2124288 + }, + { + "epoch": 0.02, + "learning_rate": 1.5212894966662583e-05, + "loss": 3.394, + "step": 2124800 + }, + { + "epoch": 0.02, + "learning_rate": 1.5204509019152063e-05, + "loss": 3.3844, + "step": 2125312 + }, + { + "epoch": 0.02, + "learning_rate": 1.5196139450445274e-05, + "loss": 3.3915, + "step": 2125824 + }, + { + "epoch": 0.02, + "learning_rate": 1.5187753502934754e-05, + "loss": 3.3862, + "step": 2126336 + }, + { + "epoch": 0.02, + "learning_rate": 1.5179367555424234e-05, + "loss": 3.4031, + "step": 2126848 + }, + { + "epoch": 0.02, + "learning_rate": 1.5170981607913714e-05, + "loss": 3.39, + "step": 2127360 + }, + { + "epoch": 0.02, + "learning_rate": 1.5162595660403196e-05, + "loss": 3.4045, + "step": 2127872 + }, + { + "epoch": 0.02, + "learning_rate": 1.5154209712892676e-05, + "loss": 3.3786, + "step": 2128384 + }, + { + "epoch": 0.02, + "learning_rate": 1.5145840144185886e-05, + "loss": 3.3988, + "step": 2128896 + }, + { + "epoch": 0.02, + "learning_rate": 1.5137454196675366e-05, + "loss": 3.3936, + "step": 2129408 + }, + { + "epoch": 0.02, + "learning_rate": 1.5129068249164846e-05, + "loss": 3.3929, + "step": 2129920 + }, + { + "epoch": 0.02, + "learning_rate": 1.5120682301654326e-05, + "loss": 3.3927, + "step": 2130432 + }, + { + "epoch": 0.02, + "learning_rate": 1.5112296354143804e-05, + "loss": 3.384, + "step": 2130944 + }, + { + "epoch": 0.02, + "learning_rate": 1.5103910406633284e-05, + "loss": 3.4029, + "step": 2131456 + }, + { + "epoch": 0.02, + "learning_rate": 1.5095524459122764e-05, + "loss": 3.4128, + "step": 2131968 + }, + { + "epoch": 0.02, + "learning_rate": 1.5087138511612244e-05, + "loss": 3.3826, + "step": 2132480 + }, + { + "epoch": 0.02, + "learning_rate": 1.5078768942905455e-05, + "loss": 3.3949, + "step": 2132992 + }, + { + "epoch": 0.02, + "learning_rate": 1.5070382995394935e-05, + "loss": 3.3971, + "step": 2133504 + }, + { + "epoch": 0.02, + "learning_rate": 1.5061997047884415e-05, + "loss": 3.3903, + "step": 2134016 + }, + { + "epoch": 0.02, + "learning_rate": 1.5053611100373897e-05, + "loss": 3.3862, + "step": 2134528 + }, + { + "epoch": 0.02, + "learning_rate": 1.5045241531667106e-05, + "loss": 3.4002, + "step": 2135040 + }, + { + "epoch": 0.02, + "learning_rate": 1.5036855584156587e-05, + "loss": 3.3938, + "step": 2135552 + }, + { + "epoch": 0.02, + "learning_rate": 1.5028469636646067e-05, + "loss": 3.3916, + "step": 2136064 + }, + { + "epoch": 0.02, + "learning_rate": 1.5020083689135547e-05, + "loss": 3.394, + "step": 2136576 + }, + { + "epoch": 0.03, + "eval_loss": 3.8604557514190674, + "eval_runtime": 304.1511, + "eval_samples_per_second": 1254.61, + "eval_steps_per_second": 39.207, + "step": 2136960 + }, + { + "epoch": 1.0, + "learning_rate": 1.5011697741625027e-05, + "loss": 3.386, + "step": 2137088 + }, + { + "epoch": 1.0, + "learning_rate": 1.5003328172918238e-05, + "loss": 3.3787, + "step": 2137600 + }, + { + "epoch": 1.0, + "learning_rate": 1.4994942225407718e-05, + "loss": 3.3965, + "step": 2138112 + }, + { + "epoch": 1.0, + "learning_rate": 1.4986556277897198e-05, + "loss": 3.3912, + "step": 2138624 + }, + { + "epoch": 1.0, + "learning_rate": 1.497817033038668e-05, + "loss": 3.3964, + "step": 2139136 + }, + { + "epoch": 1.0, + "learning_rate": 1.496978438287616e-05, + "loss": 3.3845, + "step": 2139648 + }, + { + "epoch": 1.0, + "learning_rate": 1.4961398435365636e-05, + "loss": 3.3961, + "step": 2140160 + }, + { + "epoch": 1.0, + "learning_rate": 1.4953012487855118e-05, + "loss": 3.3865, + "step": 2140672 + }, + { + "epoch": 1.0, + "learning_rate": 1.4944626540344598e-05, + "loss": 3.3901, + "step": 2141184 + }, + { + "epoch": 1.0, + "learning_rate": 1.493625697163781e-05, + "loss": 3.3849, + "step": 2141696 + }, + { + "epoch": 1.0, + "learning_rate": 1.4927871024127288e-05, + "loss": 3.3875, + "step": 2142208 + }, + { + "epoch": 1.0, + "learning_rate": 1.4919485076616768e-05, + "loss": 3.3949, + "step": 2142720 + }, + { + "epoch": 1.0, + "learning_rate": 1.4911099129106248e-05, + "loss": 3.3999, + "step": 2143232 + }, + { + "epoch": 1.0, + "learning_rate": 1.4902713181595728e-05, + "loss": 3.3825, + "step": 2143744 + }, + { + "epoch": 1.0, + "learning_rate": 1.4894343612888939e-05, + "loss": 3.3898, + "step": 2144256 + }, + { + "epoch": 1.0, + "learning_rate": 1.4885957665378419e-05, + "loss": 3.377, + "step": 2144768 + }, + { + "epoch": 1.0, + "learning_rate": 1.4877571717867899e-05, + "loss": 3.3854, + "step": 2145280 + }, + { + "epoch": 1.0, + "learning_rate": 1.486918577035738e-05, + "loss": 3.3865, + "step": 2145792 + }, + { + "epoch": 1.0, + "learning_rate": 1.486079982284686e-05, + "loss": 3.38, + "step": 2146304 + }, + { + "epoch": 1.0, + "learning_rate": 1.485241387533634e-05, + "loss": 3.3901, + "step": 2146816 + }, + { + "epoch": 1.0, + "learning_rate": 1.4844027927825819e-05, + "loss": 3.3938, + "step": 2147328 + }, + { + "epoch": 1.0, + "learning_rate": 1.4835641980315299e-05, + "loss": 3.3909, + "step": 2147840 + }, + { + "epoch": 1.0, + "learning_rate": 1.4827272411608511e-05, + "loss": 3.398, + "step": 2148352 + }, + { + "epoch": 1.0, + "learning_rate": 1.4818886464097991e-05, + "loss": 3.3946, + "step": 2148864 + }, + { + "epoch": 1.0, + "learning_rate": 1.481050051658747e-05, + "loss": 3.3834, + "step": 2149376 + }, + { + "epoch": 1.0, + "learning_rate": 1.480211456907695e-05, + "loss": 3.3945, + "step": 2149888 + }, + { + "epoch": 1.0, + "learning_rate": 1.4793745000370162e-05, + "loss": 3.3817, + "step": 2150400 + }, + { + "epoch": 1.0, + "learning_rate": 1.4785375431663373e-05, + "loss": 3.3902, + "step": 2150912 + }, + { + "epoch": 1.0, + "learning_rate": 1.4776989484152853e-05, + "loss": 3.3828, + "step": 2151424 + }, + { + "epoch": 1.0, + "learning_rate": 1.4768603536642334e-05, + "loss": 3.3851, + "step": 2151936 + }, + { + "epoch": 1.01, + "learning_rate": 1.4760217589131814e-05, + "loss": 3.3868, + "step": 2152448 + }, + { + "epoch": 1.01, + "learning_rate": 1.4751848020425023e-05, + "loss": 3.3857, + "step": 2152960 + }, + { + "epoch": 1.01, + "learning_rate": 1.4743462072914505e-05, + "loss": 3.3858, + "step": 2153472 + }, + { + "epoch": 1.01, + "learning_rate": 1.4735076125403985e-05, + "loss": 3.3942, + "step": 2153984 + }, + { + "epoch": 1.01, + "learning_rate": 1.4726690177893465e-05, + "loss": 3.384, + "step": 2154496 + }, + { + "epoch": 1.01, + "learning_rate": 1.4718320609186676e-05, + "loss": 3.3861, + "step": 2155008 + }, + { + "epoch": 1.01, + "learning_rate": 1.4709934661676156e-05, + "loss": 3.3938, + "step": 2155520 + }, + { + "epoch": 1.01, + "learning_rate": 1.4701548714165636e-05, + "loss": 3.3736, + "step": 2156032 + }, + { + "epoch": 1.01, + "learning_rate": 1.4693162766655114e-05, + "loss": 3.3865, + "step": 2156544 + }, + { + "epoch": 1.01, + "learning_rate": 1.4684776819144594e-05, + "loss": 3.3818, + "step": 2157056 + }, + { + "epoch": 1.01, + "learning_rate": 1.4676390871634074e-05, + "loss": 3.3789, + "step": 2157568 + }, + { + "epoch": 1.01, + "learning_rate": 1.4668004924123554e-05, + "loss": 3.3837, + "step": 2158080 + }, + { + "epoch": 1.01, + "learning_rate": 1.4659618976613035e-05, + "loss": 3.3917, + "step": 2158592 + }, + { + "epoch": 1.01, + "learning_rate": 1.4651249407906245e-05, + "loss": 3.3948, + "step": 2159104 + }, + { + "epoch": 1.01, + "learning_rate": 1.4642863460395726e-05, + "loss": 3.3905, + "step": 2159616 + }, + { + "epoch": 1.01, + "learning_rate": 1.4634493891688935e-05, + "loss": 3.3922, + "step": 2160128 + }, + { + "epoch": 1.01, + "learning_rate": 1.4626107944178415e-05, + "loss": 3.3914, + "step": 2160640 + }, + { + "epoch": 1.01, + "learning_rate": 1.4617721996667897e-05, + "loss": 3.3866, + "step": 2161152 + }, + { + "epoch": 1.01, + "learning_rate": 1.4609336049157377e-05, + "loss": 3.3638, + "step": 2161664 + }, + { + "epoch": 1.01, + "learning_rate": 1.4600950101646857e-05, + "loss": 3.3946, + "step": 2162176 + }, + { + "epoch": 1.01, + "learning_rate": 1.4592564154136337e-05, + "loss": 3.3818, + "step": 2162688 + }, + { + "epoch": 1.01, + "learning_rate": 1.4584178206625818e-05, + "loss": 3.3828, + "step": 2163200 + }, + { + "epoch": 1.01, + "learning_rate": 1.4575808637919028e-05, + "loss": 3.3822, + "step": 2163712 + }, + { + "epoch": 1.01, + "learning_rate": 1.4567422690408507e-05, + "loss": 3.3777, + "step": 2164224 + }, + { + "epoch": 1.01, + "learning_rate": 1.4559053121701718e-05, + "loss": 3.3796, + "step": 2164736 + }, + { + "epoch": 1.01, + "learning_rate": 1.4550667174191198e-05, + "loss": 3.3723, + "step": 2165248 + }, + { + "epoch": 1.01, + "learning_rate": 1.454228122668068e-05, + "loss": 3.3906, + "step": 2165760 + }, + { + "epoch": 1.01, + "learning_rate": 1.453389527917016e-05, + "loss": 3.3708, + "step": 2166272 + }, + { + "epoch": 1.01, + "learning_rate": 1.452550933165964e-05, + "loss": 3.4004, + "step": 2166784 + }, + { + "epoch": 1.01, + "learning_rate": 1.4517123384149118e-05, + "loss": 3.3853, + "step": 2167296 + }, + { + "epoch": 1.01, + "learning_rate": 1.4508737436638598e-05, + "loss": 3.3667, + "step": 2167808 + }, + { + "epoch": 1.01, + "learning_rate": 1.450036786793181e-05, + "loss": 3.3959, + "step": 2168320 + }, + { + "epoch": 1.01, + "learning_rate": 1.449198192042129e-05, + "loss": 3.371, + "step": 2168832 + }, + { + "epoch": 1.01, + "learning_rate": 1.4483595972910769e-05, + "loss": 3.3778, + "step": 2169344 + }, + { + "epoch": 1.01, + "learning_rate": 1.4475210025400249e-05, + "loss": 3.3807, + "step": 2169856 + }, + { + "epoch": 1.01, + "learning_rate": 1.4466824077889729e-05, + "loss": 3.3931, + "step": 2170368 + }, + { + "epoch": 1.01, + "learning_rate": 1.4458438130379209e-05, + "loss": 3.3769, + "step": 2170880 + }, + { + "epoch": 1.01, + "learning_rate": 1.445005218286869e-05, + "loss": 3.3799, + "step": 2171392 + }, + { + "epoch": 1.01, + "learning_rate": 1.44416826141619e-05, + "loss": 3.3638, + "step": 2171904 + }, + { + "epoch": 1.01, + "learning_rate": 1.4433296666651381e-05, + "loss": 3.3842, + "step": 2172416 + }, + { + "epoch": 1.01, + "learning_rate": 1.4424910719140861e-05, + "loss": 3.3886, + "step": 2172928 + }, + { + "epoch": 1.01, + "learning_rate": 1.4416524771630341e-05, + "loss": 3.3884, + "step": 2173440 + }, + { + "epoch": 1.01, + "learning_rate": 1.440813882411982e-05, + "loss": 3.3874, + "step": 2173952 + }, + { + "epoch": 1.01, + "learning_rate": 1.4399769255413032e-05, + "loss": 3.3857, + "step": 2174464 + }, + { + "epoch": 1.01, + "learning_rate": 1.4391383307902512e-05, + "loss": 3.3969, + "step": 2174976 + }, + { + "epoch": 1.01, + "learning_rate": 1.4382997360391992e-05, + "loss": 3.385, + "step": 2175488 + }, + { + "epoch": 1.01, + "learning_rate": 1.4374611412881473e-05, + "loss": 3.3927, + "step": 2176000 + }, + { + "epoch": 1.01, + "learning_rate": 1.436622546537095e-05, + "loss": 3.3801, + "step": 2176512 + }, + { + "epoch": 1.01, + "learning_rate": 1.435783951786043e-05, + "loss": 3.3834, + "step": 2177024 + }, + { + "epoch": 1.01, + "learning_rate": 1.4349469949153644e-05, + "loss": 3.3853, + "step": 2177536 + }, + { + "epoch": 1.01, + "learning_rate": 1.4341084001643124e-05, + "loss": 3.382, + "step": 2178048 + }, + { + "epoch": 1.01, + "learning_rate": 1.43326980541326e-05, + "loss": 3.391, + "step": 2178560 + }, + { + "epoch": 1.01, + "learning_rate": 1.4324312106622082e-05, + "loss": 3.3893, + "step": 2179072 + }, + { + "epoch": 1.01, + "learning_rate": 1.4315926159111562e-05, + "loss": 3.3896, + "step": 2179584 + }, + { + "epoch": 1.01, + "learning_rate": 1.4307556590404773e-05, + "loss": 3.3721, + "step": 2180096 + }, + { + "epoch": 1.01, + "learning_rate": 1.4299170642894253e-05, + "loss": 3.384, + "step": 2180608 + }, + { + "epoch": 1.01, + "learning_rate": 1.4290784695383733e-05, + "loss": 3.3882, + "step": 2181120 + }, + { + "epoch": 1.01, + "learning_rate": 1.4282398747873213e-05, + "loss": 3.3797, + "step": 2181632 + }, + { + "epoch": 1.01, + "learning_rate": 1.4274012800362693e-05, + "loss": 3.3771, + "step": 2182144 + }, + { + "epoch": 1.01, + "learning_rate": 1.4265643231655903e-05, + "loss": 3.3899, + "step": 2182656 + }, + { + "epoch": 1.02, + "learning_rate": 1.4257257284145383e-05, + "loss": 3.3858, + "step": 2183168 + }, + { + "epoch": 1.02, + "learning_rate": 1.4248871336634865e-05, + "loss": 3.3798, + "step": 2183680 + }, + { + "epoch": 1.02, + "learning_rate": 1.4240485389124345e-05, + "loss": 3.3778, + "step": 2184192 + }, + { + "epoch": 1.02, + "learning_rate": 1.4232099441613825e-05, + "loss": 3.3842, + "step": 2184704 + }, + { + "epoch": 1.02, + "learning_rate": 1.4223713494103305e-05, + "loss": 3.3924, + "step": 2185216 + }, + { + "epoch": 1.02, + "learning_rate": 1.4215343925396516e-05, + "loss": 3.3886, + "step": 2185728 + }, + { + "epoch": 1.02, + "learning_rate": 1.4206957977885996e-05, + "loss": 3.3726, + "step": 2186240 + }, + { + "epoch": 1.02, + "learning_rate": 1.4198572030375476e-05, + "loss": 3.3841, + "step": 2186752 + }, + { + "epoch": 1.02, + "learning_rate": 1.4190186082864954e-05, + "loss": 3.3772, + "step": 2187264 + }, + { + "epoch": 1.02, + "learning_rate": 1.4181816514158166e-05, + "loss": 3.3872, + "step": 2187776 + }, + { + "epoch": 1.02, + "learning_rate": 1.4173430566647646e-05, + "loss": 3.3935, + "step": 2188288 + }, + { + "epoch": 1.02, + "learning_rate": 1.4165044619137128e-05, + "loss": 3.3804, + "step": 2188800 + }, + { + "epoch": 1.02, + "learning_rate": 1.4156658671626605e-05, + "loss": 3.3757, + "step": 2189312 + }, + { + "epoch": 1.02, + "learning_rate": 1.4148289102919817e-05, + "loss": 3.3806, + "step": 2189824 + }, + { + "epoch": 1.02, + "learning_rate": 1.4139903155409299e-05, + "loss": 3.3764, + "step": 2190336 + }, + { + "epoch": 1.02, + "learning_rate": 1.4131517207898779e-05, + "loss": 3.3726, + "step": 2190848 + }, + { + "epoch": 1.02, + "learning_rate": 1.4123131260388255e-05, + "loss": 3.3806, + "step": 2191360 + }, + { + "epoch": 1.02, + "learning_rate": 1.4114745312877737e-05, + "loss": 3.3788, + "step": 2191872 + }, + { + "epoch": 1.02, + "learning_rate": 1.4106359365367217e-05, + "loss": 3.3797, + "step": 2192384 + }, + { + "epoch": 1.02, + "learning_rate": 1.4097973417856697e-05, + "loss": 3.3733, + "step": 2192896 + }, + { + "epoch": 1.02, + "learning_rate": 1.4089603849149908e-05, + "loss": 3.3754, + "step": 2193408 + }, + { + "epoch": 1.02, + "learning_rate": 1.4081217901639387e-05, + "loss": 3.3731, + "step": 2193920 + }, + { + "epoch": 1.02, + "learning_rate": 1.4072831954128867e-05, + "loss": 3.393, + "step": 2194432 + }, + { + "epoch": 1.02, + "learning_rate": 1.4064446006618347e-05, + "loss": 3.378, + "step": 2194944 + }, + { + "epoch": 1.02, + "learning_rate": 1.4056076437911558e-05, + "loss": 3.3924, + "step": 2195456 + }, + { + "epoch": 1.02, + "learning_rate": 1.4047690490401038e-05, + "loss": 3.3878, + "step": 2195968 + }, + { + "epoch": 1.02, + "learning_rate": 1.403930454289052e-05, + "loss": 3.3989, + "step": 2196480 + }, + { + "epoch": 1.02, + "learning_rate": 1.403091859538e-05, + "loss": 3.3787, + "step": 2196992 + }, + { + "epoch": 1.02, + "learning_rate": 1.402253264786948e-05, + "loss": 3.3773, + "step": 2197504 + }, + { + "epoch": 1.02, + "learning_rate": 1.401416307916269e-05, + "loss": 3.3821, + "step": 2198016 + }, + { + "epoch": 1.02, + "learning_rate": 1.400577713165217e-05, + "loss": 3.3853, + "step": 2198528 + }, + { + "epoch": 1.02, + "learning_rate": 1.399739118414165e-05, + "loss": 3.3806, + "step": 2199040 + }, + { + "epoch": 1.02, + "learning_rate": 1.398900523663113e-05, + "loss": 3.3814, + "step": 2199552 + }, + { + "epoch": 1.02, + "learning_rate": 1.3980635667924341e-05, + "loss": 3.3792, + "step": 2200064 + }, + { + "epoch": 1.02, + "learning_rate": 1.3972249720413821e-05, + "loss": 3.3957, + "step": 2200576 + }, + { + "epoch": 1.02, + "learning_rate": 1.3963863772903301e-05, + "loss": 3.3809, + "step": 2201088 + }, + { + "epoch": 1.02, + "learning_rate": 1.3955477825392783e-05, + "loss": 3.3762, + "step": 2201600 + }, + { + "epoch": 1.02, + "learning_rate": 1.3947108256685992e-05, + "loss": 3.3783, + "step": 2202112 + }, + { + "epoch": 1.02, + "learning_rate": 1.3938722309175473e-05, + "loss": 3.3808, + "step": 2202624 + }, + { + "epoch": 1.02, + "learning_rate": 1.3930336361664953e-05, + "loss": 3.3925, + "step": 2203136 + }, + { + "epoch": 1.02, + "learning_rate": 1.392195041415443e-05, + "loss": 3.377, + "step": 2203648 + }, + { + "epoch": 1.02, + "learning_rate": 1.3913580845447644e-05, + "loss": 3.3931, + "step": 2204160 + }, + { + "epoch": 1.02, + "learning_rate": 1.3905194897937124e-05, + "loss": 3.3735, + "step": 2204672 + }, + { + "epoch": 1.02, + "learning_rate": 1.3896808950426604e-05, + "loss": 3.386, + "step": 2205184 + }, + { + "epoch": 1.02, + "learning_rate": 1.3888423002916082e-05, + "loss": 3.3827, + "step": 2205696 + }, + { + "epoch": 1.02, + "learning_rate": 1.3880037055405562e-05, + "loss": 3.3856, + "step": 2206208 + }, + { + "epoch": 1.02, + "learning_rate": 1.3871651107895042e-05, + "loss": 3.3773, + "step": 2206720 + }, + { + "epoch": 1.02, + "learning_rate": 1.3863265160384522e-05, + "loss": 3.3805, + "step": 2207232 + }, + { + "epoch": 1.02, + "learning_rate": 1.3854895591677733e-05, + "loss": 3.3927, + "step": 2207744 + }, + { + "epoch": 1.02, + "learning_rate": 1.3846509644167213e-05, + "loss": 3.4001, + "step": 2208256 + }, + { + "epoch": 1.02, + "learning_rate": 1.3838123696656693e-05, + "loss": 3.3757, + "step": 2208768 + }, + { + "epoch": 1.02, + "learning_rate": 1.3829737749146175e-05, + "loss": 3.3822, + "step": 2209280 + }, + { + "epoch": 1.02, + "learning_rate": 1.3821368180439384e-05, + "loss": 3.3865, + "step": 2209792 + }, + { + "epoch": 1.02, + "learning_rate": 1.3812982232928864e-05, + "loss": 3.3814, + "step": 2210304 + }, + { + "epoch": 1.02, + "learning_rate": 1.3804596285418345e-05, + "loss": 3.3752, + "step": 2210816 + }, + { + "epoch": 1.02, + "learning_rate": 1.3796210337907825e-05, + "loss": 3.3947, + "step": 2211328 + }, + { + "epoch": 1.02, + "learning_rate": 