{ "best_metric": 3.8544273376464844, "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/rel-cl2/transformer/1/checkpoints/checkpoint-686880", "epoch": 1.0250006060157382, "eval_steps": 10, "global_step": 686880, "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": 10.9931, "step": 1 }, { "epoch": 0.0, "learning_rate": 4.999161405248948e-05, "loss": 6.8206, "step": 512 }, { "epoch": 0.0, "learning_rate": 4.998322810497896e-05, "loss": 6.2067, "step": 1024 }, { "epoch": 0.0, "learning_rate": 4.997484215746844e-05, "loss": 6.0045, "step": 1536 }, { "epoch": 0.0, "learning_rate": 4.996645620995792e-05, "loss": 5.8356, "step": 2048 }, { "epoch": 0.0, "learning_rate": 4.99580702624474e-05, "loss": 5.7277, "step": 2560 }, { "epoch": 0.0, "learning_rate": 4.994968431493688e-05, "loss": 5.6144, "step": 3072 }, { "epoch": 0.0, "learning_rate": 4.994129836742636e-05, "loss": 5.5429, "step": 3584 }, { "epoch": 0.0, "learning_rate": 4.993291241991584e-05, "loss": 5.4633, "step": 4096 }, { "epoch": 0.0, "learning_rate": 4.992452647240532e-05, "loss": 5.4028, "step": 4608 }, { "epoch": 0.0, "learning_rate": 4.99161405248948e-05, "loss": 5.364, "step": 5120 }, { "epoch": 0.0, "learning_rate": 4.990775457738428e-05, "loss": 5.316, "step": 5632 }, { "epoch": 0.0, "learning_rate": 4.989936862987376e-05, "loss": 5.269, "step": 6144 }, { "epoch": 0.0, "learning_rate": 4.989098268236324e-05, "loss": 5.2209, "step": 6656 }, { "epoch": 0.0, "learning_rate": 4.988259673485272e-05, "loss": 5.1951, "step": 7168 }, { "epoch": 0.0, "learning_rate": 4.98742107873422e-05, "loss": 5.1482, "step": 7680 }, { "epoch": 0.0, "learning_rate": 4.986584121863541e-05, "loss": 5.1226, "step": 8192 }, { "epoch": 0.0, "learning_rate": 4.985745527112489e-05, "loss": 5.0968, "step": 8704 }, { "epoch": 0.0, "learning_rate": 4.984906932361437e-05, "loss": 5.064, "step": 9216 }, { "epoch": 0.0, "learning_rate": 4.984068337610385e-05, "loss": 5.0333, "step": 9728 }, { "epoch": 0.0, "learning_rate": 4.983229742859333e-05, "loss": 5.0177, "step": 10240 }, { "epoch": 0.0, "learning_rate": 4.9823927859886547e-05, "loss": 4.986, "step": 10752 }, { "epoch": 0.0, "learning_rate": 4.9815541912376026e-05, "loss": 4.9694, "step": 11264 }, { "epoch": 0.0, "learning_rate": 4.9807155964865506e-05, "loss": 4.9416, "step": 11776 }, { "epoch": 0.0, "learning_rate": 4.9798770017354986e-05, "loss": 4.9363, "step": 12288 }, { "epoch": 0.0, "learning_rate": 4.9790400448648195e-05, "loss": 4.901, "step": 12800 }, { "epoch": 0.0, "learning_rate": 4.9782014501137675e-05, "loss": 4.8872, "step": 13312 }, { "epoch": 0.0, "learning_rate": 4.9773628553627155e-05, "loss": 4.8597, "step": 13824 }, { "epoch": 0.0, "learning_rate": 4.9765242606116635e-05, "loss": 4.8517, "step": 14336 }, { "epoch": 0.0, "learning_rate": 4.9756873037409844e-05, "loss": 4.8274, "step": 14848 }, { "epoch": 0.01, "learning_rate": 4.9748487089899324e-05, "loss": 4.8213, "step": 15360 }, { "epoch": 0.01, "learning_rate": 4.9740101142388804e-05, "loss": 4.8086, "step": 15872 }, { "epoch": 0.01, "learning_rate": 4.9731715194878284e-05, "loss": 4.7926, "step": 16384 }, { "epoch": 0.01, "learning_rate": 4.9723329247367764e-05, "loss": 4.7812, "step": 16896 }, { "epoch": 0.01, "learning_rate": 4.9714943299857244e-05, "loss": 4.7671, "step": 17408 }, { "epoch": 0.01, "learning_rate": 4.970659010995419e-05, "loss": 4.7526, "step": 17920 }, { "epoch": 0.01, "learning_rate": 4.969820416244367e-05, "loss": 4.7505, "step": 18432 }, { "epoch": 0.01, "learning_rate": 4.968981821493315e-05, "loss": 4.7196, "step": 18944 }, { "epoch": 0.01, "learning_rate": 4.968143226742263e-05, "loss": 4.7092, "step": 19456 }, { "epoch": 0.01, "learning_rate": 4.967304631991211e-05, "loss": 4.6879, "step": 19968 }, { "epoch": 0.01, "learning_rate": 4.966466037240159e-05, "loss": 4.6908, "step": 20480 }, { "epoch": 0.01, "learning_rate": 4.965627442489107e-05, "loss": 4.6757, "step": 20992 }, { "epoch": 0.01, "learning_rate": 4.964788847738054e-05, "loss": 4.6789, "step": 21504 }, { "epoch": 0.01, "learning_rate": 4.963951890867376e-05, "loss": 4.6558, "step": 22016 }, { "epoch": 0.01, "learning_rate": 4.963113296116324e-05, "loss": 4.6507, "step": 22528 }, { "epoch": 0.01, "learning_rate": 4.962274701365272e-05, "loss": 4.6451, "step": 23040 }, { "epoch": 0.01, "learning_rate": 4.96143610661422e-05, "loss": 4.6392, "step": 23552 }, { "epoch": 0.01, "learning_rate": 4.960597511863168e-05, "loss": 4.6264, "step": 24064 }, { "epoch": 0.01, "learning_rate": 4.959758917112116e-05, "loss": 4.6105, "step": 24576 }, { "epoch": 0.01, "learning_rate": 4.9589219602414374e-05, "loss": 4.6, "step": 25088 }, { "epoch": 0.01, "learning_rate": 4.958085003370758e-05, "loss": 4.6196, "step": 25600 }, { "epoch": 0.01, "learning_rate": 4.957246408619706e-05, "loss": 4.6088, "step": 26112 }, { "epoch": 0.01, "learning_rate": 4.956407813868654e-05, "loss": 4.5851, "step": 26624 }, { "epoch": 0.01, "learning_rate": 4.9555692191176016e-05, "loss": 4.5728, "step": 27136 }, { "epoch": 0.01, "learning_rate": 4.9547306243665496e-05, "loss": 4.5805, "step": 27648 }, { "epoch": 0.01, "learning_rate": 4.9538920296154976e-05, "loss": 4.5585, "step": 28160 }, { "epoch": 0.01, "learning_rate": 4.9530534348644456e-05, "loss": 4.5683, "step": 28672 }, { "epoch": 0.01, "learning_rate": 4.9522148401133936e-05, "loss": 4.5391, "step": 29184 }, { "epoch": 0.01, "learning_rate": 4.951376245362342e-05, "loss": 4.5604, "step": 29696 }, { "epoch": 0.01, "learning_rate": 4.950539288491663e-05, "loss": 4.5444, "step": 30208 }, { "epoch": 0.01, "learning_rate": 4.949700693740611e-05, "loss": 4.5224, "step": 30720 }, { "epoch": 0.01, "learning_rate": 4.948862098989559e-05, "loss": 4.5168, "step": 31232 }, { "epoch": 0.01, "learning_rate": 4.948023504238507e-05, "loss": 4.53, "step": 31744 }, { "epoch": 0.01, "learning_rate": 4.947184909487455e-05, "loss": 4.4904, "step": 32256 }, { "epoch": 0.01, "learning_rate": 4.946347952616776e-05, "loss": 4.5044, "step": 32768 }, { "epoch": 0.01, "learning_rate": 4.945509357865724e-05, "loss": 4.5108, "step": 33280 }, { "epoch": 0.01, "learning_rate": 4.944670763114672e-05, "loss": 4.495, "step": 33792 }, { "epoch": 0.01, "learning_rate": 4.94383216836362e-05, "loss": 4.4886, "step": 34304 }, { "epoch": 0.01, "learning_rate": 4.942995211492941e-05, "loss": 4.471, "step": 34816 }, { "epoch": 0.01, "learning_rate": 4.9421582546222625e-05, "loss": 4.4701, "step": 35328 }, { "epoch": 0.01, "learning_rate": 4.9413196598712105e-05, "loss": 4.4657, "step": 35840 }, { "epoch": 0.01, "learning_rate": 4.9404810651201585e-05, "loss": 4.483, "step": 36352 }, { "epoch": 0.01, "learning_rate": 4.9396424703691065e-05, "loss": 4.458, "step": 36864 }, { "epoch": 0.01, "learning_rate": 4.9388038756180545e-05, "loss": 4.468, "step": 37376 }, { "epoch": 0.01, "learning_rate": 4.9379652808670025e-05, "loss": 4.4616, "step": 37888 }, { "epoch": 0.01, "learning_rate": 4.9371266861159505e-05, "loss": 4.4608, "step": 38400 }, { "epoch": 0.01, "learning_rate": 4.9362897292452714e-05, "loss": 4.4439, "step": 38912 }, { "epoch": 0.01, "learning_rate": 4.9354511344942194e-05, "loss": 4.4426, "step": 39424 }, { "epoch": 0.01, "learning_rate": 4.9346125397431674e-05, "loss": 4.4391, "step": 39936 }, { "epoch": 0.01, "learning_rate": 4.9337739449921154e-05, "loss": 4.435, "step": 40448 }, { "epoch": 0.01, "learning_rate": 4.9329353502410634e-05, "loss": 4.4266, "step": 40960 }, { "epoch": 0.01, "learning_rate": 4.9320967554900114e-05, "loss": 4.4196, "step": 41472 }, { "epoch": 0.01, "learning_rate": 4.9312581607389594e-05, "loss": 4.4218, "step": 41984 }, { "epoch": 0.01, "learning_rate": 4.9304195659879074e-05, "loss": 4.4218, "step": 42496 }, { "epoch": 0.01, "learning_rate": 4.929582609117229e-05, "loss": 4.4004, "step": 43008 }, { "epoch": 0.01, "learning_rate": 4.928744014366177e-05, "loss": 4.4067, "step": 43520 }, { "epoch": 0.01, "learning_rate": 4.927905419615125e-05, "loss": 4.4066, "step": 44032 }, { "epoch": 0.01, "learning_rate": 4.927066824864073e-05, "loss": 4.4098, "step": 44544 }, { "epoch": 0.01, "learning_rate": 4.926229867993394e-05, "loss": 4.3933, "step": 45056 }, { "epoch": 0.01, "learning_rate": 4.925392911122715e-05, "loss": 4.3914, "step": 45568 }, { "epoch": 0.02, "learning_rate": 4.924554316371663e-05, "loss": 4.3841, "step": 46080 }, { "epoch": 0.02, "learning_rate": 4.923715721620611e-05, "loss": 4.3783, "step": 46592 }, { "epoch": 0.02, "learning_rate": 4.922877126869559e-05, "loss": 4.3791, "step": 47104 }, { "epoch": 0.02, "learning_rate": 4.922038532118507e-05, "loss": 4.3816, "step": 47616 }, { "epoch": 0.02, "learning_rate": 4.921201575247828e-05, "loss": 4.3752, "step": 48128 }, { "epoch": 0.02, "learning_rate": 4.920362980496776e-05, "loss": 4.3825, "step": 48640 }, { "epoch": 0.02, "learning_rate": 4.919524385745724e-05, "loss": 4.3724, "step": 49152 }, { "epoch": 0.02, "learning_rate": 4.918685790994672e-05, "loss": 4.3567, "step": 49664 }, { "epoch": 0.02, "learning_rate": 4.91784719624362e-05, "loss": 4.3554, "step": 50176 }, { "epoch": 0.02, "learning_rate": 4.9170086014925676e-05, "loss": 4.3648, "step": 50688 }, { "epoch": 0.02, "learning_rate": 4.9161700067415156e-05, "loss": 4.3604, "step": 51200 }, { "epoch": 0.02, "learning_rate": 4.9153314119904636e-05, "loss": 4.3596, "step": 51712 }, { "epoch": 0.02, "learning_rate": 4.914494455119785e-05, "loss": 4.3484, "step": 52224 }, { "epoch": 0.02, "learning_rate": 4.9136558603687325e-05, "loss": 4.3395, "step": 52736 }, { "epoch": 0.02, "learning_rate": 4.9128172656176805e-05, "loss": 4.3523, "step": 53248 }, { "epoch": 0.02, "learning_rate": 4.9119786708666285e-05, "loss": 4.3292, "step": 53760 }, { "epoch": 0.02, "learning_rate": 4.911143351876323e-05, "loss": 4.3351, "step": 54272 }, { "epoch": 0.02, "learning_rate": 4.910304757125272e-05, "loss": 4.3313, "step": 54784 }, { "epoch": 0.02, "learning_rate": 4.90946616237422e-05, "loss": 4.3313, "step": 55296 }, { "epoch": 0.02, "learning_rate": 4.908627567623168e-05, "loss": 4.321, "step": 55808 }, { "epoch": 0.02, "learning_rate": 4.907788972872115e-05, "loss": 4.3209, "step": 56320 }, { "epoch": 0.02, "learning_rate": 4.906950378121063e-05, "loss": 4.315, "step": 56832 }, { "epoch": 0.02, "learning_rate": 4.906111783370011e-05, "loss": 4.322, "step": 57344 }, { "epoch": 0.02, "learning_rate": 4.9052748264993326e-05, "loss": 4.3163, "step": 57856 }, { "epoch": 0.02, "learning_rate": 4.90443623174828e-05, "loss": 4.3067, "step": 58368 }, { "epoch": 0.02, "learning_rate": 4.903597636997228e-05, "loss": 4.3196, "step": 58880 }, { "epoch": 0.02, "learning_rate": 4.902759042246176e-05, "loss": 4.323, "step": 59392 }, { "epoch": 0.02, "learning_rate": 4.9019220853754975e-05, "loss": 4.3104, "step": 59904 }, { "epoch": 0.02, "learning_rate": 4.9010834906244455e-05, "loss": 4.2994, "step": 60416 }, { "epoch": 0.02, "learning_rate": 4.9002448958733935e-05, "loss": 4.2952, "step": 60928 }, { "epoch": 0.02, "learning_rate": 4.8994063011223415e-05, "loss": 4.2948, "step": 61440 }, { "epoch": 0.02, "learning_rate": 4.8985677063712895e-05, "loss": 4.3004, "step": 61952 }, { "epoch": 0.02, "learning_rate": 4.8977291116202375e-05, "loss": 4.2969, "step": 62464 }, { "epoch": 0.02, "learning_rate": 4.8968905168691855e-05, "loss": 4.2846, "step": 62976 }, { "epoch": 0.02, "learning_rate": 4.8960535599985064e-05, "loss": 4.2939, "step": 63488 }, { "epoch": 0.02, "learning_rate": 4.8952149652474544e-05, "loss": 4.2869, "step": 64000 }, { "epoch": 0.02, "learning_rate": 4.8943763704964024e-05, "loss": 4.2863, "step": 64512 }, { "epoch": 0.02, "learning_rate": 4.8935377757453504e-05, "loss": 4.2799, "step": 65024 }, { "epoch": 0.02, "learning_rate": 4.8926991809942984e-05, "loss": 4.2802, "step": 65536 }, { "epoch": 0.02, "learning_rate": 4.8918605862432463e-05, "loss": 4.2728, "step": 66048 }, { "epoch": 0.02, "learning_rate": 4.8910219914921943e-05, "loss": 4.2827, "step": 66560 }, { "epoch": 0.02, "learning_rate": 4.8901833967411423e-05, "loss": 4.2813, "step": 67072 }, { "epoch": 0.02, "learning_rate": 4.889346439870464e-05, "loss": 4.2799, "step": 67584 }, { "epoch": 0.02, "learning_rate": 4.888507845119412e-05, "loss": 4.2573, "step": 68096 }, { "epoch": 0.02, "learning_rate": 4.887670888248733e-05, "loss": 4.2724, "step": 68608 }, { "epoch": 0.02, "learning_rate": 4.886832293497681e-05, "loss": 4.2666, "step": 69120 }, { "epoch": 0.02, "learning_rate": 4.885993698746629e-05, "loss": 4.2693, "step": 69632 }, { "epoch": 0.02, "learning_rate": 4.885155103995577e-05, "loss": 4.2594, "step": 70144 }, { "epoch": 0.02, "learning_rate": 4.884316509244525e-05, "loss": 4.2672, "step": 70656 }, { "epoch": 0.02, "learning_rate": 4.883479552373846e-05, "loss": 4.2572, "step": 71168 }, { "epoch": 0.02, "learning_rate": 4.882640957622794e-05, "loss": 4.2737, "step": 71680 }, { "epoch": 0.02, "learning_rate": 4.881802362871742e-05, "loss": 4.2439, "step": 72192 }, { "epoch": 0.02, "learning_rate": 4.88096376812069e-05, "loss": 4.2614, "step": 72704 }, { "epoch": 0.02, "learning_rate": 4.880125173369638e-05, "loss": 4.2468, "step": 73216 }, { "epoch": 0.02, "learning_rate": 4.8792882164989586e-05, "loss": 4.2432, "step": 73728 }, { "epoch": 0.02, "learning_rate": 4.878449621747907e-05, "loss": 4.2471, "step": 74240 }, { "epoch": 0.02, "learning_rate": 4.877611026996855e-05, "loss": 4.2341, "step": 74752 }, { "epoch": 0.02, "learning_rate": 4.876772432245803e-05, "loss": 4.2379, "step": 75264 }, { "epoch": 0.02, "learning_rate": 4.875933837494751e-05, "loss": 4.2444, "step": 75776 }, { "epoch": 0.02, "learning_rate": 4.8750952427436986e-05, "loss": 4.2329, "step": 76288 }, { "epoch": 0.03, "eval_loss": 4.200936317443848, "eval_runtime": 303.3774, "eval_samples_per_second": 1257.81, "eval_steps_per_second": 39.307, "step": 76320 }, { "epoch": 1.0, "learning_rate": 4.8742566479926466e-05, "loss": 4.2284, "step": 76800 }, { "epoch": 1.0, "learning_rate": 4.8734180532415946e-05, "loss": 4.2245, "step": 77312 }, { "epoch": 1.0, "learning_rate": 4.872581096370916e-05, "loss": 4.2383, "step": 77824 }, { "epoch": 1.0, "learning_rate": 4.8717425016198635e-05, "loss": 4.2284, "step": 78336 }, { "epoch": 1.0, "learning_rate": 4.8709039068688115e-05, "loss": 4.2377, "step": 78848 }, { "epoch": 1.0, "learning_rate": 4.8700653121177595e-05, "loss": 4.2149, "step": 79360 }, { "epoch": 1.0, "learning_rate": 4.8692267173667075e-05, "loss": 4.2172, "step": 79872 }, { "epoch": 1.0, "learning_rate": 4.8683881226156555e-05, "loss": 4.2077, "step": 80384 }, { "epoch": 1.0, "learning_rate": 4.867551165744977e-05, "loss": 4.2168, "step": 80896 }, { "epoch": 1.0, "learning_rate": 4.866712570993925e-05, "loss": 4.2138, "step": 81408 }, { "epoch": 1.0, "learning_rate": 4.865873976242873e-05, "loss": 4.2097, "step": 81920 }, { "epoch": 1.0, "learning_rate": 4.865035381491821e-05, "loss": 4.2144, "step": 82432 }, { "epoch": 1.0, "learning_rate": 4.864198424621142e-05, "loss": 4.1946, "step": 82944 }, { "epoch": 1.0, "learning_rate": 4.86335982987009e-05, "loss": 4.2068, "step": 83456 }, { "epoch": 1.0, "learning_rate": 4.862521235119038e-05, "loss": 4.1924, "step": 83968 }, { "epoch": 1.0, "learning_rate": 4.861682640367986e-05, "loss": 4.193, "step": 84480 }, { "epoch": 1.0, "learning_rate": 4.860844045616934e-05, "loss": 4.1975, "step": 84992 }, { "epoch": 1.0, "learning_rate": 4.860005450865882e-05, "loss": 4.1908, "step": 85504 }, { "epoch": 