diff --git "a/checkpoint-2900160/trainer_state.json" "b/checkpoint-2900160/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-2900160/trainer_state.json" @@ -0,0 +1,34313 @@ +{ + "best_metric": 3.8431339263916016, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/binding-domain/transformer/1/checkpoints/checkpoint-915840", + "epoch": 0.025000606015738065, + "eval_steps": 10, + "global_step": 2900160, + "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": 10.9442, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 6.8159, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 6.1825, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 5.9707, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 5.8071, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 5.7081, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 5.5931, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 5.5266, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 5.4395, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 5.3928, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 5.3424, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 5.3031, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989936862987376e-05, + "loss": 5.2534, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989099906116697e-05, + "loss": 5.2032, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988261311365645e-05, + "loss": 5.1676, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.987422716614593e-05, + "loss": 5.1263, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986584121863541e-05, + "loss": 5.0976, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985745527112489e-05, + "loss": 5.0754, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984906932361437e-05, + "loss": 5.0474, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.0163, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 5.0041, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.9823927859886547e-05, + "loss": 4.9666, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.9815541912376026e-05, + "loss": 4.9505, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.9807155964865506e-05, + "loss": 4.9255, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 4.9149, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790400448648195e-05, + "loss": 4.8877, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9782014501137675e-05, + "loss": 4.868, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773628553627155e-05, + "loss": 4.8473, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 4.8306, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756873037409844e-05, + "loss": 4.8159, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748487089899324e-05, + "loss": 4.7985, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.9740101142388804e-05, + "loss": 4.7944, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731715194878284e-05, + "loss": 4.7736, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.9723329247367764e-05, + "loss": 4.7668, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.971495967866098e-05, + "loss": 4.7599, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.970657373115046e-05, + "loss": 4.7426, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969820416244367e-05, + "loss": 4.7332, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968981821493315e-05, + "loss": 4.7059, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.968143226742263e-05, + "loss": 4.7025, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967304631991211e-05, + "loss": 4.6833, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966466037240159e-05, + "loss": 4.683, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965627442489107e-05, + "loss": 4.6713, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964788847738054e-05, + "loss": 4.6618, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963950252987002e-05, + "loss": 4.6407, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.963113296116324e-05, + "loss": 4.652, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962274701365272e-05, + "loss": 4.6377, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.96143610661422e-05, + "loss": 4.631, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960597511863168e-05, + "loss": 4.6229, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.9597605549924894e-05, + "loss": 4.5922, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.95892359812181e-05, + "loss": 4.5904, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958085003370758e-05, + "loss": 4.5977, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957246408619706e-05, + "loss": 4.5871, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956407813868654e-05, + "loss": 4.5702, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.9555692191176016e-05, + "loss": 4.5507, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.9547306243665496e-05, + "loss": 4.5534, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.9538920296154976e-05, + "loss": 4.5408, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.953055072744819e-05, + "loss": 4.567, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.952216477993767e-05, + "loss": 4.525, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951377883242715e-05, + "loss": 4.5374, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.950539288491663e-05, + "loss": 4.5326, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949700693740611e-05, + "loss": 4.5087, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948862098989559e-05, + "loss": 4.5133, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.948023504238507e-05, + "loss": 4.5017, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947184909487455e-05, + "loss": 4.4855, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946346314736403e-05, + "loss": 4.485, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945509357865724e-05, + "loss": 4.5051, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944670763114672e-05, + "loss": 4.4823, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.94383216836362e-05, + "loss": 4.4708, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942993573612568e-05, + "loss": 4.4625, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.942156616741889e-05, + "loss": 4.464, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.941318021990837e-05, + "loss": 4.4755, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.9404810651201585e-05, + "loss": 4.4733, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396424703691065e-05, + "loss": 4.4607, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388038756180545e-05, + "loss": 4.4662, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379652808670025e-05, + "loss": 4.4659, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371266861159505e-05, + "loss": 4.4519, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.9362897292452714e-05, + "loss": 4.4405, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.9354511344942194e-05, + "loss": 4.4304, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.9346125397431674e-05, + "loss": 4.4308, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.9337739449921154e-05, + "loss": 4.4242, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.9329353502410634e-05, + "loss": 4.4181, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.9320967554900114e-05, + "loss": 4.4202, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.9312581607389594e-05, + "loss": 4.4205, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.9304195659879074e-05, + "loss": 4.4165, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.929582609117229e-05, + "loss": 4.3917, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.928744014366177e-05, + "loss": 4.3912, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.927905419615125e-05, + "loss": 4.4003, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.927066824864073e-05, + "loss": 4.4041, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.926229867993394e-05, + "loss": 4.3836, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925392911122715e-05, + "loss": 4.3861, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.924554316371663e-05, + "loss": 4.3913, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923715721620611e-05, + "loss": 4.376, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922878764749932e-05, + "loss": 4.3708, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.92204016999888e-05, + "loss": 4.3744, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921201575247828e-05, + "loss": 4.3661, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920362980496776e-05, + "loss": 4.3728, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919524385745724e-05, + "loss": 4.3604, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918685790994672e-05, + "loss": 4.3474, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.91784719624362e-05, + "loss": 4.3544, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.9170086014925676e-05, + "loss": 4.3565, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.9161700067415156e-05, + "loss": 4.35, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.9153314119904636e-05, + "loss": 4.3492, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.9144928172394116e-05, + "loss": 4.3441, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.9136542224883596e-05, + "loss": 4.341, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.9128172656176805e-05, + "loss": 4.34, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.9119786708666285e-05, + "loss": 4.3174, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.91114171399595e-05, + "loss": 4.3196, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.910303119244898e-05, + "loss": 4.3271, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.909464524493846e-05, + "loss": 4.323, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908625929742794e-05, + "loss": 4.3137, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907787334991742e-05, + "loss": 4.3104, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.90694874024069e-05, + "loss": 4.3079, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906110145489638e-05, + "loss": 4.3122, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.905273188618959e-05, + "loss": 4.3059, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.904434593867907e-05, + "loss": 4.3073, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903595999116855e-05, + "loss": 4.3015, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.902757404365803e-05, + "loss": 4.3073, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.901918809614751e-05, + "loss": 4.3013, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.901080214863699e-05, + "loss": 4.2978, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.900241620112647e-05, + "loss": 4.3002, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.8994046632419686e-05, + "loss": 4.2978, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.8985660684909166e-05, + "loss": 4.2876, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.8977274737398646e-05, + "loss": 4.2935, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968888789888125e-05, + "loss": 4.281, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.8960519221181335e-05, + "loss": 4.2909, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.8952133273670815e-05, + "loss": 4.2679, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.8943747326160294e-05, + "loss": 4.2787, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.8935361378649774e-05, + "loss": 4.2645, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.8926991809942984e-05, + "loss": 4.2691, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.8918605862432463e-05, + "loss": 4.254, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.8910219914921943e-05, + "loss": 4.2842, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.8901833967411423e-05, + "loss": 4.272, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.889346439870464e-05, + "loss": 4.2579, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888507845119412e-05, + "loss": 4.2597, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.88766925036836e-05, + "loss": 4.2622, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886830655617308e-05, + "loss": 4.2675, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885992060866256e-05, + "loss": 4.2645, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.885155103995577e-05, + "loss": 4.2512, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884316509244525e-05, + "loss": 4.2596, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883477914493473e-05, + "loss": 4.2461, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882639319742421e-05, + "loss": 4.2582, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.881800724991369e-05, + "loss": 4.2432, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.880962130240316e-05, + "loss": 4.245, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.880123535489264e-05, + "loss": 4.2438, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.879286578618586e-05, + "loss": 4.2345, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.878447983867534e-05, + "loss": 4.2405, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877609389116482e-05, + "loss": 4.2353, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.87677079436543e-05, + "loss": 4.235, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875932199614378e-05, + "loss": 4.2367, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.875093604863326e-05, + "loss": 4.2283, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.194109916687012, + "eval_runtime": 367.2307, + "eval_samples_per_second": 1039.104, + "eval_steps_per_second": 32.473, + "step": 76320 + }, + { + "epoch": 1.0, + "learning_rate": 4.874255010112274e-05, + "loss": 4.2116, + "step": 76800 + }, + { + "epoch": 1.0, + "learning_rate": 4.873416415361222e-05, + "loss": 4.2104, + "step": 77312 + }, + { + "epoch": 1.0, + "learning_rate": 4.8725794584905426e-05, + "loss": 4.2294, + "step": 77824 + }, + { + "epoch": 1.0, + "learning_rate": 4.8717408637394906e-05, + "loss": 4.213, + "step": 78336 + }, + { + "epoch": 1.0, + "learning_rate": 4.8709022689884386e-05, + "loss": 4.2306, + "step": 78848 + }, + { + "epoch": 1.0, + "learning_rate": 4.8700636742373866e-05, + "loss": 4.2022, + "step": 79360 + }, + { + "epoch": 1.0, + "learning_rate": 4.8692267173667075e-05, + "loss": 4.2096, + "step": 79872 + }, + { + "epoch": 1.0, + "learning_rate": 4.8683881226156555e-05, + "loss": 4.1932, + "step": 80384 + }, + { + "epoch": 1.0, + "learning_rate": 4.867549527864604e-05, + "loss": 4.2088, + "step": 80896 + }, + { + "epoch": 1.0, + "learning_rate": 4.866710933113552e-05, + "loss": 4.2033, + "step": 81408 + }, + { + "epoch": 1.0, + "learning_rate": 4.8658723383625e-05, + "loss": 4.2083, + "step": 81920 + }, + { + "epoch": 1.0, + "learning_rate": 4.865033743611448e-05, + "loss": 4.203, + "step": 82432 + }, + { + "epoch": 1.0, + "learning_rate": 4.864198424621142e-05, + "loss": 4.1892, + "step": 82944 + }, + { + "epoch": 1.0, + "learning_rate": 4.86335982987009e-05, + "loss": 4.1912, + "step": 83456 + }, + { + "epoch": 1.0, + "learning_rate": 4.862521235119038e-05, + "loss": 4.1859, + "step": 83968 + }, + { + "epoch": 1.0, + "learning_rate": 4.861682640367986e-05, + "loss": 4.1815, + "step": 84480 + }, + { + "epoch": 1.0, + "learning_rate": 4.860844045616934e-05, + "loss": 4.1882, + "step": 84992 + }, + { + "epoch": 1.0, + "learning_rate": 4.860005450865882e-05, + "loss": 4.1843, + "step": 85504 + }, + { + "epoch": 1.0, + "learning_rate": 4.85916685611483e-05, + "loss": 4.1804, + "step": 86016 + }, + { + "epoch": 1.0, + "learning_rate": 4.858329899244151e-05, + "loss": 4.1994, + "step": 86528 + }, + { + "epoch": 1.0, + "learning_rate": 4.8574913044930995e-05, + "loss": 4.1726, + "step": 87040 + }, + { + "epoch": 1.0, + "learning_rate": 4.8566527097420475e-05, + "loss": 4.1829, + "step": 87552 + }, + { + "epoch": 1.0, + "learning_rate": 4.8558141149909955e-05, + "loss": 4.1785, + "step": 88064 + }, + { + "epoch": 1.0, + "learning_rate": 4.8549755202399435e-05, + "loss": 4.1884, + "step": 88576 + }, + { + "epoch": 1.0, + "learning_rate": 4.8541385633692644e-05, + "loss": 4.1634, + "step": 89088 + }, + { + "epoch": 1.0, + "learning_rate": 4.8532999686182124e-05, + "loss": 4.1707, + "step": 89600 + }, + { + "epoch": 1.0, + "learning_rate": 4.8524613738671604e-05, + "loss": 4.165, + "step": 90112 + }, + { + "epoch": 1.0, + "learning_rate": 4.8516227791161084e-05, + "loss": 4.1697, + "step": 90624 + }, + { + "epoch": 1.0, + "learning_rate": 4.8507841843650564e-05, + "loss": 4.1546, + "step": 91136 + }, + { + "epoch": 1.01, + "learning_rate": 4.849947227494377e-05, + "loss": 4.1581, + "step": 91648 + }, + { + "epoch": 1.01, + "learning_rate": 4.849108632743325e-05, + "loss": 4.1658, + "step": 92160 + }, + { + "epoch": 1.01, + "learning_rate": 4.848270037992273e-05, + "loss": 4.1614, + "step": 92672 + }, + { + "epoch": 1.01, + "learning_rate": 4.847431443241221e-05, + "loss": 4.1617, + "step": 93184 + }, + { + "epoch": 1.01, + "learning_rate": 4.846592848490169e-05, + "loss": 4.1652, + "step": 93696 + }, + { + "epoch": 1.01, + "learning_rate": 4.845754253739117e-05, + "loss": 4.1595, + "step": 94208 + }, + { + "epoch": 1.01, + "learning_rate": 4.844917296868439e-05, + "loss": 4.1591, + "step": 94720 + }, + { + "epoch": 1.01, + "learning_rate": 4.844078702117387e-05, + "loss": 4.147, + "step": 95232 + }, + { + "epoch": 1.01, + "learning_rate": 4.843240107366335e-05, + "loss": 4.1529, + "step": 95744 + }, + { + "epoch": 1.01, + "learning_rate": 4.842401512615282e-05, + "loss": 4.1399, + "step": 96256 + }, + { + "epoch": 1.01, + "learning_rate": 4.84156291786423e-05, + "loss": 4.1465, + "step": 96768 + }, + { + "epoch": 1.01, + "learning_rate": 4.840725960993552e-05, + "loss": 4.1473, + "step": 97280 + }, + { + "epoch": 1.01, + "learning_rate": 4.8398873662425e-05, + "loss": 4.1452, + "step": 97792 + }, + { + "epoch": 1.01, + "learning_rate": 4.839048771491447e-05, + "loss": 4.1357, + "step": 98304 + }, + { + "epoch": 1.01, + "learning_rate": 4.838210176740395e-05, + "loss": 4.1441, + "step": 98816 + }, + { + "epoch": 1.01, + "learning_rate": 4.8373732198697167e-05, + "loss": 4.1474, + "step": 99328 + }, + { + "epoch": 1.01, + "learning_rate": 4.8365346251186646e-05, + "loss": 4.1401, + "step": 99840 + }, + { + "epoch": 1.01, + "learning_rate": 4.8356960303676126e-05, + "loss": 4.1424, + "step": 100352 + }, + { + "epoch": 1.01, + "learning_rate": 4.8348574356165606e-05, + "loss": 4.1138, + "step": 100864 + }, + { + "epoch": 1.01, + "learning_rate": 4.834020478745882e-05, + "loss": 4.1202, + "step": 101376 + }, + { + "epoch": 1.01, + "learning_rate": 4.8331818839948295e-05, + "loss": 4.1387, + "step": 101888 + }, + { + "epoch": 1.01, + "learning_rate": 4.8323432892437775e-05, + "loss": 4.1304, + "step": 102400 + }, + { + "epoch": 1.01, + "learning_rate": 4.8315046944927255e-05, + "loss": 4.126, + "step": 102912 + }, + { + "epoch": 1.01, + "learning_rate": 4.830667737622047e-05, + "loss": 4.1089, + "step": 103424 + }, + { + "epoch": 1.01, + "learning_rate": 4.8298291428709944e-05, + "loss": 4.1144, + "step": 103936 + }, + { + "epoch": 1.01, + "learning_rate": 4.8289905481199424e-05, + "loss": 4.1075, + "step": 104448 + }, + { + "epoch": 1.01, + "learning_rate": 4.8281519533688904e-05, + "loss": 4.132, + "step": 104960 + }, + { + "epoch": 1.01, + "learning_rate": 4.8273133586178384e-05, + "loss": 4.1058, + "step": 105472 + }, + { + "epoch": 1.01, + "learning_rate": 4.82647640174716e-05, + "loss": 4.1194, + "step": 105984 + }, + { + "epoch": 1.01, + "learning_rate": 4.825637806996108e-05, + "loss": 4.1235, + "step": 106496 + }, + { + "epoch": 1.01, + "learning_rate": 4.824799212245056e-05, + "loss": 4.103, + "step": 107008 + }, + { + "epoch": 1.01, + "learning_rate": 4.823960617494004e-05, + "loss": 4.1104, + "step": 107520 + }, + { + "epoch": 1.01, + "learning_rate": 4.823123660623325e-05, + "loss": 4.1026, + "step": 108032 + }, + { + "epoch": 1.01, + "learning_rate": 4.822285065872273e-05, + "loss": 4.0981, + "step": 108544 + }, + { + "epoch": 1.01, + "learning_rate": 4.821446471121221e-05, + "loss": 4.0991, + "step": 109056 + }, + { + "epoch": 1.01, + "learning_rate": 4.820607876370169e-05, + "loss": 4.1143, + "step": 109568 + }, + { + "epoch": 1.01, + "learning_rate": 4.81977091949949e-05, + "loss": 4.1051, + "step": 110080 + }, + { + "epoch": 1.01, + "learning_rate": 4.818932324748438e-05, + "loss": 4.0947, + "step": 110592 + }, + { + "epoch": 1.01, + "learning_rate": 4.818093729997386e-05, + "loss": 4.0934, + "step": 111104 + }, + { + "epoch": 1.01, + "learning_rate": 4.817255135246334e-05, + "loss": 4.0944, + "step": 111616 + }, + { + "epoch": 1.01, + "learning_rate": 4.8164181783756554e-05, + "loss": 4.1095, + "step": 112128 + }, + { + "epoch": 1.01, + "learning_rate": 4.8155795836246034e-05, + "loss": 4.1114, + "step": 112640 + }, + { + "epoch": 1.01, + "learning_rate": 4.8147409888735514e-05, + "loss": 4.1042, + "step": 113152 + }, + { + "epoch": 1.01, + "learning_rate": 4.8139023941224994e-05, + "loss": 4.1135, + "step": 113664 + }, + { + "epoch": 1.01, + "learning_rate": 4.8130637993714474e-05, + "loss": 4.1096, + "step": 114176 + }, + { + "epoch": 1.01, + "learning_rate": 4.8122252046203954e-05, + "loss": 4.106, + "step": 114688 + }, + { + "epoch": 1.01, + "learning_rate": 4.811388247749716e-05, + "loss": 4.0945, + "step": 115200 + }, + { + "epoch": 1.01, + "learning_rate": 4.810549652998664e-05, + "loss": 4.0927, + "step": 115712 + }, + { + "epoch": 1.01, + "learning_rate": 4.809711058247612e-05, + "loss": 4.0939, + "step": 116224 + }, + { + "epoch": 1.01, + "learning_rate": 4.80887246349656e-05, + "loss": 4.0904, + "step": 116736 + }, + { + "epoch": 1.01, + "learning_rate": 4.808035506625881e-05, + "loss": 4.0852, + "step": 117248 + }, + { + "epoch": 1.01, + "learning_rate": 4.807196911874829e-05, + "loss": 4.0935, + "step": 117760 + }, + { + "epoch": 1.01, + "learning_rate": 4.806358317123777e-05, + "loss": 4.0998, + "step": 118272 + }, + { + "epoch": 1.01, + "learning_rate": 4.805519722372726e-05, + "loss": 4.0913, + "step": 118784 + }, + { + "epoch": 1.01, + "learning_rate": 4.804681127621674e-05, + "loss": 4.0773, + "step": 119296 + }, + { + "epoch": 1.01, + "learning_rate": 4.803844170750995e-05, + "loss": 4.0759, + "step": 119808 + }, + { + "epoch": 1.01, + "learning_rate": 4.803005575999943e-05, + "loss": 4.0839, + "step": 120320 + }, + { + "epoch": 1.01, + "learning_rate": 4.802166981248891e-05, + "loss": 4.0918, + "step": 120832 + }, + { + "epoch": 1.01, + "learning_rate": 4.801328386497839e-05, + "loss": 4.0746, + "step": 121344 + }, + { + "epoch": 1.01, + "learning_rate": 4.8004914296271596e-05, + "loss": 4.0783, + "step": 121856 + }, + { + "epoch": 1.02, + "learning_rate": 4.7996528348761076e-05, + "loss": 4.0856, + "step": 122368 + }, + { + "epoch": 1.02, + "learning_rate": 4.7988142401250556e-05, + "loss": 4.0764, + "step": 122880 + }, + { + "epoch": 1.02, + "learning_rate": 4.7979756453740036e-05, + "loss": 4.0704, + "step": 123392 + }, + { + "epoch": 1.02, + "learning_rate": 4.7971386885033245e-05, + "loss": 4.0742, + "step": 123904 + }, + { + "epoch": 1.02, + "learning_rate": 4.7963000937522725e-05, + "loss": 4.077, + "step": 124416 + }, + { + "epoch": 1.02, + "learning_rate": 4.795461499001221e-05, + "loss": 4.0771, + "step": 124928 + }, + { + "epoch": 1.02, + "learning_rate": 4.794622904250169e-05, + "loss": 4.0763, + "step": 125440 + }, + { + "epoch": 1.02, + "learning_rate": 4.79378594737949e-05, + "loss": 4.0616, + "step": 125952 + }, + { + "epoch": 1.02, + "learning_rate": 4.792947352628438e-05, + "loss": 4.0725, + "step": 126464 + }, + { + "epoch": 1.02, + "learning_rate": 4.792108757877386e-05, + "loss": 4.069, + "step": 126976 + }, + { + "epoch": 1.02, + "learning_rate": 4.791270163126334e-05, + "loss": 4.0762, + "step": 127488 + }, + { + "epoch": 1.02, + "learning_rate": 4.790433206255655e-05, + "loss": 4.0706, + "step": 128000 + }, + { + "epoch": 1.02, + "learning_rate": 4.789594611504603e-05, + "loss": 4.07, + "step": 128512 + }, + { + "epoch": 1.02, + "learning_rate": 4.788756016753551e-05, + "loss": 4.0659, + "step": 129024 + }, + { + "epoch": 1.02, + "learning_rate": 4.787917422002499e-05, + "loss": 4.069, + "step": 129536 + }, + { + "epoch": 1.02, + "learning_rate": 4.78708046513182e-05, + "loss": 4.0482, + "step": 130048 + }, + { + "epoch": 1.02, + "learning_rate": 4.786241870380768e-05, + "loss": 4.0528, + "step": 130560 + }, + { + "epoch": 1.02, + "learning_rate": 4.7854049135100895e-05, + "loss": 4.0618, + "step": 131072 + }, + { + "epoch": 1.02, + "learning_rate": 4.7845663187590375e-05, + "loss": 4.0581, + "step": 131584 + }, + { + "epoch": 1.02, + "learning_rate": 4.7837277240079855e-05, + "loss": 4.0517, + "step": 132096 + }, + { + "epoch": 1.02, + "learning_rate": 4.7828891292569335e-05, + "loss": 4.0497, + "step": 132608 + }, + { + "epoch": 1.02, + "learning_rate": 4.7820505345058815e-05, + "loss": 4.0479, + "step": 133120 + }, + { + "epoch": 1.02, + "learning_rate": 4.7812119397548295e-05, + "loss": 4.0566, + "step": 133632 + }, + { + "epoch": 1.02, + "learning_rate": 4.7803733450037775e-05, + "loss": 4.0503, + "step": 134144 + }, + { + "epoch": 1.02, + "learning_rate": 4.7795363881330984e-05, + "loss": 4.0519, + "step": 134656 + }, + { + "epoch": 1.02, + "learning_rate": 4.7786977933820464e-05, + "loss": 4.0551, + "step": 135168 + }, + { + "epoch": 1.02, + "learning_rate": 4.7778591986309944e-05, + "loss": 4.0582, + "step": 135680 + }, + { + "epoch": 1.02, + "learning_rate": 4.7770206038799423e-05, + "loss": 4.052, + "step": 136192 + }, + { + "epoch": 1.02, + "learning_rate": 4.776183647009263e-05, + "loss": 4.0491, + "step": 136704 + }, + { + "epoch": 1.02, + "learning_rate": 4.775345052258212e-05, + "loss": 4.056, + "step": 137216 + }, + { + "epoch": 1.02, + "learning_rate": 4.77450645750716e-05, + "loss": 4.0548, + "step": 137728 + }, + { + "epoch": 1.02, + "learning_rate": 4.773667862756108e-05, + "loss": 4.0451, + "step": 138240 + }, + { + "epoch": 1.02, + "learning_rate": 4.772829268005055e-05, + "loss": 4.053, + "step": 138752 + }, + { + "epoch": 1.02, + "learning_rate": 4.771992311134377e-05, + "loss": 4.0428, + "step": 139264 + }, + { + "epoch": 1.02, + "learning_rate": 4.771153716383325e-05, + "loss": 4.0548, + "step": 139776 + }, + { + "epoch": 1.02, + "learning_rate": 4.770315121632272e-05, + "loss": 4.029, + "step": 140288 + }, + { + "epoch": 1.02, + "learning_rate": 4.76947652688122e-05, + "loss": 4.0461, + "step": 140800 + }, + { + "epoch": 1.02, + "learning_rate": 4.768639570010542e-05, + "loss": 4.0306, + "step": 141312 + }, + { + "epoch": 1.02, + "learning_rate": 4.76780097525949e-05, + "loss": 4.0343, + "step": 141824 + }, + { + "epoch": 1.02, + "learning_rate": 4.766962380508437e-05, + "loss": 4.0255, + "step": 142336 + }, + { + "epoch": 1.02, + "learning_rate": 4.766123785757386e-05, + "loss": 4.0551, + "step": 142848 + }, + { + "epoch": 1.02, + "learning_rate": 4.765286828886707e-05, + "loss": 4.044, + "step": 143360 + }, + { + "epoch": 1.02, + "learning_rate": 4.764448234135655e-05, + "loss": 4.0366, + "step": 143872 + }, + { + "epoch": 1.02, + "learning_rate": 4.7636096393846026e-05, + "loss": 4.0315, + "step": 144384 + }, + { + "epoch": 1.02, + "learning_rate": 4.7627710446335506e-05, + "loss": 4.0402, + "step": 144896 + }, + { + "epoch": 1.02, + "learning_rate": 4.761934087762872e-05, + "loss": 4.0456, + "step": 145408 + }, + { + "epoch": 1.02, + "learning_rate": 4.7610954930118195e-05, + "loss": 4.042, + "step": 145920 + }, + { + "epoch": 1.02, + "learning_rate": 4.7602568982607675e-05, + "loss": 4.0352, + "step": 146432 + }, + { + "epoch": 1.02, + "learning_rate": 4.7594183035097155e-05, + "loss": 4.039, + "step": 146944 + }, + { + "epoch": 1.02, + "learning_rate": 4.758581346639037e-05, + "loss": 4.0305, + "step": 147456 + }, + { + "epoch": 1.02, + "learning_rate": 4.7577427518879844e-05, + "loss": 4.0457, + "step": 147968 + }, + { + "epoch": 1.02, + "learning_rate": 4.7569041571369324e-05, + "loss": 4.0272, + "step": 148480 + }, + { + "epoch": 1.02, + "learning_rate": 4.756065562385881e-05, + "loss": 4.0304, + "step": 148992 + }, + { + "epoch": 1.02, + "learning_rate": 4.755228605515202e-05, + "loss": 4.0294, + "step": 149504 + }, + { + "epoch": 1.02, + "learning_rate": 4.75439001076415e-05, + "loss": 4.0232, + "step": 150016 + }, + { + "epoch": 1.02, + "learning_rate": 4.7535530538934716e-05, + "loss": 4.0342, + "step": 150528 + }, + { + "epoch": 1.02, + "learning_rate": 4.7527144591424196e-05, + "loss": 4.0256, + "step": 151040 + }, + { + "epoch": 1.02, + "learning_rate": 4.751875864391367e-05, + "loss": 4.0302, + "step": 151552 + }, + { + "epoch": 1.02, + "learning_rate": 4.751037269640315e-05, + "loss": 4.0269, + "step": 152064 + }, + { + "epoch": 1.02, + "learning_rate": 4.750198674889263e-05, + "loss": 4.0243, + "step": 152576 + }, + { + "epoch": 1.03, + "eval_loss": 4.026165962219238, + "eval_runtime": 354.9808, + "eval_samples_per_second": 1074.962, + "eval_steps_per_second": 33.593, + "step": 152640 + }, + { + "epoch": 0.0, + "learning_rate": 4.749360080138211e-05, + "loss": 4.0097, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.748521485387159e-05, + "loss": 4.0084, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.747682890636107e-05, + "loss": 4.0273, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.746844295885055e-05, + "loss": 4.0119, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.746005701134003e-05, + "loss": 4.0362, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.745167106382951e-05, + "loss": 4.0045, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.744328511631899e-05, + "loss": 4.0167, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.7434899168808475e-05, + "loss": 3.9997, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.7426513221297955e-05, + "loss": 4.0174, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.7418127273787435e-05, + "loss": 4.0109, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.740974132627691e-05, + "loss": 4.0149, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.7401371757570124e-05, + "loss": 4.0112, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.739301856766706e-05, + "loss": 4.0004, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.738463262015654e-05, + "loss": 4.0064, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.737624667264602e-05, + "loss": 4.0007, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.73678607251355e-05, + "loss": 3.9969, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.735947477762498e-05, + "loss": 3.998, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.735108883011446e-05, + "loss": 4.0028, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.734270288260394e-05, + "loss": 3.9958, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.733431693509343e-05, + "loss": 4.0181, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.732594736638664e-05, + "loss": 3.9939, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.731756141887612e-05, + "loss": 4.0035, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.73091754713656e-05, + "loss": 3.9996, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.730078952385508e-05, + "loss": 4.0097, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.729240357634456e-05, + "loss": 3.988, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.728401762883403e-05, + "loss": 3.999, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.727563168132351e-05, + "loss": 3.9922, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.726726211261673e-05, + "loss": 3.9942, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.725887616510621e-05, + "loss": 3.9809, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.7250506596399416e-05, + "loss": 3.9863, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.7242120648888896e-05, + "loss": 3.9952, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.723373470137838e-05, + "loss": 3.9948, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.7225348753867856e-05, + "loss": 3.9947, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.7216962806357336e-05, + "loss": 3.996, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.7208576858846816e-05, + "loss": 3.9907, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.7200190911336296e-05, + "loss": 3.994, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.7191804963825775e-05, + "loss": 3.9811, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.7183435395118985e-05, + "loss": 3.9929, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.7175049447608465e-05, + "loss": 3.9755, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.7166663500097945e-05, + "loss": 3.9836, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.7158277552587424e-05, + "loss": 3.9808, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.714992436268437e-05, + "loss": 3.9876, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.714153841517385e-05, + "loss": 3.9812, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.713315246766333e-05, + "loss": 3.9789, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.712476652015281e-05, + "loss": 3.9888, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.711638057264229e-05, + "loss": 3.9837, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.710799462513177e-05, + "loss": 3.9824, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.709962505642498e-05, + "loss": 3.9643, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.709123910891446e-05, + "loss": 3.9616, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.708285316140394e-05, + "loss": 3.9782, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.707446721389342e-05, + "loss": 3.9764, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.706609764518663e-05, + "loss": 3.9733, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.705771169767611e-05, + "loss": 3.9569, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.704932575016559e-05, + "loss": 3.9623, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.7040939802655074e-05, + "loss": 3.9606, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.7032553855144554e-05, + "loss": 3.9739, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.7024167907634034e-05, + "loss": 3.9578, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.7015781960123514e-05, + "loss": 3.9719, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.7007396012612994e-05, + "loss": 3.9704, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.69990264439062e-05, + "loss": 3.9571, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.699065687519941e-05, + "loss": 3.9626, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.698227092768889e-05, + "loss": 3.9589, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.697388498017837e-05, + "loss": 3.9502, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.696549903266785e-05, + "loss": 3.9581, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.695711308515733e-05, + "loss": 3.9629, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694872713764681e-05, + "loss": 3.9682, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.694034119013629e-05, + "loss": 3.9456, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.693197162142951e-05, + "loss": 3.9514, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.692358567391899e-05, + "loss": 3.9491, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.691519972640847e-05, + "loss": 3.9749, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.690681377889795e-05, + "loss": 3.9631, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.689842783138743e-05, + "loss": 3.9635, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.689004188387691e-05, + "loss": 3.9764, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.688165593636639e-05, + "loss": 3.9716, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.687326998885587e-05, + "loss": 3.9664, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.6864900420149076e-05, + "loss": 3.9558, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.6856514472638556e-05, + "loss": 3.9581, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.6848128525128036e-05, + "loss": 3.957, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.683974257761751e-05, + "loss": 3.9546, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.6831373008910725e-05, + "loss": 3.9535, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.6822987061400205e-05, + "loss": 3.9563, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.681460111388969e-05, + "loss": 3.9649, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.6806215166379165e-05, + "loss": 3.9551, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.679784559767238e-05, + "loss": 3.9475, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.678945965016186e-05, + "loss": 3.94, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.678107370265134e-05, + "loss": 3.953, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.677270413394455e-05, + "loss": 3.9588, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.676431818643403e-05, + "loss": 3.9468, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.675593223892351e-05, + "loss": 3.9445, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.674754629141298e-05, + "loss": 3.9566, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.673916034390246e-05, + "loss": 3.9369, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.673079077519568e-05, + "loss": 3.9457, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.672240482768516e-05, + "loss": 3.9444, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.671401888017464e-05, + "loss": 3.9508, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.670563293266412e-05, + "loss": 3.95, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.66972469851536e-05, + "loss": 3.945, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.668886103764308e-05, + "loss": 3.9351, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.668047509013256e-05, + "loss": 3.9477, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.667208914262204e-05, + "loss": 3.9395, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.666371957391525e-05, + "loss": 3.9531, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.665535000520846e-05, + "loss": 3.9447, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.664696405769794e-05, + "loss": 3.9465, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.663857811018742e-05, + "loss": 3.936, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.66301921626769e-05, + "loss": 3.9492, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.662182259397011e-05, + "loss": 3.9226, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.661343664645959e-05, + "loss": 3.9295, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.660505069894907e-05, + "loss": 3.9373, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.659666475143855e-05, + "loss": 3.9375, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.658827880392803e-05, + "loss": 3.9263, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.657990923522124e-05, + "loss": 3.9296, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.657152328771072e-05, + "loss": 3.9262, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.65631373402002e-05, + "loss": 3.9374, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.655475139268968e-05, + "loss": 3.93, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.654636544517916e-05, + "loss": 3.9281, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.653799587647237e-05, + "loss": 3.941, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.652960992896185e-05, + "loss": 3.9405, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.652122398145134e-05, + "loss": 3.938, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.651283803394082e-05, + "loss": 3.9291, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.6504468465234026e-05, + "loss": 3.9389, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.6496082517723506e-05, + "loss": 3.9335, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.6487696570212986e-05, + "loss": 3.9278, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.6479310622702466e-05, + "loss": 3.941, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.6470924675191946e-05, + "loss": 3.922, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.6462538727681426e-05, + "loss": 3.9374, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.6454152780170906e-05, + "loss": 3.9171, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.6445766832660386e-05, + "loss": 3.932, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.6437397263953595e-05, + "loss": 3.9146, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.6429027695246804e-05, + "loss": 3.9201, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.642064174773629e-05, + "loss": 3.9137, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.641225580022577e-05, + "loss": 3.9399, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.640386985271525e-05, + "loss": 3.9297, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.639548390520473e-05, + "loss": 3.9252, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.638709795769421e-05, + "loss": 3.9192, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.637872838898742e-05, + "loss": 3.9251, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.63703424414769e-05, + "loss": 3.9374, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.636195649396638e-05, + "loss": 3.9257, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.635357054645586e-05, + "loss": 3.9217, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.634520097774907e-05, + "loss": 3.9321, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.633681503023855e-05, + "loss": 3.9222, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.632842908272803e-05, + "loss": 3.9308, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.632004313521751e-05, + "loss": 3.918, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.631165718770699e-05, + "loss": 3.9215, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.6303271240196475e-05, + "loss": 3.9202, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.6294901671489684e-05, + "loss": 3.9174, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.6286515723979164e-05, + "loss": 3.9208, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.6278129776468644e-05, + "loss": 3.9231, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.626974382895812e-05, + "loss": 3.9161, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.62613578814476e-05, + "loss": 3.9171, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.625298831274081e-05, + "loss": 3.9173, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 3.951378107070923, + "eval_runtime": 304.2171, + "eval_samples_per_second": 1254.338, + "eval_steps_per_second": 39.199, + "step": 228960 + }, + { + "epoch": 1.0, + "learning_rate": 4.624460236523029e-05, + "loss": 3.9092, + "step": 229376 + }, + { + "epoch": 1.0, + "learning_rate": 4.6236216417719766e-05, + "loss": 3.9054, + "step": 229888 + }, + { + "epoch": 1.0, + "learning_rate": 4.6227830470209246e-05, + "loss": 3.9211, + "step": 230400 + }, + { + "epoch": 1.0, + "learning_rate": 4.621946090150246e-05, + "loss": 3.9051, + "step": 230912 + }, + { + "epoch": 1.0, + "learning_rate": 4.621107495399194e-05, + "loss": 3.9331, + "step": 231424 + }, + { + "epoch": 1.0, + "learning_rate": 4.620268900648142e-05, + "loss": 3.8996, + "step": 231936 + }, + { + "epoch": 1.0, + "learning_rate": 4.61943030589709e-05, + "loss": 3.9104, + "step": 232448 + }, + { + "epoch": 1.0, + "learning_rate": 4.618591711146038e-05, + "loss": 3.8953, + "step": 232960 + }, + { + "epoch": 1.0, + "learning_rate": 4.617754754275359e-05, + "loss": 3.9124, + "step": 233472 + }, + { + "epoch": 1.0, + "learning_rate": 4.616916159524307e-05, + "loss": 3.9104, + "step": 233984 + }, + { + "epoch": 1.0, + "learning_rate": 4.616077564773255e-05, + "loss": 3.9069, + "step": 234496 + }, + { + "epoch": 1.0, + "learning_rate": 4.615238970022203e-05, + "loss": 3.9084, + "step": 235008 + }, + { + "epoch": 1.0, + "learning_rate": 4.614402013151524e-05, + "loss": 3.8963, + "step": 235520 + }, + { + "epoch": 1.0, + "learning_rate": 4.613563418400472e-05, + "loss": 3.9061, + "step": 236032 + }, + { + "epoch": 1.0, + "learning_rate": 4.61272482364942e-05, + "loss": 3.9008, + "step": 236544 + }, + { + "epoch": 1.0, + "learning_rate": 4.611886228898368e-05, + "loss": 3.8986, + "step": 237056 + }, + { + "epoch": 1.0, + "learning_rate": 4.611047634147316e-05, + "loss": 3.8981, + "step": 237568 + }, + { + "epoch": 1.0, + "learning_rate": 4.610209039396265e-05, + "loss": 3.9016, + "step": 238080 + }, + { + "epoch": 1.0, + "learning_rate": 4.609370444645213e-05, + "loss": 3.8989, + "step": 238592 + }, + { + "epoch": 1.0, + "learning_rate": 4.6085318498941607e-05, + "loss": 3.9144, + "step": 239104 + }, + { + "epoch": 1.0, + "learning_rate": 4.6076948930234816e-05, + "loss": 3.8958, + "step": 239616 + }, + { + "epoch": 1.0, + "learning_rate": 4.6068562982724296e-05, + "loss": 3.9034, + "step": 240128 + }, + { + "epoch": 1.0, + "learning_rate": 4.6060177035213776e-05, + "loss": 3.9005, + "step": 240640 + }, + { + "epoch": 1.0, + "learning_rate": 4.6051791087703256e-05, + "loss": 3.9111, + "step": 241152 + }, + { + "epoch": 1.0, + "learning_rate": 4.6043405140192735e-05, + "loss": 3.8904, + "step": 241664 + }, + { + "epoch": 1.0, + "learning_rate": 4.6035035571485945e-05, + "loss": 3.9042, + "step": 242176 + }, + { + "epoch": 1.0, + "learning_rate": 4.6026649623975425e-05, + "loss": 3.8949, + "step": 242688 + }, + { + "epoch": 1.0, + "learning_rate": 4.6018263676464904e-05, + "loss": 3.8939, + "step": 243200 + }, + { + "epoch": 1.0, + "learning_rate": 4.6009877728954384e-05, + "loss": 3.8832, + "step": 243712 + }, + { + "epoch": 1.01, + "learning_rate": 4.60015081602476e-05, + "loss": 3.8961, + "step": 244224 + }, + { + "epoch": 1.01, + "learning_rate": 4.599312221273708e-05, + "loss": 3.8952, + "step": 244736 + }, + { + "epoch": 1.01, + "learning_rate": 4.598473626522656e-05, + "loss": 3.8982, + "step": 245248 + }, + { + "epoch": 1.01, + "learning_rate": 4.597635031771604e-05, + "loss": 3.8969, + "step": 245760 + }, + { + "epoch": 1.01, + "learning_rate": 4.596796437020552e-05, + "loss": 3.9012, + "step": 246272 + }, + { + "epoch": 1.01, + "learning_rate": 4.595959480149873e-05, + "loss": 3.8926, + "step": 246784 + }, + { + "epoch": 1.01, + "learning_rate": 4.595120885398821e-05, + "loss": 3.8995, + "step": 247296 + }, + { + "epoch": 1.01, + "learning_rate": 4.594282290647769e-05, + "loss": 3.8889, + "step": 247808 + }, + { + "epoch": 1.01, + "learning_rate": 4.593443695896717e-05, + "loss": 3.8966, + "step": 248320 + }, + { + "epoch": 1.01, + "learning_rate": 4.592606739026038e-05, + "loss": 3.8802, + "step": 248832 + }, + { + "epoch": 1.01, + "learning_rate": 4.591768144274986e-05, + "loss": 3.8878, + "step": 249344 + }, + { + "epoch": 1.01, + "learning_rate": 4.590929549523934e-05, + "loss": 3.8892, + "step": 249856 + }, + { + "epoch": 1.01, + "learning_rate": 4.590090954772882e-05, + "loss": 3.8976, + "step": 250368 + }, + { + "epoch": 1.01, + "learning_rate": 4.58925236002183e-05, + "loss": 3.888, + "step": 250880 + }, + { + "epoch": 1.01, + "learning_rate": 4.5884154031511514e-05, + "loss": 3.8867, + "step": 251392 + }, + { + "epoch": 1.01, + "learning_rate": 4.5875768084000994e-05, + "loss": 3.894, + "step": 251904 + }, + { + "epoch": 1.01, + "learning_rate": 4.5867382136490474e-05, + "loss": 3.8915, + "step": 252416 + }, + { + "epoch": 1.01, + "learning_rate": 4.5858996188979954e-05, + "loss": 3.8907, + "step": 252928 + }, + { + "epoch": 1.01, + "learning_rate": 4.585062662027316e-05, + "loss": 3.878, + "step": 253440 + }, + { + "epoch": 1.01, + "learning_rate": 4.584224067276264e-05, + "loss": 3.8644, + "step": 253952 + }, + { + "epoch": 1.01, + "learning_rate": 4.583385472525212e-05, + "loss": 3.8883, + "step": 254464 + }, + { + "epoch": 1.01, + "learning_rate": 4.58254687777416e-05, + "loss": 3.8844, + "step": 254976 + }, + { + "epoch": 1.01, + "learning_rate": 4.581709920903481e-05, + "loss": 3.8797, + "step": 255488 + }, + { + "epoch": 1.01, + "learning_rate": 4.580871326152429e-05, + "loss": 3.8733, + "step": 256000 + }, + { + "epoch": 1.01, + "learning_rate": 4.580032731401377e-05, + "loss": 3.8719, + "step": 256512 + }, + { + "epoch": 1.01, + "learning_rate": 4.579194136650325e-05, + "loss": 3.8671, + "step": 257024 + }, + { + "epoch": 1.01, + "learning_rate": 4.578355541899273e-05, + "loss": 3.8849, + "step": 257536 + }, + { + "epoch": 1.01, + "learning_rate": 4.577516947148221e-05, + "loss": 3.8711, + "step": 258048 + }, + { + "epoch": 1.01, + "learning_rate": 4.576679990277543e-05, + "loss": 3.8791, + "step": 258560 + }, + { + "epoch": 1.01, + "learning_rate": 4.57584139552649e-05, + "loss": 3.8847, + "step": 259072 + }, + { + "epoch": 1.01, + "learning_rate": 4.575002800775438e-05, + "loss": 3.8704, + "step": 259584 + }, + { + "epoch": 1.01, + "learning_rate": 4.574164206024386e-05, + "loss": 3.8728, + "step": 260096 + }, + { + "epoch": 1.01, + "learning_rate": 4.5733272491537076e-05, + "loss": 3.8755, + "step": 260608 + }, + { + "epoch": 1.01, + "learning_rate": 4.572488654402655e-05, + "loss": 3.8568, + "step": 261120 + }, + { + "epoch": 1.01, + "learning_rate": 4.571650059651603e-05, + "loss": 3.8711, + "step": 261632 + }, + { + "epoch": 1.01, + "learning_rate": 4.570811464900551e-05, + "loss": 3.8791, + "step": 262144 + }, + { + "epoch": 1.01, + "learning_rate": 4.569972870149499e-05, + "loss": 3.8781, + "step": 262656 + }, + { + "epoch": 1.01, + "learning_rate": 4.5691359132788205e-05, + "loss": 3.8604, + "step": 263168 + }, + { + "epoch": 1.01, + "learning_rate": 4.5682973185277685e-05, + "loss": 3.8679, + "step": 263680 + }, + { + "epoch": 1.01, + "learning_rate": 4.5674587237767165e-05, + "loss": 3.8631, + "step": 264192 + }, + { + "epoch": 1.01, + "learning_rate": 4.5666201290256645e-05, + "loss": 3.8845, + "step": 264704 + }, + { + "epoch": 1.01, + "learning_rate": 4.5657831721549854e-05, + "loss": 3.8771, + "step": 265216 + }, + { + "epoch": 1.01, + "learning_rate": 4.5649445774039334e-05, + "loss": 3.8778, + "step": 265728 + }, + { + "epoch": 1.01, + "learning_rate": 4.5641059826528814e-05, + "loss": 3.8882, + "step": 266240 + }, + { + "epoch": 1.01, + "learning_rate": 4.5632673879018294e-05, + "loss": 3.8859, + "step": 266752 + }, + { + "epoch": 1.01, + "learning_rate": 4.5624287931507774e-05, + "loss": 3.8854, + "step": 267264 + }, + { + "epoch": 1.01, + "learning_rate": 4.5615901983997254e-05, + "loss": 3.867, + "step": 267776 + }, + { + "epoch": 1.01, + "learning_rate": 4.560753241529046e-05, + "loss": 3.8758, + "step": 268288 + }, + { + "epoch": 1.01, + "learning_rate": 4.559914646777994e-05, + "loss": 3.876, + "step": 268800 + }, + { + "epoch": 1.01, + "learning_rate": 4.559076052026943e-05, + "loss": 3.8683, + "step": 269312 + }, + { + "epoch": 1.01, + "learning_rate": 4.558237457275891e-05, + "loss": 3.8742, + "step": 269824 + }, + { + "epoch": 1.01, + "learning_rate": 4.557398862524839e-05, + "loss": 3.8705, + "step": 270336 + }, + { + "epoch": 1.01, + "learning_rate": 4.55656190565416e-05, + "loss": 3.8786, + "step": 270848 + }, + { + "epoch": 1.01, + "learning_rate": 4.555723310903108e-05, + "loss": 3.8715, + "step": 271360 + }, + { + "epoch": 1.01, + "learning_rate": 4.554884716152056e-05, + "loss": 3.8565, + "step": 271872 + }, + { + "epoch": 1.01, + "learning_rate": 4.554046121401004e-05, + "loss": 3.8597, + "step": 272384 + }, + { + "epoch": 1.01, + "learning_rate": 4.553209164530325e-05, + "loss": 3.8708, + "step": 272896 + }, + { + "epoch": 1.01, + "learning_rate": 4.552370569779273e-05, + "loss": 3.8743, + "step": 273408 + }, + { + "epoch": 1.01, + "learning_rate": 4.551531975028221e-05, + "loss": 3.8644, + "step": 273920 + }, + { + "epoch": 1.01, + "learning_rate": 4.550693380277169e-05, + "loss": 3.8616, + "step": 274432 + }, + { + "epoch": 1.02, + "learning_rate": 4.549854785526117e-05, + "loss": 3.8728, + "step": 274944 + }, + { + "epoch": 1.02, + "learning_rate": 4.549016190775065e-05, + "loss": 3.8597, + "step": 275456 + }, + { + "epoch": 1.02, + "learning_rate": 4.5481792339043864e-05, + "loss": 3.8613, + "step": 275968 + }, + { + "epoch": 1.02, + "learning_rate": 4.5473406391533343e-05, + "loss": 3.8655, + "step": 276480 + }, + { + "epoch": 1.02, + "learning_rate": 4.5465020444022823e-05, + "loss": 3.8717, + "step": 276992 + }, + { + "epoch": 1.02, + "learning_rate": 4.54566344965123e-05, + "loss": 3.8724, + "step": 277504 + }, + { + "epoch": 1.02, + "learning_rate": 4.544826492780551e-05, + "loss": 3.8635, + "step": 278016 + }, + { + "epoch": 1.02, + "learning_rate": 4.543987898029499e-05, + "loss": 3.8496, + "step": 278528 + }, + { + "epoch": 1.02, + "learning_rate": 4.543149303278447e-05, + "loss": 3.8702, + "step": 279040 + }, + { + "epoch": 1.02, + "learning_rate": 4.542310708527395e-05, + "loss": 3.8562, + "step": 279552 + }, + { + "epoch": 1.02, + "learning_rate": 4.541473751656716e-05, + "loss": 3.8748, + "step": 280064 + }, + { + "epoch": 1.02, + "learning_rate": 4.540635156905664e-05, + "loss": 3.8673, + "step": 280576 + }, + { + "epoch": 1.02, + "learning_rate": 4.539796562154612e-05, + "loss": 3.8661, + "step": 281088 + }, + { + "epoch": 1.02, + "learning_rate": 4.53895796740356e-05, + "loss": 3.856, + "step": 281600 + }, + { + "epoch": 1.02, + "learning_rate": 4.538121010532882e-05, + "loss": 3.8697, + "step": 282112 + }, + { + "epoch": 1.02, + "learning_rate": 4.53728241578183e-05, + "loss": 3.846, + "step": 282624 + }, + { + "epoch": 1.02, + "learning_rate": 4.536443821030778e-05, + "loss": 3.8544, + "step": 283136 + }, + { + "epoch": 1.02, + "learning_rate": 4.535605226279726e-05, + "loss": 3.8537, + "step": 283648 + }, + { + "epoch": 1.02, + "learning_rate": 4.5347682694090466e-05, + "loss": 3.8595, + "step": 284160 + }, + { + "epoch": 1.02, + "learning_rate": 4.5339313125383675e-05, + "loss": 3.8477, + "step": 284672 + }, + { + "epoch": 1.02, + "learning_rate": 4.5330927177873155e-05, + "loss": 3.8549, + "step": 285184 + }, + { + "epoch": 1.02, + "learning_rate": 4.5322541230362635e-05, + "loss": 3.852, + "step": 285696 + }, + { + "epoch": 1.02, + "learning_rate": 4.5314155282852115e-05, + "loss": 3.8534, + "step": 286208 + }, + { + "epoch": 1.02, + "learning_rate": 4.5305769335341595e-05, + "loss": 3.8562, + "step": 286720 + }, + { + "epoch": 1.02, + "learning_rate": 4.5297383387831075e-05, + "loss": 3.8471, + "step": 287232 + }, + { + "epoch": 1.02, + "learning_rate": 4.5288997440320555e-05, + "loss": 3.8652, + "step": 287744 + }, + { + "epoch": 1.02, + "learning_rate": 4.5280611492810035e-05, + "loss": 3.8613, + "step": 288256 + }, + { + "epoch": 1.02, + "learning_rate": 4.527224192410325e-05, + "loss": 3.8615, + "step": 288768 + }, + { + "epoch": 1.02, + "learning_rate": 4.526385597659273e-05, + "loss": 3.8526, + "step": 289280 + }, + { + "epoch": 1.02, + "learning_rate": 4.525547002908221e-05, + "loss": 3.861, + "step": 289792 + }, + { + "epoch": 1.02, + "learning_rate": 4.5247084081571684e-05, + "loss": 3.8617, + "step": 290304 + }, + { + "epoch": 1.02, + "learning_rate": 4.52387145128649e-05, + "loss": 3.8491, + "step": 290816 + }, + { + "epoch": 1.02, + "learning_rate": 4.523032856535438e-05, + "loss": 3.8616, + "step": 291328 + }, + { + "epoch": 1.02, + "learning_rate": 4.522194261784386e-05, + "loss": 3.8502, + "step": 291840 + }, + { + "epoch": 1.02, + "learning_rate": 4.521355667033333e-05, + "loss": 3.859, + "step": 292352 + }, + { + "epoch": 1.02, + "learning_rate": 4.520518710162655e-05, + "loss": 3.8444, + "step": 292864 + }, + { + "epoch": 1.02, + "learning_rate": 4.519680115411603e-05, + "loss": 3.8549, + "step": 293376 + }, + { + "epoch": 1.02, + "learning_rate": 4.518841520660551e-05, + "loss": 3.8395, + "step": 293888 + }, + { + "epoch": 1.02, + "learning_rate": 4.518002925909499e-05, + "loss": 3.847, + "step": 294400 + }, + { + "epoch": 1.02, + "learning_rate": 4.5171659690388204e-05, + "loss": 3.8434, + "step": 294912 + }, + { + "epoch": 1.02, + "learning_rate": 4.5163273742877684e-05, + "loss": 3.8596, + "step": 295424 + }, + { + "epoch": 1.02, + "learning_rate": 4.515488779536716e-05, + "loss": 3.8507, + "step": 295936 + }, + { + "epoch": 1.02, + "learning_rate": 4.514650184785664e-05, + "loss": 3.8543, + "step": 296448 + }, + { + "epoch": 1.02, + "learning_rate": 4.513811590034612e-05, + "loss": 3.8458, + "step": 296960 + }, + { + "epoch": 1.02, + "learning_rate": 4.5129746331639333e-05, + "loss": 3.8543, + "step": 297472 + }, + { + "epoch": 1.02, + "learning_rate": 4.5121360384128807e-05, + "loss": 3.862, + "step": 297984 + }, + { + "epoch": 1.02, + "learning_rate": 4.5112974436618287e-05, + "loss": 3.851, + "step": 298496 + }, + { + "epoch": 1.02, + "learning_rate": 4.5104588489107766e-05, + "loss": 3.8474, + "step": 299008 + }, + { + "epoch": 1.02, + "learning_rate": 4.5096218920400976e-05, + "loss": 3.8575, + "step": 299520 + }, + { + "epoch": 1.02, + "learning_rate": 4.508783297289046e-05, + "loss": 3.8485, + "step": 300032 + }, + { + "epoch": 1.02, + "learning_rate": 4.507944702537994e-05, + "loss": 3.8585, + "step": 300544 + }, + { + "epoch": 1.02, + "learning_rate": 4.507106107786942e-05, + "loss": 3.8397, + "step": 301056 + }, + { + "epoch": 1.02, + "learning_rate": 4.50626751303589e-05, + "loss": 3.8524, + "step": 301568 + }, + { + "epoch": 1.02, + "learning_rate": 4.505430556165211e-05, + "loss": 3.8479, + "step": 302080 + }, + { + "epoch": 1.02, + "learning_rate": 4.504591961414159e-05, + "loss": 3.8431, + "step": 302592 + }, + { + "epoch": 1.02, + "learning_rate": 4.503753366663107e-05, + "loss": 3.8513, + "step": 303104 + }, + { + "epoch": 1.02, + "learning_rate": 4.502914771912055e-05, + "loss": 3.8465, + "step": 303616 + }, + { + "epoch": 1.02, + "learning_rate": 4.502077815041376e-05, + "loss": 3.8455, + "step": 304128 + }, + { + "epoch": 1.02, + "learning_rate": 4.501239220290324e-05, + "loss": 3.841, + "step": 304640 + }, + { + "epoch": 1.02, + "learning_rate": 4.500400625539272e-05, + "loss": 3.8504, + "step": 305152 + }, + { + "epoch": 1.03, + "eval_loss": 3.911092519760132, + "eval_runtime": 304.611, + "eval_samples_per_second": 1252.716, + "eval_steps_per_second": 39.148, + "step": 305280 + }, + { + "epoch": 0.0, + "learning_rate": 4.49956203078822e-05, + "loss": 3.8344, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.498723436037168e-05, + "loss": 3.8322, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.497884841286116e-05, + "loss": 3.8486, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.497046246535065e-05, + "loss": 3.8351, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.496207651784013e-05, + "loss": 3.8598, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.495369057032961e-05, + "loss": 3.8354, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.4945304622819087e-05, + "loss": 3.8358, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.4936918675308567e-05, + "loss": 3.8234, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.4928549106601776e-05, + "loss": 3.8409, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.4920163159091256e-05, + "loss": 3.8433, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.4911777211580736e-05, + "loss": 3.8347, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.4903391264070216e-05, + "loss": 3.8354, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.4895038074167154e-05, + "loss": 3.8282, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.4886652126656634e-05, + "loss": 3.8358, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.4878266179146114e-05, + "loss": 3.8335, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.48698802316356e-05, + "loss": 3.8276, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.486149428412508e-05, + "loss": 3.8286, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.485310833661456e-05, + "loss": 3.8348, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.484472238910404e-05, + "loss": 3.8284, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.483633644159352e-05, + "loss": 3.8435, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.482796687288673e-05, + "loss": 3.834, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.481958092537621e-05, + "loss": 3.8379, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.481119497786569e-05, + "loss": 3.8333, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.480280903035516e-05, + "loss": 3.8425, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.479443946164838e-05, + "loss": 3.8215, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.478605351413786e-05, + "loss": 3.8332, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.477766756662734e-05, + "loss": 3.8299, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.476928161911682e-05, + "loss": 3.8232, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.4760912050410034e-05, + "loss": 3.8192, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.4752526102899514e-05, + "loss": 3.8248, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.4744140155388994e-05, + "loss": 3.8335, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.473575420787847e-05, + "loss": 3.8322, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.472738463917168e-05, + "loss": 3.8323, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.471899869166116e-05, + "loss": 3.8323, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.4710612744150636e-05, + "loss": 3.8259, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.4702226796640116e-05, + "loss": 3.8315, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.469385722793333e-05, + "loss": 3.8267, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.468547128042281e-05, + "loss": 3.828, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.4677085332912285e-05, + "loss": 3.8171, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.466869938540177e-05, + "loss": 3.8241, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.466032981669499e-05, + "loss": 3.8234, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.465194386918447e-05, + "loss": 3.8324, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.464355792167394e-05, + "loss": 3.8241, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.463517197416342e-05, + "loss": 3.8225, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.462680240545664e-05, + "loss": 3.8327, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.461841645794611e-05, + "loss": 3.8248, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.461003051043559e-05, + "loss": 3.8244, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.460164456292507e-05, + "loss": 3.8153, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.4593274994218286e-05, + "loss": 3.7995, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.458488904670776e-05, + "loss": 3.8265, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.457650309919724e-05, + "loss": 3.8219, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.4568117151686725e-05, + "loss": 3.8188, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.4559731204176205e-05, + "loss": 3.805, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.4551361635469415e-05, + "loss": 3.8101, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.4542975687958895e-05, + "loss": 3.8005, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.4534589740448374e-05, + "loss": 3.8222, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.4526203792937854e-05, + "loss": 3.8081, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.4517834224231064e-05, + "loss": 3.8146, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.4509448276720543e-05, + "loss": 3.8234, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.4501062329210023e-05, + "loss": 3.8084, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.44926763816995e-05, + "loss": 3.8116, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.448430681299271e-05, + "loss": 3.8161, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.447592086548219e-05, + "loss": 3.7948, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.446753491797168e-05, + "loss": 3.8104, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.445914897046116e-05, + "loss": 3.8133, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.445077940175437e-05, + "loss": 3.8186, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.444239345424385e-05, + "loss": 3.7999, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.443400750673333e-05, + "loss": 3.8059, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.442562155922281e-05, + "loss": 3.7975, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.441725199051602e-05, + "loss": 3.8236, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.44088660430055e-05, + "loss": 3.8155, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.440048009549498e-05, + "loss": 3.8118, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.439209414798446e-05, + "loss": 3.8274, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.438370820047394e-05, + "loss": 3.8207, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.437532225296342e-05, + "loss": 3.8327, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.436695268425663e-05, + "loss": 3.8098, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.435856673674611e-05, + "loss": 3.8112, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.435018078923559e-05, + "loss": 3.8157, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.43418112205288e-05, + "loss": 3.8037, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.433342527301828e-05, + "loss": 3.8152, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.432503932550776e-05, + "loss": 3.8098, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.431665337799724e-05, + "loss": 3.8175, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.430826743048672e-05, + "loss": 3.8107, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.429989786177993e-05, + "loss": 3.7987, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.429151191426941e-05, + "loss": 3.807, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.428312596675889e-05, + "loss": 3.8018, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.427474001924837e-05, + "loss": 3.8181, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.4266370450541586e-05, + "loss": 3.808, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.4257984503031066e-05, + "loss": 3.8, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.4249598555520546e-05, + "loss": 3.8131, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.4241212608010026e-05, + "loss": 3.8058, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.4232843039303235e-05, + "loss": 3.7968, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.4224457091792715e-05, + "loss": 3.8054, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.4216071144282195e-05, + "loss": 3.8142, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.4207685196771675e-05, + "loss": 3.8133, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.4199315628064884e-05, + "loss": 3.8074, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.4190929680554364e-05, + "loss": 3.7918, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.4182543733043844e-05, + "loss": 3.8091, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.4174157785533324e-05, + "loss": 3.7999, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.416578821682654e-05, + "loss": 3.8134, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.415740226931602e-05, + "loss": 3.8116, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.41490163218055e-05, + "loss": 3.8082, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.414063037429498e-05, + "loss": 3.798, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.413226080558819e-05, + "loss": 3.8142, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.412387485807767e-05, + "loss": 3.7866, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.411548891056715e-05, + "loss": 3.7983, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.410710296305663e-05, + "loss": 3.7948, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.409873339434984e-05, + "loss": 3.8063, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.409036382564305e-05, + "loss": 3.7885, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.408197787813253e-05, + "loss": 3.7961, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.407359193062201e-05, + "loss": 3.7952, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.4065205983111494e-05, + "loss": 3.7968, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.4056820035600974e-05, + "loss": 3.7969, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.4048434088090454e-05, + "loss": 3.7947, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.4040048140579934e-05, + "loss": 3.8083, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.4031662193069414e-05, + "loss": 3.8065, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.402329262436262e-05, + "loss": 3.8018, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.40149066768521e-05, + "loss": 3.7949, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.400652072934158e-05, + "loss": 3.8064, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.399813478183106e-05, + "loss": 3.801, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.398976521312427e-05, + "loss": 3.7933, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.398137926561375e-05, + "loss": 3.809, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.397299331810323e-05, + "loss": 3.7923, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.396460737059271e-05, + "loss": 3.8003, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.395623780188593e-05, + "loss": 3.7878, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.394785185437541e-05, + "loss": 3.8009, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.393946590686489e-05, + "loss": 3.7867, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.393107995935437e-05, + "loss": 3.7887, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.3922710390647576e-05, + "loss": 3.7919, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.3914324443137056e-05, + "loss": 3.8034, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.3905938495626536e-05, + "loss": 3.7954, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.3897552548116016e-05, + "loss": 3.799, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.3889182979409225e-05, + "loss": 3.7869, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.3880797031898705e-05, + "loss": 3.8, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.3872411084388185e-05, + "loss": 3.8071, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.3864025136877665e-05, + "loss": 3.797, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.385565556817088e-05, + "loss": 3.7938, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.384726962066036e-05, + "loss": 3.8024, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.383888367314984e-05, + "loss": 3.7946, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.3830497725639314e-05, + "loss": 3.8049, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.382212815693253e-05, + "loss": 3.7882, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.381374220942201e-05, + "loss": 3.7971, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.380535626191148e-05, + "loss": 3.7927, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.379697031440096e-05, + "loss": 3.7912, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.378860074569418e-05, + "loss": 3.7951, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.378021479818366e-05, + "loss": 3.793, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.377182885067313e-05, + "loss": 3.7956, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.376344290316262e-05, + "loss": 3.7831, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.3755073334455835e-05, + "loss": 3.7979, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 3.8852906227111816, + "eval_runtime": 342.0505, + "eval_samples_per_second": 1115.598, + "eval_steps_per_second": 34.863, + "step": 381600 + }, + { + "epoch": 1.0, + "learning_rate": 4.3746687386945315e-05, + "loss": 3.785, + "step": 381952 + }, + { + "epoch": 1.0, + "learning_rate": 4.373830143943479e-05, + "loss": 3.7779, + "step": 382464 + }, + { + "epoch": 1.0, + "learning_rate": 4.372991549192427e-05, + "loss": 3.7966, + "step": 382976 + }, + { + "epoch": 1.0, + "learning_rate": 4.3721545923217484e-05, + "loss": 3.7855, + "step": 383488 + }, + { + "epoch": 1.0, + "learning_rate": 4.371315997570696e-05, + "loss": 3.8038, + "step": 384000 + }, + { + "epoch": 1.0, + "learning_rate": 4.370477402819644e-05, + "loss": 3.7858, + "step": 384512 + }, + { + "epoch": 1.0, + "learning_rate": 4.369638808068592e-05, + "loss": 3.776, + "step": 385024 + }, + { + "epoch": 1.0, + "learning_rate": 4.368801851197913e-05, + "loss": 3.7779, + "step": 385536 + }, + { + "epoch": 