1.3787824390397305e-05, + "loss": 3.3805, + "step": 2211840 + }, + { + "epoch": 1.02, + "learning_rate": 1.3779454821690516e-05, + "loss": 3.3894, + "step": 2212352 + }, + { + "epoch": 1.02, + "learning_rate": 1.3771068874179996e-05, + "loss": 3.3779, + "step": 2212864 + }, + { + "epoch": 1.03, + "eval_loss": 3.860935688018799, + "eval_runtime": 303.4913, + "eval_samples_per_second": 1257.338, + "eval_steps_per_second": 39.293, + "step": 2213280 + }, + { + "epoch": 0.0, + "learning_rate": 1.3762682926669476e-05, + "loss": 3.3792, + "step": 2213376 + }, + { + "epoch": 0.0, + "learning_rate": 1.3754313357962687e-05, + "loss": 3.3666, + "step": 2213888 + }, + { + "epoch": 0.0, + "learning_rate": 1.3745927410452167e-05, + "loss": 3.3854, + "step": 2214400 + }, + { + "epoch": 0.0, + "learning_rate": 1.3737541462941647e-05, + "loss": 3.383, + "step": 2214912 + }, + { + "epoch": 0.0, + "learning_rate": 1.3729155515431128e-05, + "loss": 3.3849, + "step": 2215424 + }, + { + "epoch": 0.0, + "learning_rate": 1.3720769567920608e-05, + "loss": 3.3767, + "step": 2215936 + }, + { + "epoch": 0.0, + "learning_rate": 1.3712383620410085e-05, + "loss": 3.3835, + "step": 2216448 + }, + { + "epoch": 0.0, + "learning_rate": 1.3703997672899566e-05, + "loss": 3.3783, + "step": 2216960 + }, + { + "epoch": 0.0, + "learning_rate": 1.3695628104192779e-05, + "loss": 3.3782, + "step": 2217472 + }, + { + "epoch": 0.0, + "learning_rate": 1.3687242156682259e-05, + "loss": 3.3818, + "step": 2217984 + }, + { + "epoch": 0.0, + "learning_rate": 1.3678856209171737e-05, + "loss": 3.3755, + "step": 2218496 + }, + { + "epoch": 0.0, + "learning_rate": 1.3670470261661217e-05, + "loss": 3.3867, + "step": 2219008 + }, + { + "epoch": 0.0, + "learning_rate": 1.3662084314150697e-05, + "loss": 3.3946, + "step": 2219520 + }, + { + "epoch": 0.0, + "learning_rate": 1.365371474544391e-05, + "loss": 3.3703, + "step": 2220032 + }, + { + "epoch": 0.0, + "learning_rate": 1.3645328797933388e-05, + "loss": 3.3754, + "step": 2220544 + }, + { + "epoch": 0.0, + "learning_rate": 1.3636942850422868e-05, + "loss": 3.3713, + "step": 2221056 + }, + { + "epoch": 0.0, + "learning_rate": 1.3628556902912348e-05, + "loss": 3.3759, + "step": 2221568 + }, + { + "epoch": 0.0, + "learning_rate": 1.362017095540183e-05, + "loss": 3.3781, + "step": 2222080 + }, + { + "epoch": 0.0, + "learning_rate": 1.361178500789131e-05, + "loss": 3.3704, + "step": 2222592 + }, + { + "epoch": 0.0, + "learning_rate": 1.360339906038079e-05, + "loss": 3.376, + "step": 2223104 + }, + { + "epoch": 0.0, + "learning_rate": 1.3595013112870267e-05, + "loss": 3.3891, + "step": 2223616 + }, + { + "epoch": 0.0, + "learning_rate": 1.358664354416348e-05, + "loss": 3.3791, + "step": 2224128 + }, + { + "epoch": 0.0, + "learning_rate": 1.357825759665296e-05, + "loss": 3.3855, + "step": 2224640 + }, + { + "epoch": 0.0, + "learning_rate": 1.356987164914244e-05, + "loss": 3.3856, + "step": 2225152 + }, + { + "epoch": 0.0, + "learning_rate": 1.3561485701631918e-05, + "loss": 3.3743, + "step": 2225664 + }, + { + "epoch": 0.0, + "learning_rate": 1.355311613292513e-05, + "loss": 3.3828, + "step": 2226176 + }, + { + "epoch": 0.0, + "learning_rate": 1.354473018541461e-05, + "loss": 3.3698, + "step": 2226688 + }, + { + "epoch": 0.0, + "learning_rate": 1.3536360616707821e-05, + "loss": 3.3812, + "step": 2227200 + }, + { + "epoch": 0.0, + "learning_rate": 1.3527974669197301e-05, + "loss": 3.3727, + "step": 2227712 + }, + { + "epoch": 0.0, + "learning_rate": 1.3519588721686783e-05, + "loss": 3.3724, + "step": 2228224 + }, + { + "epoch": 0.01, + "learning_rate": 1.3511202774176263e-05, + "loss": 3.3804, + "step": 2228736 + }, + { + "epoch": 0.01, + "learning_rate": 1.3502833205469472e-05, + "loss": 3.3751, + "step": 2229248 + }, + { + "epoch": 0.01, + "learning_rate": 1.3494447257958954e-05, + "loss": 3.3823, + "step": 2229760 + }, + { + "epoch": 0.01, + "learning_rate": 1.3486061310448434e-05, + "loss": 3.3779, + "step": 2230272 + }, + { + "epoch": 0.01, + "learning_rate": 1.3477675362937914e-05, + "loss": 3.3759, + "step": 2230784 + }, + { + "epoch": 0.01, + "learning_rate": 1.3469305794231124e-05, + "loss": 3.3803, + "step": 2231296 + }, + { + "epoch": 0.01, + "learning_rate": 1.3460919846720604e-05, + "loss": 3.3845, + "step": 2231808 + }, + { + "epoch": 0.01, + "learning_rate": 1.3452533899210084e-05, + "loss": 3.3615, + "step": 2232320 + }, + { + "epoch": 0.01, + "learning_rate": 1.3444147951699563e-05, + "loss": 3.3796, + "step": 2232832 + }, + { + "epoch": 0.01, + "learning_rate": 1.3435762004189042e-05, + "loss": 3.3722, + "step": 2233344 + }, + { + "epoch": 0.01, + "learning_rate": 1.3427376056678522e-05, + "loss": 3.3652, + "step": 2233856 + }, + { + "epoch": 0.01, + "learning_rate": 1.3418990109168002e-05, + "loss": 3.3723, + "step": 2234368 + }, + { + "epoch": 0.01, + "learning_rate": 1.3410604161657484e-05, + "loss": 3.3856, + "step": 2234880 + }, + { + "epoch": 0.01, + "learning_rate": 1.3402234592950693e-05, + "loss": 3.3817, + "step": 2235392 + }, + { + "epoch": 0.01, + "learning_rate": 1.3393848645440175e-05, + "loss": 3.3825, + "step": 2235904 + }, + { + "epoch": 0.01, + "learning_rate": 1.3385462697929655e-05, + "loss": 3.3829, + "step": 2236416 + }, + { + "epoch": 0.01, + "learning_rate": 1.3377076750419135e-05, + "loss": 3.3798, + "step": 2236928 + }, + { + "epoch": 0.01, + "learning_rate": 1.3368690802908615e-05, + "loss": 3.374, + "step": 2237440 + }, + { + "epoch": 0.01, + "learning_rate": 1.3360321234201825e-05, + "loss": 3.3577, + "step": 2237952 + }, + { + "epoch": 0.01, + "learning_rate": 1.3351935286691305e-05, + "loss": 3.385, + "step": 2238464 + }, + { + "epoch": 0.01, + "learning_rate": 1.3343549339180785e-05, + "loss": 3.3738, + "step": 2238976 + }, + { + "epoch": 0.01, + "learning_rate": 1.3335163391670267e-05, + "loss": 3.3759, + "step": 2239488 + }, + { + "epoch": 0.01, + "learning_rate": 1.3326777444159744e-05, + "loss": 3.3708, + "step": 2240000 + }, + { + "epoch": 0.01, + "learning_rate": 1.3318391496649224e-05, + "loss": 3.3685, + "step": 2240512 + }, + { + "epoch": 0.01, + "learning_rate": 1.3310005549138704e-05, + "loss": 3.3663, + "step": 2241024 + }, + { + "epoch": 0.01, + "learning_rate": 1.3301635980431918e-05, + "loss": 3.3601, + "step": 2241536 + }, + { + "epoch": 0.01, + "learning_rate": 1.3293250032921394e-05, + "loss": 3.3814, + "step": 2242048 + }, + { + "epoch": 0.01, + "learning_rate": 1.3284864085410876e-05, + "loss": 3.3635, + "step": 2242560 + }, + { + "epoch": 0.01, + "learning_rate": 1.3276478137900356e-05, + "loss": 3.386, + "step": 2243072 + }, + { + "epoch": 0.01, + "learning_rate": 1.3268108569193568e-05, + "loss": 3.3752, + "step": 2243584 + }, + { + "epoch": 0.01, + "learning_rate": 1.3259722621683047e-05, + "loss": 3.3604, + "step": 2244096 + }, + { + "epoch": 0.01, + "learning_rate": 1.3251336674172527e-05, + "loss": 3.3825, + "step": 2244608 + }, + { + "epoch": 0.01, + "learning_rate": 1.3242950726662007e-05, + "loss": 3.3644, + "step": 2245120 + }, + { + "epoch": 0.01, + "learning_rate": 1.3234581157955217e-05, + "loss": 3.3688, + "step": 2245632 + }, + { + "epoch": 0.01, + "learning_rate": 1.3226195210444697e-05, + "loss": 3.3678, + "step": 2246144 + }, + { + "epoch": 0.01, + "learning_rate": 1.3217809262934177e-05, + "loss": 3.3835, + "step": 2246656 + }, + { + "epoch": 0.01, + "learning_rate": 1.3209423315423657e-05, + "loss": 3.3691, + "step": 2247168 + }, + { + "epoch": 0.01, + "learning_rate": 1.3201037367913139e-05, + "loss": 3.3704, + "step": 2247680 + }, + { + "epoch": 0.01, + "learning_rate": 1.3192651420402619e-05, + "loss": 3.3533, + "step": 2248192 + }, + { + "epoch": 0.01, + "learning_rate": 1.3184265472892099e-05, + "loss": 3.3707, + "step": 2248704 + }, + { + "epoch": 0.01, + "learning_rate": 1.3175879525381577e-05, + "loss": 3.3818, + "step": 2249216 + }, + { + "epoch": 0.01, + "learning_rate": 1.3167526335478519e-05, + "loss": 3.3825, + "step": 2249728 + }, + { + "epoch": 0.01, + "learning_rate": 1.3159140387968e-05, + "loss": 3.3739, + "step": 2250240 + }, + { + "epoch": 0.01, + "learning_rate": 1.315075444045748e-05, + "loss": 3.3788, + "step": 2250752 + }, + { + "epoch": 0.01, + "learning_rate": 1.314236849294696e-05, + "loss": 3.3852, + "step": 2251264 + }, + { + "epoch": 0.01, + "learning_rate": 1.313398254543644e-05, + "loss": 3.3696, + "step": 2251776 + }, + { + "epoch": 0.01, + "learning_rate": 1.3125612976729651e-05, + "loss": 3.3779, + "step": 2252288 + }, + { + "epoch": 0.01, + "learning_rate": 1.3117227029219131e-05, + "loss": 3.3753, + "step": 2252800 + }, + { + "epoch": 0.01, + "learning_rate": 1.310884108170861e-05, + "loss": 3.3713, + "step": 2253312 + }, + { + "epoch": 0.01, + "learning_rate": 1.3100455134198092e-05, + "loss": 3.3746, + "step": 2253824 + }, + { + "epoch": 0.01, + "learning_rate": 1.3092085565491302e-05, + "loss": 3.3714, + "step": 2254336 + }, + { + "epoch": 0.01, + "learning_rate": 1.3083699617980783e-05, + "loss": 3.3808, + "step": 2254848 + }, + { + "epoch": 0.01, + "learning_rate": 1.3075313670470263e-05, + "loss": 3.3817, + "step": 2255360 + }, + { + "epoch": 0.01, + "learning_rate": 1.3066927722959743e-05, + "loss": 3.3794, + "step": 2255872 + }, + { + "epoch": 0.01, + "learning_rate": 1.3058541775449223e-05, + "loss": 3.3624, + "step": 2256384 + }, + { + "epoch": 0.01, + "learning_rate": 1.3050172206742434e-05, + "loss": 3.376, + "step": 2256896 + }, + { + "epoch": 0.01, + "learning_rate": 1.3041786259231914e-05, + "loss": 3.376, + "step": 2257408 + }, + { + "epoch": 0.01, + "learning_rate": 1.3033400311721394e-05, + "loss": 3.3697, + "step": 2257920 + }, + { + "epoch": 0.01, + "learning_rate": 1.3025014364210872e-05, + "loss": 3.3679, + "step": 2258432 + }, + { + "epoch": 0.01, + "learning_rate": 1.3016628416700352e-05, + "loss": 3.3805, + "step": 2258944 + }, + { + "epoch": 0.02, + "learning_rate": 1.3008258847993565e-05, + "loss": 3.3725, + "step": 2259456 + }, + { + "epoch": 0.02, + "learning_rate": 1.2999872900483046e-05, + "loss": 3.3716, + "step": 2259968 + }, + { + "epoch": 0.02, + "learning_rate": 1.2991486952972523e-05, + "loss": 3.3695, + "step": 2260480 + }, + { + "epoch": 0.02, + "learning_rate": 1.2983101005462003e-05, + "loss": 3.3767, + "step": 2260992 + }, + { + "epoch": 0.02, + "learning_rate": 1.2974715057951484e-05, + "loss": 3.3811, + "step": 2261504 + }, + { + "epoch": 0.02, + "learning_rate": 1.2966329110440964e-05, + "loss": 3.3802, + "step": 2262016 + }, + { + "epoch": 0.02, + "learning_rate": 1.2957943162930444e-05, + "loss": 3.3604, + "step": 2262528 + }, + { + "epoch": 0.02, + "learning_rate": 1.2949557215419924e-05, + "loss": 3.3763, + "step": 2263040 + }, + { + "epoch": 0.02, + "learning_rate": 1.2941187646713135e-05, + "loss": 3.3703, + "step": 2263552 + }, + { + "epoch": 0.02, + "learning_rate": 1.2932801699202615e-05, + "loss": 3.3753, + "step": 2264064 + }, + { + "epoch": 0.02, + "learning_rate": 1.2924415751692095e-05, + "loss": 3.3847, + "step": 2264576 + }, + { + "epoch": 0.02, + "learning_rate": 1.2916029804181577e-05, + "loss": 3.3694, + "step": 2265088 + }, + { + "epoch": 0.02, + "learning_rate": 1.2907643856671053e-05, + "loss": 3.3661, + "step": 2265600 + }, + { + "epoch": 0.02, + "learning_rate": 1.2899274287964266e-05, + "loss": 3.3672, + "step": 2266112 + }, + { + "epoch": 0.02, + "learning_rate": 1.2890888340453747e-05, + "loss": 3.3722, + "step": 2266624 + }, + { + "epoch": 0.02, + "learning_rate": 1.2882502392943227e-05, + "loss": 3.3634, + "step": 2267136 + }, + { + "epoch": 0.02, + "learning_rate": 1.2874116445432704e-05, + "loss": 3.3681, + "step": 2267648 + }, + { + "epoch": 0.02, + "learning_rate": 1.2865730497922185e-05, + "loss": 3.3702, + "step": 2268160 + }, + { + "epoch": 0.02, + "learning_rate": 1.2857344550411665e-05, + "loss": 3.3691, + "step": 2268672 + }, + { + "epoch": 0.02, + "learning_rate": 1.2848958602901145e-05, + "loss": 3.3643, + "step": 2269184 + }, + { + "epoch": 0.02, + "learning_rate": 1.2840589034194356e-05, + "loss": 3.3688, + "step": 2269696 + }, + { + "epoch": 0.02, + "learning_rate": 1.2832203086683836e-05, + "loss": 3.3614, + "step": 2270208 + }, + { + "epoch": 0.02, + "learning_rate": 1.2823817139173316e-05, + "loss": 3.3829, + "step": 2270720 + }, + { + "epoch": 0.02, + "learning_rate": 1.2815431191662796e-05, + "loss": 3.3692, + "step": 2271232 + }, + { + "epoch": 0.02, + "learning_rate": 1.2807061622956007e-05, + "loss": 3.3802, + "step": 2271744 + }, + { + "epoch": 0.02, + "learning_rate": 1.2798675675445487e-05, + "loss": 3.3807, + "step": 2272256 + }, + { + "epoch": 0.02, + "learning_rate": 1.2790289727934968e-05, + "loss": 3.3912, + "step": 2272768 + }, + { + "epoch": 0.02, + "learning_rate": 1.2781903780424448e-05, + "loss": 3.3694, + "step": 2273280 + }, + { + "epoch": 0.02, + "learning_rate": 1.2773517832913928e-05, + "loss": 3.3686, + "step": 2273792 + }, + { + "epoch": 0.02, + "learning_rate": 1.2765148264207139e-05, + "loss": 3.3745, + "step": 2274304 + }, + { + "epoch": 0.02, + "learning_rate": 1.2756762316696619e-05, + "loss": 3.3741, + "step": 2274816 + }, + { + "epoch": 0.02, + "learning_rate": 1.2748376369186099e-05, + "loss": 3.3685, + "step": 2275328 + }, + { + "epoch": 0.02, + "learning_rate": 1.2739990421675579e-05, + "loss": 3.3724, + "step": 2275840 + }, + { + "epoch": 0.02, + "learning_rate": 1.2731604474165057e-05, + "loss": 3.3712, + "step": 2276352 + }, + { + "epoch": 0.02, + "learning_rate": 1.2723218526654537e-05, + "loss": 3.3817, + "step": 2276864 + }, + { + "epoch": 0.02, + "learning_rate": 1.271484895794775e-05, + "loss": 3.3717, + "step": 2277376 + }, + { + "epoch": 0.02, + "learning_rate": 1.2706463010437231e-05, + "loss": 3.3653, + "step": 2277888 + }, + { + "epoch": 0.02, + "learning_rate": 1.2698077062926708e-05, + "loss": 3.3724, + "step": 2278400 + }, + { + "epoch": 0.02, + "learning_rate": 1.2689691115416188e-05, + "loss": 3.3721, + "step": 2278912 + }, + { + "epoch": 0.02, + "learning_rate": 1.2681321546709402e-05, + "loss": 3.3772, + "step": 2279424 + }, + { + "epoch": 0.02, + "learning_rate": 1.2672935599198882e-05, + "loss": 3.3716, + "step": 2279936 + }, + { + "epoch": 0.02, + "learning_rate": 1.266454965168836e-05, + "loss": 3.3811, + "step": 2280448 + }, + { + "epoch": 0.02, + "learning_rate": 1.265616370417784e-05, + "loss": 3.3667, + "step": 2280960 + }, + { + "epoch": 0.02, + "learning_rate": 1.264777775666732e-05, + "loss": 3.374, + "step": 2281472 + }, + { + "epoch": 0.02, + "learning_rate": 1.2639408187960531e-05, + "loss": 3.376, + "step": 2281984 + }, + { + "epoch": 0.02, + "learning_rate": 1.2631022240450011e-05, + "loss": 3.3722, + "step": 2282496 + }, + { + "epoch": 0.02, + "learning_rate": 1.262263629293949e-05, + "loss": 3.3693, + "step": 2283008 + }, + { + "epoch": 0.02, + "learning_rate": 1.261425034542897e-05, + "loss": 3.3693, + "step": 2283520 + }, + { + "epoch": 0.02, + "learning_rate": 1.2605880776722182e-05, + "loss": 3.3836, + "step": 2284032 + }, + { + "epoch": 0.02, + "learning_rate": 1.2597494829211662e-05, + "loss": 3.3923, + "step": 2284544 + }, + { + "epoch": 0.02, + "learning_rate": 1.2589108881701141e-05, + "loss": 3.368, + "step": 2285056 + }, + { + "epoch": 0.02, + "learning_rate": 1.2580722934190623e-05, + "loss": 3.3708, + "step": 2285568 + }, + { + "epoch": 0.02, + "learning_rate": 1.2572336986680103e-05, + "loss": 3.3738, + "step": 2286080 + }, + { + "epoch": 0.02, + "learning_rate": 1.2563951039169583e-05, + "loss": 3.3743, + "step": 2286592 + }, + { + "epoch": 0.02, + "learning_rate": 1.2555565091659063e-05, + "loss": 3.3638, + "step": 2287104 + }, + { + "epoch": 0.02, + "learning_rate": 1.2547195522952274e-05, + "loss": 3.3817, + "step": 2287616 + }, + { + "epoch": 0.02, + "learning_rate": 1.2538809575441754e-05, + "loss": 3.3747, + "step": 2288128 + }, + { + "epoch": 0.02, + "learning_rate": 1.2530423627931234e-05, + "loss": 3.3805, + "step": 2288640 + }, + { + "epoch": 0.02, + "learning_rate": 1.2522037680420712e-05, + "loss": 3.3627, + "step": 2289152 + }, + { + "epoch": 0.03, + "eval_loss": 3.8606276512145996, + "eval_runtime": 303.3543, + "eval_samples_per_second": 1257.905, + "eval_steps_per_second": 39.31, + "step": 2289600 + }, + { + "epoch": 1.0, + "learning_rate": 1.2513651732910192e-05, + "loss": 3.3707, + "step": 2289664 + }, + { + "epoch": 1.0, + "learning_rate": 1.2505265785399672e-05, + "loss": 3.3616, + "step": 2290176 + }, + { + "epoch": 1.0, + "learning_rate": 1.2496879837889154e-05, + "loss": 3.3752, + "step": 2290688 + }, + { + "epoch": 1.0, + "learning_rate": 1.2488510269182364e-05, + "loss": 3.3747, + "step": 2291200 + }, + { + "epoch": 1.0, + "learning_rate": 1.2480124321671844e-05, + "loss": 3.3764, + "step": 2291712 + }, + { + "epoch": 1.0, + "learning_rate": 1.2471738374161324e-05, + "loss": 3.3691, + "step": 2292224 + }, + { + "epoch": 1.0, + "learning_rate": 1.2463352426650804e-05, + "loss": 3.3702, + "step": 2292736 + }, + { + "epoch": 1.0, + "learning_rate": 1.2454966479140284e-05, + "loss": 3.3682, + "step": 2293248 + }, + { + "epoch": 1.0, + "learning_rate": 1.2446580531629762e-05, + "loss": 3.3686, + "step": 2293760 + }, + { + "epoch": 1.0, + "learning_rate": 1.2438210962922975e-05, + "loss": 3.3726, + "step": 2294272 + }, + { + "epoch": 1.0, + "learning_rate": 1.2429825015412455e-05, + "loss": 3.3654, + "step": 2294784 + }, + { + "epoch": 1.0, + "learning_rate": 1.2421439067901935e-05, + "loss": 3.3775, + "step": 2295296 + }, + { + "epoch": 1.0, + "learning_rate": 1.2413053120391415e-05, + "loss": 3.3835, + "step": 2295808 + }, + { + "epoch": 1.0, + "learning_rate": 1.2404683551684626e-05, + "loss": 3.3613, + "step": 2296320 + }, + { + "epoch": 1.0, + "learning_rate": 1.2396297604174106e-05, + "loss": 3.3681, + "step": 2296832 + }, + { + "epoch": 1.0, + "learning_rate": 1.2387911656663585e-05, + "loss": 3.3598, + "step": 2297344 + }, + { + "epoch": 1.0, + "learning_rate": 1.2379525709153065e-05, + "loss": 3.3691, + "step": 2297856 + }, + { + "epoch": 1.0, + "learning_rate": 