1.0, "learning_rate": 4.85916685611483e-05, "loss": 4.1948, "step": 86016 }, { "epoch": 1.0, "learning_rate": 4.858328261363778e-05, "loss": 4.2094, "step": 86528 }, { "epoch": 1.0, "learning_rate": 4.857489666612726e-05, "loss": 4.1843, "step": 87040 }, { "epoch": 1.0, "learning_rate": 4.8566527097420475e-05, "loss": 4.1883, "step": 87552 }, { "epoch": 1.0, "learning_rate": 4.8558141149909955e-05, "loss": 4.1875, "step": 88064 }, { "epoch": 1.0, "learning_rate": 4.8549755202399435e-05, "loss": 4.1935, "step": 88576 }, { "epoch": 1.0, "learning_rate": 4.8541369254888915e-05, "loss": 4.1843, "step": 89088 }, { "epoch": 1.0, "learning_rate": 4.8532983307378395e-05, "loss": 4.1848, "step": 89600 }, { "epoch": 1.0, "learning_rate": 4.8524613738671604e-05, "loss": 4.1704, "step": 90112 }, { "epoch": 1.0, "learning_rate": 4.8516227791161084e-05, "loss": 4.1762, "step": 90624 }, { "epoch": 1.0, "learning_rate": 4.8507841843650564e-05, "loss": 4.1656, "step": 91136 }, { "epoch": 1.01, "learning_rate": 4.8499455896140044e-05, "loss": 4.175, "step": 91648 }, { "epoch": 1.01, "learning_rate": 4.8491069948629524e-05, "loss": 4.1702, "step": 92160 }, { "epoch": 1.01, "learning_rate": 4.848270037992273e-05, "loss": 4.1736, "step": 92672 }, { "epoch": 1.01, "learning_rate": 4.847431443241221e-05, "loss": 4.1779, "step": 93184 }, { "epoch": 1.01, "learning_rate": 4.846592848490169e-05, "loss": 4.1655, "step": 93696 }, { "epoch": 1.01, "learning_rate": 4.845755891619491e-05, "loss": 4.1719, "step": 94208 }, { "epoch": 1.01, "learning_rate": 4.844917296868439e-05, "loss": 4.1682, "step": 94720 }, { "epoch": 1.01, "learning_rate": 4.844078702117387e-05, "loss": 4.1574, "step": 95232 }, { "epoch": 1.01, "learning_rate": 4.843240107366335e-05, "loss": 4.1509, "step": 95744 }, { "epoch": 1.01, "learning_rate": 4.842401512615282e-05, "loss": 4.1432, "step": 96256 }, { "epoch": 1.01, "learning_rate": 4.84156291786423e-05, "loss": 4.1506, "step": 96768 }, { "epoch": 1.01, "learning_rate": 4.840724323113178e-05, "loss": 4.1483, "step": 97280 }, { "epoch": 1.01, "learning_rate": 4.839885728362126e-05, "loss": 4.1594, "step": 97792 }, { "epoch": 1.01, "learning_rate": 4.839047133611074e-05, "loss": 4.1446, "step": 98304 }, { "epoch": 1.01, "learning_rate": 4.838208538860022e-05, "loss": 4.1449, "step": 98816 }, { "epoch": 1.01, "learning_rate": 4.837371581989343e-05, "loss": 4.1496, "step": 99328 }, { "epoch": 1.01, "learning_rate": 4.836532987238292e-05, "loss": 4.1418, "step": 99840 }, { "epoch": 1.01, "learning_rate": 4.83569439248724e-05, "loss": 4.1443, "step": 100352 }, { "epoch": 1.01, "learning_rate": 4.834855797736188e-05, "loss": 4.1306, "step": 100864 }, { "epoch": 1.01, "learning_rate": 4.8340188408655086e-05, "loss": 4.1282, "step": 101376 }, { "epoch": 1.01, "learning_rate": 4.8331802461144566e-05, "loss": 4.152, "step": 101888 }, { "epoch": 1.01, "learning_rate": 4.8323416513634046e-05, "loss": 4.1481, "step": 102400 }, { "epoch": 1.01, "learning_rate": 4.8315030566123526e-05, "loss": 4.131, "step": 102912 }, { "epoch": 1.01, "learning_rate": 4.8306644618613006e-05, "loss": 4.1331, "step": 103424 }, { "epoch": 1.01, "learning_rate": 4.8298275049906215e-05, "loss": 4.1391, "step": 103936 }, { "epoch": 1.01, "learning_rate": 4.8289889102395695e-05, "loss": 4.1196, "step": 104448 }, { "epoch": 1.01, "learning_rate": 4.8281503154885175e-05, "loss": 4.1384, "step": 104960 }, { "epoch": 1.01, "learning_rate": 4.8273117207374655e-05, "loss": 4.1138, "step": 105472 }, { "epoch": 1.01, "learning_rate": 4.8264731259864135e-05, "loss": 4.1401, "step": 105984 }, { "epoch": 1.01, "learning_rate": 4.8256345312353615e-05, "loss": 4.1346, "step": 106496 }, { "epoch": 1.01, "learning_rate": 4.8247959364843095e-05, "loss": 4.1165, "step": 107008 }, { "epoch": 1.01, "learning_rate": 4.823958979613631e-05, "loss": 4.1145, "step": 107520 }, { "epoch": 1.01, "learning_rate": 4.823120384862579e-05, "loss": 4.1289, "step": 108032 }, { "epoch": 1.01, "learning_rate": 4.822281790111527e-05, "loss": 4.0973, "step": 108544 }, { "epoch": 1.01, "learning_rate": 4.821443195360475e-05, "loss": 4.1129, "step": 109056 }, { "epoch": 1.01, "learning_rate": 4.820606238489796e-05, "loss": 4.1245, "step": 109568 }, { "epoch": 1.01, "learning_rate": 4.819767643738744e-05, "loss": 4.1161, "step": 110080 }, { "epoch": 1.01, "learning_rate": 4.818929048987692e-05, "loss": 4.1088, "step": 110592 }, { "epoch": 1.01, "learning_rate": 4.81809045423664e-05, "loss": 4.0975, "step": 111104 }, { "epoch": 1.01, "learning_rate": 4.817255135246334e-05, "loss": 4.1041, "step": 111616 }, { "epoch": 1.01, "learning_rate": 4.816416540495282e-05, "loss": 4.1054, "step": 112128 }, { "epoch": 1.01, "learning_rate": 4.8155779457442305e-05, "loss": 4.1117, "step": 112640 }, { "epoch": 1.01, "learning_rate": 4.8147393509931785e-05, "loss": 4.1015, "step": 113152 }, { "epoch": 1.01, "learning_rate": 4.8139007562421265e-05, "loss": 4.1116, "step": 113664 }, { "epoch": 1.01, "learning_rate": 4.8130621614910745e-05, "loss": 4.1126, "step": 114176 }, { "epoch": 1.01, "learning_rate": 4.8122235667400224e-05, "loss": 4.1107, "step": 114688 }, { "epoch": 1.01, "learning_rate": 4.8113849719889704e-05, "loss": 4.0946, "step": 115200 }, { "epoch": 1.01, "learning_rate": 4.8105480151182914e-05, "loss": 4.1032, "step": 115712 }, { "epoch": 1.01, "learning_rate": 4.8097094203672393e-05, "loss": 4.1025, "step": 116224 }, { "epoch": 1.01, "learning_rate": 4.8088708256161873e-05, "loss": 4.0981, "step": 116736 }, { "epoch": 1.01, "learning_rate": 4.808032230865135e-05, "loss": 4.0955, "step": 117248 }, { "epoch": 1.01, "learning_rate": 4.8071936361140827e-05, "loss": 4.0918, "step": 117760 }, { "epoch": 1.01, "learning_rate": 4.806356679243404e-05, "loss": 4.1002, "step": 118272 }, { "epoch": 1.01, "learning_rate": 4.805518084492352e-05, "loss": 4.095, "step": 118784 }, { "epoch": 1.01, "learning_rate": 4.8046794897413e-05, "loss": 4.0801, "step": 119296 }, { "epoch": 1.01, "learning_rate": 4.803840894990248e-05, "loss": 4.0878, "step": 119808 }, { "epoch": 1.01, "learning_rate": 4.80300393811957e-05, "loss": 4.0892, "step": 120320 }, { "epoch": 1.01, "learning_rate": 4.802165343368518e-05, "loss": 4.0959, "step": 120832 }, { "epoch": 1.01, "learning_rate": 4.801326748617466e-05, "loss": 4.0873, "step": 121344 }, { "epoch": 1.01, "learning_rate": 4.800488153866413e-05, "loss": 4.0824, "step": 121856 }, { "epoch": 1.02, "learning_rate": 4.799649559115361e-05, "loss": 4.0816, "step": 122368 }, { "epoch": 1.02, "learning_rate": 4.798812602244683e-05, "loss": 4.0728, "step": 122880 }, { "epoch": 1.02, "learning_rate": 4.79797400749363e-05, "loss": 4.0769, "step": 123392 }, { "epoch": 1.02, "learning_rate": 4.797135412742578e-05, "loss": 4.0861, "step": 123904 }, { "epoch": 1.02, "learning_rate": 4.796296817991526e-05, "loss": 4.0831, "step": 124416 }, { "epoch": 1.02, "learning_rate": 4.7954598611208476e-05, "loss": 4.0915, "step": 124928 }, { "epoch": 1.02, "learning_rate": 4.7946212663697956e-05, "loss": 4.081, "step": 125440 }, { "epoch": 1.02, "learning_rate": 4.7937826716187436e-05, "loss": 4.0724, "step": 125952 }, { "epoch": 1.02, "learning_rate": 4.7929440768676916e-05, "loss": 4.071, "step": 126464 }, { "epoch": 1.02, "learning_rate": 4.7921054821166396e-05, "loss": 4.0783, "step": 126976 }, { "epoch": 1.02, "learning_rate": 4.7912685252459605e-05, "loss": 4.0827, "step": 127488 }, { "epoch": 1.02, "learning_rate": 4.7904299304949085e-05, "loss": 4.082, "step": 128000 }, { "epoch": 1.02, "learning_rate": 4.7895913357438565e-05, "loss": 4.0721, "step": 128512 }, { "epoch": 1.02, "learning_rate": 4.7887527409928045e-05, "loss": 4.0617, "step": 129024 }, { "epoch": 1.02, "learning_rate": 4.7879157841221254e-05, "loss": 4.0815, "step": 129536 }, { "epoch": 1.02, "learning_rate": 4.7870771893710734e-05, "loss": 4.0601, "step": 130048 }, { "epoch": 1.02, "learning_rate": 4.786240232500395e-05, "loss": 4.0673, "step": 130560 }, { "epoch": 1.02, "learning_rate": 4.785401637749343e-05, "loss": 4.0671, "step": 131072 }, { "epoch": 1.02, "learning_rate": 4.784563042998291e-05, "loss": 4.0657, "step": 131584 }, { "epoch": 1.02, "learning_rate": 4.783724448247239e-05, "loss": 4.0545, "step": 132096 }, { "epoch": 1.02, "learning_rate": 4.782885853496187e-05, "loss": 4.0638, "step": 132608 }, { "epoch": 1.02, "learning_rate": 4.782047258745135e-05, "loss": 4.0539, "step": 133120 }, { "epoch": 1.02, "learning_rate": 4.781208663994083e-05, "loss": 4.0633, "step": 133632 }, { "epoch": 1.02, "learning_rate": 4.780370069243031e-05, "loss": 4.0609, "step": 134144 }, { "epoch": 1.02, "learning_rate": 4.779531474491979e-05, "loss": 4.0529, "step": 134656 }, { "epoch": 1.02, "learning_rate": 4.7786945176213e-05, "loss": 4.0737, "step": 135168 }, { "epoch": 1.02, "learning_rate": 4.777855922870248e-05, "loss": 4.072, "step": 135680 }, { "epoch": 1.02, "learning_rate": 4.777017328119196e-05, "loss": 4.064, "step": 136192 }, { "epoch": 1.02, "learning_rate": 4.776178733368144e-05, "loss": 4.0552, "step": 136704 }, { "epoch": 1.02, "learning_rate": 4.775340138617092e-05, "loss": 4.0483, "step": 137216 }, { "epoch": 1.02, "learning_rate": 4.7745031817464134e-05, "loss": 4.0548, "step": 137728 }, { "epoch": 1.02, "learning_rate": 4.7736645869953614e-05, "loss": 4.0513, "step": 138240 }, { "epoch": 1.02, "learning_rate": 4.7728259922443094e-05, "loss": 4.061, "step": 138752 }, { "epoch": 1.02, "learning_rate": 4.7719873974932574e-05, "loss": 4.043, "step": 139264 }, { "epoch": 1.02, "learning_rate": 4.771150440622578e-05, "loss": 4.0527, "step": 139776 }, { "epoch": 1.02, "learning_rate": 4.770311845871526e-05, "loss": 4.0543, "step": 140288 }, { "epoch": 1.02, "learning_rate": 4.769473251120474e-05, "loss": 4.0552, "step": 140800 }, { "epoch": 1.02, "learning_rate": 4.768634656369422e-05, "loss": 4.0429, "step": 141312 }, { "epoch": 1.02, "learning_rate": 4.767797699498743e-05, "loss": 4.0489, "step": 141824 }, { "epoch": 1.02, "learning_rate": 4.766959104747691e-05, "loss": 4.0479, "step": 142336 }, { "epoch": 1.02, "learning_rate": 4.766120509996639e-05, "loss": 4.0496, "step": 142848 }, { "epoch": 1.02, "learning_rate": 4.765281915245587e-05, "loss": 4.0541, "step": 143360 }, { "epoch": 1.02, "learning_rate": 4.764444958374909e-05, "loss": 4.0545, "step": 143872 }, { "epoch": 1.02, "learning_rate": 4.763606363623857e-05, "loss": 4.0322, "step": 144384 }, { "epoch": 1.02, "learning_rate": 4.762767768872805e-05, "loss": 4.0452, "step": 144896 }, { "epoch": 1.02, "learning_rate": 4.761930812002126e-05, "loss": 4.0486, "step": 145408 }, { "epoch": 1.02, "learning_rate": 4.761092217251074e-05, "loss": 4.0459, "step": 145920 }, { "epoch": 1.02, "learning_rate": 4.760253622500022e-05, "loss": 4.0417, "step": 146432 }, { "epoch": 1.02, "learning_rate": 4.75941502774897e-05, "loss": 4.0482, "step": 146944 }, { "epoch": 1.02, "learning_rate": 4.758576432997918e-05, "loss": 4.0414, "step": 147456 }, { "epoch": 1.02, "learning_rate": 4.757737838246866e-05, "loss": 4.0585, "step": 147968 }, { "epoch": 1.02, "learning_rate": 4.7568992434958137e-05, "loss": 4.0316, "step": 148480 }, { "epoch": 1.02, "learning_rate": 4.7560622866251346e-05, "loss": 4.0462, "step": 148992 }, { "epoch": 1.02, "learning_rate": 4.7552236918740826e-05, "loss": 4.0367, "step": 149504 }, { "epoch": 1.02, "learning_rate": 4.7543850971230306e-05, "loss": 4.0306, "step": 150016 }, { "epoch": 1.02, "learning_rate": 4.753548140252352e-05, "loss": 4.0378, "step": 150528 }, { "epoch": 1.02, "learning_rate": 4.7527095455013e-05, "loss": 4.0289, "step": 151040 }, { "epoch": 1.02, "learning_rate": 4.751870950750248e-05, "loss": 4.0302, "step": 151552 }, { "epoch": 1.02, "learning_rate": 4.751032355999196e-05, "loss": 4.0317, "step": 152064 }, { "epoch": 1.02, "learning_rate": 4.7501937612481435e-05, "loss": 4.0289, "step": 152576 }, { "epoch": 1.03, "eval_loss": 4.030747413635254, "eval_runtime": 317.6174, "eval_samples_per_second": 1201.417, "eval_steps_per_second": 37.545, "step": 152640 }, { "epoch": 0.0, "learning_rate": 4.7493551664970914e-05, "loss": 4.0236, "step": 153088 }, { "epoch": 0.0, "learning_rate": 4.7485165717460394e-05, "loss": 4.0207, "step": 153600 }, { "epoch": 0.0, "learning_rate": 4.7476779769949874e-05, "loss": 4.0383, "step": 154112 }, { "epoch": 0.0, "learning_rate": 4.7468393822439354e-05, "loss": 4.0271, "step": 154624 }, { "epoch": 0.0, "learning_rate": 4.7460007874928834e-05, "loss": 4.0439, "step": 155136 }, { "epoch": 0.0, "learning_rate": 4.7451621927418314e-05, "loss": 4.0167, "step": 155648 }, { "epoch": 0.0, "learning_rate": 4.7443235979907794e-05, "loss": 4.0239, "step": 156160 }, { "epoch": 0.0, "learning_rate": 4.7434850032397274e-05, "loss": 4.0108, "step": 156672 }, { "epoch": 0.0, "learning_rate": 4.7426464084886754e-05, "loss": 4.0255, "step": 157184 }, { "epoch": 0.0, "learning_rate": 4.7418078137376234e-05, "loss": 4.0209, "step": 157696 }, { "epoch": 0.0, "learning_rate": 4.740969218986572e-05, "loss": 4.0158, "step": 158208 }, { "epoch": 0.0, "learning_rate": 4.740132262115893e-05, "loss": 4.0285, "step": 158720 }, { "epoch": 0.0, "learning_rate": 4.739295305245214e-05, "loss": 4.0052, "step": 159232 }, { "epoch": 0.0, "learning_rate": 4.738456710494162e-05, "loss": 4.022, "step": 159744 }, { "epoch": 0.0, "learning_rate": 4.73761811574311e-05, "loss": 4.0038, "step": 160256 }, { "epoch": 0.0, "learning_rate": 4.736779520992058e-05, "loss": 4.0067, "step": 160768 }, { "epoch": 0.0, "learning_rate": 4.735940926241006e-05, "loss": 4.005, "step": 161280 }, { "epoch": 0.0, "learning_rate": 4.735102331489954e-05, "loss": 4.0143, "step": 161792 }, { "epoch": 0.0, "learning_rate": 4.734263736738902e-05, "loss": 4.0088, "step": 162304 }, { "epoch": 0.0, "learning_rate": 4.73342514198785e-05, "loss": 4.0286, "step": 162816 }, { "epoch": 0.0, "learning_rate": 4.732588185117171e-05, "loss": 4.0062, "step": 163328 }, { "epoch": 0.0, "learning_rate": 4.731749590366119e-05, "loss": 4.0108, "step": 163840 }, { "epoch": 0.0, "learning_rate": 4.7309109956150674e-05, "loss": 4.0087, "step": 164352 }, { "epoch": 0.0, "learning_rate": 4.7300724008640154e-05, "loss": 4.0156, "step": 164864 }, { "epoch": 0.0, "learning_rate": 4.7292354439933364e-05, "loss": 4.0045, "step": 165376 }, { "epoch": 0.0, "learning_rate": 4.7283968492422844e-05, "loss": 4.0103, "step": 165888 }, { "epoch": 0.0, "learning_rate": 4.7275582544912323e-05, "loss": 3.9977, "step": 166400 }, { "epoch": 0.0, "learning_rate": 4.72671965974018e-05, "loss": 4.0036, "step": 166912 }, { "epoch": 0.0, "learning_rate": 4.725882702869501e-05, "loss": 3.991, "step": 167424 }, { "epoch": 0.01, "learning_rate": 4.725044108118449e-05, "loss": 4.0048, "step": 167936 }, { "epoch": 0.01, "learning_rate": 4.724205513367397e-05, "loss": 4.0034, "step": 168448 }, { "epoch": 0.01, "learning_rate": 4.723368556496718e-05, "loss": 4.0037, "step": 168960 }, { "epoch": 0.01, "learning_rate": 4.722529961745666e-05, "loss": 4.0112, "step": 169472 }, { "epoch": 0.01, "learning_rate": 4.721691366994614e-05, "loss": 3.9987, "step": 169984 }, { "epoch": 0.01, "learning_rate": 4.720854410123936e-05, "loss": 3.9976, "step": 170496 }, { "epoch": 0.01, "learning_rate": 4.720015815372884e-05, "loss": 4.0052, "step": 171008 }, { "epoch": 0.01, "learning_rate": 4.719177220621832e-05, "loss": 3.9932, "step": 171520 }, { "epoch": 0.01, "learning_rate": 4.71833862587078e-05, "loss": 