diff --git "a/checkpoint-2060640/trainer_state.json" "b/checkpoint-2060640/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-2060640/trainer_state.json" @@ -0,0 +1,24385 @@ +{ + "best_metric": 3.842787981033325, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/binding-c-command/transformer/0/checkpoints/checkpoint-992160", + "epoch": 0.025000606015738065, + "eval_steps": 10, + "global_step": 2060640, + "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": 10.9624, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 6.822, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 6.1893, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 5.9774, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 5.8082, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 5.6938, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 5.5921, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 5.5277, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 5.4338, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 5.4008, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 5.3401, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 5.3007, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989938500867749e-05, + "loss": 5.2593, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989099906116697e-05, + "loss": 5.1918, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988261311365645e-05, + "loss": 5.1743, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.987422716614593e-05, + "loss": 5.1266, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986584121863541e-05, + "loss": 5.1042, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985745527112489e-05, + "loss": 5.0762, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984906932361437e-05, + "loss": 5.0383, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.0149, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 5.0018, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.9823927859886547e-05, + "loss": 4.972, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.9815541912376026e-05, + "loss": 4.9446, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.9807155964865506e-05, + "loss": 4.9231, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 4.9142, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790400448648195e-05, + "loss": 4.8885, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9782014501137675e-05, + "loss": 4.8615, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773628553627155e-05, + "loss": 4.8521, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 4.8317, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756873037409844e-05, + "loss": 4.8177, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748487089899324e-05, + "loss": 4.8048, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.9740101142388804e-05, + "loss": 4.7885, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731715194878284e-05, + "loss": 4.7788, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.97233456261715e-05, + "loss": 4.7606, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.971495967866098e-05, + "loss": 4.7554, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.970657373115046e-05, + "loss": 4.756, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969818778363994e-05, + "loss": 4.7316, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968981821493315e-05, + "loss": 4.6953, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.968143226742263e-05, + "loss": 4.7007, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967304631991211e-05, + "loss": 4.6801, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966466037240159e-05, + "loss": 4.6846, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.96562908036948e-05, + "loss": 4.6714, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964790485618428e-05, + "loss": 4.6626, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963951890867376e-05, + "loss": 4.6429, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.963113296116324e-05, + "loss": 4.6519, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962274701365272e-05, + "loss": 4.6346, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.9614377444945934e-05, + "loss": 4.6331, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.9605991497435414e-05, + "loss": 4.623, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.9597605549924894e-05, + "loss": 4.6016, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.95892359812181e-05, + "loss": 4.6024, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958085003370758e-05, + "loss": 4.6049, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957246408619706e-05, + "loss": 4.5845, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956407813868654e-05, + "loss": 4.5752, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.9555692191176016e-05, + "loss": 4.5654, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.9547306243665496e-05, + "loss": 4.5651, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.9538920296154976e-05, + "loss": 4.5488, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.9530534348644456e-05, + "loss": 4.5677, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.952216477993767e-05, + "loss": 4.5365, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951377883242715e-05, + "loss": 4.5446, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.950539288491663e-05, + "loss": 4.5359, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949700693740611e-05, + "loss": 4.5111, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948862098989559e-05, + "loss": 4.5192, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.94802514211888e-05, + "loss": 4.5095, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947186547367828e-05, + "loss": 4.4953, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946347952616776e-05, + "loss": 4.4871, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945509357865724e-05, + "loss": 4.5026, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944672400995045e-05, + "loss": 4.482, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.943833806243993e-05, + "loss": 4.4749, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942995211492941e-05, + "loss": 4.464, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.9421582546222625e-05, + "loss": 4.4767, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.9413196598712105e-05, + "loss": 4.481, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.9404810651201585e-05, + "loss": 4.466, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396424703691065e-05, + "loss": 4.4608, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388038756180545e-05, + "loss": 4.4643, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379652808670025e-05, + "loss": 4.4623, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371266861159505e-05, + "loss": 4.4513, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.9362897292452714e-05, + "loss": 4.4343, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.9354511344942194e-05, + "loss": 4.4415, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.9346125397431674e-05, + "loss": 4.4303, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.9337739449921154e-05, + "loss": 4.4284, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.9329353502410634e-05, + "loss": 4.417, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.9320967554900114e-05, + "loss": 4.4235, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.9312581607389594e-05, + "loss": 4.428, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.9304195659879074e-05, + "loss": 4.4195, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.929582609117229e-05, + "loss": 4.3942, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.92874565224655e-05, + "loss": 4.3995, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.927907057495498e-05, + "loss": 4.4045, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.927068462744446e-05, + "loss": 4.3984, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.926229867993394e-05, + "loss": 4.3933, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925391273242342e-05, + "loss": 4.3903, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.92455267849129e-05, + "loss": 4.3846, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923714083740238e-05, + "loss": 4.3713, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922877126869559e-05, + "loss": 4.3764, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.922038532118507e-05, + "loss": 4.3763, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921199937367455e-05, + "loss": 4.3682, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920361342616403e-05, + "loss": 4.3771, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919522747865351e-05, + "loss": 4.3572, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918684153114299e-05, + "loss": 4.358, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.917845558363247e-05, + "loss": 4.3554, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.917006963612195e-05, + "loss": 4.3545, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.916171644621889e-05, + "loss": 4.3583, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.915333049870837e-05, + "loss": 4.3416, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.914494455119785e-05, + "loss": 4.3392, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.9136558603687325e-05, + "loss": 4.3352, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.9128172656176805e-05, + "loss": 4.34, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.9119786708666285e-05, + "loss": 4.3212, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.91114171399595e-05, + "loss": 4.3129, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.910303119244898e-05, + "loss": 4.324, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.909464524493846e-05, + "loss": 4.3285, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908625929742794e-05, + "loss": 4.3214, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907787334991742e-05, + "loss": 4.32, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.90694874024069e-05, + "loss": 4.3071, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906110145489638e-05, + "loss": 4.3175, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.905273188618959e-05, + "loss": 4.3005, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.904434593867907e-05, + "loss": 4.3082, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903595999116855e-05, + "loss": 4.3083, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.902757404365803e-05, + "loss": 4.3094, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.901920447495124e-05, + "loss": 4.2979, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.901081852744072e-05, + "loss": 4.2957, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.90024325799302e-05, + "loss": 4.2959, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.8994046632419686e-05, + "loss": 4.2984, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.8985660684909166e-05, + "loss": 4.2861, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.8977274737398646e-05, + "loss": 4.2889, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968888789888125e-05, + "loss": 4.285, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.8960519221181335e-05, + "loss": 4.2868, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.8952133273670815e-05, + "loss": 4.2715, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.8943747326160294e-05, + "loss": 4.2681, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.8935361378649774e-05, + "loss": 4.274, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.8926991809942984e-05, + "loss": 4.2763, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.8918605862432463e-05, + "loss": 4.2667, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.8910219914921943e-05, + "loss": 4.2809, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.8901833967411423e-05, + "loss": 4.2703, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.889346439870464e-05, + "loss": 4.2557, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888507845119412e-05, + "loss": 4.2638, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.88766925036836e-05, + "loss": 4.2722, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886830655617308e-05, + "loss": 4.2618, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885993698746629e-05, + "loss": 4.2588, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.885155103995577e-05, + "loss": 4.2492, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884316509244525e-05, + "loss": 4.257, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883479552373846e-05, + "loss": 4.2614, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882640957622794e-05, + "loss": 4.2466, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.881802362871742e-05, + "loss": 4.2398, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.88096376812069e-05, + "loss": 4.2453, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.880125173369638e-05, + "loss": 4.2382, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.8792882164989586e-05, + "loss": 4.2353, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.878449621747907e-05, + "loss": 4.2438, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877611026996855e-05, + "loss": 4.2317, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.876772432245803e-05, + "loss": 4.2344, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875933837494751e-05, + "loss": 4.2301, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.8750952427436986e-05, + "loss": 4.2256, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.193907260894775, + "eval_runtime": 305.9942, + "eval_samples_per_second": 1247.053, + "eval_steps_per_second": 38.971, + "step": 76320 + }, + { + "epoch": 1.0, + "learning_rate": 4.8742566479926466e-05, + "loss": 4.2149, + "step": 76800 + }, + { + "epoch": 1.0, + "learning_rate": 4.8734180532415946e-05, + "loss": 4.2221, + "step": 77312 + }, + { + "epoch": 1.0, + "learning_rate": 4.872581096370916e-05, + "loss": 4.2301, + "step": 77824 + }, + { + "epoch": 1.0, + "learning_rate": 4.8717425016198635e-05, + "loss": 4.219, + "step": 78336 + }, + { + "epoch": 1.0, + "learning_rate": 4.8709039068688115e-05, + "loss": 4.2201, + "step": 78848 + }, + { + "epoch": 1.0, + "learning_rate": 4.8700653121177595e-05, + "loss": 4.2136, + "step": 79360 + }, + { + "epoch": 1.0, + "learning_rate": 4.869228355247081e-05, + "loss": 4.2104, + "step": 79872 + }, + { + "epoch": 1.0, + "learning_rate": 4.868389760496029e-05, + "loss": 4.1966, + "step": 80384 + }, + { + "epoch": 1.0, + "learning_rate": 4.8675528036253507e-05, + "loss": 4.2225, + "step": 80896 + }, + { + "epoch": 1.0, + "learning_rate": 4.8667142088742986e-05, + "loss": 4.2065, + "step": 81408 + }, + { + "epoch": 1.0, + "learning_rate": 4.865875614123246e-05, + "loss": 4.2163, + "step": 81920 + }, + { + "epoch": 1.0, + "learning_rate": 4.865037019372194e-05, + "loss": 4.2125, + "step": 82432 + }, + { + "epoch": 1.0, + "learning_rate": 4.8642000625015155e-05, + "loss": 4.1956, + "step": 82944 + }, + { + "epoch": 1.0, + "learning_rate": 4.8633614677504635e-05, + "loss": 4.1966, + "step": 83456 + }, + { + "epoch": 1.0, + "learning_rate": 4.862522872999411e-05, + "loss": 4.1915, + "step": 83968 + }, + { + "epoch": 1.0, + "learning_rate": 4.861684278248359e-05, + "loss": 4.1838, + "step": 84480 + }, + { + "epoch": 1.0, + "learning_rate": 4.860845683497307e-05, + "loss": 4.1903, + "step": 84992 + }, + { + "epoch": 1.0, + "learning_rate": 4.860007088746255e-05, + "loss": 4.1828, + "step": 85504 + }, + { + "epoch": 1.0, + "learning_rate": 4.859168493995203e-05, + "loss": 4.1796, + "step": 86016 + }, + { + "epoch": 1.0, + "learning_rate": 4.858329899244151e-05, + "loss": 4.2006, + "step": 86528 + }, + { + "epoch": 1.0, + "learning_rate": 4.8574913044930995e-05, + "loss": 4.1851, + "step": 87040 + }, + { + "epoch": 1.0, + "learning_rate": 4.8566527097420475e-05, + "loss": 4.1773, + "step": 87552 + }, + { + "epoch": 1.0, + "learning_rate": 4.8558141149909955e-05, + "loss": 4.175, + "step": 88064 + }, + { + "epoch": 1.0, + "learning_rate": 4.8549771581203164e-05, + "loss": 4.1887, + "step": 88576 + }, + { + "epoch": 1.0, + "learning_rate": 4.854140201249637e-05, + "loss": 4.167, + "step": 89088 + }, + { + "epoch": 1.0, + "learning_rate": 4.853301606498585e-05, + "loss": 4.163, + "step": 89600 + }, + { + "epoch": 1.0, + "learning_rate": 4.852463011747533e-05, + "loss": 4.1674, + "step": 90112 + }, + { + "epoch": 1.0, + "learning_rate": 4.851624416996481e-05, + "loss": 4.168, + "step": 90624 + }, + { + "epoch": 1.0, + "learning_rate": 4.850785822245429e-05, + "loss": 4.1622, + "step": 91136 + }, + { + "epoch": 1.01, + "learning_rate": 4.849947227494377e-05, + "loss": 4.1625, + "step": 91648 + }, + { + "epoch": 1.01, + "learning_rate": 4.849110270623698e-05, + "loss": 4.1634, + "step": 92160 + }, + { + "epoch": 1.01, + "learning_rate": 4.848271675872646e-05, + "loss": 4.1675, + "step": 92672 + }, + { + "epoch": 1.01, + "learning_rate": 4.847433081121595e-05, + "loss": 4.1523, + "step": 93184 + }, + { + "epoch": 1.01, + "learning_rate": 4.846594486370543e-05, + "loss": 4.1616, + "step": 93696 + }, + { + "epoch": 1.01, + "learning_rate": 4.845755891619491e-05, + "loss": 4.1674, + "step": 94208 + }, + { + "epoch": 1.01, + "learning_rate": 4.844918934748812e-05, + "loss": 4.1636, + "step": 94720 + }, + { + "epoch": 1.01, + "learning_rate": 4.84408033999776e-05, + "loss": 4.1358, + "step": 95232 + }, + { + "epoch": 1.01, + "learning_rate": 4.843241745246708e-05, + "loss": 4.1439, + "step": 95744 + }, + { + "epoch": 1.01, + "learning_rate": 4.842403150495656e-05, + "loss": 4.1424, + "step": 96256 + }, + { + "epoch": 1.01, + "learning_rate": 4.841564555744604e-05, + "loss": 4.1458, + "step": 96768 + }, + { + "epoch": 1.01, + "learning_rate": 4.840725960993552e-05, + "loss": 4.1399, + "step": 97280 + }, + { + "epoch": 1.01, + "learning_rate": 4.8398873662425e-05, + "loss": 4.146, + "step": 97792 + }, + { + "epoch": 1.01, + "learning_rate": 4.839050409371821e-05, + "loss": 4.1351, + "step": 98304 + }, + { + "epoch": 1.01, + "learning_rate": 4.8382118146207687e-05, + "loss": 4.1434, + "step": 98816 + }, + { + "epoch": 1.01, + "learning_rate": 4.8373732198697167e-05, + "loss": 4.1413, + "step": 99328 + }, + { + "epoch": 1.01, + "learning_rate": 4.8365346251186646e-05, + "loss": 4.1428, + "step": 99840 + }, + { + "epoch": 1.01, + "learning_rate": 4.8356960303676126e-05, + "loss": 4.1404, + "step": 100352 + }, + { + "epoch": 1.01, + "learning_rate": 4.8348574356165606e-05, + "loss": 4.1203, + "step": 100864 + }, + { + "epoch": 1.01, + "learning_rate": 4.834020478745882e-05, + "loss": 4.1345, + "step": 101376 + }, + { + "epoch": 1.01, + "learning_rate": 4.8331818839948295e-05, + "loss": 4.1379, + "step": 101888 + }, + { + "epoch": 1.01, + "learning_rate": 4.8323432892437775e-05, + "loss": 4.1326, + "step": 102400 + }, + { + "epoch": 1.01, + "learning_rate": 4.8315046944927255e-05, + "loss": 4.1246, + "step": 102912 + }, + { + "epoch": 1.01, + "learning_rate": 4.8306660997416735e-05, + "loss": 4.1176, + "step": 103424 + }, + { + "epoch": 1.01, + "learning_rate": 4.8298291428709944e-05, + "loss": 4.1278, + "step": 103936 + }, + { + "epoch": 1.01, + "learning_rate": 4.8289905481199424e-05, + "loss": 4.1091, + "step": 104448 + }, + { + "epoch": 1.01, + "learning_rate": 4.8281519533688904e-05, + "loss": 4.1373, + "step": 104960 + }, + { + "epoch": 1.01, + "learning_rate": 4.8273133586178384e-05, + "loss": 4.1155, + "step": 105472 + }, + { + "epoch": 1.01, + "learning_rate": 4.826474763866787e-05, + "loss": 4.1284, + "step": 105984 + }, + { + "epoch": 1.01, + "learning_rate": 4.825636169115735e-05, + "loss": 4.1272, + "step": 106496 + }, + { + "epoch": 1.01, + "learning_rate": 4.824797574364683e-05, + "loss": 4.1017, + "step": 107008 + }, + { + "epoch": 1.01, + "learning_rate": 4.823960617494004e-05, + "loss": 4.1165, + "step": 107520 + }, + { + "epoch": 1.01, + "learning_rate": 4.823122022742952e-05, + "loss": 4.1112, + "step": 108032 + }, + { + "epoch": 1.01, + "learning_rate": 4.8222834279919e-05, + "loss": 4.0996, + "step": 108544 + }, + { + "epoch": 1.01, + "learning_rate": 4.821444833240848e-05, + "loss": 4.0981, + "step": 109056 + }, + { + "epoch": 1.01, + "learning_rate": 4.820607876370169e-05, + "loss": 4.1153, + "step": 109568 + }, + { + "epoch": 1.01, + "learning_rate": 4.819769281619117e-05, + "loss": 4.1039, + "step": 110080 + }, + { + "epoch": 1.01, + "learning_rate": 4.818930686868065e-05, + "loss": 4.0985, + "step": 110592 + }, + { + "epoch": 1.01, + "learning_rate": 4.818092092117013e-05, + "loss": 4.0888, + "step": 111104 + }, + { + "epoch": 1.01, + "learning_rate": 4.817255135246334e-05, + "loss": 4.1075, + "step": 111616 + }, + { + "epoch": 1.01, + "learning_rate": 4.816416540495282e-05, + "loss": 4.1111, + "step": 112128 + }, + { + "epoch": 1.01, + "learning_rate": 4.8155779457442305e-05, + "loss": 4.1065, + "step": 112640 + }, + { + "epoch": 1.01, + "learning_rate": 4.8147393509931785e-05, + "loss": 4.1007, + "step": 113152 + }, + { + "epoch": 1.01, + "learning_rate": 4.8139007562421265e-05, + "loss": 4.1118, + "step": 113664 + }, + { + "epoch": 1.01, + "learning_rate": 4.8130637993714474e-05, + "loss": 4.1066, + "step": 114176 + }, + { + "epoch": 1.01, + "learning_rate": 4.8122252046203954e-05, + "loss": 4.1054, + "step": 114688 + }, + { + "epoch": 1.01, + "learning_rate": 4.8113866098693434e-05, + "loss": 4.0887, + "step": 115200 + }, + { + "epoch": 1.01, + "learning_rate": 4.8105480151182914e-05, + "loss": 4.1013, + "step": 115712 + }, + { + "epoch": 1.01, + "learning_rate": 4.809711058247612e-05, + "loss": 4.0927, + "step": 116224 + }, + { + "epoch": 1.01, + "learning_rate": 4.80887246349656e-05, + "loss": 4.091, + "step": 116736 + }, + { + "epoch": 1.01, + "learning_rate": 4.808033868745508e-05, + "loss": 4.0877, + "step": 117248 + }, + { + "epoch": 1.01, + "learning_rate": 4.807195273994456e-05, + "loss": 4.0923, + "step": 117760 + }, + { + "epoch": 1.01, + "learning_rate": 4.806356679243404e-05, + "loss": 4.1039, + "step": 118272 + }, + { + "epoch": 1.01, + "learning_rate": 4.805519722372726e-05, + "loss": 4.0968, + "step": 118784 + }, + { + "epoch": 1.01, + "learning_rate": 4.804681127621674e-05, + "loss": 4.0725, + "step": 119296 + }, + { + "epoch": 1.01, + "learning_rate": 4.803842532870622e-05, + "loss": 4.0783, + "step": 119808 + }, + { + "epoch": 1.01, + "learning_rate": 4.80300393811957e-05, + "loss": 4.0856, + "step": 120320 + }, + { + "epoch": 1.01, + "learning_rate": 4.802165343368518e-05, + "loss": 4.0833, + "step": 120832 + }, + { + "epoch": 1.01, + "learning_rate": 4.801328386497839e-05, + "loss": 4.0852, + "step": 121344 + }, + { + "epoch": 1.01, + "learning_rate": 4.8004914296271596e-05, + "loss": 4.0805, + "step": 121856 + }, + { + "epoch": 1.02, + "learning_rate": 4.7996528348761076e-05, + "loss": 4.0797, + "step": 122368 + }, + { + "epoch": 1.02, + "learning_rate": 4.7988142401250556e-05, + "loss": 4.0686, + "step": 122880 + }, + { + "epoch": 1.02, + "learning_rate": 4.7979756453740036e-05, + "loss": 4.0794, + "step": 123392 + }, + { + "epoch": 1.02, + "learning_rate": 4.7971370506229516e-05, + "loss": 4.0773, + "step": 123904 + }, + { + "epoch": 1.02, + "learning_rate": 4.7962984558718996e-05, + "loss": 4.0762, + "step": 124416 + }, + { + "epoch": 1.02, + "learning_rate": 4.795461499001221e-05, + "loss": 4.0835, + "step": 124928 + }, + { + "epoch": 1.02, + "learning_rate": 4.794622904250169e-05, + "loss": 4.0746, + "step": 125440 + }, + { + "epoch": 1.02, + "learning_rate": 4.793784309499117e-05, + "loss": 4.0674, + "step": 125952 + }, + { + "epoch": 1.02, + "learning_rate": 4.792945714748065e-05, + "loss": 4.0728, + "step": 126464 + }, + { + "epoch": 1.02, + "learning_rate": 4.792107119997013e-05, + "loss": 4.0732, + "step": 126976 + }, + { + "epoch": 1.02, + "learning_rate": 4.791270163126334e-05, + "loss": 4.0752, + "step": 127488 + }, + { + "epoch": 1.02, + "learning_rate": 4.790431568375282e-05, + "loss": 4.0651, + "step": 128000 + }, + { + "epoch": 1.02, + "learning_rate": 4.78959297362423e-05, + "loss": 4.0608, + "step": 128512 + }, + { + "epoch": 1.02, + "learning_rate": 4.7887543788731774e-05, + "loss": 4.0612, + "step": 129024 + }, + { + "epoch": 1.02, + "learning_rate": 4.7879157841221254e-05, + "loss": 4.0713, + "step": 129536 + }, + { + "epoch": 1.02, + "learning_rate": 4.7870771893710734e-05, + "loss": 4.0542, + "step": 130048 + }, + { + "epoch": 1.02, + "learning_rate": 4.786240232500395e-05, + "loss": 4.0424, + "step": 130560 + }, + { + "epoch": 1.02, + "learning_rate": 4.785401637749343e-05, + "loss": 4.0614, + "step": 131072 + }, + { + "epoch": 1.02, + "learning_rate": 4.784563042998291e-05, + "loss": 4.0617, + "step": 131584 + }, + { + "epoch": 1.02, + "learning_rate": 4.783724448247239e-05, + "loss": 4.0555, + "step": 132096 + }, + { + "epoch": 1.02, + "learning_rate": 4.782885853496187e-05, + "loss": 4.0567, + "step": 132608 + }, + { + "epoch": 1.02, + "learning_rate": 4.782047258745135e-05, + "loss": 4.0518, + "step": 133120 + }, + { + "epoch": 1.02, + "learning_rate": 4.781208663994083e-05, + "loss": 4.06, + "step": 133632 + }, + { + "epoch": 1.02, + "learning_rate": 4.780370069243031e-05, + "loss": 4.0467, + "step": 134144 + }, + { + "epoch": 1.02, + "learning_rate": 4.779531474491979e-05, + "loss": 4.0517, + "step": 134656 + }, + { + "epoch": 1.02, + "learning_rate": 4.7786945176213e-05, + "loss": 4.061, + "step": 135168 + }, + { + "epoch": 1.02, + "learning_rate": 4.777855922870248e-05, + "loss": 4.0615, + "step": 135680 + }, + { + "epoch": 1.02, + "learning_rate": 4.777018965999569e-05, + "loss": 4.048, + "step": 136192 + }, + { + "epoch": 1.02, + "learning_rate": 4.776180371248517e-05, + "loss": 4.0478, + "step": 136704 + }, + { + "epoch": 1.02, + "learning_rate": 4.775341776497465e-05, + "loss": 4.0537, + "step": 137216 + }, + { + "epoch": 1.02, + "learning_rate": 4.7745031817464134e-05, + "loss": 4.0553, + "step": 137728 + }, + { + "epoch": 1.02, + "learning_rate": 4.7736645869953614e-05, + "loss": 4.0399, + "step": 138240 + }, + { + "epoch": 1.02, + "learning_rate": 4.7728259922443094e-05, + "loss": 4.0511, + "step": 138752 + }, + { + "epoch": 1.02, + "learning_rate": 4.7719873974932574e-05, + "loss": 4.0416, + "step": 139264 + }, + { + "epoch": 1.02, + "learning_rate": 4.7711488027422054e-05, + "loss": 4.0541, + "step": 139776 + }, + { + "epoch": 1.02, + "learning_rate": 4.770311845871526e-05, + "loss": 4.0341, + "step": 140288 + }, + { + "epoch": 1.02, + "learning_rate": 4.769473251120474e-05, + "loss": 4.0366, + "step": 140800 + }, + { + "epoch": 1.02, + "learning_rate": 4.768634656369422e-05, + "loss": 4.0399, + "step": 141312 + }, + { + "epoch": 1.02, + "learning_rate": 4.76779606161837e-05, + "loss": 4.0428, + "step": 141824 + }, + { + "epoch": 1.02, + "learning_rate": 4.766959104747691e-05, + "loss": 4.0351, + "step": 142336 + }, + { + "epoch": 1.02, + "learning_rate": 4.766120509996639e-05, + "loss": 4.0529, + "step": 142848 + }, + { + "epoch": 1.02, + "learning_rate": 4.765281915245587e-05, + "loss": 4.0416, + "step": 143360 + }, + { + "epoch": 1.02, + "learning_rate": 4.764443320494535e-05, + "loss": 4.0332, + "step": 143872 + }, + { + "epoch": 1.02, + "learning_rate": 4.763606363623857e-05, + "loss": 4.0343, + "step": 144384 + }, + { + "epoch": 1.02, + "learning_rate": 4.762767768872805e-05, + "loss": 4.0495, + "step": 144896 + }, + { + "epoch": 1.02, + "learning_rate": 4.761929174121753e-05, + "loss": 4.0427, + "step": 145408 + }, + { + "epoch": 1.02, + "learning_rate": 4.761090579370701e-05, + "loss": 4.0376, + "step": 145920 + }, + { + "epoch": 1.02, + "learning_rate": 4.760253622500022e-05, + "loss": 4.0297, + "step": 146432 + }, + { + "epoch": 1.02, + "learning_rate": 4.75941502774897e-05, + "loss": 4.0398, + "step": 146944 + }, + { + "epoch": 1.02, + "learning_rate": 4.758576432997918e-05, + "loss": 4.0432, + "step": 147456 + }, + { + "epoch": 1.02, + "learning_rate": 4.757737838246866e-05, + "loss": 4.0326, + "step": 147968 + }, + { + "epoch": 1.02, + "learning_rate": 4.7569008813761866e-05, + "loss": 4.0278, + "step": 148480 + }, + { + "epoch": 1.02, + "learning_rate": 4.7560622866251346e-05, + "loss": 4.03, + "step": 148992 + }, + { + "epoch": 1.02, + "learning_rate": 4.7552236918740826e-05, + "loss": 4.0257, + "step": 149504 + }, + { + "epoch": 1.02, + "learning_rate": 4.7543867350034035e-05, + "loss": 4.0224, + "step": 150016 + }, + { + "epoch": 1.02, + "learning_rate": 4.753548140252352e-05, + "loss": 4.0376, + "step": 150528 + }, + { + "epoch": 1.02, + "learning_rate": 4.7527095455013e-05, + "loss": 4.0228, + "step": 151040 + }, + { + "epoch": 1.02, + "learning_rate": 4.751870950750248e-05, + "loss": 4.0267, + "step": 151552 + }, + { + "epoch": 1.02, + "learning_rate": 4.751032355999196e-05, + "loss": 4.0247, + "step": 152064 + }, + { + "epoch": 1.02, + "learning_rate": 4.7501937612481435e-05, + "loss": 4.0197, + "step": 152576 + }, + { + "epoch": 1.03, + "eval_loss": 4.026294708251953, + "eval_runtime": 306.1917, + "eval_samples_per_second": 1246.249, + "eval_steps_per_second": 38.946, + "step": 152640 + }, + { + "epoch": 0.0, + "learning_rate": 4.7493551664970914e-05, + "loss": 4.0101, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.7485165717460394e-05, + "loss": 4.0192, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.7476779769949874e-05, + "loss": 4.0327, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.7468393822439354e-05, + "loss": 4.0198, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.7460007874928834e-05, + "loss": 4.0238, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.7451621927418314e-05, + "loss": 4.015, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.7443235979907794e-05, + "loss": 4.0183, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.7434850032397274e-05, + "loss": 4.0012, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.742648046369049e-05, + "loss": 4.0258, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.741809451617997e-05, + "loss": 4.0216, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.740970856866945e-05, + "loss": 4.0176, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.740132262115893e-05, + "loss": 4.0246, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.739295305245214e-05, + "loss": 4.0054, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.738456710494162e-05, + "loss": 4.0074, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.73761811574311e-05, + "loss": 4.0111, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.736779520992058e-05, + "loss": 3.9957, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.735940926241006e-05, + "loss": 4.0045, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.735102331489954e-05, + "loss": 3.9984, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.734263736738902e-05, + "loss": 3.9972, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.73342514198785e-05, + "loss": 4.0236, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.732586547236797e-05, + "loss": 4.0041, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.731747952485746e-05, + "loss": 4.0046, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.730909357734694e-05, + "loss": 3.9952, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.7300724008640154e-05, + "loss": 4.0105, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.7292354439933364e-05, + "loss": 3.9854, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.7283968492422844e-05, + "loss": 3.9907, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.7275582544912323e-05, + "loss": 3.9903, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.72671965974018e-05, + "loss": 3.9992, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.7258810649891277e-05, + "loss": 3.9893, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.7250424702380757e-05, + "loss": 3.9887, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.7242038754870237e-05, + "loss": 3.9958, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.7233652807359716e-05, + "loss": 3.9995, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.7225283238652926e-05, + "loss": 3.9806, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.721689729114241e-05, + "loss": 3.9949, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.720851134363189e-05, + "loss": 3.9978, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.720012539612137e-05, + "loss": 3.9939, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.719175582741458e-05, + "loss": 3.9727, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.718336987990406e-05, + "loss": 3.9834, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.717498393239354e-05, + "loss": 3.973, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.716659798488302e-05, + "loss": 3.9852, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.715822841617623e-05, + "loss": 3.9788, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.714984246866571e-05, + "loss": 3.9865, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.714145652115519e-05, + "loss": 3.9769, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.713307057364467e-05, + "loss": 3.9808, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.712470100493788e-05, + "loss": 3.9854, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.7116315057427366e-05, + "loss": 3.9878, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.7107929109916846e-05, + "loss": 3.983, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.7099543162406326e-05, + "loss": 3.963, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.7091173593699535e-05, + "loss": 3.9769, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.7082787646189015e-05, + "loss": 3.9864, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.7074401698678495e-05, + "loss": 3.9742, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.7066032129971704e-05, + "loss": 3.9706, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.7057646182461184e-05, + "loss": 3.968, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.7049260234950664e-05, + "loss": 3.9735, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.7040874287440144e-05, + "loss": 3.959, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.7032488339929624e-05, + "loss": 3.9818, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.7024102392419104e-05, + "loss": 3.9704, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.7015716444908584e-05, + "loss": 3.9748, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.7007330497398064e-05, + "loss": 3.984, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.699896092869128e-05, + "loss": 3.9512, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.699057498118076e-05, + "loss": 3.969, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.698218903367024e-05, + "loss": 3.963, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.697380308615972e-05, + "loss": 3.957, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.696543351745293e-05, + "loss": 3.9524, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.695704756994241e-05, + "loss": 3.9674, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694866162243189e-05, + "loss": 3.9615, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.694027567492137e-05, + "loss": 3.9541, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.693190610621458e-05, + "loss": 3.9458, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.692352015870406e-05, + "loss": 3.9663, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.691513421119354e-05, + "loss": 3.9716, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.690674826368302e-05, + "loss": 3.9639, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.689837869497623e-05, + "loss": 3.9618, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.688999274746571e-05, + "loss": 3.9716, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.688160679995519e-05, + "loss": 3.9654, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.687322085244467e-05, + "loss": 3.9699, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.686485128373788e-05, + "loss": 3.9469, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.685646533622736e-05, + "loss": 3.9644, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.684807938871684e-05, + "loss": 3.9589, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.683969344120632e-05, + "loss": 3.952, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.683132387249953e-05, + "loss": 3.9567, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.682293792498901e-05, + "loss": 3.9586, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.681455197747849e-05, + "loss": 3.969, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.680616602996797e-05, + "loss": 3.9566, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.679779646126119e-05, + "loss": 3.9384, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.678941051375067e-05, + "loss": 3.9439, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.678102456624015e-05, + "loss": 3.9511, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.677263861872963e-05, + "loss": 3.9541, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.6764285428826565e-05, + "loss": 3.9536, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.6755899481316045e-05, + "loss": 3.9478, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.6747513533805525e-05, + "loss": 3.9491, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.6739127586295005e-05, + "loss": 3.9381, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.6730741638784485e-05, + "loss": 3.9527, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.6722355691273965e-05, + "loss": 3.9436, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.6713969743763445e-05, + "loss": 3.9478, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.670560017505666e-05, + "loss": 3.9575, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.669721422754614e-05, + "loss": 3.9477, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.668882828003562e-05, + "loss": 3.9403, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.66804423325251e-05, + "loss": 3.9468, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.667205638501458e-05, + "loss": 3.9453, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.666368681630779e-05, + "loss": 3.948, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.665530086879727e-05, + "loss": 3.9415, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.664691492128675e-05, + "loss": 3.9387, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.663852897377623e-05, + "loss": 3.9327, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.66301430262657e-05, + "loss": 3.9468, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.662175707875518e-05, + "loss": 3.9344, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.66133875100484e-05, + "loss": 3.9226, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.660500156253788e-05, + "loss": 3.9345, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.659661561502736e-05, + "loss": 3.9402, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.658822966751684e-05, + "loss": 3.9311, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.657984372000632e-05, + "loss": 3.9402, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.65714577724958e-05, + "loss": 3.9285, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.656307182498528e-05, + "loss": 3.941, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.655468587747476e-05, + "loss": 3.9271, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.654631630876797e-05, + "loss": 3.9285, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.6537946740061176e-05, + "loss": 3.9455, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.6529560792550656e-05, + "loss": 3.9411, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.6521174845040136e-05, + "loss": 3.9305, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.6512788897529616e-05, + "loss": 3.9321, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.6504402950019096e-05, + "loss": 3.9302, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.649603338131231e-05, + "loss": 3.9368, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.648764743380179e-05, + "loss": 3.9238, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.647926148629127e-05, + "loss": 3.9362, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.647087553878075e-05, + "loss": 3.9261, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.646248959127023e-05, + "loss": 3.9368, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.645410364375971e-05, + "loss": 3.9161, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.644571769624919e-05, + "loss": 3.9263, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.64373481275424e-05, + "loss": 3.9212, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.642896218003188e-05, + "loss": 3.9272, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.642057623252136e-05, + "loss": 3.9233, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.641219028501084e-05, + "loss": 3.9417, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.640382071630405e-05, + "loss": 3.9288, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.6395434768793536e-05, + "loss": 3.9228, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.6387048821283016e-05, + "loss": 3.9169, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.6378662873772496e-05, + "loss": 3.9355, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.6370276926261976e-05, + "loss": 3.9314, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.6361907357555185e-05, + "loss": 3.9288, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.6353521410044665e-05, + "loss": 3.9203, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.6345135462534145e-05, + "loss": 3.9267, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.6336749515023625e-05, + "loss": 3.9319, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.6328363567513105e-05, + "loss": 3.9228, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.6319977620002585e-05, + "loss": 3.9174, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.631159167249206e-05, + "loss": 3.9234, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.630320572498154e-05, + "loss": 3.9186, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.6294836156274754e-05, + "loss": 3.9116, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.628646658756797e-05, + "loss": 3.9268, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.627808064005745e-05, + "loss": 3.9225, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.626969469254693e-05, + "loss": 3.9167, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.626130874503641e-05, + "loss": 3.9151, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.625293917632962e-05, + "loss": 3.9124, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 3.9520537853240967, + "eval_runtime": 306.6915, + "eval_samples_per_second": 1244.218, + "eval_steps_per_second": 38.883, + "step": 228960 + }, + { + "epoch": 1.0, + "learning_rate": 4.62445532288191e-05, + "loss": 3.9144, + "step": 229376 + }, + { + "epoch": 1.0, + "learning_rate": 4.623616728130858e-05, + "loss": 3.9133, + "step": 229888 + }, + { + "epoch": 1.0, + "learning_rate": 4.622778133379806e-05, + "loss": 3.9265, + "step": 230400 + }, + { + "epoch": 1.0, + "learning_rate": 4.621939538628753e-05, + "loss": 3.9128, + "step": 230912 + }, + { + "epoch": 1.0, + "learning_rate": 4.621100943877701e-05, + "loss": 3.9216, + "step": 231424 + }, + { + "epoch": 1.0, + "learning_rate": 4.620262349126649e-05, + "loss": 3.9075, + "step": 231936 + }, + { + "epoch": 1.0, + "learning_rate": 4.619425392255971e-05, + "loss": 3.9152, + "step": 232448 + }, + { + "epoch": 1.0, + "learning_rate": 4.618586797504919e-05, + "loss": 3.8992, + "step": 232960 + }, + { + "epoch": 1.0, + "learning_rate": 4.617748202753867e-05, + "loss": 3.9235, + "step": 233472 + }, + { + "epoch": 1.0, + "learning_rate": 4.616909608002815e-05, + "loss": 3.9174, + "step": 233984 + }, + { + "epoch": 1.0, + "learning_rate": 4.6160726511321364e-05, + "loss": 3.9151, + "step": 234496 + }, + { + "epoch": 1.0, + "learning_rate": 4.615234056381084e-05, + "loss": 3.9203, + "step": 235008 + }, + { + "epoch": 1.0, + "learning_rate": 4.614397099510405e-05, + "loss": 3.9006, + "step": 235520 + }, + { + "epoch": 1.0, + "learning_rate": 4.613558504759353e-05, + "loss": 3.9055, + "step": 236032 + }, + { + "epoch": 1.0, + "learning_rate": 4.6127199100083006e-05, + "loss": 3.9108, + "step": 236544 + }, + { + "epoch": 1.0, + "learning_rate": 4.6118813152572486e-05, + "loss": 3.8995, + "step": 237056 + }, + { + "epoch": 1.0, + "learning_rate": 4.6110427205061966e-05, + "loss": 3.8992, + "step": 237568 + }, + { + "epoch": 1.0, + "learning_rate": 4.6102041257551446e-05, + "loss": 3.8967, + "step": 238080 + }, + { + "epoch": 1.0, + "learning_rate": 4.6093655310040926e-05, + "loss": 3.8984, + "step": 238592 + }, + { + "epoch": 1.0, + "learning_rate": 4.6085269362530406e-05, + "loss": 3.9262, + "step": 239104 + }, + { + "epoch": 1.0, + "learning_rate": 4.607688341501989e-05, + "loss": 3.9033, + "step": 239616 + }, + { + "epoch": 1.0, + "learning_rate": 4.60685138463131e-05, + "loss": 3.9033, + "step": 240128 + }, + { + "epoch": 1.0, + "learning_rate": 4.606012789880258e-05, + "loss": 3.8991, + "step": 240640 + }, + { + "epoch": 1.0, + "learning_rate": 4.605174195129206e-05, + "loss": 3.9071, + "step": 241152 + }, + { + "epoch": 1.0, + "learning_rate": 4.604335600378154e-05, + "loss": 3.8902, + "step": 241664 + }, + { + "epoch": 1.0, + "learning_rate": 4.603497005627102e-05, + "loss": 3.8919, + "step": 242176 + }, + { + "epoch": 1.0, + "learning_rate": 4.60265841087605e-05, + "loss": 3.8959, + "step": 242688 + }, + { + "epoch": 1.0, + "learning_rate": 4.601821454005371e-05, + "loss": 3.9045, + "step": 243200 + }, + { + "epoch": 1.0, + "learning_rate": 4.600982859254319e-05, + "loss": 3.8882, + "step": 243712 + }, + { + "epoch": 1.01, + "learning_rate": 4.600144264503267e-05, + "loss": 3.8946, + "step": 244224 + }, + { + "epoch": 1.01, + "learning_rate": 4.599305669752215e-05, + "loss": 3.8947, + "step": 244736 + }, + { + "epoch": 1.01, + "learning_rate": 4.598468712881536e-05, + "loss": 3.9034, + "step": 245248 + }, + { + "epoch": 1.01, + "learning_rate": 4.5976301181304846e-05, + "loss": 3.8915, + "step": 245760 + }, + { + "epoch": 1.01, + "learning_rate": 4.5967915233794326e-05, + "loss": 3.8959, + "step": 246272 + }, + { + "epoch": 1.01, + "learning_rate": 4.5959529286283806e-05, + "loss": 3.9, + "step": 246784 + }, + { + "epoch": 1.01, + "learning_rate": 4.5951143338773286e-05, + "loss": 3.8998, + "step": 247296 + }, + { + "epoch": 1.01, + "learning_rate": 4.5942757391262766e-05, + "loss": 3.8787, + "step": 247808 + }, + { + "epoch": 1.01, + "learning_rate": 4.5934371443752246e-05, + "loss": 3.8921, + "step": 248320 + }, + { + "epoch": 1.01, + "learning_rate": 4.5926001875045455e-05, + "loss": 3.8779, + "step": 248832 + }, + { + "epoch": 1.01, + "learning_rate": 4.5917615927534935e-05, + "loss": 3.893, + "step": 249344 + }, + { + "epoch": 1.01, + "learning_rate": 4.5909229980024415e-05, + "loss": 3.8832, + "step": 249856 + }, + { + "epoch": 1.01, + "learning_rate": 4.5900844032513895e-05, + "loss": 3.8952, + "step": 250368 + }, + { + "epoch": 1.01, + "learning_rate": 4.5892474463807104e-05, + "loss": 3.8876, + "step": 250880 + }, + { + "epoch": 1.01, + "learning_rate": 4.5884088516296584e-05, + "loss": 3.8856, + "step": 251392 + }, + { + "epoch": 1.01, + "learning_rate": 4.5875702568786064e-05, + "loss": 3.8948, + "step": 251904 + }, + { + "epoch": 1.01, + "learning_rate": 4.5867316621275544e-05, + "loss": 3.8937, + "step": 252416 + }, + { + "epoch": 1.01, + "learning_rate": 4.585894705256876e-05, + "loss": 3.8889, + "step": 252928 + }, + { + "epoch": 1.01, + "learning_rate": 4.585056110505824e-05, + "loss": 3.8764, + "step": 253440 + }, + { + "epoch": 1.01, + "learning_rate": 4.584217515754772e-05, + "loss": 3.882, + "step": 253952 + }, + { + "epoch": 1.01, + "learning_rate": 4.58337892100372e-05, + "loss": 3.8963, + "step": 254464 + }, + { + "epoch": 1.01, + "learning_rate": 4.582541964133041e-05, + "loss": 3.8853, + "step": 254976 + }, + { + "epoch": 1.01, + "learning_rate": 4.581703369381989e-05, + "loss": 3.8781, + "step": 255488 + }, + { + "epoch": 1.01, + "learning_rate": 4.580864774630937e-05, + "loss": 3.8791, + "step": 256000 + }, + { + "epoch": 1.01, + "learning_rate": 4.580026179879884e-05, + "loss": 3.8866, + "step": 256512 + }, + { + "epoch": 1.01, + "learning_rate": 4.579187585128832e-05, + "loss": 3.8692, + "step": 257024 + }, + { + "epoch": 1.01, + "learning_rate": 4.578350628258154e-05, + "loss": 3.8874, + "step": 257536 + }, + { + "epoch": 1.01, + "learning_rate": 4.577512033507102e-05, + "loss": 3.88, + "step": 258048 + }, + { + "epoch": 1.01, + "learning_rate": 4.57667343875605e-05, + "loss": 3.8873, + "step": 258560 + }, + { + "epoch": 1.01, + "learning_rate": 4.575834844004998e-05, + "loss": 3.8905, + "step": 259072 + }, + { + "epoch": 1.01, + "learning_rate": 4.574997887134319e-05, + "loss": 3.8691, + "step": 259584 + }, + { + "epoch": 1.01, + "learning_rate": 4.5741592923832666e-05, + "loss": 3.8722, + "step": 260096 + }, + { + "epoch": 1.01, + "learning_rate": 4.5733206976322146e-05, + "loss": 3.8796, + "step": 260608 + }, + { + "epoch": 1.01, + "learning_rate": 4.5724821028811626e-05, + "loss": 3.8671, + "step": 261120 + }, + { + "epoch": 1.01, + "learning_rate": 4.571645146010484e-05, + "loss": 3.8675, + "step": 261632 + }, + { + "epoch": 1.01, + "learning_rate": 4.5708065512594315e-05, + "loss": 3.8785, + "step": 262144 + }, + { + "epoch": 1.01, + "learning_rate": 4.5699679565083795e-05, + "loss": 3.877, + "step": 262656 + }, + { + "epoch": 1.01, + "learning_rate": 4.5691293617573275e-05, + "loss": 3.8672, + "step": 263168 + }, + { + "epoch": 1.01, + "learning_rate": 4.5682907670062755e-05, + "loss": 3.8603, + "step": 263680 + }, + { + "epoch": 1.01, + "learning_rate": 4.567453810135597e-05, + "loss": 3.8755, + "step": 264192 + }, + { + "epoch": 1.01, + "learning_rate": 4.566615215384545e-05, + "loss": 3.8833, + "step": 264704 + }, + { + "epoch": 1.01, + "learning_rate": 4.565776620633493e-05, + "loss": 3.8752, + "step": 265216 + }, + { + "epoch": 1.01, + "learning_rate": 4.564938025882441e-05, + "loss": 3.8797, + "step": 265728 + }, + { + "epoch": 1.01, + "learning_rate": 4.564099431131389e-05, + "loss": 3.8854, + "step": 266240 + }, + { + "epoch": 1.01, + "learning_rate": 4.56326247426071e-05, + "loss": 3.8816, + "step": 266752 + }, + { + "epoch": 1.01, + "learning_rate": 4.562423879509658e-05, + "loss": 3.8879, + "step": 267264 + }, + { + "epoch": 1.01, + "learning_rate": 4.561585284758606e-05, + "loss": 3.8603, + "step": 267776 + }, + { + "epoch": 1.01, + "learning_rate": 4.560746690007554e-05, + "loss": 3.8801, + "step": 268288 + }, + { + "epoch": 1.01, + "learning_rate": 