1.2371139761642545e-05, + "loss": 3.3644, + "step": 2298368 + }, + { + "epoch": 1.0, + "learning_rate": 1.2362753814132027e-05, + "loss": 3.3659, + "step": 2298880 + }, + { + "epoch": 1.0, + "learning_rate": 1.2354367866621505e-05, + "loss": 3.3604, + "step": 2299392 + }, + { + "epoch": 1.0, + "learning_rate": 1.2345981919110985e-05, + "loss": 3.3815, + "step": 2299904 + }, + { + "epoch": 1.0, + "learning_rate": 1.2337612350404198e-05, + "loss": 3.3693, + "step": 2300416 + }, + { + "epoch": 1.0, + "learning_rate": 1.2329226402893676e-05, + "loss": 3.3757, + "step": 2300928 + }, + { + "epoch": 1.0, + "learning_rate": 1.2320840455383156e-05, + "loss": 3.3733, + "step": 2301440 + }, + { + "epoch": 1.0, + "learning_rate": 1.2312454507872636e-05, + "loss": 3.3742, + "step": 2301952 + }, + { + "epoch": 1.0, + "learning_rate": 1.2304084939165848e-05, + "loss": 3.3699, + "step": 2302464 + }, + { + "epoch": 1.0, + "learning_rate": 1.2295698991655327e-05, + "loss": 3.3614, + "step": 2302976 + }, + { + "epoch": 1.0, + "learning_rate": 1.2287313044144808e-05, + "loss": 3.3712, + "step": 2303488 + }, + { + "epoch": 1.0, + "learning_rate": 1.2278927096634288e-05, + "loss": 3.364, + "step": 2304000 + }, + { + "epoch": 1.0, + "learning_rate": 1.2270573906731232e-05, + "loss": 3.3639, + "step": 2304512 + }, + { + "epoch": 1.01, + "learning_rate": 1.226218795922071e-05, + "loss": 3.3688, + "step": 2305024 + }, + { + "epoch": 1.01, + "learning_rate": 1.225380201171019e-05, + "loss": 3.3615, + "step": 2305536 + }, + { + "epoch": 1.01, + "learning_rate": 1.224541606419967e-05, + "loss": 3.3739, + "step": 2306048 + }, + { + "epoch": 1.01, + "learning_rate": 1.223703011668915e-05, + "loss": 3.3648, + "step": 2306560 + }, + { + "epoch": 1.01, + "learning_rate": 1.222864416917863e-05, + "loss": 3.3662, + "step": 2307072 + }, + { + "epoch": 1.01, + "learning_rate": 1.2220274600471842e-05, + "loss": 3.3758, + "step": 2307584 + }, + { + "epoch": 1.01, + "learning_rate": 1.2211888652961322e-05, + "loss": 3.3707, + "step": 2308096 + }, + { + "epoch": 1.01, + "learning_rate": 1.22035027054508e-05, + "loss": 3.3498, + "step": 2308608 + }, + { + "epoch": 1.01, + "learning_rate": 1.219511675794028e-05, + "loss": 3.3691, + "step": 2309120 + }, + { + "epoch": 1.01, + "learning_rate": 1.2186730810429762e-05, + "loss": 3.3647, + "step": 2309632 + }, + { + "epoch": 1.01, + "learning_rate": 1.217834486291924e-05, + "loss": 3.353, + "step": 2310144 + }, + { + "epoch": 1.01, + "learning_rate": 1.216995891540872e-05, + "loss": 3.3667, + "step": 2310656 + }, + { + "epoch": 1.01, + "learning_rate": 1.21615729678982e-05, + "loss": 3.3804, + "step": 2311168 + }, + { + "epoch": 1.01, + "learning_rate": 1.2153203399191413e-05, + "loss": 3.3676, + "step": 2311680 + }, + { + "epoch": 1.01, + "learning_rate": 1.2144833830484623e-05, + "loss": 3.3728, + "step": 2312192 + }, + { + "epoch": 1.01, + "learning_rate": 1.2136447882974103e-05, + "loss": 3.3746, + "step": 2312704 + }, + { + "epoch": 1.01, + "learning_rate": 1.2128061935463583e-05, + "loss": 3.371, + "step": 2313216 + }, + { + "epoch": 1.01, + "learning_rate": 1.2119675987953062e-05, + "loss": 3.3644, + "step": 2313728 + }, + { + "epoch": 1.01, + "learning_rate": 1.2111290040442543e-05, + "loss": 3.3506, + "step": 2314240 + }, + { + "epoch": 1.01, + "learning_rate": 1.2102904092932023e-05, + "loss": 3.3739, + "step": 2314752 + }, + { + "epoch": 1.01, + "learning_rate": 1.2094534524225234e-05, + "loss": 3.3661, + "step": 2315264 + }, + { + "epoch": 1.01, + "learning_rate": 1.2086148576714714e-05, + "loss": 3.3649, + "step": 2315776 + }, + { + "epoch": 1.01, + "learning_rate": 1.2077762629204194e-05, + "loss": 3.3626, + "step": 2316288 + }, + { + "epoch": 1.01, + "learning_rate": 1.2069376681693674e-05, + "loss": 3.36, + "step": 2316800 + }, + { + "epoch": 1.01, + "learning_rate": 1.2060990734183154e-05, + "loss": 3.3539, + "step": 2317312 + }, + { + "epoch": 1.01, + "learning_rate": 1.2052621165476365e-05, + "loss": 3.3538, + "step": 2317824 + }, + { + "epoch": 1.01, + "learning_rate": 1.2044235217965845e-05, + "loss": 3.3748, + "step": 2318336 + }, + { + "epoch": 1.01, + "learning_rate": 1.2035849270455324e-05, + "loss": 3.3541, + "step": 2318848 + }, + { + "epoch": 1.01, + "learning_rate": 1.2027463322944804e-05, + "loss": 3.3739, + "step": 2319360 + }, + { + "epoch": 1.01, + "learning_rate": 1.2019077375434284e-05, + "loss": 3.3663, + "step": 2319872 + }, + { + "epoch": 1.01, + "learning_rate": 1.2010691427923764e-05, + "loss": 3.3544, + "step": 2320384 + }, + { + "epoch": 1.01, + "learning_rate": 1.2002321859216977e-05, + "loss": 3.3661, + "step": 2320896 + }, + { + "epoch": 1.01, + "learning_rate": 1.1993935911706455e-05, + "loss": 3.3596, + "step": 2321408 + }, + { + "epoch": 1.01, + "learning_rate": 1.1985549964195935e-05, + "loss": 3.3615, + "step": 2321920 + }, + { + "epoch": 1.01, + "learning_rate": 1.1977164016685417e-05, + "loss": 3.3539, + "step": 2322432 + }, + { + "epoch": 1.01, + "learning_rate": 1.1968778069174895e-05, + "loss": 3.376, + "step": 2322944 + }, + { + "epoch": 1.01, + "learning_rate": 1.1960392121664375e-05, + "loss": 3.3611, + "step": 2323456 + }, + { + "epoch": 1.01, + "learning_rate": 1.1952006174153855e-05, + "loss": 3.3548, + "step": 2323968 + }, + { + "epoch": 1.01, + "learning_rate": 1.1943620226643335e-05, + "loss": 3.3469, + "step": 2324480 + }, + { + "epoch": 1.01, + "learning_rate": 1.1935250657936546e-05, + "loss": 3.3611, + "step": 2324992 + }, + { + "epoch": 1.01, + "learning_rate": 1.1926864710426026e-05, + "loss": 3.3667, + "step": 2325504 + }, + { + "epoch": 1.01, + "learning_rate": 1.1918478762915507e-05, + "loss": 3.3764, + "step": 2326016 + }, + { + "epoch": 1.01, + "learning_rate": 1.1910092815404986e-05, + "loss": 3.363, + "step": 2326528 + }, + { + "epoch": 1.01, + "learning_rate": 1.1901739625501929e-05, + "loss": 3.3728, + "step": 2327040 + }, + { + "epoch": 1.01, + "learning_rate": 1.1893353677991409e-05, + "loss": 3.3711, + "step": 2327552 + }, + { + "epoch": 1.01, + "learning_rate": 1.1884967730480889e-05, + "loss": 3.365, + "step": 2328064 + }, + { + "epoch": 1.01, + "learning_rate": 1.1876581782970369e-05, + "loss": 3.3667, + "step": 2328576 + }, + { + "epoch": 1.01, + "learning_rate": 1.1868195835459849e-05, + "loss": 3.365, + "step": 2329088 + }, + { + "epoch": 1.01, + "learning_rate": 1.1859809887949329e-05, + "loss": 3.3638, + "step": 2329600 + }, + { + "epoch": 1.01, + "learning_rate": 1.1851440319242541e-05, + "loss": 3.3639, + "step": 2330112 + }, + { + "epoch": 1.01, + "learning_rate": 1.184305437173202e-05, + "loss": 3.364, + "step": 2330624 + }, + { + "epoch": 1.01, + "learning_rate": 1.18346684242215e-05, + "loss": 3.3729, + "step": 2331136 + }, + { + "epoch": 1.01, + "learning_rate": 1.182628247671098e-05, + "loss": 3.3745, + "step": 2331648 + }, + { + "epoch": 1.01, + "learning_rate": 1.181789652920046e-05, + "loss": 3.3664, + "step": 2332160 + }, + { + "epoch": 1.01, + "learning_rate": 1.180952696049367e-05, + "loss": 3.353, + "step": 2332672 + }, + { + "epoch": 1.01, + "learning_rate": 1.1801141012983152e-05, + "loss": 3.365, + "step": 2333184 + }, + { + "epoch": 1.01, + "learning_rate": 1.1792755065472632e-05, + "loss": 3.3677, + "step": 2333696 + }, + { + "epoch": 1.01, + "learning_rate": 1.178436911796211e-05, + "loss": 3.3649, + "step": 2334208 + }, + { + "epoch": 1.01, + "learning_rate": 1.177598317045159e-05, + "loss": 3.3616, + "step": 2334720 + }, + { + "epoch": 1.01, + "learning_rate": 1.1767597222941071e-05, + "loss": 3.3688, + "step": 2335232 + }, + { + "epoch": 1.02, + "learning_rate": 1.175922765423428e-05, + "loss": 3.3675, + "step": 2335744 + }, + { + "epoch": 1.02, + "learning_rate": 1.1750841706723762e-05, + "loss": 3.3571, + "step": 2336256 + }, + { + "epoch": 1.02, + "learning_rate": 1.1742455759213242e-05, + "loss": 3.3618, + "step": 2336768 + }, + { + "epoch": 1.02, + "learning_rate": 1.1734069811702722e-05, + "loss": 3.3648, + "step": 2337280 + }, + { + "epoch": 1.02, + "learning_rate": 1.17256838641922e-05, + "loss": 3.3682, + "step": 2337792 + }, + { + "epoch": 1.02, + "learning_rate": 1.1717314295485413e-05, + "loss": 3.3744, + "step": 2338304 + }, + { + "epoch": 1.02, + "learning_rate": 1.1708928347974893e-05, + "loss": 3.3492, + "step": 2338816 + }, + { + "epoch": 1.02, + "learning_rate": 1.1700542400464371e-05, + "loss": 3.3661, + "step": 2339328 + }, + { + "epoch": 1.02, + "learning_rate": 1.1692156452953853e-05, + "loss": 3.3645, + "step": 2339840 + }, + { + "epoch": 1.02, + "learning_rate": 1.1683770505443333e-05, + "loss": 3.3613, + "step": 2340352 + }, + { + "epoch": 1.02, + "learning_rate": 1.1675384557932813e-05, + "loss": 3.3782, + "step": 2340864 + }, + { + "epoch": 1.02, + "learning_rate": 1.1667014989226023e-05, + "loss": 3.3619, + "step": 2341376 + }, + { + "epoch": 1.02, + "learning_rate": 1.1658629041715503e-05, + "loss": 3.3534, + "step": 2341888 + }, + { + "epoch": 1.02, + "learning_rate": 1.1650243094204983e-05, + "loss": 3.3631, + "step": 2342400 + }, + { + "epoch": 1.02, + "learning_rate": 1.1641857146694463e-05, + "loss": 3.361, + "step": 2342912 + }, + { + "epoch": 1.02, + "learning_rate": 1.1633487577987674e-05, + "loss": 3.3497, + "step": 2343424 + }, + { + "epoch": 1.02, + "learning_rate": 1.1625101630477154e-05, + "loss": 3.3589, + "step": 2343936 + }, + { + "epoch": 1.02, + "learning_rate": 1.1616715682966636e-05, + "loss": 3.3638, + "step": 2344448 + }, + { + "epoch": 1.02, + "learning_rate": 1.1608329735456114e-05, + "loss": 3.3596, + "step": 2344960 + }, + { + "epoch": 1.02, + "learning_rate": 1.1599943787945594e-05, + "loss": 3.3526, + "step": 2345472 + }, + { + "epoch": 1.02, + "learning_rate": 1.1591574219238806e-05, + "loss": 3.3645, + "step": 2345984 + }, + { + "epoch": 1.02, + "learning_rate": 1.1583188271728285e-05, + "loss": 3.3495, + "step": 2346496 + }, + { + "epoch": 1.02, + "learning_rate": 1.1574802324217765e-05, + "loss": 3.372, + "step": 2347008 + }, + { + "epoch": 1.02, + "learning_rate": 1.1566416376707245e-05, + "loss": 3.3606, + "step": 2347520 + }, + { + "epoch": 1.02, + "learning_rate": 1.1558046808000457e-05, + "loss": 3.3671, + "step": 2348032 + }, + { + "epoch": 1.02, + "learning_rate": 1.1549660860489935e-05, + "loss": 3.3706, + "step": 2348544 + }, + { + "epoch": 1.02, + "learning_rate": 1.1541274912979417e-05, + "loss": 3.3832, + "step": 2349056 + }, + { + "epoch": 1.02, + "learning_rate": 1.1532888965468897e-05, + "loss": 3.3598, + "step": 2349568 + }, + { + "epoch": 1.02, + "learning_rate": 1.1524503017958375e-05, + "loss": 3.3563, + "step": 2350080 + }, + { + "epoch": 1.02, + "learning_rate": 1.1516117070447855e-05, + "loss": 3.3673, + "step": 2350592 + }, + { + "epoch": 1.02, + "learning_rate": 1.1507747501741068e-05, + "loss": 3.3609, + "step": 2351104 + }, + { + "epoch": 1.02, + "learning_rate": 1.1499361554230548e-05, + "loss": 3.3633, + "step": 2351616 + }, + { + "epoch": 1.02, + "learning_rate": 1.1490975606720026e-05, + "loss": 3.362, + "step": 2352128 + }, + { + "epoch": 1.02, + "learning_rate": 1.1482589659209508e-05, + "loss": 3.3592, + "step": 2352640 + }, + { + "epoch": 1.02, + "learning_rate": 1.1474203711698987e-05, + "loss": 3.3707, + "step": 2353152 + }, + { + "epoch": 1.02, + "learning_rate": 1.1465817764188466e-05, + "loss": 3.3622, + "step": 2353664 + }, + { + "epoch": 1.02, + "learning_rate": 1.1457448195481678e-05, + "loss": 3.3572, + "step": 2354176 + }, + { + "epoch": 1.02, + "learning_rate": 1.1449062247971158e-05, + "loss": 3.3607, + "step": 2354688 + }, + { + "epoch": 1.02, + "learning_rate": 1.1440676300460638e-05, + "loss": 3.3678, + "step": 2355200 + }, + { + "epoch": 1.02, + "learning_rate": 1.1432290352950118e-05, + "loss": 3.3614, + "step": 2355712 + }, + { + "epoch": 1.02, + "learning_rate": 1.1423904405439598e-05, + "loss": 3.3642, + "step": 2356224 + }, + { + "epoch": 1.02, + "learning_rate": 1.1415534836732809e-05, + "loss": 3.3708, + "step": 2356736 + }, + { + "epoch": 1.02, + "learning_rate": 1.140714888922229e-05, + "loss": 3.3573, + "step": 2357248 + }, + { + "epoch": 1.02, + "learning_rate": 1.1398762941711769e-05, + "loss": 3.3644, + "step": 2357760 + }, + { + "epoch": 1.02, + "learning_rate": 1.1390376994201249e-05, + "loss": 3.3643, + "step": 2358272 + }, + { + "epoch": 1.02, + "learning_rate": 1.1381991046690729e-05, + "loss": 3.3681, + "step": 2358784 + }, + { + "epoch": 1.02, + "learning_rate": 1.137362147798394e-05, + "loss": 3.3575, + "step": 2359296 + }, + { + "epoch": 1.02, + "learning_rate": 1.136523553047342e-05, + "loss": 3.3623, + "step": 2359808 + }, + { + "epoch": 1.02, + "learning_rate": 1.13568495829629e-05, + "loss": 3.374, + "step": 2360320 + }, + { + "epoch": 1.02, + "learning_rate": 1.1348463635452381e-05, + "loss": 3.3737, + "step": 2360832 + }, + { + "epoch": 1.02, + "learning_rate": 1.134007768794186e-05, + "loss": 3.3622, + "step": 2361344 + }, + { + "epoch": 1.02, + "learning_rate": 1.133169174043134e-05, + "loss": 3.365, + "step": 2361856 + }, + { + "epoch": 1.02, + "learning_rate": 1.132330579292082e-05, + "loss": 3.3614, + "step": 2362368 + }, + { + "epoch": 1.02, + "learning_rate": 1.131493622421403e-05, + "loss": 3.3638, + "step": 2362880 + }, + { + "epoch": 1.02, + "learning_rate": 1.130655027670351e-05, + "loss": 3.352, + "step": 2363392 + }, + { + "epoch": 1.02, + "learning_rate": 1.1298164329192992e-05, + "loss": 3.3751, + "step": 2363904 + }, + { + "epoch": 1.02, + "learning_rate": 1.1289778381682472e-05, + "loss": 3.3642, + "step": 2364416 + }, + { + "epoch": 1.02, + "learning_rate": 1.128139243417195e-05, + "loss": 3.3684, + "step": 2364928 + }, + { + "epoch": 1.02, + "learning_rate": 1.127300648666143e-05, + "loss": 3.3563, + "step": 2365440 + }, + { + "epoch": 1.03, + "eval_loss": 3.8615846633911133, + "eval_runtime": 305.5631, + "eval_samples_per_second": 1248.812, + "eval_steps_per_second": 39.026, + "step": 2365920 + }, + { + "epoch": 0.0, + "learning_rate": 1.1264620539150911e-05, + "loss": 3.3185, + "step": 2365952 + }, + { + "epoch": 0.0, + "learning_rate": 1.125623459164039e-05, + "loss": 3.3518, + "step": 2366464 + }, + { + "epoch": 0.0, + "learning_rate": 1.124784864412987e-05, + "loss": 3.363, + "step": 2366976 + }, + { + "epoch": 0.0, + "learning_rate": 1.123946269661935e-05, + "loss": 3.3638, + "step": 2367488 + }, + { + "epoch": 0.0, + "learning_rate": 1.1231093127912562e-05, + "loss": 3.3635, + "step": 2368000 + }, + { + "epoch": 0.0, + "learning_rate": 1.122270718040204e-05, + "loss": 3.3622, + "step": 2368512 + }, + { + "epoch": 0.0, + "learning_rate": 1.1214321232891522e-05, + "loss": 3.3576, + "step": 2369024 + }, + { + "epoch": 0.0, + "learning_rate": 1.1205935285381002e-05, + "loss": 3.3603, + "step": 2369536 + }, + { + "epoch": 0.0, + "learning_rate": 1.119754933787048e-05, + "loss": 3.3614, + "step": 2370048 + }, + { + "epoch": 0.0, + "learning_rate": 1.1189179769163693e-05, + "loss": 3.3613, + "step": 2370560 + }, + { + "epoch": 0.0, + "learning_rate": 1.1180793821653173e-05, + "loss": 3.3572, + "step": 2371072 + }, + { + "epoch": 0.0, + "learning_rate": 1.1172407874142653e-05, + "loss": 3.3669, + "step": 2371584 + }, + { + "epoch": 0.0, + "learning_rate": 1.116402192663213e-05, + "loss": 3.3725, + "step": 2372096 + }, + { + "epoch": 0.0, + "learning_rate": 1.1155652357925343e-05, + "loss": 3.3521, + "step": 2372608 + }, + { + "epoch": 0.0, + "learning_rate": 1.1147266410414823e-05, + "loss": 3.3581, + "step": 2373120 + }, + { + "epoch": 0.0, + "learning_rate": 1.1138880462904303e-05, + "loss": 3.3508, + "step": 2373632 + }, + { + "epoch": 0.0, + "learning_rate": 1.1130494515393783e-05, + "loss": 3.3627, + "step": 2374144 + }, + { + "epoch": 0.0, + "learning_rate": 1.1122108567883263e-05, + "loss": 3.3503, + "step": 2374656 + }, + { + "epoch": 0.0, + "learning_rate": 1.1113722620372743e-05, + "loss": 3.3579, + "step": 2375168 + }, + { + "epoch": 0.0, + "learning_rate": 1.1105336672862223e-05, + "loss": 3.3552, + "step": 2375680 + }, + { + "epoch": 0.0, + "learning_rate": 1.1096950725351703e-05, + "loss": 3.3694, + "step": 2376192 + }, + { + "epoch": 0.0, + "learning_rate": 1.1088581156644914e-05, + "loss": 3.3615, + "step": 2376704 + }, + { + "epoch": 0.0, + "learning_rate": 1.1080195209134394e-05, + "loss": 3.3614, + "step": 2377216 + }, + { + "epoch": 0.0, + "learning_rate": 1.1071809261623874e-05, + "loss": 3.3666, + "step": 2377728 + }, + { + "epoch": 0.0, + "learning_rate": 1.1063423314113354e-05, + "loss": 3.3653, + "step": 2378240 + }, + { + "epoch": 0.0, + "learning_rate": 1.1055053745406566e-05, + "loss": 3.3563, + "step": 2378752 + }, + { + "epoch": 0.0, + "learning_rate": 1.1046667797896044e-05, + "loss": 3.3525, + "step": 2379264 + }, + { + "epoch": 0.0, + "learning_rate": 1.1038298229189257e-05, + "loss": 3.3616, + "step": 2379776 + }, + { + "epoch": 0.0, + "learning_rate": 1.1029912281678737e-05, + "loss": 3.3524, + "step": 2380288 + }, + { + "epoch": 0.0, + "learning_rate": 1.1021526334168215e-05, + "loss": 3.354, + "step": 2380800 + }, + { + "epoch": 0.01, + "learning_rate": 1.1013140386657695e-05, + "loss": 3.3598, + "step": 2381312 + }, + { + "epoch": 0.01, + "learning_rate": 1.1004754439147177e-05, + "loss": 3.3533, + "step": 2381824 + }, + { + "epoch": 0.01, + "learning_rate": 1.0996368491636657e-05, + "loss": 3.3634, + "step": 2382336 + }, + { + "epoch": 0.01, + "learning_rate": 1.0987998922929866e-05, + "loss": 3.3567, + "step": 2382848 + }, + { + "epoch": 0.01, + "learning_rate": 1.0979612975419347e-05, + "loss": 3.3587, + "step": 2383360 + }, + { + "epoch": 0.01, + "learning_rate": 1.0971227027908827e-05, + "loss": 3.3677, + "step": 2383872 + }, + { + "epoch": 0.01, + "learning_rate": 1.0962841080398306e-05, + "loss": 3.3614, + "step": 2384384 + }, + { + "epoch": 0.01, + "learning_rate": 1.0954455132887787e-05, + "loss": 3.3394, + "step": 2384896 + }, + { + "epoch": 0.01, + "learning_rate": 1.0946085564180998e-05, + "loss": 3.3664, + "step": 2385408 + }, + { + "epoch": 