3.9868, "step": 172032 }, { "epoch": 0.01, "learning_rate": 4.717500031119727e-05, "loss": 3.9785, "step": 172544 }, { "epoch": 0.01, "learning_rate": 4.716661436368675e-05, "loss": 3.9864, "step": 173056 }, { "epoch": 0.01, "learning_rate": 4.715822841617623e-05, "loss": 3.987, "step": 173568 }, { "epoch": 0.01, "learning_rate": 4.714984246866571e-05, "loss": 3.9975, "step": 174080 }, { "epoch": 0.01, "learning_rate": 4.714147289995892e-05, "loss": 3.9872, "step": 174592 }, { "epoch": 0.01, "learning_rate": 4.71330869524484e-05, "loss": 3.9797, "step": 175104 }, { "epoch": 0.01, "learning_rate": 4.712470100493788e-05, "loss": 3.9943, "step": 175616 }, { "epoch": 0.01, "learning_rate": 4.7116315057427366e-05, "loss": 3.9865, "step": 176128 }, { "epoch": 0.01, "learning_rate": 4.7107945488720575e-05, "loss": 3.9843, "step": 176640 }, { "epoch": 0.01, "learning_rate": 4.7099559541210055e-05, "loss": 3.9756, "step": 177152 }, { "epoch": 0.01, "learning_rate": 4.7091173593699535e-05, "loss": 3.9697, "step": 177664 }, { "epoch": 0.01, "learning_rate": 4.7082787646189015e-05, "loss": 3.996, "step": 178176 }, { "epoch": 0.01, "learning_rate": 4.7074418077482224e-05, "loss": 3.9941, "step": 178688 }, { "epoch": 0.01, "learning_rate": 4.7066032129971704e-05, "loss": 3.9787, "step": 179200 }, { "epoch": 0.01, "learning_rate": 4.7057646182461184e-05, "loss": 3.9796, "step": 179712 }, { "epoch": 0.01, "learning_rate": 4.704927661375439e-05, "loss": 3.9874, "step": 180224 }, { "epoch": 0.01, "learning_rate": 4.704089066624387e-05, "loss": 3.9647, "step": 180736 }, { "epoch": 0.01, "learning_rate": 4.703250471873335e-05, "loss": 3.9848, "step": 181248 }, { "epoch": 0.01, "learning_rate": 4.702411877122283e-05, "loss": 3.9652, "step": 181760 }, { "epoch": 0.01, "learning_rate": 4.701573282371232e-05, "loss": 3.9849, "step": 182272 }, { "epoch": 0.01, "learning_rate": 4.70073468762018e-05, "loss": 3.9901, "step": 182784 }, { "epoch": 0.01, "learning_rate": 4.699896092869128e-05, "loss": 3.9705, "step": 183296 }, { "epoch": 0.01, "learning_rate": 4.699059135998449e-05, "loss": 3.9634, "step": 183808 }, { "epoch": 0.01, "learning_rate": 4.698220541247397e-05, "loss": 3.9835, "step": 184320 }, { "epoch": 0.01, "learning_rate": 4.697381946496345e-05, "loss": 3.9542, "step": 184832 }, { "epoch": 0.01, "learning_rate": 4.696543351745293e-05, "loss": 3.9682, "step": 185344 }, { "epoch": 0.01, "learning_rate": 4.695706394874614e-05, "loss": 3.9779, "step": 185856 }, { "epoch": 0.01, "learning_rate": 4.694867800123562e-05, "loss": 3.9753, "step": 186368 }, { "epoch": 0.01, "learning_rate": 4.69402920537251e-05, "loss": 3.9671, "step": 186880 }, { "epoch": 0.01, "learning_rate": 4.693190610621458e-05, "loss": 3.9555, "step": 187392 }, { "epoch": 0.01, "learning_rate": 4.692355291631152e-05, "loss": 3.9593, "step": 187904 }, { "epoch": 0.01, "learning_rate": 4.6915166968801e-05, "loss": 3.9619, "step": 188416 }, { "epoch": 0.01, "learning_rate": 4.690678102129048e-05, "loss": 3.9722, "step": 188928 }, { "epoch": 0.01, "learning_rate": 4.689839507377996e-05, "loss": 3.9602, "step": 189440 }, { "epoch": 0.01, "learning_rate": 4.689000912626944e-05, "loss": 3.9732, "step": 189952 }, { "epoch": 0.01, "learning_rate": 4.688162317875892e-05, "loss": 3.9726, "step": 190464 }, { "epoch": 0.01, "learning_rate": 4.68732372312484e-05, "loss": 3.9722, "step": 190976 }, { "epoch": 0.01, "learning_rate": 4.686485128373788e-05, "loss": 3.9563, "step": 191488 }, { "epoch": 0.01, "learning_rate": 4.685648171503109e-05, "loss": 3.9632, "step": 192000 }, { "epoch": 0.01, "learning_rate": 4.684809576752057e-05, "loss": 3.9677, "step": 192512 }, { "epoch": 0.01, "learning_rate": 4.683970982001005e-05, "loss": 3.9595, "step": 193024 }, { "epoch": 0.01, "learning_rate": 4.683132387249953e-05, "loss": 3.9614, "step": 193536 }, { "epoch": 0.01, "learning_rate": 4.682295430379274e-05, "loss": 3.9611, "step": 194048 }, { "epoch": 0.01, "learning_rate": 4.681456835628222e-05, "loss": 3.9591, "step": 194560 }, { "epoch": 0.01, "learning_rate": 4.680618240877171e-05, "loss": 3.9637, "step": 195072 }, { "epoch": 0.01, "learning_rate": 4.679779646126119e-05, "loss": 3.9452, "step": 195584 }, { "epoch": 0.01, "learning_rate": 4.6789426892554396e-05, "loss": 3.9573, "step": 196096 }, { "epoch": 0.01, "learning_rate": 4.6781040945043876e-05, "loss": 3.9553, "step": 196608 }, { "epoch": 0.01, "learning_rate": 4.6772654997533356e-05, "loss": 3.9647, "step": 197120 }, { "epoch": 0.01, "learning_rate": 4.6764269050022836e-05, "loss": 3.9546, "step": 197632 }, { "epoch": 0.01, "learning_rate": 4.6755899481316045e-05, "loss": 3.9523, "step": 198144 }, { "epoch": 0.02, "learning_rate": 4.6747513533805525e-05, "loss": 3.9498, "step": 198656 }, { "epoch": 0.02, "learning_rate": 4.6739127586295005e-05, "loss": 3.9457, "step": 199168 }, { "epoch": 0.02, "learning_rate": 4.6730741638784485e-05, "loss": 3.9438, "step": 199680 }, { "epoch": 0.02, "learning_rate": 4.6722372070077694e-05, "loss": 3.9537, "step": 200192 }, { "epoch": 0.02, "learning_rate": 4.6713986122567174e-05, "loss": 3.963, "step": 200704 }, { "epoch": 0.02, "learning_rate": 4.670560017505666e-05, "loss": 3.9611, "step": 201216 }, { "epoch": 0.02, "learning_rate": 4.669723060634987e-05, "loss": 3.953, "step": 201728 }, { "epoch": 0.02, "learning_rate": 4.668884465883935e-05, "loss": 3.9447, "step": 202240 }, { "epoch": 0.02, "learning_rate": 4.668045871132883e-05, "loss": 3.9478, "step": 202752 }, { "epoch": 0.02, "learning_rate": 4.667207276381831e-05, "loss": 3.9482, "step": 203264 }, { "epoch": 0.02, "learning_rate": 4.666368681630779e-05, "loss": 3.9573, "step": 203776 }, { "epoch": 0.02, "learning_rate": 4.665530086879727e-05, "loss": 3.9552, "step": 204288 }, { "epoch": 0.02, "learning_rate": 4.664691492128675e-05, "loss": 3.9473, "step": 204800 }, { "epoch": 0.02, "learning_rate": 4.663852897377623e-05, "loss": 3.9376, "step": 205312 }, { "epoch": 0.02, "learning_rate": 4.663015940506944e-05, "loss": 3.9587, "step": 205824 }, { "epoch": 0.02, "learning_rate": 4.662177345755892e-05, "loss": 3.9363, "step": 206336 }, { "epoch": 0.02, "learning_rate": 4.66133875100484e-05, "loss": 3.9467, "step": 206848 }, { "epoch": 0.02, "learning_rate": 4.660500156253788e-05, "loss": 3.9397, "step": 207360 }, { "epoch": 0.02, "learning_rate": 4.6596631993831094e-05, "loss": 3.9446, "step": 207872 }, { "epoch": 0.02, "learning_rate": 4.65882624251243e-05, "loss": 3.9359, "step": 208384 }, { "epoch": 0.02, "learning_rate": 4.657987647761378e-05, "loss": 3.9447, "step": 208896 }, { "epoch": 0.02, "learning_rate": 4.657149053010326e-05, "loss": 3.936, "step": 209408 }, { "epoch": 0.02, "learning_rate": 4.656310458259274e-05, "loss": 3.9367, "step": 209920 }, { "epoch": 0.02, "learning_rate": 4.655471863508222e-05, "loss": 3.9474, "step": 210432 }, { "epoch": 0.02, "learning_rate": 4.65463326875717e-05, "loss": 3.9315, "step": 210944 }, { "epoch": 0.02, "learning_rate": 4.6537946740061176e-05, "loss": 3.9549, "step": 211456 }, { "epoch": 0.02, "learning_rate": 4.6529560792550656e-05, "loss": 3.9524, "step": 211968 }, { "epoch": 0.02, "learning_rate": 4.652119122384387e-05, "loss": 3.9445, "step": 212480 }, { "epoch": 0.02, "learning_rate": 4.651280527633335e-05, "loss": 3.9369, "step": 212992 }, { "epoch": 0.02, "learning_rate": 4.650441932882283e-05, "loss": 3.9336, "step": 213504 }, { "epoch": 0.02, "learning_rate": 4.649603338131231e-05, "loss": 3.9352, "step": 214016 }, { "epoch": 0.02, "learning_rate": 4.648766381260553e-05, "loss": 3.9354, "step": 214528 }, { "epoch": 0.02, "learning_rate": 4.6479277865095e-05, "loss": 3.9426, "step": 215040 }, { "epoch": 0.02, "learning_rate": 4.647089191758448e-05, "loss": 3.9261, "step": 215552 }, { "epoch": 0.02, "learning_rate": 4.646250597007396e-05, "loss": 3.9374, "step": 216064 }, { "epoch": 0.02, "learning_rate": 4.645413640136718e-05, "loss": 3.9411, "step": 216576 }, { "epoch": 0.02, "learning_rate": 4.644575045385665e-05, "loss": 3.9379, "step": 217088 }, { "epoch": 0.02, "learning_rate": 4.643736450634613e-05, "loss": 3.9298, "step": 217600 }, { "epoch": 0.02, "learning_rate": 4.642897855883561e-05, "loss": 3.9321, "step": 218112 }, { "epoch": 0.02, "learning_rate": 4.642060899012882e-05, "loss": 3.9357, "step": 218624 }, { "epoch": 0.02, "learning_rate": 4.6412223042618306e-05, "loss": 3.9365, "step": 219136 }, { "epoch": 0.02, "learning_rate": 4.6403837095107786e-05, "loss": 3.938, "step": 219648 }, { "epoch": 0.02, "learning_rate": 4.6395451147597266e-05, "loss": 3.9427, "step": 220160 }, { "epoch": 0.02, "learning_rate": 4.6387081578890475e-05, "loss": 3.9188, "step": 220672 }, { "epoch": 0.02, "learning_rate": 4.6378695631379955e-05, "loss": 3.9358, "step": 221184 }, { "epoch": 0.02, "learning_rate": 4.6370309683869435e-05, "loss": 3.9372, "step": 221696 }, { "epoch": 0.02, "learning_rate": 4.6361923736358915e-05, "loss": 3.9319, "step": 222208 }, { "epoch": 0.02, "learning_rate": 4.6353554167652124e-05, "loss": 3.9297, "step": 222720 }, { "epoch": 0.02, "learning_rate": 4.6345168220141604e-05, "loss": 3.9416, "step": 223232 }, { "epoch": 0.02, "learning_rate": 4.633679865143482e-05, "loss": 3.9316, "step": 223744 }, { "epoch": 0.02, "learning_rate": 4.632841270392429e-05, "loss": 3.9469, "step": 224256 }, { "epoch": 0.02, "learning_rate": 4.632002675641377e-05, "loss": 3.9236, "step": 224768 }, { "epoch": 0.02, "learning_rate": 4.631164080890326e-05, "loss": 3.9321, "step": 225280 }, { "epoch": 0.02, "learning_rate": 4.630325486139274e-05, "loss": 3.9288, "step": 225792 }, { "epoch": 0.02, "learning_rate": 4.629486891388222e-05, "loss": 3.9222, "step": 226304 }, { "epoch": 0.02, "learning_rate": 4.628649934517543e-05, "loss": 3.9267, "step": 226816 }, { "epoch": 0.02, "learning_rate": 4.627811339766491e-05, "loss": 3.922, "step": 227328 }, { "epoch": 0.02, "learning_rate": 4.626972745015439e-05, "loss": 3.9201, "step": 227840 }, { "epoch": 0.02, "learning_rate": 4.626134150264387e-05, "loss": 3.9239, "step": 228352 }, { "epoch": 0.02, "learning_rate": 4.625295555513335e-05, "loss": 3.9231, "step": 228864 }, { "epoch": 0.03, "eval_loss": 3.9575917720794678, "eval_runtime": 314.063, "eval_samples_per_second": 1215.014, "eval_steps_per_second": 37.97, "step": 228960 }, { "epoch": 1.0, "learning_rate": 4.624456960762283e-05, "loss": 3.9228, "step": 229376 }, { "epoch": 1.0, "learning_rate": 4.623618366011231e-05, "loss": 3.9151, "step": 229888 }, { "epoch": 1.0, "learning_rate": 4.622781409140552e-05, "loss": 3.9298, "step": 230400 }, { "epoch": 1.0, "learning_rate": 4.6219428143895e-05, "loss": 3.9221, "step": 230912 }, { "epoch": 1.0, "learning_rate": 4.621104219638448e-05, "loss": 3.9399, "step": 231424 }, { "epoch": 1.0, "learning_rate": 4.620265624887396e-05, "loss": 3.9147, "step": 231936 }, { "epoch": 1.0, "learning_rate": 4.619428668016717e-05, "loss": 3.9202, "step": 232448 }, { "epoch": 1.0, "learning_rate": 4.618590073265665e-05, "loss": 3.9068, "step": 232960 }, { "epoch": 1.0, "learning_rate": 4.617751478514613e-05, "loss": 3.9216, "step": 233472 }, { "epoch": 1.0, "learning_rate": 4.616912883763561e-05, "loss": 3.9181, "step": 233984 }, { "epoch": 1.0, "learning_rate": 4.616075926892882e-05, "loss": 3.9119, "step": 234496 }, { "epoch": 1.0, "learning_rate": 4.61523733214183e-05, "loss": 3.9192, "step": 235008 }, { "epoch": 1.0, "learning_rate": 4.614400375271151e-05, "loss": 3.9072, "step": 235520 }, { "epoch": 1.0, "learning_rate": 4.613561780520099e-05, "loss": 3.921, "step": 236032 }, { "epoch": 1.0, "learning_rate": 4.612723185769047e-05, "loss": 3.9053, "step": 236544 }, { "epoch": 1.0, "learning_rate": 4.611884591017995e-05, "loss": 3.9044, "step": 237056 }, { "epoch": 1.0, "learning_rate": 4.611045996266943e-05, "loss": 3.905, "step": 237568 }, { "epoch": 1.0, "learning_rate": 4.610207401515891e-05, "loss": 3.9112, "step": 238080 }, { "epoch": 1.0, "learning_rate": 4.609368806764839e-05, "loss": 3.9075, "step": 238592 }, { "epoch": 1.0, "learning_rate": 4.608530212013788e-05, "loss": 3.9276, "step": 239104 }, { "epoch": 1.0, "learning_rate": 4.6076932551431087e-05, "loss": 3.9086, "step": 239616 }, { "epoch": 1.0, "learning_rate": 4.6068546603920566e-05, "loss": 3.9177, "step": 240128 }, { "epoch": 1.0, "learning_rate": 4.6060177035213776e-05, "loss": 3.9075, "step": 240640 }, { "epoch": 1.0, "learning_rate": 4.6051791087703256e-05, "loss": 3.914, "step": 241152 }, { "epoch": 1.0, "learning_rate": 4.6043405140192735e-05, "loss": 3.9064, "step": 241664 }, { "epoch": 1.0, "learning_rate": 4.6035019192682215e-05, "loss": 3.9112, "step": 242176 }, { "epoch": 1.0, "learning_rate": 4.6026633245171695e-05, "loss": 3.9041, "step": 242688 }, { "epoch": 1.0, "learning_rate": 4.6018247297661175e-05, "loss": 3.9008, "step": 243200 }, { "epoch": 1.0, "learning_rate": 4.6009861350150655e-05, "loss": 3.8976, "step": 243712 }, { "epoch": 1.01, "learning_rate": 4.6001491781443864e-05, "loss": 3.9059, "step": 244224 }, { "epoch": 1.01, "learning_rate": 4.5993105833933344e-05, "loss": 3.9092, "step": 244736 }, { "epoch": 1.01, "learning_rate": 4.598471988642283e-05, "loss": 3.9063, "step": 245248 }, { "epoch": 1.01, "learning_rate": 4.597633393891231e-05, "loss": 3.9164, "step": 245760 }, { "epoch": 1.01, "learning_rate": 4.596796437020552e-05, "loss": 3.9058, "step": 246272 }, { "epoch": 1.01, "learning_rate": 4.595959480149873e-05, "loss": 3.9005, "step": 246784 }, { "epoch": 1.01, "learning_rate": 4.595120885398821e-05, "loss": 3.9064, "step": 247296 }, { "epoch": 1.01, "learning_rate": 4.594282290647769e-05, "loss": 3.9055, "step": 247808 }, { "epoch": 1.01, "learning_rate": 4.593443695896717e-05, "loss": 3.8898, "step": 248320 }, { "epoch": 1.01, "learning_rate": 4.592605101145665e-05, "loss": 3.8859, "step": 248832 }, { "epoch": 1.01, "learning_rate": 4.591768144274986e-05, "loss": 3.8902, "step": 249344 }, { "epoch": 1.01, "learning_rate": 4.590929549523934e-05, "loss": 3.898, "step": 249856 }, { "epoch": 1.01, "learning_rate": 4.590090954772882e-05, "loss": 3.9028, "step": 250368 }, { "epoch": 1.01, "learning_rate": 4.58925236002183e-05, "loss": 3.8989, "step": 250880 }, { "epoch": 1.01, "learning_rate": 4.5884137652707785e-05, "loss": 3.8852, "step": 251392 }, { "epoch": 1.01, "learning_rate": 4.587575170519726e-05, "loss": 3.9008, "step": 251904 }, { "epoch": 1.01, "learning_rate": 4.586736575768674e-05, "loss": 3.8954, "step": 252416 }, { "epoch": 1.01, "learning_rate": 4.585897981017622e-05, "loss": 3.8932, "step": 252928 }, { "epoch": 1.01, "learning_rate": 4.585061024146943e-05, "loss": 3.8831, "step": 253440 }, { "epoch": 1.01, "learning_rate": 4.584222429395891e-05, "loss": 3.8722, "step": 253952 }, { "epoch": 1.01, "learning_rate": 4.583383834644839e-05, "loss": 3.9127, "step": 254464 }, { "epoch": 1.01, "learning_rate": 4.582545239893787e-05, "loss": 3.8991, "step": 254976 }, { "epoch": 1.01, "learning_rate": 4.5817082830231076e-05, "loss": 3.8909, "step": 255488 }, { "epoch": 1.01, "learning_rate": 4.5808696882720556e-05, "loss": 3.8924, "step": 256000 }, { "epoch": 1.01, "learning_rate": 4.580032731401377e-05, "loss": 3.8925, "step": 256512 }, { "epoch": 1.01, "learning_rate": 4.579194136650325e-05, "loss": 3.8765, "step": 257024 }, { "epoch": 1.01, "learning_rate": 4.578355541899273e-05, "loss": 3.8941, "step": 257536 }, { "epoch": 1.01, "learning_rate": 4.577516947148221e-05, "loss": 3.8809, "step": 