4.559909733136875e-05, + "loss": 3.8794, + "step": 268800 + }, + { + "epoch": 1.01, + "learning_rate": 4.559071138385823e-05, + "loss": 3.865, + "step": 269312 + }, + { + "epoch": 1.01, + "learning_rate": 4.558232543634771e-05, + "loss": 3.877, + "step": 269824 + }, + { + "epoch": 1.01, + "learning_rate": 4.557393948883719e-05, + "loss": 3.8723, + "step": 270336 + }, + { + "epoch": 1.01, + "learning_rate": 4.5565569920130405e-05, + "loss": 3.8817, + "step": 270848 + }, + { + "epoch": 1.01, + "learning_rate": 4.5557183972619885e-05, + "loss": 3.875, + "step": 271360 + }, + { + "epoch": 1.01, + "learning_rate": 4.5548798025109365e-05, + "loss": 3.8547, + "step": 271872 + }, + { + "epoch": 1.01, + "learning_rate": 4.5540412077598845e-05, + "loss": 3.8629, + "step": 272384 + }, + { + "epoch": 1.01, + "learning_rate": 4.5532026130088325e-05, + "loss": 3.8663, + "step": 272896 + }, + { + "epoch": 1.01, + "learning_rate": 4.5523656561381534e-05, + "loss": 3.871, + "step": 273408 + }, + { + "epoch": 1.01, + "learning_rate": 4.5515270613871014e-05, + "loss": 3.8725, + "step": 273920 + }, + { + "epoch": 1.01, + "learning_rate": 4.5506884666360494e-05, + "loss": 3.8649, + "step": 274432 + }, + { + "epoch": 1.02, + "learning_rate": 4.5498498718849973e-05, + "loss": 3.8662, + "step": 274944 + }, + { + "epoch": 1.02, + "learning_rate": 4.549012915014318e-05, + "loss": 3.8582, + "step": 275456 + }, + { + "epoch": 1.02, + "learning_rate": 4.548174320263266e-05, + "loss": 3.8688, + "step": 275968 + }, + { + "epoch": 1.02, + "learning_rate": 4.547335725512214e-05, + "loss": 3.861, + "step": 276480 + }, + { + "epoch": 1.02, + "learning_rate": 4.546497130761162e-05, + "loss": 3.869, + "step": 276992 + }, + { + "epoch": 1.02, + "learning_rate": 4.545660173890484e-05, + "loss": 3.8784, + "step": 277504 + }, + { + "epoch": 1.02, + "learning_rate": 4.544821579139432e-05, + "loss": 3.869, + "step": 278016 + }, + { + "epoch": 1.02, + "learning_rate": 4.54398298438838e-05, + "loss": 3.8584, + "step": 278528 + }, + { + "epoch": 1.02, + "learning_rate": 4.543144389637328e-05, + "loss": 3.8675, + "step": 279040 + }, + { + "epoch": 1.02, + "learning_rate": 4.542307432766649e-05, + "loss": 3.8645, + "step": 279552 + }, + { + "epoch": 1.02, + "learning_rate": 4.541468838015597e-05, + "loss": 3.8687, + "step": 280064 + }, + { + "epoch": 1.02, + "learning_rate": 4.540630243264545e-05, + "loss": 3.8634, + "step": 280576 + }, + { + "epoch": 1.02, + "learning_rate": 4.539791648513493e-05, + "loss": 3.8597, + "step": 281088 + }, + { + "epoch": 1.02, + "learning_rate": 4.538953053762441e-05, + "loss": 3.8526, + "step": 281600 + }, + { + "epoch": 1.02, + "learning_rate": 4.5381160968917616e-05, + "loss": 3.869, + "step": 282112 + }, + { + "epoch": 1.02, + "learning_rate": 4.5372775021407096e-05, + "loss": 3.8509, + "step": 282624 + }, + { + "epoch": 1.02, + "learning_rate": 4.5364389073896576e-05, + "loss": 3.8468, + "step": 283136 + }, + { + "epoch": 1.02, + "learning_rate": 4.535600312638606e-05, + "loss": 3.8533, + "step": 283648 + }, + { + "epoch": 1.02, + "learning_rate": 4.534763355767927e-05, + "loss": 3.8607, + "step": 284160 + }, + { + "epoch": 1.02, + "learning_rate": 4.533924761016875e-05, + "loss": 3.8546, + "step": 284672 + }, + { + "epoch": 1.02, + "learning_rate": 4.533086166265823e-05, + "loss": 3.8672, + "step": 285184 + }, + { + "epoch": 1.02, + "learning_rate": 4.532247571514771e-05, + "loss": 3.8516, + "step": 285696 + }, + { + "epoch": 1.02, + "learning_rate": 4.531408976763719e-05, + "loss": 3.8546, + "step": 286208 + }, + { + "epoch": 1.02, + "learning_rate": 4.53057201989304e-05, + "loss": 3.8549, + "step": 286720 + }, + { + "epoch": 1.02, + "learning_rate": 4.529733425141988e-05, + "loss": 3.8463, + "step": 287232 + }, + { + "epoch": 1.02, + "learning_rate": 4.528894830390936e-05, + "loss": 3.8712, + "step": 287744 + }, + { + "epoch": 1.02, + "learning_rate": 4.528056235639884e-05, + "loss": 3.8629, + "step": 288256 + }, + { + "epoch": 1.02, + "learning_rate": 4.527219278769205e-05, + "loss": 3.8561, + "step": 288768 + }, + { + "epoch": 1.02, + "learning_rate": 4.526380684018153e-05, + "loss": 3.8549, + "step": 289280 + }, + { + "epoch": 1.02, + "learning_rate": 4.5255420892671017e-05, + "loss": 3.85, + "step": 289792 + }, + { + "epoch": 1.02, + "learning_rate": 4.5247034945160496e-05, + "loss": 3.861, + "step": 290304 + }, + { + "epoch": 1.02, + "learning_rate": 4.5238665376453706e-05, + "loss": 3.8484, + "step": 290816 + }, + { + "epoch": 1.02, + "learning_rate": 4.5230279428943186e-05, + "loss": 3.8634, + "step": 291328 + }, + { + "epoch": 1.02, + "learning_rate": 4.5221893481432665e-05, + "loss": 3.8477, + "step": 291840 + }, + { + "epoch": 1.02, + "learning_rate": 4.5213507533922145e-05, + "loss": 3.8566, + "step": 292352 + }, + { + "epoch": 1.02, + "learning_rate": 4.5205137965215355e-05, + "loss": 3.8469, + "step": 292864 + }, + { + "epoch": 1.02, + "learning_rate": 4.5196752017704834e-05, + "loss": 3.8501, + "step": 293376 + }, + { + "epoch": 1.02, + "learning_rate": 4.5188366070194314e-05, + "loss": 3.8478, + "step": 293888 + }, + { + "epoch": 1.02, + "learning_rate": 4.5179980122683794e-05, + "loss": 3.8525, + "step": 294400 + }, + { + "epoch": 1.02, + "learning_rate": 4.5171610553977003e-05, + "loss": 3.8467, + "step": 294912 + }, + { + "epoch": 1.02, + "learning_rate": 4.5163224606466483e-05, + "loss": 3.8653, + "step": 295424 + }, + { + "epoch": 1.02, + "learning_rate": 4.515483865895597e-05, + "loss": 3.8575, + "step": 295936 + }, + { + "epoch": 1.02, + "learning_rate": 4.514645271144545e-05, + "loss": 3.8499, + "step": 296448 + }, + { + "epoch": 1.02, + "learning_rate": 4.513808314273866e-05, + "loss": 3.8391, + "step": 296960 + }, + { + "epoch": 1.02, + "learning_rate": 4.512969719522814e-05, + "loss": 3.8597, + "step": 297472 + }, + { + "epoch": 1.02, + "learning_rate": 4.512131124771762e-05, + "loss": 3.8548, + "step": 297984 + }, + { + "epoch": 1.02, + "learning_rate": 4.51129253002071e-05, + "loss": 3.8591, + "step": 298496 + }, + { + "epoch": 1.02, + "learning_rate": 4.510455573150031e-05, + "loss": 3.8461, + "step": 299008 + }, + { + "epoch": 1.02, + "learning_rate": 4.509616978398979e-05, + "loss": 3.8507, + "step": 299520 + }, + { + "epoch": 1.02, + "learning_rate": 4.508778383647927e-05, + "loss": 3.8584, + "step": 300032 + }, + { + "epoch": 1.02, + "learning_rate": 4.507939788896874e-05, + "loss": 3.8529, + "step": 300544 + }, + { + "epoch": 1.02, + "learning_rate": 4.507102832026196e-05, + "loss": 3.8431, + "step": 301056 + }, + { + "epoch": 1.02, + "learning_rate": 4.506264237275144e-05, + "loss": 3.8518, + "step": 301568 + }, + { + "epoch": 1.02, + "learning_rate": 4.5054256425240924e-05, + "loss": 3.8436, + "step": 302080 + }, + { + "epoch": 1.02, + "learning_rate": 4.50458704777304e-05, + "loss": 3.8399, + "step": 302592 + }, + { + "epoch": 1.02, + "learning_rate": 4.503750090902361e-05, + "loss": 3.8527, + "step": 303104 + }, + { + "epoch": 1.02, + "learning_rate": 4.502911496151309e-05, + "loss": 3.8546, + "step": 303616 + }, + { + "epoch": 1.02, + "learning_rate": 4.502072901400257e-05, + "loss": 3.8425, + "step": 304128 + }, + { + "epoch": 1.02, + "learning_rate": 4.5012343066492046e-05, + "loss": 3.8414, + "step": 304640 + }, + { + "epoch": 1.02, + "learning_rate": 4.5003957118981526e-05, + "loss": 3.8474, + "step": 305152 + }, + { + "epoch": 1.03, + "eval_loss": 3.9112818241119385, + "eval_runtime": 306.1952, + "eval_samples_per_second": 1246.234, + "eval_steps_per_second": 38.946, + "step": 305280 + }, + { + "epoch": 0.0, + "learning_rate": 4.4995571171471006e-05, + "loss": 3.8358, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.4987185223960486e-05, + "loss": 3.8425, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.4978799276449966e-05, + "loss": 3.8536, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.4970413328939446e-05, + "loss": 3.844, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.4962027381428926e-05, + "loss": 3.8547, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.4953641433918406e-05, + "loss": 3.8367, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.4945255486407886e-05, + "loss": 3.8423, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.493686953889737e-05, + "loss": 3.8291, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.492849997019058e-05, + "loss": 3.8536, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.492011402268006e-05, + "loss": 3.8459, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.491172807516954e-05, + "loss": 3.8432, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.490334212765902e-05, + "loss": 3.8532, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.489498893775596e-05, + "loss": 3.8297, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.488660299024544e-05, + "loss": 3.8409, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.487821704273492e-05, + "loss": 3.8414, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.48698310952244e-05, + "loss": 3.8296, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.486144514771388e-05, + "loss": 3.83, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.485305920020336e-05, + "loss": 3.8291, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.484467325269284e-05, + "loss": 3.8335, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.4836287305182326e-05, + "loss": 3.8524, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.4827917736475535e-05, + "loss": 3.8368, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.4819531788965015e-05, + "loss": 3.8332, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.4811145841454495e-05, + "loss": 3.8306, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.4802759893943975e-05, + "loss": 3.8414, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.4794390325237184e-05, + "loss": 3.8241, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.4786004377726664e-05, + "loss": 3.8267, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.4777618430216144e-05, + "loss": 3.8255, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.4769232482705624e-05, + "loss": 3.837, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.476086291399883e-05, + "loss": 3.8197, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.475247696648831e-05, + "loss": 3.8293, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.474409101897779e-05, + "loss": 3.8297, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.473570507146728e-05, + "loss": 3.836, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.472733550276049e-05, + "loss": 3.8248, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.471894955524997e-05, + "loss": 3.8301, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.471056360773945e-05, + "loss": 3.8319, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.470217766022893e-05, + "loss": 3.8335, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.469380809152214e-05, + "loss": 3.8184, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.468542214401162e-05, + "loss": 3.821, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.46770361965011e-05, + "loss": 3.8122, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.466865024899058e-05, + "loss": 3.8252, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.466028068028379e-05, + "loss": 3.8173, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.465189473277327e-05, + "loss": 3.8284, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.464350878526275e-05, + "loss": 3.8233, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.463512283775223e-05, + "loss": 3.824, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.462675326904544e-05, + "loss": 3.8282, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.461836732153492e-05, + "loss": 3.8282, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.46099813740244e-05, + "loss": 3.8277, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.460159542651388e-05, + "loss": 3.8135, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.459322585780709e-05, + "loss": 3.8087, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.458483991029657e-05, + "loss": 3.8329, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.457645396278605e-05, + "loss": 3.8218, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.4568068015275525e-05, + "loss": 3.8155, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.455969844656874e-05, + "loss": 3.816, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.455131249905822e-05, + "loss": 3.8231, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.45429265515477e-05, + "loss": 3.8039, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.453454060403718e-05, + "loss": 3.8254, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.4526171035330396e-05, + "loss": 3.8182, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.4517785087819876e-05, + "loss": 3.8217, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.4509399140309356e-05, + "loss": 3.8284, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.450101319279883e-05, + "loss": 3.8111, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.4492643624092045e-05, + "loss": 3.8072, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.4484257676581525e-05, + "loss": 3.8228, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.4475871729071e-05, + "loss": 3.8005, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.446748578156048e-05, + "loss": 3.8044, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.4459116212853694e-05, + "loss": 3.8172, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.4450730265343174e-05, + "loss": 3.8159, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.4442344317832654e-05, + "loss": 3.8052, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.4433958370322134e-05, + "loss": 3.8014, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.442558880161535e-05, + "loss": 3.8123, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.441720285410482e-05, + "loss": 3.8193, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.44088169065943e-05, + "loss": 3.8168, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.440043095908378e-05, + "loss": 3.8136, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.4392061390377e-05, + "loss": 3.8249, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.438367544286647e-05, + "loss": 3.8169, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.437528949535595e-05, + "loss": 3.8298, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.436690354784543e-05, + "loss": 3.7998, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.435853397913865e-05, + "loss": 3.8201, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.435014803162813e-05, + "loss": 3.8149, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.434176208411761e-05, + "loss": 3.803, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.433337613660709e-05, + "loss": 3.8203, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.432499018909657e-05, + "loss": 3.8112, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.431662062038978e-05, + "loss": 3.8196, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.4308234672879257e-05, + "loss": 3.8184, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.4299848725368737e-05, + "loss": 3.7941, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.4291462777858217e-05, + "loss": 3.8053, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.4283093209151426e-05, + "loss": 3.8038, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.4274707261640906e-05, + "loss": 3.8151, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.4266321314130386e-05, + "loss": 3.812, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.4257935366619865e-05, + "loss": 3.8047, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.424956579791308e-05, + "loss": 3.8095, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.424117985040256e-05, + "loss": 3.8005, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.423279390289204e-05, + "loss": 3.8066, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.422440795538152e-05, + "loss": 3.8017, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.421603838667473e-05, + "loss": 3.8109, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.420765243916421e-05, + "loss": 3.819, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.419926649165369e-05, + "loss": 3.8092, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.419088054414317e-05, + "loss": 3.7986, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.418251097543638e-05, + "loss": 3.8073, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.417412502792586e-05, + "loss": 3.8087, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.416573908041534e-05, + "loss": 3.8124, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.415735313290482e-05, + "loss": 3.8058, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.4148983564198035e-05, + "loss": 3.8004, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.4140597616687515e-05, + "loss": 3.7948, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.4132211669176995e-05, + "loss": 3.8091, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.4123825721666475e-05, + "loss": 3.7941, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.4115456152959684e-05, + "loss": 3.7932, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.4107070205449164e-05, + "loss": 3.7915, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.4098684257938644e-05, + "loss": 3.8061, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.4090298310428124e-05, + "loss": 3.7899, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.408192874172133e-05, + "loss": 3.8147, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.407354279421081e-05, + "loss": 3.7898, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.406515684670029e-05, + "loss": 3.8033, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.405677089918977e-05, + "loss": 3.7987, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.404840133048299e-05, + "loss": 3.7898, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.404001538297247e-05, + "loss": 3.8142, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.403162943546195e-05, + "loss": 3.8093, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.402324348795143e-05, + "loss": 3.7997, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.401487391924464e-05, + "loss": 3.798, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.400648797173412e-05, + "loss": 3.7939, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.39981020242236e-05, + "loss": 3.8044, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.398971607671308e-05, + "loss": 3.7873, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.3981346508006287e-05, + "loss": 3.809, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.3972960560495767e-05, + "loss": 3.7962, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.3964574612985247e-05, + "loss": 3.7991, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.3956188665474726e-05, + "loss": 3.7941, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.394781909676794e-05, + "loss": 3.795, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.393943314925742e-05, + "loss": 3.7892, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.39310472017469e-05, + "loss": 3.7996, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.392266125423638e-05, + "loss": 3.7923, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.391429168552959e-05, + "loss": 3.808, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.390590573801907e-05, + "loss": 3.8012, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.389751979050855e-05, + "loss": 3.7982, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.388913384299803e-05, + "loss": 3.7842, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.388076427429124e-05, + "loss": 3.8034, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.387237832678072e-05, + "loss": 3.7992, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.38639923792702e-05, + "loss": 3.801, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.385560643175968e-05, + "loss": 3.7908, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.3847236863052896e-05, + "loss": 3.7961, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.3838850915542376e-05, + "loss": 3.7999, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.3830464968031856e-05, + "loss": 3.8048, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.3822079020521336e-05, + "loss": 3.7873, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.3813709451814545e-05, + "loss": 3.7983, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.3805323504304025e-05, + "loss": 3.7867, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.3796937556793505e-05, + "loss": 3.7867, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.3788567988086714e-05, + "loss": 3.8026, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.3780182040576194e-05, + "loss": 3.7927, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.3771796093065674e-05, + "loss": 3.7914, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.3763410145555154e-05, + "loss": 3.7865, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.3755024198044634e-05, + "loss": 3.7939, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 3.8861770629882812, + "eval_runtime": 307.5955, + "eval_samples_per_second": 1240.561, + "eval_steps_per_second": 38.768, + "step": 381600 + }, + { + "epoch": 1.0, + "learning_rate": 4.3746638250534114e-05, + "loss": 3.7894, + "step": 381952 + }, + { + "epoch": 1.0, + "learning_rate": 4.3738252303023594e-05, + "loss": 3.7851, + "step": 382464 + }, + { + "epoch": 1.0, + "learning_rate": 4.372986635551308e-05, + "loss": 3.8008, + "step": 382976 + }, + { + "epoch": 1.0, + "learning_rate": 4.372149678680629e-05, + "loss": 3.7926, + "step": 383488 + }, + { + "epoch": 1.0, + "learning_rate": 4.371311083929577e-05, + "loss": 3.7946, + "step": 384000 + }, + { + "epoch": 1.0, + "learning_rate": 4.370472489178525e-05, + "loss": 3.7909, + "step": 384512 + }, + { + "epoch": 1.0, + "learning_rate": 4.369633894427473e-05, + "loss": 3.786, + "step": 385024 + }, + { + "epoch": 1.0, + "learning_rate": 4.368796937556794e-05, + "loss": 3.7781, + "step": 385536 + }, + { + "epoch": 1.0, + "learning_rate": 4.367958342805742e-05, + "loss": 3.7958, + "step": 386048 + }, + { + "epoch": 1.0, + "learning_rate": 4.36711974805469e-05, + "loss": 3.7971, + "step": 386560 + }, + { + "epoch": 1.0, + "learning_rate": 4.366281153303637e-05, + "loss": 3.7892, + "step": 387072 + }, + { + "epoch": 1.0, + "learning_rate": 4.365444196432959e-05, + "loss": 3.7992, + "step": 387584 + }, + { + "epoch": 1.0, + "learning_rate": 4.36460723956228e-05, + "loss": 3.7782, + "step": 388096 + }, + { + "epoch": 1.0, + "learning_rate": 4.363768644811228e-05, + "loss": 3.7875, + "step": 388608 + }, + { + "epoch": 1.0, + "learning_rate": 4.362930050060176e-05, + "loss": 3.792, + "step": 389120 + }, + { + "epoch": 1.0, + "learning_rate": 4.362091455309124e-05, + "loss": 3.7769, + "step": 389632 + }, + { + "epoch": 1.0, + "learning_rate": 4.361252860558072e-05, + "loss": 3.7794, + "step": 390144 + }, + { + "epoch": 1.0, + "learning_rate": 4.36041426580702e-05, + "loss": 3.779, + "step": 390656 + }, + { + "epoch": 1.0, + "learning_rate": 4.3595756710559676e-05, + "loss": 3.7802, + "step": 391168 + }, + { + "epoch": 1.0, + "learning_rate": 4.358738714185289e-05, + "loss": 3.7973, + "step": 391680 + }, + { + "epoch": 1.0, + "learning_rate": 4.357900119434237e-05, + "loss": 3.7875, + "step": 392192 + }, + { + "epoch": 1.0, + "learning_rate": 4.3570615246831845e-05, + "loss": 3.7865, + "step": 392704 + }, + { + "epoch": 1.0, + "learning_rate": 4.3562229299321325e-05, + "loss": 3.7771, + "step": 393216 + }, + { + "epoch": 1.0, + "learning_rate": 4.3553843351810805e-05, + "loss": 3.7894, + "step": 393728 + }, + { + "epoch": 1.0, + "learning_rate": 4.3545457404300285e-05, + "loss": 3.7722, + "step": 394240 + }, + { + "epoch": 1.0, + "learning_rate": 4.353707145678977e-05, + "loss": 3.7753, + "step": 394752 + }, + { + "epoch": 1.0, + "learning_rate": 4.352868550927925e-05, + "loss": 3.7774, + "step": 395264 + }, + { + "epoch": 1.0, + "learning_rate": 4.352031594057246e-05, + "loss": 3.783, + "step": 395776 + }, + { + "epoch": 1.0, + "learning_rate": 4.351192999306194e-05, + "loss": 3.77, + "step": 396288 + }, + { + "epoch": 1.0, + "learning_rate": 4.350354404555142e-05, + "loss": 3.7774, + "step": 396800 + }, + { + "epoch": 1.01, + "learning_rate": 4.349517447684463e-05, + "loss": 3.7823, + "step": 397312 + }, + { + "epoch": 1.01, + "learning_rate": 4.348678852933411e-05, + "loss": 3.7838, + "step": 397824 + }, + { + "epoch": 1.01, + "learning_rate": 4.347840258182359e-05, + "loss": 3.7766, + "step": 398336 + }, + { + "epoch": 1.01, + "learning_rate": 4.347001663431307e-05, + "loss": 3.7776, + "step": 398848 + }, + { + "epoch": 1.01, + "learning_rate": 4.346164706560628e-05, + "loss": 3.7824, + "step": 399360 + }, + { + "epoch": 1.01, + "learning_rate": 4.345326111809576e-05, + "loss": 3.7783, + "step": 399872 + }, + { + "epoch": 1.01, + "learning_rate": 4.344487517058524e-05, + "loss": 3.7723, + "step": 400384 + }, + { + "epoch": 1.01, + "learning_rate": 4.3436489223074726e-05, + "loss": 3.7671, + "step": 400896 + }, + { + "epoch": 1.01, + "learning_rate": 4.3428119654367935e-05, + "loss": 3.764, + "step": 401408 + }, + { + "epoch": 1.01, + "learning_rate": 4.3419733706857415e-05, + "loss": 3.7746, + "step": 401920 + }, + { + "epoch": 1.01, + "learning_rate": 4.3411347759346895e-05, + "loss": 3.7707, + "step": 402432 + }, + { + "epoch": 1.01, + "learning_rate": 4.3402961811836375e-05, + "loss": 3.7803, + "step": 402944 + }, + { + "epoch": 1.01, + "learning_rate": 4.3394592243129584e-05, + "loss": 3.7722, + "step": 403456 + }, + { + "epoch": 1.01, + "learning_rate": 4.3386206295619064e-05, + "loss": 3.7727, + "step": 403968 + }, + { + "epoch": 1.01, + "learning_rate": 4.3377820348108544e-05, + "loss": 3.7818, + "step": 404480 + }, + { + "epoch": 1.01, + "learning_rate": 4.3369434400598024e-05, + "loss": 3.7754, + "step": 404992 + }, + { + "epoch": 1.01, + "learning_rate": 4.336106483189123e-05, + "loss": 3.7799, + "step": 405504 + }, + { + "epoch": 1.01, + "learning_rate": 4.335267888438071e-05, + "loss": 3.7636, + "step": 406016 + }, + { + "epoch": 1.01, + "learning_rate": 4.334429293687019e-05, + "loss": 3.7594, + "step": 406528 + }, + { + "epoch": 1.01, + "learning_rate": 4.333590698935968e-05, + "loss": 3.7866, + "step": 407040 + }, + { + "epoch": 1.01, + "learning_rate": 4.332753742065289e-05, + "loss": 3.7708, + "step": 407552 + }, + { + "epoch": 1.01, + "learning_rate": 4.331915147314237e-05, + "loss": 3.7683, + "step": 408064 + }, + { + "epoch": 1.01, + "learning_rate": 4.331076552563185e-05, + "loss": 3.7648, + "step": 408576 + }, + { + "epoch": 1.01, + "learning_rate": 4.330237957812133e-05, + "loss": 3.7746, + "step": 409088 + }, + { + "epoch": 1.01, + "learning_rate": 4.329401000941454e-05, + "loss": 3.7542, + "step": 409600 + }, + { + "epoch": 1.01, + "learning_rate": 4.328562406190402e-05, + "loss": 3.7737, + "step": 410112 + }, + { + "epoch": 1.01, + "learning_rate": 4.32772381143935e-05, + "loss": 3.771, + "step": 410624 + }, + { + "epoch": 1.01, + "learning_rate": 4.326885216688298e-05, + "loss": 3.7696, + "step": 411136 + }, + { + "epoch": 1.01, + "learning_rate": 4.3260482598176186e-05, + "loss": 3.7859, + "step": 411648 + }, + { + "epoch": 1.01, + "learning_rate": 4.3252096650665666e-05, + "loss": 3.7605, + "step": 412160 + }, + { + "epoch": 1.01, + "learning_rate": 4.3243710703155146e-05, + "loss": 3.7623, + "step": 412672 + }, + { + "epoch": 1.01, + "learning_rate": 4.3235324755644626e-05, + "loss": 3.7748, + "step": 413184 + }, + { + "epoch": 1.01, + "learning_rate": 4.322695518693784e-05, + "loss": 3.7562, + "step": 413696 + }, + { + "epoch": 1.01, + "learning_rate": 4.321856923942732e-05, + "loss": 3.7578, + "step": 414208 + }, + { + "epoch": 1.01, + "learning_rate": 4.32101832919168e-05, + "loss": 3.7658, + "step": 414720 + }, + { + "epoch": 1.01, + "learning_rate": 4.320179734440628e-05, + "loss": 3.7679, + "step": 415232 + }, + { + "epoch": 1.01, + "learning_rate": 4.319342777569949e-05, + "loss": 3.76, + "step": 415744 + }, + { + "epoch": 1.01, + "learning_rate": 4.318504182818897e-05, + "loss": 3.7552, + "step": 416256 + }, + { + "epoch": 1.01, + "learning_rate": 4.317665588067845e-05, + "loss": 3.7597, + "step": 416768 + }, + { + "epoch": 1.01, + "learning_rate": 4.316826993316793e-05, + "loss": 3.7702, + "step": 417280 + }, + { + "epoch": 1.01, + "learning_rate": 4.315990036446114e-05, + "loss": 3.77, + "step": 417792 + }, + { + "epoch": 1.01, + "learning_rate": 4.315151441695062e-05, + "loss": 3.769, + "step": 418304 + }, + { + "epoch": 1.01, + "learning_rate": 4.31431284694401e-05, + "loss": 3.7743, + "step": 418816 + }, + { + "epoch": 1.01, + "learning_rate": 4.313474252192958e-05, + "loss": 3.7712, + "step": 419328 + }, + { + "epoch": 1.01, + "learning_rate": 4.3126372953222796e-05, + "loss": 3.7834, + "step": 419840 + }, + { + "epoch": 1.01, + "learning_rate": 4.3117987005712276e-05, + "loss": 3.7513, + "step": 420352 + }, + { + "epoch": 1.01, + "learning_rate": 4.3109601058201756e-05, + "loss": 3.777, + "step": 420864 + }, + { + "epoch": 1.01, + "learning_rate": 4.3101231489494965e-05, + "loss": 3.772, + "step": 421376 + }, + { + "epoch": 1.01, + "learning_rate": 4.3092845541984445e-05, + "loss": 3.7507, + "step": 421888 + }, + { + "epoch": 1.01, + "learning_rate": 4.3084459594473925e-05, + "loss": 3.7764, + "step": 422400 + }, + { + "epoch": 1.01, + "learning_rate": 4.3076073646963405e-05, + "loss": 3.7626, + "step": 422912 + }, + { + "epoch": 1.01, + "learning_rate": 4.3067687699452885e-05, + "loss": 3.7741, + "step": 423424 + }, + { + "epoch": 1.01, + "learning_rate": 4.3059301751942364e-05, + "loss": 3.774, + "step": 423936 + }, + { + "epoch": 1.01, + "learning_rate": 4.3050915804431844e-05, + "loss": 3.7511, + "step": 424448 + }, + { + "epoch": 1.01, + "learning_rate": 4.3042529856921324e-05, + "loss": 3.754, + "step": 424960 + }, + { + "epoch": 1.01, + "learning_rate": 4.3034160288214533e-05, + "loss": 3.7573, + "step": 425472 + }, + { + "epoch": 1.01, + "learning_rate": 4.302577434070402e-05, + "loss": 3.7697, + "step": 425984 + }, + { + "epoch": 1.01, + "learning_rate": 4.30173883931935e-05, + "loss": 3.7627, + "step": 426496 + }, + { + "epoch": 1.01, + "learning_rate": 4.300900244568298e-05, + "loss": 3.7622, + "step": 427008 + }, + { + "epoch": 1.02, + "learning_rate": 4.300063287697619e-05, + "loss": 3.7584, + "step": 427520 + }, + { + "epoch": 1.02, + "learning_rate": 4.299224692946567e-05, + "loss": 3.7579, + "step": 428032 + }, + { + "epoch": 1.02, + "learning_rate": 4.298386098195515e-05, + "loss": 3.7604, + "step": 428544 + }, + { + "epoch": 1.02, + "learning_rate": 4.297547503444463e-05, + "loss": 3.7549, + "step": 429056 + }, + { + "epoch": 1.02, + "learning_rate": 4.296710546573784e-05, + "loss": 3.7678, + "step": 429568 + }, + { + "epoch": 1.02, + "learning_rate": 4.295871951822732e-05, + "loss": 3.7702, + "step": 430080 + }, + { + "epoch": 1.02, + "learning_rate": 4.29503335707168e-05, + "loss": 3.7688, + "step": 430592 + }, + { + "epoch": 1.02, + "learning_rate": 4.294194762320628e-05, + "loss": 3.7503, + "step": 431104 + }, + { + "epoch": 1.02, + "learning_rate": 4.293357805449949e-05, + "loss": 3.7621, + "step": 431616 + }, + { + "epoch": 1.02, + "learning_rate": 4.2925192106988974e-05, + "loss": 3.76, + "step": 432128 + }, + { + "epoch": 1.02, + "learning_rate": 4.2916806159478454e-05, + "loss": 3.7631, + "step": 432640 + }, + { + "epoch": 1.02, + "learning_rate": 4.290842021196793e-05, + "loss": 3.7631, + "step": 433152 + }, + { + "epoch": 1.02, + "learning_rate": 4.290005064326114e-05, + "loss": 3.7591, + "step": 433664 + }, + { + "epoch": 1.02, + "learning_rate": 4.289166469575062e-05, + "loss": 3.7515, + "step": 434176 + }, + { + "epoch": 1.02, + "learning_rate": 4.28832787482401e-05, + "loss": 3.7614, + "step": 434688 + }, + { + "epoch": 1.02, + "learning_rate": 4.2874892800729576e-05, + "loss": 3.7526, + "step": 435200 + }, + { + "epoch": 1.02, + "learning_rate": 4.286652323202279e-05, + "loss": 3.7469, + "step": 435712 + }, + { + "epoch": 1.02, + "learning_rate": 4.285813728451227e-05, + "loss": 3.7417, + "step": 436224 + }, + { + "epoch": 1.02, + "learning_rate": 4.284975133700175e-05, + "loss": 3.7592, + "step": 436736 + }, + { + "epoch": 1.02, + "learning_rate": 4.2841365389491225e-05, + "loss": 3.7501, + "step": 437248 + }, + { + "epoch": 1.02, + "learning_rate": 4.283299582078444e-05, + "loss": 3.7661, + "step": 437760 + }, + { + "epoch": 1.02, + "learning_rate": 4.282460987327393e-05, + "loss": 3.7485, + "step": 438272 + }, + { + "epoch": 1.02, + "learning_rate": 4.28162239257634e-05, + "loss": 3.7574, + "step": 438784 + }, + { + "epoch": 1.02, + "learning_rate": 4.280783797825288e-05, + "loss": 3.7561, + "step": 439296 + }, + { + "epoch": 1.02, + "learning_rate": 4.2799468409546097e-05, + "loss": 3.7446, + "step": 439808 + }, + { + "epoch": 1.02, + "learning_rate": 4.2791082462035576e-05, + "loss": 3.7697, + "step": 440320 + }, + { + "epoch": 1.02, + "learning_rate": 4.278269651452505e-05, + "loss": 3.7619, + "step": 440832 + }, + { + "epoch": 1.02, + "learning_rate": 4.277431056701453e-05, + "loss": 3.7523, + "step": 441344 + }, + { + "epoch": 1.02, + "learning_rate": 4.2765940998307746e-05, + "loss": 3.7546, + "step": 441856 + }, + { + "epoch": 1.02, + "learning_rate": 4.2757555050797225e-05, + "loss": 3.7521, + "step": 442368 + }, + { + "epoch": 1.02, + "learning_rate": 4.27491691032867e-05, + "loss": 3.7613, + "step": 442880 + }, + { + "epoch": 1.02, + "learning_rate": 4.274078315577618e-05, + "loss": 3.7379, + "step": 443392 + }, + { + "epoch": 1.02, + "learning_rate": 4.2732413587069394e-05, + "loss": 3.767, + "step": 443904 + }, + { + "epoch": 1.02, + "learning_rate": 4.2724027639558874e-05, + "loss": 3.7486, + "step": 444416 + }, + { + "epoch": 1.02, + "learning_rate": 4.2715641692048354e-05, + "loss": 3.754, + "step": 444928 + }, + { + "epoch": 1.02, + "learning_rate": 4.2707255744537834e-05, + "loss": 3.7531, + "step": 445440 + }, + { + "epoch": 1.02, + "learning_rate": 4.269888617583105e-05, + "loss": 3.7512, + "step": 445952 + }, + { + "epoch": 1.02, + "learning_rate": 4.2690500228320523e-05, + "loss": 3.7505, + "step": 446464 + }, + { + "epoch": 1.02, + "learning_rate": 4.268211428081e-05, + "loss": 3.7529, + "step": 446976 + }, + { + "epoch": 1.02, + "learning_rate": 4.267372833329948e-05, + "loss": 3.7525, + "step": 447488 + }, + { + "epoch": 1.02, + "learning_rate": 4.26653587645927e-05, + "loss": 3.762, + "step": 448000 + }, + { + "epoch": 1.02, + "learning_rate": 4.265697281708217e-05, + "loss": 3.7551, + "step": 448512 + }, + { + "epoch": 1.02, + "learning_rate": 4.264858686957165e-05, + "loss": 3.7582, + "step": 449024 + }, + { + "epoch": 1.02, + "learning_rate": 4.264020092206113e-05, + "loss": 3.7383, + "step": 449536 + }, + { + "epoch": 1.02, + "learning_rate": 4.263183135335435e-05, + "loss": 3.7641, + "step": 450048 + }, + { + "epoch": 1.02, + "learning_rate": 4.262344540584383e-05, + "loss": 3.7534, + "step": 450560 + }, + { + "epoch": 1.02, + "learning_rate": 4.261505945833331e-05, + "loss": 3.7563, + "step": 451072 + }, + { + "epoch": 1.02, + "learning_rate": 4.260667351082279e-05, + "loss": 3.7513, + "step": 451584 + }, + { + "epoch": 1.02, + "learning_rate": 4.2598303942116e-05, + "loss": 3.7517, + "step": 452096 + }, + { + "epoch": 1.02, + "learning_rate": 4.258991799460548e-05, + "loss": 3.7602, + "step": 452608 + }, + { + "epoch": 1.02, + "learning_rate": 4.258153204709496e-05, + "loss": 3.7603, + "step": 453120 + }, + { + "epoch": 1.02, + "learning_rate": 4.257316247838817e-05, + "loss": 3.7448, + "step": 453632 + }, + { + "epoch": 1.02, + "learning_rate": 4.2564776530877646e-05, + "loss": 3.7519, + "step": 454144 + }, + { + "epoch": 1.02, + "learning_rate": 4.2556390583367126e-05, + "loss": 3.7471, + "step": 454656 + }, + { + "epoch": 1.02, + "learning_rate": 4.2548004635856606e-05, + "loss": 3.7431, + "step": 455168 + }, + { + "epoch": 1.02, + "learning_rate": 4.253963506714982e-05, + "loss": 3.7604, + "step": 455680 + }, + { + "epoch": 1.02, + "learning_rate": 4.25312491196393e-05, + "loss": 3.7479, + "step": 456192 + }, + { + "epoch": 1.02, + "learning_rate": 4.252286317212878e-05, + "loss": 3.7541, + "step": 456704 + }, + { + "epoch": 1.02, + "learning_rate": 4.251447722461826e-05, + "loss": 3.7381, + "step": 457216 + }, + { + "epoch": 1.02, + "learning_rate": 4.250609127710774e-05, + "loss": 3.7531, + "step": 457728 + }, + { + "epoch": 1.03, + "eval_loss": 3.8700764179229736, + "eval_runtime": 304.2989, + "eval_samples_per_second": 1254.0, + "eval_steps_per_second": 39.188, + "step": 457920 + }, + { + "epoch": 0.0, + "learning_rate": 4.249770532959722e-05, + "loss": 3.7474, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.24893193820867e-05, + "loss": 3.7401, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.248093343457618e-05, + "loss": 3.7591, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.247254748706566e-05, + "loss": 3.7533, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.246416153955514e-05, + "loss": 3.7528, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.245577559204462e-05, + "loss": 3.7474, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.24473896445341e-05, + "loss": 3.7389, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.243900369702358e-05, + "loss": 3.7423, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.243063412831679e-05, + "loss": 3.7506, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.242224818080627e-05, + "loss": 3.7569, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.241386223329575e-05, + "loss": 3.7468, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.240547628578524e-05, + "loss": 3.7568, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.2397123095882175e-05, + "loss": 3.7404, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.2388737148371655e-05, + "loss": 3.74, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.2380351200861135e-05, + "loss": 3.7499, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.2371965253350615e-05, + "loss": 3.735, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.2363579305840095e-05, + "loss": 3.7381, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.2355193358329575e-05, + "loss": 3.7357, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.2346807410819055e-05, + "loss": 3.7429, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.233842146330853e-05, + "loss": 3.7515, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.2330051894601744e-05, + "loss": 3.7471, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.2321665947091224e-05, + "loss": 3.7466, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.2313279999580704e-05, + "loss": 3.7334, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.2304894052070184e-05, + "loss": 3.7493, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.22965244833634e-05, + "loss": 3.7343, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.228813853585288e-05, + "loss": 3.7366, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.227975258834236e-05, + "loss": 3.7318, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.227136664083183e-05, + "loss": 3.7391, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.226299707212505e-05, + "loss": 3.7379, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.225461112461453e-05, + "loss": 3.7318, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.2246225177104e-05, + "loss": 3.7424, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.223785560839722e-05, + "loss": 3.7431, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.22294696608867e-05, + "loss": 3.7357, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.222108371337618e-05, + "loss": 3.7413, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.221269776586566e-05, + "loss": 3.7387, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.2204328197158874e-05, + "loss": 3.7377, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.2195942249648353e-05, + "loss": 3.7366, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.2187556302137833e-05, + "loss": 3.7225, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.217917035462731e-05, + "loss": 3.7223, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.217080078592052e-05, + "loss": 3.7333, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.216241483841e-05, + "loss": 3.7315, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.2154028890899476e-05, + "loss": 3.7374, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.2145642943388956e-05, + "loss": 3.7335, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.213727337468217e-05, + "loss": 3.7319, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.212888742717165e-05, + "loss": 3.7419, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.212050147966113e-05, + "loss": 3.7353, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.211211553215061e-05, + "loss": 3.7414, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.210374596344383e-05, + "loss": 3.723, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.209536001593331e-05, + "loss": 3.7167, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.208697406842278e-05, + "loss": 3.7489, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.207858812091226e-05, + "loss": 3.7346, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.2070218552205476e-05, + "loss": 3.7265, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.2061848983498685e-05, + "loss": 3.7288, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.2053463035988165e-05, + "loss": 3.7328, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.2045077088477645e-05, + "loss": 3.7185, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.2036691140967125e-05, + "loss": 3.7305, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.2028305193456605e-05, + "loss": 3.7325, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.2019919245946085e-05, + "loss": 3.7329, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.2011533298435565e-05, + "loss": 3.7441, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.200316372972878e-05, + "loss": 3.7195, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.1994777782218254e-05, + "loss": 3.7233, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.1986391834707734e-05, + "loss": 3.7393, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.1978005887197214e-05, + "loss": 3.717, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.196963631849042e-05, + "loss": 3.716, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.19612503709799e-05, + "loss": 3.726, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.195286442346938e-05, + "loss": 3.7285, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.194447847595886e-05, + "loss": 3.7194, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.193612528605581e-05, + "loss": 3.7195, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.192773933854529e-05, + "loss": 3.717, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.1919353391034775e-05, + "loss": 3.7372, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.191096744352425e-05, + "loss": 3.7303, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.190258149601373e-05, + "loss": 3.7301, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.189419554850321e-05, + "loss": 3.735, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.188580960099269e-05, + "loss": 3.7313, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.187742365348217e-05, + "loss": 3.7448, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.186905408477538e-05, + "loss": 3.7154, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.186066813726486e-05, + "loss": 3.7368, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.185228218975434e-05, + "loss": 3.7323, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.1843912621047546e-05, + "loss": 3.7156, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.1835526673537026e-05, + "loss": 3.7345, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.182714072602651e-05, + "loss": 3.727, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.181875477851599e-05, + "loss": 3.7351, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.181036883100547e-05, + "loss": 3.7356, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.180198288349495e-05, + "loss": 3.7179, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.179359693598443e-05, + "loss": 3.7101, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.178522736727764e-05, + "loss": 3.718, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.177684141976712e-05, + "loss": 3.7343, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.17684554722566e-05, + "loss": 3.724, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.176006952474608e-05, + "loss": 3.7239, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.175169995603929e-05, + "loss": 3.722, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.174331400852877e-05, + "loss": 3.7196, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.173494443982198e-05, + "loss": 3.7263, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.1726558492311466e-05, + "loss": 3.7184, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.1718172544800946e-05, + "loss": 3.7304, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.1709786597290426e-05, + "loss": 3.7315, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.1701400649779906e-05, + "loss": 3.7294, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.1693014702269386e-05, + "loss": 3.7136, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.1684628754758866e-05, + "loss": 3.7242, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.1676242807248346e-05, + "loss": 3.7237, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.1667873238541555e-05, + "loss": 3.7248, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.1659487291031035e-05, + "loss": 3.7266, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.1651101343520515e-05, + "loss": 3.7186, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.1642715396009995e-05, + "loss": 3.7162, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.1634345827303204e-05, + "loss": 3.7204, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.1625959879792684e-05, + "loss": 3.7125, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.1617573932282164e-05, + "loss": 3.7182, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.1609187984771644e-05, + "loss": 3.6985, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.160083479486859e-05, + "loss": 3.7244, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.159244884735807e-05, + "loss": 3.7152, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.158406289984755e-05, + "loss": 3.7244, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.157567695233703e-05, + "loss": 3.7116, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.156729100482651e-05, + "loss": 3.7221, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.155890505731599e-05, + "loss": 3.7218, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.155051910980547e-05, + "loss": 3.7054, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.154213316229495e-05, + "loss": 3.7354, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.153376359358816e-05, + "loss": 3.7235, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.152537764607764e-05, + "loss": 3.7181, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.151699169856712e-05, + "loss": 3.7224, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.15086057510566e-05, + "loss": 3.7081, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.150023618234981e-05, + "loss": 3.7279, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.149186661364302e-05, + "loss": 3.7049, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.14834806661325e-05, + "loss": 3.7279, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.147509471862198e-05, + "loss": 3.7101, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.146670877111146e-05, + "loss": 3.7185, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.145833920240467e-05, + "loss": 3.7134, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.144995325489415e-05, + "loss": 3.7172, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.144156730738363e-05, + "loss": 3.7156, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.143318135987311e-05, + "loss": 3.7126, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.142479541236259e-05, + "loss": 3.7189, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.141640946485207e-05, + "loss": 3.7245, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.140802351734155e-05, + "loss": 3.7164, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.139963756983103e-05, + "loss": 3.7228, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.139126800112425e-05, + "loss": 3.7036, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.138288205361373e-05, + "loss": 3.726, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.1374512484906936e-05, + "loss": 3.722, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.1366126537396416e-05, + "loss": 3.7172, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.1357740589885896e-05, + "loss": 3.7143, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.1349354642375376e-05, + "loss": 3.7192, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.1340968694864856e-05, + "loss": 3.7207, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.133258274735433e-05, + "loss": 3.7278, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.132419679984381e-05, + "loss": 3.7066, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.131581085233329e-05, + "loss": 3.7174, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.1307441283626505e-05, + "loss": 3.7114, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.1299055336115985e-05, + "loss": 3.7096, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.12906857674092e-05, + "loss": 3.7211, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.128229981989868e-05, + "loss": 3.7146, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.1273913872388154e-05, + "loss": 3.7179, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.1265527924877634e-05, + "loss": 3.7037, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.125715835617085e-05, + "loss": 3.7234, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 3.858917236328125, + "eval_runtime": 303.0469, + "eval_samples_per_second": 1259.181, + "eval_steps_per_second": 39.35, + "step": 534240 + }, + { + "epoch": 1.0, + "learning_rate": 4.124877240866032e-05, + "loss": 3.7104, + "step": 534528 + }, + { + "epoch": 1.0, + "learning_rate": 4.12403864611498e-05, + "loss": 3.7059, + "step": 535040 + }, + { + "epoch": 1.0, + "learning_rate": 4.123200051363928e-05, + "loss": 3.7198, + "step": 535552 + }, + { + "epoch": 