0.01, + "learning_rate": 1.0937699616670478e-05, + "loss": 3.351, + "step": 2385920 + }, + { + "epoch": 0.01, + "learning_rate": 1.0929313669159958e-05, + "loss": 3.3441, + "step": 2386432 + }, + { + "epoch": 0.01, + "learning_rate": 1.0920927721649438e-05, + "loss": 3.3595, + "step": 2386944 + }, + { + "epoch": 0.01, + "learning_rate": 1.0912541774138918e-05, + "loss": 3.3706, + "step": 2387456 + }, + { + "epoch": 0.01, + "learning_rate": 1.0904155826628396e-05, + "loss": 3.3589, + "step": 2387968 + }, + { + "epoch": 0.01, + "learning_rate": 1.0895786257921609e-05, + "loss": 3.36, + "step": 2388480 + }, + { + "epoch": 0.01, + "learning_rate": 1.0887400310411089e-05, + "loss": 3.3651, + "step": 2388992 + }, + { + "epoch": 0.01, + "learning_rate": 1.0879014362900569e-05, + "loss": 3.3624, + "step": 2389504 + }, + { + "epoch": 0.01, + "learning_rate": 1.0870628415390049e-05, + "loss": 3.3541, + "step": 2390016 + }, + { + "epoch": 0.01, + "learning_rate": 1.0862242467879528e-05, + "loss": 3.341, + "step": 2390528 + }, + { + "epoch": 0.01, + "learning_rate": 1.0853856520369008e-05, + "loss": 3.3621, + "step": 2391040 + }, + { + "epoch": 0.01, + "learning_rate": 1.0845470572858488e-05, + "loss": 3.3607, + "step": 2391552 + }, + { + "epoch": 0.01, + "learning_rate": 1.08371010041517e-05, + "loss": 3.3548, + "step": 2392064 + }, + { + "epoch": 0.01, + "learning_rate": 1.0828715056641179e-05, + "loss": 3.3499, + "step": 2392576 + }, + { + "epoch": 0.01, + "learning_rate": 1.082032910913066e-05, + "loss": 3.3485, + "step": 2393088 + }, + { + "epoch": 0.01, + "learning_rate": 1.0811943161620139e-05, + "loss": 3.3497, + "step": 2393600 + }, + { + "epoch": 0.01, + "learning_rate": 1.080357359291335e-05, + "loss": 3.3402, + "step": 2394112 + }, + { + "epoch": 0.01, + "learning_rate": 1.0795187645402831e-05, + "loss": 3.3667, + "step": 2394624 + }, + { + "epoch": 0.01, + "learning_rate": 1.0786801697892311e-05, + "loss": 3.3443, + "step": 2395136 + }, + { + "epoch": 0.01, + "learning_rate": 1.077841575038179e-05, + "loss": 3.3636, + "step": 2395648 + }, + { + "epoch": 0.01, + "learning_rate": 1.077002980287127e-05, + "loss": 3.3567, + "step": 2396160 + }, + { + "epoch": 0.01, + "learning_rate": 1.0761643855360751e-05, + "loss": 3.3455, + "step": 2396672 + }, + { + "epoch": 0.01, + "learning_rate": 1.075325790785023e-05, + "loss": 3.3555, + "step": 2397184 + }, + { + "epoch": 0.01, + "learning_rate": 1.0744888339143442e-05, + "loss": 3.3523, + "step": 2397696 + }, + { + "epoch": 0.01, + "learning_rate": 1.0736502391632922e-05, + "loss": 3.3503, + "step": 2398208 + }, + { + "epoch": 0.01, + "learning_rate": 1.0728116444122402e-05, + "loss": 3.3424, + "step": 2398720 + }, + { + "epoch": 0.01, + "learning_rate": 1.071973049661188e-05, + "loss": 3.3707, + "step": 2399232 + }, + { + "epoch": 0.01, + "learning_rate": 1.0711344549101362e-05, + "loss": 3.3515, + "step": 2399744 + }, + { + "epoch": 0.01, + "learning_rate": 1.0702958601590842e-05, + "loss": 3.3457, + "step": 2400256 + }, + { + "epoch": 0.01, + "learning_rate": 1.069457265408032e-05, + "loss": 3.3374, + "step": 2400768 + }, + { + "epoch": 0.01, + "learning_rate": 1.0686203085373533e-05, + "loss": 3.3515, + "step": 2401280 + }, + { + "epoch": 0.01, + "learning_rate": 1.0677817137863013e-05, + "loss": 3.3577, + "step": 2401792 + }, + { + "epoch": 0.01, + "learning_rate": 1.0669431190352492e-05, + "loss": 3.365, + "step": 2402304 + }, + { + "epoch": 0.01, + "learning_rate": 1.0661061621645703e-05, + "loss": 3.3526, + "step": 2402816 + }, + { + "epoch": 0.01, + "learning_rate": 1.0652675674135183e-05, + "loss": 3.3634, + "step": 2403328 + }, + { + "epoch": 0.01, + "learning_rate": 1.0644289726624663e-05, + "loss": 3.3643, + "step": 2403840 + }, + { + "epoch": 0.01, + "learning_rate": 1.0635903779114143e-05, + "loss": 3.354, + "step": 2404352 + }, + { + "epoch": 0.01, + "learning_rate": 1.0627534210407354e-05, + "loss": 3.3549, + "step": 2404864 + }, + { + "epoch": 0.01, + "learning_rate": 1.0619148262896834e-05, + "loss": 3.3567, + "step": 2405376 + }, + { + "epoch": 0.01, + "learning_rate": 1.0610762315386316e-05, + "loss": 3.3544, + "step": 2405888 + }, + { + "epoch": 0.01, + "learning_rate": 1.0602376367875794e-05, + "loss": 3.3556, + "step": 2406400 + }, + { + "epoch": 0.01, + "learning_rate": 1.0594006799169005e-05, + "loss": 3.3519, + "step": 2406912 + }, + { + "epoch": 0.01, + "learning_rate": 1.0585620851658486e-05, + "loss": 3.3624, + "step": 2407424 + }, + { + "epoch": 0.01, + "learning_rate": 1.0577234904147966e-05, + "loss": 3.3606, + "step": 2407936 + }, + { + "epoch": 0.01, + "learning_rate": 1.0568848956637444e-05, + "loss": 3.3591, + "step": 2408448 + }, + { + "epoch": 0.01, + "learning_rate": 1.0560463009126924e-05, + "loss": 3.3444, + "step": 2408960 + }, + { + "epoch": 0.01, + "learning_rate": 1.0552077061616406e-05, + "loss": 3.356, + "step": 2409472 + }, + { + "epoch": 0.01, + "learning_rate": 1.0543691114105884e-05, + "loss": 3.3613, + "step": 2409984 + }, + { + "epoch": 0.01, + "learning_rate": 1.0535305166595364e-05, + "loss": 3.3576, + "step": 2410496 + }, + { + "epoch": 0.01, + "learning_rate": 1.0526935597888577e-05, + "loss": 3.3502, + "step": 2411008 + }, + { + "epoch": 0.01, + "learning_rate": 1.0518549650378057e-05, + "loss": 3.356, + "step": 2411520 + }, + { + "epoch": 0.02, + "learning_rate": 1.0510163702867535e-05, + "loss": 3.3631, + "step": 2412032 + }, + { + "epoch": 0.02, + "learning_rate": 1.0501777755357017e-05, + "loss": 3.3453, + "step": 2412544 + }, + { + "epoch": 0.02, + "learning_rate": 1.0493391807846497e-05, + "loss": 3.3528, + "step": 2413056 + }, + { + "epoch": 0.02, + "learning_rate": 1.0485022239139707e-05, + "loss": 3.3553, + "step": 2413568 + }, + { + "epoch": 0.02, + "learning_rate": 1.0476636291629187e-05, + "loss": 3.3569, + "step": 2414080 + }, + { + "epoch": 0.02, + "learning_rate": 1.0468250344118667e-05, + "loss": 3.363, + "step": 2414592 + }, + { + "epoch": 0.02, + "learning_rate": 1.0459864396608147e-05, + "loss": 3.3472, + "step": 2415104 + }, + { + "epoch": 0.02, + "learning_rate": 1.0451478449097627e-05, + "loss": 3.3519, + "step": 2415616 + }, + { + "epoch": 0.02, + "learning_rate": 1.0443108880390838e-05, + "loss": 3.3557, + "step": 2416128 + }, + { + "epoch": 0.02, + "learning_rate": 1.0434722932880318e-05, + "loss": 3.3532, + "step": 2416640 + }, + { + "epoch": 0.02, + "learning_rate": 1.0426336985369798e-05, + "loss": 3.3637, + "step": 2417152 + }, + { + "epoch": 0.02, + "learning_rate": 1.0417951037859278e-05, + "loss": 3.3574, + "step": 2417664 + }, + { + "epoch": 0.02, + "learning_rate": 1.0409565090348758e-05, + "loss": 3.3435, + "step": 2418176 + }, + { + "epoch": 0.02, + "learning_rate": 1.0401179142838236e-05, + "loss": 3.349, + "step": 2418688 + }, + { + "epoch": 0.02, + "learning_rate": 1.0392809574131449e-05, + "loss": 3.3588, + "step": 2419200 + }, + { + "epoch": 0.02, + "learning_rate": 1.0384423626620929e-05, + "loss": 3.3324, + "step": 2419712 + }, + { + "epoch": 0.02, + "learning_rate": 1.0376037679110408e-05, + "loss": 3.3506, + "step": 2420224 + }, + { + "epoch": 0.02, + "learning_rate": 1.0367651731599888e-05, + "loss": 3.3588, + "step": 2420736 + }, + { + "epoch": 0.02, + "learning_rate": 1.0359265784089368e-05, + "loss": 3.3458, + "step": 2421248 + }, + { + "epoch": 0.02, + "learning_rate": 1.0350879836578848e-05, + "loss": 3.3418, + "step": 2421760 + }, + { + "epoch": 0.02, + "learning_rate": 1.034251026787206e-05, + "loss": 3.353, + "step": 2422272 + }, + { + "epoch": 0.02, + "learning_rate": 1.0334124320361539e-05, + "loss": 3.3395, + "step": 2422784 + }, + { + "epoch": 0.02, + "learning_rate": 1.0325738372851019e-05, + "loss": 3.3644, + "step": 2423296 + }, + { + "epoch": 0.02, + "learning_rate": 1.03173524253405e-05, + "loss": 3.3492, + "step": 2423808 + }, + { + "epoch": 0.02, + "learning_rate": 1.030898285663371e-05, + "loss": 3.355, + "step": 2424320 + }, + { + "epoch": 0.02, + "learning_rate": 1.030059690912319e-05, + "loss": 3.3618, + "step": 2424832 + }, + { + "epoch": 0.02, + "learning_rate": 1.0292210961612671e-05, + "loss": 3.377, + "step": 2425344 + }, + { + "epoch": 0.02, + "learning_rate": 1.0283825014102151e-05, + "loss": 3.3531, + "step": 2425856 + }, + { + "epoch": 0.02, + "learning_rate": 1.027543906659163e-05, + "loss": 3.3464, + "step": 2426368 + }, + { + "epoch": 0.02, + "learning_rate": 1.0267069497884842e-05, + "loss": 3.3578, + "step": 2426880 + }, + { + "epoch": 0.02, + "learning_rate": 1.0258683550374322e-05, + "loss": 3.3523, + "step": 2427392 + }, + { + "epoch": 0.02, + "learning_rate": 1.02502976028638e-05, + "loss": 3.3508, + "step": 2427904 + }, + { + "epoch": 0.02, + "learning_rate": 1.0241911655353282e-05, + "loss": 3.3526, + "step": 2428416 + }, + { + "epoch": 0.02, + "learning_rate": 1.0233525707842762e-05, + "loss": 3.3512, + "step": 2428928 + }, + { + "epoch": 0.02, + "learning_rate": 1.0225139760332242e-05, + "loss": 3.364, + "step": 2429440 + }, + { + "epoch": 0.02, + "learning_rate": 1.0216770191625453e-05, + "loss": 3.3544, + "step": 2429952 + }, + { + "epoch": 0.02, + "learning_rate": 1.0208384244114933e-05, + "loss": 3.349, + "step": 2430464 + }, + { + "epoch": 0.02, + "learning_rate": 1.0199998296604413e-05, + "loss": 3.3526, + "step": 2430976 + }, + { + "epoch": 0.02, + "learning_rate": 1.0191612349093893e-05, + "loss": 3.3562, + "step": 2431488 + }, + { + "epoch": 0.02, + "learning_rate": 1.0183242780387103e-05, + "loss": 3.3505, + "step": 2432000 + }, + { + "epoch": 0.02, + "learning_rate": 1.0174856832876583e-05, + "loss": 3.3561, + "step": 2432512 + }, + { + "epoch": 0.02, + "learning_rate": 1.0166470885366063e-05, + "loss": 3.363, + "step": 2433024 + }, + { + "epoch": 0.02, + "learning_rate": 1.0158084937855543e-05, + "loss": 3.3521, + "step": 2433536 + }, + { + "epoch": 0.02, + "learning_rate": 1.0149698990345023e-05, + "loss": 3.3472, + "step": 2434048 + }, + { + "epoch": 0.02, + "learning_rate": 1.0141329421638236e-05, + "loss": 3.3573, + "step": 2434560 + }, + { + "epoch": 0.02, + "learning_rate": 1.0132943474127716e-05, + "loss": 3.3558, + "step": 2435072 + }, + { + "epoch": 0.02, + "learning_rate": 1.0124557526617194e-05, + "loss": 3.3537, + "step": 2435584 + }, + { + "epoch": 0.02, + "learning_rate": 1.0116171579106674e-05, + "loss": 3.3542, + "step": 2436096 + }, + { + "epoch": 0.02, + "learning_rate": 1.0107785631596155e-05, + "loss": 3.366, + "step": 2436608 + }, + { + "epoch": 0.02, + "learning_rate": 1.0099399684085634e-05, + "loss": 3.3609, + "step": 2437120 + }, + { + "epoch": 0.02, + "learning_rate": 1.0091013736575114e-05, + "loss": 3.3545, + "step": 2437632 + }, + { + "epoch": 0.02, + "learning_rate": 1.0082627789064594e-05, + "loss": 3.3543, + "step": 2438144 + }, + { + "epoch": 0.02, + "learning_rate": 1.0074258220357806e-05, + "loss": 3.3529, + "step": 2438656 + }, + { + "epoch": 0.02, + "learning_rate": 1.0065888651651017e-05, + "loss": 3.3562, + "step": 2439168 + }, + { + "epoch": 0.02, + "learning_rate": 1.0057502704140497e-05, + "loss": 3.3404, + "step": 2439680 + }, + { + "epoch": 0.02, + "learning_rate": 1.0049116756629977e-05, + "loss": 3.3655, + "step": 2440192 + }, + { + "epoch": 0.02, + "learning_rate": 1.0040730809119455e-05, + "loss": 3.3608, + "step": 2440704 + }, + { + "epoch": 0.02, + "learning_rate": 1.0032361240412668e-05, + "loss": 3.3573, + "step": 2441216 + }, + { + "epoch": 0.02, + "learning_rate": 1.0023975292902148e-05, + "loss": 3.3465, + "step": 2441728 + }, + { + "epoch": 0.03, + "learning_rate": 1.0015589345391627e-05, + "loss": 3.351, + "step": 2442240 + }, + { + "epoch": 0.03, + "eval_loss": 3.863635778427124, + "eval_runtime": 311.8998, + "eval_samples_per_second": 1223.441, + "eval_steps_per_second": 38.233, + "step": 2442240 + }, + { + "epoch": 1.0, + "learning_rate": 1.0007203397881107e-05, + "loss": 3.3412, + "step": 2442752 + }, + { + "epoch": 1.0, + "learning_rate": 9.998817450370587e-06, + "loss": 3.3516, + "step": 2443264 + }, + { + "epoch": 1.0, + "learning_rate": 9.990447881663798e-06, + "loss": 3.358, + "step": 2443776 + }, + { + "epoch": 1.0, + "learning_rate": 9.98206193415328e-06, + "loss": 3.3535, + "step": 2444288 + }, + { + "epoch": 1.0, + "learning_rate": 9.973675986642758e-06, + "loss": 3.3571, + "step": 2444800 + }, + { + "epoch": 1.0, + "learning_rate": 9.965290039132238e-06, + "loss": 3.3484, + "step": 2445312 + }, + { + "epoch": 1.0, + "learning_rate": 9.956904091621718e-06, + "loss": 3.3507, + "step": 2445824 + }, + { + "epoch": 1.0, + "learning_rate": 9.948534522914929e-06, + "loss": 3.3468, + "step": 2446336 + }, + { + "epoch": 1.0, + "learning_rate": 9.940148575404409e-06, + "loss": 3.3566, + "step": 2446848 + }, + { + "epoch": 1.0, + "learning_rate": 9.93176262789389e-06, + "loss": 3.3413, + "step": 2447360 + }, + { + "epoch": 1.0, + "learning_rate": 9.92337668038337e-06, + "loss": 3.3615, + "step": 2447872 + }, + { + "epoch": 1.0, + "learning_rate": 9.91500711167658e-06, + "loss": 3.366, + "step": 2448384 + }, + { + "epoch": 1.0, + "learning_rate": 9.906621164166061e-06, + "loss": 3.3446, + "step": 2448896 + }, + { + "epoch": 1.0, + "learning_rate": 9.898235216655541e-06, + "loss": 3.346, + "step": 2449408 + }, + { + "epoch": 1.0, + "learning_rate": 9.88984926914502e-06, + "loss": 3.3417, + "step": 2449920 + }, + { + "epoch": 1.0, + "learning_rate": 9.881463321634501e-06, + "loss": 3.3511, + "step": 2450432 + }, + { + "epoch": 1.0, + "learning_rate": 9.873077374123981e-06, + "loss": 3.3462, + "step": 2450944 + }, + { + "epoch": 1.0, + "learning_rate": 9.864691426613461e-06, + "loss": 3.3492, + "step": 2451456 + }, + { + "epoch": 1.0, + "learning_rate": 9.856321857906672e-06, + "loss": 3.3448, + "step": 2451968 + }, + { + "epoch": 1.0, + "learning_rate": 9.847935910396152e-06, + "loss": 3.3573, + "step": 2452480 + }, + { + "epoch": 1.0, + "learning_rate": 9.839566341689362e-06, + "loss": 3.3511, + "step": 2452992 + }, + { + "epoch": 1.0, + "learning_rate": 9.831180394178842e-06, + "loss": 3.3548, + "step": 2453504 + }, + { + "epoch": 1.0, + "learning_rate": 9.822794446668322e-06, + "loss": 3.3559, + "step": 2454016 + }, + { + "epoch": 1.0, + "learning_rate": 9.814408499157802e-06, + "loss": 3.3587, + "step": 2454528 + }, + { + "epoch": 1.0, + "learning_rate": 9.806022551647282e-06, + "loss": 3.3444, + "step": 2455040 + }, + { + "epoch": 1.0, + "learning_rate": 9.797636604136762e-06, + "loss": 3.3425, + "step": 2455552 + }, + { + "epoch": 1.0, + "learning_rate": 9.789267035429973e-06, + "loss": 3.3527, + "step": 2456064 + }, + { + "epoch": 1.0, + "learning_rate": 9.780881087919453e-06, + "loss": 3.3462, + "step": 2456576 + }, + { + "epoch": 1.0, + "learning_rate": 9.772495140408933e-06, + "loss": 3.3446, + "step": 2457088 + }, + { + "epoch": 1.01, + "learning_rate": 9.764109192898413e-06, + "loss": 3.3449, + "step": 2457600 + }, + { + "epoch": 1.01, + "learning_rate": 9.755723245387893e-06, + "loss": 3.3511, + "step": 2458112 + }, + { + "epoch": 1.01, + "learning_rate": 9.747353676681105e-06, + "loss": 3.3552, + "step": 2458624 + }, + { + "epoch": 1.01, + "learning_rate": 9.738967729170584e-06, + "loss": 3.3441, + "step": 2459136 + }, + { + "epoch": 1.01, + "learning_rate": 9.730581781660063e-06, + "loss": 3.3509, + "step": 2459648 + }, + { + "epoch": 1.01, + "learning_rate": 9.722195834149545e-06, + "loss": 3.3572, + "step": 2460160 + }, + { + "epoch": 1.01, + "learning_rate": 9.713826265442756e-06, + "loss": 3.3481, + "step": 2460672 + }, + { + "epoch": 1.01, + "learning_rate": 9.705440317932236e-06, + "loss": 3.3363, + "step": 2461184 + }, + { + "epoch": 1.01, + "learning_rate": 9.697054370421716e-06, + "loss": 3.3571, + "step": 2461696 + }, + { + "epoch": 1.01, + "learning_rate": 9.688668422911196e-06, + "loss": 3.3396, + "step": 2462208 + }, + { + "epoch": 1.01, + "learning_rate": 9.680282475400674e-06, + "loss": 3.3379, + "step": 2462720 + }, + { + "epoch": 1.01, + "learning_rate": 9.671896527890156e-06, + "loss": 3.348, + "step": 2463232 + }, + { + "epoch": 1.01, + "learning_rate": 9.663510580379636e-06, + "loss": 3.3579, + "step": 2463744 + }, + { + "epoch": 1.01, + "learning_rate": 9.655141011672846e-06, + "loss": 3.3505, + "step": 2464256 + }, + { + "epoch": 1.01, + "learning_rate": 9.646771442966057e-06, + "loss": 3.3518, + "step": 2464768 + }, + { + "epoch": 1.01, + "learning_rate": 9.638385495455537e-06, + "loss": 3.3571, + "step": 2465280 + }, + { + "epoch": 1.01, + "learning_rate": 9.629999547945017e-06, + "loss": 3.3536, + "step": 2465792 + }, + { + "epoch": 1.01, + "learning_rate": 9.621613600434497e-06, + "loss": 3.3475, + "step": 2466304 + }, + { + "epoch": 1.01, + "learning_rate": 9.613227652923977e-06, + "loss": 3.3312, + "step": 2466816 + }, + { + "epoch": 1.01, + "learning_rate": 9.604841705413457e-06, + "loss": 3.3505, + "step": 2467328 + }, + { + "epoch": 1.01, + "learning_rate": 9.596455757902937e-06, + "loss": 3.3542, + "step": 2467840 + }, + { + "epoch": 1.01, + "learning_rate": 9.588086189196148e-06, + "loss": 3.3452, + "step": 2468352 + }, + { + "epoch": 1.01, + "learning_rate": 9.579700241685628e-06, + "loss": 3.3393, + "step": 2468864 + }, + { + "epoch": 1.01, + "learning_rate": 9.57131429417511e-06, + "loss": 3.3397, + "step": 2469376 + }, + { + "epoch": 1.01, + "learning_rate": 9.562928346664588e-06, + "loss": 3.3423, + "step": 2469888 + }, + { + "epoch": 1.01, + "learning_rate": 9.554542399154068e-06, + "loss": 3.33, + "step": 2470400 + }, + { + "epoch": 1.01, + "learning_rate": 9.54617283044728e-06, + "loss": 3.3529, + "step": 2470912 + }, + { + "epoch": 1.01, + "learning_rate": 9.53778688293676e-06, + "loss": 3.3385, + "step": 2471424 + }, + { + "epoch": 1.01, + "learning_rate": 9.529400935426238e-06, + "loss": 3.3551, + "step": 2471936 + }, + { + "epoch": 1.01, + "learning_rate": 9.521014987915718e-06, + "loss": 3.3467, + "step": 2472448 + }, + { + "epoch": 1.01, + "learning_rate": 9.5126290404052e-06, + "loss": 3.3327, + "step": 2472960 + }, + { + "epoch": 