258048 }, { "epoch": 1.01, "learning_rate": 4.576678352397169e-05, "loss": 3.8902, "step": 258560 }, { "epoch": 1.01, "learning_rate": 4.575839757646117e-05, "loss": 3.9042, "step": 259072 }, { "epoch": 1.01, "learning_rate": 4.575001162895065e-05, "loss": 3.8822, "step": 259584 }, { "epoch": 1.01, "learning_rate": 4.574162568144013e-05, "loss": 3.8724, "step": 260096 }, { "epoch": 1.01, "learning_rate": 4.573325611273334e-05, "loss": 3.9005, "step": 260608 }, { "epoch": 1.01, "learning_rate": 4.572487016522282e-05, "loss": 3.8671, "step": 261120 }, { "epoch": 1.01, "learning_rate": 4.57164842177123e-05, "loss": 3.8764, "step": 261632 }, { "epoch": 1.01, "learning_rate": 4.570811464900551e-05, "loss": 3.8939, "step": 262144 }, { "epoch": 1.01, "learning_rate": 4.569972870149499e-05, "loss": 3.8871, "step": 262656 }, { "epoch": 1.01, "learning_rate": 4.5691342753984476e-05, "loss": 3.8798, "step": 263168 }, { "epoch": 1.01, "learning_rate": 4.5682973185277685e-05, "loss": 3.8737, "step": 263680 }, { "epoch": 1.01, "learning_rate": 4.5674587237767165e-05, "loss": 3.8682, "step": 264192 }, { "epoch": 1.01, "learning_rate": 4.5666201290256645e-05, "loss": 3.8745, "step": 264704 }, { "epoch": 1.01, "learning_rate": 4.5657815342746125e-05, "loss": 3.8885, "step": 265216 }, { "epoch": 1.01, "learning_rate": 4.5649429395235605e-05, "loss": 3.8708, "step": 265728 }, { "epoch": 1.01, "learning_rate": 4.5641043447725085e-05, "loss": 3.8905, "step": 266240 }, { "epoch": 1.01, "learning_rate": 4.5632673879018294e-05, "loss": 3.8834, "step": 266752 }, { "epoch": 1.01, "learning_rate": 4.5624287931507774e-05, "loss": 3.8909, "step": 267264 }, { "epoch": 1.01, "learning_rate": 4.5615901983997254e-05, "loss": 3.8741, "step": 267776 }, { "epoch": 1.01, "learning_rate": 4.5607516036486734e-05, "loss": 3.8738, "step": 268288 }, { "epoch": 1.01, "learning_rate": 4.5599130088976214e-05, "loss": 3.8831, "step": 268800 }, { "epoch": 1.01, "learning_rate": 4.5590744141465694e-05, "loss": 3.8721, "step": 269312 }, { "epoch": 1.01, "learning_rate": 4.558237457275891e-05, "loss": 3.8838, "step": 269824 }, { "epoch": 1.01, "learning_rate": 4.557398862524839e-05, "loss": 3.8749, "step": 270336 }, { "epoch": 1.01, "learning_rate": 4.556560267773787e-05, "loss": 3.8748, "step": 270848 }, { "epoch": 1.01, "learning_rate": 4.555721673022735e-05, "loss": 3.8784, "step": 271360 }, { "epoch": 1.01, "learning_rate": 4.554883078271683e-05, "loss": 3.8641, "step": 271872 }, { "epoch": 1.01, "learning_rate": 4.554044483520631e-05, "loss": 3.8723, "step": 272384 }, { "epoch": 1.01, "learning_rate": 4.553205888769579e-05, "loss": 3.8738, "step": 272896 }, { "epoch": 1.01, "learning_rate": 4.552367294018526e-05, "loss": 3.8815, "step": 273408 }, { "epoch": 1.01, "learning_rate": 4.551530337147848e-05, "loss": 3.8698, "step": 273920 }, { "epoch": 1.01, "learning_rate": 4.550691742396796e-05, "loss": 3.8726, "step": 274432 }, { "epoch": 1.02, "learning_rate": 4.549853147645744e-05, "loss": 3.8682, "step": 274944 }, { "epoch": 1.02, "learning_rate": 4.549014552894691e-05, "loss": 3.8626, "step": 275456 }, { "epoch": 1.02, "learning_rate": 4.548175958143639e-05, "loss": 3.8632, "step": 275968 }, { "epoch": 1.02, "learning_rate": 4.547337363392588e-05, "loss": 3.8706, "step": 276480 }, { "epoch": 1.02, "learning_rate": 4.546498768641536e-05, "loss": 3.8803, "step": 276992 }, { "epoch": 1.02, "learning_rate": 4.545660173890484e-05, "loss": 3.8838, "step": 277504 }, { "epoch": 1.02, "learning_rate": 4.544823217019805e-05, "loss": 3.8735, "step": 278016 }, { "epoch": 1.02, "learning_rate": 4.543984622268753e-05, "loss": 3.861, "step": 278528 }, { "epoch": 1.02, "learning_rate": 4.543146027517701e-05, "loss": 3.8659, "step": 279040 }, { "epoch": 1.02, "learning_rate": 4.5423090706470216e-05, "loss": 3.8706, "step": 279552 }, { "epoch": 1.02, "learning_rate": 4.5414704758959696e-05, "loss": 3.8765, "step": 280064 }, { "epoch": 1.02, "learning_rate": 4.5406318811449176e-05, "loss": 3.8757, "step": 280576 }, { "epoch": 1.02, "learning_rate": 4.5397932863938656e-05, "loss": 3.8704, "step": 281088 }, { "epoch": 1.02, "learning_rate": 4.5389546916428136e-05, "loss": 3.8585, "step": 281600 }, { "epoch": 1.02, "learning_rate": 4.5381177347721345e-05, "loss": 3.8828, "step": 282112 }, { "epoch": 1.02, "learning_rate": 4.537279140021083e-05, "loss": 3.8539, "step": 282624 }, { "epoch": 1.02, "learning_rate": 4.536440545270031e-05, "loss": 3.871, "step": 283136 }, { "epoch": 1.02, "learning_rate": 4.535601950518979e-05, "loss": 3.8599, "step": 283648 }, { "epoch": 1.02, "learning_rate": 4.534763355767927e-05, "loss": 3.8679, "step": 284160 }, { "epoch": 1.02, "learning_rate": 4.533926398897248e-05, "loss": 3.8579, "step": 284672 }, { "epoch": 1.02, "learning_rate": 4.533087804146196e-05, "loss": 3.8651, "step": 285184 }, { "epoch": 1.02, "learning_rate": 4.532249209395144e-05, "loss": 3.8592, "step": 285696 }, { "epoch": 1.02, "learning_rate": 4.531410614644092e-05, "loss": 3.8593, "step": 286208 }, { "epoch": 1.02, "learning_rate": 4.53057201989304e-05, "loss": 3.8671, "step": 286720 }, { "epoch": 1.02, "learning_rate": 4.529733425141988e-05, "loss": 3.8571, "step": 287232 }, { "epoch": 1.02, "learning_rate": 4.528896468271309e-05, "loss": 3.8744, "step": 287744 }, { "epoch": 1.02, "learning_rate": 4.528057873520257e-05, "loss": 3.8761, "step": 288256 }, { "epoch": 1.02, "learning_rate": 4.527219278769205e-05, "loss": 3.8703, "step": 288768 }, { "epoch": 1.02, "learning_rate": 4.526380684018153e-05, "loss": 3.8587, "step": 289280 }, { "epoch": 1.02, "learning_rate": 4.5255420892671017e-05, "loss": 3.8597, "step": 289792 }, { "epoch": 1.02, "learning_rate": 4.5247034945160496e-05, "loss": 3.8575, "step": 290304 }, { "epoch": 1.02, "learning_rate": 4.5238648997649976e-05, "loss": 3.8583, "step": 290816 }, { "epoch": 1.02, "learning_rate": 4.523026305013945e-05, "loss": 3.8683, "step": 291328 }, { "epoch": 1.02, "learning_rate": 4.5221893481432665e-05, "loss": 3.845, "step": 291840 }, { "epoch": 1.02, "learning_rate": 4.5213507533922145e-05, "loss": 3.8636, "step": 292352 }, { "epoch": 1.02, "learning_rate": 4.5205121586411625e-05, "loss": 3.8611, "step": 292864 }, { "epoch": 1.02, "learning_rate": 4.51967356389011e-05, "loss": 3.8667, "step": 293376 }, { "epoch": 1.02, "learning_rate": 4.5188366070194314e-05, "loss": 3.8536, "step": 293888 }, { "epoch": 1.02, "learning_rate": 4.5179996501487524e-05, "loss": 3.8582, "step": 294400 }, { "epoch": 1.02, "learning_rate": 4.5171610553977003e-05, "loss": 3.8549, "step": 294912 }, { "epoch": 1.02, "learning_rate": 4.5163224606466483e-05, "loss": 3.8685, "step": 295424 }, { "epoch": 1.02, "learning_rate": 4.515483865895597e-05, "loss": 3.859, "step": 295936 }, { "epoch": 1.02, "learning_rate": 4.514645271144545e-05, "loss": 3.8704, "step": 296448 }, { "epoch": 1.02, "learning_rate": 4.513808314273866e-05, "loss": 3.8451, "step": 296960 }, { "epoch": 1.02, "learning_rate": 4.512969719522814e-05, "loss": 3.8616, "step": 297472 }, { "epoch": 1.02, "learning_rate": 4.512131124771762e-05, "loss": 3.8634, "step": 297984 }, { "epoch": 1.02, "learning_rate": 4.51129253002071e-05, "loss": 3.855, "step": 298496 }, { "epoch": 1.02, "learning_rate": 4.510455573150031e-05, "loss": 3.8563, "step": 299008 }, { "epoch": 1.02, "learning_rate": 4.509616978398979e-05, "loss": 3.8665, "step": 299520 }, { "epoch": 1.02, "learning_rate": 4.508778383647927e-05, "loss": 3.8614, "step": 300032 }, { "epoch": 1.02, "learning_rate": 4.507939788896874e-05, "loss": 3.8753, "step": 300544 }, { "epoch": 1.02, "learning_rate": 4.507102832026196e-05, "loss": 3.8487, "step": 301056 }, { "epoch": 1.02, "learning_rate": 4.506264237275144e-05, "loss": 3.8618, "step": 301568 }, { "epoch": 1.02, "learning_rate": 4.5054256425240924e-05, "loss": 3.852, "step": 302080 }, { "epoch": 1.02, "learning_rate": 4.50458704777304e-05, "loss": 3.8532, "step": 302592 }, { "epoch": 1.02, "learning_rate": 4.503748453021988e-05, "loss": 3.8576, "step": 303104 }, { "epoch": 1.02, "learning_rate": 4.502911496151309e-05, "loss": 3.8503, "step": 303616 }, { "epoch": 1.02, "learning_rate": 4.502072901400257e-05, "loss": 3.8487, "step": 304128 }, { "epoch": 1.02, "learning_rate": 4.5012343066492046e-05, "loss": 3.8482, "step": 304640 }, { "epoch": 1.02, "learning_rate": 4.5003957118981526e-05, "loss": 3.8535, "step": 305152 }, { "epoch": 1.03, "eval_loss": 3.9170939922332764, "eval_runtime": 317.3907, "eval_samples_per_second": 1202.275, "eval_steps_per_second": 37.572, "step": 305280 }, { "epoch": 0.0, "learning_rate": 4.4995571171471006e-05, "loss": 3.8477, "step": 305664 }, { "epoch": 0.0, "learning_rate": 4.4987185223960486e-05, "loss": 3.8429, "step": 306176 }, { "epoch": 0.0, "learning_rate": 4.4978799276449966e-05, "loss": 3.8618, "step": 306688 }, { "epoch": 0.0, "learning_rate": 4.4970413328939446e-05, "loss": 3.851, "step": 307200 }, { "epoch": 0.0, "learning_rate": 4.4962027381428926e-05, "loss": 3.8663, "step": 307712 }, { "epoch": 0.0, "learning_rate": 4.4953641433918406e-05, "loss": 3.8479, "step": 308224 }, { "epoch": 0.0, "learning_rate": 4.4945255486407886e-05, "loss": 3.8482, "step": 308736 }, { "epoch": 0.0, "learning_rate": 4.493686953889737e-05, "loss": 3.8356, "step": 309248 }, { "epoch": 0.0, "learning_rate": 4.492849997019058e-05, "loss": 3.8504, "step": 309760 }, { "epoch": 0.0, "learning_rate": 4.492011402268006e-05, "loss": 3.8477, "step": 310272 }, { "epoch": 0.0, "learning_rate": 4.491172807516954e-05, "loss": 3.8462, "step": 310784 }, { "epoch": 0.0, "learning_rate": 4.490334212765902e-05, "loss": 3.8461, "step": 311296 }, { "epoch": 0.0, "learning_rate": 4.489497255895223e-05, "loss": 3.8373, "step": 311808 }, { "epoch": 0.0, "learning_rate": 4.488658661144171e-05, "loss": 3.8526, "step": 312320 }, { "epoch": 0.0, "learning_rate": 4.487820066393119e-05, "loss": 3.8354, "step": 312832 }, { "epoch": 0.0, "learning_rate": 4.486981471642067e-05, "loss": 3.8349, "step": 313344 }, { "epoch": 0.0, "learning_rate": 4.486142876891015e-05, "loss": 3.8358, "step": 313856 }, { "epoch": 0.0, "learning_rate": 4.485304282139963e-05, "loss": 3.8464, "step": 314368 }, { "epoch": 0.0, "learning_rate": 4.484465687388911e-05, "loss": 3.8378, "step": 314880 }, { "epoch": 0.0, "learning_rate": 4.483627092637859e-05, "loss": 3.8572, "step": 315392 }, { "epoch": 0.0, "learning_rate": 4.482788497886807e-05, "loss": 3.8415, "step": 315904 }, { "epoch": 0.0, "learning_rate": 4.481949903135755e-05, "loss": 3.8499, "step": 316416 }, { "epoch": 0.0, "learning_rate": 4.481112946265076e-05, "loss": 3.8395, "step": 316928 }, { "epoch": 0.0, "learning_rate": 4.480274351514024e-05, "loss": 3.8417, "step": 317440 }, { "epoch": 0.0, "learning_rate": 4.479435756762972e-05, "loss": 3.8392, "step": 317952 }, { "epoch": 0.0, "learning_rate": 4.47859716201192e-05, "loss": 3.8444, "step": 318464 }, { "epoch": 0.0, "learning_rate": 4.477758567260868e-05, "loss": 3.8362, "step": 318976 }, { "epoch": 0.0, "learning_rate": 4.476919972509816e-05, "loss": 3.8379, "step": 319488 }, { "epoch": 0.0, "learning_rate": 4.476081377758764e-05, "loss": 3.8296, "step": 320000 }, { "epoch": 0.0, "learning_rate": 4.475244420888085e-05, "loss": 3.8379, "step": 320512 }, { "epoch": 0.01, "learning_rate": 4.474405826137033e-05, "loss": 3.8439, "step": 321024 }, { "epoch": 0.01, "learning_rate": 4.473567231385981e-05, "loss": 3.8419, "step": 321536 }, { "epoch": 0.01, "learning_rate": 4.4727286366349295e-05, "loss": 3.8463, "step": 322048 }, { "epoch": 0.01, "learning_rate": 4.4718900418838775e-05, "loss": 3.836, "step": 322560 }, { "epoch": 0.01, "learning_rate": 4.4710514471328255e-05, "loss": 3.8366, "step": 323072 }, { "epoch": 0.01, "learning_rate": 4.4702144902621464e-05, "loss": 3.8454, "step": 323584 }, { "epoch": 0.01, "learning_rate": 4.4693758955110944e-05, "loss": 3.8418, "step": 324096 }, { "epoch": 0.01, "learning_rate": 4.4685373007600424e-05, "loss": 3.8195, "step": 324608 }, { "epoch": 0.01, "learning_rate": 4.4676987060089903e-05, "loss": 3.8259, "step": 325120 }, { "epoch": 0.01, "learning_rate": 4.466861749138311e-05, "loss": 3.8237, "step": 325632 }, { "epoch": 0.01, "learning_rate": 4.466023154387259e-05, "loss": 3.8283, "step": 326144 }, { "epoch": 0.01, "learning_rate": 4.465184559636207e-05, "loss": 3.8407, "step": 326656 }, { "epoch": 0.01, "learning_rate": 4.464345964885155e-05, "loss": 3.8305, "step": 327168 }, { "epoch": 0.01, "learning_rate": 4.463507370134103e-05, "loss": 3.8262, "step": 327680 }, { "epoch": 0.01, "learning_rate": 4.462670413263425e-05, "loss": 3.8335, "step": 328192 }, { "epoch": 0.01, "learning_rate": 4.461831818512373e-05, "loss": 3.8268, "step": 328704 }, { "epoch": 0.01, "learning_rate": 4.460993223761321e-05, "loss": 3.8316, "step": 329216 }, { "epoch": 0.01, "learning_rate": 4.460154629010269e-05, "loss": 3.8215, "step": 329728 }, { "epoch": 0.01, "learning_rate": 4.459316034259217e-05, "loss": 3.8017, "step": 330240 }, { "epoch": 0.01, "learning_rate": 4.458477439508165e-05, "loss": 3.8499, "step": 330752 }, { "epoch": 0.01, "learning_rate": 4.457638844757112e-05, "loss": 3.8353, "step": 331264 }, { "epoch": 0.01, "learning_rate": 4.45680025000606e-05, "loss": 3.8325, "step": 331776 }, { "epoch": 0.01, "learning_rate": 4.455963293135382e-05, "loss": 3.827, "step": 332288 }, { "epoch": 0.01, "learning_rate": 4.4551263362647026e-05, "loss": 3.8276, "step": 332800 }, { "epoch": 0.01, "learning_rate": 4.4542877415136506e-05, "loss": 3.8155, "step": 333312 }, { "epoch": 0.01, "learning_rate": 4.4534491467625986e-05, "loss": 3.8281, "step": 333824 }, { "epoch": 0.01, "learning_rate": 4.4526105520115466e-05, "loss": 3.8218, "step": 334336 }, { "epoch": 0.01, "learning_rate": 4.451773595140868e-05, "loss": 3.8242, "step": 334848 }, { "epoch": 0.01, "learning_rate": 4.450935000389816e-05, "loss": 3.8401, "step": 335360 }, { "epoch": 0.01, "learning_rate": 4.450096405638764e-05, "loss": 3.8177, "step": 335872 }, { "epoch": 0.01, "learning_rate": 4.449257810887712e-05, "loss": 3.8133, "step": 336384 }, { "epoch": 0.01, "learning_rate": 4.448420854017033e-05, "loss": 3.8366, "step": 336896 }, { "epoch": 0.01, "learning_rate": 4.447582259265981e-05, "loss": 3.806, "step": 337408 }, { "epoch": 0.01, "learning_rate": 4.446743664514929e-05, "loss": 3.8164, "step": 337920 }, { "epoch": 0.01, "learning_rate": 4.4459050697638764e-05, "loss": 3.8284, "step": 338432 }, { "epoch": 0.01, "learning_rate": 4.445068112893198e-05, "loss": 3.8251, "step": 338944 }, { "epoch": 0.01, "learning_rate": 4.444229518142146e-05, "loss": 3.8167, "step": 339456 }, { "epoch": 0.01, "learning_rate": 4.443390923391094e-05, "loss": 3.8144, "step": 339968 }, { "epoch": 0.01, "learning_rate": 4.442552328640042e-05, "loss": 3.8041, "step": 340480 }, { "epoch": 0.01, "learning_rate": 4.44171373388899e-05, "loss": 3.8131, "step": 340992 }, { "epoch": 0.01, "learning_rate": 4.440875139137938e-05, "loss": 3.8246, "step": 341504 }, { "epoch": 0.01, "learning_rate": 4.4400381822672595e-05, "loss": 3.8135, "step": 342016 }, { "epoch": 0.01, "learning_rate": 4.439199587516207e-05, "loss": 3.8237, "step": 342528 }, { "epoch": 0.01, "learning_rate": 4.438360992765155e-05, "loss": 3.8243, "step": 343040 }, { "epoch": 0.01, "learning_rate": 4.437522398014103e-05, "loss": 3.8312, "step": 343552 }, { "epoch": 0.01, "learning_rate": 4.436683803263051e-05, "loss": 3.8134, "step": 