1.0, + "learning_rate": 4.3679632564468606e-05, + "loss": 3.7839, + "step": 386048 + }, + { + "epoch": 1.0, + "learning_rate": 4.3671246616958086e-05, + "loss": 3.7905, + "step": 386560 + }, + { + "epoch": 1.0, + "learning_rate": 4.366286066944757e-05, + "loss": 3.7805, + "step": 387072 + }, + { + "epoch": 1.0, + "learning_rate": 4.365449110074079e-05, + "loss": 3.7848, + "step": 387584 + }, + { + "epoch": 1.0, + "learning_rate": 4.364613791083773e-05, + "loss": 3.7787, + "step": 388096 + }, + { + "epoch": 1.0, + "learning_rate": 4.363775196332721e-05, + "loss": 3.7788, + "step": 388608 + }, + { + "epoch": 1.0, + "learning_rate": 4.3629366015816687e-05, + "loss": 3.7845, + "step": 389120 + }, + { + "epoch": 1.0, + "learning_rate": 4.3620980068306167e-05, + "loss": 3.7732, + "step": 389632 + }, + { + "epoch": 1.0, + "learning_rate": 4.3612594120795647e-05, + "loss": 3.7743, + "step": 390144 + }, + { + "epoch": 1.0, + "learning_rate": 4.3604208173285126e-05, + "loss": 3.7825, + "step": 390656 + }, + { + "epoch": 1.0, + "learning_rate": 4.3595822225774606e-05, + "loss": 3.7778, + "step": 391168 + }, + { + "epoch": 1.0, + "learning_rate": 4.358743627826408e-05, + "loss": 3.7894, + "step": 391680 + }, + { + "epoch": 1.0, + "learning_rate": 4.357905033075356e-05, + "loss": 3.7846, + "step": 392192 + }, + { + "epoch": 1.0, + "learning_rate": 4.357066438324304e-05, + "loss": 3.7852, + "step": 392704 + }, + { + "epoch": 1.0, + "learning_rate": 4.3562278435732526e-05, + "loss": 3.7816, + "step": 393216 + }, + { + "epoch": 1.0, + "learning_rate": 4.3553892488222006e-05, + "loss": 3.7862, + "step": 393728 + }, + { + "epoch": 1.0, + "learning_rate": 4.3545522919515215e-05, + "loss": 3.771, + "step": 394240 + }, + { + "epoch": 1.0, + "learning_rate": 4.3537136972004695e-05, + "loss": 3.7881, + "step": 394752 + }, + { + "epoch": 1.0, + "learning_rate": 4.3528751024494175e-05, + "loss": 3.7752, + "step": 395264 + }, + { + "epoch": 1.0, + "learning_rate": 4.3520365076983655e-05, + "loss": 3.7718, + "step": 395776 + }, + { + "epoch": 1.0, + "learning_rate": 4.3511995508276864e-05, + "loss": 3.77, + "step": 396288 + }, + { + "epoch": 1.0, + "learning_rate": 4.3503609560766344e-05, + "loss": 3.7724, + "step": 396800 + }, + { + "epoch": 1.01, + "learning_rate": 4.3495223613255824e-05, + "loss": 3.7828, + "step": 397312 + }, + { + "epoch": 1.01, + "learning_rate": 4.3486837665745304e-05, + "loss": 3.7783, + "step": 397824 + }, + { + "epoch": 1.01, + "learning_rate": 4.347846809703851e-05, + "loss": 3.7842, + "step": 398336 + }, + { + "epoch": 1.01, + "learning_rate": 4.347008214952799e-05, + "loss": 3.7861, + "step": 398848 + }, + { + "epoch": 1.01, + "learning_rate": 4.346169620201748e-05, + "loss": 3.7733, + "step": 399360 + }, + { + "epoch": 1.01, + "learning_rate": 4.345331025450696e-05, + "loss": 3.7804, + "step": 399872 + }, + { + "epoch": 1.01, + "learning_rate": 4.344492430699644e-05, + "loss": 3.7779, + "step": 400384 + }, + { + "epoch": 1.01, + "learning_rate": 4.343655473828965e-05, + "loss": 3.7751, + "step": 400896 + }, + { + "epoch": 1.01, + "learning_rate": 4.342816879077913e-05, + "loss": 3.7713, + "step": 401408 + }, + { + "epoch": 1.01, + "learning_rate": 4.341978284326861e-05, + "loss": 3.7707, + "step": 401920 + }, + { + "epoch": 1.01, + "learning_rate": 4.341139689575809e-05, + "loss": 3.7754, + "step": 402432 + }, + { + "epoch": 1.01, + "learning_rate": 4.34030273270513e-05, + "loss": 3.7831, + "step": 402944 + }, + { + "epoch": 1.01, + "learning_rate": 4.339464137954078e-05, + "loss": 3.7735, + "step": 403456 + }, + { + "epoch": 1.01, + "learning_rate": 4.338625543203026e-05, + "loss": 3.7748, + "step": 403968 + }, + { + "epoch": 1.01, + "learning_rate": 4.337786948451974e-05, + "loss": 3.7809, + "step": 404480 + }, + { + "epoch": 1.01, + "learning_rate": 4.336949991581295e-05, + "loss": 3.7773, + "step": 404992 + }, + { + "epoch": 1.01, + "learning_rate": 4.3361113968302434e-05, + "loss": 3.7757, + "step": 405504 + }, + { + "epoch": 1.01, + "learning_rate": 4.3352728020791914e-05, + "loss": 3.7668, + "step": 406016 + }, + { + "epoch": 1.01, + "learning_rate": 4.3344342073281393e-05, + "loss": 3.747, + "step": 406528 + }, + { + "epoch": 1.01, + "learning_rate": 4.33359725045746e-05, + "loss": 3.7807, + "step": 407040 + }, + { + "epoch": 1.01, + "learning_rate": 4.332758655706408e-05, + "loss": 3.7722, + "step": 407552 + }, + { + "epoch": 1.01, + "learning_rate": 4.331920060955356e-05, + "loss": 3.7716, + "step": 408064 + }, + { + "epoch": 1.01, + "learning_rate": 4.331081466204304e-05, + "loss": 3.7612, + "step": 408576 + }, + { + "epoch": 1.01, + "learning_rate": 4.330244509333625e-05, + "loss": 3.7539, + "step": 409088 + }, + { + "epoch": 1.01, + "learning_rate": 4.329405914582573e-05, + "loss": 3.7545, + "step": 409600 + }, + { + "epoch": 1.01, + "learning_rate": 4.328567319831521e-05, + "loss": 3.7703, + "step": 410112 + }, + { + "epoch": 1.01, + "learning_rate": 4.327728725080469e-05, + "loss": 3.761, + "step": 410624 + }, + { + "epoch": 1.01, + "learning_rate": 4.32689176820979e-05, + "loss": 3.767, + "step": 411136 + }, + { + "epoch": 1.01, + "learning_rate": 4.326053173458739e-05, + "loss": 3.7728, + "step": 411648 + }, + { + "epoch": 1.01, + "learning_rate": 4.325214578707687e-05, + "loss": 3.7593, + "step": 412160 + }, + { + "epoch": 1.01, + "learning_rate": 4.324375983956635e-05, + "loss": 3.7641, + "step": 412672 + }, + { + "epoch": 1.01, + "learning_rate": 4.3235390270859556e-05, + "loss": 3.7704, + "step": 413184 + }, + { + "epoch": 1.01, + "learning_rate": 4.3227004323349036e-05, + "loss": 3.7489, + "step": 413696 + }, + { + "epoch": 1.01, + "learning_rate": 4.3218618375838516e-05, + "loss": 3.7584, + "step": 414208 + }, + { + "epoch": 1.01, + "learning_rate": 4.3210232428327996e-05, + "loss": 3.7654, + "step": 414720 + }, + { + "epoch": 1.01, + "learning_rate": 4.3201862859621205e-05, + "loss": 3.7714, + "step": 415232 + }, + { + "epoch": 1.01, + "learning_rate": 4.3193476912110685e-05, + "loss": 3.7503, + "step": 415744 + }, + { + "epoch": 1.01, + "learning_rate": 4.3185090964600165e-05, + "loss": 3.7594, + "step": 416256 + }, + { + "epoch": 1.01, + "learning_rate": 4.3176705017089645e-05, + "loss": 3.7502, + "step": 416768 + }, + { + "epoch": 1.01, + "learning_rate": 4.3168335448382854e-05, + "loss": 3.7741, + "step": 417280 + }, + { + "epoch": 1.01, + "learning_rate": 4.315994950087234e-05, + "loss": 3.7694, + "step": 417792 + }, + { + "epoch": 1.01, + "learning_rate": 4.315156355336182e-05, + "loss": 3.7663, + "step": 418304 + }, + { + "epoch": 1.01, + "learning_rate": 4.31431776058513e-05, + "loss": 3.7775, + "step": 418816 + }, + { + "epoch": 1.01, + "learning_rate": 4.313480803714451e-05, + "loss": 3.775, + "step": 419328 + }, + { + "epoch": 1.01, + "learning_rate": 4.312642208963399e-05, + "loss": 3.7865, + "step": 419840 + }, + { + "epoch": 1.01, + "learning_rate": 4.311803614212347e-05, + "loss": 3.7646, + "step": 420352 + }, + { + "epoch": 1.01, + "learning_rate": 4.310965019461295e-05, + "loss": 3.7647, + "step": 420864 + }, + { + "epoch": 1.01, + "learning_rate": 4.310128062590616e-05, + "loss": 3.7643, + "step": 421376 + }, + { + "epoch": 1.01, + "learning_rate": 4.309289467839564e-05, + "loss": 3.7562, + "step": 421888 + }, + { + "epoch": 1.01, + "learning_rate": 4.308450873088512e-05, + "loss": 3.7733, + "step": 422400 + }, + { + "epoch": 1.01, + "learning_rate": 4.30761227833746e-05, + "loss": 3.762, + "step": 422912 + }, + { + "epoch": 1.01, + "learning_rate": 4.306775321466781e-05, + "loss": 3.7718, + "step": 423424 + }, + { + "epoch": 1.01, + "learning_rate": 4.305936726715729e-05, + "loss": 3.7646, + "step": 423936 + }, + { + "epoch": 1.01, + "learning_rate": 4.3050981319646775e-05, + "loss": 3.7522, + "step": 424448 + }, + { + "epoch": 1.01, + "learning_rate": 4.3042595372136254e-05, + "loss": 3.7598, + "step": 424960 + }, + { + "epoch": 1.01, + "learning_rate": 4.3034225803429464e-05, + "loss": 3.7543, + "step": 425472 + }, + { + "epoch": 1.01, + "learning_rate": 4.3025839855918944e-05, + "loss": 3.7721, + "step": 425984 + }, + { + "epoch": 1.01, + "learning_rate": 4.3017453908408424e-05, + "loss": 3.7634, + "step": 426496 + }, + { + "epoch": 1.01, + "learning_rate": 4.3009067960897903e-05, + "loss": 3.7475, + "step": 427008 + }, + { + "epoch": 1.02, + "learning_rate": 4.300069839219111e-05, + "loss": 3.7703, + "step": 427520 + }, + { + "epoch": 1.02, + "learning_rate": 4.299231244468059e-05, + "loss": 3.7602, + "step": 428032 + }, + { + "epoch": 1.02, + "learning_rate": 4.298392649717007e-05, + "loss": 3.7519, + "step": 428544 + }, + { + "epoch": 1.02, + "learning_rate": 4.297554054965955e-05, + "loss": 3.7585, + "step": 429056 + }, + { + "epoch": 1.02, + "learning_rate": 4.296717098095276e-05, + "loss": 3.7688, + "step": 429568 + }, + { + "epoch": 1.02, + "learning_rate": 4.295878503344224e-05, + "loss": 3.7643, + "step": 430080 + }, + { + "epoch": 1.02, + "learning_rate": 4.295039908593173e-05, + "loss": 3.7659, + "step": 430592 + }, + { + "epoch": 1.02, + "learning_rate": 4.294201313842121e-05, + "loss": 3.7468, + "step": 431104 + }, + { + "epoch": 1.02, + "learning_rate": 4.293364356971442e-05, + "loss": 3.7629, + "step": 431616 + }, + { + "epoch": 1.02, + "learning_rate": 4.29252576222039e-05, + "loss": 3.755, + "step": 432128 + }, + { + "epoch": 1.02, + "learning_rate": 4.291687167469338e-05, + "loss": 3.7661, + "step": 432640 + }, + { + "epoch": 1.02, + "learning_rate": 4.290848572718286e-05, + "loss": 3.7679, + "step": 433152 + }, + { + "epoch": 1.02, + "learning_rate": 4.2900116158476066e-05, + "loss": 3.7582, + "step": 433664 + }, + { + "epoch": 1.02, + "learning_rate": 4.2891730210965546e-05, + "loss": 3.758, + "step": 434176 + }, + { + "epoch": 1.02, + "learning_rate": 4.2883344263455026e-05, + "loss": 3.7659, + "step": 434688 + }, + { + "epoch": 1.02, + "learning_rate": 4.2874958315944506e-05, + "loss": 3.7442, + "step": 435200 + }, + { + "epoch": 1.02, + "learning_rate": 4.2866588747237715e-05, + "loss": 3.7517, + "step": 435712 + }, + { + "epoch": 1.02, + "learning_rate": 4.2858202799727195e-05, + "loss": 3.7486, + "step": 436224 + }, + { + "epoch": 1.02, + "learning_rate": 4.284981685221668e-05, + "loss": 3.7597, + "step": 436736 + }, + { + "epoch": 1.02, + "learning_rate": 4.284144728350989e-05, + "loss": 3.7459, + "step": 437248 + }, + { + "epoch": 1.02, + "learning_rate": 4.283306133599937e-05, + "loss": 3.7537, + "step": 437760 + }, + { + "epoch": 1.02, + "learning_rate": 4.282467538848885e-05, + "loss": 3.7503, + "step": 438272 + }, + { + "epoch": 1.02, + "learning_rate": 4.281628944097833e-05, + "loss": 3.7523, + "step": 438784 + }, + { + "epoch": 1.02, + "learning_rate": 4.280790349346781e-05, + "loss": 3.7556, + "step": 439296 + }, + { + "epoch": 1.02, + "learning_rate": 4.2799517545957284e-05, + "loss": 3.7479, + "step": 439808 + }, + { + "epoch": 1.02, + "learning_rate": 4.2791131598446764e-05, + "loss": 3.7639, + "step": 440320 + }, + { + "epoch": 1.02, + "learning_rate": 4.2782745650936244e-05, + "loss": 3.7604, + "step": 440832 + }, + { + "epoch": 1.02, + "learning_rate": 4.277437608222945e-05, + "loss": 3.7591, + "step": 441344 + }, + { + "epoch": 1.02, + "learning_rate": 4.276599013471893e-05, + "loss": 3.7499, + "step": 441856 + }, + { + "epoch": 1.02, + "learning_rate": 4.275760418720842e-05, + "loss": 3.7598, + "step": 442368 + }, + { + "epoch": 1.02, + "learning_rate": 4.27492182396979e-05, + "loss": 3.76, + "step": 442880 + }, + { + "epoch": 1.02, + "learning_rate": 4.274084867099111e-05, + "loss": 3.7457, + "step": 443392 + }, + { + "epoch": 1.02, + "learning_rate": 4.273246272348059e-05, + "loss": 3.7672, + "step": 443904 + }, + { + "epoch": 1.02, + "learning_rate": 4.272407677597007e-05, + "loss": 3.7446, + "step": 444416 + }, + { + "epoch": 1.02, + "learning_rate": 4.271569082845955e-05, + "loss": 3.7587, + "step": 444928 + }, + { + "epoch": 1.02, + "learning_rate": 4.270732125975276e-05, + "loss": 3.7408, + "step": 445440 + }, + { + "epoch": 1.02, + "learning_rate": 4.269893531224224e-05, + "loss": 3.759, + "step": 445952 + }, + { + "epoch": 1.02, + "learning_rate": 4.269054936473172e-05, + "loss": 3.7417, + "step": 446464 + }, + { + "epoch": 1.02, + "learning_rate": 4.26821634172212e-05, + "loss": 3.7472, + "step": 446976 + }, + { + "epoch": 1.02, + "learning_rate": 4.267379384851441e-05, + "loss": 3.7446, + "step": 447488 + }, + { + "epoch": 1.02, + "learning_rate": 4.2665407901003887e-05, + "loss": 3.7641, + "step": 448000 + }, + { + "epoch": 1.02, + "learning_rate": 4.265702195349337e-05, + "loss": 3.75, + "step": 448512 + }, + { + "epoch": 1.02, + "learning_rate": 4.264863600598285e-05, + "loss": 3.7573, + "step": 449024 + }, + { + "epoch": 1.02, + "learning_rate": 4.264026643727606e-05, + "loss": 3.7438, + "step": 449536 + }, + { + "epoch": 1.02, + "learning_rate": 4.263188048976554e-05, + "loss": 3.7582, + "step": 450048 + }, + { + "epoch": 1.02, + "learning_rate": 4.262349454225502e-05, + "loss": 3.7607, + "step": 450560 + }, + { + "epoch": 1.02, + "learning_rate": 4.26151085947445e-05, + "loss": 3.7536, + "step": 451072 + }, + { + "epoch": 1.02, + "learning_rate": 4.260673902603771e-05, + "loss": 3.7524, + "step": 451584 + }, + { + "epoch": 1.02, + "learning_rate": 4.259835307852719e-05, + "loss": 3.7531, + "step": 452096 + }, + { + "epoch": 1.02, + "learning_rate": 4.258996713101667e-05, + "loss": 3.752, + "step": 452608 + }, + { + "epoch": 1.02, + "learning_rate": 4.258158118350615e-05, + "loss": 3.7631, + "step": 453120 + }, + { + "epoch": 1.02, + "learning_rate": 4.257321161479936e-05, + "loss": 3.7455, + "step": 453632 + }, + { + "epoch": 1.02, + "learning_rate": 4.256482566728884e-05, + "loss": 3.753, + "step": 454144 + }, + { + "epoch": 1.02, + "learning_rate": 4.255643971977833e-05, + "loss": 3.7491, + "step": 454656 + }, + { + "epoch": 1.02, + "learning_rate": 4.254805377226781e-05, + "loss": 3.7499, + "step": 455168 + }, + { + "epoch": 1.02, + "learning_rate": 4.2539684203561016e-05, + "loss": 3.7523, + "step": 455680 + }, + { + "epoch": 1.02, + "learning_rate": 4.2531298256050496e-05, + "loss": 3.7445, + "step": 456192 + }, + { + "epoch": 1.02, + "learning_rate": 4.2522912308539976e-05, + "loss": 3.7594, + "step": 456704 + }, + { + "epoch": 1.02, + "learning_rate": 4.2514526361029456e-05, + "loss": 3.7366, + "step": 457216 + }, + { + "epoch": 1.02, + "learning_rate": 4.2506156792322665e-05, + "loss": 3.7588, + "step": 457728 + }, + { + "epoch": 1.03, + "eval_loss": 3.869939088821411, + "eval_runtime": 345.3939, + "eval_samples_per_second": 1104.799, + "eval_steps_per_second": 34.526, + "step": 457920 + }, + { + "epoch": 0.0, + "learning_rate": 4.2497770844812145e-05, + "loss": 3.7434, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.2489384897301625e-05, + "loss": 3.7328, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.2480998949791105e-05, + "loss": 3.7497, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.2472613002280585e-05, + "loss": 3.7458, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.2464227054770065e-05, + "loss": 3.7591, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.2455841107259545e-05, + "loss": 3.7431, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.2447455159749025e-05, + "loss": 3.7357, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.243906921223851e-05, + "loss": 3.7348, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.243069964353172e-05, + "loss": 3.7421, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.24223136960212e-05, + "loss": 3.7483, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.241392774851068e-05, + "loss": 3.7396, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.240554180100016e-05, + "loss": 3.7419, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.239720498990083e-05, + "loss": 3.7436, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.238881904239031e-05, + "loss": 3.7353, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.238043309487979e-05, + "loss": 3.7412, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.237204714736927e-05, + "loss": 3.7293, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.236366119985875e-05, + "loss": 3.7355, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.2355275252348234e-05, + "loss": 3.7387, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.2346889304837714e-05, + "loss": 3.7361, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.2338503357327194e-05, + "loss": 3.7477, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.2330117409816674e-05, + "loss": 3.7496, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.2321731462306154e-05, + "loss": 3.7396, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.2313345514795634e-05, + "loss": 3.7394, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.2304959567285114e-05, + "loss": 3.7475, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.229658999857832e-05, + "loss": 3.7263, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.22882040510678e-05, + "loss": 3.7506, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.227981810355728e-05, + "loss": 3.733, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.227143215604676e-05, + "loss": 3.7322, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.226306258733997e-05, + "loss": 3.7286, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.225467663982945e-05, + "loss": 3.7359, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.224629069231893e-05, + "loss": 3.7374, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.223790474480841e-05, + "loss": 3.7394, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.222953517610163e-05, + "loss": 3.7413, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.222114922859111e-05, + "loss": 3.7439, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.221276328108059e-05, + "loss": 3.7318, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.220437733357006e-05, + "loss": 3.7408, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.219600776486328e-05, + "loss": 3.7407, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.218762181735276e-05, + "loss": 3.7311, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.217923586984224e-05, + "loss": 3.73, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.217084992233171e-05, + "loss": 3.7336, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.2162480353624926e-05, + "loss": 3.7311, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.2154094406114406e-05, + "loss": 3.7443, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.2145708458603886e-05, + "loss": 3.7334, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.2137322511093366e-05, + "loss": 3.7322, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.212895294238658e-05, + "loss": 3.7432, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.212056699487606e-05, + "loss": 3.7345, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.2112181047365535e-05, + "loss": 3.7388, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.2103795099855015e-05, + "loss": 3.7287, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.209542553114823e-05, + "loss": 3.7011, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.208703958363771e-05, + "loss": 3.7447, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.2078653636127184e-05, + "loss": 3.7306, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.20702840674204e-05, + "loss": 3.7329, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.206189811990988e-05, + "loss": 3.7227, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.205351217239936e-05, + "loss": 3.7129, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.204512622488884e-05, + "loss": 3.7176, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.2036756656182055e-05, + "loss": 3.7294, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.2028370708671535e-05, + "loss": 3.7242, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.201998476116101e-05, + "loss": 3.727, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.201159881365049e-05, + "loss": 3.7367, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.2003229244943704e-05, + "loss": 3.72, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.1994843297433184e-05, + "loss": 3.7207, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.198645734992266e-05, + "loss": 3.7349, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.197807140241214e-05, + "loss": 3.7068, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.196970183370535e-05, + "loss": 3.7196, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.196131588619483e-05, + "loss": 3.7253, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.195292993868431e-05, + "loss": 3.7352, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.194454399117379e-05, + "loss": 3.711, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.193617442246701e-05, + "loss": 3.7242, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.192778847495648e-05, + "loss": 3.7097, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.191940252744596e-05, + "loss": 3.7361, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.191101657993544e-05, + "loss": 3.733, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.190264701122866e-05, + "loss": 3.727, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.189426106371813e-05, + "loss": 3.7346, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.188587511620761e-05, + "loss": 3.7372, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.187748916869709e-05, + "loss": 3.7506, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.18691195999903e-05, + "loss": 3.7241, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.186073365247978e-05, + "loss": 3.7285, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.185234770496927e-05, + "loss": 3.7283, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.184396175745875e-05, + "loss": 3.7173, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.1835592188751956e-05, + "loss": 3.73, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.1827206241241436e-05, + "loss": 3.7257, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.1818820293730916e-05, + "loss": 3.7306, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.1810434346220396e-05, + "loss": 3.7345, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.1802064777513605e-05, + "loss": 3.7169, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.1793678830003085e-05, + "loss": 3.7149, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.1785292882492565e-05, + "loss": 3.7183, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.1776906934982045e-05, + "loss": 3.7365, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.1768537366275254e-05, + "loss": 3.7232, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.1760151418764734e-05, + "loss": 3.7152, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.175176547125422e-05, + "loss": 3.7208, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.17433795237437e-05, + "loss": 3.7288, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.173500995503691e-05, + "loss": 3.7153, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.172662400752639e-05, + "loss": 3.7202, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.171823806001587e-05, + "loss": 3.7354, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.170985211250535e-05, + "loss": 3.7262, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.170148254379856e-05, + "loss": 3.727, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.169309659628804e-05, + "loss": 3.7093, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.168471064877752e-05, + "loss": 3.7236, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.1676324701267e-05, + "loss": 3.7165, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.166795513256021e-05, + "loss": 3.7282, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.165956918504969e-05, + "loss": 3.7285, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.1651183237539174e-05, + "loss": 3.7245, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.1642797290028654e-05, + "loss": 3.7221, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.163442772132186e-05, + "loss": 3.7277, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.162604177381134e-05, + "loss": 3.706, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.161765582630082e-05, + "loss": 3.7162, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.16092698787903e-05, + "loss": 3.7074, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.160090031008351e-05, + "loss": 3.7259, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.159253074137672e-05, + "loss": 3.7084, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.15841447938662e-05, + "loss": 3.7148, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.157575884635568e-05, + "loss": 3.7101, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.156737289884516e-05, + "loss": 3.716, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.155898695133464e-05, + "loss": 3.7175, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.155060100382413e-05, + "loss": 3.7092, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.154221505631361e-05, + "loss": 3.7234, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.153382910880309e-05, + "loss": 3.7297, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.15254595400963e-05, + "loss": 3.7177, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.151707359258578e-05, + "loss": 3.7216, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.150868764507526e-05, + "loss": 3.719, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.150030169756474e-05, + "loss": 3.7238, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.1491932128857946e-05, + "loss": 3.7158, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.1483546181347426e-05, + "loss": 3.727, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.1475160233836906e-05, + "loss": 3.709, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.1466774286326386e-05, + "loss": 3.7223, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.1458404717619595e-05, + "loss": 3.7079, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.145001877010908e-05, + "loss": 3.7159, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.144163282259856e-05, + "loss": 3.7114, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.143324687508804e-05, + "loss": 3.7094, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.142487730638125e-05, + "loss": 3.7084, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.141649135887073e-05, + "loss": 3.7225, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.140810541136021e-05, + "loss": 3.7178, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.139971946384969e-05, + "loss": 3.721, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.13913498951429e-05, + "loss": 3.7062, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.138296394763238e-05, + "loss": 3.7229, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.137457800012186e-05, + "loss": 3.7229, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.136619205261134e-05, + "loss": 3.7191, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.135782248390455e-05, + "loss": 3.7166, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.1349436536394035e-05, + "loss": 3.7158, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.1341050588883515e-05, + "loss": 3.7164, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.1332664641372995e-05, + "loss": 3.7304, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.1324295072666204e-05, + "loss": 3.7073, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.1315909125155684e-05, + "loss": 3.7159, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.1307523177645164e-05, + "loss": 3.7176, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.1299137230134644e-05, + "loss": 3.7175, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.129076766142785e-05, + "loss": 3.709, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.128238171391733e-05, + "loss": 3.7107, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.127399576640681e-05, + "loss": 3.7261, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.126560981889629e-05, + "loss": 3.7026, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.12572402501895e-05, + "loss": 3.7224, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 3.8585259914398193, + "eval_runtime": 307.1982, + "eval_samples_per_second": 1242.166, + "eval_steps_per_second": 38.819, + "step": 534240 + }, + { + "epoch": 1.0, + "learning_rate": 4.124885430267898e-05, + "loss": 3.7075, + "step": 534528 + }, + { + "epoch": 1.0, + "learning_rate": 4.124046835516847e-05, + "loss": 3.6978, + "step": 535040 + }, + { + "epoch": 1.0, + "learning_rate": 4.123208240765795e-05, + "loss": 3.7163, + "step": 535552 + }, + { + "epoch": 1.0, + "learning_rate": 4.122371283895116e-05, + "loss": 3.7061, + "step": 536064 + }, + { + "epoch": 1.0, + "learning_rate": 4.121532689144064e-05, + "loss": 3.7217, + "step": 536576 + }, + { + "epoch": 1.0, + "learning_rate": 4.120694094393012e-05, + "loss": 3.711, + "step": 537088 + }, + { + "epoch": 1.0, + "learning_rate": 4.119857137522333e-05, + "loss": 3.7034, + "step": 537600 + }, + { + "epoch": 1.0, + "learning_rate": 4.119018542771281e-05, + "loss": 3.7021, + "step": 538112 + }, + { + "epoch": 1.0, + "learning_rate": 4.118179948020229e-05, + "loss": 3.709, + "step": 538624 + }, + { + "epoch": 1.0, + "learning_rate": 4.117341353269177e-05, + "loss": 3.7128, + "step": 539136 + }, + { + "epoch": 1.0, + "learning_rate": 4.1165027585181247e-05, + "loss": 3.7034, + "step": 539648 + }, + { + "epoch": 1.0, + "learning_rate": 4.1156641637670727e-05, + "loss": 3.706, + "step": 540160 + }, + { + "epoch": 1.0, + "learning_rate": 4.114828844776767e-05, + "loss": 3.7066, + "step": 540672 + }, + { + "epoch": 1.0, + "learning_rate": 4.113990250025715e-05, + "loss": 3.7029, + "step": 541184 + }, + { + "epoch": 1.0, + "learning_rate": 4.113151655274663e-05, + "loss": 3.708, + "step": 541696 + }, + { + "epoch": 1.0, + "learning_rate": 4.112313060523611e-05, + "loss": 3.6975, + "step": 542208 + }, + { + "epoch": 1.0, + "learning_rate": 4.111474465772559e-05, + "loss": 3.6992, + "step": 542720 + }, + { + "epoch": 1.0, + "learning_rate": 4.110635871021507e-05, + "loss": 3.7054, + "step": 543232 + }, + { + "epoch": 1.0, + "learning_rate": 4.109797276270455e-05, + "loss": 3.7041, + "step": 543744 + }, + { + "epoch": 1.0, + "learning_rate": 4.108958681519403e-05, + "loss": 3.7091, + "step": 544256 + }, + { + "epoch": 1.0, + "learning_rate": 4.1081200867683504e-05, + "loss": 3.7164, + "step": 544768 + }, + { + "epoch": 1.0, + "learning_rate": 4.1072814920172984e-05, + "loss": 3.7078, + "step": 545280 + }, + { + "epoch": 1.0, + "learning_rate": 4.1064428972662464e-05, + "loss": 3.7045, + "step": 545792 + }, + { + "epoch": 1.0, + "learning_rate": 4.1056043025151944e-05, + "loss": 3.7096, + "step": 546304 + }, + { + "epoch": 1.0, + "learning_rate": 4.104767345644516e-05, + "loss": 3.6976, + "step": 546816 + }, + { + "epoch": 1.0, + "learning_rate": 4.103928750893464e-05, + "loss": 3.7132, + "step": 547328 + }, + { + "epoch": 1.0, + "learning_rate": 4.103090156142412e-05, + "loss": 3.6979, + "step": 547840 + }, + { + "epoch": 1.0, + "learning_rate": 4.10225156139136e-05, + "loss": 3.7024, + "step": 548352 + }, + { + "epoch": 1.0, + "learning_rate": 4.101414604520681e-05, + "loss": 3.6964, + "step": 548864 + }, + { + "epoch": 1.0, + "learning_rate": 4.100576009769629e-05, + "loss": 3.6981, + "step": 549376 + }, + { + "epoch": 1.01, + "learning_rate": 4.099737415018577e-05, + "loss": 3.7017, + "step": 549888 + }, + { + "epoch": 1.01, + "learning_rate": 4.098900458147898e-05, + "loss": 3.709, + "step": 550400 + }, + { + "epoch": 1.01, + "learning_rate": 4.098061863396846e-05, + "loss": 3.705, + "step": 550912 + }, + { + "epoch": 1.01, + "learning_rate": 4.097223268645794e-05, + "loss": 3.7075, + "step": 551424 + }, + { + "epoch": 1.01, + "learning_rate": 4.096384673894742e-05, + "loss": 3.6967, + "step": 551936 + }, + { + "epoch": 1.01, + "learning_rate": 4.09554607914369e-05, + "loss": 3.7111, + "step": 552448 + }, + { + "epoch": 1.01, + "learning_rate": 4.094707484392638e-05, + "loss": 3.7081, + "step": 552960 + }, + { + "epoch": 1.01, + "learning_rate": 4.093868889641586e-05, + "loss": 3.6945, + "step": 553472 + }, + { + "epoch": 1.01, + "learning_rate": 4.0930302948905345e-05, + "loss": 3.6984, + "step": 553984 + }, + { + "epoch": 1.01, + "learning_rate": 4.0921933380198554e-05, + "loss": 3.6982, + "step": 554496 + }, + { + "epoch": 1.01, + "learning_rate": 4.0913547432688034e-05, + "loss": 3.6967, + "step": 555008 + }, + { + "epoch": 1.01, + "learning_rate": 4.0905161485177514e-05, + "loss": 3.7085, + "step": 555520 + }, + { + "epoch": 1.01, + "learning_rate": 4.0896775537666994e-05, + "loss": 3.7017, + "step": 556032 + }, + { + "epoch": 1.01, + "learning_rate": 4.08884059689602e-05, + "loss": 3.701, + "step": 556544 + }, + { + "epoch": 1.01, + "learning_rate": 4.088002002144968e-05, + "loss": 3.7092, + "step": 557056 + }, + { + "epoch": 1.01, + "learning_rate": 4.087163407393916e-05, + "loss": 3.7023, + "step": 557568 + }, + { + "epoch": 1.01, + "learning_rate": 4.086324812642864e-05, + "loss": 3.7042, + "step": 558080 + }, + { + "epoch": 1.01, + "learning_rate": 4.085487855772185e-05, + "loss": 3.6991, + "step": 558592 + }, + { + "epoch": 1.01, + "learning_rate": 4.084649261021133e-05, + "loss": 3.6667, + "step": 559104 + }, + { + "epoch": 1.01, + "learning_rate": 4.083810666270081e-05, + "loss": 3.7141, + "step": 559616 + }, + { + "epoch": 1.01, + "learning_rate": 4.08297207151903e-05, + "loss": 3.6968, + "step": 560128 + }, + { + "epoch": 1.01, + "learning_rate": 4.082135114648351e-05, + "loss": 3.704, + "step": 560640 + }, + { + "epoch": 1.01, + "learning_rate": 4.081296519897299e-05, + "loss": 3.6845, + "step": 561152 + }, + { + "epoch": 1.01, + "learning_rate": 4.080457925146247e-05, + "loss": 3.6835, + "step": 561664 + }, + { + "epoch": 1.01, + "learning_rate": 4.0796209682755676e-05, + "loss": 3.6819, + "step": 562176 + }, + { + "epoch": 1.01, + "learning_rate": 4.0787823735245156e-05, + "loss": 3.695, + "step": 562688 + }, + { + "epoch": 1.01, + "learning_rate": 4.0779437787734636e-05, + "loss": 3.6951, + "step": 563200 + }, + { + "epoch": 1.01, + "learning_rate": 4.0771051840224116e-05, + "loss": 3.6893, + "step": 563712 + }, + { + "epoch": 1.01, + "learning_rate": 4.0762682271517325e-05, + "loss": 3.7095, + "step": 564224 + }, + { + "epoch": 1.01, + "learning_rate": 4.0754296324006805e-05, + "loss": 3.6882, + "step": 564736 + }, + { + "epoch": 1.01, + "learning_rate": 4.0745910376496285e-05, + "loss": 3.6872, + "step": 565248 + }, + { + "epoch": 1.01, + "learning_rate": 4.0737524428985765e-05, + "loss": 3.7018, + "step": 565760 + }, + { + "epoch": 1.01, + "learning_rate": 4.072915486027898e-05, + "loss": 3.6756, + "step": 566272 + }, + { + "epoch": 1.01, + "learning_rate": 4.072076891276846e-05, + "loss": 3.6842, + "step": 566784 + }, + { + "epoch": 1.01, + "learning_rate": 4.071238296525794e-05, + "loss": 3.6938, + "step": 567296 + }, + { + "epoch": 1.01, + "learning_rate": 4.070399701774742e-05, + "loss": 3.703, + "step": 567808 + }, + { + "epoch": 1.01, + "learning_rate": 4.069562744904063e-05, + "loss": 3.6792, + "step": 568320 + }, + { + "epoch": 1.01, + "learning_rate": 4.068724150153011e-05, + "loss": 3.6907, + "step": 568832 + }, + { + "epoch": 1.01, + "learning_rate": 4.067885555401959e-05, + "loss": 3.6769, + "step": 569344 + }, + { + "epoch": 1.01, + "learning_rate": 4.067046960650907e-05, + "loss": 3.7056, + "step": 569856 + }, + { + "epoch": 1.01, + "learning_rate": 4.066210003780228e-05, + "loss": 3.6982, + "step": 570368 + }, + { + "epoch": 1.01, + "learning_rate": 4.065371409029176e-05, + "loss": 3.6956, + "step": 570880 + }, + { + "epoch": 1.01, + "learning_rate": 4.064532814278124e-05, + "loss": 3.7003, + "step": 571392 + }, + { + "epoch": 1.01, + "learning_rate": 4.0636958574074455e-05, + "loss": 3.7044, + "step": 571904 + }, + { + "epoch": 1.01, + "learning_rate": 4.0628572626563935e-05, + "loss": 3.7154, + "step": 572416 + }, + { + "epoch": 1.01, + "learning_rate": 4.0620186679053415e-05, + "loss": 3.6939, + "step": 572928 + }, + { + "epoch": 1.01, + "learning_rate": 4.0611800731542895e-05, + "loss": 3.6941, + "step": 573440 + }, + { + "epoch": 1.01, + "learning_rate": 4.0603414784032375e-05, + "loss": 3.6978, + "step": 573952 + }, + { + "epoch": 1.01, + "learning_rate": 4.0595028836521855e-05, + "loss": 3.6837, + "step": 574464 + }, + { + "epoch": 1.01, + "learning_rate": 4.0586642889011335e-05, + "loss": 3.6949, + "step": 574976 + }, + { + "epoch": 1.01, + "learning_rate": 4.0578273320304544e-05, + "loss": 3.696, + "step": 575488 + }, + { + "epoch": 1.01, + "learning_rate": 4.0569887372794024e-05, + "loss": 3.6993, + "step": 576000 + }, + { + "epoch": 1.01, + "learning_rate": 4.0561501425283504e-05, + "loss": 3.6994, + "step": 576512 + }, + { + "epoch": 1.01, + "learning_rate": 4.0553115477772983e-05, + "loss": 3.6866, + "step": 577024 + }, + { + "epoch": 1.01, + "learning_rate": 4.054474590906619e-05, + "loss": 3.6814, + "step": 577536 + }, + { + "epoch": 1.01, + "learning_rate": 4.053635996155567e-05, + "loss": 3.6869, + "step": 578048 + }, + { + "epoch": 1.01, + "learning_rate": 4.052797401404515e-05, + "loss": 3.703, + "step": 578560 + }, + { + "epoch": 1.01, + "learning_rate": 4.051958806653464e-05, + "loss": 3.6927, + "step": 579072 + }, + { + "epoch": 1.01, + "learning_rate": 4.051121849782785e-05, + "loss": 3.6843, + "step": 579584 + }, + { + "epoch": 1.02, + "learning_rate": 4.050283255031733e-05, + "loss": 3.6878, + "step": 580096 + }, + { + "epoch": 1.02, + "learning_rate": 4.049446298161054e-05, + "loss": 3.6971, + "step": 580608 + }, + { + "epoch": 1.02, + "learning_rate": 4.048607703410002e-05, + "loss": 3.6853, + "step": 581120 + }, + { + "epoch": 1.02, + "learning_rate": 4.04776910865895e-05, + "loss": 3.687, + "step": 581632 + }, + { + "epoch": 1.02, + "learning_rate": 4.046930513907898e-05, + "loss": 3.7029, + "step": 582144 + }, + { + "epoch": 1.02, + "learning_rate": 4.046091919156846e-05, + "loss": 3.6924, + "step": 582656 + }, + { + "epoch": 1.02, + "learning_rate": 4.045253324405793e-05, + "loss": 3.6951, + "step": 583168 + }, + { + "epoch": 1.02, + "learning_rate": 4.044414729654741e-05, + "loss": 3.6809, + "step": 583680 + }, + { + "epoch": 1.02, + "learning_rate": 4.043576134903689e-05, + "loss": 3.6891, + "step": 584192 + }, + { + "epoch": 1.02, + "learning_rate": 4.0427391780330106e-05, + "loss": 3.686, + "step": 584704 + }, + { + "epoch": 1.02, + "learning_rate": 4.0419005832819586e-05, + "loss": 3.6983, + "step": 585216 + }, + { + "epoch": 1.02, + "learning_rate": 4.0410619885309066e-05, + "loss": 3.6936, + "step": 585728 + }, + { + "epoch": 1.02, + "learning_rate": 4.0402233937798546e-05, + "loss": 3.6957, + "step": 586240 + }, + { + "epoch": 1.02, + "learning_rate": 4.039386436909176e-05, + "loss": 3.6917, + "step": 586752 + }, + { + "epoch": 1.02, + "learning_rate": 4.038549480038497e-05, + "loss": 3.6921, + "step": 587264 + }, + { + "epoch": 1.02, + "learning_rate": 4.037710885287445e-05, + "loss": 3.6808, + "step": 587776 + }, + { + "epoch": 1.02, + "learning_rate": 4.036872290536393e-05, + "loss": 3.6824, + "step": 588288 + }, + { + "epoch": 1.02, + "learning_rate": 4.0360336957853404e-05, + "loss": 3.6782, + "step": 588800 + }, + { + "epoch": 1.02, + "learning_rate": 4.0351951010342884e-05, + "loss": 3.6968, + "step": 589312 + }, + { + "epoch": 1.02, + "learning_rate": 4.03435814416361e-05, + "loss": 3.6784, + "step": 589824 + }, + { + "epoch": 1.02, + "learning_rate": 4.033519549412558e-05, + "loss": 3.6811, + "step": 590336 + }, + { + "epoch": 1.02, + "learning_rate": 4.032680954661506e-05, + "loss": 3.6762, + "step": 590848 + }, + { + "epoch": 1.02, + "learning_rate": 4.031842359910454e-05, + "loss": 3.6901, + "step": 591360 + }, + { + "epoch": 1.02, + "learning_rate": 4.031003765159402e-05, + "loss": 3.6859, + "step": 591872 + }, + { + "epoch": 1.02, + "learning_rate": 4.03016517040835e-05, + "loss": 3.677, + "step": 592384 + }, + { + "epoch": 1.02, + "learning_rate": 4.029326575657298e-05, + "loss": 3.6962, + "step": 592896 + }, + { + "epoch": 1.02, + "learning_rate": 4.028487980906246e-05, + "loss": 3.6938, + "step": 593408 + }, + { + "epoch": 1.02, + "learning_rate": 4.027651024035567e-05, + "loss": 3.6865, + "step": 593920 + }, + { + "epoch": 1.02, + "learning_rate": 4.026812429284515e-05, + "loss": 3.6909, + "step": 594432 + }, + { + "epoch": 1.02, + "learning_rate": 4.025973834533463e-05, + "loss": 3.6876, + "step": 594944 + }, + { + "epoch": 1.02, + "learning_rate": 4.025135239782411e-05, + "loss": 3.6896, + "step": 595456 + }, + { + "epoch": 1.02, + "learning_rate": 4.024296645031359e-05, + "loss": 3.6863, + "step": 595968 + }, + { + "epoch": 1.02, + "learning_rate": 4.023458050280307e-05, + "loss": 3.6921, + "step": 596480 + }, + { + "epoch": 1.02, + "learning_rate": 4.022619455529255e-05, + "loss": 3.6806, + "step": 596992 + }, + { + "epoch": 1.02, + "learning_rate": 4.021780860778203e-05, + "loss": 3.6907, + "step": 597504 + }, + { + "epoch": 1.02, + "learning_rate": 4.0209439039075244e-05, + "loss": 3.6814, + "step": 598016 + }, + { + "epoch": 1.02, + "learning_rate": 4.0201053091564724e-05, + "loss": 3.6858, + "step": 598528 + }, + { + "epoch": 1.02, + "learning_rate": 4.0192667144054204e-05, + "loss": 3.6787, + "step": 599040 + }, + { + "epoch": 1.02, + "learning_rate": 4.018429757534741e-05, + "loss": 3.6783, + "step": 599552 + }, + { + "epoch": 1.02, + "learning_rate": 4.017591162783689e-05, + "loss": 3.6785, + "step": 600064 + }, + { + "epoch": 1.02, + "learning_rate": 4.016752568032637e-05, + "loss": 3.6916, + "step": 600576 + }, + { + "epoch": 1.02, + "learning_rate": 4.015913973281585e-05, + "loss": 3.6852, + "step": 601088 + }, + { + "epoch": 1.02, + "learning_rate": 4.015077016410906e-05, + "loss": 3.6922, + "step": 601600 + }, + { + "epoch": 1.02, + "learning_rate": 4.014238421659854e-05, + "loss": 3.6733, + "step": 602112 + }, + { + "epoch": 1.02, + "learning_rate": 4.013399826908802e-05, + "loss": 3.6976, + "step": 602624 + }, + { + "epoch": 1.02, + "learning_rate": 4.01256123215775e-05, + "loss": 3.687, + "step": 603136 + }, + { + "epoch": 1.02, + "learning_rate": 4.011724275287072e-05, + "loss": 3.6905, + "step": 603648 + }, + { + "epoch": 1.02, + "learning_rate": 4.01088568053602e-05, + "loss": 3.6871, + "step": 604160 + }, + { + "epoch": 1.02, + "learning_rate": 4.010047085784968e-05, + "loss": 3.6831, + "step": 604672 + }, + { + "epoch": 1.02, + "learning_rate": 4.009208491033916e-05, + "loss": 3.6859, + "step": 605184 + }, + { + "epoch": 1.02, + "learning_rate": 4.008371534163237e-05, + "loss": 3.6983, + "step": 605696 + }, + { + "epoch": 1.02, + "learning_rate": 4.007532939412185e-05, + "loss": 3.6791, + "step": 606208 + }, + { + "epoch": 1.02, + "learning_rate": 4.006694344661133e-05, + "loss": 3.6874, + "step": 606720 + }, + { + "epoch": 1.02, + "learning_rate": 4.005855749910081e-05, + "loss": 3.6865, + "step": 607232 + }, + { + "epoch": 1.02, + "learning_rate": 4.0050187930394016e-05, + "loss": 3.6831, + "step": 607744 + }, + { + "epoch": 1.02, + "learning_rate": 4.0041801982883496e-05, + "loss": 3.6794, + "step": 608256 + }, + { + "epoch": 1.02, + "learning_rate": 4.0033416035372976e-05, + "loss": 3.682, + "step": 608768 + }, + { + "epoch": 1.02, + "learning_rate": 4.0025030087862456e-05, + "loss": 3.6931, + "step": 609280 + }, + { + "epoch": 1.02, + "learning_rate": 4.001666051915567e-05, + "loss": 3.6771, + "step": 609792 + }, + { + "epoch": 1.02, + "learning_rate": 4.000827457164515e-05, + "loss": 3.6906, + "step": 610304 + }, + { + "epoch": 1.03, + "eval_loss": 3.8526551723480225, + "eval_runtime": 302.7295, + "eval_samples_per_second": 1260.502, + "eval_steps_per_second": 39.392, + "step": 610560 + }, + { + "epoch": 0.0, + "learning_rate": 3.999988862413463e-05, + "loss": 3.6737, + "step": 610816 + }, + { + "epoch": 0.0, + "learning_rate": 3.999150267662411e-05, + "loss": 3.6733, + "step": 611328 + }, + { + "epoch": 0.0, + "learning_rate": 3.998311672911359e-05, + "loss": 3.6802, + "step": 611840 + }, + { + "epoch": 0.0, + "learning_rate": 3.9974730781603065e-05, + "loss": 3.6799, + "step": 612352 + }, + { + "epoch": 0.0, + "learning_rate": 3.9966344834092545e-05, + "loss": 3.6915, + "step": 612864 + }, + { + "epoch": 0.0, + "learning_rate": 3.9957958886582025e-05, + "loss": 3.6815, + "step": 613376 + }, + { + "epoch": 0.0, + "learning_rate": 3.994958931787524e-05, + "loss": 3.6748, + "step": 613888 + }, + { + "epoch": 0.0, + "learning_rate": 3.9941203370364714e-05, + "loss": 3.6751, + "step": 614400 + }, + { + "epoch": 0.0, + "learning_rate": 3.9932817422854194e-05, + "loss": 3.6748, + "step": 614912 + }, + { + "epoch": 0.0, + "learning_rate": 3.9924431475343674e-05, + "loss": 3.6861, + "step": 615424 + }, + { + "epoch": 0.0, + "learning_rate": 3.991604552783316e-05, + "loss": 3.6738, + "step": 615936 + }, + { + "epoch": 0.0, + "learning_rate": 3.990765958032264e-05, + "loss": 3.6738, + "step": 616448 + }, + { + "epoch": 0.0, + "learning_rate": 3.9899306390419585e-05, + "loss": 3.6866, + "step": 616960 + }, + { + "epoch": 0.0, + "learning_rate": 3.9890920442909065e-05, + "loss": 3.6672, + "step": 617472 + }, + { + "epoch": 0.0, + "learning_rate": 3.988253449539854e-05, + "loss": 3.6752, + "step": 617984 + }, + { + "epoch": 0.0, + "learning_rate": 3.987414854788802e-05, + "loss": 3.6709, + "step": 618496 + }, + { + "epoch": 0.0, + "learning_rate": 3.98657626003775e-05, + "loss": 3.6696, + "step": 619008 + }, + { + "epoch": 0.0, + "learning_rate": 3.985737665286698e-05, + "loss": 3.6762, + "step": 619520 + }, + { + "epoch": 0.0, + "learning_rate": 3.984899070535646e-05, + "loss": 3.6745, + "step": 620032 + }, + { + "epoch": 0.0, + "learning_rate": 3.984060475784594e-05, + "loss": 3.6772, + "step": 620544 + }, + { + "epoch": 0.0, + "learning_rate": 3.983221881033542e-05, + "loss": 3.6902, + "step": 621056 + }, + { + "epoch": 0.0, + "learning_rate": 3.98238328628249e-05, + "loss": 3.6785, + "step": 621568 + }, + { + "epoch": 0.0, + "learning_rate": 3.981544691531438e-05, + "loss": 3.6788, + "step": 622080 + }, + { + "epoch": 0.0, + "learning_rate": 3.980706096780386e-05, + "loss": 3.6753, + "step": 622592 + }, + { + "epoch": 0.0, + "learning_rate": 3.9798691399097074e-05, + "loss": 3.6714, + "step": 623104 + }, + { + "epoch": 0.0, + "learning_rate": 3.9790305451586554e-05, + "loss": 3.6828, + "step": 623616 + }, + { + "epoch": 0.0, + "learning_rate": 3.9781919504076034e-05, + "loss": 3.67, + "step": 624128 + }, + { + "epoch": 0.0, + "learning_rate": 3.9773533556565514e-05, + "loss": 3.6758, + "step": 624640 + }, + { + "epoch": 0.0, + "learning_rate": 3.976516398785872e-05, + "loss": 3.6628, + "step": 625152 + }, + { + "epoch": 0.0, + "learning_rate": 3.97567780403482e-05, + "loss": 3.6708, + "step": 625664 + }, + { + "epoch": 0.01, + "learning_rate": 3.974839209283768e-05, + "loss": 3.6688, + "step": 626176 + }, + { + "epoch": 0.01, + "learning_rate": 3.974002252413089e-05, + "loss": 3.6787, + "step": 626688 + }, + { + "epoch": 0.01, + "learning_rate": 3.973163657662037e-05, + "loss": 3.6813, + "step": 627200 + }, + { + "epoch": 0.01, + "learning_rate": 3.972325062910985e-05, + "loss": 3.6801, + "step": 627712 + }, + { + "epoch": 0.01, + "learning_rate": 3.971486468159933e-05, + "loss": 3.671, + "step": 628224 + }, + { + "epoch": 0.01, + "learning_rate": 3.970647873408881e-05, + "loss": 3.6749, + "step": 628736 + }, + { + "epoch": 0.01, + "learning_rate": 3.969809278657829e-05, + "loss": 3.6829, + "step": 629248 + }, + { + "epoch": 0.01, + "learning_rate": 3.968970683906778e-05, + "loss": 3.669, + "step": 629760 + }, + { + "epoch": 0.01, + "learning_rate": 3.968132089155726e-05, + "loss": 3.6677, + "step": 630272 + }, + { + "epoch": 0.01, + "learning_rate": 3.967295132285047e-05, + "loss": 3.6692, + "step": 630784 + }, + { + "epoch": 0.01, + "learning_rate": 3.966456537533995e-05, + "loss": 3.6715, + "step": 631296 + }, + { + "epoch": 0.01, + "learning_rate": 3.965617942782943e-05, + "loss": 3.6723, + "step": 631808 + }, + { + "epoch": 0.01, + "learning_rate": 3.96477934803189e-05, + "loss": 3.6798, + "step": 632320 + }, + { + "epoch": 0.01, + "learning_rate": 3.9639423911612116e-05, + "loss": 3.6734, + "step": 632832 + }, + { + "epoch": 0.01, + "learning_rate": 3.9631054342905325e-05, + "loss": 3.6774, + "step": 633344 + }, + { + "epoch": 0.01, + "learning_rate": 3.9622668395394805e-05, + "loss": 3.6753, + "step": 633856 + }, + { + "epoch": 0.01, + "learning_rate": 3.9614282447884285e-05, + "loss": 3.6733, + "step": 634368 + }, + { + "epoch": 0.01, + "learning_rate": 3.9605896500373765e-05, + "loss": 3.6713, + "step": 634880 + }, + { + "epoch": 0.01, + "learning_rate": 3.9597510552863245e-05, + "loss": 3.6364, + "step": 635392 + }, + { + "epoch": 0.01, + "learning_rate": 3.958912460535273e-05, + "loss": 3.6843, + "step": 635904 + }, + { + "epoch": 0.01, + "learning_rate": 3.9580738657842205e-05, + "loss": 3.6665, + "step": 636416 + }, + { + "epoch": 0.01, + "learning_rate": 3.9572352710331685e-05, + "loss": 3.6782, + "step": 636928 + }, + { + "epoch": 0.01, + "learning_rate": 3.95639831416249e-05, + "loss": 3.6599, + "step": 637440 + }, + { + "epoch": 0.01, + "learning_rate": 3.9555597194114374e-05, + "loss": 3.6561, + "step": 637952 + }, + { + "epoch": 0.01, + "learning_rate": 3.9547211246603854e-05, + "loss": 3.6516, + "step": 638464 + }, + { + "epoch": 0.01, + "learning_rate": 3.9538825299093334e-05, + "loss": 3.6649, + "step": 638976 + }, + { + "epoch": 0.01, + "learning_rate": 3.953045573038655e-05, + "loss": 3.6673, + "step": 639488 + }, + { + "epoch": 0.01, + "learning_rate": 3.952206978287602e-05, + "loss": 3.6612, + "step": 640000 + }, + { + "epoch": 0.01, + "learning_rate": 3.95136838353655e-05, + "loss": 3.6768, + "step": 640512 + }, + { + "epoch": 0.01, + "learning_rate": 3.950531426665872e-05, + "loss": 3.6624, + "step": 641024 + }, + { + "epoch": 0.01, + "learning_rate": 3.9496944697951935e-05, + "loss": 3.6602, + "step": 641536 + }, + { + "epoch": 0.01, + "learning_rate": 3.9488558750441415e-05, + "loss": 3.6729, + "step": 642048 + }, + { + "epoch": 0.01, + "learning_rate": 3.9480172802930895e-05, + "loss": 3.651, + "step": 642560 + }, + { + "epoch": 0.01, + "learning_rate": 3.9471786855420375e-05, + "loss": 3.6559, + "step": 643072 + }, + { + "epoch": 0.01, + "learning_rate": 3.946340090790985e-05, + "loss": 3.6668, + "step": 643584 + }, + { + "epoch": 0.01, + "learning_rate": 3.945501496039933e-05, + "loss": 3.6699, + "step": 644096 + }, + { + "epoch": 0.01, + "learning_rate": 3.944662901288881e-05, + "loss": 3.6539, + "step": 644608 + }, + { + "epoch": 0.01, + "learning_rate": 3.943824306537829e-05, + "loss": 3.6603, + "step": 645120 + }, + { + "epoch": 0.01, + "learning_rate": 3.94298734966715e-05, + "loss": 3.6495, + "step": 645632 + }, + { + "epoch": 0.01, + "learning_rate": 3.942148754916098e-05, + "loss": 3.6744, + "step": 646144 + }, + { + "epoch": 0.01, + "learning_rate": 3.941310160165046e-05, + "loss": 3.6726, + "step": 646656 + }, + { + "epoch": 0.01, + "learning_rate": 3.940473203294367e-05, + "loss": 3.6653, + "step": 647168 + }, + { + "epoch": 0.01, + "learning_rate": 3.939634608543315e-05, + "loss": 3.6713, + "step": 647680 + }, + { + "epoch": 0.01, + "learning_rate": 3.938797651672637e-05, + "loss": 3.6753, + "step": 648192 + }, + { + "epoch": 0.01, + "learning_rate": 3.937959056921585e-05, + "loss": 3.6897, + "step": 648704 + }, + { + "epoch": 0.01, + "learning_rate": 3.937120462170532e-05, + "loss": 3.6675, + "step": 649216 + }, + { + "epoch": 0.01, + "learning_rate": 3.93628186741948e-05, + "loss": 3.6676, + "step": 649728 + }, + { + "epoch": 0.01, + "learning_rate": 3.935443272668428e-05, + "loss": 3.6644, + "step": 650240 + }, + { + "epoch": 0.01, + "learning_rate": 3.934604677917376e-05, + "loss": 3.6612, + "step": 650752 + }, + { + "epoch": 0.01, + "learning_rate": 3.933766083166324e-05, + "loss": 3.6668, + "step": 651264 + }, + { + "epoch": 0.01, + "learning_rate": 3.932929126295645e-05, + "loss": 3.6702, + "step": 651776 + }, + { + "epoch": 0.01, + "learning_rate": 3.932090531544593e-05, + "loss": 3.6688, + "step": 652288 + }, + { + "epoch": 0.01, + "learning_rate": 3.931251936793541e-05, + "loss": 3.6744, + "step": 652800 + }, + { + "epoch": 0.01, + "learning_rate": 3.9304149799228626e-05, + "loss": 3.6559, + "step": 653312 + }, + { + "epoch": 0.01, + "learning_rate": 3.9295763851718106e-05, + "loss": 3.6531, + "step": 653824 + }, + { + "epoch": 0.01, + "learning_rate": 3.9287377904207586e-05, + "loss": 3.6579, + "step": 654336 + }, + { + "epoch": 0.01, + "learning_rate": 3.9278991956697066e-05, + "loss": 3.6774, + "step": 654848 + }, + { + "epoch": 0.01, + "learning_rate": 3.9270606009186546e-05, + "loss": 3.6664, + "step": 655360 + }, + { + "epoch": 0.01, + "learning_rate": 3.9262220061676026e-05, + "loss": 3.6537, + "step": 655872 + }, + { + "epoch": 0.02, + "learning_rate": 3.9253834114165506e-05, + "loss": 3.66, + "step": 656384 + }, + { + "epoch": 0.02, + "learning_rate": 3.9245448166654986e-05, + "loss": 3.6701, + "step": 656896 + }, + { + "epoch": 0.02, + "learning_rate": 3.9237078597948195e-05, + "loss": 3.659, + "step": 657408 + }, + { + "epoch": 0.02, + "learning_rate": 3.9228692650437675e-05, + "loss": 3.6583, + "step": 657920 + }, + { + "epoch": 0.02, + "learning_rate": 3.9220306702927155e-05, + "loss": 3.6744, + "step": 658432 + }, + { + "epoch": 0.02, + "learning_rate": 3.9211920755416635e-05, + "loss": 3.6678, + "step": 658944 + }, + { + "epoch": 0.02, + "learning_rate": 3.9203534807906115e-05, + "loss": 3.6664, + "step": 659456 + }, + { + "epoch": 0.02, + "learning_rate": 3.9195148860395595e-05, + "loss": 3.6551, + "step": 659968 + }, + { + "epoch": 0.02, + "learning_rate": 3.9186762912885075e-05, + "loss": 3.6583, + "step": 660480 + }, + { + "epoch": 0.02, + "learning_rate": 3.917839334417829e-05, + "loss": 3.6604, + "step": 660992 + }, + { + "epoch": 0.02, + "learning_rate": 3.917000739666777e-05, + "loss": 3.6695, + "step": 661504 + }, + { + "epoch": 0.02, + "learning_rate": 3.916162144915725e-05, + "loss": 3.6679, + "step": 662016 + }, + { + "epoch": 0.02, + "learning_rate": 3.915323550164673e-05, + "loss": 3.6662, + "step": 662528 + }, + { + "epoch": 0.02, + "learning_rate": 3.914486593293994e-05, + "loss": 3.6653, + "step": 663040 + }, + { + "epoch": 0.02, + "learning_rate": 3.913649636423315e-05, + "loss": 3.6616, + "step": 663552 + }, + { + "epoch": 0.02, + "learning_rate": 3.912811041672263e-05, + "loss": 3.6597, + "step": 664064 + }, + { + "epoch": 0.02, + "learning_rate": 3.911972446921211e-05, + "loss": 3.6519, + "step": 664576 + }, + { + "epoch": 0.02, + "learning_rate": 3.911133852170159e-05, + "loss": 3.6486, + "step": 665088 + }, + { + "epoch": 0.02, + "learning_rate": 3.910295257419107e-05, + "loss": 3.6716, + "step": 665600 + }, + { + "epoch": 0.02, + "learning_rate": 3.909458300548428e-05, + "loss": 3.6563, + "step": 666112 + }, + { + "epoch": 0.02, + "learning_rate": 3.9086197057973764e-05, + "loss": 3.6493, + "step": 666624 + }, + { + "epoch": 0.02, + "learning_rate": 3.9077811110463244e-05, + "loss": 3.6502, + "step": 667136 + }, + { + "epoch": 0.02, + "learning_rate": 3.9069425162952724e-05, + "loss": 3.6563, + "step": 667648 + }, + { + "epoch": 0.02, + "learning_rate": 3.9061039215442204e-05, + "loss": 3.6636, + "step": 668160 + }, + { + "epoch": 0.02, + "learning_rate": 3.905266964673541e-05, + "loss": 3.6523, + "step": 668672 + }, + { + "epoch": 0.02, + "learning_rate": 3.904428369922489e-05, + "loss": 3.6657, + "step": 669184 + }, + { + "epoch": 0.02, + "learning_rate": 3.903589775171437e-05, + "loss": 3.6668, + "step": 669696 + }, + { + "epoch": 0.02, + "learning_rate": 3.902751180420385e-05, + "loss": 3.6615, + "step": 670208 + }, + { + "epoch": 0.02, + "learning_rate": 3.901912585669333e-05, + "loss": 3.6621, + "step": 670720 + }, + { + "epoch": 0.02, + "learning_rate": 3.901075628798654e-05, + "loss": 3.6599, + "step": 671232 + }, + { + "epoch": 0.02, + "learning_rate": 3.900237034047602e-05, + "loss": 3.6613, + "step": 671744 + }, + { + "epoch": 0.02, + "learning_rate": 3.89939843929655e-05, + "loss": 3.6608, + "step": 672256 + }, + { + "epoch": 0.02, + "learning_rate": 3.898559844545498e-05, + "loss": 3.6638, + "step": 672768 + }, + { + "epoch": 0.02, + "learning_rate": 3.897721249794446e-05, + "loss": 3.6568, + "step": 673280 + }, + { + "epoch": 0.02, + "learning_rate": 3.896882655043394e-05, + "loss": 3.6636, + "step": 673792 + }, + { + "epoch": 0.02, + "learning_rate": 3.896044060292342e-05, + "loss": 3.6562, + "step": 674304 + }, + { + "epoch": 0.02, + "learning_rate": 3.89520546554129e-05, + "loss": 3.6572, + "step": 674816 + }, + { + "epoch": 0.02, + "learning_rate": 3.894368508670611e-05, + "loss": 3.6506, + "step": 675328 + }, + { + "epoch": 0.02, + "learning_rate": 3.893529913919559e-05, + "loss": 3.6509, + "step": 675840 + }, + { + "epoch": 0.02, + "learning_rate": 3.892692957048881e-05, + "loss": 3.6528, + "step": 676352 + }, + { + "epoch": 0.02, + "learning_rate": 3.891854362297828e-05, + "loss": 3.6625, + "step": 676864 + }, + { + "epoch": 0.02, + "learning_rate": 3.891015767546776e-05, + "loss": 3.6573, + "step": 677376 + }, + { + "epoch": 0.02, + "learning_rate": 3.890177172795724e-05, + "loss": 3.6695, + "step": 677888 + }, + { + "epoch": 0.02, + "learning_rate": 3.889338578044672e-05, + "loss": 3.6479, + "step": 678400 + }, + { + "epoch": 0.02, + "learning_rate": 3.88849998329362e-05, + "loss": 3.6667, + "step": 678912 + }, + { + "epoch": 0.02, + "learning_rate": 3.887661388542569e-05, + "loss": 3.6617, + "step": 679424 + }, + { + "epoch": 0.02, + "learning_rate": 3.8868227937915167e-05, + "loss": 3.6625, + "step": 679936 + }, + { + "epoch": 0.02, + "learning_rate": 3.8859858369208376e-05, + "loss": 3.6605, + "step": 680448 + }, + { + "epoch": 0.02, + "learning_rate": 3.8851472421697856e-05, + "loss": 3.6562, + "step": 680960 + }, + { + "epoch": 0.02, + "learning_rate": 3.8843086474187336e-05, + "loss": 3.6615, + "step": 681472 + }, + { + "epoch": 0.02, + "learning_rate": 3.8834700526676816e-05, + "loss": 3.6712, + "step": 681984 + }, + { + "epoch": 0.02, + "learning_rate": 3.8826347336773754e-05, + "loss": 3.651, + "step": 682496 + }, + { + "epoch": 0.02, + "learning_rate": 3.8817961389263234e-05, + "loss": 3.6614, + "step": 683008 + }, + { + "epoch": 0.02, + "learning_rate": 3.8809575441752714e-05, + "loss": 3.657, + "step": 683520 + }, + { + "epoch": 0.02, + "learning_rate": 3.8801189494242194e-05, + "loss": 3.6565, + "step": 684032 + }, + { + "epoch": 0.02, + "learning_rate": 3.879281992553541e-05, + "loss": 3.6562, + "step": 684544 + }, + { + "epoch": 0.02, + "learning_rate": 3.878443397802489e-05, + "loss": 3.655, + "step": 685056 + }, + { + "epoch": 0.02, + "learning_rate": 3.877604803051437e-05, + "loss": 3.6655, + "step": 685568 + }, + { + "epoch": 0.02, + "learning_rate": 3.876766208300385e-05, + "loss": 3.6532, + "step": 686080 + }, + { + "epoch": 0.02, + "learning_rate": 3.875929251429706e-05, + "loss": 3.6618, + "step": 686592 + }, + { + "epoch": 0.03, + "eval_loss": 3.848236322402954, + "eval_runtime": 303.1034, + "eval_samples_per_second": 1258.946, + "eval_steps_per_second": 39.343, + "step": 686880 + }, + { + "epoch": 1.0, + "learning_rate": 3.875090656678654e-05, + "loss": 3.6471, + "step": 687104 + }, + { + "epoch": 1.0, + "learning_rate": 3.874252061927602e-05, + "loss": 3.6471, + "step": 687616 + }, + { + "epoch": 1.0, + "learning_rate": 3.87341346717655e-05, + "loss": 3.6524, + "step": 688128 + }, + { + "epoch": 1.0, + "learning_rate": 3.872574872425498e-05, + "loss": 3.6543, + "step": 688640 + }, + { + "epoch": 1.0, + "learning_rate": 3.871736277674446e-05, + "loss": 3.6684, + "step": 689152 + }, + { + "epoch": 1.0, + "learning_rate": 3.870897682923394e-05, + "loss": 3.6534, + "step": 689664 + }, + { + "epoch": 1.0, + "learning_rate": 3.870060726052715e-05, + "loss": 3.6514, + "step": 690176 + }, + { + "epoch": 1.0, + "learning_rate": 3.869222131301663e-05, + "loss": 3.6503, + "step": 690688 + }, + { + "epoch": 1.0, + "learning_rate": 3.868383536550611e-05, + "loss": 3.6472, + "step": 691200 + }, + { + "epoch": 1.0, + "learning_rate": 3.8675449417995594e-05, + "loss": 3.6587, + "step": 691712 + }, + { + "epoch": 1.0, + "learning_rate": 3.8667063470485074e-05, + "loss": 3.6479, + "step": 692224 + }, + { + "epoch": 1.0, + "learning_rate": 3.8658677522974554e-05, + "loss": 3.6484, + "step": 692736 + }, + { + "epoch": 1.0, + "learning_rate": 3.865032433307149e-05, + "loss": 3.6606, + "step": 693248 + }, + { + "epoch": 1.0, + "learning_rate": 3.864193838556097e-05, + "loss": 3.6407, + "step": 693760 + }, + { + "epoch": 1.0, + "learning_rate": 3.863355243805045e-05, + "loss": 3.6483, + "step": 694272 + }, + { + "epoch": 1.0, + "learning_rate": 3.862516649053993e-05, + "loss": 3.6416, + "step": 694784 + }, + { + "epoch": 1.0, + "learning_rate": 3.861678054302941e-05, + "loss": 3.6466, + "step": 695296 + }, + { + "epoch": 1.0, + "learning_rate": 3.860839459551889e-05, + "loss": 3.6437, + "step": 695808 + }, + { + "epoch": 1.0, + "learning_rate": 3.860000864800837e-05, + "loss": 3.6506, + "step": 696320 + }, + { + "epoch": 1.0, + "learning_rate": 3.859162270049785e-05, + "loss": 3.6521, + "step": 696832 + }, + { + "epoch": 1.0, + "learning_rate": 3.858323675298733e-05, + "loss": 3.6639, + "step": 697344 + }, + { + "epoch": 1.0, + "learning_rate": 3.857485080547681e-05, + "loss": 3.6507, + "step": 697856 + }, + { + "epoch": 1.0, + "learning_rate": 3.856646485796629e-05, + "loss": 3.6517, + "step": 698368 + }, + { + "epoch": 1.0, + "learning_rate": 3.855807891045577e-05, + "loss": 3.6473, + "step": 698880 + }, + { + "epoch": 1.0, + "learning_rate": 3.854970934174899e-05, + "loss": 3.6483, + "step": 699392 + }, + { + "epoch": 1.0, + "learning_rate": 3.854132339423847e-05, + "loss": 3.6553, + "step": 699904 + }, + { + "epoch": 1.0, + "learning_rate": 3.853293744672794e-05, + "loss": 3.6427, + "step": 700416 + }, + { + "epoch": 1.0, + "learning_rate": 3.852455149921742e-05, + "loss": 3.6527, + "step": 700928 + }, + { + "epoch": 1.0, + "learning_rate": 3.8516181930510636e-05, + "loss": 3.6342, + "step": 701440 + }, + { + "epoch": 1.0, + "learning_rate": 3.850779598300011e-05, + "loss": 3.6451, + "step": 701952 + }, + { + "epoch": 1.01, + "learning_rate": 3.849941003548959e-05, + "loss": 3.6454, + "step": 702464 + }, + { + "epoch": 1.01, + "learning_rate": 3.8491040466782805e-05, + "loss": 3.6503, + "step": 702976 + }, + { + "epoch": 1.01, + "learning_rate": 3.8482654519272285e-05, + "loss": 3.6574, + "step": 703488 + }, + { + "epoch": 1.01, + "learning_rate": 3.8474268571761765e-05, + "loss": 3.6544, + "step": 704000 + }, + { + "epoch": 1.01, + "learning_rate": 3.8465882624251245e-05, + "loss": 3.6449, + "step": 704512 + }, + { + "epoch": 1.01, + "learning_rate": 3.8457496676740725e-05, + "loss": 3.6447, + "step": 705024 + }, + { + "epoch": 1.01, + "learning_rate": 3.844912710803394e-05, + "loss": 3.6609, + "step": 705536 + }, + { + "epoch": 1.01, + "learning_rate": 3.8440741160523414e-05, + "loss": 3.6446, + "step": 706048 + }, + { + "epoch": 1.01, + "learning_rate": 3.8432355213012894e-05, + "loss": 3.643, + "step": 706560 + }, + { + "epoch": 1.01, + "learning_rate": 3.8423969265502374e-05, + "loss": 3.6428, + "step": 707072 + }, + { + "epoch": 1.01, + "learning_rate": 3.8415583317991854e-05, + "loss": 3.6476, + "step": 707584 + }, + { + "epoch": 1.01, + "learning_rate": 3.8407197370481334e-05, + "loss": 3.6458, + "step": 708096 + }, + { + "epoch": 1.01, + "learning_rate": 3.8398811422970814e-05, + "loss": 3.6513, + "step": 708608 + }, + { + "epoch": 1.01, + "learning_rate": 3.839044185426402e-05, + "loss": 3.6498, + "step": 709120 + }, + { + "epoch": 1.01, + "learning_rate": 3.83820559067535e-05, + "loss": 3.6473, + "step": 709632 + }, + { + "epoch": 1.01, + "learning_rate": 3.837366995924298e-05, + "loss": 3.6502, + "step": 710144 + }, + { + "epoch": 1.01, + "learning_rate": 3.836528401173246e-05, + "loss": 3.6471, + "step": 710656 + }, + { + "epoch": 1.01, + "learning_rate": 3.835689806422195e-05, + "loss": 3.649, + "step": 711168 + }, + { + "epoch": 1.01, + "learning_rate": 3.834851211671143e-05, + "loss": 3.6115, + "step": 711680 + }, + { + "epoch": 1.01, + "learning_rate": 3.834012616920091e-05, + "loss": 3.6553, + "step": 712192 + }, + { + "epoch": 1.01, + "learning_rate": 3.833174022169039e-05, + "loss": 3.6406, + "step": 712704 + }, + { + "epoch": 1.01, + "learning_rate": 3.83233706529836e-05, + "loss": 3.6556, + "step": 713216 + }, + { + "epoch": 1.01, + "learning_rate": 3.831498470547308e-05, + "loss": 3.6342, + "step": 713728 + }, + { + "epoch": 1.01, + "learning_rate": 3.830659875796256e-05, + "loss": 3.6304, + "step": 714240 + }, + { + "epoch": 1.01, + "learning_rate": 3.829822918925577e-05, + "loss": 3.6264, + "step": 714752 + }, + { + "epoch": 1.01, + "learning_rate": 3.828984324174525e-05, + "loss": 3.6371, + "step": 715264 + }, + { + "epoch": 1.01, + "learning_rate": 3.828145729423473e-05, + "loss": 3.6487, + "step": 715776 + }, + { + "epoch": 1.01, + "learning_rate": 3.827307134672421e-05, + "loss": 3.633, + "step": 716288 + }, + { + "epoch": 1.01, + "learning_rate": 3.826468539921369e-05, + "loss": 3.6521, + "step": 716800 + }, + { + "epoch": 1.01, + "learning_rate": 3.8256315830506903e-05, + "loss": 3.6412, + "step": 717312 + }, + { + "epoch": 1.01, + "learning_rate": 3.8247929882996383e-05, + "loss": 3.6293, + "step": 717824 + }, + { + "epoch": 1.01, + "learning_rate": 3.823954393548586e-05, + "loss": 3.6484, + "step": 718336 + }, + { + "epoch": 1.01, + "learning_rate": 3.823115798797534e-05, + "loss": 3.629, + "step": 718848 + }, + { + "epoch": 1.01, + "learning_rate": 3.822277204046482e-05, + "loss": 3.627, + "step": 719360 + }, + { + "epoch": 1.01, + "learning_rate": 3.82143860929543e-05, + "loss": 3.6412, + "step": 719872 + }, + { + "epoch": 1.01, + "learning_rate": 3.820601652424751e-05, + "loss": 3.6467, + "step": 720384 + }, + { + "epoch": 1.01, + "learning_rate": 3.819763057673699e-05, + "loss": 3.6304, + "step": 720896 + }, + { + "epoch": 1.01, + "learning_rate": 3.818924462922647e-05, + "loss": 3.6345, + "step": 721408 + }, + { + "epoch": 1.01, + "learning_rate": 3.8180858681715945e-05, + "loss": 3.6255, + "step": 721920 + }, + { + "epoch": 1.01, + "learning_rate": 3.8172472734205425e-05, + "loss": 3.6471, + "step": 722432 + }, + { + "epoch": 1.01, + "learning_rate": 3.8164086786694905e-05, + "loss": 3.6499, + "step": 722944 + }, + { + "epoch": 1.01, + "learning_rate": 3.8155700839184385e-05, + "loss": 3.6391, + "step": 723456 + }, + { + "epoch": 1.01, + "learning_rate": 3.814731489167387e-05, + "loss": 3.6457, + "step": 723968 + }, + { + "epoch": 1.01, + "learning_rate": 3.813896170177082e-05, + "loss": 3.6491, + "step": 724480 + }, + { + "epoch": 1.01, + "learning_rate": 3.81305757542603e-05, + "loss": 3.6633, + "step": 724992 + }, + { + "epoch": 1.01, + "learning_rate": 3.812218980674977e-05, + "loss": 3.6419, + "step": 725504 + }, + { + "epoch": 1.01, + "learning_rate": 3.811380385923925e-05, + "loss": 3.6477, + "step": 726016 + }, + { + "epoch": 1.01, + "learning_rate": 3.810541791172873e-05, + "loss": 3.6373, + "step": 726528 + }, + { + "epoch": 1.01, + "learning_rate": 3.809703196421821e-05, + "loss": 3.6383, + "step": 727040 + }, + { + "epoch": 1.01, + "learning_rate": 3.808864601670769e-05, + "loss": 3.6391, + "step": 727552 + }, + { + "epoch": 1.01, + "learning_rate": 3.808026006919717e-05, + "loss": 3.6468, + "step": 728064 + }, + { + "epoch": 1.01, + "learning_rate": 3.807189050049038e-05, + "loss": 3.6434, + "step": 728576 + }, + { + "epoch": 1.01, + "learning_rate": 3.8063520931783595e-05, + "loss": 3.6525, + "step": 729088 + }, + { + "epoch": 1.01, + "learning_rate": 3.8055134984273075e-05, + "loss": 3.6291, + "step": 729600 + }, + { + "epoch": 1.01, + "learning_rate": 3.8046749036762555e-05, + "loss": 3.6277, + "step": 730112 + }, + { + "epoch": 1.01, + "learning_rate": 3.8038363089252035e-05, + "loss": 3.6369, + "step": 730624 + }, + { + "epoch": 1.01, + "learning_rate": 3.8029993520545244e-05, + "loss": 3.6468, + "step": 731136 + }, + { + "epoch": 1.01, + "learning_rate": 3.8021607573034724e-05, + "loss": 3.6432, + "step": 731648 + }, + { + "epoch": 1.01, + "learning_rate": 3.8013221625524204e-05, + "loss": 3.6331, + "step": 732160 + }, + { + "epoch": 1.02, + "learning_rate": 3.8004835678013684e-05, + "loss": 3.6372, + "step": 732672 + }, + { + "epoch": 1.02, + "learning_rate": 3.7996449730503164e-05, + "loss": 3.6449, + "step": 733184 + }, + { + "epoch": 1.02, + "learning_rate": 3.798808016179637e-05, + "loss": 3.6341, + "step": 733696 + }, + { + "epoch": 1.02, + "learning_rate": 3.797969421428585e-05, + "loss": 3.6315, + "step": 734208 + }, + { + "epoch": 1.02, + "learning_rate": 3.797130826677533e-05, + "loss": 3.6505, + "step": 734720 + }, + { + "epoch": 1.02, + "learning_rate": 3.796292231926481e-05, + "loss": 3.6417, + "step": 735232 + }, + { + "epoch": 1.02, + "learning_rate": 3.795453637175429e-05, + "loss": 3.6461, + "step": 735744 + }, + { + "epoch": 1.02, + "learning_rate": 3.794615042424377e-05, + "loss": 3.6302, + "step": 736256 + }, + { + "epoch": 1.02, + "learning_rate": 3.793778085553699e-05, + "loss": 3.636, + "step": 736768 + }, + { + "epoch": 1.02, + "learning_rate": 3.792939490802647e-05, + "loss": 3.6338, + "step": 737280 + }, + { + "epoch": 1.02, + "learning_rate": 3.792100896051595e-05, + "loss": 3.6463, + "step": 737792 + }, + { + "epoch": 1.02, + "learning_rate": 3.791262301300543e-05, + "loss": 3.6457, + "step": 738304 + }, + { + "epoch": 1.02, + "learning_rate": 3.790423706549491e-05, + "loss": 3.6376, + "step": 738816 + }, + { + "epoch": 1.02, + "learning_rate": 3.789585111798439e-05, + "loss": 3.6428, + "step": 739328 + }, + { + "epoch": 1.02, + "learning_rate": 3.78874815492776e-05, + "loss": 3.6365, + "step": 739840 + }, + { + "epoch": 1.02, + "learning_rate": 3.787909560176708e-05, + "loss": 3.6399, + "step": 740352 + }, + { + "epoch": 1.02, + "learning_rate": 3.787070965425656e-05, + "loss": 3.6261, + "step": 740864 + }, + { + "epoch": 1.02, + "learning_rate": 3.786232370674604e-05, + "loss": 3.6277, + "step": 741376 + }, + { + "epoch": 1.02, + "learning_rate": 3.785393775923552e-05, + "loss": 3.6419, + "step": 741888 + }, + { + "epoch": 1.02, + "learning_rate": 3.7845568190528726e-05, + "loss": 3.6382, + "step": 742400 + }, + { + "epoch": 1.02, + "learning_rate": 3.783718224301821e-05, + "loss": 3.6209, + "step": 742912 + }, + { + "epoch": 1.02, + "learning_rate": 3.782879629550769e-05, + "loss": 3.6286, + "step": 743424 + }, + { + "epoch": 1.02, + "learning_rate": 3.782041034799717e-05, + "loss": 3.6304, + "step": 743936 + }, + { + "epoch": 1.02, + "learning_rate": 3.781202440048665e-05, + "loss": 3.6384, + "step": 744448 + }, + { + "epoch": 1.02, + "learning_rate": 3.780365483177986e-05, + "loss": 3.6271, + "step": 744960 + }, + { + "epoch": 1.02, + "learning_rate": 3.779526888426934e-05, + "loss": 3.6419, + "step": 745472 + }, + { + "epoch": 1.02, + "learning_rate": 3.778688293675882e-05, + "loss": 3.6443, + "step": 745984 + }, + { + "epoch": 1.02, + "learning_rate": 3.77784969892483e-05, + "loss": 3.6372, + "step": 746496 + }, + { + "epoch": 1.02, + "learning_rate": 3.777011104173778e-05, + "loss": 3.6347, + "step": 747008 + }, + { + "epoch": 1.02, + "learning_rate": 3.776174147303099e-05, + "loss": 3.6413, + "step": 747520 + }, + { + "epoch": 1.02, + "learning_rate": 3.775335552552047e-05, + "loss": 3.6356, + "step": 748032 + }, + { + "epoch": 1.02, + "learning_rate": 3.774496957800995e-05, + "loss": 3.6401, + "step": 748544 + }, + { + "epoch": 1.02, + "learning_rate": 3.773658363049943e-05, + "loss": 3.6398, + "step": 749056 + }, + { + "epoch": 1.02, + "learning_rate": 3.772819768298891e-05, + "loss": 3.6313, + "step": 749568 + }, + { + "epoch": 1.02, + "learning_rate": 3.7719828114282127e-05, + "loss": 3.6386, + "step": 750080 + }, + { + "epoch": 1.02, + "learning_rate": 3.7711442166771607e-05, + "loss": 3.6348, + "step": 750592 + }, + { + "epoch": 1.02, + "learning_rate": 3.770305621926108e-05, + "loss": 3.6297, + "step": 751104 + }, + { + "epoch": 1.02, + "learning_rate": 3.769467027175056e-05, + "loss": 3.6332, + "step": 751616 + }, + { + "epoch": 1.02, + "learning_rate": 3.768628432424004e-05, + "loss": 3.6272, + "step": 752128 + }, + { + "epoch": 1.02, + "learning_rate": 3.7677914755533255e-05, + "loss": 3.624, + "step": 752640 + }, + { + "epoch": 1.02, + "learning_rate": 3.766952880802273e-05, + "loss": 3.6415, + "step": 753152 + }, + { + "epoch": 1.02, + "learning_rate": 3.766114286051221e-05, + "loss": 3.6314, + "step": 753664 + }, + { + "epoch": 1.02, + "learning_rate": 3.765275691300169e-05, + "loss": 3.6464, + "step": 754176 + }, + { + "epoch": 1.02, + "learning_rate": 3.764437096549117e-05, + "loss": 3.6239, + "step": 754688 + }, + { + "epoch": 1.02, + "learning_rate": 3.7636001396784384e-05, + "loss": 3.6413, + "step": 755200 + }, + { + "epoch": 1.02, + "learning_rate": 3.7627615449273864e-05, + "loss": 3.6395, + "step": 