1.0, + "learning_rate": 4.122361456612876e-05, + "loss": 3.7191, + "step": 536064 + }, + { + "epoch": 1.0, + "learning_rate": 4.121522861861824e-05, + "loss": 3.7178, + "step": 536576 + }, + { + "epoch": 1.0, + "learning_rate": 4.120684267110773e-05, + "loss": 3.7135, + "step": 537088 + }, + { + "epoch": 1.0, + "learning_rate": 4.119845672359721e-05, + "loss": 3.705, + "step": 537600 + }, + { + "epoch": 1.0, + "learning_rate": 4.119008715489042e-05, + "loss": 3.7067, + "step": 538112 + }, + { + "epoch": 1.0, + "learning_rate": 4.11817012073799e-05, + "loss": 3.7178, + "step": 538624 + }, + { + "epoch": 1.0, + "learning_rate": 4.117333163867311e-05, + "loss": 3.7198, + "step": 539136 + }, + { + "epoch": 1.0, + "learning_rate": 4.116494569116259e-05, + "loss": 3.713, + "step": 539648 + }, + { + "epoch": 1.0, + "learning_rate": 4.115655974365207e-05, + "loss": 3.72, + "step": 540160 + }, + { + "epoch": 1.0, + "learning_rate": 4.114817379614155e-05, + "loss": 3.7097, + "step": 540672 + }, + { + "epoch": 1.0, + "learning_rate": 4.113978784863103e-05, + "loss": 3.7055, + "step": 541184 + }, + { + "epoch": 1.0, + "learning_rate": 4.113140190112051e-05, + "loss": 3.7119, + "step": 541696 + }, + { + "epoch": 1.0, + "learning_rate": 4.112301595360999e-05, + "loss": 3.699, + "step": 542208 + }, + { + "epoch": 1.0, + "learning_rate": 4.111463000609947e-05, + "loss": 3.7041, + "step": 542720 + }, + { + "epoch": 1.0, + "learning_rate": 4.110626043739268e-05, + "loss": 3.7014, + "step": 543232 + }, + { + "epoch": 1.0, + "learning_rate": 4.109787448988216e-05, + "loss": 3.7072, + "step": 543744 + }, + { + "epoch": 1.0, + "learning_rate": 4.108950492117537e-05, + "loss": 3.7144, + "step": 544256 + }, + { + "epoch": 1.0, + "learning_rate": 4.108111897366485e-05, + "loss": 3.7188, + "step": 544768 + }, + { + "epoch": 1.0, + "learning_rate": 4.107273302615433e-05, + "loss": 3.7087, + "step": 545280 + }, + { + "epoch": 1.0, + "learning_rate": 4.106434707864381e-05, + "loss": 3.7003, + "step": 545792 + }, + { + "epoch": 1.0, + "learning_rate": 4.105596113113329e-05, + "loss": 3.7133, + "step": 546304 + }, + { + "epoch": 1.0, + "learning_rate": 4.104757518362277e-05, + "loss": 3.6976, + "step": 546816 + }, + { + "epoch": 1.0, + "learning_rate": 4.103918923611225e-05, + "loss": 3.7046, + "step": 547328 + }, + { + "epoch": 1.0, + "learning_rate": 4.103080328860173e-05, + "loss": 3.6975, + "step": 547840 + }, + { + "epoch": 1.0, + "learning_rate": 4.102243371989494e-05, + "loss": 3.7081, + "step": 548352 + }, + { + "epoch": 1.0, + "learning_rate": 4.101404777238442e-05, + "loss": 3.7009, + "step": 548864 + }, + { + "epoch": 1.0, + "learning_rate": 4.10056618248739e-05, + "loss": 3.7037, + "step": 549376 + }, + { + "epoch": 1.01, + "learning_rate": 4.0997292256167117e-05, + "loss": 3.7035, + "step": 549888 + }, + { + "epoch": 1.01, + "learning_rate": 4.0988906308656597e-05, + "loss": 3.7149, + "step": 550400 + }, + { + "epoch": 1.01, + "learning_rate": 4.0980520361146076e-05, + "loss": 3.702, + "step": 550912 + }, + { + "epoch": 1.01, + "learning_rate": 4.0972134413635556e-05, + "loss": 3.7016, + "step": 551424 + }, + { + "epoch": 1.01, + "learning_rate": 4.0963748466125036e-05, + "loss": 3.7058, + "step": 551936 + }, + { + "epoch": 1.01, + "learning_rate": 4.0955362518614516e-05, + "loss": 3.7035, + "step": 552448 + }, + { + "epoch": 1.01, + "learning_rate": 4.094697657110399e-05, + "loss": 3.7067, + "step": 552960 + }, + { + "epoch": 1.01, + "learning_rate": 4.0938607002397205e-05, + "loss": 3.6853, + "step": 553472 + }, + { + "epoch": 1.01, + "learning_rate": 4.0930221054886685e-05, + "loss": 3.6914, + "step": 553984 + }, + { + "epoch": 1.01, + "learning_rate": 4.092183510737616e-05, + "loss": 3.6973, + "step": 554496 + }, + { + "epoch": 1.01, + "learning_rate": 4.091344915986564e-05, + "loss": 3.702, + "step": 555008 + }, + { + "epoch": 1.01, + "learning_rate": 4.0905079591158854e-05, + "loss": 3.7029, + "step": 555520 + }, + { + "epoch": 1.01, + "learning_rate": 4.0896693643648334e-05, + "loss": 3.6996, + "step": 556032 + }, + { + "epoch": 1.01, + "learning_rate": 4.0888307696137814e-05, + "loss": 3.6976, + "step": 556544 + }, + { + "epoch": 1.01, + "learning_rate": 4.0879921748627294e-05, + "loss": 3.7101, + "step": 557056 + }, + { + "epoch": 1.01, + "learning_rate": 4.087155217992051e-05, + "loss": 3.697, + "step": 557568 + }, + { + "epoch": 1.01, + "learning_rate": 4.086316623240999e-05, + "loss": 3.7171, + "step": 558080 + }, + { + "epoch": 1.01, + "learning_rate": 4.085478028489946e-05, + "loss": 3.6877, + "step": 558592 + }, + { + "epoch": 1.01, + "learning_rate": 4.084639433738894e-05, + "loss": 3.6781, + "step": 559104 + }, + { + "epoch": 1.01, + "learning_rate": 4.083802476868216e-05, + "loss": 3.7181, + "step": 559616 + }, + { + "epoch": 1.01, + "learning_rate": 4.082963882117163e-05, + "loss": 3.6988, + "step": 560128 + }, + { + "epoch": 1.01, + "learning_rate": 4.082125287366111e-05, + "loss": 3.6975, + "step": 560640 + }, + { + "epoch": 1.01, + "learning_rate": 4.081288330495433e-05, + "loss": 3.6961, + "step": 561152 + }, + { + "epoch": 1.01, + "learning_rate": 4.080449735744381e-05, + "loss": 3.6966, + "step": 561664 + }, + { + "epoch": 1.01, + "learning_rate": 4.079611140993329e-05, + "loss": 3.6869, + "step": 562176 + }, + { + "epoch": 1.01, + "learning_rate": 4.078772546242277e-05, + "loss": 3.6962, + "step": 562688 + }, + { + "epoch": 1.01, + "learning_rate": 4.0779355893715984e-05, + "loss": 3.6989, + "step": 563200 + }, + { + "epoch": 1.01, + "learning_rate": 4.0770969946205464e-05, + "loss": 3.6999, + "step": 563712 + }, + { + "epoch": 1.01, + "learning_rate": 4.076258399869494e-05, + "loss": 3.712, + "step": 564224 + }, + { + "epoch": 1.01, + "learning_rate": 4.075419805118442e-05, + "loss": 3.6875, + "step": 564736 + }, + { + "epoch": 1.01, + "learning_rate": 4.07458121036739e-05, + "loss": 3.6893, + "step": 565248 + }, + { + "epoch": 1.01, + "learning_rate": 4.073742615616338e-05, + "loss": 3.7085, + "step": 565760 + }, + { + "epoch": 1.01, + "learning_rate": 4.072904020865286e-05, + "loss": 3.6818, + "step": 566272 + }, + { + "epoch": 1.01, + "learning_rate": 4.0720670639946066e-05, + "loss": 3.6836, + "step": 566784 + }, + { + "epoch": 1.01, + "learning_rate": 4.0712284692435546e-05, + "loss": 3.6928, + "step": 567296 + }, + { + "epoch": 1.01, + "learning_rate": 4.0703898744925026e-05, + "loss": 3.6957, + "step": 567808 + }, + { + "epoch": 1.01, + "learning_rate": 4.0695512797414506e-05, + "loss": 3.6831, + "step": 568320 + }, + { + "epoch": 1.01, + "learning_rate": 4.068715960751146e-05, + "loss": 3.6915, + "step": 568832 + }, + { + "epoch": 1.01, + "learning_rate": 4.067877366000094e-05, + "loss": 3.6845, + "step": 569344 + }, + { + "epoch": 1.01, + "learning_rate": 4.067038771249041e-05, + "loss": 3.7009, + "step": 569856 + }, + { + "epoch": 1.01, + "learning_rate": 4.066200176497989e-05, + "loss": 3.7021, + "step": 570368 + }, + { + "epoch": 1.01, + "learning_rate": 4.065361581746937e-05, + "loss": 3.6937, + "step": 570880 + }, + { + "epoch": 1.01, + "learning_rate": 4.064522986995885e-05, + "loss": 3.7006, + "step": 571392 + }, + { + "epoch": 1.01, + "learning_rate": 4.063684392244833e-05, + "loss": 3.6988, + "step": 571904 + }, + { + "epoch": 1.01, + "learning_rate": 4.062845797493781e-05, + "loss": 3.7141, + "step": 572416 + }, + { + "epoch": 1.01, + "learning_rate": 4.062008840623102e-05, + "loss": 3.6826, + "step": 572928 + }, + { + "epoch": 1.01, + "learning_rate": 4.06117024587205e-05, + "loss": 3.7091, + "step": 573440 + }, + { + "epoch": 1.01, + "learning_rate": 4.060331651120998e-05, + "loss": 3.696, + "step": 573952 + }, + { + "epoch": 1.01, + "learning_rate": 4.0594946942503195e-05, + "loss": 3.6844, + "step": 574464 + }, + { + "epoch": 1.01, + "learning_rate": 4.0586560994992675e-05, + "loss": 3.7, + "step": 574976 + }, + { + "epoch": 1.01, + "learning_rate": 4.0578175047482155e-05, + "loss": 3.6984, + "step": 575488 + }, + { + "epoch": 1.01, + "learning_rate": 4.0569789099971635e-05, + "loss": 3.7002, + "step": 576000 + }, + { + "epoch": 1.01, + "learning_rate": 4.0561403152461115e-05, + "loss": 3.7054, + "step": 576512 + }, + { + "epoch": 1.01, + "learning_rate": 4.0553033583754324e-05, + "loss": 3.6843, + "step": 577024 + }, + { + "epoch": 1.01, + "learning_rate": 4.0544647636243804e-05, + "loss": 3.6773, + "step": 577536 + }, + { + "epoch": 1.01, + "learning_rate": 4.0536261688733284e-05, + "loss": 3.6891, + "step": 578048 + }, + { + "epoch": 1.01, + "learning_rate": 4.0527875741222764e-05, + "loss": 3.7033, + "step": 578560 + }, + { + "epoch": 1.01, + "learning_rate": 4.0519489793712244e-05, + "loss": 3.6926, + "step": 579072 + }, + { + "epoch": 1.01, + "learning_rate": 4.0511103846201724e-05, + "loss": 3.6912, + "step": 579584 + }, + { + "epoch": 1.02, + "learning_rate": 4.0502717898691204e-05, + "loss": 3.6862, + "step": 580096 + }, + { + "epoch": 1.02, + "learning_rate": 4.049434832998441e-05, + "loss": 3.6901, + "step": 580608 + }, + { + "epoch": 1.02, + "learning_rate": 4.048597876127763e-05, + "loss": 3.6924, + "step": 581120 + }, + { + "epoch": 1.02, + "learning_rate": 4.047759281376711e-05, + "loss": 3.6877, + "step": 581632 + }, + { + "epoch": 1.02, + "learning_rate": 4.046920686625659e-05, + "loss": 3.6981, + "step": 582144 + }, + { + "epoch": 1.02, + "learning_rate": 4.046082091874607e-05, + "loss": 3.7008, + "step": 582656 + }, + { + "epoch": 1.02, + "learning_rate": 4.045243497123555e-05, + "loss": 3.6976, + "step": 583168 + }, + { + "epoch": 1.02, + "learning_rate": 4.044404902372503e-05, + "loss": 3.685, + "step": 583680 + }, + { + "epoch": 1.02, + "learning_rate": 4.043566307621451e-05, + "loss": 3.694, + "step": 584192 + }, + { + "epoch": 1.02, + "learning_rate": 4.042727712870399e-05, + "loss": 3.6868, + "step": 584704 + }, + { + "epoch": 1.02, + "learning_rate": 4.04189075599972e-05, + "loss": 3.693, + "step": 585216 + }, + { + "epoch": 1.02, + "learning_rate": 4.041052161248668e-05, + "loss": 3.6966, + "step": 585728 + }, + { + "epoch": 1.02, + "learning_rate": 4.040215204377989e-05, + "loss": 3.6914, + "step": 586240 + }, + { + "epoch": 1.02, + "learning_rate": 4.039376609626937e-05, + "loss": 3.6827, + "step": 586752 + }, + { + "epoch": 1.02, + "learning_rate": 4.0385380148758853e-05, + "loss": 3.6847, + "step": 587264 + }, + { + "epoch": 1.02, + "learning_rate": 4.0376994201248333e-05, + "loss": 3.6877, + "step": 587776 + }, + { + "epoch": 1.02, + "learning_rate": 4.036860825373781e-05, + "loss": 3.6846, + "step": 588288 + }, + { + "epoch": 1.02, + "learning_rate": 4.036023868503102e-05, + "loss": 3.6709, + "step": 588800 + }, + { + "epoch": 1.02, + "learning_rate": 4.03518527375205e-05, + "loss": 3.6936, + "step": 589312 + }, + { + "epoch": 1.02, + "learning_rate": 4.034346679000998e-05, + "loss": 3.6872, + "step": 589824 + }, + { + "epoch": 1.02, + "learning_rate": 4.033508084249946e-05, + "loss": 3.6899, + "step": 590336 + }, + { + "epoch": 1.02, + "learning_rate": 4.032669489498894e-05, + "loss": 3.6784, + "step": 590848 + }, + { + "epoch": 1.02, + "learning_rate": 4.0318308947478415e-05, + "loss": 3.6971, + "step": 591360 + }, + { + "epoch": 1.02, + "learning_rate": 4.030993937877163e-05, + "loss": 3.6863, + "step": 591872 + }, + { + "epoch": 1.02, + "learning_rate": 4.030155343126111e-05, + "loss": 3.6761, + "step": 592384 + }, + { + "epoch": 1.02, + "learning_rate": 4.029316748375059e-05, + "loss": 3.7008, + "step": 592896 + }, + { + "epoch": 1.02, + "learning_rate": 4.028478153624007e-05, + "loss": 3.6926, + "step": 593408 + }, + { + "epoch": 1.02, + "learning_rate": 4.027639558872955e-05, + "loss": 3.6855, + "step": 593920 + }, + { + "epoch": 1.02, + "learning_rate": 4.026800964121903e-05, + "loss": 3.6943, + "step": 594432 + }, + { + "epoch": 1.02, + "learning_rate": 4.025962369370851e-05, + "loss": 3.6785, + "step": 594944 + }, + { + "epoch": 1.02, + "learning_rate": 4.025123774619799e-05, + "loss": 3.6946, + "step": 595456 + }, + { + "epoch": 1.02, + "learning_rate": 4.0242884556294936e-05, + "loss": 3.6765, + "step": 595968 + }, + { + "epoch": 1.02, + "learning_rate": 4.0234498608784416e-05, + "loss": 3.6929, + "step": 596480 + }, + { + "epoch": 1.02, + "learning_rate": 4.022611266127389e-05, + "loss": 3.6794, + "step": 596992 + }, + { + "epoch": 1.02, + "learning_rate": 4.021772671376337e-05, + "loss": 3.6882, + "step": 597504 + }, + { + "epoch": 1.02, + "learning_rate": 4.0209357145056585e-05, + "loss": 3.6839, + "step": 598016 + }, + { + "epoch": 1.02, + "learning_rate": 4.0200971197546065e-05, + "loss": 3.6862, + "step": 598528 + }, + { + "epoch": 1.02, + "learning_rate": 4.0192585250035545e-05, + "loss": 3.682, + "step": 599040 + }, + { + "epoch": 1.02, + "learning_rate": 4.0184199302525025e-05, + "loss": 3.6845, + "step": 599552 + }, + { + "epoch": 1.02, + "learning_rate": 4.0175813355014505e-05, + "loss": 3.6905, + "step": 600064 + }, + { + "epoch": 1.02, + "learning_rate": 4.0167427407503985e-05, + "loss": 3.6944, + "step": 600576 + }, + { + "epoch": 1.02, + "learning_rate": 4.0159041459993465e-05, + "loss": 3.6819, + "step": 601088 + }, + { + "epoch": 1.02, + "learning_rate": 4.0150655512482945e-05, + "loss": 3.6991, + "step": 601600 + }, + { + "epoch": 1.02, + "learning_rate": 4.0142285943776154e-05, + "loss": 3.6706, + "step": 602112 + }, + { + "epoch": 1.02, + "learning_rate": 4.0133899996265634e-05, + "loss": 3.696, + "step": 602624 + }, + { + "epoch": 1.02, + "learning_rate": 4.012553042755884e-05, + "loss": 3.6923, + "step": 603136 + }, + { + "epoch": 1.02, + "learning_rate": 4.011714448004832e-05, + "loss": 3.6884, + "step": 603648 + }, + { + "epoch": 1.02, + "learning_rate": 4.01087585325378e-05, + "loss": 3.6827, + "step": 604160 + }, + { + "epoch": 1.02, + "learning_rate": 4.010037258502728e-05, + "loss": 3.6893, + "step": 604672 + }, + { + "epoch": 1.02, + "learning_rate": 4.009200301632049e-05, + "loss": 3.6894, + "step": 605184 + }, + { + "epoch": 1.02, + "learning_rate": 4.008361706880998e-05, + "loss": 3.6988, + "step": 605696 + }, + { + "epoch": 1.02, + "learning_rate": 4.007523112129946e-05, + "loss": 3.6775, + "step": 606208 + }, + { + "epoch": 1.02, + "learning_rate": 4.006684517378894e-05, + "loss": 3.6865, + "step": 606720 + }, + { + "epoch": 1.02, + "learning_rate": 4.005845922627842e-05, + "loss": 3.6794, + "step": 607232 + }, + { + "epoch": 1.02, + "learning_rate": 4.00500732787679e-05, + "loss": 3.6858, + "step": 607744 + }, + { + "epoch": 1.02, + "learning_rate": 4.004170371006111e-05, + "loss": 3.6849, + "step": 608256 + }, + { + "epoch": 1.02, + "learning_rate": 4.003331776255059e-05, + "loss": 3.6846, + "step": 608768 + }, + { + "epoch": 1.02, + "learning_rate": 4.002493181504007e-05, + "loss": 3.6915, + "step": 609280 + }, + { + "epoch": 1.02, + "learning_rate": 4.001654586752955e-05, + "loss": 3.6725, + "step": 609792 + }, + { + "epoch": 1.02, + "learning_rate": 4.000815992001903e-05, + "loss": 3.6922, + "step": 610304 + }, + { + "epoch": 1.03, + "eval_loss": 3.8520939350128174, + "eval_runtime": 302.6209, + "eval_samples_per_second": 1260.954, + "eval_steps_per_second": 39.406, + "step": 610560 + }, + { + "epoch": 0.0, + "learning_rate": 3.999977397250851e-05, + "loss": 3.6828, + "step": 610816 + }, + { + "epoch": 0.0, + "learning_rate": 3.999138802499799e-05, + "loss": 3.6779, + "step": 611328 + }, + { + "epoch": 0.0, + "learning_rate": 3.998300207748747e-05, + "loss": 3.6873, + "step": 611840 + }, + { + "epoch": 0.0, + "learning_rate": 3.997461612997695e-05, + "loss": 3.6864, + "step": 612352 + }, + { + "epoch": 0.0, + "learning_rate": 3.996623018246643e-05, + "loss": 3.6895, + "step": 612864 + }, + { + "epoch": 0.0, + "learning_rate": 3.995784423495591e-05, + "loss": 3.68, + "step": 613376 + }, + { + "epoch": 0.0, + "learning_rate": 3.994945828744539e-05, + "loss": 3.6783, + "step": 613888 + }, + { + "epoch": 0.0, + "learning_rate": 3.994107233993487e-05, + "loss": 3.681, + "step": 614400 + }, + { + "epoch": 0.0, + "learning_rate": 3.993271915003181e-05, + "loss": 3.6836, + "step": 614912 + }, + { + "epoch": 0.0, + "learning_rate": 3.992433320252129e-05, + "loss": 3.6902, + "step": 615424 + }, + { + "epoch": 0.0, + "learning_rate": 3.991594725501077e-05, + "loss": 3.6846, + "step": 615936 + }, + { + "epoch": 0.0, + "learning_rate": 3.990756130750025e-05, + "loss": 3.688, + "step": 616448 + }, + { + "epoch": 0.0, + "learning_rate": 3.989919173879346e-05, + "loss": 3.6778, + "step": 616960 + }, + { + "epoch": 0.0, + "learning_rate": 3.989080579128294e-05, + "loss": 3.6756, + "step": 617472 + }, + { + "epoch": 0.0, + "learning_rate": 3.988241984377242e-05, + "loss": 3.6831, + "step": 617984 + }, + { + "epoch": 0.0, + "learning_rate": 3.98740338962619e-05, + "loss": 3.6702, + "step": 618496 + }, + { + "epoch": 0.0, + "learning_rate": 3.986564794875138e-05, + "loss": 3.6736, + "step": 619008 + }, + { + "epoch": 0.0, + "learning_rate": 3.9857278380044597e-05, + "loss": 3.6732, + "step": 619520 + }, + { + "epoch": 0.0, + "learning_rate": 3.9848892432534077e-05, + "loss": 3.6793, + "step": 620032 + }, + { + "epoch": 0.0, + "learning_rate": 3.984050648502355e-05, + "loss": 3.6823, + "step": 620544 + }, + { + "epoch": 0.0, + "learning_rate": 3.983212053751303e-05, + "loss": 3.6906, + "step": 621056 + }, + { + "epoch": 0.0, + "learning_rate": 3.982373459000251e-05, + "loss": 3.6802, + "step": 621568 + }, + { + "epoch": 0.0, + "learning_rate": 3.981534864249199e-05, + "loss": 3.6718, + "step": 622080 + }, + { + "epoch": 0.0, + "learning_rate": 3.980696269498147e-05, + "loss": 3.6798, + "step": 622592 + }, + { + "epoch": 0.0, + "learning_rate": 3.979857674747095e-05, + "loss": 3.6742, + "step": 623104 + }, + { + "epoch": 0.0, + "learning_rate": 3.979020717876416e-05, + "loss": 3.6747, + "step": 623616 + }, + { + "epoch": 0.0, + "learning_rate": 3.978182123125364e-05, + "loss": 3.666, + "step": 624128 + }, + { + "epoch": 0.0, + "learning_rate": 3.977343528374312e-05, + "loss": 3.6797, + "step": 624640 + }, + { + "epoch": 0.0, + "learning_rate": 3.97650493362326e-05, + "loss": 3.6754, + "step": 625152 + }, + { + "epoch": 0.0, + "learning_rate": 3.9756679767525814e-05, + "loss": 3.6688, + "step": 625664 + }, + { + "epoch": 0.01, + "learning_rate": 3.9748293820015294e-05, + "loss": 3.6726, + "step": 626176 + }, + { + "epoch": 0.01, + "learning_rate": 3.9739924251308503e-05, + "loss": 3.6861, + "step": 626688 + }, + { + "epoch": 0.01, + "learning_rate": 3.973153830379798e-05, + "loss": 3.6717, + "step": 627200 + }, + { + "epoch": 0.01, + "learning_rate": 3.972315235628746e-05, + "loss": 3.6724, + "step": 627712 + }, + { + "epoch": 0.01, + "learning_rate": 3.971476640877694e-05, + "loss": 3.676, + "step": 628224 + }, + { + "epoch": 0.01, + "learning_rate": 3.970638046126642e-05, + "loss": 3.6803, + "step": 628736 + }, + { + "epoch": 0.01, + "learning_rate": 3.96979945137559e-05, + "loss": 3.6743, + "step": 629248 + }, + { + "epoch": 0.01, + "learning_rate": 3.968960856624538e-05, + "loss": 3.6589, + "step": 629760 + }, + { + "epoch": 0.01, + "learning_rate": 3.968123899753859e-05, + "loss": 3.6632, + "step": 630272 + }, + { + "epoch": 0.01, + "learning_rate": 3.967285305002807e-05, + "loss": 3.669, + "step": 630784 + }, + { + "epoch": 0.01, + "learning_rate": 3.966446710251755e-05, + "loss": 3.6717, + "step": 631296 + }, + { + "epoch": 0.01, + "learning_rate": 3.965608115500703e-05, + "loss": 3.6737, + "step": 631808 + }, + { + "epoch": 0.01, + "learning_rate": 3.964771158630025e-05, + "loss": 3.6738, + "step": 632320 + }, + { + "epoch": 0.01, + "learning_rate": 3.963932563878973e-05, + "loss": 3.6696, + "step": 632832 + }, + { + "epoch": 0.01, + "learning_rate": 3.963093969127921e-05, + "loss": 3.6798, + "step": 633344 + }, + { + "epoch": 0.01, + "learning_rate": 3.962255374376869e-05, + "loss": 3.6688, + "step": 633856 + }, + { + "epoch": 0.01, + "learning_rate": 3.96141841750619e-05, + "loss": 3.6851, + "step": 634368 + }, + { + "epoch": 0.01, + "learning_rate": 3.960579822755138e-05, + "loss": 3.6618, + "step": 634880 + }, + { + "epoch": 0.01, + "learning_rate": 3.959741228004086e-05, + "loss": 3.6479, + "step": 635392 + }, + { + "epoch": 0.01, + "learning_rate": 3.958902633253034e-05, + "loss": 3.6902, + "step": 635904 + }, + { + "epoch": 0.01, + "learning_rate": 3.9580656763823546e-05, + "loss": 3.6686, + "step": 636416 + }, + { + "epoch": 0.01, + "learning_rate": 3.9572270816313026e-05, + "loss": 3.6727, + "step": 636928 + }, + { + "epoch": 0.01, + "learning_rate": 3.956390124760624e-05, + "loss": 3.6657, + "step": 637440 + }, + { + "epoch": 0.01, + "learning_rate": 3.955551530009572e-05, + "loss": 3.6659, + "step": 637952 + }, + { + "epoch": 0.01, + "learning_rate": 3.95471293525852e-05, + "loss": 3.6589, + "step": 638464 + }, + { + "epoch": 0.01, + "learning_rate": 3.953874340507468e-05, + "loss": 3.6654, + "step": 638976 + }, + { + "epoch": 0.01, + "learning_rate": 3.953037383636789e-05, + "loss": 3.6718, + "step": 639488 + }, + { + "epoch": 0.01, + "learning_rate": 3.952198788885737e-05, + "loss": 3.6725, + "step": 640000 + }, + { + "epoch": 0.01, + "learning_rate": 3.951360194134685e-05, + "loss": 3.6854, + "step": 640512 + }, + { + "epoch": 0.01, + "learning_rate": 3.950521599383633e-05, + "loss": 3.6602, + "step": 641024 + }, + { + "epoch": 0.01, + "learning_rate": 3.949683004632581e-05, + "loss": 3.6596, + "step": 641536 + }, + { + "epoch": 0.01, + "learning_rate": 3.948844409881529e-05, + "loss": 3.6819, + "step": 642048 + }, + { + "epoch": 0.01, + "learning_rate": 3.948005815130477e-05, + "loss": 3.6526, + "step": 642560 + }, + { + "epoch": 0.01, + "learning_rate": 3.947167220379425e-05, + "loss": 3.6518, + "step": 643072 + }, + { + "epoch": 0.01, + "learning_rate": 3.946330263508746e-05, + "loss": 3.6655, + "step": 643584 + }, + { + "epoch": 0.01, + "learning_rate": 3.9454933066380675e-05, + "loss": 3.6675, + "step": 644096 + }, + { + "epoch": 0.01, + "learning_rate": 3.9446547118870155e-05, + "loss": 3.6591, + "step": 644608 + }, + { + "epoch": 0.01, + "learning_rate": 3.9438161171359635e-05, + "loss": 3.6635, + "step": 645120 + }, + { + "epoch": 0.01, + "learning_rate": 3.9429775223849115e-05, + "loss": 3.6549, + "step": 645632 + }, + { + "epoch": 0.01, + "learning_rate": 3.9421389276338595e-05, + "loss": 3.6738, + "step": 646144 + }, + { + "epoch": 0.01, + "learning_rate": 3.9413003328828075e-05, + "loss": 3.6708, + "step": 646656 + }, + { + "epoch": 0.01, + "learning_rate": 3.9404617381317555e-05, + "loss": 3.669, + "step": 647168 + }, + { + "epoch": 0.01, + "learning_rate": 3.9396247812610764e-05, + "loss": 3.6733, + "step": 647680 + }, + { + "epoch": 0.01, + "learning_rate": 3.9387861865100244e-05, + "loss": 3.672, + "step": 648192 + }, + { + "epoch": 0.01, + "learning_rate": 3.9379475917589724e-05, + "loss": 3.6836, + "step": 648704 + }, + { + "epoch": 0.01, + "learning_rate": 3.9371089970079204e-05, + "loss": 3.658, + "step": 649216 + }, + { + "epoch": 0.01, + "learning_rate": 3.936272040137241e-05, + "loss": 3.6796, + "step": 649728 + }, + { + "epoch": 0.01, + "learning_rate": 3.935433445386189e-05, + "loss": 3.6633, + "step": 650240 + }, + { + "epoch": 0.01, + "learning_rate": 3.934596488515511e-05, + "loss": 3.6576, + "step": 650752 + }, + { + "epoch": 0.01, + "learning_rate": 3.933757893764459e-05, + "loss": 3.6733, + "step": 651264 + }, + { + "epoch": 0.01, + "learning_rate": 3.932919299013407e-05, + "loss": 3.6713, + "step": 651776 + }, + { + "epoch": 0.01, + "learning_rate": 3.932080704262355e-05, + "loss": 3.671, + "step": 652288 + }, + { + "epoch": 0.01, + "learning_rate": 3.931243747391676e-05, + "loss": 3.6791, + "step": 652800 + }, + { + "epoch": 0.01, + "learning_rate": 3.930405152640624e-05, + "loss": 3.6535, + "step": 653312 + }, + { + "epoch": 0.01, + "learning_rate": 3.929566557889572e-05, + "loss": 3.6476, + "step": 653824 + }, + { + "epoch": 0.01, + "learning_rate": 3.92872796313852e-05, + "loss": 3.6626, + "step": 654336 + }, + { + "epoch": 0.01, + "learning_rate": 3.927889368387468e-05, + "loss": 3.6748, + "step": 654848 + }, + { + "epoch": 0.01, + "learning_rate": 3.927050773636415e-05, + "loss": 3.6684, + "step": 655360 + }, + { + "epoch": 0.01, + "learning_rate": 3.926212178885363e-05, + "loss": 3.6656, + "step": 655872 + }, + { + "epoch": 0.02, + "learning_rate": 3.925375222014685e-05, + "loss": 3.6591, + "step": 656384 + }, + { + "epoch": 0.02, + "learning_rate": 3.9245366272636333e-05, + "loss": 3.6603, + "step": 656896 + }, + { + "epoch": 0.02, + "learning_rate": 3.923698032512581e-05, + "loss": 3.6686, + "step": 657408 + }, + { + "epoch": 0.02, + "learning_rate": 3.922859437761529e-05, + "loss": 3.6604, + "step": 657920 + }, + { + "epoch": 0.02, + "learning_rate": 3.9220208430104767e-05, + "loss": 3.6667, + "step": 658432 + }, + { + "epoch": 0.02, + "learning_rate": 3.9211822482594247e-05, + "loss": 3.6724, + "step": 658944 + }, + { + "epoch": 0.02, + "learning_rate": 3.9203436535083726e-05, + "loss": 3.6703, + "step": 659456 + }, + { + "epoch": 0.02, + "learning_rate": 3.9195066966376936e-05, + "loss": 3.6609, + "step": 659968 + }, + { + "epoch": 0.02, + "learning_rate": 3.9186681018866416e-05, + "loss": 3.6627, + "step": 660480 + }, + { + "epoch": 0.02, + "learning_rate": 3.9178295071355896e-05, + "loss": 3.6591, + "step": 660992 + }, + { + "epoch": 0.02, + "learning_rate": 3.9169909123845375e-05, + "loss": 3.6644, + "step": 661504 + }, + { + "epoch": 0.02, + "learning_rate": 3.9161523176334855e-05, + "loss": 3.6685, + "step": 662016 + }, + { + "epoch": 0.02, + "learning_rate": 3.915315360762807e-05, + "loss": 3.6655, + "step": 662528 + }, + { + "epoch": 0.02, + "learning_rate": 3.914476766011755e-05, + "loss": 3.6603, + "step": 663040 + }, + { + "epoch": 0.02, + "learning_rate": 3.913638171260703e-05, + "loss": 3.652, + "step": 663552 + }, + { + "epoch": 0.02, + "learning_rate": 3.912799576509651e-05, + "loss": 3.6635, + "step": 664064 + }, + { + "epoch": 0.02, + "learning_rate": 3.911960981758599e-05, + "loss": 3.6564, + "step": 664576 + }, + { + "epoch": 0.02, + "learning_rate": 3.91112402488792e-05, + "loss": 3.6418, + "step": 665088 + }, + { + "epoch": 0.02, + "learning_rate": 3.910285430136868e-05, + "loss": 3.6677, + "step": 665600 + }, + { + "epoch": 0.02, + "learning_rate": 3.909446835385816e-05, + "loss": 3.6594, + "step": 666112 + }, + { + "epoch": 0.02, + "learning_rate": 3.908608240634764e-05, + "loss": 3.662, + "step": 666624 + }, + { + "epoch": 0.02, + "learning_rate": 3.907769645883712e-05, + "loss": 3.6496, + "step": 667136 + }, + { + "epoch": 0.02, + "learning_rate": 3.90693105113266e-05, + "loss": 3.6669, + "step": 667648 + }, + { + "epoch": 0.02, + "learning_rate": 3.906094094261981e-05, + "loss": 3.6625, + "step": 668160 + }, + { + "epoch": 0.02, + "learning_rate": 3.905255499510929e-05, + "loss": 3.6495, + "step": 668672 + }, + { + "epoch": 0.02, + "learning_rate": 3.904416904759877e-05, + "loss": 3.6741, + "step": 669184 + }, + { + "epoch": 0.02, + "learning_rate": 3.9035783100088256e-05, + "loss": 3.6676, + "step": 669696 + }, + { + "epoch": 0.02, + "learning_rate": 3.9027397152577736e-05, + "loss": 3.6592, + "step": 670208 + }, + { + "epoch": 0.02, + "learning_rate": 3.9019011205067216e-05, + "loss": 3.6647, + "step": 670720 + }, + { + "epoch": 0.02, + "learning_rate": 3.9010625257556696e-05, + "loss": 3.6483, + "step": 671232 + }, + { + "epoch": 0.02, + "learning_rate": 3.900223931004617e-05, + "loss": 3.6676, + "step": 671744 + }, + { + "epoch": 0.02, + "learning_rate": 3.8993886120143114e-05, + "loss": 3.6558, + "step": 672256 + }, + { + "epoch": 0.02, + "learning_rate": 3.8985500172632594e-05, + "loss": 3.663, + "step": 672768 + }, + { + "epoch": 0.02, + "learning_rate": 3.8977114225122074e-05, + "loss": 3.6539, + "step": 673280 + }, + { + "epoch": 0.02, + "learning_rate": 3.8968728277611554e-05, + "loss": 3.6655, + "step": 673792 + }, + { + "epoch": 0.02, + "learning_rate": 3.896035870890476e-05, + "loss": 3.6578, + "step": 674304 + }, + { + "epoch": 0.02, + "learning_rate": 3.895197276139424e-05, + "loss": 3.6571, + "step": 674816 + }, + { + "epoch": 0.02, + "learning_rate": 3.894358681388372e-05, + "loss": 3.655, + "step": 675328 + }, + { + "epoch": 0.02, + "learning_rate": 3.89352008663732e-05, + "loss": 3.6624, + "step": 675840 + }, + { + "epoch": 0.02, + "learning_rate": 3.892681491886269e-05, + "loss": 3.659, + "step": 676352 + }, + { + "epoch": 0.02, + "learning_rate": 3.891842897135217e-05, + "loss": 3.6663, + "step": 676864 + }, + { + "epoch": 0.02, + "learning_rate": 3.891004302384164e-05, + "loss": 3.658, + "step": 677376 + }, + { + "epoch": 0.02, + "learning_rate": 3.890165707633112e-05, + "loss": 3.6749, + "step": 677888 + }, + { + "epoch": 0.02, + "learning_rate": 3.889328750762434e-05, + "loss": 3.6426, + "step": 678400 + }, + { + "epoch": 0.02, + "learning_rate": 3.888490156011381e-05, + "loss": 3.6681, + "step": 678912 + }, + { + "epoch": 0.02, + "learning_rate": 3.887653199140703e-05, + "loss": 3.6646, + "step": 679424 + }, + { + "epoch": 0.02, + "learning_rate": 3.886814604389651e-05, + "loss": 3.6626, + "step": 679936 + }, + { + "epoch": 0.02, + "learning_rate": 3.885976009638599e-05, + "loss": 3.6566, + "step": 680448 + }, + { + "epoch": 0.02, + "learning_rate": 3.885137414887546e-05, + "loss": 3.6608, + "step": 680960 + }, + { + "epoch": 0.02, + "learning_rate": 3.8843004580168676e-05, + "loss": 3.659, + "step": 681472 + }, + { + "epoch": 0.02, + "learning_rate": 3.8834618632658156e-05, + "loss": 3.6783, + "step": 681984 + }, + { + "epoch": 0.02, + "learning_rate": 3.882623268514764e-05, + "loss": 3.6501, + "step": 682496 + }, + { + "epoch": 0.02, + "learning_rate": 3.8817846737637116e-05, + "loss": 3.6583, + "step": 683008 + }, + { + "epoch": 0.02, + "learning_rate": 3.8809460790126596e-05, + "loss": 3.6527, + "step": 683520 + }, + { + "epoch": 0.02, + "learning_rate": 3.8801074842616076e-05, + "loss": 3.6635, + "step": 684032 + }, + { + "epoch": 0.02, + "learning_rate": 3.8792705273909285e-05, + "loss": 3.653, + "step": 684544 + }, + { + "epoch": 0.02, + "learning_rate": 3.8784319326398765e-05, + "loss": 3.6612, + "step": 685056 + }, + { + "epoch": 0.02, + "learning_rate": 3.8775933378888245e-05, + "loss": 3.6594, + "step": 685568 + }, + { + "epoch": 0.02, + "learning_rate": 3.8767547431377725e-05, + "loss": 3.6524, + "step": 686080 + }, + { + "epoch": 0.02, + "learning_rate": 3.8759161483867205e-05, + "loss": 3.6629, + "step": 686592 + }, + { + "epoch": 0.03, + "eval_loss": 3.8484647274017334, + "eval_runtime": 315.724, + "eval_samples_per_second": 1208.622, + "eval_steps_per_second": 37.77, + "step": 686880 + }, + { + "epoch": 1.0, + "learning_rate": 3.8750791915160414e-05, + "loss": 3.6526, + "step": 687104 + }, + { + "epoch": 1.0, + "learning_rate": 3.8742405967649894e-05, + "loss": 3.6489, + "step": 687616 + }, + { + "epoch": 1.0, + "learning_rate": 3.873402002013938e-05, + "loss": 3.6621, + "step": 688128 + }, + { + "epoch": 1.0, + "learning_rate": 3.872563407262886e-05, + "loss": 3.6598, + "step": 688640 + }, + { + "epoch": 1.0, + "learning_rate": 3.871726450392207e-05, + "loss": 3.6638, + "step": 689152 + }, + { + "epoch": 1.0, + "learning_rate": 3.870887855641155e-05, + "loss": 3.6544, + "step": 689664 + }, + { + "epoch": 1.0, + "learning_rate": 3.870049260890103e-05, + "loss": 3.6511, + "step": 690176 + }, + { + "epoch": 1.0, + "learning_rate": 3.869210666139051e-05, + "loss": 3.657, + "step": 690688 + }, + { + "epoch": 1.0, + "learning_rate": 3.868373709268372e-05, + "loss": 3.654, + "step": 691200 + }, + { + "epoch": 1.0, + "learning_rate": 3.86753511451732e-05, + "loss": 3.6662, + "step": 691712 + }, + { + "epoch": 1.0, + "learning_rate": 3.866696519766268e-05, + "loss": 3.6595, + "step": 692224 + }, + { + "epoch": 1.0, + "learning_rate": 3.865857925015216e-05, + "loss": 3.6595, + "step": 692736 + }, + { + "epoch": 1.0, + "learning_rate": 3.865020968144537e-05, + "loss": 3.6626, + "step": 693248 + }, + { + "epoch": 1.0, + "learning_rate": 3.864182373393485e-05, + "loss": 3.6434, + "step": 693760 + }, + { + "epoch": 1.0, + "learning_rate": 3.8633437786424334e-05, + "loss": 3.6574, + "step": 694272 + }, + { + "epoch": 1.0, + "learning_rate": 3.8625051838913814e-05, + "loss": 3.6471, + "step": 694784 + }, + { + "epoch": 1.0, + "learning_rate": 3.8616665891403294e-05, + "loss": 3.6451, + "step": 695296 + }, + { + "epoch": 1.0, + "learning_rate": 3.8608296322696503e-05, + "loss": 3.6509, + "step": 695808 + }, + { + "epoch": 1.0, + "learning_rate": 3.8599910375185983e-05, + "loss": 3.6485, + "step": 696320 + }, + { + "epoch": 1.0, + "learning_rate": 3.8591524427675463e-05, + "loss": 3.656, + "step": 696832 + }, + { + "epoch": 1.0, + "learning_rate": 3.858313848016494e-05, + "loss": 3.6671, + "step": 697344 + }, + { + "epoch": 1.0, + "learning_rate": 3.857475253265442e-05, + "loss": 3.6582, + "step": 697856 + }, + { + "epoch": 1.0, + "learning_rate": 3.85663665851439e-05, + "loss": 3.6464, + "step": 698368 + }, + { + "epoch": 1.0, + "learning_rate": 3.855798063763338e-05, + "loss": 3.6499, + "step": 698880 + }, + { + "epoch": 1.0, + "learning_rate": 3.854959469012286e-05, + "loss": 3.6479, + "step": 699392 + }, + { + "epoch": 1.0, + "learning_rate": 3.854122512141607e-05, + "loss": 3.65, + "step": 699904 + }, + { + "epoch": 1.0, + "learning_rate": 3.853283917390555e-05, + "loss": 3.6421, + "step": 700416 + }, + { + "epoch": 1.0, + "learning_rate": 3.852446960519877e-05, + "loss": 3.6575, + "step": 700928 + }, + { + "epoch": 1.0, + "learning_rate": 3.851608365768825e-05, + "loss": 3.6458, + "step": 701440 + }, + { + "epoch": 1.0, + "learning_rate": 3.850769771017773e-05, + "loss": 3.6466, + "step": 701952 + }, + { + "epoch": 1.01, + "learning_rate": 3.849931176266721e-05, + "loss": 3.6428, + "step": 702464 + }, + { + "epoch": 1.01, + "learning_rate": 3.849092581515669e-05, + "loss": 3.6615, + "step": 702976 + }, + { + "epoch": 1.01, + "learning_rate": 3.848253986764617e-05, + "loss": 3.6488, + "step": 703488 + }, + { + "epoch": 1.01, + "learning_rate": 3.847415392013565e-05, + "loss": 3.6472, + "step": 704000 + }, + { + "epoch": 1.01, + "learning_rate": 3.846578435142886e-05, + "loss": 3.6503, + "step": 704512 + }, + { + "epoch": 1.01, + "learning_rate": 3.845739840391834e-05, + "loss": 3.6509, + "step": 705024 + }, + { + "epoch": 1.01, + "learning_rate": 3.844901245640782e-05, + "loss": 3.6539, + "step": 705536 + }, + { + "epoch": 1.01, + "learning_rate": 3.84406265088973e-05, + "loss": 3.6355, + "step": 706048 + }, + { + "epoch": 1.01, + "learning_rate": 3.8432256940190506e-05, + "loss": 3.638, + "step": 706560 + }, + { + "epoch": 1.01, + "learning_rate": 3.8423870992679986e-05, + "loss": 3.6433, + "step": 707072 + }, + { + "epoch": 1.01, + "learning_rate": 3.841548504516947e-05, + "loss": 3.6416, + "step": 707584 + }, + { + "epoch": 1.01, + "learning_rate": 3.8407099097658946e-05, + "loss": 3.6479, + "step": 708096 + }, + { + "epoch": 1.01, + "learning_rate": 3.839872952895216e-05, + "loss": 3.6469, + "step": 708608 + }, + { + "epoch": 1.01, + "learning_rate": 3.839034358144164e-05, + "loss": 3.6501, + "step": 709120 + }, + { + "epoch": 1.01, + "learning_rate": 3.838195763393112e-05, + "loss": 3.6467, + "step": 709632 + }, + { + "epoch": 1.01, + "learning_rate": 3.8373571686420595e-05, + "loss": 3.6479, + "step": 710144 + }, + { + "epoch": 1.01, + "learning_rate": 3.8365185738910075e-05, + "loss": 3.6571, + "step": 710656 + }, + { + "epoch": 1.01, + "learning_rate": 3.8356799791399555e-05, + "loss": 3.6402, + "step": 711168 + }, + { + "epoch": 1.01, + "learning_rate": 3.834843022269277e-05, + "loss": 3.6235, + "step": 711680 + }, + { + "epoch": 1.01, + "learning_rate": 3.8340044275182244e-05, + "loss": 3.6599, + "step": 712192 + }, + { + "epoch": 1.01, + "learning_rate": 3.8331658327671724e-05, + "loss": 3.6432, + "step": 712704 + }, + { + "epoch": 1.01, + "learning_rate": 3.832327238016121e-05, + "loss": 3.6498, + "step": 713216 + }, + { + "epoch": 1.01, + "learning_rate": 3.831488643265069e-05, + "loss": 3.6442, + "step": 713728 + }, + { + "epoch": 1.01, + "learning_rate": 3.83065168639439e-05, + "loss": 3.6395, + "step": 714240 + }, + { + "epoch": 1.01, + "learning_rate": 3.829813091643338e-05, + "loss": 3.634, + "step": 714752 + }, + { + "epoch": 1.01, + "learning_rate": 3.828974496892286e-05, + "loss": 3.6385, + "step": 715264 + }, + { + "epoch": 1.01, + "learning_rate": 3.828135902141234e-05, + "loss": 3.6518, + "step": 715776 + }, + { + "epoch": 1.01, + "learning_rate": 3.827297307390182e-05, + "loss": 3.645, + "step": 716288 + }, + { + "epoch": 1.01, + "learning_rate": 3.82645871263913e-05, + "loss": 3.6581, + "step": 716800 + }, + { + "epoch": 1.01, + "learning_rate": 3.825620117888078e-05, + "loss": 3.6439, + "step": 717312 + }, + { + "epoch": 1.01, + "learning_rate": 3.824781523137026e-05, + "loss": 3.6318, + "step": 717824 + }, + { + "epoch": 1.01, + "learning_rate": 3.823944566266347e-05, + "loss": 3.657, + "step": 718336 + }, + { + "epoch": 1.01, + "learning_rate": 3.823105971515295e-05, + "loss": 3.6306, + "step": 718848 + }, + { + "epoch": 1.01, + "learning_rate": 3.822267376764243e-05, + "loss": 3.6282, + "step": 719360 + }, + { + "epoch": 1.01, + "learning_rate": 3.821428782013191e-05, + "loss": 3.6421, + "step": 719872 + }, + { + "epoch": 1.01, + "learning_rate": 3.8205918251425124e-05, + "loss": 3.6392, + "step": 720384 + }, + { + "epoch": 1.01, + "learning_rate": 3.8197532303914604e-05, + "loss": 3.6353, + "step": 720896 + }, + { + "epoch": 1.01, + "learning_rate": 3.8189146356404084e-05, + "loss": 3.6357, + "step": 721408 + }, + { + "epoch": 1.01, + "learning_rate": 3.8180760408893564e-05, + "loss": 3.633, + "step": 721920 + }, + { + "epoch": 1.01, + "learning_rate": 3.8172374461383044e-05, + "loss": 3.6477, + "step": 722432 + }, + { + "epoch": 1.01, + "learning_rate": 3.8163988513872524e-05, + "loss": 3.6488, + "step": 722944 + }, + { + "epoch": 1.01, + "learning_rate": 3.8155602566362004e-05, + "loss": 3.6437, + "step": 723456 + }, + { + "epoch": 1.01, + "learning_rate": 3.8147216618851484e-05, + "loss": 3.6471, + "step": 723968 + }, + { + "epoch": 1.01, + "learning_rate": 3.813886342894842e-05, + "loss": 3.6467, + "step": 724480 + }, + { + "epoch": 1.01, + "learning_rate": 3.81304774814379e-05, + "loss": 3.6578, + "step": 724992 + }, + { + "epoch": 1.01, + "learning_rate": 3.812209153392738e-05, + "loss": 3.6358, + "step": 725504 + }, + { + "epoch": 1.01, + "learning_rate": 3.811370558641686e-05, + "loss": 3.6564, + "step": 726016 + }, + { + "epoch": 1.01, + "learning_rate": 3.810531963890634e-05, + "loss": 3.6373, + "step": 726528 + }, + { + "epoch": 1.01, + "learning_rate": 3.809695007019956e-05, + "loss": 3.6364, + "step": 727040 + }, + { + "epoch": 1.01, + "learning_rate": 3.808856412268904e-05, + "loss": 3.643, + "step": 727552 + }, + { + "epoch": 1.01, + "learning_rate": 3.808017817517852e-05, + "loss": 3.6499, + "step": 728064 + }, + { + "epoch": 1.01, + "learning_rate": 3.8071792227668e-05, + "loss": 3.65, + "step": 728576 + }, + { + "epoch": 1.01, + "learning_rate": 3.806340628015748e-05, + "loss": 3.6553, + "step": 729088 + }, + { + "epoch": 1.01, + "learning_rate": 3.8055036711450686e-05, + "loss": 3.6273, + "step": 729600 + }, + { + "epoch": 1.01, + "learning_rate": 3.8046650763940166e-05, + "loss": 3.6269, + "step": 730112 + }, + { + "epoch": 1.01, + "learning_rate": 3.8038264816429646e-05, + "loss": 3.6373, + "step": 730624 + }, + { + "epoch": 1.01, + "learning_rate": 3.8029878868919126e-05, + "loss": 3.6495, + "step": 731136 + }, + { + "epoch": 1.01, + "learning_rate": 3.8021509300212335e-05, + "loss": 3.6403, + "step": 731648 + }, + { + "epoch": 1.01, + "learning_rate": 3.8013123352701815e-05, + "loss": 3.6407, + "step": 732160 + }, + { + "epoch": 1.02, + "learning_rate": 3.8004737405191295e-05, + "loss": 3.6376, + "step": 732672 + }, + { + "epoch": 1.02, + "learning_rate": 3.799635145768078e-05, + "loss": 3.6394, + "step": 733184 + }, + { + "epoch": 1.02, + "learning_rate": 3.798798188897399e-05, + "loss": 3.6403, + "step": 733696 + }, + { + "epoch": 1.02, + "learning_rate": 3.797959594146347e-05, + "loss": 3.6385, + "step": 734208 + }, + { + "epoch": 1.02, + "learning_rate": 3.797120999395295e-05, + "loss": 3.6426, + "step": 734720 + }, + { + "epoch": 1.02, + "learning_rate": 3.796282404644243e-05, + "loss": 3.6483, + "step": 735232 + }, + { + "epoch": 1.02, + "learning_rate": 3.7954438098931904e-05, + "loss": 3.6483, + "step": 735744 + }, + { + "epoch": 1.02, + "learning_rate": 3.794606853022512e-05, + "loss": 3.6383, + "step": 736256 + }, + { + "epoch": 1.02, + "learning_rate": 3.79376825827146e-05, + "loss": 3.6366, + "step": 736768 + }, + { + "epoch": 1.02, + "learning_rate": 3.792929663520407e-05, + "loss": 3.6374, + "step": 737280 + }, + { + "epoch": 1.02, + "learning_rate": 3.792091068769355e-05, + "loss": 3.6378, + "step": 737792 + }, + { + "epoch": 1.02, + "learning_rate": 3.791252474018303e-05, + "loss": 3.6438, + "step": 738304 + }, + { + "epoch": 1.02, + "learning_rate": 3.790415517147625e-05, + "loss": 3.6432, + "step": 738816 + }, + { + "epoch": 1.02, + "learning_rate": 3.789576922396573e-05, + "loss": 3.6341, + "step": 739328 + }, + { + "epoch": 1.02, + "learning_rate": 3.788738327645521e-05, + "loss": 3.626, + "step": 739840 + }, + { + "epoch": 1.02, + "learning_rate": 3.787899732894469e-05, + "loss": 3.643, + "step": 740352 + }, + { + "epoch": 1.02, + "learning_rate": 3.787061138143417e-05, + "loss": 3.632, + "step": 740864 + }, + { + "epoch": 1.02, + "learning_rate": 3.786222543392365e-05, + "loss": 3.616, + "step": 741376 + }, + { + "epoch": 1.02, + "learning_rate": 3.785385586521686e-05, + "loss": 3.6406, + "step": 741888 + }, + { + "epoch": 1.02, + "learning_rate": 3.784546991770634e-05, + "loss": 3.6451, + "step": 742400 + }, + { + "epoch": 1.02, + "learning_rate": 3.783708397019582e-05, + "loss": 3.6337, + "step": 742912 + }, + { + "epoch": 1.02, + "learning_rate": 3.78286980226853e-05, + "loss": 3.628, + "step": 743424 + }, + { + "epoch": 1.02, + "learning_rate": 3.782032845397851e-05, + "loss": 3.6379, + "step": 743936 + }, + { + "epoch": 1.02, + "learning_rate": 3.781194250646799e-05, + "loss": 3.6375, + "step": 744448 + }, + { + "epoch": 1.02, + "learning_rate": 3.7803556558957474e-05, + "loss": 3.6248, + "step": 744960 + }, + { + "epoch": 1.02, + "learning_rate": 3.7795170611446954e-05, + "loss": 3.6525, + "step": 745472 + }, + { + "epoch": 1.02, + "learning_rate": 3.7786784663936433e-05, + "loss": 3.646, + "step": 745984 + }, + { + "epoch": 1.02, + "learning_rate": 3.777841509522964e-05, + "loss": 3.6322, + "step": 746496 + }, + { + "epoch": 1.02, + "learning_rate": 3.777002914771912e-05, + "loss": 3.6406, + "step": 747008 + }, + { + "epoch": 1.02, + "learning_rate": 3.77616432002086e-05, + "loss": 3.6283, + "step": 747520 + }, + { + "epoch": 1.02, + "learning_rate": 3.775325725269808e-05, + "loss": 3.643, + "step": 748032 + }, + { + "epoch": 1.02, + "learning_rate": 3.774488768399129e-05, + "loss": 3.6321, + "step": 748544 + }, + { + "epoch": 1.02, + "learning_rate": 3.773650173648077e-05, + "loss": 3.6368, + "step": 749056 + }, + { + "epoch": 1.02, + "learning_rate": 3.772811578897025e-05, + "loss": 3.6303, + "step": 749568 + }, + { + "epoch": 1.02, + "learning_rate": 3.771972984145973e-05, + "loss": 3.641, + "step": 750080 + }, + { + "epoch": 1.02, + "learning_rate": 3.771136027275294e-05, + "loss": 3.6351, + "step": 750592 + }, + { + "epoch": 1.02, + "learning_rate": 3.770297432524243e-05, + "loss": 3.6358, + "step": 751104 + }, + { + "epoch": 1.02, + "learning_rate": 3.769458837773191e-05, + "loss": 3.628, + "step": 751616 + }, + { + "epoch": 1.02, + "learning_rate": 3.768620243022139e-05, + "loss": 3.6361, + "step": 752128 + }, + { + "epoch": 1.02, + "learning_rate": 3.767781648271087e-05, + "loss": 3.6331, + "step": 752640 + }, + { + "epoch": 1.02, + "learning_rate": 3.766943053520035e-05, + "loss": 3.6426, + "step": 753152 + }, + { + "epoch": 1.02, + "learning_rate": 3.766104458768983e-05, + "loss": 3.6355, + "step": 753664 + }, + { + "epoch": 1.02, + "learning_rate": 3.7652675018983036e-05, + "loss": 3.6456, + "step": 754176 + }, + { + "epoch": 1.02, + "learning_rate": 3.7644289071472516e-05, + "loss": 3.6186, + "step": 754688 + }, + { + "epoch": 1.02, + "learning_rate": 3.7635903123961996e-05, + "loss": 3.6463, + "step": 755200 + }, + { + "epoch": 1.02, + "learning_rate": 3.7627533555255205e-05, + "loss": 3.6397, + "step": 755712 + }, + { + "epoch": 1.02, + "learning_rate": 3.7619147607744685e-05, + "loss": 3.638, + "step": 756224 + }, + { + "epoch": 1.02, + "learning_rate": 3.7610761660234165e-05, + "loss": 3.6374, + "step": 756736 + }, + { + "epoch": 1.02, + "learning_rate": 3.7602375712723645e-05, + "loss": 3.6342, + "step": 757248 + }, + { + "epoch": 1.02, + "learning_rate": 3.7593989765213125e-05, + "loss": 3.6368, + "step": 757760 + }, + { + "epoch": 1.02, + "learning_rate": 3.758562019650634e-05, + "loss": 3.6579, + "step": 758272 + }, + { + "epoch": 1.02, + "learning_rate": 3.757723424899582e-05, + "loss": 3.624, + "step": 758784 + }, + { + "epoch": 1.02, + "learning_rate": 3.75688483014853e-05, + "loss": 3.6363, + "step": 759296 + }, + { + "epoch": 1.02, + "learning_rate": 3.756046235397478e-05, + "loss": 3.63, + "step": 759808 + }, + { + "epoch": 1.02, + "learning_rate": 3.755207640646426e-05, + "loss": 3.6358, + "step": 760320 + }, + { + "epoch": 1.02, + "learning_rate": 3.754370683775747e-05, + "loss": 3.6292, + "step": 760832 + }, + { + "epoch": 1.02, + "learning_rate": 3.753532089024695e-05, + "loss": 3.6406, + "step": 761344 + }, + { + "epoch": 1.02, + "learning_rate": 3.752693494273643e-05, + "loss": 3.6357, + "step": 761856 + }, + { + "epoch": 1.02, + "learning_rate": 3.751854899522591e-05, + "loss": 3.6334, + "step": 762368 + }, + { + "epoch": 1.02, + "learning_rate": 3.751016304771538e-05, + "loss": 3.6356, + "step": 762880 + }, + { + "epoch": 1.03, + "eval_loss": 3.845120429992676, + "eval_runtime": 315.3922, + "eval_samples_per_second": 1209.893, + "eval_steps_per_second": 37.81, + "step": 763200 + }, + { + "epoch": 0.0, + "learning_rate": 3.75017934790086e-05, + "loss": 3.6306, + "step": 763392 + }, + { + "epoch": 0.0, + "learning_rate": 3.749340753149808e-05, + "loss": 3.6279, + "step": 763904 + }, + { + "epoch": 0.0, + "learning_rate": 3.748502158398756e-05, + "loss": 3.6387, + "step": 764416 + }, + { + "epoch": 0.0, + "learning_rate": 3.747663563647704e-05, + "loss": 3.6409, + "step": 764928 + }, + { + "epoch": 0.0, + "learning_rate": 3.7468266067770254e-05, + "loss": 3.6395, + "step": 765440 + }, + { + "epoch": 0.0, + "learning_rate": 3.7459880120259734e-05, + "loss": 3.6316, + "step": 765952 + }, + { + "epoch": 0.0, + "learning_rate": 3.745149417274921e-05, + "loss": 3.6282, + "step": 766464 + }, + { + "epoch": 0.0, + "learning_rate": 3.744310822523869e-05, + "loss": 3.6327, + "step": 766976 + }, + { + "epoch": 0.0, + "learning_rate": 3.74347386565319e-05, + "loss": 3.6335, + "step": 767488 + }, + { + "epoch": 0.0, + "learning_rate": 3.742635270902138e-05, + "loss": 3.6408, + "step": 768000 + }, + { + "epoch": 0.0, + "learning_rate": 3.7417966761510856e-05, + "loss": 3.6348, + "step": 768512 + }, + { + "epoch": 0.0, + "learning_rate": 3.7409580814000336e-05, + "loss": 3.6355, + "step": 769024 + }, + { + "epoch": 0.0, + "learning_rate": 3.7401194866489816e-05, + "loss": 3.6429, + "step": 769536 + }, + { + "epoch": 0.0, + "learning_rate": 3.739282529778303e-05, + "loss": 3.6156, + "step": 770048 + }, + { + "epoch": 0.0, + "learning_rate": 3.738443935027251e-05, + "loss": 3.6399, + "step": 770560 + }, + { + "epoch": 0.0, + "learning_rate": 3.737605340276199e-05, + "loss": 3.6195, + "step": 771072 + }, + { + "epoch": 0.0, + "learning_rate": 3.736766745525147e-05, + "loss": 3.6226, + "step": 771584 + }, + { + "epoch": 0.0, + "learning_rate": 3.735929788654468e-05, + "loss": 3.6252, + "step": 772096 + }, + { + "epoch": 0.0, + "learning_rate": 3.735091193903416e-05, + "loss": 3.6257, + "step": 772608 + }, + { + "epoch": 0.0, + "learning_rate": 3.734252599152364e-05, + "loss": 3.6339, + "step": 773120 + }, + { + "epoch": 0.0, + "learning_rate": 3.733414004401312e-05, + "loss": 3.6401, + "step": 773632 + }, + { + "epoch": 0.0, + "learning_rate": 3.73257540965026e-05, + "loss": 3.6375, + "step": 774144 + }, + { + "epoch": 0.0, + "learning_rate": 3.731736814899208e-05, + "loss": 3.6259, + "step": 774656 + }, + { + "epoch": 0.0, + "learning_rate": 3.730898220148156e-05, + "loss": 3.6236, + "step": 775168 + }, + { + "epoch": 0.0, + "learning_rate": 3.730059625397104e-05, + "loss": 3.6297, + "step": 775680 + }, + { + "epoch": 0.0, + "learning_rate": 3.729222668526425e-05, + "loss": 3.6239, + "step": 776192 + }, + { + "epoch": 0.0, + "learning_rate": 3.728384073775374e-05, + "loss": 3.6207, + "step": 776704 + }, + { + "epoch": 0.0, + "learning_rate": 3.7275471169046946e-05, + "loss": 3.6366, + "step": 777216 + }, + { + "epoch": 0.0, + "learning_rate": 3.7267085221536426e-05, + "loss": 3.6191, + "step": 777728 + }, + { + "epoch": 0.0, + "learning_rate": 3.7258699274025906e-05, + "loss": 3.6276, + "step": 778240 + }, + { + "epoch": 0.01, + "learning_rate": 3.7250313326515386e-05, + "loss": 3.6171, + "step": 778752 + }, + { + "epoch": 0.01, + "learning_rate": 3.7241927379004866e-05, + "loss": 3.636, + "step": 779264 + }, + { + "epoch": 0.01, + "learning_rate": 3.7233541431494346e-05, + "loss": 3.6307, + "step": 779776 + }, + { + "epoch": 0.01, + "learning_rate": 3.7225171862787555e-05, + "loss": 3.6219, + "step": 780288 + }, + { + "epoch": 0.01, + "learning_rate": 3.7216785915277035e-05, + "loss": 3.632, + "step": 780800 + }, + { + "epoch": 0.01, + "learning_rate": 3.7208399967766515e-05, + "loss": 3.6209, + "step": 781312 + }, + { + "epoch": 0.01, + "learning_rate": 3.7200014020255995e-05, + "loss": 3.6335, + "step": 781824 + }, + { + "epoch": 0.01, + "learning_rate": 3.7191628072745475e-05, + "loss": 3.6174, + "step": 782336 + }, + { + "epoch": 0.01, + "learning_rate": 3.7183242125234954e-05, + "loss": 3.6116, + "step": 782848 + }, + { + "epoch": 0.01, + "learning_rate": 3.717487255652817e-05, + "loss": 3.6198, + "step": 783360 + }, + { + "epoch": 0.01, + "learning_rate": 3.716648660901765e-05, + "loss": 3.6221, + "step": 783872 + }, + { + "epoch": 0.01, + "learning_rate": 3.715810066150713e-05, + "loss": 3.6195, + "step": 784384 + }, + { + "epoch": 0.01, + "learning_rate": 3.714971471399661e-05, + "loss": 3.6216, + "step": 784896 + }, + { + "epoch": 0.01, + "learning_rate": 3.714132876648609e-05, + "loss": 3.6274, + "step": 785408 + }, + { + "epoch": 0.01, + "learning_rate": 3.71329591977793e-05, + "loss": 3.6255, + "step": 785920 + }, + { + "epoch": 0.01, + "learning_rate": 3.712457325026878e-05, + "loss": 3.6278, + "step": 786432 + }, + { + "epoch": 0.01, + "learning_rate": 3.711618730275826e-05, + "loss": 3.6384, + "step": 786944 + }, + { + "epoch": 0.01, + "learning_rate": 3.710780135524774e-05, + "loss": 3.617, + "step": 787456 + }, + { + "epoch": 0.01, + "learning_rate": 3.709943178654095e-05, + "loss": 3.5979, + "step": 