1.01, + "learning_rate": 9.504243092894678e-06, + "loss": 3.3489, + "step": 2473472 + }, + { + "epoch": 1.01, + "learning_rate": 9.49587352418789e-06, + "loss": 3.3436, + "step": 2473984 + }, + { + "epoch": 1.01, + "learning_rate": 9.48748757667737e-06, + "loss": 3.3395, + "step": 2474496 + }, + { + "epoch": 1.01, + "learning_rate": 9.47910162916685e-06, + "loss": 3.3337, + "step": 2475008 + }, + { + "epoch": 1.01, + "learning_rate": 9.470715681656329e-06, + "loss": 3.3566, + "step": 2475520 + }, + { + "epoch": 1.01, + "learning_rate": 9.46232973414581e-06, + "loss": 3.3458, + "step": 2476032 + }, + { + "epoch": 1.01, + "learning_rate": 9.45394378663529e-06, + "loss": 3.3386, + "step": 2476544 + }, + { + "epoch": 1.01, + "learning_rate": 9.445557839124769e-06, + "loss": 3.3289, + "step": 2477056 + }, + { + "epoch": 1.01, + "learning_rate": 9.437188270417981e-06, + "loss": 3.3395, + "step": 2477568 + }, + { + "epoch": 1.01, + "learning_rate": 9.428802322907461e-06, + "loss": 3.3481, + "step": 2478080 + }, + { + "epoch": 1.01, + "learning_rate": 9.420416375396941e-06, + "loss": 3.357, + "step": 2478592 + }, + { + "epoch": 1.01, + "learning_rate": 9.412030427886421e-06, + "loss": 3.3445, + "step": 2479104 + }, + { + "epoch": 1.01, + "learning_rate": 9.403660859179632e-06, + "loss": 3.3569, + "step": 2479616 + }, + { + "epoch": 1.01, + "learning_rate": 9.395274911669112e-06, + "loss": 3.3536, + "step": 2480128 + }, + { + "epoch": 1.01, + "learning_rate": 9.386905342962324e-06, + "loss": 3.3483, + "step": 2480640 + }, + { + "epoch": 1.01, + "learning_rate": 9.378519395451803e-06, + "loss": 3.3449, + "step": 2481152 + }, + { + "epoch": 1.01, + "learning_rate": 9.370133447941282e-06, + "loss": 3.3494, + "step": 2481664 + }, + { + "epoch": 1.01, + "learning_rate": 9.361747500430764e-06, + "loss": 3.3455, + "step": 2482176 + }, + { + "epoch": 1.01, + "learning_rate": 9.353361552920242e-06, + "loss": 3.3445, + "step": 2482688 + }, + { + "epoch": 1.01, + "learning_rate": 9.344975605409722e-06, + "loss": 3.3433, + "step": 2483200 + }, + { + "epoch": 1.01, + "learning_rate": 9.336606036702935e-06, + "loss": 3.3488, + "step": 2483712 + }, + { + "epoch": 1.01, + "learning_rate": 9.328220089192415e-06, + "loss": 3.353, + "step": 2484224 + }, + { + "epoch": 1.01, + "learning_rate": 9.319834141681893e-06, + "loss": 3.3485, + "step": 2484736 + }, + { + "epoch": 1.01, + "learning_rate": 9.311448194171373e-06, + "loss": 3.3398, + "step": 2485248 + }, + { + "epoch": 1.01, + "learning_rate": 9.303078625464585e-06, + "loss": 3.3428, + "step": 2485760 + }, + { + "epoch": 1.01, + "learning_rate": 9.294692677954065e-06, + "loss": 3.3509, + "step": 2486272 + }, + { + "epoch": 1.01, + "learning_rate": 9.286306730443545e-06, + "loss": 3.3475, + "step": 2486784 + }, + { + "epoch": 1.01, + "learning_rate": 9.277920782933025e-06, + "loss": 3.3418, + "step": 2487296 + }, + { + "epoch": 1.01, + "learning_rate": 9.269551214226236e-06, + "loss": 3.3447, + "step": 2487808 + }, + { + "epoch": 1.02, + "learning_rate": 9.261165266715716e-06, + "loss": 3.3533, + "step": 2488320 + }, + { + "epoch": 1.02, + "learning_rate": 9.252779319205196e-06, + "loss": 3.3379, + "step": 2488832 + }, + { + "epoch": 1.02, + "learning_rate": 9.244393371694676e-06, + "loss": 3.3459, + "step": 2489344 + }, + { + "epoch": 1.02, + "learning_rate": 9.236023802987889e-06, + "loss": 3.3424, + "step": 2489856 + }, + { + "epoch": 1.02, + "learning_rate": 9.227637855477367e-06, + "loss": 3.3516, + "step": 2490368 + }, + { + "epoch": 1.02, + "learning_rate": 9.219251907966847e-06, + "loss": 3.3476, + "step": 2490880 + }, + { + "epoch": 1.02, + "learning_rate": 9.210865960456327e-06, + "loss": 3.3474, + "step": 2491392 + }, + { + "epoch": 1.02, + "learning_rate": 9.202480012945807e-06, + "loss": 3.338, + "step": 2491904 + }, + { + "epoch": 1.02, + "learning_rate": 9.194110444239017e-06, + "loss": 3.3452, + "step": 2492416 + }, + { + "epoch": 1.02, + "learning_rate": 9.185724496728499e-06, + "loss": 3.3451, + "step": 2492928 + }, + { + "epoch": 1.02, + "learning_rate": 9.177338549217979e-06, + "loss": 3.3548, + "step": 2493440 + }, + { + "epoch": 1.02, + "learning_rate": 9.168952601707457e-06, + "loss": 3.3492, + "step": 2493952 + }, + { + "epoch": 1.02, + "learning_rate": 9.160566654196937e-06, + "loss": 3.3373, + "step": 2494464 + }, + { + "epoch": 1.02, + "learning_rate": 9.15219708549015e-06, + "loss": 3.3383, + "step": 2494976 + }, + { + "epoch": 1.02, + "learning_rate": 9.143811137979628e-06, + "loss": 3.3511, + "step": 2495488 + }, + { + "epoch": 1.02, + "learning_rate": 9.135425190469108e-06, + "loss": 3.3259, + "step": 2496000 + }, + { + "epoch": 1.02, + "learning_rate": 9.12703924295859e-06, + "loss": 3.3389, + "step": 2496512 + }, + { + "epoch": 1.02, + "learning_rate": 9.1186696742518e-06, + "loss": 3.3463, + "step": 2497024 + }, + { + "epoch": 1.02, + "learning_rate": 9.11028372674128e-06, + "loss": 3.3426, + "step": 2497536 + }, + { + "epoch": 1.02, + "learning_rate": 9.10189777923076e-06, + "loss": 3.33, + "step": 2498048 + }, + { + "epoch": 1.02, + "learning_rate": 9.09351183172024e-06, + "loss": 3.3481, + "step": 2498560 + }, + { + "epoch": 1.02, + "learning_rate": 9.085125884209719e-06, + "loss": 3.3314, + "step": 2499072 + }, + { + "epoch": 1.02, + "learning_rate": 9.0767399366992e-06, + "loss": 3.3556, + "step": 2499584 + }, + { + "epoch": 1.02, + "learning_rate": 9.06835398918868e-06, + "loss": 3.3375, + "step": 2500096 + }, + { + "epoch": 1.02, + "learning_rate": 9.059984420481891e-06, + "loss": 3.3475, + "step": 2500608 + }, + { + "epoch": 1.02, + "learning_rate": 9.051598472971371e-06, + "loss": 3.3524, + "step": 2501120 + }, + { + "epoch": 1.02, + "learning_rate": 9.04321252546085e-06, + "loss": 3.367, + "step": 2501632 + }, + { + "epoch": 1.02, + "learning_rate": 9.03482657795033e-06, + "loss": 3.3412, + "step": 2502144 + }, + { + "epoch": 1.02, + "learning_rate": 9.02644063043981e-06, + "loss": 3.34, + "step": 2502656 + }, + { + "epoch": 1.02, + "learning_rate": 9.018071061733022e-06, + "loss": 3.3486, + "step": 2503168 + }, + { + "epoch": 1.02, + "learning_rate": 9.009685114222501e-06, + "loss": 3.3359, + "step": 2503680 + }, + { + "epoch": 1.02, + "learning_rate": 9.001299166711981e-06, + "loss": 3.3476, + "step": 2504192 + }, + { + "epoch": 1.02, + "learning_rate": 8.992913219201461e-06, + "loss": 3.3437, + "step": 2504704 + }, + { + "epoch": 1.02, + "learning_rate": 8.984527271690941e-06, + "loss": 3.3392, + "step": 2505216 + }, + { + "epoch": 1.02, + "learning_rate": 8.976157702984154e-06, + "loss": 3.3594, + "step": 2505728 + }, + { + "epoch": 1.02, + "learning_rate": 8.967771755473634e-06, + "loss": 3.3436, + "step": 2506240 + }, + { + "epoch": 1.02, + "learning_rate": 8.959385807963112e-06, + "loss": 3.3391, + "step": 2506752 + }, + { + "epoch": 1.02, + "learning_rate": 8.950999860452592e-06, + "loss": 3.3401, + "step": 2507264 + }, + { + "epoch": 1.02, + "learning_rate": 8.942613912942074e-06, + "loss": 3.3462, + "step": 2507776 + }, + { + "epoch": 1.02, + "learning_rate": 8.934244344235283e-06, + "loss": 3.3403, + "step": 2508288 + }, + { + "epoch": 1.02, + "learning_rate": 8.925858396724764e-06, + "loss": 3.3503, + "step": 2508800 + }, + { + "epoch": 1.02, + "learning_rate": 8.917472449214244e-06, + "loss": 3.3551, + "step": 2509312 + }, + { + "epoch": 1.02, + "learning_rate": 8.909086501703724e-06, + "loss": 3.3423, + "step": 2509824 + }, + { + "epoch": 1.02, + "learning_rate": 8.900700554193203e-06, + "loss": 3.3345, + "step": 2510336 + }, + { + "epoch": 1.02, + "learning_rate": 8.892330985486415e-06, + "loss": 3.3454, + "step": 2510848 + }, + { + "epoch": 1.02, + "learning_rate": 8.883945037975895e-06, + "loss": 3.3467, + "step": 2511360 + }, + { + "epoch": 1.02, + "learning_rate": 8.875559090465373e-06, + "loss": 3.3467, + "step": 2511872 + }, + { + "epoch": 1.02, + "learning_rate": 8.867173142954855e-06, + "loss": 3.3447, + "step": 2512384 + }, + { + "epoch": 1.02, + "learning_rate": 8.858803574248066e-06, + "loss": 3.3564, + "step": 2512896 + }, + { + "epoch": 1.02, + "learning_rate": 8.850417626737546e-06, + "loss": 3.35, + "step": 2513408 + }, + { + "epoch": 1.02, + "learning_rate": 8.842031679227026e-06, + "loss": 3.3462, + "step": 2513920 + }, + { + "epoch": 1.02, + "learning_rate": 8.833645731716506e-06, + "loss": 3.3475, + "step": 2514432 + }, + { + "epoch": 1.02, + "learning_rate": 8.825259784205986e-06, + "loss": 3.3443, + "step": 2514944 + }, + { + "epoch": 1.02, + "learning_rate": 8.816873836695465e-06, + "loss": 3.3492, + "step": 2515456 + }, + { + "epoch": 1.02, + "learning_rate": 8.808504267988676e-06, + "loss": 3.3281, + "step": 2515968 + }, + { + "epoch": 1.02, + "learning_rate": 8.800118320478156e-06, + "loss": 3.3543, + "step": 2516480 + }, + { + "epoch": 1.02, + "learning_rate": 8.791732372967638e-06, + "loss": 3.3527, + "step": 2516992 + }, + { + "epoch": 1.02, + "learning_rate": 8.783346425457116e-06, + "loss": 3.3487, + "step": 2517504 + }, + { + "epoch": 1.02, + "learning_rate": 8.774960477946596e-06, + "loss": 3.3378, + "step": 2518016 + }, + { + "epoch": 1.02, + "learning_rate": 8.766574530436076e-06, + "loss": 3.3426, + "step": 2518528 + }, + { + "epoch": 1.03, + "eval_loss": 3.8638408184051514, + "eval_runtime": 316.1143, + "eval_samples_per_second": 1207.13, + "eval_steps_per_second": 37.724, + "step": 2518560 + }, + { + "epoch": 0.0, + "learning_rate": 8.758188582925556e-06, + "loss": 3.3312, + "step": 2519040 + }, + { + "epoch": 0.0, + "learning_rate": 8.749819014218767e-06, + "loss": 3.3452, + "step": 2519552 + }, + { + "epoch": 0.0, + "learning_rate": 8.741433066708247e-06, + "loss": 3.3491, + "step": 2520064 + }, + { + "epoch": 0.0, + "learning_rate": 8.733047119197728e-06, + "loss": 3.3409, + "step": 2520576 + }, + { + "epoch": 0.0, + "learning_rate": 8.724661171687207e-06, + "loss": 3.3479, + "step": 2521088 + }, + { + "epoch": 0.0, + "learning_rate": 8.716275224176687e-06, + "loss": 3.3385, + "step": 2521600 + }, + { + "epoch": 0.0, + "learning_rate": 8.707905655469899e-06, + "loss": 3.3399, + "step": 2522112 + }, + { + "epoch": 0.0, + "learning_rate": 8.699519707959379e-06, + "loss": 3.3389, + "step": 2522624 + }, + { + "epoch": 0.0, + "learning_rate": 8.691133760448857e-06, + "loss": 3.3469, + "step": 2523136 + }, + { + "epoch": 0.0, + "learning_rate": 8.682747812938339e-06, + "loss": 3.3375, + "step": 2523648 + }, + { + "epoch": 0.0, + "learning_rate": 8.67437824423155e-06, + "loss": 3.3509, + "step": 2524160 + }, + { + "epoch": 0.0, + "learning_rate": 8.665992296721028e-06, + "loss": 3.3553, + "step": 2524672 + }, + { + "epoch": 0.0, + "learning_rate": 8.65760634921051e-06, + "loss": 3.3372, + "step": 2525184 + }, + { + "epoch": 0.0, + "learning_rate": 8.64922040169999e-06, + "loss": 3.3354, + "step": 2525696 + }, + { + "epoch": 0.0, + "learning_rate": 8.64083445418947e-06, + "loss": 3.3379, + "step": 2526208 + }, + { + "epoch": 0.0, + "learning_rate": 8.63244850667895e-06, + "loss": 3.3374, + "step": 2526720 + }, + { + "epoch": 0.0, + "learning_rate": 8.62406255916843e-06, + "loss": 3.3326, + "step": 2527232 + }, + { + "epoch": 0.0, + "learning_rate": 8.61567661165791e-06, + "loss": 3.3421, + "step": 2527744 + }, + { + "epoch": 0.0, + "learning_rate": 8.60730704295112e-06, + "loss": 3.3336, + "step": 2528256 + }, + { + "epoch": 0.0, + "learning_rate": 8.5989210954406e-06, + "loss": 3.3506, + "step": 2528768 + }, + { + "epoch": 0.0, + "learning_rate": 8.59053514793008e-06, + "loss": 3.3403, + "step": 2529280 + }, + { + "epoch": 0.0, + "learning_rate": 8.582149200419558e-06, + "loss": 3.3454, + "step": 2529792 + }, + { + "epoch": 0.0, + "learning_rate": 8.573779631712771e-06, + "loss": 3.3464, + "step": 2530304 + }, + { + "epoch": 0.0, + "learning_rate": 8.565393684202251e-06, + "loss": 3.3526, + "step": 2530816 + }, + { + "epoch": 0.0, + "learning_rate": 8.55700773669173e-06, + "loss": 3.3313, + "step": 2531328 + }, + { + "epoch": 0.0, + "learning_rate": 8.54862178918121e-06, + "loss": 3.3392, + "step": 2531840 + }, + { + "epoch": 0.0, + "learning_rate": 8.540268599278154e-06, + "loss": 3.3397, + "step": 2532352 + }, + { + "epoch": 0.0, + "learning_rate": 8.531882651767634e-06, + "loss": 3.338, + "step": 2532864 + }, + { + "epoch": 0.0, + "learning_rate": 8.523496704257114e-06, + "loss": 3.334, + "step": 2533376 + }, + { + "epoch": 0.01, + "learning_rate": 8.515110756746592e-06, + "loss": 3.3373, + "step": 2533888 + }, + { + "epoch": 0.01, + "learning_rate": 8.506724809236074e-06, + "loss": 3.3443, + "step": 2534400 + }, + { + "epoch": 0.01, + "learning_rate": 8.498355240529285e-06, + "loss": 3.3435, + "step": 2534912 + }, + { + "epoch": 0.01, + "learning_rate": 8.489969293018765e-06, + "loss": 3.3337, + "step": 2535424 + }, + { + "epoch": 0.01, + "learning_rate": 8.481583345508245e-06, + "loss": 3.3451, + "step": 2535936 + }, + { + "epoch": 0.01, + "learning_rate": 8.473197397997725e-06, + "loss": 3.3484, + "step": 2536448 + }, + { + "epoch": 0.01, + "learning_rate": 8.464811450487205e-06, + "loss": 3.3392, + "step": 2536960 + }, + { + "epoch": 0.01, + "learning_rate": 8.456425502976684e-06, + "loss": 3.3263, + "step": 2537472 + }, + { + "epoch": 0.01, + "learning_rate": 8.448039555466164e-06, + "loss": 3.343, + "step": 2537984 + }, + { + "epoch": 0.01, + "learning_rate": 8.439669986759375e-06, + "loss": 3.3293, + "step": 2538496 + }, + { + "epoch": 0.01, + "learning_rate": 8.431284039248855e-06, + "loss": 3.3324, + "step": 2539008 + }, + { + "epoch": 0.01, + "learning_rate": 8.422898091738335e-06, + "loss": 3.3355, + "step": 2539520 + }, + { + "epoch": 0.01, + "learning_rate": 8.414512144227815e-06, + "loss": 3.3518, + "step": 2540032 + }, + { + "epoch": 0.01, + "learning_rate": 8.406126196717295e-06, + "loss": 3.3401, + "step": 2540544 + }, + { + "epoch": 0.01, + "learning_rate": 8.397740249206775e-06, + "loss": 3.3439, + "step": 2541056 + }, + { + "epoch": 0.01, + "learning_rate": 8.389370680499986e-06, + "loss": 3.348, + "step": 2541568 + }, + { + "epoch": 0.01, + "learning_rate": 8.380984732989466e-06, + "loss": 3.3439, + "step": 2542080 + }, + { + "epoch": 0.01, + "learning_rate": 8.372598785478947e-06, + "loss": 3.3397, + "step": 2542592 + }, + { + "epoch": 0.01, + "learning_rate": 8.364212837968426e-06, + "loss": 3.324, + "step": 2543104 + }, + { + "epoch": 0.01, + "learning_rate": 8.355826890457906e-06, + "loss": 3.3419, + "step": 2543616 + }, + { + "epoch": 0.01, + "learning_rate": 8.347440942947386e-06, + "loss": 3.344, + "step": 2544128 + }, + { + "epoch": 0.01, + "learning_rate": 8.339071374240596e-06, + "loss": 3.3389, + "step": 2544640 + }, + { + "epoch": 0.01, + "learning_rate": 8.330685426730076e-06, + "loss": 3.3361, + "step": 2545152 + }, + { + "epoch": 0.01, + "learning_rate": 8.322299479219558e-06, + "loss": 3.3243, + "step": 2545664 + }, + { + "epoch": 0.01, + "learning_rate": 8.313913531709038e-06, + "loss": 3.3372, + "step": 2546176 + }, + { + "epoch": 0.01, + "learning_rate": 8.305527584198516e-06, + "loss": 3.3217, + "step": 2546688 + }, + { + "epoch": 0.01, + "learning_rate": 8.297158015491729e-06, + "loss": 3.3407, + "step": 2547200 + }, + { + "epoch": 0.01, + "learning_rate": 8.288772067981209e-06, + "loss": 3.3306, + "step": 2547712 + }, + { + "epoch": 0.01, + "learning_rate": 8.280386120470687e-06, + "loss": 3.3436, + "step": 2548224 + }, + { + "epoch": 0.01, + "learning_rate": 8.272000172960167e-06, + "loss": 3.3426, + "step": 2548736 + }, + { + "epoch": 0.01, + "learning_rate": 8.263614225449648e-06, + "loss": 3.3229, + "step": 2549248 + }, + { + "epoch": 0.01, + "learning_rate": 8.255228277939128e-06, + "loss": 3.3383, + "step": 2549760 + }, + { + "epoch": 0.01, + "learning_rate": 8.24685870923234e-06, + "loss": 3.3371, + "step": 2550272 + }, + { + "epoch": 0.01, + "learning_rate": 8.23847276172182e-06, + "loss": 3.3294, + "step": 2550784 + }, + { + "epoch": 0.01, + "learning_rate": 8.2300868142113e-06, + "loss": 3.3271, + "step": 2551296 + }, + { + "epoch": 0.01, + "learning_rate": 8.221700866700777e-06, + "loss": 3.3438, + "step": 2551808 + }, + { + "epoch": 0.01, + "learning_rate": 8.213314919190259e-06, + "loss": 3.3396, + "step": 2552320 + }, + { + "epoch": 0.01, + "learning_rate": 8.204928971679739e-06, + "loss": 3.3269, + "step": 2552832 + }, + { + "epoch": 0.01, + "learning_rate": 8.196543024169219e-06, + "loss": 3.3202, + "step": 2553344 + }, + { + "epoch": 0.01, + "learning_rate": 8.18817345546243e-06, + "loss": 3.3325, + "step": 2553856 + }, + { + "epoch": 0.01, + "learning_rate": 8.17978750795191e-06, + "loss": 3.3386, + "step": 2554368 + }, + { + "epoch": 0.01, + "learning_rate": 8.17140156044139e-06, + "loss": 3.3459, + "step": 2554880 + }, + { + "epoch": 0.01, + "learning_rate": 8.16301561293087e-06, + "loss": 3.3368, + "step": 2555392 + }, + { + "epoch": 0.01, + "learning_rate": 8.15464604422408e-06, + "loss": 3.348, + "step": 2555904 + }, + { + "epoch": 0.01, + "learning_rate": 8.146276475517293e-06, + "loss": 3.3423, + "step": 2556416 + }, + { + "epoch": 0.01, + "learning_rate": 8.137890528006773e-06, + "loss": 3.3426, + "step": 2556928 + }, + { + "epoch": 0.01, + "learning_rate": 8.129504580496251e-06, + "loss": 3.3323, + "step": 2557440 + }, + { + "epoch": 0.01, + "learning_rate": 8.121118632985731e-06, + "loss": 3.3435, + "step": 2557952 + }, + { + "epoch": 0.01, + "learning_rate": 8.112732685475213e-06, + "loss": 3.3376, + "step": 2558464 + }, + { + "epoch": 0.01, + "learning_rate": 8.104363116768424e-06, + "loss": 3.3357, + "step": 2558976 + }, + { + "epoch": 0.01, + "learning_rate": 8.095977169257902e-06, + "loss": 3.3365, + "step": 2559488 + }, + { + "epoch": 0.01, + "learning_rate": 8.087591221747383e-06, + "loss": 3.3364, + "step": 2560000 + }, + { + "epoch": 0.01, + "learning_rate": 8.079205274236863e-06, + "loss": 3.3484, + "step": 2560512 + }, + { + "epoch": 0.01, + "learning_rate": 8.070819326726342e-06, + "loss": 3.3345, + "step": 2561024 + }, + { + "epoch": 0.01, + "learning_rate": 