344064 }, { "epoch": 0.01, "learning_rate": 4.435846846392372e-05, "loss": 3.8104, "step": 344576 }, { "epoch": 0.01, "learning_rate": 4.43500825164132e-05, "loss": 3.8221, "step": 345088 }, { "epoch": 0.01, "learning_rate": 4.434169656890268e-05, "loss": 3.8094, "step": 345600 }, { "epoch": 0.01, "learning_rate": 4.433331062139216e-05, "loss": 3.8279, "step": 346112 }, { "epoch": 0.01, "learning_rate": 4.432494105268537e-05, "loss": 3.8159, "step": 346624 }, { "epoch": 0.01, "learning_rate": 4.431655510517485e-05, "loss": 3.8144, "step": 347136 }, { "epoch": 0.01, "learning_rate": 4.430816915766433e-05, "loss": 3.8212, "step": 347648 }, { "epoch": 0.01, "learning_rate": 4.429978321015381e-05, "loss": 3.8054, "step": 348160 }, { "epoch": 0.01, "learning_rate": 4.429139726264329e-05, "loss": 3.8109, "step": 348672 }, { "epoch": 0.01, "learning_rate": 4.42830276939365e-05, "loss": 3.8129, "step": 349184 }, { "epoch": 0.01, "learning_rate": 4.427464174642598e-05, "loss": 3.8226, "step": 349696 }, { "epoch": 0.01, "learning_rate": 4.426625579891546e-05, "loss": 3.8072, "step": 350208 }, { "epoch": 0.01, "learning_rate": 4.425786985140494e-05, "loss": 3.8136, "step": 350720 }, { "epoch": 0.02, "learning_rate": 4.424948390389442e-05, "loss": 3.8088, "step": 351232 }, { "epoch": 0.02, "learning_rate": 4.424111433518763e-05, "loss": 3.8094, "step": 351744 }, { "epoch": 0.02, "learning_rate": 4.423272838767711e-05, "loss": 3.8003, "step": 352256 }, { "epoch": 0.02, "learning_rate": 4.422434244016659e-05, "loss": 3.8132, "step": 352768 }, { "epoch": 0.02, "learning_rate": 4.421595649265607e-05, "loss": 3.8213, "step": 353280 }, { "epoch": 0.02, "learning_rate": 4.420757054514556e-05, "loss": 3.8213, "step": 353792 }, { "epoch": 0.02, "learning_rate": 4.419920097643877e-05, "loss": 3.8186, "step": 354304 }, { "epoch": 0.02, "learning_rate": 4.419081502892825e-05, "loss": 3.8015, "step": 354816 }, { "epoch": 0.02, "learning_rate": 4.418242908141773e-05, "loss": 3.8061, "step": 355328 }, { "epoch": 0.02, "learning_rate": 4.417404313390721e-05, "loss": 3.812, "step": 355840 }, { "epoch": 0.02, "learning_rate": 4.4165673565200416e-05, "loss": 3.8184, "step": 356352 }, { "epoch": 0.02, "learning_rate": 4.4157287617689896e-05, "loss": 3.8164, "step": 356864 }, { "epoch": 0.02, "learning_rate": 4.4148901670179376e-05, "loss": 3.8111, "step": 357376 }, { "epoch": 0.02, "learning_rate": 4.4140515722668856e-05, "loss": 3.8041, "step": 357888 }, { "epoch": 0.02, "learning_rate": 4.4132129775158336e-05, "loss": 3.8238, "step": 358400 }, { "epoch": 0.02, "learning_rate": 4.4123760206451545e-05, "loss": 3.7982, "step": 358912 }, { "epoch": 0.02, "learning_rate": 4.4115374258941025e-05, "loss": 3.8117, "step": 359424 }, { "epoch": 0.02, "learning_rate": 4.410698831143051e-05, "loss": 3.8019, "step": 359936 }, { "epoch": 0.02, "learning_rate": 4.409860236391999e-05, "loss": 3.8112, "step": 360448 }, { "epoch": 0.02, "learning_rate": 4.409021641640947e-05, "loss": 3.7997, "step": 360960 }, { "epoch": 0.02, "learning_rate": 4.408183046889895e-05, "loss": 3.8099, "step": 361472 }, { "epoch": 0.02, "learning_rate": 4.407346090019216e-05, "loss": 3.7995, "step": 361984 }, { "epoch": 0.02, "learning_rate": 4.406507495268164e-05, "loss": 3.8061, "step": 362496 }, { "epoch": 0.02, "learning_rate": 4.405668900517112e-05, "loss": 3.8089, "step": 363008 }, { "epoch": 0.02, "learning_rate": 4.40483030576606e-05, "loss": 3.8022, "step": 363520 }, { "epoch": 0.02, "learning_rate": 4.403993348895381e-05, "loss": 3.816, "step": 364032 }, { "epoch": 0.02, "learning_rate": 4.403154754144329e-05, "loss": 3.8183, "step": 364544 }, { "epoch": 0.02, "learning_rate": 4.402316159393277e-05, "loss": 3.8102, "step": 365056 }, { "epoch": 0.02, "learning_rate": 4.401477564642225e-05, "loss": 3.8078, "step": 365568 }, { "epoch": 0.02, "learning_rate": 4.4006406077715465e-05, "loss": 3.7998, "step": 366080 }, { "epoch": 0.02, "learning_rate": 4.3998020130204945e-05, "loss": 3.8045, "step": 366592 }, { "epoch": 0.02, "learning_rate": 4.3989634182694425e-05, "loss": 3.801, "step": 367104 }, { "epoch": 0.02, "learning_rate": 4.3981248235183905e-05, "loss": 3.8137, "step": 367616 }, { "epoch": 0.02, "learning_rate": 4.397286228767338e-05, "loss": 3.7871, "step": 368128 }, { "epoch": 0.02, "learning_rate": 4.396447634016286e-05, "loss": 3.8074, "step": 368640 }, { "epoch": 0.02, "learning_rate": 4.3956106771456074e-05, "loss": 3.8037, "step": 369152 }, { "epoch": 0.02, "learning_rate": 4.394772082394555e-05, "loss": 3.8101, "step": 369664 }, { "epoch": 0.02, "learning_rate": 4.393933487643503e-05, "loss": 3.801, "step": 370176 }, { "epoch": 0.02, "learning_rate": 4.393094892892451e-05, "loss": 3.8036, "step": 370688 }, { "epoch": 0.02, "learning_rate": 4.392257936021772e-05, "loss": 3.7984, "step": 371200 }, { "epoch": 0.02, "learning_rate": 4.39141934127072e-05, "loss": 3.8126, "step": 371712 }, { "epoch": 0.02, "learning_rate": 4.390580746519668e-05, "loss": 3.8067, "step": 372224 }, { "epoch": 0.02, "learning_rate": 4.389742151768616e-05, "loss": 3.8112, "step": 372736 }, { "epoch": 0.02, "learning_rate": 4.388905194897937e-05, "loss": 3.792, "step": 373248 }, { "epoch": 0.02, "learning_rate": 4.388066600146885e-05, "loss": 3.8077, "step": 373760 }, { "epoch": 0.02, "learning_rate": 4.387228005395833e-05, "loss": 3.8083, "step": 374272 }, { "epoch": 0.02, "learning_rate": 4.386389410644781e-05, "loss": 3.8002, "step": 374784 }, { "epoch": 0.02, "learning_rate": 4.385552453774102e-05, "loss": 3.8022, "step": 375296 }, { "epoch": 0.02, "learning_rate": 4.38471385902305e-05, "loss": 3.8104, "step": 375808 }, { "epoch": 0.02, "learning_rate": 4.383875264271998e-05, "loss": 3.8038, "step": 376320 }, { "epoch": 0.02, "learning_rate": 4.383036669520946e-05, "loss": 3.8236, "step": 376832 }, { "epoch": 0.02, "learning_rate": 4.382199712650267e-05, "loss": 3.7942, "step": 377344 }, { "epoch": 0.02, "learning_rate": 4.3813611178992157e-05, "loss": 3.8058, "step": 377856 }, { "epoch": 0.02, "learning_rate": 4.3805225231481637e-05, "loss": 3.7971, "step": 378368 }, { "epoch": 0.02, "learning_rate": 4.3796839283971116e-05, "loss": 3.7989, "step": 378880 }, { "epoch": 0.02, "learning_rate": 4.3788453336460596e-05, "loss": 3.8038, "step": 379392 }, { "epoch": 0.02, "learning_rate": 4.3780083767753806e-05, "loss": 3.7975, "step": 379904 }, { "epoch": 0.02, "learning_rate": 4.3771697820243285e-05, "loss": 3.7996, "step": 380416 }, { "epoch": 0.02, "learning_rate": 4.3763311872732765e-05, "loss": 3.7862, "step": 380928 }, { "epoch": 0.02, "learning_rate": 4.3754925925222245e-05, "loss": 3.804, "step": 381440 }, { "epoch": 0.03, "eval_loss": 3.8917667865753174, "eval_runtime": 304.2835, "eval_samples_per_second": 1254.064, "eval_steps_per_second": 39.19, "step": 381600 }, { "epoch": 1.0, "learning_rate": 4.3746539977711725e-05, "loss": 3.8007, "step": 381952 }, { "epoch": 1.0, "learning_rate": 4.3738170409004934e-05, "loss": 3.7878, "step": 382464 }, { "epoch": 1.0, "learning_rate": 4.3729784461494414e-05, "loss": 3.8045, "step": 382976 }, { "epoch": 1.0, "learning_rate": 4.3721398513983894e-05, "loss": 3.8023, "step": 383488 }, { "epoch": 1.0, "learning_rate": 4.3713012566473374e-05, "loss": 3.8089, "step": 384000 }, { "epoch": 1.0, "learning_rate": 4.370464299776659e-05, "loss": 3.7938, "step": 384512 }, { "epoch": 1.0, "learning_rate": 4.369625705025607e-05, "loss": 3.7965, "step": 385024 }, { "epoch": 1.0, "learning_rate": 4.368787110274555e-05, "loss": 3.7848, "step": 385536 }, { "epoch": 1.0, "learning_rate": 4.367948515523503e-05, "loss": 3.7985, "step": 386048 }, { "epoch": 1.0, "learning_rate": 4.367111558652824e-05, "loss": 3.7956, "step": 386560 }, { "epoch": 1.0, "learning_rate": 4.366272963901772e-05, "loss": 3.7965, "step": 387072 }, { "epoch": 1.0, "learning_rate": 4.36543436915072e-05, "loss": 3.7901, "step": 387584 }, { "epoch": 1.0, "learning_rate": 4.364597412280041e-05, "loss": 3.7896, "step": 388096 }, { "epoch": 1.0, "learning_rate": 4.363758817528989e-05, "loss": 3.7923, "step": 388608 }, { "epoch": 1.0, "learning_rate": 4.362920222777937e-05, "loss": 3.7851, "step": 389120 }, { "epoch": 1.0, "learning_rate": 4.362081628026885e-05, "loss": 3.7796, "step": 389632 }, { "epoch": 1.0, "learning_rate": 4.361243033275833e-05, "loss": 3.785, "step": 390144 }, { "epoch": 1.0, "learning_rate": 4.360404438524781e-05, "loss": 3.7925, "step": 390656 }, { "epoch": 1.0, "learning_rate": 4.359565843773729e-05, "loss": 3.7855, "step": 391168 }, { "epoch": 1.0, "learning_rate": 4.3587272490226775e-05, "loss": 3.8048, "step": 391680 }, { "epoch": 1.0, "learning_rate": 4.3578902921519984e-05, "loss": 3.7923, "step": 392192 }, { "epoch": 1.0, "learning_rate": 4.3570516974009464e-05, "loss": 3.7994, "step": 392704 }, { "epoch": 1.0, "learning_rate": 4.3562131026498944e-05, "loss": 3.7866, "step": 393216 }, { "epoch": 1.0, "learning_rate": 4.3553745078988424e-05, "loss": 3.7892, "step": 393728 }, { "epoch": 1.0, "learning_rate": 4.354537551028163e-05, "loss": 3.786, "step": 394240 }, { "epoch": 1.0, "learning_rate": 4.353698956277111e-05, "loss": 3.7967, "step": 394752 }, { "epoch": 1.0, "learning_rate": 4.352860361526059e-05, "loss": 3.7864, "step": 395264 }, { "epoch": 1.0, "learning_rate": 4.352021766775007e-05, "loss": 3.7844, "step": 395776 }, { "epoch": 1.0, "learning_rate": 4.351184809904328e-05, "loss": 3.7797, "step": 396288 }, { "epoch": 1.0, "learning_rate": 4.350346215153276e-05, "loss": 3.7886, "step": 396800 }, { "epoch": 1.01, "learning_rate": 4.349507620402224e-05, "loss": 3.7898, "step": 397312 }, { "epoch": 1.01, "learning_rate": 4.348669025651173e-05, "loss": 3.791, "step": 397824 }, { "epoch": 1.01, "learning_rate": 4.347832068780494e-05, "loss": 3.7941, "step": 398336 }, { "epoch": 1.01, "learning_rate": 4.346993474029442e-05, "loss": 3.7902, "step": 398848 }, { "epoch": 1.01, "learning_rate": 4.34615487927839e-05, "loss": 3.786, "step": 399360 }, { "epoch": 1.01, "learning_rate": 4.345316284527338e-05, "loss": 3.7947, "step": 399872 }, { "epoch": 1.01, "learning_rate": 4.3444793276566586e-05, "loss": 3.7896, "step": 400384 }, { "epoch": 1.01, "learning_rate": 4.3436407329056066e-05, "loss": 3.7747, "step": 400896 }, { "epoch": 1.01, "learning_rate": 4.3428021381545546e-05, "loss": 3.7753, "step": 401408 }, { "epoch": 1.01, "learning_rate": 4.3419635434035026e-05, "loss": 3.7711, "step": 401920 }, { "epoch": 1.01, "learning_rate": 4.3411249486524506e-05, "loss": 3.7762, "step": 402432 }, { "epoch": 1.01, "learning_rate": 4.3402879917817715e-05, "loss": 3.7909, "step": 402944 }, { "epoch": 1.01, "learning_rate": 4.3394493970307195e-05, "loss": 3.7841, "step": 403456 }, { "epoch": 1.01, "learning_rate": 4.338610802279668e-05, "loss": 3.7742, "step": 403968 }, { "epoch": 1.01, "learning_rate": 4.3377722075286155e-05, "loss": 3.7848, "step": 404480 }, { "epoch": 1.01, "learning_rate": 4.3369336127775635e-05, "loss": 3.7773, "step": 404992 }, { "epoch": 1.01, "learning_rate": 4.3360950180265115e-05, "loss": 3.7841, "step": 405504 }, { "epoch": 1.01, "learning_rate": 4.335258061155833e-05, "loss": 3.7711, "step": 406016 }, { "epoch": 1.01, "learning_rate": 4.3344194664047804e-05, "loss": 3.7528, "step": 406528 }, { "epoch": 1.01, "learning_rate": 4.3335808716537284e-05, "loss": 3.8019, "step": 407040 }, { "epoch": 1.01, "learning_rate": 4.3327422769026764e-05, "loss": 3.7832, "step": 407552 }, { "epoch": 1.01, "learning_rate": 4.3319036821516244e-05, "loss": 3.7872, "step": 408064 }, { "epoch": 1.01, "learning_rate": 4.331066725280945e-05, "loss": 3.774, "step": 408576 }, { "epoch": 1.01, "learning_rate": 4.330229768410267e-05, "loss": 3.7829, "step": 409088 }, { "epoch": 1.01, "learning_rate": 4.329391173659215e-05, "loss": 3.7655, "step": 409600 }, { "epoch": 1.01, "learning_rate": 4.328552578908163e-05, "loss": 3.7765, "step": 410112 }, { "epoch": 1.01, "learning_rate": 4.327713984157111e-05, "loss": 3.7768, "step": 410624 }, { "epoch": 1.01, "learning_rate": 4.326875389406059e-05, "loss": 3.775, "step": 411136 }, { "epoch": 1.01, "learning_rate": 4.326036794655007e-05, "loss": 3.7957, "step": 411648 }, { "epoch": 1.01, "learning_rate": 4.325198199903955e-05, "loss": 3.7686, "step": 412160 }, { "epoch": 1.01, "learning_rate": 4.324359605152903e-05, "loss": 3.7628, "step": 412672 }, { "epoch": 1.01, "learning_rate": 4.323522648282224e-05, "loss": 3.79, "step": 413184 }, { "epoch": 1.01, "learning_rate": 4.322684053531172e-05, "loss": 3.7569, "step": 413696 }, { "epoch": 1.01, "learning_rate": 4.32184545878012e-05, "loss": 3.766, "step": 414208 }, { "epoch": 1.01, "learning_rate": 4.321006864029068e-05, "loss": 3.782, "step": 414720 }, { "epoch": 1.01, "learning_rate": 4.320169907158389e-05, "loss": 3.7817, "step": 415232 }, { "epoch": 1.01, "learning_rate": 4.3193313124073373e-05, "loss": 3.763, "step": 415744 }, { "epoch": 1.01, "learning_rate": 4.318492717656285e-05, "loss": 3.7723, "step": 416256 }, { "epoch": 1.01, "learning_rate": 4.317654122905233e-05, "loss": 3.7545, "step": 416768 }, { "epoch": 1.01, "learning_rate": 4.316817166034554e-05, "loss": 3.7693, "step": 417280 }, { "epoch": 1.01, "learning_rate": 4.315978571283502e-05, "loss": 3.7754, "step": 417792 }, { "epoch": 1.01, "learning_rate": 4.31513997653245e-05, "loss": 3.764, "step": 418304 }, { "epoch": 1.01, "learning_rate": 4.314301381781398e-05, "loss": 3.7775, "step": 418816 }, { "epoch": 1.01, "learning_rate": 4.313464424910719e-05, "loss": 3.7752, "step": 419328 }, { "epoch": 1.01, "learning_rate": 4.312625830159667e-05, "loss": 3.7866, "step": 419840 }, { "epoch": 1.01, "learning_rate": 4.311787235408615e-05, "loss": 3.764, "step": 420352 }, { "epoch": 1.01, "learning_rate": 4.310948640657563e-05, "loss": 3.77, "step": 420864 }, { "epoch": 1.01, "learning_rate": 4.310110045906511e-05, "loss": 3.7747, "step": 421376 }, { "epoch": 1.01, "learning_rate": 4.309273089035833e-05, "loss": 3.763, "step": 421888 }, { "epoch": 1.01, "learning_rate": 4.308434494284781e-05, "loss": 3.7763, "step": 422400 }, { "epoch": 1.01, "learning_rate": 4.307595899533729e-05, "loss": 3.7706, "step": 422912 }, { "epoch": 1.01, "learning_rate": 4.306757304782677e-05, "loss": 3.7679, "step": 423424 }, { "epoch": 1.01, "learning_rate": 4.3059203479119976e-05, "loss": 3.7758, "step": 423936 }, { "epoch": 1.01, "learning_rate": 4.3050817531609456e-05, "loss": 3.7595, "step": 424448 }, { "epoch": 1.01, "learning_rate": 4.3042431584098936e-05, "loss": 3.7606, "step": 424960 }, { "epoch": 1.01, "learning_rate": 4.3034045636588416e-05, "loss": 3.7691, "step": 425472 }, { "epoch": 1.01, "learning_rate": 4.3025676067881625e-05, "loss": 3.7738, "step": 425984 }, { "epoch": 1.01, "learning_rate": 4.3017290120371105e-05, "loss": 3.764, "step": 426496 }, { "epoch": 1.01, "learning_rate": 4.3008904172860585e-05, "loss": 3.766, "step": 427008 }, { "epoch": 1.02, "learning_rate": 4.3000518225350065e-05, "loss": 3.7566, "step": 427520 }, { "epoch": 1.02, "learning_rate": 4.299214865664328e-05, "loss": 3.7653, "step": 428032 }, { "epoch": 1.02, "learning_rate": 4.298376270913276e-05, "loss": 3.7567, "step": 428544 }, { "epoch": 1.02, "learning_rate": 4.297537676162224e-05, "loss": 3.7645, "step": 429056 }, { "epoch": 1.02, "learning_rate": 4.296699081411172e-05, "loss": 3.7789, "step": 429568 }, { "epoch": 1.02, "learning_rate": 4.295862124540493e-05, "loss": 3.7696, "step": 430080 }, { "epoch": 