755712 + }, + { + "epoch": 1.02, + "learning_rate": 3.7619229501763344e-05, + "loss": 3.641, + "step": 756224 + }, + { + "epoch": 1.02, + "learning_rate": 3.7610843554252824e-05, + "loss": 3.6358, + "step": 756736 + }, + { + "epoch": 1.02, + "learning_rate": 3.760247398554603e-05, + "loss": 3.6298, + "step": 757248 + }, + { + "epoch": 1.02, + "learning_rate": 3.759408803803551e-05, + "loss": 3.641, + "step": 757760 + }, + { + "epoch": 1.02, + "learning_rate": 3.758570209052499e-05, + "loss": 3.6449, + "step": 758272 + }, + { + "epoch": 1.02, + "learning_rate": 3.757731614301447e-05, + "loss": 3.6306, + "step": 758784 + }, + { + "epoch": 1.02, + "learning_rate": 3.756893019550395e-05, + "loss": 3.6362, + "step": 759296 + }, + { + "epoch": 1.02, + "learning_rate": 3.756054424799343e-05, + "loss": 3.6362, + "step": 759808 + }, + { + "epoch": 1.02, + "learning_rate": 3.755217467928664e-05, + "loss": 3.6323, + "step": 760320 + }, + { + "epoch": 1.02, + "learning_rate": 3.754378873177612e-05, + "loss": 3.6341, + "step": 760832 + }, + { + "epoch": 1.02, + "learning_rate": 3.75354027842656e-05, + "loss": 3.6306, + "step": 761344 + }, + { + "epoch": 1.02, + "learning_rate": 3.752701683675509e-05, + "loss": 3.6411, + "step": 761856 + }, + { + "epoch": 1.02, + "learning_rate": 3.75186472680483e-05, + "loss": 3.6325, + "step": 762368 + }, + { + "epoch": 1.02, + "learning_rate": 3.751026132053778e-05, + "loss": 3.6386, + "step": 762880 + }, + { + "epoch": 1.03, + "eval_loss": 3.845885992050171, + "eval_runtime": 303.0764, + "eval_samples_per_second": 1259.059, + "eval_steps_per_second": 39.347, + "step": 763200 + }, + { + "epoch": 0.0, + "learning_rate": 3.750187537302726e-05, + "loss": 3.6204, + "step": 763392 + }, + { + "epoch": 0.0, + "learning_rate": 3.749348942551674e-05, + "loss": 3.6231, + "step": 763904 + }, + { + "epoch": 0.0, + "learning_rate": 3.748510347800622e-05, + "loss": 3.6276, + "step": 764416 + }, + { + "epoch": 0.0, + "learning_rate": 3.74767175304957e-05, + "loss": 3.6307, + "step": 764928 + }, + { + "epoch": 0.0, + "learning_rate": 3.746833158298518e-05, + "loss": 3.6447, + "step": 765440 + }, + { + "epoch": 0.0, + "learning_rate": 3.745996201427839e-05, + "loss": 3.6342, + "step": 765952 + }, + { + "epoch": 0.0, + "learning_rate": 3.745157606676787e-05, + "loss": 3.6253, + "step": 766464 + }, + { + "epoch": 0.0, + "learning_rate": 3.744319011925735e-05, + "loss": 3.6282, + "step": 766976 + }, + { + "epoch": 0.0, + "learning_rate": 3.743480417174683e-05, + "loss": 3.6245, + "step": 767488 + }, + { + "epoch": 0.0, + "learning_rate": 3.742643460304004e-05, + "loss": 3.6309, + "step": 768000 + }, + { + "epoch": 0.0, + "learning_rate": 3.741804865552952e-05, + "loss": 3.6273, + "step": 768512 + }, + { + "epoch": 0.0, + "learning_rate": 3.7409662708019e-05, + "loss": 3.6291, + "step": 769024 + }, + { + "epoch": 0.0, + "learning_rate": 3.740129313931221e-05, + "loss": 3.6355, + "step": 769536 + }, + { + "epoch": 0.0, + "learning_rate": 3.739290719180169e-05, + "loss": 3.6153, + "step": 770048 + }, + { + "epoch": 0.0, + "learning_rate": 3.738452124429117e-05, + "loss": 3.6263, + "step": 770560 + }, + { + "epoch": 0.0, + "learning_rate": 3.737613529678065e-05, + "loss": 3.6158, + "step": 771072 + }, + { + "epoch": 0.0, + "learning_rate": 3.736774934927013e-05, + "loss": 3.6297, + "step": 771584 + }, + { + "epoch": 0.0, + "learning_rate": 3.735936340175961e-05, + "loss": 3.6232, + "step": 772096 + }, + { + "epoch": 0.0, + "learning_rate": 3.735097745424909e-05, + "loss": 3.6264, + "step": 772608 + }, + { + "epoch": 0.0, + "learning_rate": 3.7342591506738564e-05, + "loss": 3.626, + "step": 773120 + }, + { + "epoch": 0.0, + "learning_rate": 3.7334205559228044e-05, + "loss": 3.6412, + "step": 773632 + }, + { + "epoch": 0.0, + "learning_rate": 3.732583599052126e-05, + "loss": 3.6264, + "step": 774144 + }, + { + "epoch": 0.0, + "learning_rate": 3.731745004301074e-05, + "loss": 3.6316, + "step": 774656 + }, + { + "epoch": 0.0, + "learning_rate": 3.730906409550022e-05, + "loss": 3.6266, + "step": 775168 + }, + { + "epoch": 0.0, + "learning_rate": 3.73006781479897e-05, + "loss": 3.6266, + "step": 775680 + }, + { + "epoch": 0.0, + "learning_rate": 3.7292308579282916e-05, + "loss": 3.6306, + "step": 776192 + }, + { + "epoch": 0.0, + "learning_rate": 3.728392263177239e-05, + "loss": 3.6175, + "step": 776704 + }, + { + "epoch": 0.0, + "learning_rate": 3.727553668426187e-05, + "loss": 3.6273, + "step": 777216 + }, + { + "epoch": 0.0, + "learning_rate": 3.726715073675135e-05, + "loss": 3.6167, + "step": 777728 + }, + { + "epoch": 0.0, + "learning_rate": 3.725876478924083e-05, + "loss": 3.6198, + "step": 778240 + }, + { + "epoch": 0.01, + "learning_rate": 3.725037884173031e-05, + "loss": 3.6254, + "step": 778752 + }, + { + "epoch": 0.01, + "learning_rate": 3.724200927302352e-05, + "loss": 3.6288, + "step": 779264 + }, + { + "epoch": 0.01, + "learning_rate": 3.7233623325513e-05, + "loss": 3.6264, + "step": 779776 + }, + { + "epoch": 0.01, + "learning_rate": 3.722523737800248e-05, + "loss": 3.6362, + "step": 780288 + }, + { + "epoch": 0.01, + "learning_rate": 3.721685143049196e-05, + "loss": 3.6213, + "step": 780800 + }, + { + "epoch": 0.01, + "learning_rate": 3.7208465482981445e-05, + "loss": 3.6229, + "step": 781312 + }, + { + "epoch": 0.01, + "learning_rate": 3.7200095914274654e-05, + "loss": 3.6379, + "step": 781824 + }, + { + "epoch": 0.01, + "learning_rate": 3.7191709966764134e-05, + "loss": 3.6228, + "step": 782336 + }, + { + "epoch": 0.01, + "learning_rate": 3.7183324019253614e-05, + "loss": 3.6217, + "step": 782848 + }, + { + "epoch": 0.01, + "learning_rate": 3.7174938071743094e-05, + "loss": 3.6217, + "step": 783360 + }, + { + "epoch": 0.01, + "learning_rate": 3.7166552124232574e-05, + "loss": 3.6191, + "step": 783872 + }, + { + "epoch": 0.01, + "learning_rate": 3.7158166176722054e-05, + "loss": 3.6245, + "step": 784384 + }, + { + "epoch": 0.01, + "learning_rate": 3.7149780229211534e-05, + "loss": 3.6276, + "step": 784896 + }, + { + "epoch": 0.01, + "learning_rate": 3.714141066050474e-05, + "loss": 3.631, + "step": 785408 + }, + { + "epoch": 0.01, + "learning_rate": 3.713302471299422e-05, + "loss": 3.6215, + "step": 785920 + }, + { + "epoch": 0.01, + "learning_rate": 3.71246387654837e-05, + "loss": 3.6309, + "step": 786432 + }, + { + "epoch": 0.01, + "learning_rate": 3.711625281797318e-05, + "loss": 3.6225, + "step": 786944 + }, + { + "epoch": 0.01, + "learning_rate": 3.710786687046266e-05, + "loss": 3.6297, + "step": 787456 + }, + { + "epoch": 0.01, + "learning_rate": 3.709948092295214e-05, + "loss": 3.5916, + "step": 787968 + }, + { + "epoch": 0.01, + "learning_rate": 3.709109497544163e-05, + "loss": 3.6318, + "step": 788480 + }, + { + "epoch": 0.01, + "learning_rate": 3.70827090279311e-05, + "loss": 3.615, + "step": 788992 + }, + { + "epoch": 0.01, + "learning_rate": 3.707435583802805e-05, + "loss": 3.6311, + "step": 789504 + }, + { + "epoch": 0.01, + "learning_rate": 3.706596989051753e-05, + "loss": 3.6123, + "step": 790016 + }, + { + "epoch": 0.01, + "learning_rate": 3.705758394300701e-05, + "loss": 3.6099, + "step": 790528 + }, + { + "epoch": 0.01, + "learning_rate": 3.704919799549649e-05, + "loss": 3.6042, + "step": 791040 + }, + { + "epoch": 0.01, + "learning_rate": 3.704081204798597e-05, + "loss": 3.6149, + "step": 791552 + }, + { + "epoch": 0.01, + "learning_rate": 3.703242610047545e-05, + "loss": 3.6252, + "step": 792064 + }, + { + "epoch": 0.01, + "learning_rate": 3.7024056531768656e-05, + "loss": 3.6079, + "step": 792576 + }, + { + "epoch": 0.01, + "learning_rate": 3.7015670584258136e-05, + "loss": 3.6315, + "step": 793088 + }, + { + "epoch": 0.01, + "learning_rate": 3.7007284636747616e-05, + "loss": 3.6221, + "step": 793600 + }, + { + "epoch": 0.01, + "learning_rate": 3.6998898689237096e-05, + "loss": 3.6042, + "step": 794112 + }, + { + "epoch": 0.01, + "learning_rate": 3.6990512741726576e-05, + "loss": 3.6246, + "step": 794624 + }, + { + "epoch": 0.01, + "learning_rate": 3.698214317301979e-05, + "loss": 3.608, + "step": 795136 + }, + { + "epoch": 0.01, + "learning_rate": 3.697375722550927e-05, + "loss": 3.6067, + "step": 795648 + }, + { + "epoch": 0.01, + "learning_rate": 3.696537127799875e-05, + "loss": 3.6179, + "step": 796160 + }, + { + "epoch": 0.01, + "learning_rate": 3.6956985330488225e-05, + "loss": 3.6239, + "step": 796672 + }, + { + "epoch": 0.01, + "learning_rate": 3.694861576178144e-05, + "loss": 3.6045, + "step": 797184 + }, + { + "epoch": 0.01, + "learning_rate": 3.694022981427092e-05, + "loss": 3.6173, + "step": 797696 + }, + { + "epoch": 0.01, + "learning_rate": 3.69318438667604e-05, + "loss": 3.6056, + "step": 798208 + }, + { + "epoch": 0.01, + "learning_rate": 3.6923457919249874e-05, + "loss": 3.6198, + "step": 798720 + }, + { + "epoch": 0.01, + "learning_rate": 3.6915071971739354e-05, + "loss": 3.6277, + "step": 799232 + }, + { + "epoch": 0.01, + "learning_rate": 3.690670240303257e-05, + "loss": 3.6174, + "step": 799744 + }, + { + "epoch": 0.01, + "learning_rate": 3.689831645552205e-05, + "loss": 3.6255, + "step": 800256 + }, + { + "epoch": 0.01, + "learning_rate": 3.688993050801153e-05, + "loss": 3.6235, + "step": 800768 + }, + { + "epoch": 0.01, + "learning_rate": 3.688154456050101e-05, + "loss": 3.6411, + "step": 801280 + }, + { + "epoch": 0.01, + "learning_rate": 3.6873174991794226e-05, + "loss": 3.6221, + "step": 801792 + }, + { + "epoch": 0.01, + "learning_rate": 3.68647890442837e-05, + "loss": 3.6279, + "step": 802304 + }, + { + "epoch": 0.01, + "learning_rate": 3.685640309677318e-05, + "loss": 3.6115, + "step": 802816 + }, + { + "epoch": 0.01, + "learning_rate": 3.684801714926266e-05, + "loss": 3.6167, + "step": 803328 + }, + { + "epoch": 0.01, + "learning_rate": 3.683964758055587e-05, + "loss": 3.6181, + "step": 803840 + }, + { + "epoch": 0.01, + "learning_rate": 3.683126163304535e-05, + "loss": 3.6213, + "step": 804352 + }, + { + "epoch": 0.01, + "learning_rate": 3.682287568553483e-05, + "loss": 3.6246, + "step": 804864 + }, + { + "epoch": 0.01, + "learning_rate": 3.681448973802431e-05, + "loss": 3.6304, + "step": 805376 + }, + { + "epoch": 0.01, + "learning_rate": 3.6806120169317523e-05, + "loss": 3.6068, + "step": 805888 + }, + { + "epoch": 0.01, + "learning_rate": 3.6797734221807003e-05, + "loss": 3.6088, + "step": 806400 + }, + { + "epoch": 0.01, + "learning_rate": 3.6789348274296483e-05, + "loss": 3.6104, + "step": 806912 + }, + { + "epoch": 0.01, + "learning_rate": 3.678096232678596e-05, + "loss": 3.6261, + "step": 807424 + }, + { + "epoch": 0.01, + "learning_rate": 3.677257637927544e-05, + "loss": 3.62, + "step": 807936 + }, + { + "epoch": 0.01, + "learning_rate": 3.676420681056865e-05, + "loss": 3.6137, + "step": 808448 + }, + { + "epoch": 0.01, + "learning_rate": 3.675582086305813e-05, + "loss": 3.617, + "step": 808960 + }, + { + "epoch": 0.02, + "learning_rate": 3.674743491554761e-05, + "loss": 3.621, + "step": 809472 + }, + { + "epoch": 0.02, + "learning_rate": 3.673904896803709e-05, + "loss": 3.6114, + "step": 809984 + }, + { + "epoch": 0.02, + "learning_rate": 3.673066302052657e-05, + "loss": 3.6116, + "step": 810496 + }, + { + "epoch": 0.02, + "learning_rate": 3.672229345181978e-05, + "loss": 3.626, + "step": 811008 + }, + { + "epoch": 0.02, + "learning_rate": 3.671390750430926e-05, + "loss": 3.6249, + "step": 811520 + }, + { + "epoch": 0.02, + "learning_rate": 3.670552155679874e-05, + "loss": 3.6217, + "step": 812032 + }, + { + "epoch": 0.02, + "learning_rate": 3.669713560928822e-05, + "loss": 3.6061, + "step": 812544 + }, + { + "epoch": 0.02, + "learning_rate": 3.668876604058144e-05, + "loss": 3.6138, + "step": 813056 + }, + { + "epoch": 0.02, + "learning_rate": 3.668038009307092e-05, + "loss": 3.614, + "step": 813568 + }, + { + "epoch": 0.02, + "learning_rate": 3.66719941455604e-05, + "loss": 3.6206, + "step": 814080 + }, + { + "epoch": 0.02, + "learning_rate": 3.666360819804988e-05, + "loss": 3.6262, + "step": 814592 + }, + { + "epoch": 0.02, + "learning_rate": 3.665522225053936e-05, + "loss": 3.6133, + "step": 815104 + }, + { + "epoch": 0.02, + "learning_rate": 3.664683630302884e-05, + "loss": 3.6207, + "step": 815616 + }, + { + "epoch": 0.02, + "learning_rate": 3.6638466734322046e-05, + "loss": 3.6178, + "step": 816128 + }, + { + "epoch": 0.02, + "learning_rate": 3.6630080786811526e-05, + "loss": 3.6175, + "step": 816640 + }, + { + "epoch": 0.02, + "learning_rate": 3.6621694839301006e-05, + "loss": 3.6076, + "step": 817152 + }, + { + "epoch": 0.02, + "learning_rate": 3.6613308891790486e-05, + "loss": 3.6064, + "step": 817664 + }, + { + "epoch": 0.02, + "learning_rate": 3.6604922944279966e-05, + "loss": 3.6178, + "step": 818176 + }, + { + "epoch": 0.02, + "learning_rate": 3.6596536996769446e-05, + "loss": 3.6144, + "step": 818688 + }, + { + "epoch": 0.02, + "learning_rate": 3.658816742806266e-05, + "loss": 3.6043, + "step": 819200 + }, + { + "epoch": 0.02, + "learning_rate": 3.657978148055214e-05, + "loss": 3.608, + "step": 819712 + }, + { + "epoch": 0.02, + "learning_rate": 3.657139553304162e-05, + "loss": 3.6022, + "step": 820224 + }, + { + "epoch": 0.02, + "learning_rate": 3.65630095855311e-05, + "loss": 3.6189, + "step": 820736 + }, + { + "epoch": 0.02, + "learning_rate": 3.655464001682431e-05, + "loss": 3.6102, + "step": 821248 + }, + { + "epoch": 0.02, + "learning_rate": 3.654625406931379e-05, + "loss": 3.6189, + "step": 821760 + }, + { + "epoch": 0.02, + "learning_rate": 3.653786812180327e-05, + "loss": 3.6233, + "step": 822272 + }, + { + "epoch": 0.02, + "learning_rate": 3.652948217429275e-05, + "loss": 3.6164, + "step": 822784 + }, + { + "epoch": 0.02, + "learning_rate": 3.652109622678223e-05, + "loss": 3.613, + "step": 823296 + }, + { + "epoch": 0.02, + "learning_rate": 3.651272665807544e-05, + "loss": 3.6232, + "step": 823808 + }, + { + "epoch": 0.02, + "learning_rate": 3.650434071056492e-05, + "loss": 3.6149, + "step": 824320 + }, + { + "epoch": 0.02, + "learning_rate": 3.64959547630544e-05, + "loss": 3.6185, + "step": 824832 + }, + { + "epoch": 0.02, + "learning_rate": 3.648756881554388e-05, + "loss": 3.6151, + "step": 825344 + }, + { + "epoch": 0.02, + "learning_rate": 3.647918286803336e-05, + "loss": 3.6144, + "step": 825856 + }, + { + "epoch": 0.02, + "learning_rate": 3.6470813299326575e-05, + "loss": 3.6155, + "step": 826368 + }, + { + "epoch": 0.02, + "learning_rate": 3.6462427351816055e-05, + "loss": 3.6129, + "step": 826880 + }, + { + "epoch": 0.02, + "learning_rate": 3.6454041404305535e-05, + "loss": 3.6091, + "step": 827392 + }, + { + "epoch": 0.02, + "learning_rate": 3.644565545679501e-05, + "loss": 3.609, + "step": 827904 + }, + { + "epoch": 0.02, + "learning_rate": 3.6437285888088224e-05, + "loss": 3.6042, + "step": 828416 + }, + { + "epoch": 0.02, + "learning_rate": 3.6428899940577704e-05, + "loss": 3.6066, + "step": 828928 + }, + { + "epoch": 0.02, + "learning_rate": 3.642051399306718e-05, + "loss": 3.6189, + "step": 829440 + }, + { + "epoch": 0.02, + "learning_rate": 3.641212804555666e-05, + "loss": 3.6129, + "step": 829952 + }, + { + "epoch": 0.02, + "learning_rate": 3.640375847684987e-05, + "loss": 3.6233, + "step": 830464 + }, + { + "epoch": 0.02, + "learning_rate": 3.639537252933935e-05, + "loss": 3.6057, + "step": 830976 + }, + { + "epoch": 0.02, + "learning_rate": 3.638698658182883e-05, + "loss": 3.6193, + "step": 831488 + }, + { + "epoch": 0.02, + "learning_rate": 3.637860063431831e-05, + "loss": 3.6185, + "step": 832000 + }, + { + "epoch": 0.02, + "learning_rate": 3.637023106561153e-05, + "loss": 3.6157, + "step": 832512 + }, + { + "epoch": 0.02, + "learning_rate": 3.636184511810101e-05, + "loss": 3.6128, + "step": 833024 + }, + { + "epoch": 0.02, + "learning_rate": 3.635345917059048e-05, + "loss": 3.6104, + "step": 833536 + }, + { + "epoch": 0.02, + "learning_rate": 3.634507322307996e-05, + "loss": 3.6244, + "step": 834048 + }, + { + "epoch": 0.02, + "learning_rate": 3.633668727556944e-05, + "loss": 3.6256, + "step": 834560 + }, + { + "epoch": 0.02, + "learning_rate": 3.632831770686265e-05, + "loss": 3.6073, + "step": 835072 + }, + { + "epoch": 0.02, + "learning_rate": 3.631993175935213e-05, + "loss": 3.6135, + "step": 835584 + }, + { + "epoch": 0.02, + "learning_rate": 3.631154581184161e-05, + "loss": 3.6165, + "step": 836096 + }, + { + "epoch": 0.02, + "learning_rate": 3.630315986433109e-05, + "loss": 3.6111, + "step": 836608 + }, + { + "epoch": 0.02, + "learning_rate": 3.629479029562431e-05, + "loss": 3.61, + "step": 837120 + }, + { + "epoch": 0.02, + "learning_rate": 3.628640434811379e-05, + "loss": 3.6134, + "step": 837632 + }, + { + "epoch": 0.02, + "learning_rate": 3.627801840060327e-05, + "loss": 3.6158, + "step": 838144 + }, + { + "epoch": 0.02, + "learning_rate": 3.6269632453092747e-05, + "loss": 3.6146, + "step": 838656 + }, + { + "epoch": 0.02, + "learning_rate": 3.6261262884385956e-05, + "loss": 3.6152, + "step": 839168 + }, + { + "epoch": 0.03, + "eval_loss": 3.8439133167266846, + "eval_runtime": 308.2965, + "eval_samples_per_second": 1237.74, + "eval_steps_per_second": 38.68, + "step": 839520 + }, + { + "epoch": 1.0, + "learning_rate": 3.6252876936875436e-05, + "loss": 3.6028, + "step": 839680 + }, + { + "epoch": 1.0, + "learning_rate": 3.6244490989364916e-05, + "loss": 3.6007, + "step": 840192 + }, + { + "epoch": 1.0, + "learning_rate": 3.6236105041854396e-05, + "loss": 3.6061, + "step": 840704 + }, + { + "epoch": 1.0, + "learning_rate": 3.6227735473147605e-05, + "loss": 3.6099, + "step": 841216 + }, + { + "epoch": 1.0, + "learning_rate": 3.6219349525637085e-05, + "loss": 3.6208, + "step": 841728 + }, + { + "epoch": 1.0, + "learning_rate": 3.6210963578126565e-05, + "loss": 3.6134, + "step": 842240 + }, + { + "epoch": 1.0, + "learning_rate": 3.6202577630616045e-05, + "loss": 3.6071, + "step": 842752 + }, + { + "epoch": 1.0, + "learning_rate": 3.6194191683105524e-05, + "loss": 3.6081, + "step": 843264 + }, + { + "epoch": 1.0, + "learning_rate": 3.6185805735595004e-05, + "loss": 3.6008, + "step": 843776 + }, + { + "epoch": 1.0, + "learning_rate": 3.617743616688822e-05, + "loss": 3.6052, + "step": 844288 + }, + { + "epoch": 1.0, + "learning_rate": 3.61690502193777e-05, + "loss": 3.6133, + "step": 844800 + }, + { + "epoch": 1.0, + "learning_rate": 3.616066427186718e-05, + "loss": 3.6071, + "step": 845312 + }, + { + "epoch": 1.0, + "learning_rate": 3.615229470316039e-05, + "loss": 3.6147, + "step": 845824 + }, + { + "epoch": 1.0, + "learning_rate": 3.614390875564987e-05, + "loss": 3.5958, + "step": 846336 + }, + { + "epoch": 1.0, + "learning_rate": 3.613552280813935e-05, + "loss": 3.6067, + "step": 846848 + }, + { + "epoch": 1.0, + "learning_rate": 3.612713686062883e-05, + "loss": 3.591, + "step": 847360 + }, + { + "epoch": 1.0, + "learning_rate": 3.611875091311831e-05, + "loss": 3.6105, + "step": 847872 + }, + { + "epoch": 1.0, + "learning_rate": 3.611036496560779e-05, + "loss": 3.603, + "step": 848384 + }, + { + "epoch": 1.0, + "learning_rate": 3.610197901809727e-05, + "loss": 3.6053, + "step": 848896 + }, + { + "epoch": 1.0, + "learning_rate": 3.609359307058675e-05, + "loss": 3.6046, + "step": 849408 + }, + { + "epoch": 1.0, + "learning_rate": 3.608520712307623e-05, + "loss": 3.6243, + "step": 849920 + }, + { + "epoch": 1.0, + "learning_rate": 3.6076837554369445e-05, + "loss": 3.6048, + "step": 850432 + }, + { + "epoch": 1.0, + "learning_rate": 3.6068451606858925e-05, + "loss": 3.6125, + "step": 850944 + }, + { + "epoch": 1.0, + "learning_rate": 3.6060065659348405e-05, + "loss": 3.6054, + "step": 851456 + }, + { + "epoch": 1.0, + "learning_rate": 3.6051679711837885e-05, + "loss": 3.6083, + "step": 851968 + }, + { + "epoch": 1.0, + "learning_rate": 3.6043310143131094e-05, + "loss": 3.6133, + "step": 852480 + }, + { + "epoch": 1.0, + "learning_rate": 3.6034924195620574e-05, + "loss": 3.5949, + "step": 852992 + }, + { + "epoch": 1.0, + "learning_rate": 3.6026538248110054e-05, + "loss": 3.6066, + "step": 853504 + }, + { + "epoch": 1.0, + "learning_rate": 3.6018152300599534e-05, + "loss": 3.5978, + "step": 854016 + }, + { + "epoch": 1.0, + "learning_rate": 3.600978273189274e-05, + "loss": 3.5972, + "step": 854528 + }, + { + "epoch": 1.01, + "learning_rate": 3.600139678438222e-05, + "loss": 3.6073, + "step": 855040 + }, + { + "epoch": 1.01, + "learning_rate": 3.59930108368717e-05, + "loss": 3.6093, + "step": 855552 + }, + { + "epoch": 1.01, + "learning_rate": 3.598462488936118e-05, + "loss": 3.6026, + "step": 856064 + }, + { + "epoch": 1.01, + "learning_rate": 3.597623894185066e-05, + "loss": 3.621, + "step": 856576 + }, + { + "epoch": 1.01, + "learning_rate": 3.596785299434014e-05, + "loss": 3.6011, + "step": 857088 + }, + { + "epoch": 1.01, + "learning_rate": 3.595948342563336e-05, + "loss": 3.6003, + "step": 857600 + }, + { + "epoch": 1.01, + "learning_rate": 3.595109747812284e-05, + "loss": 3.6158, + "step": 858112 + }, + { + "epoch": 1.01, + "learning_rate": 3.594271153061231e-05, + "loss": 3.6008, + "step": 858624 + }, + { + "epoch": 1.01, + "learning_rate": 3.593432558310179e-05, + "loss": 3.6004, + "step": 859136 + }, + { + "epoch": 1.01, + "learning_rate": 3.592595601439501e-05, + "loss": 3.6057, + "step": 859648 + }, + { + "epoch": 1.01, + "learning_rate": 3.591757006688449e-05, + "loss": 3.5971, + "step": 860160 + }, + { + "epoch": 1.01, + "learning_rate": 3.590918411937396e-05, + "loss": 3.603, + "step": 860672 + }, + { + "epoch": 1.01, + "learning_rate": 3.590079817186344e-05, + "loss": 3.611, + "step": 861184 + }, + { + "epoch": 1.01, + "learning_rate": 3.5892428603156656e-05, + "loss": 3.6054, + "step": 861696 + }, + { + "epoch": 1.01, + "learning_rate": 3.5884042655646136e-05, + "loss": 3.6057, + "step": 862208 + }, + { + "epoch": 1.01, + "learning_rate": 3.5875656708135616e-05, + "loss": 3.6074, + "step": 862720 + }, + { + "epoch": 1.01, + "learning_rate": 3.5867270760625096e-05, + "loss": 3.6022, + "step": 863232 + }, + { + "epoch": 1.01, + "learning_rate": 3.5858884813114576e-05, + "loss": 3.6078, + "step": 863744 + }, + { + "epoch": 1.01, + "learning_rate": 3.5850515244407785e-05, + "loss": 3.5758, + "step": 864256 + }, + { + "epoch": 1.01, + "learning_rate": 3.5842129296897265e-05, + "loss": 3.6087, + "step": 864768 + }, + { + "epoch": 1.01, + "learning_rate": 3.5833743349386745e-05, + "loss": 3.598, + "step": 865280 + }, + { + "epoch": 1.01, + "learning_rate": 3.5825357401876225e-05, + "loss": 3.6122, + "step": 865792 + }, + { + "epoch": 1.01, + "learning_rate": 3.5816971454365705e-05, + "loss": 3.5946, + "step": 866304 + }, + { + "epoch": 1.01, + "learning_rate": 3.5808601885658914e-05, + "loss": 3.5858, + "step": 866816 + }, + { + "epoch": 1.01, + "learning_rate": 3.5800215938148394e-05, + "loss": 3.5873, + "step": 867328 + }, + { + "epoch": 1.01, + "learning_rate": 3.5791829990637874e-05, + "loss": 3.5933, + "step": 867840 + }, + { + "epoch": 1.01, + "learning_rate": 3.5783444043127354e-05, + "loss": 3.6062, + "step": 868352 + }, + { + "epoch": 1.01, + "learning_rate": 3.577507447442057e-05, + "loss": 3.5853, + "step": 868864 + }, + { + "epoch": 1.01, + "learning_rate": 3.576668852691005e-05, + "loss": 3.6125, + "step": 869376 + }, + { + "epoch": 1.01, + "learning_rate": 3.575830257939953e-05, + "loss": 3.604, + "step": 869888 + }, + { + "epoch": 1.01, + "learning_rate": 3.574991663188901e-05, + "loss": 3.5823, + "step": 870400 + }, + { + "epoch": 1.01, + "learning_rate": 3.574153068437849e-05, + "loss": 3.6058, + "step": 870912 + }, + { + "epoch": 1.01, + "learning_rate": 3.57331611156717e-05, + "loss": 3.5893, + "step": 871424 + }, + { + "epoch": 1.01, + "learning_rate": 3.572477516816118e-05, + "loss": 3.5845, + "step": 871936 + }, + { + "epoch": 1.01, + "learning_rate": 3.571638922065066e-05, + "loss": 3.5941, + "step": 872448 + }, + { + "epoch": 1.01, + "learning_rate": 3.570800327314014e-05, + "loss": 3.6069, + "step": 872960 + }, + { + "epoch": 1.01, + "learning_rate": 3.569963370443335e-05, + "loss": 3.5832, + "step": 873472 + }, + { + "epoch": 1.01, + "learning_rate": 3.569124775692283e-05, + "loss": 3.5989, + "step": 873984 + }, + { + "epoch": 1.01, + "learning_rate": 3.568286180941231e-05, + "loss": 3.5815, + "step": 874496 + }, + { + "epoch": 1.01, + "learning_rate": 3.567447586190179e-05, + "loss": 3.6001, + "step": 875008 + }, + { + "epoch": 1.01, + "learning_rate": 3.566608991439127e-05, + "loss": 3.6054, + "step": 875520 + }, + { + "epoch": 1.01, + "learning_rate": 3.5657720345684483e-05, + "loss": 3.6031, + "step": 876032 + }, + { + "epoch": 1.01, + "learning_rate": 3.5649334398173963e-05, + "loss": 3.6028, + "step": 876544 + }, + { + "epoch": 1.01, + "learning_rate": 3.5640948450663443e-05, + "loss": 3.606, + "step": 877056 + }, + { + "epoch": 1.01, + "learning_rate": 3.563256250315292e-05, + "loss": 3.6207, + "step": 877568 + }, + { + "epoch": 1.01, + "learning_rate": 3.562419293444613e-05, + "loss": 3.6021, + "step": 878080 + }, + { + "epoch": 1.01, + "learning_rate": 3.561580698693561e-05, + "loss": 3.6101, + "step": 878592 + }, + { + "epoch": 1.01, + "learning_rate": 3.560742103942509e-05, + "loss": 3.59, + "step": 879104 + }, + { + "epoch": 1.01, + "learning_rate": 3.559903509191457e-05, + "loss": 3.5976, + "step": 879616 + }, + { + "epoch": 1.01, + "learning_rate": 3.559066552320778e-05, + "loss": 3.5976, + "step": 880128 + }, + { + "epoch": 1.01, + "learning_rate": 3.558227957569726e-05, + "loss": 3.6006, + "step": 880640 + }, + { + "epoch": 1.01, + "learning_rate": 3.557389362818674e-05, + "loss": 3.6073, + "step": 881152 + }, + { + "epoch": 1.01, + "learning_rate": 3.556550768067622e-05, + "loss": 3.6079, + "step": 881664 + }, + { + "epoch": 1.01, + "learning_rate": 3.555712173316571e-05, + "loss": 3.5913, + "step": 882176 + }, + { + "epoch": 1.01, + "learning_rate": 3.554875216445892e-05, + "loss": 3.5893, + "step": 882688 + }, + { + "epoch": 1.01, + "learning_rate": 3.55403662169484e-05, + "loss": 3.5872, + "step": 883200 + }, + { + "epoch": 1.01, + "learning_rate": 3.553198026943788e-05, + "loss": 3.6096, + "step": 883712 + }, + { + "epoch": 1.01, + "learning_rate": 3.552359432192736e-05, + "loss": 3.5976, + "step": 884224 + }, + { + "epoch": 1.01, + "learning_rate": 3.5515224753220566e-05, + "loss": 3.5917, + "step": 884736 + }, + { + "epoch": 1.01, + "learning_rate": 3.5506838805710046e-05, + "loss": 3.6009, + "step": 885248 + }, + { + "epoch": 1.02, + "learning_rate": 3.5498452858199526e-05, + "loss": 3.598, + "step": 885760 + }, + { + "epoch": 1.02, + "learning_rate": 3.5490066910689006e-05, + "loss": 3.5924, + "step": 886272 + }, + { + "epoch": 1.02, + "learning_rate": 3.5481697341982215e-05, + "loss": 3.5922, + "step": 886784 + }, + { + "epoch": 1.02, + "learning_rate": 3.5473311394471695e-05, + "loss": 3.6075, + "step": 887296 + }, + { + "epoch": 1.02, + "learning_rate": 3.5464925446961175e-05, + "loss": 3.6022, + "step": 887808 + }, + { + "epoch": 1.02, + "learning_rate": 3.545653949945066e-05, + "loss": 3.6038, + "step": 888320 + }, + { + "epoch": 1.02, + "learning_rate": 3.544815355194014e-05, + "loss": 3.5872, + "step": 888832 + }, + { + "epoch": 1.02, + "learning_rate": 3.543978398323335e-05, + "loss": 3.5943, + "step": 889344 + }, + { + "epoch": 1.02, + "learning_rate": 3.543139803572283e-05, + "loss": 3.5945, + "step": 889856 + }, + { + "epoch": 1.02, + "learning_rate": 3.542301208821231e-05, + "loss": 3.6023, + "step": 890368 + }, + { + "epoch": 1.02, + "learning_rate": 3.541462614070179e-05, + "loss": 3.6023, + "step": 890880 + }, + { + "epoch": 1.02, + "learning_rate": 3.540624019319127e-05, + "loss": 3.6002, + "step": 891392 + }, + { + "epoch": 1.02, + "learning_rate": 3.539787062448448e-05, + "loss": 3.5985, + "step": 891904 + }, + { + "epoch": 1.02, + "learning_rate": 3.538948467697396e-05, + "loss": 3.599, + "step": 892416 + }, + { + "epoch": 1.02, + "learning_rate": 3.538109872946344e-05, + "loss": 3.597, + "step": 892928 + }, + { + "epoch": 1.02, + "learning_rate": 3.537271278195291e-05, + "loss": 3.5855, + "step": 893440 + }, + { + "epoch": 1.02, + "learning_rate": 3.536434321324613e-05, + "loss": 3.589, + "step": 893952 + }, + { + "epoch": 1.02, + "learning_rate": 3.535595726573561e-05, + "loss": 3.5947, + "step": 894464 + }, + { + "epoch": 1.02, + "learning_rate": 3.5347571318225095e-05, + "loss": 3.595, + "step": 894976 + }, + { + "epoch": 1.02, + "learning_rate": 3.533918537071457e-05, + "loss": 3.5841, + "step": 895488 + }, + { + "epoch": 1.02, + "learning_rate": 3.5330815802007784e-05, + "loss": 3.586, + "step": 896000 + }, + { + "epoch": 1.02, + "learning_rate": 3.5322429854497264e-05, + "loss": 3.5864, + "step": 896512 + }, + { + "epoch": 1.02, + "learning_rate": 3.5314043906986744e-05, + "loss": 3.5948, + "step": 897024 + }, + { + "epoch": 1.02, + "learning_rate": 3.530565795947622e-05, + "loss": 3.5925, + "step": 897536 + }, + { + "epoch": 1.02, + "learning_rate": 3.52972720119657e-05, + "loss": 3.5967, + "step": 898048 + }, + { + "epoch": 1.02, + "learning_rate": 3.528890244325891e-05, + "loss": 3.6031, + "step": 898560 + }, + { + "epoch": 1.02, + "learning_rate": 3.5280516495748386e-05, + "loss": 3.5997, + "step": 899072 + }, + { + "epoch": 1.02, + "learning_rate": 3.5272130548237866e-05, + "loss": 3.5933, + "step": 899584 + }, + { + "epoch": 1.02, + "learning_rate": 3.526374460072735e-05, + "loss": 3.6018, + "step": 900096 + }, + { + "epoch": 1.02, + "learning_rate": 3.525537503202056e-05, + "loss": 3.5966, + "step": 900608 + }, + { + "epoch": 1.02, + "learning_rate": 3.524698908451004e-05, + "loss": 3.5994, + "step": 901120 + }, + { + "epoch": 1.02, + "learning_rate": 3.523860313699952e-05, + "loss": 3.5958, + "step": 901632 + }, + { + "epoch": 1.02, + "learning_rate": 3.5230217189489e-05, + "loss": 3.5957, + "step": 902144 + }, + { + "epoch": 1.02, + "learning_rate": 3.522184762078222e-05, + "loss": 3.595, + "step": 902656 + }, + { + "epoch": 1.02, + "learning_rate": 3.521346167327169e-05, + "loss": 3.5962, + "step": 903168 + }, + { + "epoch": 1.02, + "learning_rate": 3.520507572576117e-05, + "loss": 3.5886, + "step": 903680 + }, + { + "epoch": 1.02, + "learning_rate": 3.519668977825065e-05, + "loss": 3.5891, + "step": 904192 + }, + { + "epoch": 1.02, + "learning_rate": 3.518832020954386e-05, + "loss": 3.5797, + "step": 904704 + }, + { + "epoch": 1.02, + "learning_rate": 3.517993426203334e-05, + "loss": 3.5906, + "step": 905216 + }, + { + "epoch": 1.02, + "learning_rate": 3.517154831452282e-05, + "loss": 3.5996, + "step": 905728 + }, + { + "epoch": 1.02, + "learning_rate": 3.51631623670123e-05, + "loss": 3.5931, + "step": 906240 + }, + { + "epoch": 1.02, + "learning_rate": 3.5154792798305516e-05, + "loss": 3.6045, + "step": 906752 + }, + { + "epoch": 1.02, + "learning_rate": 3.5146406850794996e-05, + "loss": 3.5801, + "step": 907264 + }, + { + "epoch": 1.02, + "learning_rate": 3.5138020903284476e-05, + "loss": 3.6037, + "step": 907776 + }, + { + "epoch": 1.02, + "learning_rate": 3.5129634955773956e-05, + "loss": 3.5993, + "step": 908288 + }, + { + "epoch": 1.02, + "learning_rate": 3.5121249008263436e-05, + "loss": 3.5984, + "step": 908800 + }, + { + "epoch": 1.02, + "learning_rate": 3.5112879439556645e-05, + "loss": 3.5859, + "step": 909312 + }, + { + "epoch": 1.02, + "learning_rate": 3.5104493492046125e-05, + "loss": 3.5921, + "step": 909824 + }, + { + "epoch": 1.02, + "learning_rate": 3.5096107544535605e-05, + "loss": 3.6046, + "step": 910336 + }, + { + "epoch": 1.02, + "learning_rate": 3.5087721597025085e-05, + "loss": 3.6048, + "step": 910848 + }, + { + "epoch": 1.02, + "learning_rate": 3.5079352028318294e-05, + "loss": 3.5906, + "step": 911360 + }, + { + "epoch": 1.02, + "learning_rate": 3.5070966080807774e-05, + "loss": 3.5906, + "step": 911872 + }, + { + "epoch": 1.02, + "learning_rate": 3.5062580133297254e-05, + "loss": 3.5945, + "step": 912384 + }, + { + "epoch": 1.02, + "learning_rate": 3.505419418578674e-05, + "loss": 3.5957, + "step": 912896 + }, + { + "epoch": 1.02, + "learning_rate": 3.504582461707995e-05, + "loss": 3.5899, + "step": 913408 + }, + { + "epoch": 1.02, + "learning_rate": 3.503743866956943e-05, + "loss": 3.5983, + "step": 913920 + }, + { + "epoch": 1.02, + "learning_rate": 3.502905272205891e-05, + "loss": 3.5921, + "step": 914432 + }, + { + "epoch": 1.02, + "learning_rate": 3.502066677454839e-05, + "loss": 3.5938, + "step": 914944 + }, + { + "epoch": 1.02, + "learning_rate": 3.501228082703787e-05, + "loss": 3.5967, + "step": 915456 + }, + { + "epoch": 1.03, + "eval_loss": 3.8431339263916016, + "eval_runtime": 306.2, + "eval_samples_per_second": 1246.215, + "eval_steps_per_second": 38.945, + "step": 915840 + }, + { + "epoch": 0.0, + "learning_rate": 3.500391125833108e-05, + "loss": 3.5881, + "step": 915968 + }, + { + "epoch": 0.0, + "learning_rate": 3.499552531082056e-05, + "loss": 3.577, + "step": 916480 + }, + { + "epoch": 0.0, + "learning_rate": 3.498713936331004e-05, + "loss": 3.5886, + "step": 916992 + }, + { + "epoch": 0.0, + "learning_rate": 3.497875341579952e-05, + "loss": 3.5943, + "step": 917504 + }, + { + "epoch": 0.0, + "learning_rate": 3.4970367468289e-05, + "loss": 3.5938, + "step": 918016 + }, + { + "epoch": 0.0, + "learning_rate": 3.496199789958221e-05, + "loss": 3.5977, + "step": 918528 + }, + { + "epoch": 0.0, + "learning_rate": 3.4953611952071694e-05, + "loss": 3.5909, + "step": 919040 + }, + { + "epoch": 0.0, + "learning_rate": 3.4945226004561174e-05, + "loss": 3.5885, + "step": 919552 + }, + { + "epoch": 0.0, + "learning_rate": 3.4936840057050654e-05, + "loss": 3.579, + "step": 920064 + }, + { + "epoch": 0.0, + "learning_rate": 3.492847048834386e-05, + "loss": 3.5901, + "step": 920576 + }, + { + "epoch": 0.0, + "learning_rate": 3.492008454083334e-05, + "loss": 3.5936, + "step": 921088 + }, + { + "epoch": 0.0, + "learning_rate": 3.491169859332282e-05, + "loss": 3.5893, + "step": 921600 + }, + { + "epoch": 0.0, + "learning_rate": 3.490332902461603e-05, + "loss": 3.5984, + "step": 922112 + }, + { + "epoch": 0.0, + "learning_rate": 3.489494307710551e-05, + "loss": 3.5731, + "step": 922624 + }, + { + "epoch": 0.0, + "learning_rate": 3.488655712959499e-05, + "loss": 3.5861, + "step": 923136 + }, + { + "epoch": 0.0, + "learning_rate": 3.487817118208447e-05, + "loss": 3.5746, + "step": 923648 + }, + { + "epoch": 0.0, + "learning_rate": 3.486978523457395e-05, + "loss": 3.5897, + "step": 924160 + }, + { + "epoch": 0.0, + "learning_rate": 3.486139928706343e-05, + "loss": 3.5839, + "step": 924672 + }, + { + "epoch": 0.0, + "learning_rate": 3.485301333955291e-05, + "loss": 3.585, + "step": 925184 + }, + { + "epoch": 0.0, + "learning_rate": 3.484462739204239e-05, + "loss": 3.5839, + "step": 925696 + }, + { + "epoch": 0.0, + "learning_rate": 3.483624144453188e-05, + "loss": 3.6068, + "step": 926208 + }, + { + "epoch": 0.0, + "learning_rate": 3.482787187582509e-05, + "loss": 3.5859, + "step": 926720 + }, + { + "epoch": 0.0, + "learning_rate": 3.481948592831457e-05, + "loss": 3.5919, + "step": 927232 + }, + { + "epoch": 0.0, + "learning_rate": 3.481109998080405e-05, + "loss": 3.5854, + "step": 927744 + }, + { + "epoch": 0.0, + "learning_rate": 3.480271403329352e-05, + "loss": 3.5922, + "step": 928256 + }, + { + "epoch": 0.0, + "learning_rate": 3.4794344464586737e-05, + "loss": 3.5931, + "step": 928768 + }, + { + "epoch": 0.0, + "learning_rate": 3.4785958517076217e-05, + "loss": 3.5768, + "step": 929280 + }, + { + "epoch": 0.0, + "learning_rate": 3.4777572569565697e-05, + "loss": 3.5882, + "step": 929792 + }, + { + "epoch": 0.0, + "learning_rate": 3.476918662205517e-05, + "loss": 3.5763, + "step": 930304 + }, + { + "epoch": 0.0, + "learning_rate": 3.4760817053348386e-05, + "loss": 3.5792, + "step": 930816 + }, + { + "epoch": 0.01, + "learning_rate": 3.4752431105837866e-05, + "loss": 3.5906, + "step": 931328 + }, + { + "epoch": 0.01, + "learning_rate": 3.4744045158327345e-05, + "loss": 3.5887, + "step": 931840 + }, + { + "epoch": 0.01, + "learning_rate": 3.4735659210816825e-05, + "loss": 3.5841, + "step": 932352 + }, + { + "epoch": 0.01, + "learning_rate": 3.4727273263306305e-05, + "loss": 3.5983, + "step": 932864 + }, + { + "epoch": 0.01, + "learning_rate": 3.4718887315795785e-05, + "loss": 3.5816, + "step": 933376 + }, + { + "epoch": 0.01, + "learning_rate": 3.4710517747088994e-05, + "loss": 3.5865, + "step": 933888 + }, + { + "epoch": 0.01, + "learning_rate": 3.4702131799578474e-05, + "loss": 3.5948, + "step": 934400 + }, + { + "epoch": 0.01, + "learning_rate": 3.4693745852067954e-05, + "loss": 3.5798, + "step": 934912 + }, + { + "epoch": 0.01, + "learning_rate": 3.4685359904557434e-05, + "loss": 3.5853, + "step": 935424 + }, + { + "epoch": 0.01, + "learning_rate": 3.4676990335850643e-05, + "loss": 3.5834, + "step": 935936 + }, + { + "epoch": 0.01, + "learning_rate": 3.466860438834012e-05, + "loss": 3.5775, + "step": 936448 + }, + { + "epoch": 0.01, + "learning_rate": 3.46602184408296e-05, + "loss": 3.5867, + "step": 936960 + }, + { + "epoch": 0.01, + "learning_rate": 3.465183249331908e-05, + "loss": 3.594, + "step": 937472 + }, + { + "epoch": 0.01, + "learning_rate": 3.46434629246123e-05, + "loss": 3.5852, + "step": 937984 + }, + { + "epoch": 0.01, + "learning_rate": 3.463507697710178e-05, + "loss": 3.5872, + "step": 938496 + }, + { + "epoch": 0.01, + "learning_rate": 3.462669102959126e-05, + "loss": 3.5884, + "step": 939008 + }, + { + "epoch": 0.01, + "learning_rate": 3.461830508208074e-05, + "loss": 3.5831, + "step": 939520 + }, + { + "epoch": 0.01, + "learning_rate": 3.460991913457022e-05, + "loss": 3.5892, + "step": 940032 + }, + { + "epoch": 0.01, + "learning_rate": 3.46015331870597e-05, + "loss": 3.5577, + "step": 940544 + }, + { + "epoch": 0.01, + "learning_rate": 3.459316361835291e-05, + "loss": 3.5863, + "step": 941056 + }, + { + "epoch": 0.01, + "learning_rate": 3.458477767084239e-05, + "loss": 3.5841, + "step": 941568 + }, + { + "epoch": 0.01, + "learning_rate": 3.457639172333187e-05, + "loss": 3.5917, + "step": 942080 + }, + { + "epoch": 0.01, + "learning_rate": 3.456800577582135e-05, + "loss": 3.5776, + "step": 942592 + }, + { + "epoch": 0.01, + "learning_rate": 3.455963620711456e-05, + "loss": 3.5647, + "step": 943104 + }, + { + "epoch": 0.01, + "learning_rate": 3.455125025960404e-05, + "loss": 3.5696, + "step": 943616 + }, + { + "epoch": 0.01, + "learning_rate": 3.454286431209352e-05, + "loss": 3.5727, + "step": 944128 + }, + { + "epoch": 0.01, + "learning_rate": 3.4534478364583004e-05, + "loss": 3.59, + "step": 944640 + }, + { + "epoch": 0.01, + "learning_rate": 3.452610879587621e-05, + "loss": 3.5654, + "step": 945152 + }, + { + "epoch": 0.01, + "learning_rate": 3.451772284836569e-05, + "loss": 3.5935, + "step": 945664 + }, + { + "epoch": 0.01, + "learning_rate": 3.450933690085517e-05, + "loss": 3.5832, + "step": 946176 + }, + { + "epoch": 0.01, + "learning_rate": 3.450095095334465e-05, + "loss": 3.5697, + "step": 946688 + }, + { + "epoch": 0.01, + "learning_rate": 3.449258138463786e-05, + "loss": 3.5853, + "step": 947200 + }, + { + "epoch": 0.01, + "learning_rate": 3.448419543712734e-05, + "loss": 3.5695, + "step": 947712 + }, + { + "epoch": 0.01, + "learning_rate": 3.447580948961682e-05, + "loss": 3.5694, + "step": 948224 + }, + { + "epoch": 0.01, + "learning_rate": 3.44674235421063e-05, + "loss": 3.5722, + "step": 948736 + }, + { + "epoch": 0.01, + "learning_rate": 3.445903759459578e-05, + "loss": 3.5862, + "step": 949248 + }, + { + "epoch": 0.01, + "learning_rate": 3.445066802588899e-05, + "loss": 3.5709, + "step": 949760 + }, + { + "epoch": 0.01, + "learning_rate": 3.444228207837847e-05, + "loss": 3.5821, + "step": 950272 + }, + { + "epoch": 0.01, + "learning_rate": 3.443389613086796e-05, + "loss": 3.5616, + "step": 950784 + }, + { + "epoch": 0.01, + "learning_rate": 3.442551018335744e-05, + "loss": 3.5823, + "step": 951296 + }, + { + "epoch": 0.01, + "learning_rate": 3.4417140614650646e-05, + "loss": 3.587, + "step": 951808 + }, + { + "epoch": 0.01, + "learning_rate": 3.4408754667140126e-05, + "loss": 3.5844, + "step": 952320 + }, + { + "epoch": 0.01, + "learning_rate": 3.4400368719629606e-05, + "loss": 3.5836, + "step": 952832 + }, + { + "epoch": 0.01, + "learning_rate": 3.4391982772119086e-05, + "loss": 3.5884, + "step": 953344 + }, + { + "epoch": 0.01, + "learning_rate": 3.4383613203412295e-05, + "loss": 3.5993, + "step": 953856 + }, + { + "epoch": 0.01, + "learning_rate": 3.4375227255901775e-05, + "loss": 3.5858, + "step": 954368 + }, + { + "epoch": 0.01, + "learning_rate": 3.4366841308391255e-05, + "loss": 3.5915, + "step": 954880 + }, + { + "epoch": 0.01, + "learning_rate": 3.4358455360880735e-05, + "loss": 3.5716, + "step": 955392 + }, + { + "epoch": 0.01, + "learning_rate": 3.4350085792173944e-05, + "loss": 3.5773, + "step": 955904 + }, + { + "epoch": 0.01, + "learning_rate": 3.4341699844663424e-05, + "loss": 3.5803, + "step": 956416 + }, + { + "epoch": 0.01, + "learning_rate": 3.433331389715291e-05, + "loss": 3.5808, + "step": 956928 + }, + { + "epoch": 0.01, + "learning_rate": 3.432492794964239e-05, + "loss": 3.5887, + "step": 957440 + }, + { + "epoch": 0.01, + "learning_rate": 3.43165583809356e-05, + "loss": 3.5905, + "step": 957952 + }, + { + "epoch": 0.01, + "learning_rate": 3.430817243342508e-05, + "loss": 3.5769, + "step": 958464 + }, + { + "epoch": 0.01, + "learning_rate": 3.429978648591456e-05, + "loss": 3.5682, + "step": 958976 + }, + { + "epoch": 0.01, + "learning_rate": 3.429140053840404e-05, + "loss": 3.5697, + "step": 959488 + }, + { + "epoch": 0.01, + "learning_rate": 3.428303096969725e-05, + "loss": 3.5912, + "step": 960000 + }, + { + "epoch": 0.01, + "learning_rate": 3.427464502218673e-05, + "loss": 3.5799, + "step": 960512 + }, + { + "epoch": 0.01, + "learning_rate": 3.426625907467621e-05, + "loss": 3.5748, + "step": 961024 + }, + { + "epoch": 0.01, + "learning_rate": 3.425787312716569e-05, + "loss": 3.582, + "step": 961536 + }, + { + "epoch": 0.02, + "learning_rate": 3.424948717965517e-05, + "loss": 3.5802, + "step": 962048 + }, + { + "epoch": 0.02, + "learning_rate": 3.424111761094838e-05, + "loss": 3.572, + "step": 962560 + }, + { + "epoch": 0.02, + "learning_rate": 3.4232731663437865e-05, + "loss": 3.5743, + "step": 963072 + }, + { + "epoch": 0.02, + "learning_rate": 3.4224345715927345e-05, + "loss": 3.5873, + "step": 963584 + }, + { + "epoch": 0.02, + "learning_rate": 3.4215959768416825e-05, + "loss": 3.5861, + "step": 964096 + }, + { + "epoch": 0.02, + "learning_rate": 3.4207590199710034e-05, + "loss": 3.5844, + "step": 964608 + }, + { + "epoch": 0.02, + "learning_rate": 3.4199204252199514e-05, + "loss": 3.5678, + "step": 965120 + }, + { + "epoch": 0.02, + "learning_rate": 3.4190818304688994e-05, + "loss": 3.5778, + "step": 965632 + }, + { + "epoch": 0.02, + "learning_rate": 3.4182432357178473e-05, + "loss": 3.5773, + "step": 966144 + }, + { + "epoch": 0.02, + "learning_rate": 3.4174046409667953e-05, + "loss": 3.5808, + "step": 966656 + }, + { + "epoch": 0.02, + "learning_rate": 3.416567684096116e-05, + "loss": 3.5861, + "step": 967168 + }, + { + "epoch": 0.02, + "learning_rate": 3.415729089345064e-05, + "loss": 3.5796, + "step": 967680 + }, + { + "epoch": 0.02, + "learning_rate": 3.414890494594012e-05, + "loss": 3.5803, + "step": 968192 + }, + { + "epoch": 0.02, + "learning_rate": 3.41405189984296e-05, + "loss": 3.5794, + "step": 968704 + }, + { + "epoch": 0.02, + "learning_rate": 3.413214942972282e-05, + "loss": 3.5806, + "step": 969216 + }, + { + "epoch": 0.02, + "learning_rate": 3.41237634822123e-05, + "loss": 3.5711, + "step": 969728 + }, + { + "epoch": 0.02, + "learning_rate": 3.411537753470178e-05, + "loss": 3.572, + "step": 970240 + }, + { + "epoch": 0.02, + "learning_rate": 3.410699158719125e-05, + "loss": 3.5788, + "step": 970752 + }, + { + "epoch": 0.02, + "learning_rate": 3.409862201848447e-05, + "loss": 3.5785, + "step": 971264 + }, + { + "epoch": 0.02, + "learning_rate": 3.409023607097395e-05, + "loss": 3.5629, + "step": 971776 + }, + { + "epoch": 0.02, + "learning_rate": 3.408185012346343e-05, + "loss": 3.5736, + "step": 972288 + }, + { + "epoch": 0.02, + "learning_rate": 3.40734641759529e-05, + "loss": 3.561, + "step": 972800 + }, + { + "epoch": 0.02, + "learning_rate": 3.4065094607246116e-05, + "loss": 3.5807, + "step": 973312 + }, + { + "epoch": 0.02, + "learning_rate": 3.4056708659735596e-05, + "loss": 3.5742, + "step": 973824 + }, + { + "epoch": 0.02, + "learning_rate": 3.404832271222507e-05, + "loss": 3.5785, + "step": 974336 + }, + { + "epoch": 0.02, + "learning_rate": 3.4039936764714556e-05, + "loss": 3.5814, + "step": 974848 + }, + { + "epoch": 0.02, + "learning_rate": 3.403156719600777e-05, + "loss": 3.5825, + "step": 975360 + }, + { + "epoch": 0.02, + "learning_rate": 3.402318124849725e-05, + "loss": 3.5793, + "step": 975872 + }, + { + "epoch": 0.02, + "learning_rate": 3.4014795300986725e-05, + "loss": 3.5794, + "step": 976384 + }, + { + "epoch": 0.02, + "learning_rate": 3.4006409353476205e-05, + "loss": 3.5841, + "step": 976896 + }, + { + "epoch": 0.02, + "learning_rate": 3.399803978476942e-05, + "loss": 3.5799, + "step": 977408 + }, + { + "epoch": 0.02, + "learning_rate": 3.39896538372589e-05, + "loss": 3.5775, + "step": 977920 + }, + { + "epoch": 0.02, + "learning_rate": 3.3981267889748374e-05, + "loss": 3.5775, + "step": 978432 + }, + { + "epoch": 0.02, + "learning_rate": 3.3972881942237854e-05, + "loss": 3.5775, + "step": 978944 + }, + { + "epoch": 0.02, + "learning_rate": 3.396451237353107e-05, + "loss": 3.575, + "step": 979456 + }, + { + "epoch": 0.02, + "learning_rate": 3.395612642602054e-05, + "loss": 3.5721, + "step": 979968 + }, + { + "epoch": 0.02, + "learning_rate": 3.394774047851002e-05, + "loss": 3.5735, + "step": 980480 + }, + { + "epoch": 0.02, + "learning_rate": 3.393935453099951e-05, + "loss": 3.5595, + "step": 980992 + }, + { + "epoch": 0.02, + "learning_rate": 3.3930984962292726e-05, + "loss": 3.5736, + "step": 981504 + }, + { + "epoch": 0.02, + "learning_rate": 3.39225990147822e-05, + "loss": 3.578, + "step": 982016 + }, + { + "epoch": 0.02, + "learning_rate": 3.391421306727168e-05, + "loss": 3.5797, + "step": 982528 + }, + { + "epoch": 0.02, + "learning_rate": 3.390582711976116e-05, + "loss": 3.5822, + "step": 983040 + }, + { + "epoch": 0.02, + "learning_rate": 3.3897457551054375e-05, + "loss": 3.5686, + "step": 983552 + }, + { + "epoch": 0.02, + "learning_rate": 3.388907160354385e-05, + "loss": 3.5827, + "step": 984064 + }, + { + "epoch": 0.02, + "learning_rate": 3.388068565603333e-05, + "loss": 3.5821, + "step": 984576 + }, + { + "epoch": 0.02, + "learning_rate": 3.387229970852281e-05, + "loss": 3.5776, + "step": 985088 + }, + { + "epoch": 0.02, + "learning_rate": 3.386393013981602e-05, + "loss": 3.5754, + "step": 985600 + }, + { + "epoch": 0.02, + "learning_rate": 3.38555441923055e-05, + "loss": 3.5754, + "step": 986112 + }, + { + "epoch": 0.02, + "learning_rate": 3.384715824479498e-05, + "loss": 3.5877, + "step": 986624 + }, + { + "epoch": 0.02, + "learning_rate": 3.3838772297284463e-05, + "loss": 3.5827, + "step": 987136 + }, + { + "epoch": 0.02, + "learning_rate": 3.383038634977394e-05, + "loss": 3.5754, + "step": 987648 + }, + { + "epoch": 0.02, + "learning_rate": 3.382201678106715e-05, + "loss": 3.5708, + "step": 988160 + }, + { + "epoch": 0.02, + "learning_rate": 3.381363083355663e-05, + "loss": 3.5767, + "step": 988672 + }, + { + "epoch": 0.02, + "learning_rate": 3.380524488604611e-05, + "loss": 3.5756, + "step": 989184 + }, + { + "epoch": 0.02, + "learning_rate": 3.379685893853559e-05, + "loss": 3.5736, + "step": 989696 + }, + { + "epoch": 0.02, + "learning_rate": 3.37884893698288e-05, + "loss": 3.5784, + "step": 990208 + }, + { + "epoch": 0.02, + "learning_rate": 3.378010342231828e-05, + "loss": 3.5747, + "step": 990720 + }, + { + "epoch": 0.02, + "learning_rate": 3.377171747480776e-05, + "loss": 3.5775, + "step": 991232 + }, + { + "epoch": 0.02, + "learning_rate": 3.376333152729724e-05, + "loss": 3.5763, + "step": 991744 + }, + { + "epoch": 0.03, + "eval_loss": 3.843687057495117, + "eval_runtime": 311.6413, + "eval_samples_per_second": 1224.456, + "eval_steps_per_second": 38.265, + "step": 992160 + }, + { + "epoch": 1.0, + "learning_rate": 3.375496195859045e-05, + "loss": 3.5749, + "step": 992256 + }, + { + "epoch": 1.0, + "learning_rate": 3.374657601107993e-05, + "loss": 3.5589, + "step": 992768 + }, + { + "epoch": 1.0, + "learning_rate": 3.373819006356942e-05, + "loss": 3.5688, + "step": 993280 + }, + { + "epoch": 1.0, + "learning_rate": 3.37298041160589e-05, + "loss": 3.58, + "step": 993792 + }, + { + "epoch": 1.0, + "learning_rate": 3.372141816854838e-05, + "loss": 3.5766, + "step": 994304 + }, + { + "epoch": 1.0, + "learning_rate": 3.3713048599841586e-05, + "loss": 3.5817, + "step": 994816 + }, + { + "epoch": 1.0, + "learning_rate": 3.3704662652331066e-05, + "loss": 3.5692, + "step": 995328 + }, + { + "epoch": 1.0, + "learning_rate": 3.3696276704820546e-05, + "loss": 3.5724, + "step": 995840 + }, + { + "epoch": 1.0, + "learning_rate": 3.3687890757310026e-05, + "loss": 3.5599, + "step": 996352 + }, + { + "epoch": 1.0, + "learning_rate": 3.3679521188603235e-05, + "loss": 3.5765, + "step": 996864 + }, + { + "epoch": 1.0, + "learning_rate": 3.3671135241092715e-05, + "loss": 3.5712, + "step": 997376 + }, + { + "epoch": 1.0, + "learning_rate": 3.3662749293582195e-05, + "loss": 3.5722, + "step": 997888 + }, + { + "epoch": 1.0, + "learning_rate": 3.3654379724875404e-05, + "loss": 3.583, + "step": 998400 + }, + { + "epoch": 1.0, + "learning_rate": 3.3645993777364884e-05, + "loss": 3.5559, + "step": 998912 + }, + { + "epoch": 1.0, + "learning_rate": 3.3637607829854364e-05, + "loss": 3.5714, + "step": 999424 + }, + { + "epoch": 1.0, + "learning_rate": 3.362922188234385e-05, + "loss": 3.5535, + "step": 999936 + }, + { + "epoch": 1.0, + "learning_rate": 3.362083593483333e-05, + "loss": 3.5733, + "step": 1000448 + }, + { + "epoch": 1.0, + "learning_rate": 3.361244998732281e-05, + "loss": 3.5618, + "step": 1000960 + }, + { + "epoch": 1.0, + "learning_rate": 3.360406403981229e-05, + "loss": 3.5721, + "step": 1001472 + }, + { + "epoch": 1.0, + "learning_rate": 3.359567809230177e-05, + "loss": 3.5628, + "step": 1001984 + }, + { + "epoch": 1.0, + "learning_rate": 3.358730852359498e-05, + "loss": 3.5875, + "step": 1002496 + }, + { + "epoch": 1.0, + "learning_rate": 3.357892257608446e-05, + "loss": 3.5705, + "step": 1003008 + }, + { + "epoch": 1.0, + "learning_rate": 3.357053662857394e-05, + "loss": 3.5717, + "step": 1003520 + }, + { + "epoch": 1.0, + "learning_rate": 3.356215068106342e-05, + "loss": 3.5707, + "step": 1004032 + }, + { + "epoch": 1.0, + "learning_rate": 3.35537647335529e-05, + "loss": 3.5788, + "step": 1004544 + }, + { + "epoch": 1.0, + "learning_rate": 3.354539516484611e-05, + "loss": 3.5713, + "step": 1005056 + }, + { + "epoch": 1.0, + "learning_rate": 3.353700921733559e-05, + "loss": 3.5585, + "step": 1005568 + }, + { + "epoch": 1.0, + "learning_rate": 3.352862326982507e-05, + "loss": 3.5732, + "step": 1006080 + }, + { + "epoch": 1.0, + "learning_rate": 3.352023732231455e-05, + "loss": 3.5582, + "step": 1006592 + }, + { + "epoch": 1.0, + "learning_rate": 3.3511867753607764e-05, + "loss": 3.5619, + "step": 1007104 + }, + { + "epoch": 1.01, + "learning_rate": 3.3503481806097244e-05, + "loss": 3.5702, + "step": 1007616 + }, + { + "epoch": 1.01, + "learning_rate": 3.3495095858586724e-05, + "loss": 3.568, + "step": 1008128 + }, + { + "epoch": 1.01, + "learning_rate": 3.3486709911076204e-05, + "loss": 3.5691, + "step": 1008640 + }, + { + "epoch": 1.01, + "learning_rate": 3.347834034236941e-05, + "loss": 3.5806, + "step": 1009152 + }, + { + "epoch": 1.01, + "learning_rate": 3.346995439485889e-05, + "loss": 3.565, + "step": 1009664 + }, + { + "epoch": 1.01, + "learning_rate": 3.346156844734837e-05, + "loss": 3.5725, + "step": 1010176 + }, + { + "epoch": 1.01, + "learning_rate": 3.345318249983785e-05, + "loss": 3.5739, + "step": 1010688 + }, + { + "epoch": 1.01, + "learning_rate": 3.3444796552327326e-05, + "loss": 3.563, + "step": 1011200 + }, + { + "epoch": 1.01, + "learning_rate": 3.343642698362054e-05, + "loss": 3.5698, + "step": 1011712 + }, + { + "epoch": 1.01, + "learning_rate": 3.342804103611002e-05, + "loss": 3.564, + "step": 1012224 + }, + { + "epoch": 1.01, + "learning_rate": 3.34196550885995e-05, + "loss": 3.5594, + "step": 1012736 + }, + { + "epoch": 1.01, + "learning_rate": 3.341128551989272e-05, + "loss": 3.5705, + "step": 1013248 + }, + { + "epoch": 1.01, + "learning_rate": 3.34028995723822e-05, + "loss": 3.5805, + "step": 1013760 + }, + { + "epoch": 1.01, + "learning_rate": 3.339451362487168e-05, + "loss": 3.5641, + "step": 1014272 + }, + { + "epoch": 1.01, + "learning_rate": 3.338612767736115e-05, + "loss": 3.5728, + "step": 1014784 + }, + { + "epoch": 1.01, + "learning_rate": 3.337775810865437e-05, + "loss": 3.5737, + "step": 1015296 + }, + { + "epoch": 1.01, + "learning_rate": 3.336937216114385e-05, + "loss": 3.5665, + "step": 1015808 + }, + { + "epoch": 1.01, + "learning_rate": 3.336098621363333e-05, + "loss": 3.5717, + "step": 1016320 + }, + { + "epoch": 1.01, + "learning_rate": 3.33526002661228e-05, + "loss": 3.539, + "step": 1016832 + }, + { + "epoch": 1.01, + "learning_rate": 3.334421431861228e-05, + "loss": 3.572, + "step": 1017344 + }, + { + "epoch": 1.01, + "learning_rate": 3.3335844749905496e-05, + "loss": 3.5656, + "step": 1017856 + }, + { + "epoch": 1.01, + "learning_rate": 3.3327458802394976e-05, + "loss": 3.5754, + "step": 1018368 + }, + { + "epoch": 1.01, + "learning_rate": 3.3319072854884456e-05, + "loss": 3.5607, + "step": 1018880 + }, + { + "epoch": 1.01, + "learning_rate": 3.3310686907373936e-05, + "loss": 3.55, + "step": 1019392 + }, + { + "epoch": 1.01, + "learning_rate": 3.330231733866715e-05, + "loss": 3.5492, + "step": 1019904 + }, + { + "epoch": 1.01, + "learning_rate": 3.3293931391156625e-05, + "loss": 3.5512, + "step": 1020416 + }, + { + "epoch": 1.01, + "learning_rate": 3.3285545443646105e-05, + "loss": 3.5753, + "step": 1020928 + }, + { + "epoch": 1.01, + "learning_rate": 3.3277159496135585e-05, + "loss": 3.5508, + "step": 1021440 + }, + { + "epoch": 1.01, + "learning_rate": 3.32687899274288e-05, + "loss": 3.574, + "step": 1021952 + }, + { + "epoch": 1.01, + "learning_rate": 3.3260403979918274e-05, + "loss": 3.5641, + "step": 1022464 + }, + { + "epoch": 1.01, + "learning_rate": 3.3252018032407754e-05, + "loss": 3.557, + "step": 1022976 + }, + { + "epoch": 1.01, + "learning_rate": 3.3243632084897234e-05, + "loss": 3.5667, + "step": 1023488 + }, + { + "epoch": 1.01, + "learning_rate": 3.323526251619045e-05, + "loss": 3.5512, + "step": 1024000 + }, + { + "epoch": 1.01, + "learning_rate": 3.322687656867993e-05, + "loss": 3.5536, + "step": 1024512 + }, + { + "epoch": 1.01, + "learning_rate": 3.321849062116941e-05, + "loss": 3.5549, + "step": 1025024 + }, + { + "epoch": 1.01, + "learning_rate": 3.321010467365889e-05, + "loss": 3.5706, + "step": 1025536 + }, + { + "epoch": 1.01, + "learning_rate": 3.32017351049521e-05, + "loss": 3.5547, + "step": 1026048 + }, + { + "epoch": 1.01, + "learning_rate": 3.319334915744158e-05, + "loss": 3.5591, + "step": 1026560 + }, + { + "epoch": 1.01, + "learning_rate": 3.318496320993106e-05, + "loss": 3.5486, + "step": 1027072 + }, + { + "epoch": 1.01, + "learning_rate": 3.317657726242054e-05, + "loss": 3.5621, + "step": 1027584 + }, + { + "epoch": 1.01, + "learning_rate": 3.316820769371375e-05, + "loss": 3.5721, + "step": 1028096 + }, + { + "epoch": 1.01, + "learning_rate": 3.315982174620323e-05, + "loss": 3.5681, + "step": 1028608 + }, + { + "epoch": 1.01, + "learning_rate": 3.315143579869271e-05, + "loss": 3.5674, + "step": 1029120 + }, + { + "epoch": 1.01, + "learning_rate": 3.314304985118219e-05, + "loss": 3.5703, + "step": 1029632 + }, + { + "epoch": 1.01, + "learning_rate": 3.31346802824754e-05, + "loss": 3.5834, + "step": 1030144 + }, + { + "epoch": 1.01, + "learning_rate": 3.312629433496488e-05, + "loss": 3.5671, + "step": 1030656 + }, + { + "epoch": 1.01, + "learning_rate": 3.311790838745436e-05, + "loss": 3.5741, + "step": 1031168 + }, + { + "epoch": 1.01, + "learning_rate": 3.310952243994384e-05, + "loss": 3.5588, + "step": 1031680 + }, + { + "epoch": 1.01, + "learning_rate": 3.310115287123705e-05, + "loss": 3.5622, + "step": 1032192 + }, + { + "epoch": 1.01, + "learning_rate": 3.309276692372653e-05, + "loss": 3.5617, + "step": 1032704 + }, + { + "epoch": 1.01, + "learning_rate": 3.308438097621601e-05, + "loss": 3.5596, + "step": 1033216 + }, + { + "epoch": 1.01, + "learning_rate": 3.307599502870549e-05, + "loss": 3.5722, + "step": 1033728 + }, + { + "epoch": 1.01, + "learning_rate": 3.30676254599987e-05, + "loss": 3.5711, + "step": 1034240 + }, + { + "epoch": 1.01, + "learning_rate": 3.305923951248818e-05, + "loss": 3.5667, + "step": 1034752 + }, + { + "epoch": 1.01, + "learning_rate": 3.305085356497766e-05, + "loss": 3.5483, + "step": 1035264 + }, + { + "epoch": 1.01, + "learning_rate": 3.304246761746714e-05, + "loss": 3.5527, + "step": 1035776 + }, + { + "epoch": 1.01, + "learning_rate": 3.303409804876036e-05, + "loss": 3.5703, + "step": 1036288 + }, + { + "epoch": 1.01, + "learning_rate": 3.302571210124984e-05, + "loss": 3.5643, + "step": 1036800 + }, + { + "epoch": 1.01, + "learning_rate": 3.301732615373932e-05, + "loss": 3.5593, + "step": 1037312 + }, + { + "epoch": 1.01, + "learning_rate": 3.30089402062288e-05, + "loss": 3.5632, + "step": 1037824 + }, + { + "epoch": 1.02, + "learning_rate": 3.300055425871828e-05, + "loss": 3.5648, + "step": 1038336 + }, + { + "epoch": 1.02, + "learning_rate": 3.2992184690011486e-05, + "loss": 3.5583, + "step": 1038848 + }, + { + "epoch": 1.02, + "learning_rate": 3.2983798742500966e-05, + "loss": 3.5604, + "step": 1039360 + }, + { + "epoch": 1.02, + "learning_rate": 3.2975412794990446e-05, + "loss": 3.5706, + "step": 1039872 + }, + { + "epoch": 1.02, + "learning_rate": 3.2967026847479926e-05, + "loss": 3.5678, + "step": 1040384 + }, + { + "epoch": 1.02, + "learning_rate": 3.2958657278773135e-05, + "loss": 3.5681, + "step": 1040896 + }, + { + "epoch": 1.02, + "learning_rate": 3.2950271331262615e-05, + "loss": 3.5519, + "step": 1041408 + }, + { + "epoch": 1.02, + "learning_rate": 3.2941885383752095e-05, + "loss": 3.559, + "step": 1041920 + }, + { + "epoch": 1.02, + "learning_rate": 3.293351581504531e-05, + "loss": 3.5626, + "step": 1042432 + }, + { + "epoch": 1.02, + "learning_rate": 3.292512986753479e-05, + "loss": 3.5663, + "step": 1042944 + }, + { + "epoch": 1.02, + "learning_rate": 3.291674392002427e-05, + "loss": 3.5679, + "step": 1043456 + }, + { + "epoch": 1.02, + "learning_rate": 3.290835797251375e-05, + "loss": 3.5651, + "step": 1043968 + }, + { + "epoch": 1.02, + "learning_rate": 3.289998840380696e-05, + "loss": 3.5628, + "step": 1044480 + }, + { + "epoch": 1.02, + "learning_rate": 3.289160245629644e-05, + "loss": 3.5611, + "step": 1044992 + }, + { + "epoch": 1.02, + "learning_rate": 3.288321650878592e-05, + "loss": 3.5655, + "step": 1045504 + }, + { + "epoch": 1.02, + "learning_rate": 3.28748305612754e-05, + "loss": 3.5541, + "step": 1046016 + }, + { + "epoch": 1.02, + "learning_rate": 3.286644461376488e-05, + "loss": 3.5519, + "step": 1046528 + }, + { + "epoch": 1.02, + "learning_rate": 3.285807504505809e-05, + "loss": 3.5642, + "step": 1047040 + }, + { + "epoch": 1.02, + "learning_rate": 3.284968909754757e-05, + "loss": 3.563, + "step": 1047552 + }, + { + "epoch": 1.02, + "learning_rate": 3.284130315003705e-05, + "loss": 3.5464, + "step": 1048064 + }, + { + "epoch": 1.02, + "learning_rate": 3.283291720252653e-05, + "loss": 3.5541, + "step": 1048576 + }, + { + "epoch": 1.02, + "learning_rate": 3.2824547633819744e-05, + "loss": 3.5476, + "step": 1049088 + }, + { + "epoch": 1.02, + "learning_rate": 3.2816161686309224e-05, + "loss": 3.56, + "step": 1049600 + }, + { + "epoch": 1.02, + "learning_rate": 3.2807775738798704e-05, + "loss": 3.558, + "step": 1050112 + }, + { + "epoch": 1.02, + "learning_rate": 3.2799389791288184e-05, + "loss": 3.5586, + "step": 1050624 + }, + { + "epoch": 1.02, + "learning_rate": 3.279102022258139e-05, + "loss": 3.5642, + "step": 1051136 + }, + { + "epoch": 1.02, + "learning_rate": 3.278263427507087e-05, + "loss": 3.5679, + "step": 1051648 + }, + { + "epoch": 1.02, + "learning_rate": 3.277424832756035e-05, + "loss": 3.5597, + "step": 1052160 + }, + { + "epoch": 1.02, + "learning_rate": 3.276586238004983e-05, + "loss": 3.5626, + "step": 1052672 + }, + { + "epoch": 1.02, + "learning_rate": 3.275747643253931e-05, + "loss": 3.5695, + "step": 1053184 + }, + { + "epoch": 1.02, + "learning_rate": 3.274910686383252e-05, + "loss": 3.5602, + "step": 1053696 + }, + { + "epoch": 1.02, + "learning_rate": 3.2740720916322e-05, + "loss": 3.5573, + "step": 1054208 + }, + { + "epoch": 1.02, + "learning_rate": 3.273233496881148e-05, + "loss": 3.5636, + "step": 1054720 + }, + { + "epoch": 1.02, + "learning_rate": 3.27239654001047e-05, + "loss": 3.5612, + "step": 1055232 + }, + { + "epoch": 1.02, + "learning_rate": 3.271557945259418e-05, + "loss": 3.5556, + "step": 1055744 + }, + { + "epoch": 1.02, + "learning_rate": 3.270719350508366e-05, + "loss": 3.552, + "step": 1056256 + }, + { + "epoch": 1.02, + "learning_rate": 3.269880755757314e-05, + "loss": 3.5606, + "step": 1056768 + }, + { + "epoch": 1.02, + "learning_rate": 3.269043798886635e-05, + "loss": 3.5506, + "step": 1057280 + }, + { + "epoch": 1.02, + "learning_rate": 3.268205204135583e-05, + "loss": 3.5567, + "step": 1057792 + }, + { + "epoch": 1.02, + "learning_rate": 3.267366609384531e-05, + "loss": 3.5517, + "step": 1058304 + }, + { + "epoch": 1.02, + "learning_rate": 3.266528014633479e-05, + "loss": 3.5645, + "step": 1058816 + }, + { + "epoch": 1.02, + "learning_rate": 3.2656894198824267e-05, + "loss": 3.5658, + "step": 1059328 + }, + { + "epoch": 1.02, + "learning_rate": 3.2648524630117476e-05, + "loss": 3.5537, + "step": 1059840 + }, + { + "epoch": 1.02, + "learning_rate": 3.2640138682606956e-05, + "loss": 3.5636, + "step": 1060352 + }, + { + "epoch": 1.02, + "learning_rate": 3.2631752735096436e-05, + "loss": 3.5643, + "step": 1060864 + }, + { + "epoch": 1.02, + "learning_rate": 3.2623366787585916e-05, + "loss": 3.5658, + "step": 1061376 + }, + { + "epoch": 1.02, + "learning_rate": 3.261499721887913e-05, + "loss": 3.559, + "step": 1061888 + }, + { + "epoch": 1.02, + "learning_rate": 3.260661127136861e-05, + "loss": 3.5544, + "step": 1062400 + }, + { + "epoch": 1.02, + "learning_rate": 3.259822532385809e-05, + "loss": 3.575, + "step": 1062912 + }, + { + "epoch": 1.02, + "learning_rate": 3.258983937634757e-05, + "loss": 3.5586, + "step": 1063424 + }, + { + "epoch": 1.02, + "learning_rate": 3.258146980764078e-05, + "loss": 3.5663, + "step": 1063936 + }, + { + "epoch": 1.02, + "learning_rate": 3.257308386013026e-05, + "loss": 3.5562, + "step": 1064448 + }, + { + "epoch": 1.02, + "learning_rate": 3.256469791261974e-05, + "loss": 3.5608, + "step": 1064960 + }, + { + "epoch": 1.02, + "learning_rate": 3.255631196510922e-05, + "loss": 3.5557, + "step": 1065472 + }, + { + "epoch": 1.02, + "learning_rate": 3.254794239640243e-05, + "loss": 3.5561, + "step": 1065984 + }, + { + "epoch": 1.02, + "learning_rate": 3.253955644889191e-05, + "loss": 3.5659, + "step": 1066496 + }, + { + "epoch": 1.02, + "learning_rate": 3.253117050138139e-05, + "loss": 3.5598, + "step": 1067008 + }, + { + "epoch": 1.02, + "learning_rate": 3.252278455387087e-05, + "loss": 3.5629, + "step": 1067520 + }, + { + "epoch": 1.02, + "learning_rate": 3.2514414985164085e-05, + "loss": 3.5566, + "step": 1068032 + }, + { + "epoch": 1.03, + "eval_loss": 3.8448195457458496, + "eval_runtime": 307.7868, + "eval_samples_per_second": 1239.79, + "eval_steps_per_second": 38.744, + "step": 1068480 + }, + { + "epoch": 0.0, + "learning_rate": 3.2506029037653565e-05, + "loss": 3.5393, + "step": 1068544 + }, + { + "epoch": 0.0, + "learning_rate": 3.2497643090143045e-05, + "loss": 3.5476, + "step": 1069056 + }, + { + "epoch": 0.0, + "learning_rate": 3.2489257142632525e-05, + "loss": 3.5516, + "step": 1069568 + }, + { + "epoch": 0.0, + "learning_rate": 3.2480871195122e-05, + "loss": 3.5641, + "step": 1070080 + }, + { + "epoch": 0.0, + "learning_rate": 3.2472501626415214e-05, + "loss": 3.5614, + "step": 1070592 + }, + { + "epoch": 0.0, + "learning_rate": 3.2464115678904694e-05, + "loss": 3.5674, + "step": 1071104 + }, + { + "epoch": 0.0, + "learning_rate": 3.2455729731394174e-05, + "loss": 3.5491, + "step": 1071616 + }, + { + "epoch": 0.0, + "learning_rate": 3.244734378388365e-05, + "loss": 3.5548, + "step": 1072128 + }, + { + "epoch": 0.0, + "learning_rate": 3.243897421517686e-05, + "loss": 3.5455, + "step": 1072640 + }, + { + "epoch": 0.0, + "learning_rate": 3.243058826766634e-05, + "loss": 3.5575, + "step": 1073152 + }, + { + "epoch": 0.0, + "learning_rate": 3.242220232015582e-05, + "loss": 3.5577, + "step": 1073664 + }, + { + "epoch": 0.0, + "learning_rate": 3.24138163726453e-05, + "loss": 3.5567, + "step": 1074176 + }, + { + "epoch": 0.0, + "learning_rate": 3.240544680393852e-05, + "loss": 3.5644, + "step": 1074688 + }, + { + "epoch": 0.0, + "learning_rate": 3.2397060856428e-05, + "loss": 3.5425, + "step": 1075200 + }, + { + "epoch": 0.0, + "learning_rate": 3.238867490891747e-05, + "loss": 3.5485, + "step": 1075712 + }, + { + "epoch": 0.0, + "learning_rate": 3.238028896140695e-05, + "loss": 3.5419, + "step": 1076224 + }, + { + "epoch": 0.0, + "learning_rate": 3.237190301389643e-05, + "loss": 3.5568, + "step": 1076736 + }, + { + "epoch": 0.0, + "learning_rate": 3.236353344518965e-05, + "loss": 3.545, + "step": 1077248 + }, + { + "epoch": 0.0, + "learning_rate": 3.235514749767912e-05, + "loss": 3.556, + "step": 1077760 + }, + { + "epoch": 0.0, + "learning_rate": 3.23467615501686e-05, + "loss": 3.5481, + "step": 1078272 + }, + { + "epoch": 0.0, + "learning_rate": 3.233837560265808e-05, + "loss": 3.5696, + "step": 1078784 + }, + { + "epoch": 0.0, + "learning_rate": 3.2330006033951297e-05, + "loss": 3.5544, + "step": 1079296 + }, + { + "epoch": 0.0, + "learning_rate": 3.2321620086440777e-05, + "loss": 3.5527, + "step": 1079808 + }, + { + "epoch": 0.0, + "learning_rate": 3.2313234138930256e-05, + "loss": 3.5556, + "step": 1080320 + }, + { + "epoch": 0.0, + "learning_rate": 3.2304848191419736e-05, + "loss": 3.5639, + "step": 1080832 + }, + { + "epoch": 0.0, + "learning_rate": 3.2296478622712946e-05, + "loss": 3.5555, + "step": 1081344 + }, + { + "epoch": 0.0, + "learning_rate": 3.2288092675202425e-05, + "loss": 3.5473, + "step": 1081856 + }, + { + "epoch": 0.0, + "learning_rate": 3.2279706727691905e-05, + "loss": 3.5558, + "step": 1082368 + }, + { + "epoch": 0.0, + "learning_rate": 3.2271320780181385e-05, + "loss": 3.5403, + "step": 1082880 + }, + { + "epoch": 0.0, + "learning_rate": 3.2262951211474595e-05, + "loss": 3.5442, + "step": 1083392 + }, + { + "epoch": 0.01, + "learning_rate": 3.2254565263964074e-05, + "loss": 3.5542, + "step": 1083904 + }, + { + "epoch": 0.01, + "learning_rate": 3.2246179316453554e-05, + "loss": 3.5506, + "step": 1084416 + }, + { + "epoch": 0.01, + "learning_rate": 3.2237793368943034e-05, + "loss": 3.5541, + "step": 1084928 + }, + { + "epoch": 0.01, + "learning_rate": 3.2229407421432514e-05, + "loss": 3.5628, + "step": 1085440 + }, + { + "epoch": 0.01, + "learning_rate": 3.222103785272573e-05, + "loss": 3.5504, + "step": 1085952 + }, + { + "epoch": 0.01, + "learning_rate": 3.221265190521521e-05, + "loss": 3.5555, + "step": 1086464 + }, + { + "epoch": 0.01, + "learning_rate": 3.220426595770469e-05, + "loss": 3.5562, + "step": 1086976 + }, + { + "epoch": 0.01, + "learning_rate": 3.219588001019417e-05, + "loss": 3.5465, + "step": 1087488 + }, + { + "epoch": 0.01, + "learning_rate": 3.218751044148738e-05, + "loss": 3.5583, + "step": 1088000 + }, + { + "epoch": 0.01, + "learning_rate": 3.217912449397686e-05, + "loss": 3.5467, + "step": 1088512 + }, + { + "epoch": 0.01, + "learning_rate": 3.217073854646634e-05, + "loss": 3.5444, + "step": 1089024 + }, + { + "epoch": 0.01, + "learning_rate": 3.216235259895582e-05, + "loss": 3.5519, + "step": 1089536 + }, + { + "epoch": 0.01, + "learning_rate": 3.215398303024903e-05, + "loss": 3.5648, + "step": 1090048 + }, + { + "epoch": 0.01, + "learning_rate": 3.214559708273851e-05, + "loss": 3.5469, + "step": 1090560 + }, + { + "epoch": 0.01, + "learning_rate": 3.213721113522799e-05, + "loss": 3.5614, + "step": 1091072 + }, + { + "epoch": 0.01, + "learning_rate": 3.2128841566521204e-05, + "loss": 3.5518, + "step": 1091584 + }, + { + "epoch": 0.01, + "learning_rate": 3.2120455619010684e-05, + "loss": 3.5534, + "step": 1092096 + }, + { + "epoch": 0.01, + "learning_rate": 3.2112069671500164e-05, + "loss": 3.5541, + "step": 1092608 + }, + { + "epoch": 0.01, + "learning_rate": 3.2103683723989644e-05, + "loss": 3.5238, + "step": 1093120 + }, + { + "epoch": 0.01, + "learning_rate": 3.2095297776479124e-05, + "loss": 3.5509, + "step": 1093632 + }, + { + "epoch": 0.01, + "learning_rate": 3.208692820777233e-05, + "loss": 3.5564, + "step": 1094144 + }, + { + "epoch": 0.01, + "learning_rate": 3.207854226026181e-05, + "loss": 3.5546, + "step": 1094656 + }, + { + "epoch": 0.01, + "learning_rate": 3.207015631275129e-05, + "loss": 3.5418, + "step": 1095168 + }, + { + "epoch": 0.01, + "learning_rate": 3.206177036524077e-05, + "loss": 3.5366, + "step": 1095680 + }, + { + "epoch": 0.01, + "learning_rate": 3.205340079653398e-05, + "loss": 3.534, + "step": 1096192 + }, + { + "epoch": 0.01, + "learning_rate": 3.204501484902346e-05, + "loss": 3.5344, + "step": 1096704 + }, + { + "epoch": 0.01, + "learning_rate": 3.203662890151294e-05, + "loss": 3.5624, + "step": 1097216 + }, + { + "epoch": 0.01, + "learning_rate": 3.202824295400242e-05, + "loss": 3.5325, + "step": 1097728 + }, + { + "epoch": 0.01, + "learning_rate": 3.201987338529564e-05, + "loss": 3.5574, + "step": 1098240 + }, + { + "epoch": 0.01, + "learning_rate": 3.201148743778512e-05, + "loss": 3.5493, + "step": 1098752 + }, + { + "epoch": 0.01, + "learning_rate": 3.20031014902746e-05, + "loss": 3.5376, + "step": 1099264 + }, + { + "epoch": 0.01, + "learning_rate": 3.199471554276408e-05, + "loss": 3.5531, + "step": 1099776 + }, + { + "epoch": 0.01, + "learning_rate": 3.1986345974057287e-05, + "loss": 3.5397, + "step": 1100288 + }, + { + "epoch": 0.01, + "learning_rate": 3.1977960026546766e-05, + "loss": 3.5381, + "step": 1100800 + }, + { + "epoch": 0.01, + "learning_rate": 3.1969574079036246e-05, + "loss": 3.5345, + "step": 1101312 + }, + { + "epoch": 0.01, + "learning_rate": 3.1961188131525726e-05, + "loss": 3.5549, + "step": 1101824 + }, + { + "epoch": 0.01, + "learning_rate": 3.1952818562818935e-05, + "loss": 3.5423, + "step": 1102336 + }, + { + "epoch": 0.01, + "learning_rate": 3.1944432615308415e-05, + "loss": 3.5409, + "step": 1102848 + }, + { + "epoch": 0.01, + "learning_rate": 3.1936046667797895e-05, + "loss": 3.537, + "step": 1103360 + }, + { + "epoch": 0.01, + "learning_rate": 3.1927660720287375e-05, + "loss": 3.5443, + "step": 1103872 + }, + { + "epoch": 0.01, + "learning_rate": 3.191929115158059e-05, + "loss": 3.5557, + "step": 1104384 + }, + { + "epoch": 0.01, + "learning_rate": 3.191090520407007e-05, + "loss": 3.552, + "step": 1104896 + }, + { + "epoch": 0.01, + "learning_rate": 3.190251925655955e-05, + "loss": 3.5499, + "step": 1105408 + }, + { + "epoch": 0.01, + "learning_rate": 3.189413330904903e-05, + "loss": 3.5549, + "step": 1105920 + }, + { + "epoch": 0.01, + "learning_rate": 3.188576374034224e-05, + "loss": 3.5655, + "step": 1106432 + }, + { + "epoch": 0.01, + "learning_rate": 3.187737779283172e-05, + "loss": 3.5516, + "step": 1106944 + }, + { + "epoch": 0.01, + "learning_rate": 3.18689918453212e-05, + "loss": 3.5572, + "step": 1107456 + }, + { + "epoch": 0.01, + "learning_rate": 3.186060589781068e-05, + "loss": 3.5469, + "step": 1107968 + }, + { + "epoch": 0.01, + "learning_rate": 3.185223632910389e-05, + "loss": 3.5474, + "step": 1108480 + }, + { + "epoch": 0.01, + "learning_rate": 3.184385038159337e-05, + "loss": 3.5461, + "step": 1108992 + }, + { + "epoch": 0.01, + "learning_rate": 3.183546443408285e-05, + "loss": 3.5422, + "step": 1109504 + }, + { + "epoch": 0.01, + "learning_rate": 3.182707848657233e-05, + "loss": 3.5595, + "step": 1110016 + }, + { + "epoch": 0.01, + "learning_rate": 3.1818708917865545e-05, + "loss": 3.5586, + "step": 1110528 + }, + { + "epoch": 0.01, + "learning_rate": 3.1810322970355025e-05, + "loss": 3.5514, + "step": 1111040 + }, + { + "epoch": 0.01, + "learning_rate": 3.1801937022844505e-05, + "loss": 3.5294, + "step": 1111552 + }, + { + "epoch": 0.01, + "learning_rate": 3.1793551075333985e-05, + "loss": 3.538, + "step": 1112064 + }, + { + "epoch": 0.01, + "learning_rate": 3.1785181506627194e-05, + "loss": 3.5528, + "step": 1112576 + }, + { + "epoch": 0.01, + "learning_rate": 3.1776795559116674e-05, + "loss": 3.5518, + "step": 1113088 + }, + { + "epoch": 0.01, + "learning_rate": 3.1768409611606154e-05, + "loss": 3.5402, + "step": 1113600 + }, + { + "epoch": 0.01, + "learning_rate": 3.1760023664095634e-05, + "loss": 3.5513, + "step": 1114112 + }, + { + "epoch": 0.02, + "learning_rate": 3.175165409538884e-05, + "loss": 3.5474, + "step": 1114624 + }, + { + "epoch": 0.02, + "learning_rate": 3.174328452668205e-05, + "loss": 3.541, + "step": 1115136 + }, + { + "epoch": 0.02, + "learning_rate": 3.173489857917153e-05, + "loss": 3.541, + "step": 1115648 + }, + { + "epoch": 