8.062433379215822e-06, + "loss": 3.3317, + "step": 2561536 + }, + { + "epoch": 0.01, + "learning_rate": 8.054047431705303e-06, + "loss": 3.3347, + "step": 2562048 + }, + { + "epoch": 0.01, + "learning_rate": 8.045661484194783e-06, + "loss": 3.3416, + "step": 2562560 + }, + { + "epoch": 0.01, + "learning_rate": 8.037291915487994e-06, + "loss": 3.3399, + "step": 2563072 + }, + { + "epoch": 0.01, + "learning_rate": 8.028922346781205e-06, + "loss": 3.3352, + "step": 2563584 + }, + { + "epoch": 0.01, + "learning_rate": 8.020536399270685e-06, + "loss": 3.3328, + "step": 2564096 + }, + { + "epoch": 0.02, + "learning_rate": 8.012150451760166e-06, + "loss": 3.3459, + "step": 2564608 + }, + { + "epoch": 0.02, + "learning_rate": 8.003764504249645e-06, + "loss": 3.3287, + "step": 2565120 + }, + { + "epoch": 0.02, + "learning_rate": 7.995378556739125e-06, + "loss": 3.334, + "step": 2565632 + }, + { + "epoch": 0.02, + "learning_rate": 7.987008988032337e-06, + "loss": 3.3288, + "step": 2566144 + }, + { + "epoch": 0.02, + "learning_rate": 7.978623040521815e-06, + "loss": 3.3438, + "step": 2566656 + }, + { + "epoch": 0.02, + "learning_rate": 7.970237093011295e-06, + "loss": 3.341, + "step": 2567168 + }, + { + "epoch": 0.02, + "learning_rate": 7.961851145500775e-06, + "loss": 3.3391, + "step": 2567680 + }, + { + "epoch": 0.02, + "learning_rate": 7.953465197990255e-06, + "loss": 3.3269, + "step": 2568192 + }, + { + "epoch": 0.02, + "learning_rate": 7.945095629283466e-06, + "loss": 3.339, + "step": 2568704 + }, + { + "epoch": 0.02, + "learning_rate": 7.936709681772948e-06, + "loss": 3.3371, + "step": 2569216 + }, + { + "epoch": 0.02, + "learning_rate": 7.928323734262428e-06, + "loss": 3.3453, + "step": 2569728 + }, + { + "epoch": 0.02, + "learning_rate": 7.919937786751906e-06, + "loss": 3.3382, + "step": 2570240 + }, + { + "epoch": 0.02, + "learning_rate": 7.911551839241386e-06, + "loss": 3.33, + "step": 2570752 + }, + { + "epoch": 0.02, + "learning_rate": 7.903182270534598e-06, + "loss": 3.3279, + "step": 2571264 + }, + { + "epoch": 0.02, + "learning_rate": 7.894796323024078e-06, + "loss": 3.3406, + "step": 2571776 + }, + { + "epoch": 0.02, + "learning_rate": 7.886410375513557e-06, + "loss": 3.3152, + "step": 2572288 + }, + { + "epoch": 0.02, + "learning_rate": 7.878024428003038e-06, + "loss": 3.3324, + "step": 2572800 + }, + { + "epoch": 0.02, + "learning_rate": 7.869654859296249e-06, + "loss": 3.3356, + "step": 2573312 + }, + { + "epoch": 0.02, + "learning_rate": 7.861268911785729e-06, + "loss": 3.3323, + "step": 2573824 + }, + { + "epoch": 0.02, + "learning_rate": 7.852882964275209e-06, + "loss": 3.3216, + "step": 2574336 + }, + { + "epoch": 0.02, + "learning_rate": 7.844497016764689e-06, + "loss": 3.3383, + "step": 2574848 + }, + { + "epoch": 0.02, + "learning_rate": 7.836111069254169e-06, + "loss": 3.3267, + "step": 2575360 + }, + { + "epoch": 0.02, + "learning_rate": 7.82774150054738e-06, + "loss": 3.3416, + "step": 2575872 + }, + { + "epoch": 0.02, + "learning_rate": 7.81935555303686e-06, + "loss": 3.3333, + "step": 2576384 + }, + { + "epoch": 0.02, + "learning_rate": 7.81096960552634e-06, + "loss": 3.3318, + "step": 2576896 + }, + { + "epoch": 0.02, + "learning_rate": 7.80258365801582e-06, + "loss": 3.347, + "step": 2577408 + }, + { + "epoch": 0.02, + "learning_rate": 7.7941977105053e-06, + "loss": 3.3565, + "step": 2577920 + }, + { + "epoch": 0.02, + "learning_rate": 7.78582814179851e-06, + "loss": 3.3328, + "step": 2578432 + }, + { + "epoch": 0.02, + "learning_rate": 7.777442194287992e-06, + "loss": 3.3308, + "step": 2578944 + }, + { + "epoch": 0.02, + "learning_rate": 7.76905624677747e-06, + "loss": 3.3429, + "step": 2579456 + }, + { + "epoch": 0.02, + "learning_rate": 7.76067029926695e-06, + "loss": 3.3297, + "step": 2579968 + }, + { + "epoch": 0.02, + "learning_rate": 7.75228435175643e-06, + "loss": 3.3326, + "step": 2580480 + }, + { + "epoch": 0.02, + "learning_rate": 7.743914783049643e-06, + "loss": 3.3385, + "step": 2580992 + }, + { + "epoch": 0.02, + "learning_rate": 7.73552883553912e-06, + "loss": 3.3286, + "step": 2581504 + }, + { + "epoch": 0.02, + "learning_rate": 7.727142888028602e-06, + "loss": 3.3463, + "step": 2582016 + }, + { + "epoch": 0.02, + "learning_rate": 7.718756940518082e-06, + "loss": 3.3345, + "step": 2582528 + }, + { + "epoch": 0.02, + "learning_rate": 7.71037099300756e-06, + "loss": 3.3352, + "step": 2583040 + }, + { + "epoch": 0.02, + "learning_rate": 7.70198504549704e-06, + "loss": 3.329, + "step": 2583552 + }, + { + "epoch": 0.02, + "learning_rate": 7.693599097986522e-06, + "loss": 3.3348, + "step": 2584064 + }, + { + "epoch": 0.02, + "learning_rate": 7.685229529279733e-06, + "loss": 3.3321, + "step": 2584576 + }, + { + "epoch": 0.02, + "learning_rate": 7.676843581769213e-06, + "loss": 3.3419, + "step": 2585088 + }, + { + "epoch": 0.02, + "learning_rate": 7.668457634258693e-06, + "loss": 3.3458, + "step": 2585600 + }, + { + "epoch": 0.02, + "learning_rate": 7.660071686748173e-06, + "loss": 3.3349, + "step": 2586112 + }, + { + "epoch": 0.02, + "learning_rate": 7.651702118041384e-06, + "loss": 3.3224, + "step": 2586624 + }, + { + "epoch": 0.02, + "learning_rate": 7.643316170530864e-06, + "loss": 3.3405, + "step": 2587136 + }, + { + "epoch": 0.02, + "learning_rate": 7.634930223020344e-06, + "loss": 3.3352, + "step": 2587648 + }, + { + "epoch": 0.02, + "learning_rate": 7.626544275509824e-06, + "loss": 3.3387, + "step": 2588160 + }, + { + "epoch": 0.02, + "learning_rate": 7.618158327999303e-06, + "loss": 3.335, + "step": 2588672 + }, + { + "epoch": 0.02, + "learning_rate": 7.609788759292514e-06, + "loss": 3.3432, + "step": 2589184 + }, + { + "epoch": 0.02, + "learning_rate": 7.601402811781995e-06, + "loss": 3.3392, + "step": 2589696 + }, + { + "epoch": 0.02, + "learning_rate": 7.593016864271474e-06, + "loss": 3.343, + "step": 2590208 + }, + { + "epoch": 0.02, + "learning_rate": 7.584630916760954e-06, + "loss": 3.3342, + "step": 2590720 + }, + { + "epoch": 0.02, + "learning_rate": 7.576244969250434e-06, + "loss": 3.3322, + "step": 2591232 + }, + { + "epoch": 0.02, + "learning_rate": 7.567875400543646e-06, + "loss": 3.3415, + "step": 2591744 + }, + { + "epoch": 0.02, + "learning_rate": 7.559489453033125e-06, + "loss": 3.3241, + "step": 2592256 + }, + { + "epoch": 0.02, + "learning_rate": 7.551103505522606e-06, + "loss": 3.3418, + "step": 2592768 + }, + { + "epoch": 0.02, + "learning_rate": 7.542717558012086e-06, + "loss": 3.3494, + "step": 2593280 + }, + { + "epoch": 0.02, + "learning_rate": 7.534331610501565e-06, + "loss": 3.3372, + "step": 2593792 + }, + { + "epoch": 0.02, + "learning_rate": 7.525945662991045e-06, + "loss": 3.3251, + "step": 2594304 + }, + { + "epoch": 0.02, + "learning_rate": 7.5175597154805255e-06, + "loss": 3.3328, + "step": 2594816 + }, + { + "epoch": 0.03, + "eval_loss": 3.864424228668213, + "eval_runtime": 310.5561, + "eval_samples_per_second": 1228.734, + "eval_steps_per_second": 38.399, + "step": 2594880 + }, + { + "epoch": 0.0, + "learning_rate": 7.5091737679700055e-06, + "loss": 3.3232, + "step": 2595328 + }, + { + "epoch": 0.0, + "learning_rate": 7.5007878204594846e-06, + "loss": 3.3346, + "step": 2595840 + }, + { + "epoch": 0.0, + "learning_rate": 7.492418251752696e-06, + "loss": 3.3384, + "step": 2596352 + }, + { + "epoch": 0.0, + "learning_rate": 7.484032304242176e-06, + "loss": 3.3342, + "step": 2596864 + }, + { + "epoch": 0.0, + "learning_rate": 7.475646356731655e-06, + "loss": 3.3401, + "step": 2597376 + }, + { + "epoch": 0.0, + "learning_rate": 7.467260409221136e-06, + "loss": 3.3284, + "step": 2597888 + }, + { + "epoch": 0.0, + "learning_rate": 7.458874461710616e-06, + "loss": 3.3376, + "step": 2598400 + }, + { + "epoch": 0.0, + "learning_rate": 7.450504893003828e-06, + "loss": 3.3263, + "step": 2598912 + }, + { + "epoch": 0.0, + "learning_rate": 7.442118945493307e-06, + "loss": 3.3345, + "step": 2599424 + }, + { + "epoch": 0.0, + "learning_rate": 7.433732997982787e-06, + "loss": 3.3319, + "step": 2599936 + }, + { + "epoch": 0.0, + "learning_rate": 7.4253470504722675e-06, + "loss": 3.3358, + "step": 2600448 + }, + { + "epoch": 0.0, + "learning_rate": 7.416977481765479e-06, + "loss": 3.3451, + "step": 2600960 + }, + { + "epoch": 0.0, + "learning_rate": 7.4085915342549574e-06, + "loss": 3.329, + "step": 2601472 + }, + { + "epoch": 0.0, + "learning_rate": 7.400205586744438e-06, + "loss": 3.3296, + "step": 2601984 + }, + { + "epoch": 0.0, + "learning_rate": 7.391819639233918e-06, + "loss": 3.3297, + "step": 2602496 + }, + { + "epoch": 0.0, + "learning_rate": 7.383433691723397e-06, + "loss": 3.3268, + "step": 2603008 + }, + { + "epoch": 0.0, + "learning_rate": 7.375047744212877e-06, + "loss": 3.3252, + "step": 2603520 + }, + { + "epoch": 0.0, + "learning_rate": 7.366661796702358e-06, + "loss": 3.3322, + "step": 2604032 + }, + { + "epoch": 0.0, + "learning_rate": 7.358275849191837e-06, + "loss": 3.323, + "step": 2604544 + }, + { + "epoch": 0.0, + "learning_rate": 7.349906280485049e-06, + "loss": 3.3481, + "step": 2605056 + }, + { + "epoch": 0.0, + "learning_rate": 7.341520332974529e-06, + "loss": 3.3279, + "step": 2605568 + }, + { + "epoch": 0.0, + "learning_rate": 7.3331343854640096e-06, + "loss": 3.3406, + "step": 2606080 + }, + { + "epoch": 0.0, + "learning_rate": 7.324748437953488e-06, + "loss": 3.338, + "step": 2606592 + }, + { + "epoch": 0.0, + "learning_rate": 7.3163788692466995e-06, + "loss": 3.3424, + "step": 2607104 + }, + { + "epoch": 0.0, + "learning_rate": 7.30799292173618e-06, + "loss": 3.3219, + "step": 2607616 + }, + { + "epoch": 0.0, + "learning_rate": 7.299606974225659e-06, + "loss": 3.3328, + "step": 2608128 + }, + { + "epoch": 0.0, + "learning_rate": 7.291237405518871e-06, + "loss": 3.3259, + "step": 2608640 + }, + { + "epoch": 0.0, + "learning_rate": 7.282867836812083e-06, + "loss": 3.3315, + "step": 2609152 + }, + { + "epoch": 0.0, + "learning_rate": 7.274481889301563e-06, + "loss": 3.3236, + "step": 2609664 + }, + { + "epoch": 0.01, + "learning_rate": 7.266095941791042e-06, + "loss": 3.3253, + "step": 2610176 + }, + { + "epoch": 0.01, + "learning_rate": 7.257709994280522e-06, + "loss": 3.3379, + "step": 2610688 + }, + { + "epoch": 0.01, + "learning_rate": 7.2493240467700025e-06, + "loss": 3.3332, + "step": 2611200 + }, + { + "epoch": 0.01, + "learning_rate": 7.240954478063214e-06, + "loss": 3.3226, + "step": 2611712 + }, + { + "epoch": 0.01, + "learning_rate": 7.232568530552692e-06, + "loss": 3.3379, + "step": 2612224 + }, + { + "epoch": 0.01, + "learning_rate": 7.224182583042173e-06, + "loss": 3.335, + "step": 2612736 + }, + { + "epoch": 0.01, + "learning_rate": 7.215796635531653e-06, + "loss": 3.3281, + "step": 2613248 + }, + { + "epoch": 0.01, + "learning_rate": 7.207410688021132e-06, + "loss": 3.318, + "step": 2613760 + }, + { + "epoch": 0.01, + "learning_rate": 7.199024740510612e-06, + "loss": 3.3352, + "step": 2614272 + }, + { + "epoch": 0.01, + "learning_rate": 7.190655171803824e-06, + "loss": 3.3185, + "step": 2614784 + }, + { + "epoch": 0.01, + "learning_rate": 7.182269224293305e-06, + "loss": 3.3295, + "step": 2615296 + }, + { + "epoch": 0.01, + "learning_rate": 7.173883276782784e-06, + "loss": 3.3276, + "step": 2615808 + }, + { + "epoch": 0.01, + "learning_rate": 7.165497329272264e-06, + "loss": 3.3391, + "step": 2616320 + }, + { + "epoch": 0.01, + "learning_rate": 7.1571113817617445e-06, + "loss": 3.3313, + "step": 2616832 + }, + { + "epoch": 0.01, + "learning_rate": 7.148741813054956e-06, + "loss": 3.3337, + "step": 2617344 + }, + { + "epoch": 0.01, + "learning_rate": 7.140355865544434e-06, + "loss": 3.338, + "step": 2617856 + }, + { + "epoch": 0.01, + "learning_rate": 7.131969918033915e-06, + "loss": 3.3363, + "step": 2618368 + }, + { + "epoch": 0.01, + "learning_rate": 7.123583970523395e-06, + "loss": 3.331, + "step": 2618880 + }, + { + "epoch": 0.01, + "learning_rate": 7.115198023012874e-06, + "loss": 3.3154, + "step": 2619392 + }, + { + "epoch": 0.01, + "learning_rate": 7.106812075502354e-06, + "loss": 3.3271, + "step": 2619904 + }, + { + "epoch": 0.01, + "learning_rate": 7.098426127991835e-06, + "loss": 3.3373, + "step": 2620416 + }, + { + "epoch": 0.01, + "learning_rate": 7.090056559285047e-06, + "loss": 3.328, + "step": 2620928 + }, + { + "epoch": 0.01, + "learning_rate": 7.081670611774526e-06, + "loss": 3.3236, + "step": 2621440 + }, + { + "epoch": 0.01, + "learning_rate": 7.073284664264006e-06, + "loss": 3.3181, + "step": 2621952 + }, + { + "epoch": 0.01, + "learning_rate": 7.064898716753486e-06, + "loss": 3.3264, + "step": 2622464 + }, + { + "epoch": 0.01, + "learning_rate": 7.0565291480466965e-06, + "loss": 3.3103, + "step": 2622976 + }, + { + "epoch": 0.01, + "learning_rate": 7.0481432005361764e-06, + "loss": 3.3315, + "step": 2623488 + }, + { + "epoch": 0.01, + "learning_rate": 7.039757253025657e-06, + "loss": 3.3233, + "step": 2624000 + }, + { + "epoch": 0.01, + "learning_rate": 7.031371305515137e-06, + "loss": 3.3371, + "step": 2624512 + }, + { + "epoch": 0.01, + "learning_rate": 7.022985358004616e-06, + "loss": 3.3304, + "step": 2625024 + }, + { + "epoch": 0.01, + "learning_rate": 7.014599410494096e-06, + "loss": 3.3165, + "step": 2625536 + }, + { + "epoch": 0.01, + "learning_rate": 7.006213462983577e-06, + "loss": 3.3252, + "step": 2626048 + }, + { + "epoch": 0.01, + "learning_rate": 6.997843894276787e-06, + "loss": 3.329, + "step": 2626560 + }, + { + "epoch": 0.01, + "learning_rate": 6.989457946766268e-06, + "loss": 3.3171, + "step": 2627072 + }, + { + "epoch": 0.01, + "learning_rate": 6.981071999255748e-06, + "loss": 3.3245, + "step": 2627584 + }, + { + "epoch": 0.01, + "learning_rate": 6.972686051745228e-06, + "loss": 3.3294, + "step": 2628096 + }, + { + "epoch": 0.01, + "learning_rate": 6.964300104234707e-06, + "loss": 3.3322, + "step": 2628608 + }, + { + "epoch": 0.01, + "learning_rate": 6.955914156724188e-06, + "loss": 3.3226, + "step": 2629120 + }, + { + "epoch": 0.01, + "learning_rate": 6.947528209213668e-06, + "loss": 3.3095, + "step": 2629632 + }, + { + "epoch": 0.01, + "learning_rate": 6.939142261703147e-06, + "loss": 3.3205, + "step": 2630144 + }, + { + "epoch": 0.01, + "learning_rate": 6.930772692996358e-06, + "loss": 3.3324, + "step": 2630656 + }, + { + "epoch": 0.01, + "learning_rate": 6.922386745485838e-06, + "loss": 3.337, + "step": 2631168 + }, + { + "epoch": 0.01, + "learning_rate": 6.914000797975319e-06, + "loss": 3.3261, + "step": 2631680 + }, + { + "epoch": 0.01, + "learning_rate": 6.905631229268529e-06, + "loss": 3.3389, + "step": 2632192 + }, + { + "epoch": 0.01, + "learning_rate": 6.897261660561741e-06, + "loss": 3.3359, + "step": 2632704 + }, + { + "epoch": 0.01, + "learning_rate": 6.888875713051221e-06, + "loss": 3.3353, + "step": 2633216 + }, + { + "epoch": 0.01, + "learning_rate": 6.880489765540701e-06, + "loss": 3.3179, + "step": 2633728 + }, + { + "epoch": 0.01, + "learning_rate": 6.8721038180301805e-06, + "loss": 3.3364, + "step": 2634240 + }, + { + "epoch": 0.01, + "learning_rate": 6.8637178705196605e-06, + "loss": 3.3304, + "step": 2634752 + }, + { + "epoch": 0.01, + "learning_rate": 6.855348301812872e-06, + "loss": 3.3239, + "step": 2635264 + }, + { + "epoch": 0.01, + "learning_rate": 6.846962354302351e-06, + "loss": 3.3307, + "step": 2635776 + }, + { + "epoch": 0.01, + "learning_rate": 6.838576406791831e-06, + "loss": 3.3263, + "step": 2636288 + }, + { + "epoch": 0.01, + "learning_rate": 6.830190459281312e-06, + "loss": 3.3354, + "step": 2636800 + }, + { + "epoch": 0.01, + "learning_rate": 6.821804511770792e-06, + "loss": 3.3303, + "step": 2637312 + }, + { + "epoch": 0.01, + "learning_rate": 6.813434943064003e-06, + "loss": 3.3195, + "step": 2637824 + }, + { + "epoch": 0.01, + "learning_rate": 6.805048995553483e-06, + "loss": 3.3261, + "step": 2638336 + }, + { + "epoch": 0.01, + "learning_rate": 6.796663048042963e-06, + "loss": 3.329, + "step": 2638848 + }, + { + "epoch": 0.01, + "learning_rate": 6.788277100532442e-06, + "loss": 3.3315, + "step": 2639360 + }, + { + "epoch": 0.01, + "learning_rate": 6.7798911530219226e-06, + "loss": 3.325, + "step": 2639872 + }, + { + "epoch": 0.01, + "learning_rate": 6.7715052055114025e-06, + "loss": 3.3258, + "step": 2640384 + }, + { + "epoch": 0.02, + "learning_rate": 6.763119258000882e-06, + "loss": 3.3329, + "step": 2640896 + }, + { + "epoch": 0.02, + "learning_rate": 6.754733310490362e-06, + "loss": 3.3191, + "step": 2641408 + }, + { + "epoch": 0.02, + "learning_rate": 6.746380120587305e-06, + "loss": 3.3279, + "step": 2641920 + }, + { + "epoch": 0.02, + "learning_rate": 6.737994173076785e-06, + "loss": 3.3192, + "step": 2642432 + }, + { + "epoch": 0.02, + "learning_rate": 6.729608225566264e-06, + "loss": 3.3353, + "step": 2642944 + }, + { + "epoch": 0.02, + "learning_rate": 6.721222278055744e-06, + "loss": 3.3314, + "step": 2643456 + }, + { + "epoch": 0.02, + "learning_rate": 6.712836330545225e-06, + "loss": 3.3285, + "step": 2643968 + }, + { + "epoch": 0.02, + "learning_rate": 6.704450383034705e-06, + "loss": 3.3202, + "step": 2644480 + }, + { + "epoch": 0.02, + "learning_rate": 6.6960808143279155e-06, + "loss": 3.3327, + "step": 2644992 + }, + { + "epoch": 0.02, + "learning_rate": 6.6876948668173954e-06, + "loss": 3.3194, + "step": 2645504 + }, + { + "epoch": 0.02, + "learning_rate": 6.679308919306876e-06, + "loss": 3.3391, + "step": 2646016 + }, + { + "epoch": 0.02, + "learning_rate": 6.6709229717963545e-06, + "loss": 3.3257, + "step": 2646528 + }, + { + "epoch": 0.02, + "learning_rate": 6.662537024285835e-06, + "loss": 3.3239, + "step": 2647040 + }, + { + "epoch": 0.02, + "learning_rate": 6.654167455579047e-06, + "loss": 3.3181, + "step": 2647552 + }, + { + "epoch": 0.02, + "learning_rate": 6.645781508068527e-06, + "loss": 3.3288, + "step": 2648064 + }, + { + "epoch": 0.02, + "learning_rate": 6.637395560558006e-06, + "loss": 3.3084, + "step": 2648576 + }, + { + "epoch": 0.02, + "learning_rate": 6.629009613047486e-06, + "loss": 3.3242, + "step": 2649088 + }, + { + "epoch": 0.02, + "learning_rate": 