787968 + }, + { + "epoch": 0.01, + "learning_rate": 3.709104583903043e-05, + "loss": 3.6372, + "step": 788480 + }, + { + "epoch": 0.01, + "learning_rate": 3.708265989151991e-05, + "loss": 3.62, + "step": 788992 + }, + { + "epoch": 0.01, + "learning_rate": 3.707427394400939e-05, + "loss": 3.6269, + "step": 789504 + }, + { + "epoch": 0.01, + "learning_rate": 3.706588799649887e-05, + "loss": 3.6197, + "step": 790016 + }, + { + "epoch": 0.01, + "learning_rate": 3.7057518427792084e-05, + "loss": 3.6202, + "step": 790528 + }, + { + "epoch": 0.01, + "learning_rate": 3.7049132480281564e-05, + "loss": 3.6123, + "step": 791040 + }, + { + "epoch": 0.01, + "learning_rate": 3.7040746532771044e-05, + "loss": 3.6132, + "step": 791552 + }, + { + "epoch": 0.01, + "learning_rate": 3.703236058526052e-05, + "loss": 3.635, + "step": 792064 + }, + { + "epoch": 0.01, + "learning_rate": 3.702397463775e-05, + "loss": 3.6183, + "step": 792576 + }, + { + "epoch": 0.01, + "learning_rate": 3.701558869023948e-05, + "loss": 3.6386, + "step": 793088 + }, + { + "epoch": 0.01, + "learning_rate": 3.700720274272896e-05, + "loss": 3.6192, + "step": 793600 + }, + { + "epoch": 0.01, + "learning_rate": 3.699881679521844e-05, + "loss": 3.6058, + "step": 794112 + }, + { + "epoch": 0.01, + "learning_rate": 3.6990447226511646e-05, + "loss": 3.6336, + "step": 794624 + }, + { + "epoch": 0.01, + "learning_rate": 3.6982061279001126e-05, + "loss": 3.616, + "step": 795136 + }, + { + "epoch": 0.01, + "learning_rate": 3.6973675331490606e-05, + "loss": 3.6029, + "step": 795648 + }, + { + "epoch": 0.01, + "learning_rate": 3.696528938398009e-05, + "loss": 3.6182, + "step": 796160 + }, + { + "epoch": 0.01, + "learning_rate": 3.69569198152733e-05, + "loss": 3.6175, + "step": 796672 + }, + { + "epoch": 0.01, + "learning_rate": 3.694853386776278e-05, + "loss": 3.6119, + "step": 797184 + }, + { + "epoch": 0.01, + "learning_rate": 3.694014792025226e-05, + "loss": 3.6126, + "step": 797696 + }, + { + "epoch": 0.01, + "learning_rate": 3.693176197274174e-05, + "loss": 3.6123, + "step": 798208 + }, + { + "epoch": 0.01, + "learning_rate": 3.692339240403495e-05, + "loss": 3.6224, + "step": 798720 + }, + { + "epoch": 0.01, + "learning_rate": 3.691500645652443e-05, + "loss": 3.6271, + "step": 799232 + }, + { + "epoch": 0.01, + "learning_rate": 3.690662050901391e-05, + "loss": 3.6172, + "step": 799744 + }, + { + "epoch": 0.01, + "learning_rate": 3.689823456150339e-05, + "loss": 3.6268, + "step": 800256 + }, + { + "epoch": 0.01, + "learning_rate": 3.688984861399287e-05, + "loss": 3.6245, + "step": 800768 + }, + { + "epoch": 0.01, + "learning_rate": 3.688146266648235e-05, + "loss": 3.6355, + "step": 801280 + }, + { + "epoch": 0.01, + "learning_rate": 3.687307671897183e-05, + "loss": 3.6136, + "step": 801792 + }, + { + "epoch": 0.01, + "learning_rate": 3.686469077146131e-05, + "loss": 3.6349, + "step": 802304 + }, + { + "epoch": 0.01, + "learning_rate": 3.6856321202754526e-05, + "loss": 3.6153, + "step": 802816 + }, + { + "epoch": 0.01, + "learning_rate": 3.6847951634047735e-05, + "loss": 3.6134, + "step": 803328 + }, + { + "epoch": 0.01, + "learning_rate": 3.6839565686537215e-05, + "loss": 3.6246, + "step": 803840 + }, + { + "epoch": 0.01, + "learning_rate": 3.6831179739026695e-05, + "loss": 3.6223, + "step": 804352 + }, + { + "epoch": 0.01, + "learning_rate": 3.6822793791516175e-05, + "loss": 3.6279, + "step": 804864 + }, + { + "epoch": 0.01, + "learning_rate": 3.6814407844005655e-05, + "loss": 3.6318, + "step": 805376 + }, + { + "epoch": 0.01, + "learning_rate": 3.6806038275298864e-05, + "loss": 3.6079, + "step": 805888 + }, + { + "epoch": 0.01, + "learning_rate": 3.6797652327788344e-05, + "loss": 3.6041, + "step": 806400 + }, + { + "epoch": 0.01, + "learning_rate": 3.6789266380277824e-05, + "loss": 3.6127, + "step": 806912 + }, + { + "epoch": 0.01, + "learning_rate": 3.6780880432767304e-05, + "loss": 3.6311, + "step": 807424 + }, + { + "epoch": 0.01, + "learning_rate": 3.677251086406051e-05, + "loss": 3.6147, + "step": 807936 + }, + { + "epoch": 0.01, + "learning_rate": 3.676412491655e-05, + "loss": 3.619, + "step": 808448 + }, + { + "epoch": 0.01, + "learning_rate": 3.675573896903948e-05, + "loss": 3.6211, + "step": 808960 + }, + { + "epoch": 0.02, + "learning_rate": 3.674735302152896e-05, + "loss": 3.6102, + "step": 809472 + }, + { + "epoch": 0.02, + "learning_rate": 3.673898345282217e-05, + "loss": 3.6229, + "step": 809984 + }, + { + "epoch": 0.02, + "learning_rate": 3.673059750531165e-05, + "loss": 3.6141, + "step": 810496 + }, + { + "epoch": 0.02, + "learning_rate": 3.672221155780113e-05, + "loss": 3.6228, + "step": 811008 + }, + { + "epoch": 0.02, + "learning_rate": 3.671382561029061e-05, + "loss": 3.6229, + "step": 811520 + }, + { + "epoch": 0.02, + "learning_rate": 3.670543966278009e-05, + "loss": 3.6282, + "step": 812032 + }, + { + "epoch": 0.02, + "learning_rate": 3.66970700940733e-05, + "loss": 3.611, + "step": 812544 + }, + { + "epoch": 0.02, + "learning_rate": 3.668868414656278e-05, + "loss": 3.6182, + "step": 813056 + }, + { + "epoch": 0.02, + "learning_rate": 3.668029819905226e-05, + "loss": 3.6127, + "step": 813568 + }, + { + "epoch": 0.02, + "learning_rate": 3.667191225154174e-05, + "loss": 3.6197, + "step": 814080 + }, + { + "epoch": 0.02, + "learning_rate": 3.6663542682834954e-05, + "loss": 3.6225, + "step": 814592 + }, + { + "epoch": 0.02, + "learning_rate": 3.6655156735324434e-05, + "loss": 3.617, + "step": 815104 + }, + { + "epoch": 0.02, + "learning_rate": 3.6646770787813914e-05, + "loss": 3.616, + "step": 815616 + }, + { + "epoch": 0.02, + "learning_rate": 3.6638384840303393e-05, + "loss": 3.6073, + "step": 816128 + }, + { + "epoch": 0.02, + "learning_rate": 3.6629998892792873e-05, + "loss": 3.6168, + "step": 816640 + }, + { + "epoch": 0.02, + "learning_rate": 3.662161294528235e-05, + "loss": 3.6128, + "step": 817152 + }, + { + "epoch": 0.02, + "learning_rate": 3.661324337657556e-05, + "loss": 3.5941, + "step": 817664 + }, + { + "epoch": 0.02, + "learning_rate": 3.660485742906504e-05, + "loss": 3.6185, + "step": 818176 + }, + { + "epoch": 0.02, + "learning_rate": 3.659647148155452e-05, + "loss": 3.6185, + "step": 818688 + }, + { + "epoch": 0.02, + "learning_rate": 3.6588085534044e-05, + "loss": 3.614, + "step": 819200 + }, + { + "epoch": 0.02, + "learning_rate": 3.6579699586533476e-05, + "loss": 3.6094, + "step": 819712 + }, + { + "epoch": 0.02, + "learning_rate": 3.6571313639022955e-05, + "loss": 3.6141, + "step": 820224 + }, + { + "epoch": 0.02, + "learning_rate": 3.656294407031617e-05, + "loss": 3.6175, + "step": 820736 + }, + { + "epoch": 0.02, + "learning_rate": 3.655455812280565e-05, + "loss": 3.6033, + "step": 821248 + }, + { + "epoch": 0.02, + "learning_rate": 3.654617217529513e-05, + "loss": 3.6319, + "step": 821760 + }, + { + "epoch": 0.02, + "learning_rate": 3.653778622778461e-05, + "loss": 3.6214, + "step": 822272 + }, + { + "epoch": 0.02, + "learning_rate": 3.652941665907783e-05, + "loss": 3.6119, + "step": 822784 + }, + { + "epoch": 0.02, + "learning_rate": 3.65210307115673e-05, + "loss": 3.6214, + "step": 823296 + }, + { + "epoch": 0.02, + "learning_rate": 3.651264476405678e-05, + "loss": 3.6075, + "step": 823808 + }, + { + "epoch": 0.02, + "learning_rate": 3.650425881654626e-05, + "loss": 3.6199, + "step": 824320 + }, + { + "epoch": 0.02, + "learning_rate": 3.6495889247839476e-05, + "loss": 3.6123, + "step": 824832 + }, + { + "epoch": 0.02, + "learning_rate": 3.648750330032895e-05, + "loss": 3.6117, + "step": 825344 + }, + { + "epoch": 0.02, + "learning_rate": 3.647911735281843e-05, + "loss": 3.6113, + "step": 825856 + }, + { + "epoch": 0.02, + "learning_rate": 3.647073140530791e-05, + "loss": 3.6163, + "step": 826368 + }, + { + "epoch": 0.02, + "learning_rate": 3.6462361836601125e-05, + "loss": 3.6167, + "step": 826880 + }, + { + "epoch": 0.02, + "learning_rate": 3.6453975889090605e-05, + "loss": 3.6104, + "step": 827392 + }, + { + "epoch": 0.02, + "learning_rate": 3.6445589941580085e-05, + "loss": 3.6116, + "step": 827904 + }, + { + "epoch": 0.02, + "learning_rate": 3.6437203994069565e-05, + "loss": 3.6089, + "step": 828416 + }, + { + "epoch": 0.02, + "learning_rate": 3.6428818046559045e-05, + "loss": 3.6123, + "step": 828928 + }, + { + "epoch": 0.02, + "learning_rate": 3.6420432099048525e-05, + "loss": 3.623, + "step": 829440 + }, + { + "epoch": 0.02, + "learning_rate": 3.6412062530341734e-05, + "loss": 3.6161, + "step": 829952 + }, + { + "epoch": 0.02, + "learning_rate": 3.6403676582831214e-05, + "loss": 3.624, + "step": 830464 + }, + { + "epoch": 0.02, + "learning_rate": 3.6395290635320694e-05, + "loss": 3.5956, + "step": 830976 + }, + { + "epoch": 0.02, + "learning_rate": 3.6386904687810174e-05, + "loss": 3.6284, + "step": 831488 + }, + { + "epoch": 0.02, + "learning_rate": 3.637853511910338e-05, + "loss": 3.6161, + "step": 832000 + }, + { + "epoch": 0.02, + "learning_rate": 3.637014917159286e-05, + "loss": 3.6167, + "step": 832512 + }, + { + "epoch": 0.02, + "learning_rate": 3.636176322408234e-05, + "loss": 3.6153, + "step": 833024 + }, + { + "epoch": 0.02, + "learning_rate": 3.635337727657183e-05, + "loss": 3.6072, + "step": 833536 + }, + { + "epoch": 0.02, + "learning_rate": 3.634500770786504e-05, + "loss": 3.6151, + "step": 834048 + }, + { + "epoch": 0.02, + "learning_rate": 3.633662176035452e-05, + "loss": 3.6337, + "step": 834560 + }, + { + "epoch": 0.02, + "learning_rate": 3.6328235812844e-05, + "loss": 3.6043, + "step": 835072 + }, + { + "epoch": 0.02, + "learning_rate": 3.631984986533348e-05, + "loss": 3.6162, + "step": 835584 + }, + { + "epoch": 0.02, + "learning_rate": 3.631146391782296e-05, + "loss": 3.6075, + "step": 836096 + }, + { + "epoch": 0.02, + "learning_rate": 3.630309434911617e-05, + "loss": 3.6132, + "step": 836608 + }, + { + "epoch": 0.02, + "learning_rate": 3.629470840160565e-05, + "loss": 3.6107, + "step": 837120 + }, + { + "epoch": 0.02, + "learning_rate": 3.628632245409513e-05, + "loss": 3.6166, + "step": 837632 + }, + { + "epoch": 0.02, + "learning_rate": 3.627793650658461e-05, + "loss": 3.6162, + "step": 838144 + }, + { + "epoch": 0.02, + "learning_rate": 3.626955055907409e-05, + "loss": 3.6169, + "step": 838656 + }, + { + "epoch": 0.02, + "learning_rate": 3.626116461156357e-05, + "loss": 3.6128, + "step": 839168 + }, + { + "epoch": 0.03, + "eval_loss": 3.8435885906219482, + "eval_runtime": 310.7073, + "eval_samples_per_second": 1228.137, + "eval_steps_per_second": 38.38, + "step": 839520 + }, + { + "epoch": 1.0, + "learning_rate": 3.6252795042856776e-05, + "loss": 3.6096, + "step": 839680 + }, + { + "epoch": 1.0, + "learning_rate": 3.624440909534626e-05, + "loss": 3.6068, + "step": 840192 + }, + { + "epoch": 1.0, + "learning_rate": 3.623602314783574e-05, + "loss": 3.6187, + "step": 840704 + }, + { + "epoch": 1.0, + "learning_rate": 3.622763720032522e-05, + "loss": 3.6169, + "step": 841216 + }, + { + "epoch": 1.0, + "learning_rate": 3.621926763161843e-05, + "loss": 3.6216, + "step": 841728 + }, + { + "epoch": 1.0, + "learning_rate": 3.621088168410791e-05, + "loss": 3.6095, + "step": 842240 + }, + { + "epoch": 1.0, + "learning_rate": 3.620249573659739e-05, + "loss": 3.6082, + "step": 842752 + }, + { + "epoch": 1.0, + "learning_rate": 3.619410978908687e-05, + "loss": 3.6155, + "step": 843264 + }, + { + "epoch": 1.0, + "learning_rate": 3.618574022038008e-05, + "loss": 3.6088, + "step": 843776 + }, + { + "epoch": 1.0, + "learning_rate": 3.617735427286956e-05, + "loss": 3.6171, + "step": 844288 + }, + { + "epoch": 1.0, + "learning_rate": 3.616896832535904e-05, + "loss": 3.6154, + "step": 844800 + }, + { + "epoch": 1.0, + "learning_rate": 3.616058237784852e-05, + "loss": 3.6194, + "step": 845312 + }, + { + "epoch": 1.0, + "learning_rate": 3.615221280914173e-05, + "loss": 3.6177, + "step": 845824 + }, + { + "epoch": 1.0, + "learning_rate": 3.614382686163122e-05, + "loss": 3.5962, + "step": 846336 + }, + { + "epoch": 1.0, + "learning_rate": 3.61354409141207e-05, + "loss": 3.6181, + "step": 846848 + }, + { + "epoch": 1.0, + "learning_rate": 3.612705496661018e-05, + "loss": 3.5959, + "step": 847360 + }, + { + "epoch": 1.0, + "learning_rate": 3.611866901909966e-05, + "loss": 3.6054, + "step": 847872 + }, + { + "epoch": 1.0, + "learning_rate": 3.6110299450392866e-05, + "loss": 3.6069, + "step": 848384 + }, + { + "epoch": 1.0, + "learning_rate": 3.6101913502882346e-05, + "loss": 3.6021, + "step": 848896 + }, + { + "epoch": 1.0, + "learning_rate": 3.6093527555371826e-05, + "loss": 3.6104, + "step": 849408 + }, + { + "epoch": 1.0, + "learning_rate": 3.6085141607861306e-05, + "loss": 3.6236, + "step": 849920 + }, + { + "epoch": 1.0, + "learning_rate": 3.607675566035078e-05, + "loss": 3.6114, + "step": 850432 + }, + { + "epoch": 1.0, + "learning_rate": 3.606836971284026e-05, + "loss": 3.6085, + "step": 850944 + }, + { + "epoch": 1.0, + "learning_rate": 3.605998376532974e-05, + "loss": 3.6067, + "step": 851456 + }, + { + "epoch": 1.0, + "learning_rate": 3.605159781781922e-05, + "loss": 3.6072, + "step": 851968 + }, + { + "epoch": 1.0, + "learning_rate": 3.604324462791617e-05, + "loss": 3.6038, + "step": 852480 + }, + { + "epoch": 1.0, + "learning_rate": 3.603485868040565e-05, + "loss": 3.5993, + "step": 852992 + }, + { + "epoch": 1.0, + "learning_rate": 3.602647273289513e-05, + "loss": 3.6142, + "step": 853504 + }, + { + "epoch": 1.0, + "learning_rate": 3.601808678538461e-05, + "loss": 3.6, + "step": 854016 + }, + { + "epoch": 1.0, + "learning_rate": 3.600971721667782e-05, + "loss": 3.6053, + "step": 854528 + }, + { + "epoch": 1.01, + "learning_rate": 3.60013312691673e-05, + "loss": 3.5998, + "step": 855040 + }, + { + "epoch": 1.01, + "learning_rate": 3.599294532165678e-05, + "loss": 3.6156, + "step": 855552 + }, + { + "epoch": 1.01, + "learning_rate": 3.598455937414625e-05, + "loss": 3.6033, + "step": 856064 + }, + { + "epoch": 1.01, + "learning_rate": 3.597618980543947e-05, + "loss": 3.6059, + "step": 856576 + }, + { + "epoch": 1.01, + "learning_rate": 3.596780385792895e-05, + "loss": 3.6094, + "step": 857088 + }, + { + "epoch": 1.01, + "learning_rate": 3.595941791041843e-05, + "loss": 3.6009, + "step": 857600 + }, + { + "epoch": 1.01, + "learning_rate": 3.595103196290791e-05, + "loss": 3.6149, + "step": 858112 + }, + { + "epoch": 1.01, + "learning_rate": 3.594264601539739e-05, + "loss": 3.5926, + "step": 858624 + }, + { + "epoch": 1.01, + "learning_rate": 3.5934276446690604e-05, + "loss": 3.5947, + "step": 859136 + }, + { + "epoch": 1.01, + "learning_rate": 3.5925890499180084e-05, + "loss": 3.5997, + "step": 859648 + }, + { + "epoch": 1.01, + "learning_rate": 3.591750455166956e-05, + "loss": 3.6036, + "step": 860160 + }, + { + "epoch": 1.01, + "learning_rate": 3.590911860415904e-05, + "loss": 3.599, + "step": 860672 + }, + { + "epoch": 1.01, + "learning_rate": 3.590073265664852e-05, + "loss": 3.6028, + "step": 861184 + }, + { + "epoch": 1.01, + "learning_rate": 3.5892363087941726e-05, + "loss": 3.607, + "step": 861696 + }, + { + "epoch": 1.01, + "learning_rate": 3.5883977140431206e-05, + "loss": 3.6015, + "step": 862208 + }, + { + "epoch": 1.01, + "learning_rate": 3.5875591192920686e-05, + "loss": 3.6059, + "step": 862720 + }, + { + "epoch": 1.01, + "learning_rate": 3.5867205245410166e-05, + "loss": 3.6145, + "step": 863232 + }, + { + "epoch": 1.01, + "learning_rate": 3.5858819297899646e-05, + "loss": 3.6018, + "step": 863744 + }, + { + "epoch": 1.01, + "learning_rate": 3.5850433350389126e-05, + "loss": 3.5804, + "step": 864256 + }, + { + "epoch": 1.01, + "learning_rate": 3.584206378168234e-05, + "loss": 3.6159, + "step": 864768 + }, + { + "epoch": 1.01, + "learning_rate": 3.583367783417182e-05, + "loss": 3.6005, + "step": 865280 + }, + { + "epoch": 1.01, + "learning_rate": 3.58252918866613e-05, + "loss": 3.6034, + "step": 865792 + }, + { + "epoch": 1.01, + "learning_rate": 3.581690593915078e-05, + "loss": 3.5994, + "step": 866304 + }, + { + "epoch": 1.01, + "learning_rate": 3.580853637044399e-05, + "loss": 3.6002, + "step": 866816 + }, + { + "epoch": 1.01, + "learning_rate": 3.580015042293347e-05, + "loss": 3.5905, + "step": 867328 + }, + { + "epoch": 1.01, + "learning_rate": 3.579176447542295e-05, + "loss": 3.5931, + "step": 867840 + }, + { + "epoch": 1.01, + "learning_rate": 3.578337852791243e-05, + "loss": 3.6161, + "step": 868352 + }, + { + "epoch": 1.01, + "learning_rate": 3.577500895920564e-05, + "loss": 3.5977, + "step": 868864 + }, + { + "epoch": 1.01, + "learning_rate": 3.576662301169512e-05, + "loss": 3.6173, + "step": 869376 + }, + { + "epoch": 1.01, + "learning_rate": 3.57582370641846e-05, + "loss": 3.5992, + "step": 869888 + }, + { + "epoch": 1.01, + "learning_rate": 3.574985111667408e-05, + "loss": 3.584, + "step": 870400 + }, + { + "epoch": 1.01, + "learning_rate": 3.574146516916356e-05, + "loss": 3.6145, + "step": 870912 + }, + { + "epoch": 1.01, + "learning_rate": 3.5733095600456775e-05, + "loss": 3.5953, + "step": 871424 + }, + { + "epoch": 1.01, + "learning_rate": 3.5724709652946255e-05, + "loss": 3.5864, + "step": 871936 + }, + { + "epoch": 1.01, + "learning_rate": 3.5716323705435735e-05, + "loss": 3.5973, + "step": 872448 + }, + { + "epoch": 1.01, + "learning_rate": 3.5707937757925215e-05, + "loss": 3.5954, + "step": 872960 + }, + { + "epoch": 1.01, + "learning_rate": 3.5699551810414695e-05, + "loss": 3.5905, + "step": 873472 + }, + { + "epoch": 1.01, + "learning_rate": 3.5691165862904175e-05, + "loss": 3.5968, + "step": 873984 + }, + { + "epoch": 1.01, + "learning_rate": 3.5682796294197384e-05, + "loss": 3.5924, + "step": 874496 + }, + { + "epoch": 1.01, + "learning_rate": 3.5674410346686864e-05, + "loss": 3.6003, + "step": 875008 + }, + { + "epoch": 1.01, + "learning_rate": 3.5666024399176344e-05, + "loss": 3.6091, + "step": 875520 + }, + { + "epoch": 1.01, + "learning_rate": 3.5657638451665824e-05, + "loss": 3.5996, + "step": 876032 + }, + { + "epoch": 1.01, + "learning_rate": 3.5649252504155304e-05, + "loss": 3.6068, + "step": 876544 + }, + { + "epoch": 1.01, + "learning_rate": 3.564088293544851e-05, + "loss": 3.603, + "step": 877056 + }, + { + "epoch": 1.01, + "learning_rate": 3.563249698793799e-05, + "loss": 3.6147, + "step": 877568 + }, + { + "epoch": 1.01, + "learning_rate": 3.562411104042748e-05, + "loss": 3.5971, + "step": 878080 + }, + { + "epoch": 1.01, + "learning_rate": 3.561572509291696e-05, + "loss": 3.6159, + "step": 878592 + }, + { + "epoch": 1.01, + "learning_rate": 3.560733914540644e-05, + "loss": 3.5951, + "step": 879104 + }, + { + "epoch": 1.01, + "learning_rate": 3.559896957669965e-05, + "loss": 3.5944, + "step": 879616 + }, + { + "epoch": 1.01, + "learning_rate": 3.559058362918913e-05, + "loss": 3.5998, + "step": 880128 + }, + { + "epoch": 1.01, + "learning_rate": 3.558219768167861e-05, + "loss": 3.6028, + "step": 880640 + }, + { + "epoch": 1.01, + "learning_rate": 3.557381173416809e-05, + "loss": 3.6067, + "step": 881152 + }, + { + "epoch": 1.01, + "learning_rate": 3.556542578665756e-05, + "loss": 3.6134, + "step": 881664 + }, + { + "epoch": 1.01, + "learning_rate": 3.555705621795078e-05, + "loss": 3.5918, + "step": 882176 + }, + { + "epoch": 1.01, + "learning_rate": 3.554867027044026e-05, + "loss": 3.5831, + "step": 882688 + }, + { + "epoch": 1.01, + "learning_rate": 3.554028432292974e-05, + "loss": 3.5905, + "step": 883200 + }, + { + "epoch": 1.01, + "learning_rate": 3.553189837541922e-05, + "loss": 3.6121, + "step": 883712 + }, + { + "epoch": 1.01, + "learning_rate": 3.5523528806712434e-05, + "loss": 3.5935, + "step": 884224 + }, + { + "epoch": 1.01, + "learning_rate": 3.5515142859201914e-05, + "loss": 3.6024, + "step": 884736 + }, + { + "epoch": 1.01, + "learning_rate": 3.550675691169139e-05, + "loss": 3.603, + "step": 885248 + }, + { + "epoch": 1.02, + "learning_rate": 3.549837096418087e-05, + "loss": 3.5887, + "step": 885760 + }, + { + "epoch": 1.02, + "learning_rate": 3.548998501667035e-05, + "loss": 3.5989, + "step": 886272 + }, + { + "epoch": 1.02, + "learning_rate": 3.548161544796356e-05, + "loss": 3.5976, + "step": 886784 + }, + { + "epoch": 1.02, + "learning_rate": 3.5473229500453036e-05, + "loss": 3.5987, + "step": 887296 + }, + { + "epoch": 1.02, + "learning_rate": 3.5464843552942516e-05, + "loss": 3.6081, + "step": 887808 + }, + { + "epoch": 1.02, + "learning_rate": 3.5456457605431996e-05, + "loss": 3.6079, + "step": 888320 + }, + { + "epoch": 1.02, + "learning_rate": 3.544808803672521e-05, + "loss": 3.5959, + "step": 888832 + }, + { + "epoch": 1.02, + "learning_rate": 3.5439702089214685e-05, + "loss": 3.598, + "step": 889344 + }, + { + "epoch": 1.02, + "learning_rate": 3.543131614170417e-05, + "loss": 3.5923, + "step": 889856 + }, + { + "epoch": 1.02, + "learning_rate": 3.542293019419365e-05, + "loss": 3.6006, + "step": 890368 + }, + { + "epoch": 1.02, + "learning_rate": 3.541456062548686e-05, + "loss": 3.6013, + "step": 890880 + }, + { + "epoch": 1.02, + "learning_rate": 3.540617467797634e-05, + "loss": 3.5965, + "step": 891392 + }, + { + "epoch": 1.02, + "learning_rate": 3.539778873046582e-05, + "loss": 3.5959, + "step": 891904 + }, + { + "epoch": 1.02, + "learning_rate": 3.53894027829553e-05, + "loss": 3.5864, + "step": 892416 + }, + { + "epoch": 1.02, + "learning_rate": 3.538103321424851e-05, + "loss": 3.5991, + "step": 892928 + }, + { + "epoch": 1.02, + "learning_rate": 3.537264726673799e-05, + "loss": 3.5924, + "step": 893440 + }, + { + "epoch": 1.02, + "learning_rate": 3.536426131922747e-05, + "loss": 3.5773, + "step": 893952 + }, + { + "epoch": 1.02, + "learning_rate": 3.535587537171695e-05, + "loss": 3.5982, + "step": 894464 + }, + { + "epoch": 1.02, + "learning_rate": 3.534748942420643e-05, + "loss": 3.5999, + "step": 894976 + }, + { + "epoch": 1.02, + "learning_rate": 3.533911985549964e-05, + "loss": 3.5935, + "step": 895488 + }, + { + "epoch": 1.02, + "learning_rate": 3.5330733907989125e-05, + "loss": 3.5901, + "step": 896000 + }, + { + "epoch": 1.02, + "learning_rate": 3.5322347960478605e-05, + "loss": 3.5961, + "step": 896512 + }, + { + "epoch": 1.02, + "learning_rate": 3.5313962012968085e-05, + "loss": 3.5963, + "step": 897024 + }, + { + "epoch": 1.02, + "learning_rate": 3.5305576065457565e-05, + "loss": 3.5835, + "step": 897536 + }, + { + "epoch": 1.02, + "learning_rate": 3.5297206496750774e-05, + "loss": 3.6077, + "step": 898048 + }, + { + "epoch": 1.02, + "learning_rate": 3.5288820549240254e-05, + "loss": 3.6001, + "step": 898560 + }, + { + "epoch": 1.02, + "learning_rate": 3.5280434601729734e-05, + "loss": 3.5932, + "step": 899072 + }, + { + "epoch": 1.02, + "learning_rate": 3.5272048654219214e-05, + "loss": 3.6015, + "step": 899584 + }, + { + "epoch": 1.02, + "learning_rate": 3.526367908551242e-05, + "loss": 3.5891, + "step": 900096 + }, + { + "epoch": 1.02, + "learning_rate": 3.52552931380019e-05, + "loss": 3.599, + "step": 900608 + }, + { + "epoch": 1.02, + "learning_rate": 3.524690719049138e-05, + "loss": 3.5959, + "step": 901120 + }, + { + "epoch": 1.02, + "learning_rate": 3.523852124298086e-05, + "loss": 3.5932, + "step": 901632 + }, + { + "epoch": 1.02, + "learning_rate": 3.523013529547034e-05, + "loss": 3.5924, + "step": 902144 + }, + { + "epoch": 1.02, + "learning_rate": 3.522176572676356e-05, + "loss": 3.5964, + "step": 902656 + }, + { + "epoch": 1.02, + "learning_rate": 3.521337977925304e-05, + "loss": 3.597, + "step": 903168 + }, + { + "epoch": 1.02, + "learning_rate": 3.520499383174252e-05, + "loss": 3.5918, + "step": 903680 + }, + { + "epoch": 1.02, + "learning_rate": 3.5196607884232e-05, + "loss": 3.5894, + "step": 904192 + }, + { + "epoch": 1.02, + "learning_rate": 3.518822193672148e-05, + "loss": 3.5904, + "step": 904704 + }, + { + "epoch": 1.02, + "learning_rate": 3.517985236801469e-05, + "loss": 3.5894, + "step": 905216 + }, + { + "epoch": 1.02, + "learning_rate": 3.517146642050417e-05, + "loss": 3.6053, + "step": 905728 + }, + { + "epoch": 1.02, + "learning_rate": 3.516308047299365e-05, + "loss": 3.5916, + "step": 906240 + }, + { + "epoch": 1.02, + "learning_rate": 3.515469452548313e-05, + "loss": 3.6082, + "step": 906752 + }, + { + "epoch": 1.02, + "learning_rate": 3.5146324956776337e-05, + "loss": 3.5748, + "step": 907264 + }, + { + "epoch": 1.02, + "learning_rate": 3.5137939009265817e-05, + "loss": 3.6095, + "step": 907776 + }, + { + "epoch": 1.02, + "learning_rate": 3.5129553061755297e-05, + "loss": 3.5912, + "step": 908288 + }, + { + "epoch": 1.02, + "learning_rate": 3.5121167114244776e-05, + "loss": 3.6035, + "step": 908800 + }, + { + "epoch": 1.02, + "learning_rate": 3.511279754553799e-05, + "loss": 3.5943, + "step": 909312 + }, + { + "epoch": 1.02, + "learning_rate": 3.510441159802747e-05, + "loss": 3.5849, + "step": 909824 + }, + { + "epoch": 1.02, + "learning_rate": 3.509602565051695e-05, + "loss": 3.5987, + "step": 910336 + }, + { + "epoch": 1.02, + "learning_rate": 3.508763970300643e-05, + "loss": 3.6193, + "step": 910848 + }, + { + "epoch": 1.02, + "learning_rate": 3.507927013429964e-05, + "loss": 3.5795, + "step": 911360 + }, + { + "epoch": 1.02, + "learning_rate": 3.507088418678912e-05, + "loss": 3.5978, + "step": 911872 + }, + { + "epoch": 1.02, + "learning_rate": 3.50624982392786e-05, + "loss": 3.5899, + "step": 912384 + }, + { + "epoch": 1.02, + "learning_rate": 3.505411229176808e-05, + "loss": 3.5927, + "step": 912896 + }, + { + "epoch": 1.02, + "learning_rate": 3.504572634425756e-05, + "loss": 3.5908, + "step": 913408 + }, + { + "epoch": 1.02, + "learning_rate": 3.503735677555077e-05, + "loss": 3.5979, + "step": 913920 + }, + { + "epoch": 1.02, + "learning_rate": 3.502897082804025e-05, + "loss": 3.5909, + "step": 914432 + }, + { + "epoch": 1.02, + "learning_rate": 3.502058488052973e-05, + "loss": 3.5961, + "step": 914944 + }, + { + "epoch": 1.02, + "learning_rate": 3.501219893301922e-05, + "loss": 3.5929, + "step": 915456 + }, + { + "epoch": 1.03, + "eval_loss": 3.8428921699523926, + "eval_runtime": 313.501, + "eval_samples_per_second": 1217.192, + "eval_steps_per_second": 38.038, + "step": 915840 + }, + { + "epoch": 0.0, + "learning_rate": 3.5003829364312426e-05, + "loss": 3.6001, + "step": 915968 + }, + { + "epoch": 0.0, + "learning_rate": 3.4995443416801906e-05, + "loss": 3.5841, + "step": 916480 + }, + { + "epoch": 0.0, + "learning_rate": 3.4987057469291386e-05, + "loss": 3.5977, + "step": 916992 + }, + { + "epoch": 0.0, + "learning_rate": 3.4978671521780866e-05, + "loss": 3.6023, + "step": 917504 + }, + { + "epoch": 0.0, + "learning_rate": 3.4970301953074075e-05, + "loss": 3.5991, + "step": 918016 + }, + { + "epoch": 0.0, + "learning_rate": 3.4961916005563555e-05, + "loss": 3.5901, + "step": 918528 + }, + { + "epoch": 0.0, + "learning_rate": 3.4953530058053035e-05, + "loss": 3.5952, + "step": 919040 + }, + { + "epoch": 0.0, + "learning_rate": 3.4945144110542515e-05, + "loss": 3.5923, + "step": 919552 + }, + { + "epoch": 0.0, + "learning_rate": 3.4936774541835724e-05, + "loss": 3.589, + "step": 920064 + }, + { + "epoch": 0.0, + "learning_rate": 3.4928388594325204e-05, + "loss": 3.5951, + "step": 920576 + }, + { + "epoch": 0.0, + "learning_rate": 3.4920002646814684e-05, + "loss": 3.6004, + "step": 921088 + }, + { + "epoch": 0.0, + "learning_rate": 3.4911616699304164e-05, + "loss": 3.5979, + "step": 921600 + }, + { + "epoch": 0.0, + "learning_rate": 3.490324713059738e-05, + "loss": 3.5999, + "step": 922112 + }, + { + "epoch": 0.0, + "learning_rate": 3.489486118308686e-05, + "loss": 3.5766, + "step": 922624 + }, + { + "epoch": 0.0, + "learning_rate": 3.488647523557634e-05, + "loss": 3.5983, + "step": 923136 + }, + { + "epoch": 0.0, + "learning_rate": 3.487808928806582e-05, + "loss": 3.5793, + "step": 923648 + }, + { + "epoch": 0.0, + "learning_rate": 3.486970334055529e-05, + "loss": 3.5891, + "step": 924160 + }, + { + "epoch": 0.0, + "learning_rate": 3.486133377184851e-05, + "loss": 3.5843, + "step": 924672 + }, + { + "epoch": 0.0, + "learning_rate": 3.485294782433799e-05, + "loss": 3.5828, + "step": 925184 + }, + { + "epoch": 0.0, + "learning_rate": 3.484456187682746e-05, + "loss": 3.5908, + "step": 925696 + }, + { + "epoch": 0.0, + "learning_rate": 3.483617592931694e-05, + "loss": 3.6018, + "step": 926208 + }, + { + "epoch": 0.0, + "learning_rate": 3.482778998180642e-05, + "loss": 3.5933, + "step": 926720 + }, + { + "epoch": 0.0, + "learning_rate": 3.48194040342959e-05, + "loss": 3.5894, + "step": 927232 + }, + { + "epoch": 0.0, + "learning_rate": 3.481101808678539e-05, + "loss": 3.5856, + "step": 927744 + }, + { + "epoch": 0.0, + "learning_rate": 3.48026485180786e-05, + "loss": 3.5923, + "step": 928256 + }, + { + "epoch": 0.0, + "learning_rate": 3.479426257056808e-05, + "loss": 3.5851, + "step": 928768 + }, + { + "epoch": 0.0, + "learning_rate": 3.478587662305756e-05, + "loss": 3.5764, + "step": 929280 + }, + { + "epoch": 0.0, + "learning_rate": 3.477749067554704e-05, + "loss": 3.596, + "step": 929792 + }, + { + "epoch": 0.0, + "learning_rate": 3.476910472803652e-05, + "loss": 3.5803, + "step": 930304 + }, + { + "epoch": 0.0, + "learning_rate": 3.4760735159329726e-05, + "loss": 3.5864, + "step": 930816 + }, + { + "epoch": 0.01, + "learning_rate": 3.4752349211819206e-05, + "loss": 3.5856, + "step": 931328 + }, + { + "epoch": 0.01, + "learning_rate": 3.4743963264308686e-05, + "loss": 3.5933, + "step": 931840 + }, + { + "epoch": 0.01, + "learning_rate": 3.4735577316798166e-05, + "loss": 3.5808, + "step": 932352 + }, + { + "epoch": 0.01, + "learning_rate": 3.4727207748091375e-05, + "loss": 3.5894, + "step": 932864 + }, + { + "epoch": 0.01, + "learning_rate": 3.4718821800580855e-05, + "loss": 3.5903, + "step": 933376 + }, + { + "epoch": 0.01, + "learning_rate": 3.471043585307034e-05, + "loss": 3.5853, + "step": 933888 + }, + { + "epoch": 0.01, + "learning_rate": 3.470204990555982e-05, + "loss": 3.5982, + "step": 934400 + }, + { + "epoch": 0.01, + "learning_rate": 3.469368033685303e-05, + "loss": 3.5699, + "step": 934912 + }, + { + "epoch": 0.01, + "learning_rate": 3.468529438934251e-05, + "loss": 3.5808, + "step": 935424 + }, + { + "epoch": 0.01, + "learning_rate": 3.467690844183199e-05, + "loss": 3.5795, + "step": 935936 + }, + { + "epoch": 0.01, + "learning_rate": 3.466852249432147e-05, + "loss": 3.5813, + "step": 936448 + }, + { + "epoch": 0.01, + "learning_rate": 3.466013654681095e-05, + "loss": 3.5806, + "step": 936960 + }, + { + "epoch": 0.01, + "learning_rate": 3.465176697810416e-05, + "loss": 3.5861, + "step": 937472 + }, + { + "epoch": 0.01, + "learning_rate": 3.464338103059364e-05, + "loss": 3.5896, + "step": 937984 + }, + { + "epoch": 0.01, + "learning_rate": 3.463499508308312e-05, + "loss": 3.5844, + "step": 938496 + }, + { + "epoch": 0.01, + "learning_rate": 3.46266091355726e-05, + "loss": 3.5862, + "step": 939008 + }, + { + "epoch": 0.01, + "learning_rate": 3.461822318806208e-05, + "loss": 3.5956, + "step": 939520 + }, + { + "epoch": 0.01, + "learning_rate": 3.460983724055156e-05, + "loss": 3.5799, + "step": 940032 + }, + { + "epoch": 0.01, + "learning_rate": 3.460145129304104e-05, + "loss": 3.5633, + "step": 940544 + }, + { + "epoch": 0.01, + "learning_rate": 3.4593081724334256e-05, + "loss": 3.5957, + "step": 941056 + }, + { + "epoch": 0.01, + "learning_rate": 3.4584695776823735e-05, + "loss": 3.5844, + "step": 941568 + }, + { + "epoch": 0.01, + "learning_rate": 3.4576309829313215e-05, + "loss": 3.5815, + "step": 942080 + }, + { + "epoch": 0.01, + "learning_rate": 3.4567923881802695e-05, + "loss": 3.5847, + "step": 942592 + }, + { + "epoch": 0.01, + "learning_rate": 3.4559554313095904e-05, + "loss": 3.5789, + "step": 943104 + }, + { + "epoch": 0.01, + "learning_rate": 3.4551168365585384e-05, + "loss": 3.574, + "step": 943616 + }, + { + "epoch": 0.01, + "learning_rate": 3.4542782418074864e-05, + "loss": 3.5722, + "step": 944128 + }, + { + "epoch": 0.01, + "learning_rate": 3.4534396470564344e-05, + "loss": 3.5944, + "step": 944640 + }, + { + "epoch": 0.01, + "learning_rate": 3.4526026901857553e-05, + "loss": 3.5792, + "step": 945152 + }, + { + "epoch": 0.01, + "learning_rate": 3.4517640954347033e-05, + "loss": 3.6001, + "step": 945664 + }, + { + "epoch": 0.01, + "learning_rate": 3.450925500683651e-05, + "loss": 3.5832, + "step": 946176 + }, + { + "epoch": 0.01, + "learning_rate": 3.450086905932599e-05, + "loss": 3.5633, + "step": 946688 + }, + { + "epoch": 0.01, + "learning_rate": 3.449248311181548e-05, + "loss": 3.593, + "step": 947200 + }, + { + "epoch": 0.01, + "learning_rate": 3.448411354310869e-05, + "loss": 3.5754, + "step": 947712 + }, + { + "epoch": 0.01, + "learning_rate": 3.447572759559817e-05, + "loss": 3.5701, + "step": 948224 + }, + { + "epoch": 0.01, + "learning_rate": 3.446734164808765e-05, + "loss": 3.5763, + "step": 948736 + }, + { + "epoch": 0.01, + "learning_rate": 3.445895570057712e-05, + "loss": 3.5797, + "step": 949248 + }, + { + "epoch": 0.01, + "learning_rate": 3.44505697530666e-05, + "loss": 3.5746, + "step": 949760 + }, + { + "epoch": 0.01, + "learning_rate": 3.444220018435982e-05, + "loss": 3.5818, + "step": 950272 + }, + { + "epoch": 0.01, + "learning_rate": 3.44338142368493e-05, + "loss": 3.5699, + "step": 950784 + }, + { + "epoch": 0.01, + "learning_rate": 3.442542828933877e-05, + "loss": 3.5847, + "step": 951296 + }, + { + "epoch": 0.01, + "learning_rate": 3.441704234182825e-05, + "loss": 3.5884, + "step": 951808 + }, + { + "epoch": 0.01, + "learning_rate": 3.440867277312147e-05, + "loss": 3.5802, + "step": 952320 + }, + { + "epoch": 0.01, + "learning_rate": 3.440028682561095e-05, + "loss": 3.5871, + "step": 952832 + }, + { + "epoch": 0.01, + "learning_rate": 3.439190087810043e-05, + "loss": 3.584, + "step": 953344 + }, + { + "epoch": 0.01, + "learning_rate": 3.438351493058991e-05, + "loss": 3.5955, + "step": 953856 + }, + { + "epoch": 0.01, + "learning_rate": 3.437512898307939e-05, + "loss": 3.5791, + "step": 954368 + }, + { + "epoch": 0.01, + "learning_rate": 3.4366759414372596e-05, + "loss": 3.5911, + "step": 954880 + }, + { + "epoch": 0.01, + "learning_rate": 3.4358373466862076e-05, + "loss": 3.582, + "step": 955392 + }, + { + "epoch": 0.01, + "learning_rate": 3.4349987519351556e-05, + "loss": 3.5757, + "step": 955904 + }, + { + "epoch": 0.01, + "learning_rate": 3.4341601571841036e-05, + "loss": 3.5864, + "step": 956416 + }, + { + "epoch": 0.01, + "learning_rate": 3.4333232003134245e-05, + "loss": 3.5795, + "step": 956928 + }, + { + "epoch": 0.01, + "learning_rate": 3.4324846055623725e-05, + "loss": 3.5896, + "step": 957440 + }, + { + "epoch": 0.01, + "learning_rate": 3.4316460108113205e-05, + "loss": 3.5956, + "step": 957952 + }, + { + "epoch": 0.01, + "learning_rate": 3.4308074160602685e-05, + "loss": 3.5785, + "step": 958464 + }, + { + "epoch": 0.01, + "learning_rate": 3.42997045918959e-05, + "loss": 3.5593, + "step": 958976 + }, + { + "epoch": 0.01, + "learning_rate": 3.429131864438538e-05, + "loss": 3.5714, + "step": 959488 + }, + { + "epoch": 0.01, + "learning_rate": 3.428293269687486e-05, + "loss": 3.5914, + "step": 960000 + }, + { + "epoch": 0.01, + "learning_rate": 3.427454674936434e-05, + "loss": 3.5773, + "step": 960512 + }, + { + "epoch": 0.01, + "learning_rate": 3.426616080185382e-05, + "loss": 3.5814, + "step": 961024 + }, + { + "epoch": 0.01, + "learning_rate": 3.425779123314703e-05, + "loss": 3.5851, + "step": 961536 + }, + { + "epoch": 0.02, + "learning_rate": 3.424940528563651e-05, + "loss": 3.5709, + "step": 962048 + }, + { + "epoch": 0.02, + "learning_rate": 3.424101933812599e-05, + "loss": 3.5836, + "step": 962560 + }, + { + "epoch": 0.02, + "learning_rate": 3.423263339061547e-05, + "loss": 3.5769, + "step": 963072 + }, + { + "epoch": 0.02, + "learning_rate": 3.422424744310495e-05, + "loss": 3.5849, + "step": 963584 + }, + { + "epoch": 0.02, + "learning_rate": 3.421586149559443e-05, + "loss": 3.5866, + "step": 964096 + }, + { + "epoch": 0.02, + "learning_rate": 3.420749192688764e-05, + "loss": 3.5895, + "step": 964608 + }, + { + "epoch": 0.02, + "learning_rate": 3.4199105979377125e-05, + "loss": 3.574, + "step": 965120 + }, + { + "epoch": 0.02, + "learning_rate": 3.4190720031866605e-05, + "loss": 3.5802, + "step": 965632 + }, + { + "epoch": 0.02, + "learning_rate": 3.4182334084356085e-05, + "loss": 3.5808, + "step": 966144 + }, + { + "epoch": 0.02, + "learning_rate": 3.4173964515649294e-05, + "loss": 3.5786, + "step": 966656 + }, + { + "epoch": 0.02, + "learning_rate": 3.4165578568138774e-05, + "loss": 3.5851, + "step": 967168 + }, + { + "epoch": 0.02, + "learning_rate": 3.4157192620628254e-05, + "loss": 3.5779, + "step": 967680 + }, + { + "epoch": 0.02, + "learning_rate": 3.4148806673117734e-05, + "loss": 3.577, + "step": 968192 + }, + { + "epoch": 0.02, + "learning_rate": 3.414043710441094e-05, + "loss": 3.5718, + "step": 968704 + }, + { + "epoch": 0.02, + "learning_rate": 3.413205115690042e-05, + "loss": 3.581, + "step": 969216 + }, + { + "epoch": 0.02, + "learning_rate": 3.41236652093899e-05, + "loss": 3.573, + "step": 969728 + }, + { + "epoch": 0.02, + "learning_rate": 3.411527926187938e-05, + "loss": 3.5612, + "step": 970240 + }, + { + "epoch": 0.02, + "learning_rate": 3.410690969317259e-05, + "loss": 3.5787, + "step": 970752 + }, + { + "epoch": 0.02, + "learning_rate": 3.409852374566207e-05, + "loss": 3.5821, + "step": 971264 + }, + { + "epoch": 0.02, + "learning_rate": 3.409013779815156e-05, + "loss": 3.5709, + "step": 971776 + }, + { + "epoch": 0.02, + "learning_rate": 3.408175185064104e-05, + "loss": 3.5748, + "step": 972288 + }, + { + "epoch": 0.02, + "learning_rate": 3.407336590313052e-05, + "loss": 3.572, + "step": 972800 + }, + { + "epoch": 0.02, + "learning_rate": 3.406499633442373e-05, + "loss": 3.5809, + "step": 973312 + }, + { + "epoch": 0.02, + "learning_rate": 3.405661038691321e-05, + "loss": 3.5692, + "step": 973824 + }, + { + "epoch": 0.02, + "learning_rate": 3.404822443940269e-05, + "loss": 3.5858, + "step": 974336 + }, + { + "epoch": 0.02, + "learning_rate": 3.403983849189217e-05, + "loss": 3.5792, + "step": 974848 + }, + { + "epoch": 0.02, + "learning_rate": 3.403145254438165e-05, + "loss": 3.5819, + "step": 975360 + }, + { + "epoch": 0.02, + "learning_rate": 3.402308297567486e-05, + "loss": 3.5816, + "step": 975872 + }, + { + "epoch": 0.02, + "learning_rate": 3.401469702816434e-05, + "loss": 3.5708, + "step": 976384 + }, + { + "epoch": 0.02, + "learning_rate": 3.400631108065382e-05, + "loss": 3.5793, + "step": 976896 + }, + { + "epoch": 0.02, + "learning_rate": 3.3997941511947026e-05, + "loss": 3.5778, + "step": 977408 + }, + { + "epoch": 0.02, + "learning_rate": 3.398955556443651e-05, + "loss": 3.5773, + "step": 977920 + }, + { + "epoch": 0.02, + "learning_rate": 3.398116961692599e-05, + "loss": 3.5754, + "step": 978432 + }, + { + "epoch": 0.02, + "learning_rate": 3.397278366941547e-05, + "loss": 3.573, + "step": 978944 + }, + { + "epoch": 0.02, + "learning_rate": 3.396439772190495e-05, + "loss": 3.5808, + "step": 979456 + }, + { + "epoch": 0.02, + "learning_rate": 3.395602815319816e-05, + "loss": 3.5747, + "step": 979968 + }, + { + "epoch": 0.02, + "learning_rate": 3.394764220568764e-05, + "loss": 3.5747, + "step": 980480 + }, + { + "epoch": 0.02, + "learning_rate": 3.393925625817712e-05, + "loss": 3.5675, + "step": 980992 + }, + { + "epoch": 0.02, + "learning_rate": 3.39308703106666e-05, + "loss": 3.5719, + "step": 981504 + }, + { + "epoch": 0.02, + "learning_rate": 3.392250074195981e-05, + "loss": 3.5886, + "step": 982016 + }, + { + "epoch": 0.02, + "learning_rate": 3.391411479444929e-05, + "loss": 3.5744, + "step": 982528 + }, + { + "epoch": 0.02, + "learning_rate": 3.390572884693877e-05, + "loss": 3.59, + "step": 983040 + }, + { + "epoch": 0.02, + "learning_rate": 3.389734289942825e-05, + "loss": 3.561, + "step": 983552 + }, + { + "epoch": 0.02, + "learning_rate": 3.388895695191773e-05, + "loss": 3.5843, + "step": 984064 + }, + { + "epoch": 0.02, + "learning_rate": 3.3880587383210946e-05, + "loss": 3.5797, + "step": 984576 + }, + { + "epoch": 0.02, + "learning_rate": 3.3872201435700426e-05, + "loss": 3.5821, + "step": 985088 + }, + { + "epoch": 0.02, + "learning_rate": 3.3863815488189906e-05, + "loss": 3.5774, + "step": 985600 + }, + { + "epoch": 0.02, + "learning_rate": 3.385542954067938e-05, + "loss": 3.5679, + "step": 986112 + }, + { + "epoch": 0.02, + "learning_rate": 3.3847059971972595e-05, + "loss": 3.5788, + "step": 986624 + }, + { + "epoch": 0.02, + "learning_rate": 3.3838674024462075e-05, + "loss": 3.5975, + "step": 987136 + }, + { + "epoch": 0.02, + "learning_rate": 3.3830288076951555e-05, + "loss": 3.5661, + "step": 987648 + }, + { + "epoch": 0.02, + "learning_rate": 3.382190212944103e-05, + "loss": 3.5772, + "step": 988160 + }, + { + "epoch": 0.02, + "learning_rate": 3.381351618193051e-05, + "loss": 3.5746, + "step": 988672 + }, + { + "epoch": 0.02, + "learning_rate": 3.3805146613223724e-05, + "loss": 3.5747, + "step": 989184 + }, + { + "epoch": 0.02, + "learning_rate": 3.3796760665713204e-05, + "loss": 3.5753, + "step": 989696 + }, + { + "epoch": 0.02, + "learning_rate": 3.3788374718202684e-05, + "loss": 3.5799, + "step": 990208 + }, + { + "epoch": 0.02, + "learning_rate": 3.3779988770692164e-05, + "loss": 3.5734, + "step": 990720 + }, + { + "epoch": 0.02, + "learning_rate": 3.377161920198538e-05, + "loss": 3.5807, + "step": 991232 + }, + { + "epoch": 0.02, + "learning_rate": 3.376323325447485e-05, + "loss": 3.574, + "step": 991744 + }, + { + "epoch": 0.03, + "eval_loss": 3.842787981033325, + "eval_runtime": 309.0366, + "eval_samples_per_second": 1234.776, + "eval_steps_per_second": 38.588, + "step": 992160 + }, + { + "epoch": 1.0, + "learning_rate": 3.375484730696433e-05, + "loss": 3.5739, + "step": 992256 + }, + { + "epoch": 1.0, + "learning_rate": 3.374646135945381e-05, + "loss": 3.5638, + "step": 992768 + }, + { + "epoch": 1.0, + "learning_rate": 3.373809179074703e-05, + "loss": 3.5814, + "step": 993280 + }, + { + "epoch": 1.0, + "learning_rate": 3.37297058432365e-05, + "loss": 3.5865, + "step": 993792 + }, + { + "epoch": 1.0, + "learning_rate": 3.372131989572598e-05, + "loss": 3.5765, + "step": 994304 + }, + { + "epoch": 1.0, + "learning_rate": 3.371293394821546e-05, + "loss": 3.575, + "step": 994816 + }, + { + "epoch": 1.0, + "learning_rate": 3.370454800070494e-05, + "loss": 3.5761, + "step": 995328 + }, + { + "epoch": 1.0, + "learning_rate": 3.369617843199816e-05, + "loss": 3.577, + "step": 995840 + }, + { + "epoch": 1.0, + "learning_rate": 3.368779248448764e-05, + "loss": 3.5674, + "step": 996352 + }, + { + "epoch": 1.0, + "learning_rate": 3.367940653697712e-05, + "loss": 3.5821, + "step": 996864 + }, + { + "epoch": 1.0, + "learning_rate": 3.36710205894666e-05, + "loss": 3.5837, + "step": 997376 + }, + { + "epoch": 1.0, + "learning_rate": 3.3662651020759807e-05, + "loss": 3.5776, + "step": 997888 + }, + { + "epoch": 1.0, + "learning_rate": 3.365428145205302e-05, + "loss": 3.5888, + "step": 998400 + }, + { + "epoch": 1.0, + "learning_rate": 3.36458955045425e-05, + "loss": 3.5568, + "step": 998912 + }, + { + "epoch": 1.0, + "learning_rate": 3.3637509557031976e-05, + "loss": 3.5743, + "step": 999424 + }, + { + "epoch": 1.0, + "learning_rate": 3.3629123609521456e-05, + "loss": 3.5646, + "step": 999936 + }, + { + "epoch": 1.0, + "learning_rate": 3.3620737662010935e-05, + "loss": 3.5722, + "step": 1000448 + }, + { + "epoch": 1.0, + "learning_rate": 3.3612351714500415e-05, + "loss": 3.5687, + "step": 1000960 + }, + { + "epoch": 1.0, + "learning_rate": 3.3603965766989895e-05, + "loss": 3.5659, + "step": 1001472 + }, + { + "epoch": 1.0, + "learning_rate": 3.3595579819479375e-05, + "loss": 3.5651, + "step": 1001984 + }, + { + "epoch": 1.0, + "learning_rate": 3.358721025077259e-05, + "loss": 3.5903, + "step": 1002496 + }, + { + "epoch": 1.0, + "learning_rate": 3.357882430326207e-05, + "loss": 3.5766, + "step": 1003008 + }, + { + "epoch": 1.0, + "learning_rate": 3.357043835575155e-05, + "loss": 3.5709, + "step": 1003520 + }, + { + "epoch": 1.0, + "learning_rate": 3.356205240824103e-05, + "loss": 3.5698, + "step": 1004032 + }, + { + "epoch": 1.0, + "learning_rate": 3.355368283953424e-05, + "loss": 3.5777, + "step": 1004544 + }, + { + "epoch": 1.0, + "learning_rate": 3.354529689202372e-05, + "loss": 3.5627, + "step": 1005056 + }, + { + "epoch": 1.0, + "learning_rate": 3.35369109445132e-05, + "loss": 3.5595, + "step": 1005568 + }, + { + "epoch": 1.0, + "learning_rate": 3.352852499700268e-05, + "loss": 3.5784, + "step": 1006080 + }, + { + "epoch": 1.0, + "learning_rate": 3.352013904949216e-05, + "loss": 3.5635, + "step": 1006592 + }, + { + "epoch": 1.0, + "learning_rate": 3.351176948078537e-05, + "loss": 3.5639, + "step": 1007104 + }, + { + "epoch": 1.01, + "learning_rate": 3.350338353327485e-05, + "loss": 3.5712, + "step": 1007616 + }, + { + "epoch": 1.01, + "learning_rate": 3.349499758576433e-05, + "loss": 3.5724, + "step": 1008128 + }, + { + "epoch": 1.01, + "learning_rate": 3.348661163825381e-05, + "loss": 3.5678, + "step": 1008640 + }, + { + "epoch": 1.01, + "learning_rate": 3.347822569074329e-05, + "loss": 3.5695, + "step": 1009152 + }, + { + "epoch": 1.01, + "learning_rate": 3.3469856122036505e-05, + "loss": 3.5696, + "step": 1009664 + }, + { + "epoch": 1.01, + "learning_rate": 3.3461470174525985e-05, + "loss": 3.5751, + "step": 1010176 + }, + { + "epoch": 1.01, + "learning_rate": 3.3453084227015465e-05, + "loss": 3.5789, + "step": 1010688 + }, + { + "epoch": 1.01, + "learning_rate": 3.3444714658308674e-05, + "loss": 3.5531, + "step": 1011200 + }, + { + "epoch": 1.01, + "learning_rate": 3.3436328710798154e-05, + "loss": 3.563, + "step": 1011712 + }, + { + "epoch": 1.01, + "learning_rate": 3.3427942763287634e-05, + "loss": 3.5627, + "step": 1012224 + }, + { + "epoch": 1.01, + "learning_rate": 3.3419556815777114e-05, + "loss": 3.5634, + "step": 1012736 + }, + { + "epoch": 1.01, + "learning_rate": 3.3411170868266594e-05, + "loss": 3.5644, + "step": 1013248 + }, + { + "epoch": 1.01, + "learning_rate": 3.34028012995598e-05, + "loss": 3.5707, + "step": 1013760 + }, + { + "epoch": 1.01, + "learning_rate": 3.339441535204928e-05, + "loss": 3.5662, + "step": 1014272 + }, + { + "epoch": 1.01, + "learning_rate": 3.338602940453876e-05, + "loss": 3.5684, + "step": 1014784 + }, + { + "epoch": 1.01, + "learning_rate": 3.337764345702824e-05, + "loss": 3.5695, + "step": 1015296 + }, + { + "epoch": 1.01, + "learning_rate": 3.336927388832146e-05, + "loss": 3.5753, + "step": 1015808 + }, + { + "epoch": 1.01, + "learning_rate": 3.336088794081094e-05, + "loss": 3.5676, + "step": 1016320 + }, + { + "epoch": 1.01, + "learning_rate": 3.335250199330042e-05, + "loss": 3.5458, + "step": 1016832 + }, + { + "epoch": 1.01, + "learning_rate": 3.33441160457899e-05, + "loss": 3.5766, + "step": 1017344 + }, + { + "epoch": 1.01, + "learning_rate": 3.333573009827938e-05, + "loss": 3.5684, + "step": 1017856 + }, + { + "epoch": 1.01, + "learning_rate": 3.332734415076886e-05, + "loss": 3.5662, + "step": 1018368 + }, + { + "epoch": 1.01, + "learning_rate": 3.331897458206207e-05, + "loss": 3.5635, + "step": 1018880 + }, + { + "epoch": 1.01, + "learning_rate": 3.331058863455155e-05, + "loss": 3.5615, + "step": 1019392 + }, + { + "epoch": 1.01, + "learning_rate": 3.330220268704103e-05, + "loss": 3.5563, + "step": 1019904 + }, + { + "epoch": 1.01, + "learning_rate": 3.329381673953051e-05, + "loss": 3.5566, + "step": 1020416 + }, + { + "epoch": 1.01, + "learning_rate": 3.3285447170823716e-05, + "loss": 3.5755, + "step": 1020928 + }, + { + "epoch": 1.01, + "learning_rate": 3.3277061223313196e-05, + "loss": 3.5586, + "step": 1021440 + }, + { + "epoch": 1.01, + "learning_rate": 3.326867527580268e-05, + "loss": 3.5821, + "step": 1021952 + }, + { + "epoch": 1.01, + "learning_rate": 3.326028932829216e-05, + "loss": 3.5712, + "step": 1022464 + }, + { + "epoch": 1.01, + "learning_rate": 3.325191975958537e-05, + "loss": 3.5484, + "step": 1022976 + }, + { + "epoch": 1.01, + "learning_rate": 3.324353381207485e-05, + "loss": 3.5744, + "step": 1023488 + }, + { + "epoch": 1.01, + "learning_rate": 3.323514786456433e-05, + "loss": 3.5578, + "step": 1024000 + }, + { + "epoch": 1.01, + "learning_rate": 3.3226761917053805e-05, + "loss": 3.5531, + "step": 1024512 + }, + { + "epoch": 1.01, + "learning_rate": 3.321839234834702e-05, + "loss": 3.556, + "step": 1025024 + }, + { + "epoch": 1.01, + "learning_rate": 3.32100064008365e-05, + "loss": 3.559, + "step": 1025536 + }, + { + "epoch": 1.01, + "learning_rate": 3.320162045332598e-05, + "loss": 3.5603, + "step": 1026048 + }, + { + "epoch": 1.01, + "learning_rate": 3.3193234505815454e-05, + "loss": 3.5646, + "step": 1026560 + }, + { + "epoch": 1.01, + "learning_rate": 3.3184848558304934e-05, + "loss": 3.5512, + "step": 1027072 + }, + { + "epoch": 1.01, + "learning_rate": 3.317647898959815e-05, + "loss": 3.5666, + "step": 1027584 + }, + { + "epoch": 1.01, + "learning_rate": 3.316809304208764e-05, + "loss": 3.5722, + "step": 1028096 + }, + { + "epoch": 1.01, + "learning_rate": 3.315970709457711e-05, + "loss": 3.5652, + "step": 1028608 + }, + { + "epoch": 1.01, + "learning_rate": 3.315132114706659e-05, + "loss": 3.5678, + "step": 1029120 + }, + { + "epoch": 1.01, + "learning_rate": 3.3142951578359806e-05, + "loss": 3.568, + "step": 1029632 + }, + { + "epoch": 1.01, + "learning_rate": 3.313456563084928e-05, + "loss": 3.5785, + "step": 1030144 + }, + { + "epoch": 1.01, + "learning_rate": 3.312617968333876e-05, + "loss": 3.5599, + "step": 1030656 + }, + { + "epoch": 1.01, + "learning_rate": 3.311779373582824e-05, + "loss": 3.5725, + "step": 1031168 + }, + { + "epoch": 1.01, + "learning_rate": 3.310940778831772e-05, + "loss": 3.566, + "step": 1031680 + }, + { + "epoch": 1.01, + "learning_rate": 3.310103821961093e-05, + "loss": 3.5603, + "step": 1032192 + }, + { + "epoch": 1.01, + "learning_rate": 3.309265227210041e-05, + "loss": 3.5681, + "step": 1032704 + }, + { + "epoch": 1.01, + "learning_rate": 3.308426632458989e-05, + "loss": 3.5642, + "step": 1033216 + }, + { + "epoch": 1.01, + "learning_rate": 3.3075880377079374e-05, + "loss": 3.5717, + "step": 1033728 + }, + { + "epoch": 1.01, + "learning_rate": 3.3067510808372584e-05, + "loss": 3.5793, + "step": 1034240 + }, + { + "epoch": 1.01, + "learning_rate": 3.3059124860862063e-05, + "loss": 3.5628, + "step": 1034752 + }, + { + "epoch": 1.01, + "learning_rate": 3.3050738913351543e-05, + "loss": 3.5476, + "step": 1035264 + }, + { + "epoch": 1.01, + "learning_rate": 3.3042352965841023e-05, + "loss": 3.5559, + "step": 1035776 + }, + { + "epoch": 1.01, + "learning_rate": 3.303398339713423e-05, + "loss": 3.5693, + "step": 1036288 + }, + { + "epoch": 1.01, + "learning_rate": 3.302559744962371e-05, + "loss": 3.5649, + "step": 1036800 + }, + { + "epoch": 1.01, + "learning_rate": 3.301721150211319e-05, + "loss": 3.5619, + "step": 1037312 + }, + { + "epoch": 1.01, + "learning_rate": 3.300882555460267e-05, + "loss": 3.5669, + "step": 1037824 + }, + { + "epoch": 1.02, + "learning_rate": 3.300043960709215e-05, + "loss": 3.5581, + "step": 1038336 + }, + { + "epoch": 1.02, + "learning_rate": 3.299205365958163e-05, + "loss": 3.5616, + "step": 1038848 + }, + { + "epoch": 1.02, + "learning_rate": 3.298368409087484e-05, + "loss": 3.5627, + "step": 1039360 + }, + { + "epoch": 1.02, + "learning_rate": 