0.02, + "learning_rate": 3.172651263166101e-05, + "loss": 3.5558, + "step": 1116160 + }, + { + "epoch": 0.02, + "learning_rate": 3.17181266841505e-05, + "loss": 3.5459, + "step": 1116672 + }, + { + "epoch": 0.02, + "learning_rate": 3.170974073663998e-05, + "loss": 3.5563, + "step": 1117184 + }, + { + "epoch": 0.02, + "learning_rate": 3.170135478912946e-05, + "loss": 3.5351, + "step": 1117696 + }, + { + "epoch": 0.02, + "learning_rate": 3.169296884161894e-05, + "loss": 3.5414, + "step": 1118208 + }, + { + "epoch": 0.02, + "learning_rate": 3.168458289410842e-05, + "loss": 3.5497, + "step": 1118720 + }, + { + "epoch": 0.02, + "learning_rate": 3.167621332540163e-05, + "loss": 3.5496, + "step": 1119232 + }, + { + "epoch": 0.02, + "learning_rate": 3.166782737789111e-05, + "loss": 3.5529, + "step": 1119744 + }, + { + "epoch": 0.02, + "learning_rate": 3.165944143038059e-05, + "loss": 3.549, + "step": 1120256 + }, + { + "epoch": 0.02, + "learning_rate": 3.165105548287007e-05, + "loss": 3.5467, + "step": 1120768 + }, + { + "epoch": 0.02, + "learning_rate": 3.1642685914163276e-05, + "loss": 3.5476, + "step": 1121280 + }, + { + "epoch": 0.02, + "learning_rate": 3.1634316345456486e-05, + "loss": 3.5514, + "step": 1121792 + }, + { + "epoch": 0.02, + "learning_rate": 3.1625930397945965e-05, + "loss": 3.5321, + "step": 1122304 + }, + { + "epoch": 0.02, + "learning_rate": 3.161754445043545e-05, + "loss": 3.5407, + "step": 1122816 + }, + { + "epoch": 0.02, + "learning_rate": 3.160915850292493e-05, + "loss": 3.5439, + "step": 1123328 + }, + { + "epoch": 0.02, + "learning_rate": 3.160077255541441e-05, + "loss": 3.5459, + "step": 1123840 + }, + { + "epoch": 0.02, + "learning_rate": 3.159238660790389e-05, + "loss": 3.5334, + "step": 1124352 + }, + { + "epoch": 0.02, + "learning_rate": 3.158400066039337e-05, + "loss": 3.537, + "step": 1124864 + }, + { + "epoch": 0.02, + "learning_rate": 3.157561471288285e-05, + "loss": 3.5295, + "step": 1125376 + }, + { + "epoch": 0.02, + "learning_rate": 3.156724514417606e-05, + "loss": 3.5476, + "step": 1125888 + }, + { + "epoch": 0.02, + "learning_rate": 3.155885919666554e-05, + "loss": 3.5409, + "step": 1126400 + }, + { + "epoch": 0.02, + "learning_rate": 3.155047324915502e-05, + "loss": 3.5445, + "step": 1126912 + }, + { + "epoch": 0.02, + "learning_rate": 3.1542087301644494e-05, + "loss": 3.5495, + "step": 1127424 + }, + { + "epoch": 0.02, + "learning_rate": 3.153371773293771e-05, + "loss": 3.552, + "step": 1127936 + }, + { + "epoch": 0.02, + "learning_rate": 3.152533178542719e-05, + "loss": 3.5461, + "step": 1128448 + }, + { + "epoch": 0.02, + "learning_rate": 3.151694583791667e-05, + "loss": 3.5446, + "step": 1128960 + }, + { + "epoch": 0.02, + "learning_rate": 3.150855989040615e-05, + "loss": 3.5546, + "step": 1129472 + }, + { + "epoch": 0.02, + "learning_rate": 3.1500190321699366e-05, + "loss": 3.544, + "step": 1129984 + }, + { + "epoch": 0.02, + "learning_rate": 3.1491804374188846e-05, + "loss": 3.5382, + "step": 1130496 + }, + { + "epoch": 0.02, + "learning_rate": 3.1483418426678326e-05, + "loss": 3.5472, + "step": 1131008 + }, + { + "epoch": 0.02, + "learning_rate": 3.14750324791678e-05, + "loss": 3.5458, + "step": 1131520 + }, + { + "epoch": 0.02, + "learning_rate": 3.1466662910461015e-05, + "loss": 3.5467, + "step": 1132032 + }, + { + "epoch": 0.02, + "learning_rate": 3.1458276962950495e-05, + "loss": 3.5336, + "step": 1132544 + }, + { + "epoch": 0.02, + "learning_rate": 3.144989101543997e-05, + "loss": 3.5468, + "step": 1133056 + }, + { + "epoch": 0.02, + "learning_rate": 3.1441521446733184e-05, + "loss": 3.5345, + "step": 1133568 + }, + { + "epoch": 0.02, + "learning_rate": 3.1433135499222664e-05, + "loss": 3.5421, + "step": 1134080 + }, + { + "epoch": 0.02, + "learning_rate": 3.1424749551712144e-05, + "loss": 3.5336, + "step": 1134592 + }, + { + "epoch": 0.02, + "learning_rate": 3.1416363604201624e-05, + "loss": 3.554, + "step": 1135104 + }, + { + "epoch": 0.02, + "learning_rate": 3.1407977656691104e-05, + "loss": 3.5509, + "step": 1135616 + }, + { + "epoch": 0.02, + "learning_rate": 3.139960808798432e-05, + "loss": 3.5341, + "step": 1136128 + }, + { + "epoch": 0.02, + "learning_rate": 3.13912221404738e-05, + "loss": 3.5517, + "step": 1136640 + }, + { + "epoch": 0.02, + "learning_rate": 3.138283619296327e-05, + "loss": 3.5503, + "step": 1137152 + }, + { + "epoch": 0.02, + "learning_rate": 3.137445024545275e-05, + "loss": 3.5503, + "step": 1137664 + }, + { + "epoch": 0.02, + "learning_rate": 3.136608067674597e-05, + "loss": 3.5447, + "step": 1138176 + }, + { + "epoch": 0.02, + "learning_rate": 3.135769472923544e-05, + "loss": 3.5427, + "step": 1138688 + }, + { + "epoch": 0.02, + "learning_rate": 3.134930878172492e-05, + "loss": 3.5587, + "step": 1139200 + }, + { + "epoch": 0.02, + "learning_rate": 3.13409228342144e-05, + "loss": 3.5423, + "step": 1139712 + }, + { + "epoch": 0.02, + "learning_rate": 3.133255326550762e-05, + "loss": 3.5505, + "step": 1140224 + }, + { + "epoch": 0.02, + "learning_rate": 3.13241673179971e-05, + "loss": 3.5413, + "step": 1140736 + }, + { + "epoch": 0.02, + "learning_rate": 3.131578137048658e-05, + "loss": 3.5442, + "step": 1141248 + }, + { + "epoch": 0.02, + "learning_rate": 3.130739542297606e-05, + "loss": 3.5399, + "step": 1141760 + }, + { + "epoch": 0.02, + "learning_rate": 3.129902585426927e-05, + "loss": 3.5401, + "step": 1142272 + }, + { + "epoch": 0.02, + "learning_rate": 3.1290639906758746e-05, + "loss": 3.5494, + "step": 1142784 + }, + { + "epoch": 0.02, + "learning_rate": 3.1282253959248226e-05, + "loss": 3.5428, + "step": 1143296 + }, + { + "epoch": 0.02, + "learning_rate": 3.127388439054144e-05, + "loss": 3.5505, + "step": 1143808 + }, + { + "epoch": 0.02, + "learning_rate": 3.1265498443030915e-05, + "loss": 3.5413, + "step": 1144320 + }, + { + "epoch": 0.03, + "eval_loss": 3.844851493835449, + "eval_runtime": 303.1176, + "eval_samples_per_second": 1258.888, + "eval_steps_per_second": 39.341, + "step": 1144800 + }, + { + "epoch": 1.0, + "learning_rate": 3.1257112495520395e-05, + "loss": 3.5396, + "step": 1144832 + }, + { + "epoch": 1.0, + "learning_rate": 3.1248726548009875e-05, + "loss": 3.5364, + "step": 1145344 + }, + { + "epoch": 1.0, + "learning_rate": 3.124035697930309e-05, + "loss": 3.5342, + "step": 1145856 + }, + { + "epoch": 1.0, + "learning_rate": 3.1231971031792564e-05, + "loss": 3.5446, + "step": 1146368 + }, + { + "epoch": 1.0, + "learning_rate": 3.122358508428205e-05, + "loss": 3.5429, + "step": 1146880 + }, + { + "epoch": 1.0, + "learning_rate": 3.121519913677153e-05, + "loss": 3.5526, + "step": 1147392 + }, + { + "epoch": 1.0, + "learning_rate": 3.120682956806475e-05, + "loss": 3.5345, + "step": 1147904 + }, + { + "epoch": 1.0, + "learning_rate": 3.119844362055422e-05, + "loss": 3.5381, + "step": 1148416 + }, + { + "epoch": 1.0, + "learning_rate": 3.11900576730437e-05, + "loss": 3.5308, + "step": 1148928 + }, + { + "epoch": 1.0, + "learning_rate": 3.118167172553318e-05, + "loss": 3.5447, + "step": 1149440 + }, + { + "epoch": 1.0, + "learning_rate": 3.117330215682639e-05, + "loss": 3.5366, + "step": 1149952 + }, + { + "epoch": 1.0, + "learning_rate": 3.116491620931587e-05, + "loss": 3.5459, + "step": 1150464 + }, + { + "epoch": 1.0, + "learning_rate": 3.115653026180535e-05, + "loss": 3.5471, + "step": 1150976 + }, + { + "epoch": 1.0, + "learning_rate": 3.114814431429483e-05, + "loss": 3.5306, + "step": 1151488 + }, + { + "epoch": 1.0, + "learning_rate": 3.113977474558804e-05, + "loss": 3.5315, + "step": 1152000 + }, + { + "epoch": 1.0, + "learning_rate": 3.113138879807752e-05, + "loss": 3.5294, + "step": 1152512 + }, + { + "epoch": 1.0, + "learning_rate": 3.1123002850567e-05, + "loss": 3.5389, + "step": 1153024 + }, + { + "epoch": 1.0, + "learning_rate": 3.1114616903056485e-05, + "loss": 3.5336, + "step": 1153536 + }, + { + "epoch": 1.0, + "learning_rate": 3.1106230955545965e-05, + "loss": 3.5425, + "step": 1154048 + }, + { + "epoch": 1.0, + "learning_rate": 3.1097861386839174e-05, + "loss": 3.5319, + "step": 1154560 + }, + { + "epoch": 1.0, + "learning_rate": 3.1089475439328654e-05, + "loss": 3.5525, + "step": 1155072 + }, + { + "epoch": 1.0, + "learning_rate": 3.1081089491818134e-05, + "loss": 3.5366, + "step": 1155584 + }, + { + "epoch": 1.0, + "learning_rate": 3.1072703544307614e-05, + "loss": 3.5408, + "step": 1156096 + }, + { + "epoch": 1.0, + "learning_rate": 3.106433397560082e-05, + "loss": 3.54, + "step": 1156608 + }, + { + "epoch": 1.0, + "learning_rate": 3.10559480280903e-05, + "loss": 3.5475, + "step": 1157120 + }, + { + "epoch": 1.0, + "learning_rate": 3.104756208057978e-05, + "loss": 3.5383, + "step": 1157632 + }, + { + "epoch": 1.0, + "learning_rate": 3.103917613306926e-05, + "loss": 3.5336, + "step": 1158144 + }, + { + "epoch": 1.0, + "learning_rate": 3.103080656436247e-05, + "loss": 3.5391, + "step": 1158656 + }, + { + "epoch": 1.0, + "learning_rate": 3.102242061685195e-05, + "loss": 3.5228, + "step": 1159168 + }, + { + "epoch": 1.0, + "learning_rate": 3.101403466934144e-05, + "loss": 3.5333, + "step": 1159680 + }, + { + "epoch": 1.01, + "learning_rate": 3.100564872183092e-05, + "loss": 3.5335, + "step": 1160192 + }, + { + "epoch": 1.01, + "learning_rate": 3.099727915312413e-05, + "loss": 3.5398, + "step": 1160704 + }, + { + "epoch": 1.01, + "learning_rate": 3.098889320561361e-05, + "loss": 3.5368, + "step": 1161216 + }, + { + "epoch": 1.01, + "learning_rate": 3.098050725810309e-05, + "loss": 3.5432, + "step": 1161728 + }, + { + "epoch": 1.01, + "learning_rate": 3.097212131059257e-05, + "loss": 3.5397, + "step": 1162240 + }, + { + "epoch": 1.01, + "learning_rate": 3.0963751741885776e-05, + "loss": 3.541, + "step": 1162752 + }, + { + "epoch": 1.01, + "learning_rate": 3.0955365794375256e-05, + "loss": 3.5434, + "step": 1163264 + }, + { + "epoch": 1.01, + "learning_rate": 3.0946979846864736e-05, + "loss": 3.5305, + "step": 1163776 + }, + { + "epoch": 1.01, + "learning_rate": 3.0938593899354216e-05, + "loss": 3.544, + "step": 1164288 + }, + { + "epoch": 1.01, + "learning_rate": 3.0930224330647425e-05, + "loss": 3.5292, + "step": 1164800 + }, + { + "epoch": 1.01, + "learning_rate": 3.0921838383136905e-05, + "loss": 3.5313, + "step": 1165312 + }, + { + "epoch": 1.01, + "learning_rate": 3.091345243562639e-05, + "loss": 3.5368, + "step": 1165824 + }, + { + "epoch": 1.01, + "learning_rate": 3.090506648811587e-05, + "loss": 3.5448, + "step": 1166336 + }, + { + "epoch": 1.01, + "learning_rate": 3.089669691940908e-05, + "loss": 3.5363, + "step": 1166848 + }, + { + "epoch": 1.01, + "learning_rate": 3.088831097189856e-05, + "loss": 3.542, + "step": 1167360 + }, + { + "epoch": 1.01, + "learning_rate": 3.087992502438804e-05, + "loss": 3.538, + "step": 1167872 + }, + { + "epoch": 1.01, + "learning_rate": 3.087153907687752e-05, + "loss": 3.5366, + "step": 1168384 + }, + { + "epoch": 1.01, + "learning_rate": 3.086316950817073e-05, + "loss": 3.5401, + "step": 1168896 + }, + { + "epoch": 1.01, + "learning_rate": 3.085478356066021e-05, + "loss": 3.5112, + "step": 1169408 + }, + { + "epoch": 1.01, + "learning_rate": 3.084639761314969e-05, + "loss": 3.5304, + "step": 1169920 + }, + { + "epoch": 1.01, + "learning_rate": 3.083801166563917e-05, + "loss": 3.5428, + "step": 1170432 + }, + { + "epoch": 1.01, + "learning_rate": 3.082964209693238e-05, + "loss": 3.5402, + "step": 1170944 + }, + { + "epoch": 1.01, + "learning_rate": 3.082125614942186e-05, + "loss": 3.5278, + "step": 1171456 + }, + { + "epoch": 1.01, + "learning_rate": 3.0812870201911346e-05, + "loss": 3.5143, + "step": 1171968 + }, + { + "epoch": 1.01, + "learning_rate": 3.0804484254400826e-05, + "loss": 3.5243, + "step": 1172480 + }, + { + "epoch": 1.01, + "learning_rate": 3.0796114685694035e-05, + "loss": 3.5155, + "step": 1172992 + }, + { + "epoch": 1.01, + "learning_rate": 3.0787728738183515e-05, + "loss": 3.5499, + "step": 1173504 + }, + { + "epoch": 1.01, + "learning_rate": 3.0779342790672995e-05, + "loss": 3.5175, + "step": 1174016 + }, + { + "epoch": 1.01, + "learning_rate": 3.0770956843162475e-05, + "loss": 3.5395, + "step": 1174528 + }, + { + "epoch": 1.01, + "learning_rate": 3.0762587274455684e-05, + "loss": 3.5341, + "step": 1175040 + }, + { + "epoch": 1.01, + "learning_rate": 3.0754201326945164e-05, + "loss": 3.5233, + "step": 1175552 + }, + { + "epoch": 1.01, + "learning_rate": 3.0745815379434644e-05, + "loss": 3.5347, + "step": 1176064 + }, + { + "epoch": 1.01, + "learning_rate": 3.0737429431924124e-05, + "loss": 3.5284, + "step": 1176576 + }, + { + "epoch": 1.01, + "learning_rate": 3.072905986321733e-05, + "loss": 3.523, + "step": 1177088 + }, + { + "epoch": 1.01, + "learning_rate": 3.072067391570681e-05, + "loss": 3.5186, + "step": 1177600 + }, + { + "epoch": 1.01, + "learning_rate": 3.07122879681963e-05, + "loss": 3.5422, + "step": 1178112 + }, + { + "epoch": 1.01, + "learning_rate": 3.070390202068578e-05, + "loss": 3.5263, + "step": 1178624 + }, + { + "epoch": 1.01, + "learning_rate": 3.069553245197899e-05, + "loss": 3.5241, + "step": 1179136 + }, + { + "epoch": 1.01, + "learning_rate": 3.068714650446847e-05, + "loss": 3.5194, + "step": 1179648 + }, + { + "epoch": 1.01, + "learning_rate": 3.067876055695795e-05, + "loss": 3.5295, + "step": 1180160 + }, + { + "epoch": 1.01, + "learning_rate": 3.067037460944743e-05, + "loss": 3.5412, + "step": 1180672 + }, + { + "epoch": 1.01, + "learning_rate": 3.066200504074064e-05, + "loss": 3.5398, + "step": 1181184 + }, + { + "epoch": 1.01, + "learning_rate": 3.065361909323012e-05, + "loss": 3.5361, + "step": 1181696 + }, + { + "epoch": 1.01, + "learning_rate": 3.06452331457196e-05, + "loss": 3.5398, + "step": 1182208 + }, + { + "epoch": 1.01, + "learning_rate": 3.063684719820908e-05, + "loss": 3.5494, + "step": 1182720 + }, + { + "epoch": 1.01, + "learning_rate": 3.0628477629502286e-05, + "loss": 3.5399, + "step": 1183232 + }, + { + "epoch": 1.01, + "learning_rate": 3.0620091681991766e-05, + "loss": 3.54, + "step": 1183744 + }, + { + "epoch": 1.01, + "learning_rate": 3.061170573448125e-05, + "loss": 3.5297, + "step": 1184256 + }, + { + "epoch": 1.01, + "learning_rate": 3.060331978697073e-05, + "loss": 3.5341, + "step": 1184768 + }, + { + "epoch": 1.01, + "learning_rate": 3.059495021826394e-05, + "loss": 3.5297, + "step": 1185280 + }, + { + "epoch": 1.01, + "learning_rate": 3.058656427075342e-05, + "loss": 3.5312, + "step": 1185792 + }, + { + "epoch": 1.01, + "learning_rate": 3.05781783232429e-05, + "loss": 3.5408, + "step": 1186304 + }, + { + "epoch": 1.01, + "learning_rate": 3.056979237573238e-05, + "loss": 3.5434, + "step": 1186816 + }, + { + "epoch": 1.01, + "learning_rate": 3.056142280702559e-05, + "loss": 3.5342, + "step": 1187328 + }, + { + "epoch": 1.01, + "learning_rate": 3.055303685951507e-05, + "loss": 3.5197, + "step": 1187840 + }, + { + "epoch": 1.01, + "learning_rate": 3.054465091200455e-05, + "loss": 3.5209, + "step": 1188352 + }, + { + "epoch": 1.01, + "learning_rate": 3.053626496449403e-05, + "loss": 3.5346, + "step": 1188864 + }, + { + "epoch": 1.01, + "learning_rate": 3.052789539578724e-05, + "loss": 3.5413, + "step": 1189376 + }, + { + "epoch": 1.01, + "learning_rate": 3.051950944827672e-05, + "loss": 3.5227, + "step": 1189888 + }, + { + "epoch": 1.01, + "learning_rate": 3.0511123500766203e-05, + "loss": 3.5358, + "step": 1190400 + }, + { + "epoch": 1.02, + "learning_rate": 3.0502737553255683e-05, + "loss": 3.5353, + "step": 1190912 + }, + { + "epoch": 1.02, + "learning_rate": 3.0494367984548892e-05, + "loss": 3.5257, + "step": 1191424 + }, + { + "epoch": 1.02, + "learning_rate": 3.0485982037038376e-05, + "loss": 3.527, + "step": 1191936 + }, + { + "epoch": 1.02, + "learning_rate": 3.0477596089527856e-05, + "loss": 3.5399, + "step": 1192448 + }, + { + "epoch": 1.02, + "learning_rate": 3.0469210142017336e-05, + "loss": 3.5314, + "step": 1192960 + }, + { + "epoch": 1.02, + "learning_rate": 3.0460824194506815e-05, + "loss": 3.5413, + "step": 1193472 + }, + { + "epoch": 1.02, + "learning_rate": 3.045243824699629e-05, + "loss": 3.5247, + "step": 1193984 + }, + { + "epoch": 1.02, + "learning_rate": 3.044405229948577e-05, + "loss": 3.5263, + "step": 1194496 + }, + { + "epoch": 1.02, + "learning_rate": 3.0435666351975252e-05, + "loss": 3.532, + "step": 1195008 + }, + { + "epoch": 1.02, + "learning_rate": 3.0427296783268468e-05, + "loss": 3.5386, + "step": 1195520 + }, + { + "epoch": 1.02, + "learning_rate": 3.041891083575794e-05, + "loss": 3.5348, + "step": 1196032 + }, + { + "epoch": 1.02, + "learning_rate": 3.041052488824742e-05, + "loss": 3.5354, + "step": 1196544 + }, + { + "epoch": 1.02, + "learning_rate": 3.04021389407369e-05, + "loss": 3.5343, + "step": 1197056 + }, + { + "epoch": 1.02, + "learning_rate": 3.0393769372030117e-05, + "loss": 3.5341, + "step": 1197568 + }, + { + "epoch": 1.02, + "learning_rate": 3.038539980332333e-05, + "loss": 3.5338, + "step": 1198080 + }, + { + "epoch": 1.02, + "learning_rate": 3.037701385581281e-05, + "loss": 3.5162, + "step": 1198592 + }, + { + "epoch": 1.02, + "learning_rate": 3.036862790830229e-05, + "loss": 3.5252, + "step": 1199104 + }, + { + "epoch": 1.02, + "learning_rate": 3.0360241960791762e-05, + "loss": 3.5323, + "step": 1199616 + }, + { + "epoch": 1.02, + "learning_rate": 3.0351856013281242e-05, + "loss": 3.5292, + "step": 1200128 + }, + { + "epoch": 1.02, + "learning_rate": 3.0343470065770722e-05, + "loss": 3.5193, + "step": 1200640 + }, + { + "epoch": 1.02, + "learning_rate": 3.0335084118260206e-05, + "loss": 3.5243, + "step": 1201152 + }, + { + "epoch": 1.02, + "learning_rate": 3.0326698170749686e-05, + "loss": 3.5165, + "step": 1201664 + }, + { + "epoch": 1.02, + "learning_rate": 3.0318328602042895e-05, + "loss": 3.531, + "step": 1202176 + }, + { + "epoch": 1.02, + "learning_rate": 3.0309942654532375e-05, + "loss": 3.523, + "step": 1202688 + }, + { + "epoch": 1.02, + "learning_rate": 3.0301556707021855e-05, + "loss": 3.5328, + "step": 1203200 + }, + { + "epoch": 1.02, + "learning_rate": 3.0293170759511335e-05, + "loss": 3.5307, + "step": 1203712 + }, + { + "epoch": 1.02, + "learning_rate": 3.0284801190804547e-05, + "loss": 3.5373, + "step": 1204224 + }, + { + "epoch": 1.02, + "learning_rate": 3.0276415243294027e-05, + "loss": 3.5322, + "step": 1204736 + }, + { + "epoch": 1.02, + "learning_rate": 3.0268029295783507e-05, + "loss": 3.5308, + "step": 1205248 + }, + { + "epoch": 1.02, + "learning_rate": 3.0259643348272987e-05, + "loss": 3.538, + "step": 1205760 + }, + { + "epoch": 1.02, + "learning_rate": 3.0251273779566196e-05, + "loss": 3.5302, + "step": 1206272 + }, + { + "epoch": 1.02, + "learning_rate": 3.0242887832055676e-05, + "loss": 3.5284, + "step": 1206784 + }, + { + "epoch": 1.02, + "learning_rate": 3.023450188454516e-05, + "loss": 3.5315, + "step": 1207296 + }, + { + "epoch": 1.02, + "learning_rate": 3.022611593703464e-05, + "loss": 3.5312, + "step": 1207808 + }, + { + "epoch": 1.02, + "learning_rate": 3.021774636832785e-05, + "loss": 3.5316, + "step": 1208320 + }, + { + "epoch": 1.02, + "learning_rate": 3.020936042081733e-05, + "loss": 3.5231, + "step": 1208832 + }, + { + "epoch": 1.02, + "learning_rate": 3.0200974473306808e-05, + "loss": 3.5268, + "step": 1209344 + }, + { + "epoch": 1.02, + "learning_rate": 3.0192588525796288e-05, + "loss": 3.5199, + "step": 1209856 + }, + { + "epoch": 1.02, + "learning_rate": 3.01842189570895e-05, + "loss": 3.5242, + "step": 1210368 + }, + { + "epoch": 1.02, + "learning_rate": 3.017583300957898e-05, + "loss": 3.5206, + "step": 1210880 + }, + { + "epoch": 1.02, + "learning_rate": 3.016744706206846e-05, + "loss": 3.5427, + "step": 1211392 + }, + { + "epoch": 1.02, + "learning_rate": 3.015907749336167e-05, + "loss": 3.5366, + "step": 1211904 + }, + { + "epoch": 1.02, + "learning_rate": 3.015069154585115e-05, + "loss": 3.5251, + "step": 1212416 + }, + { + "epoch": 1.02, + "learning_rate": 3.014230559834063e-05, + "loss": 3.5302, + "step": 1212928 + }, + { + "epoch": 1.02, + "learning_rate": 3.0133919650830113e-05, + "loss": 3.5301, + "step": 1213440 + }, + { + "epoch": 1.02, + "learning_rate": 3.0125550082123322e-05, + "loss": 3.5385, + "step": 1213952 + }, + { + "epoch": 1.02, + "learning_rate": 3.0117164134612802e-05, + "loss": 3.5311, + "step": 1214464 + }, + { + "epoch": 1.02, + "learning_rate": 3.0108778187102282e-05, + "loss": 3.5266, + "step": 1214976 + }, + { + "epoch": 1.02, + "learning_rate": 3.0100392239591762e-05, + "loss": 3.5403, + "step": 1215488 + }, + { + "epoch": 1.02, + "learning_rate": 3.0092022670884974e-05, + "loss": 3.5252, + "step": 1216000 + }, + { + "epoch": 1.02, + "learning_rate": 3.0083636723374454e-05, + "loss": 3.5363, + "step": 1216512 + }, + { + "epoch": 1.02, + "learning_rate": 3.0075250775863934e-05, + "loss": 3.5278, + "step": 1217024 + }, + { + "epoch": 1.02, + "learning_rate": 3.0066864828353414e-05, + "loss": 3.5341, + "step": 1217536 + }, + { + "epoch": 1.02, + "learning_rate": 3.0058495259646623e-05, + "loss": 3.5287, + "step": 1218048 + }, + { + "epoch": 1.02, + "learning_rate": 3.0050109312136103e-05, + "loss": 3.5211, + "step": 1218560 + }, + { + "epoch": 1.02, + "learning_rate": 3.0041723364625583e-05, + "loss": 3.5365, + "step": 1219072 + }, + { + "epoch": 1.02, + "learning_rate": 3.0033337417115067e-05, + "loss": 3.531, + "step": 1219584 + }, + { + "epoch": 1.02, + "learning_rate": 3.0024967848408276e-05, + "loss": 3.5332, + "step": 1220096 + }, + { + "epoch": 1.02, + "learning_rate": 3.0016581900897756e-05, + "loss": 3.5264, + "step": 1220608 + }, + { + "epoch": 1.03, + "learning_rate": 3.0008195953387236e-05, + "loss": 3.5279, + "step": 1221120 + }, + { + "epoch": 1.03, + "eval_loss": 3.846381664276123, + "eval_runtime": 303.1903, + "eval_samples_per_second": 1258.586, + "eval_steps_per_second": 39.332, + "step": 1221120 + }, + { + "epoch": 0.0, + "learning_rate": 2.9999810005876716e-05, + "loss": 3.5194, + "step": 1221632 + }, + { + "epoch": 0.0, + "learning_rate": 2.9991424058366196e-05, + "loss": 3.5173, + "step": 1222144 + }, + { + "epoch": 0.0, + "learning_rate": 2.9983038110855676e-05, + "loss": 3.5319, + "step": 1222656 + }, + { + "epoch": 0.0, + "learning_rate": 2.9974668542148888e-05, + "loss": 3.5304, + "step": 1223168 + }, + { + "epoch": 0.0, + "learning_rate": 2.9966282594638368e-05, + "loss": 3.5393, + "step": 1223680 + }, + { + "epoch": 0.0, + "learning_rate": 2.9957896647127848e-05, + "loss": 3.5204, + "step": 1224192 + }, + { + "epoch": 0.0, + "learning_rate": 2.9949510699617328e-05, + "loss": 3.5244, + "step": 1224704 + }, + { + "epoch": 0.0, + "learning_rate": 2.9941141130910537e-05, + "loss": 3.5135, + "step": 1225216 + }, + { + "epoch": 0.0, + "learning_rate": 2.9932755183400017e-05, + "loss": 3.5324, + "step": 1225728 + }, + { + "epoch": 0.0, + "learning_rate": 2.99243692358895e-05, + "loss": 3.5233, + "step": 1226240 + }, + { + "epoch": 0.0, + "learning_rate": 2.991598328837898e-05, + "loss": 3.5313, + "step": 1226752 + }, + { + "epoch": 0.0, + "learning_rate": 2.990759734086846e-05, + "loss": 3.5286, + "step": 1227264 + }, + { + "epoch": 0.0, + "learning_rate": 2.989922777216167e-05, + "loss": 3.5224, + "step": 1227776 + }, + { + "epoch": 0.0, + "learning_rate": 2.989084182465115e-05, + "loss": 3.5181, + "step": 1228288 + }, + { + "epoch": 0.0, + "learning_rate": 2.988245587714063e-05, + "loss": 3.5165, + "step": 1228800 + }, + { + "epoch": 0.0, + "learning_rate": 2.987406992963011e-05, + "loss": 3.5166, + "step": 1229312 + }, + { + "epoch": 0.0, + "learning_rate": 2.986570036092332e-05, + "loss": 3.5214, + "step": 1229824 + }, + { + "epoch": 0.0, + "learning_rate": 2.98573144134128e-05, + "loss": 3.5259, + "step": 1230336 + }, + { + "epoch": 0.0, + "learning_rate": 2.984892846590228e-05, + "loss": 3.5163, + "step": 1230848 + }, + { + "epoch": 0.0, + "learning_rate": 2.984054251839176e-05, + "loss": 3.5421, + "step": 1231360 + }, + { + "epoch": 0.0, + "learning_rate": 2.983217294968497e-05, + "loss": 3.5226, + "step": 1231872 + }, + { + "epoch": 0.0, + "learning_rate": 2.9823787002174454e-05, + "loss": 3.5267, + "step": 1232384 + }, + { + "epoch": 0.0, + "learning_rate": 2.9815401054663934e-05, + "loss": 3.5233, + "step": 1232896 + }, + { + "epoch": 0.0, + "learning_rate": 2.9807015107153414e-05, + "loss": 3.5333, + "step": 1233408 + }, + { + "epoch": 0.0, + "learning_rate": 2.9798645538446623e-05, + "loss": 3.5199, + "step": 1233920 + }, + { + "epoch": 0.0, + "learning_rate": 2.9790259590936103e-05, + "loss": 3.5255, + "step": 1234432 + }, + { + "epoch": 0.0, + "learning_rate": 2.9781873643425583e-05, + "loss": 3.5212, + "step": 1234944 + }, + { + "epoch": 0.0, + "learning_rate": 2.9773487695915063e-05, + "loss": 3.5184, + "step": 1235456 + }, + { + "epoch": 0.0, + "learning_rate": 2.9765118127208275e-05, + "loss": 3.5139, + "step": 1235968 + }, + { + "epoch": 0.01, + "learning_rate": 2.9756732179697755e-05, + "loss": 3.5163, + "step": 1236480 + }, + { + "epoch": 0.01, + "learning_rate": 2.9748346232187235e-05, + "loss": 3.5273, + "step": 1236992 + }, + { + "epoch": 0.01, + "learning_rate": 2.9739960284676715e-05, + "loss": 3.5256, + "step": 1237504 + }, + { + "epoch": 0.01, + "learning_rate": 2.9731590715969924e-05, + "loss": 3.5263, + "step": 1238016 + }, + { + "epoch": 0.01, + "learning_rate": 2.9723204768459408e-05, + "loss": 3.5281, + "step": 1238528 + }, + { + "epoch": 0.01, + "learning_rate": 2.9714818820948888e-05, + "loss": 3.5254, + "step": 1239040 + }, + { + "epoch": 0.01, + "learning_rate": 2.9706432873438368e-05, + "loss": 3.527, + "step": 1239552 + }, + { + "epoch": 0.01, + "learning_rate": 2.9698063304731577e-05, + "loss": 3.5219, + "step": 1240064 + }, + { + "epoch": 0.01, + "learning_rate": 2.9689677357221057e-05, + "loss": 3.5256, + "step": 1240576 + }, + { + "epoch": 0.01, + "learning_rate": 2.9681291409710537e-05, + "loss": 3.5167, + "step": 1241088 + }, + { + "epoch": 0.01, + "learning_rate": 2.9672905462200016e-05, + "loss": 3.5203, + "step": 1241600 + }, + { + "epoch": 0.01, + "learning_rate": 2.966453589349323e-05, + "loss": 3.522, + "step": 1242112 + }, + { + "epoch": 0.01, + "learning_rate": 2.965614994598271e-05, + "loss": 3.5315, + "step": 1242624 + }, + { + "epoch": 0.01, + "learning_rate": 2.964776399847219e-05, + "loss": 3.519, + "step": 1243136 + }, + { + "epoch": 0.01, + "learning_rate": 2.963937805096167e-05, + "loss": 3.5254, + "step": 1243648 + }, + { + "epoch": 0.01, + "learning_rate": 2.9631008482254878e-05, + "loss": 3.527, + "step": 1244160 + }, + { + "epoch": 0.01, + "learning_rate": 2.962262253474436e-05, + "loss": 3.5252, + "step": 1244672 + }, + { + "epoch": 0.01, + "learning_rate": 2.961423658723384e-05, + "loss": 3.5234, + "step": 1245184 + }, + { + "epoch": 0.01, + "learning_rate": 2.9605850639723314e-05, + "loss": 3.4995, + "step": 1245696 + }, + { + "epoch": 0.01, + "learning_rate": 2.959748107101653e-05, + "loss": 3.5181, + "step": 1246208 + }, + { + "epoch": 0.01, + "learning_rate": 2.958909512350601e-05, + "loss": 3.5247, + "step": 1246720 + }, + { + "epoch": 0.01, + "learning_rate": 2.958070917599549e-05, + "loss": 3.5283, + "step": 1247232 + }, + { + "epoch": 0.01, + "learning_rate": 2.9572323228484967e-05, + "loss": 3.5133, + "step": 1247744 + }, + { + "epoch": 0.01, + "learning_rate": 2.9563953659778183e-05, + "loss": 3.501, + "step": 1248256 + }, + { + "epoch": 0.01, + "learning_rate": 2.9555567712267663e-05, + "loss": 3.5118, + "step": 1248768 + }, + { + "epoch": 0.01, + "learning_rate": 2.9547181764757143e-05, + "loss": 3.5014, + "step": 1249280 + }, + { + "epoch": 0.01, + "learning_rate": 2.953881219605035e-05, + "loss": 3.5327, + "step": 1249792 + }, + { + "epoch": 0.01, + "learning_rate": 2.953042624853983e-05, + "loss": 3.5077, + "step": 1250304 + }, + { + "epoch": 0.01, + "learning_rate": 2.9522040301029315e-05, + "loss": 3.5238, + "step": 1250816 + }, + { + "epoch": 0.01, + "learning_rate": 2.9513654353518788e-05, + "loss": 3.5233, + "step": 1251328 + }, + { + "epoch": 0.01, + "learning_rate": 2.9505284784812004e-05, + "loss": 3.5063, + "step": 1251840 + }, + { + "epoch": 0.01, + "learning_rate": 2.9496898837301484e-05, + "loss": 3.5199, + "step": 1252352 + }, + { + "epoch": 0.01, + "learning_rate": 2.9488512889790964e-05, + "loss": 3.5141, + "step": 1252864 + }, + { + "epoch": 0.01, + "learning_rate": 2.948012694228044e-05, + "loss": 3.5056, + "step": 1253376 + }, + { + "epoch": 0.01, + "learning_rate": 2.9471757373573656e-05, + "loss": 3.5022, + "step": 1253888 + }, + { + "epoch": 0.01, + "learning_rate": 2.9463371426063136e-05, + "loss": 3.5318, + "step": 1254400 + }, + { + "epoch": 0.01, + "learning_rate": 2.9454985478552616e-05, + "loss": 3.5169, + "step": 1254912 + }, + { + "epoch": 0.01, + "learning_rate": 2.944659953104209e-05, + "loss": 3.5094, + "step": 1255424 + }, + { + "epoch": 0.01, + "learning_rate": 2.9438229962335305e-05, + "loss": 3.5054, + "step": 1255936 + }, + { + "epoch": 0.01, + "learning_rate": 2.9429844014824785e-05, + "loss": 3.5133, + "step": 1256448 + }, + { + "epoch": 0.01, + "learning_rate": 2.9421458067314262e-05, + "loss": 3.5259, + "step": 1256960 + }, + { + "epoch": 0.01, + "learning_rate": 2.9413072119803742e-05, + "loss": 3.5252, + "step": 1257472 + }, + { + "epoch": 0.01, + "learning_rate": 2.9404702551096958e-05, + "loss": 3.5212, + "step": 1257984 + }, + { + "epoch": 0.01, + "learning_rate": 2.9396316603586438e-05, + "loss": 3.5268, + "step": 1258496 + }, + { + "epoch": 0.01, + "learning_rate": 2.9387930656075914e-05, + "loss": 3.5315, + "step": 1259008 + }, + { + "epoch": 0.01, + "learning_rate": 2.9379544708565394e-05, + "loss": 3.5251, + "step": 1259520 + }, + { + "epoch": 0.01, + "learning_rate": 2.937117513985861e-05, + "loss": 3.5237, + "step": 1260032 + }, + { + "epoch": 0.01, + "learning_rate": 2.936278919234809e-05, + "loss": 3.5156, + "step": 1260544 + }, + { + "epoch": 0.01, + "learning_rate": 2.9354403244837563e-05, + "loss": 3.5219, + "step": 1261056 + }, + { + "epoch": 0.01, + "learning_rate": 2.9346017297327043e-05, + "loss": 3.521, + "step": 1261568 + }, + { + "epoch": 0.01, + "learning_rate": 2.933764772862026e-05, + "loss": 3.5165, + "step": 1262080 + }, + { + "epoch": 0.01, + "learning_rate": 2.9329261781109736e-05, + "loss": 3.5244, + "step": 1262592 + }, + { + "epoch": 0.01, + "learning_rate": 2.9320875833599215e-05, + "loss": 3.5259, + "step": 1263104 + }, + { + "epoch": 0.01, + "learning_rate": 2.9312489886088695e-05, + "loss": 3.5232, + "step": 1263616 + }, + { + "epoch": 0.01, + "learning_rate": 2.930412031738191e-05, + "loss": 3.5048, + "step": 1264128 + }, + { + "epoch": 0.01, + "learning_rate": 2.9295734369871385e-05, + "loss": 3.5058, + "step": 1264640 + }, + { + "epoch": 0.01, + "learning_rate": 2.9287348422360868e-05, + "loss": 3.5221, + "step": 1265152 + }, + { + "epoch": 0.01, + "learning_rate": 2.9278962474850348e-05, + "loss": 3.5269, + "step": 1265664 + }, + { + "epoch": 0.01, + "learning_rate": 2.9270592906143564e-05, + "loss": 3.5119, + "step": 1266176 + }, + { + "epoch": 0.01, + "learning_rate": 2.9262206958633037e-05, + "loss": 3.5199, + "step": 1266688 + }, + { + "epoch": 0.02, + "learning_rate": 2.9253821011122517e-05, + "loss": 3.5246, + "step": 1267200 + }, + { + "epoch": 0.02, + "learning_rate": 2.9245451442415733e-05, + "loss": 3.5107, + "step": 1267712 + }, + { + "epoch": 0.02, + "learning_rate": 2.923706549490521e-05, + "loss": 3.5127, + "step": 1268224 + }, + { + "epoch": 0.02, + "learning_rate": 2.922867954739469e-05, + "loss": 3.5209, + "step": 1268736 + }, + { + "epoch": 0.02, + "learning_rate": 2.922029359988417e-05, + "loss": 3.5213, + "step": 1269248 + }, + { + "epoch": 0.02, + "learning_rate": 2.921190765237365e-05, + "loss": 3.5232, + "step": 1269760 + }, + { + "epoch": 0.02, + "learning_rate": 2.920352170486313e-05, + "loss": 3.5179, + "step": 1270272 + }, + { + "epoch": 0.02, + "learning_rate": 2.919513575735261e-05, + "loss": 3.5081, + "step": 1270784 + }, + { + "epoch": 0.02, + "learning_rate": 2.918674980984209e-05, + "loss": 3.5226, + "step": 1271296 + }, + { + "epoch": 0.02, + "learning_rate": 2.91783802411353e-05, + "loss": 3.523, + "step": 1271808 + }, + { + "epoch": 0.02, + "learning_rate": 2.916999429362478e-05, + "loss": 3.5181, + "step": 1272320 + }, + { + "epoch": 0.02, + "learning_rate": 2.916160834611426e-05, + "loss": 3.5239, + "step": 1272832 + }, + { + "epoch": 0.02, + "learning_rate": 2.915322239860374e-05, + "loss": 3.5168, + "step": 1273344 + }, + { + "epoch": 0.02, + "learning_rate": 2.914485282989695e-05, + "loss": 3.5198, + "step": 1273856 + }, + { + "epoch": 0.02, + "learning_rate": 2.9136483261190163e-05, + "loss": 3.5262, + "step": 1274368 + }, + { + "epoch": 0.02, + "learning_rate": 2.9128097313679643e-05, + "loss": 3.5019, + "step": 1274880 + }, + { + "epoch": 0.02, + "learning_rate": 2.9119711366169123e-05, + "loss": 3.5056, + "step": 1275392 + }, + { + "epoch": 0.02, + "learning_rate": 2.9111325418658603e-05, + "loss": 3.519, + "step": 1275904 + }, + { + "epoch": 0.02, + "learning_rate": 2.9102939471148083e-05, + "loss": 3.5195, + "step": 1276416 + }, + { + "epoch": 0.02, + "learning_rate": 2.9094553523637563e-05, + "loss": 3.5016, + "step": 1276928 + }, + { + "epoch": 0.02, + "learning_rate": 2.9086167576127043e-05, + "loss": 3.5121, + "step": 1277440 + }, + { + "epoch": 0.02, + "learning_rate": 2.9077781628616523e-05, + "loss": 3.5068, + "step": 1277952 + }, + { + "epoch": 0.02, + "learning_rate": 2.9069412059909735e-05, + "loss": 3.5155, + "step": 1278464 + }, + { + "epoch": 0.02, + "learning_rate": 2.9061026112399215e-05, + "loss": 3.5113, + "step": 1278976 + }, + { + "epoch": 0.02, + "learning_rate": 2.9052640164888695e-05, + "loss": 3.5146, + "step": 1279488 + }, + { + "epoch": 0.02, + "learning_rate": 2.9044254217378175e-05, + "loss": 3.5165, + "step": 1280000 + }, + { + "epoch": 0.02, + "learning_rate": 2.9035884648671384e-05, + "loss": 3.5243, + "step": 1280512 + }, + { + "epoch": 0.02, + "learning_rate": 2.9027498701160864e-05, + "loss": 3.5183, + "step": 1281024 + }, + { + "epoch": 0.02, + "learning_rate": 2.9019112753650347e-05, + "loss": 3.5195, + "step": 1281536 + }, + { + "epoch": 0.02, + "learning_rate": 2.9010726806139827e-05, + "loss": 3.5229, + "step": 1282048 + }, + { + "epoch": 0.02, + "learning_rate": 2.9002357237433036e-05, + "loss": 3.5186, + "step": 1282560 + }, + { + "epoch": 0.02, + "learning_rate": 2.8993971289922516e-05, + "loss": 3.5079, + "step": 1283072 + }, + { + "epoch": 0.02, + "learning_rate": 2.8985585342411996e-05, + "loss": 3.5194, + "step": 1283584 + }, + { + "epoch": 0.02, + "learning_rate": 2.8977199394901476e-05, + "loss": 3.5135, + "step": 1284096 + }, + { + "epoch": 0.02, + "learning_rate": 2.896882982619469e-05, + "loss": 3.5233, + "step": 1284608 + }, + { + "epoch": 0.02, + "learning_rate": 2.896044387868417e-05, + "loss": 3.5037, + "step": 1285120 + }, + { + "epoch": 0.02, + "learning_rate": 2.895205793117365e-05, + "loss": 3.5174, + "step": 1285632 + }, + { + "epoch": 0.02, + "learning_rate": 2.894367198366313e-05, + "loss": 3.5022, + "step": 1286144 + }, + { + "epoch": 0.02, + "learning_rate": 2.8935302414956338e-05, + "loss": 3.5083, + "step": 1286656 + }, + { + "epoch": 0.02, + "learning_rate": 2.8926916467445818e-05, + "loss": 3.5043, + "step": 1287168 + }, + { + "epoch": 0.02, + "learning_rate": 2.89185305199353e-05, + "loss": 3.5282, + "step": 1287680 + }, + { + "epoch": 0.02, + "learning_rate": 2.891014457242478e-05, + "loss": 3.527, + "step": 1288192 + }, + { + "epoch": 0.02, + "learning_rate": 2.890177500371799e-05, + "loss": 3.5098, + "step": 1288704 + }, + { + "epoch": 0.02, + "learning_rate": 2.889338905620747e-05, + "loss": 3.5149, + "step": 1289216 + }, + { + "epoch": 0.02, + "learning_rate": 2.888500310869695e-05, + "loss": 3.5162, + "step": 1289728 + }, + { + "epoch": 0.02, + "learning_rate": 2.887661716118643e-05, + "loss": 3.5227, + "step": 1290240 + }, + { + "epoch": 0.02, + "learning_rate": 2.8868247592479642e-05, + "loss": 3.5224, + "step": 1290752 + }, + { + "epoch": 0.02, + "learning_rate": 2.8859861644969122e-05, + "loss": 3.5096, + "step": 1291264 + }, + { + "epoch": 0.02, + "learning_rate": 2.8851475697458602e-05, + "loss": 3.5274, + "step": 1291776 + }, + { + "epoch": 0.02, + "learning_rate": 2.8843089749948082e-05, + "loss": 3.5103, + "step": 1292288 + }, + { + "epoch": 0.02, + "learning_rate": 2.883472018124129e-05, + "loss": 3.5233, + "step": 1292800 + }, + { + "epoch": 0.02, + "learning_rate": 2.882633423373077e-05, + "loss": 3.5145, + "step": 1293312 + }, + { + "epoch": 0.02, + "learning_rate": 2.8817948286220255e-05, + "loss": 3.5141, + "step": 1293824 + }, + { + "epoch": 0.02, + "learning_rate": 2.8809562338709735e-05, + "loss": 3.5168, + "step": 1294336 + }, + { + "epoch": 0.02, + "learning_rate": 2.8801192770002944e-05, + "loss": 3.5084, + "step": 1294848 + }, + { + "epoch": 0.02, + "learning_rate": 2.8792806822492424e-05, + "loss": 3.5208, + "step": 1295360 + }, + { + "epoch": 0.02, + "learning_rate": 2.8784420874981904e-05, + "loss": 3.5196, + "step": 1295872 + }, + { + "epoch": 0.02, + "learning_rate": 2.8776034927471384e-05, + "loss": 3.5184, + "step": 1296384 + }, + { + "epoch": 0.02, + "learning_rate": 2.8767665358764596e-05, + "loss": 3.5132, + "step": 1296896 + }, + { + "epoch": 0.02, + "learning_rate": 2.8759279411254076e-05, + "loss": 3.5106, + "step": 1297408 + }, + { + "epoch": 0.03, + "eval_loss": 3.848146915435791, + "eval_runtime": 303.1055, + "eval_samples_per_second": 1258.938, + "eval_steps_per_second": 39.343, + "step": 1297440 + }, + { + "epoch": 1.0, + "learning_rate": 2.8750893463743556e-05, + "loss": 3.5055, + "step": 1297920 + }, + { + "epoch": 1.0, + "learning_rate": 2.8742523895036765e-05, + "loss": 3.5057, + "step": 1298432 + }, + { + "epoch": 1.0, + "learning_rate": 2.8734137947526245e-05, + "loss": 3.5206, + "step": 1298944 + }, + { + "epoch": 1.0, + "learning_rate": 2.8725752000015725e-05, + "loss": 3.5121, + "step": 1299456 + }, + { + "epoch": 1.0, + "learning_rate": 2.871736605250521e-05, + "loss": 3.528, + "step": 1299968 + }, + { + "epoch": 1.0, + "learning_rate": 2.8708996483798417e-05, + "loss": 3.5031, + "step": 1300480 + }, + { + "epoch": 1.0, + "learning_rate": 2.8700626915091627e-05, + "loss": 3.514, + "step": 1300992 + }, + { + "epoch": 1.0, + "learning_rate": 2.8692240967581107e-05, + "loss": 3.4991, + "step": 1301504 + }, + { + "epoch": 1.0, + "learning_rate": 2.8683855020070586e-05, + "loss": 3.5185, + "step": 1302016 + }, + { + "epoch": 1.0, + "learning_rate": 2.867546907256007e-05, + "loss": 3.5118, + "step": 1302528 + }, + { + "epoch": 1.0, + "learning_rate": 2.866708312504955e-05, + "loss": 3.5152, + "step": 1303040 + }, + { + "epoch": 1.0, + "learning_rate": 2.865869717753903e-05, + "loss": 3.5132, + "step": 1303552 + }, + { + "epoch": 1.0, + "learning_rate": 2.865032760883224e-05, + "loss": 3.5078, + "step": 1304064 + }, + { + "epoch": 1.0, + "learning_rate": 2.864194166132172e-05, + "loss": 3.5056, + "step": 1304576 + }, + { + "epoch": 1.0, + "learning_rate": 2.86335557138112e-05, + "loss": 3.5052, + "step": 1305088 + }, + { + "epoch": 1.0, + "learning_rate": 2.862516976630068e-05, + "loss": 3.5011, + "step": 1305600 + }, + { + "epoch": 1.0, + "learning_rate": 2.8616783818790162e-05, + "loss": 3.5089, + "step": 1306112 + }, + { + "epoch": 1.0, + "learning_rate": 2.8608397871279642e-05, + "loss": 3.5118, + "step": 1306624 + }, + { + "epoch": 1.0, + "learning_rate": 2.8600011923769115e-05, + "loss": 3.5045, + "step": 1307136 + }, + { + "epoch": 1.0, + "learning_rate": 2.8591625976258595e-05, + "loss": 3.5292, + "step": 1307648 + }, + { + "epoch": 1.0, + "learning_rate": 2.858325640755181e-05, + "loss": 3.5072, + "step": 1308160 + }, + { + "epoch": 1.0, + "learning_rate": 2.8574870460041288e-05, + "loss": 3.5132, + "step": 1308672 + }, + { + "epoch": 1.0, + "learning_rate": 2.8566484512530768e-05, + "loss": 3.5113, + "step": 1309184 + }, + { + "epoch": 1.0, + "learning_rate": 2.8558098565020247e-05, + "loss": 3.5218, + "step": 1309696 + }, + { + "epoch": 1.0, + "learning_rate": 2.8549728996313463e-05, + "loss": 3.5017, + "step": 1310208 + }, + { + "epoch": 1.0, + "learning_rate": 2.8541343048802937e-05, + "loss": 3.5115, + "step": 1310720 + }, + { + "epoch": 1.0, + "learning_rate": 2.8532957101292416e-05, + "loss": 3.5056, + "step": 1311232 + }, + { + "epoch": 1.0, + "learning_rate": 2.85245711537819e-05, + "loss": 3.5108, + "step": 1311744 + }, + { + "epoch": 1.0, + "learning_rate": 2.851620158507511e-05, + "loss": 3.4953, + "step": 1312256 + }, + { + "epoch": 1.01, + "learning_rate": 2.850781563756459e-05, + "loss": 3.5036, + "step": 1312768 + }, + { + "epoch": 1.01, + "learning_rate": 2.849942969005407e-05, + "loss": 3.5149, + "step": 1313280 + }, + { + "epoch": 1.01, + "learning_rate": 2.849104374254355e-05, + "loss": 3.5104, + "step": 1313792 + }, + { + "epoch": 1.01, + "learning_rate": 2.848267417383676e-05, + "loss": 3.5106, + "step": 1314304 + }, + { + "epoch": 1.01, + "learning_rate": 2.847428822632624e-05, + "loss": 3.5154, + "step": 1314816 + }, + { + "epoch": 1.01, + "learning_rate": 2.846590227881572e-05, + "loss": 3.5116, + "step": 1315328 + }, + { + "epoch": 1.01, + "learning_rate": 2.84575163313052e-05, + "loss": 3.5116, + "step": 1315840 + }, + { + "epoch": 1.01, + "learning_rate": 2.844914676259841e-05, + "loss": 3.5091, + "step": 1316352 + }, + { + "epoch": 1.01, + "learning_rate": 2.844076081508789e-05, + "loss": 3.515, + "step": 1316864 + }, + { + "epoch": 1.01, + "learning_rate": 2.843237486757737e-05, + "loss": 3.5002, + "step": 1317376 + }, + { + "epoch": 1.01, + "learning_rate": 2.8423988920066853e-05, + "loss": 3.506, + "step": 1317888 + }, + { + "epoch": 1.01, + "learning_rate": 2.8415619351360063e-05, + "loss": 3.5104, + "step": 1318400 + }, + { + "epoch": 1.01, + "learning_rate": 2.8407233403849543e-05, + "loss": 3.5163, + "step": 1318912 + }, + { + "epoch": 1.01, + "learning_rate": 2.8398847456339022e-05, + "loss": 3.5046, + "step": 1319424 + }, + { + "epoch": 1.01, + "learning_rate": 2.8390461508828502e-05, + "loss": 3.5113, + "step": 1319936 + }, + { + "epoch": 1.01, + "learning_rate": 2.8382091940121715e-05, + "loss": 3.5167, + "step": 1320448 + }, + { + "epoch": 1.01, + "learning_rate": 2.8373705992611195e-05, + "loss": 3.5101, + "step": 1320960 + }, + { + "epoch": 1.01, + "learning_rate": 2.8365320045100675e-05, + "loss": 3.5122, + "step": 1321472 + }, + { + "epoch": 1.01, + "learning_rate": 2.8356934097590155e-05, + "loss": 3.488, + "step": 1321984 + }, + { + "epoch": 1.01, + "learning_rate": 2.8348564528883364e-05, + "loss": 3.499, + "step": 1322496 + }, + { + "epoch": 1.01, + "learning_rate": 2.8340178581372844e-05, + "loss": 3.5131, + "step": 1323008 + }, + { + "epoch": 1.01, + "learning_rate": 2.8331792633862324e-05, + "loss": 3.5118, + "step": 1323520 + }, + { + "epoch": 1.01, + "learning_rate": 2.8323406686351807e-05, + "loss": 3.5053, + "step": 1324032 + }, + { + "epoch": 1.01, + "learning_rate": 2.8315037117645016e-05, + "loss": 3.4881, + "step": 1324544 + }, + { + "epoch": 1.01, + "learning_rate": 2.8306651170134496e-05, + "loss": 3.498, + "step": 1325056 + }, + { + "epoch": 1.01, + "learning_rate": 2.8298265222623976e-05, + "loss": 3.4881, + "step": 1325568 + }, + { + "epoch": 1.01, + "learning_rate": 2.8289879275113456e-05, + "loss": 3.5158, + "step": 1326080 + }, + { + "epoch": 1.01, + "learning_rate": 2.828150970640667e-05, + "loss": 3.4967, + "step": 1326592 + }, + { + "epoch": 1.01, + "learning_rate": 2.827312375889615e-05, + "loss": 3.5113, + "step": 1327104 + }, + { + "epoch": 1.01, + "learning_rate": 2.826473781138563e-05, + "loss": 3.5102, + "step": 1327616 + }, + { + "epoch": 1.01, + "learning_rate": 2.8256368242678838e-05, + "loss": 3.4961, + "step": 1328128 + }, + { + "epoch": 1.01, + "learning_rate": 2.8247982295168318e-05, + "loss": 3.5057, + "step": 1328640 + }, + { + "epoch": 1.01, + "learning_rate": 2.8239596347657798e-05, + "loss": 3.4967, + "step": 1329152 + }, + { + "epoch": 1.01, + "learning_rate": 2.8231210400147277e-05, + "loss": 3.4956, + "step": 1329664 + }, + { + "epoch": 1.01, + "learning_rate": 2.822284083144049e-05, + "loss": 3.4909, + "step": 1330176 + }, + { + "epoch": 1.01, + "learning_rate": 2.821445488392997e-05, + "loss": 3.5106, + "step": 1330688 + }, + { + "epoch": 1.01, + "learning_rate": 2.820606893641945e-05, + "loss": 3.5056, + "step": 1331200 + }, + { + "epoch": 1.01, + "learning_rate": 2.819768298890893e-05, + "loss": 3.4946, + "step": 1331712 + }, + { + "epoch": 1.01, + "learning_rate": 2.818931342020214e-05, + "loss": 3.4953, + "step": 1332224 + }, + { + "epoch": 1.01, + "learning_rate": 2.8180927472691622e-05, + "loss": 3.4984, + "step": 1332736 + }, + { + "epoch": 1.01, + "learning_rate": 2.8172541525181102e-05, + "loss": 3.5139, + "step": 1333248 + }, + { + "epoch": 1.01, + "learning_rate": 2.8164155577670582e-05, + "loss": 3.5117, + "step": 1333760 + }, + { + "epoch": 1.01, + "learning_rate": 2.815578600896379e-05, + "loss": 3.5074, + "step": 1334272 + }, + { + "epoch": 1.01, + "learning_rate": 2.814740006145327e-05, + "loss": 3.5188, + "step": 1334784 + }, + { + "epoch": 1.01, + "learning_rate": 2.813901411394275e-05, + "loss": 3.5146, + "step": 1335296 + }, + { + "epoch": 1.01, + "learning_rate": 2.813062816643223e-05, + "loss": 3.5161, + "step": 1335808 + }, + { + "epoch": 1.01, + "learning_rate": 2.8122258597725444e-05, + "loss": 3.5091, + "step": 1336320 + }, + { + "epoch": 1.01, + "learning_rate": 2.8113872650214924e-05, + "loss": 3.5042, + "step": 1336832 + }, + { + "epoch": 1.01, + "learning_rate": 2.8105486702704404e-05, + "loss": 3.508, + "step": 1337344 + }, + { + "epoch": 1.01, + "learning_rate": 2.8097100755193883e-05, + "loss": 3.5063, + "step": 1337856 + }, + { + "epoch": 1.01, + "learning_rate": 2.8088714807683363e-05, + "loss": 3.5034, + "step": 1338368 + }, + { + "epoch": 1.01, + "learning_rate": 2.8080345238976573e-05, + "loss": 3.5119, + "step": 1338880 + }, + { + "epoch": 1.01, + "learning_rate": 2.8071959291466056e-05, + "loss": 3.515, + "step": 1339392 + }, + { + "epoch": 1.01, + "learning_rate": 2.8063573343955536e-05, + "loss": 3.5055, + "step": 1339904 + }, + { + "epoch": 1.01, + "learning_rate": 2.8055203775248745e-05, + "loss": 3.4977, + "step": 1340416 + }, + { + "epoch": 1.01, + "learning_rate": 2.8046817827738225e-05, + "loss": 3.4909, + "step": 1340928 + }, + { + "epoch": 1.01, + "learning_rate": 2.8038431880227705e-05, + "loss": 3.5045, + "step": 1341440 + }, + { + "epoch": 1.01, + "learning_rate": 2.8030045932717185e-05, + "loss": 3.5135, + "step": 1341952 + }, + { + "epoch": 1.01, + "learning_rate": 2.8021676364010397e-05, + "loss": 3.4992, + "step": 1342464 + }, + { + "epoch": 1.01, + "learning_rate": 2.8013290416499877e-05, + "loss": 3.5065, + "step": 1342976 + }, + { + "epoch": 1.02, + "learning_rate": 2.8004904468989357e-05, + "loss": 3.5102, + "step": 1343488 + }, + { + "epoch": 1.02, + "learning_rate": 2.7996534900282566e-05, + "loss": 3.5012, + "step": 1344000 + }, + { + "epoch": 1.02, + "learning_rate": 2.7988148952772046e-05, + "loss": 3.4997, + "step": 1344512 + }, + { + "epoch": 1.02, + "learning_rate": 2.7979763005261526e-05, + "loss": 3.5021, + "step": 1345024 + }, + { + "epoch": 1.02, + "learning_rate": 2.797137705775101e-05, + "loss": 3.5062, + "step": 1345536 + }, + { + "epoch": 1.02, + "learning_rate": 2.796299111024049e-05, + "loss": 3.5069, + "step": 1346048 + }, + { + "epoch": 1.02, + "learning_rate": 2.795460516272997e-05, + "loss": 3.509, + "step": 1346560 + }, + { + "epoch": 1.02, + "learning_rate": 2.794621921521945e-05, + "loss": 3.4932, + "step": 1347072 + }, + { + "epoch": 1.02, + "learning_rate": 2.793783326770893e-05, + "loss": 3.5113, + "step": 1347584 + }, + { + "epoch": 1.02, + "learning_rate": 2.792946369900214e-05, + "loss": 3.5027, + "step": 1348096 + }, + { + "epoch": 1.02, + "learning_rate": 2.792107775149162e-05, + "loss": 3.5105, + "step": 1348608 + }, + { + "epoch": 1.02, + "learning_rate": 2.7912691803981102e-05, + "loss": 3.5052, + "step": 1349120 + }, + { + "epoch": 1.02, + "learning_rate": 2.7904305856470582e-05, + "loss": 3.5053, + "step": 1349632 + }, + { + "epoch": 1.02, + "learning_rate": 2.789593628776379e-05, + "loss": 3.5063, + "step": 1350144 + }, + { + "epoch": 1.02, + "learning_rate": 2.788755034025327e-05, + "loss": 3.5127, + "step": 1350656 + }, + { + "epoch": 1.02, + "learning_rate": 2.787916439274275e-05, + "loss": 3.4903, + "step": 1351168 + }, + { + "epoch": 1.02, + "learning_rate": 2.787077844523223e-05, + "loss": 3.4973, + "step": 1351680 + }, + { + "epoch": 1.02, + "learning_rate": 2.7862408876525443e-05, + "loss": 3.5033, + "step": 1352192 + }, + { + "epoch": 1.02, + "learning_rate": 2.7854022929014923e-05, + "loss": 3.5026, + "step": 1352704 + }, + { + "epoch": 1.02, + "learning_rate": 2.7845636981504403e-05, + "loss": 3.491, + "step": 1353216 + }, + { + "epoch": 1.02, + "learning_rate": 2.7837251033993883e-05, + "loss": 3.497, + "step": 1353728 + }, + { + "epoch": 1.02, + "learning_rate": 2.7828881465287092e-05, + "loss": 3.4924, + "step": 1354240 + }, + { + "epoch": 1.02, + "learning_rate": 2.7820495517776572e-05, + "loss": 3.5035, + "step": 1354752 + }, + { + "epoch": 1.02, + "learning_rate": 2.7812109570266055e-05, + "loss": 3.497, + "step": 1355264 + }, + { + "epoch": 1.02, + "learning_rate": 2.7803723622755535e-05, + "loss": 3.5007, + "step": 1355776 + }, + { + "epoch": 1.02, + "learning_rate": 2.7795354054048744e-05, + "loss": 3.507, + "step": 1356288 + }, + { + "epoch": 1.02, + "learning_rate": 2.7786968106538224e-05, + "loss": 3.5097, + "step": 1356800 + }, + { + "epoch": 1.02, + "learning_rate": 2.7778582159027704e-05, + "loss": 3.5066, + "step": 1357312 + }, + { + "epoch": 1.02, + "learning_rate": 2.7770196211517184e-05, + "loss": 3.5038, + "step": 1357824 + }, + { + "epoch": 1.02, + "learning_rate": 2.7761826642810397e-05, + "loss": 3.5123, + "step": 1358336 + }, + { + "epoch": 1.02, + "learning_rate": 2.7753440695299877e-05, + "loss": 3.5064, + "step": 1358848 + }, + { + "epoch": 1.02, + "learning_rate": 2.7745054747789357e-05, + "loss": 3.4937, + "step": 1359360 + }, + { + "epoch": 1.02, + "learning_rate": 2.7736668800278837e-05, + "loss": 3.5092, + "step": 1359872 + }, + { + "epoch": 1.02, + "learning_rate": 2.7728299231572046e-05, + "loss": 3.5016, + "step": 1360384 + }, + { + "epoch": 1.02, + "learning_rate": 2.7719913284061526e-05, + "loss": 3.5099, + "step": 1360896 + }, + { + "epoch": 1.02, + "learning_rate": 2.771152733655101e-05, + "loss": 3.4882, + "step": 1361408 + }, + { + "epoch": 1.02, + "learning_rate": 2.770314138904049e-05, + "loss": 3.5074, + "step": 1361920 + }, + { + "epoch": 1.02, + "learning_rate": 2.7694771820333698e-05, + "loss": 3.4888, + "step": 1362432 + }, + { + "epoch": 1.02, + "learning_rate": 2.7686385872823178e-05, + "loss": 3.4917, + "step": 1362944 + }, + { + "epoch": 1.02, + "learning_rate": 2.7677999925312658e-05, + "loss": 3.4909, + "step": 1363456 + }, + { + "epoch": 1.02, + "learning_rate": 2.7669613977802135e-05, + "loss": 3.5165, + "step": 1363968 + }, + { + "epoch": 1.02, + "learning_rate": 2.766124440909535e-05, + "loss": 3.5121, + "step": 1364480 + }, + { + "epoch": 1.02, + "learning_rate": 2.765285846158483e-05, + "loss": 3.5016, + "step": 1364992 + }, + { + "epoch": 1.02, + "learning_rate": 2.764447251407431e-05, + "loss": 3.5003, + "step": 1365504 + }, + { + "epoch": 1.02, + "learning_rate": 2.7636086566563784e-05, + "loss": 3.5041, + "step": 1366016 + }, + { + "epoch": 1.02, + "learning_rate": 2.7627716997857e-05, + "loss": 3.5096, + "step": 1366528 + }, + { + "epoch": 1.02, + "learning_rate": 2.761933105034648e-05, + "loss": 3.5064, + "step": 1367040 + }, + { + "epoch": 1.02, + "learning_rate": 2.7610945102835963e-05, + "loss": 3.5015, + "step": 1367552 + }, + { + "epoch": 1.02, + "learning_rate": 2.7602559155325436e-05, + "loss": 3.5082, + "step": 1368064 + }, + { + "epoch": 1.02, + "learning_rate": 2.7594189586618652e-05, + "loss": 3.5001, + "step": 1368576 + }, + { + "epoch": 1.02, + "learning_rate": 2.7585803639108132e-05, + "loss": 3.5137, + "step": 1369088 + }, + { + "epoch": 1.02, + "learning_rate": 2.757741769159761e-05, + "loss": 3.5009, + "step": 1369600 + }, + { + "epoch": 1.02, + "learning_rate": 2.7569048122890824e-05, + "loss": 3.5001, + "step": 1370112 + }, + { + "epoch": 1.02, + "learning_rate": 2.7560662175380304e-05, + "loss": 3.5022, + "step": 1370624 + }, + { + "epoch": 1.02, + "learning_rate": 2.7552276227869784e-05, + "loss": 3.497, + "step": 1371136 + }, + { + "epoch": 1.02, + "learning_rate": 2.7543890280359257e-05, + "loss": 3.5096, + "step": 1371648 + }, + { + "epoch": 1.02, + "learning_rate": 2.7535520711652473e-05, + "loss": 3.5033, + "step": 1372160 + }, + { + "epoch": 1.02, + "learning_rate": 2.7527134764141953e-05, + "loss": 3.5072, + "step": 1372672 + }, + { + "epoch": 1.02, + "learning_rate": 2.7518748816631433e-05, + "loss": 3.4999, + "step": 1373184 + }, + { + "epoch": 1.02, + "learning_rate": 2.751036286912091e-05, + "loss": 3.4966, + "step": 1373696 + }, + { + "epoch": 1.03, + "eval_loss": 3.8490428924560547, + "eval_runtime": 303.0409, + "eval_samples_per_second": 1259.206, + "eval_steps_per_second": 39.351, + "step": 1373760 + }, + { + "epoch": 0.0, + "learning_rate": 2.750197692161039e-05, + "loss": 3.4941, + "step": 1374208 + }, + { + "epoch": 0.0, + "learning_rate": 2.749359097409987e-05, + "loss": 3.4933, + "step": 1374720 + }, + { + "epoch": 0.0, + "learning_rate": 2.748520502658935e-05, + "loss": 3.506, + "step": 1375232 + }, + { + "epoch": 0.0, + "learning_rate": 2.747681907907883e-05, + "loss": 3.4959, + "step": 1375744 + }, + { + "epoch": 0.0, + "learning_rate": 2.7468449510372042e-05, + "loss": 3.5184, + "step": 1376256 + }, + { + "epoch": 0.0, + "learning_rate": 2.7460063562861522e-05, + "loss": 3.4891, + "step": 1376768 + }, + { + "epoch": 0.0, + "learning_rate": 2.7451677615351002e-05, + "loss": 3.5028, + "step": 1377280 + }, + { + "epoch": 0.0, + "learning_rate": 2.7443291667840482e-05, + "loss": 3.4868, + "step": 1377792 + }, + { + "epoch": 0.0, + "learning_rate": 2.743492209913369e-05, + "loss": 3.5038, + "step": 1378304 + }, + { + "epoch": 0.0, + "learning_rate": 2.742653615162317e-05, + "loss": 3.499, + "step": 1378816 + }, + { + "epoch": 0.0, + "learning_rate": 2.7418150204112654e-05, + "loss": 3.5031, + "step": 1379328 + }, + { + "epoch": 0.0, + "learning_rate": 2.7409764256602134e-05, + "loss": 3.4989, + "step": 1379840 + }, + { + "epoch": 0.0, + "learning_rate": 2.740141106669908e-05, + "loss": 3.4923, + "step": 1380352 + }, + { + "epoch": 0.0, + "learning_rate": 2.7393025119188552e-05, + "loss": 3.4968, + "step": 1380864 + }, + { + "epoch": 0.0, + "learning_rate": 2.7384639171678032e-05, + "loss": 3.4951, + "step": 1381376 + }, + { + "epoch": 0.0, + "learning_rate": 2.7376253224167516e-05, + "loss": 3.4909, + "step": 1381888 + }, + { + "epoch": 0.0, + "learning_rate": 2.7367867276656996e-05, + "loss": 3.4909, + "step": 1382400 + }, + { + "epoch": 0.0, + "learning_rate": 2.7359481329146476e-05, + "loss": 3.4978, + "step": 1382912 + }, + { + "epoch": 0.0, + "learning_rate": 2.7351095381635956e-05, + "loss": 3.4919, + "step": 1383424 + }, + { + "epoch": 0.0, + "learning_rate": 2.7342709434125436e-05, + "loss": 3.5153, + "step": 1383936 + }, + { + "epoch": 0.0, + "learning_rate": 2.7334339865418645e-05, + "loss": 3.4953, + "step": 1384448 + }, + { + "epoch": 0.0, + "learning_rate": 2.7325953917908125e-05, + "loss": 3.4981, + "step": 1384960 + }, + { + "epoch": 0.0, + "learning_rate": 2.7317567970397605e-05, + "loss": 3.4994, + "step": 1385472 + }, + { + "epoch": 0.0, + "learning_rate": 2.7309182022887088e-05, + "loss": 3.5087, + "step": 1385984 + }, + { + "epoch": 0.0, + "learning_rate": 2.7300812454180297e-05, + "loss": 3.4911, + "step": 1386496 + }, + { + "epoch": 0.0, + "learning_rate": 2.7292426506669777e-05, + "loss": 3.4999, + "step": 1387008 + }, + { + "epoch": 0.0, + "learning_rate": 2.7284040559159257e-05, + "loss": 3.4935, + "step": 1387520 + }, + { + "epoch": 0.0, + "learning_rate": 2.7275654611648737e-05, + "loss": 3.497, + "step": 1388032 + }, + { + "epoch": 0.0, + "learning_rate": 2.726728504294195e-05, + "loss": 3.4809, + "step": 1388544 + }, + { + "epoch": 0.01, + "learning_rate": 2.725889909543143e-05, + "loss": 3.49, + "step": 1389056 + }, + { + "epoch": 0.01, + "learning_rate": 2.725051314792091e-05, + "loss": 3.499, + "step": 1389568 + }, + { + "epoch": 0.01, + "learning_rate": 2.724212720041039e-05, + "loss": 3.4996, + "step": 1390080 + }, + { + "epoch": 0.01, + "learning_rate": 2.7233757631703598e-05, + "loss": 3.5002, + "step": 1390592 + }, + { + "epoch": 0.01, + "learning_rate": 2.7225371684193078e-05, + "loss": 3.503, + "step": 1391104 + }, + { + "epoch": 0.01, + "learning_rate": 2.7216985736682558e-05, + "loss": 3.4964, + "step": 1391616 + }, + { + "epoch": 0.01, + "learning_rate": 2.720859978917204e-05, + "loss": 3.5007, + "step": 1392128 + }, + { + "epoch": 0.01, + "learning_rate": 2.720023022046525e-05, + "loss": 3.4927, + "step": 1392640 + }, + { + "epoch": 0.01, + "learning_rate": 2.719184427295473e-05, + "loss": 3.5043, + "step": 1393152 + }, + { + "epoch": 0.01, + "learning_rate": 2.718345832544421e-05, + "loss": 3.4882, + "step": 1393664 + }, + { + "epoch": 0.01, + "learning_rate": 2.717507237793369e-05, + "loss": 3.4944, + "step": 1394176 + }, + { + "epoch": 0.01, + "learning_rate": 2.7166702809226903e-05, + "loss": 3.4935, + "step": 1394688 + }, + { + "epoch": 0.01, + "learning_rate": 2.7158316861716383e-05, + "loss": 3.5053, + "step": 1395200 + }, + { + "epoch": 0.01, + "learning_rate": 2.7149930914205863e-05, + "loss": 3.498, + "step": 1395712 + }, + { + "epoch": 0.01, + "learning_rate": 2.7141544966695343e-05, + "loss": 3.4949, + "step": 1396224 + }, + { + "epoch": 0.01, + "learning_rate": 2.7133175397988552e-05, + "loss": 3.5029, + "step": 1396736 + }, + { + "epoch": 0.01, + "learning_rate": 2.7124789450478032e-05, + "loss": 3.5002, + "step": 1397248 + }, + { + "epoch": 0.01, + "learning_rate": 2.7116403502967512e-05, + "loss": 3.4965, + "step": 1397760 + }, + { + "epoch": 0.01, + "learning_rate": 2.7108017555456995e-05, + "loss": 3.4816, + "step": 1398272 + }, + { + "epoch": 0.01, + "learning_rate": 2.7099647986750204e-05, + "loss": 3.4824, + "step": 1398784 + }, + { + "epoch": 0.01, + "learning_rate": 2.7091262039239684e-05, + "loss": 3.4982, + "step": 1399296 + }, + { + "epoch": 0.01, + "learning_rate": 2.7082876091729164e-05, + "loss": 3.4985, + "step": 1399808 + }, + { + "epoch": 0.01, + "learning_rate": 2.7074490144218644e-05, + "loss": 3.493, + "step": 1400320 + }, + { + "epoch": 0.01, + "learning_rate": 2.7066120575511857e-05, + "loss": 3.4751, + "step": 1400832 + }, + { + "epoch": 0.01, + "learning_rate": 2.7057734628001337e-05, + "loss": 3.4826, + "step": 1401344 + }, + { + "epoch": 0.01, + "learning_rate": 2.7049348680490817e-05, + "loss": 3.4823, + "step": 1401856 + }, + { + "epoch": 0.01, + "learning_rate": 2.7040979111784026e-05, + "loss": 3.4948, + "step": 1402368 + }, + { + "epoch": 0.01, + "learning_rate": 2.7032593164273506e-05, + "loss": 3.4854, + "step": 1402880 + }, + { + "epoch": 0.01, + "learning_rate": 2.7024207216762986e-05, + "loss": 3.4971, + "step": 1403392 + }, + { + "epoch": 0.01, + "learning_rate": 2.7015821269252466e-05, + "loss": 3.4948, + "step": 1403904 + }, + { + "epoch": 0.01, + "learning_rate": 2.7007451700545678e-05, + "loss": 3.4848, + "step": 1404416 + }, + { + "epoch": 0.01, + "learning_rate": 2.6999065753035158e-05, + "loss": 3.4923, + "step": 1404928 + }, + { + "epoch": 0.01, + "learning_rate": 2.6990679805524638e-05, + "loss": 3.4859, + "step": 1405440 + }, + { + "epoch": 0.01, + "learning_rate": 2.6982293858014118e-05, + "loss": 3.4791, + "step": 1405952 + }, + { + "epoch": 0.01, + "learning_rate": 2.6973924289307327e-05, + "loss": 3.4868, + "step": 1406464 + }, + { + "epoch": 0.01, + "learning_rate": 2.696553834179681e-05, + "loss": 3.4902, + "step": 1406976 + }, + { + "epoch": 0.01, + "learning_rate": 2.695715239428629e-05, + "loss": 3.4986, + "step": 1407488 + }, + { + "epoch": 0.01, + "learning_rate": 2.694876644677577e-05, + "loss": 3.4777, + "step": 1408000 + }, + { + "epoch": 0.01, + "learning_rate": 2.694039687806898e-05, + "loss": 3.4818, + "step": 1408512 + }, + { + "epoch": 0.01, + "learning_rate": 2.693201093055846e-05, + "loss": 3.4824, + "step": 1409024 + }, + { + "epoch": 0.01, + "learning_rate": 2.692362498304794e-05, + "loss": 3.5062, + "step": 1409536 + }, + { + "epoch": 0.01, + "learning_rate": 2.691523903553742e-05, + "loss": 3.4929, + "step": 1410048 + }, + { + "epoch": 0.01, + "learning_rate": 2.690686946683063e-05, + "loss": 3.4911, + "step": 1410560 + }, + { + "epoch": 0.01, + "learning_rate": 2.689848351932011e-05, + "loss": 3.508, + "step": 1411072 + }, + { + "epoch": 0.01, + "learning_rate": 2.689009757180959e-05, + "loss": 3.5011, + "step": 1411584 + }, + { + "epoch": 0.01, + "learning_rate": 2.688171162429907e-05, + "loss": 3.5038, + "step": 1412096 + }, + { + "epoch": 0.01, + "learning_rate": 2.687334205559228e-05, + "loss": 3.4937, + "step": 1412608 + }, + { + "epoch": 0.01, + "learning_rate": 2.6864956108081764e-05, + "loss": 3.4958, + "step": 1413120 + }, + { + "epoch": 0.01, + "learning_rate": 2.6856570160571244e-05, + "loss": 3.4943, + "step": 1413632 + }, + { + "epoch": 0.01, + "learning_rate": 2.6848184213060724e-05, + "loss": 3.4915, + "step": 1414144 + }, + { + "epoch": 0.01, + "learning_rate": 2.6839814644353933e-05, + "loss": 3.4938, + "step": 1414656 + }, + { + "epoch": 0.01, + "learning_rate": 2.6831428696843413e-05, + "loss": 3.4963, + "step": 1415168 + }, + { + "epoch": 0.01, + "learning_rate": 2.6823042749332893e-05, + "loss": 3.5017, + "step": 1415680 + }, + { + "epoch": 0.01, + "learning_rate": 2.6814656801822373e-05, + "loss": 3.491, + "step": 1416192 + }, + { + "epoch": 0.01, + "learning_rate": 2.6806287233115585e-05, + "loss": 3.4881, + "step": 1416704 + }, + { + "epoch": 0.01, + "learning_rate": 2.6797901285605065e-05, + "loss": 3.4759, + "step": 1417216 + }, + { + "epoch": 0.01, + "learning_rate": 2.6789515338094545e-05, + "loss": 3.4957, + "step": 1417728 + }, + { + "epoch": 0.01, + "learning_rate": 2.6781129390584025e-05, + "loss": 3.5005, + "step": 1418240 + }, + { + "epoch": 0.01, + "learning_rate": 2.6772759821877234e-05, + "loss": 3.489, + "step": 1418752 + }, + { + "epoch": 0.01, + "learning_rate": 2.6764373874366718e-05, + "loss": 3.4908, + "step": 1419264 + }, + { + "epoch": 0.02, + "learning_rate": 2.6755987926856198e-05, + "loss": 3.4979, + "step": 1419776 + }, + { + "epoch": 0.02, + "learning_rate": 2.6747618358149407e-05, + "loss": 3.4833, + "step": 1420288 + }, + { + "epoch": 0.02, + "learning_rate": 2.6739232410638887e-05, + "loss": 3.4906, + "step": 1420800 + }, + { + "epoch": 0.02, + "learning_rate": 2.6730846463128367e-05, + "loss": 3.4868, + "step": 1421312 + }, + { + "epoch": 0.02, + "learning_rate": 2.6722460515617847e-05, + "loss": 3.4963, + "step": 1421824 + }, + { + "epoch": 0.02, + "learning_rate": 2.6714074568107327e-05, + "loss": 3.4956, + "step": 1422336 + }, + { + "epoch": 0.02, + "learning_rate": 2.670568862059681e-05, + "loss": 3.4936, + "step": 1422848 + }, + { + "epoch": 0.02, + "learning_rate": 2.6697302673086283e-05, + "loss": 3.4816, + "step": 1423360 + }, + { + "epoch": 0.02, + "learning_rate": 2.6688916725575763e-05, + "loss": 3.5004, + "step": 1423872 + }, + { + "epoch": 0.02, + "learning_rate": 2.668054715686898e-05, + "loss": 3.4867, + "step": 1424384 + }, + { + "epoch": 0.02, + "learning_rate": 2.667216120935846e-05, + "loss": 3.5025, + "step": 1424896 + }, + { + "epoch": 0.02, + "learning_rate": 2.6663775261847935e-05, + "loss": 3.4925, + "step": 1425408 + }, + { + "epoch": 0.02, + "learning_rate": 2.6655389314337415e-05, + "loss": 3.4936, + "step": 1425920 + }, + { + "epoch": 0.02, + "learning_rate": 2.664701974563063e-05, + "loss": 3.4893, + "step": 1426432 + }, + { + "epoch": 0.02, + "learning_rate": 2.663865017692384e-05, + "loss": 3.503, + "step": 1426944 + }, + { + "epoch": 0.02, + "learning_rate": 2.663026422941332e-05, + "loss": 3.4778, + "step": 1427456 + }, + { + "epoch": 0.02, + "learning_rate": 2.66218782819028e-05, + "loss": 3.4826, + "step": 1427968 + }, + { + "epoch": 0.02, + "learning_rate": 2.661349233439228e-05, + "loss": 3.4903, + "step": 1428480 + }, + { + "epoch": 0.02, + "learning_rate": 2.6605106386881757e-05, + "loss": 3.4931, + "step": 1428992 + }, + { + "epoch": 0.02, + "learning_rate": 2.6596720439371237e-05, + "loss": 3.4762, + "step": 1429504 + }, + { + "epoch": 0.02, + "learning_rate": 2.6588334491860717e-05, + "loss": 3.4871, + "step": 1430016 + }, + { + "epoch": 0.02, + "learning_rate": 2.6579948544350197e-05, + "loss": 3.4771, + "step": 1430528 + }, + { + "epoch": 0.02, + "learning_rate": 2.657157897564341e-05, + "loss": 3.4892, + "step": 1431040 + }, + { + "epoch": 0.02, + "learning_rate": 2.656319302813289e-05, + "loss": 3.4841, + "step": 1431552 + }, + { + "epoch": 0.02, + "learning_rate": 2.655480708062237e-05, + "loss": 3.4843, + "step": 1432064 + }, + { + "epoch": 0.02, + "learning_rate": 2.654642113311185e-05, + "loss": 3.4972, + "step": 1432576 + }, + { + "epoch": 0.02, + "learning_rate": 2.6538051564405058e-05, + "loss": 3.4994, + "step": 1433088 + }, + { + "epoch": 0.02, + "learning_rate": 2.6529665616894538e-05, + "loss": 3.4963, + "step": 1433600 + }, + { + "epoch": 0.02, + "learning_rate": 2.6521279669384018e-05, + "loss": 3.4879, + "step": 1434112 + }, + { + "epoch": 0.02, + "learning_rate": 2.6512893721873498e-05, + "loss": 3.5019, + "step": 1434624 + }, + { + "epoch": 0.02, + "learning_rate": 2.6504540531970446e-05, + "loss": 3.4904, + "step": 1435136 + }, + { + "epoch": 0.02, + "learning_rate": 2.6496154584459926e-05, + "loss": 3.4842, + "step": 1435648 + }, + { + "epoch": 0.02, + "learning_rate": 2.64877686369494e-05, + "loss": 3.5004, + "step": 1436160 + }, + { + "epoch": 0.02, + "learning_rate": 2.647938268943888e-05, + "loss": 3.4842, + "step": 1436672 + }, + { + "epoch": 0.02, + "learning_rate": 2.6470996741928363e-05, + "loss": 3.4974, + "step": 1437184 + }, + { + "epoch": 0.02, + "learning_rate": 2.6462610794417843e-05, + "loss": 3.4794, + "step": 1437696 + }, + { + "epoch": 0.02, + "learning_rate": 2.6454224846907323e-05, + "loss": 3.4947, + "step": 1438208 + }, + { + "epoch": 0.02, + "learning_rate": 2.6445838899396803e-05, + "loss": 3.4755, + "step": 1438720 + }, + { + "epoch": 0.02, + "learning_rate": 2.6437469330690012e-05, + "loss": 3.4803, + "step": 1439232 + }, + { + "epoch": 0.02, + "learning_rate": 2.642908338317949e-05, + "loss": 3.4813, + "step": 1439744 + }, + { + "epoch": 0.02, + "learning_rate": 2.642069743566897e-05, + "loss": 3.5017, + "step": 1440256 + }, + { + "epoch": 0.02, + "learning_rate": 2.641231148815845e-05, + "loss": 3.4967, + "step": 1440768 + }, + { + "epoch": 0.02, + "learning_rate": 2.6403941919451664e-05, + "loss": 3.492, + "step": 1441280 + }, + { + "epoch": 0.02, + "learning_rate": 2.6395555971941144e-05, + "loss": 3.4877, + "step": 1441792 + }, + { + "epoch": 0.02, + "learning_rate": 2.6387170024430624e-05, + "loss": 3.4897, + "step": 1442304 + }, + { + "epoch": 0.02, + "learning_rate": 2.6378784076920104e-05, + "loss": 3.5015, + "step": 1442816 + }, + { + "epoch": 0.02, + "learning_rate": 2.6370414508213313e-05, + "loss": 3.4906, + "step": 1443328 + }, + { + "epoch": 0.02, + "learning_rate": 2.6362028560702796e-05, + "loss": 3.4866, + "step": 1443840 + }, + { + "epoch": 0.02, + "learning_rate": 2.6353642613192276e-05, + "loss": 3.4979, + "step": 1444352 + }, + { + "epoch": 0.02, + "learning_rate": 2.6345256665681756e-05, + "loss": 3.4896, + "step": 1444864 + }, + { + "epoch": 0.02, + "learning_rate": 2.6336887096974965e-05, + "loss": 3.496, + "step": 1445376 + }, + { + "epoch": 0.02, + "learning_rate": 2.6328501149464445e-05, + "loss": 3.4867, + "step": 1445888 + }, + { + "epoch": 0.02, + "learning_rate": 2.6320115201953925e-05, + "loss": 3.4885, + "step": 1446400 + }, + { + "epoch": 0.02, + "learning_rate": 2.6311729254443405e-05, + "loss": 3.4898, + "step": 1446912 + }, + { + "epoch": 0.02, + "learning_rate": 2.6303359685736618e-05, + "loss": 3.4872, + "step": 1447424 + }, + { + "epoch": 0.02, + "learning_rate": 2.6294973738226098e-05, + "loss": 3.4916, + "step": 1447936 + }, + { + "epoch": 0.02, + "learning_rate": 2.6286587790715578e-05, + "loss": 3.4955, + "step": 1448448 + }, + { + "epoch": 0.02, + "learning_rate": 2.6278201843205058e-05, + "loss": 3.49, + "step": 1448960 + }, + { + "epoch": 0.02, + "learning_rate": 2.6269832274498267e-05, + "loss": 3.487, + "step": 1449472 + }, + { + "epoch": 0.02, + "learning_rate": 2.626144632698775e-05, + "loss": 3.4844, + "step": 1449984 + }, + { + "epoch": 0.03, + "eval_loss": 3.851285457611084, + "eval_runtime": 304.8391, + "eval_samples_per_second": 1251.779, + "eval_steps_per_second": 39.119, + "step": 1450080 + }, + { + "epoch": 1.0, + "learning_rate": 2.625306037947723e-05, + "loss": 3.4832, + "step": 1450496 + }, + { + "epoch": 1.0, + "learning_rate": 2.624467443196671e-05, + "loss": 3.4825, + "step": 1451008 + }, + { + "epoch": 1.0, + "learning_rate": 2.623630486325992e-05, + "loss": 3.4921, + "step": 1451520 + }, + { + "epoch": 1.0, + "learning_rate": 2.62279189157494e-05, + "loss": 3.4822, + "step": 1452032 + }, + { + "epoch": 1.0, + "learning_rate": 2.621953296823888e-05, + "loss": 3.5068, + "step": 1452544 + }, + { + "epoch": 1.0, + "learning_rate": 2.621114702072836e-05, + "loss": 3.4756, + "step": 1453056 + }, + { + "epoch": 1.0, + "learning_rate": 2.620277745202157e-05, + "loss": 3.4894, + "step": 1453568 + }, + { + "epoch": 1.0, + "learning_rate": 2.619439150451105e-05, + "loss": 3.4731, + "step": 1454080 + }, + { + "epoch": 1.0, + "learning_rate": 2.618600555700053e-05, + "loss": 3.4889, + "step": 1454592 + }, + { + "epoch": 1.0, + "learning_rate": 2.617761960949001e-05, + "loss": 3.4875, + "step": 1455104 + }, + { + "epoch": 1.0, + "learning_rate": 2.616925004078322e-05, + "loss": 3.4865, + "step": 1455616 + }, + { + "epoch": 1.0, + "learning_rate": 2.6160864093272704e-05, + "loss": 3.4868, + "step": 1456128 + }, + { + "epoch": 1.0, + "learning_rate": 2.6152494524565913e-05, + "loss": 3.4806, + "step": 1456640 + }, + { + "epoch": 1.0, + "learning_rate": 2.6144108577055393e-05, + "loss": 3.4856, + "step": 1457152 + }, + { + "epoch": 1.0, + "learning_rate": 2.6135722629544873e-05, + "loss": 3.4811, + "step": 1457664 + }, + { + "epoch": 1.0, + "learning_rate": 2.6127336682034353e-05, + "loss": 3.4812, + "step": 1458176 + }, + { + "epoch": 1.0, + "learning_rate": 2.6118950734523833e-05, + "loss": 3.4779, + "step": 1458688 + }, + { + "epoch": 1.0, + "learning_rate": 2.6110564787013313e-05, + "loss": 3.4856, + "step": 1459200 + }, + { + "epoch": 1.0, + "learning_rate": 2.6102178839502796e-05, + "loss": 3.4826, + "step": 1459712 + }, + { + "epoch": 1.0, + "learning_rate": 2.6093792891992276e-05, + "loss": 3.4984, + "step": 1460224 + }, + { + "epoch": 1.0, + "learning_rate": 2.6085423323285485e-05, + "loss": 3.4853, + "step": 1460736 + }, + { + "epoch": 1.0, + "learning_rate": 2.6077037375774965e-05, + "loss": 3.4849, + "step": 1461248 + }, + { + "epoch": 1.0, + "learning_rate": 2.6068651428264445e-05, + "loss": 3.487, + "step": 1461760 + }, + { + "epoch": 1.0, + "learning_rate": 2.6060265480753925e-05, + "loss": 3.4965, + "step": 1462272 + }, + { + "epoch": 1.0, + "learning_rate": 2.6051895912047137e-05, + "loss": 3.4767, + "step": 1462784 + }, + { + "epoch": 1.0, + "learning_rate": 2.6043509964536617e-05, + "loss": 3.4899, + "step": 1463296 + }, + { + "epoch": 1.0, + "learning_rate": 2.6035124017026097e-05, + "loss": 3.4797, + "step": 1463808 + }, + { + "epoch": 1.0, + "learning_rate": 2.6026738069515577e-05, + "loss": 3.483, + "step": 1464320 + }, + { + "epoch": 1.0, + "learning_rate": 2.6018368500808786e-05, + "loss": 3.4692, + "step": 1464832 + }, + { + "epoch": 1.01, + "learning_rate": 2.6009982553298266e-05, + "loss": 3.4836, + "step": 1465344 + }, + { + "epoch": 1.01, + "learning_rate": 2.600159660578775e-05, + "loss": 3.4828, + "step": 1465856 + }, + { + "epoch": 1.01, + "learning_rate": 2.599321065827723e-05, + "loss": 3.488, + "step": 1466368 + }, + { + "epoch": 1.01, + "learning_rate": 2.598484108957044e-05, + "loss": 3.4853, + "step": 1466880 + }, + { + "epoch": 1.01, + "learning_rate": 2.597645514205992e-05, + "loss": 3.4915, + "step": 1467392 + }, + { + "epoch": 1.01, + "learning_rate": 2.59680691945494e-05, + "loss": 3.4794, + "step": 1467904 + }, + { + "epoch": 1.01, + "learning_rate": 2.595968324703888e-05, + "loss": 3.4884, + "step": 1468416 + }, + { + "epoch": 1.01, + "learning_rate": 2.595131367833209e-05, + "loss": 3.4815, + "step": 1468928 + }, + { + "epoch": 1.01, + "learning_rate": 2.594292773082157e-05, + "loss": 3.4919, + "step": 1469440 + }, + { + "epoch": 1.01, + "learning_rate": 2.593454178331105e-05, + "loss": 3.4744, + "step": 1469952 + }, + { + "epoch": 1.01, + "learning_rate": 2.592615583580053e-05, + "loss": 3.4818, + "step": 1470464 + }, + { + "epoch": 1.01, + "learning_rate": 2.591778626709374e-05, + "loss": 3.4817, + "step": 1470976 + }, + { + "epoch": 1.01, + "learning_rate": 2.590940031958322e-05, + "loss": 3.4936, + "step": 1471488 + }, + { + "epoch": 1.01, + "learning_rate": 2.5901014372072703e-05, + "loss": 3.4849, + "step": 1472000 + }, + { + "epoch": 1.01, + "learning_rate": 2.5892628424562183e-05, + "loss": 3.4821, + "step": 