6.620640044340698e-06, + "loss": 3.3254, + "step": 2649600 + }, + { + "epoch": 0.02, + "learning_rate": 6.612254096830178e-06, + "loss": 3.3254, + "step": 2650112 + }, + { + "epoch": 0.02, + "learning_rate": 6.6038681493196575e-06, + "loss": 3.311, + "step": 2650624 + }, + { + "epoch": 0.02, + "learning_rate": 6.5954822018091375e-06, + "loss": 3.3311, + "step": 2651136 + }, + { + "epoch": 0.02, + "learning_rate": 6.587096254298617e-06, + "loss": 3.3129, + "step": 2651648 + }, + { + "epoch": 0.02, + "learning_rate": 6.578726685591828e-06, + "loss": 3.3348, + "step": 2652160 + }, + { + "epoch": 0.02, + "learning_rate": 6.570340738081308e-06, + "loss": 3.3244, + "step": 2652672 + }, + { + "epoch": 0.02, + "learning_rate": 6.561954790570789e-06, + "loss": 3.3204, + "step": 2653184 + }, + { + "epoch": 0.02, + "learning_rate": 6.553568843060269e-06, + "loss": 3.339, + "step": 2653696 + }, + { + "epoch": 0.02, + "learning_rate": 6.545182895549748e-06, + "loss": 3.3504, + "step": 2654208 + }, + { + "epoch": 0.02, + "learning_rate": 6.536796948039228e-06, + "loss": 3.3256, + "step": 2654720 + }, + { + "epoch": 0.02, + "learning_rate": 6.528411000528709e-06, + "loss": 3.3181, + "step": 2655232 + }, + { + "epoch": 0.02, + "learning_rate": 6.520025053018188e-06, + "loss": 3.3317, + "step": 2655744 + }, + { + "epoch": 0.02, + "learning_rate": 6.5116554843113995e-06, + "loss": 3.3221, + "step": 2656256 + }, + { + "epoch": 0.02, + "learning_rate": 6.5032695368008795e-06, + "loss": 3.3232, + "step": 2656768 + }, + { + "epoch": 0.02, + "learning_rate": 6.4948835892903594e-06, + "loss": 3.3335, + "step": 2657280 + }, + { + "epoch": 0.02, + "learning_rate": 6.4864976417798385e-06, + "loss": 3.3179, + "step": 2657792 + }, + { + "epoch": 0.02, + "learning_rate": 6.478111694269319e-06, + "loss": 3.3379, + "step": 2658304 + }, + { + "epoch": 0.02, + "learning_rate": 6.469725746758799e-06, + "loss": 3.3267, + "step": 2658816 + }, + { + "epoch": 0.02, + "learning_rate": 6.461356178052009e-06, + "loss": 3.3275, + "step": 2659328 + }, + { + "epoch": 0.02, + "learning_rate": 6.45297023054149e-06, + "loss": 3.32, + "step": 2659840 + }, + { + "epoch": 0.02, + "learning_rate": 6.44458428303097e-06, + "loss": 3.3298, + "step": 2660352 + }, + { + "epoch": 0.02, + "learning_rate": 6.436198335520451e-06, + "loss": 3.319, + "step": 2660864 + }, + { + "epoch": 0.02, + "learning_rate": 6.427812388009929e-06, + "loss": 3.3336, + "step": 2661376 + }, + { + "epoch": 0.02, + "learning_rate": 6.419442819303141e-06, + "loss": 3.3325, + "step": 2661888 + }, + { + "epoch": 0.02, + "learning_rate": 6.4110568717926215e-06, + "loss": 3.3281, + "step": 2662400 + }, + { + "epoch": 0.02, + "learning_rate": 6.402670924282101e-06, + "loss": 3.3146, + "step": 2662912 + }, + { + "epoch": 0.02, + "learning_rate": 6.3942849767715806e-06, + "loss": 3.3332, + "step": 2663424 + }, + { + "epoch": 0.02, + "learning_rate": 6.385899029261061e-06, + "loss": 3.3277, + "step": 2663936 + }, + { + "epoch": 0.02, + "learning_rate": 6.377529460554273e-06, + "loss": 3.3266, + "step": 2664448 + }, + { + "epoch": 0.02, + "learning_rate": 6.369143513043751e-06, + "loss": 3.3232, + "step": 2664960 + }, + { + "epoch": 0.02, + "learning_rate": 6.360757565533232e-06, + "loss": 3.3365, + "step": 2665472 + }, + { + "epoch": 0.02, + "learning_rate": 6.352371618022712e-06, + "loss": 3.3331, + "step": 2665984 + }, + { + "epoch": 0.02, + "learning_rate": 6.343985670512191e-06, + "loss": 3.3355, + "step": 2666496 + }, + { + "epoch": 0.02, + "learning_rate": 6.335599723001671e-06, + "loss": 3.3248, + "step": 2667008 + }, + { + "epoch": 0.02, + "learning_rate": 6.327213775491152e-06, + "loss": 3.3249, + "step": 2667520 + }, + { + "epoch": 0.02, + "learning_rate": 6.3188442067843635e-06, + "loss": 3.3298, + "step": 2668032 + }, + { + "epoch": 0.02, + "learning_rate": 6.310458259273843e-06, + "loss": 3.3136, + "step": 2668544 + }, + { + "epoch": 0.02, + "learning_rate": 6.302072311763323e-06, + "loss": 3.3311, + "step": 2669056 + }, + { + "epoch": 0.02, + "learning_rate": 6.2936863642528026e-06, + "loss": 3.3417, + "step": 2669568 + }, + { + "epoch": 0.02, + "learning_rate": 6.285300416742282e-06, + "loss": 3.3289, + "step": 2670080 + }, + { + "epoch": 0.02, + "learning_rate": 6.2769144692317625e-06, + "loss": 3.3165, + "step": 2670592 + }, + { + "epoch": 0.02, + "learning_rate": 6.2685285217212424e-06, + "loss": 3.326, + "step": 2671104 + }, + { + "epoch": 0.03, + "eval_loss": 3.863739252090454, + "eval_runtime": 306.9724, + "eval_samples_per_second": 1243.079, + "eval_steps_per_second": 38.847, + "step": 2671200 + }, + { + "epoch": 1.0, + "learning_rate": 6.260142574210723e-06, + "loss": 3.3187, + "step": 2671616 + }, + { + "epoch": 1.0, + "learning_rate": 6.251773005503933e-06, + "loss": 3.3253, + "step": 2672128 + }, + { + "epoch": 1.0, + "learning_rate": 6.243403436797145e-06, + "loss": 3.3295, + "step": 2672640 + }, + { + "epoch": 1.0, + "learning_rate": 6.235017489286625e-06, + "loss": 3.3209, + "step": 2673152 + }, + { + "epoch": 1.0, + "learning_rate": 6.226631541776105e-06, + "loss": 3.3359, + "step": 2673664 + }, + { + "epoch": 1.0, + "learning_rate": 6.218245594265585e-06, + "loss": 3.3174, + "step": 2674176 + }, + { + "epoch": 1.0, + "learning_rate": 6.209859646755065e-06, + "loss": 3.3291, + "step": 2674688 + }, + { + "epoch": 1.0, + "learning_rate": 6.201490078048275e-06, + "loss": 3.3164, + "step": 2675200 + }, + { + "epoch": 1.0, + "learning_rate": 6.193104130537756e-06, + "loss": 3.3287, + "step": 2675712 + }, + { + "epoch": 1.0, + "learning_rate": 6.184718183027235e-06, + "loss": 3.3225, + "step": 2676224 + }, + { + "epoch": 1.0, + "learning_rate": 6.176332235516716e-06, + "loss": 3.3255, + "step": 2676736 + }, + { + "epoch": 1.0, + "learning_rate": 6.167962666809927e-06, + "loss": 3.3353, + "step": 2677248 + }, + { + "epoch": 1.0, + "learning_rate": 6.159576719299407e-06, + "loss": 3.3199, + "step": 2677760 + }, + { + "epoch": 1.0, + "learning_rate": 6.151190771788887e-06, + "loss": 3.3222, + "step": 2678272 + }, + { + "epoch": 1.0, + "learning_rate": 6.142804824278366e-06, + "loss": 3.3228, + "step": 2678784 + }, + { + "epoch": 1.0, + "learning_rate": 6.134418876767847e-06, + "loss": 3.3229, + "step": 2679296 + }, + { + "epoch": 1.0, + "learning_rate": 6.1260493080610575e-06, + "loss": 3.3152, + "step": 2679808 + }, + { + "epoch": 1.0, + "learning_rate": 6.1176633605505375e-06, + "loss": 3.3204, + "step": 2680320 + }, + { + "epoch": 1.0, + "learning_rate": 6.1092774130400175e-06, + "loss": 3.314, + "step": 2680832 + }, + { + "epoch": 1.0, + "learning_rate": 6.100891465529498e-06, + "loss": 3.3422, + "step": 2681344 + }, + { + "epoch": 1.0, + "learning_rate": 6.092505518018977e-06, + "loss": 3.3209, + "step": 2681856 + }, + { + "epoch": 1.0, + "learning_rate": 6.084119570508457e-06, + "loss": 3.3273, + "step": 2682368 + }, + { + "epoch": 1.0, + "learning_rate": 6.075733622997937e-06, + "loss": 3.3324, + "step": 2682880 + }, + { + "epoch": 1.0, + "learning_rate": 6.067347675487417e-06, + "loss": 3.3298, + "step": 2683392 + }, + { + "epoch": 1.0, + "learning_rate": 6.058978106780629e-06, + "loss": 3.313, + "step": 2683904 + }, + { + "epoch": 1.0, + "learning_rate": 6.050592159270108e-06, + "loss": 3.3239, + "step": 2684416 + }, + { + "epoch": 1.0, + "learning_rate": 6.042206211759589e-06, + "loss": 3.3204, + "step": 2684928 + }, + { + "epoch": 1.0, + "learning_rate": 6.0338366430527996e-06, + "loss": 3.3234, + "step": 2685440 + }, + { + "epoch": 1.0, + "learning_rate": 6.0254506955422795e-06, + "loss": 3.3134, + "step": 2685952 + }, + { + "epoch": 1.01, + "learning_rate": 6.0170647480317595e-06, + "loss": 3.3179, + "step": 2686464 + }, + { + "epoch": 1.01, + "learning_rate": 6.0086788005212394e-06, + "loss": 3.3284, + "step": 2686976 + }, + { + "epoch": 1.01, + "learning_rate": 6.000309231814451e-06, + "loss": 3.3257, + "step": 2687488 + }, + { + "epoch": 1.01, + "learning_rate": 5.99192328430393e-06, + "loss": 3.3199, + "step": 2688000 + }, + { + "epoch": 1.01, + "learning_rate": 5.983537336793411e-06, + "loss": 3.3274, + "step": 2688512 + }, + { + "epoch": 1.01, + "learning_rate": 5.97515138928289e-06, + "loss": 3.3249, + "step": 2689024 + }, + { + "epoch": 1.01, + "learning_rate": 5.966781820576102e-06, + "loss": 3.3215, + "step": 2689536 + }, + { + "epoch": 1.01, + "learning_rate": 5.958395873065582e-06, + "loss": 3.3098, + "step": 2690048 + }, + { + "epoch": 1.01, + "learning_rate": 5.950009925555062e-06, + "loss": 3.3284, + "step": 2690560 + }, + { + "epoch": 1.01, + "learning_rate": 5.941623978044542e-06, + "loss": 3.307, + "step": 2691072 + }, + { + "epoch": 1.01, + "learning_rate": 5.9332380305340216e-06, + "loss": 3.3191, + "step": 2691584 + }, + { + "epoch": 1.01, + "learning_rate": 5.9248520830235015e-06, + "loss": 3.3181, + "step": 2692096 + }, + { + "epoch": 1.01, + "learning_rate": 5.9164661355129815e-06, + "loss": 3.3294, + "step": 2692608 + }, + { + "epoch": 1.01, + "learning_rate": 5.908080188002461e-06, + "loss": 3.3283, + "step": 2693120 + }, + { + "epoch": 1.01, + "learning_rate": 5.899710619295672e-06, + "loss": 3.3191, + "step": 2693632 + }, + { + "epoch": 1.01, + "learning_rate": 5.891341050588884e-06, + "loss": 3.3297, + "step": 2694144 + }, + { + "epoch": 1.01, + "learning_rate": 5.882955103078364e-06, + "loss": 3.3294, + "step": 2694656 + }, + { + "epoch": 1.01, + "learning_rate": 5.874569155567843e-06, + "loss": 3.3201, + "step": 2695168 + }, + { + "epoch": 1.01, + "learning_rate": 5.866183208057324e-06, + "loss": 3.3087, + "step": 2695680 + }, + { + "epoch": 1.01, + "learning_rate": 5.857797260546803e-06, + "loss": 3.3158, + "step": 2696192 + }, + { + "epoch": 1.01, + "learning_rate": 5.849411313036284e-06, + "loss": 3.3321, + "step": 2696704 + }, + { + "epoch": 1.01, + "learning_rate": 5.841041744329494e-06, + "loss": 3.3173, + "step": 2697216 + }, + { + "epoch": 1.01, + "learning_rate": 5.832655796818974e-06, + "loss": 3.3134, + "step": 2697728 + }, + { + "epoch": 1.01, + "learning_rate": 5.824269849308454e-06, + "loss": 3.3125, + "step": 2698240 + }, + { + "epoch": 1.01, + "learning_rate": 5.815883901797934e-06, + "loss": 3.3192, + "step": 2698752 + }, + { + "epoch": 1.01, + "learning_rate": 5.807497954287414e-06, + "loss": 3.3064, + "step": 2699264 + }, + { + "epoch": 1.01, + "learning_rate": 5.799128385580625e-06, + "loss": 3.3174, + "step": 2699776 + }, + { + "epoch": 1.01, + "learning_rate": 5.790742438070106e-06, + "loss": 3.3199, + "step": 2700288 + }, + { + "epoch": 1.01, + "learning_rate": 5.782356490559585e-06, + "loss": 3.3233, + "step": 2700800 + }, + { + "epoch": 1.01, + "learning_rate": 5.773970543049066e-06, + "loss": 3.3217, + "step": 2701312 + }, + { + "epoch": 1.01, + "learning_rate": 5.765584595538545e-06, + "loss": 3.3106, + "step": 2701824 + }, + { + "epoch": 1.01, + "learning_rate": 5.757198648028025e-06, + "loss": 3.3104, + "step": 2702336 + }, + { + "epoch": 1.01, + "learning_rate": 5.7488290793212364e-06, + "loss": 3.3246, + "step": 2702848 + }, + { + "epoch": 1.01, + "learning_rate": 5.740443131810716e-06, + "loss": 3.3071, + "step": 2703360 + }, + { + "epoch": 1.01, + "learning_rate": 5.732057184300196e-06, + "loss": 3.3143, + "step": 2703872 + }, + { + "epoch": 1.01, + "learning_rate": 5.723671236789676e-06, + "loss": 3.3218, + "step": 2704384 + }, + { + "epoch": 1.01, + "learning_rate": 5.715285289279156e-06, + "loss": 3.3259, + "step": 2704896 + }, + { + "epoch": 1.01, + "learning_rate": 5.706899341768636e-06, + "loss": 3.3097, + "step": 2705408 + }, + { + "epoch": 1.01, + "learning_rate": 5.698513394258115e-06, + "loss": 3.3064, + "step": 2705920 + }, + { + "epoch": 1.01, + "learning_rate": 5.690127446747596e-06, + "loss": 3.3116, + "step": 2706432 + }, + { + "epoch": 1.01, + "learning_rate": 5.681757878040807e-06, + "loss": 3.3228, + "step": 2706944 + }, + { + "epoch": 1.01, + "learning_rate": 5.673371930530287e-06, + "loss": 3.3269, + "step": 2707456 + }, + { + "epoch": 1.01, + "learning_rate": 5.664985983019767e-06, + "loss": 3.3201, + "step": 2707968 + }, + { + "epoch": 1.01, + "learning_rate": 5.656600035509247e-06, + "loss": 3.328, + "step": 2708480 + }, + { + "epoch": 1.01, + "learning_rate": 5.648230466802458e-06, + "loss": 3.3252, + "step": 2708992 + }, + { + "epoch": 1.01, + "learning_rate": 5.639844519291938e-06, + "loss": 3.327, + "step": 2709504 + }, + { + "epoch": 1.01, + "learning_rate": 5.631474950585149e-06, + "loss": 3.3118, + "step": 2710016 + }, + { + "epoch": 1.01, + "learning_rate": 5.62308900307463e-06, + "loss": 3.3267, + "step": 2710528 + }, + { + "epoch": 1.01, + "learning_rate": 5.614703055564109e-06, + "loss": 3.3208, + "step": 2711040 + }, + { + "epoch": 1.01, + "learning_rate": 5.606317108053589e-06, + "loss": 3.3154, + "step": 2711552 + }, + { + "epoch": 1.01, + "learning_rate": 5.597931160543069e-06, + "loss": 3.3228, + "step": 2712064 + }, + { + "epoch": 1.01, + "learning_rate": 5.58956159183628e-06, + "loss": 3.3197, + "step": 2712576 + }, + { + "epoch": 1.01, + "learning_rate": 5.581175644325761e-06, + "loss": 3.3256, + "step": 2713088 + }, + { + "epoch": 1.01, + "learning_rate": 5.57278969681524e-06, + "loss": 3.321, + "step": 2713600 + }, + { + "epoch": 1.01, + "learning_rate": 5.5644037493047205e-06, + "loss": 3.3123, + "step": 2714112 + }, + { + "epoch": 1.01, + "learning_rate": 5.556034180597931e-06, + "loss": 3.32, + "step": 2714624 + }, + { + "epoch": 1.01, + "learning_rate": 5.547648233087411e-06, + "loss": 3.3169, + "step": 2715136 + }, + { + "epoch": 1.01, + "learning_rate": 5.539262285576891e-06, + "loss": 3.3238, + "step": 2715648 + }, + { + "epoch": 1.01, + "learning_rate": 5.530876338066371e-06, + "loss": 3.319, + "step": 2716160 + }, + { + "epoch": 1.01, + "learning_rate": 5.522490390555851e-06, + "loss": 3.3163, + "step": 2716672 + }, + { + "epoch": 1.02, + "learning_rate": 5.514104443045331e-06, + "loss": 3.3263, + "step": 2717184 + }, + { + "epoch": 1.02, + "learning_rate": 5.505718495534811e-06, + "loss": 3.315, + "step": 2717696 + }, + { + "epoch": 1.02, + "learning_rate": 5.497348926828022e-06, + "loss": 3.313, + "step": 2718208 + }, + { + "epoch": 1.02, + "learning_rate": 5.488962979317503e-06, + "loss": 3.3117, + "step": 2718720 + }, + { + "epoch": 1.02, + "learning_rate": 5.480577031806982e-06, + "loss": 3.3309, + "step": 2719232 + }, + { + "epoch": 1.02, + "learning_rate": 5.472191084296462e-06, + "loss": 3.3263, + "step": 2719744 + }, + { + "epoch": 1.02, + "learning_rate": 5.463805136785942e-06, + "loss": 3.318, + "step": 2720256 + }, + { + "epoch": 1.02, + "learning_rate": 5.455419189275422e-06, + "loss": 3.3103, + "step": 2720768 + }, + { + "epoch": 1.02, + "learning_rate": 5.447049620568633e-06, + "loss": 3.3226, + "step": 2721280 + }, + { + "epoch": 1.02, + "learning_rate": 5.438663673058113e-06, + "loss": 3.3095, + "step": 2721792 + }, + { + "epoch": 1.02, + "learning_rate": 5.430277725547593e-06, + "loss": 3.3333, + "step": 2722304 + }, + { + "epoch": 1.02, + "learning_rate": 5.421891778037073e-06, + "loss": 3.3204, + "step": 2722816 + }, + { + "epoch": 1.02, + "learning_rate": 5.413505830526552e-06, + "loss": 3.3153, + "step": 2723328 + }, + { + "epoch": 1.02, + "learning_rate": 5.405119883016033e-06, + "loss": 3.3105, + "step": 2723840 + }, + { + "epoch": 1.02, + "learning_rate": 5.396750314309244e-06, + "loss": 3.3217, + "step": 2724352 + }, + { + "epoch": 1.02, + "learning_rate": 5.388364366798724e-06, + "loss": 3.2963, + "step": 2724864 + }, + { + "epoch": 1.02, + "learning_rate": 5.379978419288204e-06, + "loss": 3.3161, + "step": 2725376 + }, + { + "epoch": 1.02, + "learning_rate": 5.371592471777684e-06, + "loss": 3.3153, + "step": 2725888 + }, + { + "epoch": 1.02, + "learning_rate": 5.363206524267164e-06, + "loss": 3.3168, + "step": 2726400 + }, + { + "epoch": 1.02, + "learning_rate": 5.354820576756643e-06, + "loss": 3.3035, + "step": 2726912 + }, + { + "epoch": 1.02, + "learning_rate": 5.346451008049854e-06, + "loss": 3.324, + "step": 2727424 + }, + { + "epoch": 1.02, + "learning_rate": 5.338065060539334e-06, + "loss": 3.3062, + "step": 2727936 + }, + { + "epoch": 1.02, + "learning_rate": 5.329679113028814e-06, + "loss": 3.3228, + "step": 2728448 + }, + { + "epoch": 1.02, + "learning_rate": 5.321293165518294e-06, + "loss": 3.3195, + "step": 2728960 + }, + { + "epoch": 1.02, + "learning_rate": 5.312923596811506e-06, + "loss": 3.31, + "step": 2729472 + }, + { + "epoch": 1.02, + "learning_rate": 5.304537649300986e-06, + "loss": 3.3297, + "step": 2729984 + }, + { + "epoch": 1.02, + "learning_rate": 5.296151701790466e-06, + "loss": 3.3389, + "step": 2730496 + }, + { + "epoch": 1.02, + "learning_rate": 5.287765754279946e-06, + "loss": 3.3204, + "step": 2731008 + }, + { + "epoch": 1.02, + "learning_rate": 5.279379806769425e-06, + "loss": 3.3106, + "step": 2731520 + }, + { + "epoch": 1.02, + "learning_rate": 5.270993859258906e-06, + "loss": 3.3206, + "step": 2732032 + }, + { + "epoch": 1.02, + "learning_rate": 5.2626242905521164e-06, + "loss": 3.3111, + "step": 2732544 + }, + { + "epoch": 1.02, + "learning_rate": 5.254238343041596e-06, + "loss": 3.3131, + "step": 2733056 + }, + { + "epoch": 1.02, + "learning_rate": 5.245852395531076e-06, + "loss": 3.3273, + "step": 2733568 + }, + { + "epoch": 1.02, + "learning_rate": 5.237466448020556e-06, + "loss": 3.3119, + "step": 2734080 + }, + { + "epoch": 1.02, + "learning_rate": 5.229080500510036e-06, + "loss": 3.3261, + "step": 2734592 + }, + { + "epoch": 1.02, + "learning_rate": 5.220694552999516e-06, + "loss": 3.3194, + "step": 2735104 + }, + { + "epoch": 1.02, + "learning_rate": 5.212324984292728e-06, + "loss": 3.32, + "step": 2735616 + }, + { + "epoch": 1.02, + "learning_rate": 5.203939036782207e-06, + "loss": 3.3035, + "step": 2736128 + }, + { + "epoch": 1.02, + "learning_rate": 5.195553089271688e-06, + "loss": 3.3218, + "step": 2736640 + }, + { + "epoch": 1.02, + "learning_rate": 5.187167141761167e-06, + "loss": 3.312, + "step": 2737152 + }, + { + "epoch": 