3.297529814336433e-05, + "loss": 3.565, + "step": 1039872 + }, + { + "epoch": 1.02, + "learning_rate": 3.296691219585381e-05, + "loss": 3.5702, + "step": 1040384 + }, + { + "epoch": 1.02, + "learning_rate": 3.295852624834329e-05, + "loss": 3.5736, + "step": 1040896 + }, + { + "epoch": 1.02, + "learning_rate": 3.29501566796365e-05, + "loss": 3.555, + "step": 1041408 + }, + { + "epoch": 1.02, + "learning_rate": 3.294177073212598e-05, + "loss": 3.5629, + "step": 1041920 + }, + { + "epoch": 1.02, + "learning_rate": 3.293338478461546e-05, + "loss": 3.5637, + "step": 1042432 + }, + { + "epoch": 1.02, + "learning_rate": 3.292499883710494e-05, + "loss": 3.5591, + "step": 1042944 + }, + { + "epoch": 1.02, + "learning_rate": 3.2916629268398146e-05, + "loss": 3.5674, + "step": 1043456 + }, + { + "epoch": 1.02, + "learning_rate": 3.2908243320887626e-05, + "loss": 3.5604, + "step": 1043968 + }, + { + "epoch": 1.02, + "learning_rate": 3.2899857373377106e-05, + "loss": 3.5564, + "step": 1044480 + }, + { + "epoch": 1.02, + "learning_rate": 3.2891471425866586e-05, + "loss": 3.5546, + "step": 1044992 + }, + { + "epoch": 1.02, + "learning_rate": 3.2883101857159795e-05, + "loss": 3.5672, + "step": 1045504 + }, + { + "epoch": 1.02, + "learning_rate": 3.287471590964928e-05, + "loss": 3.5577, + "step": 1046016 + }, + { + "epoch": 1.02, + "learning_rate": 3.286632996213876e-05, + "loss": 3.5406, + "step": 1046528 + }, + { + "epoch": 1.02, + "learning_rate": 3.285794401462824e-05, + "loss": 3.5627, + "step": 1047040 + }, + { + "epoch": 1.02, + "learning_rate": 3.284955806711772e-05, + "loss": 3.5652, + "step": 1047552 + }, + { + "epoch": 1.02, + "learning_rate": 3.284118849841093e-05, + "loss": 3.5575, + "step": 1048064 + }, + { + "epoch": 1.02, + "learning_rate": 3.283280255090041e-05, + "loss": 3.5562, + "step": 1048576 + }, + { + "epoch": 1.02, + "learning_rate": 3.282441660338989e-05, + "loss": 3.5553, + "step": 1049088 + }, + { + "epoch": 1.02, + "learning_rate": 3.281603065587937e-05, + "loss": 3.5651, + "step": 1049600 + }, + { + "epoch": 1.02, + "learning_rate": 3.280766108717258e-05, + "loss": 3.5548, + "step": 1050112 + }, + { + "epoch": 1.02, + "learning_rate": 3.279927513966206e-05, + "loss": 3.5645, + "step": 1050624 + }, + { + "epoch": 1.02, + "learning_rate": 3.279088919215154e-05, + "loss": 3.5674, + "step": 1051136 + }, + { + "epoch": 1.02, + "learning_rate": 3.278250324464102e-05, + "loss": 3.5646, + "step": 1051648 + }, + { + "epoch": 1.02, + "learning_rate": 3.27741172971305e-05, + "loss": 3.5632, + "step": 1052160 + }, + { + "epoch": 1.02, + "learning_rate": 3.2765747728423715e-05, + "loss": 3.5559, + "step": 1052672 + }, + { + "epoch": 1.02, + "learning_rate": 3.2757361780913195e-05, + "loss": 3.5608, + "step": 1053184 + }, + { + "epoch": 1.02, + "learning_rate": 3.2748975833402675e-05, + "loss": 3.5598, + "step": 1053696 + }, + { + "epoch": 1.02, + "learning_rate": 3.2740589885892155e-05, + "loss": 3.5563, + "step": 1054208 + }, + { + "epoch": 1.02, + "learning_rate": 3.2732220317185364e-05, + "loss": 3.5606, + "step": 1054720 + }, + { + "epoch": 1.02, + "learning_rate": 3.2723834369674844e-05, + "loss": 3.5557, + "step": 1055232 + }, + { + "epoch": 1.02, + "learning_rate": 3.2715448422164324e-05, + "loss": 3.5626, + "step": 1055744 + }, + { + "epoch": 1.02, + "learning_rate": 3.2707062474653804e-05, + "loss": 3.5559, + "step": 1056256 + }, + { + "epoch": 1.02, + "learning_rate": 3.269869290594701e-05, + "loss": 3.5602, + "step": 1056768 + }, + { + "epoch": 1.02, + "learning_rate": 3.269030695843649e-05, + "loss": 3.5488, + "step": 1057280 + }, + { + "epoch": 1.02, + "learning_rate": 3.268192101092597e-05, + "loss": 3.5579, + "step": 1057792 + }, + { + "epoch": 1.02, + "learning_rate": 3.267353506341545e-05, + "loss": 3.5696, + "step": 1058304 + }, + { + "epoch": 1.02, + "learning_rate": 3.266514911590493e-05, + "loss": 3.5583, + "step": 1058816 + }, + { + "epoch": 1.02, + "learning_rate": 3.265677954719815e-05, + "loss": 3.5741, + "step": 1059328 + }, + { + "epoch": 1.02, + "learning_rate": 3.264839359968763e-05, + "loss": 3.5421, + "step": 1059840 + }, + { + "epoch": 1.02, + "learning_rate": 3.264000765217711e-05, + "loss": 3.5668, + "step": 1060352 + }, + { + "epoch": 1.02, + "learning_rate": 3.263162170466659e-05, + "loss": 3.5668, + "step": 1060864 + }, + { + "epoch": 1.02, + "learning_rate": 3.26232521359598e-05, + "loss": 3.5632, + "step": 1061376 + }, + { + "epoch": 1.02, + "learning_rate": 3.261486618844928e-05, + "loss": 3.5613, + "step": 1061888 + }, + { + "epoch": 1.02, + "learning_rate": 3.260648024093876e-05, + "loss": 3.5477, + "step": 1062400 + }, + { + "epoch": 1.02, + "learning_rate": 3.259809429342824e-05, + "loss": 3.5671, + "step": 1062912 + }, + { + "epoch": 1.02, + "learning_rate": 3.258972472472145e-05, + "loss": 3.5804, + "step": 1063424 + }, + { + "epoch": 1.02, + "learning_rate": 3.258133877721093e-05, + "loss": 3.5512, + "step": 1063936 + }, + { + "epoch": 1.02, + "learning_rate": 3.257295282970041e-05, + "loss": 3.5557, + "step": 1064448 + }, + { + "epoch": 1.02, + "learning_rate": 3.256456688218989e-05, + "loss": 3.5622, + "step": 1064960 + }, + { + "epoch": 1.02, + "learning_rate": 3.255618093467937e-05, + "loss": 3.5584, + "step": 1065472 + }, + { + "epoch": 1.02, + "learning_rate": 3.254781136597258e-05, + "loss": 3.5572, + "step": 1065984 + }, + { + "epoch": 1.02, + "learning_rate": 3.253942541846206e-05, + "loss": 3.5658, + "step": 1066496 + }, + { + "epoch": 1.02, + "learning_rate": 3.2531039470951536e-05, + "loss": 3.5537, + "step": 1067008 + }, + { + "epoch": 1.02, + "learning_rate": 3.252266990224475e-05, + "loss": 3.5663, + "step": 1067520 + }, + { + "epoch": 1.02, + "learning_rate": 3.251428395473423e-05, + "loss": 3.5508, + "step": 1068032 + }, + { + "epoch": 1.03, + "eval_loss": 3.843315601348877, + "eval_runtime": 304.6712, + "eval_samples_per_second": 1252.468, + "eval_steps_per_second": 39.141, + "step": 1068480 + }, + { + "epoch": 0.0, + "learning_rate": 3.250589800722371e-05, + "loss": 3.5666, + "step": 1068544 + }, + { + "epoch": 0.0, + "learning_rate": 3.2497512059713185e-05, + "loss": 3.5501, + "step": 1069056 + }, + { + "epoch": 0.0, + "learning_rate": 3.2489126112202665e-05, + "loss": 3.5632, + "step": 1069568 + }, + { + "epoch": 0.0, + "learning_rate": 3.2480740164692145e-05, + "loss": 3.5722, + "step": 1070080 + }, + { + "epoch": 0.0, + "learning_rate": 3.247237059598536e-05, + "loss": 3.5618, + "step": 1070592 + }, + { + "epoch": 0.0, + "learning_rate": 3.246398464847484e-05, + "loss": 3.5587, + "step": 1071104 + }, + { + "epoch": 0.0, + "learning_rate": 3.245559870096432e-05, + "loss": 3.5563, + "step": 1071616 + }, + { + "epoch": 0.0, + "learning_rate": 3.24472127534538e-05, + "loss": 3.5598, + "step": 1072128 + }, + { + "epoch": 0.0, + "learning_rate": 3.243884318474701e-05, + "loss": 3.5505, + "step": 1072640 + }, + { + "epoch": 0.0, + "learning_rate": 3.243045723723649e-05, + "loss": 3.5699, + "step": 1073152 + }, + { + "epoch": 0.0, + "learning_rate": 3.242207128972597e-05, + "loss": 3.5641, + "step": 1073664 + }, + { + "epoch": 0.0, + "learning_rate": 3.241368534221545e-05, + "loss": 3.5627, + "step": 1074176 + }, + { + "epoch": 0.0, + "learning_rate": 3.240531577350866e-05, + "loss": 3.5742, + "step": 1074688 + }, + { + "epoch": 0.0, + "learning_rate": 3.239692982599814e-05, + "loss": 3.5391, + "step": 1075200 + }, + { + "epoch": 0.0, + "learning_rate": 3.238854387848762e-05, + "loss": 3.5626, + "step": 1075712 + }, + { + "epoch": 0.0, + "learning_rate": 3.23801579309771e-05, + "loss": 3.5452, + "step": 1076224 + }, + { + "epoch": 0.0, + "learning_rate": 3.237177198346658e-05, + "loss": 3.5576, + "step": 1076736 + }, + { + "epoch": 0.0, + "learning_rate": 3.2363402414759794e-05, + "loss": 3.5461, + "step": 1077248 + }, + { + "epoch": 0.0, + "learning_rate": 3.2355016467249274e-05, + "loss": 3.5549, + "step": 1077760 + }, + { + "epoch": 0.0, + "learning_rate": 3.2346630519738754e-05, + "loss": 3.5477, + "step": 1078272 + }, + { + "epoch": 0.0, + "learning_rate": 3.2338244572228234e-05, + "loss": 3.5755, + "step": 1078784 + }, + { + "epoch": 0.0, + "learning_rate": 3.232987500352144e-05, + "loss": 3.5607, + "step": 1079296 + }, + { + "epoch": 0.0, + "learning_rate": 3.232148905601092e-05, + "loss": 3.5549, + "step": 1079808 + }, + { + "epoch": 0.0, + "learning_rate": 3.23131031085004e-05, + "loss": 3.5521, + "step": 1080320 + }, + { + "epoch": 0.0, + "learning_rate": 3.230471716098988e-05, + "loss": 3.5634, + "step": 1080832 + }, + { + "epoch": 0.0, + "learning_rate": 3.229633121347936e-05, + "loss": 3.546, + "step": 1081344 + }, + { + "epoch": 0.0, + "learning_rate": 3.228796164477257e-05, + "loss": 3.5457, + "step": 1081856 + }, + { + "epoch": 0.0, + "learning_rate": 3.227957569726205e-05, + "loss": 3.5596, + "step": 1082368 + }, + { + "epoch": 0.0, + "learning_rate": 3.227118974975153e-05, + "loss": 3.5503, + "step": 1082880 + }, + { + "epoch": 0.0, + "learning_rate": 3.226280380224101e-05, + "loss": 3.5492, + "step": 1083392 + }, + { + "epoch": 0.01, + "learning_rate": 3.225443423353423e-05, + "loss": 3.5516, + "step": 1083904 + }, + { + "epoch": 0.01, + "learning_rate": 3.224604828602371e-05, + "loss": 3.5542, + "step": 1084416 + }, + { + "epoch": 0.01, + "learning_rate": 3.223766233851319e-05, + "loss": 3.5559, + "step": 1084928 + }, + { + "epoch": 0.01, + "learning_rate": 3.222927639100267e-05, + "loss": 3.5501, + "step": 1085440 + }, + { + "epoch": 0.01, + "learning_rate": 3.222090682229588e-05, + "loss": 3.549, + "step": 1085952 + }, + { + "epoch": 0.01, + "learning_rate": 3.221252087478536e-05, + "loss": 3.5634, + "step": 1086464 + }, + { + "epoch": 0.01, + "learning_rate": 3.220413492727484e-05, + "loss": 3.5602, + "step": 1086976 + }, + { + "epoch": 0.01, + "learning_rate": 3.2195748979764317e-05, + "loss": 3.5348, + "step": 1087488 + }, + { + "epoch": 0.01, + "learning_rate": 3.2187379411057526e-05, + "loss": 3.5484, + "step": 1088000 + }, + { + "epoch": 0.01, + "learning_rate": 3.2178993463547006e-05, + "loss": 3.5463, + "step": 1088512 + }, + { + "epoch": 0.01, + "learning_rate": 3.2170607516036486e-05, + "loss": 3.5445, + "step": 1089024 + }, + { + "epoch": 0.01, + "learning_rate": 3.2162221568525966e-05, + "loss": 3.5505, + "step": 1089536 + }, + { + "epoch": 0.01, + "learning_rate": 3.215385199981918e-05, + "loss": 3.5574, + "step": 1090048 + }, + { + "epoch": 0.01, + "learning_rate": 3.214546605230866e-05, + "loss": 3.5491, + "step": 1090560 + }, + { + "epoch": 0.01, + "learning_rate": 3.213708010479814e-05, + "loss": 3.5492, + "step": 1091072 + }, + { + "epoch": 0.01, + "learning_rate": 3.212869415728762e-05, + "loss": 3.5586, + "step": 1091584 + }, + { + "epoch": 0.01, + "learning_rate": 3.212032458858083e-05, + "loss": 3.554, + "step": 1092096 + }, + { + "epoch": 0.01, + "learning_rate": 3.211193864107031e-05, + "loss": 3.5544, + "step": 1092608 + }, + { + "epoch": 0.01, + "learning_rate": 3.210355269355979e-05, + "loss": 3.5303, + "step": 1093120 + }, + { + "epoch": 0.01, + "learning_rate": 3.209516674604927e-05, + "loss": 3.5557, + "step": 1093632 + }, + { + "epoch": 0.01, + "learning_rate": 3.208679717734248e-05, + "loss": 3.5572, + "step": 1094144 + }, + { + "epoch": 0.01, + "learning_rate": 3.207841122983196e-05, + "loss": 3.55, + "step": 1094656 + }, + { + "epoch": 0.01, + "learning_rate": 3.207002528232144e-05, + "loss": 3.5463, + "step": 1095168 + }, + { + "epoch": 0.01, + "learning_rate": 3.206163933481092e-05, + "loss": 3.5499, + "step": 1095680 + }, + { + "epoch": 0.01, + "learning_rate": 3.2053269766104135e-05, + "loss": 3.5331, + "step": 1096192 + }, + { + "epoch": 0.01, + "learning_rate": 3.2044883818593615e-05, + "loss": 3.5443, + "step": 1096704 + }, + { + "epoch": 0.01, + "learning_rate": 3.2036497871083095e-05, + "loss": 3.559, + "step": 1097216 + }, + { + "epoch": 0.01, + "learning_rate": 3.2028111923572575e-05, + "loss": 3.5448, + "step": 1097728 + }, + { + "epoch": 0.01, + "learning_rate": 3.2019742354865784e-05, + "loss": 3.5619, + "step": 1098240 + }, + { + "epoch": 0.01, + "learning_rate": 3.2011356407355264e-05, + "loss": 3.5538, + "step": 1098752 + }, + { + "epoch": 0.01, + "learning_rate": 3.2002970459844744e-05, + "loss": 3.5337, + "step": 1099264 + }, + { + "epoch": 0.01, + "learning_rate": 3.1994584512334224e-05, + "loss": 3.5594, + "step": 1099776 + }, + { + "epoch": 0.01, + "learning_rate": 3.198621494362743e-05, + "loss": 3.5396, + "step": 1100288 + }, + { + "epoch": 0.01, + "learning_rate": 3.197782899611691e-05, + "loss": 3.5386, + "step": 1100800 + }, + { + "epoch": 0.01, + "learning_rate": 3.196944304860639e-05, + "loss": 3.5396, + "step": 1101312 + }, + { + "epoch": 0.01, + "learning_rate": 3.196105710109587e-05, + "loss": 3.5481, + "step": 1101824 + }, + { + "epoch": 0.01, + "learning_rate": 3.195268753238909e-05, + "loss": 3.5428, + "step": 1102336 + }, + { + "epoch": 0.01, + "learning_rate": 3.194430158487857e-05, + "loss": 3.5431, + "step": 1102848 + }, + { + "epoch": 0.01, + "learning_rate": 3.193591563736805e-05, + "loss": 3.5351, + "step": 1103360 + }, + { + "epoch": 0.01, + "learning_rate": 3.192752968985753e-05, + "loss": 3.5518, + "step": 1103872 + }, + { + "epoch": 0.01, + "learning_rate": 3.191914374234701e-05, + "loss": 3.5552, + "step": 1104384 + }, + { + "epoch": 0.01, + "learning_rate": 3.191077417364022e-05, + "loss": 3.5521, + "step": 1104896 + }, + { + "epoch": 0.01, + "learning_rate": 3.19023882261297e-05, + "loss": 3.5514, + "step": 1105408 + }, + { + "epoch": 0.01, + "learning_rate": 3.189400227861918e-05, + "loss": 3.5539, + "step": 1105920 + }, + { + "epoch": 0.01, + "learning_rate": 3.188561633110866e-05, + "loss": 3.5578, + "step": 1106432 + }, + { + "epoch": 0.01, + "learning_rate": 3.187723038359814e-05, + "loss": 3.551, + "step": 1106944 + }, + { + "epoch": 0.01, + "learning_rate": 3.186886081489135e-05, + "loss": 3.5506, + "step": 1107456 + }, + { + "epoch": 0.01, + "learning_rate": 3.1860474867380827e-05, + "loss": 3.5523, + "step": 1107968 + }, + { + "epoch": 0.01, + "learning_rate": 3.1852088919870307e-05, + "loss": 3.5471, + "step": 1108480 + }, + { + "epoch": 0.01, + "learning_rate": 3.184370297235979e-05, + "loss": 3.5517, + "step": 1108992 + }, + { + "epoch": 0.01, + "learning_rate": 3.1835333403653e-05, + "loss": 3.549, + "step": 1109504 + }, + { + "epoch": 0.01, + "learning_rate": 3.182694745614248e-05, + "loss": 3.5543, + "step": 1110016 + }, + { + "epoch": 0.01, + "learning_rate": 3.181856150863196e-05, + "loss": 3.5647, + "step": 1110528 + }, + { + "epoch": 0.01, + "learning_rate": 3.1810175561121435e-05, + "loss": 3.5488, + "step": 1111040 + }, + { + "epoch": 0.01, + "learning_rate": 3.180180599241465e-05, + "loss": 3.5273, + "step": 1111552 + }, + { + "epoch": 0.01, + "learning_rate": 3.179342004490413e-05, + "loss": 3.5428, + "step": 1112064 + }, + { + "epoch": 0.01, + "learning_rate": 3.178503409739361e-05, + "loss": 3.5518, + "step": 1112576 + }, + { + "epoch": 0.01, + "learning_rate": 3.1776648149883084e-05, + "loss": 3.5485, + "step": 1113088 + }, + { + "epoch": 0.01, + "learning_rate": 3.17682785811763e-05, + "loss": 3.5476, + "step": 1113600 + }, + { + "epoch": 0.01, + "learning_rate": 3.175989263366578e-05, + "loss": 3.5509, + "step": 1114112 + }, + { + "epoch": 0.02, + "learning_rate": 3.175150668615526e-05, + "loss": 3.5393, + "step": 1114624 + }, + { + "epoch": 0.02, + "learning_rate": 3.174312073864474e-05, + "loss": 3.5463, + "step": 1115136 + }, + { + "epoch": 0.02, + "learning_rate": 3.173473479113422e-05, + "loss": 3.5453, + "step": 1115648 + }, + { + "epoch": 0.02, + "learning_rate": 3.1726365222427436e-05, + "loss": 3.5536, + "step": 1116160 + }, + { + "epoch": 0.02, + "learning_rate": 3.171797927491691e-05, + "loss": 3.5514, + "step": 1116672 + }, + { + "epoch": 0.02, + "learning_rate": 3.170959332740639e-05, + "loss": 3.5607, + "step": 1117184 + }, + { + "epoch": 0.02, + "learning_rate": 3.170120737989587e-05, + "loss": 3.5377, + "step": 1117696 + }, + { + "epoch": 0.02, + "learning_rate": 3.1692837811189085e-05, + "loss": 3.5483, + "step": 1118208 + }, + { + "epoch": 0.02, + "learning_rate": 3.168445186367856e-05, + "loss": 3.5486, + "step": 1118720 + }, + { + "epoch": 0.02, + "learning_rate": 3.167606591616804e-05, + "loss": 3.5478, + "step": 1119232 + }, + { + "epoch": 0.02, + "learning_rate": 3.166767996865752e-05, + "loss": 3.558, + "step": 1119744 + }, + { + "epoch": 0.02, + "learning_rate": 3.1659310399950734e-05, + "loss": 3.5417, + "step": 1120256 + }, + { + "epoch": 0.02, + "learning_rate": 3.1650924452440214e-05, + "loss": 3.5393, + "step": 1120768 + }, + { + "epoch": 0.02, + "learning_rate": 3.1642538504929694e-05, + "loss": 3.5398, + "step": 1121280 + }, + { + "epoch": 0.02, + "learning_rate": 3.1634152557419174e-05, + "loss": 3.5518, + "step": 1121792 + }, + { + "epoch": 0.02, + "learning_rate": 3.162578298871238e-05, + "loss": 3.5397, + "step": 1122304 + }, + { + "epoch": 0.02, + "learning_rate": 3.161739704120186e-05, + "loss": 3.5304, + "step": 1122816 + }, + { + "epoch": 0.02, + "learning_rate": 3.160901109369134e-05, + "loss": 3.5449, + "step": 1123328 + }, + { + "epoch": 0.02, + "learning_rate": 3.160062514618082e-05, + "loss": 3.545, + "step": 1123840 + }, + { + "epoch": 0.02, + "learning_rate": 3.159225557747403e-05, + "loss": 3.5426, + "step": 1124352 + }, + { + "epoch": 0.02, + "learning_rate": 3.158386962996351e-05, + "loss": 3.5466, + "step": 1124864 + }, + { + "epoch": 0.02, + "learning_rate": 3.157548368245299e-05, + "loss": 3.5352, + "step": 1125376 + }, + { + "epoch": 0.02, + "learning_rate": 3.156709773494247e-05, + "loss": 3.5516, + "step": 1125888 + }, + { + "epoch": 0.02, + "learning_rate": 3.155872816623569e-05, + "loss": 3.5387, + "step": 1126400 + }, + { + "epoch": 0.02, + "learning_rate": 3.155034221872517e-05, + "loss": 3.546, + "step": 1126912 + }, + { + "epoch": 0.02, + "learning_rate": 3.154195627121465e-05, + "loss": 3.5535, + "step": 1127424 + }, + { + "epoch": 0.02, + "learning_rate": 3.153357032370413e-05, + "loss": 3.5523, + "step": 1127936 + }, + { + "epoch": 0.02, + "learning_rate": 3.1525200754997337e-05, + "loss": 3.5457, + "step": 1128448 + }, + { + "epoch": 0.02, + "learning_rate": 3.1516814807486816e-05, + "loss": 3.54, + "step": 1128960 + }, + { + "epoch": 0.02, + "learning_rate": 3.1508428859976296e-05, + "loss": 3.547, + "step": 1129472 + }, + { + "epoch": 0.02, + "learning_rate": 3.1500042912465776e-05, + "loss": 3.5439, + "step": 1129984 + }, + { + "epoch": 0.02, + "learning_rate": 3.1491673343758985e-05, + "loss": 3.5383, + "step": 1130496 + }, + { + "epoch": 0.02, + "learning_rate": 3.1483287396248465e-05, + "loss": 3.5498, + "step": 1131008 + }, + { + "epoch": 0.02, + "learning_rate": 3.1474901448737945e-05, + "loss": 3.5414, + "step": 1131520 + }, + { + "epoch": 0.02, + "learning_rate": 3.1466515501227425e-05, + "loss": 3.545, + "step": 1132032 + }, + { + "epoch": 0.02, + "learning_rate": 3.1458129553716905e-05, + "loss": 3.5393, + "step": 1132544 + }, + { + "epoch": 0.02, + "learning_rate": 3.144975998501012e-05, + "loss": 3.5444, + "step": 1133056 + }, + { + "epoch": 0.02, + "learning_rate": 3.14413740374996e-05, + "loss": 3.5379, + "step": 1133568 + }, + { + "epoch": 0.02, + "learning_rate": 3.143298808998908e-05, + "loss": 3.5407, + "step": 1134080 + }, + { + "epoch": 0.02, + "learning_rate": 3.142460214247856e-05, + "loss": 3.5548, + "step": 1134592 + }, + { + "epoch": 0.02, + "learning_rate": 3.141623257377177e-05, + "loss": 3.5461, + "step": 1135104 + }, + { + "epoch": 0.02, + "learning_rate": 3.140784662626125e-05, + "loss": 3.5549, + "step": 1135616 + }, + { + "epoch": 0.02, + "learning_rate": 3.139946067875073e-05, + "loss": 3.5324, + "step": 1136128 + }, + { + "epoch": 0.02, + "learning_rate": 3.139107473124021e-05, + "loss": 3.5475, + "step": 1136640 + }, + { + "epoch": 0.02, + "learning_rate": 3.138270516253342e-05, + "loss": 3.5515, + "step": 1137152 + }, + { + "epoch": 0.02, + "learning_rate": 3.13743192150229e-05, + "loss": 3.5495, + "step": 1137664 + }, + { + "epoch": 0.02, + "learning_rate": 3.136593326751238e-05, + "loss": 3.5421, + "step": 1138176 + }, + { + "epoch": 0.02, + "learning_rate": 3.135754732000186e-05, + "loss": 3.5363, + "step": 1138688 + }, + { + "epoch": 0.02, + "learning_rate": 3.1349161372491346e-05, + "loss": 3.5528, + "step": 1139200 + }, + { + "epoch": 0.02, + "learning_rate": 3.1340791803784555e-05, + "loss": 3.5641, + "step": 1139712 + }, + { + "epoch": 0.02, + "learning_rate": 3.1332405856274035e-05, + "loss": 3.5396, + "step": 1140224 + }, + { + "epoch": 0.02, + "learning_rate": 3.1324019908763515e-05, + "loss": 3.5382, + "step": 1140736 + }, + { + "epoch": 0.02, + "learning_rate": 3.1315633961252995e-05, + "loss": 3.5447, + "step": 1141248 + }, + { + "epoch": 0.02, + "learning_rate": 3.1307264392546204e-05, + "loss": 3.5401, + "step": 1141760 + }, + { + "epoch": 0.02, + "learning_rate": 3.1298878445035684e-05, + "loss": 3.5412, + "step": 1142272 + }, + { + "epoch": 0.02, + "learning_rate": 3.1290492497525164e-05, + "loss": 3.5505, + "step": 1142784 + }, + { + "epoch": 0.02, + "learning_rate": 3.1282106550014644e-05, + "loss": 3.54, + "step": 1143296 + }, + { + "epoch": 0.02, + "learning_rate": 3.127373698130785e-05, + "loss": 3.5526, + "step": 1143808 + }, + { + "epoch": 0.02, + "learning_rate": 3.126535103379733e-05, + "loss": 3.5355, + "step": 1144320 + }, + { + "epoch": 0.03, + "eval_loss": 3.8434953689575195, + "eval_runtime": 303.9826, + "eval_samples_per_second": 1255.305, + "eval_steps_per_second": 39.229, + "step": 1144800 + }, + { + "epoch": 1.0, + "learning_rate": 3.125696508628681e-05, + "loss": 3.5424, + "step": 1144832 + }, + { + "epoch": 1.0, + "learning_rate": 3.12485791387763e-05, + "loss": 3.5401, + "step": 1145344 + }, + { + "epoch": 1.0, + "learning_rate": 3.124020957006951e-05, + "loss": 3.5468, + "step": 1145856 + }, + { + "epoch": 1.0, + "learning_rate": 3.123182362255899e-05, + "loss": 3.5543, + "step": 1146368 + }, + { + "epoch": 1.0, + "learning_rate": 3.122343767504847e-05, + "loss": 3.5463, + "step": 1146880 + }, + { + "epoch": 1.0, + "learning_rate": 3.121505172753795e-05, + "loss": 3.5436, + "step": 1147392 + }, + { + "epoch": 1.0, + "learning_rate": 3.120668215883116e-05, + "loss": 3.5421, + "step": 1147904 + }, + { + "epoch": 1.0, + "learning_rate": 3.119829621132064e-05, + "loss": 3.5415, + "step": 1148416 + }, + { + "epoch": 1.0, + "learning_rate": 3.118991026381012e-05, + "loss": 3.5389, + "step": 1148928 + }, + { + "epoch": 1.0, + "learning_rate": 3.11815243162996e-05, + "loss": 3.5505, + "step": 1149440 + }, + { + "epoch": 1.0, + "learning_rate": 3.1173154747592806e-05, + "loss": 3.5489, + "step": 1149952 + }, + { + "epoch": 1.0, + "learning_rate": 3.1164768800082286e-05, + "loss": 3.5495, + "step": 1150464 + }, + { + "epoch": 1.0, + "learning_rate": 3.11563992313755e-05, + "loss": 3.5585, + "step": 1150976 + }, + { + "epoch": 1.0, + "learning_rate": 3.114801328386498e-05, + "loss": 3.5267, + "step": 1151488 + }, + { + "epoch": 1.0, + "learning_rate": 3.113962733635446e-05, + "loss": 3.545, + "step": 1152000 + }, + { + "epoch": 1.0, + "learning_rate": 3.113124138884394e-05, + "loss": 3.5318, + "step": 1152512 + }, + { + "epoch": 1.0, + "learning_rate": 3.112285544133342e-05, + "loss": 3.5451, + "step": 1153024 + }, + { + "epoch": 1.0, + "learning_rate": 3.11144694938229e-05, + "loss": 3.5286, + "step": 1153536 + }, + { + "epoch": 1.0, + "learning_rate": 3.110608354631238e-05, + "loss": 3.5386, + "step": 1154048 + }, + { + "epoch": 1.0, + "learning_rate": 3.109769759880186e-05, + "loss": 3.5361, + "step": 1154560 + }, + { + "epoch": 1.0, + "learning_rate": 3.108932803009507e-05, + "loss": 3.5562, + "step": 1155072 + }, + { + "epoch": 1.0, + "learning_rate": 3.108094208258455e-05, + "loss": 3.5495, + "step": 1155584 + }, + { + "epoch": 1.0, + "learning_rate": 3.107255613507403e-05, + "loss": 3.5352, + "step": 1156096 + }, + { + "epoch": 1.0, + "learning_rate": 3.106417018756351e-05, + "loss": 3.537, + "step": 1156608 + }, + { + "epoch": 1.0, + "learning_rate": 3.105580061885672e-05, + "loss": 3.5489, + "step": 1157120 + }, + { + "epoch": 1.0, + "learning_rate": 3.10474146713462e-05, + "loss": 3.5299, + "step": 1157632 + }, + { + "epoch": 1.0, + "learning_rate": 3.103902872383569e-05, + "loss": 3.5294, + "step": 1158144 + }, + { + "epoch": 1.0, + "learning_rate": 3.103064277632517e-05, + "loss": 3.5457, + "step": 1158656 + }, + { + "epoch": 1.0, + "learning_rate": 3.102225682881464e-05, + "loss": 3.5296, + "step": 1159168 + }, + { + "epoch": 1.0, + "learning_rate": 3.1013887260107856e-05, + "loss": 3.5346, + "step": 1159680 + }, + { + "epoch": 1.01, + "learning_rate": 3.1005501312597336e-05, + "loss": 3.538, + "step": 1160192 + }, + { + "epoch": 1.01, + "learning_rate": 3.0997115365086816e-05, + "loss": 3.538, + "step": 1160704 + }, + { + "epoch": 1.01, + "learning_rate": 3.098872941757629e-05, + "loss": 3.543, + "step": 1161216 + }, + { + "epoch": 1.01, + "learning_rate": 3.0980359848869505e-05, + "loss": 3.5337, + "step": 1161728 + }, + { + "epoch": 1.01, + "learning_rate": 3.0971973901358985e-05, + "loss": 3.5362, + "step": 1162240 + }, + { + "epoch": 1.01, + "learning_rate": 3.096358795384846e-05, + "loss": 3.5481, + "step": 1162752 + }, + { + "epoch": 1.01, + "learning_rate": 3.095520200633794e-05, + "loss": 3.5466, + "step": 1163264 + }, + { + "epoch": 1.01, + "learning_rate": 3.0946832437631154e-05, + "loss": 3.5187, + "step": 1163776 + }, + { + "epoch": 1.01, + "learning_rate": 3.093844649012064e-05, + "loss": 3.5358, + "step": 1164288 + }, + { + "epoch": 1.01, + "learning_rate": 3.0930060542610114e-05, + "loss": 3.5255, + "step": 1164800 + }, + { + "epoch": 1.01, + "learning_rate": 3.0921674595099593e-05, + "loss": 3.5311, + "step": 1165312 + }, + { + "epoch": 1.01, + "learning_rate": 3.091330502639281e-05, + "loss": 3.5335, + "step": 1165824 + }, + { + "epoch": 1.01, + "learning_rate": 3.090491907888229e-05, + "loss": 3.5418, + "step": 1166336 + }, + { + "epoch": 1.01, + "learning_rate": 3.089653313137176e-05, + "loss": 3.5347, + "step": 1166848 + }, + { + "epoch": 1.01, + "learning_rate": 3.088814718386124e-05, + "loss": 3.5343, + "step": 1167360 + }, + { + "epoch": 1.01, + "learning_rate": 3.087977761515446e-05, + "loss": 3.5411, + "step": 1167872 + }, + { + "epoch": 1.01, + "learning_rate": 3.087139166764393e-05, + "loss": 3.5412, + "step": 1168384 + }, + { + "epoch": 1.01, + "learning_rate": 3.086300572013341e-05, + "loss": 3.5362, + "step": 1168896 + }, + { + "epoch": 1.01, + "learning_rate": 3.085461977262289e-05, + "loss": 3.5176, + "step": 1169408 + }, + { + "epoch": 1.01, + "learning_rate": 3.084625020391611e-05, + "loss": 3.5405, + "step": 1169920 + }, + { + "epoch": 1.01, + "learning_rate": 3.083786425640559e-05, + "loss": 3.5433, + "step": 1170432 + }, + { + "epoch": 1.01, + "learning_rate": 3.082947830889507e-05, + "loss": 3.5351, + "step": 1170944 + }, + { + "epoch": 1.01, + "learning_rate": 3.082109236138455e-05, + "loss": 3.5282, + "step": 1171456 + }, + { + "epoch": 1.01, + "learning_rate": 3.081272279267776e-05, + "loss": 3.5338, + "step": 1171968 + }, + { + "epoch": 1.01, + "learning_rate": 3.0804336845167236e-05, + "loss": 3.5268, + "step": 1172480 + }, + { + "epoch": 1.01, + "learning_rate": 3.0795950897656716e-05, + "loss": 3.5207, + "step": 1172992 + }, + { + "epoch": 1.01, + "learning_rate": 3.0787564950146196e-05, + "loss": 3.5456, + "step": 1173504 + }, + { + "epoch": 1.01, + "learning_rate": 3.0779195381439405e-05, + "loss": 3.5303, + "step": 1174016 + }, + { + "epoch": 1.01, + "learning_rate": 3.0770809433928885e-05, + "loss": 3.5449, + "step": 1174528 + }, + { + "epoch": 1.01, + "learning_rate": 3.0762423486418365e-05, + "loss": 3.5433, + "step": 1175040 + }, + { + "epoch": 1.01, + "learning_rate": 3.0754037538907845e-05, + "loss": 3.518, + "step": 1175552 + }, + { + "epoch": 1.01, + "learning_rate": 3.074566797020106e-05, + "loss": 3.5398, + "step": 1176064 + }, + { + "epoch": 1.01, + "learning_rate": 3.073728202269054e-05, + "loss": 3.5309, + "step": 1176576 + }, + { + "epoch": 1.01, + "learning_rate": 3.072889607518002e-05, + "loss": 3.5265, + "step": 1177088 + }, + { + "epoch": 1.01, + "learning_rate": 3.07205101276695e-05, + "loss": 3.519, + "step": 1177600 + }, + { + "epoch": 1.01, + "learning_rate": 3.071214055896271e-05, + "loss": 3.5341, + "step": 1178112 + }, + { + "epoch": 1.01, + "learning_rate": 3.070375461145219e-05, + "loss": 3.5308, + "step": 1178624 + }, + { + "epoch": 1.01, + "learning_rate": 3.069536866394167e-05, + "loss": 3.5228, + "step": 1179136 + }, + { + "epoch": 1.01, + "learning_rate": 3.068698271643115e-05, + "loss": 3.5231, + "step": 1179648 + }, + { + "epoch": 1.01, + "learning_rate": 3.067861314772436e-05, + "loss": 3.5378, + "step": 1180160 + }, + { + "epoch": 1.01, + "learning_rate": 3.067022720021384e-05, + "loss": 3.5388, + "step": 1180672 + }, + { + "epoch": 1.01, + "learning_rate": 3.066184125270332e-05, + "loss": 3.5379, + "step": 1181184 + }, + { + "epoch": 1.01, + "learning_rate": 3.06534553051928e-05, + "loss": 3.5365, + "step": 1181696 + }, + { + "epoch": 1.01, + "learning_rate": 3.0645085736486015e-05, + "loss": 3.5394, + "step": 1182208 + }, + { + "epoch": 1.01, + "learning_rate": 3.0636699788975495e-05, + "loss": 3.541, + "step": 1182720 + }, + { + "epoch": 1.01, + "learning_rate": 3.0628313841464975e-05, + "loss": 3.5399, + "step": 1183232 + }, + { + "epoch": 1.01, + "learning_rate": 3.0619927893954454e-05, + "loss": 3.5375, + "step": 1183744 + }, + { + "epoch": 1.01, + "learning_rate": 3.0611541946443934e-05, + "loss": 3.5376, + "step": 1184256 + }, + { + "epoch": 1.01, + "learning_rate": 3.0603172377737144e-05, + "loss": 3.5328, + "step": 1184768 + }, + { + "epoch": 1.01, + "learning_rate": 3.0594786430226623e-05, + "loss": 3.5368, + "step": 1185280 + }, + { + "epoch": 1.01, + "learning_rate": 3.0586400482716103e-05, + "loss": 3.5322, + "step": 1185792 + }, + { + "epoch": 1.01, + "learning_rate": 3.0578014535205583e-05, + "loss": 3.5424, + "step": 1186304 + }, + { + "epoch": 1.01, + "learning_rate": 3.056964496649879e-05, + "loss": 3.5435, + "step": 1186816 + }, + { + "epoch": 1.01, + "learning_rate": 3.056125901898827e-05, + "loss": 3.5363, + "step": 1187328 + }, + { + "epoch": 1.01, + "learning_rate": 3.055287307147775e-05, + "loss": 3.5144, + "step": 1187840 + }, + { + "epoch": 1.01, + "learning_rate": 3.054448712396724e-05, + "loss": 3.5264, + "step": 1188352 + }, + { + "epoch": 1.01, + "learning_rate": 3.053611755526045e-05, + "loss": 3.5384, + "step": 1188864 + }, + { + "epoch": 1.01, + "learning_rate": 3.052773160774993e-05, + "loss": 3.5346, + "step": 1189376 + }, + { + "epoch": 1.01, + "learning_rate": 3.051934566023941e-05, + "loss": 3.5315, + "step": 1189888 + }, + { + "epoch": 1.01, + "learning_rate": 3.0510959712728888e-05, + "loss": 3.5403, + "step": 1190400 + }, + { + "epoch": 1.02, + "learning_rate": 3.0502590144022097e-05, + "loss": 3.5288, + "step": 1190912 + }, + { + "epoch": 1.02, + "learning_rate": 3.0494204196511577e-05, + "loss": 3.5257, + "step": 1191424 + }, + { + "epoch": 1.02, + "learning_rate": 3.0485818249001057e-05, + "loss": 3.5296, + "step": 1191936 + }, + { + "epoch": 1.02, + "learning_rate": 3.0477432301490537e-05, + "loss": 3.5385, + "step": 1192448 + }, + { + "epoch": 1.02, + "learning_rate": 3.046906273278375e-05, + "loss": 3.5339, + "step": 1192960 + }, + { + "epoch": 1.02, + "learning_rate": 3.046067678527323e-05, + "loss": 3.5439, + "step": 1193472 + }, + { + "epoch": 1.02, + "learning_rate": 3.045229083776271e-05, + "loss": 3.5255, + "step": 1193984 + }, + { + "epoch": 1.02, + "learning_rate": 3.044390489025219e-05, + "loss": 3.5344, + "step": 1194496 + }, + { + "epoch": 1.02, + "learning_rate": 3.04355353215454e-05, + "loss": 3.5344, + "step": 1195008 + }, + { + "epoch": 1.02, + "learning_rate": 3.042714937403488e-05, + "loss": 3.5317, + "step": 1195520 + }, + { + "epoch": 1.02, + "learning_rate": 3.0418763426524362e-05, + "loss": 3.5381, + "step": 1196032 + }, + { + "epoch": 1.02, + "learning_rate": 3.0410377479013842e-05, + "loss": 3.531, + "step": 1196544 + }, + { + "epoch": 1.02, + "learning_rate": 3.040200791030705e-05, + "loss": 3.525, + "step": 1197056 + }, + { + "epoch": 1.02, + "learning_rate": 3.039362196279653e-05, + "loss": 3.5254, + "step": 1197568 + }, + { + "epoch": 1.02, + "learning_rate": 3.038523601528601e-05, + "loss": 3.5385, + "step": 1198080 + }, + { + "epoch": 1.02, + "learning_rate": 3.037685006777549e-05, + "loss": 3.5217, + "step": 1198592 + }, + { + "epoch": 1.02, + "learning_rate": 3.0368480499068703e-05, + "loss": 3.5145, + "step": 1199104 + }, + { + "epoch": 1.02, + "learning_rate": 3.0360094551558183e-05, + "loss": 3.5341, + "step": 1199616 + }, + { + "epoch": 1.02, + "learning_rate": 3.0351708604047663e-05, + "loss": 3.5306, + "step": 1200128 + }, + { + "epoch": 1.02, + "learning_rate": 3.0343322656537143e-05, + "loss": 3.5259, + "step": 1200640 + }, + { + "epoch": 1.02, + "learning_rate": 3.0334953087830352e-05, + "loss": 3.5331, + "step": 1201152 + }, + { + "epoch": 1.02, + "learning_rate": 3.0326567140319832e-05, + "loss": 3.5212, + "step": 1201664 + }, + { + "epoch": 1.02, + "learning_rate": 3.0318181192809315e-05, + "loss": 3.5386, + "step": 1202176 + }, + { + "epoch": 1.02, + "learning_rate": 3.0309795245298795e-05, + "loss": 3.5198, + "step": 1202688 + }, + { + "epoch": 1.02, + "learning_rate": 3.0301425676592005e-05, + "loss": 3.5315, + "step": 1203200 + }, + { + "epoch": 1.02, + "learning_rate": 3.0293039729081484e-05, + "loss": 3.5378, + "step": 1203712 + }, + { + "epoch": 1.02, + "learning_rate": 3.0284653781570964e-05, + "loss": 3.5392, + "step": 1204224 + }, + { + "epoch": 1.02, + "learning_rate": 3.0276267834060444e-05, + "loss": 3.5276, + "step": 1204736 + }, + { + "epoch": 1.02, + "learning_rate": 3.0267898265353657e-05, + "loss": 3.5266, + "step": 1205248 + }, + { + "epoch": 1.02, + "learning_rate": 3.0259512317843137e-05, + "loss": 3.5319, + "step": 1205760 + }, + { + "epoch": 1.02, + "learning_rate": 3.0251126370332617e-05, + "loss": 3.5283, + "step": 1206272 + }, + { + "epoch": 1.02, + "learning_rate": 3.0242740422822097e-05, + "loss": 3.5209, + "step": 1206784 + }, + { + "epoch": 1.02, + "learning_rate": 3.0234370854115306e-05, + "loss": 3.5348, + "step": 1207296 + }, + { + "epoch": 1.02, + "learning_rate": 3.0225984906604786e-05, + "loss": 3.5258, + "step": 1207808 + }, + { + "epoch": 1.02, + "learning_rate": 3.021759895909427e-05, + "loss": 3.5296, + "step": 1208320 + }, + { + "epoch": 1.02, + "learning_rate": 3.020921301158375e-05, + "loss": 3.5276, + "step": 1208832 + }, + { + "epoch": 1.02, + "learning_rate": 3.0200843442876958e-05, + "loss": 3.527, + "step": 1209344 + }, + { + "epoch": 1.02, + "learning_rate": 3.0192457495366438e-05, + "loss": 3.5288, + "step": 1209856 + }, + { + "epoch": 1.02, + "learning_rate": 3.0184071547855918e-05, + "loss": 3.5243, + "step": 1210368 + }, + { + "epoch": 1.02, + "learning_rate": 3.0175685600345398e-05, + "loss": 3.5311, + "step": 1210880 + }, + { + "epoch": 1.02, + "learning_rate": 3.016731603163861e-05, + "loss": 3.5392, + "step": 1211392 + }, + { + "epoch": 1.02, + "learning_rate": 3.015893008412809e-05, + "loss": 3.5409, + "step": 1211904 + }, + { + "epoch": 1.02, + "learning_rate": 3.015054413661757e-05, + "loss": 3.5191, + "step": 1212416 + }, + { + "epoch": 1.02, + "learning_rate": 3.014215818910705e-05, + "loss": 3.5326, + "step": 1212928 + }, + { + "epoch": 1.02, + "learning_rate": 3.013378862040026e-05, + "loss": 3.5365, + "step": 1213440 + }, + { + "epoch": 1.02, + "learning_rate": 3.012540267288974e-05, + "loss": 3.5333, + "step": 1213952 + }, + { + "epoch": 1.02, + "learning_rate": 3.0117016725379223e-05, + "loss": 3.5275, + "step": 1214464 + }, + { + "epoch": 1.02, + "learning_rate": 3.0108630777868703e-05, + "loss": 3.523, + "step": 1214976 + }, + { + "epoch": 1.02, + "learning_rate": 3.0100261209161912e-05, + "loss": 3.5378, + "step": 1215488 + }, + { + "epoch": 1.02, + "learning_rate": 3.0091875261651392e-05, + "loss": 3.5474, + "step": 1216000 + }, + { + "epoch": 1.02, + "learning_rate": 3.0083489314140872e-05, + "loss": 3.5268, + "step": 1216512 + }, + { + "epoch": 1.02, + "learning_rate": 3.0075103366630352e-05, + "loss": 3.5229, + "step": 1217024 + }, + { + "epoch": 1.02, + "learning_rate": 3.0066733797923564e-05, + "loss": 3.5303, + "step": 1217536 + }, + { + "epoch": 1.02, + "learning_rate": 3.0058347850413044e-05, + "loss": 3.5258, + "step": 1218048 + }, + { + "epoch": 1.02, + "learning_rate": 3.0049961902902524e-05, + "loss": 3.5278, + "step": 1218560 + }, + { + "epoch": 1.02, + "learning_rate": 3.0041575955392004e-05, + "loss": 3.538, + "step": 1219072 + }, + { + "epoch": 1.02, + "learning_rate": 3.0033206386685213e-05, + "loss": 3.5216, + "step": 1219584 + }, + { + "epoch": 1.02, + "learning_rate": 3.0024820439174693e-05, + "loss": 3.5399, + "step": 1220096 + }, + { + "epoch": 1.02, + "learning_rate": 3.0016434491664176e-05, + "loss": 3.5214, + "step": 1220608 + }, + { + "epoch": 1.03, + "learning_rate": 3.0008048544153656e-05, + "loss": 3.5278, + "step": 1221120 + }, + { + "epoch": 1.03, + "eval_loss": 3.845343828201294, + "eval_runtime": 304.3959, + "eval_samples_per_second": 1253.601, + "eval_steps_per_second": 39.176, + "step": 1221120 + }, + { + "epoch": 0.0, + "learning_rate": 2.9999662596643136e-05, + "loss": 3.5207, + "step": 1221632 + }, + { + "epoch": 0.0, + "learning_rate": 2.999127664913261e-05, + "loss": 3.5321, + "step": 1222144 + }, + { + "epoch": 0.0, + "learning_rate": 2.998289070162209e-05, + "loss": 3.5403, + "step": 1222656 + }, + { + "epoch": 0.0, + "learning_rate": 2.9974521132915305e-05, + "loss": 3.5328, + "step": 1223168 + }, + { + "epoch": 0.0, + "learning_rate": 2.9966135185404782e-05, + "loss": 3.5313, + "step": 1223680 + }, + { + "epoch": 0.0, + "learning_rate": 2.9957749237894262e-05, + "loss": 3.5278, + "step": 1224192 + }, + { + "epoch": 0.0, + "learning_rate": 2.9949363290383742e-05, + "loss": 3.5269, + "step": 1224704 + }, + { + "epoch": 0.0, + "learning_rate": 2.9940993721676958e-05, + "loss": 3.5165, + "step": 1225216 + }, + { + "epoch": 0.0, + "learning_rate": 2.993260777416643e-05, + "loss": 3.543, + "step": 1225728 + }, + { + "epoch": 0.0, + "learning_rate": 2.9924221826655914e-05, + "loss": 3.528, + "step": 1226240 + }, + { + "epoch": 0.0, + "learning_rate": 2.9915835879145394e-05, + "loss": 3.5381, + "step": 1226752 + }, + { + "epoch": 0.0, + "learning_rate": 2.990746631043861e-05, + "loss": 3.5414, + "step": 1227264 + }, + { + "epoch": 0.0, + "learning_rate": 2.9899080362928083e-05, + "loss": 3.515, + "step": 1227776 + }, + { + "epoch": 0.0, + "learning_rate": 2.9890694415417563e-05, + "loss": 3.5236, + "step": 1228288 + }, + { + "epoch": 0.0, + "learning_rate": 2.9882308467907043e-05, + "loss": 3.5194, + "step": 1228800 + }, + { + "epoch": 0.0, + "learning_rate": 2.9873922520396523e-05, + "loss": 3.5241, + "step": 1229312 + }, + { + "epoch": 0.0, + "learning_rate": 2.9865552951689736e-05, + "loss": 3.522, + "step": 1229824 + }, + { + "epoch": 0.0, + "learning_rate": 2.9857167004179216e-05, + "loss": 3.5225, + "step": 1230336 + }, + { + "epoch": 0.0, + "learning_rate": 2.9848781056668696e-05, + "loss": 3.5205, + "step": 1230848 + }, + { + "epoch": 0.0, + "learning_rate": 2.9840395109158176e-05, + "loss": 3.5383, + "step": 1231360 + }, + { + "epoch": 0.0, + "learning_rate": 2.9832025540451385e-05, + "loss": 3.5344, + "step": 1231872 + }, + { + "epoch": 0.0, + "learning_rate": 2.9823639592940868e-05, + "loss": 3.5223, + "step": 1232384 + }, + { + "epoch": 0.0, + "learning_rate": 2.9815253645430348e-05, + "loss": 3.5214, + "step": 1232896 + }, + { + "epoch": 0.0, + "learning_rate": 2.9806867697919828e-05, + "loss": 3.5382, + "step": 1233408 + }, + { + "epoch": 0.0, + "learning_rate": 2.9798498129213037e-05, + "loss": 3.518, + "step": 1233920 + }, + { + "epoch": 0.0, + "learning_rate": 2.9790112181702517e-05, + "loss": 3.5134, + "step": 1234432 + }, + { + "epoch": 0.0, + "learning_rate": 2.9781726234191997e-05, + "loss": 3.5276, + "step": 1234944 + }, + { + "epoch": 0.0, + "learning_rate": 2.9773340286681477e-05, + "loss": 3.521, + "step": 1235456 + }, + { + "epoch": 0.0, + "learning_rate": 2.976497071797469e-05, + "loss": 3.5205, + "step": 1235968 + }, + { + "epoch": 0.01, + "learning_rate": 2.975658477046417e-05, + "loss": 3.5205, + "step": 1236480 + }, + { + "epoch": 0.01, + "learning_rate": 2.974819882295365e-05, + "loss": 3.5244, + "step": 1236992 + }, + { + "epoch": 0.01, + "learning_rate": 2.973981287544313e-05, + "loss": 3.5283, + "step": 1237504 + }, + { + "epoch": 0.01, + "learning_rate": 2.9731443306736338e-05, + "loss": 3.5199, + "step": 1238016 + }, + { + "epoch": 0.01, + "learning_rate": 2.9723057359225818e-05, + "loss": 3.5247, + "step": 1238528 + }, + { + "epoch": 0.01, + "learning_rate": 2.97146714117153e-05, + "loss": 3.5351, + "step": 1239040 + }, + { + "epoch": 0.01, + "learning_rate": 2.970628546420478e-05, + "loss": 3.5306, + "step": 1239552 + }, + { + "epoch": 0.01, + "learning_rate": 2.969791589549799e-05, + "loss": 3.5067, + "step": 1240064 + }, + { + "epoch": 0.01, + "learning_rate": 2.968952994798747e-05, + "loss": 3.5213, + "step": 1240576 + }, + { + "epoch": 0.01, + "learning_rate": 2.968114400047695e-05, + "loss": 3.5093, + "step": 1241088 + }, + { + "epoch": 0.01, + "learning_rate": 2.967275805296643e-05, + "loss": 3.523, + "step": 1241600 + }, + { + "epoch": 0.01, + "learning_rate": 2.9664388484259643e-05, + "loss": 3.5171, + "step": 1242112 + }, + { + "epoch": 0.01, + "learning_rate": 2.9656002536749123e-05, + "loss": 3.5275, + "step": 1242624 + }, + { + "epoch": 0.01, + "learning_rate": 2.9647616589238603e-05, + "loss": 3.519, + "step": 1243136 + }, + { + "epoch": 0.01, + "learning_rate": 2.9639230641728083e-05, + "loss": 3.5241, + "step": 1243648 + }, + { + "epoch": 0.01, + "learning_rate": 2.9630861073021292e-05, + "loss": 3.526, + "step": 1244160 + }, + { + "epoch": 0.01, + "learning_rate": 2.9622475125510772e-05, + "loss": 3.5277, + "step": 1244672 + }, + { + "epoch": 0.01, + "learning_rate": 2.9614089178000255e-05, + "loss": 3.5196, + "step": 1245184 + }, + { + "epoch": 0.01, + "learning_rate": 2.9605703230489735e-05, + "loss": 3.5054, + "step": 1245696 + }, + { + "epoch": 0.01, + "learning_rate": 2.9597333661782944e-05, + "loss": 3.5231, + "step": 1246208 + }, + { + "epoch": 0.01, + "learning_rate": 2.9588947714272424e-05, + "loss": 3.5306, + "step": 1246720 + }, + { + "epoch": 0.01, + "learning_rate": 2.9580561766761904e-05, + "loss": 3.5182, + "step": 1247232 + }, + { + "epoch": 0.01, + "learning_rate": 2.9572175819251384e-05, + "loss": 3.5138, + "step": 1247744 + }, + { + "epoch": 0.01, + "learning_rate": 2.9563806250544597e-05, + "loss": 3.5166, + "step": 1248256 + }, + { + "epoch": 0.01, + "learning_rate": 2.9555420303034077e-05, + "loss": 3.517, + "step": 1248768 + }, + { + "epoch": 0.01, + "learning_rate": 2.9547034355523557e-05, + "loss": 3.5041, + "step": 1249280 + }, + { + "epoch": 0.01, + "learning_rate": 2.9538648408013037e-05, + "loss": 3.5322, + "step": 1249792 + }, + { + "epoch": 0.01, + "learning_rate": 2.9530278839306246e-05, + "loss": 3.5188, + "step": 1250304 + }, + { + "epoch": 0.01, + "learning_rate": 2.9521892891795726e-05, + "loss": 3.5313, + "step": 1250816 + }, + { + "epoch": 0.01, + "learning_rate": 2.951350694428521e-05, + "loss": 3.5257, + "step": 1251328 + }, + { + "epoch": 0.01, + "learning_rate": 2.950512099677469e-05, + "loss": 3.5066, + "step": 1251840 + }, + { + "epoch": 0.01, + "learning_rate": 2.9496751428067898e-05, + "loss": 3.5257, + "step": 1252352 + }, + { + "epoch": 0.01, + "learning_rate": 2.9488365480557378e-05, + "loss": 3.5187, + "step": 1252864 + }, + { + "epoch": 0.01, + "learning_rate": 2.9479979533046858e-05, + "loss": 3.5107, + "step": 1253376 + }, + { + "epoch": 0.01, + "learning_rate": 2.9471593585536338e-05, + "loss": 3.5067, + "step": 1253888 + }, + { + "epoch": 0.01, + "learning_rate": 2.946322401682955e-05, + "loss": 3.5241, + "step": 1254400 + }, + { + "epoch": 0.01, + "learning_rate": 2.945483806931903e-05, + "loss": 3.5138, + "step": 1254912 + }, + { + "epoch": 0.01, + "learning_rate": 2.944645212180851e-05, + "loss": 3.512, + "step": 1255424 + }, + { + "epoch": 0.01, + "learning_rate": 2.943806617429799e-05, + "loss": 3.5057, + "step": 1255936 + }, + { + "epoch": 0.01, + "learning_rate": 2.94296966055912e-05, + "loss": 3.5258, + "step": 1256448 + }, + { + "epoch": 0.01, + "learning_rate": 2.942131065808068e-05, + "loss": 3.5254, + "step": 1256960 + }, + { + "epoch": 0.01, + "learning_rate": 2.9412924710570163e-05, + "loss": 3.5209, + "step": 1257472 + }, + { + "epoch": 0.01, + "learning_rate": 2.9404538763059643e-05, + "loss": 3.5208, + "step": 1257984 + }, + { + "epoch": 0.01, + "learning_rate": 2.939616919435285e-05, + "loss": 3.5299, + "step": 1258496 + }, + { + "epoch": 0.01, + "learning_rate": 2.938778324684233e-05, + "loss": 3.5253, + "step": 1259008 + }, + { + "epoch": 0.01, + "learning_rate": 2.937939729933181e-05, + "loss": 3.5276, + "step": 1259520 + }, + { + "epoch": 0.01, + "learning_rate": 2.937101135182129e-05, + "loss": 3.5162, + "step": 1260032 + }, + { + "epoch": 0.01, + "learning_rate": 2.936262540431077e-05, + "loss": 3.5275, + "step": 1260544 + }, + { + "epoch": 0.01, + "learning_rate": 2.9354255835603984e-05, + "loss": 3.5203, + "step": 1261056 + }, + { + "epoch": 0.01, + "learning_rate": 2.9345869888093464e-05, + "loss": 3.5192, + "step": 1261568 + }, + { + "epoch": 0.01, + "learning_rate": 2.9337483940582944e-05, + "loss": 3.5191, + "step": 1262080 + }, + { + "epoch": 0.01, + "learning_rate": 2.9329097993072424e-05, + "loss": 3.5243, + "step": 1262592 + }, + { + "epoch": 0.01, + "learning_rate": 2.9320728424365633e-05, + "loss": 3.5288, + "step": 1263104 + }, + { + "epoch": 0.01, + "learning_rate": 2.9312342476855116e-05, + "loss": 3.5218, + "step": 1263616 + }, + { + "epoch": 0.01, + "learning_rate": 2.9303956529344596e-05, + "loss": 3.5011, + "step": 1264128 + }, + { + "epoch": 0.01, + "learning_rate": 2.9295570581834076e-05, + "loss": 3.5089, + "step": 1264640 + }, + { + "epoch": 0.01, + "learning_rate": 2.9287201013127285e-05, + "loss": 3.5243, + "step": 1265152 + }, + { + "epoch": 0.01, + "learning_rate": 2.9278815065616765e-05, + "loss": 3.5209, + "step": 1265664 + }, + { + "epoch": 0.01, + "learning_rate": 2.9270429118106245e-05, + "loss": 3.5198, + "step": 1266176 + }, + { + "epoch": 0.01, + "learning_rate": 2.9262043170595725e-05, + "loss": 3.5198, + "step": 1266688 + }, + { + "epoch": 0.02, + "learning_rate": 2.9253673601888938e-05, + "loss": 3.5183, + "step": 1267200 + }, + { + "epoch": 0.02, + "learning_rate": 2.9245287654378418e-05, + "loss": 3.5107, + "step": 1267712 + }, + { + "epoch": 0.02, + "learning_rate": 2.9236901706867898e-05, + "loss": 3.5177, + "step": 1268224 + }, + { + "epoch": 0.02, + "learning_rate": 2.9228515759357377e-05, + "loss": 3.5215, + "step": 1268736 + }, + { + "epoch": 0.02, + "learning_rate": 2.9220146190650587e-05, + "loss": 3.5205, + "step": 1269248 + }, + { + "epoch": 0.02, + "learning_rate": 2.921176024314007e-05, + "loss": 3.5301, + "step": 1269760 + }, + { + "epoch": 0.02, + "learning_rate": 2.920337429562955e-05, + "loss": 3.5132, + "step": 1270272 + }, + { + "epoch": 0.02, + "learning_rate": 2.919498834811903e-05, + "loss": 3.5199, + "step": 1270784 + }, + { + "epoch": 0.02, + "learning_rate": 2.918661877941224e-05, + "loss": 3.5208, + "step": 1271296 + }, + { + "epoch": 0.02, + "learning_rate": 2.917823283190172e-05, + "loss": 3.5193, + "step": 1271808 + }, + { + "epoch": 0.02, + "learning_rate": 2.91698468843912e-05, + "loss": 3.5233, + "step": 1272320 + }, + { + "epoch": 0.02, + "learning_rate": 2.916146093688068e-05, + "loss": 3.5173, + "step": 1272832 + }, + { + "epoch": 0.02, + "learning_rate": 2.915309136817389e-05, + "loss": 3.5121, + "step": 1273344 + }, + { + "epoch": 0.02, + "learning_rate": 2.914470542066337e-05, + "loss": 3.5124, + "step": 1273856 + }, + { + "epoch": 0.02, + "learning_rate": 2.913631947315285e-05, + "loss": 3.5235, + "step": 1274368 + }, + { + "epoch": 0.02, + "learning_rate": 2.912793352564233e-05, + "loss": 3.5082, + "step": 1274880 + }, + { + "epoch": 0.02, + "learning_rate": 2.911956395693554e-05, + "loss": 3.5014, + "step": 1275392 + }, + { + "epoch": 0.02, + "learning_rate": 2.9111178009425024e-05, + "loss": 3.5161, + "step": 1275904 + }, + { + "epoch": 0.02, + "learning_rate": 2.9102792061914504e-05, + "loss": 3.5206, + "step": 1276416 + }, + { + "epoch": 0.02, + "learning_rate": 2.9094406114403983e-05, + "loss": 3.51, + "step": 1276928 + }, + { + "epoch": 0.02, + "learning_rate": 2.9086036545697193e-05, + "loss": 3.5198, + "step": 1277440 + }, + { + "epoch": 0.02, + "learning_rate": 2.9077650598186673e-05, + "loss": 3.5078, + "step": 1277952 + }, + { + "epoch": 0.02, + "learning_rate": 2.9069264650676152e-05, + "loss": 3.5229, + "step": 1278464 + }, + { + "epoch": 0.02, + "learning_rate": 2.9060878703165632e-05, + "loss": 3.5065, + "step": 1278976 + }, + { + "epoch": 0.02, + "learning_rate": 2.9052509134458845e-05, + "loss": 3.517, + "step": 1279488 + }, + { + "epoch": 0.02, + "learning_rate": 2.9044123186948325e-05, + "loss": 3.5228, + "step": 1280000 + }, + { + "epoch": 0.02, + "learning_rate": 2.9035737239437805e-05, + "loss": 3.5261, + "step": 1280512 + }, + { + "epoch": 0.02, + "learning_rate": 2.9027351291927278e-05, + "loss": 3.5134, + "step": 1281024 + }, + { + "epoch": 0.02, + "learning_rate": 2.9018981723220494e-05, + "loss": 3.5139, + "step": 1281536 + }, + { + "epoch": 0.02, + "learning_rate": 2.9010595775709977e-05, + "loss": 3.5169, + "step": 1282048 + }, + { + "epoch": 0.02, + "learning_rate": 2.9002209828199457e-05, + "loss": 3.5163, + "step": 1282560 + }, + { + "epoch": 0.02, + "learning_rate": 2.899382388068893e-05, + "loss": 3.5069, + "step": 1283072 + }, + { + "epoch": 0.02, + "learning_rate": 2.8985454311982146e-05, + "loss": 3.5167, + "step": 1283584 + }, + { + "epoch": 0.02, + "learning_rate": 2.8977068364471626e-05, + "loss": 3.515, + "step": 1284096 + }, + { + "epoch": 0.02, + "learning_rate": 2.8968682416961106e-05, + "loss": 3.52, + "step": 1284608 + }, + { + "epoch": 0.02, + "learning_rate": 2.8960296469450583e-05, + "loss": 3.5116, + "step": 1285120 + }, + { + "epoch": 0.02, + "learning_rate": 2.89519269007438e-05, + "loss": 3.5111, + "step": 1285632 + }, + { + "epoch": 0.02, + "learning_rate": 2.894354095323328e-05, + "loss": 3.5126, + "step": 1286144 + }, + { + "epoch": 0.02, + "learning_rate": 2.8935155005722752e-05, + "loss": 3.5167, + "step": 1286656 + }, + { + "epoch": 0.02, + "learning_rate": 2.892676905821223e-05, + "loss": 3.5126, + "step": 1287168 + }, + { + "epoch": 0.02, + "learning_rate": 2.8918399489505448e-05, + "loss": 3.5269, + "step": 1287680 + }, + { + "epoch": 0.02, + "learning_rate": 2.8910013541994928e-05, + "loss": 3.5253, + "step": 1288192 + }, + { + "epoch": 0.02, + "learning_rate": 2.8901627594484404e-05, + "loss": 3.5058, + "step": 1288704 + }, + { + "epoch": 