1472512 + }, + { + "epoch": 1.01, + "learning_rate": 2.5884258855855392e-05, + "loss": 3.4904, + "step": 1473024 + }, + { + "epoch": 1.01, + "learning_rate": 2.5875872908344872e-05, + "loss": 3.4861, + "step": 1473536 + }, + { + "epoch": 1.01, + "learning_rate": 2.5867486960834352e-05, + "loss": 3.4866, + "step": 1474048 + }, + { + "epoch": 1.01, + "learning_rate": 2.5859101013323832e-05, + "loss": 3.4742, + "step": 1474560 + }, + { + "epoch": 1.01, + "learning_rate": 2.5850731444617045e-05, + "loss": 3.463, + "step": 1475072 + }, + { + "epoch": 1.01, + "learning_rate": 2.5842345497106525e-05, + "loss": 3.4864, + "step": 1475584 + }, + { + "epoch": 1.01, + "learning_rate": 2.5833959549596005e-05, + "loss": 3.4838, + "step": 1476096 + }, + { + "epoch": 1.01, + "learning_rate": 2.5825589980889214e-05, + "loss": 3.4778, + "step": 1476608 + }, + { + "epoch": 1.01, + "learning_rate": 2.5817204033378694e-05, + "loss": 3.4709, + "step": 1477120 + }, + { + "epoch": 1.01, + "learning_rate": 2.5808818085868174e-05, + "loss": 3.4694, + "step": 1477632 + }, + { + "epoch": 1.01, + "learning_rate": 2.5800432138357657e-05, + "loss": 3.4665, + "step": 1478144 + }, + { + "epoch": 1.01, + "learning_rate": 2.5792062569650866e-05, + "loss": 3.4836, + "step": 1478656 + }, + { + "epoch": 1.01, + "learning_rate": 2.5783676622140346e-05, + "loss": 3.4744, + "step": 1479168 + }, + { + "epoch": 1.01, + "learning_rate": 2.5775290674629826e-05, + "loss": 3.4796, + "step": 1479680 + }, + { + "epoch": 1.01, + "learning_rate": 2.5766904727119306e-05, + "loss": 3.4853, + "step": 1480192 + }, + { + "epoch": 1.01, + "learning_rate": 2.575853515841252e-05, + "loss": 3.4715, + "step": 1480704 + }, + { + "epoch": 1.01, + "learning_rate": 2.5750149210902e-05, + "loss": 3.4765, + "step": 1481216 + }, + { + "epoch": 1.01, + "learning_rate": 2.5741763263391478e-05, + "loss": 3.4786, + "step": 1481728 + }, + { + "epoch": 1.01, + "learning_rate": 2.573337731588095e-05, + "loss": 3.4626, + "step": 1482240 + }, + { + "epoch": 1.01, + "learning_rate": 2.5725007747174167e-05, + "loss": 3.4738, + "step": 1482752 + }, + { + "epoch": 1.01, + "learning_rate": 2.5716621799663647e-05, + "loss": 3.4808, + "step": 1483264 + }, + { + "epoch": 1.01, + "learning_rate": 2.5708235852153127e-05, + "loss": 3.4825, + "step": 1483776 + }, + { + "epoch": 1.01, + "learning_rate": 2.5699849904642604e-05, + "loss": 3.4656, + "step": 1484288 + }, + { + "epoch": 1.01, + "learning_rate": 2.569148033593582e-05, + "loss": 3.4732, + "step": 1484800 + }, + { + "epoch": 1.01, + "learning_rate": 2.56830943884253e-05, + "loss": 3.4689, + "step": 1485312 + }, + { + "epoch": 1.01, + "learning_rate": 2.567470844091478e-05, + "loss": 3.4898, + "step": 1485824 + }, + { + "epoch": 1.01, + "learning_rate": 2.5666322493404256e-05, + "loss": 3.4824, + "step": 1486336 + }, + { + "epoch": 1.01, + "learning_rate": 2.565795292469747e-05, + "loss": 3.4819, + "step": 1486848 + }, + { + "epoch": 1.01, + "learning_rate": 2.5649566977186952e-05, + "loss": 3.4935, + "step": 1487360 + }, + { + "epoch": 1.01, + "learning_rate": 2.5641181029676425e-05, + "loss": 3.4901, + "step": 1487872 + }, + { + "epoch": 1.01, + "learning_rate": 2.5632795082165905e-05, + "loss": 3.4948, + "step": 1488384 + }, + { + "epoch": 1.01, + "learning_rate": 2.562442551345912e-05, + "loss": 3.4768, + "step": 1488896 + }, + { + "epoch": 1.01, + "learning_rate": 2.5616055944752334e-05, + "loss": 3.4845, + "step": 1489408 + }, + { + "epoch": 1.01, + "learning_rate": 2.5607669997241813e-05, + "loss": 3.4841, + "step": 1489920 + }, + { + "epoch": 1.01, + "learning_rate": 2.5599284049731293e-05, + "loss": 3.4797, + "step": 1490432 + }, + { + "epoch": 1.01, + "learning_rate": 2.5590898102220773e-05, + "loss": 3.485, + "step": 1490944 + }, + { + "epoch": 1.01, + "learning_rate": 2.5582512154710253e-05, + "loss": 3.483, + "step": 1491456 + }, + { + "epoch": 1.01, + "learning_rate": 2.5574126207199727e-05, + "loss": 3.4872, + "step": 1491968 + }, + { + "epoch": 1.01, + "learning_rate": 2.556574025968921e-05, + "loss": 3.4803, + "step": 1492480 + }, + { + "epoch": 1.01, + "learning_rate": 2.555735431217869e-05, + "loss": 3.4698, + "step": 1492992 + }, + { + "epoch": 1.01, + "learning_rate": 2.55489847434719e-05, + "loss": 3.4672, + "step": 1493504 + }, + { + "epoch": 1.01, + "learning_rate": 2.554059879596138e-05, + "loss": 3.4837, + "step": 1494016 + }, + { + "epoch": 1.01, + "learning_rate": 2.553221284845086e-05, + "loss": 3.4878, + "step": 1494528 + }, + { + "epoch": 1.01, + "learning_rate": 2.552382690094034e-05, + "loss": 3.4776, + "step": 1495040 + }, + { + "epoch": 1.01, + "learning_rate": 2.551545733223355e-05, + "loss": 3.4763, + "step": 1495552 + }, + { + "epoch": 1.02, + "learning_rate": 2.550707138472303e-05, + "loss": 3.4857, + "step": 1496064 + }, + { + "epoch": 1.02, + "learning_rate": 2.5498701816016247e-05, + "loss": 3.4744, + "step": 1496576 + }, + { + "epoch": 1.02, + "learning_rate": 2.5490315868505727e-05, + "loss": 3.4736, + "step": 1497088 + }, + { + "epoch": 1.02, + "learning_rate": 2.54819299209952e-05, + "loss": 3.481, + "step": 1497600 + }, + { + "epoch": 1.02, + "learning_rate": 2.547354397348468e-05, + "loss": 3.4868, + "step": 1498112 + }, + { + "epoch": 1.02, + "learning_rate": 2.546515802597416e-05, + "loss": 3.4855, + "step": 1498624 + }, + { + "epoch": 1.02, + "learning_rate": 2.5456772078463643e-05, + "loss": 3.479, + "step": 1499136 + }, + { + "epoch": 1.02, + "learning_rate": 2.5448386130953123e-05, + "loss": 3.4661, + "step": 1499648 + }, + { + "epoch": 1.02, + "learning_rate": 2.5440000183442603e-05, + "loss": 3.4897, + "step": 1500160 + }, + { + "epoch": 1.02, + "learning_rate": 2.5431630614735812e-05, + "loss": 3.4724, + "step": 1500672 + }, + { + "epoch": 1.02, + "learning_rate": 2.5423244667225292e-05, + "loss": 3.4921, + "step": 1501184 + }, + { + "epoch": 1.02, + "learning_rate": 2.5414858719714772e-05, + "loss": 3.4818, + "step": 1501696 + }, + { + "epoch": 1.02, + "learning_rate": 2.5406472772204252e-05, + "loss": 3.4818, + "step": 1502208 + }, + { + "epoch": 1.02, + "learning_rate": 2.5398103203497465e-05, + "loss": 3.4763, + "step": 1502720 + }, + { + "epoch": 1.02, + "learning_rate": 2.5389733634790674e-05, + "loss": 3.4897, + "step": 1503232 + }, + { + "epoch": 1.02, + "learning_rate": 2.5381347687280154e-05, + "loss": 3.4657, + "step": 1503744 + }, + { + "epoch": 1.02, + "learning_rate": 2.5372961739769634e-05, + "loss": 3.4729, + "step": 1504256 + }, + { + "epoch": 1.02, + "learning_rate": 2.5364575792259114e-05, + "loss": 3.4717, + "step": 1504768 + }, + { + "epoch": 1.02, + "learning_rate": 2.5356189844748597e-05, + "loss": 3.4816, + "step": 1505280 + }, + { + "epoch": 1.02, + "learning_rate": 2.5347803897238077e-05, + "loss": 3.4655, + "step": 1505792 + }, + { + "epoch": 1.02, + "learning_rate": 2.5339417949727557e-05, + "loss": 3.4754, + "step": 1506304 + }, + { + "epoch": 1.02, + "learning_rate": 2.5331032002217037e-05, + "loss": 3.472, + "step": 1506816 + }, + { + "epoch": 1.02, + "learning_rate": 2.5322662433510246e-05, + "loss": 3.4718, + "step": 1507328 + }, + { + "epoch": 1.02, + "learning_rate": 2.5314276485999726e-05, + "loss": 3.4758, + "step": 1507840 + }, + { + "epoch": 1.02, + "learning_rate": 2.5305890538489206e-05, + "loss": 3.469, + "step": 1508352 + }, + { + "epoch": 1.02, + "learning_rate": 2.529750459097869e-05, + "loss": 3.487, + "step": 1508864 + }, + { + "epoch": 1.02, + "learning_rate": 2.5289151401075628e-05, + "loss": 3.4847, + "step": 1509376 + }, + { + "epoch": 1.02, + "learning_rate": 2.5280765453565108e-05, + "loss": 3.4831, + "step": 1509888 + }, + { + "epoch": 1.02, + "learning_rate": 2.5272379506054588e-05, + "loss": 3.4755, + "step": 1510400 + }, + { + "epoch": 1.02, + "learning_rate": 2.5263993558544067e-05, + "loss": 3.4852, + "step": 1510912 + }, + { + "epoch": 1.02, + "learning_rate": 2.525560761103355e-05, + "loss": 3.4834, + "step": 1511424 + }, + { + "epoch": 1.02, + "learning_rate": 2.524722166352303e-05, + "loss": 3.4687, + "step": 1511936 + }, + { + "epoch": 1.02, + "learning_rate": 2.523883571601251e-05, + "loss": 3.4861, + "step": 1512448 + }, + { + "epoch": 1.02, + "learning_rate": 2.523044976850199e-05, + "loss": 3.4737, + "step": 1512960 + }, + { + "epoch": 1.02, + "learning_rate": 2.52220801997952e-05, + "loss": 3.4842, + "step": 1513472 + }, + { + "epoch": 1.02, + "learning_rate": 2.521369425228468e-05, + "loss": 3.4703, + "step": 1513984 + }, + { + "epoch": 1.02, + "learning_rate": 2.520530830477416e-05, + "loss": 3.4795, + "step": 1514496 + }, + { + "epoch": 1.02, + "learning_rate": 2.5196922357263643e-05, + "loss": 3.4621, + "step": 1515008 + }, + { + "epoch": 1.02, + "learning_rate": 2.5188552788556852e-05, + "loss": 3.4706, + "step": 1515520 + }, + { + "epoch": 1.02, + "learning_rate": 2.5180166841046332e-05, + "loss": 3.4703, + "step": 1516032 + }, + { + "epoch": 1.02, + "learning_rate": 2.5171780893535812e-05, + "loss": 3.484, + "step": 1516544 + }, + { + "epoch": 1.02, + "learning_rate": 2.5163394946025292e-05, + "loss": 3.4806, + "step": 1517056 + }, + { + "epoch": 1.02, + "learning_rate": 2.5155025377318504e-05, + "loss": 3.4831, + "step": 1517568 + }, + { + "epoch": 1.02, + "learning_rate": 2.5146639429807984e-05, + "loss": 3.4761, + "step": 1518080 + }, + { + "epoch": 1.02, + "learning_rate": 2.5138253482297464e-05, + "loss": 3.48, + "step": 1518592 + }, + { + "epoch": 1.02, + "learning_rate": 2.5129867534786944e-05, + "loss": 3.4878, + "step": 1519104 + }, + { + "epoch": 1.02, + "learning_rate": 2.5121497966080153e-05, + "loss": 3.4809, + "step": 1519616 + }, + { + "epoch": 1.02, + "learning_rate": 2.5113112018569633e-05, + "loss": 3.4744, + "step": 1520128 + }, + { + "epoch": 1.02, + "learning_rate": 2.5104726071059113e-05, + "loss": 3.4854, + "step": 1520640 + }, + { + "epoch": 1.02, + "learning_rate": 2.5096340123548597e-05, + "loss": 3.479, + "step": 1521152 + }, + { + "epoch": 1.02, + "learning_rate": 2.5087970554841806e-05, + "loss": 3.4875, + "step": 1521664 + }, + { + "epoch": 1.02, + "learning_rate": 2.5079584607331286e-05, + "loss": 3.4709, + "step": 1522176 + }, + { + "epoch": 1.02, + "learning_rate": 2.5071198659820766e-05, + "loss": 3.4816, + "step": 1522688 + }, + { + "epoch": 1.02, + "learning_rate": 2.5062812712310246e-05, + "loss": 3.4766, + "step": 1523200 + }, + { + "epoch": 1.02, + "learning_rate": 2.5054443143603458e-05, + "loss": 3.4747, + "step": 1523712 + }, + { + "epoch": 1.02, + "learning_rate": 2.5046057196092938e-05, + "loss": 3.4805, + "step": 1524224 + }, + { + "epoch": 1.02, + "learning_rate": 2.5037671248582418e-05, + "loss": 3.4824, + "step": 1524736 + }, + { + "epoch": 1.02, + "learning_rate": 2.5029285301071898e-05, + "loss": 3.481, + "step": 1525248 + }, + { + "epoch": 1.02, + "learning_rate": 2.5020915732365107e-05, + "loss": 3.47, + "step": 1525760 + }, + { + "epoch": 1.02, + "learning_rate": 2.5012529784854587e-05, + "loss": 3.4781, + "step": 1526272 + }, + { + "epoch": 1.03, + "eval_loss": 3.852071523666382, + "eval_runtime": 302.8165, + "eval_samples_per_second": 1260.139, + "eval_steps_per_second": 39.38, + "step": 1526400 + }, + { + "epoch": 0.0, + "learning_rate": 2.5004143837344067e-05, + "loss": 3.4694, + "step": 1526784 + }, + { + "epoch": 0.0, + "learning_rate": 2.4995757889833547e-05, + "loss": 3.4681, + "step": 1527296 + }, + { + "epoch": 0.0, + "learning_rate": 2.4987371942323027e-05, + "loss": 3.4789, + "step": 1527808 + }, + { + "epoch": 0.0, + "learning_rate": 2.4978985994812507e-05, + "loss": 3.4711, + "step": 1528320 + }, + { + "epoch": 0.0, + "learning_rate": 2.4970616426105716e-05, + "loss": 3.4937, + "step": 1528832 + }, + { + "epoch": 0.0, + "learning_rate": 2.4962230478595196e-05, + "loss": 3.4722, + "step": 1529344 + }, + { + "epoch": 0.0, + "learning_rate": 2.4953844531084676e-05, + "loss": 3.4736, + "step": 1529856 + }, + { + "epoch": 0.0, + "learning_rate": 2.494545858357416e-05, + "loss": 3.4608, + "step": 1530368 + }, + { + "epoch": 0.0, + "learning_rate": 2.493708901486737e-05, + "loss": 3.4764, + "step": 1530880 + }, + { + "epoch": 0.0, + "learning_rate": 2.4928703067356848e-05, + "loss": 3.4798, + "step": 1531392 + }, + { + "epoch": 0.0, + "learning_rate": 2.4920317119846328e-05, + "loss": 3.4727, + "step": 1531904 + }, + { + "epoch": 0.0, + "learning_rate": 2.4911931172335808e-05, + "loss": 3.4732, + "step": 1532416 + }, + { + "epoch": 0.0, + "learning_rate": 2.4903577982432753e-05, + "loss": 3.4668, + "step": 1532928 + }, + { + "epoch": 0.0, + "learning_rate": 2.4895192034922233e-05, + "loss": 3.4719, + "step": 1533440 + }, + { + "epoch": 0.0, + "learning_rate": 2.4886806087411713e-05, + "loss": 3.4719, + "step": 1533952 + }, + { + "epoch": 0.0, + "learning_rate": 2.487842013990119e-05, + "loss": 3.4662, + "step": 1534464 + }, + { + "epoch": 0.0, + "learning_rate": 2.487003419239067e-05, + "loss": 3.464, + "step": 1534976 + }, + { + "epoch": 0.0, + "learning_rate": 2.486164824488015e-05, + "loss": 3.4761, + "step": 1535488 + }, + { + "epoch": 0.0, + "learning_rate": 2.485326229736963e-05, + "loss": 3.4691, + "step": 1536000 + }, + { + "epoch": 0.0, + "learning_rate": 2.4844876349859113e-05, + "loss": 3.4825, + "step": 1536512 + }, + { + "epoch": 0.0, + "learning_rate": 2.4836506781152322e-05, + "loss": 3.4765, + "step": 1537024 + }, + { + "epoch": 0.0, + "learning_rate": 2.4828120833641802e-05, + "loss": 3.4741, + "step": 1537536 + }, + { + "epoch": 0.0, + "learning_rate": 2.4819734886131282e-05, + "loss": 3.474, + "step": 1538048 + }, + { + "epoch": 0.0, + "learning_rate": 2.4811348938620762e-05, + "loss": 3.4822, + "step": 1538560 + }, + { + "epoch": 0.0, + "learning_rate": 2.4802979369913974e-05, + "loss": 3.4666, + "step": 1539072 + }, + { + "epoch": 0.0, + "learning_rate": 2.4794593422403454e-05, + "loss": 3.4749, + "step": 1539584 + }, + { + "epoch": 0.0, + "learning_rate": 2.4786207474892934e-05, + "loss": 3.4721, + "step": 1540096 + }, + { + "epoch": 0.0, + "learning_rate": 2.4777821527382414e-05, + "loss": 3.4665, + "step": 1540608 + }, + { + "epoch": 0.0, + "learning_rate": 2.4769451958675623e-05, + "loss": 3.4609, + "step": 1541120 + }, + { + "epoch": 0.0, + "learning_rate": 2.4761066011165103e-05, + "loss": 3.4695, + "step": 1541632 + }, + { + "epoch": 0.01, + "learning_rate": 2.4752680063654583e-05, + "loss": 3.4764, + "step": 1542144 + }, + { + "epoch": 0.01, + "learning_rate": 2.4744294116144067e-05, + "loss": 3.4761, + "step": 1542656 + }, + { + "epoch": 0.01, + "learning_rate": 2.4735924547437276e-05, + "loss": 3.4778, + "step": 1543168 + }, + { + "epoch": 0.01, + "learning_rate": 2.4727538599926756e-05, + "loss": 3.4778, + "step": 1543680 + }, + { + "epoch": 0.01, + "learning_rate": 2.4719152652416236e-05, + "loss": 3.4683, + "step": 1544192 + }, + { + "epoch": 0.01, + "learning_rate": 2.4710766704905716e-05, + "loss": 3.474, + "step": 1544704 + }, + { + "epoch": 0.01, + "learning_rate": 2.4702397136198928e-05, + "loss": 3.4703, + "step": 1545216 + }, + { + "epoch": 0.01, + "learning_rate": 2.4694011188688408e-05, + "loss": 3.4765, + "step": 1545728 + }, + { + "epoch": 0.01, + "learning_rate": 2.4685625241177888e-05, + "loss": 3.4638, + "step": 1546240 + }, + { + "epoch": 0.01, + "learning_rate": 2.4677239293667364e-05, + "loss": 3.4693, + "step": 1546752 + }, + { + "epoch": 0.01, + "learning_rate": 2.4668869724960577e-05, + "loss": 3.4694, + "step": 1547264 + }, + { + "epoch": 0.01, + "learning_rate": 2.4660483777450057e-05, + "loss": 3.4798, + "step": 1547776 + }, + { + "epoch": 0.01, + "learning_rate": 2.4652097829939537e-05, + "loss": 3.4736, + "step": 1548288 + }, + { + "epoch": 0.01, + "learning_rate": 2.4643711882429017e-05, + "loss": 3.4698, + "step": 1548800 + }, + { + "epoch": 0.01, + "learning_rate": 2.463534231372223e-05, + "loss": 3.4825, + "step": 1549312 + }, + { + "epoch": 0.01, + "learning_rate": 2.462695636621171e-05, + "loss": 3.4716, + "step": 1549824 + }, + { + "epoch": 0.01, + "learning_rate": 2.461857041870119e-05, + "loss": 3.4705, + "step": 1550336 + }, + { + "epoch": 0.01, + "learning_rate": 2.4610184471190666e-05, + "loss": 3.4637, + "step": 1550848 + }, + { + "epoch": 0.01, + "learning_rate": 2.460181490248388e-05, + "loss": 3.4506, + "step": 1551360 + }, + { + "epoch": 0.01, + "learning_rate": 2.459342895497336e-05, + "loss": 3.4765, + "step": 1551872 + }, + { + "epoch": 0.01, + "learning_rate": 2.4585043007462838e-05, + "loss": 3.4737, + "step": 1552384 + }, + { + "epoch": 0.01, + "learning_rate": 2.457667343875605e-05, + "loss": 3.4679, + "step": 1552896 + }, + { + "epoch": 0.01, + "learning_rate": 2.456828749124553e-05, + "loss": 3.4543, + "step": 1553408 + }, + { + "epoch": 0.01, + "learning_rate": 2.455990154373501e-05, + "loss": 3.4604, + "step": 1553920 + }, + { + "epoch": 0.01, + "learning_rate": 2.455151559622449e-05, + "loss": 3.4535, + "step": 1554432 + }, + { + "epoch": 0.01, + "learning_rate": 2.4543146027517703e-05, + "loss": 3.4749, + "step": 1554944 + }, + { + "epoch": 0.01, + "learning_rate": 2.4534760080007183e-05, + "loss": 3.4627, + "step": 1555456 + }, + { + "epoch": 0.01, + "learning_rate": 2.4526374132496663e-05, + "loss": 3.4652, + "step": 1555968 + }, + { + "epoch": 0.01, + "learning_rate": 2.451798818498614e-05, + "loss": 3.4745, + "step": 1556480 + }, + { + "epoch": 0.01, + "learning_rate": 2.4509618616279352e-05, + "loss": 3.4625, + "step": 1556992 + }, + { + "epoch": 0.01, + "learning_rate": 2.4501232668768835e-05, + "loss": 3.4661, + "step": 1557504 + }, + { + "epoch": 0.01, + "learning_rate": 2.4492846721258312e-05, + "loss": 3.47, + "step": 1558016 + }, + { + "epoch": 0.01, + "learning_rate": 2.4484460773747792e-05, + "loss": 3.451, + "step": 1558528 + }, + { + "epoch": 0.01, + "learning_rate": 2.4476091205041004e-05, + "loss": 3.462, + "step": 1559040 + }, + { + "epoch": 0.01, + "learning_rate": 2.4467705257530484e-05, + "loss": 3.4649, + "step": 1559552 + }, + { + "epoch": 0.01, + "learning_rate": 2.445931931001996e-05, + "loss": 3.4734, + "step": 1560064 + }, + { + "epoch": 0.01, + "learning_rate": 2.4450933362509444e-05, + "loss": 3.4543, + "step": 1560576 + }, + { + "epoch": 0.01, + "learning_rate": 2.4442563793802657e-05, + "loss": 3.4625, + "step": 1561088 + }, + { + "epoch": 0.01, + "learning_rate": 2.4434177846292137e-05, + "loss": 3.4542, + "step": 1561600 + }, + { + "epoch": 0.01, + "learning_rate": 2.4425791898781613e-05, + "loss": 3.4777, + "step": 1562112 + }, + { + "epoch": 0.01, + "learning_rate": 2.4417405951271093e-05, + "loss": 3.4705, + "step": 1562624 + }, + { + "epoch": 0.01, + "learning_rate": 2.4409036382564306e-05, + "loss": 3.4656, + "step": 1563136 + }, + { + "epoch": 0.01, + "learning_rate": 2.4400666813857518e-05, + "loss": 3.4843, + "step": 1563648 + }, + { + "epoch": 0.01, + "learning_rate": 2.4392280866346998e-05, + "loss": 3.4741, + "step": 1564160 + }, + { + "epoch": 0.01, + "learning_rate": 2.4383894918836478e-05, + "loss": 3.4909, + "step": 1564672 + }, + { + "epoch": 0.01, + "learning_rate": 2.4375508971325958e-05, + "loss": 3.4656, + "step": 1565184 + }, + { + "epoch": 0.01, + "learning_rate": 2.4367123023815435e-05, + "loss": 3.4698, + "step": 1565696 + }, + { + "epoch": 0.01, + "learning_rate": 2.4358737076304915e-05, + "loss": 3.4727, + "step": 1566208 + }, + { + "epoch": 0.01, + "learning_rate": 2.4350351128794398e-05, + "loss": 3.4663, + "step": 1566720 + }, + { + "epoch": 0.01, + "learning_rate": 2.4341965181283878e-05, + "loss": 3.4777, + "step": 1567232 + }, + { + "epoch": 0.01, + "learning_rate": 2.4333595612577087e-05, + "loss": 3.4699, + "step": 1567744 + }, + { + "epoch": 0.01, + "learning_rate": 2.4325209665066567e-05, + "loss": 3.4756, + "step": 1568256 + }, + { + "epoch": 0.01, + "learning_rate": 2.4316823717556047e-05, + "loss": 3.4682, + "step": 1568768 + }, + { + "epoch": 0.01, + "learning_rate": 2.4308437770045527e-05, + "loss": 3.4593, + "step": 1569280 + }, + { + "epoch": 0.01, + "learning_rate": 2.430006820133874e-05, + "loss": 3.4629, + "step": 1569792 + }, + { + "epoch": 0.01, + "learning_rate": 2.4291698632631952e-05, + "loss": 3.4618, + "step": 1570304 + }, + { + "epoch": 0.01, + "learning_rate": 2.4283312685121432e-05, + "loss": 3.4763, + "step": 1570816 + }, + { + "epoch": 0.01, + "learning_rate": 2.427492673761091e-05, + "loss": 3.4686, + "step": 1571328 + }, + { + "epoch": 0.01, + "learning_rate": 2.4266540790100388e-05, + "loss": 3.4626, + "step": 1571840 + }, + { + "epoch": 0.02, + "learning_rate": 2.4258154842589868e-05, + "loss": 3.4737, + "step": 1572352 + }, + { + "epoch": 0.02, + "learning_rate": 2.4249785273883084e-05, + "loss": 3.4672, + "step": 1572864 + }, + { + "epoch": 0.02, + "learning_rate": 2.424139932637256e-05, + "loss": 3.4573, + "step": 1573376 + }, + { + "epoch": 0.02, + "learning_rate": 2.423301337886204e-05, + "loss": 3.4656, + "step": 1573888 + }, + { + "epoch": 0.02, + "learning_rate": 2.422462743135152e-05, + "loss": 3.4757, + "step": 1574400 + }, + { + "epoch": 0.02, + "learning_rate": 2.4216241483841e-05, + "loss": 3.4744, + "step": 1574912 + }, + { + "epoch": 0.02, + "learning_rate": 2.420785553633048e-05, + "loss": 3.4695, + "step": 1575424 + }, + { + "epoch": 0.02, + "learning_rate": 2.419946958881996e-05, + "loss": 3.4536, + "step": 1575936 + }, + { + "epoch": 0.02, + "learning_rate": 2.419108364130944e-05, + "loss": 3.4756, + "step": 1576448 + }, + { + "epoch": 0.02, + "learning_rate": 2.4182714072602653e-05, + "loss": 3.4597, + "step": 1576960 + }, + { + "epoch": 0.02, + "learning_rate": 2.4174328125092133e-05, + "loss": 3.4761, + "step": 1577472 + }, + { + "epoch": 0.02, + "learning_rate": 2.4165942177581613e-05, + "loss": 3.4725, + "step": 1577984 + }, + { + "epoch": 0.02, + "learning_rate": 2.415755623007109e-05, + "loss": 3.4692, + "step": 1578496 + }, + { + "epoch": 0.02, + "learning_rate": 2.4149186661364305e-05, + "loss": 3.4641, + "step": 1579008 + }, + { + "epoch": 0.02, + "learning_rate": 2.4140817092657514e-05, + "loss": 3.4791, + "step": 1579520 + }, + { + "epoch": 0.02, + "learning_rate": 2.4132431145146994e-05, + "loss": 3.4539, + "step": 1580032 + }, + { + "epoch": 0.02, + "learning_rate": 2.4124045197636474e-05, + "loss": 3.4612, + "step": 1580544 + }, + { + "epoch": 0.02, + "learning_rate": 2.4115659250125954e-05, + "loss": 3.4585, + "step": 1581056 + }, + { + "epoch": 0.02, + "learning_rate": 2.4107273302615434e-05, + "loss": 3.4758, + "step": 1581568 + }, + { + "epoch": 0.02, + "learning_rate": 2.4098887355104914e-05, + "loss": 3.4504, + "step": 1582080 + }, + { + "epoch": 0.02, + "learning_rate": 2.4090501407594394e-05, + "loss": 3.4638, + "step": 1582592 + }, + { + "epoch": 0.02, + "learning_rate": 2.4082115460083874e-05, + "loss": 3.4611, + "step": 1583104 + }, + { + "epoch": 0.02, + "learning_rate": 2.4073745891377086e-05, + "loss": 3.4615, + "step": 1583616 + }, + { + "epoch": 0.02, + "learning_rate": 2.4065359943866563e-05, + "loss": 3.4639, + "step": 1584128 + }, + { + "epoch": 0.02, + "learning_rate": 2.4056973996356043e-05, + "loss": 3.4617, + "step": 1584640 + }, + { + "epoch": 0.02, + "learning_rate": 2.4048588048845523e-05, + "loss": 3.4737, + "step": 1585152 + }, + { + "epoch": 0.02, + "learning_rate": 2.4040234858942468e-05, + "loss": 3.4749, + "step": 1585664 + }, + { + "epoch": 0.02, + "learning_rate": 2.4031848911431948e-05, + "loss": 3.4688, + "step": 1586176 + }, + { + "epoch": 0.02, + "learning_rate": 2.4023462963921428e-05, + "loss": 3.4618, + "step": 1586688 + }, + { + "epoch": 0.02, + "learning_rate": 2.4015077016410908e-05, + "loss": 3.4762, + "step": 1587200 + }, + { + "epoch": 0.02, + "learning_rate": 2.4006691068900384e-05, + "loss": 3.468, + "step": 1587712 + }, + { + "epoch": 0.02, + "learning_rate": 2.3998305121389868e-05, + "loss": 3.4582, + "step": 1588224 + }, + { + "epoch": 0.02, + "learning_rate": 2.3989919173879348e-05, + "loss": 3.4767, + "step": 1588736 + }, + { + "epoch": 0.02, + "learning_rate": 2.3981533226368828e-05, + "loss": 3.4614, + "step": 1589248 + }, + { + "epoch": 0.02, + "learning_rate": 2.3973163657662037e-05, + "loss": 3.4719, + "step": 1589760 + }, + { + "epoch": 0.02, + "learning_rate": 2.3964777710151517e-05, + "loss": 3.4571, + "step": 1590272 + }, + { + "epoch": 0.02, + "learning_rate": 2.3956391762640997e-05, + "loss": 3.4694, + "step": 1590784 + }, + { + "epoch": 0.02, + "learning_rate": 2.3948005815130477e-05, + "loss": 3.4564, + "step": 1591296 + }, + { + "epoch": 0.02, + "learning_rate": 2.393963624642369e-05, + "loss": 3.4575, + "step": 1591808 + }, + { + "epoch": 0.02, + "learning_rate": 2.393125029891317e-05, + "loss": 3.4617, + "step": 1592320 + }, + { + "epoch": 0.02, + "learning_rate": 2.392286435140265e-05, + "loss": 3.4696, + "step": 1592832 + }, + { + "epoch": 0.02, + "learning_rate": 2.391447840389213e-05, + "loss": 3.4677, + "step": 1593344 + }, + { + "epoch": 0.02, + "learning_rate": 2.3906108835185338e-05, + "loss": 3.4726, + "step": 1593856 + }, + { + "epoch": 0.02, + "learning_rate": 2.389772288767482e-05, + "loss": 3.4619, + "step": 1594368 + }, + { + "epoch": 0.02, + "learning_rate": 2.38893369401643e-05, + "loss": 3.4717, + "step": 1594880 + }, + { + "epoch": 0.02, + "learning_rate": 2.388095099265378e-05, + "loss": 3.4761, + "step": 1595392 + }, + { + "epoch": 0.02, + "learning_rate": 2.387258142394699e-05, + "loss": 3.4694, + "step": 1595904 + }, + { + "epoch": 0.02, + "learning_rate": 2.386419547643647e-05, + "loss": 3.4626, + "step": 1596416 + }, + { + "epoch": 0.02, + "learning_rate": 2.385580952892595e-05, + "loss": 3.4719, + "step": 1596928 + }, + { + "epoch": 0.02, + "learning_rate": 2.384742358141543e-05, + "loss": 3.4652, + "step": 1597440 + }, + { + "epoch": 0.02, + "learning_rate": 2.3839054012708643e-05, + "loss": 3.4759, + "step": 1597952 + }, + { + "epoch": 0.02, + "learning_rate": 2.3830668065198123e-05, + "loss": 3.4587, + "step": 1598464 + }, + { + "epoch": 0.02, + "learning_rate": 2.3822282117687603e-05, + "loss": 3.4679, + "step": 1598976 + }, + { + "epoch": 0.02, + "learning_rate": 2.3813896170177083e-05, + "loss": 3.4633, + "step": 1599488 + }, + { + "epoch": 0.02, + "learning_rate": 2.3805526601470292e-05, + "loss": 3.4649, + "step": 1600000 + }, + { + "epoch": 0.02, + "learning_rate": 2.3797140653959775e-05, + "loss": 3.4679, + "step": 1600512 + }, + { + "epoch": 0.02, + "learning_rate": 2.3788754706449255e-05, + "loss": 3.4683, + "step": 1601024 + }, + { + "epoch": 0.02, + "learning_rate": 2.3780368758938735e-05, + "loss": 3.4702, + "step": 1601536 + }, + { + "epoch": 0.02, + "learning_rate": 2.3771999190231944e-05, + "loss": 3.4535, + "step": 1602048 + }, + { + "epoch": 0.02, + "learning_rate": 2.3763613242721424e-05, + "loss": 3.4691, + "step": 1602560 + }, + { + "epoch": 0.03, + "eval_loss": 3.854646682739258, + "eval_runtime": 304.4531, + "eval_samples_per_second": 1253.365, + "eval_steps_per_second": 39.169, + "step": 1602720 + }, + { + "epoch": 1.0, + "learning_rate": 2.3755227295210904e-05, + "loss": 3.46, + "step": 1603072 + }, + { + "epoch": 1.0, + "learning_rate": 2.3746841347700384e-05, + "loss": 3.4556, + "step": 1603584 + }, + { + "epoch": 1.0, + "learning_rate": 2.3738471778993596e-05, + "loss": 3.4688, + "step": 1604096 + }, + { + "epoch": 1.0, + "learning_rate": 2.3730085831483076e-05, + "loss": 3.4622, + "step": 1604608 + }, + { + "epoch": 1.0, + "learning_rate": 2.3721699883972556e-05, + "loss": 3.4786, + "step": 1605120 + }, + { + "epoch": 1.0, + "learning_rate": 2.3713313936462036e-05, + "loss": 3.4638, + "step": 1605632 + }, + { + "epoch": 1.0, + "learning_rate": 2.3704944367755245e-05, + "loss": 3.4554, + "step": 1606144 + }, + { + "epoch": 1.0, + "learning_rate": 2.369655842024473e-05, + "loss": 3.4578, + "step": 1606656 + }, + { + "epoch": 1.0, + "learning_rate": 2.368817247273421e-05, + "loss": 3.459, + "step": 1607168 + }, + { + "epoch": 1.0, + "learning_rate": 2.367978652522369e-05, + "loss": 3.4672, + "step": 1607680 + }, + { + "epoch": 1.0, + "learning_rate": 2.3671400577713165e-05, + "loss": 3.4611, + "step": 1608192 + }, + { + "epoch": 1.0, + "learning_rate": 2.3663014630202645e-05, + "loss": 3.4627, + "step": 1608704 + }, + { + "epoch": 1.0, + "learning_rate": 2.3654645061495858e-05, + "loss": 3.4594, + "step": 1609216 + }, + { + "epoch": 1.0, + "learning_rate": 2.3646259113985338e-05, + "loss": 3.4556, + "step": 1609728 + }, + { + "epoch": 1.0, + "learning_rate": 2.3637873166474818e-05, + "loss": 3.4624, + "step": 1610240 + }, + { + "epoch": 1.0, + "learning_rate": 2.3629487218964298e-05, + "loss": 3.4542, + "step": 1610752 + }, + { + "epoch": 1.0, + "learning_rate": 2.3621101271453778e-05, + "loss": 3.4531, + "step": 1611264 + }, + { + "epoch": 1.0, + "learning_rate": 2.3612715323943257e-05, + "loss": 3.4631, + "step": 1611776 + }, + { + "epoch": 1.0, + "learning_rate": 2.3604329376432737e-05, + "loss": 3.4624, + "step": 1612288 + }, + { + "epoch": 1.0, + "learning_rate": 2.3595943428922217e-05, + "loss": 3.4705, + "step": 1612800 + }, + { + "epoch": 1.0, + "learning_rate": 2.358757386021543e-05, + "loss": 3.4668, + "step": 1613312 + }, + { + "epoch": 1.0, + "learning_rate": 2.357918791270491e-05, + "loss": 3.4646, + "step": 1613824 + }, + { + "epoch": 1.0, + "learning_rate": 2.357080196519439e-05, + "loss": 3.4624, + "step": 1614336 + }, + { + "epoch": 1.0, + "learning_rate": 2.356241601768387e-05, + "loss": 3.4691, + "step": 1614848 + }, + { + "epoch": 1.0, + "learning_rate": 2.355404644897708e-05, + "loss": 3.4534, + "step": 1615360 + }, + { + "epoch": 1.0, + "learning_rate": 2.354566050146656e-05, + "loss": 3.4698, + "step": 1615872 + }, + { + "epoch": 1.0, + "learning_rate": 2.353727455395604e-05, + "loss": 3.4575, + "step": 1616384 + }, + { + "epoch": 1.0, + "learning_rate": 2.352888860644552e-05, + "loss": 3.4559, + "step": 1616896 + }, + { + "epoch": 1.0, + "learning_rate": 2.352051903773873e-05, + "loss": 3.4527, + "step": 1617408 + }, + { + "epoch": 1.0, + "learning_rate": 2.351213309022821e-05, + "loss": 3.4559, + "step": 1617920 + }, + { + "epoch": 1.01, + "learning_rate": 2.350374714271769e-05, + "loss": 3.464, + "step": 1618432 + }, + { + "epoch": 1.01, + "learning_rate": 2.3495361195207168e-05, + "loss": 3.4622, + "step": 1618944 + }, + { + "epoch": 1.01, + "learning_rate": 2.3486991626500384e-05, + "loss": 3.4687, + "step": 1619456 + }, + { + "epoch": 1.01, + "learning_rate": 2.3478605678989863e-05, + "loss": 3.469, + "step": 1619968 + }, + { + "epoch": 1.01, + "learning_rate": 2.3470219731479343e-05, + "loss": 3.4544, + "step": 1620480 + }, + { + "epoch": 1.01, + "learning_rate": 2.346183378396882e-05, + "loss": 3.4619, + "step": 1620992 + }, + { + "epoch": 1.01, + "learning_rate": 2.3453464215262032e-05, + "loss": 3.4603, + "step": 1621504 + }, + { + "epoch": 1.01, + "learning_rate": 2.3445078267751512e-05, + "loss": 3.4605, + "step": 1622016 + }, + { + "epoch": 1.01, + "learning_rate": 2.3436692320240992e-05, + "loss": 3.4563, + "step": 1622528 + }, + { + "epoch": 1.01, + "learning_rate": 2.3428322751534205e-05, + "loss": 3.4559, + "step": 1623040 + }, + { + "epoch": 1.01, + "learning_rate": 2.3419936804023685e-05, + "loss": 3.461, + "step": 1623552 + }, + { + "epoch": 1.01, + "learning_rate": 2.3411550856513165e-05, + "loss": 3.4686, + "step": 1624064 + }, + { + "epoch": 1.01, + "learning_rate": 2.340316490900264e-05, + "loss": 3.4617, + "step": 1624576 + }, + { + "epoch": 1.01, + "learning_rate": 2.339477896149212e-05, + "loss": 3.4596, + "step": 1625088 + }, + { + "epoch": 1.01, + "learning_rate": 2.3386409392785337e-05, + "loss": 3.4692, + "step": 1625600 + }, + { + "epoch": 1.01, + "learning_rate": 2.3378023445274814e-05, + "loss": 3.4628, + "step": 1626112 + }, + { + "epoch": 1.01, + "learning_rate": 2.3369637497764294e-05, + "loss": 3.4585, + "step": 1626624 + }, + { + "epoch": 1.01, + "learning_rate": 2.3361251550253774e-05, + "loss": 3.4549, + "step": 1627136 + }, + { + "epoch": 1.01, + "learning_rate": 2.3352881981546986e-05, + "loss": 3.4346, + "step": 1627648 + }, + { + "epoch": 1.01, + "learning_rate": 2.3344496034036463e-05, + "loss": 3.4701, + "step": 1628160 + }, + { + "epoch": 1.01, + "learning_rate": 2.3336110086525946e-05, + "loss": 3.4597, + "step": 1628672 + }, + { + "epoch": 1.01, + "learning_rate": 2.3327724139015426e-05, + "loss": 3.4592, + "step": 1629184 + }, + { + "epoch": 1.01, + "learning_rate": 2.331935457030864e-05, + "loss": 3.4475, + "step": 1629696 + }, + { + "epoch": 1.01, + "learning_rate": 2.3310968622798115e-05, + "loss": 3.4416, + "step": 1630208 + }, + { + "epoch": 1.01, + "learning_rate": 2.3302582675287595e-05, + "loss": 3.4427, + "step": 1630720 + }, + { + "epoch": 1.01, + "learning_rate": 2.3294213106580808e-05, + "loss": 3.4577, + "step": 1631232 + }, + { + "epoch": 1.01, + "learning_rate": 2.3285827159070287e-05, + "loss": 3.4518, + "step": 1631744 + }, + { + "epoch": 1.01, + "learning_rate": 2.3277441211559767e-05, + "loss": 3.4571, + "step": 1632256 + }, + { + "epoch": 1.01, + "learning_rate": 2.3269055264049247e-05, + "loss": 3.4619, + "step": 1632768 + }, + { + "epoch": 1.01, + "learning_rate": 2.326068569534246e-05, + "loss": 3.4487, + "step": 1633280 + }, + { + "epoch": 1.01, + "learning_rate": 2.3252299747831936e-05, + "loss": 3.4569, + "step": 1633792 + }, + { + "epoch": 1.01, + "learning_rate": 2.3243913800321416e-05, + "loss": 3.4582, + "step": 1634304 + }, + { + "epoch": 1.01, + "learning_rate": 2.32355278528109e-05, + "loss": 3.4411, + "step": 1634816 + }, + { + "epoch": 1.01, + "learning_rate": 2.3227158284104112e-05, + "loss": 3.4485, + "step": 1635328 + }, + { + "epoch": 1.01, + "learning_rate": 2.321877233659359e-05, + "loss": 3.4553, + "step": 1635840 + }, + { + "epoch": 1.01, + "learning_rate": 2.321038638908307e-05, + "loss": 3.4614, + "step": 1636352 + }, + { + "epoch": 1.01, + "learning_rate": 2.320200044157255e-05, + "loss": 3.4436, + "step": 1636864 + }, + { + "epoch": 1.01, + "learning_rate": 2.319363087286576e-05, + "loss": 3.452, + "step": 1637376 + }, + { + "epoch": 1.01, + "learning_rate": 2.318524492535524e-05, + "loss": 3.4419, + "step": 1637888 + }, + { + "epoch": 1.01, + "learning_rate": 2.317685897784472e-05, + "loss": 3.4645, + "step": 1638400 + }, + { + "epoch": 1.01, + "learning_rate": 2.31684730303342e-05, + "loss": 3.462, + "step": 1638912 + }, + { + "epoch": 1.01, + "learning_rate": 2.316010346162741e-05, + "loss": 3.4559, + "step": 1639424 + }, + { + "epoch": 1.01, + "learning_rate": 2.3151733892920623e-05, + "loss": 3.4694, + "step": 1639936 + }, + { + "epoch": 1.01, + "learning_rate": 2.3143347945410106e-05, + "loss": 3.4642, + "step": 1640448 + }, + { + "epoch": 1.01, + "learning_rate": 2.3134961997899586e-05, + "loss": 3.4798, + "step": 1640960 + }, + { + "epoch": 1.01, + "learning_rate": 2.3126576050389063e-05, + "loss": 3.456, + "step": 1641472 + }, + { + "epoch": 1.01, + "learning_rate": 2.3118190102878542e-05, + "loss": 3.4588, + "step": 1641984 + }, + { + "epoch": 1.01, + "learning_rate": 2.3109804155368022e-05, + "loss": 3.4586, + "step": 1642496 + }, + { + "epoch": 1.01, + "learning_rate": 2.3101418207857502e-05, + "loss": 3.4511, + "step": 1643008 + }, + { + "epoch": 1.01, + "learning_rate": 2.3093032260346982e-05, + "loss": 3.4653, + "step": 1643520 + }, + { + "epoch": 1.01, + "learning_rate": 2.3084662691640195e-05, + "loss": 3.4568, + "step": 1644032 + }, + { + "epoch": 1.01, + "learning_rate": 2.3076276744129675e-05, + "loss": 3.4637, + "step": 1644544 + }, + { + "epoch": 1.01, + "learning_rate": 2.3067890796619155e-05, + "loss": 3.4575, + "step": 1645056 + }, + { + "epoch": 1.01, + "learning_rate": 2.3059504849108635e-05, + "loss": 3.4476, + "step": 1645568 + }, + { + "epoch": 1.01, + "learning_rate": 2.3051135280401844e-05, + "loss": 3.4524, + "step": 1646080 + }, + { + "epoch": 1.01, + "learning_rate": 2.3042765711695056e-05, + "loss": 3.4489, + "step": 1646592 + }, + { + "epoch": 1.01, + "learning_rate": 2.3034379764184536e-05, + "loss": 3.4646, + "step": 1647104 + }, + { + "epoch": 1.01, + "learning_rate": 2.3025993816674016e-05, + "loss": 3.4591, + "step": 1647616 + }, + { + "epoch": 1.01, + "learning_rate": 2.3017607869163496e-05, + "loss": 3.4464, + "step": 1648128 + }, + { + "epoch": 1.02, + "learning_rate": 2.3009221921652976e-05, + "loss": 3.4642, + "step": 1648640 + }, + { + "epoch": 1.02, + "learning_rate": 2.3000852352946185e-05, + "loss": 3.4564, + "step": 1649152 + }, + { + "epoch": 1.02, + "learning_rate": 2.299246640543567e-05, + "loss": 3.4458, + "step": 1649664 + }, + { + "epoch": 1.02, + "learning_rate": 2.298408045792515e-05, + "loss": 3.4536, + "step": 1650176 + }, + { + "epoch": 1.02, + "learning_rate": 2.297569451041463e-05, + "loss": 3.4655, + "step": 1650688 + }, + { + "epoch": 1.02, + "learning_rate": 2.296730856290411e-05, + "loss": 3.4587, + "step": 1651200 + }, + { + "epoch": 1.02, + "learning_rate": 2.295892261539359e-05, + "loss": 3.4613, + "step": 1651712 + }, + { + "epoch": 1.02, + "learning_rate": 2.2950536667883065e-05, + "loss": 3.4436, + "step": 1652224 + }, + { + "epoch": 1.02, + "learning_rate": 2.2942150720372545e-05, + "loss": 3.4614, + "step": 1652736 + }, + { + "epoch": 1.02, + "learning_rate": 2.293378115166576e-05, + "loss": 3.4515, + "step": 1653248 + }, + { + "epoch": 1.02, + "learning_rate": 2.292539520415524e-05, + "loss": 3.4654, + "step": 1653760 + }, + { + "epoch": 1.02, + "learning_rate": 2.2917009256644717e-05, + "loss": 3.4612, + "step": 1654272 + }, + { + "epoch": 1.02, + "learning_rate": 2.2908623309134197e-05, + "loss": 3.4563, + "step": 1654784 + }, + { + "epoch": 1.02, + "learning_rate": 2.290025374042741e-05, + "loss": 3.458, + "step": 1655296 + }, + { + "epoch": 1.02, + "learning_rate": 2.2891884171720622e-05, + "loss": 3.4635, + "step": 1655808 + }, + { + "epoch": 1.02, + "learning_rate": 2.2883498224210102e-05, + "loss": 3.444, + "step": 1656320 + }, + { + "epoch": 1.02, + "learning_rate": 2.2875112276699582e-05, + "loss": 3.4503, + "step": 1656832 + }, + { + "epoch": 1.02, + "learning_rate": 2.2866726329189062e-05, + "loss": 3.4459, + "step": 1657344 + }, + { + "epoch": 1.02, + "learning_rate": 2.285834038167854e-05, + "loss": 3.4615, + "step": 1657856 + }, + { + "epoch": 1.02, + "learning_rate": 2.284995443416802e-05, + "loss": 3.4416, + "step": 1658368 + }, + { + "epoch": 1.02, + "learning_rate": 2.28415684866575e-05, + "loss": 3.4545, + "step": 1658880 + }, + { + "epoch": 1.02, + "learning_rate": 2.283318253914698e-05, + "loss": 3.4484, + "step": 1659392 + }, + { + "epoch": 1.02, + "learning_rate": 2.282481297044019e-05, + "loss": 3.451, + "step": 1659904 + }, + { + "epoch": 1.02, + "learning_rate": 2.2816443401733403e-05, + "loss": 3.454, + "step": 1660416 + }, + { + "epoch": 1.02, + "learning_rate": 2.2808057454222883e-05, + "loss": 3.4486, + "step": 1660928 + }, + { + "epoch": 1.02, + "learning_rate": 2.279967150671236e-05, + "loss": 3.4622, + "step": 1661440 + }, + { + "epoch": 1.02, + "learning_rate": 2.279128555920184e-05, + "loss": 3.4619, + "step": 1661952 + }, + { + "epoch": 1.02, + "learning_rate": 2.2782899611691323e-05, + "loss": 3.4609, + "step": 1662464 + }, + { + "epoch": 1.02, + "learning_rate": 2.2774513664180803e-05, + "loss": 3.4514, + "step": 1662976 + }, + { + "epoch": 1.02, + "learning_rate": 2.2766144095474012e-05, + "loss": 3.4602, + "step": 1663488 + }, + { + "epoch": 1.02, + "learning_rate": 2.2757758147963492e-05, + "loss": 3.4606, + "step": 1664000 + }, + { + "epoch": 1.02, + "learning_rate": 2.2749372200452972e-05, + "loss": 3.4434, + "step": 1664512 + }, + { + "epoch": 1.02, + "learning_rate": 2.2740986252942452e-05, + "loss": 3.4675, + "step": 1665024 + }, + { + "epoch": 1.02, + "learning_rate": 2.2732600305431932e-05, + "loss": 3.4465, + "step": 1665536 + }, + { + "epoch": 1.02, + "learning_rate": 2.2724214357921416e-05, + "loss": 3.4638, + "step": 1666048 + }, + { + "epoch": 1.02, + "learning_rate": 2.2715828410410892e-05, + "loss": 3.4445, + "step": 1666560 + }, + { + "epoch": 1.02, + "learning_rate": 2.2707442462900372e-05, + "loss": 3.4582, + "step": 1667072 + }, + { + "epoch": 1.02, + "learning_rate": 2.2699072894193585e-05, + "loss": 3.4436, + "step": 1667584 + }, + { + "epoch": 1.02, + "learning_rate": 2.2690686946683064e-05, + "loss": 3.4471, + "step": 1668096 + }, + { + "epoch": 1.02, + "learning_rate": 2.2682317377976277e-05, + "loss": 3.4451, + "step": 1668608 + }, + { + "epoch": 1.02, + "learning_rate": 2.2673931430465757e-05, + "loss": 3.4648, + "step": 1669120 + }, + { + "epoch": 1.02, + "learning_rate": 2.2665545482955237e-05, + "loss": 3.4533, + "step": 1669632 + }, + { + "epoch": 1.02, + "learning_rate": 2.2657159535444717e-05, + "loss": 3.4619, + "step": 1670144 + }, + { + "epoch": 1.02, + "learning_rate": 2.2648773587934193e-05, + "loss": 3.4483, + "step": 1670656 + }, + { + "epoch": 1.02, + "learning_rate": 2.2640387640423673e-05, + "loss": 3.4595, + "step": 1671168 + }, + { + "epoch": 1.02, + "learning_rate": 2.2632001692913153e-05, + "loss": 3.4623, + "step": 1671680 + }, + { + "epoch": 1.02, + "learning_rate": 2.2623615745402633e-05, + "loss": 3.4595, + "step": 1672192 + }, + { + "epoch": 1.02, + "learning_rate": 2.2615246176695846e-05, + "loss": 3.4543, + "step": 1672704 + }, + { + "epoch": 1.02, + "learning_rate": 2.2606860229185326e-05, + "loss": 3.4557, + "step": 1673216 + }, + { + "epoch": 1.02, + "learning_rate": 2.2598474281674806e-05, + "loss": 3.455, + "step": 1673728 + }, + { + "epoch": 1.02, + "learning_rate": 2.2590104712968015e-05, + "loss": 3.4647, + "step": 1674240 + }, + { + "epoch": 1.02, + "learning_rate": 2.2581718765457495e-05, + "loss": 3.4506, + "step": 1674752 + }, + { + "epoch": 1.02, + "learning_rate": 2.2573332817946978e-05, + "loss": 3.4564, + "step": 1675264 + }, + { + "epoch": 1.02, + "learning_rate": 2.2564946870436458e-05, + "loss": 3.4516, + "step": 1675776 + }, + { + "epoch": 1.02, + "learning_rate": 2.2556577301729667e-05, + "loss": 3.456, + "step": 1676288 + }, + { + "epoch": 1.02, + "learning_rate": 2.2548191354219147e-05, + "loss": 3.4567, + "step": 1676800 + }, + { + "epoch": 1.02, + "learning_rate": 2.2539805406708627e-05, + "loss": 3.4536, + "step": 1677312 + }, + { + "epoch": 1.02, + "learning_rate": 2.2531419459198107e-05, + "loss": 3.4641, + "step": 1677824 + }, + { + "epoch": 1.02, + "learning_rate": 2.252304989049132e-05, + "loss": 3.4398, + "step": 1678336 + }, + { + "epoch": 1.02, + "learning_rate": 2.25146639429808e-05, + "loss": 3.4597, + "step": 1678848 + }, + { + "epoch": 1.03, + "eval_loss": 3.8549306392669678, + "eval_runtime": 313.6707, + "eval_samples_per_second": 1216.534, + "eval_steps_per_second": 38.018, + "step": 1679040 + }, + { + "epoch": 0.0, + "learning_rate": 2.250627799547028e-05, + "loss": 3.45, + "step": 1679360 + }, + { + "epoch": 0.0, + "learning_rate": 2.249789204795976e-05, + "loss": 3.4437, + "step": 1679872 + }, + { + "epoch": 0.0, + "learning_rate": 2.248950610044924e-05, + "loss": 3.4518, + "step": 1680384 + }, + { + "epoch": 0.0, + "learning_rate": 2.248112015293872e-05, + "loss": 3.4533, + "step": 1680896 + }, + { + "epoch": 0.0, + "learning_rate": 2.2472750584231932e-05, + "loss": 3.4653, + "step": 1681408 + }, + { + "epoch": 0.0, + "learning_rate": 2.246436463672141e-05, + "loss": 3.4497, + "step": 1681920 + }, + { + "epoch": 0.0, + "learning_rate": 2.245597868921089e-05, + "loss": 3.4473, + "step": 1682432 + }, + { + "epoch": 0.0, + "learning_rate": 2.244759274170037e-05, + "loss": 3.4426, + "step": 1682944 + }, + { + "epoch": 0.0, + "learning_rate": 2.243923955179731e-05, + "loss": 3.4494, + "step": 1683456 + }, + { + "epoch": 0.0, + "learning_rate": 2.2430853604286793e-05, + "loss": 3.4558, + "step": 1683968 + }, + { + "epoch": 0.0, + "learning_rate": 2.2422467656776273e-05, + "loss": 3.4496, + "step": 1684480 + }, + { + "epoch": 0.0, + "learning_rate": 2.2414081709265753e-05, + "loss": 3.45, + "step": 1684992 + }, + { + "epoch": 0.0, + "learning_rate": 2.2405695761755233e-05, + "loss": 3.4536, + "step": 1685504 + }, + { + "epoch": 0.0, + "learning_rate": 2.2397326193048442e-05, + "loss": 3.443, + "step": 1686016 + }, + { + "epoch": 0.0, + "learning_rate": 2.2388940245537922e-05, + "loss": 3.4506, + "step": 1686528 + }, + { + "epoch": 0.0, + "learning_rate": 2.2380554298027402e-05, + "loss": 3.44, + "step": 1687040 + }, + { + "epoch": 0.0, + "learning_rate": 2.2372168350516885e-05, + "loss": 3.4433, + "step": 1687552 + }, + { + "epoch": 0.0, + "learning_rate": 2.2363782403006365e-05, + "loss": 3.4499, + "step": 1688064 + }, + { + "epoch": 0.0, + "learning_rate": 2.2355396455495845e-05, + "loss": 3.4498, + "step": 1688576 + }, + { + "epoch": 0.0, + "learning_rate": 2.2347010507985322e-05, + "loss": 3.4571, + "step": 1689088 + }, + { + "epoch": 0.0, + "learning_rate": 2.2338624560474802e-05, + "loss": 3.463, + "step": 1689600 + }, + { + "epoch": 0.0, + "learning_rate": 2.2330254991768014e-05, + "loss": 3.4481, + "step": 1690112 + }, + { + "epoch": 0.0, + "learning_rate": 2.2321869044257494e-05, + "loss": 3.4479, + "step": 1690624 + }, + { + "epoch": 0.0, + "learning_rate": 2.2313483096746974e-05, + "loss": 3.4577, + "step": 1691136 + }, + { + "epoch": 0.0, + "learning_rate": 2.2305097149236454e-05, + "loss": 3.4388, + "step": 1691648 + }, + { + "epoch": 0.0, + "learning_rate": 2.2296727580529667e-05, + "loss": 3.4616, + "step": 1692160 + }, + { + "epoch": 0.0, + "learning_rate": 2.2288341633019143e-05, + "loss": 3.4459, + "step": 1692672 + }, + { + "epoch": 0.0, + "learning_rate": 2.2279955685508623e-05, + "loss": 3.4427, + "step": 1693184 + }, + { + "epoch": 0.0, + "learning_rate": 2.2271569737998103e-05, + "loss": 3.4394, + "step": 1693696 + }, + { + "epoch": 0.0, + "learning_rate": 2.226320016929132e-05, + "loss": 3.4479, + "step": 1694208 + }, + { + "epoch": 0.01, + "learning_rate": 2.2254814221780796e-05, + "loss": 3.4501, + "step": 1694720 + }, + { + "epoch": 0.01, + "learning_rate": 2.2246428274270276e-05, + "loss": 3.4544, + "step": 1695232 + }, + { + "epoch": 0.01, + "learning_rate": 2.2238042326759755e-05, + "loss": 3.4561, + "step": 1695744 + }, + { + "epoch": 0.01, + "learning_rate": 2.2229672758052965e-05, + "loss": 3.4563, + "step": 1696256 + }, + { + "epoch": 0.01, + "learning_rate": 2.2221286810542448e-05, + "loss": 3.4432, + "step": 1696768 + }, + { + "epoch": 0.01, + "learning_rate": 2.2212900863031928e-05, + "loss": 3.4538, + "step": 1697280 + }, + { + "epoch": 0.01, + "learning_rate": 2.2204514915521408e-05, + "loss": 3.4532, + "step": 1697792 + }, + { + "epoch": 0.01, + "learning_rate": 2.2196145346814617e-05, + "loss": 3.4471, + "step": 1698304 + }, + { + "epoch": 0.01, + "learning_rate": 2.2187759399304097e-05, + "loss": 3.4462, + "step": 1698816 + }, + { + "epoch": 0.01, + "learning_rate": 2.2179373451793577e-05, + "loss": 3.4467, + "step": 1699328 + }, + { + "epoch": 0.01, + "learning_rate": 2.2170987504283057e-05, + "loss": 3.4464, + "step": 1699840 + }, + { + "epoch": 0.01, + "learning_rate": 2.216261793557627e-05, + "loss": 3.4578, + "step": 1700352 + }, + { + "epoch": 0.01, + "learning_rate": 2.215423198806575e-05, + "loss": 3.45, + "step": 1700864 + }, + { + "epoch": 0.01, + "learning_rate": 2.214584604055523e-05, + "loss": 3.4496, + "step": 1701376 + }, + { + "epoch": 0.01, + "learning_rate": 2.2137476471848438e-05, + "loss": 3.4592, + "step": 1701888 + }, + { + "epoch": 0.01, + "learning_rate": 2.2129090524337918e-05, + "loss": 3.4477, + "step": 1702400 + }, + { + "epoch": 0.01, + "learning_rate": 2.21207045768274e-05, + "loss": 3.4507, + "step": 1702912 + }, + { + "epoch": 0.01, + "learning_rate": 2.211231862931688e-05, + "loss": 3.4448, + "step": 1703424 + }, + { + "epoch": 0.01, + "learning_rate": 2.210394906061009e-05, + "loss": 3.4167, + "step": 1703936 + }, + { + "epoch": 0.01, + "learning_rate": 2.209556311309957e-05, + "loss": 3.4611, + "step": 1704448 + }, + { + "epoch": 0.01, + "learning_rate": 2.208717716558905e-05, + "loss": 3.4493, + "step": 1704960 + }, + { + "epoch": 0.01, + "learning_rate": 2.207879121807853e-05, + "loss": 3.4484, + "step": 1705472 + }, + { + "epoch": 0.01, + "learning_rate": 2.2070421649371743e-05, + "loss": 3.4379, + "step": 1705984 + }, + { + "epoch": 0.01, + "learning_rate": 2.2062035701861223e-05, + "loss": 3.4285, + "step": 1706496 + }, + { + "epoch": 0.01, + "learning_rate": 2.2053649754350703e-05, + "loss": 3.4347, + "step": 1707008 + }, + { + "epoch": 0.01, + "learning_rate": 2.2045263806840183e-05, + "loss": 3.4469, + "step": 1707520 + }, + { + "epoch": 0.01, + "learning_rate": 2.2036894238133392e-05, + "loss": 3.4415, + "step": 1708032 + }, + { + "epoch": 0.01, + "learning_rate": 2.2028508290622872e-05, + "loss": 3.4415, + "step": 1708544 + }, + { + "epoch": 0.01, + "learning_rate": 2.2020122343112355e-05, + "loss": 3.452, + "step": 1709056 + }, + { + "epoch": 0.01, + "learning_rate": 2.2011736395601835e-05, + "loss": 3.4381, + "step": 1709568 + }, + { + "epoch": 0.01, + "learning_rate": 2.2003366826895044e-05, + "loss": 3.4406, + "step": 1710080 + }, + { + "epoch": 0.01, + "learning_rate": 2.1994980879384524e-05, + "loss": 3.4535, + "step": 1710592 + }, + { + "epoch": 0.01, + "learning_rate": 2.1986594931874004e-05, + "loss": 3.4261, + "step": 1711104 + }, + { + "epoch": 0.01, + "learning_rate": 2.1978208984363484e-05, + "loss": 3.4372, + "step": 1711616 + }, + { + "epoch": 0.01, + "learning_rate": 2.1969839415656697e-05, + "loss": 3.4426, + "step": 1712128 + }, + { + "epoch": 0.01, + "learning_rate": 2.1961453468146177e-05, + "loss": 3.4526, + "step": 1712640 + }, + { + "epoch": 0.01, + "learning_rate": 2.1953067520635657e-05, + "loss": 3.4292, + "step": 1713152 + }, + { + "epoch": 0.01, + "learning_rate": 2.1944681573125137e-05, + "loss": 3.4441, + "step": 1713664 + }, + { + "epoch": 0.01, + "learning_rate": 2.1936312004418346e-05, + "loss": 3.4281, + "step": 1714176 + }, + { + "epoch": 0.01, + "learning_rate": 2.1927926056907826e-05, + "loss": 3.4543, + "step": 1714688 + }, + { + "epoch": 0.01, + "learning_rate": 2.191954010939731e-05, + "loss": 3.4526, + "step": 1715200 + }, + { + "epoch": 0.01, + "learning_rate": 2.191115416188679e-05, + "loss": 3.4455, + "step": 1715712 + }, + { + "epoch": 0.01, + "learning_rate": 2.1902784593179998e-05, + "loss": 3.4523, + "step": 1716224 + }, + { + "epoch": 0.01, + "learning_rate": 2.1894415024473207e-05, + "loss": 3.4553, + "step": 1716736 + }, + { + "epoch": 0.01, + "learning_rate": 2.1886029076962687e-05, + "loss": 3.4689, + "step": 1717248 + }, + { + "epoch": 0.01, + "learning_rate": 2.187764312945217e-05, + "loss": 3.4441, + "step": 1717760 + }, + { + "epoch": 0.01, + "learning_rate": 2.186925718194165e-05, + "loss": 3.4514, + "step": 1718272 + }, + { + "epoch": 0.01, + "learning_rate": 2.186087123443113e-05, + "loss": 3.447, + "step": 1718784 + }, + { + "epoch": 0.01, + "learning_rate": 2.185248528692061e-05, + "loss": 3.4391, + "step": 1719296 + }, + { + "epoch": 0.01, + "learning_rate": 2.184409933941009e-05, + "loss": 3.4523, + "step": 1719808 + }, + { + "epoch": 0.01, + "learning_rate": 2.18357297707033e-05, + "loss": 3.4484, + "step": 1720320 + }, + { + "epoch": 0.01, + "learning_rate": 2.182734382319278e-05, + "loss": 3.4506, + "step": 1720832 + }, + { + "epoch": 0.01, + "learning_rate": 2.1818957875682263e-05, + "loss": 3.4543, + "step": 1721344 + }, + { + "epoch": 0.01, + "learning_rate": 2.1810571928171743e-05, + "loss": 3.4363, + "step": 1721856 + }, + { + "epoch": 0.01, + "learning_rate": 2.180220235946495e-05, + "loss": 3.435, + "step": 1722368 + }, + { + "epoch": 0.01, + "learning_rate": 2.179383279075816e-05, + "loss": 3.4402, + "step": 1722880 + }, + { + "epoch": 0.01, + "learning_rate": 2.178544684324764e-05, + "loss": 3.4565, + "step": 1723392 + }, + { + "epoch": 0.01, + "learning_rate": 2.1777060895737124e-05, + "loss": 3.448, + "step": 1723904 + }, + { + "epoch": 0.01, + "learning_rate": 2.1768674948226604e-05, + "loss": 3.4408, + "step": 1724416 + }, + { + "epoch": 0.02, + "learning_rate": 2.1760289000716084e-05, + "loss": 3.4426, + "step": 1724928 + }, + { + "epoch": 0.02, + "learning_rate": 2.1751919432009293e-05, + "loss": 3.4536, + "step": 1725440 + }, + { + "epoch": 0.02, + "learning_rate": 2.1743533484498773e-05, + "loss": 3.4368, + "step": 1725952 + }, + { + "epoch": 0.02, + "learning_rate": 2.1735147536988253e-05, + "loss": 3.4406, + "step": 1726464 + }, + { + "epoch": 0.02, + "learning_rate": 2.1726761589477733e-05, + "loss": 3.4567, + "step": 1726976 + }, + { + "epoch": 0.02, + "learning_rate": 2.1718375641967216e-05, + "loss": 3.4476, + "step": 1727488 + }, + { + "epoch": 0.02, + "learning_rate": 2.1709989694456693e-05, + "loss": 3.4496, + "step": 1728000 + }, + { + "epoch": 0.02, + "learning_rate": 2.1701603746946173e-05, + "loss": 3.4333, + "step": 1728512 + }, + { + "epoch": 0.02, + "learning_rate": 2.1693217799435653e-05, + "loss": 3.45, + "step": 1729024 + }, + { + "epoch": 0.02, + "learning_rate": 2.1684848230728862e-05, + "loss": 3.4386, + "step": 1729536 + }, + { + "epoch": 0.02, + "learning_rate": 2.1676462283218342e-05, + "loss": 3.4521, + "step": 1730048 + }, + { + "epoch": 0.02, + "learning_rate": 2.1668076335707825e-05, + "loss": 3.4502, + "step": 1730560 + }, + { + "epoch": 0.02, + "learning_rate": 2.1659690388197305e-05, + "loss": 3.4484, + "step": 1731072 + }, + { + "epoch": 0.02, + "learning_rate": 2.1651320819490514e-05, + "loss": 3.4471, + "step": 1731584 + }, + { + "epoch": 0.02, + "learning_rate": 2.1642951250783727e-05, + "loss": 3.4508, + "step": 1732096 + }, + { + "epoch": 0.02, + "learning_rate": 2.1634565303273207e-05, + "loss": 3.433, + "step": 1732608 + }, + { + "epoch": 0.02, + "learning_rate": 2.1626179355762687e-05, + "loss": 3.4396, + "step": 1733120 + }, + { + "epoch": 0.02, + "learning_rate": 2.1617793408252167e-05, + "loss": 3.4318, + "step": 1733632 + }, + { + "epoch": 0.02, + "learning_rate": 2.1609407460741646e-05, + "loss": 3.4531, + "step": 1734144 + }, + { + "epoch": 0.02, + "learning_rate": 2.1601021513231126e-05, + "loss": 3.4334, + "step": 1734656 + }, + { + "epoch": 0.02, + "learning_rate": 2.1592635565720606e-05, + "loss": 3.44, + "step": 1735168 + }, + { + "epoch": 0.02, + "learning_rate": 2.1584249618210086e-05, + "loss": 3.4345, + "step": 1735680 + }, + { + "epoch": 0.02, + "learning_rate": 2.1575880049503295e-05, + "loss": 3.4413, + "step": 1736192 + }, + { + "epoch": 0.02, + "learning_rate": 2.156751048079651e-05, + "loss": 3.4416, + "step": 1736704 + }, + { + "epoch": 0.02, + "learning_rate": 2.1559124533285988e-05, + "loss": 3.4349, + "step": 1737216 + }, + { + "epoch": 0.02, + "learning_rate": 2.1550738585775468e-05, + "loss": 3.4475, + "step": 1737728 + }, + { + "epoch": 0.02, + "learning_rate": 2.1542352638264948e-05, + "loss": 3.4558, + "step": 1738240 + }, + { + "epoch": 0.02, + "learning_rate": 2.1533966690754428e-05, + "loss": 3.4427, + "step": 1738752 + }, + { + "epoch": 0.02, + "learning_rate": 2.1525580743243908e-05, + "loss": 3.4466, + "step": 1739264 + }, + { + "epoch": 0.02, + "learning_rate": 2.151721117453712e-05, + "loss": 3.4457, + "step": 1739776 + }, + { + "epoch": 0.02, + "learning_rate": 2.15088252270266e-05, + "loss": 3.451, + "step": 1740288 + }, + { + "epoch": 0.02, + "learning_rate": 2.150043927951608e-05, + "loss": 3.4382, + "step": 1740800 + }, + { + "epoch": 0.02, + "learning_rate": 2.149205333200556e-05, + "loss": 3.4523, + "step": 1741312 + }, + { + "epoch": 0.02, + "learning_rate": 2.148366738449504e-05, + "loss": 3.4348, + "step": 1741824 + }, + { + "epoch": 0.02, + "learning_rate": 2.1475281436984517e-05, + "loss": 3.4514, + "step": 1742336 + }, + { + "epoch": 0.02, + "learning_rate": 2.1466895489473997e-05, + "loss": 3.4344, + "step": 1742848 + }, + { + "epoch": 0.02, + "learning_rate": 2.145850954196348e-05, + "loss": 3.4417, + "step": 1743360 + }, + { + "epoch": 0.02, + "learning_rate": 2.1450139973256692e-05, + "loss": 3.4377, + "step": 1743872 + }, + { + "epoch": 0.02, + "learning_rate": 2.144175402574617e-05, + "loss": 3.4345, + "step": 1744384 + }, + { + "epoch": 0.02, + "learning_rate": 2.143338445703938e-05, + "loss": 3.4364, + "step": 1744896 + }, + { + "epoch": 0.02, + "learning_rate": 2.142499850952886e-05, + "loss": 3.4492, + "step": 1745408 + }, + { + "epoch": 0.02, + "learning_rate": 2.141661256201834e-05, + "loss": 3.4464, + "step": 1745920 + }, + { + "epoch": 0.02, + "learning_rate": 2.140822661450782e-05, + "loss": 3.4505, + "step": 1746432 + }, + { + "epoch": 0.02, + "learning_rate": 2.13998406669973e-05, + "loss": 3.4366, + "step": 1746944 + }, + { + "epoch": 0.02, + "learning_rate": 2.139145471948678e-05, + "loss": 3.4523, + "step": 1747456 + }, + { + "epoch": 0.02, + "learning_rate": 2.138306877197626e-05, + "loss": 3.4473, + "step": 1747968 + }, + { + "epoch": 0.02, + "learning_rate": 2.137468282446574e-05, + "loss": 3.4483, + "step": 1748480 + }, + { + "epoch": 0.02, + "learning_rate": 2.136631325575895e-05, + "loss": 3.4432, + "step": 1748992 + }, + { + "epoch": 0.02, + "learning_rate": 2.1357927308248434e-05, + "loss": 3.4439, + "step": 1749504 + }, + { + "epoch": 0.02, + "learning_rate": 2.1349541360737914e-05, + "loss": 3.4443, + "step": 1750016 + }, + { + "epoch": 0.02, + "learning_rate": 2.1341155413227393e-05, + "loss": 3.457, + "step": 1750528 + }, + { + "epoch": 0.02, + "learning_rate": 2.1332802223324335e-05, + "loss": 3.4364, + "step": 1751040 + }, + { + "epoch": 0.02, + "learning_rate": 2.132441627581381e-05, + "loss": 3.4447, + "step": 1751552 + }, + { + "epoch": 0.02, + "learning_rate": 2.1316030328303295e-05, + "loss": 3.4465, + "step": 1752064 + }, + { + "epoch": 0.02, + "learning_rate": 2.1307644380792775e-05, + "loss": 3.4481, + "step": 1752576 + }, + { + "epoch": 0.02, + "learning_rate": 2.1299258433282255e-05, + "loss": 3.4376, + "step": 1753088 + }, + { + "epoch": 0.02, + "learning_rate": 2.1290872485771735e-05, + "loss": 3.4413, + "step": 1753600 + }, + { + "epoch": 0.02, + "learning_rate": 2.1282486538261215e-05, + "loss": 3.4541, + "step": 1754112 + }, + { + "epoch": 0.02, + "learning_rate": 2.1274100590750695e-05, + "loss": 3.4314, + "step": 1754624 + }, + { + "epoch": 0.02, + "learning_rate": 2.1265731022043904e-05, + "loss": 3.4479, + "step": 1755136 + }, + { + "epoch": 0.03, + "eval_loss": 3.85677433013916, + "eval_runtime": 312.0731, + "eval_samples_per_second": 1222.762, + "eval_steps_per_second": 38.212, + "step": 1755360 + }, + { + "epoch": 0.0, + "learning_rate": 2.1257345074533387e-05, + "loss": 3.44, + "step": 1755648 + }, + { + "epoch": 0.0, + "learning_rate": 2.1248959127022867e-05, + "loss": 3.4307, + "step": 1756160 + }, + { + "epoch": 0.0, + "learning_rate": 2.1240573179512347e-05, + "loss": 3.446, + "step": 1756672 + }, + { + "epoch": 0.0, + "learning_rate": 2.1232187232001824e-05, + "loss": 3.4361, + "step": 1757184 + }, + { + "epoch": 0.0, + "learning_rate": 2.1223817663295036e-05, + "loss": 3.4524, + "step": 1757696 + }, + { + "epoch": 0.0, + "learning_rate": 2.1215431715784516e-05, + "loss": 3.443, + "step": 1758208 + }, + { + "epoch": 0.0, + "learning_rate": 2.120706214707773e-05, + "loss": 3.4366, + "step": 1758720 + }, + { + "epoch": 0.0, + "learning_rate": 2.119867619956721e-05, + "loss": 3.4349, + "step": 1759232 + }, + { + "epoch": 0.0, + "learning_rate": 2.119029025205669e-05, + "loss": 3.4396, + "step": 1759744 + }, + { + "epoch": 0.0, + "learning_rate": 2.118190430454617e-05, + "loss": 3.4426, + "step": 1760256 + }, + { + "epoch": 0.0, + "learning_rate": 2.1173518357035645e-05, + "loss": 3.4371, + "step": 1760768 + }, + { + "epoch": 0.0, + "learning_rate": 2.1165132409525125e-05, + "loss": 3.4377, + "step": 1761280 + }, + { + "epoch": 0.0, + "learning_rate": 2.115676284081834e-05, + "loss": 3.4389, + "step": 1761792 + }, + { + "epoch": 0.0, + "learning_rate": 2.114837689330782e-05, + "loss": 3.4342, + "step": 1762304 + }, + { + "epoch": 0.0, + "learning_rate": 2.1139990945797297e-05, + "loss": 3.4405, + "step": 1762816 + }, + { + "epoch": 0.0, + "learning_rate": 2.1131604998286777e-05, + "loss": 3.431, + "step": 1763328 + }, + { + "epoch": 0.0, + "learning_rate": 2.1123219050776257e-05, + "loss": 3.4307, + "step": 1763840 + }, + { + "epoch": 0.0, + "learning_rate": 2.111484948206947e-05, + "loss": 3.4392, + "step": 1764352 + }, + { + "epoch": 0.0, + "learning_rate": 2.110646353455895e-05, + "loss": 3.4386, + "step": 1764864 + }, + { + "epoch": 0.0, + "learning_rate": 2.109807758704843e-05, + "loss": 3.4445, + "step": 1765376 + }, + { + "epoch": 0.0, + "learning_rate": 2.108969163953791e-05, + "loss": 3.4523, + "step": 1765888 + }, + { + "epoch": 0.0, + "learning_rate": 2.108130569202739e-05, + "loss": 3.4399, + "step": 1766400 + }, + { + "epoch": 0.0, + "learning_rate": 2.107291974451687e-05, + "loss": 3.4365, + "step": 1766912 + }, + { + "epoch": 0.0, + "learning_rate": 2.106453379700635e-05, + "loss": 3.4432, + "step": 1767424 + }, + { + "epoch": 0.0, + "learning_rate": 2.1056147849495826e-05, + "loss": 3.4313, + "step": 1767936 + }, + { + "epoch": 0.0, + "learning_rate": 2.1047778280789042e-05, + "loss": 3.4494, + "step": 1768448 + }, + { + "epoch": 0.0, + "learning_rate": 2.1039392333278522e-05, + "loss": 3.432, + "step": 1768960 + }, + { + "epoch": 0.0, + "learning_rate": 2.1031006385768002e-05, + "loss": 3.4363, + "step": 1769472 + }, + { + "epoch": 0.0, + "learning_rate": 2.102262043825748e-05, + "loss": 3.4297, + "step": 1769984 + }, + { + "epoch": 0.0, + "learning_rate": 2.101425086955069e-05, + "loss": 3.4338, + "step": 1770496 + }, + { + "epoch": 0.01, + "learning_rate": 2.100586492204017e-05, + "loss": 3.4376, + "step": 1771008 + }, + { + "epoch": 0.01, + "learning_rate": 2.099747897452965e-05, + "loss": 3.444, + "step": 1771520 + }, + { + "epoch": 0.01, + "learning_rate": 2.098909302701913e-05, + "loss": 3.4424, + "step": 1772032 + }, + { + "epoch": 0.01, + "learning_rate": 2.0980723458312343e-05, + "loss": 3.4428, + "step": 1772544 + }, + { + "epoch": 0.01, + "learning_rate": 2.0972337510801823e-05, + "loss": 3.4312, + "step": 1773056 + }, + { + "epoch": 0.01, + "learning_rate": 2.09639515632913e-05, + "loss": 3.4443, + "step": 1773568 + }, + { + "epoch": 0.01, + "learning_rate": 2.095556561578078e-05, + "loss": 3.4451, + "step": 1774080 + }, + { + "epoch": 0.01, + "learning_rate": 2.0947196047073996e-05, + "loss": 3.4335, + "step": 1774592 + }, + { + "epoch": 0.01, + "learning_rate": 2.0938810099563476e-05, + "loss": 3.4377, + "step": 1775104 + }, + { + "epoch": 0.01, + "learning_rate": 2.0930424152052952e-05, + "loss": 3.435, + "step": 1775616 + }, + { + "epoch": 0.01, + "learning_rate": 2.0922038204542432e-05, + "loss": 3.4362, + "step": 1776128 + }, + { + "epoch": 0.01, + "learning_rate": 2.0913668635835645e-05, + "loss": 3.4459, + "step": 1776640 + }, + { + "epoch": 0.01, + "learning_rate": 2.0905282688325125e-05, + "loss": 3.4396, + "step": 1777152 + }, + { + "epoch": 0.01, + "learning_rate": 2.0896896740814605e-05, + "loss": 3.4369, + "step": 1777664 + }, + { + "epoch": 0.01, + "learning_rate": 2.0888510793304084e-05, + "loss": 3.4473, + "step": 1778176 + }, + { + "epoch": 0.01, + "learning_rate": 2.0880141224597297e-05, + "loss": 3.4395, + "step": 1778688 + }, + { + "epoch": 0.01, + "learning_rate": 2.0871755277086774e-05, + "loss": 3.4382, + "step": 1779200 + }, + { + "epoch": 0.01, + "learning_rate": 2.0863369329576253e-05, + "loss": 3.4373, + "step": 1779712 + }, + { + "epoch": 0.01, + "learning_rate": 2.0854983382065733e-05, + "loss": 3.405, + "step": 1780224 + }, + { + "epoch": 0.01, + "learning_rate": 2.0846613813358946e-05, + "loss": 3.4533, + "step": 1780736 + }, + { + "epoch": 0.01, + "learning_rate": 2.0838227865848426e-05, + "loss": 3.4343, + "step": 1781248 + }, + { + "epoch": 0.01, + "learning_rate": 2.0829841918337906e-05, + "loss": 3.4412, + "step": 1781760 + }, + { + "epoch": 0.01, + "learning_rate": 2.0821455970827386e-05, + "loss": 3.4222, + "step": 1782272 + }, + { + "epoch": 0.01, + "learning_rate": 2.0813086402120595e-05, + "loss": 3.4212, + "step": 1782784 + }, + { + "epoch": 0.01, + "learning_rate": 2.080471683341381e-05, + "loss": 3.4216, + "step": 1783296 + }, + { + "epoch": 0.01, + "learning_rate": 2.079633088590329e-05, + "loss": 3.4335, + "step": 1783808 + }, + { + "epoch": 0.01, + "learning_rate": 2.078794493839277e-05, + "loss": 3.4355, + "step": 1784320 + }, + { + "epoch": 0.01, + "learning_rate": 2.0779558990882247e-05, + "loss": 3.428, + "step": 1784832 + }, + { + "epoch": 0.01, + "learning_rate": 2.0771173043371727e-05, + "loss": 3.4468, + "step": 1785344 + }, + { + "epoch": 0.01, + "learning_rate": 2.0762787095861207e-05, + "loss": 3.4278, + "step": 1785856 + }, + { + "epoch": 0.01, + "learning_rate": 2.0754401148350687e-05, + "loss": 3.4299, + "step": 1786368 + }, + { + "epoch": 0.01, + "learning_rate": 2.0746015200840167e-05, + "loss": 3.4423, + "step": 1786880 + }, + { + "epoch": 0.01, + "learning_rate": 2.073764563213338e-05, + "loss": 3.4162, + "step": 1787392 + }, + { + "epoch": 0.01, + "learning_rate": 2.072925968462286e-05, + "loss": 3.4243, + "step": 1787904 + }, + { + "epoch": 0.01, + "learning_rate": 2.072087373711234e-05, + "loss": 3.4332, + "step": 1788416 + }, + { + "epoch": 0.01, + "learning_rate": 2.071248778960182e-05, + "loss": 3.4411, + "step": 1788928 + }, + { + "epoch": 0.01, + "learning_rate": 2.070411822089503e-05, + "loss": 3.4206, + "step": 1789440 + }, + { + "epoch": 0.01, + "learning_rate": 2.0695732273384512e-05, + "loss": 3.4331, + "step": 1789952 + }, + { + "epoch": 0.01, + "learning_rate": 2.0687346325873992e-05, + "loss": 3.4188, + "step": 1790464 + }, + { + "epoch": 0.01, + "learning_rate": 2.0678960378363472e-05, + "loss": 3.4424, + "step": 1790976 + }, + { + "epoch": 0.01, + "learning_rate": 2.067059080965668e-05, + "loss": 3.438, + "step": 1791488 + }, + { + "epoch": 0.01, + "learning_rate": 2.066220486214616e-05, + "loss": 3.4353, + "step": 1792000 + }, + { + "epoch": 0.01, + "learning_rate": 2.065381891463564e-05, + "loss": 3.4395, + "step": 1792512 + }, + { + "epoch": 0.01, + "learning_rate": 2.0645449345928853e-05, + "loss": 3.4449, + "step": 1793024 + }, + { + "epoch": 0.01, + "learning_rate": 2.0637063398418333e-05, + "loss": 3.4551, + "step": 1793536 + }, + { + "epoch": 0.01, + "learning_rate": 2.0628677450907813e-05, + "loss": 3.4353, + "step": 1794048 + }, + { + "epoch": 0.01, + "learning_rate": 2.0620291503397293e-05, + "loss": 3.4392, + "step": 1794560 + }, + { + "epoch": 0.01, + "learning_rate": 2.0611905555886773e-05, + "loss": 3.4394, + "step": 1795072 + }, + { + "epoch": 0.01, + "learning_rate": 2.060351960837625e-05, + "loss": 3.426, + "step": 1795584 + }, + { + "epoch": 0.01, + "learning_rate": 2.0595133660865733e-05, + "loss": 3.4392, + "step": 1796096 + }, + { + "epoch": 0.01, + "learning_rate": 2.0586764092158945e-05, + "loss": 3.4405, + "step": 1796608 + }, + { + "epoch": 0.01, + "learning_rate": 2.0578378144648425e-05, + "loss": 3.4431, + "step": 1797120 + }, + { + "epoch": 0.01, + "learning_rate": 2.0569992197137902e-05, + "loss": 3.44, + "step": 1797632 + }, + { + "epoch": 0.01, + "learning_rate": 2.0561622628431114e-05, + "loss": 3.4274, + "step": 1798144 + }, + { + "epoch": 0.01, + "learning_rate": 2.0553236680920594e-05, + "loss": 3.4239, + "step": 1798656 + }, + { + "epoch": 0.01, + "learning_rate": 2.0544850733410074e-05, + "loss": 3.4297, + "step": 1799168 + }, + { + "epoch": 0.01, + "learning_rate": 2.0536464785899554e-05, + "loss": 3.4455, + "step": 1799680 + }, + { + "epoch": 0.01, + "learning_rate": 2.0528078838389034e-05, + "loss": 3.4355, + "step": 1800192 + }, + { + "epoch": 0.01, + "learning_rate": 2.0519692890878514e-05, + "loss": 3.4304, + "step": 1800704 + }, + { + "epoch": 0.02, + "learning_rate": 2.0511323322171723e-05, + "loss": 3.4303, + "step": 1801216 + }, + { + "epoch": 0.02, + "learning_rate": 2.0502937374661203e-05, + "loss": 3.4428, + "step": 1801728 + }, + { + "epoch": 0.02, + "learning_rate": 2.0494551427150687e-05, + "loss": 3.4274, + "step": 1802240 + }, + { + "epoch": 0.02, + "learning_rate": 2.0486165479640167e-05, + "loss": 3.4288, + "step": 1802752 + }, + { + "epoch": 0.02, + "learning_rate": 2.0477795910933376e-05, + "loss": 3.4455, + "step": 1803264 + }, + { + "epoch": 0.02, + "learning_rate": 2.0469409963422856e-05, + "loss": 3.4344, + "step": 1803776 + }, + { + "epoch": 0.02, + "learning_rate": 2.0461024015912336e-05, + "loss": 3.4385, + "step": 1804288 + }, + { + "epoch": 0.02, + "learning_rate": 2.0452638068401816e-05, + "loss": 3.424, + "step": 1804800 + }, + { + "epoch": 0.02, + "learning_rate": 2.0444252120891296e-05, + "loss": 3.4353, + "step": 1805312 + }, + { + "epoch": 0.02, + "learning_rate": 2.0435866173380775e-05, + "loss": 3.4275, + "step": 1805824 + }, + { + "epoch": 0.02, + "learning_rate": 2.0427480225870255e-05, + "loss": 3.4423, + "step": 1806336 + }, + { + "epoch": 0.02, + "learning_rate": 2.0419094278359735e-05, + "loss": 3.4365, + "step": 1806848 + }, + { + "epoch": 0.02, + "learning_rate": 2.0410724709652948e-05, + "loss": 3.4401, + "step": 1807360 + }, + { + "epoch": 0.02, + "learning_rate": 2.0402338762142428e-05, + "loss": 3.4352, + "step": 1807872 + }, + { + "epoch": 0.02, + "learning_rate": 2.0393969193435637e-05, + "loss": 3.437, + "step": 1808384 + }, + { + "epoch": 0.02, + "learning_rate": 2.038558324592512e-05, + "loss": 3.4269, + "step": 1808896 + }, + { + "epoch": 0.02, + "learning_rate": 2.03771972984146e-05, + "loss": 3.4263, + "step": 1809408 + }, + { + "epoch": 0.02, + "learning_rate": 2.036881135090408e-05, + "loss": 3.4242, + "step": 1809920 + }, + { + "epoch": 0.02, + "learning_rate": 2.0360425403393557e-05, + "loss": 3.4408, + "step": 1810432 + }, + { + "epoch": 0.02, + "learning_rate": 2.0352039455883037e-05, + "loss": 3.4232, + "step": 1810944 + }, + { + "epoch": 0.02, + "learning_rate": 2.0343653508372517e-05, + "loss": 3.4261, + "step": 1811456 + }, + { + "epoch": 0.02, + "learning_rate": 2.0335267560861997e-05, + "loss": 3.422, + "step": 1811968 + }, + { + "epoch": 0.02, + "learning_rate": 2.032689799215521e-05, + "loss": 3.4341, + "step": 1812480 + }, + { + "epoch": 0.02, + "learning_rate": 2.031852842344842e-05, + "loss": 3.431, + "step": 1812992 + }, + { + "epoch": 0.02, + "learning_rate": 2.03101424759379e-05, + "loss": 3.4225, + "step": 1813504 + }, + { + "epoch": 0.02, + "learning_rate": 2.0301756528427378e-05, + "loss": 3.4413, + "step": 1814016 + }, + { + "epoch": 0.02, + "learning_rate": 2.0293370580916858e-05, + "loss": 3.4413, + "step": 1814528 + }, + { + "epoch": 0.02, + "learning_rate": 2.028498463340634e-05, + "loss": 3.4316, + "step": 1815040 + }, + { + "epoch": 0.02, + "learning_rate": 2.027659868589582e-05, + "loss": 3.4383, + "step": 1815552 + }, + { + "epoch": 0.02, + "learning_rate": 2.026822911718903e-05, + "loss": 3.437, + "step": 1816064 + }, + { + "epoch": 0.02, + "learning_rate": 2.025984316967851e-05, + "loss": 3.4377, + "step": 1816576 + }, + { + "epoch": 0.02, + "learning_rate": 2.025145722216799e-05, + "loss": 3.4303, + "step": 1817088 + }, + { + "epoch": 0.02, + "learning_rate": 2.024307127465747e-05, + "loss": 3.4385, + "step": 1817600 + }, + { + "epoch": 0.02, + "learning_rate": 2.023468532714695e-05, + "loss": 3.427, + "step": 1818112 + }, + { + "epoch": 0.02, + "learning_rate": 2.0226299379636434e-05, + "loss": 3.4382, + "step": 1818624 + }, + { + "epoch": 0.02, + "learning_rate": 2.021791343212591e-05, + "loss": 3.4271, + "step": 1819136 + }, + { + "epoch": 0.02, + "learning_rate": 2.020952748461539e-05, + "loss": 3.4331, + "step": 1819648 + }, + { + "epoch": 0.02, + "learning_rate": 2.0201157915908603e-05, + "loss": 3.4254, + "step": 1820160 + }, + { + "epoch": 0.02, + "learning_rate": 2.0192771968398083e-05, + "loss": 3.4198, + "step": 1820672 + }, + { + "epoch": 0.02, + "learning_rate": 2.0184402399691295e-05, + "loss": 3.425, + "step": 1821184 + }, + { + "epoch": 0.02, + "learning_rate": 2.0176016452180775e-05, + "loss": 3.438, + "step": 1821696 + }, + { + "epoch": 0.02, + "learning_rate": 2.0167630504670255e-05, + "loss": 3.4337, + "step": 1822208 + }, + { + "epoch": 0.02, + "learning_rate": 2.015924455715973e-05, + "loss": 3.4416, + "step": 1822720 + }, + { + "epoch": 0.02, + "learning_rate": 2.015085860964921e-05, + "loss": 3.4237, + "step": 1823232 + }, + { + "epoch": 0.02, + "learning_rate": 2.014247266213869e-05, + "loss": 3.4435, + "step": 1823744 + }, + { + "epoch": 0.02, + "learning_rate": 2.013408671462817e-05, + "loss": 3.4319, + "step": 1824256 + }, + { + "epoch": 0.02, + "learning_rate": 2.012570076711765e-05, + "loss": 3.4393, + "step": 1824768 + }, + { + "epoch": 0.02, + "learning_rate": 2.0117331198410864e-05, + "loss": 3.4332, + "step": 1825280 + }, + { + "epoch": 0.02, + "learning_rate": 2.0108945250900344e-05, + "loss": 3.4305, + "step": 1825792 + }, + { + "epoch": 0.02, + "learning_rate": 2.0100559303389824e-05, + "loss": 3.4324, + "step": 1826304 + }, + { + "epoch": 0.02, + "learning_rate": 2.0092173355879304e-05, + "loss": 3.4435, + "step": 1826816 + }, + { + "epoch": 0.02, + "learning_rate": 2.0083803787172513e-05, + "loss": 3.4267, + "step": 1827328 + }, + { + "epoch": 0.02, + "learning_rate": 2.0075417839661996e-05, + "loss": 3.4361, + "step": 1827840 + }, + { + "epoch": 0.02, + "learning_rate": 2.0067031892151476e-05, + "loss": 3.4344, + "step": 1828352 + }, + { + "epoch": 0.02, + "learning_rate": 2.0058662323444685e-05, + "loss": 3.432, + "step": 1828864 + }, + { + "epoch": 0.02, + "learning_rate": 2.0050276375934165e-05, + "loss": 3.4296, + "step": 1829376 + }, + { + "epoch": 0.02, + "learning_rate": 