1.02, "learning_rate": 4.295023529789441e-05, "loss": 3.7727, "step": 430592 }, { "epoch": 1.02, "learning_rate": 4.294184935038389e-05, "loss": 3.7575, "step": 431104 }, { "epoch": 1.02, "learning_rate": 4.293346340287337e-05, "loss": 3.7608, "step": 431616 }, { "epoch": 1.02, "learning_rate": 4.292509383416658e-05, "loss": 3.763, "step": 432128 }, { "epoch": 1.02, "learning_rate": 4.291670788665606e-05, "loss": 3.7759, "step": 432640 }, { "epoch": 1.02, "learning_rate": 4.290832193914554e-05, "loss": 3.7683, "step": 433152 }, { "epoch": 1.02, "learning_rate": 4.289993599163502e-05, "loss": 3.7725, "step": 433664 }, { "epoch": 1.02, "learning_rate": 4.289156642292823e-05, "loss": 3.7595, "step": 434176 }, { "epoch": 1.02, "learning_rate": 4.2883180475417714e-05, "loss": 3.7752, "step": 434688 }, { "epoch": 1.02, "learning_rate": 4.2874794527907194e-05, "loss": 3.7557, "step": 435200 }, { "epoch": 1.02, "learning_rate": 4.2866408580396674e-05, "loss": 3.7674, "step": 435712 }, { "epoch": 1.02, "learning_rate": 4.2858039011689883e-05, "loss": 3.7524, "step": 436224 }, { "epoch": 1.02, "learning_rate": 4.284965306417936e-05, "loss": 3.7702, "step": 436736 }, { "epoch": 1.02, "learning_rate": 4.284126711666884e-05, "loss": 3.7555, "step": 437248 }, { "epoch": 1.02, "learning_rate": 4.283288116915832e-05, "loss": 3.7618, "step": 437760 }, { "epoch": 1.02, "learning_rate": 4.28244952216478e-05, "loss": 3.7578, "step": 438272 }, { "epoch": 1.02, "learning_rate": 4.281612565294101e-05, "loss": 3.7596, "step": 438784 }, { "epoch": 1.02, "learning_rate": 4.280773970543049e-05, "loss": 3.761, "step": 439296 }, { "epoch": 1.02, "learning_rate": 4.279935375791997e-05, "loss": 3.7595, "step": 439808 }, { "epoch": 1.02, "learning_rate": 4.279096781040945e-05, "loss": 3.7692, "step": 440320 }, { "epoch": 1.02, "learning_rate": 4.278259824170267e-05, "loss": 3.7714, "step": 440832 }, { "epoch": 1.02, "learning_rate": 4.277421229419215e-05, "loss": 3.7676, "step": 441344 }, { "epoch": 1.02, "learning_rate": 4.276582634668163e-05, "loss": 3.7675, "step": 441856 }, { "epoch": 1.02, "learning_rate": 4.275744039917111e-05, "loss": 3.753, "step": 442368 }, { "epoch": 1.02, "learning_rate": 4.274907083046432e-05, "loss": 3.7584, "step": 442880 }, { "epoch": 1.02, "learning_rate": 4.27406848829538e-05, "loss": 3.7603, "step": 443392 }, { "epoch": 1.02, "learning_rate": 4.273229893544328e-05, "loss": 3.7671, "step": 443904 }, { "epoch": 1.02, "learning_rate": 4.272391298793276e-05, "loss": 3.7441, "step": 444416 }, { "epoch": 1.02, "learning_rate": 4.2715543419225966e-05, "loss": 3.7621, "step": 444928 }, { "epoch": 1.02, "learning_rate": 4.2707157471715446e-05, "loss": 3.7629, "step": 445440 }, { "epoch": 1.02, "learning_rate": 4.2698771524204926e-05, "loss": 3.7613, "step": 445952 }, { "epoch": 1.02, "learning_rate": 4.2690385576694406e-05, "loss": 3.7577, "step": 446464 }, { "epoch": 1.02, "learning_rate": 4.268201600798762e-05, "loss": 3.7602, "step": 446976 }, { "epoch": 1.02, "learning_rate": 4.26736300604771e-05, "loss": 3.7579, "step": 447488 }, { "epoch": 1.02, "learning_rate": 4.266524411296658e-05, "loss": 3.7688, "step": 448000 }, { "epoch": 1.02, "learning_rate": 4.2656858165456055e-05, "loss": 3.7655, "step": 448512 }, { "epoch": 1.02, "learning_rate": 4.264848859674927e-05, "loss": 3.7671, "step": 449024 }, { "epoch": 1.02, "learning_rate": 4.264010264923875e-05, "loss": 3.7493, "step": 449536 }, { "epoch": 1.02, "learning_rate": 4.263171670172823e-05, "loss": 3.7632, "step": 450048 }, { "epoch": 1.02, "learning_rate": 4.2623330754217704e-05, "loss": 3.7653, "step": 450560 }, { "epoch": 1.02, "learning_rate": 4.261496118551092e-05, "loss": 3.756, "step": 451072 }, { "epoch": 1.02, "learning_rate": 4.26065752380004e-05, "loss": 3.7602, "step": 451584 }, { "epoch": 1.02, "learning_rate": 4.259818929048988e-05, "loss": 3.7663, "step": 452096 }, { "epoch": 1.02, "learning_rate": 4.258980334297936e-05, "loss": 3.7632, "step": 452608 }, { "epoch": 1.02, "learning_rate": 4.2581433774272575e-05, "loss": 3.7751, "step": 453120 }, { "epoch": 1.02, "learning_rate": 4.2573047826762055e-05, "loss": 3.7555, "step": 453632 }, { "epoch": 1.02, "learning_rate": 4.256466187925153e-05, "loss": 3.7617, "step": 454144 }, { "epoch": 1.02, "learning_rate": 4.255627593174101e-05, "loss": 3.7563, "step": 454656 }, { "epoch": 1.02, "learning_rate": 4.2547906363034224e-05, "loss": 3.7582, "step": 455168 }, { "epoch": 1.02, "learning_rate": 4.2539520415523704e-05, "loss": 3.7557, "step": 455680 }, { "epoch": 1.02, "learning_rate": 4.253113446801318e-05, "loss": 3.7529, "step": 456192 }, { "epoch": 1.02, "learning_rate": 4.252274852050266e-05, "loss": 3.7591, "step": 456704 }, { "epoch": 1.02, "learning_rate": 4.251437895179587e-05, "loss": 3.7419, "step": 457216 }, { "epoch": 1.02, "learning_rate": 4.250599300428535e-05, "loss": 3.7641, "step": 457728 }, { "epoch": 1.03, "eval_loss": 3.8763163089752197, "eval_runtime": 303.2875, "eval_samples_per_second": 1258.182, "eval_steps_per_second": 39.319, "step": 457920 }, { "epoch": 0.0, "learning_rate": 4.2497607056774826e-05, "loss": 3.7587, "step": 458240 }, { "epoch": 0.0, "learning_rate": 4.248922110926431e-05, "loss": 3.7461, "step": 458752 }, { "epoch": 0.0, "learning_rate": 4.248083516175379e-05, "loss": 3.7597, "step": 459264 }, { "epoch": 0.0, "learning_rate": 4.247244921424327e-05, "loss": 3.7584, "step": 459776 }, { "epoch": 0.0, "learning_rate": 4.246406326673275e-05, "loss": 3.7676, "step": 460288 }, { "epoch": 0.0, "learning_rate": 4.245567731922223e-05, "loss": 3.7518, "step": 460800 }, { "epoch": 0.0, "learning_rate": 4.244729137171171e-05, "loss": 3.7552, "step": 461312 }, { "epoch": 0.0, "learning_rate": 4.243890542420119e-05, "loss": 3.7416, "step": 461824 }, { "epoch": 0.0, "learning_rate": 4.24305358554944e-05, "loss": 3.7554, "step": 462336 }, { "epoch": 0.0, "learning_rate": 4.242214990798388e-05, "loss": 3.7548, "step": 462848 }, { "epoch": 0.0, "learning_rate": 4.241376396047336e-05, "loss": 3.7532, "step": 463360 }, { "epoch": 0.0, "learning_rate": 4.240537801296284e-05, "loss": 3.7472, "step": 463872 }, { "epoch": 0.0, "learning_rate": 4.239702482305978e-05, "loss": 3.7468, "step": 464384 }, { "epoch": 0.0, "learning_rate": 4.238863887554927e-05, "loss": 3.7493, "step": 464896 }, { "epoch": 0.0, "learning_rate": 4.238025292803875e-05, "loss": 3.7473, "step": 465408 }, { "epoch": 0.0, "learning_rate": 4.237186698052823e-05, "loss": 3.7373, "step": 465920 }, { "epoch": 0.0, "learning_rate": 4.236348103301771e-05, "loss": 3.7427, "step": 466432 }, { "epoch": 0.0, "learning_rate": 4.235509508550719e-05, "loss": 3.7497, "step": 466944 }, { "epoch": 0.0, "learning_rate": 4.234670913799667e-05, "loss": 3.7461, "step": 467456 }, { "epoch": 0.0, "learning_rate": 4.2338323190486147e-05, "loss": 3.7605, "step": 467968 }, { "epoch": 0.0, "learning_rate": 4.2329953621779356e-05, "loss": 3.7535, "step": 468480 }, { "epoch": 0.0, "learning_rate": 4.2321567674268836e-05, "loss": 3.7593, "step": 468992 }, { "epoch": 0.0, "learning_rate": 4.2313181726758316e-05, "loss": 3.7408, "step": 469504 }, { "epoch": 0.0, "learning_rate": 4.2304795779247796e-05, "loss": 3.7478, "step": 470016 }, { "epoch": 0.0, "learning_rate": 4.2296426210541005e-05, "loss": 3.7458, "step": 470528 }, { "epoch": 0.0, "learning_rate": 4.2288040263030485e-05, "loss": 3.7551, "step": 471040 }, { "epoch": 0.0, "learning_rate": 4.2279654315519965e-05, "loss": 3.744, "step": 471552 }, { "epoch": 0.0, "learning_rate": 4.227126836800945e-05, "loss": 3.7474, "step": 472064 }, { "epoch": 0.0, "learning_rate": 4.226289879930266e-05, "loss": 3.7402, "step": 472576 }, { "epoch": 0.0, "learning_rate": 4.225451285179214e-05, "loss": 3.7435, "step": 473088 }, { "epoch": 0.01, "learning_rate": 4.224612690428162e-05, "loss": 3.7451, "step": 473600 }, { "epoch": 0.01, "learning_rate": 4.22377409567711e-05, "loss": 3.7547, "step": 474112 }, { "epoch": 0.01, "learning_rate": 4.222937138806431e-05, "loss": 3.7538, "step": 474624 }, { "epoch": 0.01, "learning_rate": 4.222098544055379e-05, "loss": 3.7509, "step": 475136 }, { "epoch": 0.01, "learning_rate": 4.221259949304327e-05, "loss": 3.7445, "step": 475648 }, { "epoch": 0.01, "learning_rate": 4.220422992433648e-05, "loss": 3.7485, "step": 476160 }, { "epoch": 0.01, "learning_rate": 4.219584397682596e-05, "loss": 3.7505, "step": 476672 }, { "epoch": 0.01, "learning_rate": 4.218745802931544e-05, "loss": 3.7372, "step": 477184 }, { "epoch": 0.01, "learning_rate": 4.217907208180492e-05, "loss": 3.7323, "step": 477696 }, { "epoch": 0.01, "learning_rate": 4.21706861342944e-05, "loss": 3.7307, "step": 478208 }, { "epoch": 0.01, "learning_rate": 4.2162300186783885e-05, "loss": 3.7396, "step": 478720 }, { "epoch": 0.01, "learning_rate": 4.2153914239273365e-05, "loss": 3.7456, "step": 479232 }, { "epoch": 0.01, "learning_rate": 4.214552829176284e-05, "loss": 3.7437, "step": 479744 }, { "epoch": 0.01, "learning_rate": 4.2137158723056054e-05, "loss": 3.7363, "step": 480256 }, { "epoch": 0.01, "learning_rate": 4.2128772775545534e-05, "loss": 3.739, "step": 480768 }, { "epoch": 0.01, "learning_rate": 4.2120386828035014e-05, "loss": 3.7391, "step": 481280 }, { "epoch": 0.01, "learning_rate": 4.211200088052449e-05, "loss": 3.7437, "step": 481792 }, { "epoch": 0.01, "learning_rate": 4.21036313118177e-05, "loss": 3.7313, "step": 482304 }, { "epoch": 0.01, "learning_rate": 4.209524536430718e-05, "loss": 3.7129, "step": 482816 }, { "epoch": 0.01, "learning_rate": 4.208685941679666e-05, "loss": 3.7568, "step": 483328 }, { "epoch": 0.01, "learning_rate": 4.2078473469286136e-05, "loss": 3.7417, "step": 483840 }, { "epoch": 0.01, "learning_rate": 4.207010390057935e-05, "loss": 3.7504, "step": 484352 }, { "epoch": 0.01, "learning_rate": 4.206171795306884e-05, "loss": 3.7376, "step": 484864 }, { "epoch": 0.01, "learning_rate": 4.205334838436205e-05, "loss": 3.7413, "step": 485376 }, { "epoch": 0.01, "learning_rate": 4.204496243685153e-05, "loss": 3.7275, "step": 485888 }, { "epoch": 0.01, "learning_rate": 4.203657648934101e-05, "loss": 3.7359, "step": 486400 }, { "epoch": 0.01, "learning_rate": 4.202819054183049e-05, "loss": 3.7401, "step": 486912 }, { "epoch": 0.01, "learning_rate": 4.201980459431996e-05, "loss": 3.7337, "step": 487424 }, { "epoch": 0.01, "learning_rate": 4.201141864680944e-05, "loss": 3.7555, "step": 487936 }, { "epoch": 0.01, "learning_rate": 4.200303269929892e-05, "loss": 3.7329, "step": 488448 }, { "epoch": 0.01, "learning_rate": 4.19946467517884e-05, "loss": 3.7243, "step": 488960 }, { "epoch": 0.01, "learning_rate": 4.198627718308161e-05, "loss": 3.7503, "step": 489472 }, { "epoch": 0.01, "learning_rate": 4.197789123557109e-05, "loss": 3.7189, "step": 489984 }, { "epoch": 0.01, "learning_rate": 4.1969505288060576e-05, "loss": 3.7219, "step": 490496 }, { "epoch": 0.01, "learning_rate": 4.1961119340550056e-05, "loss": 3.7467, "step": 491008 }, { "epoch": 0.01, "learning_rate": 4.1952749771843265e-05, "loss": 3.7431, "step": 491520 }, { "epoch": 0.01, "learning_rate": 4.1944363824332745e-05, "loss": 3.7229, "step": 492032 }, { "epoch": 0.01, "learning_rate": 4.1935977876822225e-05, "loss": 3.7347, "step": 492544 }, { "epoch": 0.01, "learning_rate": 4.1927591929311705e-05, "loss": 3.7157, "step": 493056 }, { "epoch": 0.01, "learning_rate": 4.1919222360604914e-05, "loss": 3.7319, "step": 493568 }, { "epoch": 0.01, "learning_rate": 4.1910836413094394e-05, "loss": 3.7342, "step": 494080 }, { "epoch": 0.01, "learning_rate": 4.1902450465583874e-05, "loss": 3.7291, "step": 494592 }, { "epoch": 0.01, "learning_rate": 4.1894064518073354e-05, "loss": 3.7373, "step": 495104 }, { "epoch": 0.01, "learning_rate": 4.188569494936656e-05, "loss": 3.7362, "step": 495616 }, { "epoch": 0.01, "learning_rate": 4.187730900185604e-05, "loss": 3.7461, "step": 496128 }, { "epoch": 0.01, "learning_rate": 4.186892305434553e-05, "loss": 3.7297, "step": 496640 }, { "epoch": 0.01, "learning_rate": 4.186053710683501e-05, "loss": 3.7325, "step": 497152 }, { "epoch": 0.01, "learning_rate": 4.185216753812822e-05, "loss": 3.7347, "step": 497664 }, { "epoch": 0.01, "learning_rate": 4.18437815906177e-05, "loss": 3.7246, "step": 498176 }, { "epoch": 0.01, "learning_rate": 4.183539564310718e-05, "loss": 3.7369, "step": 498688 }, { "epoch": 0.01, "learning_rate": 4.182700969559666e-05, "loss": 3.7326, "step": 499200 }, { "epoch": 0.01, "learning_rate": 4.181864012688987e-05, "loss": 3.7269, "step": 499712 }, { "epoch": 0.01, "learning_rate": 4.181025417937935e-05, "loss": 3.7434, "step": 500224 }, { "epoch": 0.01, "learning_rate": 4.180186823186883e-05, "loss": 3.7167, "step": 500736 }, { "epoch": 0.01, "learning_rate": 4.179349866316204e-05, "loss": 3.7215, "step": 501248 }, { "epoch": 0.01, "learning_rate": 4.178511271565152e-05, "loss": 3.7325, "step": 501760 }, { "epoch": 0.01, "learning_rate": 4.1776726768141e-05, "loss": 3.7369, "step": 502272 }, { "epoch": 0.01, "learning_rate": 4.1768340820630484e-05, "loss": 3.7273, "step": 502784 }, { "epoch": 0.01, "learning_rate": 4.175997125192369e-05, "loss": 3.7314, "step": 503296 }, { "epoch": 0.02, "learning_rate": 4.175158530441317e-05, "loss": 3.7169, "step": 503808 }, { "epoch": 0.02, "learning_rate": 4.174319935690265e-05, "loss": 3.7299, "step": 504320 }, { "epoch": 0.02, "learning_rate": 4.173481340939213e-05, "loss": 3.7189, "step": 504832 }, { "epoch": 0.02, "learning_rate": 4.172644384068534e-05, "loss": 3.7276, "step": 505344 }, { "epoch": 0.02, "learning_rate": 4.171805789317482e-05, "loss": 3.7399, "step": 505856 }, { "epoch": 0.02, "learning_rate": 4.17096719456643e-05, "loss": 3.7324, "step": 506368 }, { "epoch": 0.02, "learning_rate": 4.170128599815378e-05, "loss": 3.7349, "step": 506880 }, { "epoch": 0.02, "learning_rate": 4.169291642944699e-05, "loss": 3.7216, "step": 507392 }, { "epoch": 0.02, "learning_rate": 4.168453048193647e-05, "loss": 3.7245, "step": 507904 }, { "epoch": 0.02, "learning_rate": 4.167614453442595e-05, "loss": 3.7242, "step": 508416 }, { "epoch": 0.02, "learning_rate": 4.166775858691544e-05, "loss": 3.7401, "step": 508928 }, { "epoch": 0.02, "learning_rate": 4.1659389018208646e-05, "loss": 3.7318, "step": 509440 }, { "epoch": 0.02, "learning_rate": 4.1651003070698126e-05, "loss": 3.7348, "step": 509952 }, { "epoch": 0.02, "learning_rate": 4.1642617123187606e-05, "loss": 3.7199, "step": 510464 }, { "epoch": 0.02, "learning_rate": 4.1634231175677086e-05, "loss": 3.7353, "step": 510976 }, { "epoch": 0.02, "learning_rate": 4.1625861606970295e-05, "loss": 3.7219, "step": 511488 }, { "epoch": 0.02, "learning_rate": 4.1617475659459775e-05, "loss": 3.7295, "step": 512000 }, { "epoch": 0.02, "learning_rate": 4.1609089711949255e-05, "loss": 3.7156, "step": 512512 }, { "epoch": 0.02, "learning_rate": 4.1600703764438735e-05, "loss": 3.7306, "step": 513024 }, { "epoch": 0.02, "learning_rate": 4.1592350574535674e-05, "loss": 3.7182, "step": 513536 }, { "epoch": 0.02, "learning_rate": 4.158396462702516e-05, "loss": 3.728, "step": 514048 }, { "epoch": 0.02, "learning_rate": 4.157557867951464e-05, "loss": 3.7167, "step": 514560 }, { "epoch": 0.02, "learning_rate": 4.156719273200412e-05, "loss": 3.7295, "step": 515072 }, { "epoch": 0.02, "learning_rate": 4.15588067844936e-05, "loss": 3.7216, "step": 515584 }, { "epoch": 0.02, "learning_rate": 4.155042083698308e-05, "loss": 3.7204, "step": 516096 }, { "epoch": 0.02, "learning_rate": 