1.02, + "learning_rate": 5.178781194250647e-06, + "loss": 3.3229, + "step": 2737664 + }, + { + "epoch": 1.02, + "learning_rate": 5.1704116255438585e-06, + "loss": 3.3194, + "step": 2738176 + }, + { + "epoch": 1.02, + "learning_rate": 5.162025678033338e-06, + "loss": 3.3259, + "step": 2738688 + }, + { + "epoch": 1.02, + "learning_rate": 5.153639730522818e-06, + "loss": 3.3054, + "step": 2739200 + }, + { + "epoch": 1.02, + "learning_rate": 5.145253783012298e-06, + "loss": 3.3275, + "step": 2739712 + }, + { + "epoch": 1.02, + "learning_rate": 5.136867835501778e-06, + "loss": 3.3154, + "step": 2740224 + }, + { + "epoch": 1.02, + "learning_rate": 5.128481887991258e-06, + "loss": 3.3176, + "step": 2740736 + }, + { + "epoch": 1.02, + "learning_rate": 5.120095940480737e-06, + "loss": 3.3164, + "step": 2741248 + }, + { + "epoch": 1.02, + "learning_rate": 5.111709992970218e-06, + "loss": 3.3266, + "step": 2741760 + }, + { + "epoch": 1.02, + "learning_rate": 5.103340424263429e-06, + "loss": 3.3266, + "step": 2742272 + }, + { + "epoch": 1.02, + "learning_rate": 5.094954476752909e-06, + "loss": 3.3266, + "step": 2742784 + }, + { + "epoch": 1.02, + "learning_rate": 5.086568529242389e-06, + "loss": 3.3144, + "step": 2743296 + }, + { + "epoch": 1.02, + "learning_rate": 5.078182581731869e-06, + "loss": 3.3204, + "step": 2743808 + }, + { + "epoch": 1.02, + "learning_rate": 5.069829391828811e-06, + "loss": 3.3203, + "step": 2744320 + }, + { + "epoch": 1.02, + "learning_rate": 5.061443444318291e-06, + "loss": 3.3099, + "step": 2744832 + }, + { + "epoch": 1.02, + "learning_rate": 5.053057496807771e-06, + "loss": 3.3203, + "step": 2745344 + }, + { + "epoch": 1.02, + "learning_rate": 5.044671549297251e-06, + "loss": 3.3312, + "step": 2745856 + }, + { + "epoch": 1.02, + "learning_rate": 5.036285601786731e-06, + "loss": 3.3221, + "step": 2746368 + }, + { + "epoch": 1.02, + "learning_rate": 5.027899654276211e-06, + "loss": 3.3071, + "step": 2746880 + }, + { + "epoch": 1.02, + "learning_rate": 5.019513706765691e-06, + "loss": 3.3184, + "step": 2747392 + }, + { + "epoch": 1.03, + "eval_loss": 3.864123821258545, + "eval_runtime": 305.886, + "eval_samples_per_second": 1247.494, + "eval_steps_per_second": 38.985, + "step": 2747520 + }, + { + "epoch": 0.0, + "learning_rate": 5.011127759255171e-06, + "loss": 3.3051, + "step": 2747904 + }, + { + "epoch": 0.0, + "learning_rate": 5.002758190548383e-06, + "loss": 3.3139, + "step": 2748416 + }, + { + "epoch": 0.0, + "learning_rate": 4.994372243037862e-06, + "loss": 3.3208, + "step": 2748928 + }, + { + "epoch": 0.0, + "learning_rate": 4.9859862955273425e-06, + "loss": 3.3161, + "step": 2749440 + }, + { + "epoch": 0.0, + "learning_rate": 4.977600348016822e-06, + "loss": 3.3283, + "step": 2749952 + }, + { + "epoch": 0.0, + "learning_rate": 4.969214400506302e-06, + "loss": 3.311, + "step": 2750464 + }, + { + "epoch": 0.0, + "learning_rate": 4.960844831799513e-06, + "loss": 3.3184, + "step": 2750976 + }, + { + "epoch": 0.0, + "learning_rate": 4.952458884288993e-06, + "loss": 3.3072, + "step": 2751488 + }, + { + "epoch": 0.0, + "learning_rate": 4.944072936778473e-06, + "loss": 3.323, + "step": 2752000 + }, + { + "epoch": 0.0, + "learning_rate": 4.935686989267953e-06, + "loss": 3.3128, + "step": 2752512 + }, + { + "epoch": 0.0, + "learning_rate": 4.927317420561165e-06, + "loss": 3.3121, + "step": 2753024 + }, + { + "epoch": 0.0, + "learning_rate": 4.918931473050644e-06, + "loss": 3.3291, + "step": 2753536 + }, + { + "epoch": 0.0, + "learning_rate": 4.910545525540125e-06, + "loss": 3.308, + "step": 2754048 + }, + { + "epoch": 0.0, + "learning_rate": 4.902159578029604e-06, + "loss": 3.3182, + "step": 2754560 + }, + { + "epoch": 0.0, + "learning_rate": 4.893773630519084e-06, + "loss": 3.3122, + "step": 2755072 + }, + { + "epoch": 0.0, + "learning_rate": 4.885404061812295e-06, + "loss": 3.3149, + "step": 2755584 + }, + { + "epoch": 0.0, + "learning_rate": 4.8770181143017745e-06, + "loss": 3.3047, + "step": 2756096 + }, + { + "epoch": 0.0, + "learning_rate": 4.868632166791255e-06, + "loss": 3.3134, + "step": 2756608 + }, + { + "epoch": 0.0, + "learning_rate": 4.860246219280734e-06, + "loss": 3.3085, + "step": 2757120 + }, + { + "epoch": 0.0, + "learning_rate": 4.851860271770215e-06, + "loss": 3.3306, + "step": 2757632 + }, + { + "epoch": 0.0, + "learning_rate": 4.843474324259695e-06, + "loss": 3.3112, + "step": 2758144 + }, + { + "epoch": 0.0, + "learning_rate": 4.835088376749174e-06, + "loss": 3.3185, + "step": 2758656 + }, + { + "epoch": 0.0, + "learning_rate": 4.826702429238655e-06, + "loss": 3.3256, + "step": 2759168 + }, + { + "epoch": 0.0, + "learning_rate": 4.818332860531866e-06, + "loss": 3.3214, + "step": 2759680 + }, + { + "epoch": 0.0, + "learning_rate": 4.809946913021346e-06, + "loss": 3.3042, + "step": 2760192 + }, + { + "epoch": 0.0, + "learning_rate": 4.801560965510826e-06, + "loss": 3.3171, + "step": 2760704 + }, + { + "epoch": 0.0, + "learning_rate": 4.793175018000306e-06, + "loss": 3.3081, + "step": 2761216 + }, + { + "epoch": 0.0, + "learning_rate": 4.7848054492935165e-06, + "loss": 3.3163, + "step": 2761728 + }, + { + "epoch": 0.0, + "learning_rate": 4.776419501782997e-06, + "loss": 3.3032, + "step": 2762240 + }, + { + "epoch": 0.0, + "learning_rate": 4.768033554272476e-06, + "loss": 3.3097, + "step": 2762752 + }, + { + "epoch": 0.01, + "learning_rate": 4.759647606761956e-06, + "loss": 3.3182, + "step": 2763264 + }, + { + "epoch": 0.01, + "learning_rate": 4.751261659251436e-06, + "loss": 3.3154, + "step": 2763776 + }, + { + "epoch": 0.01, + "learning_rate": 4.742875711740916e-06, + "loss": 3.3111, + "step": 2764288 + }, + { + "epoch": 0.01, + "learning_rate": 4.734489764230396e-06, + "loss": 3.32, + "step": 2764800 + }, + { + "epoch": 0.01, + "learning_rate": 4.726120195523608e-06, + "loss": 3.3097, + "step": 2765312 + }, + { + "epoch": 0.01, + "learning_rate": 4.717734248013088e-06, + "loss": 3.3163, + "step": 2765824 + }, + { + "epoch": 0.01, + "learning_rate": 4.709348300502568e-06, + "loss": 3.3006, + "step": 2766336 + }, + { + "epoch": 0.01, + "learning_rate": 4.700962352992047e-06, + "loss": 3.3181, + "step": 2766848 + }, + { + "epoch": 0.01, + "learning_rate": 4.6925927842852585e-06, + "loss": 3.3048, + "step": 2767360 + }, + { + "epoch": 0.01, + "learning_rate": 4.6842068367747385e-06, + "loss": 3.308, + "step": 2767872 + }, + { + "epoch": 0.01, + "learning_rate": 4.6758208892642184e-06, + "loss": 3.3065, + "step": 2768384 + }, + { + "epoch": 0.01, + "learning_rate": 4.667434941753698e-06, + "loss": 3.3233, + "step": 2768896 + }, + { + "epoch": 0.01, + "learning_rate": 4.659048994243178e-06, + "loss": 3.3181, + "step": 2769408 + }, + { + "epoch": 0.01, + "learning_rate": 4.650663046732658e-06, + "loss": 3.316, + "step": 2769920 + }, + { + "epoch": 0.01, + "learning_rate": 4.642277099222138e-06, + "loss": 3.3201, + "step": 2770432 + }, + { + "epoch": 0.01, + "learning_rate": 4.63390753051535e-06, + "loss": 3.321, + "step": 2770944 + }, + { + "epoch": 0.01, + "learning_rate": 4.625521583004829e-06, + "loss": 3.3101, + "step": 2771456 + }, + { + "epoch": 0.01, + "learning_rate": 4.61713563549431e-06, + "loss": 3.3064, + "step": 2771968 + }, + { + "epoch": 0.01, + "learning_rate": 4.608749687983789e-06, + "loss": 3.2998, + "step": 2772480 + }, + { + "epoch": 0.01, + "learning_rate": 4.600363740473269e-06, + "loss": 3.322, + "step": 2772992 + }, + { + "epoch": 0.01, + "learning_rate": 4.5919941717664805e-06, + "loss": 3.3095, + "step": 2773504 + }, + { + "epoch": 0.01, + "learning_rate": 4.58360822425596e-06, + "loss": 3.3057, + "step": 2774016 + }, + { + "epoch": 0.01, + "learning_rate": 4.57522227674544e-06, + "loss": 3.306, + "step": 2774528 + }, + { + "epoch": 0.01, + "learning_rate": 4.5668363292349195e-06, + "loss": 3.3104, + "step": 2775040 + }, + { + "epoch": 0.01, + "learning_rate": 4.5584503817244e-06, + "loss": 3.2985, + "step": 2775552 + }, + { + "epoch": 0.01, + "learning_rate": 4.550080813017611e-06, + "loss": 3.3036, + "step": 2776064 + }, + { + "epoch": 0.01, + "learning_rate": 4.541694865507092e-06, + "loss": 3.31, + "step": 2776576 + }, + { + "epoch": 0.01, + "learning_rate": 4.533308917996571e-06, + "loss": 3.3115, + "step": 2777088 + }, + { + "epoch": 0.01, + "learning_rate": 4.524922970486051e-06, + "loss": 3.3177, + "step": 2777600 + }, + { + "epoch": 0.01, + "learning_rate": 4.516537022975531e-06, + "loss": 3.3031, + "step": 2778112 + }, + { + "epoch": 0.01, + "learning_rate": 4.508151075465011e-06, + "loss": 3.3022, + "step": 2778624 + }, + { + "epoch": 0.01, + "learning_rate": 4.4997815067582225e-06, + "loss": 3.3179, + "step": 2779136 + }, + { + "epoch": 0.01, + "learning_rate": 4.491395559247702e-06, + "loss": 3.3016, + "step": 2779648 + }, + { + "epoch": 0.01, + "learning_rate": 4.4830096117371824e-06, + "loss": 3.305, + "step": 2780160 + }, + { + "epoch": 0.01, + "learning_rate": 4.4746236642266615e-06, + "loss": 3.3137, + "step": 2780672 + }, + { + "epoch": 0.01, + "learning_rate": 4.4662377167161415e-06, + "loss": 3.3151, + "step": 2781184 + }, + { + "epoch": 0.01, + "learning_rate": 4.4578517692056215e-06, + "loss": 3.3025, + "step": 2781696 + }, + { + "epoch": 0.01, + "learning_rate": 4.449465821695101e-06, + "loss": 3.2977, + "step": 2782208 + }, + { + "epoch": 0.01, + "learning_rate": 4.441079874184581e-06, + "loss": 3.2997, + "step": 2782720 + }, + { + "epoch": 0.01, + "learning_rate": 4.432710305477793e-06, + "loss": 3.3111, + "step": 2783232 + }, + { + "epoch": 0.01, + "learning_rate": 4.424324357967273e-06, + "loss": 3.3189, + "step": 2783744 + }, + { + "epoch": 0.01, + "learning_rate": 4.415938410456753e-06, + "loss": 3.3084, + "step": 2784256 + }, + { + "epoch": 0.01, + "learning_rate": 4.407552462946232e-06, + "loss": 3.322, + "step": 2784768 + }, + { + "epoch": 0.01, + "learning_rate": 4.399182894239444e-06, + "loss": 3.3183, + "step": 2785280 + }, + { + "epoch": 0.01, + "learning_rate": 4.390796946728924e-06, + "loss": 3.3237, + "step": 2785792 + }, + { + "epoch": 0.01, + "learning_rate": 4.382427378022135e-06, + "loss": 3.3012, + "step": 2786304 + }, + { + "epoch": 0.01, + "learning_rate": 4.374041430511615e-06, + "loss": 3.3175, + "step": 2786816 + }, + { + "epoch": 0.01, + "learning_rate": 4.365655483001095e-06, + "loss": 3.3132, + "step": 2787328 + }, + { + "epoch": 0.01, + "learning_rate": 4.357269535490575e-06, + "loss": 3.3045, + "step": 2787840 + }, + { + "epoch": 0.01, + "learning_rate": 4.348883587980055e-06, + "loss": 3.3181, + "step": 2788352 + }, + { + "epoch": 0.01, + "learning_rate": 4.340514019273266e-06, + "loss": 3.3102, + "step": 2788864 + }, + { + "epoch": 0.01, + "learning_rate": 4.332128071762747e-06, + "loss": 3.3124, + "step": 2789376 + }, + { + "epoch": 0.01, + "learning_rate": 4.323742124252226e-06, + "loss": 3.3122, + "step": 2789888 + }, + { + "epoch": 0.01, + "learning_rate": 4.315356176741706e-06, + "loss": 3.3075, + "step": 2790400 + }, + { + "epoch": 0.01, + "learning_rate": 4.306986608034917e-06, + "loss": 3.3126, + "step": 2790912 + }, + { + "epoch": 0.01, + "learning_rate": 4.2986006605243965e-06, + "loss": 3.3085, + "step": 2791424 + }, + { + "epoch": 0.01, + "learning_rate": 4.290214713013877e-06, + "loss": 3.3167, + "step": 2791936 + }, + { + "epoch": 0.01, + "learning_rate": 4.281828765503356e-06, + "loss": 3.307, + "step": 2792448 + }, + { + "epoch": 0.01, + "learning_rate": 4.273442817992837e-06, + "loss": 3.3076, + "step": 2792960 + }, + { + "epoch": 0.02, + "learning_rate": 4.265056870482316e-06, + "loss": 3.3136, + "step": 2793472 + }, + { + "epoch": 0.02, + "learning_rate": 4.256670922971796e-06, + "loss": 3.3112, + "step": 2793984 + }, + { + "epoch": 0.02, + "learning_rate": 4.248301354265008e-06, + "loss": 3.3032, + "step": 2794496 + }, + { + "epoch": 0.02, + "learning_rate": 4.239915406754488e-06, + "loss": 3.3059, + "step": 2795008 + }, + { + "epoch": 0.02, + "learning_rate": 4.231529459243968e-06, + "loss": 3.3212, + "step": 2795520 + }, + { + "epoch": 0.02, + "learning_rate": 4.223143511733448e-06, + "loss": 3.3171, + "step": 2796032 + }, + { + "epoch": 0.02, + "learning_rate": 4.214757564222928e-06, + "loss": 3.311, + "step": 2796544 + }, + { + "epoch": 0.02, + "learning_rate": 4.206371616712408e-06, + "loss": 3.3028, + "step": 2797056 + }, + { + "epoch": 0.02, + "learning_rate": 4.198002048005619e-06, + "loss": 3.3134, + "step": 2797568 + }, + { + "epoch": 0.02, + "learning_rate": 4.1896161004950984e-06, + "loss": 3.3033, + "step": 2798080 + }, + { + "epoch": 0.02, + "learning_rate": 4.181230152984578e-06, + "loss": 3.318, + "step": 2798592 + }, + { + "epoch": 0.02, + "learning_rate": 4.172844205474058e-06, + "loss": 3.3156, + "step": 2799104 + }, + { + "epoch": 0.02, + "learning_rate": 4.164458257963538e-06, + "loss": 3.3071, + "step": 2799616 + }, + { + "epoch": 0.02, + "learning_rate": 4.15608868925675e-06, + "loss": 3.3039, + "step": 2800128 + }, + { + "epoch": 0.02, + "learning_rate": 4.14770274174623e-06, + "loss": 3.313, + "step": 2800640 + }, + { + "epoch": 0.02, + "learning_rate": 4.13931679423571e-06, + "loss": 3.2886, + "step": 2801152 + }, + { + "epoch": 0.02, + "learning_rate": 4.13093084672519e-06, + "loss": 3.311, + "step": 2801664 + }, + { + "epoch": 0.02, + "learning_rate": 4.122544899214669e-06, + "loss": 3.3032, + "step": 2802176 + }, + { + "epoch": 0.02, + "learning_rate": 4.1141753305078805e-06, + "loss": 3.3076, + "step": 2802688 + }, + { + "epoch": 0.02, + "learning_rate": 4.1057893829973605e-06, + "loss": 3.2951, + "step": 2803200 + }, + { + "epoch": 0.02, + "learning_rate": 4.0974034354868405e-06, + "loss": 3.3155, + "step": 2803712 + }, + { + "epoch": 0.02, + "learning_rate": 4.08901748797632e-06, + "loss": 3.3024, + "step": 2804224 + }, + { + "epoch": 0.02, + "learning_rate": 4.0806315404657995e-06, + "loss": 3.309, + "step": 2804736 + }, + { + "epoch": 0.02, + "learning_rate": 4.07224559295528e-06, + "loss": 3.3118, + "step": 2805248 + }, + { + "epoch": 0.02, + "learning_rate": 4.06385964544476e-06, + "loss": 3.3025, + "step": 2805760 + }, + { + "epoch": 0.02, + "learning_rate": 4.055490076737972e-06, + "loss": 3.323, + "step": 2806272 + }, + { + "epoch": 0.02, + "learning_rate": 4.047104129227451e-06, + "loss": 3.3339, + "step": 2806784 + }, + { + "epoch": 0.02, + "learning_rate": 4.038718181716932e-06, + "loss": 3.3125, + "step": 2807296 + }, + { + "epoch": 0.02, + "learning_rate": 4.030332234206411e-06, + "loss": 3.3005, + "step": 2807808 + }, + { + "epoch": 0.02, + "learning_rate": 4.021946286695891e-06, + "loss": 3.3151, + "step": 2808320 + }, + { + "epoch": 0.02, + "learning_rate": 4.013560339185371e-06, + "loss": 3.3052, + "step": 2808832 + }, + { + "epoch": 0.02, + "learning_rate": 4.005190770478582e-06, + "loss": 3.3034, + "step": 2809344 + }, + { + "epoch": 0.02, + "learning_rate": 3.9968048229680624e-06, + "loss": 3.3174, + "step": 2809856 + }, + { + "epoch": 0.02, + "learning_rate": 3.9884188754575415e-06, + "loss": 3.3007, + "step": 2810368 + }, + { + "epoch": 0.02, + "learning_rate": 3.980032927947022e-06, + "loss": 3.316, + "step": 2810880 + }, + { + "epoch": 0.02, + "learning_rate": 3.9716469804365015e-06, + "loss": 3.3125, + "step": 2811392 + }, + { + "epoch": 0.02, + "learning_rate": 3.963277411729713e-06, + "loss": 3.3128, + "step": 2811904 + }, + { + "epoch": 0.02, + "learning_rate": 3.954891464219193e-06, + "loss": 3.3029, + "step": 2812416 + }, + { + "epoch": 0.02, + "learning_rate": 3.946505516708673e-06, + "loss": 3.3094, + "step": 2812928 + }, + { + "epoch": 0.02, + "learning_rate": 3.938119569198153e-06, + "loss": 3.3083, + "step": 2813440 + }, + { + "epoch": 0.02, + "learning_rate": 3.929733621687633e-06, + "loss": 3.3151, + "step": 2813952 + }, + { + "epoch": 0.02, + "learning_rate": 3.9213640529808446e-06, + "loss": 3.311, + "step": 2814464 + }, + { + "epoch": 0.02, + "learning_rate": 3.912978105470324e-06, + "loss": 3.3174, + "step": 2814976 + }, + { + "epoch": 0.02, + "learning_rate": 3.9045921579598045e-06, + "loss": 3.2982, + "step": 2815488 + }, + { + "epoch": 0.02, + "learning_rate": 3.8962062104492836e-06, + "loss": 3.3194, + "step": 2816000 + }, + { + "epoch": 0.02, + "learning_rate": 3.8878202629387635e-06, + "loss": 3.3069, + "step": 2816512 + }, + { + "epoch": 0.02, + "learning_rate": 3.8794343154282435e-06, + "loss": 3.3133, + "step": 2817024 + }, + { + "epoch": 0.02, + "learning_rate": 3.8710483679177234e-06, + "loss": 3.3065, + "step": 2817536 + }, + { + "epoch": 0.02, + "learning_rate": 3.862662420407203e-06, + "loss": 3.3179, + "step": 2818048 + }, + { + "epoch": 0.02, + "learning_rate": 3.854292851700415e-06, + "loss": 3.3144, + "step": 2818560 + }, + { + "epoch": 0.02, + "learning_rate": 3.845906904189895e-06, + "loss": 3.3213, + "step": 2819072 + }, + { + "epoch": 0.02, + "learning_rate": 3.837520956679375e-06, + "loss": 3.3019, + "step": 2819584 + }, + { + "epoch": 0.02, + "learning_rate": 3.829135009168854e-06, + "loss": 3.3134, + "step": 2820096 + }, + { + "epoch": 0.02, + "learning_rate": 3.820781819265797e-06, + "loss": 3.3082, + "step": 2820608 + }, + { + "epoch": 0.02, + "learning_rate": 3.8123958717552773e-06, + "loss": 3.3029, + "step": 2821120 + }, + { + "epoch": 0.02, + "learning_rate": 3.8040099242447573e-06, + "loss": 3.316, + "step": 2821632 + }, + { + "epoch": 0.02, + "learning_rate": 3.795623976734237e-06, + "loss": 3.3189, + "step": 2822144 + }, + { + "epoch": 0.02, + "learning_rate": 3.787238029223717e-06, + "loss": 3.3172, + "step": 2822656 + }, + { + "epoch": 0.02, + "learning_rate": 3.7788520817131967e-06, + "loss": 3.2949, + "step": 2823168 + }, + { + "epoch": 0.02, + "learning_rate": 3.770466134202677e-06, + "loss": 3.3097, + "step": 2823680 + }, + { + "epoch": 0.03, + "eval_loss": 3.8638343811035156, + "eval_runtime": 302.7115, + "eval_samples_per_second": 1260.576, + "eval_steps_per_second": 39.394, + "step": 2823840 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 1.9790329655701463e+18, + "trial_name": null, + "trial_params": null +}