2.0041890428423645e-05, + "loss": 3.4311, + "step": 1829888 + }, + { + "epoch": 0.02, + "learning_rate": 2.0033504480913125e-05, + "loss": 3.4409, + "step": 1830400 + }, + { + "epoch": 0.02, + "learning_rate": 2.0025134912206338e-05, + "loss": 3.4223, + "step": 1830912 + }, + { + "epoch": 0.02, + "learning_rate": 2.0016748964695818e-05, + "loss": 3.4377, + "step": 1831424 + }, + { + "epoch": 0.03, + "eval_loss": 3.8569254875183105, + "eval_runtime": 303.2207, + "eval_samples_per_second": 1258.459, + "eval_steps_per_second": 39.328, + "step": 1831680 + }, + { + "epoch": 1.0, + "learning_rate": 2.0008363017185297e-05, + "loss": 3.4227, + "step": 1831936 + }, + { + "epoch": 1.0, + "learning_rate": 1.9999977069674777e-05, + "loss": 3.4248, + "step": 1832448 + }, + { + "epoch": 1.0, + "learning_rate": 1.9991607500967987e-05, + "loss": 3.4301, + "step": 1832960 + }, + { + "epoch": 1.0, + "learning_rate": 1.9983221553457467e-05, + "loss": 3.4302, + "step": 1833472 + }, + { + "epoch": 1.0, + "learning_rate": 1.997483560594695e-05, + "loss": 3.4443, + "step": 1833984 + }, + { + "epoch": 1.0, + "learning_rate": 1.996644965843643e-05, + "loss": 3.4319, + "step": 1834496 + }, + { + "epoch": 1.0, + "learning_rate": 1.995808008972964e-05, + "loss": 3.4264, + "step": 1835008 + }, + { + "epoch": 1.0, + "learning_rate": 1.994969414221912e-05, + "loss": 3.4262, + "step": 1835520 + }, + { + "epoch": 1.0, + "learning_rate": 1.9941324573512328e-05, + "loss": 3.4253, + "step": 1836032 + }, + { + "epoch": 1.0, + "learning_rate": 1.993293862600181e-05, + "loss": 3.4369, + "step": 1836544 + }, + { + "epoch": 1.0, + "learning_rate": 1.992455267849129e-05, + "loss": 3.4258, + "step": 1837056 + }, + { + "epoch": 1.0, + "learning_rate": 1.991616673098077e-05, + "loss": 3.4249, + "step": 1837568 + }, + { + "epoch": 1.0, + "learning_rate": 1.990779716227398e-05, + "loss": 3.4363, + "step": 1838080 + }, + { + "epoch": 1.0, + "learning_rate": 1.989941121476346e-05, + "loss": 3.4157, + "step": 1838592 + }, + { + "epoch": 1.0, + "learning_rate": 1.989102526725294e-05, + "loss": 3.4279, + "step": 1839104 + }, + { + "epoch": 1.0, + "learning_rate": 1.988263931974242e-05, + "loss": 3.4227, + "step": 1839616 + }, + { + "epoch": 1.0, + "learning_rate": 1.9874253372231904e-05, + "loss": 3.4192, + "step": 1840128 + }, + { + "epoch": 1.0, + "learning_rate": 1.9865867424721383e-05, + "loss": 3.43, + "step": 1840640 + }, + { + "epoch": 1.0, + "learning_rate": 1.985748147721086e-05, + "loss": 3.4273, + "step": 1841152 + }, + { + "epoch": 1.0, + "learning_rate": 1.984909552970034e-05, + "loss": 3.4297, + "step": 1841664 + }, + { + "epoch": 1.0, + "learning_rate": 1.9840725960993552e-05, + "loss": 3.4432, + "step": 1842176 + }, + { + "epoch": 1.0, + "learning_rate": 1.9832340013483032e-05, + "loss": 3.4313, + "step": 1842688 + }, + { + "epoch": 1.0, + "learning_rate": 1.9823954065972512e-05, + "loss": 3.4283, + "step": 1843200 + }, + { + "epoch": 1.0, + "learning_rate": 1.9815568118461992e-05, + "loss": 3.4272, + "step": 1843712 + }, + { + "epoch": 1.0, + "learning_rate": 1.9807198549755205e-05, + "loss": 3.4259, + "step": 1844224 + }, + { + "epoch": 1.0, + "learning_rate": 1.9798812602244685e-05, + "loss": 3.436, + "step": 1844736 + }, + { + "epoch": 1.0, + "learning_rate": 1.979042665473416e-05, + "loss": 3.4232, + "step": 1845248 + }, + { + "epoch": 1.0, + "learning_rate": 1.978204070722364e-05, + "loss": 3.4295, + "step": 1845760 + }, + { + "epoch": 1.0, + "learning_rate": 1.9773671138516857e-05, + "loss": 3.4163, + "step": 1846272 + }, + { + "epoch": 1.0, + "learning_rate": 1.9765285191006334e-05, + "loss": 3.4256, + "step": 1846784 + }, + { + "epoch": 1.01, + "learning_rate": 1.9756899243495814e-05, + "loss": 3.4213, + "step": 1847296 + }, + { + "epoch": 1.01, + "learning_rate": 1.9748513295985294e-05, + "loss": 3.4297, + "step": 1847808 + }, + { + "epoch": 1.01, + "learning_rate": 1.9740143727278506e-05, + "loss": 3.4333, + "step": 1848320 + }, + { + "epoch": 1.01, + "learning_rate": 1.9731757779767983e-05, + "loss": 3.4359, + "step": 1848832 + }, + { + "epoch": 1.01, + "learning_rate": 1.9723371832257466e-05, + "loss": 3.4229, + "step": 1849344 + }, + { + "epoch": 1.01, + "learning_rate": 1.9714985884746946e-05, + "loss": 3.428, + "step": 1849856 + }, + { + "epoch": 1.01, + "learning_rate": 1.970661631604016e-05, + "loss": 3.436, + "step": 1850368 + }, + { + "epoch": 1.01, + "learning_rate": 1.9698230368529635e-05, + "loss": 3.4256, + "step": 1850880 + }, + { + "epoch": 1.01, + "learning_rate": 1.9689844421019115e-05, + "loss": 3.4273, + "step": 1851392 + }, + { + "epoch": 1.01, + "learning_rate": 1.9681458473508595e-05, + "loss": 3.4216, + "step": 1851904 + }, + { + "epoch": 1.01, + "learning_rate": 1.9673088904801807e-05, + "loss": 3.4264, + "step": 1852416 + }, + { + "epoch": 1.01, + "learning_rate": 1.9664702957291287e-05, + "loss": 3.4279, + "step": 1852928 + }, + { + "epoch": 1.01, + "learning_rate": 1.9656317009780767e-05, + "loss": 3.4337, + "step": 1853440 + }, + { + "epoch": 1.01, + "learning_rate": 1.9647931062270247e-05, + "loss": 3.4273, + "step": 1853952 + }, + { + "epoch": 1.01, + "learning_rate": 1.9639561493563456e-05, + "loss": 3.4349, + "step": 1854464 + }, + { + "epoch": 1.01, + "learning_rate": 1.9631175546052936e-05, + "loss": 3.4312, + "step": 1854976 + }, + { + "epoch": 1.01, + "learning_rate": 1.962278959854242e-05, + "loss": 3.4259, + "step": 1855488 + }, + { + "epoch": 1.01, + "learning_rate": 1.96144036510319e-05, + "loss": 3.4276, + "step": 1856000 + }, + { + "epoch": 1.01, + "learning_rate": 1.960603408232511e-05, + "loss": 3.3932, + "step": 1856512 + }, + { + "epoch": 1.01, + "learning_rate": 1.959764813481459e-05, + "loss": 3.4407, + "step": 1857024 + }, + { + "epoch": 1.01, + "learning_rate": 1.958926218730407e-05, + "loss": 3.4221, + "step": 1857536 + }, + { + "epoch": 1.01, + "learning_rate": 1.958089261859728e-05, + "loss": 3.4311, + "step": 1858048 + }, + { + "epoch": 1.01, + "learning_rate": 1.957250667108676e-05, + "loss": 3.4153, + "step": 1858560 + }, + { + "epoch": 1.01, + "learning_rate": 1.956412072357624e-05, + "loss": 3.4109, + "step": 1859072 + }, + { + "epoch": 1.01, + "learning_rate": 1.9555751154869454e-05, + "loss": 3.4083, + "step": 1859584 + }, + { + "epoch": 1.01, + "learning_rate": 1.954736520735893e-05, + "loss": 3.4177, + "step": 1860096 + }, + { + "epoch": 1.01, + "learning_rate": 1.953897925984841e-05, + "loss": 3.427, + "step": 1860608 + }, + { + "epoch": 1.01, + "learning_rate": 1.953059331233789e-05, + "loss": 3.4191, + "step": 1861120 + }, + { + "epoch": 1.01, + "learning_rate": 1.9522207364827373e-05, + "loss": 3.432, + "step": 1861632 + }, + { + "epoch": 1.01, + "learning_rate": 1.9513821417316853e-05, + "loss": 3.4192, + "step": 1862144 + }, + { + "epoch": 1.01, + "learning_rate": 1.9505435469806333e-05, + "loss": 3.4184, + "step": 1862656 + }, + { + "epoch": 1.01, + "learning_rate": 1.949704952229581e-05, + "loss": 3.4296, + "step": 1863168 + }, + { + "epoch": 1.01, + "learning_rate": 1.9488679953589022e-05, + "loss": 3.4097, + "step": 1863680 + }, + { + "epoch": 1.01, + "learning_rate": 1.9480294006078502e-05, + "loss": 3.4107, + "step": 1864192 + }, + { + "epoch": 1.01, + "learning_rate": 1.9471908058567982e-05, + "loss": 3.4266, + "step": 1864704 + }, + { + "epoch": 1.01, + "learning_rate": 1.9463522111057462e-05, + "loss": 3.4262, + "step": 1865216 + }, + { + "epoch": 1.01, + "learning_rate": 1.9455152542350675e-05, + "loss": 3.4102, + "step": 1865728 + }, + { + "epoch": 1.01, + "learning_rate": 1.9446766594840155e-05, + "loss": 3.4191, + "step": 1866240 + }, + { + "epoch": 1.01, + "learning_rate": 1.9438380647329635e-05, + "loss": 3.4069, + "step": 1866752 + }, + { + "epoch": 1.01, + "learning_rate": 1.942999469981911e-05, + "loss": 3.4306, + "step": 1867264 + }, + { + "epoch": 1.01, + "learning_rate": 1.9421625131112327e-05, + "loss": 3.4294, + "step": 1867776 + }, + { + "epoch": 1.01, + "learning_rate": 1.9413239183601807e-05, + "loss": 3.4242, + "step": 1868288 + }, + { + "epoch": 1.01, + "learning_rate": 1.9404853236091284e-05, + "loss": 3.4292, + "step": 1868800 + }, + { + "epoch": 1.01, + "learning_rate": 1.9396483667384496e-05, + "loss": 3.4324, + "step": 1869312 + }, + { + "epoch": 1.01, + "learning_rate": 1.9388097719873976e-05, + "loss": 3.4475, + "step": 1869824 + }, + { + "epoch": 1.01, + "learning_rate": 1.9379711772363456e-05, + "loss": 3.4257, + "step": 1870336 + }, + { + "epoch": 1.01, + "learning_rate": 1.9371325824852936e-05, + "loss": 3.4279, + "step": 1870848 + }, + { + "epoch": 1.01, + "learning_rate": 1.9362939877342416e-05, + "loss": 3.4236, + "step": 1871360 + }, + { + "epoch": 1.01, + "learning_rate": 1.9354553929831896e-05, + "loss": 3.4204, + "step": 1871872 + }, + { + "epoch": 1.01, + "learning_rate": 1.9346167982321376e-05, + "loss": 3.4254, + "step": 1872384 + }, + { + "epoch": 1.01, + "learning_rate": 1.9337798413614585e-05, + "loss": 3.4309, + "step": 1872896 + }, + { + "epoch": 1.01, + "learning_rate": 1.9329412466104065e-05, + "loss": 3.4316, + "step": 1873408 + }, + { + "epoch": 1.01, + "learning_rate": 1.9321026518593545e-05, + "loss": 3.4329, + "step": 1873920 + }, + { + "epoch": 1.01, + "learning_rate": 1.9312640571083028e-05, + "loss": 3.4147, + "step": 1874432 + }, + { + "epoch": 1.01, + "learning_rate": 1.9304254623572508e-05, + "loss": 3.4105, + "step": 1874944 + }, + { + "epoch": 1.01, + "learning_rate": 1.929590143366945e-05, + "loss": 3.4178, + "step": 1875456 + }, + { + "epoch": 1.01, + "learning_rate": 1.928751548615893e-05, + "loss": 3.4364, + "step": 1875968 + }, + { + "epoch": 1.01, + "learning_rate": 1.9279129538648406e-05, + "loss": 3.4261, + "step": 1876480 + }, + { + "epoch": 1.01, + "learning_rate": 1.927074359113789e-05, + "loss": 3.4155, + "step": 1876992 + }, + { + "epoch": 1.02, + "learning_rate": 1.926235764362737e-05, + "loss": 3.4224, + "step": 1877504 + }, + { + "epoch": 1.02, + "learning_rate": 1.925397169611685e-05, + "loss": 3.4298, + "step": 1878016 + }, + { + "epoch": 1.02, + "learning_rate": 1.924560212741006e-05, + "loss": 3.4191, + "step": 1878528 + }, + { + "epoch": 1.02, + "learning_rate": 1.923721617989954e-05, + "loss": 3.4142, + "step": 1879040 + }, + { + "epoch": 1.02, + "learning_rate": 1.922883023238902e-05, + "loss": 3.4339, + "step": 1879552 + }, + { + "epoch": 1.02, + "learning_rate": 1.92204442848785e-05, + "loss": 3.4257, + "step": 1880064 + }, + { + "epoch": 1.02, + "learning_rate": 1.9212058337367982e-05, + "loss": 3.4278, + "step": 1880576 + }, + { + "epoch": 1.02, + "learning_rate": 1.9203672389857462e-05, + "loss": 3.4143, + "step": 1881088 + }, + { + "epoch": 1.02, + "learning_rate": 1.919528644234694e-05, + "loss": 3.4222, + "step": 1881600 + }, + { + "epoch": 1.02, + "learning_rate": 1.918691687364015e-05, + "loss": 3.4217, + "step": 1882112 + }, + { + "epoch": 1.02, + "learning_rate": 1.917853092612963e-05, + "loss": 3.4318, + "step": 1882624 + }, + { + "epoch": 1.02, + "learning_rate": 1.917014497861911e-05, + "loss": 3.4249, + "step": 1883136 + }, + { + "epoch": 1.02, + "learning_rate": 1.916175903110859e-05, + "loss": 3.4256, + "step": 1883648 + }, + { + "epoch": 1.02, + "learning_rate": 1.9153389462401803e-05, + "loss": 3.4281, + "step": 1884160 + }, + { + "epoch": 1.02, + "learning_rate": 1.9145019893695012e-05, + "loss": 3.4236, + "step": 1884672 + }, + { + "epoch": 1.02, + "learning_rate": 1.9136633946184492e-05, + "loss": 3.4222, + "step": 1885184 + }, + { + "epoch": 1.02, + "learning_rate": 1.9128247998673972e-05, + "loss": 3.4144, + "step": 1885696 + }, + { + "epoch": 1.02, + "learning_rate": 1.9119862051163452e-05, + "loss": 3.4096, + "step": 1886208 + }, + { + "epoch": 1.02, + "learning_rate": 1.9111476103652935e-05, + "loss": 3.4336, + "step": 1886720 + }, + { + "epoch": 1.02, + "learning_rate": 1.9103090156142412e-05, + "loss": 3.4169, + "step": 1887232 + }, + { + "epoch": 1.02, + "learning_rate": 1.9094704208631892e-05, + "loss": 3.4114, + "step": 1887744 + }, + { + "epoch": 1.02, + "learning_rate": 1.9086318261121372e-05, + "loss": 3.4124, + "step": 1888256 + }, + { + "epoch": 1.02, + "learning_rate": 1.9077948692414584e-05, + "loss": 3.4151, + "step": 1888768 + }, + { + "epoch": 1.02, + "learning_rate": 1.9069579123707797e-05, + "loss": 3.4256, + "step": 1889280 + }, + { + "epoch": 1.02, + "learning_rate": 1.9061193176197277e-05, + "loss": 3.4143, + "step": 1889792 + }, + { + "epoch": 1.02, + "learning_rate": 1.9052807228686757e-05, + "loss": 3.4285, + "step": 1890304 + }, + { + "epoch": 1.02, + "learning_rate": 1.9044421281176237e-05, + "loss": 3.4313, + "step": 1890816 + }, + { + "epoch": 1.02, + "learning_rate": 1.9036035333665713e-05, + "loss": 3.4235, + "step": 1891328 + }, + { + "epoch": 1.02, + "learning_rate": 1.9027649386155193e-05, + "loss": 3.426, + "step": 1891840 + }, + { + "epoch": 1.02, + "learning_rate": 1.9019279817448406e-05, + "loss": 3.425, + "step": 1892352 + }, + { + "epoch": 1.02, + "learning_rate": 1.9010893869937886e-05, + "loss": 3.4247, + "step": 1892864 + }, + { + "epoch": 1.02, + "learning_rate": 1.9002507922427366e-05, + "loss": 3.4233, + "step": 1893376 + }, + { + "epoch": 1.02, + "learning_rate": 1.8994121974916846e-05, + "loss": 3.4274, + "step": 1893888 + }, + { + "epoch": 1.02, + "learning_rate": 1.8985736027406326e-05, + "loss": 3.4168, + "step": 1894400 + }, + { + "epoch": 1.02, + "learning_rate": 1.8977350079895806e-05, + "loss": 3.431, + "step": 1894912 + }, + { + "epoch": 1.02, + "learning_rate": 1.8968964132385286e-05, + "loss": 3.418, + "step": 1895424 + }, + { + "epoch": 1.02, + "learning_rate": 1.8960578184874765e-05, + "loss": 3.42, + "step": 1895936 + }, + { + "epoch": 1.02, + "learning_rate": 1.8952208616167978e-05, + "loss": 3.4146, + "step": 1896448 + }, + { + "epoch": 1.02, + "learning_rate": 1.8943822668657458e-05, + "loss": 3.4107, + "step": 1896960 + }, + { + "epoch": 1.02, + "learning_rate": 1.8935453099950667e-05, + "loss": 3.4145, + "step": 1897472 + }, + { + "epoch": 1.02, + "learning_rate": 1.8927067152440147e-05, + "loss": 3.4261, + "step": 1897984 + }, + { + "epoch": 1.02, + "learning_rate": 1.8918681204929627e-05, + "loss": 3.4212, + "step": 1898496 + }, + { + "epoch": 1.02, + "learning_rate": 1.8910295257419107e-05, + "loss": 3.4326, + "step": 1899008 + }, + { + "epoch": 1.02, + "learning_rate": 1.890190930990859e-05, + "loss": 3.4133, + "step": 1899520 + }, + { + "epoch": 1.02, + "learning_rate": 1.8893523362398067e-05, + "loss": 3.4317, + "step": 1900032 + }, + { + "epoch": 1.02, + "learning_rate": 1.8885137414887547e-05, + "loss": 3.4233, + "step": 1900544 + }, + { + "epoch": 1.02, + "learning_rate": 1.8876751467377027e-05, + "loss": 3.4283, + "step": 1901056 + }, + { + "epoch": 1.02, + "learning_rate": 1.886838189867024e-05, + "loss": 3.4242, + "step": 1901568 + }, + { + "epoch": 1.02, + "learning_rate": 1.8859995951159716e-05, + "loss": 3.4189, + "step": 1902080 + }, + { + "epoch": 1.02, + "learning_rate": 1.88516100036492e-05, + "loss": 3.4237, + "step": 1902592 + }, + { + "epoch": 1.02, + "learning_rate": 1.884322405613868e-05, + "loss": 3.435, + "step": 1903104 + }, + { + "epoch": 1.02, + "learning_rate": 1.8834854487431888e-05, + "loss": 3.4143, + "step": 1903616 + }, + { + "epoch": 1.02, + "learning_rate": 1.8826468539921368e-05, + "loss": 3.4246, + "step": 1904128 + }, + { + "epoch": 1.02, + "learning_rate": 1.8818082592410848e-05, + "loss": 3.4223, + "step": 1904640 + }, + { + "epoch": 1.02, + "learning_rate": 1.8809696644900328e-05, + "loss": 3.4214, + "step": 1905152 + }, + { + "epoch": 1.02, + "learning_rate": 1.880132707619354e-05, + "loss": 3.4204, + "step": 1905664 + }, + { + "epoch": 1.02, + "learning_rate": 1.879294112868302e-05, + "loss": 3.4196, + "step": 1906176 + }, + { + "epoch": 1.02, + "learning_rate": 1.87845551811725e-05, + "loss": 3.4295, + "step": 1906688 + }, + { + "epoch": 1.02, + "learning_rate": 1.877616923366198e-05, + "loss": 3.4161, + "step": 1907200 + }, + { + "epoch": 1.02, + "learning_rate": 1.876779966495519e-05, + "loss": 3.4244, + "step": 1907712 + }, + { + "epoch": 1.03, + "eval_loss": 3.859090805053711, + "eval_runtime": 303.4463, + "eval_samples_per_second": 1257.524, + "eval_steps_per_second": 39.299, + "step": 1908000 + }, + { + "epoch": 0.0, + "learning_rate": 1.875941371744467e-05, + "loss": 3.4084, + "step": 1908224 + }, + { + "epoch": 0.0, + "learning_rate": 1.8751027769934153e-05, + "loss": 3.4133, + "step": 1908736 + }, + { + "epoch": 0.0, + "learning_rate": 1.8742641822423633e-05, + "loss": 3.4184, + "step": 1909248 + }, + { + "epoch": 0.0, + "learning_rate": 1.8734255874913113e-05, + "loss": 3.4189, + "step": 1909760 + }, + { + "epoch": 0.0, + "learning_rate": 1.8725886306206322e-05, + "loss": 3.4347, + "step": 1910272 + }, + { + "epoch": 0.0, + "learning_rate": 1.8717500358695802e-05, + "loss": 3.4189, + "step": 1910784 + }, + { + "epoch": 0.0, + "learning_rate": 1.8709114411185282e-05, + "loss": 3.4187, + "step": 1911296 + }, + { + "epoch": 0.0, + "learning_rate": 1.870072846367476e-05, + "loss": 3.4177, + "step": 1911808 + }, + { + "epoch": 0.0, + "learning_rate": 1.8692375273771707e-05, + "loss": 3.413, + "step": 1912320 + }, + { + "epoch": 0.0, + "learning_rate": 1.8683989326261187e-05, + "loss": 3.4258, + "step": 1912832 + }, + { + "epoch": 0.0, + "learning_rate": 1.8675603378750663e-05, + "loss": 3.4151, + "step": 1913344 + }, + { + "epoch": 0.0, + "learning_rate": 1.8667217431240143e-05, + "loss": 3.4145, + "step": 1913856 + }, + { + "epoch": 0.0, + "learning_rate": 1.865884786253336e-05, + "loss": 3.4285, + "step": 1914368 + }, + { + "epoch": 0.0, + "learning_rate": 1.8650461915022836e-05, + "loss": 3.4056, + "step": 1914880 + }, + { + "epoch": 0.0, + "learning_rate": 1.8642075967512316e-05, + "loss": 3.4139, + "step": 1915392 + }, + { + "epoch": 0.0, + "learning_rate": 1.8633690020001796e-05, + "loss": 3.4085, + "step": 1915904 + }, + { + "epoch": 0.0, + "learning_rate": 1.8625304072491275e-05, + "loss": 3.4134, + "step": 1916416 + }, + { + "epoch": 0.0, + "learning_rate": 1.8616918124980755e-05, + "loss": 3.412, + "step": 1916928 + }, + { + "epoch": 0.0, + "learning_rate": 1.8608532177470235e-05, + "loss": 3.42, + "step": 1917440 + }, + { + "epoch": 0.0, + "learning_rate": 1.8600146229959715e-05, + "loss": 3.4214, + "step": 1917952 + }, + { + "epoch": 0.0, + "learning_rate": 1.8591776661252928e-05, + "loss": 3.4333, + "step": 1918464 + }, + { + "epoch": 0.0, + "learning_rate": 1.8583390713742408e-05, + "loss": 3.419, + "step": 1918976 + }, + { + "epoch": 0.0, + "learning_rate": 1.8575004766231888e-05, + "loss": 3.4184, + "step": 1919488 + }, + { + "epoch": 0.0, + "learning_rate": 1.8566618818721368e-05, + "loss": 3.4166, + "step": 1920000 + }, + { + "epoch": 0.0, + "learning_rate": 1.8558249250014577e-05, + "loss": 3.4182, + "step": 1920512 + }, + { + "epoch": 0.0, + "learning_rate": 1.854986330250406e-05, + "loss": 3.4249, + "step": 1921024 + }, + { + "epoch": 0.0, + "learning_rate": 1.854147735499354e-05, + "loss": 3.4114, + "step": 1921536 + }, + { + "epoch": 0.0, + "learning_rate": 1.8533091407483017e-05, + "loss": 3.4225, + "step": 1922048 + }, + { + "epoch": 0.0, + "learning_rate": 1.852472183877623e-05, + "loss": 3.4038, + "step": 1922560 + }, + { + "epoch": 0.0, + "learning_rate": 1.851633589126571e-05, + "loss": 3.4129, + "step": 1923072 + }, + { + "epoch": 0.01, + "learning_rate": 1.850794994375519e-05, + "loss": 3.4143, + "step": 1923584 + }, + { + "epoch": 0.01, + "learning_rate": 1.849956399624467e-05, + "loss": 3.419, + "step": 1924096 + }, + { + "epoch": 0.01, + "learning_rate": 1.849119442753788e-05, + "loss": 3.4271, + "step": 1924608 + }, + { + "epoch": 0.01, + "learning_rate": 1.848280848002736e-05, + "loss": 3.4254, + "step": 1925120 + }, + { + "epoch": 0.01, + "learning_rate": 1.847442253251684e-05, + "loss": 3.4113, + "step": 1925632 + }, + { + "epoch": 0.01, + "learning_rate": 1.8466036585006318e-05, + "loss": 3.4118, + "step": 1926144 + }, + { + "epoch": 0.01, + "learning_rate": 1.845766701629953e-05, + "loss": 3.4298, + "step": 1926656 + }, + { + "epoch": 0.01, + "learning_rate": 1.8449281068789014e-05, + "loss": 3.4154, + "step": 1927168 + }, + { + "epoch": 0.01, + "learning_rate": 1.844089512127849e-05, + "loss": 3.415, + "step": 1927680 + }, + { + "epoch": 0.01, + "learning_rate": 1.843250917376797e-05, + "loss": 3.413, + "step": 1928192 + }, + { + "epoch": 0.01, + "learning_rate": 1.8424139605061183e-05, + "loss": 3.418, + "step": 1928704 + }, + { + "epoch": 0.01, + "learning_rate": 1.8415753657550663e-05, + "loss": 3.4172, + "step": 1929216 + }, + { + "epoch": 0.01, + "learning_rate": 1.840736771004014e-05, + "loss": 3.4232, + "step": 1929728 + }, + { + "epoch": 0.01, + "learning_rate": 1.8398981762529623e-05, + "loss": 3.418, + "step": 1930240 + }, + { + "epoch": 0.01, + "learning_rate": 1.8390612193822835e-05, + "loss": 3.4206, + "step": 1930752 + }, + { + "epoch": 0.01, + "learning_rate": 1.8382226246312315e-05, + "loss": 3.4222, + "step": 1931264 + }, + { + "epoch": 0.01, + "learning_rate": 1.837384029880179e-05, + "loss": 3.4141, + "step": 1931776 + }, + { + "epoch": 0.01, + "learning_rate": 1.836545435129127e-05, + "loss": 3.4171, + "step": 1932288 + }, + { + "epoch": 0.01, + "learning_rate": 1.8357084782584484e-05, + "loss": 3.3839, + "step": 1932800 + }, + { + "epoch": 0.01, + "learning_rate": 1.8348698835073964e-05, + "loss": 3.4267, + "step": 1933312 + }, + { + "epoch": 0.01, + "learning_rate": 1.8340312887563444e-05, + "loss": 3.4108, + "step": 1933824 + }, + { + "epoch": 0.01, + "learning_rate": 1.8331926940052924e-05, + "loss": 3.425, + "step": 1934336 + }, + { + "epoch": 0.01, + "learning_rate": 1.8323557371346136e-05, + "loss": 3.404, + "step": 1934848 + }, + { + "epoch": 0.01, + "learning_rate": 1.8315171423835613e-05, + "loss": 3.3989, + "step": 1935360 + }, + { + "epoch": 0.01, + "learning_rate": 1.830680185512883e-05, + "loss": 3.398, + "step": 1935872 + }, + { + "epoch": 0.01, + "learning_rate": 1.829841590761831e-05, + "loss": 3.4086, + "step": 1936384 + }, + { + "epoch": 0.01, + "learning_rate": 1.8290029960107785e-05, + "loss": 3.4225, + "step": 1936896 + }, + { + "epoch": 0.01, + "learning_rate": 1.8281644012597265e-05, + "loss": 3.4039, + "step": 1937408 + }, + { + "epoch": 0.01, + "learning_rate": 1.8273258065086745e-05, + "loss": 3.4242, + "step": 1937920 + }, + { + "epoch": 0.01, + "learning_rate": 1.8264872117576225e-05, + "loss": 3.4119, + "step": 1938432 + }, + { + "epoch": 0.01, + "learning_rate": 1.8256486170065705e-05, + "loss": 3.4009, + "step": 1938944 + }, + { + "epoch": 0.01, + "learning_rate": 1.8248116601358918e-05, + "loss": 3.4201, + "step": 1939456 + }, + { + "epoch": 0.01, + "learning_rate": 1.8239730653848398e-05, + "loss": 3.405, + "step": 1939968 + }, + { + "epoch": 0.01, + "learning_rate": 1.8231344706337878e-05, + "loss": 3.3967, + "step": 1940480 + }, + { + "epoch": 0.01, + "learning_rate": 1.8222958758827358e-05, + "loss": 3.4121, + "step": 1940992 + }, + { + "epoch": 0.01, + "learning_rate": 1.8214572811316838e-05, + "loss": 3.4168, + "step": 1941504 + }, + { + "epoch": 0.01, + "learning_rate": 1.8206186863806318e-05, + "loss": 3.4022, + "step": 1942016 + }, + { + "epoch": 0.01, + "learning_rate": 1.8197800916295794e-05, + "loss": 3.4077, + "step": 1942528 + }, + { + "epoch": 0.01, + "learning_rate": 1.8189414968785277e-05, + "loss": 3.3992, + "step": 1943040 + }, + { + "epoch": 0.01, + "learning_rate": 1.818104540007849e-05, + "loss": 3.4157, + "step": 1943552 + }, + { + "epoch": 0.01, + "learning_rate": 1.8172659452567966e-05, + "loss": 3.4215, + "step": 1944064 + }, + { + "epoch": 0.01, + "learning_rate": 1.8164273505057446e-05, + "loss": 3.412, + "step": 1944576 + }, + { + "epoch": 0.01, + "learning_rate": 1.8155887557546926e-05, + "loss": 3.4167, + "step": 1945088 + }, + { + "epoch": 0.01, + "learning_rate": 1.814753436764387e-05, + "loss": 3.4213, + "step": 1945600 + }, + { + "epoch": 0.01, + "learning_rate": 1.813914842013335e-05, + "loss": 3.4352, + "step": 1946112 + }, + { + "epoch": 0.01, + "learning_rate": 1.813076247262283e-05, + "loss": 3.4163, + "step": 1946624 + }, + { + "epoch": 0.01, + "learning_rate": 1.812237652511231e-05, + "loss": 3.4209, + "step": 1947136 + }, + { + "epoch": 0.01, + "learning_rate": 1.811399057760179e-05, + "loss": 3.4081, + "step": 1947648 + }, + { + "epoch": 0.01, + "learning_rate": 1.8105604630091268e-05, + "loss": 3.411, + "step": 1948160 + }, + { + "epoch": 0.01, + "learning_rate": 1.8097218682580748e-05, + "loss": 3.4143, + "step": 1948672 + }, + { + "epoch": 0.01, + "learning_rate": 1.808883273507023e-05, + "loss": 3.4207, + "step": 1949184 + }, + { + "epoch": 0.01, + "learning_rate": 1.808046316636344e-05, + "loss": 3.4181, + "step": 1949696 + }, + { + "epoch": 0.01, + "learning_rate": 1.807207721885292e-05, + "loss": 3.4259, + "step": 1950208 + }, + { + "epoch": 0.01, + "learning_rate": 1.80636912713424e-05, + "loss": 3.4023, + "step": 1950720 + }, + { + "epoch": 0.01, + "learning_rate": 1.805530532383188e-05, + "loss": 3.4008, + "step": 1951232 + }, + { + "epoch": 0.01, + "learning_rate": 1.8046952133928825e-05, + "loss": 3.4102, + "step": 1951744 + }, + { + "epoch": 0.01, + "learning_rate": 1.8038566186418305e-05, + "loss": 3.4221, + "step": 1952256 + }, + { + "epoch": 0.01, + "learning_rate": 1.8030180238907785e-05, + "loss": 3.4182, + "step": 1952768 + }, + { + "epoch": 0.01, + "learning_rate": 1.8021794291397265e-05, + "loss": 3.4101, + "step": 1953280 + }, + { + "epoch": 0.02, + "learning_rate": 1.8013424722690474e-05, + "loss": 3.4114, + "step": 1953792 + }, + { + "epoch": 0.02, + "learning_rate": 1.8005038775179954e-05, + "loss": 3.4197, + "step": 1954304 + }, + { + "epoch": 0.02, + "learning_rate": 1.7996652827669437e-05, + "loss": 3.4092, + "step": 1954816 + }, + { + "epoch": 0.02, + "learning_rate": 1.7988266880158914e-05, + "loss": 3.4042, + "step": 1955328 + }, + { + "epoch": 0.02, + "learning_rate": 1.7979897311452126e-05, + "loss": 3.4237, + "step": 1955840 + }, + { + "epoch": 0.02, + "learning_rate": 1.7971511363941606e-05, + "loss": 3.4165, + "step": 1956352 + }, + { + "epoch": 0.02, + "learning_rate": 1.7963125416431086e-05, + "loss": 3.4184, + "step": 1956864 + }, + { + "epoch": 0.02, + "learning_rate": 1.7954739468920563e-05, + "loss": 3.4034, + "step": 1957376 + }, + { + "epoch": 0.02, + "learning_rate": 1.7946353521410046e-05, + "loss": 3.4115, + "step": 1957888 + }, + { + "epoch": 0.02, + "learning_rate": 1.7937967573899526e-05, + "loss": 3.4092, + "step": 1958400 + }, + { + "epoch": 0.02, + "learning_rate": 1.7929581626389006e-05, + "loss": 3.4201, + "step": 1958912 + }, + { + "epoch": 0.02, + "learning_rate": 1.7921195678878486e-05, + "loss": 3.4166, + "step": 1959424 + }, + { + "epoch": 0.02, + "learning_rate": 1.7912826110171695e-05, + "loss": 3.4126, + "step": 1959936 + }, + { + "epoch": 0.02, + "learning_rate": 1.7904440162661175e-05, + "loss": 3.4164, + "step": 1960448 + }, + { + "epoch": 0.02, + "learning_rate": 1.7896070593954388e-05, + "loss": 3.4115, + "step": 1960960 + }, + { + "epoch": 0.02, + "learning_rate": 1.7887684646443868e-05, + "loss": 3.415, + "step": 1961472 + }, + { + "epoch": 0.02, + "learning_rate": 1.7879298698933348e-05, + "loss": 3.4022, + "step": 1961984 + }, + { + "epoch": 0.02, + "learning_rate": 1.7870912751422827e-05, + "loss": 3.4017, + "step": 1962496 + }, + { + "epoch": 0.02, + "learning_rate": 1.7862526803912307e-05, + "loss": 3.417, + "step": 1963008 + }, + { + "epoch": 0.02, + "learning_rate": 1.7854140856401787e-05, + "loss": 3.4118, + "step": 1963520 + }, + { + "epoch": 0.02, + "learning_rate": 1.7845754908891267e-05, + "loss": 3.3986, + "step": 1964032 + }, + { + "epoch": 0.02, + "learning_rate": 1.7837368961380747e-05, + "loss": 3.4043, + "step": 1964544 + }, + { + "epoch": 0.02, + "learning_rate": 1.782899939267396e-05, + "loss": 3.4054, + "step": 1965056 + }, + { + "epoch": 0.02, + "learning_rate": 1.782062982396717e-05, + "loss": 3.4151, + "step": 1965568 + }, + { + "epoch": 0.02, + "learning_rate": 1.781224387645665e-05, + "loss": 3.4044, + "step": 1966080 + }, + { + "epoch": 0.02, + "learning_rate": 1.780385792894613e-05, + "loss": 3.4179, + "step": 1966592 + }, + { + "epoch": 0.02, + "learning_rate": 1.779547198143561e-05, + "loss": 3.4202, + "step": 1967104 + }, + { + "epoch": 0.02, + "learning_rate": 1.7787086033925092e-05, + "loss": 3.4142, + "step": 1967616 + }, + { + "epoch": 0.02, + "learning_rate": 1.777870008641457e-05, + "loss": 3.4118, + "step": 1968128 + }, + { + "epoch": 0.02, + "learning_rate": 1.777033051770778e-05, + "loss": 3.419, + "step": 1968640 + }, + { + "epoch": 0.02, + "learning_rate": 1.776194457019726e-05, + "loss": 3.4139, + "step": 1969152 + }, + { + "epoch": 0.02, + "learning_rate": 1.775355862268674e-05, + "loss": 3.4136, + "step": 1969664 + }, + { + "epoch": 0.02, + "learning_rate": 1.7745172675176218e-05, + "loss": 3.4168, + "step": 1970176 + }, + { + "epoch": 0.02, + "learning_rate": 1.77367867276657e-05, + "loss": 3.405, + "step": 1970688 + }, + { + "epoch": 0.02, + "learning_rate": 1.772840078015518e-05, + "loss": 3.4154, + "step": 1971200 + }, + { + "epoch": 0.02, + "learning_rate": 1.772001483264466e-05, + "loss": 3.4123, + "step": 1971712 + }, + { + "epoch": 0.02, + "learning_rate": 1.771162888513414e-05, + "loss": 3.4049, + "step": 1972224 + }, + { + "epoch": 0.02, + "learning_rate": 1.770325931642735e-05, + "loss": 3.4076, + "step": 1972736 + }, + { + "epoch": 0.02, + "learning_rate": 1.769487336891683e-05, + "loss": 3.4027, + "step": 1973248 + }, + { + "epoch": 0.02, + "learning_rate": 1.7686503800210042e-05, + "loss": 3.4014, + "step": 1973760 + }, + { + "epoch": 0.02, + "learning_rate": 1.7678117852699522e-05, + "loss": 3.418, + "step": 1974272 + }, + { + "epoch": 0.02, + "learning_rate": 1.7669731905189002e-05, + "loss": 3.4081, + "step": 1974784 + }, + { + "epoch": 0.02, + "learning_rate": 1.7661345957678482e-05, + "loss": 3.4238, + "step": 1975296 + }, + { + "epoch": 0.02, + "learning_rate": 1.7652960010167962e-05, + "loss": 3.4, + "step": 1975808 + }, + { + "epoch": 0.02, + "learning_rate": 1.7644574062657442e-05, + "loss": 3.4181, + "step": 1976320 + }, + { + "epoch": 0.02, + "learning_rate": 1.7636188115146922e-05, + "loss": 3.4154, + "step": 1976832 + }, + { + "epoch": 0.02, + "learning_rate": 1.7627802167636402e-05, + "loss": 3.4197, + "step": 1977344 + }, + { + "epoch": 0.02, + "learning_rate": 1.7619432598929615e-05, + "loss": 3.4121, + "step": 1977856 + }, + { + "epoch": 0.02, + "learning_rate": 1.7611046651419094e-05, + "loss": 3.4055, + "step": 1978368 + }, + { + "epoch": 0.02, + "learning_rate": 1.760266070390857e-05, + "loss": 3.4173, + "step": 1978880 + }, + { + "epoch": 0.02, + "learning_rate": 1.7594291135201784e-05, + "loss": 3.4194, + "step": 1979392 + }, + { + "epoch": 0.02, + "learning_rate": 1.7585905187691264e-05, + "loss": 3.4076, + "step": 1979904 + }, + { + "epoch": 0.02, + "learning_rate": 1.7577519240180747e-05, + "loss": 3.4127, + "step": 1980416 + }, + { + "epoch": 0.02, + "learning_rate": 1.7569133292670223e-05, + "loss": 3.4123, + "step": 1980928 + }, + { + "epoch": 0.02, + "learning_rate": 1.7560747345159703e-05, + "loss": 3.4099, + "step": 1981440 + }, + { + "epoch": 0.02, + "learning_rate": 1.7552361397649183e-05, + "loss": 3.4088, + "step": 1981952 + }, + { + "epoch": 0.02, + "learning_rate": 1.7543975450138663e-05, + "loss": 3.4082, + "step": 1982464 + }, + { + "epoch": 0.02, + "learning_rate": 1.7535589502628143e-05, + "loss": 3.4179, + "step": 1982976 + }, + { + "epoch": 0.02, + "learning_rate": 1.7527236312725088e-05, + "loss": 3.4094, + "step": 1983488 + }, + { + "epoch": 0.02, + "learning_rate": 1.7518850365214568e-05, + "loss": 3.4133, + "step": 1984000 + }, + { + "epoch": 0.03, + "eval_loss": 3.8609719276428223, + "eval_runtime": 308.7742, + "eval_samples_per_second": 1235.825, + "eval_steps_per_second": 38.62, + "step": 1984320 + }, + { + "epoch": 1.0, + "learning_rate": 1.7510464417704045e-05, + "loss": 3.4007, + "step": 1984512 + }, + { + "epoch": 1.0, + "learning_rate": 1.7502078470193525e-05, + "loss": 3.4034, + "step": 1985024 + }, + { + "epoch": 1.0, + "learning_rate": 1.7493692522683005e-05, + "loss": 3.4064, + "step": 1985536 + }, + { + "epoch": 1.0, + "learning_rate": 1.7485306575172485e-05, + "loss": 3.4115, + "step": 1986048 + }, + { + "epoch": 1.0, + "learning_rate": 1.7476920627661965e-05, + "loss": 3.4244, + "step": 1986560 + }, + { + "epoch": 1.0, + "learning_rate": 1.7468534680151448e-05, + "loss": 3.4129, + "step": 1987072 + }, + { + "epoch": 1.0, + "learning_rate": 1.7460165111444657e-05, + "loss": 3.4058, + "step": 1987584 + }, + { + "epoch": 1.0, + "learning_rate": 1.7451779163934137e-05, + "loss": 3.407, + "step": 1988096 + }, + { + "epoch": 1.0, + "learning_rate": 1.7443393216423617e-05, + "loss": 3.4014, + "step": 1988608 + }, + { + "epoch": 1.0, + "learning_rate": 1.7435007268913097e-05, + "loss": 3.4111, + "step": 1989120 + }, + { + "epoch": 1.0, + "learning_rate": 1.7426621321402577e-05, + "loss": 3.4085, + "step": 1989632 + }, + { + "epoch": 1.0, + "learning_rate": 1.7418235373892057e-05, + "loss": 3.4086, + "step": 1990144 + }, + { + "epoch": 1.0, + "learning_rate": 1.740986580518527e-05, + "loss": 3.4149, + "step": 1990656 + }, + { + "epoch": 1.0, + "learning_rate": 1.740147985767475e-05, + "loss": 3.3937, + "step": 1991168 + }, + { + "epoch": 1.0, + "learning_rate": 1.7393093910164226e-05, + "loss": 3.406, + "step": 1991680 + }, + { + "epoch": 1.0, + "learning_rate": 1.7384707962653706e-05, + "loss": 3.3958, + "step": 1992192 + }, + { + "epoch": 1.0, + "learning_rate": 1.7376322015143186e-05, + "loss": 3.4095, + "step": 1992704 + }, + { + "epoch": 1.0, + "learning_rate": 1.736793606763267e-05, + "loss": 3.4042, + "step": 1993216 + }, + { + "epoch": 1.0, + "learning_rate": 1.7359566498925878e-05, + "loss": 3.4088, + "step": 1993728 + }, + { + "epoch": 1.0, + "learning_rate": 1.7351180551415358e-05, + "loss": 3.4078, + "step": 1994240 + }, + { + "epoch": 1.0, + "learning_rate": 1.7342794603904838e-05, + "loss": 3.4206, + "step": 1994752 + }, + { + "epoch": 1.0, + "learning_rate": 1.7334408656394318e-05, + "loss": 3.407, + "step": 1995264 + }, + { + "epoch": 1.0, + "learning_rate": 1.7326022708883798e-05, + "loss": 3.4099, + "step": 1995776 + }, + { + "epoch": 1.0, + "learning_rate": 1.7317636761373278e-05, + "loss": 3.4076, + "step": 1996288 + }, + { + "epoch": 1.0, + "learning_rate": 1.7309250813862758e-05, + "loss": 3.4088, + "step": 1996800 + }, + { + "epoch": 1.0, + "learning_rate": 1.730088124515597e-05, + "loss": 3.4136, + "step": 1997312 + }, + { + "epoch": 1.0, + "learning_rate": 1.729249529764545e-05, + "loss": 3.3985, + "step": 1997824 + }, + { + "epoch": 1.0, + "learning_rate": 1.728410935013493e-05, + "loss": 3.4065, + "step": 1998336 + }, + { + "epoch": 1.0, + "learning_rate": 1.7275723402624407e-05, + "loss": 3.3958, + "step": 1998848 + }, + { + "epoch": 1.0, + "learning_rate": 1.7267353833917623e-05, + "loss": 3.4007, + "step": 1999360 + }, + { + "epoch": 1.01, + "learning_rate": 1.7258967886407103e-05, + "loss": 3.4063, + "step": 1999872 + }, + { + "epoch": 1.01, + "learning_rate": 1.7250581938896583e-05, + "loss": 3.4079, + "step": 2000384 + }, + { + "epoch": 1.01, + "learning_rate": 1.724219599138606e-05, + "loss": 3.4077, + "step": 2000896 + }, + { + "epoch": 1.01, + "learning_rate": 1.7233842801483e-05, + "loss": 3.4192, + "step": 2001408 + }, + { + "epoch": 1.01, + "learning_rate": 1.7225456853972484e-05, + "loss": 3.4007, + "step": 2001920 + }, + { + "epoch": 1.01, + "learning_rate": 1.7217070906461964e-05, + "loss": 3.4037, + "step": 2002432 + }, + { + "epoch": 1.01, + "learning_rate": 1.7208684958951444e-05, + "loss": 3.4181, + "step": 2002944 + }, + { + "epoch": 1.01, + "learning_rate": 1.7200299011440924e-05, + "loss": 3.4063, + "step": 2003456 + }, + { + "epoch": 1.01, + "learning_rate": 1.7191929442734133e-05, + "loss": 3.4042, + "step": 2003968 + }, + { + "epoch": 1.01, + "learning_rate": 1.7183543495223613e-05, + "loss": 3.4025, + "step": 2004480 + }, + { + "epoch": 1.01, + "learning_rate": 1.7175157547713093e-05, + "loss": 3.4008, + "step": 2004992 + }, + { + "epoch": 1.01, + "learning_rate": 1.7166771600202573e-05, + "loss": 3.4072, + "step": 2005504 + }, + { + "epoch": 1.01, + "learning_rate": 1.7158385652692056e-05, + "loss": 3.4117, + "step": 2006016 + }, + { + "epoch": 1.01, + "learning_rate": 1.7149999705181533e-05, + "loss": 3.4115, + "step": 2006528 + }, + { + "epoch": 1.01, + "learning_rate": 1.7141613757671013e-05, + "loss": 3.406, + "step": 2007040 + }, + { + "epoch": 1.01, + "learning_rate": 1.7133227810160493e-05, + "loss": 3.4133, + "step": 2007552 + }, + { + "epoch": 1.01, + "learning_rate": 1.7124858241453705e-05, + "loss": 3.403, + "step": 2008064 + }, + { + "epoch": 1.01, + "learning_rate": 1.7116472293943185e-05, + "loss": 3.4089, + "step": 2008576 + }, + { + "epoch": 1.01, + "learning_rate": 1.7108086346432665e-05, + "loss": 3.3749, + "step": 2009088 + }, + { + "epoch": 1.01, + "learning_rate": 1.7099700398922145e-05, + "loss": 3.4171, + "step": 2009600 + }, + { + "epoch": 1.01, + "learning_rate": 1.7091330830215354e-05, + "loss": 3.3967, + "step": 2010112 + }, + { + "epoch": 1.01, + "learning_rate": 1.7082944882704834e-05, + "loss": 3.4131, + "step": 2010624 + }, + { + "epoch": 1.01, + "learning_rate": 1.7074558935194314e-05, + "loss": 3.3954, + "step": 2011136 + }, + { + "epoch": 1.01, + "learning_rate": 1.7066189366487527e-05, + "loss": 3.3911, + "step": 2011648 + }, + { + "epoch": 1.01, + "learning_rate": 1.705781979778074e-05, + "loss": 3.3884, + "step": 2012160 + }, + { + "epoch": 1.01, + "learning_rate": 1.704943385027022e-05, + "loss": 3.3968, + "step": 2012672 + }, + { + "epoch": 1.01, + "learning_rate": 1.70410479027597e-05, + "loss": 3.4097, + "step": 2013184 + }, + { + "epoch": 1.01, + "learning_rate": 1.7032661955249176e-05, + "loss": 3.3924, + "step": 2013696 + }, + { + "epoch": 1.01, + "learning_rate": 1.7024276007738656e-05, + "loss": 3.4157, + "step": 2014208 + }, + { + "epoch": 1.01, + "learning_rate": 1.701589006022814e-05, + "loss": 3.4026, + "step": 2014720 + }, + { + "epoch": 1.01, + "learning_rate": 1.700750411271762e-05, + "loss": 3.3902, + "step": 2015232 + }, + { + "epoch": 1.01, + "learning_rate": 1.69991181652071e-05, + "loss": 3.4096, + "step": 2015744 + }, + { + "epoch": 1.01, + "learning_rate": 1.6990748596500308e-05, + "loss": 3.3938, + "step": 2016256 + }, + { + "epoch": 1.01, + "learning_rate": 1.6982362648989788e-05, + "loss": 3.3869, + "step": 2016768 + }, + { + "epoch": 1.01, + "learning_rate": 1.6973976701479268e-05, + "loss": 3.4024, + "step": 2017280 + }, + { + "epoch": 1.01, + "learning_rate": 1.6965590753968748e-05, + "loss": 3.4076, + "step": 2017792 + }, + { + "epoch": 1.01, + "learning_rate": 1.695722118526196e-05, + "loss": 3.3873, + "step": 2018304 + }, + { + "epoch": 1.01, + "learning_rate": 1.694883523775144e-05, + "loss": 3.4026, + "step": 2018816 + }, + { + "epoch": 1.01, + "learning_rate": 1.694044929024092e-05, + "loss": 3.3915, + "step": 2019328 + }, + { + "epoch": 1.01, + "learning_rate": 1.69320633427304e-05, + "loss": 3.4012, + "step": 2019840 + }, + { + "epoch": 1.01, + "learning_rate": 1.692369377402361e-05, + "loss": 3.4109, + "step": 2020352 + }, + { + "epoch": 1.01, + "learning_rate": 1.6915307826513093e-05, + "loss": 3.4029, + "step": 2020864 + }, + { + "epoch": 1.01, + "learning_rate": 1.6906921879002573e-05, + "loss": 3.4084, + "step": 2021376 + }, + { + "epoch": 1.01, + "learning_rate": 1.689855231029578e-05, + "loss": 3.409, + "step": 2021888 + }, + { + "epoch": 1.01, + "learning_rate": 1.689016636278526e-05, + "loss": 3.4241, + "step": 2022400 + }, + { + "epoch": 1.01, + "learning_rate": 1.688178041527474e-05, + "loss": 3.4061, + "step": 2022912 + }, + { + "epoch": 1.01, + "learning_rate": 1.687339446776422e-05, + "loss": 3.4143, + "step": 2023424 + }, + { + "epoch": 1.01, + "learning_rate": 1.68650085202537e-05, + "loss": 3.3965, + "step": 2023936 + }, + { + "epoch": 1.01, + "learning_rate": 1.685662257274318e-05, + "loss": 3.4017, + "step": 2024448 + }, + { + "epoch": 1.01, + "learning_rate": 1.6848253004036394e-05, + "loss": 3.4047, + "step": 2024960 + }, + { + "epoch": 1.01, + "learning_rate": 1.6839867056525874e-05, + "loss": 3.4074, + "step": 2025472 + }, + { + "epoch": 1.01, + "learning_rate": 1.6831481109015354e-05, + "loss": 3.4126, + "step": 2025984 + }, + { + "epoch": 1.01, + "learning_rate": 1.682309516150483e-05, + "loss": 3.4111, + "step": 2026496 + }, + { + "epoch": 1.01, + "learning_rate": 1.681470921399431e-05, + "loss": 3.3898, + "step": 2027008 + }, + { + "epoch": 1.01, + "learning_rate": 1.6806323266483794e-05, + "loss": 3.3936, + "step": 2027520 + }, + { + "epoch": 1.01, + "learning_rate": 1.6797953697777006e-05, + "loss": 3.3963, + "step": 2028032 + }, + { + "epoch": 1.01, + "learning_rate": 1.6789567750266483e-05, + "loss": 3.4123, + "step": 2028544 + }, + { + "epoch": 1.01, + "learning_rate": 1.6781181802755963e-05, + "loss": 3.4046, + "step": 2029056 + }, + { + "epoch": 1.01, + "learning_rate": 1.6772795855245443e-05, + "loss": 3.3972, + "step": 2029568 + }, + { + "epoch": 1.01, + "learning_rate": 1.6764426286538655e-05, + "loss": 3.4038, + "step": 2030080 + }, + { + "epoch": 1.02, + "learning_rate": 1.6756040339028135e-05, + "loss": 3.406, + "step": 2030592 + }, + { + "epoch": 1.02, + "learning_rate": 1.6747654391517615e-05, + "loss": 3.3985, + "step": 2031104 + }, + { + "epoch": 1.02, + "learning_rate": 1.6739268444007095e-05, + "loss": 3.3977, + "step": 2031616 + }, + { + "epoch": 1.02, + "learning_rate": 1.6730898875300304e-05, + "loss": 3.4126, + "step": 2032128 + }, + { + "epoch": 1.02, + "learning_rate": 1.6722512927789784e-05, + "loss": 3.4088, + "step": 2032640 + }, + { + "epoch": 1.02, + "learning_rate": 1.6714126980279264e-05, + "loss": 3.408, + "step": 2033152 + }, + { + "epoch": 1.02, + "learning_rate": 1.6705741032768747e-05, + "loss": 3.3913, + "step": 2033664 + }, + { + "epoch": 1.02, + "learning_rate": 1.6697355085258227e-05, + "loss": 3.4004, + "step": 2034176 + }, + { + "epoch": 1.02, + "learning_rate": 1.6688969137747707e-05, + "loss": 3.4012, + "step": 2034688 + }, + { + "epoch": 1.02, + "learning_rate": 1.6680583190237187e-05, + "loss": 3.4052, + "step": 2035200 + }, + { + "epoch": 1.02, + "learning_rate": 1.6672197242726664e-05, + "loss": 3.4077, + "step": 2035712 + }, + { + "epoch": 1.02, + "learning_rate": 1.6663827674019876e-05, + "loss": 3.4008, + "step": 2036224 + }, + { + "epoch": 1.02, + "learning_rate": 1.6655441726509356e-05, + "loss": 3.4071, + "step": 2036736 + }, + { + "epoch": 1.02, + "learning_rate": 1.664707215780257e-05, + "loss": 3.4041, + "step": 2037248 + }, + { + "epoch": 1.02, + "learning_rate": 1.663868621029205e-05, + "loss": 3.4041, + "step": 2037760 + }, + { + "epoch": 1.02, + "learning_rate": 1.663030026278153e-05, + "loss": 3.3924, + "step": 2038272 + }, + { + "epoch": 1.02, + "learning_rate": 1.662191431527101e-05, + "loss": 3.3904, + "step": 2038784 + }, + { + "epoch": 1.02, + "learning_rate": 1.6613528367760485e-05, + "loss": 3.4059, + "step": 2039296 + }, + { + "epoch": 1.02, + "learning_rate": 1.6605142420249965e-05, + "loss": 3.4018, + "step": 2039808 + }, + { + "epoch": 1.02, + "learning_rate": 1.659675647273945e-05, + "loss": 3.3902, + "step": 2040320 + }, + { + "epoch": 1.02, + "learning_rate": 1.658837052522893e-05, + "loss": 3.3947, + "step": 2040832 + }, + { + "epoch": 1.02, + "learning_rate": 1.6580000956522138e-05, + "loss": 3.3872, + "step": 2041344 + }, + { + "epoch": 1.02, + "learning_rate": 1.657163138781535e-05, + "loss": 3.4073, + "step": 2041856 + }, + { + "epoch": 1.02, + "learning_rate": 1.656324544030483e-05, + "loss": 3.3964, + "step": 2042368 + }, + { + "epoch": 1.02, + "learning_rate": 1.655485949279431e-05, + "loss": 3.4034, + "step": 2042880 + }, + { + "epoch": 1.02, + "learning_rate": 1.654647354528379e-05, + "loss": 3.4097, + "step": 2043392 + }, + { + "epoch": 1.02, + "learning_rate": 1.653808759777327e-05, + "loss": 3.4047, + "step": 2043904 + }, + { + "epoch": 1.02, + "learning_rate": 1.652970165026275e-05, + "loss": 3.4018, + "step": 2044416 + }, + { + "epoch": 1.02, + "learning_rate": 1.652133208155596e-05, + "loss": 3.412, + "step": 2044928 + }, + { + "epoch": 1.02, + "learning_rate": 1.651294613404544e-05, + "loss": 3.4044, + "step": 2045440 + }, + { + "epoch": 1.02, + "learning_rate": 1.650456018653492e-05, + "loss": 3.4052, + "step": 2045952 + }, + { + "epoch": 1.02, + "learning_rate": 1.6496174239024402e-05, + "loss": 3.4014, + "step": 2046464 + }, + { + "epoch": 1.02, + "learning_rate": 1.6487788291513882e-05, + "loss": 3.3995, + "step": 2046976 + }, + { + "epoch": 1.02, + "learning_rate": 1.6479402344003362e-05, + "loss": 3.4039, + "step": 2047488 + }, + { + "epoch": 1.02, + "learning_rate": 1.6471016396492842e-05, + "loss": 3.4001, + "step": 2048000 + }, + { + "epoch": 1.02, + "learning_rate": 1.646263044898232e-05, + "loss": 3.3965, + "step": 2048512 + }, + { + "epoch": 1.02, + "learning_rate": 1.645426088027553e-05, + "loss": 3.3969, + "step": 2049024 + }, + { + "epoch": 1.02, + "learning_rate": 1.644587493276501e-05, + "loss": 3.3889, + "step": 2049536 + }, + { + "epoch": 1.02, + "learning_rate": 1.6437505364058223e-05, + "loss": 3.3913, + "step": 2050048 + }, + { + "epoch": 1.02, + "learning_rate": 1.6429119416547703e-05, + "loss": 3.4099, + "step": 2050560 + }, + { + "epoch": 1.02, + "learning_rate": 1.6420733469037183e-05, + "loss": 3.4, + "step": 2051072 + }, + { + "epoch": 1.02, + "learning_rate": 1.6412347521526663e-05, + "loss": 3.412, + "step": 2051584 + }, + { + "epoch": 1.02, + "learning_rate": 1.640396157401614e-05, + "loss": 3.3935, + "step": 2052096 + }, + { + "epoch": 1.02, + "learning_rate": 1.639557562650562e-05, + "loss": 3.4069, + "step": 2052608 + }, + { + "epoch": 1.02, + "learning_rate": 1.6387189678995103e-05, + "loss": 3.403, + "step": 2053120 + }, + { + "epoch": 1.02, + "learning_rate": 1.6378803731484583e-05, + "loss": 3.4035, + "step": 2053632 + }, + { + "epoch": 1.02, + "learning_rate": 1.6370434162777792e-05, + "loss": 3.4015, + "step": 2054144 + }, + { + "epoch": 1.02, + "learning_rate": 1.6362048215267272e-05, + "loss": 3.3953, + "step": 2054656 + }, + { + "epoch": 1.02, + "learning_rate": 1.6353662267756752e-05, + "loss": 3.4108, + "step": 2055168 + }, + { + "epoch": 1.02, + "learning_rate": 1.6345276320246232e-05, + "loss": 3.4115, + "step": 2055680 + }, + { + "epoch": 1.02, + "learning_rate": 1.6336906751539445e-05, + "loss": 3.3946, + "step": 2056192 + }, + { + "epoch": 1.02, + "learning_rate": 1.6328520804028925e-05, + "loss": 3.4017, + "step": 2056704 + }, + { + "epoch": 1.02, + "learning_rate": 1.6320134856518405e-05, + "loss": 3.4042, + "step": 2057216 + }, + { + "epoch": 1.02, + "learning_rate": 1.6311748909007884e-05, + "loss": 3.3982, + "step": 2057728 + }, + { + "epoch": 1.02, + "learning_rate": 1.6303379340301094e-05, + "loss": 3.3965, + "step": 2058240 + }, + { + "epoch": 1.02, + "learning_rate": 1.6294993392790574e-05, + "loss": 3.4037, + "step": 2058752 + }, + { + "epoch": 1.02, + "learning_rate": 1.6286607445280057e-05, + "loss": 3.4053, + "step": 2059264 + }, + { + "epoch": 1.02, + "learning_rate": 1.6278237876573266e-05, + "loss": 3.4032, + "step": 2059776 + }, + { + "epoch": 1.02, + "learning_rate": 1.6269851929062746e-05, + "loss": 3.4017, + "step": 2060288 + }, + { + "epoch": 1.03, + "eval_loss": 3.862107276916504, + "eval_runtime": 309.382, + "eval_samples_per_second": 1233.398, + "eval_steps_per_second": 38.545, + "step": 2060640 + }, + { + "epoch": 0.0, + "learning_rate": 1.6261465981552226e-05, + "loss": 3.3848, + "step": 2060800 + }, + { + "epoch": 0.0, + "learning_rate": 1.6253080034041706e-05, + "loss": 3.3922, + "step": 2061312 + }, + { + "epoch": 0.0, + "learning_rate": 1.6244694086531186e-05, + "loss": 3.398, + "step": 2061824 + }, + { + "epoch": 0.0, + "learning_rate": 1.6236308139020666e-05, + "loss": 3.4014, + "step": 2062336 + }, + { + "epoch": 0.0, + "learning_rate": 1.6227938570313878e-05, + "loss": 3.4114, + "step": 2062848 + }, + { + "epoch": 0.0, + "learning_rate": 1.6219552622803358e-05, + "loss": 3.4012, + "step": 2063360 + }, + { + "epoch": 0.0, + "learning_rate": 1.6211166675292838e-05, + "loss": 3.4001, + "step": 2063872 + }, + { + "epoch": 0.0, + "learning_rate": 1.6202780727782318e-05, + "loss": 3.3973, + "step": 2064384 + }, + { + "epoch": 0.0, + "learning_rate": 1.6194427537879263e-05, + "loss": 3.3878, + "step": 2064896 + }, + { + "epoch": 0.0, + "learning_rate": 1.618604159036874e-05, + "loss": 3.3981, + "step": 2065408 + }, + { + "epoch": 0.0, + "learning_rate": 1.617765564285822e-05, + "loss": 3.403, + "step": 2065920 + }, + { + "epoch": 0.0, + "learning_rate": 1.61692696953477e-05, + "loss": 3.3961, + "step": 2066432 + }, + { + "epoch": 0.0, + "learning_rate": 1.616090012664091e-05, + "loss": 3.4024, + "step": 2066944 + }, + { + "epoch": 0.0, + "learning_rate": 1.615251417913039e-05, + "loss": 3.3844, + "step": 2067456 + }, + { + "epoch": 0.0, + "learning_rate": 1.6144128231619872e-05, + "loss": 3.3975, + "step": 2067968 + }, + { + "epoch": 0.0, + "learning_rate": 1.6135742284109352e-05, + "loss": 3.3813, + "step": 2068480 + }, + { + "epoch": 0.0, + "learning_rate": 1.6127356336598832e-05, + "loss": 3.3989, + "step": 2068992 + }, + { + "epoch": 0.0, + "learning_rate": 1.6118970389088312e-05, + "loss": 3.3945, + "step": 2069504 + }, + { + "epoch": 0.0, + "learning_rate": 1.611060082038152e-05, + "loss": 3.3953, + "step": 2070016 + }, + { + "epoch": 0.0, + "learning_rate": 1.6102214872871e-05, + "loss": 3.3965, + "step": 2070528 + }, + { + "epoch": 0.0, + "learning_rate": 1.609382892536048e-05, + "loss": 3.4124, + "step": 2071040 + }, + { + "epoch": 0.0, + "learning_rate": 1.6085442977849964e-05, + "loss": 3.395, + "step": 2071552 + }, + { + "epoch": 0.0, + "learning_rate": 1.6077057030339444e-05, + "loss": 3.4011, + "step": 2072064 + }, + { + "epoch": 0.0, + "learning_rate": 1.606867108282892e-05, + "loss": 3.3963, + "step": 2072576 + }, + { + "epoch": 0.0, + "learning_rate": 1.60602851353184e-05, + "loss": 3.3989, + "step": 2073088 + }, + { + "epoch": 0.0, + "learning_rate": 1.6051915566611613e-05, + "loss": 3.4052, + "step": 2073600 + }, + { + "epoch": 0.0, + "learning_rate": 1.604352961910109e-05, + "loss": 3.3874, + "step": 2074112 + }, + { + "epoch": 0.0, + "learning_rate": 1.6035143671590573e-05, + "loss": 3.3974, + "step": 2074624 + }, + { + "epoch": 0.0, + "learning_rate": 1.6026757724080053e-05, + "loss": 3.3888, + "step": 2075136 + }, + { + "epoch": 0.0, + "learning_rate": 1.6018388155373266e-05, + "loss": 3.3885, + "step": 2075648 + }, + { + "epoch": 0.01, + "learning_rate": 1.6010002207862742e-05, + "loss": 3.3968, + "step": 2076160 + }, + { + "epoch": 0.01, + "learning_rate": 1.6001616260352222e-05, + "loss": 3.3985, + "step": 2076672 + }, + { + "epoch": 0.01, + "learning_rate": 1.5993246691645435e-05, + "loss": 3.3922, + "step": 2077184 + }, + { + "epoch": 0.01, + "learning_rate": 1.5984860744134918e-05, + "loss": 3.4123, + "step": 2077696 + }, + { + "epoch": 0.01, + "learning_rate": 1.5976474796624394e-05, + "loss": 3.393, + "step": 2078208 + }, + { + "epoch": 0.01, + "learning_rate": 1.5968088849113874e-05, + "loss": 3.3918, + "step": 2078720 + }, + { + "epoch": 0.01, + "learning_rate": 1.5959702901603354e-05, + "loss": 3.4064, + "step": 2079232 + }, + { + "epoch": 0.01, + "learning_rate": 1.5951316954092834e-05, + "loss": 3.3922, + "step": 2079744 + }, + { + "epoch": 0.01, + "learning_rate": 1.5942931006582314e-05, + "loss": 3.3948, + "step": 2080256 + }, + { + "epoch": 0.01, + "learning_rate": 1.5934545059071794e-05, + "loss": 3.3965, + "step": 2080768 + }, + { + "epoch": 0.01, + "learning_rate": 1.5926175490365007e-05, + "loss": 3.3893, + "step": 2081280 + }, + { + "epoch": 0.01, + "learning_rate": 1.5917789542854487e-05, + "loss": 3.3968, + "step": 2081792 + }, + { + "epoch": 0.01, + "learning_rate": 1.5909403595343967e-05, + "loss": 3.4049, + "step": 2082304 + }, + { + "epoch": 0.01, + "learning_rate": 1.5901017647833447e-05, + "loss": 3.3954, + "step": 2082816 + }, + { + "epoch": 0.01, + "learning_rate": 1.5892664457930388e-05, + "loss": 3.4008, + "step": 2083328 + }, + { + "epoch": 0.01, + "learning_rate": 1.5884278510419868e-05, + "loss": 3.3984, + "step": 2083840 + }, + { + "epoch": 0.01, + "learning_rate": 1.5875892562909348e-05, + "loss": 3.3942, + "step": 2084352 + }, + { + "epoch": 0.01, + "learning_rate": 1.5867506615398828e-05, + "loss": 3.3999, + "step": 2084864 + }, + { + "epoch": 0.01, + "learning_rate": 1.5859120667888308e-05, + "loss": 3.3659, + "step": 2085376 + }, + { + "epoch": 0.01, + "learning_rate": 1.5850734720377788e-05, + "loss": 3.4029, + "step": 2085888 + }, + { + "epoch": 0.01, + "learning_rate": 1.5842348772867268e-05, + "loss": 3.3898, + "step": 2086400 + }, + { + "epoch": 0.01, + "learning_rate": 1.5833962825356748e-05, + "loss": 3.402, + "step": 2086912 + }, + { + "epoch": 0.01, + "learning_rate": 1.582559325664996e-05, + "loss": 3.3848, + "step": 2087424 + }, + { + "epoch": 0.01, + "learning_rate": 1.581720730913944e-05, + "loss": 3.3786, + "step": 2087936 + }, + { + "epoch": 0.01, + "learning_rate": 1.580883774043265e-05, + "loss": 3.3822, + "step": 2088448 + }, + { + "epoch": 0.01, + "learning_rate": 1.580045179292213e-05, + "loss": 3.3847, + "step": 2088960 + }, + { + "epoch": 0.01, + "learning_rate": 1.579206584541161e-05, + "loss": 3.3994, + "step": 2089472 + }, + { + "epoch": 0.01, + "learning_rate": 1.578367989790109e-05, + "loss": 3.3791, + "step": 2089984 + }, + { + "epoch": 0.01, + "learning_rate": 1.577529395039057e-05, + "loss": 3.407, + "step": 2090496 + }, + { + "epoch": 0.01, + "learning_rate": 1.576690800288005e-05, + "loss": 3.3953, + "step": 2091008 + }, + { + "epoch": 0.01, + "learning_rate": 1.5758538434173262e-05, + "loss": 3.3774, + "step": 2091520 + }, + { + "epoch": 0.01, + "learning_rate": 1.575015248666274e-05, + "loss": 3.3981, + "step": 2092032 + }, + { + "epoch": 0.01, + "learning_rate": 1.5741766539152218e-05, + "loss": 3.3843, + "step": 2092544 + }, + { + "epoch": 0.01, + "learning_rate": 1.5733380591641698e-05, + "loss": 3.38, + "step": 2093056 + }, + { + "epoch": 0.01, + "learning_rate": 1.572499464413118e-05, + "loss": 3.3876, + "step": 2093568 + }, + { + "epoch": 0.01, + "learning_rate": 1.571660869662066e-05, + "loss": 3.4011, + "step": 2094080 + }, + { + "epoch": 0.01, + "learning_rate": 1.570823912791387e-05, + "loss": 3.3781, + "step": 2094592 + }, + { + "epoch": 0.01, + "learning_rate": 1.569985318040335e-05, + "loss": 3.3942, + "step": 2095104 + }, + { + "epoch": 0.01, + "learning_rate": 1.569146723289283e-05, + "loss": 3.3763, + "step": 2095616 + }, + { + "epoch": 0.01, + "learning_rate": 1.568308128538231e-05, + "loss": 3.3917, + "step": 2096128 + }, + { + "epoch": 0.01, + "learning_rate": 1.567469533787179e-05, + "loss": 3.3999, + "step": 2096640 + }, + { + "epoch": 0.01, + "learning_rate": 1.5666309390361274e-05, + "loss": 3.3975, + "step": 2097152 + }, + { + "epoch": 0.01, + "learning_rate": 1.565792344285075e-05, + "loss": 3.396, + "step": 2097664 + }, + { + "epoch": 0.01, + "learning_rate": 1.5649553874143963e-05, + "loss": 3.399, + "step": 2098176 + }, + { + "epoch": 0.01, + "learning_rate": 1.5641167926633443e-05, + "loss": 3.4127, + "step": 2098688 + }, + { + "epoch": 0.01, + "learning_rate": 1.5632781979122923e-05, + "loss": 3.3971, + "step": 2099200 + }, + { + "epoch": 0.01, + "learning_rate": 1.5624396031612403e-05, + "loss": 3.4043, + "step": 2099712 + }, + { + "epoch": 0.01, + "learning_rate": 1.5616010084101883e-05, + "loss": 3.3843, + "step": 2100224 + }, + { + "epoch": 0.01, + "learning_rate": 1.5607624136591363e-05, + "loss": 3.3916, + "step": 2100736 + }, + { + "epoch": 0.01, + "learning_rate": 1.5599238189080843e-05, + "loss": 3.394, + "step": 2101248 + }, + { + "epoch": 0.01, + "learning_rate": 1.5590852241570322e-05, + "loss": 3.3965, + "step": 2101760 + }, + { + "epoch": 0.01, + "learning_rate": 1.558248267286353e-05, + "loss": 3.4029, + "step": 2102272 + }, + { + "epoch": 0.01, + "learning_rate": 1.557409672535301e-05, + "loss": 3.4035, + "step": 2102784 + }, + { + "epoch": 0.01, + "learning_rate": 1.5565710777842495e-05, + "loss": 3.3824, + "step": 2103296 + }, + { + "epoch": 0.01, + "learning_rate": 1.5557324830331975e-05, + "loss": 3.3847, + "step": 2103808 + }, + { + "epoch": 0.01, + "learning_rate": 1.5548971640428916e-05, + "loss": 3.3823, + "step": 2104320 + }, + { + "epoch": 0.01, + "learning_rate": 1.5540585692918396e-05, + "loss": 3.4058, + "step": 2104832 + }, + { + "epoch": 0.01, + "learning_rate": 1.5532199745407873e-05, + "loss": 3.3925, + "step": 2105344 + }, + { + "epoch": 0.01, + "learning_rate": 1.5523813797897356e-05, + "loss": 3.3867, + "step": 2105856 + }, + { + "epoch": 0.01, + "learning_rate": 1.5515427850386836e-05, + "loss": 3.3967, + "step": 2106368 + }, + { + "epoch": 0.02, + "learning_rate": 1.5507041902876316e-05, + "loss": 3.3948, + "step": 2106880 + }, + { + "epoch": 0.02, + "learning_rate": 1.5498672334169525e-05, + "loss": 3.3875, + "step": 2107392 + }, + { + "epoch": 0.02, + "learning_rate": 1.5490286386659005e-05, + "loss": 3.3893, + "step": 2107904 + }, + { + "epoch": 0.02, + "learning_rate": 1.5481900439148485e-05, + "loss": 3.3994, + "step": 2108416 + }, + { + "epoch": 0.02, + "learning_rate": 1.5473514491637965e-05, + "loss": 3.3973, + "step": 2108928 + }, + { + "epoch": 0.02, + "learning_rate": 1.5465128544127445e-05, + "loss": 3.4, + "step": 2109440 + }, + { + "epoch": 0.02, + "learning_rate": 1.545674259661693e-05, + "loss": 3.3803, + "step": 2109952 + }, + { + "epoch": 0.02, + "learning_rate": 1.5448356649106405e-05, + "loss": 3.3915, + "step": 2110464 + }, + { + "epoch": 0.02, + "learning_rate": 1.5439970701595885e-05, + "loss": 3.3921, + "step": 2110976 + }, + { + "epoch": 0.02, + "learning_rate": 1.5431601132889098e-05, + "loss": 3.399, + "step": 2111488 + }, + { + "epoch": 0.02, + "learning_rate": 1.5423215185378577e-05, + "loss": 3.3948, + "step": 2112000 + }, + { + "epoch": 0.02, + "learning_rate": 1.5414829237868057e-05, + "loss": 3.3954, + "step": 2112512 + }, + { + "epoch": 0.02, + "learning_rate": 1.5406443290357537e-05, + "loss": 3.3941, + "step": 2113024 + }, + { + "epoch": 0.02, + "learning_rate": 1.539807372165075e-05, + "loss": 3.3949, + "step": 2113536 + }, + { + "epoch": 0.02, + "learning_rate": 1.538970415294396e-05, + "loss": 3.3935, + "step": 2114048 + }, + { + "epoch": 0.02, + "learning_rate": 1.538131820543344e-05, + "loss": 3.3819, + "step": 2114560 + }, + { + "epoch": 0.02, + "learning_rate": 1.537293225792292e-05, + "loss": 3.3852, + "step": 2115072 + }, + { + "epoch": 0.02, + "learning_rate": 1.53645463104124e-05, + "loss": 3.3916, + "step": 2115584 + }, + { + "epoch": 0.02, + "learning_rate": 1.535616036290188e-05, + "loss": 3.3921, + "step": 2116096 + }, + { + "epoch": 0.02, + "learning_rate": 1.534777441539136e-05, + "loss": 3.3791, + "step": 2116608 + }, + { + "epoch": 0.02, + "learning_rate": 1.533938846788084e-05, + "loss": 3.3851, + "step": 2117120 + }, + { + "epoch": 0.02, + "learning_rate": 1.533101889917405e-05, + "loss": 3.3801, + "step": 2117632 + }, + { + "epoch": 0.02, + "learning_rate": 1.532264933046726e-05, + "loss": 3.3911, + "step": 2118144 + }, + { + "epoch": 0.02, + "learning_rate": 1.5314263382956744e-05, + "loss": 3.3894, + "step": 2118656 + }, + { + "epoch": 0.02, + "learning_rate": 1.5305877435446224e-05, + "loss": 3.3912, + "step": 2119168 + }, + { + "epoch": 0.02, + "learning_rate": 1.5297491487935704e-05, + "loss": 3.3981, + "step": 2119680 + }, + { + "epoch": 0.02, + "learning_rate": 1.528910554042518e-05, + "loss": 3.397, + "step": 2120192 + }, + { + "epoch": 0.02, + "learning_rate": 1.528071959291466e-05, + "loss": 3.3898, + "step": 2120704 + }, + { + "epoch": 0.02, + "learning_rate": 1.527233364540414e-05, + "loss": 3.3984, + "step": 2121216 + }, + { + "epoch": 0.02, + "learning_rate": 1.5263964076697352e-05, + "loss": 3.3939, + "step": 2121728 + }, + { + "epoch": 0.02, + "learning_rate": 1.525557812918683e-05, + "loss": 3.3942, + "step": 2122240 + }, + { + "epoch": 0.02, + "learning_rate": 1.5247192181676312e-05, + "loss": 3.3932, + "step": 2122752 + }, + { + "epoch": 0.02, + "learning_rate": 1.5238806234165792e-05, + "loss": 3.3887, + "step": 2123264 + }, + { + "epoch": 0.02, + "learning_rate": 1.5230420286655272e-05, + "loss": 3.3912, + "step": 2123776 + }, + { + "epoch": 0.02, + "learning_rate": 1.5222034339144752e-05, + "loss": 3.3924, + "step": 2124288 + }, + { + "epoch": 0.02, + "learning_rate": 1.5213648391634234e-05, + "loss": 3.3871, + "step": 2124800 + }, + { + "epoch": 0.02, + "learning_rate": 1.5205278822927443e-05, + "loss": 3.3881, + "step": 2125312 + }, + { + "epoch": 0.02, + "learning_rate": 1.5196892875416923e-05, + "loss": 3.3744, + "step": 2125824 + }, + { + "epoch": 0.02, + "learning_rate": 1.5188523306710134e-05, + "loss": 3.3867, + "step": 2126336 + }, + { + "epoch": 0.02, + "learning_rate": 1.5180137359199614e-05, + "loss": 3.3966, + "step": 2126848 + }, + { + "epoch": 0.02, + "learning_rate": 1.5171751411689095e-05, + "loss": 3.392, + "step": 2127360 + }, + { + "epoch": 0.02, + "learning_rate": 1.5163365464178575e-05, + "loss": 3.402, + "step": 2127872 + }, + { + "epoch": 0.02, + "learning_rate": 1.5154979516668055e-05, + "loss": 3.3777, + "step": 2128384 + }, + { + "epoch": 0.02, + "learning_rate": 1.5146593569157534e-05, + "loss": 3.4036, + "step": 2128896 + }, + { + "epoch": 0.02, + "learning_rate": 1.5138207621647014e-05, + "loss": 3.3961, + "step": 2129408 + }, + { + "epoch": 0.02, + "learning_rate": 1.5129821674136493e-05, + "loss": 3.3985, + "step": 2129920 + }, + { + "epoch": 0.02, + "learning_rate": 1.5121452105429706e-05, + "loss": 3.3849, + "step": 2130432 + }, + { + "epoch": 0.02, + "learning_rate": 1.5113066157919184e-05, + "loss": 3.3871, + "step": 2130944 + }, + { + "epoch": 0.02, + "learning_rate": 1.5104680210408664e-05, + "loss": 3.402, + "step": 2131456 + }, + { + "epoch": 0.02, + "learning_rate": 1.5096310641701877e-05, + "loss": 3.4014, + "step": 2131968 + }, + { + "epoch": 0.02, + "learning_rate": 1.5087924694191355e-05, + "loss": 3.3872, + "step": 2132480 + }, + { + "epoch": 0.02, + "learning_rate": 1.5079538746680835e-05, + "loss": 3.3883, + "step": 2132992 + }, + { + "epoch": 0.02, + "learning_rate": 1.5071152799170315e-05, + "loss": 3.3929, + "step": 2133504 + }, + { + "epoch": 0.02, + "learning_rate": 1.5062766851659796e-05, + "loss": 3.3918, + "step": 2134016 + }, + { + "epoch": 0.02, + "learning_rate": 1.5054380904149276e-05, + "loss": 3.3843, + "step": 2134528 + }, + { + "epoch": 0.02, + "learning_rate": 1.5045994956638756e-05, + "loss": 3.3973, + "step": 2135040 + }, + { + "epoch": 0.02, + "learning_rate": 1.5037609009128236e-05, + "loss": 3.3892, + "step": 2135552 + }, + { + "epoch": 0.02, + "learning_rate": 1.502925581922518e-05, + "loss": 3.3901, + "step": 2136064 + }, + { + "epoch": 0.02, + "learning_rate": 1.5020869871714658e-05, + "loss": 3.3917, + "step": 2136576 + }, + { + "epoch": 0.03, + "eval_loss": 3.862421751022339, + "eval_runtime": 311.6886, + "eval_samples_per_second": 1224.27, + "eval_steps_per_second": 38.259, + "step": 2136960 + }, + { + "epoch": 1.0, + "learning_rate": 1.5012483924204138e-05, + "loss": 3.3851, + "step": 2137088 + }, + { + "epoch": 1.0, + "learning_rate": 1.5004097976693618e-05, + "loss": 3.3786, + "step": 2137600 + }, + { + "epoch": 1.0, + "learning_rate": 1.4995712029183098e-05, + "loss": 3.3879, + "step": 2138112 + }, + { + "epoch": 1.0, + "learning_rate": 1.4987326081672578e-05, + "loss": 3.3946, + "step": 2138624 + }, + { + "epoch": 1.0, + "learning_rate": 1.497894013416206e-05, + "loss": 3.3925, + "step": 2139136 + }, + { + "epoch": 1.0, + "learning_rate": 1.4970570565455268e-05, + "loss": 3.3961, + "step": 2139648 + }, + { + "epoch": 1.0, + "learning_rate": 1.496218461794475e-05, + "loss": 3.3902, + "step": 2140160 + }, + { + "epoch": 1.0, + "learning_rate": 1.495379867043423e-05, + "loss": 3.3874, + "step": 2140672 + }, + { + "epoch": 1.0, + "learning_rate": 1.494541272292371e-05, + "loss": 3.3768, + "step": 2141184 + }, + { + "epoch": 1.0, + "learning_rate": 1.493704315421692e-05, + "loss": 3.3891, + "step": 2141696 + }, + { + "epoch": 1.0, + "learning_rate": 1.49286572067064e-05, + "loss": 3.3927, + "step": 2142208 + }, + { + "epoch": 1.0, + "learning_rate": 1.492027125919588e-05, + "loss": 3.3886, + "step": 2142720 + }, + { + "epoch": 1.0, + "learning_rate": 1.491188531168536e-05, + "loss": 3.3958, + "step": 2143232 + }, + { + "epoch": 1.0, + "learning_rate": 1.4903499364174839e-05, + "loss": 3.372, + "step": 2143744 + }, + { + "epoch": 1.0, + "learning_rate": 1.4895113416664319e-05, + "loss": 3.3844, + "step": 2144256 + }, + { + "epoch": 1.0, + "learning_rate": 1.4886727469153799e-05, + "loss": 3.3756, + "step": 2144768 + }, + { + "epoch": 1.0, + "learning_rate": 1.487834152164328e-05, + "loss": 3.3898, + "step": 2145280 + }, + { + "epoch": 1.0, + "learning_rate": 1.486997195293649e-05, + "loss": 3.3843, + "step": 2145792 + }, + { + "epoch": 1.0, + "learning_rate": 1.4861602384229704e-05, + "loss": 3.3844, + "step": 2146304 + }, + { + "epoch": 1.0, + "learning_rate": 1.4853216436719184e-05, + "loss": 3.3832, + "step": 2146816 + }, + { + "epoch": 1.0, + "learning_rate": 1.484483048920866e-05, + "loss": 3.404, + "step": 2147328 + }, + { + "epoch": 1.0, + "learning_rate": 1.4836444541698142e-05, + "loss": 3.3875, + "step": 2147840 + }, + { + "epoch": 1.0, + "learning_rate": 1.4828058594187622e-05, + "loss": 3.3903, + "step": 2148352 + }, + { + "epoch": 1.0, + "learning_rate": 1.4819672646677102e-05, + "loss": 3.3852, + "step": 2148864 + }, + { + "epoch": 1.0, + "learning_rate": 1.4811286699166582e-05, + "loss": 3.3915, + "step": 2149376 + }, + { + "epoch": 1.0, + "learning_rate": 1.4802900751656062e-05, + "loss": 3.3934, + "step": 2149888 + }, + { + "epoch": 1.0, + "learning_rate": 1.4794531182949273e-05, + "loss": 3.3768, + "step": 2150400 + }, + { + "epoch": 1.0, + "learning_rate": 1.4786145235438753e-05, + "loss": 3.3855, + "step": 2150912 + }, + { + "epoch": 1.0, + "learning_rate": 1.4777759287928234e-05, + "loss": 3.3771, + "step": 2151424 + }, + { + "epoch": 1.0, + "learning_rate": 1.4769389719221443e-05, + "loss": 3.3809, + "step": 2151936 + }, + { + "epoch": 1.01, + "learning_rate": 1.4761003771710923e-05, + "loss": 3.3891, + "step": 2152448 + }, + { + "epoch": 1.01, + "learning_rate": 1.4752617824200405e-05, + "loss": 3.3867, + "step": 2152960 + }, + { + "epoch": 1.01, + "learning_rate": 1.4744231876689885e-05, + "loss": 3.3837, + "step": 2153472 + }, + { + "epoch": 1.01, + "learning_rate": 1.4735862307983096e-05, + "loss": 3.4007, + "step": 2153984 + }, + { + "epoch": 1.01, + "learning_rate": 1.4727492739276308e-05, + "loss": 3.3819, + "step": 2154496 + }, + { + "epoch": 1.01, + "learning_rate": 1.4719106791765785e-05, + "loss": 3.3864, + "step": 2155008 + }, + { + "epoch": 1.01, + "learning_rate": 1.4710720844255266e-05, + "loss": 3.3956, + "step": 2155520 + }, + { + "epoch": 1.01, + "learning_rate": 1.4702334896744746e-05, + "loss": 3.3793, + "step": 2156032 + }, + { + "epoch": 1.01, + "learning_rate": 1.4693948949234226e-05, + "loss": 3.3851, + "step": 2156544 + }, + { + "epoch": 1.01, + "learning_rate": 1.4685563001723706e-05, + "loss": 3.3848, + "step": 2157056 + }, + { + "epoch": 1.01, + "learning_rate": 1.4677177054213186e-05, + "loss": 3.3798, + "step": 2157568 + }, + { + "epoch": 1.01, + "learning_rate": 1.4668807485506397e-05, + "loss": 3.3876, + "step": 2158080 + }, + { + "epoch": 1.01, + "learning_rate": 1.4660421537995877e-05, + "loss": 3.398, + "step": 2158592 + }, + { + "epoch": 1.01, + "learning_rate": 1.4652035590485359e-05, + "loss": 3.3865, + "step": 2159104 + }, + { + "epoch": 1.01, + "learning_rate": 1.4643666021778568e-05, + "loss": 3.3916, + "step": 2159616 + }, + { + "epoch": 1.01, + "learning_rate": 1.463528007426805e-05, + "loss": 3.3894, + "step": 2160128 + }, + { + "epoch": 1.01, + "learning_rate": 1.462689412675753e-05, + "loss": 3.3839, + "step": 2160640 + }, + { + "epoch": 1.01, + "learning_rate": 1.461850817924701e-05, + "loss": 3.3891, + "step": 2161152 + }, + { + "epoch": 1.01, + "learning_rate": 1.4610122231736487e-05, + "loss": 3.3569, + "step": 2161664 + }, + { + "epoch": 1.01, + "learning_rate": 1.4601736284225967e-05, + "loss": 3.3902, + "step": 2162176 + }, + { + "epoch": 1.01, + "learning_rate": 1.4593350336715447e-05, + "loss": 3.386, + "step": 2162688 + }, + { + "epoch": 1.01, + "learning_rate": 1.458498076800866e-05, + "loss": 3.3927, + "step": 2163200 + }, + { + "epoch": 1.01, + "learning_rate": 1.4576594820498138e-05, + "loss": 3.3756, + "step": 2163712 + }, + { + "epoch": 1.01, + "learning_rate": 1.4568208872987618e-05, + "loss": 3.3671, + "step": 2164224 + }, + { + "epoch": 1.01, + "learning_rate": 1.455983930428083e-05, + "loss": 3.3722, + "step": 2164736 + }, + { + "epoch": 1.01, + "learning_rate": 1.4551453356770312e-05, + "loss": 3.3734, + "step": 2165248 + }, + { + "epoch": 1.01, + "learning_rate": 1.4543067409259789e-05, + "loss": 3.3927, + "step": 2165760 + }, + { + "epoch": 1.01, + "learning_rate": 1.4534681461749269e-05, + "loss": 3.3673, + "step": 2166272 + }, + { + "epoch": 1.01, + "learning_rate": 1.452629551423875e-05, + "loss": 3.3954, + "step": 2166784 + }, + { + "epoch": 1.01, + "learning_rate": 1.451790956672823e-05, + "loss": 3.3847, + "step": 2167296 + }, + { + "epoch": 1.01, + "learning_rate": 1.450952361921771e-05, + "loss": 3.3719, + "step": 2167808 + }, + { + "epoch": 1.01, + "learning_rate": 1.450113767170719e-05, + "loss": 3.3875, + "step": 2168320 + }, + { + "epoch": 1.01, + "learning_rate": 1.4492768103000401e-05, + "loss": 3.373, + "step": 2168832 + }, + { + "epoch": 1.01, + "learning_rate": 1.4484398534293612e-05, + "loss": 3.3699, + "step": 2169344 + }, + { + "epoch": 1.01, + "learning_rate": 1.4476012586783092e-05, + "loss": 3.3728, + "step": 2169856 + }, + { + "epoch": 1.01, + "learning_rate": 1.4467626639272572e-05, + "loss": 3.3875, + "step": 2170368 + }, + { + "epoch": 1.01, + "learning_rate": 1.4459240691762052e-05, + "loss": 3.3703, + "step": 2170880 + }, + { + "epoch": 1.01, + "learning_rate": 1.4450871123055263e-05, + "loss": 3.3836, + "step": 2171392 + }, + { + "epoch": 1.01, + "learning_rate": 1.4442485175544742e-05, + "loss": 3.3646, + "step": 2171904 + }, + { + "epoch": 1.01, + "learning_rate": 1.4434099228034222e-05, + "loss": 3.3843, + "step": 2172416 + }, + { + "epoch": 1.01, + "learning_rate": 1.4425713280523704e-05, + "loss": 3.3874, + "step": 2172928 + }, + { + "epoch": 1.01, + "learning_rate": 1.4417327333013184e-05, + "loss": 3.3882, + "step": 2173440 + }, + { + "epoch": 1.01, + "learning_rate": 1.4408941385502664e-05, + "loss": 3.3864, + "step": 2173952 + }, + { + "epoch": 1.01, + "learning_rate": 1.4400571816795875e-05, + "loss": 3.3893, + "step": 2174464 + }, + { + "epoch": 1.01, + "learning_rate": 1.4392185869285355e-05, + "loss": 3.4018, + "step": 2174976 + }, + { + "epoch": 1.01, + "learning_rate": 1.4383799921774835e-05, + "loss": 3.3896, + "step": 2175488 + }, + { + "epoch": 1.01, + "learning_rate": 1.4375413974264315e-05, + "loss": 3.3953, + "step": 2176000 + }, + { + "epoch": 1.01, + "learning_rate": 1.4367028026753793e-05, + "loss": 3.3746, + "step": 2176512 + }, + { + "epoch": 1.01, + "learning_rate": 1.4358642079243273e-05, + "loss": 3.3819, + "step": 2177024 + }, + { + "epoch": 1.01, + "learning_rate": 1.4350256131732753e-05, + "loss": 3.3833, + "step": 2177536 + }, + { + "epoch": 1.01, + "learning_rate": 1.4341870184222233e-05, + "loss": 3.3849, + "step": 2178048 + }, + { + "epoch": 1.01, + "learning_rate": 1.4333516994319176e-05, + "loss": 3.3919, + "step": 2178560 + }, + { + "epoch": 1.01, + "learning_rate": 1.4325131046808658e-05, + "loss": 3.3926, + "step": 2179072 + }, + { + "epoch": 1.01, + "learning_rate": 1.4316745099298138e-05, + "loss": 3.3793, + "step": 2179584 + }, + { + "epoch": 1.01, + "learning_rate": 1.4308359151787614e-05, + "loss": 3.3721, + "step": 2180096 + }, + { + "epoch": 1.01, + "learning_rate": 1.4299989583080828e-05, + "loss": 3.3739, + "step": 2180608 + }, + { + "epoch": 1.01, + "learning_rate": 1.4291603635570308e-05, + "loss": 3.3936, + "step": 2181120 + }, + { + "epoch": 1.01, + "learning_rate": 1.4283217688059788e-05, + "loss": 3.3853, + "step": 2181632 + }, + { + "epoch": 1.01, + "learning_rate": 1.4274831740549267e-05, + "loss": 3.3783, + "step": 2182144 + }, + { + "epoch": 1.01, + "learning_rate": 1.4266445793038747e-05, + "loss": 3.3846, + "step": 2182656 + }, + { + "epoch": 1.02, + "learning_rate": 1.4258076224331959e-05, + "loss": 3.3858, + "step": 2183168 + }, + { + "epoch": 1.02, + "learning_rate": 1.4249690276821439e-05, + "loss": 3.3764, + "step": 2183680 + }, + { + "epoch": 1.02, + "learning_rate": 1.4241304329310917e-05, + "loss": 3.3769, + "step": 2184192 + }, + { + "epoch": 1.02, + "learning_rate": 1.4232918381800397e-05, + "loss": 3.3897, + "step": 2184704 + }, + { + "epoch": 1.02, + "learning_rate": 1.4224532434289877e-05, + "loss": 3.3905, + "step": 2185216 + }, + { + "epoch": 1.02, + "learning_rate": 1.4216146486779359e-05, + "loss": 3.3884, + "step": 2185728 + }, + { + "epoch": 