4.154203488947256e-05, "loss": 3.7346, "step": 516608 }, { "epoch": 0.02, "learning_rate": 4.153364894196204e-05, "loss": 3.7371, "step": 517120 }, { "epoch": 0.02, "learning_rate": 4.152527937325525e-05, "loss": 3.7313, "step": 517632 }, { "epoch": 0.02, "learning_rate": 4.151689342574473e-05, "loss": 3.726, "step": 518144 }, { "epoch": 0.02, "learning_rate": 4.150850747823421e-05, "loss": 3.722, "step": 518656 }, { "epoch": 0.02, "learning_rate": 4.150012153072369e-05, "loss": 3.7216, "step": 519168 }, { "epoch": 0.02, "learning_rate": 4.14917519620169e-05, "loss": 3.7241, "step": 519680 }, { "epoch": 0.02, "learning_rate": 4.148336601450638e-05, "loss": 3.7276, "step": 520192 }, { "epoch": 0.02, "learning_rate": 4.147498006699586e-05, "loss": 3.71, "step": 520704 }, { "epoch": 0.02, "learning_rate": 4.1466594119485345e-05, "loss": 3.7263, "step": 521216 }, { "epoch": 0.02, "learning_rate": 4.1458224550778554e-05, "loss": 3.728, "step": 521728 }, { "epoch": 0.02, "learning_rate": 4.1449838603268034e-05, "loss": 3.7257, "step": 522240 }, { "epoch": 0.02, "learning_rate": 4.1441452655757514e-05, "loss": 3.7224, "step": 522752 }, { "epoch": 0.02, "learning_rate": 4.1433066708246994e-05, "loss": 3.7221, "step": 523264 }, { "epoch": 0.02, "learning_rate": 4.14246971395402e-05, "loss": 3.7192, "step": 523776 }, { "epoch": 0.02, "learning_rate": 4.141631119202968e-05, "loss": 3.7329, "step": 524288 }, { "epoch": 0.02, "learning_rate": 4.140792524451916e-05, "loss": 3.7309, "step": 524800 }, { "epoch": 0.02, "learning_rate": 4.139953929700864e-05, "loss": 3.7298, "step": 525312 }, { "epoch": 0.02, "learning_rate": 4.139116972830185e-05, "loss": 3.7145, "step": 525824 }, { "epoch": 0.02, "learning_rate": 4.138278378079133e-05, "loss": 3.7279, "step": 526336 }, { "epoch": 0.02, "learning_rate": 4.137439783328081e-05, "loss": 3.7281, "step": 526848 }, { "epoch": 0.02, "learning_rate": 4.136601188577029e-05, "loss": 3.7203, "step": 527360 }, { "epoch": 0.02, "learning_rate": 4.135764231706351e-05, "loss": 3.7257, "step": 527872 }, { "epoch": 0.02, "learning_rate": 4.134925636955299e-05, "loss": 3.7264, "step": 528384 }, { "epoch": 0.02, "learning_rate": 4.134087042204247e-05, "loss": 3.7256, "step": 528896 }, { "epoch": 0.02, "learning_rate": 4.133248447453195e-05, "loss": 3.741, "step": 529408 }, { "epoch": 0.02, "learning_rate": 4.1324114905825156e-05, "loss": 3.7174, "step": 529920 }, { "epoch": 0.02, "learning_rate": 4.1315728958314636e-05, "loss": 3.7266, "step": 530432 }, { "epoch": 0.02, "learning_rate": 4.1307343010804116e-05, "loss": 3.7238, "step": 530944 }, { "epoch": 0.02, "learning_rate": 4.1298957063293596e-05, "loss": 3.7231, "step": 531456 }, { "epoch": 0.02, "learning_rate": 4.1290587494586805e-05, "loss": 3.7173, "step": 531968 }, { "epoch": 0.02, "learning_rate": 4.1282201547076285e-05, "loss": 3.7172, "step": 532480 }, { "epoch": 0.02, "learning_rate": 4.1273815599565765e-05, "loss": 3.722, "step": 532992 }, { "epoch": 0.02, "learning_rate": 4.1265429652055245e-05, "loss": 3.7107, "step": 533504 }, { "epoch": 0.02, "learning_rate": 4.125704370454473e-05, "loss": 3.7275, "step": 534016 }, { "epoch": 0.03, "eval_loss": 3.8657584190368652, "eval_runtime": 303.1251, "eval_samples_per_second": 1258.857, "eval_steps_per_second": 39.34, "step": 534240 }, { "epoch": 0.0, "learning_rate": 4.124865775703421e-05, "loss": 3.7247, "step": 534528 }, { "epoch": 0.0, "learning_rate": 4.1240271809523685e-05, "loss": 3.7104, "step": 535040 }, { "epoch": 0.0, "learning_rate": 4.1231885862013165e-05, "loss": 3.7234, "step": 535552 }, { "epoch": 0.0, "learning_rate": 4.1223499914502645e-05, "loss": 3.7231, "step": 536064 }, { "epoch": 0.0, "learning_rate": 4.1215113966992125e-05, "loss": 3.733, "step": 536576 }, { "epoch": 0.0, "learning_rate": 4.1206728019481605e-05, "loss": 3.7165, "step": 537088 }, { "epoch": 0.0, "learning_rate": 4.1198342071971085e-05, "loss": 3.7244, "step": 537600 }, { "epoch": 0.0, "learning_rate": 4.1189956124460565e-05, "loss": 3.7109, "step": 538112 }, { "epoch": 0.0, "learning_rate": 4.1181586555753774e-05, "loss": 3.7139, "step": 538624 }, { "epoch": 0.0, "learning_rate": 4.1173200608243254e-05, "loss": 3.7251, "step": 539136 }, { "epoch": 0.0, "learning_rate": 4.1164814660732734e-05, "loss": 3.7178, "step": 539648 }, { "epoch": 0.0, "learning_rate": 4.1156428713222214e-05, "loss": 3.7107, "step": 540160 }, { "epoch": 0.0, "learning_rate": 4.114807552331916e-05, "loss": 3.7214, "step": 540672 }, { "epoch": 0.0, "learning_rate": 4.113968957580864e-05, "loss": 3.71, "step": 541184 }, { "epoch": 0.0, "learning_rate": 4.113130362829812e-05, "loss": 3.7068, "step": 541696 }, { "epoch": 0.0, "learning_rate": 4.11229176807876e-05, "loss": 3.7041, "step": 542208 }, { "epoch": 0.0, "learning_rate": 4.111453173327708e-05, "loss": 3.7072, "step": 542720 }, { "epoch": 0.0, "learning_rate": 4.110614578576656e-05, "loss": 3.7184, "step": 543232 }, { "epoch": 0.0, "learning_rate": 4.109775983825604e-05, "loss": 3.7044, "step": 543744 }, { "epoch": 0.0, "learning_rate": 4.108937389074552e-05, "loss": 3.7281, "step": 544256 }, { "epoch": 0.0, "learning_rate": 4.108100432203873e-05, "loss": 3.7192, "step": 544768 }, { "epoch": 0.0, "learning_rate": 4.107261837452821e-05, "loss": 3.7243, "step": 545280 }, { "epoch": 0.0, "learning_rate": 4.106423242701769e-05, "loss": 3.7106, "step": 545792 }, { "epoch": 0.0, "learning_rate": 4.105584647950717e-05, "loss": 3.7124, "step": 546304 }, { "epoch": 0.0, "learning_rate": 4.104747691080038e-05, "loss": 3.7172, "step": 546816 }, { "epoch": 0.0, "learning_rate": 4.103909096328986e-05, "loss": 3.7186, "step": 547328 }, { "epoch": 0.0, "learning_rate": 4.103070501577934e-05, "loss": 3.7111, "step": 547840 }, { "epoch": 0.0, "learning_rate": 4.102231906826882e-05, "loss": 3.7133, "step": 548352 }, { "epoch": 0.0, "learning_rate": 4.101394949956203e-05, "loss": 3.7026, "step": 548864 }, { "epoch": 0.0, "learning_rate": 4.100556355205151e-05, "loss": 3.7101, "step": 549376 }, { "epoch": 0.01, "learning_rate": 4.099717760454099e-05, "loss": 3.7115, "step": 549888 }, { "epoch": 0.01, "learning_rate": 4.098879165703047e-05, "loss": 3.72, "step": 550400 }, { "epoch": 0.01, "learning_rate": 4.098042208832368e-05, "loss": 3.7191, "step": 550912 }, { "epoch": 0.01, "learning_rate": 4.097203614081316e-05, "loss": 3.7171, "step": 551424 }, { "epoch": 0.01, "learning_rate": 4.096365019330264e-05, "loss": 3.7126, "step": 551936 }, { "epoch": 0.01, "learning_rate": 4.095526424579212e-05, "loss": 3.7156, "step": 552448 }, { "epoch": 0.01, "learning_rate": 4.094689467708534e-05, "loss": 3.7158, "step": 552960 }, { "epoch": 0.01, "learning_rate": 4.093850872957482e-05, "loss": 3.7042, "step": 553472 }, { "epoch": 0.01, "learning_rate": 4.0930139160868026e-05, "loss": 3.7014, "step": 553984 }, { "epoch": 0.01, "learning_rate": 4.0921753213357506e-05, "loss": 3.6969, "step": 554496 }, { "epoch": 0.01, "learning_rate": 4.0913367265846986e-05, "loss": 3.7043, "step": 555008 }, { "epoch": 0.01, "learning_rate": 4.0904981318336466e-05, "loss": 3.7061, "step": 555520 }, { "epoch": 0.01, "learning_rate": 4.0896595370825946e-05, "loss": 3.7137, "step": 556032 }, { "epoch": 0.01, "learning_rate": 4.0888209423315426e-05, "loss": 3.7074, "step": 556544 }, { "epoch": 0.01, "learning_rate": 4.0879823475804906e-05, "loss": 3.7045, "step": 557056 }, { "epoch": 0.01, "learning_rate": 4.0871453907098115e-05, "loss": 3.7079, "step": 557568 }, { "epoch": 0.01, "learning_rate": 4.0863067959587595e-05, "loss": 3.7125, "step": 558080 }, { "epoch": 0.01, "learning_rate": 4.0854682012077075e-05, "loss": 3.6967, "step": 558592 }, { "epoch": 0.01, "learning_rate": 4.084629606456656e-05, "loss": 3.6817, "step": 559104 }, { "epoch": 0.01, "learning_rate": 4.083792649585977e-05, "loss": 3.7181, "step": 559616 }, { "epoch": 0.01, "learning_rate": 4.082954054834925e-05, "loss": 3.7105, "step": 560128 }, { "epoch": 0.01, "learning_rate": 4.082115460083873e-05, "loss": 3.7181, "step": 560640 }, { "epoch": 0.01, "learning_rate": 4.081276865332821e-05, "loss": 3.7043, "step": 561152 }, { "epoch": 0.01, "learning_rate": 4.080439908462142e-05, "loss": 3.7066, "step": 561664 }, { "epoch": 0.01, "learning_rate": 4.07960131371109e-05, "loss": 3.6956, "step": 562176 }, { "epoch": 0.01, "learning_rate": 4.078762718960038e-05, "loss": 3.7025, "step": 562688 }, { "epoch": 0.01, "learning_rate": 4.077924124208986e-05, "loss": 3.7109, "step": 563200 }, { "epoch": 0.01, "learning_rate": 4.077085529457934e-05, "loss": 3.6959, "step": 563712 }, { "epoch": 0.01, "learning_rate": 4.076246934706881e-05, "loss": 3.7246, "step": 564224 }, { "epoch": 0.01, "learning_rate": 4.07540833995583e-05, "loss": 3.7043, "step": 564736 }, { "epoch": 0.01, "learning_rate": 4.074569745204778e-05, "loss": 3.686, "step": 565248 }, { "epoch": 0.01, "learning_rate": 4.0737327883340995e-05, "loss": 3.7185, "step": 565760 }, { "epoch": 0.01, "learning_rate": 4.072894193583047e-05, "loss": 3.689, "step": 566272 }, { "epoch": 0.01, "learning_rate": 4.072055598831995e-05, "loss": 3.6895, "step": 566784 }, { "epoch": 0.01, "learning_rate": 4.071217004080943e-05, "loss": 3.7133, "step": 567296 }, { "epoch": 0.01, "learning_rate": 4.0703800472102644e-05, "loss": 3.7092, "step": 567808 }, { "epoch": 0.01, "learning_rate": 4.069541452459212e-05, "loss": 3.6922, "step": 568320 }, { "epoch": 0.01, "learning_rate": 4.06870285770816e-05, "loss": 3.7002, "step": 568832 }, { "epoch": 0.01, "learning_rate": 4.067864262957108e-05, "loss": 3.687, "step": 569344 }, { "epoch": 0.01, "learning_rate": 4.0670273060864286e-05, "loss": 3.6957, "step": 569856 }, { "epoch": 0.01, "learning_rate": 4.0661887113353766e-05, "loss": 3.7028, "step": 570368 }, { "epoch": 0.01, "learning_rate": 4.065351754464698e-05, "loss": 3.6959, "step": 570880 }, { "epoch": 0.01, "learning_rate": 4.064513159713646e-05, "loss": 3.7059, "step": 571392 }, { "epoch": 0.01, "learning_rate": 4.063674564962594e-05, "loss": 3.7005, "step": 571904 }, { "epoch": 0.01, "learning_rate": 4.062835970211542e-05, "loss": 3.7142, "step": 572416 }, { "epoch": 0.01, "learning_rate": 4.06199737546049e-05, "loss": 3.6965, "step": 572928 }, { "epoch": 0.01, "learning_rate": 4.061160418589812e-05, "loss": 3.7031, "step": 573440 }, { "epoch": 0.01, "learning_rate": 4.060321823838759e-05, "loss": 3.7005, "step": 573952 }, { "epoch": 0.01, "learning_rate": 4.059483229087707e-05, "loss": 3.6935, "step": 574464 }, { "epoch": 0.01, "learning_rate": 4.058644634336655e-05, "loss": 3.7064, "step": 574976 }, { "epoch": 0.01, "learning_rate": 4.057806039585603e-05, "loss": 3.7022, "step": 575488 }, { "epoch": 0.01, "learning_rate": 4.056967444834551e-05, "loss": 3.6912, "step": 576000 }, { "epoch": 0.01, "learning_rate": 4.056128850083499e-05, "loss": 3.7107, "step": 576512 }, { "epoch": 0.01, "learning_rate": 4.055290255332447e-05, "loss": 3.6852, "step": 577024 }, { "epoch": 0.01, "learning_rate": 4.054453298461769e-05, "loss": 3.6882, "step": 577536 }, { "epoch": 0.01, "learning_rate": 4.0536147037107167e-05, "loss": 3.7028, "step": 578048 }, { "epoch": 0.01, "learning_rate": 4.0527761089596647e-05, "loss": 3.7016, "step": 578560 }, { "epoch": 0.01, "learning_rate": 4.0519375142086127e-05, "loss": 3.6955, "step": 579072 }, { "epoch": 0.01, "learning_rate": 4.0511005573379336e-05, "loss": 3.7013, "step": 579584 }, { "epoch": 0.02, "learning_rate": 4.0502619625868816e-05, "loss": 3.6854, "step": 580096 }, { "epoch": 0.02, "learning_rate": 4.0494233678358296e-05, "loss": 3.6951, "step": 580608 }, { "epoch": 0.02, "learning_rate": 4.0485847730847775e-05, "loss": 3.69, "step": 581120 }, { "epoch": 0.02, "learning_rate": 4.0477478162140985e-05, "loss": 3.6941, "step": 581632 }, { "epoch": 0.02, "learning_rate": 4.0469092214630465e-05, "loss": 3.7081, "step": 582144 }, { "epoch": 0.02, "learning_rate": 4.0460706267119944e-05, "loss": 3.7007, "step": 582656 }, { "epoch": 0.02, "learning_rate": 4.0452320319609424e-05, "loss": 3.7053, "step": 583168 }, { "epoch": 0.02, "learning_rate": 4.044395075090264e-05, "loss": 3.6895, "step": 583680 }, { "epoch": 0.02, "learning_rate": 4.043556480339212e-05, "loss": 3.6931, "step": 584192 }, { "epoch": 0.02, "learning_rate": 4.04271788558816e-05, "loss": 3.6927, "step": 584704 }, { "epoch": 0.02, "learning_rate": 4.041879290837108e-05, "loss": 3.7033, "step": 585216 }, { "epoch": 0.02, "learning_rate": 4.041042333966429e-05, "loss": 3.7001, "step": 585728 }, { "epoch": 0.02, "learning_rate": 4.040203739215377e-05, "loss": 3.7044, "step": 586240 }, { "epoch": 0.02, "learning_rate": 4.039365144464325e-05, "loss": 3.6915, "step": 586752 }, { "epoch": 0.02, "learning_rate": 4.038526549713273e-05, "loss": 3.6986, "step": 587264 }, { "epoch": 0.02, "learning_rate": 4.037689592842594e-05, "loss": 3.694, "step": 587776 }, { "epoch": 0.02, "learning_rate": 4.036850998091542e-05, "loss": 3.6966, "step": 588288 }, { "epoch": 0.02, "learning_rate": 4.03601240334049e-05, "loss": 3.6847, "step": 588800 }, { "epoch": 0.02, "learning_rate": 4.035173808589438e-05, "loss": 3.7037, "step": 589312 }, { "epoch": 0.02, "learning_rate": 4.034338489599132e-05, "loss": 3.6866, "step": 589824 }, { "epoch": 0.02, "learning_rate": 4.03349989484808e-05, "loss": 3.6944, "step": 590336 }, { "epoch": 0.02, "learning_rate": 4.032661300097028e-05, "loss": 3.6863, "step": 590848 }, { "epoch": 0.02, "learning_rate": 4.031822705345976e-05, "loss": 3.6956, "step": 591360 }, { "epoch": 0.02, "learning_rate": 4.030984110594924e-05, "loss": 3.6934, "step": 591872 }, { "epoch": 0.02, "learning_rate": 4.030145515843872e-05, "loss": 3.6903, "step": 592384 }, { "epoch": 0.02, "learning_rate": 4.02930692109282e-05, "loss": 3.7008, "step": 592896 }, { "epoch": 0.02, "learning_rate": 4.028468326341768e-05, "loss": 3.7038, "step": 593408 }, { "epoch": 0.02, "learning_rate": 4.027631369471089e-05, "loss": 3.7064, "step": 593920 }, { "epoch": 0.02, "learning_rate": 4.026792774720037e-05, "loss": 3.6933, "step": 594432 }, { "epoch": 0.02, "learning_rate": 4.025954179968985e-05, "loss": 3.6909, "step": 594944 }, { "epoch": 0.02, "learning_rate": 4.025115585217933e-05, "loss": 3.6888, "step": 595456 }, { "epoch": 0.02, "learning_rate": 4.024278628347255e-05, "loss": 3.6923, "step": 595968 }, { "epoch": 0.02, "learning_rate": 4.023440033596203e-05, "loss": 3.6943, "step": 596480 }, { "epoch": 0.02, "learning_rate": 4.022601438845151e-05, "loss": 3.6815, "step": 596992 }, { "epoch": 0.02, "learning_rate": 4.021762844094099e-05, "loss": 3.6945, "step": 597504 }, { "epoch": 0.02, "learning_rate": 4.0209258872234197e-05, "loss": 3.6992, "step": 598016 }, { "epoch": 0.02, "learning_rate": 4.0200872924723677e-05, "loss": 3.6905, "step": 598528 }, { "epoch": 0.02, "learning_rate": 4.0192486977213157e-05, "loss": 3.6923, "step": 599040 }, { "epoch": 0.02, "learning_rate": 4.0184101029702636e-05, "loss": 3.6938, "step": 599552 }, { "epoch": 0.02, "learning_rate": 4.0175731460995846e-05, "loss": 3.6881, "step": 600064 }, { "epoch": 0.02, "learning_rate": 4.0167345513485326e-05, "loss": 3.7002, "step": 600576 }, { "epoch": 0.02, "learning_rate": 4.0158959565974805e-05, "loss": 3.6979, "step": 601088 }, { "epoch": 0.02, "learning_rate": 4.0150573618464285e-05, "loss": 3.7016, "step": 601600 }, { "epoch": 0.02, "learning_rate": 4.01422040497575e-05, "loss": 3.6826, "step": 602112 }, { "epoch": 0.02, "learning_rate": 