0.02, + "learning_rate": 2.8893241646973884e-05, + "loss": 3.5142, + "step": 1289216 + }, + { + "epoch": 0.02, + "learning_rate": 2.88848720782671e-05, + "loss": 3.5253, + "step": 1289728 + }, + { + "epoch": 0.02, + "learning_rate": 2.887648613075658e-05, + "loss": 3.5235, + "step": 1290240 + }, + { + "epoch": 0.02, + "learning_rate": 2.8868100183246056e-05, + "loss": 3.5135, + "step": 1290752 + }, + { + "epoch": 0.02, + "learning_rate": 2.8859714235735536e-05, + "loss": 3.5064, + "step": 1291264 + }, + { + "epoch": 0.02, + "learning_rate": 2.8851344667028752e-05, + "loss": 3.5248, + "step": 1291776 + }, + { + "epoch": 0.02, + "learning_rate": 2.8842958719518225e-05, + "loss": 3.5274, + "step": 1292288 + }, + { + "epoch": 0.02, + "learning_rate": 2.8834572772007705e-05, + "loss": 3.5147, + "step": 1292800 + }, + { + "epoch": 0.02, + "learning_rate": 2.8826186824497185e-05, + "loss": 3.5124, + "step": 1293312 + }, + { + "epoch": 0.02, + "learning_rate": 2.88178172557904e-05, + "loss": 3.5138, + "step": 1293824 + }, + { + "epoch": 0.02, + "learning_rate": 2.8809431308279878e-05, + "loss": 3.5141, + "step": 1294336 + }, + { + "epoch": 0.02, + "learning_rate": 2.8801045360769358e-05, + "loss": 3.512, + "step": 1294848 + }, + { + "epoch": 0.02, + "learning_rate": 2.8792659413258838e-05, + "loss": 3.525, + "step": 1295360 + }, + { + "epoch": 0.02, + "learning_rate": 2.8784289844552054e-05, + "loss": 3.516, + "step": 1295872 + }, + { + "epoch": 0.02, + "learning_rate": 2.8775903897041527e-05, + "loss": 3.5209, + "step": 1296384 + }, + { + "epoch": 0.02, + "learning_rate": 2.876751794953101e-05, + "loss": 3.5106, + "step": 1296896 + }, + { + "epoch": 0.02, + "learning_rate": 2.875913200202049e-05, + "loss": 3.5109, + "step": 1297408 + }, + { + "epoch": 0.03, + "eval_loss": 3.8458547592163086, + "eval_runtime": 329.3355, + "eval_samples_per_second": 1158.67, + "eval_steps_per_second": 36.209, + "step": 1297440 + }, + { + "epoch": 0.0, + "learning_rate": 2.875074605450997e-05, + "loss": 3.5067, + "step": 1297920 + }, + { + "epoch": 0.0, + "learning_rate": 2.874236010699945e-05, + "loss": 3.5189, + "step": 1298432 + }, + { + "epoch": 0.0, + "learning_rate": 2.873397415948893e-05, + "loss": 3.5251, + "step": 1298944 + }, + { + "epoch": 0.0, + "learning_rate": 2.872560459078214e-05, + "loss": 3.5158, + "step": 1299456 + }, + { + "epoch": 0.0, + "learning_rate": 2.871721864327162e-05, + "loss": 3.5196, + "step": 1299968 + }, + { + "epoch": 0.0, + "learning_rate": 2.8708832695761102e-05, + "loss": 3.5142, + "step": 1300480 + }, + { + "epoch": 0.0, + "learning_rate": 2.8700446748250582e-05, + "loss": 3.5116, + "step": 1300992 + }, + { + "epoch": 0.0, + "learning_rate": 2.8692060800740062e-05, + "loss": 3.5061, + "step": 1301504 + }, + { + "epoch": 0.0, + "learning_rate": 2.868369123203327e-05, + "loss": 3.529, + "step": 1302016 + }, + { + "epoch": 0.0, + "learning_rate": 2.867530528452275e-05, + "loss": 3.5147, + "step": 1302528 + }, + { + "epoch": 0.0, + "learning_rate": 2.866691933701223e-05, + "loss": 3.5253, + "step": 1303040 + }, + { + "epoch": 0.0, + "learning_rate": 2.865853338950171e-05, + "loss": 3.5236, + "step": 1303552 + }, + { + "epoch": 0.0, + "learning_rate": 2.8650163820794924e-05, + "loss": 3.5093, + "step": 1304064 + }, + { + "epoch": 0.0, + "learning_rate": 2.8641777873284404e-05, + "loss": 3.5065, + "step": 1304576 + }, + { + "epoch": 0.0, + "learning_rate": 2.8633391925773884e-05, + "loss": 3.5121, + "step": 1305088 + }, + { + "epoch": 0.0, + "learning_rate": 2.8625022357067093e-05, + "loss": 3.5065, + "step": 1305600 + }, + { + "epoch": 0.0, + "learning_rate": 2.8616636409556573e-05, + "loss": 3.5101, + "step": 1306112 + }, + { + "epoch": 0.0, + "learning_rate": 2.8608250462046056e-05, + "loss": 3.509, + "step": 1306624 + }, + { + "epoch": 0.0, + "learning_rate": 2.8599864514535536e-05, + "loss": 3.5041, + "step": 1307136 + }, + { + "epoch": 0.0, + "learning_rate": 2.8591494945828745e-05, + "loss": 3.53, + "step": 1307648 + }, + { + "epoch": 0.0, + "learning_rate": 2.8583108998318225e-05, + "loss": 3.5196, + "step": 1308160 + }, + { + "epoch": 0.0, + "learning_rate": 2.8574723050807705e-05, + "loss": 3.5108, + "step": 1308672 + }, + { + "epoch": 0.0, + "learning_rate": 2.8566337103297185e-05, + "loss": 3.5083, + "step": 1309184 + }, + { + "epoch": 0.0, + "learning_rate": 2.8557967534590397e-05, + "loss": 3.525, + "step": 1309696 + }, + { + "epoch": 0.0, + "learning_rate": 2.8549581587079877e-05, + "loss": 3.5006, + "step": 1310208 + }, + { + "epoch": 0.0, + "learning_rate": 2.8541195639569357e-05, + "loss": 3.5025, + "step": 1310720 + }, + { + "epoch": 0.0, + "learning_rate": 2.8532809692058837e-05, + "loss": 3.5102, + "step": 1311232 + }, + { + "epoch": 0.0, + "learning_rate": 2.8524440123352046e-05, + "loss": 3.5115, + "step": 1311744 + }, + { + "epoch": 0.0, + "learning_rate": 2.8516054175841526e-05, + "loss": 3.5048, + "step": 1312256 + }, + { + "epoch": 0.01, + "learning_rate": 2.850766822833101e-05, + "loss": 3.5066, + "step": 1312768 + }, + { + "epoch": 0.01, + "learning_rate": 2.849928228082049e-05, + "loss": 3.513, + "step": 1313280 + }, + { + "epoch": 0.01, + "learning_rate": 2.84909127121137e-05, + "loss": 3.5154, + "step": 1313792 + }, + { + "epoch": 0.01, + "learning_rate": 2.848252676460318e-05, + "loss": 3.5039, + "step": 1314304 + }, + { + "epoch": 0.01, + "learning_rate": 2.847414081709266e-05, + "loss": 3.5138, + "step": 1314816 + }, + { + "epoch": 0.01, + "learning_rate": 2.846575486958214e-05, + "loss": 3.5184, + "step": 1315328 + }, + { + "epoch": 0.01, + "learning_rate": 2.845738530087535e-05, + "loss": 3.5159, + "step": 1315840 + }, + { + "epoch": 0.01, + "learning_rate": 2.844899935336483e-05, + "loss": 3.4959, + "step": 1316352 + }, + { + "epoch": 0.01, + "learning_rate": 2.844061340585431e-05, + "loss": 3.5059, + "step": 1316864 + }, + { + "epoch": 0.01, + "learning_rate": 2.843222745834379e-05, + "loss": 3.5012, + "step": 1317376 + }, + { + "epoch": 0.01, + "learning_rate": 2.8423857889637e-05, + "loss": 3.509, + "step": 1317888 + }, + { + "epoch": 0.01, + "learning_rate": 2.841547194212648e-05, + "loss": 3.5032, + "step": 1318400 + }, + { + "epoch": 0.01, + "learning_rate": 2.8407085994615963e-05, + "loss": 3.5113, + "step": 1318912 + }, + { + "epoch": 0.01, + "learning_rate": 2.8398700047105443e-05, + "loss": 3.5042, + "step": 1319424 + }, + { + "epoch": 0.01, + "learning_rate": 2.8390330478398652e-05, + "loss": 3.5096, + "step": 1319936 + }, + { + "epoch": 0.01, + "learning_rate": 2.8381944530888132e-05, + "loss": 3.5151, + "step": 1320448 + }, + { + "epoch": 0.01, + "learning_rate": 2.8373558583377612e-05, + "loss": 3.5118, + "step": 1320960 + }, + { + "epoch": 0.01, + "learning_rate": 2.8365172635867092e-05, + "loss": 3.5094, + "step": 1321472 + }, + { + "epoch": 0.01, + "learning_rate": 2.8356803067160305e-05, + "loss": 3.4912, + "step": 1321984 + }, + { + "epoch": 0.01, + "learning_rate": 2.8348417119649785e-05, + "loss": 3.5114, + "step": 1322496 + }, + { + "epoch": 0.01, + "learning_rate": 2.8340031172139265e-05, + "loss": 3.5137, + "step": 1323008 + }, + { + "epoch": 0.01, + "learning_rate": 2.8331645224628745e-05, + "loss": 3.5088, + "step": 1323520 + }, + { + "epoch": 0.01, + "learning_rate": 2.8323275655921954e-05, + "loss": 3.5024, + "step": 1324032 + }, + { + "epoch": 0.01, + "learning_rate": 2.8314889708411434e-05, + "loss": 3.4983, + "step": 1324544 + }, + { + "epoch": 0.01, + "learning_rate": 2.8306503760900917e-05, + "loss": 3.5071, + "step": 1325056 + }, + { + "epoch": 0.01, + "learning_rate": 2.8298117813390397e-05, + "loss": 3.4884, + "step": 1325568 + }, + { + "epoch": 0.01, + "learning_rate": 2.8289748244683606e-05, + "loss": 3.5194, + "step": 1326080 + }, + { + "epoch": 0.01, + "learning_rate": 2.8281362297173086e-05, + "loss": 3.5059, + "step": 1326592 + }, + { + "epoch": 0.01, + "learning_rate": 2.8272976349662566e-05, + "loss": 3.5178, + "step": 1327104 + }, + { + "epoch": 0.01, + "learning_rate": 2.8264590402152046e-05, + "loss": 3.5141, + "step": 1327616 + }, + { + "epoch": 0.01, + "learning_rate": 2.825622083344526e-05, + "loss": 3.4936, + "step": 1328128 + }, + { + "epoch": 0.01, + "learning_rate": 2.824783488593474e-05, + "loss": 3.51, + "step": 1328640 + }, + { + "epoch": 0.01, + "learning_rate": 2.8239448938424218e-05, + "loss": 3.5057, + "step": 1329152 + }, + { + "epoch": 0.01, + "learning_rate": 2.8231062990913698e-05, + "loss": 3.4948, + "step": 1329664 + }, + { + "epoch": 0.01, + "learning_rate": 2.8222677043403178e-05, + "loss": 3.4928, + "step": 1330176 + }, + { + "epoch": 0.01, + "learning_rate": 2.8214307474696387e-05, + "loss": 3.5108, + "step": 1330688 + }, + { + "epoch": 0.01, + "learning_rate": 2.820592152718587e-05, + "loss": 3.5029, + "step": 1331200 + }, + { + "epoch": 0.01, + "learning_rate": 2.819753557967535e-05, + "loss": 3.4971, + "step": 1331712 + }, + { + "epoch": 0.01, + "learning_rate": 2.818914963216483e-05, + "loss": 3.4941, + "step": 1332224 + }, + { + "epoch": 0.01, + "learning_rate": 2.818078006345804e-05, + "loss": 3.513, + "step": 1332736 + }, + { + "epoch": 0.01, + "learning_rate": 2.817239411594752e-05, + "loss": 3.5092, + "step": 1333248 + }, + { + "epoch": 0.01, + "learning_rate": 2.8164008168437e-05, + "loss": 3.5075, + "step": 1333760 + }, + { + "epoch": 0.01, + "learning_rate": 2.8155638599730212e-05, + "loss": 3.5076, + "step": 1334272 + }, + { + "epoch": 0.01, + "learning_rate": 2.8147252652219692e-05, + "loss": 3.519, + "step": 1334784 + }, + { + "epoch": 0.01, + "learning_rate": 2.8138866704709172e-05, + "loss": 3.5111, + "step": 1335296 + }, + { + "epoch": 0.01, + "learning_rate": 2.8130480757198652e-05, + "loss": 3.5166, + "step": 1335808 + }, + { + "epoch": 0.01, + "learning_rate": 2.812211118849186e-05, + "loss": 3.4975, + "step": 1336320 + }, + { + "epoch": 0.01, + "learning_rate": 2.811372524098134e-05, + "loss": 3.5151, + "step": 1336832 + }, + { + "epoch": 0.01, + "learning_rate": 2.810533929347082e-05, + "loss": 3.5073, + "step": 1337344 + }, + { + "epoch": 0.01, + "learning_rate": 2.8096953345960304e-05, + "loss": 3.5072, + "step": 1337856 + }, + { + "epoch": 0.01, + "learning_rate": 2.8088583777253513e-05, + "loss": 3.509, + "step": 1338368 + }, + { + "epoch": 0.01, + "learning_rate": 2.8080197829742993e-05, + "loss": 3.5082, + "step": 1338880 + }, + { + "epoch": 0.01, + "learning_rate": 2.8071811882232473e-05, + "loss": 3.5196, + "step": 1339392 + }, + { + "epoch": 0.01, + "learning_rate": 2.8063425934721953e-05, + "loss": 3.5095, + "step": 1339904 + }, + { + "epoch": 0.01, + "learning_rate": 2.8055056366015166e-05, + "loss": 3.4902, + "step": 1340416 + }, + { + "epoch": 0.01, + "learning_rate": 2.8046670418504646e-05, + "loss": 3.4949, + "step": 1340928 + }, + { + "epoch": 0.01, + "learning_rate": 2.8038284470994126e-05, + "loss": 3.5092, + "step": 1341440 + }, + { + "epoch": 0.01, + "learning_rate": 2.80298985234836e-05, + "loss": 3.5094, + "step": 1341952 + }, + { + "epoch": 0.01, + "learning_rate": 2.8021528954776815e-05, + "loss": 3.5105, + "step": 1342464 + }, + { + "epoch": 0.01, + "learning_rate": 2.8013143007266295e-05, + "loss": 3.5084, + "step": 1342976 + }, + { + "epoch": 0.02, + "learning_rate": 2.8004757059755775e-05, + "loss": 3.5031, + "step": 1343488 + }, + { + "epoch": 0.02, + "learning_rate": 2.799637111224525e-05, + "loss": 3.497, + "step": 1344000 + }, + { + "epoch": 0.02, + "learning_rate": 2.7988001543538467e-05, + "loss": 3.5054, + "step": 1344512 + }, + { + "epoch": 0.02, + "learning_rate": 2.7979615596027947e-05, + "loss": 3.5071, + "step": 1345024 + }, + { + "epoch": 0.02, + "learning_rate": 2.7971229648517427e-05, + "loss": 3.5067, + "step": 1345536 + }, + { + "epoch": 0.02, + "learning_rate": 2.7962843701006904e-05, + "loss": 3.5124, + "step": 1346048 + }, + { + "epoch": 0.02, + "learning_rate": 2.795447413230012e-05, + "loss": 3.5069, + "step": 1346560 + }, + { + "epoch": 0.02, + "learning_rate": 2.79460881847896e-05, + "loss": 3.5015, + "step": 1347072 + }, + { + "epoch": 0.02, + "learning_rate": 2.7937702237279073e-05, + "loss": 3.5067, + "step": 1347584 + }, + { + "epoch": 0.02, + "learning_rate": 2.7929316289768552e-05, + "loss": 3.5054, + "step": 1348096 + }, + { + "epoch": 0.02, + "learning_rate": 2.792094672106177e-05, + "loss": 3.5083, + "step": 1348608 + }, + { + "epoch": 0.02, + "learning_rate": 2.791256077355125e-05, + "loss": 3.5028, + "step": 1349120 + }, + { + "epoch": 0.02, + "learning_rate": 2.7904174826040725e-05, + "loss": 3.4989, + "step": 1349632 + }, + { + "epoch": 0.02, + "learning_rate": 2.7895788878530205e-05, + "loss": 3.4993, + "step": 1350144 + }, + { + "epoch": 0.02, + "learning_rate": 2.788741930982342e-05, + "loss": 3.5119, + "step": 1350656 + }, + { + "epoch": 0.02, + "learning_rate": 2.78790333623129e-05, + "loss": 3.4972, + "step": 1351168 + }, + { + "epoch": 0.02, + "learning_rate": 2.7870647414802374e-05, + "loss": 3.4877, + "step": 1351680 + }, + { + "epoch": 0.02, + "learning_rate": 2.7862261467291857e-05, + "loss": 3.5031, + "step": 1352192 + }, + { + "epoch": 0.02, + "learning_rate": 2.7853891898585073e-05, + "loss": 3.5063, + "step": 1352704 + }, + { + "epoch": 0.02, + "learning_rate": 2.7845505951074546e-05, + "loss": 3.498, + "step": 1353216 + }, + { + "epoch": 0.02, + "learning_rate": 2.7837120003564026e-05, + "loss": 3.5065, + "step": 1353728 + }, + { + "epoch": 0.02, + "learning_rate": 2.7828734056053506e-05, + "loss": 3.496, + "step": 1354240 + }, + { + "epoch": 0.02, + "learning_rate": 2.7820364487346722e-05, + "loss": 3.5066, + "step": 1354752 + }, + { + "epoch": 0.02, + "learning_rate": 2.78119785398362e-05, + "loss": 3.4937, + "step": 1355264 + }, + { + "epoch": 0.02, + "learning_rate": 2.780359259232568e-05, + "loss": 3.5026, + "step": 1355776 + }, + { + "epoch": 0.02, + "learning_rate": 2.779520664481516e-05, + "loss": 3.5125, + "step": 1356288 + }, + { + "epoch": 0.02, + "learning_rate": 2.778682069730464e-05, + "loss": 3.5133, + "step": 1356800 + }, + { + "epoch": 0.02, + "learning_rate": 2.7778451128597848e-05, + "loss": 3.4985, + "step": 1357312 + }, + { + "epoch": 0.02, + "learning_rate": 2.7770065181087328e-05, + "loss": 3.5012, + "step": 1357824 + }, + { + "epoch": 0.02, + "learning_rate": 2.776167923357681e-05, + "loss": 3.5048, + "step": 1358336 + }, + { + "epoch": 0.02, + "learning_rate": 2.775329328606629e-05, + "loss": 3.5058, + "step": 1358848 + }, + { + "epoch": 0.02, + "learning_rate": 2.77449237173595e-05, + "loss": 3.4911, + "step": 1359360 + }, + { + "epoch": 0.02, + "learning_rate": 2.773653776984898e-05, + "loss": 3.507, + "step": 1359872 + }, + { + "epoch": 0.02, + "learning_rate": 2.772815182233846e-05, + "loss": 3.4984, + "step": 1360384 + }, + { + "epoch": 0.02, + "learning_rate": 2.7719782253631672e-05, + "loss": 3.5112, + "step": 1360896 + }, + { + "epoch": 0.02, + "learning_rate": 2.7711396306121152e-05, + "loss": 3.4953, + "step": 1361408 + }, + { + "epoch": 0.02, + "learning_rate": 2.7703010358610632e-05, + "loss": 3.4993, + "step": 1361920 + }, + { + "epoch": 0.02, + "learning_rate": 2.7694624411100112e-05, + "loss": 3.4988, + "step": 1362432 + }, + { + "epoch": 0.02, + "learning_rate": 2.768625484239332e-05, + "loss": 3.5035, + "step": 1362944 + }, + { + "epoch": 0.02, + "learning_rate": 2.76778688948828e-05, + "loss": 3.4985, + "step": 1363456 + }, + { + "epoch": 0.02, + "learning_rate": 2.766948294737228e-05, + "loss": 3.5175, + "step": 1363968 + }, + { + "epoch": 0.02, + "learning_rate": 2.7661096999861765e-05, + "loss": 3.5095, + "step": 1364480 + }, + { + "epoch": 0.02, + "learning_rate": 2.7652711052351244e-05, + "loss": 3.4974, + "step": 1364992 + }, + { + "epoch": 0.02, + "learning_rate": 2.7644341483644454e-05, + "loss": 3.4974, + "step": 1365504 + }, + { + "epoch": 0.02, + "learning_rate": 2.7635955536133934e-05, + "loss": 3.5099, + "step": 1366016 + }, + { + "epoch": 0.02, + "learning_rate": 2.7627569588623413e-05, + "loss": 3.5092, + "step": 1366528 + }, + { + "epoch": 0.02, + "learning_rate": 2.7619183641112893e-05, + "loss": 3.5012, + "step": 1367040 + }, + { + "epoch": 0.02, + "learning_rate": 2.7610814072406106e-05, + "loss": 3.4977, + "step": 1367552 + }, + { + "epoch": 0.02, + "learning_rate": 2.7602428124895586e-05, + "loss": 3.5126, + "step": 1368064 + }, + { + "epoch": 0.02, + "learning_rate": 2.7594042177385066e-05, + "loss": 3.5111, + "step": 1368576 + }, + { + "epoch": 0.02, + "learning_rate": 2.7585672608678275e-05, + "loss": 3.5015, + "step": 1369088 + }, + { + "epoch": 0.02, + "learning_rate": 2.7577286661167755e-05, + "loss": 3.5014, + "step": 1369600 + }, + { + "epoch": 0.02, + "learning_rate": 2.7568900713657235e-05, + "loss": 3.501, + "step": 1370112 + }, + { + "epoch": 0.02, + "learning_rate": 2.7560514766146718e-05, + "loss": 3.4999, + "step": 1370624 + }, + { + "epoch": 0.02, + "learning_rate": 2.7552145197439927e-05, + "loss": 3.4974, + "step": 1371136 + }, + { + "epoch": 0.02, + "learning_rate": 2.7543759249929407e-05, + "loss": 3.5146, + "step": 1371648 + }, + { + "epoch": 0.02, + "learning_rate": 2.7535373302418887e-05, + "loss": 3.5031, + "step": 1372160 + }, + { + "epoch": 0.02, + "learning_rate": 2.7526987354908367e-05, + "loss": 3.5057, + "step": 1372672 + }, + { + "epoch": 0.02, + "learning_rate": 2.751861778620158e-05, + "loss": 3.4991, + "step": 1373184 + }, + { + "epoch": 0.02, + "learning_rate": 2.751023183869106e-05, + "loss": 3.4986, + "step": 1373696 + }, + { + "epoch": 0.03, + "eval_loss": 3.8483388423919678, + "eval_runtime": 306.3583, + "eval_samples_per_second": 1245.571, + "eval_steps_per_second": 38.925, + "step": 1373760 + }, + { + "epoch": 1.0, + "learning_rate": 2.750184589118054e-05, + "loss": 3.4962, + "step": 1374208 + }, + { + "epoch": 1.0, + "learning_rate": 2.749345994367002e-05, + "loss": 3.5062, + "step": 1374720 + }, + { + "epoch": 1.0, + "learning_rate": 2.748509037496323e-05, + "loss": 3.5142, + "step": 1375232 + }, + { + "epoch": 1.0, + "learning_rate": 2.747670442745271e-05, + "loss": 3.5026, + "step": 1375744 + }, + { + "epoch": 1.0, + "learning_rate": 2.746831847994219e-05, + "loss": 3.5079, + "step": 1376256 + }, + { + "epoch": 1.0, + "learning_rate": 2.7459932532431672e-05, + "loss": 3.5003, + "step": 1376768 + }, + { + "epoch": 1.0, + "learning_rate": 2.745156296372488e-05, + "loss": 3.5008, + "step": 1377280 + }, + { + "epoch": 1.0, + "learning_rate": 2.744317701621436e-05, + "loss": 3.4909, + "step": 1377792 + }, + { + "epoch": 1.0, + "learning_rate": 2.743479106870384e-05, + "loss": 3.5116, + "step": 1378304 + }, + { + "epoch": 1.0, + "learning_rate": 2.742640512119332e-05, + "loss": 3.5086, + "step": 1378816 + }, + { + "epoch": 1.0, + "learning_rate": 2.7418035552486533e-05, + "loss": 3.5032, + "step": 1379328 + }, + { + "epoch": 1.0, + "learning_rate": 2.7409649604976013e-05, + "loss": 3.5102, + "step": 1379840 + }, + { + "epoch": 1.0, + "learning_rate": 2.7401280036269222e-05, + "loss": 3.4971, + "step": 1380352 + }, + { + "epoch": 1.0, + "learning_rate": 2.7392894088758702e-05, + "loss": 3.4923, + "step": 1380864 + }, + { + "epoch": 1.0, + "learning_rate": 2.7384508141248182e-05, + "loss": 3.5055, + "step": 1381376 + }, + { + "epoch": 1.0, + "learning_rate": 2.7376122193737662e-05, + "loss": 3.4906, + "step": 1381888 + }, + { + "epoch": 1.0, + "learning_rate": 2.7367736246227142e-05, + "loss": 3.4948, + "step": 1382400 + }, + { + "epoch": 1.0, + "learning_rate": 2.7359350298716626e-05, + "loss": 3.4952, + "step": 1382912 + }, + { + "epoch": 1.0, + "learning_rate": 2.7350964351206105e-05, + "loss": 3.4933, + "step": 1383424 + }, + { + "epoch": 1.0, + "learning_rate": 2.7342594782499315e-05, + "loss": 3.5175, + "step": 1383936 + }, + { + "epoch": 1.0, + "learning_rate": 2.7334208834988795e-05, + "loss": 3.5032, + "step": 1384448 + }, + { + "epoch": 1.0, + "learning_rate": 2.7325822887478274e-05, + "loss": 3.5018, + "step": 1384960 + }, + { + "epoch": 1.0, + "learning_rate": 2.7317436939967754e-05, + "loss": 3.4936, + "step": 1385472 + }, + { + "epoch": 1.0, + "learning_rate": 2.7309050992457234e-05, + "loss": 3.5102, + "step": 1385984 + }, + { + "epoch": 1.0, + "learning_rate": 2.7300681423750447e-05, + "loss": 3.4854, + "step": 1386496 + }, + { + "epoch": 1.0, + "learning_rate": 2.7292295476239927e-05, + "loss": 3.4922, + "step": 1387008 + }, + { + "epoch": 1.0, + "learning_rate": 2.7283909528729407e-05, + "loss": 3.4943, + "step": 1387520 + }, + { + "epoch": 1.0, + "learning_rate": 2.7275523581218887e-05, + "loss": 3.5019, + "step": 1388032 + }, + { + "epoch": 1.0, + "learning_rate": 2.7267154012512096e-05, + "loss": 3.4925, + "step": 1388544 + }, + { + "epoch": 1.01, + "learning_rate": 2.725876806500158e-05, + "loss": 3.4916, + "step": 1389056 + }, + { + "epoch": 1.01, + "learning_rate": 2.725038211749106e-05, + "loss": 3.5023, + "step": 1389568 + }, + { + "epoch": 1.01, + "learning_rate": 2.724199616998054e-05, + "loss": 3.5033, + "step": 1390080 + }, + { + "epoch": 1.01, + "learning_rate": 2.7233626601273748e-05, + "loss": 3.486, + "step": 1390592 + }, + { + "epoch": 1.01, + "learning_rate": 2.7225240653763228e-05, + "loss": 3.5015, + "step": 1391104 + }, + { + "epoch": 1.01, + "learning_rate": 2.7216854706252708e-05, + "loss": 3.5023, + "step": 1391616 + }, + { + "epoch": 1.01, + "learning_rate": 2.7208468758742188e-05, + "loss": 3.5015, + "step": 1392128 + }, + { + "epoch": 1.01, + "learning_rate": 2.72000991900354e-05, + "loss": 3.4834, + "step": 1392640 + }, + { + "epoch": 1.01, + "learning_rate": 2.719171324252488e-05, + "loss": 3.4936, + "step": 1393152 + }, + { + "epoch": 1.01, + "learning_rate": 2.718332729501436e-05, + "loss": 3.4823, + "step": 1393664 + }, + { + "epoch": 1.01, + "learning_rate": 2.717494134750384e-05, + "loss": 3.4976, + "step": 1394176 + }, + { + "epoch": 1.01, + "learning_rate": 2.716657177879705e-05, + "loss": 3.4918, + "step": 1394688 + }, + { + "epoch": 1.01, + "learning_rate": 2.715818583128653e-05, + "loss": 3.501, + "step": 1395200 + }, + { + "epoch": 1.01, + "learning_rate": 2.7149799883776013e-05, + "loss": 3.4934, + "step": 1395712 + }, + { + "epoch": 1.01, + "learning_rate": 2.7141413936265493e-05, + "loss": 3.4931, + "step": 1396224 + }, + { + "epoch": 1.01, + "learning_rate": 2.7133044367558702e-05, + "loss": 3.503, + "step": 1396736 + }, + { + "epoch": 1.01, + "learning_rate": 2.7124658420048182e-05, + "loss": 3.5029, + "step": 1397248 + }, + { + "epoch": 1.01, + "learning_rate": 2.7116272472537662e-05, + "loss": 3.4982, + "step": 1397760 + }, + { + "epoch": 1.01, + "learning_rate": 2.7107886525027142e-05, + "loss": 3.4769, + "step": 1398272 + }, + { + "epoch": 1.01, + "learning_rate": 2.7099516956320354e-05, + "loss": 3.4935, + "step": 1398784 + }, + { + "epoch": 1.01, + "learning_rate": 2.7091131008809834e-05, + "loss": 3.5023, + "step": 1399296 + }, + { + "epoch": 1.01, + "learning_rate": 2.7082745061299314e-05, + "loss": 3.4931, + "step": 1399808 + }, + { + "epoch": 1.01, + "learning_rate": 2.7074359113788794e-05, + "loss": 3.4915, + "step": 1400320 + }, + { + "epoch": 1.01, + "learning_rate": 2.7065989545082003e-05, + "loss": 3.4872, + "step": 1400832 + }, + { + "epoch": 1.01, + "learning_rate": 2.7057603597571483e-05, + "loss": 3.4921, + "step": 1401344 + }, + { + "epoch": 1.01, + "learning_rate": 2.7049217650060966e-05, + "loss": 3.4789, + "step": 1401856 + }, + { + "epoch": 1.01, + "learning_rate": 2.7040831702550446e-05, + "loss": 3.5013, + "step": 1402368 + }, + { + "epoch": 1.01, + "learning_rate": 2.7032462133843656e-05, + "loss": 3.4951, + "step": 1402880 + }, + { + "epoch": 1.01, + "learning_rate": 2.7024076186333135e-05, + "loss": 3.5015, + "step": 1403392 + }, + { + "epoch": 1.01, + "learning_rate": 2.7015690238822615e-05, + "loss": 3.5068, + "step": 1403904 + }, + { + "epoch": 1.01, + "learning_rate": 2.7007304291312095e-05, + "loss": 3.4801, + "step": 1404416 + }, + { + "epoch": 1.01, + "learning_rate": 2.6998934722605308e-05, + "loss": 3.4968, + "step": 1404928 + }, + { + "epoch": 1.01, + "learning_rate": 2.6990548775094788e-05, + "loss": 3.4912, + "step": 1405440 + }, + { + "epoch": 1.01, + "learning_rate": 2.6982162827584268e-05, + "loss": 3.4858, + "step": 1405952 + }, + { + "epoch": 1.01, + "learning_rate": 2.6973776880073748e-05, + "loss": 3.4789, + "step": 1406464 + }, + { + "epoch": 1.01, + "learning_rate": 2.6965407311366957e-05, + "loss": 3.4956, + "step": 1406976 + }, + { + "epoch": 1.01, + "learning_rate": 2.6957021363856437e-05, + "loss": 3.4925, + "step": 1407488 + }, + { + "epoch": 1.01, + "learning_rate": 2.694863541634592e-05, + "loss": 3.4858, + "step": 1408000 + }, + { + "epoch": 1.01, + "learning_rate": 2.69402494688354e-05, + "loss": 3.4775, + "step": 1408512 + }, + { + "epoch": 1.01, + "learning_rate": 2.693187990012861e-05, + "loss": 3.4979, + "step": 1409024 + }, + { + "epoch": 1.01, + "learning_rate": 2.692349395261809e-05, + "loss": 3.5006, + "step": 1409536 + }, + { + "epoch": 1.01, + "learning_rate": 2.691510800510757e-05, + "loss": 3.4926, + "step": 1410048 + }, + { + "epoch": 1.01, + "learning_rate": 2.6906722057597046e-05, + "loss": 3.4945, + "step": 1410560 + }, + { + "epoch": 1.01, + "learning_rate": 2.689835248889026e-05, + "loss": 3.508, + "step": 1411072 + }, + { + "epoch": 1.01, + "learning_rate": 2.688996654137974e-05, + "loss": 3.4989, + "step": 1411584 + }, + { + "epoch": 1.01, + "learning_rate": 2.688158059386922e-05, + "loss": 3.504, + "step": 1412096 + }, + { + "epoch": 1.01, + "learning_rate": 2.6873194646358695e-05, + "loss": 3.4822, + "step": 1412608 + }, + { + "epoch": 1.01, + "learning_rate": 2.686482507765191e-05, + "loss": 3.501, + "step": 1413120 + }, + { + "epoch": 1.01, + "learning_rate": 2.685643913014139e-05, + "loss": 3.4983, + "step": 1413632 + }, + { + "epoch": 1.01, + "learning_rate": 2.6848053182630874e-05, + "loss": 3.4912, + "step": 1414144 + }, + { + "epoch": 1.01, + "learning_rate": 2.6839667235120347e-05, + "loss": 3.4999, + "step": 1414656 + }, + { + "epoch": 1.01, + "learning_rate": 2.6831297666413563e-05, + "loss": 3.4958, + "step": 1415168 + }, + { + "epoch": 1.01, + "learning_rate": 2.6822911718903043e-05, + "loss": 3.5058, + "step": 1415680 + }, + { + "epoch": 1.01, + "learning_rate": 2.681452577139252e-05, + "loss": 3.4952, + "step": 1416192 + }, + { + "epoch": 1.01, + "learning_rate": 2.6806139823882e-05, + "loss": 3.4765, + "step": 1416704 + }, + { + "epoch": 1.01, + "learning_rate": 2.6797770255175215e-05, + "loss": 3.4826, + "step": 1417216 + }, + { + "epoch": 1.01, + "learning_rate": 2.6789384307664695e-05, + "loss": 3.4928, + "step": 1417728 + }, + { + "epoch": 1.01, + "learning_rate": 2.678099836015417e-05, + "loss": 3.4977, + "step": 1418240 + }, + { + "epoch": 1.01, + "learning_rate": 2.6772612412643648e-05, + "loss": 3.498, + "step": 1418752 + }, + { + "epoch": 1.01, + "learning_rate": 2.6764242843936864e-05, + "loss": 3.4918, + "step": 1419264 + }, + { + "epoch": 1.02, + "learning_rate": 2.675585689642634e-05, + "loss": 3.4906, + "step": 1419776 + }, + { + "epoch": 1.02, + "learning_rate": 2.674747094891582e-05, + "loss": 3.4848, + "step": 1420288 + }, + { + "epoch": 1.02, + "learning_rate": 2.67390850014053e-05, + "loss": 3.4932, + "step": 1420800 + }, + { + "epoch": 1.02, + "learning_rate": 2.6730715432698517e-05, + "loss": 3.4881, + "step": 1421312 + }, + { + "epoch": 1.02, + "learning_rate": 2.672232948518799e-05, + "loss": 3.4965, + "step": 1421824 + }, + { + "epoch": 1.02, + "learning_rate": 2.6713943537677473e-05, + "loss": 3.5016, + "step": 1422336 + }, + { + "epoch": 1.02, + "learning_rate": 2.6705557590166953e-05, + "loss": 3.4964, + "step": 1422848 + }, + { + "epoch": 1.02, + "learning_rate": 2.669718802146017e-05, + "loss": 3.4887, + "step": 1423360 + }, + { + "epoch": 1.02, + "learning_rate": 2.6688802073949642e-05, + "loss": 3.496, + "step": 1423872 + }, + { + "epoch": 1.02, + "learning_rate": 2.6680416126439122e-05, + "loss": 3.4915, + "step": 1424384 + }, + { + "epoch": 1.02, + "learning_rate": 2.6672030178928602e-05, + "loss": 3.4942, + "step": 1424896 + }, + { + "epoch": 1.02, + "learning_rate": 2.6663660610221814e-05, + "loss": 3.4921, + "step": 1425408 + }, + { + "epoch": 1.02, + "learning_rate": 2.6655274662711294e-05, + "loss": 3.4886, + "step": 1425920 + }, + { + "epoch": 1.02, + "learning_rate": 2.6646888715200774e-05, + "loss": 3.4832, + "step": 1426432 + }, + { + "epoch": 1.02, + "learning_rate": 2.6638502767690254e-05, + "loss": 3.4973, + "step": 1426944 + }, + { + "epoch": 1.02, + "learning_rate": 2.6630133198983463e-05, + "loss": 3.4862, + "step": 1427456 + }, + { + "epoch": 1.02, + "learning_rate": 2.6621747251472943e-05, + "loss": 3.4774, + "step": 1427968 + }, + { + "epoch": 1.02, + "learning_rate": 2.6613361303962427e-05, + "loss": 3.4856, + "step": 1428480 + }, + { + "epoch": 1.02, + "learning_rate": 2.6604975356451907e-05, + "loss": 3.4945, + "step": 1428992 + }, + { + "epoch": 1.02, + "learning_rate": 2.6596605787745116e-05, + "loss": 3.484, + "step": 1429504 + }, + { + "epoch": 1.02, + "learning_rate": 2.6588219840234596e-05, + "loss": 3.4984, + "step": 1430016 + }, + { + "epoch": 1.02, + "learning_rate": 2.6579833892724076e-05, + "loss": 3.482, + "step": 1430528 + }, + { + "epoch": 1.02, + "learning_rate": 2.6571447945213556e-05, + "loss": 3.4971, + "step": 1431040 + }, + { + "epoch": 1.02, + "learning_rate": 2.6563078376506768e-05, + "loss": 3.4838, + "step": 1431552 + }, + { + "epoch": 1.02, + "learning_rate": 2.6554692428996248e-05, + "loss": 3.4867, + "step": 1432064 + }, + { + "epoch": 1.02, + "learning_rate": 2.6546306481485728e-05, + "loss": 3.5034, + "step": 1432576 + }, + { + "epoch": 1.02, + "learning_rate": 2.6537920533975208e-05, + "loss": 3.5012, + "step": 1433088 + }, + { + "epoch": 1.02, + "learning_rate": 2.6529550965268417e-05, + "loss": 3.4868, + "step": 1433600 + }, + { + "epoch": 1.02, + "learning_rate": 2.6521165017757897e-05, + "loss": 3.4904, + "step": 1434112 + }, + { + "epoch": 1.02, + "learning_rate": 2.651277907024738e-05, + "loss": 3.4901, + "step": 1434624 + }, + { + "epoch": 1.02, + "learning_rate": 2.650439312273686e-05, + "loss": 3.492, + "step": 1435136 + }, + { + "epoch": 1.02, + "learning_rate": 2.649602355403007e-05, + "loss": 3.4834, + "step": 1435648 + }, + { + "epoch": 1.02, + "learning_rate": 2.648763760651955e-05, + "loss": 3.4946, + "step": 1436160 + }, + { + "epoch": 1.02, + "learning_rate": 2.647925165900903e-05, + "loss": 3.4878, + "step": 1436672 + }, + { + "epoch": 1.02, + "learning_rate": 2.647086571149851e-05, + "loss": 3.4955, + "step": 1437184 + }, + { + "epoch": 1.02, + "learning_rate": 2.6462496142791722e-05, + "loss": 3.4793, + "step": 1437696 + }, + { + "epoch": 1.02, + "learning_rate": 2.6454110195281202e-05, + "loss": 3.4917, + "step": 1438208 + }, + { + "epoch": 1.02, + "learning_rate": 2.6445724247770682e-05, + "loss": 3.4846, + "step": 1438720 + }, + { + "epoch": 1.02, + "learning_rate": 2.643733830026016e-05, + "loss": 3.489, + "step": 1439232 + }, + { + "epoch": 1.02, + "learning_rate": 2.642896873155337e-05, + "loss": 3.4856, + "step": 1439744 + }, + { + "epoch": 1.02, + "learning_rate": 2.642058278404285e-05, + "loss": 3.5055, + "step": 1440256 + }, + { + "epoch": 1.02, + "learning_rate": 2.6412196836532334e-05, + "loss": 3.4952, + "step": 1440768 + }, + { + "epoch": 1.02, + "learning_rate": 2.6403810889021814e-05, + "loss": 3.4892, + "step": 1441280 + }, + { + "epoch": 1.02, + "learning_rate": 2.6395441320315023e-05, + "loss": 3.4799, + "step": 1441792 + }, + { + "epoch": 1.02, + "learning_rate": 2.6387055372804503e-05, + "loss": 3.4975, + "step": 1442304 + }, + { + "epoch": 1.02, + "learning_rate": 2.6378669425293983e-05, + "loss": 3.4963, + "step": 1442816 + }, + { + "epoch": 1.02, + "learning_rate": 2.6370283477783463e-05, + "loss": 3.4909, + "step": 1443328 + }, + { + "epoch": 1.02, + "learning_rate": 2.6361913909076675e-05, + "loss": 3.4847, + "step": 1443840 + }, + { + "epoch": 1.02, + "learning_rate": 2.6353527961566155e-05, + "loss": 3.4973, + "step": 1444352 + }, + { + "epoch": 1.02, + "learning_rate": 2.6345142014055635e-05, + "loss": 3.4979, + "step": 1444864 + }, + { + "epoch": 1.02, + "learning_rate": 2.6336756066545115e-05, + "loss": 3.4891, + "step": 1445376 + }, + { + "epoch": 1.02, + "learning_rate": 2.6328386497838324e-05, + "loss": 3.4893, + "step": 1445888 + }, + { + "epoch": 1.02, + "learning_rate": 2.6320000550327804e-05, + "loss": 3.4901, + "step": 1446400 + }, + { + "epoch": 1.02, + "learning_rate": 2.6311614602817288e-05, + "loss": 3.4891, + "step": 1446912 + }, + { + "epoch": 1.02, + "learning_rate": 2.6303228655306768e-05, + "loss": 3.4817, + "step": 1447424 + }, + { + "epoch": 1.02, + "learning_rate": 2.6294859086599977e-05, + "loss": 3.4958, + "step": 1447936 + }, + { + "epoch": 1.02, + "learning_rate": 2.6286473139089457e-05, + "loss": 3.4956, + "step": 1448448 + }, + { + "epoch": 1.02, + "learning_rate": 2.6278087191578937e-05, + "loss": 3.4915, + "step": 1448960 + }, + { + "epoch": 1.02, + "learning_rate": 2.6269701244068417e-05, + "loss": 3.4837, + "step": 1449472 + }, + { + "epoch": 1.02, + "learning_rate": 2.626133167536163e-05, + "loss": 3.4819, + "step": 1449984 + }, + { + "epoch": 1.03, + "eval_loss": 3.849757194519043, + "eval_runtime": 318.5676, + "eval_samples_per_second": 1197.834, + "eval_steps_per_second": 37.433, + "step": 1450080 + }, + { + "epoch": 0.0, + "learning_rate": 2.625294572785111e-05, + "loss": 3.4811, + "step": 1450496 + }, + { + "epoch": 0.0, + "learning_rate": 2.624455978034059e-05, + "loss": 3.4916, + "step": 1451008 + }, + { + "epoch": 0.0, + "learning_rate": 2.623617383283007e-05, + "loss": 3.5002, + "step": 1451520 + }, + { + "epoch": 0.0, + "learning_rate": 2.622778788531955e-05, + "loss": 3.4906, + "step": 1452032 + }, + { + "epoch": 0.0, + "learning_rate": 2.6219418316612758e-05, + "loss": 3.4959, + "step": 1452544 + }, + { + "epoch": 0.0, + "learning_rate": 2.621103236910224e-05, + "loss": 3.4845, + "step": 1453056 + }, + { + "epoch": 0.0, + "learning_rate": 2.620264642159172e-05, + "loss": 3.4878, + "step": 1453568 + }, + { + "epoch": 0.0, + "learning_rate": 2.61942604740812e-05, + "loss": 3.4793, + "step": 1454080 + }, + { + "epoch": 0.0, + "learning_rate": 2.618589090537441e-05, + "loss": 3.4997, + "step": 1454592 + }, + { + "epoch": 0.0, + "learning_rate": 2.617750495786389e-05, + "loss": 3.4952, + "step": 1455104 + }, + { + "epoch": 0.0, + "learning_rate": 2.616911901035337e-05, + "loss": 3.4925, + "step": 1455616 + }, + { + "epoch": 0.0, + "learning_rate": 2.616073306284285e-05, + "loss": 3.4957, + "step": 1456128 + }, + { + "epoch": 0.0, + "learning_rate": 2.6152379872939792e-05, + "loss": 3.4826, + "step": 1456640 + }, + { + "epoch": 0.0, + "learning_rate": 2.6143993925429272e-05, + "loss": 3.4809, + "step": 1457152 + }, + { + "epoch": 0.0, + "learning_rate": 2.6135607977918752e-05, + "loss": 3.4937, + "step": 1457664 + }, + { + "epoch": 0.0, + "learning_rate": 2.6127222030408232e-05, + "loss": 3.481, + "step": 1458176 + }, + { + "epoch": 0.0, + "learning_rate": 2.6118836082897712e-05, + "loss": 3.4808, + "step": 1458688 + }, + { + "epoch": 0.0, + "learning_rate": 2.611045013538719e-05, + "loss": 3.4814, + "step": 1459200 + }, + { + "epoch": 0.0, + "learning_rate": 2.6102064187876675e-05, + "loss": 3.4817, + "step": 1459712 + }, + { + "epoch": 0.0, + "learning_rate": 2.6093678240366155e-05, + "loss": 3.5078, + "step": 1460224 + }, + { + "epoch": 0.0, + "learning_rate": 2.6085308671659364e-05, + "loss": 3.4922, + "step": 1460736 + }, + { + "epoch": 0.0, + "learning_rate": 2.6076922724148844e-05, + "loss": 3.4886, + "step": 1461248 + }, + { + "epoch": 0.0, + "learning_rate": 2.6068536776638324e-05, + "loss": 3.4848, + "step": 1461760 + }, + { + "epoch": 0.0, + "learning_rate": 2.6060150829127804e-05, + "loss": 3.4922, + "step": 1462272 + }, + { + "epoch": 0.0, + "learning_rate": 2.6051781260421016e-05, + "loss": 3.476, + "step": 1462784 + }, + { + "epoch": 0.0, + "learning_rate": 2.6043395312910496e-05, + "loss": 3.4789, + "step": 1463296 + }, + { + "epoch": 0.0, + "learning_rate": 2.6035009365399976e-05, + "loss": 3.481, + "step": 1463808 + }, + { + "epoch": 0.0, + "learning_rate": 2.6026623417889456e-05, + "loss": 3.4908, + "step": 1464320 + }, + { + "epoch": 0.0, + "learning_rate": 2.6018253849182665e-05, + "loss": 3.4768, + "step": 1464832 + }, + { + "epoch": 0.01, + "learning_rate": 2.6009867901672145e-05, + "loss": 3.4827, + "step": 1465344 + }, + { + "epoch": 0.01, + "learning_rate": 2.600148195416163e-05, + "loss": 3.4854, + "step": 1465856 + }, + { + "epoch": 0.01, + "learning_rate": 2.599309600665111e-05, + "loss": 3.4909, + "step": 1466368 + }, + { + "epoch": 0.01, + "learning_rate": 2.5984726437944318e-05, + "loss": 3.4789, + "step": 1466880 + }, + { + "epoch": 0.01, + "learning_rate": 2.5976340490433798e-05, + "loss": 3.4854, + "step": 1467392 + }, + { + "epoch": 0.01, + "learning_rate": 2.5967954542923278e-05, + "loss": 3.4883, + "step": 1467904 + }, + { + "epoch": 0.01, + "learning_rate": 2.5959568595412758e-05, + "loss": 3.4886, + "step": 1468416 + }, + { + "epoch": 0.01, + "learning_rate": 2.595119902670597e-05, + "loss": 3.4728, + "step": 1468928 + }, + { + "epoch": 0.01, + "learning_rate": 2.594281307919545e-05, + "loss": 3.4847, + "step": 1469440 + }, + { + "epoch": 0.01, + "learning_rate": 2.593442713168493e-05, + "loss": 3.4705, + "step": 1469952 + }, + { + "epoch": 0.01, + "learning_rate": 2.592605756297814e-05, + "loss": 3.4853, + "step": 1470464 + }, + { + "epoch": 0.01, + "learning_rate": 2.591767161546762e-05, + "loss": 3.4783, + "step": 1470976 + }, + { + "epoch": 0.01, + "learning_rate": 2.59092856679571e-05, + "loss": 3.4888, + "step": 1471488 + }, + { + "epoch": 0.01, + "learning_rate": 2.5900899720446582e-05, + "loss": 3.4831, + "step": 1472000 + }, + { + "epoch": 0.01, + "learning_rate": 2.589253015173979e-05, + "loss": 3.4794, + "step": 1472512 + }, + { + "epoch": 0.01, + "learning_rate": 2.588414420422927e-05, + "loss": 3.4919, + "step": 1473024 + }, + { + "epoch": 0.01, + "learning_rate": 2.587575825671875e-05, + "loss": 3.4867, + "step": 1473536 + }, + { + "epoch": 0.01, + "learning_rate": 2.586737230920823e-05, + "loss": 3.485, + "step": 1474048 + }, + { + "epoch": 0.01, + "learning_rate": 2.5859002740501444e-05, + "loss": 3.4709, + "step": 1474560 + }, + { + "epoch": 0.01, + "learning_rate": 2.5850616792990924e-05, + "loss": 3.476, + "step": 1475072 + }, + { + "epoch": 0.01, + "learning_rate": 2.5842230845480404e-05, + "loss": 3.4919, + "step": 1475584 + }, + { + "epoch": 0.01, + "learning_rate": 2.5833844897969884e-05, + "loss": 3.4813, + "step": 1476096 + }, + { + "epoch": 0.01, + "learning_rate": 2.5825475329263093e-05, + "loss": 3.4771, + "step": 1476608 + }, + { + "epoch": 0.01, + "learning_rate": 2.5817089381752573e-05, + "loss": 3.4775, + "step": 1477120 + }, + { + "epoch": 0.01, + "learning_rate": 2.5808703434242053e-05, + "loss": 3.4813, + "step": 1477632 + }, + { + "epoch": 0.01, + "learning_rate": 2.5800317486731536e-05, + "loss": 3.4663, + "step": 1478144 + }, + { + "epoch": 0.01, + "learning_rate": 2.5791947918024745e-05, + "loss": 3.4843, + "step": 1478656 + }, + { + "epoch": 0.01, + "learning_rate": 2.5783561970514225e-05, + "loss": 3.4845, + "step": 1479168 + }, + { + "epoch": 0.01, + "learning_rate": 2.5775176023003705e-05, + "loss": 3.4892, + "step": 1479680 + }, + { + "epoch": 0.01, + "learning_rate": 2.5766790075493185e-05, + "loss": 3.4909, + "step": 1480192 + }, + { + "epoch": 0.01, + "learning_rate": 2.5758420506786397e-05, + "loss": 3.4735, + "step": 1480704 + }, + { + "epoch": 0.01, + "learning_rate": 2.5750034559275877e-05, + "loss": 3.4776, + "step": 1481216 + }, + { + "epoch": 0.01, + "learning_rate": 2.5741648611765357e-05, + "loss": 3.4827, + "step": 1481728 + }, + { + "epoch": 0.01, + "learning_rate": 2.5733262664254837e-05, + "loss": 3.4712, + "step": 1482240 + }, + { + "epoch": 0.01, + "learning_rate": 2.5724893095548046e-05, + "loss": 3.4698, + "step": 1482752 + }, + { + "epoch": 0.01, + "learning_rate": 2.5716507148037526e-05, + "loss": 3.48, + "step": 1483264 + }, + { + "epoch": 0.01, + "learning_rate": 2.5708121200527006e-05, + "loss": 3.4825, + "step": 1483776 + }, + { + "epoch": 0.01, + "learning_rate": 2.569973525301649e-05, + "loss": 3.4725, + "step": 1484288 + }, + { + "epoch": 0.01, + "learning_rate": 2.56913656843097e-05, + "loss": 3.4675, + "step": 1484800 + }, + { + "epoch": 0.01, + "learning_rate": 2.568297973679918e-05, + "loss": 3.4829, + "step": 1485312 + }, + { + "epoch": 0.01, + "learning_rate": 2.567459378928866e-05, + "loss": 3.4896, + "step": 1485824 + }, + { + "epoch": 0.01, + "learning_rate": 2.566620784177814e-05, + "loss": 3.4783, + "step": 1486336 + }, + { + "epoch": 0.01, + "learning_rate": 2.565783827307135e-05, + "loss": 3.486, + "step": 1486848 + }, + { + "epoch": 0.01, + "learning_rate": 2.564945232556083e-05, + "loss": 3.493, + "step": 1487360 + }, + { + "epoch": 0.01, + "learning_rate": 2.564106637805031e-05, + "loss": 3.4866, + "step": 1487872 + }, + { + "epoch": 0.01, + "learning_rate": 2.5632680430539784e-05, + "loss": 3.4943, + "step": 1488384 + }, + { + "epoch": 0.01, + "learning_rate": 2.5624310861833e-05, + "loss": 3.4685, + "step": 1488896 + }, + { + "epoch": 0.01, + "learning_rate": 2.561592491432248e-05, + "loss": 3.4868, + "step": 1489408 + }, + { + "epoch": 0.01, + "learning_rate": 2.560753896681196e-05, + "loss": 3.4882, + "step": 1489920 + }, + { + "epoch": 0.01, + "learning_rate": 2.5599153019301437e-05, + "loss": 3.4754, + "step": 1490432 + }, + { + "epoch": 0.01, + "learning_rate": 2.5590783450594652e-05, + "loss": 3.4915, + "step": 1490944 + }, + { + "epoch": 0.01, + "learning_rate": 2.5582397503084132e-05, + "loss": 3.4831, + "step": 1491456 + }, + { + "epoch": 0.01, + "learning_rate": 2.5574011555573612e-05, + "loss": 3.4921, + "step": 1491968 + }, + { + "epoch": 0.01, + "learning_rate": 2.556562560806309e-05, + "loss": 3.4857, + "step": 1492480 + }, + { + "epoch": 0.01, + "learning_rate": 2.5557256039356305e-05, + "loss": 3.4667, + "step": 1492992 + }, + { + "epoch": 0.01, + "learning_rate": 2.5548870091845785e-05, + "loss": 3.4732, + "step": 1493504 + }, + { + "epoch": 0.01, + "learning_rate": 2.5540484144335258e-05, + "loss": 3.4784, + "step": 1494016 + }, + { + "epoch": 0.01, + "learning_rate": 2.5532098196824738e-05, + "loss": 3.4848, + "step": 1494528 + }, + { + "epoch": 0.01, + "learning_rate": 2.5523728628117954e-05, + "loss": 3.4854, + "step": 1495040 + }, + { + "epoch": 0.01, + "learning_rate": 2.5515342680607434e-05, + "loss": 3.4799, + "step": 1495552 + }, + { + "epoch": 0.02, + "learning_rate": 2.550695673309691e-05, + "loss": 3.4782, + "step": 1496064 + }, + { + "epoch": 0.02, + "learning_rate": 2.549857078558639e-05, + "loss": 3.4729, + "step": 1496576 + }, + { + "epoch": 0.02, + "learning_rate": 2.5490201216879606e-05, + "loss": 3.4809, + "step": 1497088 + }, + { + "epoch": 0.02, + "learning_rate": 2.5481815269369086e-05, + "loss": 3.4766, + "step": 1497600 + }, + { + "epoch": 0.02, + "learning_rate": 2.547342932185856e-05, + "loss": 3.4859, + "step": 1498112 + }, + { + "epoch": 0.02, + "learning_rate": 2.5465043374348043e-05, + "loss": 3.4927, + "step": 1498624 + }, + { + "epoch": 0.02, + "learning_rate": 2.545667380564126e-05, + "loss": 3.4845, + "step": 1499136 + }, + { + "epoch": 0.02, + "learning_rate": 2.544828785813073e-05, + "loss": 3.476, + "step": 1499648 + }, + { + "epoch": 0.02, + "learning_rate": 2.543990191062021e-05, + "loss": 3.4839, + "step": 1500160 + }, + { + "epoch": 0.02, + "learning_rate": 2.543151596310969e-05, + "loss": 3.4787, + "step": 1500672 + }, + { + "epoch": 0.02, + "learning_rate": 2.5423146394402907e-05, + "loss": 3.4829, + "step": 1501184 + }, + { + "epoch": 0.02, + "learning_rate": 2.5414760446892384e-05, + "loss": 3.4818, + "step": 1501696 + }, + { + "epoch": 0.02, + "learning_rate": 2.5406374499381864e-05, + "loss": 3.4768, + "step": 1502208 + }, + { + "epoch": 0.02, + "learning_rate": 2.5397988551871344e-05, + "loss": 3.4696, + "step": 1502720 + }, + { + "epoch": 0.02, + "learning_rate": 2.5389618983164553e-05, + "loss": 3.4864, + "step": 1503232 + }, + { + "epoch": 0.02, + "learning_rate": 2.5381233035654033e-05, + "loss": 3.4712, + "step": 1503744 + }, + { + "epoch": 0.02, + "learning_rate": 2.5372847088143513e-05, + "loss": 3.4689, + "step": 1504256 + }, + { + "epoch": 0.02, + "learning_rate": 2.5364461140632996e-05, + "loss": 3.4736, + "step": 1504768 + }, + { + "epoch": 0.02, + "learning_rate": 2.5356091571926205e-05, + "loss": 3.4812, + "step": 1505280 + }, + { + "epoch": 0.02, + "learning_rate": 2.5347705624415685e-05, + "loss": 3.4717, + "step": 1505792 + }, + { + "epoch": 0.02, + "learning_rate": 2.5339319676905165e-05, + "loss": 3.4907, + "step": 1506304 + }, + { + "epoch": 0.02, + "learning_rate": 2.5330933729394645e-05, + "loss": 3.4704, + "step": 1506816 + }, + { + "epoch": 0.02, + "learning_rate": 2.5322564160687858e-05, + "loss": 3.4776, + "step": 1507328 + }, + { + "epoch": 0.02, + "learning_rate": 2.5314178213177338e-05, + "loss": 3.4756, + "step": 1507840 + }, + { + "epoch": 0.02, + "learning_rate": 2.5305792265666818e-05, + "loss": 3.4678, + "step": 1508352 + }, + { + "epoch": 0.02, + "learning_rate": 2.5297406318156298e-05, + "loss": 3.4922, + "step": 1508864 + }, + { + "epoch": 0.02, + "learning_rate": 2.5289036749449507e-05, + "loss": 3.4868, + "step": 1509376 + }, + { + "epoch": 0.02, + "learning_rate": 2.5280650801938987e-05, + "loss": 3.4775, + "step": 1509888 + }, + { + "epoch": 0.02, + "learning_rate": 2.5272264854428467e-05, + "loss": 3.4792, + "step": 1510400 + }, + { + "epoch": 0.02, + "learning_rate": 2.526387890691795e-05, + "loss": 3.4716, + "step": 1510912 + }, + { + "epoch": 0.02, + "learning_rate": 2.525550933821116e-05, + "loss": 3.4823, + "step": 1511424 + }, + { + "epoch": 0.02, + "learning_rate": 2.524712339070064e-05, + "loss": 3.4697, + "step": 1511936 + }, + { + "epoch": 0.02, + "learning_rate": 2.523873744319012e-05, + "loss": 3.4861, + "step": 1512448 + }, + { + "epoch": 0.02, + "learning_rate": 2.52303514956796e-05, + "loss": 3.4716, + "step": 1512960 + }, + { + "epoch": 0.02, + "learning_rate": 2.522198192697281e-05, + "loss": 3.479, + "step": 1513472 + }, + { + "epoch": 0.02, + "learning_rate": 2.521359597946229e-05, + "loss": 3.4734, + "step": 1513984 + }, + { + "epoch": 0.02, + "learning_rate": 2.520521003195177e-05, + "loss": 3.4781, + "step": 1514496 + }, + { + "epoch": 0.02, + "learning_rate": 2.519682408444125e-05, + "loss": 3.4732, + "step": 1515008 + }, + { + "epoch": 0.02, + "learning_rate": 2.518845451573446e-05, + "loss": 3.4755, + "step": 1515520 + }, + { + "epoch": 0.02, + "learning_rate": 2.518006856822394e-05, + "loss": 3.4727, + "step": 1516032 + }, + { + "epoch": 0.02, + "learning_rate": 2.517168262071342e-05, + "loss": 3.4904, + "step": 1516544 + }, + { + "epoch": 0.02, + "learning_rate": 2.51632966732029e-05, + "loss": 3.4844, + "step": 1517056 + }, + { + "epoch": 0.02, + "learning_rate": 2.5154927104496113e-05, + "loss": 3.4798, + "step": 1517568 + }, + { + "epoch": 0.02, + "learning_rate": 2.5146541156985593e-05, + "loss": 3.4643, + "step": 1518080 + }, + { + "epoch": 0.02, + "learning_rate": 2.5138155209475073e-05, + "loss": 3.4846, + "step": 1518592 + }, + { + "epoch": 0.02, + "learning_rate": 2.5129769261964553e-05, + "loss": 3.4821, + "step": 1519104 + }, + { + "epoch": 0.02, + "learning_rate": 2.512139969325776e-05, + "loss": 3.4834, + "step": 1519616 + }, + { + "epoch": 0.02, + "learning_rate": 2.5113013745747245e-05, + "loss": 3.4733, + "step": 1520128 + }, + { + "epoch": 0.02, + "learning_rate": 2.5104627798236725e-05, + "loss": 3.4831, + "step": 1520640 + }, + { + "epoch": 0.02, + "learning_rate": 2.5096241850726205e-05, + "loss": 3.4852, + "step": 1521152 + }, + { + "epoch": 0.02, + "learning_rate": 2.5087872282019414e-05, + "loss": 3.4809, + "step": 1521664 + }, + { + "epoch": 0.02, + "learning_rate": 2.5079486334508894e-05, + "loss": 3.4744, + "step": 1522176 + }, + { + "epoch": 0.02, + "learning_rate": 2.5071100386998374e-05, + "loss": 3.4798, + "step": 1522688 + }, + { + "epoch": 0.02, + "learning_rate": 2.5062714439487854e-05, + "loss": 3.4732, + "step": 1523200 + }, + { + "epoch": 0.02, + "learning_rate": 2.5054344870781066e-05, + "loss": 3.4717, + "step": 1523712 + }, + { + "epoch": 0.02, + "learning_rate": 2.5045958923270546e-05, + "loss": 3.4825, + "step": 1524224 + }, + { + "epoch": 0.02, + "learning_rate": 2.5037572975760026e-05, + "loss": 3.488, + "step": 1524736 + }, + { + "epoch": 0.02, + "learning_rate": 2.5029187028249506e-05, + "loss": 3.4773, + "step": 1525248 + }, + { + "epoch": 0.02, + "learning_rate": 2.5020817459542715e-05, + "loss": 3.4688, + "step": 1525760 + }, + { + "epoch": 0.02, + "learning_rate": 2.50124315120322e-05, + "loss": 3.4765, + "step": 1526272 + }, + { + "epoch": 0.03, + "eval_loss": 3.851848840713501, + "eval_runtime": 310.7884, + "eval_samples_per_second": 1227.816, + "eval_steps_per_second": 38.37, + "step": 1526400 + }, + { + "epoch": 0.0, + "learning_rate": 2.500404556452168e-05, + "loss": 3.4725, + "step": 1526784 + }, + { + "epoch": 0.0, + "learning_rate": 2.499565961701116e-05, + "loss": 3.4779, + "step": 1527296 + }, + { + "epoch": 0.0, + "learning_rate": 2.498727366950064e-05, + "loss": 3.4839, + "step": 1527808 + }, + { + "epoch": 0.0, + "learning_rate": 2.497888772199012e-05, + "loss": 3.4799, + "step": 1528320 + }, + { + "epoch": 0.0, + "learning_rate": 2.4970518153283328e-05, + "loss": 3.4892, + "step": 1528832 + }, + { + "epoch": 0.0, + "learning_rate": 2.4962132205772808e-05, + "loss": 3.4723, + "step": 1529344 + }, + { + "epoch": 0.0, + "learning_rate": 2.495374625826229e-05, + "loss": 3.4737, + "step": 1529856 + }, + { + "epoch": 0.0, + "learning_rate": 2.494536031075177e-05, + "loss": 3.4674, + "step": 1530368 + }, + { + "epoch": 0.0, + "learning_rate": 2.493699074204498e-05, + "loss": 3.4893, + "step": 1530880 + }, + { + "epoch": 0.0, + "learning_rate": 2.492860479453446e-05, + "loss": 3.4806, + "step": 1531392 + }, + { + "epoch": 0.0, + "learning_rate": 2.492021884702394e-05, + "loss": 3.4759, + "step": 1531904 + }, + { + "epoch": 0.0, + "learning_rate": 2.491183289951342e-05, + "loss": 3.4846, + "step": 1532416 + }, + { + "epoch": 0.0, + "learning_rate": 2.4903479709610365e-05, + "loss": 3.4712, + "step": 1532928 + }, + { + "epoch": 0.0, + "learning_rate": 2.489509376209984e-05, + "loss": 3.4736, + "step": 1533440 + }, + { + "epoch": 0.0, + "learning_rate": 2.488670781458932e-05, + "loss": 3.4801, + "step": 1533952 + }, + { + "epoch": 0.0, + "learning_rate": 2.48783218670788e-05, + "loss": 3.4704, + "step": 1534464 + }, + { + "epoch": 0.0, + "learning_rate": 2.486993591956828e-05, + "loss": 3.4689, + "step": 1534976 + }, + { + "epoch": 0.0, + "learning_rate": 2.486154997205776e-05, + "loss": 3.4682, + "step": 1535488 + }, + { + "epoch": 0.0, + "learning_rate": 2.4853164024547245e-05, + "loss": 3.474, + "step": 1536000 + }, + { + "epoch": 0.0, + "learning_rate": 2.484477807703672e-05, + "loss": 3.4909, + "step": 1536512 + }, + { + "epoch": 0.0, + "learning_rate": 