1.02, + "learning_rate": 1.4207760539268839e-05, + "loss": 3.3697, + "step": 2186240 + }, + { + "epoch": 1.02, + "learning_rate": 1.4199390970562048e-05, + "loss": 3.3808, + "step": 2186752 + }, + { + "epoch": 1.02, + "learning_rate": 1.419100502305153e-05, + "loss": 3.3817, + "step": 2187264 + }, + { + "epoch": 1.02, + "learning_rate": 1.418261907554101e-05, + "loss": 3.3858, + "step": 2187776 + }, + { + "epoch": 1.02, + "learning_rate": 1.417423312803049e-05, + "loss": 3.3875, + "step": 2188288 + }, + { + "epoch": 1.02, + "learning_rate": 1.41658635593237e-05, + "loss": 3.3835, + "step": 2188800 + }, + { + "epoch": 1.02, + "learning_rate": 1.4157493990616913e-05, + "loss": 3.3814, + "step": 2189312 + }, + { + "epoch": 1.02, + "learning_rate": 1.4149108043106391e-05, + "loss": 3.3848, + "step": 2189824 + }, + { + "epoch": 1.02, + "learning_rate": 1.4140722095595871e-05, + "loss": 3.3848, + "step": 2190336 + }, + { + "epoch": 1.02, + "learning_rate": 1.4132336148085351e-05, + "loss": 3.3754, + "step": 2190848 + }, + { + "epoch": 1.02, + "learning_rate": 1.4123966579378562e-05, + "loss": 3.3767, + "step": 2191360 + }, + { + "epoch": 1.02, + "learning_rate": 1.4115580631868042e-05, + "loss": 3.3812, + "step": 2191872 + }, + { + "epoch": 1.02, + "learning_rate": 1.4107194684357522e-05, + "loss": 3.3805, + "step": 2192384 + }, + { + "epoch": 1.02, + "learning_rate": 1.4098808736847002e-05, + "loss": 3.3649, + "step": 2192896 + }, + { + "epoch": 1.02, + "learning_rate": 1.4090422789336483e-05, + "loss": 3.3779, + "step": 2193408 + }, + { + "epoch": 1.02, + "learning_rate": 1.4082036841825963e-05, + "loss": 3.3676, + "step": 2193920 + }, + { + "epoch": 1.02, + "learning_rate": 1.4073667273119174e-05, + "loss": 3.3859, + "step": 2194432 + }, + { + "epoch": 1.02, + "learning_rate": 1.4065281325608654e-05, + "loss": 3.3795, + "step": 2194944 + }, + { + "epoch": 1.02, + "learning_rate": 1.4056895378098134e-05, + "loss": 3.3804, + "step": 2195456 + }, + { + "epoch": 1.02, + "learning_rate": 1.4048509430587614e-05, + "loss": 3.3848, + "step": 2195968 + }, + { + "epoch": 1.02, + "learning_rate": 1.4040123483077094e-05, + "loss": 3.3874, + "step": 2196480 + }, + { + "epoch": 1.02, + "learning_rate": 1.4031737535566572e-05, + "loss": 3.3826, + "step": 2196992 + }, + { + "epoch": 1.02, + "learning_rate": 1.4023351588056052e-05, + "loss": 3.3833, + "step": 2197504 + }, + { + "epoch": 1.02, + "learning_rate": 1.4014982019349266e-05, + "loss": 3.3901, + "step": 2198016 + }, + { + "epoch": 1.02, + "learning_rate": 1.4006596071838743e-05, + "loss": 3.383, + "step": 2198528 + }, + { + "epoch": 1.02, + "learning_rate": 1.3998210124328223e-05, + "loss": 3.381, + "step": 2199040 + }, + { + "epoch": 1.02, + "learning_rate": 1.3989824176817704e-05, + "loss": 3.3827, + "step": 2199552 + }, + { + "epoch": 1.02, + "learning_rate": 1.3981438229307184e-05, + "loss": 3.3805, + "step": 2200064 + }, + { + "epoch": 1.02, + "learning_rate": 1.3973052281796664e-05, + "loss": 3.3795, + "step": 2200576 + }, + { + "epoch": 1.02, + "learning_rate": 1.3964682713089875e-05, + "loss": 3.3778, + "step": 2201088 + }, + { + "epoch": 1.02, + "learning_rate": 1.3956296765579355e-05, + "loss": 3.379, + "step": 2201600 + }, + { + "epoch": 1.02, + "learning_rate": 1.3947910818068835e-05, + "loss": 3.3636, + "step": 2202112 + }, + { + "epoch": 1.02, + "learning_rate": 1.3939524870558315e-05, + "loss": 3.3781, + "step": 2202624 + }, + { + "epoch": 1.02, + "learning_rate": 1.3931155301851526e-05, + "loss": 3.3828, + "step": 2203136 + }, + { + "epoch": 1.02, + "learning_rate": 1.3922769354341006e-05, + "loss": 3.3842, + "step": 2203648 + }, + { + "epoch": 1.02, + "learning_rate": 1.3914383406830486e-05, + "loss": 3.3893, + "step": 2204160 + }, + { + "epoch": 1.02, + "learning_rate": 1.3905997459319967e-05, + "loss": 3.3754, + "step": 2204672 + }, + { + "epoch": 1.02, + "learning_rate": 1.3897611511809447e-05, + "loss": 3.3895, + "step": 2205184 + }, + { + "epoch": 1.02, + "learning_rate": 1.3889225564298924e-05, + "loss": 3.3845, + "step": 2205696 + }, + { + "epoch": 1.02, + "learning_rate": 1.3880839616788405e-05, + "loss": 3.3833, + "step": 2206208 + }, + { + "epoch": 1.02, + "learning_rate": 1.3872470048081618e-05, + "loss": 3.3797, + "step": 2206720 + }, + { + "epoch": 1.02, + "learning_rate": 1.3864084100571098e-05, + "loss": 3.3784, + "step": 2207232 + }, + { + "epoch": 1.02, + "learning_rate": 1.3855698153060576e-05, + "loss": 3.3926, + "step": 2207744 + }, + { + "epoch": 1.02, + "learning_rate": 1.3847328584353789e-05, + "loss": 3.3872, + "step": 2208256 + }, + { + "epoch": 1.02, + "learning_rate": 1.3838942636843269e-05, + "loss": 3.3796, + "step": 2208768 + }, + { + "epoch": 1.02, + "learning_rate": 1.3830556689332747e-05, + "loss": 3.3778, + "step": 2209280 + }, + { + "epoch": 1.02, + "learning_rate": 1.3822170741822227e-05, + "loss": 3.3806, + "step": 2209792 + }, + { + "epoch": 1.02, + "learning_rate": 1.3813784794311707e-05, + "loss": 3.3794, + "step": 2210304 + }, + { + "epoch": 1.02, + "learning_rate": 1.3805398846801187e-05, + "loss": 3.377, + "step": 2210816 + }, + { + "epoch": 1.02, + "learning_rate": 1.3797012899290668e-05, + "loss": 3.3847, + "step": 2211328 + }, + { + "epoch": 1.02, + "learning_rate": 1.3788626951780148e-05, + "loss": 3.3803, + "step": 2211840 + }, + { + "epoch": 1.02, + "learning_rate": 1.3780257383073359e-05, + "loss": 3.382, + "step": 2212352 + }, + { + "epoch": 1.02, + "learning_rate": 1.3771871435562839e-05, + "loss": 3.3815, + "step": 2212864 + }, + { + "epoch": 1.03, + "eval_loss": 3.8638553619384766, + "eval_runtime": 308.5616, + "eval_samples_per_second": 1236.677, + "eval_steps_per_second": 38.647, + "step": 2213280 + }, + { + "epoch": 0.0, + "learning_rate": 1.3763501866856048e-05, + "loss": 3.3803, + "step": 2213376 + }, + { + "epoch": 0.0, + "learning_rate": 1.375511591934553e-05, + "loss": 3.3681, + "step": 2213888 + }, + { + "epoch": 0.0, + "learning_rate": 1.374672997183501e-05, + "loss": 3.376, + "step": 2214400 + }, + { + "epoch": 0.0, + "learning_rate": 1.373834402432449e-05, + "loss": 3.3877, + "step": 2214912 + }, + { + "epoch": 0.0, + "learning_rate": 1.37299744556177e-05, + "loss": 3.3832, + "step": 2215424 + }, + { + "epoch": 0.0, + "learning_rate": 1.3721604886910913e-05, + "loss": 3.3871, + "step": 2215936 + }, + { + "epoch": 0.0, + "learning_rate": 1.3713218939400393e-05, + "loss": 3.3762, + "step": 2216448 + }, + { + "epoch": 0.0, + "learning_rate": 1.3704832991889871e-05, + "loss": 3.3781, + "step": 2216960 + }, + { + "epoch": 0.0, + "learning_rate": 1.3696447044379351e-05, + "loss": 3.3683, + "step": 2217472 + }, + { + "epoch": 0.0, + "learning_rate": 1.3688077475672564e-05, + "loss": 3.381, + "step": 2217984 + }, + { + "epoch": 0.0, + "learning_rate": 1.3679691528162045e-05, + "loss": 3.3781, + "step": 2218496 + }, + { + "epoch": 0.0, + "learning_rate": 1.3671305580651522e-05, + "loss": 3.3819, + "step": 2219008 + }, + { + "epoch": 0.0, + "learning_rate": 1.3662919633141002e-05, + "loss": 3.3876, + "step": 2219520 + }, + { + "epoch": 0.0, + "learning_rate": 1.3654533685630483e-05, + "loss": 3.36, + "step": 2220032 + }, + { + "epoch": 0.0, + "learning_rate": 1.3646164116923693e-05, + "loss": 3.377, + "step": 2220544 + }, + { + "epoch": 0.0, + "learning_rate": 1.3637778169413174e-05, + "loss": 3.3626, + "step": 2221056 + }, + { + "epoch": 0.0, + "learning_rate": 1.3629392221902654e-05, + "loss": 3.38, + "step": 2221568 + }, + { + "epoch": 0.0, + "learning_rate": 1.3621006274392134e-05, + "loss": 3.3701, + "step": 2222080 + }, + { + "epoch": 0.0, + "learning_rate": 1.3612620326881614e-05, + "loss": 3.379, + "step": 2222592 + }, + { + "epoch": 0.0, + "learning_rate": 1.3604234379371094e-05, + "loss": 3.3718, + "step": 2223104 + }, + { + "epoch": 0.0, + "learning_rate": 1.3595848431860576e-05, + "loss": 3.394, + "step": 2223616 + }, + { + "epoch": 0.0, + "learning_rate": 1.3587478863153785e-05, + "loss": 3.3774, + "step": 2224128 + }, + { + "epoch": 0.0, + "learning_rate": 1.3579092915643265e-05, + "loss": 3.3799, + "step": 2224640 + }, + { + "epoch": 0.0, + "learning_rate": 1.3570706968132746e-05, + "loss": 3.3777, + "step": 2225152 + }, + { + "epoch": 0.0, + "learning_rate": 1.3562321020622226e-05, + "loss": 3.385, + "step": 2225664 + }, + { + "epoch": 0.0, + "learning_rate": 1.3553951451915437e-05, + "loss": 3.3805, + "step": 2226176 + }, + { + "epoch": 0.0, + "learning_rate": 1.3545565504404917e-05, + "loss": 3.3707, + "step": 2226688 + }, + { + "epoch": 0.0, + "learning_rate": 1.3537179556894397e-05, + "loss": 3.3816, + "step": 2227200 + }, + { + "epoch": 0.0, + "learning_rate": 1.3528793609383875e-05, + "loss": 3.3647, + "step": 2227712 + }, + { + "epoch": 0.0, + "learning_rate": 1.3520424040677088e-05, + "loss": 3.3697, + "step": 2228224 + }, + { + "epoch": 0.01, + "learning_rate": 1.3512038093166568e-05, + "loss": 3.3766, + "step": 2228736 + }, + { + "epoch": 0.01, + "learning_rate": 1.3503652145656048e-05, + "loss": 3.3735, + "step": 2229248 + }, + { + "epoch": 0.01, + "learning_rate": 1.3495266198145526e-05, + "loss": 3.3778, + "step": 2229760 + }, + { + "epoch": 0.01, + "learning_rate": 1.3486896629438738e-05, + "loss": 3.3884, + "step": 2230272 + }, + { + "epoch": 0.01, + "learning_rate": 1.347852706073195e-05, + "loss": 3.3722, + "step": 2230784 + }, + { + "epoch": 0.01, + "learning_rate": 1.347014111322143e-05, + "loss": 3.38, + "step": 2231296 + }, + { + "epoch": 0.01, + "learning_rate": 1.3461755165710909e-05, + "loss": 3.3811, + "step": 2231808 + }, + { + "epoch": 0.01, + "learning_rate": 1.345336921820039e-05, + "loss": 3.3709, + "step": 2232320 + }, + { + "epoch": 0.01, + "learning_rate": 1.34449996494936e-05, + "loss": 3.3793, + "step": 2232832 + }, + { + "epoch": 0.01, + "learning_rate": 1.343661370198308e-05, + "loss": 3.3714, + "step": 2233344 + }, + { + "epoch": 0.01, + "learning_rate": 1.3428227754472561e-05, + "loss": 3.3683, + "step": 2233856 + }, + { + "epoch": 0.01, + "learning_rate": 1.3419841806962041e-05, + "loss": 3.3786, + "step": 2234368 + }, + { + "epoch": 0.01, + "learning_rate": 1.3411455859451521e-05, + "loss": 3.3893, + "step": 2234880 + }, + { + "epoch": 0.01, + "learning_rate": 1.3403069911941e-05, + "loss": 3.3722, + "step": 2235392 + }, + { + "epoch": 0.01, + "learning_rate": 1.3394700343234212e-05, + "loss": 3.3822, + "step": 2235904 + }, + { + "epoch": 0.01, + "learning_rate": 1.3386314395723692e-05, + "loss": 3.3822, + "step": 2236416 + }, + { + "epoch": 0.01, + "learning_rate": 1.337792844821317e-05, + "loss": 3.3736, + "step": 2236928 + }, + { + "epoch": 0.01, + "learning_rate": 1.336954250070265e-05, + "loss": 3.38, + "step": 2237440 + }, + { + "epoch": 0.01, + "learning_rate": 1.336115655319213e-05, + "loss": 3.3461, + "step": 2237952 + }, + { + "epoch": 0.01, + "learning_rate": 1.335277060568161e-05, + "loss": 3.3802, + "step": 2238464 + }, + { + "epoch": 0.01, + "learning_rate": 1.3344384658171092e-05, + "loss": 3.3734, + "step": 2238976 + }, + { + "epoch": 0.01, + "learning_rate": 1.3335998710660572e-05, + "loss": 3.3832, + "step": 2239488 + }, + { + "epoch": 0.01, + "learning_rate": 1.3327629141953783e-05, + "loss": 3.3675, + "step": 2240000 + }, + { + "epoch": 0.01, + "learning_rate": 1.3319243194443263e-05, + "loss": 3.3574, + "step": 2240512 + }, + { + "epoch": 0.01, + "learning_rate": 1.3310873625736472e-05, + "loss": 3.36, + "step": 2241024 + }, + { + "epoch": 0.01, + "learning_rate": 1.3302487678225953e-05, + "loss": 3.3601, + "step": 2241536 + }, + { + "epoch": 0.01, + "learning_rate": 1.3294101730715433e-05, + "loss": 3.384, + "step": 2242048 + }, + { + "epoch": 0.01, + "learning_rate": 1.3285715783204913e-05, + "loss": 3.3587, + "step": 2242560 + }, + { + "epoch": 0.01, + "learning_rate": 1.3277329835694393e-05, + "loss": 3.3815, + "step": 2243072 + }, + { + "epoch": 0.01, + "learning_rate": 1.3268943888183875e-05, + "loss": 3.3726, + "step": 2243584 + }, + { + "epoch": 0.01, + "learning_rate": 1.3260574319477084e-05, + "loss": 3.3653, + "step": 2244096 + }, + { + "epoch": 0.01, + "learning_rate": 1.3252188371966564e-05, + "loss": 3.3745, + "step": 2244608 + }, + { + "epoch": 0.01, + "learning_rate": 1.3243802424456046e-05, + "loss": 3.3597, + "step": 2245120 + }, + { + "epoch": 0.01, + "learning_rate": 1.3235416476945526e-05, + "loss": 3.3626, + "step": 2245632 + }, + { + "epoch": 0.01, + "learning_rate": 1.3227030529435002e-05, + "loss": 3.3644, + "step": 2246144 + }, + { + "epoch": 0.01, + "learning_rate": 1.3218644581924484e-05, + "loss": 3.3782, + "step": 2246656 + }, + { + "epoch": 0.01, + "learning_rate": 1.3210275013217696e-05, + "loss": 3.3625, + "step": 2247168 + }, + { + "epoch": 0.01, + "learning_rate": 1.3201889065707176e-05, + "loss": 3.3675, + "step": 2247680 + }, + { + "epoch": 0.01, + "learning_rate": 1.3193503118196654e-05, + "loss": 3.3581, + "step": 2248192 + }, + { + "epoch": 0.01, + "learning_rate": 1.3185117170686134e-05, + "loss": 3.3701, + "step": 2248704 + }, + { + "epoch": 0.01, + "learning_rate": 1.3176731223175614e-05, + "loss": 3.38, + "step": 2249216 + }, + { + "epoch": 0.01, + "learning_rate": 1.3168345275665094e-05, + "loss": 3.3766, + "step": 2249728 + }, + { + "epoch": 0.01, + "learning_rate": 1.3159959328154576e-05, + "loss": 3.3784, + "step": 2250240 + }, + { + "epoch": 0.01, + "learning_rate": 1.3151589759447785e-05, + "loss": 3.3782, + "step": 2250752 + }, + { + "epoch": 0.01, + "learning_rate": 1.3143203811937265e-05, + "loss": 3.3913, + "step": 2251264 + }, + { + "epoch": 0.01, + "learning_rate": 1.3134817864426747e-05, + "loss": 3.3774, + "step": 2251776 + }, + { + "epoch": 0.01, + "learning_rate": 1.3126431916916227e-05, + "loss": 3.3849, + "step": 2252288 + }, + { + "epoch": 0.01, + "learning_rate": 1.3118045969405707e-05, + "loss": 3.37, + "step": 2252800 + }, + { + "epoch": 0.01, + "learning_rate": 1.3109660021895185e-05, + "loss": 3.3735, + "step": 2253312 + }, + { + "epoch": 0.01, + "learning_rate": 1.3101274074384665e-05, + "loss": 3.3739, + "step": 2253824 + }, + { + "epoch": 0.01, + "learning_rate": 1.3092888126874145e-05, + "loss": 3.371, + "step": 2254336 + }, + { + "epoch": 0.01, + "learning_rate": 1.3084518558167357e-05, + "loss": 3.3827, + "step": 2254848 + }, + { + "epoch": 0.01, + "learning_rate": 1.3076132610656835e-05, + "loss": 3.3815, + "step": 2255360 + }, + { + "epoch": 0.01, + "learning_rate": 1.3067746663146315e-05, + "loss": 3.3759, + "step": 2255872 + }, + { + "epoch": 0.01, + "learning_rate": 1.3059360715635795e-05, + "loss": 3.3572, + "step": 2256384 + }, + { + "epoch": 0.01, + "learning_rate": 1.3051007525732739e-05, + "loss": 3.3632, + "step": 2256896 + }, + { + "epoch": 0.01, + "learning_rate": 1.3042621578222219e-05, + "loss": 3.3813, + "step": 2257408 + }, + { + "epoch": 0.01, + "learning_rate": 1.30342356307117e-05, + "loss": 3.3747, + "step": 2257920 + }, + { + "epoch": 0.01, + "learning_rate": 1.302584968320118e-05, + "loss": 3.3693, + "step": 2258432 + }, + { + "epoch": 0.01, + "learning_rate": 1.3017463735690657e-05, + "loss": 3.3749, + "step": 2258944 + }, + { + "epoch": 0.02, + "learning_rate": 1.3009077788180138e-05, + "loss": 3.3764, + "step": 2259456 + }, + { + "epoch": 0.02, + "learning_rate": 1.3000708219473351e-05, + "loss": 3.3677, + "step": 2259968 + }, + { + "epoch": 0.02, + "learning_rate": 1.2992322271962831e-05, + "loss": 3.3682, + "step": 2260480 + }, + { + "epoch": 0.02, + "learning_rate": 1.298393632445231e-05, + "loss": 3.3784, + "step": 2260992 + }, + { + "epoch": 0.02, + "learning_rate": 1.2975550376941789e-05, + "loss": 3.3782, + "step": 2261504 + }, + { + "epoch": 0.02, + "learning_rate": 1.2967164429431269e-05, + "loss": 3.3778, + "step": 2262016 + }, + { + "epoch": 0.02, + "learning_rate": 1.2958778481920749e-05, + "loss": 3.3593, + "step": 2262528 + }, + { + "epoch": 0.02, + "learning_rate": 1.295039253441023e-05, + "loss": 3.369, + "step": 2263040 + }, + { + "epoch": 0.02, + "learning_rate": 1.294200658689971e-05, + "loss": 3.3745, + "step": 2263552 + }, + { + "epoch": 0.02, + "learning_rate": 1.2933637018192921e-05, + "loss": 3.3778, + "step": 2264064 + }, + { + "epoch": 0.02, + "learning_rate": 1.2925251070682401e-05, + "loss": 3.3751, + "step": 2264576 + }, + { + "epoch": 0.02, + "learning_rate": 1.2916865123171881e-05, + "loss": 3.3752, + "step": 2265088 + }, + { + "epoch": 0.02, + "learning_rate": 1.2908495554465092e-05, + "loss": 3.3714, + "step": 2265600 + }, + { + "epoch": 0.02, + "learning_rate": 1.2900109606954572e-05, + "loss": 3.373, + "step": 2266112 + }, + { + "epoch": 0.02, + "learning_rate": 1.2891723659444052e-05, + "loss": 3.375, + "step": 2266624 + }, + { + "epoch": 0.02, + "learning_rate": 1.2883337711933532e-05, + "loss": 3.3664, + "step": 2267136 + }, + { + "epoch": 0.02, + "learning_rate": 1.2874968143226743e-05, + "loss": 3.3642, + "step": 2267648 + }, + { + "epoch": 0.02, + "learning_rate": 1.2866582195716223e-05, + "loss": 3.3717, + "step": 2268160 + }, + { + "epoch": 0.02, + "learning_rate": 1.2858196248205703e-05, + "loss": 3.3736, + "step": 2268672 + }, + { + "epoch": 0.02, + "learning_rate": 1.2849810300695184e-05, + "loss": 3.3573, + "step": 2269184 + }, + { + "epoch": 0.02, + "learning_rate": 1.2841424353184661e-05, + "loss": 3.3675, + "step": 2269696 + }, + { + "epoch": 0.02, + "learning_rate": 1.2833038405674141e-05, + "loss": 3.3584, + "step": 2270208 + }, + { + "epoch": 0.02, + "learning_rate": 1.2824668836967355e-05, + "loss": 3.3722, + "step": 2270720 + }, + { + "epoch": 0.02, + "learning_rate": 1.2816282889456835e-05, + "loss": 3.3691, + "step": 2271232 + }, + { + "epoch": 0.02, + "learning_rate": 1.2807896941946312e-05, + "loss": 3.3681, + "step": 2271744 + }, + { + "epoch": 0.02, + "learning_rate": 1.2799510994435793e-05, + "loss": 3.3749, + "step": 2272256 + }, + { + "epoch": 0.02, + "learning_rate": 1.2791125046925273e-05, + "loss": 3.3796, + "step": 2272768 + }, + { + "epoch": 0.02, + "learning_rate": 1.2782739099414753e-05, + "loss": 3.373, + "step": 2273280 + }, + { + "epoch": 0.02, + "learning_rate": 1.2774353151904233e-05, + "loss": 3.374, + "step": 2273792 + }, + { + "epoch": 0.02, + "learning_rate": 1.2765983583197444e-05, + "loss": 3.3818, + "step": 2274304 + }, + { + "epoch": 0.02, + "learning_rate": 1.2757597635686924e-05, + "loss": 3.371, + "step": 2274816 + }, + { + "epoch": 0.02, + "learning_rate": 1.2749211688176404e-05, + "loss": 3.3694, + "step": 2275328 + }, + { + "epoch": 0.02, + "learning_rate": 1.2740825740665885e-05, + "loss": 3.3772, + "step": 2275840 + }, + { + "epoch": 0.02, + "learning_rate": 1.2732456171959095e-05, + "loss": 3.374, + "step": 2276352 + }, + { + "epoch": 0.02, + "learning_rate": 1.2724070224448576e-05, + "loss": 3.3672, + "step": 2276864 + }, + { + "epoch": 0.02, + "learning_rate": 1.2715684276938056e-05, + "loss": 3.3625, + "step": 2277376 + }, + { + "epoch": 0.02, + "learning_rate": 1.2707298329427536e-05, + "loss": 3.3713, + "step": 2277888 + }, + { + "epoch": 0.02, + "learning_rate": 1.2698912381917016e-05, + "loss": 3.3621, + "step": 2278400 + }, + { + "epoch": 0.02, + "learning_rate": 1.2690542813210227e-05, + "loss": 3.3675, + "step": 2278912 + }, + { + "epoch": 0.02, + "learning_rate": 1.2682156865699707e-05, + "loss": 3.3662, + "step": 2279424 + }, + { + "epoch": 0.02, + "learning_rate": 1.2673770918189187e-05, + "loss": 3.3754, + "step": 2279936 + }, + { + "epoch": 0.02, + "learning_rate": 1.2665384970678665e-05, + "loss": 3.3807, + "step": 2280448 + }, + { + "epoch": 0.02, + "learning_rate": 1.2656999023168145e-05, + "loss": 3.3653, + "step": 2280960 + }, + { + "epoch": 0.02, + "learning_rate": 1.2648613075657625e-05, + "loss": 3.3805, + "step": 2281472 + }, + { + "epoch": 0.02, + "learning_rate": 1.2640227128147105e-05, + "loss": 3.3743, + "step": 2281984 + }, + { + "epoch": 0.02, + "learning_rate": 1.2631841180636587e-05, + "loss": 3.3768, + "step": 2282496 + }, + { + "epoch": 0.02, + "learning_rate": 1.2623471611929796e-05, + "loss": 3.3697, + "step": 2283008 + }, + { + "epoch": 0.02, + "learning_rate": 1.2615085664419277e-05, + "loss": 3.3656, + "step": 2283520 + }, + { + "epoch": 0.02, + "learning_rate": 1.2606699716908757e-05, + "loss": 3.3844, + "step": 2284032 + }, + { + "epoch": 0.02, + "learning_rate": 1.2598313769398237e-05, + "loss": 3.3693, + "step": 2284544 + }, + { + "epoch": 0.02, + "learning_rate": 1.2589944200691448e-05, + "loss": 3.3743, + "step": 2285056 + }, + { + "epoch": 0.02, + "learning_rate": 1.2581558253180928e-05, + "loss": 3.3686, + "step": 2285568 + }, + { + "epoch": 0.02, + "learning_rate": 1.2573172305670408e-05, + "loss": 3.3716, + "step": 2286080 + }, + { + "epoch": 0.02, + "learning_rate": 1.2564786358159888e-05, + "loss": 3.3681, + "step": 2286592 + }, + { + "epoch": 0.02, + "learning_rate": 1.255640041064937e-05, + "loss": 3.3682, + "step": 2287104 + }, + { + "epoch": 0.02, + "learning_rate": 1.2548014463138846e-05, + "loss": 3.3777, + "step": 2287616 + }, + { + "epoch": 0.02, + "learning_rate": 1.2539628515628326e-05, + "loss": 3.3715, + "step": 2288128 + }, + { + "epoch": 0.02, + "learning_rate": 1.2531242568117808e-05, + "loss": 3.3754, + "step": 2288640 + }, + { + "epoch": 0.02, + "learning_rate": 1.252287299941102e-05, + "loss": 3.3687, + "step": 2289152 + }, + { + "epoch": 0.03, + "eval_loss": 3.864597797393799, + "eval_runtime": 306.8174, + "eval_samples_per_second": 1243.707, + "eval_steps_per_second": 38.867, + "step": 2289600 + }, + { + "epoch": 1.0, + "learning_rate": 1.2514487051900497e-05, + "loss": 3.3676, + "step": 2289664 + }, + { + "epoch": 1.0, + "learning_rate": 1.2506101104389978e-05, + "loss": 3.3598, + "step": 2290176 + }, + { + "epoch": 1.0, + "learning_rate": 1.2497715156879458e-05, + "loss": 3.3633, + "step": 2290688 + }, + { + "epoch": 1.0, + "learning_rate": 1.2489329209368938e-05, + "loss": 3.3777, + "step": 2291200 + }, + { + "epoch": 1.0, + "learning_rate": 1.2480943261858418e-05, + "loss": 3.3742, + "step": 2291712 + }, + { + "epoch": 1.0, + "learning_rate": 1.2472573693151629e-05, + "loss": 3.3809, + "step": 2292224 + }, + { + "epoch": 1.0, + "learning_rate": 1.2464187745641109e-05, + "loss": 3.363, + "step": 2292736 + }, + { + "epoch": 1.0, + "learning_rate": 1.2455801798130589e-05, + "loss": 3.3686, + "step": 2293248 + }, + { + "epoch": 1.0, + "learning_rate": 1.244741585062007e-05, + "loss": 3.3604, + "step": 2293760 + }, + { + "epoch": 1.0, + "learning_rate": 1.243904628191328e-05, + "loss": 3.3699, + "step": 2294272 + }, + { + "epoch": 1.0, + "learning_rate": 1.2430660334402761e-05, + "loss": 3.37, + "step": 2294784 + }, + { + "epoch": 1.0, + "learning_rate": 1.2422274386892241e-05, + "loss": 3.3702, + "step": 2295296 + }, + { + "epoch": 1.0, + "learning_rate": 1.241388843938172e-05, + "loss": 3.375, + "step": 2295808 + }, + { + "epoch": 1.0, + "learning_rate": 1.24055024918712e-05, + "loss": 3.3569, + "step": 2296320 + }, + { + "epoch": 1.0, + "learning_rate": 1.2397132923164412e-05, + "loss": 3.3625, + "step": 2296832 + }, + { + "epoch": 1.0, + "learning_rate": 1.2388746975653892e-05, + "loss": 3.3571, + "step": 2297344 + }, + { + "epoch": 1.0, + "learning_rate": 1.238036102814337e-05, + "loss": 3.369, + "step": 2297856 + }, + { + "epoch": 1.0, + "learning_rate": 1.2371975080632852e-05, + "loss": 3.3598, + "step": 2298368 + }, + { + "epoch": 1.0, + "learning_rate": 1.2363605511926063e-05, + "loss": 3.3726, + "step": 2298880 + }, + { + "epoch": 1.0, + "learning_rate": 1.2355219564415543e-05, + "loss": 3.3643, + "step": 2299392 + }, + { + "epoch": 1.0, + "learning_rate": 1.2346833616905023e-05, + "loss": 3.3824, + "step": 2299904 + }, + { + "epoch": 1.0, + "learning_rate": 1.2338447669394503e-05, + "loss": 3.3688, + "step": 2300416 + }, + { + "epoch": 1.0, + "learning_rate": 1.2330061721883982e-05, + "loss": 3.3645, + "step": 2300928 + }, + { + "epoch": 1.0, + "learning_rate": 1.2321675774373462e-05, + "loss": 3.368, + "step": 2301440 + }, + { + "epoch": 1.0, + "learning_rate": 1.2313289826862942e-05, + "loss": 3.3771, + "step": 2301952 + }, + { + "epoch": 1.0, + "learning_rate": 1.2304903879352422e-05, + "loss": 3.3701, + "step": 2302464 + }, + { + "epoch": 1.0, + "learning_rate": 1.2296534310645635e-05, + "loss": 3.3631, + "step": 2302976 + }, + { + "epoch": 1.0, + "learning_rate": 1.2288164741938844e-05, + "loss": 3.3697, + "step": 2303488 + }, + { + "epoch": 1.0, + "learning_rate": 1.2279778794428324e-05, + "loss": 3.3539, + "step": 2304000 + }, + { + "epoch": 1.0, + "learning_rate": 1.2271392846917806e-05, + "loss": 3.3589, + "step": 2304512 + }, + { + "epoch": 1.01, + "learning_rate": 1.2263006899407284e-05, + "loss": 3.3677, + "step": 2305024 + }, + { + "epoch": 1.01, + "learning_rate": 1.2254620951896764e-05, + "loss": 3.3645, + "step": 2305536 + }, + { + "epoch": 1.01, + "learning_rate": 1.2246251383189976e-05, + "loss": 3.3673, + "step": 2306048 + }, + { + "epoch": 1.01, + "learning_rate": 1.2237865435679456e-05, + "loss": 3.3773, + "step": 2306560 + }, + { + "epoch": 1.01, + "learning_rate": 1.2229479488168934e-05, + "loss": 3.3656, + "step": 2307072 + }, + { + "epoch": 1.01, + "learning_rate": 1.2221093540658416e-05, + "loss": 3.3677, + "step": 2307584 + }, + { + "epoch": 1.01, + "learning_rate": 1.2212707593147896e-05, + "loss": 3.3708, + "step": 2308096 + }, + { + "epoch": 1.01, + "learning_rate": 1.2204321645637374e-05, + "loss": 3.3615, + "step": 2308608 + }, + { + "epoch": 1.01, + "learning_rate": 1.2195952076930587e-05, + "loss": 3.3735, + "step": 2309120 + }, + { + "epoch": 1.01, + "learning_rate": 1.2187566129420067e-05, + "loss": 3.3628, + "step": 2309632 + }, + { + "epoch": 1.01, + "learning_rate": 1.2179180181909547e-05, + "loss": 3.3596, + "step": 2310144 + }, + { + "epoch": 1.01, + "learning_rate": 1.2170794234399025e-05, + "loss": 3.3669, + "step": 2310656 + }, + { + "epoch": 1.01, + "learning_rate": 1.2162408286888507e-05, + "loss": 3.3783, + "step": 2311168 + }, + { + "epoch": 1.01, + "learning_rate": 1.2154022339377987e-05, + "loss": 3.3608, + "step": 2311680 + }, + { + "epoch": 1.01, + "learning_rate": 1.2145636391867465e-05, + "loss": 3.3764, + "step": 2312192 + }, + { + "epoch": 1.01, + "learning_rate": 1.2137250444356947e-05, + "loss": 3.3688, + "step": 2312704 + }, + { + "epoch": 1.01, + "learning_rate": 1.2128880875650157e-05, + "loss": 3.3658, + "step": 2313216 + }, + { + "epoch": 1.01, + "learning_rate": 1.2120494928139637e-05, + "loss": 3.367, + "step": 2313728 + }, + { + "epoch": 1.01, + "learning_rate": 1.2112108980629117e-05, + "loss": 3.3377, + "step": 2314240 + }, + { + "epoch": 1.01, + "learning_rate": 1.2103723033118597e-05, + "loss": 3.3657, + "step": 2314752 + }, + { + "epoch": 1.01, + "learning_rate": 1.2095353464411808e-05, + "loss": 3.3718, + "step": 2315264 + }, + { + "epoch": 1.01, + "learning_rate": 1.2086967516901288e-05, + "loss": 3.3707, + "step": 2315776 + }, + { + "epoch": 1.01, + "learning_rate": 1.2078581569390768e-05, + "loss": 3.3559, + "step": 2316288 + }, + { + "epoch": 1.01, + "learning_rate": 1.2070212000683979e-05, + "loss": 3.3501, + "step": 2316800 + }, + { + "epoch": 1.01, + "learning_rate": 1.206182605317346e-05, + "loss": 3.3491, + "step": 2317312 + }, + { + "epoch": 1.01, + "learning_rate": 1.2053440105662939e-05, + "loss": 3.3486, + "step": 2317824 + }, + { + "epoch": 1.01, + "learning_rate": 1.2045054158152419e-05, + "loss": 3.3772, + "step": 2318336 + }, + { + "epoch": 1.01, + "learning_rate": 1.2036668210641898e-05, + "loss": 3.3495, + "step": 2318848 + }, + { + "epoch": 1.01, + "learning_rate": 1.2028282263131378e-05, + "loss": 3.3724, + "step": 2319360 + }, + { + "epoch": 1.01, + "learning_rate": 1.2019896315620858e-05, + "loss": 3.3633, + "step": 2319872 + }, + { + "epoch": 1.01, + "learning_rate": 1.2011526746914071e-05, + "loss": 3.3538, + "step": 2320384 + }, + { + "epoch": 1.01, + "learning_rate": 1.200314079940355e-05, + "loss": 3.3666, + "step": 2320896 + }, + { + "epoch": 1.01, + "learning_rate": 1.1994754851893029e-05, + "loss": 3.3558, + "step": 2321408 + }, + { + "epoch": 1.01, + "learning_rate": 1.1986368904382509e-05, + "loss": 3.3571, + "step": 2321920 + }, + { + "epoch": 1.01, + "learning_rate": 1.197798295687199e-05, + "loss": 3.3497, + "step": 2322432 + }, + { + "epoch": 1.01, + "learning_rate": 1.1969597009361469e-05, + "loss": 3.3684, + "step": 2322944 + }, + { + "epoch": 1.01, + "learning_rate": 1.1961227440654681e-05, + "loss": 3.3565, + "step": 2323456 + }, + { + "epoch": 1.01, + "learning_rate": 1.1952841493144161e-05, + "loss": 3.3554, + "step": 2323968 + }, + { + "epoch": 1.01, + "learning_rate": 1.1944455545633641e-05, + "loss": 3.3526, + "step": 2324480 + }, + { + "epoch": 1.01, + "learning_rate": 1.193606959812312e-05, + "loss": 3.3603, + "step": 2324992 + }, + { + "epoch": 1.01, + "learning_rate": 1.1927683650612601e-05, + "loss": 3.3693, + "step": 2325504 + }, + { + "epoch": 1.01, + "learning_rate": 1.1919314081905812e-05, + "loss": 3.3666, + "step": 2326016 + }, + { + "epoch": 1.01, + "learning_rate": 1.1910928134395292e-05, + "loss": 3.3655, + "step": 2326528 + }, + { + "epoch": 1.01, + "learning_rate": 1.1902542186884772e-05, + "loss": 3.3691, + "step": 2327040 + }, + { + "epoch": 1.01, + "learning_rate": 1.1894156239374252e-05, + "loss": 3.3792, + "step": 2327552 + }, + { + "epoch": 1.01, + "learning_rate": 1.1885770291863732e-05, + "loss": 3.3682, + "step": 2328064 + }, + { + "epoch": 1.01, + "learning_rate": 1.187738434435321e-05, + "loss": 3.3736, + "step": 2328576 + }, + { + "epoch": 1.01, + "learning_rate": 1.1869014775646423e-05, + "loss": 3.3631, + "step": 2329088 + }, + { + "epoch": 1.01, + "learning_rate": 1.1860628828135903e-05, + "loss": 3.3629, + "step": 2329600 + }, + { + "epoch": 1.01, + "learning_rate": 1.1852242880625383e-05, + "loss": 3.3644, + "step": 2330112 + }, + { + "epoch": 1.01, + "learning_rate": 1.1843856933114862e-05, + "loss": 3.3575, + "step": 2330624 + }, + { + "epoch": 1.01, + "learning_rate": 1.1835470985604342e-05, + "loss": 3.3744, + "step": 2331136 + }, + { + "epoch": 1.01, + "learning_rate": 1.1827085038093822e-05, + "loss": 3.3739, + "step": 2331648 + }, + { + "epoch": 1.01, + "learning_rate": 1.1818699090583302e-05, + "loss": 3.3656, + "step": 2332160 + }, + { + "epoch": 1.01, + "learning_rate": 1.1810329521876513e-05, + "loss": 3.3464, + "step": 2332672 + }, + { + "epoch": 1.01, + "learning_rate": 1.1801959953169726e-05, + "loss": 3.356, + "step": 2333184 + }, + { + "epoch": 1.01, + "learning_rate": 1.1793574005659206e-05, + "loss": 3.3697, + "step": 2333696 + }, + { + "epoch": 1.01, + "learning_rate": 1.1785188058148684e-05, + "loss": 3.3662, + "step": 2334208 + }, + { + "epoch": 1.01, + "learning_rate": 1.1776802110638164e-05, + "loss": 3.3568, + "step": 2334720 + }, + { + "epoch": 1.01, + "learning_rate": 1.1768416163127645e-05, + "loss": 3.367, + "step": 2335232 + }, + { + "epoch": 1.02, + "learning_rate": 1.1760046594420856e-05, + "loss": 3.3651, + "step": 2335744 + }, + { + "epoch": 1.02, + "learning_rate": 1.1751660646910336e-05, + "loss": 3.3569, + "step": 2336256 + }, + { + "epoch": 1.02, + "learning_rate": 1.1743274699399816e-05, + "loss": 3.3581, + "step": 2336768 + }, + { + "epoch": 1.02, + "learning_rate": 1.1734888751889296e-05, + "loss": 3.3685, + "step": 2337280 + }, + { + "epoch": 1.02, + "learning_rate": 1.1726519183182507e-05, + "loss": 3.3629, + "step": 2337792 + }, + { + "epoch": 1.02, + "learning_rate": 1.1718133235671987e-05, + "loss": 3.3718, + "step": 2338304 + }, + { + "epoch": 1.02, + "learning_rate": 1.1709747288161467e-05, + "loss": 3.3504, + "step": 2338816 + }, + { + "epoch": 1.02, + "learning_rate": 1.1701361340650947e-05, + "loss": 3.3579, + "step": 2339328 + }, + { + "epoch": 1.02, + "learning_rate": 1.1692975393140427e-05, + "loss": 3.3661, + "step": 2339840 + }, + { + "epoch": 1.02, + "learning_rate": 1.1684589445629907e-05, + "loss": 3.367, + "step": 2340352 + }, + { + "epoch": 1.02, + "learning_rate": 1.1676203498119387e-05, + "loss": 3.3656, + "step": 2340864 + }, + { + "epoch": 1.02, + "learning_rate": 1.1667833929412597e-05, + "loss": 3.3658, + "step": 2341376 + }, + { + "epoch": 1.02, + "learning_rate": 1.1659464360705808e-05, + "loss": 3.3632, + "step": 2341888 + }, + { + "epoch": 1.02, + "learning_rate": 1.165107841319529e-05, + "loss": 3.3638, + "step": 2342400 + }, + { + "epoch": 1.02, + "learning_rate": 1.164269246568477e-05, + "loss": 3.3688, + "step": 2342912 + }, + { + "epoch": 1.02, + "learning_rate": 1.1634306518174248e-05, + "loss": 3.3505, + "step": 2343424 + }, + { + "epoch": 1.02, + "learning_rate": 1.162593694946746e-05, + "loss": 3.3588, + "step": 2343936 + }, + { + "epoch": 1.02, + "learning_rate": 1.161755100195694e-05, + "loss": 3.3583, + "step": 2344448 + }, + { + "epoch": 1.02, + "learning_rate": 1.160916505444642e-05, + "loss": 3.363, + "step": 2344960 + }, + { + "epoch": 1.02, + "learning_rate": 1.1600779106935899e-05, + "loss": 3.3515, + "step": 2345472 + }, + { + "epoch": 1.02, + "learning_rate": 1.159239315942538e-05, + "loss": 3.3555, + "step": 2345984 + }, + { + "epoch": 1.02, + "learning_rate": 1.158400721191486e-05, + "loss": 3.3461, + "step": 2346496 + }, + { + "epoch": 1.02, + "learning_rate": 1.1575637643208071e-05, + "loss": 3.3658, + "step": 2347008 + }, + { + "epoch": 1.02, + "learning_rate": 1.1567251695697551e-05, + "loss": 3.3579, + "step": 2347520 + }, + { + "epoch": 1.02, + "learning_rate": 1.1558865748187031e-05, + "loss": 3.358, + "step": 2348032 + }, + { + "epoch": 1.02, + "learning_rate": 1.155047980067651e-05, + "loss": 3.3653, + "step": 2348544 + }, + { + "epoch": 1.02, + "learning_rate": 1.1542093853165991e-05, + "loss": 3.3687, + "step": 2349056 + }, + { + "epoch": 1.02, + "learning_rate": 1.1533707905655471e-05, + "loss": 3.3632, + "step": 2349568 + }, + { + "epoch": 1.02, + "learning_rate": 1.1525321958144951e-05, + "loss": 3.3603, + "step": 2350080 + }, + { + "epoch": 1.02, + "learning_rate": 1.1516952389438162e-05, + "loss": 3.3733, + "step": 2350592 + }, + { + "epoch": 1.02, + "learning_rate": 1.1508566441927642e-05, + "loss": 3.3607, + "step": 2351104 + }, + { + "epoch": 1.02, + "learning_rate": 1.1500180494417122e-05, + "loss": 3.3578, + "step": 2351616 + }, + { + "epoch": 1.02, + "learning_rate": 1.1491794546906602e-05, + "loss": 3.3667, + "step": 2352128 + }, + { + "epoch": 1.02, + "learning_rate": 1.1483424978199812e-05, + "loss": 3.3633, + "step": 2352640 + }, + { + "epoch": 1.02, + "learning_rate": 1.1475039030689292e-05, + "loss": 3.3623, + "step": 2353152 + }, + { + "epoch": 1.02, + "learning_rate": 1.1466653083178772e-05, + "loss": 3.3505, + "step": 2353664 + }, + { + "epoch": 1.02, + "learning_rate": 1.1458267135668252e-05, + "loss": 3.3643, + "step": 2354176 + }, + { + "epoch": 1.02, + "learning_rate": 1.1449881188157732e-05, + "loss": 3.3508, + "step": 2354688 + }, + { + "epoch": 1.02, + "learning_rate": 1.1441511619450945e-05, + "loss": 3.3589, + "step": 2355200 + }, + { + "epoch": 1.02, + "learning_rate": 1.1433125671940425e-05, + "loss": 3.3506, + "step": 2355712 + }, + { + "epoch": 1.02, + "learning_rate": 1.1424739724429903e-05, + "loss": 3.3717, + "step": 2356224 + }, + { + "epoch": 1.02, + "learning_rate": 1.1416353776919383e-05, + "loss": 3.3705, + "step": 2356736 + }, + { + "epoch": 1.02, + "learning_rate": 1.1407967829408864e-05, + "loss": 3.3489, + "step": 2357248 + }, + { + "epoch": 1.02, + "learning_rate": 1.1399581881898343e-05, + "loss": 3.3715, + "step": 2357760 + }, + { + "epoch": 1.02, + "learning_rate": 1.1391195934387823e-05, + "loss": 3.3637, + "step": 2358272 + }, + { + "epoch": 1.02, + "learning_rate": 1.1382809986877303e-05, + "loss": 3.3678, + "step": 2358784 + }, + { + "epoch": 1.02, + "learning_rate": 1.1374440418170515e-05, + "loss": 3.3617, + "step": 2359296 + }, + { + "epoch": 1.02, + "learning_rate": 1.1366054470659993e-05, + "loss": 3.3605, + "step": 2359808 + }, + { + "epoch": 1.02, + "learning_rate": 1.1357668523149475e-05, + "loss": 3.374, + "step": 2360320 + }, + { + "epoch": 1.02, + "learning_rate": 1.1349282575638955e-05, + "loss": 3.3589, + "step": 2360832 + }, + { + "epoch": 1.02, + "learning_rate": 1.1340913006932164e-05, + "loss": 3.3667, + "step": 2361344 + }, + { + "epoch": 1.02, + "learning_rate": 1.1332527059421646e-05, + "loss": 3.3583, + "step": 2361856 + }, + { + "epoch": 1.02, + "learning_rate": 1.1324141111911126e-05, + "loss": 3.3614, + "step": 2362368 + }, + { + "epoch": 1.02, + "learning_rate": 1.1315755164400606e-05, + "loss": 3.3566, + "step": 2362880 + }, + { + "epoch": 1.02, + "learning_rate": 1.1307369216890084e-05, + "loss": 3.357, + "step": 2363392 + }, + { + "epoch": 1.02, + "learning_rate": 1.1298983269379566e-05, + "loss": 3.3683, + "step": 2363904 + }, + { + "epoch": 1.02, + "learning_rate": 1.1290597321869046e-05, + "loss": 3.3592, + "step": 2364416 + }, + { + "epoch": 1.02, + "learning_rate": 1.1282227753162256e-05, + "loss": 3.3685, + "step": 2364928 + }, + { + "epoch": 1.02, + "learning_rate": 1.1273858184455467e-05, + "loss": 3.359, + "step": 2365440 + }, + { + "epoch": 1.03, + "eval_loss": 3.86554217338562, + "eval_runtime": 306.4067, + "eval_samples_per_second": 1245.374, + "eval_steps_per_second": 38.919, + "step": 2365920 + }, + { + "epoch": 0.0, + "learning_rate": 1.1265472236944947e-05, + "loss": 3.3107, + "step": 2365952 + }, + { + "epoch": 0.0, + "learning_rate": 1.1257086289434427e-05, + "loss": 3.3552, + "step": 2366464 + }, + { + "epoch": 0.0, + "learning_rate": 1.1248700341923907e-05, + "loss": 3.3549, + "step": 2366976 + }, + { + "epoch": 0.0, + "learning_rate": 1.1240314394413387e-05, + "loss": 3.3661, + "step": 2367488 + }, + { + "epoch": 0.0, + "learning_rate": 1.12319448257066e-05, + "loss": 3.362, + "step": 2368000 + }, + { + "epoch": 0.0, + "learning_rate": 1.122357525699981e-05, + "loss": 3.3704, + "step": 2368512 + }, + { + "epoch": 0.0, + "learning_rate": 1.121518930948929e-05, + "loss": 3.3528, + "step": 2369024 + }, + { + "epoch": 0.0, + "learning_rate": 1.120680336197877e-05, + "loss": 3.3595, + "step": 2369536 + }, + { + "epoch": 0.0, + "learning_rate": 1.119841741446825e-05, + "loss": 3.3494, + "step": 2370048 + }, + { + "epoch": 0.0, + "learning_rate": 1.119004784576146e-05, + "loss": 3.3627, + "step": 2370560 + }, + { + "epoch": 0.0, + "learning_rate": 1.118166189825094e-05, + "loss": 3.3566, + "step": 2371072 + }, + { + "epoch": 0.0, + "learning_rate": 1.117327595074042e-05, + "loss": 3.3656, + "step": 2371584 + }, + { + "epoch": 0.0, + "learning_rate": 1.11648900032299e-05, + "loss": 3.362, + "step": 2372096 + }, + { + "epoch": 0.0, + "learning_rate": 1.115650405571938e-05, + "loss": 3.3495, + "step": 2372608 + }, + { + "epoch": 0.0, + "learning_rate": 1.1148134487012591e-05, + "loss": 3.351, + "step": 2373120 + }, + { + "epoch": 0.0, + "learning_rate": 1.1139748539502071e-05, + "loss": 3.3496, + "step": 2373632 + }, + { + "epoch": 0.0, + "learning_rate": 1.1131362591991553e-05, + "loss": 3.356, + "step": 2374144 + }, + { + "epoch": 0.0, + "learning_rate": 1.1122976644481031e-05, + "loss": 3.3519, + "step": 2374656 + }, + { + "epoch": 0.0, + "learning_rate": 1.1114607075774242e-05, + "loss": 3.3606, + "step": 2375168 + }, + { + "epoch": 0.0, + "learning_rate": 1.1106221128263724e-05, + "loss": 3.3521, + "step": 2375680 + }, + { + "epoch": 0.0, + "learning_rate": 1.1097835180753202e-05, + "loss": 3.3724, + "step": 2376192 + }, + { + "epoch": 0.0, + "learning_rate": 1.1089449233242682e-05, + "loss": 3.3562, + "step": 2376704 + }, + { + "epoch": 0.0, + "learning_rate": 1.1081063285732164e-05, + "loss": 3.3581, + "step": 2377216 + }, + { + "epoch": 0.0, + "learning_rate": 1.1072677338221644e-05, + "loss": 3.3574, + "step": 2377728 + }, + { + "epoch": 0.0, + "learning_rate": 1.1064291390711122e-05, + "loss": 3.3678, + "step": 2378240 + }, + { + "epoch": 0.0, + "learning_rate": 1.1055905443200602e-05, + "loss": 3.3599, + "step": 2378752 + }, + { + "epoch": 0.0, + "learning_rate": 1.1047535874493814e-05, + "loss": 3.3535, + "step": 2379264 + }, + { + "epoch": 0.0, + "learning_rate": 1.1039166305787025e-05, + "loss": 3.3601, + "step": 2379776 + }, + { + "epoch": 0.0, + "learning_rate": 1.1030780358276505e-05, + "loss": 3.3448, + "step": 2380288 + }, + { + "epoch": 0.0, + "learning_rate": 1.1022394410765985e-05, + "loss": 3.3522, + "step": 2380800 + }, + { + "epoch": 0.01, + "learning_rate": 1.1014008463255465e-05, + "loss": 3.3529, + "step": 2381312 + }, + { + "epoch": 0.01, + "learning_rate": 1.1005622515744945e-05, + "loss": 3.3592, + "step": 2381824 + }, + { + "epoch": 0.01, + "learning_rate": 1.0997252947038156e-05, + "loss": 3.356, + "step": 2382336 + }, + { + "epoch": 0.01, + "learning_rate": 1.0988866999527636e-05, + "loss": 3.3638, + "step": 2382848 + }, + { + "epoch": 0.01, + "learning_rate": 1.0980481052017116e-05, + "loss": 3.3599, + "step": 2383360 + }, + { + "epoch": 0.01, + "learning_rate": 1.0972095104506596e-05, + "loss": 3.3573, + "step": 2383872 + }, + { + "epoch": 0.01, + "learning_rate": 1.0963709156996076e-05, + "loss": 3.3618, + "step": 2384384 + }, + { + "epoch": 0.01, + "learning_rate": 1.0955323209485555e-05, + "loss": 3.3529, + "step": 2384896 + }, + { + "epoch": 0.01, + "learning_rate": 1.0946953640778766e-05, + "loss": 3.3621, + "step": 2385408 + }, + { + "epoch": 0.01, + "learning_rate": 1.0938567693268246e-05, + "loss": 3.3494, + "step": 2385920 + }, + { + "epoch": 0.01, + "learning_rate": 1.0930181745757726e-05, + "loss": 3.3514, + "step": 2386432 + }, + { + "epoch": 0.01, + "learning_rate": 1.0921795798247206e-05, + "loss": 3.3586, + "step": 2386944 + }, + { + "epoch": 0.01, + "learning_rate": 1.0913409850736686e-05, + "loss": 3.366, + "step": 2387456 + }, + { + "epoch": 0.01, + "learning_rate": 1.0905023903226166e-05, + "loss": 3.3563, + "step": 2387968 + }, + { + "epoch": 0.01, + "learning_rate": 1.0896637955715646e-05, + "loss": 3.3625, + "step": 2388480 + }, + { + "epoch": 0.01, + "learning_rate": 1.0888252008205126e-05, + "loss": 3.3605, + "step": 2388992 + }, + { + "epoch": 0.01, + "learning_rate": 1.0879882439498337e-05, + "loss": 3.3565, + "step": 2389504 + }, + { + "epoch": 0.01, + "learning_rate": 1.0871496491987818e-05, + "loss": 3.3602, + "step": 2390016 + }, + { + "epoch": 0.01, + "learning_rate": 1.0863110544477297e-05, + "loss": 3.3307, + "step": 2390528 + }, + { + "epoch": 0.01, + "learning_rate": 1.0854724596966777e-05, + "loss": 3.3526, + "step": 2391040 + }, + { + "epoch": 0.01, + "learning_rate": 1.0846355028259989e-05, + "loss": 3.3629, + "step": 2391552 + }, + { + "epoch": 0.01, + "learning_rate": 1.0837969080749469e-05, + "loss": 3.3618, + "step": 2392064 + }, + { + "epoch": 0.01, + "learning_rate": 1.082959951204268e-05, + "loss": 3.346, + "step": 2392576 + }, + { + "epoch": 0.01, + "learning_rate": 1.082121356453216e-05, + "loss": 3.3357, + "step": 2393088 + }, + { + "epoch": 0.01, + "learning_rate": 1.081282761702164e-05, + "loss": 3.3474, + "step": 2393600 + }, + { + "epoch": 0.01, + "learning_rate": 1.080444166951112e-05, + "loss": 3.3374, + "step": 2394112 + }, + { + "epoch": 0.01, + "learning_rate": 1.07960557220006e-05, + "loss": 3.3715, + "step": 2394624 + }, + { + "epoch": 0.01, + "learning_rate": 1.078766977449008e-05, + "loss": 3.3403, + "step": 2395136 + }, + { + "epoch": 0.01, + "learning_rate": 1.077928382697956e-05, + "loss": 3.3605, + "step": 2395648 + }, + { + "epoch": 0.01, + "learning_rate": 1.0770897879469038e-05, + "loss": 3.3539, + "step": 2396160 + }, + { + "epoch": 0.01, + "learning_rate": 1.0762544689565981e-05, + "loss": 3.345, + "step": 2396672 + }, + { + "epoch": 0.01, + "learning_rate": 1.0754158742055461e-05, + "loss": 3.3563, + "step": 2397184 + }, + { + "epoch": 0.01, + "learning_rate": 1.0745772794544943e-05, + "loss": 3.3469, + "step": 2397696 + }, + { + "epoch": 0.01, + "learning_rate": 1.0737386847034421e-05, + "loss": 3.3442, + "step": 2398208 + }, + { + "epoch": 0.01, + "learning_rate": 1.0729000899523901e-05, + "loss": 3.3398, + "step": 2398720 + }, + { + "epoch": 0.01, + "learning_rate": 1.0720631330817113e-05, + "loss": 3.3618, + "step": 2399232 + }, + { + "epoch": 0.01, + "learning_rate": 1.0712245383306593e-05, + "loss": 3.3488, + "step": 2399744 + }, + { + "epoch": 0.01, + "learning_rate": 1.0703859435796072e-05, + "loss": 3.3417, + "step": 2400256 + }, + { + "epoch": 0.01, + "learning_rate": 1.0695473488285553e-05, + "loss": 3.3427, + "step": 2400768 + }, + { + "epoch": 0.01, + "learning_rate": 1.0687087540775033e-05, + "loss": 3.3496, + "step": 2401280 + }, + { + "epoch": 0.01, + "learning_rate": 1.0678701593264512e-05, + "loss": 3.3592, + "step": 2401792 + }, + { + "epoch": 0.01, + "learning_rate": 1.0670315645753991e-05, + "loss": 3.3595, + "step": 2402304 + }, + { + "epoch": 0.01, + "learning_rate": 1.0661946077047204e-05, + "loss": 3.3573, + "step": 2402816 + }, + { + "epoch": 0.01, + "learning_rate": 1.0653576508340415e-05, + "loss": 3.3605, + "step": 2403328 + }, + { + "epoch": 0.01, + "learning_rate": 1.0645190560829895e-05, + "loss": 3.3686, + "step": 2403840 + }, + { + "epoch": 0.01, + "learning_rate": 1.0636804613319375e-05, + "loss": 3.3631, + "step": 2404352 + }, + { + "epoch": 0.01, + "learning_rate": 1.0628418665808855e-05, + "loss": 3.3629, + "step": 2404864 + }, + { + "epoch": 0.01, + "learning_rate": 1.0620032718298335e-05, + "loss": 3.3508, + "step": 2405376 + }, + { + "epoch": 0.01, + "learning_rate": 1.0611646770787815e-05, + "loss": 3.3566, + "step": 2405888 + }, + { + "epoch": 0.01, + "learning_rate": 1.0603277202081025e-05, + "loss": 3.3535, + "step": 2406400 + }, + { + "epoch": 0.01, + "learning_rate": 1.0594891254570507e-05, + "loss": 3.3536, + "step": 2406912 + }, + { + "epoch": 0.01, + "learning_rate": 1.0586505307059985e-05, + "loss": 3.3636, + "step": 2407424 + }, + { + "epoch": 0.01, + "learning_rate": 1.0578119359549465e-05, + "loss": 3.3649, + "step": 2407936 + }, + { + "epoch": 0.01, + "learning_rate": 1.0569733412038945e-05, + "loss": 3.3537, + "step": 2408448 + }, + { + "epoch": 0.01, + "learning_rate": 1.0561347464528425e-05, + "loss": 3.3406, + "step": 2408960 + }, + { + "epoch": 0.01, + "learning_rate": 1.0552977895821636e-05, + "loss": 3.3453, + "step": 2409472 + }, + { + "epoch": 0.01, + "learning_rate": 1.0544591948311116e-05, + "loss": 3.356, + "step": 2409984 + }, + { + "epoch": 0.01, + "learning_rate": 1.0536206000800598e-05, + "loss": 3.3604, + "step": 2410496 + }, + { + "epoch": 0.01, + "learning_rate": 1.0527820053290076e-05, + "loss": 3.3446, + "step": 2411008 + }, + { + "epoch": 0.01, + "learning_rate": 1.0519434105779556e-05, + "loss": 3.3574, + "step": 2411520 + }, + { + "epoch": 0.02, + "learning_rate": 1.0511048158269036e-05, + "loss": 3.359, + "step": 2412032 + }, + { + "epoch": 0.02, + "learning_rate": 1.0502678589562248e-05, + "loss": 3.3479, + "step": 2412544 + }, + { + "epoch": 0.02, + "learning_rate": 1.0494292642051726e-05, + "loss": 3.3475, + "step": 2413056 + }, + { + "epoch": 0.02, + "learning_rate": 1.0485906694541208e-05, + "loss": 3.3598, + "step": 2413568 + }, + { + "epoch": 0.02, + "learning_rate": 1.0477520747030688e-05, + "loss": 3.3533, + "step": 2414080 + }, + { + "epoch": 0.02, + "learning_rate": 1.0469134799520166e-05, + "loss": 3.361, + "step": 2414592 + }, + { + "epoch": 0.02, + "learning_rate": 1.0460748852009646e-05, + "loss": 3.3455, + "step": 2415104 + }, + { + "epoch": 0.02, + "learning_rate": 1.0452362904499128e-05, + "loss": 3.3483, + "step": 2415616 + }, + { + "epoch": 0.02, + "learning_rate": 1.0443976956988606e-05, + "loss": 3.3551, + "step": 2416128 + }, + { + "epoch": 0.02, + "learning_rate": 1.0435607388281819e-05, + "loss": 3.3607, + "step": 2416640 + }, + { + "epoch": 0.02, + "learning_rate": 1.0427221440771299e-05, + "loss": 3.3543, + "step": 2417152 + }, + { + "epoch": 0.02, + "learning_rate": 1.0418835493260779e-05, + "loss": 3.3564, + "step": 2417664 + }, + { + "epoch": 0.02, + "learning_rate": 1.041046592455399e-05, + "loss": 3.3553, + "step": 2418176 + }, + { + "epoch": 0.02, + "learning_rate": 1.040207997704347e-05, + "loss": 3.3562, + "step": 2418688 + }, + { + "epoch": 0.02, + "learning_rate": 1.039369402953295e-05, + "loss": 3.3566, + "step": 2419200 + }, + { + "epoch": 0.02, + "learning_rate": 1.038530808202243e-05, + "loss": 3.3393, + "step": 2419712 + }, + { + "epoch": 0.02, + "learning_rate": 1.037693851331564e-05, + "loss": 3.3476, + "step": 2420224 + }, + { + "epoch": 0.02, + "learning_rate": 1.036855256580512e-05, + "loss": 3.3538, + "step": 2420736 + }, + { + "epoch": 0.02, + "learning_rate": 1.03601666182946e-05, + "loss": 3.352, + "step": 2421248 + }, + { + "epoch": 0.02, + "learning_rate": 1.035178067078408e-05, + "loss": 3.3418, + "step": 2421760 + }, + { + "epoch": 0.02, + "learning_rate": 1.034339472327356e-05, + "loss": 3.3443, + "step": 2422272 + }, + { + "epoch": 0.02, + "learning_rate": 1.033500877576304e-05, + "loss": 3.3375, + "step": 2422784 + }, + { + "epoch": 0.02, + "learning_rate": 1.0326639207056252e-05, + "loss": 3.3552, + "step": 2423296 + }, + { + "epoch": 0.02, + "learning_rate": 1.031825325954573e-05, + "loss": 3.3469, + "step": 2423808 + }, + { + "epoch": 0.02, + "learning_rate": 1.030986731203521e-05, + "loss": 3.3537, + "step": 2424320 + }, + { + "epoch": 0.02, + "learning_rate": 1.0301481364524692e-05, + "loss": 3.3525, + "step": 2424832 + }, + { + "epoch": 0.02, + "learning_rate": 1.029309541701417e-05, + "loss": 3.3604, + "step": 2425344 + }, + { + "epoch": 0.02, + "learning_rate": 1.028470946950365e-05, + "loss": 3.3558, + "step": 2425856 + }, + { + "epoch": 0.02, + "learning_rate": 1.027632352199313e-05, + "loss": 3.355, + "step": 2426368 + }, + { + "epoch": 0.02, + "learning_rate": 1.0267953953286343e-05, + "loss": 3.361, + "step": 2426880 + }, + { + "epoch": 0.02, + "learning_rate": 1.0259568005775821e-05, + "loss": 3.3506, + "step": 2427392 + }, + { + "epoch": 0.02, + "learning_rate": 1.0251182058265301e-05, + "loss": 3.3523, + "step": 2427904 + }, + { + "epoch": 0.02, + "learning_rate": 1.0242796110754783e-05, + "loss": 3.3547, + "step": 2428416 + }, + { + "epoch": 0.02, + "learning_rate": 1.0234410163244261e-05, + "loss": 3.3536, + "step": 2428928 + }, + { + "epoch": 0.02, + "learning_rate": 1.0226040594537473e-05, + "loss": 3.3535, + "step": 2429440 + }, + { + "epoch": 0.02, + "learning_rate": 1.0217654647026953e-05, + "loss": 3.3446, + "step": 2429952 + }, + { + "epoch": 0.02, + "learning_rate": 1.0209268699516433e-05, + "loss": 3.3493, + "step": 2430464 + }, + { + "epoch": 0.02, + "learning_rate": 1.0200882752005912e-05, + "loss": 3.343, + "step": 2430976 + }, + { + "epoch": 0.02, + "learning_rate": 1.0192513183299124e-05, + "loss": 3.3464, + "step": 2431488 + }, + { + "epoch": 0.02, + "learning_rate": 1.0184127235788604e-05, + "loss": 3.3407, + "step": 2432000 + }, + { + "epoch": 0.02, + "learning_rate": 1.0175741288278082e-05, + "loss": 3.365, + "step": 2432512 + }, + { + "epoch": 0.02, + "learning_rate": 1.0167355340767564e-05, + "loss": 3.361, + "step": 2433024 + }, + { + "epoch": 0.02, + "learning_rate": 1.0158969393257044e-05, + "loss": 3.3482, + "step": 2433536 + }, + { + "epoch": 0.02, + "learning_rate": 1.0150583445746524e-05, + "loss": 3.3539, + "step": 2434048 + }, + { + "epoch": 0.02, + "learning_rate": 1.0142197498236004e-05, + "loss": 3.3531, + "step": 2434560 + }, + { + "epoch": 0.02, + "learning_rate": 1.0133811550725484e-05, + "loss": 3.3608, + "step": 2435072 + }, + { + "epoch": 0.02, + "learning_rate": 1.0125441982018695e-05, + "loss": 3.3533, + "step": 2435584 + }, + { + "epoch": 0.02, + "learning_rate": 1.0117056034508175e-05, + "loss": 3.3501, + "step": 2436096 + }, + { + "epoch": 0.02, + "learning_rate": 1.0108670086997654e-05, + "loss": 3.3622, + "step": 2436608 + }, + { + "epoch": 0.02, + "learning_rate": 1.0100284139487134e-05, + "loss": 3.3464, + "step": 2437120 + }, + { + "epoch": 0.02, + "learning_rate": 1.0091914570780347e-05, + "loss": 3.356, + "step": 2437632 + }, + { + "epoch": 0.02, + "learning_rate": 1.0083528623269825e-05, + "loss": 3.3515, + "step": 2438144 + }, + { + "epoch": 0.02, + "learning_rate": 1.0075142675759305e-05, + "loss": 3.3547, + "step": 2438656 + }, + { + "epoch": 0.02, + "learning_rate": 1.0066756728248785e-05, + "loss": 3.351, + "step": 2439168 + }, + { + "epoch": 0.02, + "learning_rate": 1.0058370780738265e-05, + "loss": 3.3411, + "step": 2439680 + }, + { + "epoch": 0.02, + "learning_rate": 1.0049984833227745e-05, + "loss": 3.3599, + "step": 2440192 + }, + { + "epoch": 0.02, + "learning_rate": 1.0041598885717225e-05, + "loss": 3.3526, + "step": 2440704 + }, + { + "epoch": 0.02, + "learning_rate": 1.0033212938206705e-05, + "loss": 3.357, + "step": 2441216 + }, + { + "epoch": 0.02, + "learning_rate": 1.0024859748303647e-05, + "loss": 3.3483, + "step": 2441728 + }, + { + "epoch": 0.03, + "learning_rate": 1.0016473800793128e-05, + "loss": 3.3507, + "step": 2442240 + }, + { + "epoch": 0.03, + "eval_loss": 3.8656537532806396, + "eval_runtime": 311.904, + "eval_samples_per_second": 1223.424, + "eval_steps_per_second": 38.233, + "step": 2442240 + }, + { + "epoch": 1.0, + "learning_rate": 1.0008087853282608e-05, + "loss": 3.3422, + "step": 2442752 + }, + { + "epoch": 1.0, + "learning_rate": 9.999701905772088e-06, + "loss": 3.3431, + "step": 2443264 + }, + { + "epoch": 1.0, + "learning_rate": 9.991315958261566e-06, + "loss": 3.358, + "step": 2443776 + }, + { + "epoch": 1.0, + "learning_rate": 9.982930010751048e-06, + "loss": 3.3541, + "step": 2444288 + }, + { + "epoch": 1.0, + "learning_rate": 9.974560442044259e-06, + "loss": 3.3623, + "step": 2444800 + }, + { + "epoch": 1.0, + "learning_rate": 9.966174494533739e-06, + "loss": 3.3441, + "step": 2445312 + }, + { + "epoch": 1.0, + "learning_rate": 9.957788547023219e-06, + "loss": 3.3487, + "step": 2445824 + }, + { + "epoch": 1.0, + "learning_rate": 9.949402599512699e-06, + "loss": 3.3397, + "step": 2446336 + }, + { + "epoch": 1.0, + "learning_rate": 9.94103303080591e-06, + "loss": 3.3547, + "step": 2446848 + }, + { + "epoch": 1.0, + "learning_rate": 9.93264708329539e-06, + "loss": 3.3463, + "step": 2447360 + }, + { + "epoch": 1.0, + "learning_rate": 9.92426113578487e-06, + "loss": 3.3559, + "step": 2447872 + }, + { + "epoch": 1.0, + "learning_rate": 9.91587518827435e-06, + "loss": 3.3519, + "step": 2448384 + }, + { + "epoch": 1.0, + "learning_rate": 9.90748924076383e-06, + "loss": 3.3442, + "step": 2448896 + }, + { + "epoch": 1.0, + "learning_rate": 9.89911967205704e-06, + "loss": 3.3401, + "step": 2449408 + }, + { + "epoch": 1.0, + "learning_rate": 9.89073372454652e-06, + "loss": 3.3422, + "step": 2449920 + }, + { + "epoch": 1.0, + "learning_rate": 9.882347777036002e-06, + "loss": 3.3399, + "step": 2450432 + }, + { + "epoch": 1.0, + "learning_rate": 9.87396182952548e-06, + "loss": 3.3456, + "step": 2450944 + }, + { + "epoch": 1.0, + "learning_rate": 9.86559226081869e-06, + "loss": 3.3487, + "step": 2451456 + }, + { + "epoch": 1.0, + "learning_rate": 9.857206313308172e-06, + "loss": 3.3396, + "step": 2451968 + }, + { + "epoch": 1.0, + "learning_rate": 9.848820365797652e-06, + "loss": 3.3675, + "step": 2452480 + }, + { + "epoch": 1.0, + "learning_rate": 9.84043441828713e-06, + "loss": 3.3477, + "step": 2452992 + }, + { + "epoch": 1.0, + "learning_rate": 9.832048470776612e-06, + "loss": 3.3508, + "step": 2453504 + }, + { + "epoch": 1.0, + "learning_rate": 9.823662523266092e-06, + "loss": 3.3467, + "step": 2454016 + }, + { + "epoch": 1.0, + "learning_rate": 9.81527657575557e-06, + "loss": 3.3582, + "step": 2454528 + }, + { + "epoch": 1.0, + "learning_rate": 9.80689062824505e-06, + "loss": 3.3455, + "step": 2455040 + }, + { + "epoch": 1.0, + "learning_rate": 9.798521059538263e-06, + "loss": 3.3494, + "step": 2455552 + }, + { + "epoch": 1.0, + "learning_rate": 9.790151490831474e-06, + "loss": 3.3455, + "step": 2456064 + }, + { + "epoch": 1.0, + "learning_rate": 9.781765543320954e-06, + "loss": 3.3433, + "step": 2456576 + }, + { + "epoch": 1.0, + "learning_rate": 9.773379595810434e-06, + "loss": 3.338, + "step": 2457088 + }, + { + "epoch": 1.01, + "learning_rate": 9.764993648299914e-06, + "loss": 3.3422, + "step": 2457600 + }, + { + "epoch": 1.01, + "learning_rate": 9.756607700789394e-06, + "loss": 3.3515, + "step": 2458112 + }, + { + "epoch": 1.01, + "learning_rate": 9.748238132082604e-06, + "loss": 3.348, + "step": 2458624 + }, + { + "epoch": 1.01, + "learning_rate": 9.739852184572084e-06, + "loss": 3.3514, + "step": 2459136 + }, + { + "epoch": 1.01, + "learning_rate": 9.731466237061564e-06, + "loss": 3.3536, + "step": 2459648 + }, + { + "epoch": 1.01, + "learning_rate": 9.723080289551044e-06, + "loss": 3.3494, + "step": 2460160 + }, + { + "epoch": 1.01, + "learning_rate": 9.714694342040524e-06, + "loss": 3.35, + "step": 2460672 + }, + { + "epoch": 1.01, + "learning_rate": 9.706308394530004e-06, + "loss": 3.3456, + "step": 2461184 + }, + { + "epoch": 1.01, + "learning_rate": 9.697922447019484e-06, + "loss": 3.3497, + "step": 2461696 + }, + { + "epoch": 1.01, + "learning_rate": 9.689536499508964e-06, + "loss": 3.3422, + "step": 2462208 + }, + { + "epoch": 1.01, + "learning_rate": 9.681166930802175e-06, + "loss": 3.3437, + "step": 2462720 + }, + { + "epoch": 1.01, + "learning_rate": 9.672780983291656e-06, + "loss": 3.3467, + "step": 2463232 + }, + { + "epoch": 1.01, + "learning_rate": 9.664395035781135e-06, + "loss": 3.3569, + "step": 2463744 + }, + { + "epoch": 1.01, + "learning_rate": 9.656009088270615e-06, + "loss": 3.3445, + "step": 2464256 + }, + { + "epoch": 1.01, + "learning_rate": 9.647655898367558e-06, + "loss": 3.3528, + "step": 2464768 + }, + { + "epoch": 1.01, + "learning_rate": 9.639269950857038e-06, + "loss": 3.3524, + "step": 2465280 + }, + { + "epoch": 1.01, + "learning_rate": 9.630884003346518e-06, + "loss": 3.3525, + "step": 2465792 + }, + { + "epoch": 1.01, + "learning_rate": 9.622498055835998e-06, + "loss": 3.3463, + "step": 2466304 + }, + { + "epoch": 1.01, + "learning_rate": 9.614112108325478e-06, + "loss": 3.3227, + "step": 2466816 + }, + { + "epoch": 1.01, + "learning_rate": 9.605726160814956e-06, + "loss": 3.3442, + "step": 2467328 + }, + { + "epoch": 1.01, + "learning_rate": 9.597340213304438e-06, + "loss": 3.3501, + "step": 2467840 + }, + { + "epoch": 1.01, + "learning_rate": 9.588954265793918e-06, + "loss": 3.3544, + "step": 2468352 + }, + { + "epoch": 1.01, + "learning_rate": 9.580584697087128e-06, + "loss": 3.3383, + "step": 2468864 + }, + { + "epoch": 1.01, + "learning_rate": 9.572198749576608e-06, + "loss": 3.3253, + "step": 2469376 + }, + { + "epoch": 1.01, + "learning_rate": 9.563812802066088e-06, + "loss": 3.3377, + "step": 2469888 + }, + { + "epoch": 1.01, + "learning_rate": 9.555426854555568e-06, + "loss": 3.3259, + "step": 2470400 + }, + { + "epoch": 1.01, + "learning_rate": 9.547057285848779e-06, + "loss": 3.3584, + "step": 2470912 + }, + { + "epoch": 1.01, + "learning_rate": 9.538671338338259e-06, + "loss": 3.3333, + "step": 2471424 + }, + { + "epoch": 1.01, + "learning_rate": 9.530285390827739e-06, + "loss": 3.3492, + "step": 2471936 + }, + { + "epoch": 1.01, + "learning_rate": 9.52189944331722e-06, + "loss": 3.3451, + "step": 2472448 + }, + { + "epoch": 1.01, + "learning_rate": 9.513546253414162e-06, + "loss": 3.3343, + "step": 2472960 + }, + { + "epoch": 1.01, + "learning_rate": 9.505160305903642e-06, + "loss": 3.3471, + "step": 2473472 + }, + { + "epoch": 1.01, + "learning_rate": 9.496774358393122e-06, + "loss": 3.338, + "step": 2473984 + }, + { + "epoch": 1.01, + "learning_rate": 9.488388410882602e-06, + "loss": 3.3325, + "step": 2474496 + }, + { + "epoch": 1.01, + "learning_rate": 9.480002463372082e-06, + "loss": 3.3269, + "step": 2475008 + }, + { + "epoch": 1.01, + "learning_rate": 9.471632894665293e-06, + "loss": 3.3551, + "step": 2475520 + }, + { + "epoch": 1.01, + "learning_rate": 9.463246947154773e-06, + "loss": 3.3415, + "step": 2476032 + }, + { + "epoch": 1.01, + "learning_rate": 9.454860999644253e-06, + "loss": 3.3335, + "step": 2476544 + }, + { + "epoch": 1.01, + "learning_rate": 9.446475052133733e-06, + "loss": 3.332, + "step": 2477056 + }, + { + "epoch": 1.01, + "learning_rate": 9.438089104623213e-06, + "loss": 3.3397, + "step": 2477568 + }, + { + "epoch": 1.01, + "learning_rate": 9.429703157112693e-06, + "loss": 3.3512, + "step": 2478080 + }, + { + "epoch": 1.01, + "learning_rate": 9.421317209602173e-06, + "loss": 3.351, + "step": 2478592 + }, + { + "epoch": 1.01, + "learning_rate": 9.412947640895383e-06, + "loss": 3.3467, + "step": 2479104 + }, + { + "epoch": 1.01, + "learning_rate": 9.404578072188596e-06, + "loss": 3.3532, + "step": 2479616 + }, + { + "epoch": 1.01, + "learning_rate": 9.396192124678076e-06, + "loss": 3.3577, + "step": 2480128 + }, + { + "epoch": 1.01, + "learning_rate": 9.387806177167554e-06, + "loss": 3.3504, + "step": 2480640 + }, + { + "epoch": 1.01, + "learning_rate": 9.379420229657036e-06, + "loss": 3.3501, + "step": 2481152 + }, + { + "epoch": 1.01, + "learning_rate": 9.371034282146516e-06, + "loss": 3.343, + "step": 2481664 + }, + { + "epoch": 1.01, + "learning_rate": 9.362648334635994e-06, + "loss": 3.3481, + "step": 2482176 + }, + { + "epoch": 1.01, + "learning_rate": 9.354262387125474e-06, + "loss": 3.3472, + "step": 2482688 + }, + { + "epoch": 1.01, + "learning_rate": 9.345876439614956e-06, + "loss": 3.3428, + "step": 2483200 + }, + { + "epoch": 1.01, + "learning_rate": 9.337506870908166e-06, + "loss": 3.3515, + "step": 2483712 + }, + { + "epoch": 1.01, + "learning_rate": 9.329120923397645e-06, + "loss": 3.3527, + "step": 2484224 + }, + { + "epoch": 1.01, + "learning_rate": 9.320734975887126e-06, + "loss": 3.3479, + "step": 2484736 + }, + { + "epoch": 1.01, + "learning_rate": 9.312349028376606e-06, + "loss": 3.3311, + "step": 2485248 + }, + { + "epoch": 1.01, + "learning_rate": 9.30399583847355e-06, + "loss": 3.3325, + "step": 2485760 + }, + { + "epoch": 1.01, + "learning_rate": 9.295609890963028e-06, + "loss": 3.3497, + "step": 2486272 + }, + { + "epoch": 1.01, + "learning_rate": 9.287223943452508e-06, + "loss": 3.3535, + "step": 2486784 + }, + { + "epoch": 1.01, + "learning_rate": 9.278837995941988e-06, + "loss": 3.3372, + "step": 2487296 + }, + { + "epoch": 1.01, + "learning_rate": 9.270452048431468e-06, + "loss": 3.3471, + "step": 2487808 + }, + { + "epoch": 1.02, + "learning_rate": 9.262082479724678e-06, + "loss": 3.3523, + "step": 2488320 + }, + { + "epoch": 1.02, + "learning_rate": 9.25369653221416e-06, + "loss": 3.3373, + "step": 2488832 + }, + { + "epoch": 1.02, + "learning_rate": 9.24531058470364e-06, + "loss": 3.3382, + "step": 2489344 + }, + { + "epoch": 1.02, + "learning_rate": 9.236924637193118e-06, + "loss": 3.3444, + "step": 2489856 + }, + { + "epoch": 1.02, + "learning_rate": 9.22855506848633e-06, + "loss": 3.3453, + "step": 2490368 + }, + { + "epoch": 1.02, + "learning_rate": 9.22016912097581e-06, + "loss": 3.3492, + "step": 2490880 + }, + { + "epoch": 1.02, + "learning_rate": 9.211783173465289e-06, + "loss": 3.3442, + "step": 2491392 + }, + { + "epoch": 1.02, + "learning_rate": 9.20339722595477e-06, + "loss": 3.3331, + "step": 2491904 + }, + { + "epoch": 1.02, + "learning_rate": 9.19501127844425e-06, + "loss": 3.3492, + "step": 2492416 + }, + { + "epoch": 1.02, + "learning_rate": 9.18662533093373e-06, + "loss": 3.3481, + "step": 2492928 + }, + { + "epoch": 1.02, + "learning_rate": 9.178239383423209e-06, + "loss": 3.3413, + "step": 2493440 + }, + { + "epoch": 1.02, + "learning_rate": 9.16985343591269e-06, + "loss": 3.3487, + "step": 2493952 + }, + { + "epoch": 1.02, + "learning_rate": 9.161483867205901e-06, + "loss": 3.3425, + "step": 2494464 + }, + { + "epoch": 1.02, + "learning_rate": 9.15309791969538e-06, + "loss": 3.3475, + "step": 2494976 + }, + { + "epoch": 1.02, + "learning_rate": 9.144728350988592e-06, + "loss": 3.3505, + "step": 2495488 + }, + { + "epoch": 1.02, + "learning_rate": 9.136342403478072e-06, + "loss": 3.3307, + "step": 2496000 + }, + { + "epoch": 1.02, + "learning_rate": 9.127956455967552e-06, + "loss": 3.3336, + "step": 2496512 + }, + { + "epoch": 1.02, + "learning_rate": 9.119570508457032e-06, + "loss": 3.3469, + "step": 2497024 + }, + { + "epoch": 1.02, + "learning_rate": 9.111184560946512e-06, + "loss": 3.3443, + "step": 2497536 + }, + { + "epoch": 1.02, + "learning_rate": 9.102798613435992e-06, + "loss": 3.3268, + "step": 2498048 + }, + { + "epoch": 1.02, + "learning_rate": 9.094412665925472e-06, + "loss": 3.3393, + "step": 2498560 + }, + { + "epoch": 1.02, + "learning_rate": 9.086026718414952e-06, + "loss": 3.3327, + "step": 2499072 + }, + { + "epoch": 1.02, + "learning_rate": 9.077673528511895e-06, + "loss": 3.3437, + "step": 2499584 + }, + { + "epoch": 1.02, + "learning_rate": 9.069287581001375e-06, + "loss": 3.3384, + "step": 2500096 + }, + { + "epoch": 1.02, + "learning_rate": 9.060901633490853e-06, + "loss": 3.3397, + "step": 2500608 + }, + { + "epoch": 1.02, + "learning_rate": 9.052515685980333e-06, + "loss": 3.3447, + "step": 2501120 + }, + { + "epoch": 1.02, + "learning_rate": 9.044129738469815e-06, + "loss": 3.3522, + "step": 2501632 + }, + { + "epoch": 1.02, + "learning_rate": 9.035743790959293e-06, + "loss": 3.3463, + "step": 2502144 + }, + { + "epoch": 1.02, + "learning_rate": 9.027357843448773e-06, + "loss": 3.3484, + "step": 2502656 + }, + { + "epoch": 1.02, + "learning_rate": 9.018988274741986e-06, + "loss": 3.3501, + "step": 2503168 + }, + { + "epoch": 1.02, + "learning_rate": 9.010602327231466e-06, + "loss": 3.3439, + "step": 2503680 + }, + { + "epoch": 1.02, + "learning_rate": 9.002216379720944e-06, + "loss": 3.3348, + "step": 2504192 + }, + { + "epoch": 1.02, + "learning_rate": 8.993830432210425e-06, + "loss": 3.3459, + "step": 2504704 + }, + { + "epoch": 1.02, + "learning_rate": 8.985444484699905e-06, + "loss": 3.3391, + "step": 2505216 + }, + { + "epoch": 1.02, + "learning_rate": 8.977074915993116e-06, + "loss": 3.3504, + "step": 2505728 + }, + { + "epoch": 1.02, + "learning_rate": 8.968688968482596e-06, + "loss": 3.3305, + "step": 2506240 + }, + { + "epoch": 1.02, + "learning_rate": 8.960303020972076e-06, + "loss": 3.3439, + "step": 2506752 + }, + { + "epoch": 1.02, + "learning_rate": 8.951917073461556e-06, + "loss": 3.3296, + "step": 2507264 + }, + { + "epoch": 1.02, + "learning_rate": 8.943547504754767e-06, + "loss": 3.3347, + "step": 2507776 + }, + { + "epoch": 1.02, + "learning_rate": 8.935161557244247e-06, + "loss": 3.3303, + "step": 2508288 + }, + { + "epoch": 1.02, + "learning_rate": 8.926775609733727e-06, + "loss": 3.3564, + "step": 2508800 + }, + { + "epoch": 1.02, + "learning_rate": 8.918389662223207e-06, + "loss": 3.3562, + "step": 2509312 + }, + { + "epoch": 1.02, + "learning_rate": 8.910003714712687e-06, + "loss": 3.338, + "step": 2509824 + }, + { + "epoch": 1.02, + "learning_rate": 8.901617767202167e-06, + "loss": 3.3429, + "step": 2510336 + }, + { + "epoch": 1.02, + "learning_rate": 8.893231819691647e-06, + "loss": 3.3442, + "step": 2510848 + }, + { + "epoch": 1.02, + "learning_rate": 8.884845872181127e-06, + "loss": 3.3509, + "step": 2511360 + }, + { + "epoch": 1.02, + "learning_rate": 8.876476303474337e-06, + "loss": 3.3472, + "step": 2511872 + }, + { + "epoch": 1.02, + "learning_rate": 8.868090355963817e-06, + "loss": 3.3382, + "step": 2512384 + }, + { + "epoch": 1.02, + "learning_rate": 8.859704408453299e-06, + "loss": 3.3523, + "step": 2512896 + }, + { + "epoch": 1.02, + "learning_rate": 8.851318460942777e-06, + "loss": 3.3379, + "step": 2513408 + }, + { + "epoch": 1.02, + "learning_rate": 8.842948892235988e-06, + "loss": 3.3509, + "step": 2513920 + }, + { + "epoch": 1.02, + "learning_rate": 8.83456294472547e-06, + "loss": 3.3414, + "step": 2514432 + }, + { + "epoch": 1.02, + "learning_rate": 8.826176997214948e-06, + "loss": 3.3412, + "step": 2514944 + }, + { + "epoch": 1.02, + "learning_rate": 8.817791049704428e-06, + "loss": 3.3442, + "step": 2515456 + }, + { + "epoch": 1.02, + "learning_rate": 8.809405102193908e-06, + "loss": 3.3343, + "step": 2515968 + }, + { + "epoch": 1.02, + "learning_rate": 8.80101915468339e-06, + "loss": 3.3476, + "step": 2516480 + }, + { + "epoch": 1.02, + "learning_rate": 8.792633207172868e-06, + "loss": 3.3472, + "step": 2516992 + }, + { + "epoch": 1.02, + "learning_rate": 8.784247259662348e-06, + "loss": 3.3464, + "step": 2517504 + }, + { + "epoch": 1.02, + "learning_rate": 8.775894069759291e-06, + "loss": 3.3405, + "step": 2518016 + }, + { + "epoch": 1.02, + "learning_rate": 8.767508122248771e-06, + "loss": 3.3372, + "step": 2518528 + }, + { + "epoch": 1.03, + "eval_loss": 3.867246389389038, + "eval_runtime": 312.6033, + "eval_samples_per_second": 1220.688, + "eval_steps_per_second": 38.147, + "step": 2518560 + }, + { + "epoch": 0.0, + "learning_rate": 8.759122174738251e-06, + "loss": 3.331, + "step": 2519040 + }, + { + "epoch": 0.0, + "learning_rate": 8.750736227227731e-06, + "loss": 3.3348, + "step": 2519552 + }, + { + "epoch": 0.0, + "learning_rate": 8.74235027971721e-06, + "loss": 3.3495, + "step": 2520064 + }, + { + "epoch": 0.0, + "learning_rate": 8.733980711010422e-06, + "loss": 3.3396, + "step": 2520576 + }, + { + "epoch": 0.0, + "learning_rate": 8.725611142303632e-06, + "loss": 3.3569, + "step": 2521088 + }, + { + "epoch": 0.0, + "learning_rate": 8.717225194793114e-06, + "loss": 3.3337, + "step": 2521600 + }, + { + "epoch": 0.0, + "learning_rate": 8.708839247282594e-06, + "loss": 3.3426, + "step": 2522112 + }, + { + "epoch": 0.0, + "learning_rate": 8.700453299772072e-06, + "loss": 3.3281, + "step": 2522624 + }, + { + "epoch": 0.0, + "learning_rate": 8.692083731065285e-06, + "loss": 3.3447, + "step": 2523136 + }, + { + "epoch": 0.0, + "learning_rate": 8.683697783554765e-06, + "loss": 3.3396, + "step": 2523648 + }, + { + "epoch": 0.0, + "learning_rate": 8.675311836044245e-06, + "loss": 3.3428, + "step": 2524160 + }, + { + "epoch": 0.0, + "learning_rate": 8.666925888533723e-06, + "loss": 3.3397, + "step": 2524672 + }, + { + "epoch": 0.0, + "learning_rate": 8.658539941023205e-06, + "loss": 3.3346, + "step": 2525184 + }, + { + "epoch": 0.0, + "learning_rate": 8.650170372316415e-06, + "loss": 3.335, + "step": 2525696 + }, + { + "epoch": 0.0, + "learning_rate": 8.641784424805895e-06, + "loss": 3.3333, + "step": 2526208 + }, + { + "epoch": 0.0, + "learning_rate": 8.633398477295375e-06, + "loss": 3.3304, + "step": 2526720 + }, + { + "epoch": 0.0, + "learning_rate": 8.625012529784855e-06, + "loss": 3.3375, + "step": 2527232 + }, + { + "epoch": 0.0, + "learning_rate": 8.616642961078068e-06, + "loss": 3.342, + "step": 2527744 + }, + { + "epoch": 0.0, + "learning_rate": 8.608257013567546e-06, + "loss": 3.3348, + "step": 2528256 + }, + { + "epoch": 0.0, + "learning_rate": 8.599871066057026e-06, + "loss": 3.3603, + "step": 2528768 + }, + { + "epoch": 0.0, + "learning_rate": 8.591485118546506e-06, + "loss": 3.3374, + "step": 2529280 + }, + { + "epoch": 0.0, + "learning_rate": 8.583099171035986e-06, + "loss": 3.3437, + "step": 2529792 + }, + { + "epoch": 0.0, + "learning_rate": 8.574713223525466e-06, + "loss": 3.3388, + "step": 2530304 + }, + { + "epoch": 0.0, + "learning_rate": 8.566327276014946e-06, + "loss": 3.3503, + "step": 2530816 + }, + { + "epoch": 0.0, + "learning_rate": 8.557941328504426e-06, + "loss": 3.3318, + "step": 2531328 + }, + { + "epoch": 0.0, + "learning_rate": 8.549571759797637e-06, + "loss": 3.3417, + "step": 2531840 + }, + { + "epoch": 0.0, + "learning_rate": 8.541202191090849e-06, + "loss": 3.3358, + "step": 2532352 + }, + { + "epoch": 0.0, + "learning_rate": 8.532816243580329e-06, + "loss": 3.3394, + "step": 2532864 + }, + { + "epoch": 0.0, + "learning_rate": 8.524430296069809e-06, + "loss": 3.3244, + "step": 2533376 + }, + { + "epoch": 0.01, + "learning_rate": 8.516044348559287e-06, + "loss": 3.3296, + "step": 2533888 + }, + { + "epoch": 0.01, + "learning_rate": 8.507658401048769e-06, + "loss": 3.3435, + "step": 2534400 + }, + { + "epoch": 0.01, + "learning_rate": 8.49928883234198e-06, + "loss": 3.34, + "step": 2534912 + }, + { + "epoch": 0.01, + "learning_rate": 8.490902884831458e-06, + "loss": 3.3405, + "step": 2535424 + }, + { + "epoch": 0.01, + "learning_rate": 8.48251693732094e-06, + "loss": 3.3448, + "step": 2535936 + }, + { + "epoch": 0.01, + "learning_rate": 8.47413098981042e-06, + "loss": 3.3398, + "step": 2536448 + }, + { + "epoch": 0.01, + "learning_rate": 8.465745042299898e-06, + "loss": 3.339, + "step": 2536960 + }, + { + "epoch": 0.01, + "learning_rate": 8.457359094789378e-06, + "loss": 3.3383, + "step": 2537472 + }, + { + "epoch": 0.01, + "learning_rate": 8.44897314727886e-06, + "loss": 3.3438, + "step": 2537984 + }, + { + "epoch": 0.01, + "learning_rate": 8.44060357857207e-06, + "loss": 3.3294, + "step": 2538496 + }, + { + "epoch": 0.01, + "learning_rate": 8.43221763106155e-06, + "loss": 3.3328, + "step": 2539008 + }, + { + "epoch": 0.01, + "learning_rate": 8.42383168355103e-06, + "loss": 3.3391, + "step": 2539520 + }, + { + "epoch": 0.01, + "learning_rate": 8.41544573604051e-06, + "loss": 3.3476, + "step": 2540032 + }, + { + "epoch": 0.01, + "learning_rate": 8.407059788529988e-06, + "loss": 3.335, + "step": 2540544 + }, + { + "epoch": 0.01, + "learning_rate": 8.3986902198232e-06, + "loss": 3.3421, + "step": 2541056 + }, + { + "epoch": 0.01, + "learning_rate": 8.39030427231268e-06, + "loss": 3.3469, + "step": 2541568 + }, + { + "epoch": 0.01, + "learning_rate": 8.38191832480216e-06, + "loss": 3.3386, + "step": 2542080 + }, + { + "epoch": 0.01, + "learning_rate": 8.37353237729164e-06, + "loss": 3.338, + "step": 2542592 + }, + { + "epoch": 