4.013381810224698e-05, "loss": 3.6967, "step": 602624 }, { "epoch": 0.02, "learning_rate": 4.012543215473646e-05, "loss": 3.6965, "step": 603136 }, { "epoch": 0.02, "learning_rate": 4.011704620722594e-05, "loss": 3.6892, "step": 603648 }, { "epoch": 0.02, "learning_rate": 4.010867663851915e-05, "loss": 3.6953, "step": 604160 }, { "epoch": 0.02, "learning_rate": 4.010030706981236e-05, "loss": 3.6945, "step": 604672 }, { "epoch": 0.02, "learning_rate": 4.009192112230184e-05, "loss": 3.6959, "step": 605184 }, { "epoch": 0.02, "learning_rate": 4.008353517479132e-05, "loss": 3.7144, "step": 605696 }, { "epoch": 0.02, "learning_rate": 4.00751492272808e-05, "loss": 3.6826, "step": 606208 }, { "epoch": 0.02, "learning_rate": 4.006676327977028e-05, "loss": 3.6995, "step": 606720 }, { "epoch": 0.02, "learning_rate": 4.005837733225976e-05, "loss": 3.6908, "step": 607232 }, { "epoch": 0.02, "learning_rate": 4.004999138474924e-05, "loss": 3.6926, "step": 607744 }, { "epoch": 0.02, "learning_rate": 4.0041621816042455e-05, "loss": 3.688, "step": 608256 }, { "epoch": 0.02, "learning_rate": 4.0033235868531935e-05, "loss": 3.6849, "step": 608768 }, { "epoch": 0.02, "learning_rate": 4.0024849921021415e-05, "loss": 3.6933, "step": 609280 }, { "epoch": 0.02, "learning_rate": 4.0016463973510895e-05, "loss": 3.6787, "step": 609792 }, { "epoch": 0.02, "learning_rate": 4.000807802600037e-05, "loss": 3.696, "step": 610304 }, { "epoch": 0.03, "eval_loss": 3.859010934829712, "eval_runtime": 304.7053, "eval_samples_per_second": 1252.328, "eval_steps_per_second": 39.136, "step": 610560 }, { "epoch": 1.0, "learning_rate": 3.999969207848985e-05, "loss": 3.6903, "step": 610816 }, { "epoch": 1.0, "learning_rate": 3.999130613097933e-05, "loss": 3.683, "step": 611328 }, { "epoch": 1.0, "learning_rate": 3.998292018346881e-05, "loss": 3.6923, "step": 611840 }, { "epoch": 1.0, "learning_rate": 3.997455061476202e-05, "loss": 3.6941, "step": 612352 }, { "epoch": 1.0, "learning_rate": 3.99661646672515e-05, "loss": 3.7006, "step": 612864 }, { "epoch": 1.0, "learning_rate": 3.995777871974098e-05, "loss": 3.6879, "step": 613376 }, { "epoch": 1.0, "learning_rate": 3.994939277223046e-05, "loss": 3.6963, "step": 613888 }, { "epoch": 1.0, "learning_rate": 3.994102320352367e-05, "loss": 3.6793, "step": 614400 }, { "epoch": 1.0, "learning_rate": 3.993263725601315e-05, "loss": 3.6845, "step": 614912 }, { "epoch": 1.0, "learning_rate": 3.992425130850263e-05, "loss": 3.6964, "step": 615424 }, { "epoch": 1.0, "learning_rate": 3.991586536099211e-05, "loss": 3.6877, "step": 615936 }, { "epoch": 1.0, "learning_rate": 3.990749579228532e-05, "loss": 3.6788, "step": 616448 }, { "epoch": 1.0, "learning_rate": 3.989912622357854e-05, "loss": 3.6928, "step": 616960 }, { "epoch": 1.0, "learning_rate": 3.989074027606802e-05, "loss": 3.6769, "step": 617472 }, { "epoch": 1.0, "learning_rate": 3.988235432855749e-05, "loss": 3.6795, "step": 617984 }, { "epoch": 1.0, "learning_rate": 3.987396838104697e-05, "loss": 3.6697, "step": 618496 }, { "epoch": 1.0, "learning_rate": 3.986558243353645e-05, "loss": 3.6802, "step": 619008 }, { "epoch": 1.0, "learning_rate": 3.985719648602593e-05, "loss": 3.6901, "step": 619520 }, { "epoch": 1.0, "learning_rate": 3.984881053851541e-05, "loss": 3.6755, "step": 620032 }, { "epoch": 1.0, "learning_rate": 3.984042459100489e-05, "loss": 3.6963, "step": 620544 }, { "epoch": 1.0, "learning_rate": 3.9832055022298106e-05, "loss": 3.6926, "step": 621056 }, { "epoch": 1.0, "learning_rate": 3.9823669074787586e-05, "loss": 3.6921, "step": 621568 }, { "epoch": 1.0, "learning_rate": 3.9815283127277066e-05, "loss": 3.6842, "step": 622080 }, { "epoch": 1.0, "learning_rate": 3.9806897179766546e-05, "loss": 3.6831, "step": 622592 }, { "epoch": 1.0, "learning_rate": 3.9798527611059755e-05, "loss": 3.6867, "step": 623104 }, { "epoch": 1.0, "learning_rate": 3.9790141663549235e-05, "loss": 3.688, "step": 623616 }, { "epoch": 1.0, "learning_rate": 3.9781755716038715e-05, "loss": 3.6807, "step": 624128 }, { "epoch": 1.0, "learning_rate": 3.9773369768528195e-05, "loss": 3.6866, "step": 624640 }, { "epoch": 1.0, "learning_rate": 3.9765000199821404e-05, "loss": 3.6733, "step": 625152 }, { "epoch": 1.0, "learning_rate": 3.9756614252310884e-05, "loss": 3.6812, "step": 625664 }, { "epoch": 1.01, "learning_rate": 3.9748228304800364e-05, "loss": 3.6817, "step": 626176 }, { "epoch": 1.01, "learning_rate": 3.9739842357289844e-05, "loss": 3.6862, "step": 626688 }, { "epoch": 1.01, "learning_rate": 3.973147278858306e-05, "loss": 3.6902, "step": 627200 }, { "epoch": 1.01, "learning_rate": 3.972308684107254e-05, "loss": 3.6915, "step": 627712 }, { "epoch": 1.01, "learning_rate": 3.971470089356202e-05, "loss": 3.6775, "step": 628224 }, { "epoch": 1.01, "learning_rate": 3.97063149460515e-05, "loss": 3.6857, "step": 628736 }, { "epoch": 1.01, "learning_rate": 3.969794537734471e-05, "loss": 3.6917, "step": 629248 }, { "epoch": 1.01, "learning_rate": 3.968955942983419e-05, "loss": 3.6718, "step": 629760 }, { "epoch": 1.01, "learning_rate": 3.96811898611274e-05, "loss": 3.6749, "step": 630272 }, { "epoch": 1.01, "learning_rate": 3.967280391361688e-05, "loss": 3.6702, "step": 630784 }, { "epoch": 1.01, "learning_rate": 3.966441796610636e-05, "loss": 3.6722, "step": 631296 }, { "epoch": 1.01, "learning_rate": 3.965603201859584e-05, "loss": 3.6785, "step": 631808 }, { "epoch": 1.01, "learning_rate": 3.964764607108532e-05, "loss": 3.6866, "step": 632320 }, { "epoch": 1.01, "learning_rate": 3.96392601235748e-05, "loss": 3.6779, "step": 632832 }, { "epoch": 1.01, "learning_rate": 3.963087417606428e-05, "loss": 3.6748, "step": 633344 }, { "epoch": 1.01, "learning_rate": 3.9622488228553764e-05, "loss": 3.6748, "step": 633856 }, { "epoch": 1.01, "learning_rate": 3.9614118659846974e-05, "loss": 3.6874, "step": 634368 }, { "epoch": 1.01, "learning_rate": 3.9605732712336454e-05, "loss": 3.6669, "step": 634880 }, { "epoch": 1.01, "learning_rate": 3.9597346764825933e-05, "loss": 3.6557, "step": 635392 }, { "epoch": 1.01, "learning_rate": 3.958897719611914e-05, "loss": 3.6881, "step": 635904 }, { "epoch": 1.01, "learning_rate": 3.958059124860862e-05, "loss": 3.6813, "step": 636416 }, { "epoch": 1.01, "learning_rate": 3.95722053010981e-05, "loss": 3.6883, "step": 636928 }, { "epoch": 1.01, "learning_rate": 3.956381935358758e-05, "loss": 3.6753, "step": 637440 }, { "epoch": 1.01, "learning_rate": 3.955544978488079e-05, "loss": 3.6772, "step": 637952 }, { "epoch": 1.01, "learning_rate": 3.954706383737027e-05, "loss": 3.6697, "step": 638464 }, { "epoch": 1.01, "learning_rate": 3.953867788985975e-05, "loss": 3.6754, "step": 638976 }, { "epoch": 1.01, "learning_rate": 3.953029194234923e-05, "loss": 3.6839, "step": 639488 }, { "epoch": 1.01, "learning_rate": 3.952190599483872e-05, "loss": 3.6654, "step": 640000 }, { "epoch": 1.01, "learning_rate": 3.95135200473282e-05, "loss": 3.6992, "step": 640512 }, { "epoch": 1.01, "learning_rate": 3.950513409981768e-05, "loss": 3.6727, "step": 641024 }, { "epoch": 1.01, "learning_rate": 3.949674815230715e-05, "loss": 3.6572, "step": 641536 }, { "epoch": 1.01, "learning_rate": 3.948837858360037e-05, "loss": 3.6902, "step": 642048 }, { "epoch": 1.01, "learning_rate": 3.947999263608985e-05, "loss": 3.6673, "step": 642560 }, { "epoch": 1.01, "learning_rate": 3.947160668857933e-05, "loss": 3.6583, "step": 643072 }, { "epoch": 1.01, "learning_rate": 3.94632207410688e-05, "loss": 3.6828, "step": 643584 }, { "epoch": 1.01, "learning_rate": 3.9454851172362016e-05, "loss": 3.6822, "step": 644096 }, { "epoch": 1.01, "learning_rate": 3.9446481603655225e-05, "loss": 3.666, "step": 644608 }, { "epoch": 1.01, "learning_rate": 3.9438095656144705e-05, "loss": 3.6706, "step": 645120 }, { "epoch": 1.01, "learning_rate": 3.9429709708634185e-05, "loss": 3.6555, "step": 645632 }, { "epoch": 1.01, "learning_rate": 3.942132376112367e-05, "loss": 3.6678, "step": 646144 }, { "epoch": 1.01, "learning_rate": 3.941293781361315e-05, "loss": 3.6774, "step": 646656 }, { "epoch": 1.01, "learning_rate": 3.940456824490636e-05, "loss": 3.6682, "step": 647168 }, { "epoch": 1.01, "learning_rate": 3.939618229739584e-05, "loss": 3.6753, "step": 647680 }, { "epoch": 1.01, "learning_rate": 3.938779634988532e-05, "loss": 3.6706, "step": 648192 }, { "epoch": 1.01, "learning_rate": 3.93794104023748e-05, "loss": 3.6862, "step": 648704 }, { "epoch": 1.01, "learning_rate": 3.937104083366801e-05, "loss": 3.6684, "step": 649216 }, { "epoch": 1.01, "learning_rate": 3.936265488615749e-05, "loss": 3.6759, "step": 649728 }, { "epoch": 1.01, "learning_rate": 3.935426893864697e-05, "loss": 3.6721, "step": 650240 }, { "epoch": 1.01, "learning_rate": 3.934588299113644e-05, "loss": 3.6672, "step": 650752 }, { "epoch": 1.01, "learning_rate": 3.933749704362592e-05, "loss": 3.6797, "step": 651264 }, { "epoch": 1.01, "learning_rate": 3.932912747491914e-05, "loss": 3.6725, "step": 651776 }, { "epoch": 1.01, "learning_rate": 3.9320741527408625e-05, "loss": 3.6682, "step": 652288 }, { "epoch": 1.01, "learning_rate": 3.93123555798981e-05, "loss": 3.6817, "step": 652800 }, { "epoch": 1.01, "learning_rate": 3.930396963238758e-05, "loss": 3.6583, "step": 653312 }, { "epoch": 1.01, "learning_rate": 3.9295600063680794e-05, "loss": 3.6627, "step": 653824 }, { "epoch": 1.01, "learning_rate": 3.9287214116170274e-05, "loss": 3.6713, "step": 654336 }, { "epoch": 1.01, "learning_rate": 3.927882816865975e-05, "loss": 3.676, "step": 654848 }, { "epoch": 1.01, "learning_rate": 3.927044222114923e-05, "loss": 3.6625, "step": 655360 }, { "epoch": 1.01, "learning_rate": 3.926205627363871e-05, "loss": 3.6764, "step": 655872 }, { "epoch": 1.02, "learning_rate": 3.925367032612819e-05, "loss": 3.6628, "step": 656384 }, { "epoch": 1.02, "learning_rate": 3.924528437861767e-05, "loss": 3.6653, "step": 656896 }, { "epoch": 1.02, "learning_rate": 3.923689843110715e-05, "loss": 3.6596, "step": 657408 }, { "epoch": 1.02, "learning_rate": 3.922852886240036e-05, "loss": 3.6668, "step": 657920 }, { "epoch": 1.02, "learning_rate": 3.922014291488984e-05, "loss": 3.681, "step": 658432 }, { "epoch": 1.02, "learning_rate": 3.921175696737932e-05, "loss": 3.671, "step": 658944 }, { "epoch": 1.02, "learning_rate": 3.92033710198688e-05, "loss": 3.6767, "step": 659456 }, { "epoch": 1.02, "learning_rate": 3.919500145116201e-05, "loss": 3.6641, "step": 659968 }, { "epoch": 1.02, "learning_rate": 3.918661550365149e-05, "loss": 3.6636, "step": 660480 }, { "epoch": 1.02, "learning_rate": 3.91782459349447e-05, "loss": 3.665, "step": 660992 }, { "epoch": 1.02, "learning_rate": 3.916985998743418e-05, "loss": 3.6758, "step": 661504 }, { "epoch": 1.02, "learning_rate": 3.916147403992366e-05, "loss": 3.6723, "step": 662016 }, { "epoch": 1.02, "learning_rate": 3.915308809241314e-05, "loss": 3.6744, "step": 662528 }, { "epoch": 1.02, "learning_rate": 3.914470214490262e-05, "loss": 3.6706, "step": 663040 }, { "epoch": 1.02, "learning_rate": 3.91363161973921e-05, "loss": 3.6684, "step": 663552 }, { "epoch": 1.02, "learning_rate": 3.912793024988158e-05, "loss": 3.6678, "step": 664064 }, { "epoch": 1.02, "learning_rate": 3.911954430237106e-05, "loss": 3.6673, "step": 664576 }, { "epoch": 1.02, "learning_rate": 3.911117473366428e-05, "loss": 3.6588, "step": 665088 }, { "epoch": 1.02, "learning_rate": 3.910278878615376e-05, "loss": 3.6734, "step": 665600 }, { "epoch": 1.02, "learning_rate": 3.909440283864324e-05, "loss": 3.6606, "step": 666112 }, { "epoch": 1.02, "learning_rate": 3.908601689113272e-05, "loss": 3.666, "step": 666624 }, { "epoch": 1.02, "learning_rate": 3.90776309436222e-05, "loss": 3.6629, "step": 667136 }, { "epoch": 1.02, "learning_rate": 3.906924499611168e-05, "loss": 3.6634, "step": 667648 }, { "epoch": 1.02, "learning_rate": 3.9060859048601157e-05, "loss": 3.6674, "step": 668160 }, { "epoch": 1.02, "learning_rate": 3.9052473101090637e-05, "loss": 3.6625, "step": 668672 }, { "epoch": 1.02, "learning_rate": 3.9044103532383846e-05, "loss": 3.6767, "step": 669184 }, { "epoch": 1.02, "learning_rate": 3.9035717584873326e-05, "loss": 3.6778, "step": 669696 }, { "epoch": 1.02, "learning_rate": 3.9027331637362806e-05, "loss": 3.6753, "step": 670208 }, { "epoch": 1.02, "learning_rate": 3.901894568985228e-05, "loss": 3.664, "step": 670720 }, { "epoch": 1.02, "learning_rate": 3.9010576121145495e-05, "loss": 3.6681, "step": 671232 }, { "epoch": 1.02, "learning_rate": 3.900219017363498e-05, "loss": 3.6614, "step": 671744 }, { "epoch": 1.02, "learning_rate": 3.899380422612446e-05, "loss": 3.6677, "step": 672256 }, { "epoch": 1.02, "learning_rate": 3.898543465741767e-05, "loss": 3.6691, "step": 672768 }, { "epoch": 1.02, "learning_rate": 3.897704870990715e-05, "loss": 3.6543, "step": 673280 }, { "epoch": 1.02, "learning_rate": 3.896866276239663e-05, "loss": 3.666, "step": 673792 }, { "epoch": 1.02, "learning_rate": 3.896027681488611e-05, "loss": 3.6703, "step": 674304 }, { "epoch": 1.02, "learning_rate": 3.8951890867375583e-05, "loss": 3.6683, "step": 674816 }, { "epoch": 1.02, "learning_rate": 3.8943504919865063e-05, "loss": 3.6622, "step": 675328 }, { "epoch": 1.02, "learning_rate": 3.893511897235454e-05, "loss": 3.6641, "step": 675840 }, { "epoch": 1.02, "learning_rate": 3.892673302484402e-05, "loss": 3.6608, "step": 676352 }, { "epoch": 1.02, "learning_rate": 3.891836345613723e-05, "loss": 3.6754, "step": 676864 }, { "epoch": 1.02, "learning_rate": 3.890997750862672e-05, "loss": 3.6671, "step": 677376 }, { "epoch": 1.02, "learning_rate": 3.89015915611162e-05, "loss": 3.6786, "step": 677888 }, { "epoch": 1.02, "learning_rate": 3.889320561360568e-05, "loss": 3.6571, "step": 678400 }, { "epoch": 1.02, "learning_rate": 3.888483604489889e-05, "loss": 3.6661, "step": 678912 }, { "epoch": 1.02, "learning_rate": 3.887645009738837e-05, "loss": 3.6722, "step": 679424 }, { "epoch": 1.02, "learning_rate": 3.886806414987785e-05, "loss": 3.6651, "step": 679936 }, { "epoch": 1.02, "learning_rate": 3.885967820236733e-05, "loss": 3.666, "step": 680448 }, { "epoch": 1.02, "learning_rate": 3.885130863366054e-05, "loss": 3.6693, "step": 680960 }, { "epoch": 1.02, "learning_rate": 3.884292268615002e-05, "loss": 3.6683, "step": 681472 }, { "epoch": 1.02, "learning_rate": 3.88345367386395e-05, "loss": 3.6852, "step": 681984 }, { "epoch": 1.02, "learning_rate": 3.882615079112898e-05, "loss": 3.6624, "step": 682496 }, { "epoch": 1.02, "learning_rate": 3.881776484361846e-05, "loss": 3.6708, "step": 683008 }, { "epoch": 1.02, "learning_rate": 3.880939527491167e-05, "loss": 3.6681, "step": 683520 }, { "epoch": 1.02, "learning_rate": 3.880100932740115e-05, "loss": 3.6625, "step": 684032 }, { "epoch": 1.02, "learning_rate": 3.879262337989063e-05, "loss": 3.664, "step": 684544 }, { "epoch": 1.02, "learning_rate": 3.878423743238011e-05, "loss": 3.6587, "step": 685056 }, { "epoch": 1.02, "learning_rate": 3.877585148486959e-05, "loss": 3.6659, "step": 685568 }, { "epoch": 1.02, "learning_rate": 3.876746553735907e-05, "loss": 3.6577, "step": 686080 }, { "epoch": 1.02, "learning_rate": 3.875907958984855e-05, "loss": 3.6663, "step": 686592 }, { "epoch": 1.03, "eval_loss": 3.8544273376464844, "eval_runtime": 304.6113, "eval_samples_per_second": 1252.715, "eval_steps_per_second": 39.148, "step": 686880 } ], "logging_steps": 512, "max_steps": 3052726, "num_train_epochs": 9223372036854775807, "save_steps": 10, "total_flos": 4.690546389251574e+17, "trial_name": null, "trial_params": null }