2.4836408508329934e-05, + "loss": 3.48, + "step": 1537024 + }, + { + "epoch": 0.0, + "learning_rate": 2.4828022560819414e-05, + "loss": 3.4727, + "step": 1537536 + }, + { + "epoch": 0.0, + "learning_rate": 2.4819636613308894e-05, + "loss": 3.4733, + "step": 1538048 + }, + { + "epoch": 0.0, + "learning_rate": 2.481125066579837e-05, + "loss": 3.4807, + "step": 1538560 + }, + { + "epoch": 0.0, + "learning_rate": 2.4802881097091586e-05, + "loss": 3.4667, + "step": 1539072 + }, + { + "epoch": 0.0, + "learning_rate": 2.4794495149581066e-05, + "loss": 3.469, + "step": 1539584 + }, + { + "epoch": 0.0, + "learning_rate": 2.4786109202070542e-05, + "loss": 3.4681, + "step": 1540096 + }, + { + "epoch": 0.0, + "learning_rate": 2.4777739633363755e-05, + "loss": 3.4791, + "step": 1540608 + }, + { + "epoch": 0.0, + "learning_rate": 2.4769353685853235e-05, + "loss": 3.4634, + "step": 1541120 + }, + { + "epoch": 0.0, + "learning_rate": 2.4760967738342715e-05, + "loss": 3.4735, + "step": 1541632 + }, + { + "epoch": 0.01, + "learning_rate": 2.4752581790832195e-05, + "loss": 3.4742, + "step": 1542144 + }, + { + "epoch": 0.01, + "learning_rate": 2.4744212222125407e-05, + "loss": 3.4779, + "step": 1542656 + }, + { + "epoch": 0.01, + "learning_rate": 2.4735826274614887e-05, + "loss": 3.4684, + "step": 1543168 + }, + { + "epoch": 0.01, + "learning_rate": 2.4727440327104367e-05, + "loss": 3.4764, + "step": 1543680 + }, + { + "epoch": 0.01, + "learning_rate": 2.4719054379593844e-05, + "loss": 3.474, + "step": 1544192 + }, + { + "epoch": 0.01, + "learning_rate": 2.471068481088706e-05, + "loss": 3.4769, + "step": 1544704 + }, + { + "epoch": 0.01, + "learning_rate": 2.470229886337654e-05, + "loss": 3.4648, + "step": 1545216 + }, + { + "epoch": 0.01, + "learning_rate": 2.4693912915866016e-05, + "loss": 3.4685, + "step": 1545728 + }, + { + "epoch": 0.01, + "learning_rate": 2.4685526968355496e-05, + "loss": 3.4583, + "step": 1546240 + }, + { + "epoch": 0.01, + "learning_rate": 2.467715739964871e-05, + "loss": 3.4713, + "step": 1546752 + }, + { + "epoch": 0.01, + "learning_rate": 2.466877145213819e-05, + "loss": 3.4657, + "step": 1547264 + }, + { + "epoch": 0.01, + "learning_rate": 2.466038550462767e-05, + "loss": 3.4775, + "step": 1547776 + }, + { + "epoch": 0.01, + "learning_rate": 2.465199955711715e-05, + "loss": 3.4713, + "step": 1548288 + }, + { + "epoch": 0.01, + "learning_rate": 2.464362998841036e-05, + "loss": 3.4726, + "step": 1548800 + }, + { + "epoch": 0.01, + "learning_rate": 2.463524404089984e-05, + "loss": 3.4775, + "step": 1549312 + }, + { + "epoch": 0.01, + "learning_rate": 2.4626858093389317e-05, + "loss": 3.4725, + "step": 1549824 + }, + { + "epoch": 0.01, + "learning_rate": 2.4618472145878797e-05, + "loss": 3.474, + "step": 1550336 + }, + { + "epoch": 0.01, + "learning_rate": 2.4610102577172013e-05, + "loss": 3.4623, + "step": 1550848 + }, + { + "epoch": 0.01, + "learning_rate": 2.460171662966149e-05, + "loss": 3.4576, + "step": 1551360 + }, + { + "epoch": 0.01, + "learning_rate": 2.459333068215097e-05, + "loss": 3.4795, + "step": 1551872 + }, + { + "epoch": 0.01, + "learning_rate": 2.458494473464045e-05, + "loss": 3.4689, + "step": 1552384 + }, + { + "epoch": 0.01, + "learning_rate": 2.4576575165933662e-05, + "loss": 3.4656, + "step": 1552896 + }, + { + "epoch": 0.01, + "learning_rate": 2.456818921842314e-05, + "loss": 3.4646, + "step": 1553408 + }, + { + "epoch": 0.01, + "learning_rate": 2.4559803270912622e-05, + "loss": 3.4716, + "step": 1553920 + }, + { + "epoch": 0.01, + "learning_rate": 2.4551417323402102e-05, + "loss": 3.4531, + "step": 1554432 + }, + { + "epoch": 0.01, + "learning_rate": 2.4543047754695315e-05, + "loss": 3.474, + "step": 1554944 + }, + { + "epoch": 0.01, + "learning_rate": 2.453466180718479e-05, + "loss": 3.4709, + "step": 1555456 + }, + { + "epoch": 0.01, + "learning_rate": 2.452627585967427e-05, + "loss": 3.4737, + "step": 1555968 + }, + { + "epoch": 0.01, + "learning_rate": 2.451788991216375e-05, + "loss": 3.4815, + "step": 1556480 + }, + { + "epoch": 0.01, + "learning_rate": 2.4509520343456964e-05, + "loss": 3.4652, + "step": 1556992 + }, + { + "epoch": 0.01, + "learning_rate": 2.4501134395946444e-05, + "loss": 3.4648, + "step": 1557504 + }, + { + "epoch": 0.01, + "learning_rate": 2.4492748448435924e-05, + "loss": 3.4752, + "step": 1558016 + }, + { + "epoch": 0.01, + "learning_rate": 2.4484362500925403e-05, + "loss": 3.457, + "step": 1558528 + }, + { + "epoch": 0.01, + "learning_rate": 2.4475992932218613e-05, + "loss": 3.4582, + "step": 1559040 + }, + { + "epoch": 0.01, + "learning_rate": 2.4467606984708093e-05, + "loss": 3.4711, + "step": 1559552 + }, + { + "epoch": 0.01, + "learning_rate": 2.4459221037197576e-05, + "loss": 3.4706, + "step": 1560064 + }, + { + "epoch": 0.01, + "learning_rate": 2.4450835089687056e-05, + "loss": 3.4587, + "step": 1560576 + }, + { + "epoch": 0.01, + "learning_rate": 2.4442465520980265e-05, + "loss": 3.4587, + "step": 1561088 + }, + { + "epoch": 0.01, + "learning_rate": 2.4434079573469745e-05, + "loss": 3.4691, + "step": 1561600 + }, + { + "epoch": 0.01, + "learning_rate": 2.4425693625959225e-05, + "loss": 3.4746, + "step": 1562112 + }, + { + "epoch": 0.01, + "learning_rate": 2.4417307678448705e-05, + "loss": 3.4697, + "step": 1562624 + }, + { + "epoch": 0.01, + "learning_rate": 2.4408938109741917e-05, + "loss": 3.4682, + "step": 1563136 + }, + { + "epoch": 0.01, + "learning_rate": 2.4400552162231397e-05, + "loss": 3.4828, + "step": 1563648 + }, + { + "epoch": 0.01, + "learning_rate": 2.4392166214720877e-05, + "loss": 3.4719, + "step": 1564160 + }, + { + "epoch": 0.01, + "learning_rate": 2.4383780267210357e-05, + "loss": 3.4872, + "step": 1564672 + }, + { + "epoch": 0.01, + "learning_rate": 2.4375410698503566e-05, + "loss": 3.4574, + "step": 1565184 + }, + { + "epoch": 0.01, + "learning_rate": 2.4367024750993046e-05, + "loss": 3.4777, + "step": 1565696 + }, + { + "epoch": 0.01, + "learning_rate": 2.435863880348253e-05, + "loss": 3.4747, + "step": 1566208 + }, + { + "epoch": 0.01, + "learning_rate": 2.435025285597201e-05, + "loss": 3.464, + "step": 1566720 + }, + { + "epoch": 0.01, + "learning_rate": 2.434188328726522e-05, + "loss": 3.483, + "step": 1567232 + }, + { + "epoch": 0.01, + "learning_rate": 2.43334973397547e-05, + "loss": 3.4694, + "step": 1567744 + }, + { + "epoch": 0.01, + "learning_rate": 2.432511139224418e-05, + "loss": 3.4763, + "step": 1568256 + }, + { + "epoch": 0.01, + "learning_rate": 2.431672544473366e-05, + "loss": 3.4774, + "step": 1568768 + }, + { + "epoch": 0.01, + "learning_rate": 2.430835587602687e-05, + "loss": 3.4543, + "step": 1569280 + }, + { + "epoch": 0.01, + "learning_rate": 2.429996992851635e-05, + "loss": 3.4638, + "step": 1569792 + }, + { + "epoch": 0.01, + "learning_rate": 2.429158398100583e-05, + "loss": 3.4639, + "step": 1570304 + }, + { + "epoch": 0.01, + "learning_rate": 2.428319803349531e-05, + "loss": 3.4739, + "step": 1570816 + }, + { + "epoch": 0.01, + "learning_rate": 2.427482846478852e-05, + "loss": 3.4738, + "step": 1571328 + }, + { + "epoch": 0.01, + "learning_rate": 2.4266442517278e-05, + "loss": 3.4673, + "step": 1571840 + }, + { + "epoch": 0.02, + "learning_rate": 2.4258056569767483e-05, + "loss": 3.4681, + "step": 1572352 + }, + { + "epoch": 0.02, + "learning_rate": 2.4249670622256963e-05, + "loss": 3.4619, + "step": 1572864 + }, + { + "epoch": 0.02, + "learning_rate": 2.4241301053550172e-05, + "loss": 3.4655, + "step": 1573376 + }, + { + "epoch": 0.02, + "learning_rate": 2.4232915106039652e-05, + "loss": 3.4648, + "step": 1573888 + }, + { + "epoch": 0.02, + "learning_rate": 2.4224529158529132e-05, + "loss": 3.476, + "step": 1574400 + }, + { + "epoch": 0.02, + "learning_rate": 2.4216143211018612e-05, + "loss": 3.4774, + "step": 1574912 + }, + { + "epoch": 0.02, + "learning_rate": 2.4207773642311825e-05, + "loss": 3.4714, + "step": 1575424 + }, + { + "epoch": 0.02, + "learning_rate": 2.4199387694801305e-05, + "loss": 3.4629, + "step": 1575936 + }, + { + "epoch": 0.02, + "learning_rate": 2.4191001747290785e-05, + "loss": 3.4706, + "step": 1576448 + }, + { + "epoch": 0.02, + "learning_rate": 2.4182615799780264e-05, + "loss": 3.4685, + "step": 1576960 + }, + { + "epoch": 0.02, + "learning_rate": 2.4174246231073474e-05, + "loss": 3.4733, + "step": 1577472 + }, + { + "epoch": 0.02, + "learning_rate": 2.4165860283562954e-05, + "loss": 3.4708, + "step": 1577984 + }, + { + "epoch": 0.02, + "learning_rate": 2.4157474336052437e-05, + "loss": 3.4646, + "step": 1578496 + }, + { + "epoch": 0.02, + "learning_rate": 2.4149088388541917e-05, + "loss": 3.4589, + "step": 1579008 + }, + { + "epoch": 0.02, + "learning_rate": 2.4140718819835126e-05, + "loss": 3.4729, + "step": 1579520 + }, + { + "epoch": 0.02, + "learning_rate": 2.4132332872324606e-05, + "loss": 3.4607, + "step": 1580032 + }, + { + "epoch": 0.02, + "learning_rate": 2.4123946924814086e-05, + "loss": 3.4587, + "step": 1580544 + }, + { + "epoch": 0.02, + "learning_rate": 2.4115560977303562e-05, + "loss": 3.4531, + "step": 1581056 + }, + { + "epoch": 0.02, + "learning_rate": 2.4107191408596778e-05, + "loss": 3.4695, + "step": 1581568 + }, + { + "epoch": 0.02, + "learning_rate": 2.4098805461086258e-05, + "loss": 3.4559, + "step": 1582080 + }, + { + "epoch": 0.02, + "learning_rate": 2.4090419513575738e-05, + "loss": 3.4831, + "step": 1582592 + }, + { + "epoch": 0.02, + "learning_rate": 2.4082033566065215e-05, + "loss": 3.4559, + "step": 1583104 + }, + { + "epoch": 0.02, + "learning_rate": 2.4073663997358427e-05, + "loss": 3.4713, + "step": 1583616 + }, + { + "epoch": 0.02, + "learning_rate": 2.4065278049847907e-05, + "loss": 3.4647, + "step": 1584128 + }, + { + "epoch": 0.02, + "learning_rate": 2.4056892102337387e-05, + "loss": 3.457, + "step": 1584640 + }, + { + "epoch": 0.02, + "learning_rate": 2.4048506154826867e-05, + "loss": 3.4806, + "step": 1585152 + }, + { + "epoch": 0.02, + "learning_rate": 2.404013658612008e-05, + "loss": 3.4755, + "step": 1585664 + }, + { + "epoch": 0.02, + "learning_rate": 2.403175063860956e-05, + "loss": 3.4648, + "step": 1586176 + }, + { + "epoch": 0.02, + "learning_rate": 2.4023364691099036e-05, + "loss": 3.4671, + "step": 1586688 + }, + { + "epoch": 0.02, + "learning_rate": 2.4014995122392252e-05, + "loss": 3.4617, + "step": 1587200 + }, + { + "epoch": 0.02, + "learning_rate": 2.4006609174881732e-05, + "loss": 3.4708, + "step": 1587712 + }, + { + "epoch": 0.02, + "learning_rate": 2.3998223227371212e-05, + "loss": 3.4529, + "step": 1588224 + }, + { + "epoch": 0.02, + "learning_rate": 2.398983727986069e-05, + "loss": 3.476, + "step": 1588736 + }, + { + "epoch": 0.02, + "learning_rate": 2.39814677111539e-05, + "loss": 3.4652, + "step": 1589248 + }, + { + "epoch": 0.02, + "learning_rate": 2.397308176364338e-05, + "loss": 3.4662, + "step": 1589760 + }, + { + "epoch": 0.02, + "learning_rate": 2.396469581613286e-05, + "loss": 3.4624, + "step": 1590272 + }, + { + "epoch": 0.02, + "learning_rate": 2.395630986862234e-05, + "loss": 3.4685, + "step": 1590784 + }, + { + "epoch": 0.02, + "learning_rate": 2.3947940299915553e-05, + "loss": 3.4572, + "step": 1591296 + }, + { + "epoch": 0.02, + "learning_rate": 2.3939554352405033e-05, + "loss": 3.4668, + "step": 1591808 + }, + { + "epoch": 0.02, + "learning_rate": 2.393116840489451e-05, + "loss": 3.4635, + "step": 1592320 + }, + { + "epoch": 0.02, + "learning_rate": 2.392278245738399e-05, + "loss": 3.4771, + "step": 1592832 + }, + { + "epoch": 0.02, + "learning_rate": 2.3914412888677206e-05, + "loss": 3.4743, + "step": 1593344 + }, + { + "epoch": 0.02, + "learning_rate": 2.3906026941166686e-05, + "loss": 3.4716, + "step": 1593856 + }, + { + "epoch": 0.02, + "learning_rate": 2.3897640993656162e-05, + "loss": 3.4528, + "step": 1594368 + }, + { + "epoch": 0.02, + "learning_rate": 2.3889255046145642e-05, + "loss": 3.4726, + "step": 1594880 + }, + { + "epoch": 0.02, + "learning_rate": 2.3880885477438855e-05, + "loss": 3.4689, + "step": 1595392 + }, + { + "epoch": 0.02, + "learning_rate": 2.387249952992833e-05, + "loss": 3.4698, + "step": 1595904 + }, + { + "epoch": 0.02, + "learning_rate": 2.3864113582417815e-05, + "loss": 3.4612, + "step": 1596416 + }, + { + "epoch": 0.02, + "learning_rate": 2.3855727634907294e-05, + "loss": 3.4701, + "step": 1596928 + }, + { + "epoch": 0.02, + "learning_rate": 2.3847358066200507e-05, + "loss": 3.4729, + "step": 1597440 + }, + { + "epoch": 0.02, + "learning_rate": 2.3838972118689984e-05, + "loss": 3.474, + "step": 1597952 + }, + { + "epoch": 0.02, + "learning_rate": 2.3830586171179463e-05, + "loss": 3.4587, + "step": 1598464 + }, + { + "epoch": 0.02, + "learning_rate": 2.3822200223668943e-05, + "loss": 3.4695, + "step": 1598976 + }, + { + "epoch": 0.02, + "learning_rate": 2.3813830654962156e-05, + "loss": 3.4595, + "step": 1599488 + }, + { + "epoch": 0.02, + "learning_rate": 2.3805444707451636e-05, + "loss": 3.461, + "step": 1600000 + }, + { + "epoch": 0.02, + "learning_rate": 2.3797058759941116e-05, + "loss": 3.4751, + "step": 1600512 + }, + { + "epoch": 0.02, + "learning_rate": 2.3788672812430596e-05, + "loss": 3.4703, + "step": 1601024 + }, + { + "epoch": 0.02, + "learning_rate": 2.3780303243723805e-05, + "loss": 3.4671, + "step": 1601536 + }, + { + "epoch": 0.02, + "learning_rate": 2.3771917296213285e-05, + "loss": 3.4574, + "step": 1602048 + }, + { + "epoch": 0.02, + "learning_rate": 2.3763531348702768e-05, + "loss": 3.4654, + "step": 1602560 + }, + { + "epoch": 0.03, + "eval_loss": 3.8522932529449463, + "eval_runtime": 304.3766, + "eval_samples_per_second": 1253.68, + "eval_steps_per_second": 39.178, + "step": 1602720 + }, + { + "epoch": 1.0, + "learning_rate": 2.3755145401192248e-05, + "loss": 3.4659, + "step": 1603072 + }, + { + "epoch": 1.0, + "learning_rate": 2.3746775832485457e-05, + "loss": 3.4651, + "step": 1603584 + }, + { + "epoch": 1.0, + "learning_rate": 2.3738389884974937e-05, + "loss": 3.4749, + "step": 1604096 + }, + { + "epoch": 1.0, + "learning_rate": 2.3730003937464417e-05, + "loss": 3.4697, + "step": 1604608 + }, + { + "epoch": 1.0, + "learning_rate": 2.3721617989953897e-05, + "loss": 3.4721, + "step": 1605120 + }, + { + "epoch": 1.0, + "learning_rate": 2.371324842124711e-05, + "loss": 3.4662, + "step": 1605632 + }, + { + "epoch": 1.0, + "learning_rate": 2.370486247373659e-05, + "loss": 3.4596, + "step": 1606144 + }, + { + "epoch": 1.0, + "learning_rate": 2.369647652622607e-05, + "loss": 3.455, + "step": 1606656 + }, + { + "epoch": 1.0, + "learning_rate": 2.368809057871555e-05, + "loss": 3.473, + "step": 1607168 + }, + { + "epoch": 1.0, + "learning_rate": 2.367972101000876e-05, + "loss": 3.474, + "step": 1607680 + }, + { + "epoch": 1.0, + "learning_rate": 2.367133506249824e-05, + "loss": 3.4636, + "step": 1608192 + }, + { + "epoch": 1.0, + "learning_rate": 2.3662949114987722e-05, + "loss": 3.4754, + "step": 1608704 + }, + { + "epoch": 1.0, + "learning_rate": 2.365457954628093e-05, + "loss": 3.4614, + "step": 1609216 + }, + { + "epoch": 1.0, + "learning_rate": 2.364619359877041e-05, + "loss": 3.4612, + "step": 1609728 + }, + { + "epoch": 1.0, + "learning_rate": 2.363780765125989e-05, + "loss": 3.4705, + "step": 1610240 + }, + { + "epoch": 1.0, + "learning_rate": 2.362942170374937e-05, + "loss": 3.4572, + "step": 1610752 + }, + { + "epoch": 1.0, + "learning_rate": 2.362103575623885e-05, + "loss": 3.4578, + "step": 1611264 + }, + { + "epoch": 1.0, + "learning_rate": 2.361264980872833e-05, + "loss": 3.4576, + "step": 1611776 + }, + { + "epoch": 1.0, + "learning_rate": 2.3604263861217814e-05, + "loss": 3.4598, + "step": 1612288 + }, + { + "epoch": 1.0, + "learning_rate": 2.359587791370729e-05, + "loss": 3.4776, + "step": 1612800 + }, + { + "epoch": 1.0, + "learning_rate": 2.3587508345000503e-05, + "loss": 3.4681, + "step": 1613312 + }, + { + "epoch": 1.0, + "learning_rate": 2.3579122397489983e-05, + "loss": 3.4651, + "step": 1613824 + }, + { + "epoch": 1.0, + "learning_rate": 2.357073644997946e-05, + "loss": 3.4574, + "step": 1614336 + }, + { + "epoch": 1.0, + "learning_rate": 2.356235050246894e-05, + "loss": 3.47, + "step": 1614848 + }, + { + "epoch": 1.0, + "learning_rate": 2.3553980933762155e-05, + "loss": 3.4542, + "step": 1615360 + }, + { + "epoch": 1.0, + "learning_rate": 2.3545594986251635e-05, + "loss": 3.4562, + "step": 1615872 + }, + { + "epoch": 1.0, + "learning_rate": 2.3537209038741112e-05, + "loss": 3.4584, + "step": 1616384 + }, + { + "epoch": 1.0, + "learning_rate": 2.3528839470034324e-05, + "loss": 3.4644, + "step": 1616896 + }, + { + "epoch": 1.0, + "learning_rate": 2.3520453522523804e-05, + "loss": 3.4522, + "step": 1617408 + }, + { + "epoch": 1.0, + "learning_rate": 2.3512067575013284e-05, + "loss": 3.4602, + "step": 1617920 + }, + { + "epoch": 1.01, + "learning_rate": 2.3503681627502764e-05, + "loss": 3.4663, + "step": 1618432 + }, + { + "epoch": 1.01, + "learning_rate": 2.3495312058795977e-05, + "loss": 3.4664, + "step": 1618944 + }, + { + "epoch": 1.01, + "learning_rate": 2.3486926111285457e-05, + "loss": 3.458, + "step": 1619456 + }, + { + "epoch": 1.01, + "learning_rate": 2.3478540163774933e-05, + "loss": 3.4617, + "step": 1619968 + }, + { + "epoch": 1.01, + "learning_rate": 2.3470154216264413e-05, + "loss": 3.4631, + "step": 1620480 + }, + { + "epoch": 1.01, + "learning_rate": 2.346178464755763e-05, + "loss": 3.4621, + "step": 1620992 + }, + { + "epoch": 1.01, + "learning_rate": 2.345339870004711e-05, + "loss": 3.457, + "step": 1621504 + }, + { + "epoch": 1.01, + "learning_rate": 2.3445012752536586e-05, + "loss": 3.4544, + "step": 1622016 + }, + { + "epoch": 1.01, + "learning_rate": 2.3436626805026066e-05, + "loss": 3.4483, + "step": 1622528 + }, + { + "epoch": 1.01, + "learning_rate": 2.3428257236319278e-05, + "loss": 3.4573, + "step": 1623040 + }, + { + "epoch": 1.01, + "learning_rate": 2.3419871288808755e-05, + "loss": 3.4561, + "step": 1623552 + }, + { + "epoch": 1.01, + "learning_rate": 2.3411485341298238e-05, + "loss": 3.4639, + "step": 1624064 + }, + { + "epoch": 1.01, + "learning_rate": 2.3403099393787718e-05, + "loss": 3.4581, + "step": 1624576 + }, + { + "epoch": 1.01, + "learning_rate": 2.3394713446277198e-05, + "loss": 3.458, + "step": 1625088 + }, + { + "epoch": 1.01, + "learning_rate": 2.3386327498766678e-05, + "loss": 3.4692, + "step": 1625600 + }, + { + "epoch": 1.01, + "learning_rate": 2.3377941551256158e-05, + "loss": 3.4611, + "step": 1626112 + }, + { + "epoch": 1.01, + "learning_rate": 2.3369555603745638e-05, + "loss": 3.4651, + "step": 1626624 + }, + { + "epoch": 1.01, + "learning_rate": 2.3361186035038847e-05, + "loss": 3.4496, + "step": 1627136 + }, + { + "epoch": 1.01, + "learning_rate": 2.335280008752833e-05, + "loss": 3.4471, + "step": 1627648 + }, + { + "epoch": 1.01, + "learning_rate": 2.334441414001781e-05, + "loss": 3.4714, + "step": 1628160 + }, + { + "epoch": 1.01, + "learning_rate": 2.333602819250729e-05, + "loss": 3.4562, + "step": 1628672 + }, + { + "epoch": 1.01, + "learning_rate": 2.33276586238005e-05, + "loss": 3.4552, + "step": 1629184 + }, + { + "epoch": 1.01, + "learning_rate": 2.331927267628998e-05, + "loss": 3.4524, + "step": 1629696 + }, + { + "epoch": 1.01, + "learning_rate": 2.331088672877946e-05, + "loss": 3.4607, + "step": 1630208 + }, + { + "epoch": 1.01, + "learning_rate": 2.330250078126894e-05, + "loss": 3.4425, + "step": 1630720 + }, + { + "epoch": 1.01, + "learning_rate": 2.329413121256215e-05, + "loss": 3.4607, + "step": 1631232 + }, + { + "epoch": 1.01, + "learning_rate": 2.328574526505163e-05, + "loss": 3.4604, + "step": 1631744 + }, + { + "epoch": 1.01, + "learning_rate": 2.327735931754111e-05, + "loss": 3.4586, + "step": 1632256 + }, + { + "epoch": 1.01, + "learning_rate": 2.326898974883432e-05, + "loss": 3.4731, + "step": 1632768 + }, + { + "epoch": 1.01, + "learning_rate": 2.32606038013238e-05, + "loss": 3.4516, + "step": 1633280 + }, + { + "epoch": 1.01, + "learning_rate": 2.3252217853813284e-05, + "loss": 3.4526, + "step": 1633792 + }, + { + "epoch": 1.01, + "learning_rate": 2.3243831906302764e-05, + "loss": 3.4648, + "step": 1634304 + }, + { + "epoch": 1.01, + "learning_rate": 2.3235462337595973e-05, + "loss": 3.4487, + "step": 1634816 + }, + { + "epoch": 1.01, + "learning_rate": 2.3227076390085453e-05, + "loss": 3.4454, + "step": 1635328 + }, + { + "epoch": 1.01, + "learning_rate": 2.3218690442574933e-05, + "loss": 3.4557, + "step": 1635840 + }, + { + "epoch": 1.01, + "learning_rate": 2.321030449506441e-05, + "loss": 3.4581, + "step": 1636352 + }, + { + "epoch": 1.01, + "learning_rate": 2.3201934926357625e-05, + "loss": 3.4508, + "step": 1636864 + }, + { + "epoch": 1.01, + "learning_rate": 2.3193548978847105e-05, + "loss": 3.4487, + "step": 1637376 + }, + { + "epoch": 1.01, + "learning_rate": 2.3185163031336585e-05, + "loss": 3.4516, + "step": 1637888 + }, + { + "epoch": 1.01, + "learning_rate": 2.3176777083826062e-05, + "loss": 3.4608, + "step": 1638400 + }, + { + "epoch": 1.01, + "learning_rate": 2.3168407515119274e-05, + "loss": 3.4598, + "step": 1638912 + }, + { + "epoch": 1.01, + "learning_rate": 2.3160021567608754e-05, + "loss": 3.4604, + "step": 1639424 + }, + { + "epoch": 1.01, + "learning_rate": 2.3151635620098238e-05, + "loss": 3.4684, + "step": 1639936 + }, + { + "epoch": 1.01, + "learning_rate": 2.3143249672587714e-05, + "loss": 3.4627, + "step": 1640448 + }, + { + "epoch": 1.01, + "learning_rate": 2.3134880103880927e-05, + "loss": 3.4756, + "step": 1640960 + }, + { + "epoch": 1.01, + "learning_rate": 2.3126494156370407e-05, + "loss": 3.4469, + "step": 1641472 + }, + { + "epoch": 1.01, + "learning_rate": 2.3118108208859883e-05, + "loss": 3.4688, + "step": 1641984 + }, + { + "epoch": 1.01, + "learning_rate": 2.3109722261349363e-05, + "loss": 3.4648, + "step": 1642496 + }, + { + "epoch": 1.01, + "learning_rate": 2.310135269264258e-05, + "loss": 3.4447, + "step": 1643008 + }, + { + "epoch": 1.01, + "learning_rate": 2.309296674513206e-05, + "loss": 3.4721, + "step": 1643520 + }, + { + "epoch": 1.01, + "learning_rate": 2.3084580797621536e-05, + "loss": 3.4587, + "step": 1644032 + }, + { + "epoch": 1.01, + "learning_rate": 2.3076194850111016e-05, + "loss": 3.4679, + "step": 1644544 + }, + { + "epoch": 1.01, + "learning_rate": 2.3067825281404228e-05, + "loss": 3.4678, + "step": 1645056 + }, + { + "epoch": 1.01, + "learning_rate": 2.3059439333893708e-05, + "loss": 3.4443, + "step": 1645568 + }, + { + "epoch": 1.01, + "learning_rate": 2.3051053386383188e-05, + "loss": 3.4481, + "step": 1646080 + }, + { + "epoch": 1.01, + "learning_rate": 2.3042667438872668e-05, + "loss": 3.4512, + "step": 1646592 + }, + { + "epoch": 1.01, + "learning_rate": 2.303429787016588e-05, + "loss": 3.4622, + "step": 1647104 + }, + { + "epoch": 1.01, + "learning_rate": 2.3025911922655357e-05, + "loss": 3.4613, + "step": 1647616 + }, + { + "epoch": 1.01, + "learning_rate": 2.3017525975144837e-05, + "loss": 3.4575, + "step": 1648128 + }, + { + "epoch": 1.02, + "learning_rate": 2.3009140027634317e-05, + "loss": 3.4507, + "step": 1648640 + }, + { + "epoch": 1.02, + "learning_rate": 2.3000770458927533e-05, + "loss": 3.4564, + "step": 1649152 + }, + { + "epoch": 1.02, + "learning_rate": 2.299238451141701e-05, + "loss": 3.4561, + "step": 1649664 + }, + { + "epoch": 1.02, + "learning_rate": 2.298399856390649e-05, + "loss": 3.4502, + "step": 1650176 + }, + { + "epoch": 1.02, + "learning_rate": 2.297561261639597e-05, + "loss": 3.4671, + "step": 1650688 + }, + { + "epoch": 1.02, + "learning_rate": 2.296724304768918e-05, + "loss": 3.4646, + "step": 1651200 + }, + { + "epoch": 1.02, + "learning_rate": 2.295885710017866e-05, + "loss": 3.4654, + "step": 1651712 + }, + { + "epoch": 1.02, + "learning_rate": 2.295047115266814e-05, + "loss": 3.4494, + "step": 1652224 + }, + { + "epoch": 1.02, + "learning_rate": 2.294208520515762e-05, + "loss": 3.4606, + "step": 1652736 + }, + { + "epoch": 1.02, + "learning_rate": 2.293371563645083e-05, + "loss": 3.4551, + "step": 1653248 + }, + { + "epoch": 1.02, + "learning_rate": 2.292532968894031e-05, + "loss": 3.4607, + "step": 1653760 + }, + { + "epoch": 1.02, + "learning_rate": 2.291694374142979e-05, + "loss": 3.4591, + "step": 1654272 + }, + { + "epoch": 1.02, + "learning_rate": 2.290855779391927e-05, + "loss": 3.456, + "step": 1654784 + }, + { + "epoch": 1.02, + "learning_rate": 2.2900188225212483e-05, + "loss": 3.4475, + "step": 1655296 + }, + { + "epoch": 1.02, + "learning_rate": 2.2891802277701963e-05, + "loss": 3.4578, + "step": 1655808 + }, + { + "epoch": 1.02, + "learning_rate": 2.2883416330191443e-05, + "loss": 3.4525, + "step": 1656320 + }, + { + "epoch": 1.02, + "learning_rate": 2.2875030382680923e-05, + "loss": 3.4459, + "step": 1656832 + }, + { + "epoch": 1.02, + "learning_rate": 2.2866660813974132e-05, + "loss": 3.4395, + "step": 1657344 + }, + { + "epoch": 1.02, + "learning_rate": 2.2858274866463615e-05, + "loss": 3.458, + "step": 1657856 + }, + { + "epoch": 1.02, + "learning_rate": 2.2849888918953095e-05, + "loss": 3.4493, + "step": 1658368 + }, + { + "epoch": 1.02, + "learning_rate": 2.2841502971442575e-05, + "loss": 3.4682, + "step": 1658880 + }, + { + "epoch": 1.02, + "learning_rate": 2.2833133402735784e-05, + "loss": 3.4467, + "step": 1659392 + }, + { + "epoch": 1.02, + "learning_rate": 2.2824747455225264e-05, + "loss": 3.4583, + "step": 1659904 + }, + { + "epoch": 1.02, + "learning_rate": 2.2816361507714744e-05, + "loss": 3.4553, + "step": 1660416 + }, + { + "epoch": 1.02, + "learning_rate": 2.2807975560204224e-05, + "loss": 3.4452, + "step": 1660928 + }, + { + "epoch": 1.02, + "learning_rate": 2.2799605991497437e-05, + "loss": 3.4679, + "step": 1661440 + }, + { + "epoch": 1.02, + "learning_rate": 2.2791220043986917e-05, + "loss": 3.4638, + "step": 1661952 + }, + { + "epoch": 1.02, + "learning_rate": 2.2782834096476397e-05, + "loss": 3.4535, + "step": 1662464 + }, + { + "epoch": 1.02, + "learning_rate": 2.2774448148965877e-05, + "loss": 3.4559, + "step": 1662976 + }, + { + "epoch": 1.02, + "learning_rate": 2.2766078580259086e-05, + "loss": 3.4512, + "step": 1663488 + }, + { + "epoch": 1.02, + "learning_rate": 2.275769263274857e-05, + "loss": 3.46, + "step": 1664000 + }, + { + "epoch": 1.02, + "learning_rate": 2.274930668523805e-05, + "loss": 3.4394, + "step": 1664512 + }, + { + "epoch": 1.02, + "learning_rate": 2.274092073772753e-05, + "loss": 3.4645, + "step": 1665024 + }, + { + "epoch": 1.02, + "learning_rate": 2.2732551169020738e-05, + "loss": 3.45, + "step": 1665536 + }, + { + "epoch": 1.02, + "learning_rate": 2.2724165221510218e-05, + "loss": 3.4551, + "step": 1666048 + }, + { + "epoch": 1.02, + "learning_rate": 2.2715779273999698e-05, + "loss": 3.4539, + "step": 1666560 + }, + { + "epoch": 1.02, + "learning_rate": 2.2707393326489178e-05, + "loss": 3.4547, + "step": 1667072 + }, + { + "epoch": 1.02, + "learning_rate": 2.269902375778239e-05, + "loss": 3.4512, + "step": 1667584 + }, + { + "epoch": 1.02, + "learning_rate": 2.269063781027187e-05, + "loss": 3.4523, + "step": 1668096 + }, + { + "epoch": 1.02, + "learning_rate": 2.268225186276135e-05, + "loss": 3.4555, + "step": 1668608 + }, + { + "epoch": 1.02, + "learning_rate": 2.267386591525083e-05, + "loss": 3.4627, + "step": 1669120 + }, + { + "epoch": 1.02, + "learning_rate": 2.266549634654404e-05, + "loss": 3.4592, + "step": 1669632 + }, + { + "epoch": 1.02, + "learning_rate": 2.2657110399033523e-05, + "loss": 3.4612, + "step": 1670144 + }, + { + "epoch": 1.02, + "learning_rate": 2.2648724451523003e-05, + "loss": 3.4407, + "step": 1670656 + }, + { + "epoch": 1.02, + "learning_rate": 2.264035488281621e-05, + "loss": 3.4633, + "step": 1671168 + }, + { + "epoch": 1.02, + "learning_rate": 2.263196893530569e-05, + "loss": 3.4565, + "step": 1671680 + }, + { + "epoch": 1.02, + "learning_rate": 2.262358298779517e-05, + "loss": 3.4599, + "step": 1672192 + }, + { + "epoch": 1.02, + "learning_rate": 2.261519704028465e-05, + "loss": 3.4532, + "step": 1672704 + }, + { + "epoch": 1.02, + "learning_rate": 2.2606827471577864e-05, + "loss": 3.4542, + "step": 1673216 + }, + { + "epoch": 1.02, + "learning_rate": 2.2598441524067344e-05, + "loss": 3.4646, + "step": 1673728 + }, + { + "epoch": 1.02, + "learning_rate": 2.2590055576556824e-05, + "loss": 3.4624, + "step": 1674240 + }, + { + "epoch": 1.02, + "learning_rate": 2.2581669629046304e-05, + "loss": 3.4461, + "step": 1674752 + }, + { + "epoch": 1.02, + "learning_rate": 2.2573300060339513e-05, + "loss": 3.4556, + "step": 1675264 + }, + { + "epoch": 1.02, + "learning_rate": 2.2564914112828993e-05, + "loss": 3.4521, + "step": 1675776 + }, + { + "epoch": 1.02, + "learning_rate": 2.2556528165318473e-05, + "loss": 3.4491, + "step": 1676288 + }, + { + "epoch": 1.02, + "learning_rate": 2.2548142217807956e-05, + "loss": 3.4633, + "step": 1676800 + }, + { + "epoch": 1.02, + "learning_rate": 2.2539772649101165e-05, + "loss": 3.4572, + "step": 1677312 + }, + { + "epoch": 1.02, + "learning_rate": 2.2531386701590645e-05, + "loss": 3.461, + "step": 1677824 + }, + { + "epoch": 1.02, + "learning_rate": 2.2523000754080125e-05, + "loss": 3.4417, + "step": 1678336 + }, + { + "epoch": 1.02, + "learning_rate": 2.2514614806569605e-05, + "loss": 3.4555, + "step": 1678848 + }, + { + "epoch": 1.03, + "eval_loss": 3.8527402877807617, + "eval_runtime": 304.3168, + "eval_samples_per_second": 1253.927, + "eval_steps_per_second": 39.186, + "step": 1679040 + }, + { + "epoch": 0.0, + "learning_rate": 2.2506228859059085e-05, + "loss": 3.4534, + "step": 1679360 + }, + { + "epoch": 0.0, + "learning_rate": 2.2497842911548565e-05, + "loss": 3.4508, + "step": 1679872 + }, + { + "epoch": 0.0, + "learning_rate": 2.2489456964038045e-05, + "loss": 3.4633, + "step": 1680384 + }, + { + "epoch": 0.0, + "learning_rate": 2.2481071016527525e-05, + "loss": 3.4611, + "step": 1680896 + }, + { + "epoch": 0.0, + "learning_rate": 2.2472701447820734e-05, + "loss": 3.4585, + "step": 1681408 + }, + { + "epoch": 0.0, + "learning_rate": 2.2464315500310214e-05, + "loss": 3.4547, + "step": 1681920 + }, + { + "epoch": 0.0, + "learning_rate": 2.2455929552799694e-05, + "loss": 3.4442, + "step": 1682432 + }, + { + "epoch": 0.0, + "learning_rate": 2.2447543605289177e-05, + "loss": 3.45, + "step": 1682944 + }, + { + "epoch": 0.0, + "learning_rate": 2.2439174036582386e-05, + "loss": 3.4593, + "step": 1683456 + }, + { + "epoch": 0.0, + "learning_rate": 2.2430788089071866e-05, + "loss": 3.4655, + "step": 1683968 + }, + { + "epoch": 0.0, + "learning_rate": 2.2422402141561346e-05, + "loss": 3.4532, + "step": 1684480 + }, + { + "epoch": 0.0, + "learning_rate": 2.2414016194050826e-05, + "loss": 3.4643, + "step": 1684992 + }, + { + "epoch": 0.0, + "learning_rate": 2.240566300414777e-05, + "loss": 3.4511, + "step": 1685504 + }, + { + "epoch": 0.0, + "learning_rate": 2.239727705663725e-05, + "loss": 3.4446, + "step": 1686016 + }, + { + "epoch": 0.0, + "learning_rate": 2.2388891109126728e-05, + "loss": 3.4617, + "step": 1686528 + }, + { + "epoch": 0.0, + "learning_rate": 2.2380505161616208e-05, + "loss": 3.4456, + "step": 1687040 + }, + { + "epoch": 0.0, + "learning_rate": 2.2372119214105688e-05, + "loss": 3.4445, + "step": 1687552 + }, + { + "epoch": 0.0, + "learning_rate": 2.2363733266595168e-05, + "loss": 3.4447, + "step": 1688064 + }, + { + "epoch": 0.0, + "learning_rate": 2.2355347319084648e-05, + "loss": 3.4514, + "step": 1688576 + }, + { + "epoch": 0.0, + "learning_rate": 2.234696137157413e-05, + "loss": 3.4612, + "step": 1689088 + }, + { + "epoch": 0.0, + "learning_rate": 2.233859180286734e-05, + "loss": 3.4594, + "step": 1689600 + }, + { + "epoch": 0.0, + "learning_rate": 2.233020585535682e-05, + "loss": 3.455, + "step": 1690112 + }, + { + "epoch": 0.0, + "learning_rate": 2.23218199078463e-05, + "loss": 3.446, + "step": 1690624 + }, + { + "epoch": 0.0, + "learning_rate": 2.231343396033578e-05, + "loss": 3.4575, + "step": 1691136 + }, + { + "epoch": 0.0, + "learning_rate": 2.2305064391628992e-05, + "loss": 3.4465, + "step": 1691648 + }, + { + "epoch": 0.0, + "learning_rate": 2.2296678444118472e-05, + "loss": 3.4468, + "step": 1692160 + }, + { + "epoch": 0.0, + "learning_rate": 2.2288292496607952e-05, + "loss": 3.4433, + "step": 1692672 + }, + { + "epoch": 0.0, + "learning_rate": 2.2279906549097432e-05, + "loss": 3.4512, + "step": 1693184 + }, + { + "epoch": 0.0, + "learning_rate": 2.227153698039064e-05, + "loss": 3.4491, + "step": 1693696 + }, + { + "epoch": 0.0, + "learning_rate": 2.226315103288012e-05, + "loss": 3.4462, + "step": 1694208 + }, + { + "epoch": 0.01, + "learning_rate": 2.22547650853696e-05, + "loss": 3.4552, + "step": 1694720 + }, + { + "epoch": 0.01, + "learning_rate": 2.2246395516662814e-05, + "loss": 3.454, + "step": 1695232 + }, + { + "epoch": 0.01, + "learning_rate": 2.2238009569152294e-05, + "loss": 3.4454, + "step": 1695744 + }, + { + "epoch": 0.01, + "learning_rate": 2.2229623621641774e-05, + "loss": 3.4555, + "step": 1696256 + }, + { + "epoch": 0.01, + "learning_rate": 2.2221237674131254e-05, + "loss": 3.4499, + "step": 1696768 + }, + { + "epoch": 0.01, + "learning_rate": 2.2212868105424463e-05, + "loss": 3.4529, + "step": 1697280 + }, + { + "epoch": 0.01, + "learning_rate": 2.2204482157913946e-05, + "loss": 3.4498, + "step": 1697792 + }, + { + "epoch": 0.01, + "learning_rate": 2.2196096210403426e-05, + "loss": 3.4381, + "step": 1698304 + }, + { + "epoch": 0.01, + "learning_rate": 2.2187710262892906e-05, + "loss": 3.4382, + "step": 1698816 + }, + { + "epoch": 0.01, + "learning_rate": 2.2179340694186115e-05, + "loss": 3.4466, + "step": 1699328 + }, + { + "epoch": 0.01, + "learning_rate": 2.2170954746675595e-05, + "loss": 3.4448, + "step": 1699840 + }, + { + "epoch": 0.01, + "learning_rate": 2.2162568799165075e-05, + "loss": 3.45, + "step": 1700352 + }, + { + "epoch": 0.01, + "learning_rate": 2.2154182851654555e-05, + "loss": 3.4493, + "step": 1700864 + }, + { + "epoch": 0.01, + "learning_rate": 2.2145813282947768e-05, + "loss": 3.4474, + "step": 1701376 + }, + { + "epoch": 0.01, + "learning_rate": 2.2137427335437247e-05, + "loss": 3.457, + "step": 1701888 + }, + { + "epoch": 0.01, + "learning_rate": 2.2129041387926727e-05, + "loss": 3.4507, + "step": 1702400 + }, + { + "epoch": 0.01, + "learning_rate": 2.2120655440416204e-05, + "loss": 3.4546, + "step": 1702912 + }, + { + "epoch": 0.01, + "learning_rate": 2.2112269492905684e-05, + "loss": 3.4386, + "step": 1703424 + }, + { + "epoch": 0.01, + "learning_rate": 2.2103899924198896e-05, + "loss": 3.4307, + "step": 1703936 + }, + { + "epoch": 0.01, + "learning_rate": 2.209551397668838e-05, + "loss": 3.4616, + "step": 1704448 + }, + { + "epoch": 0.01, + "learning_rate": 2.2087128029177856e-05, + "loss": 3.4463, + "step": 1704960 + }, + { + "epoch": 0.01, + "learning_rate": 2.207875846047107e-05, + "loss": 3.4419, + "step": 1705472 + }, + { + "epoch": 0.01, + "learning_rate": 2.207037251296055e-05, + "loss": 3.4451, + "step": 1705984 + }, + { + "epoch": 0.01, + "learning_rate": 2.206198656545003e-05, + "loss": 3.4451, + "step": 1706496 + }, + { + "epoch": 0.01, + "learning_rate": 2.205361699674324e-05, + "loss": 3.4367, + "step": 1707008 + }, + { + "epoch": 0.01, + "learning_rate": 2.204523104923272e-05, + "loss": 3.4456, + "step": 1707520 + }, + { + "epoch": 0.01, + "learning_rate": 2.20368451017222e-05, + "loss": 3.4514, + "step": 1708032 + }, + { + "epoch": 0.01, + "learning_rate": 2.2028459154211678e-05, + "loss": 3.4499, + "step": 1708544 + }, + { + "epoch": 0.01, + "learning_rate": 2.2020073206701158e-05, + "loss": 3.4593, + "step": 1709056 + }, + { + "epoch": 0.01, + "learning_rate": 2.2011687259190638e-05, + "loss": 3.4399, + "step": 1709568 + }, + { + "epoch": 0.01, + "learning_rate": 2.2003301311680118e-05, + "loss": 3.442, + "step": 1710080 + }, + { + "epoch": 0.01, + "learning_rate": 2.199493174297333e-05, + "loss": 3.4564, + "step": 1710592 + }, + { + "epoch": 0.01, + "learning_rate": 2.198654579546281e-05, + "loss": 3.435, + "step": 1711104 + }, + { + "epoch": 0.01, + "learning_rate": 2.197815984795229e-05, + "loss": 3.4324, + "step": 1711616 + }, + { + "epoch": 0.01, + "learning_rate": 2.196977390044177e-05, + "loss": 3.4457, + "step": 1712128 + }, + { + "epoch": 0.01, + "learning_rate": 2.196140433173498e-05, + "loss": 3.4467, + "step": 1712640 + }, + { + "epoch": 0.01, + "learning_rate": 2.1953018384224462e-05, + "loss": 3.4381, + "step": 1713152 + }, + { + "epoch": 0.01, + "learning_rate": 2.1944632436713942e-05, + "loss": 3.4429, + "step": 1713664 + }, + { + "epoch": 0.01, + "learning_rate": 2.1936246489203422e-05, + "loss": 3.4351, + "step": 1714176 + }, + { + "epoch": 0.01, + "learning_rate": 2.192787692049663e-05, + "loss": 3.4549, + "step": 1714688 + }, + { + "epoch": 0.01, + "learning_rate": 2.191949097298611e-05, + "loss": 3.4481, + "step": 1715200 + }, + { + "epoch": 0.01, + "learning_rate": 2.191110502547559e-05, + "loss": 3.4498, + "step": 1715712 + }, + { + "epoch": 0.01, + "learning_rate": 2.190271907796507e-05, + "loss": 3.4554, + "step": 1716224 + }, + { + "epoch": 0.01, + "learning_rate": 2.1894349509258284e-05, + "loss": 3.4511, + "step": 1716736 + }, + { + "epoch": 0.01, + "learning_rate": 2.1885963561747764e-05, + "loss": 3.4644, + "step": 1717248 + }, + { + "epoch": 0.01, + "learning_rate": 2.1877577614237244e-05, + "loss": 3.4358, + "step": 1717760 + }, + { + "epoch": 0.01, + "learning_rate": 2.1869191666726724e-05, + "loss": 3.4583, + "step": 1718272 + }, + { + "epoch": 0.01, + "learning_rate": 2.1860822098019933e-05, + "loss": 3.4533, + "step": 1718784 + }, + { + "epoch": 0.01, + "learning_rate": 2.1852436150509416e-05, + "loss": 3.4366, + "step": 1719296 + }, + { + "epoch": 0.01, + "learning_rate": 2.1844050202998896e-05, + "loss": 3.4581, + "step": 1719808 + }, + { + "epoch": 0.01, + "learning_rate": 2.1835664255488376e-05, + "loss": 3.4488, + "step": 1720320 + }, + { + "epoch": 0.01, + "learning_rate": 2.1827294686781585e-05, + "loss": 3.4547, + "step": 1720832 + }, + { + "epoch": 0.01, + "learning_rate": 2.1818908739271065e-05, + "loss": 3.4567, + "step": 1721344 + }, + { + "epoch": 0.01, + "learning_rate": 2.1810522791760545e-05, + "loss": 3.4367, + "step": 1721856 + }, + { + "epoch": 0.01, + "learning_rate": 2.1802136844250025e-05, + "loss": 3.4327, + "step": 1722368 + }, + { + "epoch": 0.01, + "learning_rate": 2.1793767275543237e-05, + "loss": 3.4396, + "step": 1722880 + }, + { + "epoch": 0.01, + "learning_rate": 2.1785381328032717e-05, + "loss": 3.4551, + "step": 1723392 + }, + { + "epoch": 0.01, + "learning_rate": 2.1776995380522197e-05, + "loss": 3.4474, + "step": 1723904 + }, + { + "epoch": 0.01, + "learning_rate": 2.1768609433011677e-05, + "loss": 3.4458, + "step": 1724416 + }, + { + "epoch": 0.02, + "learning_rate": 2.1760239864304886e-05, + "loss": 3.4408, + "step": 1724928 + }, + { + "epoch": 0.02, + "learning_rate": 2.175185391679437e-05, + "loss": 3.4437, + "step": 1725440 + }, + { + "epoch": 0.02, + "learning_rate": 2.174346796928385e-05, + "loss": 3.4467, + "step": 1725952 + }, + { + "epoch": 0.02, + "learning_rate": 2.173508202177333e-05, + "loss": 3.4412, + "step": 1726464 + }, + { + "epoch": 0.02, + "learning_rate": 2.172671245306654e-05, + "loss": 3.4555, + "step": 1726976 + }, + { + "epoch": 0.02, + "learning_rate": 2.171832650555602e-05, + "loss": 3.4537, + "step": 1727488 + }, + { + "epoch": 0.02, + "learning_rate": 2.17099405580455e-05, + "loss": 3.452, + "step": 1728000 + }, + { + "epoch": 0.02, + "learning_rate": 2.170155461053498e-05, + "loss": 3.4384, + "step": 1728512 + }, + { + "epoch": 0.02, + "learning_rate": 2.169318504182819e-05, + "loss": 3.4494, + "step": 1729024 + }, + { + "epoch": 0.02, + "learning_rate": 2.168479909431767e-05, + "loss": 3.4436, + "step": 1729536 + }, + { + "epoch": 0.02, + "learning_rate": 2.167641314680715e-05, + "loss": 3.45, + "step": 1730048 + }, + { + "epoch": 0.02, + "learning_rate": 2.166802719929663e-05, + "loss": 3.4491, + "step": 1730560 + }, + { + "epoch": 0.02, + "learning_rate": 2.165965763058984e-05, + "loss": 3.4421, + "step": 1731072 + }, + { + "epoch": 0.02, + "learning_rate": 2.165127168307932e-05, + "loss": 3.4401, + "step": 1731584 + }, + { + "epoch": 0.02, + "learning_rate": 2.1642885735568803e-05, + "loss": 3.4461, + "step": 1732096 + }, + { + "epoch": 0.02, + "learning_rate": 2.163449978805828e-05, + "loss": 3.438, + "step": 1732608 + }, + { + "epoch": 0.02, + "learning_rate": 2.1626130219351492e-05, + "loss": 3.4442, + "step": 1733120 + }, + { + "epoch": 0.02, + "learning_rate": 2.1617744271840972e-05, + "loss": 3.4246, + "step": 1733632 + }, + { + "epoch": 0.02, + "learning_rate": 2.1609358324330452e-05, + "loss": 3.4487, + "step": 1734144 + }, + { + "epoch": 0.02, + "learning_rate": 2.1600972376819932e-05, + "loss": 3.4402, + "step": 1734656 + }, + { + "epoch": 0.02, + "learning_rate": 2.1592602808113145e-05, + "loss": 3.452, + "step": 1735168 + }, + { + "epoch": 0.02, + "learning_rate": 2.1584216860602625e-05, + "loss": 3.4363, + "step": 1735680 + }, + { + "epoch": 0.02, + "learning_rate": 2.1575830913092105e-05, + "loss": 3.4483, + "step": 1736192 + }, + { + "epoch": 0.02, + "learning_rate": 2.156744496558158e-05, + "loss": 3.4466, + "step": 1736704 + }, + { + "epoch": 0.02, + "learning_rate": 2.1559075396874794e-05, + "loss": 3.4317, + "step": 1737216 + }, + { + "epoch": 0.02, + "learning_rate": 2.1550689449364274e-05, + "loss": 3.4586, + "step": 1737728 + }, + { + "epoch": 0.02, + "learning_rate": 2.1542303501853754e-05, + "loss": 3.4511, + "step": 1738240 + }, + { + "epoch": 0.02, + "learning_rate": 2.1533933933146966e-05, + "loss": 3.4429, + "step": 1738752 + }, + { + "epoch": 0.02, + "learning_rate": 2.1525547985636446e-05, + "loss": 3.4488, + "step": 1739264 + }, + { + "epoch": 0.02, + "learning_rate": 2.1517162038125926e-05, + "loss": 3.4346, + "step": 1739776 + }, + { + "epoch": 0.02, + "learning_rate": 2.1508776090615403e-05, + "loss": 3.4528, + "step": 1740288 + }, + { + "epoch": 0.02, + "learning_rate": 2.150040652190862e-05, + "loss": 3.4299, + "step": 1740800 + }, + { + "epoch": 0.02, + "learning_rate": 2.14920205743981e-05, + "loss": 3.4532, + "step": 1741312 + }, + { + "epoch": 0.02, + "learning_rate": 2.1483634626887575e-05, + "loss": 3.4381, + "step": 1741824 + }, + { + "epoch": 0.02, + "learning_rate": 2.1475248679377055e-05, + "loss": 3.4444, + "step": 1742336 + }, + { + "epoch": 0.02, + "learning_rate": 2.1466879110670267e-05, + "loss": 3.4402, + "step": 1742848 + }, + { + "epoch": 0.02, + "learning_rate": 2.1458493163159747e-05, + "loss": 3.4443, + "step": 1743360 + }, + { + "epoch": 0.02, + "learning_rate": 2.1450107215649227e-05, + "loss": 3.4449, + "step": 1743872 + }, + { + "epoch": 0.02, + "learning_rate": 2.1441721268138707e-05, + "loss": 3.4393, + "step": 1744384 + }, + { + "epoch": 0.02, + "learning_rate": 2.143335169943192e-05, + "loss": 3.4468, + "step": 1744896 + }, + { + "epoch": 0.02, + "learning_rate": 2.14249657519214e-05, + "loss": 3.4516, + "step": 1745408 + }, + { + "epoch": 0.02, + "learning_rate": 2.1416579804410876e-05, + "loss": 3.4468, + "step": 1745920 + }, + { + "epoch": 0.02, + "learning_rate": 2.1408193856900356e-05, + "loss": 3.4535, + "step": 1746432 + }, + { + "epoch": 0.02, + "learning_rate": 2.1399824288193572e-05, + "loss": 3.4301, + "step": 1746944 + }, + { + "epoch": 0.02, + "learning_rate": 2.139143834068305e-05, + "loss": 3.4498, + "step": 1747456 + }, + { + "epoch": 0.02, + "learning_rate": 2.138305239317253e-05, + "loss": 3.4494, + "step": 1747968 + }, + { + "epoch": 0.02, + "learning_rate": 2.137466644566201e-05, + "loss": 3.4443, + "step": 1748480 + }, + { + "epoch": 0.02, + "learning_rate": 2.136629687695522e-05, + "loss": 3.4428, + "step": 1748992 + }, + { + "epoch": 0.02, + "learning_rate": 2.13579109294447e-05, + "loss": 3.4478, + "step": 1749504 + }, + { + "epoch": 0.02, + "learning_rate": 2.134952498193418e-05, + "loss": 3.4492, + "step": 1750016 + }, + { + "epoch": 0.02, + "learning_rate": 2.134113903442366e-05, + "loss": 3.456, + "step": 1750528 + }, + { + "epoch": 0.02, + "learning_rate": 2.1332769465716873e-05, + "loss": 3.4345, + "step": 1751040 + }, + { + "epoch": 0.02, + "learning_rate": 2.132438351820635e-05, + "loss": 3.4474, + "step": 1751552 + }, + { + "epoch": 0.02, + "learning_rate": 2.131599757069583e-05, + "loss": 3.441, + "step": 1752064 + }, + { + "epoch": 0.02, + "learning_rate": 2.130761162318531e-05, + "loss": 3.4411, + "step": 1752576 + }, + { + "epoch": 0.02, + "learning_rate": 2.1299242054478522e-05, + "loss": 3.4492, + "step": 1753088 + }, + { + "epoch": 0.02, + "learning_rate": 2.1290856106968002e-05, + "loss": 3.4442, + "step": 1753600 + }, + { + "epoch": 0.02, + "learning_rate": 2.1282470159457482e-05, + "loss": 3.4488, + "step": 1754112 + }, + { + "epoch": 0.02, + "learning_rate": 2.1274084211946962e-05, + "loss": 3.4307, + "step": 1754624 + }, + { + "epoch": 0.02, + "learning_rate": 2.126571464324017e-05, + "loss": 3.4499, + "step": 1755136 + }, + { + "epoch": 0.03, + "eval_loss": 3.8554577827453613, + "eval_runtime": 310.5235, + "eval_samples_per_second": 1228.864, + "eval_steps_per_second": 38.403, + "step": 1755360 + }, + { + "epoch": 0.0, + "learning_rate": 2.1257345074533387e-05, + "loss": 3.4462, + "step": 1755648 + }, + { + "epoch": 0.0, + "learning_rate": 2.1248959127022867e-05, + "loss": 3.4407, + "step": 1756160 + }, + { + "epoch": 0.0, + "learning_rate": 2.1240573179512347e-05, + "loss": 3.449, + "step": 1756672 + }, + { + "epoch": 0.0, + "learning_rate": 2.1232187232001824e-05, + "loss": 3.4504, + "step": 1757184 + }, + { + "epoch": 0.0, + "learning_rate": 2.1223817663295036e-05, + "loss": 3.4502, + "step": 1757696 + }, + { + "epoch": 0.0, + "learning_rate": 2.1215431715784516e-05, + "loss": 3.4446, + "step": 1758208 + }, + { + "epoch": 0.0, + "learning_rate": 2.1207045768273996e-05, + "loss": 3.4343, + "step": 1758720 + }, + { + "epoch": 0.0, + "learning_rate": 2.119867619956721e-05, + "loss": 3.4386, + "step": 1759232 + }, + { + "epoch": 0.0, + "learning_rate": 2.119029025205669e-05, + "loss": 3.4484, + "step": 1759744 + }, + { + "epoch": 0.0, + "learning_rate": 2.118190430454617e-05, + "loss": 3.45, + "step": 1760256 + }, + { + "epoch": 0.0, + "learning_rate": 2.1173518357035645e-05, + "loss": 3.4426, + "step": 1760768 + }, + { + "epoch": 0.0, + "learning_rate": 2.1165132409525125e-05, + "loss": 3.4504, + "step": 1761280 + }, + { + "epoch": 0.0, + "learning_rate": 2.115676284081834e-05, + "loss": 3.4457, + "step": 1761792 + }, + { + "epoch": 0.0, + "learning_rate": 2.114837689330782e-05, + "loss": 3.4343, + "step": 1762304 + }, + { + "epoch": 0.0, + "learning_rate": 2.1139990945797297e-05, + "loss": 3.4466, + "step": 1762816 + }, + { + "epoch": 0.0, + "learning_rate": 2.1131604998286777e-05, + "loss": 3.4319, + "step": 1763328 + }, + { + "epoch": 0.0, + "learning_rate": 2.1123219050776257e-05, + "loss": 3.4357, + "step": 1763840 + }, + { + "epoch": 0.0, + "learning_rate": 2.1114833103265737e-05, + "loss": 3.4361, + "step": 1764352 + }, + { + "epoch": 0.0, + "learning_rate": 2.1106447155755217e-05, + "loss": 3.4416, + "step": 1764864 + }, + { + "epoch": 0.0, + "learning_rate": 2.1098061208244697e-05, + "loss": 3.4481, + "step": 1765376 + }, + { + "epoch": 0.0, + "learning_rate": 2.108969163953791e-05, + "loss": 3.4522, + "step": 1765888 + }, + { + "epoch": 0.0, + "learning_rate": 2.108130569202739e-05, + "loss": 3.4422, + "step": 1766400 + }, + { + "epoch": 0.0, + "learning_rate": 2.107291974451687e-05, + "loss": 3.4329, + "step": 1766912 + }, + { + "epoch": 0.0, + "learning_rate": 2.106453379700635e-05, + "loss": 3.4459, + "step": 1767424 + }, + { + "epoch": 0.0, + "learning_rate": 2.105616422829956e-05, + "loss": 3.4337, + "step": 1767936 + }, + { + "epoch": 0.0, + "learning_rate": 2.1047778280789042e-05, + "loss": 3.4404, + "step": 1768448 + }, + { + "epoch": 0.0, + "learning_rate": 2.1039392333278522e-05, + "loss": 3.4285, + "step": 1768960 + }, + { + "epoch": 0.0, + "learning_rate": 2.1031006385768002e-05, + "loss": 3.4418, + "step": 1769472 + }, + { + "epoch": 0.0, + "learning_rate": 2.102263681706121e-05, + "loss": 3.4335, + "step": 1769984 + }, + { + "epoch": 0.0, + "learning_rate": 2.101425086955069e-05, + "loss": 3.4408, + "step": 1770496 + }, + { + "epoch": 0.01, + "learning_rate": 2.100586492204017e-05, + "loss": 3.4394, + "step": 1771008 + }, + { + "epoch": 0.01, + "learning_rate": 2.099747897452965e-05, + "loss": 3.4466, + "step": 1771520 + }, + { + "epoch": 0.01, + "learning_rate": 2.0989109405822863e-05, + "loss": 3.4376, + "step": 1772032 + }, + { + "epoch": 0.01, + "learning_rate": 2.0980723458312343e-05, + "loss": 3.4373, + "step": 1772544 + }, + { + "epoch": 0.01, + "learning_rate": 2.0972337510801823e-05, + "loss": 3.4416, + "step": 1773056 + }, + { + "epoch": 0.01, + "learning_rate": 2.0963967942095032e-05, + "loss": 3.4405, + "step": 1773568 + }, + { + "epoch": 0.01, + "learning_rate": 2.0955581994584512e-05, + "loss": 3.4424, + "step": 1774080 + }, + { + "epoch": 0.01, + "learning_rate": 2.0947196047073996e-05, + "loss": 3.4237, + "step": 1774592 + }, + { + "epoch": 0.01, + "learning_rate": 2.0938810099563476e-05, + "loss": 3.4295, + "step": 1775104 + }, + { + "epoch": 0.01, + "learning_rate": 2.0930440530856685e-05, + "loss": 3.4342, + "step": 1775616 + }, + { + "epoch": 0.01, + "learning_rate": 2.0922054583346165e-05, + "loss": 3.4387, + "step": 1776128 + }, + { + "epoch": 0.01, + "learning_rate": 2.0913668635835645e-05, + "loss": 3.4378, + "step": 1776640 + }, + { + "epoch": 0.01, + "learning_rate": 2.0905282688325125e-05, + "loss": 3.4384, + "step": 1777152 + }, + { + "epoch": 0.01, + "learning_rate": 2.0896896740814605e-05, + "loss": 3.4355, + "step": 1777664 + }, + { + "epoch": 0.01, + "learning_rate": 2.0888510793304084e-05, + "loss": 3.4476, + "step": 1778176 + }, + { + "epoch": 0.01, + "learning_rate": 2.0880124845793564e-05, + "loss": 3.4369, + "step": 1778688 + }, + { + "epoch": 0.01, + "learning_rate": 2.0871738898283044e-05, + "loss": 3.4516, + "step": 1779200 + }, + { + "epoch": 0.01, + "learning_rate": 2.0863369329576253e-05, + "loss": 3.4252, + "step": 1779712 + }, + { + "epoch": 0.01, + "learning_rate": 2.0854983382065733e-05, + "loss": 3.4153, + "step": 1780224 + }, + { + "epoch": 0.01, + "learning_rate": 2.0846597434555213e-05, + "loss": 3.454, + "step": 1780736 + }, + { + "epoch": 0.01, + "learning_rate": 2.0838211487044697e-05, + "loss": 3.4343, + "step": 1781248 + }, + { + "epoch": 0.01, + "learning_rate": 2.0829841918337906e-05, + "loss": 3.4359, + "step": 1781760 + }, + { + "epoch": 0.01, + "learning_rate": 2.0821455970827386e-05, + "loss": 3.4339, + "step": 1782272 + }, + { + "epoch": 0.01, + "learning_rate": 2.0813070023316866e-05, + "loss": 3.4326, + "step": 1782784 + }, + { + "epoch": 0.01, + "learning_rate": 2.0804700454610078e-05, + "loss": 3.426, + "step": 1783296 + }, + { + "epoch": 0.01, + "learning_rate": 2.0796314507099558e-05, + "loss": 3.4333, + "step": 1783808 + }, + { + "epoch": 0.01, + "learning_rate": 2.0787928559589038e-05, + "loss": 3.4378, + "step": 1784320 + }, + { + "epoch": 0.01, + "learning_rate": 2.0779542612078518e-05, + "loss": 3.4392, + "step": 1784832 + }, + { + "epoch": 0.01, + "learning_rate": 2.0771156664567998e-05, + "loss": 3.4506, + "step": 1785344 + }, + { + "epoch": 0.01, + "learning_rate": 