0.01, + "learning_rate": 8.36514642978112e-06, + "loss": 3.3146, + "step": 2543104 + }, + { + "epoch": 0.01, + "learning_rate": 8.3567604822706e-06, + "loss": 3.3294, + "step": 2543616 + }, + { + "epoch": 0.01, + "learning_rate": 8.34837453476008e-06, + "loss": 3.3413, + "step": 2544128 + }, + { + "epoch": 0.01, + "learning_rate": 8.33998858724956e-06, + "loss": 3.3417, + "step": 2544640 + }, + { + "epoch": 0.01, + "learning_rate": 8.331619018542771e-06, + "loss": 3.3345, + "step": 2545152 + }, + { + "epoch": 0.01, + "learning_rate": 8.323233071032251e-06, + "loss": 3.3171, + "step": 2545664 + }, + { + "epoch": 0.01, + "learning_rate": 8.314863502325462e-06, + "loss": 3.3272, + "step": 2546176 + }, + { + "epoch": 0.01, + "learning_rate": 8.306477554814942e-06, + "loss": 3.3193, + "step": 2546688 + }, + { + "epoch": 0.01, + "learning_rate": 8.298091607304424e-06, + "loss": 3.3454, + "step": 2547200 + }, + { + "epoch": 0.01, + "learning_rate": 8.289705659793904e-06, + "loss": 3.3265, + "step": 2547712 + }, + { + "epoch": 0.01, + "learning_rate": 8.281336091087114e-06, + "loss": 3.3401, + "step": 2548224 + }, + { + "epoch": 0.01, + "learning_rate": 8.272950143576594e-06, + "loss": 3.3403, + "step": 2548736 + }, + { + "epoch": 0.01, + "learning_rate": 8.264564196066074e-06, + "loss": 3.3244, + "step": 2549248 + }, + { + "epoch": 0.01, + "learning_rate": 8.256178248555553e-06, + "loss": 3.3367, + "step": 2549760 + }, + { + "epoch": 0.01, + "learning_rate": 8.247792301045034e-06, + "loss": 3.3264, + "step": 2550272 + }, + { + "epoch": 0.01, + "learning_rate": 8.239406353534514e-06, + "loss": 3.3248, + "step": 2550784 + }, + { + "epoch": 0.01, + "learning_rate": 8.231036784827725e-06, + "loss": 3.3213, + "step": 2551296 + }, + { + "epoch": 0.01, + "learning_rate": 8.222650837317205e-06, + "loss": 3.3398, + "step": 2551808 + }, + { + "epoch": 0.01, + "learning_rate": 8.214264889806685e-06, + "loss": 3.334, + "step": 2552320 + }, + { + "epoch": 0.01, + "learning_rate": 8.205878942296165e-06, + "loss": 3.3241, + "step": 2552832 + }, + { + "epoch": 0.01, + "learning_rate": 8.197492994785643e-06, + "loss": 3.3244, + "step": 2553344 + }, + { + "epoch": 0.01, + "learning_rate": 8.189107047275125e-06, + "loss": 3.3271, + "step": 2553856 + }, + { + "epoch": 0.01, + "learning_rate": 8.180721099764605e-06, + "loss": 3.3414, + "step": 2554368 + }, + { + "epoch": 0.01, + "learning_rate": 8.172351531057815e-06, + "loss": 3.3404, + "step": 2554880 + }, + { + "epoch": 0.01, + "learning_rate": 8.163965583547295e-06, + "loss": 3.3361, + "step": 2555392 + }, + { + "epoch": 0.01, + "learning_rate": 8.155579636036775e-06, + "loss": 3.3489, + "step": 2555904 + }, + { + "epoch": 0.01, + "learning_rate": 8.147193688526255e-06, + "loss": 3.3452, + "step": 2556416 + }, + { + "epoch": 0.01, + "learning_rate": 8.138807741015735e-06, + "loss": 3.3466, + "step": 2556928 + }, + { + "epoch": 0.01, + "learning_rate": 8.130421793505215e-06, + "loss": 3.34, + "step": 2557440 + }, + { + "epoch": 0.01, + "learning_rate": 8.122052224798426e-06, + "loss": 3.3357, + "step": 2557952 + }, + { + "epoch": 0.01, + "learning_rate": 8.113666277287908e-06, + "loss": 3.3376, + "step": 2558464 + }, + { + "epoch": 0.01, + "learning_rate": 8.105280329777386e-06, + "loss": 3.3369, + "step": 2558976 + }, + { + "epoch": 0.01, + "learning_rate": 8.096894382266866e-06, + "loss": 3.334, + "step": 2559488 + }, + { + "epoch": 0.01, + "learning_rate": 8.088508434756346e-06, + "loss": 3.3418, + "step": 2560000 + }, + { + "epoch": 0.01, + "learning_rate": 8.080122487245826e-06, + "loss": 3.3452, + "step": 2560512 + }, + { + "epoch": 0.01, + "learning_rate": 8.071736539735306e-06, + "loss": 3.3325, + "step": 2561024 + }, + { + "epoch": 0.01, + "learning_rate": 8.063350592224786e-06, + "loss": 3.3271, + "step": 2561536 + }, + { + "epoch": 0.01, + "learning_rate": 8.054997402321729e-06, + "loss": 3.3228, + "step": 2562048 + }, + { + "epoch": 0.01, + "learning_rate": 8.046611454811207e-06, + "loss": 3.3367, + "step": 2562560 + }, + { + "epoch": 0.01, + "learning_rate": 8.038225507300689e-06, + "loss": 3.3464, + "step": 2563072 + }, + { + "epoch": 0.01, + "learning_rate": 8.029839559790169e-06, + "loss": 3.3296, + "step": 2563584 + }, + { + "epoch": 0.01, + "learning_rate": 8.021453612279649e-06, + "loss": 3.3375, + "step": 2564096 + }, + { + "epoch": 0.02, + "learning_rate": 8.01308404357286e-06, + "loss": 3.3436, + "step": 2564608 + }, + { + "epoch": 0.02, + "learning_rate": 8.00469809606234e-06, + "loss": 3.3317, + "step": 2565120 + }, + { + "epoch": 0.02, + "learning_rate": 7.99631214855182e-06, + "loss": 3.3287, + "step": 2565632 + }, + { + "epoch": 0.02, + "learning_rate": 7.987926201041298e-06, + "loss": 3.3324, + "step": 2566144 + }, + { + "epoch": 0.02, + "learning_rate": 7.97955663233451e-06, + "loss": 3.3378, + "step": 2566656 + }, + { + "epoch": 0.02, + "learning_rate": 7.97117068482399e-06, + "loss": 3.3366, + "step": 2567168 + }, + { + "epoch": 0.02, + "learning_rate": 7.96278473731347e-06, + "loss": 3.3394, + "step": 2567680 + }, + { + "epoch": 0.02, + "learning_rate": 7.95439878980295e-06, + "loss": 3.3227, + "step": 2568192 + }, + { + "epoch": 0.02, + "learning_rate": 7.94601284229243e-06, + "loss": 3.3421, + "step": 2568704 + }, + { + "epoch": 0.02, + "learning_rate": 7.93762689478191e-06, + "loss": 3.335, + "step": 2569216 + }, + { + "epoch": 0.02, + "learning_rate": 7.92924094727139e-06, + "loss": 3.3412, + "step": 2569728 + }, + { + "epoch": 0.02, + "learning_rate": 7.92085499976087e-06, + "loss": 3.3346, + "step": 2570240 + }, + { + "epoch": 0.02, + "learning_rate": 7.912501809857813e-06, + "loss": 3.3356, + "step": 2570752 + }, + { + "epoch": 0.02, + "learning_rate": 7.904115862347293e-06, + "loss": 3.338, + "step": 2571264 + }, + { + "epoch": 0.02, + "learning_rate": 7.895729914836772e-06, + "loss": 3.342, + "step": 2571776 + }, + { + "epoch": 0.02, + "learning_rate": 7.887343967326251e-06, + "loss": 3.3226, + "step": 2572288 + }, + { + "epoch": 0.02, + "learning_rate": 7.878974398619464e-06, + "loss": 3.3291, + "step": 2572800 + }, + { + "epoch": 0.02, + "learning_rate": 7.870588451108944e-06, + "loss": 3.3325, + "step": 2573312 + }, + { + "epoch": 0.02, + "learning_rate": 7.862202503598424e-06, + "loss": 3.3349, + "step": 2573824 + }, + { + "epoch": 0.02, + "learning_rate": 7.853816556087904e-06, + "loss": 3.3222, + "step": 2574336 + }, + { + "epoch": 0.02, + "learning_rate": 7.845430608577384e-06, + "loss": 3.3286, + "step": 2574848 + }, + { + "epoch": 0.02, + "learning_rate": 7.837044661066862e-06, + "loss": 3.3236, + "step": 2575360 + }, + { + "epoch": 0.02, + "learning_rate": 7.828658713556344e-06, + "loss": 3.3322, + "step": 2575872 + }, + { + "epoch": 0.02, + "learning_rate": 7.820289144849554e-06, + "loss": 3.3303, + "step": 2576384 + }, + { + "epoch": 0.02, + "learning_rate": 7.811903197339034e-06, + "loss": 3.3291, + "step": 2576896 + }, + { + "epoch": 0.02, + "learning_rate": 7.803517249828514e-06, + "loss": 3.3363, + "step": 2577408 + }, + { + "epoch": 0.02, + "learning_rate": 7.795131302317994e-06, + "loss": 3.3421, + "step": 2577920 + }, + { + "epoch": 0.02, + "learning_rate": 7.786745354807474e-06, + "loss": 3.3361, + "step": 2578432 + }, + { + "epoch": 0.02, + "learning_rate": 7.778359407296954e-06, + "loss": 3.3347, + "step": 2578944 + }, + { + "epoch": 0.02, + "learning_rate": 7.769989838590165e-06, + "loss": 3.3436, + "step": 2579456 + }, + { + "epoch": 0.02, + "learning_rate": 7.761603891079645e-06, + "loss": 3.3356, + "step": 2579968 + }, + { + "epoch": 0.02, + "learning_rate": 7.753217943569125e-06, + "loss": 3.3258, + "step": 2580480 + }, + { + "epoch": 0.02, + "learning_rate": 7.744831996058605e-06, + "loss": 3.3423, + "step": 2580992 + }, + { + "epoch": 0.02, + "learning_rate": 7.736446048548085e-06, + "loss": 3.3312, + "step": 2581504 + }, + { + "epoch": 0.02, + "learning_rate": 7.728076479841297e-06, + "loss": 3.3396, + "step": 2582016 + }, + { + "epoch": 0.02, + "learning_rate": 7.719690532330776e-06, + "loss": 3.3199, + "step": 2582528 + }, + { + "epoch": 0.02, + "learning_rate": 7.711304584820256e-06, + "loss": 3.3381, + "step": 2583040 + }, + { + "epoch": 0.02, + "learning_rate": 7.702918637309736e-06, + "loss": 3.3204, + "step": 2583552 + }, + { + "epoch": 0.02, + "learning_rate": 7.694549068602948e-06, + "loss": 3.3234, + "step": 2584064 + }, + { + "epoch": 0.02, + "learning_rate": 7.686163121092426e-06, + "loss": 3.3212, + "step": 2584576 + }, + { + "epoch": 0.02, + "learning_rate": 7.677777173581906e-06, + "loss": 3.3475, + "step": 2585088 + }, + { + "epoch": 0.02, + "learning_rate": 7.669391226071388e-06, + "loss": 3.3413, + "step": 2585600 + }, + { + "epoch": 0.02, + "learning_rate": 7.661005278560866e-06, + "loss": 3.3326, + "step": 2586112 + }, + { + "epoch": 0.02, + "learning_rate": 7.652619331050346e-06, + "loss": 3.3307, + "step": 2586624 + }, + { + "epoch": 0.02, + "learning_rate": 7.644233383539828e-06, + "loss": 3.3338, + "step": 2587136 + }, + { + "epoch": 0.02, + "learning_rate": 7.635847436029308e-06, + "loss": 3.3398, + "step": 2587648 + }, + { + "epoch": 0.02, + "learning_rate": 7.627477867322518e-06, + "loss": 3.3371, + "step": 2588160 + }, + { + "epoch": 0.02, + "learning_rate": 7.619091919811998e-06, + "loss": 3.3325, + "step": 2588672 + }, + { + "epoch": 0.02, + "learning_rate": 7.610705972301478e-06, + "loss": 3.3379, + "step": 2589184 + }, + { + "epoch": 0.02, + "learning_rate": 7.602320024790957e-06, + "loss": 3.3294, + "step": 2589696 + }, + { + "epoch": 0.02, + "learning_rate": 7.593950456084168e-06, + "loss": 3.3444, + "step": 2590208 + }, + { + "epoch": 0.02, + "learning_rate": 7.585564508573649e-06, + "loss": 3.3328, + "step": 2590720 + }, + { + "epoch": 0.02, + "learning_rate": 7.577178561063129e-06, + "loss": 3.3315, + "step": 2591232 + }, + { + "epoch": 0.02, + "learning_rate": 7.568792613552608e-06, + "loss": 3.3332, + "step": 2591744 + }, + { + "epoch": 0.02, + "learning_rate": 7.560406666042089e-06, + "loss": 3.3275, + "step": 2592256 + }, + { + "epoch": 0.02, + "learning_rate": 7.552020718531569e-06, + "loss": 3.3386, + "step": 2592768 + }, + { + "epoch": 0.02, + "learning_rate": 7.543634771021048e-06, + "loss": 3.3339, + "step": 2593280 + }, + { + "epoch": 0.02, + "learning_rate": 7.535248823510528e-06, + "loss": 3.3403, + "step": 2593792 + }, + { + "epoch": 0.02, + "learning_rate": 7.52687925480374e-06, + "loss": 3.3303, + "step": 2594304 + }, + { + "epoch": 0.02, + "learning_rate": 7.5184933072932204e-06, + "loss": 3.3274, + "step": 2594816 + }, + { + "epoch": 0.03, + "eval_loss": 3.8672103881835938, + "eval_runtime": 302.5771, + "eval_samples_per_second": 1261.136, + "eval_steps_per_second": 39.411, + "step": 2594880 + }, + { + "epoch": 1.0, + "learning_rate": 7.510107359782699e-06, + "loss": 3.325, + "step": 2595328 + }, + { + "epoch": 1.0, + "learning_rate": 7.5017214122721795e-06, + "loss": 3.3265, + "step": 2595840 + }, + { + "epoch": 1.0, + "learning_rate": 7.4933354647616594e-06, + "loss": 3.3375, + "step": 2596352 + }, + { + "epoch": 1.0, + "learning_rate": 7.4849495172511386e-06, + "loss": 3.3291, + "step": 2596864 + }, + { + "epoch": 1.0, + "learning_rate": 7.4765635697406185e-06, + "loss": 3.3506, + "step": 2597376 + }, + { + "epoch": 1.0, + "learning_rate": 7.468177622230099e-06, + "loss": 3.3238, + "step": 2597888 + }, + { + "epoch": 1.0, + "learning_rate": 7.459808053523311e-06, + "loss": 3.3334, + "step": 2598400 + }, + { + "epoch": 1.0, + "learning_rate": 7.45142210601279e-06, + "loss": 3.3207, + "step": 2598912 + }, + { + "epoch": 1.0, + "learning_rate": 7.443052537306002e-06, + "loss": 3.3357, + "step": 2599424 + }, + { + "epoch": 1.0, + "learning_rate": 7.434666589795482e-06, + "loss": 3.329, + "step": 2599936 + }, + { + "epoch": 1.0, + "learning_rate": 7.4262806422849625e-06, + "loss": 3.3339, + "step": 2600448 + }, + { + "epoch": 1.0, + "learning_rate": 7.417894694774441e-06, + "loss": 3.3284, + "step": 2600960 + }, + { + "epoch": 1.0, + "learning_rate": 7.4095087472639215e-06, + "loss": 3.3239, + "step": 2601472 + }, + { + "epoch": 1.0, + "learning_rate": 7.401139178557133e-06, + "loss": 3.3282, + "step": 2601984 + }, + { + "epoch": 1.0, + "learning_rate": 7.392753231046612e-06, + "loss": 3.3272, + "step": 2602496 + }, + { + "epoch": 1.0, + "learning_rate": 7.384367283536092e-06, + "loss": 3.3215, + "step": 2603008 + }, + { + "epoch": 1.0, + "learning_rate": 7.375981336025572e-06, + "loss": 3.3238, + "step": 2603520 + }, + { + "epoch": 1.0, + "learning_rate": 7.367611767318784e-06, + "loss": 3.3317, + "step": 2604032 + }, + { + "epoch": 1.0, + "learning_rate": 7.359225819808263e-06, + "loss": 3.3242, + "step": 2604544 + }, + { + "epoch": 1.0, + "learning_rate": 7.350839872297744e-06, + "loss": 3.3499, + "step": 2605056 + }, + { + "epoch": 1.0, + "learning_rate": 7.342453924787224e-06, + "loss": 3.3277, + "step": 2605568 + }, + { + "epoch": 1.0, + "learning_rate": 7.334067977276703e-06, + "loss": 3.3291, + "step": 2606080 + }, + { + "epoch": 1.0, + "learning_rate": 7.325682029766183e-06, + "loss": 3.331, + "step": 2606592 + }, + { + "epoch": 1.0, + "learning_rate": 7.3172960822556635e-06, + "loss": 3.3404, + "step": 2607104 + }, + { + "epoch": 1.0, + "learning_rate": 7.308926513548875e-06, + "loss": 3.3227, + "step": 2607616 + }, + { + "epoch": 1.0, + "learning_rate": 7.3005405660383534e-06, + "loss": 3.3351, + "step": 2608128 + }, + { + "epoch": 1.0, + "learning_rate": 7.292154618527834e-06, + "loss": 3.3256, + "step": 2608640 + }, + { + "epoch": 1.0, + "learning_rate": 7.283768671017314e-06, + "loss": 3.3301, + "step": 2609152 + }, + { + "epoch": 1.0, + "learning_rate": 7.275382723506793e-06, + "loss": 3.3153, + "step": 2609664 + }, + { + "epoch": 1.01, + "learning_rate": 7.266996775996274e-06, + "loss": 3.3212, + "step": 2610176 + }, + { + "epoch": 1.01, + "learning_rate": 7.258627207289486e-06, + "loss": 3.3331, + "step": 2610688 + }, + { + "epoch": 1.01, + "learning_rate": 7.250241259778966e-06, + "loss": 3.3322, + "step": 2611200 + }, + { + "epoch": 1.01, + "learning_rate": 7.241855312268445e-06, + "loss": 3.3329, + "step": 2611712 + }, + { + "epoch": 1.01, + "learning_rate": 7.233469364757925e-06, + "loss": 3.3363, + "step": 2612224 + }, + { + "epoch": 1.01, + "learning_rate": 7.2250834172474056e-06, + "loss": 3.3262, + "step": 2612736 + }, + { + "epoch": 1.01, + "learning_rate": 7.216697469736884e-06, + "loss": 3.3318, + "step": 2613248 + }, + { + "epoch": 1.01, + "learning_rate": 7.208311522226365e-06, + "loss": 3.327, + "step": 2613760 + }, + { + "epoch": 1.01, + "learning_rate": 7.199925574715845e-06, + "loss": 3.3363, + "step": 2614272 + }, + { + "epoch": 1.01, + "learning_rate": 7.191556006009056e-06, + "loss": 3.3199, + "step": 2614784 + }, + { + "epoch": 1.01, + "learning_rate": 7.183170058498535e-06, + "loss": 3.3254, + "step": 2615296 + }, + { + "epoch": 1.01, + "learning_rate": 7.174784110988015e-06, + "loss": 3.3272, + "step": 2615808 + }, + { + "epoch": 1.01, + "learning_rate": 7.166398163477496e-06, + "loss": 3.3394, + "step": 2616320 + }, + { + "epoch": 1.01, + "learning_rate": 7.158012215966975e-06, + "loss": 3.3292, + "step": 2616832 + }, + { + "epoch": 1.01, + "learning_rate": 7.149626268456455e-06, + "loss": 3.3279, + "step": 2617344 + }, + { + "epoch": 1.01, + "learning_rate": 7.141240320945935e-06, + "loss": 3.3386, + "step": 2617856 + }, + { + "epoch": 1.01, + "learning_rate": 7.132854373435414e-06, + "loss": 3.3327, + "step": 2618368 + }, + { + "epoch": 1.01, + "learning_rate": 7.124484804728626e-06, + "loss": 3.3283, + "step": 2618880 + }, + { + "epoch": 1.01, + "learning_rate": 7.116098857218107e-06, + "loss": 3.3138, + "step": 2619392 + }, + { + "epoch": 1.01, + "learning_rate": 7.107712909707587e-06, + "loss": 3.3158, + "step": 2619904 + }, + { + "epoch": 1.01, + "learning_rate": 7.099326962197066e-06, + "loss": 3.3291, + "step": 2620416 + }, + { + "epoch": 1.01, + "learning_rate": 7.090957393490277e-06, + "loss": 3.3322, + "step": 2620928 + }, + { + "epoch": 1.01, + "learning_rate": 7.082587824783489e-06, + "loss": 3.3258, + "step": 2621440 + }, + { + "epoch": 1.01, + "learning_rate": 7.074201877272969e-06, + "loss": 3.3083, + "step": 2621952 + }, + { + "epoch": 1.01, + "learning_rate": 7.065815929762448e-06, + "loss": 3.3175, + "step": 2622464 + }, + { + "epoch": 1.01, + "learning_rate": 7.057429982251929e-06, + "loss": 3.3175, + "step": 2622976 + }, + { + "epoch": 1.01, + "learning_rate": 7.049044034741409e-06, + "loss": 3.3298, + "step": 2623488 + }, + { + "epoch": 1.01, + "learning_rate": 7.040658087230888e-06, + "loss": 3.3199, + "step": 2624000 + }, + { + "epoch": 1.01, + "learning_rate": 7.032272139720368e-06, + "loss": 3.3292, + "step": 2624512 + }, + { + "epoch": 1.01, + "learning_rate": 7.023886192209849e-06, + "loss": 3.3271, + "step": 2625024 + }, + { + "epoch": 1.01, + "learning_rate": 7.01551662350306e-06, + "loss": 3.3175, + "step": 2625536 + }, + { + "epoch": 1.01, + "learning_rate": 7.007130675992539e-06, + "loss": 3.3251, + "step": 2626048 + }, + { + "epoch": 1.01, + "learning_rate": 6.998744728482019e-06, + "loss": 3.3189, + "step": 2626560 + }, + { + "epoch": 1.01, + "learning_rate": 6.990358780971499e-06, + "loss": 3.313, + "step": 2627072 + }, + { + "epoch": 1.01, + "learning_rate": 6.981989212264711e-06, + "loss": 3.3198, + "step": 2627584 + }, + { + "epoch": 1.01, + "learning_rate": 6.97360326475419e-06, + "loss": 3.324, + "step": 2628096 + }, + { + "epoch": 1.01, + "learning_rate": 6.965233696047402e-06, + "loss": 3.3329, + "step": 2628608 + }, + { + "epoch": 1.01, + "learning_rate": 6.9568477485368825e-06, + "loss": 3.3119, + "step": 2629120 + }, + { + "epoch": 1.01, + "learning_rate": 6.948461801026361e-06, + "loss": 3.3158, + "step": 2629632 + }, + { + "epoch": 1.01, + "learning_rate": 6.940075853515842e-06, + "loss": 3.3145, + "step": 2630144 + }, + { + "epoch": 1.01, + "learning_rate": 6.9316899060053216e-06, + "loss": 3.3372, + "step": 2630656 + }, + { + "epoch": 1.01, + "learning_rate": 6.923320337298533e-06, + "loss": 3.3269, + "step": 2631168 + }, + { + "epoch": 1.01, + "learning_rate": 6.914934389788012e-06, + "loss": 3.3261, + "step": 2631680 + }, + { + "epoch": 1.01, + "learning_rate": 6.906548442277492e-06, + "loss": 3.3425, + "step": 2632192 + }, + { + "epoch": 1.01, + "learning_rate": 6.898162494766973e-06, + "loss": 3.3346, + "step": 2632704 + }, + { + "epoch": 1.01, + "learning_rate": 6.889776547256452e-06, + "loss": 3.3385, + "step": 2633216 + }, + { + "epoch": 1.01, + "learning_rate": 6.881390599745932e-06, + "loss": 3.3275, + "step": 2633728 + }, + { + "epoch": 1.01, + "learning_rate": 6.873021031039144e-06, + "loss": 3.3297, + "step": 2634240 + }, + { + "epoch": 1.01, + "learning_rate": 6.864635083528624e-06, + "loss": 3.3288, + "step": 2634752 + }, + { + "epoch": 1.01, + "learning_rate": 6.856249136018103e-06, + "loss": 3.3268, + "step": 2635264 + }, + { + "epoch": 1.01, + "learning_rate": 6.847863188507584e-06, + "loss": 3.3282, + "step": 2635776 + }, + { + "epoch": 1.01, + "learning_rate": 6.839477240997064e-06, + "loss": 3.3306, + "step": 2636288 + }, + { + "epoch": 1.01, + "learning_rate": 6.831107672290275e-06, + "loss": 3.3365, + "step": 2636800 + }, + { + "epoch": 1.01, + "learning_rate": 6.822721724779754e-06, + "loss": 3.3215, + "step": 2637312 + }, + { + "epoch": 1.01, + "learning_rate": 6.814335777269234e-06, + "loss": 3.3217, + "step": 2637824 + }, + { + "epoch": 1.01, + "learning_rate": 6.805949829758715e-06, + "loss": 3.3109, + "step": 2638336 + }, + { + "epoch": 1.01, + "learning_rate": 6.797580261051925e-06, + "loss": 3.3292, + "step": 2638848 + }, + { + "epoch": 1.01, + "learning_rate": 6.789194313541406e-06, + "loss": 3.3341, + "step": 2639360 + }, + { + "epoch": 1.01, + "learning_rate": 6.780808366030886e-06, + "loss": 3.3222, + "step": 2639872 + }, + { + "epoch": 1.01, + "learning_rate": 6.772422418520366e-06, + "loss": 3.3249, + "step": 2640384 + }, + { + "epoch": 1.02, + "learning_rate": 6.764036471009845e-06, + "loss": 3.3333, + "step": 2640896 + }, + { + "epoch": 1.02, + "learning_rate": 6.7556669023030565e-06, + "loss": 3.316, + "step": 2641408 + }, + { + "epoch": 1.02, + "learning_rate": 6.747280954792537e-06, + "loss": 3.3239, + "step": 2641920 + }, + { + "epoch": 1.02, + "learning_rate": 6.7388950072820156e-06, + "loss": 3.3227, + "step": 2642432 + }, + { + "epoch": 1.02, + "learning_rate": 6.730509059771496e-06, + "loss": 3.3311, + "step": 2642944 + }, + { + "epoch": 1.02, + "learning_rate": 6.722123112260976e-06, + "loss": 3.3293, + "step": 2643456 + }, + { + "epoch": 1.02, + "learning_rate": 6.713737164750457e-06, + "loss": 3.3283, + "step": 2643968 + }, + { + "epoch": 1.02, + "learning_rate": 6.705351217239935e-06, + "loss": 3.3152, + "step": 2644480 + }, + { + "epoch": 1.02, + "learning_rate": 6.696965269729416e-06, + "loss": 3.333, + "step": 2644992 + }, + { + "epoch": 1.02, + "learning_rate": 6.688595701022628e-06, + "loss": 3.3208, + "step": 2645504 + }, + { + "epoch": 1.02, + "learning_rate": 6.680209753512107e-06, + "loss": 3.3347, + "step": 2646016 + }, + { + "epoch": 1.02, + "learning_rate": 6.671823806001587e-06, + "loss": 3.3254, + "step": 2646528 + }, + { + "epoch": 1.02, + "learning_rate": 6.6634542372947985e-06, + "loss": 3.3287, + "step": 2647040 + }, + { + "epoch": 1.02, + "learning_rate": 6.655068289784279e-06, + "loss": 3.3245, + "step": 2647552 + }, + { + "epoch": 1.02, + "learning_rate": 6.646682342273758e-06, + "loss": 3.3361, + "step": 2648064 + }, + { + "epoch": 1.02, + "learning_rate": 6.638296394763238e-06, + "loss": 3.3102, + "step": 2648576 + }, + { + "epoch": 1.02, + "learning_rate": 6.62992682605645e-06, + "loss": 3.3201, + "step": 2649088 + }, + { + "epoch": 1.02, + "learning_rate": 6.621540878545929e-06, + "loss": 3.3241, + "step": 2649600 + }, + { + "epoch": 1.02, + "learning_rate": 6.613154931035409e-06, + "loss": 3.325, + "step": 2650112 + }, + { + "epoch": 1.02, + "learning_rate": 6.604768983524889e-06, + "loss": 3.3113, + "step": 2650624 + }, + { + "epoch": 1.02, + "learning_rate": 6.59638303601437e-06, + "loss": 3.3225, + "step": 2651136 + }, + { + "epoch": 1.02, + "learning_rate": 6.587997088503849e-06, + "loss": 3.3129, + "step": 2651648 + }, + { + "epoch": 1.02, + "learning_rate": 6.579611140993329e-06, + "loss": 3.3257, + "step": 2652160 + }, + { + "epoch": 1.02, + "learning_rate": 6.5712415722865406e-06, + "loss": 3.3202, + "step": 2652672 + }, + { + "epoch": 1.02, + "learning_rate": 6.56285562477602e-06, + "loss": 3.3169, + "step": 2653184 + }, + { + "epoch": 1.02, + "learning_rate": 6.5544696772655e-06, + "loss": 3.3305, + "step": 2653696 + }, + { + "epoch": 1.02, + "learning_rate": 6.54608372975498e-06, + "loss": 3.3331, + "step": 2654208 + }, + { + "epoch": 1.02, + "learning_rate": 6.53769778224446e-06, + "loss": 3.3311, + "step": 2654720 + }, + { + "epoch": 1.02, + "learning_rate": 6.5293118347339395e-06, + "loss": 3.3206, + "step": 2655232 + }, + { + "epoch": 1.02, + "learning_rate": 6.520942266027151e-06, + "loss": 3.3355, + "step": 2655744 + }, + { + "epoch": 1.02, + "learning_rate": 6.512556318516631e-06, + "loss": 3.3249, + "step": 2656256 + }, + { + "epoch": 1.02, + "learning_rate": 6.50417037100611e-06, + "loss": 3.3185, + "step": 2656768 + }, + { + "epoch": 1.02, + "learning_rate": 6.495784423495591e-06, + "loss": 3.3358, + "step": 2657280 + }, + { + "epoch": 1.02, + "learning_rate": 6.487414854788803e-06, + "loss": 3.319, + "step": 2657792 + }, + { + "epoch": 1.02, + "learning_rate": 6.479028907278283e-06, + "loss": 3.3331, + "step": 2658304 + }, + { + "epoch": 1.02, + "learning_rate": 6.470642959767762e-06, + "loss": 3.3134, + "step": 2658816 + }, + { + "epoch": 1.02, + "learning_rate": 6.462257012257242e-06, + "loss": 3.3276, + "step": 2659328 + }, + { + "epoch": 1.02, + "learning_rate": 6.4538710647467225e-06, + "loss": 3.3129, + "step": 2659840 + }, + { + "epoch": 1.02, + "learning_rate": 6.445485117236201e-06, + "loss": 3.3142, + "step": 2660352 + }, + { + "epoch": 1.02, + "learning_rate": 6.437115548529412e-06, + "loss": 3.3149, + "step": 2660864 + }, + { + "epoch": 1.02, + "learning_rate": 6.428729601018893e-06, + "loss": 3.3358, + "step": 2661376 + }, + { + "epoch": 1.02, + "learning_rate": 6.420343653508373e-06, + "loss": 3.332, + "step": 2661888 + }, + { + "epoch": 1.02, + "learning_rate": 6.411957705997852e-06, + "loss": 3.3276, + "step": 2662400 + }, + { + "epoch": 1.02, + "learning_rate": 6.403571758487332e-06, + "loss": 3.3239, + "step": 2662912 + }, + { + "epoch": 1.02, + "learning_rate": 6.395185810976813e-06, + "loss": 3.3228, + "step": 2663424 + }, + { + "epoch": 1.02, + "learning_rate": 6.386799863466292e-06, + "loss": 3.3357, + "step": 2663936 + }, + { + "epoch": 1.02, + "learning_rate": 6.378430294759504e-06, + "loss": 3.3249, + "step": 2664448 + }, + { + "epoch": 1.02, + "learning_rate": 6.370044347248984e-06, + "loss": 3.3225, + "step": 2664960 + }, + { + "epoch": 1.02, + "learning_rate": 6.3616583997384645e-06, + "loss": 3.3308, + "step": 2665472 + }, + { + "epoch": 1.02, + "learning_rate": 6.353272452227943e-06, + "loss": 3.3233, + "step": 2665984 + }, + { + "epoch": 1.02, + "learning_rate": 6.344902883521154e-06, + "loss": 3.332, + "step": 2666496 + }, + { + "epoch": 1.02, + "learning_rate": 6.336516936010635e-06, + "loss": 3.3238, + "step": 2667008 + }, + { + "epoch": 1.02, + "learning_rate": 6.328130988500115e-06, + "loss": 3.3222, + "step": 2667520 + }, + { + "epoch": 1.02, + "learning_rate": 6.319745040989594e-06, + "loss": 3.3241, + "step": 2668032 + }, + { + "epoch": 1.02, + "learning_rate": 6.311359093479074e-06, + "loss": 3.3226, + "step": 2668544 + }, + { + "epoch": 1.02, + "learning_rate": 6.302973145968555e-06, + "loss": 3.3233, + "step": 2669056 + }, + { + "epoch": 1.02, + "learning_rate": 6.294587198458034e-06, + "loss": 3.3309, + "step": 2669568 + }, + { + "epoch": 1.02, + "learning_rate": 6.286201250947514e-06, + "loss": 3.3262, + "step": 2670080 + }, + { + "epoch": 1.02, + "learning_rate": 6.277848061044457e-06, + "loss": 3.3207, + "step": 2670592 + }, + { + "epoch": 1.02, + "learning_rate": 6.269462113533937e-06, + "loss": 3.3177, + "step": 2671104 + }, + { + "epoch": 1.03, + "eval_loss": 3.867680072784424, + "eval_runtime": 302.4852, + "eval_samples_per_second": 1261.52, + "eval_steps_per_second": 39.423, + "step": 2671200 + }, + { + "epoch": 0.0, + "learning_rate": 6.2610761660234165e-06, + "loss": 3.3156, + "step": 2671616 + }, + { + "epoch": 0.0, + "learning_rate": 6.252690218512896e-06, + "loss": 3.3176, + "step": 2672128 + }, + { + "epoch": 0.0, + "learning_rate": 6.244304271002376e-06, + "loss": 3.3298, + "step": 2672640 + }, + { + "epoch": 0.0, + "learning_rate": 6.235918323491856e-06, + "loss": 3.3178, + "step": 2673152 + }, + { + "epoch": 0.0, + "learning_rate": 6.227548754785067e-06, + "loss": 3.3417, + "step": 2673664 + }, + { + "epoch": 0.0, + "learning_rate": 6.219162807274548e-06, + "loss": 3.3117, + "step": 2674176 + }, + { + "epoch": 0.0, + "learning_rate": 6.210776859764027e-06, + "loss": 3.3241, + "step": 2674688 + }, + { + "epoch": 0.0, + "learning_rate": 6.202390912253508e-06, + "loss": 3.3117, + "step": 2675200 + }, + { + "epoch": 0.0, + "learning_rate": 6.19403772235045e-06, + "loss": 3.3273, + "step": 2675712 + }, + { + "epoch": 0.0, + "learning_rate": 6.18565177483993e-06, + "loss": 3.3215, + "step": 2676224 + }, + { + "epoch": 0.0, + "learning_rate": 6.17726582732941e-06, + "loss": 3.3213, + "step": 2676736 + }, + { + "epoch": 0.0, + "learning_rate": 6.16887987981889e-06, + "loss": 3.323, + "step": 2677248 + }, + { + "epoch": 0.0, + "learning_rate": 6.160510311112101e-06, + "loss": 3.3143, + "step": 2677760 + }, + { + "epoch": 0.0, + "learning_rate": 6.152124363601582e-06, + "loss": 3.3188, + "step": 2678272 + }, + { + "epoch": 0.0, + "learning_rate": 6.143738416091061e-06, + "loss": 3.3179, + "step": 2678784 + }, + { + "epoch": 0.0, + "learning_rate": 6.135352468580541e-06, + "loss": 3.3163, + "step": 2679296 + }, + { + "epoch": 0.0, + "learning_rate": 6.126966521070021e-06, + "loss": 3.3143, + "step": 2679808 + }, + { + "epoch": 0.0, + "learning_rate": 6.118596952363232e-06, + "loss": 3.3207, + "step": 2680320 + }, + { + "epoch": 0.0, + "learning_rate": 6.110211004852712e-06, + "loss": 3.3194, + "step": 2680832 + }, + { + "epoch": 0.0, + "learning_rate": 6.101825057342192e-06, + "loss": 3.3345, + "step": 2681344 + }, + { + "epoch": 0.0, + "learning_rate": 6.093439109831672e-06, + "loss": 3.3198, + "step": 2681856 + }, + { + "epoch": 0.0, + "learning_rate": 6.085053162321152e-06, + "loss": 3.3203, + "step": 2682368 + }, + { + "epoch": 0.0, + "learning_rate": 6.076667214810631e-06, + "loss": 3.3219, + "step": 2682880 + }, + { + "epoch": 0.0, + "learning_rate": 6.068281267300112e-06, + "loss": 3.3303, + "step": 2683392 + }, + { + "epoch": 0.0, + "learning_rate": 6.059895319789591e-06, + "loss": 3.3148, + "step": 2683904 + }, + { + "epoch": 0.0, + "learning_rate": 6.051525751082803e-06, + "loss": 3.3284, + "step": 2684416 + }, + { + "epoch": 0.0, + "learning_rate": 6.043156182376014e-06, + "loss": 3.3176, + "step": 2684928 + }, + { + "epoch": 0.0, + "learning_rate": 6.0347702348654945e-06, + "loss": 3.3186, + "step": 2685440 + }, + { + "epoch": 0.0, + "learning_rate": 6.0263842873549744e-06, + "loss": 3.3057, + "step": 2685952 + }, + { + "epoch": 0.01, + "learning_rate": 6.017998339844454e-06, + "loss": 3.319, + "step": 2686464 + }, + { + "epoch": 0.01, + "learning_rate": 6.009612392333934e-06, + "loss": 3.3209, + "step": 2686976 + }, + { + "epoch": 0.01, + "learning_rate": 6.0012264448234135e-06, + "loss": 3.3235, + "step": 2687488 + }, + { + "epoch": 0.01, + "learning_rate": 5.992856876116625e-06, + "loss": 3.3224, + "step": 2688000 + }, + { + "epoch": 0.01, + "learning_rate": 5.984470928606105e-06, + "loss": 3.3271, + "step": 2688512 + }, + { + "epoch": 0.01, + "learning_rate": 5.976084981095585e-06, + "loss": 3.3165, + "step": 2689024 + }, + { + "epoch": 0.01, + "learning_rate": 5.967699033585065e-06, + "loss": 3.325, + "step": 2689536 + }, + { + "epoch": 0.01, + "learning_rate": 5.959313086074545e-06, + "loss": 3.3194, + "step": 2690048 + }, + { + "epoch": 0.01, + "learning_rate": 5.950927138564025e-06, + "loss": 3.3277, + "step": 2690560 + }, + { + "epoch": 0.01, + "learning_rate": 5.9425575698572365e-06, + "loss": 3.3114, + "step": 2691072 + }, + { + "epoch": 0.01, + "learning_rate": 5.934171622346716e-06, + "loss": 3.3158, + "step": 2691584 + }, + { + "epoch": 0.01, + "learning_rate": 5.925785674836196e-06, + "loss": 3.3189, + "step": 2692096 + }, + { + "epoch": 0.01, + "learning_rate": 5.9173997273256755e-06, + "loss": 3.33, + "step": 2692608 + }, + { + "epoch": 0.01, + "learning_rate": 5.9090137798151555e-06, + "loss": 3.3196, + "step": 2693120 + }, + { + "epoch": 0.01, + "learning_rate": 5.9006278323046354e-06, + "loss": 3.3192, + "step": 2693632 + }, + { + "epoch": 0.01, + "learning_rate": 5.892241884794115e-06, + "loss": 3.3272, + "step": 2694144 + }, + { + "epoch": 0.01, + "learning_rate": 5.883855937283595e-06, + "loss": 3.3223, + "step": 2694656 + }, + { + "epoch": 0.01, + "learning_rate": 5.875486368576807e-06, + "loss": 3.3193, + "step": 2695168 + }, + { + "epoch": 0.01, + "learning_rate": 5.867100421066286e-06, + "loss": 3.31, + "step": 2695680 + }, + { + "epoch": 0.01, + "learning_rate": 5.858714473555767e-06, + "loss": 3.2994, + "step": 2696192 + }, + { + "epoch": 0.01, + "learning_rate": 5.850328526045246e-06, + "loss": 3.3218, + "step": 2696704 + }, + { + "epoch": 0.01, + "learning_rate": 5.841958957338458e-06, + "loss": 3.3207, + "step": 2697216 + }, + { + "epoch": 0.01, + "learning_rate": 5.833589388631669e-06, + "loss": 3.3157, + "step": 2697728 + }, + { + "epoch": 0.01, + "learning_rate": 5.825203441121149e-06, + "loss": 3.3059, + "step": 2698240 + }, + { + "epoch": 0.01, + "learning_rate": 5.816817493610629e-06, + "loss": 3.3062, + "step": 2698752 + }, + { + "epoch": 0.01, + "learning_rate": 5.808431546100109e-06, + "loss": 3.3039, + "step": 2699264 + }, + { + "epoch": 0.01, + "learning_rate": 5.800045598589589e-06, + "loss": 3.3198, + "step": 2699776 + }, + { + "epoch": 0.01, + "learning_rate": 5.791659651079068e-06, + "loss": 3.3124, + "step": 2700288 + }, + { + "epoch": 0.01, + "learning_rate": 5.783273703568549e-06, + "loss": 3.3168, + "step": 2700800 + }, + { + "epoch": 0.01, + "learning_rate": 5.77490413486176e-06, + "loss": 3.3237, + "step": 2701312 + }, + { + "epoch": 0.01, + "learning_rate": 5.76651818735124e-06, + "loss": 3.3099, + "step": 2701824 + }, + { + "epoch": 0.01, + "learning_rate": 5.75813223984072e-06, + "loss": 3.3149, + "step": 2702336 + }, + { + "epoch": 0.01, + "learning_rate": 5.749746292330199e-06, + "loss": 3.3171, + "step": 2702848 + }, + { + "epoch": 0.01, + "learning_rate": 5.74136034481968e-06, + "loss": 3.3001, + "step": 2703360 + }, + { + "epoch": 0.01, + "learning_rate": 5.7329907761128904e-06, + "loss": 3.314, + "step": 2703872 + }, + { + "epoch": 0.01, + "learning_rate": 5.724604828602371e-06, + "loss": 3.319, + "step": 2704384 + }, + { + "epoch": 0.01, + "learning_rate": 5.71621888109185e-06, + "loss": 3.3196, + "step": 2704896 + }, + { + "epoch": 0.01, + "learning_rate": 5.707832933581331e-06, + "loss": 3.3043, + "step": 2705408 + }, + { + "epoch": 0.01, + "learning_rate": 5.69944698607081e-06, + "loss": 3.3082, + "step": 2705920 + }, + { + "epoch": 0.01, + "learning_rate": 5.69106103856029e-06, + "loss": 3.3045, + "step": 2706432 + }, + { + "epoch": 0.01, + "learning_rate": 5.68267509104977e-06, + "loss": 3.3244, + "step": 2706944 + }, + { + "epoch": 0.01, + "learning_rate": 5.67428914353925e-06, + "loss": 3.3182, + "step": 2707456 + }, + { + "epoch": 0.01, + "learning_rate": 5.665919574832462e-06, + "loss": 3.3192, + "step": 2707968 + }, + { + "epoch": 0.01, + "learning_rate": 5.6575500061256725e-06, + "loss": 3.3312, + "step": 2708480 + }, + { + "epoch": 0.01, + "learning_rate": 5.6491640586151525e-06, + "loss": 3.3254, + "step": 2708992 + }, + { + "epoch": 0.01, + "learning_rate": 5.6407781111046325e-06, + "loss": 3.3338, + "step": 2709504 + }, + { + "epoch": 0.01, + "learning_rate": 5.632392163594112e-06, + "loss": 3.3138, + "step": 2710016 + }, + { + "epoch": 0.01, + "learning_rate": 5.624006216083592e-06, + "loss": 3.3225, + "step": 2710528 + }, + { + "epoch": 0.01, + "learning_rate": 5.615620268573072e-06, + "loss": 3.3224, + "step": 2711040 + }, + { + "epoch": 0.01, + "learning_rate": 5.607250699866284e-06, + "loss": 3.3151, + "step": 2711552 + }, + { + "epoch": 0.01, + "learning_rate": 5.598864752355763e-06, + "loss": 3.3243, + "step": 2712064 + }, + { + "epoch": 0.01, + "learning_rate": 5.590478804845244e-06, + "loss": 3.3209, + "step": 2712576 + }, + { + "epoch": 0.01, + "learning_rate": 5.582092857334723e-06, + "loss": 3.3236, + "step": 2713088 + }, + { + "epoch": 0.01, + "learning_rate": 5.573706909824204e-06, + "loss": 3.3158, + "step": 2713600 + }, + { + "epoch": 0.01, + "learning_rate": 5.565320962313683e-06, + "loss": 3.3078, + "step": 2714112 + }, + { + "epoch": 0.01, + "learning_rate": 5.5569513936068945e-06, + "loss": 3.3064, + "step": 2714624 + }, + { + "epoch": 0.01, + "learning_rate": 5.5485654460963745e-06, + "loss": 3.3218, + "step": 2715136 + }, + { + "epoch": 0.01, + "learning_rate": 5.5401794985858544e-06, + "loss": 3.3262, + "step": 2715648 + }, + { + "epoch": 0.01, + "learning_rate": 5.531793551075334e-06, + "loss": 3.3161, + "step": 2716160 + }, + { + "epoch": 0.01, + "learning_rate": 5.523407603564814e-06, + "loss": 3.315, + "step": 2716672 + }, + { + "epoch": 0.02, + "learning_rate": 5.515038034858026e-06, + "loss": 3.3243, + "step": 2717184 + }, + { + "epoch": 0.02, + "learning_rate": 5.506652087347505e-06, + "loss": 3.3117, + "step": 2717696 + }, + { + "epoch": 0.02, + "learning_rate": 5.498266139836986e-06, + "loss": 3.3102, + "step": 2718208 + }, + { + "epoch": 0.02, + "learning_rate": 5.489880192326465e-06, + "loss": 3.3154, + "step": 2718720 + }, + { + "epoch": 0.02, + "learning_rate": 5.481510623619677e-06, + "loss": 3.3224, + "step": 2719232 + }, + { + "epoch": 0.02, + "learning_rate": 5.473124676109157e-06, + "loss": 3.3228, + "step": 2719744 + }, + { + "epoch": 0.02, + "learning_rate": 5.464738728598636e-06, + "loss": 3.317, + "step": 2720256 + }, + { + "epoch": 0.02, + "learning_rate": 5.4563527810881165e-06, + "loss": 3.3033, + "step": 2720768 + }, + { + "epoch": 0.02, + "learning_rate": 5.447966833577596e-06, + "loss": 3.3247, + "step": 2721280 + }, + { + "epoch": 0.02, + "learning_rate": 5.4395808860670764e-06, + "loss": 3.3108, + "step": 2721792 + }, + { + "epoch": 0.02, + "learning_rate": 5.4311949385565555e-06, + "loss": 3.3298, + "step": 2722304 + }, + { + "epoch": 0.02, + "learning_rate": 5.4228089910460355e-06, + "loss": 3.3189, + "step": 2722816 + }, + { + "epoch": 0.02, + "learning_rate": 5.414455801142979e-06, + "loss": 3.3185, + "step": 2723328 + }, + { + "epoch": 0.02, + "learning_rate": 5.406069853632459e-06, + "loss": 3.3126, + "step": 2723840 + }, + { + "epoch": 0.02, + "learning_rate": 5.397683906121939e-06, + "loss": 3.3256, + "step": 2724352 + }, + { + "epoch": 0.02, + "learning_rate": 5.389297958611418e-06, + "loss": 3.3065, + "step": 2724864 + }, + { + "epoch": 0.02, + "learning_rate": 5.3809283899046295e-06, + "loss": 3.3123, + "step": 2725376 + }, + { + "epoch": 0.02, + "learning_rate": 5.3725424423941094e-06, + "loss": 3.3096, + "step": 2725888 + }, + { + "epoch": 0.02, + "learning_rate": 5.364156494883589e-06, + "loss": 3.3175, + "step": 2726400 + }, + { + "epoch": 0.02, + "learning_rate": 5.355770547373069e-06, + "loss": 3.3034, + "step": 2726912 + }, + { + "epoch": 0.02, + "learning_rate": 5.347384599862549e-06, + "loss": 3.3168, + "step": 2727424 + }, + { + "epoch": 0.02, + "learning_rate": 5.338998652352029e-06, + "loss": 3.3085, + "step": 2727936 + }, + { + "epoch": 0.02, + "learning_rate": 5.330612704841509e-06, + "loss": 3.3096, + "step": 2728448 + }, + { + "epoch": 0.02, + "learning_rate": 5.322243136134721e-06, + "loss": 3.3125, + "step": 2728960 + }, + { + "epoch": 0.02, + "learning_rate": 5.3138571886242e-06, + "loss": 3.3073, + "step": 2729472 + }, + { + "epoch": 0.02, + "learning_rate": 5.305471241113681e-06, + "loss": 3.3235, + "step": 2729984 + }, + { + "epoch": 0.02, + "learning_rate": 5.29708529360316e-06, + "loss": 3.3247, + "step": 2730496 + }, + { + "epoch": 0.02, + "learning_rate": 5.288699346092641e-06, + "loss": 3.3204, + "step": 2731008 + }, + { + "epoch": 0.02, + "learning_rate": 5.28031339858212e-06, + "loss": 3.3118, + "step": 2731520 + }, + { + "epoch": 0.02, + "learning_rate": 5.271943829875331e-06, + "loss": 3.3247, + "step": 2732032 + }, + { + "epoch": 0.02, + "learning_rate": 5.263557882364811e-06, + "loss": 3.3218, + "step": 2732544 + }, + { + "epoch": 0.02, + "learning_rate": 5.255171934854291e-06, + "loss": 3.3064, + "step": 2733056 + }, + { + "epoch": 0.02, + "learning_rate": 5.246785987343771e-06, + "loss": 3.3249, + "step": 2733568 + }, + { + "epoch": 0.02, + "learning_rate": 5.238400039833251e-06, + "loss": 3.3114, + "step": 2734080 + }, + { + "epoch": 0.02, + "learning_rate": 5.230030471126463e-06, + "loss": 3.323, + "step": 2734592 + }, + { + "epoch": 0.02, + "learning_rate": 5.221644523615942e-06, + "loss": 3.3067, + "step": 2735104 + }, + { + "epoch": 0.02, + "learning_rate": 5.213258576105423e-06, + "loss": 3.3185, + "step": 2735616 + }, + { + "epoch": 0.02, + "learning_rate": 5.204872628594902e-06, + "loss": 3.3028, + "step": 2736128 + }, + { + "epoch": 0.02, + "learning_rate": 5.196486681084382e-06, + "loss": 3.3088, + "step": 2736640 + }, + { + "epoch": 0.02, + "learning_rate": 5.1881171123775935e-06, + "loss": 3.3084, + "step": 2737152 + }, + { + "epoch": 0.02, + "learning_rate": 5.179731164867073e-06, + "loss": 3.3227, + "step": 2737664 + }, + { + "epoch": 0.02, + "learning_rate": 5.171345217356553e-06, + "loss": 3.318, + "step": 2738176 + }, + { + "epoch": 0.02, + "learning_rate": 5.1629592698460325e-06, + "loss": 3.3229, + "step": 2738688 + }, + { + "epoch": 0.02, + "learning_rate": 5.1545733223355125e-06, + "loss": 3.3149, + "step": 2739200 + }, + { + "epoch": 0.02, + "learning_rate": 5.146187374824992e-06, + "loss": 3.3172, + "step": 2739712 + }, + { + "epoch": 0.02, + "learning_rate": 5.137801427314472e-06, + "loss": 3.3227, + "step": 2740224 + }, + { + "epoch": 0.02, + "learning_rate": 5.129431858607684e-06, + "loss": 3.3206, + "step": 2740736 + }, + { + "epoch": 0.02, + "learning_rate": 5.121045911097164e-06, + "loss": 3.3148, + "step": 2741248 + }, + { + "epoch": 0.02, + "learning_rate": 5.112659963586644e-06, + "loss": 3.322, + "step": 2741760 + }, + { + "epoch": 0.02, + "learning_rate": 5.104274016076124e-06, + "loss": 3.3137, + "step": 2742272 + }, + { + "epoch": 0.02, + "learning_rate": 5.0959044473693355e-06, + "loss": 3.325, + "step": 2742784 + }, + { + "epoch": 0.02, + "learning_rate": 5.087518499858815e-06, + "loss": 3.3104, + "step": 2743296 + }, + { + "epoch": 0.02, + "learning_rate": 5.0791325523482946e-06, + "loss": 3.3187, + "step": 2743808 + }, + { + "epoch": 0.02, + "learning_rate": 5.0707466048377745e-06, + "loss": 3.3147, + "step": 2744320 + }, + { + "epoch": 0.02, + "learning_rate": 5.062377036130986e-06, + "loss": 3.3134, + "step": 2744832 + }, + { + "epoch": 0.02, + "learning_rate": 5.053991088620466e-06, + "loss": 3.3184, + "step": 2745344 + }, + { + "epoch": 0.02, + "learning_rate": 5.045605141109946e-06, + "loss": 3.3193, + "step": 2745856 + }, + { + "epoch": 0.02, + "learning_rate": 5.037219193599426e-06, + "loss": 3.3189, + "step": 2746368 + }, + { + "epoch": 0.02, + "learning_rate": 5.028833246088906e-06, + "loss": 3.3089, + "step": 2746880 + }, + { + "epoch": 0.02, + "learning_rate": 5.020463677382118e-06, + "loss": 3.3143, + "step": 2747392 + }, + { + "epoch": 0.03, + "eval_loss": 3.8677570819854736, + "eval_runtime": 302.5853, + "eval_samples_per_second": 1261.102, + "eval_steps_per_second": 39.41, + "step": 2747520 + }, + { + "epoch": 1.0, + "learning_rate": 5.012077729871597e-06, + "loss": 3.3096, + "step": 2747904 + }, + { + "epoch": 1.0, + "learning_rate": 5.003691782361077e-06, + "loss": 3.3099, + "step": 2748416 + }, + { + "epoch": 1.0, + "learning_rate": 4.995305834850557e-06, + "loss": 3.3183, + "step": 2748928 + }, + { + "epoch": 1.0, + "learning_rate": 4.986919887340037e-06, + "loss": 3.3108, + "step": 2749440 + }, + { + "epoch": 1.0, + "learning_rate": 4.978550318633248e-06, + "loss": 3.3319, + "step": 2749952 + }, + { + "epoch": 1.0, + "learning_rate": 4.970164371122727e-06, + "loss": 3.31, + "step": 2750464 + }, + { + "epoch": 1.0, + "learning_rate": 4.961778423612208e-06, + "loss": 3.3128, + "step": 2750976 + }, + { + "epoch": 1.0, + "learning_rate": 4.953392476101688e-06, + "loss": 3.3018, + "step": 2751488 + }, + { + "epoch": 1.0, + "learning_rate": 4.9450229073949e-06, + "loss": 3.316, + "step": 2752000 + }, + { + "epoch": 1.0, + "learning_rate": 4.936636959884379e-06, + "loss": 3.3191, + "step": 2752512 + }, + { + "epoch": 1.0, + "learning_rate": 4.928251012373859e-06, + "loss": 3.3099, + "step": 2753024 + }, + { + "epoch": 1.0, + "learning_rate": 4.919865064863339e-06, + "loss": 3.3102, + "step": 2753536 + }, + { + "epoch": 1.0, + "learning_rate": 4.911479117352819e-06, + "loss": 3.3073, + "step": 2754048 + }, + { + "epoch": 1.0, + "learning_rate": 4.90310954864603e-06, + "loss": 3.3115, + "step": 2754560 + }, + { + "epoch": 1.0, + "learning_rate": 4.8947236011355095e-06, + "loss": 3.3119, + "step": 2755072 + }, + { + "epoch": 1.0, + "learning_rate": 4.88633765362499e-06, + "loss": 3.3074, + "step": 2755584 + }, + { + "epoch": 1.0, + "learning_rate": 4.877951706114469e-06, + "loss": 3.304, + "step": 2756096 + }, + { + "epoch": 1.0, + "learning_rate": 4.869565758603949e-06, + "loss": 3.315, + "step": 2756608 + }, + { + "epoch": 1.0, + "learning_rate": 4.861179811093429e-06, + "loss": 3.3096, + "step": 2757120 + }, + { + "epoch": 1.0, + "learning_rate": 4.852793863582909e-06, + "loss": 3.3235, + "step": 2757632 + }, + { + "epoch": 1.0, + "learning_rate": 4.844407916072389e-06, + "loss": 3.3149, + "step": 2758144 + }, + { + "epoch": 1.0, + "learning_rate": 4.836038347365601e-06, + "loss": 3.314, + "step": 2758656 + }, + { + "epoch": 1.0, + "learning_rate": 4.827652399855081e-06, + "loss": 3.3099, + "step": 2759168 + }, + { + "epoch": 1.0, + "learning_rate": 4.819266452344561e-06, + "loss": 3.3219, + "step": 2759680 + }, + { + "epoch": 1.0, + "learning_rate": 4.810896883637772e-06, + "loss": 3.3067, + "step": 2760192 + }, + { + "epoch": 1.0, + "learning_rate": 4.8025109361272515e-06, + "loss": 3.3173, + "step": 2760704 + }, + { + "epoch": 1.0, + "learning_rate": 4.7941249886167315e-06, + "loss": 3.3108, + "step": 2761216 + }, + { + "epoch": 1.0, + "learning_rate": 4.785739041106211e-06, + "loss": 3.305, + "step": 2761728 + }, + { + "epoch": 1.0, + "learning_rate": 4.777353093595691e-06, + "loss": 3.2983, + "step": 2762240 + }, + { + "epoch": 1.0, + "learning_rate": 4.768967146085171e-06, + "loss": 3.3075, + "step": 2762752 + }, + { + "epoch": 1.01, + "learning_rate": 4.760597577378383e-06, + "loss": 3.3177, + "step": 2763264 + }, + { + "epoch": 1.01, + "learning_rate": 4.752211629867863e-06, + "loss": 3.3136, + "step": 2763776 + }, + { + "epoch": 1.01, + "learning_rate": 4.743825682357343e-06, + "loss": 3.317, + "step": 2764288 + }, + { + "epoch": 1.01, + "learning_rate": 4.735439734846822e-06, + "loss": 3.3161, + "step": 2764800 + }, + { + "epoch": 1.01, + "learning_rate": 4.727053787336303e-06, + "loss": 3.3061, + "step": 2765312 + }, + { + "epoch": 1.01, + "learning_rate": 4.718667839825782e-06, + "loss": 3.3133, + "step": 2765824 + }, + { + "epoch": 1.01, + "learning_rate": 4.710281892315263e-06, + "loss": 3.3127, + "step": 2766336 + }, + { + "epoch": 1.01, + "learning_rate": 4.701895944804742e-06, + "loss": 3.3168, + "step": 2766848 + }, + { + "epoch": 1.01, + "learning_rate": 4.6935263760979534e-06, + "loss": 3.3041, + "step": 2767360 + }, + { + "epoch": 1.01, + "learning_rate": 4.685140428587433e-06, + "loss": 3.3082, + "step": 2767872 + }, + { + "epoch": 1.01, + "learning_rate": 4.6767544810769125e-06, + "loss": 3.3089, + "step": 2768384 + }, + { + "epoch": 1.01, + "learning_rate": 4.668368533566393e-06, + "loss": 3.3234, + "step": 2768896 + }, + { + "epoch": 1.01, + "learning_rate": 4.659998964859604e-06, + "loss": 3.3127, + "step": 2769408 + }, + { + "epoch": 1.01, + "learning_rate": 4.651613017349085e-06, + "loss": 3.3109, + "step": 2769920 + }, + { + "epoch": 1.01, + "learning_rate": 4.643243448642296e-06, + "loss": 3.3226, + "step": 2770432 + }, + { + "epoch": 1.01, + "learning_rate": 4.634857501131776e-06, + "loss": 3.3124, + "step": 2770944 + }, + { + "epoch": 1.01, + "learning_rate": 4.626471553621256e-06, + "loss": 3.3089, + "step": 2771456 + }, + { + "epoch": 1.01, + "learning_rate": 4.6180856061107356e-06, + "loss": 3.3027, + "step": 2771968 + }, + { + "epoch": 1.01, + "learning_rate": 4.6096996586002155e-06, + "loss": 3.2912, + "step": 2772480 + }, + { + "epoch": 1.01, + "learning_rate": 4.601313711089695e-06, + "loss": 3.316, + "step": 2772992 + }, + { + "epoch": 1.01, + "learning_rate": 4.592927763579175e-06, + "loss": 3.3152, + "step": 2773504 + }, + { + "epoch": 1.01, + "learning_rate": 4.584558194872386e-06, + "loss": 3.3078, + "step": 2774016 + }, + { + "epoch": 1.01, + "learning_rate": 4.576188626165598e-06, + "loss": 3.2926, + "step": 2774528 + }, + { + "epoch": 1.01, + "learning_rate": 4.567802678655078e-06, + "loss": 3.2995, + "step": 2775040 + }, + { + "epoch": 1.01, + "learning_rate": 4.559416731144558e-06, + "loss": 3.2928, + "step": 2775552 + }, + { + "epoch": 1.01, + "learning_rate": 4.551030783634038e-06, + "loss": 3.3132, + "step": 2776064 + }, + { + "epoch": 1.01, + "learning_rate": 4.542644836123517e-06, + "loss": 3.303, + "step": 2776576 + }, + { + "epoch": 1.01, + "learning_rate": 4.534258888612998e-06, + "loss": 3.3043, + "step": 2777088 + }, + { + "epoch": 1.01, + "learning_rate": 4.525872941102477e-06, + "loss": 3.3153, + "step": 2777600 + }, + { + "epoch": 1.01, + "learning_rate": 4.51751975119942e-06, + "loss": 3.302, + "step": 2778112 + }, + { + "epoch": 1.01, + "learning_rate": 4.509133803688899e-06, + "loss": 3.3057, + "step": 2778624 + }, + { + "epoch": 1.01, + "learning_rate": 4.50074785617838e-06, + "loss": 3.3112, + "step": 2779136 + }, + { + "epoch": 1.01, + "learning_rate": 4.492361908667859e-06, + "loss": 3.2912, + "step": 2779648 + }, + { + "epoch": 1.01, + "learning_rate": 4.48397596115734e-06, + "loss": 3.3052, + "step": 2780160 + }, + { + "epoch": 1.01, + "learning_rate": 4.47559001364682e-06, + "loss": 3.3057, + "step": 2780672 + }, + { + "epoch": 1.01, + "learning_rate": 4.4672204449400315e-06, + "loss": 3.3136, + "step": 2781184 + }, + { + "epoch": 1.01, + "learning_rate": 4.458834497429511e-06, + "loss": 3.296, + "step": 2781696 + }, + { + "epoch": 1.01, + "learning_rate": 4.4504485499189905e-06, + "loss": 3.3018, + "step": 2782208 + }, + { + "epoch": 1.01, + "learning_rate": 4.4420626024084705e-06, + "loss": 3.2936, + "step": 2782720 + }, + { + "epoch": 1.01, + "learning_rate": 4.4336766548979504e-06, + "loss": 3.3198, + "step": 2783232 + }, + { + "epoch": 1.01, + "learning_rate": 4.425307086191162e-06, + "loss": 3.3109, + "step": 2783744 + }, + { + "epoch": 1.01, + "learning_rate": 4.416921138680641e-06, + "loss": 3.3071, + "step": 2784256 + }, + { + "epoch": 1.01, + "learning_rate": 4.408535191170122e-06, + "loss": 3.3248, + "step": 2784768 + }, + { + "epoch": 1.01, + "learning_rate": 4.400149243659601e-06, + "loss": 3.3135, + "step": 2785280 + }, + { + "epoch": 1.01, + "learning_rate": 4.391763296149081e-06, + "loss": 3.3311, + "step": 2785792 + }, + { + "epoch": 1.01, + "learning_rate": 4.383377348638561e-06, + "loss": 3.3058, + "step": 2786304 + }, + { + "epoch": 1.01, + "learning_rate": 4.375007779931773e-06, + "loss": 3.3128, + "step": 2786816 + }, + { + "epoch": 1.01, + "learning_rate": 4.366621832421253e-06, + "loss": 3.3137, + "step": 2787328 + }, + { + "epoch": 1.01, + "learning_rate": 4.3582358849107326e-06, + "loss": 3.3056, + "step": 2787840 + }, + { + "epoch": 1.01, + "learning_rate": 4.3498499374002125e-06, + "loss": 3.3157, + "step": 2788352 + }, + { + "epoch": 1.01, + "learning_rate": 4.3414639898896925e-06, + "loss": 3.3095, + "step": 2788864 + }, + { + "epoch": 1.01, + "learning_rate": 4.333078042379172e-06, + "loss": 3.3171, + "step": 2789376 + }, + { + "epoch": 1.01, + "learning_rate": 4.324692094868652e-06, + "loss": 3.3073, + "step": 2789888 + }, + { + "epoch": 1.01, + "learning_rate": 4.316322526161863e-06, + "loss": 3.298, + "step": 2790400 + }, + { + "epoch": 1.01, + "learning_rate": 4.307936578651343e-06, + "loss": 3.3053, + "step": 2790912 + }, + { + "epoch": 1.01, + "learning_rate": 4.299550631140823e-06, + "loss": 3.3055, + "step": 2791424 + }, + { + "epoch": 1.01, + "learning_rate": 4.291164683630303e-06, + "loss": 3.3163, + "step": 2791936 + }, + { + "epoch": 1.01, + "learning_rate": 4.282795114923515e-06, + "loss": 3.3089, + "step": 2792448 + }, + { + "epoch": 1.01, + "learning_rate": 4.274409167412995e-06, + "loss": 3.3061, + "step": 2792960 + }, + { + "epoch": 1.02, + "learning_rate": 4.266023219902475e-06, + "loss": 3.3144, + "step": 2793472 + }, + { + "epoch": 1.02, + "learning_rate": 4.257637272391954e-06, + "loss": 3.3086, + "step": 2793984 + }, + { + "epoch": 1.02, + "learning_rate": 4.2492513248814345e-06, + "loss": 3.2974, + "step": 2794496 + }, + { + "epoch": 1.02, + "learning_rate": 4.240881756174645e-06, + "loss": 3.3055, + "step": 2795008 + }, + { + "epoch": 1.02, + "learning_rate": 4.232495808664125e-06, + "loss": 3.3183, + "step": 2795520 + }, + { + "epoch": 1.02, + "learning_rate": 4.224109861153605e-06, + "loss": 3.317, + "step": 2796032 + }, + { + "epoch": 1.02, + "learning_rate": 4.215723913643085e-06, + "loss": 3.3103, + "step": 2796544 + }, + { + "epoch": 1.02, + "learning_rate": 4.207337966132565e-06, + "loss": 3.293, + "step": 2797056 + }, + { + "epoch": 1.02, + "learning_rate": 4.198952018622044e-06, + "loss": 3.3165, + "step": 2797568 + }, + { + "epoch": 1.02, + "learning_rate": 4.190566071111525e-06, + "loss": 3.3025, + "step": 2798080 + }, + { + "epoch": 1.02, + "learning_rate": 4.182180123601004e-06, + "loss": 3.3176, + "step": 2798592 + }, + { + "epoch": 1.02, + "learning_rate": 4.173810554894217e-06, + "loss": 3.3113, + "step": 2799104 + }, + { + "epoch": 1.02, + "learning_rate": 4.165440986187427e-06, + "loss": 3.311, + "step": 2799616 + }, + { + "epoch": 1.02, + "learning_rate": 4.157055038676907e-06, + "loss": 3.3062, + "step": 2800128 + }, + { + "epoch": 1.02, + "learning_rate": 4.148669091166387e-06, + "loss": 3.3192, + "step": 2800640 + }, + { + "epoch": 1.02, + "learning_rate": 4.140283143655867e-06, + "loss": 3.2951, + "step": 2801152 + }, + { + "epoch": 1.02, + "learning_rate": 4.131897196145347e-06, + "loss": 3.305, + "step": 2801664 + }, + { + "epoch": 1.02, + "learning_rate": 4.123527627438559e-06, + "loss": 3.2987, + "step": 2802176 + }, + { + "epoch": 1.02, + "learning_rate": 4.115141679928038e-06, + "loss": 3.3143, + "step": 2802688 + }, + { + "epoch": 1.02, + "learning_rate": 4.106755732417518e-06, + "loss": 3.2902, + "step": 2803200 + }, + { + "epoch": 1.02, + "learning_rate": 4.098369784906998e-06, + "loss": 3.3056, + "step": 2803712 + }, + { + "epoch": 1.02, + "learning_rate": 4.089983837396478e-06, + "loss": 3.3014, + "step": 2804224 + }, + { + "epoch": 1.02, + "learning_rate": 4.081597889885958e-06, + "loss": 3.3037, + "step": 2804736 + }, + { + "epoch": 1.02, + "learning_rate": 4.0732283211791694e-06, + "loss": 3.3034, + "step": 2805248 + }, + { + "epoch": 1.02, + "learning_rate": 4.064842373668649e-06, + "loss": 3.3015, + "step": 2805760 + }, + { + "epoch": 1.02, + "learning_rate": 4.056456426158129e-06, + "loss": 3.315, + "step": 2806272 + }, + { + "epoch": 1.02, + "learning_rate": 4.0480704786476085e-06, + "loss": 3.3164, + "step": 2806784 + }, + { + "epoch": 1.02, + "learning_rate": 4.039684531137089e-06, + "loss": 3.3111, + "step": 2807296 + }, + { + "epoch": 1.02, + "learning_rate": 4.031298583626568e-06, + "loss": 3.3039, + "step": 2807808 + }, + { + "epoch": 1.02, + "learning_rate": 4.02292901491978e-06, + "loss": 3.3179, + "step": 2808320 + }, + { + "epoch": 1.02, + "learning_rate": 4.01454306740926e-06, + "loss": 3.3092, + "step": 2808832 + }, + { + "epoch": 1.02, + "learning_rate": 4.00615711989874e-06, + "loss": 3.3006, + "step": 2809344 + }, + { + "epoch": 1.02, + "learning_rate": 3.99777117238822e-06, + "loss": 3.3188, + "step": 2809856 + }, + { + "epoch": 1.02, + "learning_rate": 3.9894016036814315e-06, + "loss": 3.3039, + "step": 2810368 + }, + { + "epoch": 1.02, + "learning_rate": 3.9810156561709115e-06, + "loss": 3.3132, + "step": 2810880 + }, + { + "epoch": 1.02, + "learning_rate": 3.972629708660391e-06, + "loss": 3.298, + "step": 2811392 + }, + { + "epoch": 1.02, + "learning_rate": 3.964243761149871e-06, + "loss": 3.3106, + "step": 2811904 + }, + { + "epoch": 1.02, + "learning_rate": 3.9558578136393505e-06, + "loss": 3.2975, + "step": 2812416 + }, + { + "epoch": 1.02, + "learning_rate": 3.947471866128831e-06, + "loss": 3.297, + "step": 2812928 + }, + { + "epoch": 1.02, + "learning_rate": 3.939102297422042e-06, + "loss": 3.3028, + "step": 2813440 + }, + { + "epoch": 1.02, + "learning_rate": 3.930716349911521e-06, + "loss": 3.3122, + "step": 2813952 + }, + { + "epoch": 1.02, + "learning_rate": 3.922330402401002e-06, + "loss": 3.31, + "step": 2814464 + }, + { + "epoch": 1.02, + "learning_rate": 3.913944454890481e-06, + "loss": 3.314, + "step": 2814976 + }, + { + "epoch": 1.02, + "learning_rate": 3.905558507379962e-06, + "loss": 3.303, + "step": 2815488 + }, + { + "epoch": 1.02, + "learning_rate": 3.897172559869441e-06, + "loss": 3.31, + "step": 2816000 + }, + { + "epoch": 1.02, + "learning_rate": 3.888786612358921e-06, + "loss": 3.3165, + "step": 2816512 + }, + { + "epoch": 1.02, + "learning_rate": 3.880417043652133e-06, + "loss": 3.312, + "step": 2817024 + }, + { + "epoch": 1.02, + "learning_rate": 3.8720310961416126e-06, + "loss": 3.3054, + "step": 2817536 + }, + { + "epoch": 1.02, + "learning_rate": 3.8636451486310925e-06, + "loss": 3.3113, + "step": 2818048 + }, + { + "epoch": 1.02, + "learning_rate": 3.8552592011205725e-06, + "loss": 3.3065, + "step": 2818560 + }, + { + "epoch": 1.02, + "learning_rate": 3.846889632413784e-06, + "loss": 3.3164, + "step": 2819072 + }, + { + "epoch": 1.02, + "learning_rate": 3.838503684903263e-06, + "loss": 3.3025, + "step": 2819584 + }, + { + "epoch": 1.02, + "learning_rate": 3.830117737392744e-06, + "loss": 3.3102, + "step": 2820096 + }, + { + "epoch": 1.02, + "learning_rate": 3.821731789882223e-06, + "loss": 3.3063, + "step": 2820608 + }, + { + "epoch": 1.02, + "learning_rate": 3.813345842371703e-06, + "loss": 3.3081, + "step": 2821120 + }, + { + "epoch": 1.02, + "learning_rate": 3.8049598948611835e-06, + "loss": 3.3082, + "step": 2821632 + }, + { + "epoch": 1.02, + "learning_rate": 3.796573947350663e-06, + "loss": 3.312, + "step": 2822144 + }, + { + "epoch": 1.02, + "learning_rate": 3.7881879998401434e-06, + "loss": 3.3111, + "step": 2822656 + }, + { + "epoch": 1.02, + "learning_rate": 3.7798348099370854e-06, + "loss": 3.297, + "step": 2823168 + }, + { + "epoch": 1.02, + "learning_rate": 3.771448862426566e-06, + "loss": 3.3102, + "step": 2823680 + }, + { + "epoch": 1.03, + "eval_loss": 3.8670473098754883, + "eval_runtime": 302.7795, + "eval_samples_per_second": 1260.294, + "eval_steps_per_second": 39.385, + "step": 2823840 + }, + { + "epoch": 0.0, + "learning_rate": 3.7630629149160453e-06, + "loss": 3.2972, + "step": 2824192 + }, + { + "epoch": 0.0, + "learning_rate": 3.7546769674055257e-06, + "loss": 3.3001, + "step": 2824704 + }, + { + "epoch": 0.0, + "learning_rate": 3.7462910198950057e-06, + "loss": 3.3103, + "step": 2825216 + }, + { + "epoch": 0.0, + "learning_rate": 3.737905072384485e-06, + "loss": 3.3034, + "step": 2825728 + }, + { + "epoch": 0.0, + "learning_rate": 3.729551882481428e-06, + "loss": 3.3203, + "step": 2826240 + }, + { + "epoch": 0.0, + "learning_rate": 3.7211659349709085e-06, + "loss": 3.3055, + "step": 2826752 + }, + { + "epoch": 0.0, + "learning_rate": 3.712779987460388e-06, + "loss": 3.2998, + "step": 2827264 + }, + { + "epoch": 0.0, + "learning_rate": 3.7043940399498675e-06, + "loss": 3.3009, + "step": 2827776 + }, + { + "epoch": 0.0, + "learning_rate": 3.696024471243079e-06, + "loss": 3.3023, + "step": 2828288 + }, + { + "epoch": 0.0, + "learning_rate": 3.6876385237325587e-06, + "loss": 3.3102, + "step": 2828800 + }, + { + "epoch": 0.0, + "learning_rate": 3.679252576222039e-06, + "loss": 3.3003, + "step": 2829312 + }, + { + "epoch": 0.0, + "learning_rate": 3.670866628711519e-06, + "loss": 3.3054, + "step": 2829824 + }, + { + "epoch": 0.0, + "learning_rate": 3.662480681200999e-06, + "loss": 3.3008, + "step": 2830336 + }, + { + "epoch": 0.0, + "learning_rate": 3.6541111124942102e-06, + "loss": 3.2971, + "step": 2830848 + }, + { + "epoch": 0.0, + "learning_rate": 3.6457251649836906e-06, + "loss": 3.3067, + "step": 2831360 + }, + { + "epoch": 0.0, + "learning_rate": 3.63733921747317e-06, + "loss": 3.2963, + "step": 2831872 + }, + { + "epoch": 0.0, + "learning_rate": 3.6289532699626497e-06, + "loss": 3.2945, + "step": 2832384 + }, + { + "epoch": 0.0, + "learning_rate": 3.6205837012558613e-06, + "loss": 3.3054, + "step": 2832896 + }, + { + "epoch": 0.0, + "learning_rate": 3.612197753745341e-06, + "loss": 3.3032, + "step": 2833408 + }, + { + "epoch": 0.0, + "learning_rate": 3.603811806234821e-06, + "loss": 3.3144, + "step": 2833920 + }, + { + "epoch": 0.0, + "learning_rate": 3.5954258587243007e-06, + "loss": 3.3088, + "step": 2834432 + }, + { + "epoch": 0.0, + "learning_rate": 3.587039911213781e-06, + "loss": 3.3057, + "step": 2834944 + }, + { + "epoch": 0.0, + "learning_rate": 3.5786539637032607e-06, + "loss": 3.3035, + "step": 2835456 + }, + { + "epoch": 0.0, + "learning_rate": 3.5702680161927406e-06, + "loss": 3.3117, + "step": 2835968 + }, + { + "epoch": 0.0, + "learning_rate": 3.5618820686822206e-06, + "loss": 3.2968, + "step": 2836480 + }, + { + "epoch": 0.0, + "learning_rate": 3.5535124999754318e-06, + "loss": 3.3125, + "step": 2836992 + }, + { + "epoch": 0.0, + "learning_rate": 3.545126552464912e-06, + "loss": 3.2997, + "step": 2837504 + }, + { + "epoch": 0.0, + "learning_rate": 3.5367406049543917e-06, + "loss": 3.296, + "step": 2838016 + }, + { + "epoch": 0.0, + "learning_rate": 3.528354657443872e-06, + "loss": 3.2934, + "step": 2838528 + }, + { + "epoch": 0.0, + "learning_rate": 3.519985088737083e-06, + "loss": 3.2989, + "step": 2839040 + }, + { + "epoch": 0.01, + "learning_rate": 3.5115991412265632e-06, + "loss": 3.3067, + "step": 2839552 + }, + { + "epoch": 0.01, + "learning_rate": 3.503229572519774e-06, + "loss": 3.3039, + "step": 2840064 + }, + { + "epoch": 0.01, + "learning_rate": 3.4948436250092544e-06, + "loss": 3.3131, + "step": 2840576 + }, + { + "epoch": 0.01, + "learning_rate": 3.486457677498734e-06, + "loss": 3.3104, + "step": 2841088 + }, + { + "epoch": 0.01, + "learning_rate": 3.478071729988214e-06, + "loss": 3.296, + "step": 2841600 + }, + { + "epoch": 0.01, + "learning_rate": 3.469685782477694e-06, + "loss": 3.3043, + "step": 2842112 + }, + { + "epoch": 0.01, + "learning_rate": 3.461299834967174e-06, + "loss": 3.3055, + "step": 2842624 + }, + { + "epoch": 0.01, + "learning_rate": 3.452913887456654e-06, + "loss": 3.3061, + "step": 2843136 + }, + { + "epoch": 0.01, + "learning_rate": 3.444544318749865e-06, + "loss": 3.3006, + "step": 2843648 + }, + { + "epoch": 0.01, + "learning_rate": 3.4361583712393454e-06, + "loss": 3.2973, + "step": 2844160 + }, + { + "epoch": 0.01, + "learning_rate": 3.427772423728825e-06, + "loss": 3.3032, + "step": 2844672 + }, + { + "epoch": 0.01, + "learning_rate": 3.4193864762183044e-06, + "loss": 3.313, + "step": 2845184 + }, + { + "epoch": 0.01, + "learning_rate": 3.411000528707785e-06, + "loss": 3.3031, + "step": 2845696 + }, + { + "epoch": 0.01, + "learning_rate": 3.4026145811972643e-06, + "loss": 3.3035, + "step": 2846208 + }, + { + "epoch": 0.01, + "learning_rate": 3.394245012490476e-06, + "loss": 3.312, + "step": 2846720 + }, + { + "epoch": 0.01, + "learning_rate": 3.3858590649799555e-06, + "loss": 3.3044, + "step": 2847232 + }, + { + "epoch": 0.01, + "learning_rate": 3.377473117469436e-06, + "loss": 3.3018, + "step": 2847744 + }, + { + "epoch": 0.01, + "learning_rate": 3.369087169958916e-06, + "loss": 3.2968, + "step": 2848256 + }, + { + "epoch": 0.01, + "learning_rate": 3.3607012224483954e-06, + "loss": 3.2786, + "step": 2848768 + }, + { + "epoch": 0.01, + "learning_rate": 3.3523152749378757e-06, + "loss": 3.3095, + "step": 2849280 + }, + { + "epoch": 0.01, + "learning_rate": 3.3439293274273553e-06, + "loss": 3.3035, + "step": 2849792 + }, + { + "epoch": 0.01, + "learning_rate": 3.335559758720567e-06, + "loss": 3.3021, + "step": 2850304 + }, + { + "epoch": 0.01, + "learning_rate": 3.3271901900137777e-06, + "loss": 3.2894, + "step": 2850816 + }, + { + "epoch": 0.01, + "learning_rate": 3.318804242503258e-06, + "loss": 3.2874, + "step": 2851328 + }, + { + "epoch": 0.01, + "learning_rate": 3.3104182949927376e-06, + "loss": 3.2883, + "step": 2851840 + }, + { + "epoch": 0.01, + "learning_rate": 3.302032347482217e-06, + "loss": 3.3016, + "step": 2852352 + }, + { + "epoch": 0.01, + "learning_rate": 3.2936463999716975e-06, + "loss": 3.296, + "step": 2852864 + }, + { + "epoch": 0.01, + "learning_rate": 3.2852604524611775e-06, + "loss": 3.3002, + "step": 2853376 + }, + { + "epoch": 0.01, + "learning_rate": 3.276890883754389e-06, + "loss": 3.3046, + "step": 2853888 + }, + { + "epoch": 0.01, + "learning_rate": 3.2685049362438687e-06, + "loss": 3.2926, + "step": 2854400 + }, + { + "epoch": 0.01, + "learning_rate": 3.260118988733349e-06, + "loss": 3.3006, + "step": 2854912 + }, + { + "epoch": 0.01, + "learning_rate": 3.2517330412228286e-06, + "loss": 3.3031, + "step": 2855424 + }, + { + "epoch": 0.01, + "learning_rate": 3.243347093712308e-06, + "loss": 3.284, + "step": 2855936 + }, + { + "epoch": 0.01, + "learning_rate": 3.2349775250055197e-06, + "loss": 3.2925, + "step": 2856448 + }, + { + "epoch": 0.01, + "learning_rate": 3.2265915774949993e-06, + "loss": 3.2993, + "step": 2856960 + }, + { + "epoch": 0.01, + "learning_rate": 3.2182056299844796e-06, + "loss": 3.3056, + "step": 2857472 + }, + { + "epoch": 0.01, + "learning_rate": 3.209819682473959e-06, + "loss": 3.2872, + "step": 2857984 + }, + { + "epoch": 0.01, + "learning_rate": 3.201450113767171e-06, + "loss": 3.295, + "step": 2858496 + }, + { + "epoch": 0.01, + "learning_rate": 3.1930641662566508e-06, + "loss": 3.286, + "step": 2859008 + }, + { + "epoch": 0.01, + "learning_rate": 3.1846782187461307e-06, + "loss": 3.3074, + "step": 2859520 + }, + { + "epoch": 0.01, + "learning_rate": 3.1762922712356107e-06, + "loss": 3.3028, + "step": 2860032 + }, + { + "epoch": 0.01, + "learning_rate": 3.1679063237250902e-06, + "loss": 3.2999, + "step": 2860544 + }, + { + "epoch": 0.01, + "learning_rate": 3.159536755018302e-06, + "loss": 3.3117, + "step": 2861056 + }, + { + "epoch": 0.01, + "learning_rate": 3.1511508075077814e-06, + "loss": 3.3078, + "step": 2861568 + }, + { + "epoch": 0.01, + "learning_rate": 3.1427648599972618e-06, + "loss": 3.3242, + "step": 2862080 + }, + { + "epoch": 0.01, + "learning_rate": 3.1343789124867413e-06, + "loss": 3.2973, + "step": 2862592 + }, + { + "epoch": 0.01, + "learning_rate": 3.1259929649762217e-06, + "loss": 3.3056, + "step": 2863104 + }, + { + "epoch": 0.01, + "learning_rate": 3.117607017465701e-06, + "loss": 3.304, + "step": 2863616 + }, + { + "epoch": 0.01, + "learning_rate": 3.1092374487589124e-06, + "loss": 3.2963, + "step": 2864128 + }, + { + "epoch": 0.01, + "learning_rate": 3.1008515012483924e-06, + "loss": 3.3114, + "step": 2864640 + }, + { + "epoch": 0.01, + "learning_rate": 3.0924655537378723e-06, + "loss": 3.3018, + "step": 2865152 + }, + { + "epoch": 0.01, + "learning_rate": 3.0840796062273523e-06, + "loss": 3.3081, + "step": 2865664 + }, + { + "epoch": 0.01, + "learning_rate": 3.0756936587168322e-06, + "loss": 3.3002, + "step": 2866176 + }, + { + "epoch": 0.01, + "learning_rate": 3.067324090010044e-06, + "loss": 3.2906, + "step": 2866688 + }, + { + "epoch": 0.01, + "learning_rate": 3.0589381424995234e-06, + "loss": 3.2958, + "step": 2867200 + }, + { + "epoch": 0.01, + "learning_rate": 3.0505521949890034e-06, + "loss": 3.2951, + "step": 2867712 + }, + { + "epoch": 0.01, + "learning_rate": 3.0421662474784833e-06, + "loss": 3.311, + "step": 2868224 + }, + { + "epoch": 0.01, + "learning_rate": 3.0337802999679633e-06, + "loss": 3.3043, + "step": 2868736 + }, + { + "epoch": 0.01, + "learning_rate": 3.0254107312611745e-06, + "loss": 3.2898, + "step": 2869248 + }, + { + "epoch": 0.02, + "learning_rate": 3.0170247837506545e-06, + "loss": 3.3099, + "step": 2869760 + }, + { + "epoch": 0.02, + "learning_rate": 3.0086388362401344e-06, + "loss": 3.3012, + "step": 2870272 + }, + { + "epoch": 0.02, + "learning_rate": 3.000252888729614e-06, + "loss": 3.2902, + "step": 2870784 + }, + { + "epoch": 0.02, + "learning_rate": 2.9918833200228256e-06, + "loss": 3.2954, + "step": 2871296 + }, + { + "epoch": 0.02, + "learning_rate": 2.9834973725123055e-06, + "loss": 3.3086, + "step": 2871808 + }, + { + "epoch": 0.02, + "learning_rate": 2.9751114250017855e-06, + "loss": 3.3043, + "step": 2872320 + }, + { + "epoch": 0.02, + "learning_rate": 2.9667254774912654e-06, + "loss": 3.3066, + "step": 2872832 + }, + { + "epoch": 0.02, + "learning_rate": 2.9583395299807454e-06, + "loss": 3.2884, + "step": 2873344 + }, + { + "epoch": 0.02, + "learning_rate": 2.9499535824702254e-06, + "loss": 3.3059, + "step": 2873856 + }, + { + "epoch": 0.02, + "learning_rate": 2.941567634959705e-06, + "loss": 3.2955, + "step": 2874368 + }, + { + "epoch": 0.02, + "learning_rate": 2.933181687449185e-06, + "loss": 3.3094, + "step": 2874880 + }, + { + "epoch": 0.02, + "learning_rate": 2.924812118742396e-06, + "loss": 3.3056, + "step": 2875392 + }, + { + "epoch": 0.02, + "learning_rate": 2.9164425500356077e-06, + "loss": 3.2998, + "step": 2875904 + }, + { + "epoch": 0.02, + "learning_rate": 2.9080566025250872e-06, + "loss": 3.3002, + "step": 2876416 + }, + { + "epoch": 0.02, + "learning_rate": 2.8996706550145676e-06, + "loss": 3.3065, + "step": 2876928 + }, + { + "epoch": 0.02, + "learning_rate": 2.8912847075040476e-06, + "loss": 3.2891, + "step": 2877440 + }, + { + "epoch": 0.02, + "learning_rate": 2.8828987599935275e-06, + "loss": 3.2952, + "step": 2877952 + }, + { + "epoch": 0.02, + "learning_rate": 2.8745291912867387e-06, + "loss": 3.2884, + "step": 2878464 + }, + { + "epoch": 0.02, + "learning_rate": 2.8661432437762187e-06, + "loss": 3.3025, + "step": 2878976 + }, + { + "epoch": 0.02, + "learning_rate": 2.8577572962656986e-06, + "loss": 3.2874, + "step": 2879488 + }, + { + "epoch": 0.02, + "learning_rate": 2.849371348755178e-06, + "loss": 3.2985, + "step": 2880000 + }, + { + "epoch": 0.02, + "learning_rate": 2.840985401244658e-06, + "loss": 3.2914, + "step": 2880512 + }, + { + "epoch": 0.02, + "learning_rate": 2.832599453734138e-06, + "loss": 3.2957, + "step": 2881024 + }, + { + "epoch": 0.02, + "learning_rate": 2.8242298850273493e-06, + "loss": 3.2988, + "step": 2881536 + }, + { + "epoch": 0.02, + "learning_rate": 2.8158439375168293e-06, + "loss": 3.2924, + "step": 2882048 + }, + { + "epoch": 0.02, + "learning_rate": 2.8074579900063092e-06, + "loss": 3.3053, + "step": 2882560 + }, + { + "epoch": 0.02, + "learning_rate": 2.799072042495789e-06, + "loss": 3.3085, + "step": 2883072 + }, + { + "epoch": 0.02, + "learning_rate": 2.790686094985269e-06, + "loss": 3.3048, + "step": 2883584 + }, + { + "epoch": 0.02, + "learning_rate": 2.782300147474749e-06, + "loss": 3.2965, + "step": 2884096 + }, + { + "epoch": 0.02, + "learning_rate": 2.7739305787679603e-06, + "loss": 3.3073, + "step": 2884608 + }, + { + "epoch": 0.02, + "learning_rate": 2.7655446312574402e-06, + "loss": 3.3055, + "step": 2885120 + }, + { + "epoch": 0.02, + "learning_rate": 2.75715868374692e-06, + "loss": 3.2883, + "step": 2885632 + }, + { + "epoch": 0.02, + "learning_rate": 2.7487727362364e-06, + "loss": 3.313, + "step": 2886144 + }, + { + "epoch": 0.02, + "learning_rate": 2.7403867887258797e-06, + "loss": 3.2909, + "step": 2886656 + }, + { + "epoch": 0.02, + "learning_rate": 2.7320172200190913e-06, + "loss": 3.308, + "step": 2887168 + }, + { + "epoch": 0.02, + "learning_rate": 2.723631272508571e-06, + "loss": 3.2881, + "step": 2887680 + }, + { + "epoch": 0.02, + "learning_rate": 2.715245324998051e-06, + "loss": 3.3028, + "step": 2888192 + }, + { + "epoch": 0.02, + "learning_rate": 2.7068593774875308e-06, + "loss": 3.2888, + "step": 2888704 + }, + { + "epoch": 0.02, + "learning_rate": 2.6984734299770107e-06, + "loss": 3.2904, + "step": 2889216 + }, + { + "epoch": 0.02, + "learning_rate": 2.6901038612702224e-06, + "loss": 3.2909, + "step": 2889728 + }, + { + "epoch": 0.02, + "learning_rate": 2.6817179137597023e-06, + "loss": 3.3075, + "step": 2890240 + }, + { + "epoch": 0.02, + "learning_rate": 2.6733319662491823e-06, + "loss": 3.2983, + "step": 2890752 + }, + { + "epoch": 0.02, + "learning_rate": 2.664946018738662e-06, + "loss": 3.3077, + "step": 2891264 + }, + { + "epoch": 0.02, + "learning_rate": 2.6565600712281418e-06, + "loss": 3.2957, + "step": 2891776 + }, + { + "epoch": 0.02, + "learning_rate": 2.6481741237176217e-06, + "loss": 3.3047, + "step": 2892288 + }, + { + "epoch": 0.02, + "learning_rate": 2.6397881762071017e-06, + "loss": 3.3078, + "step": 2892800 + }, + { + "epoch": 0.02, + "learning_rate": 2.631418607500313e-06, + "loss": 3.3038, + "step": 2893312 + }, + { + "epoch": 0.02, + "learning_rate": 2.623032659989793e-06, + "loss": 3.2996, + "step": 2893824 + }, + { + "epoch": 0.02, + "learning_rate": 2.614646712479273e-06, + "loss": 3.3003, + "step": 2894336 + }, + { + "epoch": 0.02, + "learning_rate": 2.6062607649687523e-06, + "loss": 3.2989, + "step": 2894848 + }, + { + "epoch": 0.02, + "learning_rate": 2.5978911962619644e-06, + "loss": 3.3102, + "step": 2895360 + }, + { + "epoch": 0.02, + "learning_rate": 2.589505248751444e-06, + "loss": 3.295, + "step": 2895872 + }, + { + "epoch": 0.02, + "learning_rate": 2.581119301240924e-06, + "loss": 3.3018, + "step": 2896384 + }, + { + "epoch": 0.02, + "learning_rate": 2.572733353730404e-06, + "loss": 3.2968, + "step": 2896896 + }, + { + "epoch": 0.02, + "learning_rate": 2.564347406219884e-06, + "loss": 3.3016, + "step": 2897408 + }, + { + "epoch": 0.02, + "learning_rate": 2.5559614587093633e-06, + "loss": 3.2987, + "step": 2897920 + }, + { + "epoch": 0.02, + "learning_rate": 2.5475755111988433e-06, + "loss": 3.2983, + "step": 2898432 + }, + { + "epoch": 0.02, + "learning_rate": 2.5391895636883232e-06, + "loss": 3.3091, + "step": 2898944 + }, + { + "epoch": 0.02, + "learning_rate": 2.530836373785266e-06, + "loss": 3.2857, + "step": 2899456 + }, + { + "epoch": 0.02, + "learning_rate": 2.5224504262747457e-06, + "loss": 3.3059, + "step": 2899968 + }, + { + "epoch": 0.03, + "eval_loss": 3.8661906719207764, + "eval_runtime": 305.0956, + "eval_samples_per_second": 1250.726, + "eval_steps_per_second": 39.086, + "step": 2900160 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 2.0169456754864435e+18, + "trial_name": null, + "trial_params": null +}