2.0762770717057478e-05, + "loss": 3.43, + "step": 1785856 + }, + { + "epoch": 0.01, + "learning_rate": 2.0754384769546955e-05, + "loss": 3.4283, + "step": 1786368 + }, + { + "epoch": 0.01, + "learning_rate": 2.0746015200840167e-05, + "loss": 3.448, + "step": 1786880 + }, + { + "epoch": 0.01, + "learning_rate": 2.073762925332965e-05, + "loss": 3.4238, + "step": 1787392 + }, + { + "epoch": 0.01, + "learning_rate": 2.072925968462286e-05, + "loss": 3.4241, + "step": 1787904 + }, + { + "epoch": 0.01, + "learning_rate": 2.072087373711234e-05, + "loss": 3.4346, + "step": 1788416 + }, + { + "epoch": 0.01, + "learning_rate": 2.071248778960182e-05, + "loss": 3.4357, + "step": 1788928 + }, + { + "epoch": 0.01, + "learning_rate": 2.07041018420913e-05, + "loss": 3.4258, + "step": 1789440 + }, + { + "epoch": 0.01, + "learning_rate": 2.069571589458078e-05, + "loss": 3.4339, + "step": 1789952 + }, + { + "epoch": 0.01, + "learning_rate": 2.068732994707026e-05, + "loss": 3.4258, + "step": 1790464 + }, + { + "epoch": 0.01, + "learning_rate": 2.067894399955974e-05, + "loss": 3.4413, + "step": 1790976 + }, + { + "epoch": 0.01, + "learning_rate": 2.0670574430852952e-05, + "loss": 3.441, + "step": 1791488 + }, + { + "epoch": 0.01, + "learning_rate": 2.0662188483342428e-05, + "loss": 3.4331, + "step": 1792000 + }, + { + "epoch": 0.01, + "learning_rate": 2.0653802535831908e-05, + "loss": 3.4444, + "step": 1792512 + }, + { + "epoch": 0.01, + "learning_rate": 2.0645416588321388e-05, + "loss": 3.4414, + "step": 1793024 + }, + { + "epoch": 0.01, + "learning_rate": 2.06370470196146e-05, + "loss": 3.4536, + "step": 1793536 + }, + { + "epoch": 0.01, + "learning_rate": 2.062866107210408e-05, + "loss": 3.4227, + "step": 1794048 + }, + { + "epoch": 0.01, + "learning_rate": 2.062027512459356e-05, + "loss": 3.4503, + "step": 1794560 + }, + { + "epoch": 0.01, + "learning_rate": 2.061188917708304e-05, + "loss": 3.4369, + "step": 1795072 + }, + { + "epoch": 0.01, + "learning_rate": 2.060351960837625e-05, + "loss": 3.4276, + "step": 1795584 + }, + { + "epoch": 0.01, + "learning_rate": 2.0595133660865733e-05, + "loss": 3.446, + "step": 1796096 + }, + { + "epoch": 0.01, + "learning_rate": 2.0586747713355213e-05, + "loss": 3.4413, + "step": 1796608 + }, + { + "epoch": 0.01, + "learning_rate": 2.0578378144648425e-05, + "loss": 3.4411, + "step": 1797120 + }, + { + "epoch": 0.01, + "learning_rate": 2.0569992197137902e-05, + "loss": 3.4487, + "step": 1797632 + }, + { + "epoch": 0.01, + "learning_rate": 2.0561606249627382e-05, + "loss": 3.425, + "step": 1798144 + }, + { + "epoch": 0.01, + "learning_rate": 2.0553220302116862e-05, + "loss": 3.4217, + "step": 1798656 + }, + { + "epoch": 0.01, + "learning_rate": 2.0544834354606342e-05, + "loss": 3.4329, + "step": 1799168 + }, + { + "epoch": 0.01, + "learning_rate": 2.0536448407095825e-05, + "loss": 3.4428, + "step": 1799680 + }, + { + "epoch": 0.01, + "learning_rate": 2.0528062459585305e-05, + "loss": 3.438, + "step": 1800192 + }, + { + "epoch": 0.01, + "learning_rate": 2.0519692890878514e-05, + "loss": 3.4345, + "step": 1800704 + }, + { + "epoch": 0.02, + "learning_rate": 2.0511306943367994e-05, + "loss": 3.4271, + "step": 1801216 + }, + { + "epoch": 0.02, + "learning_rate": 2.0502920995857474e-05, + "loss": 3.4338, + "step": 1801728 + }, + { + "epoch": 0.02, + "learning_rate": 2.0494535048346954e-05, + "loss": 3.433, + "step": 1802240 + }, + { + "epoch": 0.02, + "learning_rate": 2.0486165479640167e-05, + "loss": 3.4337, + "step": 1802752 + }, + { + "epoch": 0.02, + "learning_rate": 2.0477779532129647e-05, + "loss": 3.4429, + "step": 1803264 + }, + { + "epoch": 0.02, + "learning_rate": 2.0469393584619127e-05, + "loss": 3.4448, + "step": 1803776 + }, + { + "epoch": 0.02, + "learning_rate": 2.0461007637108606e-05, + "loss": 3.441, + "step": 1804288 + }, + { + "epoch": 0.02, + "learning_rate": 2.0452638068401816e-05, + "loss": 3.4287, + "step": 1804800 + }, + { + "epoch": 0.02, + "learning_rate": 2.0444252120891296e-05, + "loss": 3.4404, + "step": 1805312 + }, + { + "epoch": 0.02, + "learning_rate": 2.0435882552184508e-05, + "loss": 3.4306, + "step": 1805824 + }, + { + "epoch": 0.02, + "learning_rate": 2.0427496604673988e-05, + "loss": 3.439, + "step": 1806336 + }, + { + "epoch": 0.02, + "learning_rate": 2.0419110657163468e-05, + "loss": 3.4395, + "step": 1806848 + }, + { + "epoch": 0.02, + "learning_rate": 2.0410724709652948e-05, + "loss": 3.4357, + "step": 1807360 + }, + { + "epoch": 0.02, + "learning_rate": 2.0402338762142428e-05, + "loss": 3.4245, + "step": 1807872 + }, + { + "epoch": 0.02, + "learning_rate": 2.0393952814631904e-05, + "loss": 3.4307, + "step": 1808384 + }, + { + "epoch": 0.02, + "learning_rate": 2.0385566867121388e-05, + "loss": 3.4332, + "step": 1808896 + }, + { + "epoch": 0.02, + "learning_rate": 2.0377180919610868e-05, + "loss": 3.4316, + "step": 1809408 + }, + { + "epoch": 0.02, + "learning_rate": 2.036881135090408e-05, + "loss": 3.4174, + "step": 1809920 + }, + { + "epoch": 0.02, + "learning_rate": 2.0360425403393557e-05, + "loss": 3.4391, + "step": 1810432 + }, + { + "epoch": 0.02, + "learning_rate": 2.0352039455883037e-05, + "loss": 3.4328, + "step": 1810944 + }, + { + "epoch": 0.02, + "learning_rate": 2.0343653508372517e-05, + "loss": 3.4381, + "step": 1811456 + }, + { + "epoch": 0.02, + "learning_rate": 2.033528393966573e-05, + "loss": 3.4246, + "step": 1811968 + }, + { + "epoch": 0.02, + "learning_rate": 2.032689799215521e-05, + "loss": 3.4424, + "step": 1812480 + }, + { + "epoch": 0.02, + "learning_rate": 2.031851204464469e-05, + "loss": 3.4315, + "step": 1812992 + }, + { + "epoch": 0.02, + "learning_rate": 2.031012609713417e-05, + "loss": 3.4216, + "step": 1813504 + }, + { + "epoch": 0.02, + "learning_rate": 2.0301756528427378e-05, + "loss": 3.4473, + "step": 1814016 + }, + { + "epoch": 0.02, + "learning_rate": 2.0293370580916858e-05, + "loss": 3.4403, + "step": 1814528 + }, + { + "epoch": 0.02, + "learning_rate": 2.028498463340634e-05, + "loss": 3.4303, + "step": 1815040 + }, + { + "epoch": 0.02, + "learning_rate": 2.027659868589582e-05, + "loss": 3.4404, + "step": 1815552 + }, + { + "epoch": 0.02, + "learning_rate": 2.026822911718903e-05, + "loss": 3.4232, + "step": 1816064 + }, + { + "epoch": 0.02, + "learning_rate": 2.025984316967851e-05, + "loss": 3.443, + "step": 1816576 + }, + { + "epoch": 0.02, + "learning_rate": 2.025145722216799e-05, + "loss": 3.4232, + "step": 1817088 + }, + { + "epoch": 0.02, + "learning_rate": 2.024307127465747e-05, + "loss": 3.4388, + "step": 1817600 + }, + { + "epoch": 0.02, + "learning_rate": 2.0234701705950683e-05, + "loss": 3.4284, + "step": 1818112 + }, + { + "epoch": 0.02, + "learning_rate": 2.0226315758440163e-05, + "loss": 3.4334, + "step": 1818624 + }, + { + "epoch": 0.02, + "learning_rate": 2.0217929810929643e-05, + "loss": 3.4297, + "step": 1819136 + }, + { + "epoch": 0.02, + "learning_rate": 2.0209543863419123e-05, + "loss": 3.4352, + "step": 1819648 + }, + { + "epoch": 0.02, + "learning_rate": 2.0201174294712332e-05, + "loss": 3.4295, + "step": 1820160 + }, + { + "epoch": 0.02, + "learning_rate": 2.0192788347201812e-05, + "loss": 3.4301, + "step": 1820672 + }, + { + "epoch": 0.02, + "learning_rate": 2.0184402399691295e-05, + "loss": 3.4375, + "step": 1821184 + }, + { + "epoch": 0.02, + "learning_rate": 2.0176016452180775e-05, + "loss": 3.4414, + "step": 1821696 + }, + { + "epoch": 0.02, + "learning_rate": 2.0167646883473984e-05, + "loss": 3.4309, + "step": 1822208 + }, + { + "epoch": 0.02, + "learning_rate": 2.0159260935963464e-05, + "loss": 3.4477, + "step": 1822720 + }, + { + "epoch": 0.02, + "learning_rate": 2.0150874988452944e-05, + "loss": 3.4186, + "step": 1823232 + }, + { + "epoch": 0.02, + "learning_rate": 2.0142489040942424e-05, + "loss": 3.4407, + "step": 1823744 + }, + { + "epoch": 0.02, + "learning_rate": 2.0134119472235636e-05, + "loss": 3.4374, + "step": 1824256 + }, + { + "epoch": 0.02, + "learning_rate": 2.0125733524725116e-05, + "loss": 3.4359, + "step": 1824768 + }, + { + "epoch": 0.02, + "learning_rate": 2.0117347577214596e-05, + "loss": 3.4314, + "step": 1825280 + }, + { + "epoch": 0.02, + "learning_rate": 2.0108961629704076e-05, + "loss": 3.4374, + "step": 1825792 + }, + { + "epoch": 0.02, + "learning_rate": 2.0100592060997285e-05, + "loss": 3.4366, + "step": 1826304 + }, + { + "epoch": 0.02, + "learning_rate": 2.0092206113486765e-05, + "loss": 3.4455, + "step": 1826816 + }, + { + "epoch": 0.02, + "learning_rate": 2.0083820165976245e-05, + "loss": 3.424, + "step": 1827328 + }, + { + "epoch": 0.02, + "learning_rate": 2.0075450597269458e-05, + "loss": 3.4358, + "step": 1827840 + }, + { + "epoch": 0.02, + "learning_rate": 2.0067064649758938e-05, + "loss": 3.4282, + "step": 1828352 + }, + { + "epoch": 0.02, + "learning_rate": 2.0058678702248418e-05, + "loss": 3.4352, + "step": 1828864 + }, + { + "epoch": 0.02, + "learning_rate": 2.0050292754737898e-05, + "loss": 3.4319, + "step": 1829376 + }, + { + "epoch": 0.02, + "learning_rate": 2.004192318603111e-05, + "loss": 3.4354, + "step": 1829888 + }, + { + "epoch": 0.02, + "learning_rate": 2.003353723852059e-05, + "loss": 3.4414, + "step": 1830400 + }, + { + "epoch": 0.02, + "learning_rate": 2.002515129101007e-05, + "loss": 3.4195, + "step": 1830912 + }, + { + "epoch": 0.02, + "learning_rate": 2.001676534349955e-05, + "loss": 3.4399, + "step": 1831424 + }, + { + "epoch": 0.03, + "eval_loss": 3.855762243270874, + "eval_runtime": 309.3729, + "eval_samples_per_second": 1233.434, + "eval_steps_per_second": 38.546, + "step": 1831680 + }, + { + "epoch": 0.0, + "learning_rate": 2.000839577479276e-05, + "loss": 3.4324, + "step": 1831936 + }, + { + "epoch": 0.0, + "learning_rate": 2.000000982728224e-05, + "loss": 3.4318, + "step": 1832448 + }, + { + "epoch": 0.0, + "learning_rate": 1.999162387977172e-05, + "loss": 3.4362, + "step": 1832960 + }, + { + "epoch": 0.0, + "learning_rate": 1.99832379322612e-05, + "loss": 3.438, + "step": 1833472 + }, + { + "epoch": 0.0, + "learning_rate": 1.997486836355441e-05, + "loss": 3.4417, + "step": 1833984 + }, + { + "epoch": 0.0, + "learning_rate": 1.996648241604389e-05, + "loss": 3.4312, + "step": 1834496 + }, + { + "epoch": 0.0, + "learning_rate": 1.995809646853337e-05, + "loss": 3.4272, + "step": 1835008 + }, + { + "epoch": 0.0, + "learning_rate": 1.994972689982658e-05, + "loss": 3.4309, + "step": 1835520 + }, + { + "epoch": 0.0, + "learning_rate": 1.994134095231606e-05, + "loss": 3.4357, + "step": 1836032 + }, + { + "epoch": 0.0, + "learning_rate": 1.9932955004805544e-05, + "loss": 3.4416, + "step": 1836544 + }, + { + "epoch": 0.0, + "learning_rate": 1.9924569057295024e-05, + "loss": 3.4348, + "step": 1837056 + }, + { + "epoch": 0.0, + "learning_rate": 1.9916183109784504e-05, + "loss": 3.4384, + "step": 1837568 + }, + { + "epoch": 0.0, + "learning_rate": 1.9907813541077713e-05, + "loss": 3.4306, + "step": 1838080 + }, + { + "epoch": 0.0, + "learning_rate": 1.9899427593567193e-05, + "loss": 3.4264, + "step": 1838592 + }, + { + "epoch": 0.0, + "learning_rate": 1.9891041646056673e-05, + "loss": 3.4384, + "step": 1839104 + }, + { + "epoch": 0.0, + "learning_rate": 1.9882655698546153e-05, + "loss": 3.4224, + "step": 1839616 + }, + { + "epoch": 0.0, + "learning_rate": 1.9874269751035633e-05, + "loss": 3.4246, + "step": 1840128 + }, + { + "epoch": 0.0, + "learning_rate": 1.9865883803525113e-05, + "loss": 3.4244, + "step": 1840640 + }, + { + "epoch": 0.0, + "learning_rate": 1.9857497856014593e-05, + "loss": 3.4308, + "step": 1841152 + }, + { + "epoch": 0.0, + "learning_rate": 1.9849111908504073e-05, + "loss": 3.434, + "step": 1841664 + }, + { + "epoch": 0.0, + "learning_rate": 1.984074233979728e-05, + "loss": 3.4429, + "step": 1842176 + }, + { + "epoch": 0.0, + "learning_rate": 1.9832356392286765e-05, + "loss": 3.4315, + "step": 1842688 + }, + { + "epoch": 0.0, + "learning_rate": 1.9823970444776245e-05, + "loss": 3.4246, + "step": 1843200 + }, + { + "epoch": 0.0, + "learning_rate": 1.9815584497265725e-05, + "loss": 3.433, + "step": 1843712 + }, + { + "epoch": 0.0, + "learning_rate": 1.9807214928558934e-05, + "loss": 3.4282, + "step": 1844224 + }, + { + "epoch": 0.0, + "learning_rate": 1.9798828981048414e-05, + "loss": 3.4293, + "step": 1844736 + }, + { + "epoch": 0.0, + "learning_rate": 1.9790443033537894e-05, + "loss": 3.4175, + "step": 1845248 + }, + { + "epoch": 0.0, + "learning_rate": 1.9782057086027374e-05, + "loss": 3.4336, + "step": 1845760 + }, + { + "epoch": 0.0, + "learning_rate": 1.9773687517320586e-05, + "loss": 3.4285, + "step": 1846272 + }, + { + "epoch": 0.0, + "learning_rate": 1.9765301569810066e-05, + "loss": 3.4231, + "step": 1846784 + }, + { + "epoch": 0.01, + "learning_rate": 1.9756915622299546e-05, + "loss": 3.4268, + "step": 1847296 + }, + { + "epoch": 0.01, + "learning_rate": 1.9748529674789026e-05, + "loss": 3.438, + "step": 1847808 + }, + { + "epoch": 0.01, + "learning_rate": 1.9740160106082235e-05, + "loss": 3.4253, + "step": 1848320 + }, + { + "epoch": 0.01, + "learning_rate": 1.973177415857172e-05, + "loss": 3.4263, + "step": 1848832 + }, + { + "epoch": 0.01, + "learning_rate": 1.97233882110612e-05, + "loss": 3.4284, + "step": 1849344 + }, + { + "epoch": 0.01, + "learning_rate": 1.9715018642354408e-05, + "loss": 3.4338, + "step": 1849856 + }, + { + "epoch": 0.01, + "learning_rate": 1.9706632694843888e-05, + "loss": 3.4281, + "step": 1850368 + }, + { + "epoch": 0.01, + "learning_rate": 1.9698246747333368e-05, + "loss": 3.4156, + "step": 1850880 + }, + { + "epoch": 0.01, + "learning_rate": 1.9689860799822848e-05, + "loss": 3.4212, + "step": 1851392 + }, + { + "epoch": 0.01, + "learning_rate": 1.968149123111606e-05, + "loss": 3.4225, + "step": 1851904 + }, + { + "epoch": 0.01, + "learning_rate": 1.967310528360554e-05, + "loss": 3.4279, + "step": 1852416 + }, + { + "epoch": 0.01, + "learning_rate": 1.966471933609502e-05, + "loss": 3.4282, + "step": 1852928 + }, + { + "epoch": 0.01, + "learning_rate": 1.96563333885845e-05, + "loss": 3.4285, + "step": 1853440 + }, + { + "epoch": 0.01, + "learning_rate": 1.964794744107398e-05, + "loss": 3.4267, + "step": 1853952 + }, + { + "epoch": 0.01, + "learning_rate": 1.9639561493563456e-05, + "loss": 3.4331, + "step": 1854464 + }, + { + "epoch": 0.01, + "learning_rate": 1.9631175546052936e-05, + "loss": 3.4242, + "step": 1854976 + }, + { + "epoch": 0.01, + "learning_rate": 1.962278959854242e-05, + "loss": 3.4383, + "step": 1855488 + }, + { + "epoch": 0.01, + "learning_rate": 1.961442002983563e-05, + "loss": 3.4186, + "step": 1856000 + }, + { + "epoch": 0.01, + "learning_rate": 1.960603408232511e-05, + "loss": 3.4028, + "step": 1856512 + }, + { + "epoch": 0.01, + "learning_rate": 1.959764813481459e-05, + "loss": 3.4437, + "step": 1857024 + }, + { + "epoch": 0.01, + "learning_rate": 1.958926218730407e-05, + "loss": 3.4236, + "step": 1857536 + }, + { + "epoch": 0.01, + "learning_rate": 1.958089261859728e-05, + "loss": 3.4262, + "step": 1858048 + }, + { + "epoch": 0.01, + "learning_rate": 1.957250667108676e-05, + "loss": 3.4231, + "step": 1858560 + }, + { + "epoch": 0.01, + "learning_rate": 1.956412072357624e-05, + "loss": 3.4211, + "step": 1859072 + }, + { + "epoch": 0.01, + "learning_rate": 1.9555751154869454e-05, + "loss": 3.4154, + "step": 1859584 + }, + { + "epoch": 0.01, + "learning_rate": 1.954736520735893e-05, + "loss": 3.4219, + "step": 1860096 + }, + { + "epoch": 0.01, + "learning_rate": 1.953897925984841e-05, + "loss": 3.4281, + "step": 1860608 + }, + { + "epoch": 0.01, + "learning_rate": 1.953059331233789e-05, + "loss": 3.4313, + "step": 1861120 + }, + { + "epoch": 0.01, + "learning_rate": 1.9522207364827373e-05, + "loss": 3.4414, + "step": 1861632 + }, + { + "epoch": 0.01, + "learning_rate": 1.9513821417316853e-05, + "loss": 3.4175, + "step": 1862144 + }, + { + "epoch": 0.01, + "learning_rate": 1.9505435469806333e-05, + "loss": 3.417, + "step": 1862656 + }, + { + "epoch": 0.01, + "learning_rate": 1.9497065901099542e-05, + "loss": 3.4405, + "step": 1863168 + }, + { + "epoch": 0.01, + "learning_rate": 1.9488679953589022e-05, + "loss": 3.4105, + "step": 1863680 + }, + { + "epoch": 0.01, + "learning_rate": 1.9480310384882235e-05, + "loss": 3.4107, + "step": 1864192 + }, + { + "epoch": 0.01, + "learning_rate": 1.9471924437371715e-05, + "loss": 3.4258, + "step": 1864704 + }, + { + "epoch": 0.01, + "learning_rate": 1.9463538489861195e-05, + "loss": 3.4252, + "step": 1865216 + }, + { + "epoch": 0.01, + "learning_rate": 1.9455152542350675e-05, + "loss": 3.4159, + "step": 1865728 + }, + { + "epoch": 0.01, + "learning_rate": 1.9446766594840155e-05, + "loss": 3.4231, + "step": 1866240 + }, + { + "epoch": 0.01, + "learning_rate": 1.9438380647329635e-05, + "loss": 3.4161, + "step": 1866752 + }, + { + "epoch": 0.01, + "learning_rate": 1.942999469981911e-05, + "loss": 3.4301, + "step": 1867264 + }, + { + "epoch": 0.01, + "learning_rate": 1.9421625131112327e-05, + "loss": 3.4276, + "step": 1867776 + }, + { + "epoch": 0.01, + "learning_rate": 1.9413239183601807e-05, + "loss": 3.427, + "step": 1868288 + }, + { + "epoch": 0.01, + "learning_rate": 1.9404853236091284e-05, + "loss": 3.433, + "step": 1868800 + }, + { + "epoch": 0.01, + "learning_rate": 1.9396467288580764e-05, + "loss": 3.432, + "step": 1869312 + }, + { + "epoch": 0.01, + "learning_rate": 1.9388097719873976e-05, + "loss": 3.4418, + "step": 1869824 + }, + { + "epoch": 0.01, + "learning_rate": 1.9379711772363456e-05, + "loss": 3.416, + "step": 1870336 + }, + { + "epoch": 0.01, + "learning_rate": 1.9371325824852936e-05, + "loss": 3.4378, + "step": 1870848 + }, + { + "epoch": 0.01, + "learning_rate": 1.9362939877342416e-05, + "loss": 3.4231, + "step": 1871360 + }, + { + "epoch": 0.01, + "learning_rate": 1.935457030863563e-05, + "loss": 3.4191, + "step": 1871872 + }, + { + "epoch": 0.01, + "learning_rate": 1.934618436112511e-05, + "loss": 3.435, + "step": 1872384 + }, + { + "epoch": 0.01, + "learning_rate": 1.9337798413614585e-05, + "loss": 3.43, + "step": 1872896 + }, + { + "epoch": 0.01, + "learning_rate": 1.9329428844907797e-05, + "loss": 3.432, + "step": 1873408 + }, + { + "epoch": 0.01, + "learning_rate": 1.9321042897397277e-05, + "loss": 3.4387, + "step": 1873920 + }, + { + "epoch": 0.01, + "learning_rate": 1.9312656949886757e-05, + "loss": 3.4133, + "step": 1874432 + }, + { + "epoch": 0.01, + "learning_rate": 1.9304271002376237e-05, + "loss": 3.4058, + "step": 1874944 + }, + { + "epoch": 0.01, + "learning_rate": 1.9295885054865717e-05, + "loss": 3.4223, + "step": 1875456 + }, + { + "epoch": 0.01, + "learning_rate": 1.9287499107355197e-05, + "loss": 3.4343, + "step": 1875968 + }, + { + "epoch": 0.01, + "learning_rate": 1.9279113159844677e-05, + "loss": 3.4287, + "step": 1876480 + }, + { + "epoch": 0.01, + "learning_rate": 1.927074359113789e-05, + "loss": 3.4252, + "step": 1876992 + }, + { + "epoch": 0.02, + "learning_rate": 1.926235764362737e-05, + "loss": 3.4179, + "step": 1877504 + }, + { + "epoch": 0.02, + "learning_rate": 1.925397169611685e-05, + "loss": 3.4216, + "step": 1878016 + }, + { + "epoch": 0.02, + "learning_rate": 1.924558574860633e-05, + "loss": 3.4266, + "step": 1878528 + }, + { + "epoch": 0.02, + "learning_rate": 1.923721617989954e-05, + "loss": 3.4222, + "step": 1879040 + }, + { + "epoch": 0.02, + "learning_rate": 1.922883023238902e-05, + "loss": 3.4297, + "step": 1879552 + }, + { + "epoch": 0.02, + "learning_rate": 1.92204442848785e-05, + "loss": 3.4322, + "step": 1880064 + }, + { + "epoch": 0.02, + "learning_rate": 1.9212058337367982e-05, + "loss": 3.4316, + "step": 1880576 + }, + { + "epoch": 0.02, + "learning_rate": 1.920368876866119e-05, + "loss": 3.4206, + "step": 1881088 + }, + { + "epoch": 0.02, + "learning_rate": 1.919530282115067e-05, + "loss": 3.4283, + "step": 1881600 + }, + { + "epoch": 0.02, + "learning_rate": 1.918691687364015e-05, + "loss": 3.4184, + "step": 1882112 + }, + { + "epoch": 0.02, + "learning_rate": 1.917853092612963e-05, + "loss": 3.4264, + "step": 1882624 + }, + { + "epoch": 0.02, + "learning_rate": 1.9170161357422843e-05, + "loss": 3.4289, + "step": 1883136 + }, + { + "epoch": 0.02, + "learning_rate": 1.9161775409912323e-05, + "loss": 3.4286, + "step": 1883648 + }, + { + "epoch": 0.02, + "learning_rate": 1.9153389462401803e-05, + "loss": 3.418, + "step": 1884160 + }, + { + "epoch": 0.02, + "learning_rate": 1.9145003514891283e-05, + "loss": 3.4133, + "step": 1884672 + }, + { + "epoch": 0.02, + "learning_rate": 1.9136633946184492e-05, + "loss": 3.4251, + "step": 1885184 + }, + { + "epoch": 0.02, + "learning_rate": 1.9128247998673972e-05, + "loss": 3.4193, + "step": 1885696 + }, + { + "epoch": 0.02, + "learning_rate": 1.9119862051163452e-05, + "loss": 3.4022, + "step": 1886208 + }, + { + "epoch": 0.02, + "learning_rate": 1.9111476103652935e-05, + "loss": 3.4296, + "step": 1886720 + }, + { + "epoch": 0.02, + "learning_rate": 1.9103106534946145e-05, + "loss": 3.4233, + "step": 1887232 + }, + { + "epoch": 0.02, + "learning_rate": 1.9094720587435625e-05, + "loss": 3.4264, + "step": 1887744 + }, + { + "epoch": 0.02, + "learning_rate": 1.9086334639925104e-05, + "loss": 3.4119, + "step": 1888256 + }, + { + "epoch": 0.02, + "learning_rate": 1.9077948692414584e-05, + "loss": 3.429, + "step": 1888768 + }, + { + "epoch": 0.02, + "learning_rate": 1.9069579123707797e-05, + "loss": 3.4242, + "step": 1889280 + }, + { + "epoch": 0.02, + "learning_rate": 1.9061193176197277e-05, + "loss": 3.4113, + "step": 1889792 + }, + { + "epoch": 0.02, + "learning_rate": 1.9052807228686757e-05, + "loss": 3.4377, + "step": 1890304 + }, + { + "epoch": 0.02, + "learning_rate": 1.9044421281176237e-05, + "loss": 3.4319, + "step": 1890816 + }, + { + "epoch": 0.02, + "learning_rate": 1.9036051712469446e-05, + "loss": 3.4211, + "step": 1891328 + }, + { + "epoch": 0.02, + "learning_rate": 1.9027665764958926e-05, + "loss": 3.4271, + "step": 1891840 + }, + { + "epoch": 0.02, + "learning_rate": 1.9019279817448406e-05, + "loss": 3.4116, + "step": 1892352 + }, + { + "epoch": 0.02, + "learning_rate": 1.9010893869937886e-05, + "loss": 3.4294, + "step": 1892864 + }, + { + "epoch": 0.02, + "learning_rate": 1.9002524301231098e-05, + "loss": 3.4189, + "step": 1893376 + }, + { + "epoch": 0.02, + "learning_rate": 1.8994138353720578e-05, + "loss": 3.4248, + "step": 1893888 + }, + { + "epoch": 0.02, + "learning_rate": 1.8985752406210058e-05, + "loss": 3.4185, + "step": 1894400 + }, + { + "epoch": 0.02, + "learning_rate": 1.8977366458699535e-05, + "loss": 3.4257, + "step": 1894912 + }, + { + "epoch": 0.02, + "learning_rate": 1.896899688999275e-05, + "loss": 3.4189, + "step": 1895424 + }, + { + "epoch": 0.02, + "learning_rate": 1.896061094248223e-05, + "loss": 3.4215, + "step": 1895936 + }, + { + "epoch": 0.02, + "learning_rate": 1.8952224994971707e-05, + "loss": 3.4186, + "step": 1896448 + }, + { + "epoch": 0.02, + "learning_rate": 1.8943839047461187e-05, + "loss": 3.4209, + "step": 1896960 + }, + { + "epoch": 0.02, + "learning_rate": 1.89354694787544e-05, + "loss": 3.4219, + "step": 1897472 + }, + { + "epoch": 0.02, + "learning_rate": 1.892708353124388e-05, + "loss": 3.429, + "step": 1897984 + }, + { + "epoch": 0.02, + "learning_rate": 1.8918713962537092e-05, + "loss": 3.4219, + "step": 1898496 + }, + { + "epoch": 0.02, + "learning_rate": 1.8910328015026572e-05, + "loss": 3.4387, + "step": 1899008 + }, + { + "epoch": 0.02, + "learning_rate": 1.8901942067516052e-05, + "loss": 3.4091, + "step": 1899520 + }, + { + "epoch": 0.02, + "learning_rate": 1.8893556120005532e-05, + "loss": 3.4277, + "step": 1900032 + }, + { + "epoch": 0.02, + "learning_rate": 1.888517017249501e-05, + "loss": 3.4283, + "step": 1900544 + }, + { + "epoch": 0.02, + "learning_rate": 1.887678422498449e-05, + "loss": 3.427, + "step": 1901056 + }, + { + "epoch": 0.02, + "learning_rate": 1.886839827747397e-05, + "loss": 3.4197, + "step": 1901568 + }, + { + "epoch": 0.02, + "learning_rate": 1.886001232996345e-05, + "loss": 3.4252, + "step": 1902080 + }, + { + "epoch": 0.02, + "learning_rate": 1.885164276125666e-05, + "loss": 3.4243, + "step": 1902592 + }, + { + "epoch": 0.02, + "learning_rate": 1.884325681374614e-05, + "loss": 3.4424, + "step": 1903104 + }, + { + "epoch": 0.02, + "learning_rate": 1.883487086623562e-05, + "loss": 3.4133, + "step": 1903616 + }, + { + "epoch": 0.02, + "learning_rate": 1.88264849187251e-05, + "loss": 3.4209, + "step": 1904128 + }, + { + "epoch": 0.02, + "learning_rate": 1.8818115350018313e-05, + "loss": 3.4175, + "step": 1904640 + }, + { + "epoch": 0.02, + "learning_rate": 1.8809729402507793e-05, + "loss": 3.4268, + "step": 1905152 + }, + { + "epoch": 0.02, + "learning_rate": 1.8801343454997273e-05, + "loss": 3.4179, + "step": 1905664 + }, + { + "epoch": 0.02, + "learning_rate": 1.8792957507486753e-05, + "loss": 3.4279, + "step": 1906176 + }, + { + "epoch": 0.02, + "learning_rate": 1.8784587938779962e-05, + "loss": 3.4261, + "step": 1906688 + }, + { + "epoch": 0.02, + "learning_rate": 1.8776201991269442e-05, + "loss": 3.4184, + "step": 1907200 + }, + { + "epoch": 0.02, + "learning_rate": 1.8767816043758922e-05, + "loss": 3.4253, + "step": 1907712 + }, + { + "epoch": 0.03, + "eval_loss": 3.8576972484588623, + "eval_runtime": 624.4615, + "eval_samples_per_second": 611.072, + "eval_steps_per_second": 19.096, + "step": 1908000 + }, + { + "epoch": 1.0, + "learning_rate": 1.8759446475052134e-05, + "loss": 3.4174, + "step": 1908224 + }, + { + "epoch": 1.0, + "learning_rate": 1.8751060527541614e-05, + "loss": 3.4187, + "step": 1908736 + }, + { + "epoch": 1.0, + "learning_rate": 1.8742674580031094e-05, + "loss": 3.43, + "step": 1909248 + }, + { + "epoch": 1.0, + "learning_rate": 1.8734288632520574e-05, + "loss": 3.4283, + "step": 1909760 + }, + { + "epoch": 1.0, + "learning_rate": 1.8725902685010054e-05, + "loss": 3.4319, + "step": 1910272 + }, + { + "epoch": 1.0, + "learning_rate": 1.8717516737499534e-05, + "loss": 3.4224, + "step": 1910784 + }, + { + "epoch": 1.0, + "learning_rate": 1.8709130789989014e-05, + "loss": 3.4162, + "step": 1911296 + }, + { + "epoch": 1.0, + "learning_rate": 1.8700744842478494e-05, + "loss": 3.4214, + "step": 1911808 + }, + { + "epoch": 1.0, + "learning_rate": 1.8692375273771707e-05, + "loss": 3.4201, + "step": 1912320 + }, + { + "epoch": 1.0, + "learning_rate": 1.8683989326261187e-05, + "loss": 3.4312, + "step": 1912832 + }, + { + "epoch": 1.0, + "learning_rate": 1.8675603378750663e-05, + "loss": 3.424, + "step": 1913344 + }, + { + "epoch": 1.0, + "learning_rate": 1.8667217431240143e-05, + "loss": 3.4254, + "step": 1913856 + }, + { + "epoch": 1.0, + "learning_rate": 1.8658864241337088e-05, + "loss": 3.43, + "step": 1914368 + }, + { + "epoch": 1.0, + "learning_rate": 1.8650478293826568e-05, + "loss": 3.4075, + "step": 1914880 + }, + { + "epoch": 1.0, + "learning_rate": 1.8642092346316048e-05, + "loss": 3.4267, + "step": 1915392 + }, + { + "epoch": 1.0, + "learning_rate": 1.8633706398805528e-05, + "loss": 3.4147, + "step": 1915904 + }, + { + "epoch": 1.0, + "learning_rate": 1.8625320451295008e-05, + "loss": 3.4132, + "step": 1916416 + }, + { + "epoch": 1.0, + "learning_rate": 1.8616934503784485e-05, + "loss": 3.4181, + "step": 1916928 + }, + { + "epoch": 1.0, + "learning_rate": 1.8608548556273968e-05, + "loss": 3.4176, + "step": 1917440 + }, + { + "epoch": 1.0, + "learning_rate": 1.8600162608763448e-05, + "loss": 3.4233, + "step": 1917952 + }, + { + "epoch": 1.0, + "learning_rate": 1.859179304005666e-05, + "loss": 3.4351, + "step": 1918464 + }, + { + "epoch": 1.0, + "learning_rate": 1.8583407092546137e-05, + "loss": 3.4261, + "step": 1918976 + }, + { + "epoch": 1.0, + "learning_rate": 1.8575021145035617e-05, + "loss": 3.4151, + "step": 1919488 + }, + { + "epoch": 1.0, + "learning_rate": 1.8566635197525097e-05, + "loss": 3.4179, + "step": 1920000 + }, + { + "epoch": 1.0, + "learning_rate": 1.855826562881831e-05, + "loss": 3.4189, + "step": 1920512 + }, + { + "epoch": 1.0, + "learning_rate": 1.854987968130779e-05, + "loss": 3.42, + "step": 1921024 + }, + { + "epoch": 1.0, + "learning_rate": 1.854149373379727e-05, + "loss": 3.4088, + "step": 1921536 + }, + { + "epoch": 1.0, + "learning_rate": 1.853310778628675e-05, + "loss": 3.426, + "step": 1922048 + }, + { + "epoch": 1.0, + "learning_rate": 1.8524738217579958e-05, + "loss": 3.4134, + "step": 1922560 + }, + { + "epoch": 1.0, + "learning_rate": 1.8516352270069438e-05, + "loss": 3.4159, + "step": 1923072 + }, + { + "epoch": 1.01, + "learning_rate": 1.8507982701362654e-05, + "loss": 3.4128, + "step": 1923584 + }, + { + "epoch": 1.01, + "learning_rate": 1.8499596753852134e-05, + "loss": 3.4301, + "step": 1924096 + }, + { + "epoch": 1.01, + "learning_rate": 1.849121080634161e-05, + "loss": 3.4175, + "step": 1924608 + }, + { + "epoch": 1.01, + "learning_rate": 1.848282485883109e-05, + "loss": 3.4158, + "step": 1925120 + }, + { + "epoch": 1.01, + "learning_rate": 1.847443891132057e-05, + "loss": 3.4166, + "step": 1925632 + }, + { + "epoch": 1.01, + "learning_rate": 1.846605296381005e-05, + "loss": 3.4204, + "step": 1926144 + }, + { + "epoch": 1.01, + "learning_rate": 1.845766701629953e-05, + "loss": 3.4227, + "step": 1926656 + }, + { + "epoch": 1.01, + "learning_rate": 1.8449281068789014e-05, + "loss": 3.4064, + "step": 1927168 + }, + { + "epoch": 1.01, + "learning_rate": 1.8440911500082223e-05, + "loss": 3.4085, + "step": 1927680 + }, + { + "epoch": 1.01, + "learning_rate": 1.8432541931375432e-05, + "loss": 3.4112, + "step": 1928192 + }, + { + "epoch": 1.01, + "learning_rate": 1.8424155983864912e-05, + "loss": 3.4118, + "step": 1928704 + }, + { + "epoch": 1.01, + "learning_rate": 1.8415770036354392e-05, + "loss": 3.4173, + "step": 1929216 + }, + { + "epoch": 1.01, + "learning_rate": 1.8407384088843875e-05, + "loss": 3.4163, + "step": 1929728 + }, + { + "epoch": 1.01, + "learning_rate": 1.8398998141333355e-05, + "loss": 3.4224, + "step": 1930240 + }, + { + "epoch": 1.01, + "learning_rate": 1.8390612193822835e-05, + "loss": 3.418, + "step": 1930752 + }, + { + "epoch": 1.01, + "learning_rate": 1.8382226246312315e-05, + "loss": 3.4183, + "step": 1931264 + }, + { + "epoch": 1.01, + "learning_rate": 1.837384029880179e-05, + "loss": 3.426, + "step": 1931776 + }, + { + "epoch": 1.01, + "learning_rate": 1.8365470730095004e-05, + "loss": 3.4109, + "step": 1932288 + }, + { + "epoch": 1.01, + "learning_rate": 1.8357084782584484e-05, + "loss": 3.3927, + "step": 1932800 + }, + { + "epoch": 1.01, + "learning_rate": 1.8348698835073964e-05, + "loss": 3.4295, + "step": 1933312 + }, + { + "epoch": 1.01, + "learning_rate": 1.8340312887563444e-05, + "loss": 3.4124, + "step": 1933824 + }, + { + "epoch": 1.01, + "learning_rate": 1.8331943318856657e-05, + "loss": 3.4185, + "step": 1934336 + }, + { + "epoch": 1.01, + "learning_rate": 1.8323557371346136e-05, + "loss": 3.4173, + "step": 1934848 + }, + { + "epoch": 1.01, + "learning_rate": 1.8315171423835613e-05, + "loss": 3.4079, + "step": 1935360 + }, + { + "epoch": 1.01, + "learning_rate": 1.830680185512883e-05, + "loss": 3.4049, + "step": 1935872 + }, + { + "epoch": 1.01, + "learning_rate": 1.829841590761831e-05, + "loss": 3.4101, + "step": 1936384 + }, + { + "epoch": 1.01, + "learning_rate": 1.8290029960107785e-05, + "loss": 3.4229, + "step": 1936896 + }, + { + "epoch": 1.01, + "learning_rate": 1.8281644012597265e-05, + "loss": 3.4163, + "step": 1937408 + }, + { + "epoch": 1.01, + "learning_rate": 1.8273258065086745e-05, + "loss": 3.4278, + "step": 1937920 + }, + { + "epoch": 1.01, + "learning_rate": 1.8264872117576225e-05, + "loss": 3.4137, + "step": 1938432 + }, + { + "epoch": 1.01, + "learning_rate": 1.8256486170065705e-05, + "loss": 3.4037, + "step": 1938944 + }, + { + "epoch": 1.01, + "learning_rate": 1.8248100222555185e-05, + "loss": 3.4282, + "step": 1939456 + }, + { + "epoch": 1.01, + "learning_rate": 1.8239730653848398e-05, + "loss": 3.4026, + "step": 1939968 + }, + { + "epoch": 1.01, + "learning_rate": 1.823136108514161e-05, + "loss": 3.4012, + "step": 1940480 + }, + { + "epoch": 1.01, + "learning_rate": 1.8222975137631087e-05, + "loss": 3.4149, + "step": 1940992 + }, + { + "epoch": 1.01, + "learning_rate": 1.8214589190120567e-05, + "loss": 3.4119, + "step": 1941504 + }, + { + "epoch": 1.01, + "learning_rate": 1.8206203242610047e-05, + "loss": 3.4086, + "step": 1942016 + }, + { + "epoch": 1.01, + "learning_rate": 1.819781729509953e-05, + "loss": 3.4101, + "step": 1942528 + }, + { + "epoch": 1.01, + "learning_rate": 1.818943134758901e-05, + "loss": 3.4077, + "step": 1943040 + }, + { + "epoch": 1.01, + "learning_rate": 1.818104540007849e-05, + "loss": 3.4204, + "step": 1943552 + }, + { + "epoch": 1.01, + "learning_rate": 1.81726758313717e-05, + "loss": 3.4209, + "step": 1944064 + }, + { + "epoch": 1.01, + "learning_rate": 1.816428988386118e-05, + "loss": 3.4163, + "step": 1944576 + }, + { + "epoch": 1.01, + "learning_rate": 1.815590393635066e-05, + "loss": 3.4233, + "step": 1945088 + }, + { + "epoch": 1.01, + "learning_rate": 1.814751798884014e-05, + "loss": 3.421, + "step": 1945600 + }, + { + "epoch": 1.01, + "learning_rate": 1.813914842013335e-05, + "loss": 3.4308, + "step": 1946112 + }, + { + "epoch": 1.01, + "learning_rate": 1.813076247262283e-05, + "loss": 3.4074, + "step": 1946624 + }, + { + "epoch": 1.01, + "learning_rate": 1.812237652511231e-05, + "loss": 3.4287, + "step": 1947136 + }, + { + "epoch": 1.01, + "learning_rate": 1.811399057760179e-05, + "loss": 3.4108, + "step": 1947648 + }, + { + "epoch": 1.01, + "learning_rate": 1.8105621008895e-05, + "loss": 3.4111, + "step": 1948160 + }, + { + "epoch": 1.01, + "learning_rate": 1.8097235061384484e-05, + "loss": 3.4187, + "step": 1948672 + }, + { + "epoch": 1.01, + "learning_rate": 1.8088849113873964e-05, + "loss": 3.4237, + "step": 1949184 + }, + { + "epoch": 1.01, + "learning_rate": 1.808046316636344e-05, + "loss": 3.4226, + "step": 1949696 + }, + { + "epoch": 1.01, + "learning_rate": 1.8072093597656653e-05, + "loss": 3.4279, + "step": 1950208 + }, + { + "epoch": 1.01, + "learning_rate": 1.8063707650146133e-05, + "loss": 3.4027, + "step": 1950720 + }, + { + "epoch": 1.01, + "learning_rate": 1.8055321702635613e-05, + "loss": 3.4014, + "step": 1951232 + }, + { + "epoch": 1.01, + "learning_rate": 1.8046935755125093e-05, + "loss": 3.4105, + "step": 1951744 + }, + { + "epoch": 1.01, + "learning_rate": 1.8038566186418305e-05, + "loss": 3.4219, + "step": 1952256 + }, + { + "epoch": 1.01, + "learning_rate": 1.8030180238907785e-05, + "loss": 3.4151, + "step": 1952768 + }, + { + "epoch": 1.01, + "learning_rate": 1.8021810670200994e-05, + "loss": 3.4133, + "step": 1953280 + }, + { + "epoch": 1.02, + "learning_rate": 1.8013424722690474e-05, + "loss": 3.4108, + "step": 1953792 + }, + { + "epoch": 1.02, + "learning_rate": 1.8005038775179954e-05, + "loss": 3.4138, + "step": 1954304 + }, + { + "epoch": 1.02, + "learning_rate": 1.7996652827669437e-05, + "loss": 3.4131, + "step": 1954816 + }, + { + "epoch": 1.02, + "learning_rate": 1.7988266880158914e-05, + "loss": 3.4128, + "step": 1955328 + }, + { + "epoch": 1.02, + "learning_rate": 1.7979880932648394e-05, + "loss": 3.4185, + "step": 1955840 + }, + { + "epoch": 1.02, + "learning_rate": 1.7971494985137874e-05, + "loss": 3.4214, + "step": 1956352 + }, + { + "epoch": 1.02, + "learning_rate": 1.7963109037627354e-05, + "loss": 3.4234, + "step": 1956864 + }, + { + "epoch": 1.02, + "learning_rate": 1.7954739468920563e-05, + "loss": 3.4134, + "step": 1957376 + }, + { + "epoch": 1.02, + "learning_rate": 1.7946353521410046e-05, + "loss": 3.4148, + "step": 1957888 + }, + { + "epoch": 1.02, + "learning_rate": 1.793798395270326e-05, + "loss": 3.4094, + "step": 1958400 + }, + { + "epoch": 1.02, + "learning_rate": 1.792959800519274e-05, + "loss": 3.4135, + "step": 1958912 + }, + { + "epoch": 1.02, + "learning_rate": 1.7921212057682215e-05, + "loss": 3.4179, + "step": 1959424 + }, + { + "epoch": 1.02, + "learning_rate": 1.7912826110171695e-05, + "loss": 3.4194, + "step": 1959936 + }, + { + "epoch": 1.02, + "learning_rate": 1.7904440162661175e-05, + "loss": 3.4073, + "step": 1960448 + }, + { + "epoch": 1.02, + "learning_rate": 1.7896054215150655e-05, + "loss": 3.401, + "step": 1960960 + }, + { + "epoch": 1.02, + "learning_rate": 1.788766826764014e-05, + "loss": 3.4205, + "step": 1961472 + }, + { + "epoch": 1.02, + "learning_rate": 1.787928232012962e-05, + "loss": 3.4068, + "step": 1961984 + }, + { + "epoch": 1.02, + "learning_rate": 1.7870912751422827e-05, + "loss": 3.3935, + "step": 1962496 + }, + { + "epoch": 1.02, + "learning_rate": 1.7862526803912307e-05, + "loss": 3.4163, + "step": 1963008 + }, + { + "epoch": 1.02, + "learning_rate": 1.7854140856401787e-05, + "loss": 3.4203, + "step": 1963520 + }, + { + "epoch": 1.02, + "learning_rate": 1.7845754908891267e-05, + "loss": 3.4138, + "step": 1964032 + }, + { + "epoch": 1.02, + "learning_rate": 1.783738534018448e-05, + "loss": 3.4035, + "step": 1964544 + }, + { + "epoch": 1.02, + "learning_rate": 1.782899939267396e-05, + "loss": 3.4143, + "step": 1965056 + }, + { + "epoch": 1.02, + "learning_rate": 1.782061344516344e-05, + "loss": 3.4145, + "step": 1965568 + }, + { + "epoch": 1.02, + "learning_rate": 1.781222749765292e-05, + "loss": 3.4006, + "step": 1966080 + }, + { + "epoch": 1.02, + "learning_rate": 1.780385792894613e-05, + "loss": 3.4271, + "step": 1966592 + }, + { + "epoch": 1.02, + "learning_rate": 1.779547198143561e-05, + "loss": 3.4214, + "step": 1967104 + }, + { + "epoch": 1.02, + "learning_rate": 1.7787086033925092e-05, + "loss": 3.4089, + "step": 1967616 + }, + { + "epoch": 1.02, + "learning_rate": 1.777870008641457e-05, + "loss": 3.4155, + "step": 1968128 + }, + { + "epoch": 1.02, + "learning_rate": 1.777033051770778e-05, + "loss": 3.4045, + "step": 1968640 + }, + { + "epoch": 1.02, + "learning_rate": 1.776194457019726e-05, + "loss": 3.4177, + "step": 1969152 + }, + { + "epoch": 1.02, + "learning_rate": 1.775357500149047e-05, + "loss": 3.4072, + "step": 1969664 + }, + { + "epoch": 1.02, + "learning_rate": 1.7745189053979954e-05, + "loss": 3.4137, + "step": 1970176 + }, + { + "epoch": 1.02, + "learning_rate": 1.7736803106469433e-05, + "loss": 3.4072, + "step": 1970688 + }, + { + "epoch": 1.02, + "learning_rate": 1.7728417158958913e-05, + "loss": 3.4159, + "step": 1971200 + }, + { + "epoch": 1.02, + "learning_rate": 1.772003121144839e-05, + "loss": 3.4118, + "step": 1971712 + }, + { + "epoch": 1.02, + "learning_rate": 1.771164526393787e-05, + "loss": 3.4124, + "step": 1972224 + }, + { + "epoch": 1.02, + "learning_rate": 1.770325931642735e-05, + "loss": 3.4057, + "step": 1972736 + }, + { + "epoch": 1.02, + "learning_rate": 1.769487336891683e-05, + "loss": 3.4116, + "step": 1973248 + }, + { + "epoch": 1.02, + "learning_rate": 1.7686503800210042e-05, + "loss": 3.4098, + "step": 1973760 + }, + { + "epoch": 1.02, + "learning_rate": 1.7678117852699522e-05, + "loss": 3.4192, + "step": 1974272 + }, + { + "epoch": 1.02, + "learning_rate": 1.7669731905189002e-05, + "loss": 3.4125, + "step": 1974784 + }, + { + "epoch": 1.02, + "learning_rate": 1.7661345957678482e-05, + "loss": 3.4253, + "step": 1975296 + }, + { + "epoch": 1.02, + "learning_rate": 1.765297638897169e-05, + "loss": 3.399, + "step": 1975808 + }, + { + "epoch": 1.02, + "learning_rate": 1.764459044146117e-05, + "loss": 3.4213, + "step": 1976320 + }, + { + "epoch": 1.02, + "learning_rate": 1.7636204493950655e-05, + "loss": 3.4156, + "step": 1976832 + }, + { + "epoch": 1.02, + "learning_rate": 1.7627818546440135e-05, + "loss": 3.4168, + "step": 1977344 + }, + { + "epoch": 1.02, + "learning_rate": 1.7619448977733344e-05, + "loss": 3.412, + "step": 1977856 + }, + { + "epoch": 1.02, + "learning_rate": 1.7611063030222824e-05, + "loss": 3.4111, + "step": 1978368 + }, + { + "epoch": 1.02, + "learning_rate": 1.7602677082712304e-05, + "loss": 3.4149, + "step": 1978880 + }, + { + "epoch": 1.02, + "learning_rate": 1.7594291135201784e-05, + "loss": 3.435, + "step": 1979392 + }, + { + "epoch": 1.02, + "learning_rate": 1.7585921566494996e-05, + "loss": 3.4001, + "step": 1979904 + }, + { + "epoch": 1.02, + "learning_rate": 1.7577535618984476e-05, + "loss": 3.4134, + "step": 1980416 + }, + { + "epoch": 1.02, + "learning_rate": 1.7569149671473956e-05, + "loss": 3.4091, + "step": 1980928 + }, + { + "epoch": 1.02, + "learning_rate": 1.7560763723963436e-05, + "loss": 3.4127, + "step": 1981440 + }, + { + "epoch": 1.02, + "learning_rate": 1.7552394155256645e-05, + "loss": 3.4098, + "step": 1981952 + }, + { + "epoch": 1.02, + "learning_rate": 1.7544008207746125e-05, + "loss": 3.4185, + "step": 1982464 + }, + { + "epoch": 1.02, + "learning_rate": 1.7535638639039337e-05, + "loss": 3.4159, + "step": 1982976 + }, + { + "epoch": 1.02, + "learning_rate": 1.7527252691528817e-05, + "loss": 3.4112, + "step": 1983488 + }, + { + "epoch": 1.02, + "learning_rate": 1.7518866744018297e-05, + "loss": 3.4113, + "step": 1984000 + }, + { + "epoch": 1.03, + "eval_loss": 3.8579909801483154, + "eval_runtime": 633.6991, + "eval_samples_per_second": 602.164, + "eval_steps_per_second": 18.818, + "step": 1984320 + }, + { + "epoch": 0.0, + "learning_rate": 1.7510480796507777e-05, + "loss": 3.4094, + "step": 1984512 + }, + { + "epoch": 0.0, + "learning_rate": 1.7502094848997257e-05, + "loss": 3.4075, + "step": 1985024 + }, + { + "epoch": 0.0, + "learning_rate": 1.7493708901486737e-05, + "loss": 3.4187, + "step": 1985536 + }, + { + "epoch": 0.0, + "learning_rate": 1.7485322953976217e-05, + "loss": 3.4201, + "step": 1986048 + }, + { + "epoch": 0.0, + "learning_rate": 1.747695338526943e-05, + "loss": 3.4214, + "step": 1986560 + }, + { + "epoch": 0.0, + "learning_rate": 1.746856743775891e-05, + "loss": 3.4118, + "step": 1987072 + }, + { + "epoch": 0.0, + "learning_rate": 1.746018149024839e-05, + "loss": 3.406, + "step": 1987584 + }, + { + "epoch": 0.0, + "learning_rate": 1.74518119215416e-05, + "loss": 3.4103, + "step": 1988096 + }, + { + "epoch": 0.0, + "learning_rate": 1.744342597403108e-05, + "loss": 3.4113, + "step": 1988608 + }, + { + "epoch": 0.0, + "learning_rate": 1.7435040026520562e-05, + "loss": 3.421, + "step": 1989120 + }, + { + "epoch": 0.0, + "learning_rate": 1.7426654079010042e-05, + "loss": 3.4134, + "step": 1989632 + }, + { + "epoch": 0.0, + "learning_rate": 1.741826813149952e-05, + "loss": 3.4161, + "step": 1990144 + }, + { + "epoch": 0.0, + "learning_rate": 1.740989856279273e-05, + "loss": 3.4243, + "step": 1990656 + }, + { + "epoch": 0.0, + "learning_rate": 1.740151261528221e-05, + "loss": 3.3961, + "step": 1991168 + }, + { + "epoch": 0.0, + "learning_rate": 1.739312666777169e-05, + "loss": 3.4198, + "step": 1991680 + }, + { + "epoch": 0.0, + "learning_rate": 1.738474072026117e-05, + "loss": 3.4006, + "step": 1992192 + }, + { + "epoch": 0.0, + "learning_rate": 1.737635477275065e-05, + "loss": 3.4016, + "step": 1992704 + }, + { + "epoch": 0.0, + "learning_rate": 1.736796882524013e-05, + "loss": 3.4041, + "step": 1993216 + }, + { + "epoch": 0.0, + "learning_rate": 1.735958287772961e-05, + "loss": 3.4071, + "step": 1993728 + }, + { + "epoch": 0.0, + "learning_rate": 1.735119693021909e-05, + "loss": 3.4155, + "step": 1994240 + }, + { + "epoch": 0.0, + "learning_rate": 1.73428273615123e-05, + "loss": 3.423, + "step": 1994752 + }, + { + "epoch": 0.0, + "learning_rate": 1.733444141400178e-05, + "loss": 3.4178, + "step": 1995264 + }, + { + "epoch": 0.0, + "learning_rate": 1.7326055466491263e-05, + "loss": 3.4037, + "step": 1995776 + }, + { + "epoch": 0.0, + "learning_rate": 1.7317669518980743e-05, + "loss": 3.4032, + "step": 1996288 + }, + { + "epoch": 0.0, + "learning_rate": 1.7309299950273952e-05, + "loss": 3.4123, + "step": 1996800 + }, + { + "epoch": 0.0, + "learning_rate": 1.7300914002763432e-05, + "loss": 3.4078, + "step": 1997312 + }, + { + "epoch": 0.0, + "learning_rate": 1.7292528055252912e-05, + "loss": 3.4, + "step": 1997824 + }, + { + "epoch": 0.0, + "learning_rate": 1.7284142107742392e-05, + "loss": 3.4161, + "step": 1998336 + }, + { + "epoch": 0.0, + "learning_rate": 1.7275772539035604e-05, + "loss": 3.4005, + "step": 1998848 + }, + { + "epoch": 0.0, + "learning_rate": 1.7267386591525084e-05, + "loss": 3.4109, + "step": 1999360 + }, + { + "epoch": 0.01, + "learning_rate": 1.7259017022818294e-05, + "loss": 3.4007, + "step": 1999872 + }, + { + "epoch": 0.01, + "learning_rate": 1.7250631075307773e-05, + "loss": 3.4189, + "step": 2000384 + }, + { + "epoch": 0.01, + "learning_rate": 1.7242245127797253e-05, + "loss": 3.4113, + "step": 2000896 + }, + { + "epoch": 0.01, + "learning_rate": 1.7233859180286733e-05, + "loss": 3.4035, + "step": 2001408 + }, + { + "epoch": 0.01, + "learning_rate": 1.7225473232776217e-05, + "loss": 3.4109, + "step": 2001920 + }, + { + "epoch": 0.01, + "learning_rate": 1.7217087285265697e-05, + "loss": 3.4027, + "step": 2002432 + }, + { + "epoch": 0.01, + "learning_rate": 1.7208701337755173e-05, + "loss": 3.4153, + "step": 2002944 + }, + { + "epoch": 0.01, + "learning_rate": 1.7200315390244653e-05, + "loss": 3.4014, + "step": 2003456 + }, + { + "epoch": 0.01, + "learning_rate": 1.7191945821537866e-05, + "loss": 3.3944, + "step": 2003968 + }, + { + "epoch": 0.01, + "learning_rate": 1.7183576252831078e-05, + "loss": 3.3993, + "step": 2004480 + }, + { + "epoch": 0.01, + "learning_rate": 1.7175190305320558e-05, + "loss": 3.4082, + "step": 2004992 + }, + { + "epoch": 0.01, + "learning_rate": 1.7166804357810038e-05, + "loss": 3.4036, + "step": 2005504 + }, + { + "epoch": 0.01, + "learning_rate": 1.7158418410299518e-05, + "loss": 3.4044, + "step": 2006016 + }, + { + "epoch": 0.01, + "learning_rate": 1.7150032462788998e-05, + "loss": 3.4123, + "step": 2006528 + }, + { + "epoch": 0.01, + "learning_rate": 1.7141646515278475e-05, + "loss": 3.4084, + "step": 2007040 + }, + { + "epoch": 0.01, + "learning_rate": 1.7133260567767955e-05, + "loss": 3.4091, + "step": 2007552 + }, + { + "epoch": 0.01, + "learning_rate": 1.7124874620257434e-05, + "loss": 3.4192, + "step": 2008064 + }, + { + "epoch": 0.01, + "learning_rate": 1.7116505051550647e-05, + "loss": 3.4004, + "step": 2008576 + }, + { + "epoch": 0.01, + "learning_rate": 1.7108119104040127e-05, + "loss": 3.3791, + "step": 2009088 + }, + { + "epoch": 0.01, + "learning_rate": 1.7099733156529607e-05, + "loss": 3.4202, + "step": 2009600 + }, + { + "epoch": 0.01, + "learning_rate": 1.7091347209019087e-05, + "loss": 3.4018, + "step": 2010112 + }, + { + "epoch": 0.01, + "learning_rate": 1.70829776403123e-05, + "loss": 3.4089, + "step": 2010624 + }, + { + "epoch": 0.01, + "learning_rate": 1.707459169280178e-05, + "loss": 3.4027, + "step": 2011136 + }, + { + "epoch": 0.01, + "learning_rate": 1.706620574529126e-05, + "loss": 3.4029, + "step": 2011648 + }, + { + "epoch": 0.01, + "learning_rate": 1.705783617658447e-05, + "loss": 3.395, + "step": 2012160 + }, + { + "epoch": 0.01, + "learning_rate": 1.7049450229073948e-05, + "loss": 3.3985, + "step": 2012672 + }, + { + "epoch": 0.01, + "learning_rate": 1.7041064281563428e-05, + "loss": 3.4158, + "step": 2013184 + }, + { + "epoch": 0.01, + "learning_rate": 1.7032678334052908e-05, + "loss": 3.4036, + "step": 2013696 + }, + { + "epoch": 0.01, + "learning_rate": 1.7024292386542388e-05, + "loss": 3.4198, + "step": 2014208 + }, + { + "epoch": 0.01, + "learning_rate": 1.701590643903187e-05, + "loss": 3.4041, + "step": 2014720 + }, + { + "epoch": 0.01, + "learning_rate": 1.700752049152135e-05, + "loss": 3.3918, + "step": 2015232 + }, + { + "epoch": 0.01, + "learning_rate": 1.6999134544010828e-05, + "loss": 3.4165, + "step": 2015744 + }, + { + "epoch": 0.01, + "learning_rate": 1.699076497530404e-05, + "loss": 3.4, + "step": 2016256 + }, + { + "epoch": 0.01, + "learning_rate": 1.698239540659725e-05, + "loss": 3.3863, + "step": 2016768 + }, + { + "epoch": 0.01, + "learning_rate": 1.6974009459086733e-05, + "loss": 3.4044, + "step": 2017280 + }, + { + "epoch": 0.01, + "learning_rate": 1.6965623511576213e-05, + "loss": 3.4032, + "step": 2017792 + }, + { + "epoch": 0.01, + "learning_rate": 1.6957237564065693e-05, + "loss": 3.3961, + "step": 2018304 + }, + { + "epoch": 0.01, + "learning_rate": 1.6948851616555173e-05, + "loss": 3.3991, + "step": 2018816 + }, + { + "epoch": 0.01, + "learning_rate": 1.694046566904465e-05, + "loss": 3.3967, + "step": 2019328 + }, + { + "epoch": 0.01, + "learning_rate": 1.693207972153413e-05, + "loss": 3.4078, + "step": 2019840 + }, + { + "epoch": 0.01, + "learning_rate": 1.692369377402361e-05, + "loss": 3.4137, + "step": 2020352 + }, + { + "epoch": 0.01, + "learning_rate": 1.6915324205316825e-05, + "loss": 3.4026, + "step": 2020864 + }, + { + "epoch": 0.01, + "learning_rate": 1.6906938257806302e-05, + "loss": 3.4129, + "step": 2021376 + }, + { + "epoch": 0.01, + "learning_rate": 1.689855231029578e-05, + "loss": 3.4096, + "step": 2021888 + }, + { + "epoch": 0.01, + "learning_rate": 1.6890182741588994e-05, + "loss": 3.4211, + "step": 2022400 + }, + { + "epoch": 0.01, + "learning_rate": 1.6881796794078474e-05, + "loss": 3.3973, + "step": 2022912 + }, + { + "epoch": 0.01, + "learning_rate": 1.6873410846567954e-05, + "loss": 3.4201, + "step": 2023424 + }, + { + "epoch": 0.01, + "learning_rate": 1.6865024899057434e-05, + "loss": 3.3995, + "step": 2023936 + }, + { + "epoch": 0.01, + "learning_rate": 1.6856655330350647e-05, + "loss": 3.3987, + "step": 2024448 + }, + { + "epoch": 0.01, + "learning_rate": 1.6848269382840123e-05, + "loss": 3.4134, + "step": 2024960 + }, + { + "epoch": 0.01, + "learning_rate": 1.6839883435329603e-05, + "loss": 3.4086, + "step": 2025472 + }, + { + "epoch": 0.01, + "learning_rate": 1.6831513866622816e-05, + "loss": 3.4157, + "step": 2025984 + }, + { + "epoch": 0.01, + "learning_rate": 1.6823127919112295e-05, + "loss": 3.4177, + "step": 2026496 + }, + { + "epoch": 0.01, + "learning_rate": 1.6814741971601775e-05, + "loss": 3.3948, + "step": 2027008 + }, + { + "epoch": 0.01, + "learning_rate": 1.6806356024091255e-05, + "loss": 3.3903, + "step": 2027520 + }, + { + "epoch": 0.01, + "learning_rate": 1.6797986455384468e-05, + "loss": 3.4003, + "step": 2028032 + }, + { + "epoch": 0.01, + "learning_rate": 1.6789600507873948e-05, + "loss": 3.4166, + "step": 2028544 + }, + { + "epoch": 0.01, + "learning_rate": 1.6781214560363424e-05, + "loss": 3.4023, + "step": 2029056 + }, + { + "epoch": 0.01, + "learning_rate": 1.6772828612852908e-05, + "loss": 3.4032, + "step": 2029568 + }, + { + "epoch": 0.01, + "learning_rate": 1.6764442665342388e-05, + "loss": 3.407, + "step": 2030080 + }, + { + "epoch": 0.02, + "learning_rate": 1.6756056717831868e-05, + "loss": 3.3963, + "step": 2030592 + }, + { + "epoch": 0.02, + "learning_rate": 1.6747670770321348e-05, + "loss": 3.4077, + "step": 2031104 + }, + { + "epoch": 0.02, + "learning_rate": 1.6739284822810828e-05, + "loss": 3.4013, + "step": 2031616 + }, + { + "epoch": 0.02, + "learning_rate": 1.6730915254104037e-05, + "loss": 3.4103, + "step": 2032128 + }, + { + "epoch": 0.02, + "learning_rate": 1.6722529306593517e-05, + "loss": 3.4097, + "step": 2032640 + }, + { + "epoch": 0.02, + "learning_rate": 1.6714143359082997e-05, + "loss": 3.4149, + "step": 2033152 + }, + { + "epoch": 0.02, + "learning_rate": 1.670575741157248e-05, + "loss": 3.3984, + "step": 2033664 + }, + { + "epoch": 0.02, + "learning_rate": 1.669738784286569e-05, + "loss": 3.4079, + "step": 2034176 + }, + { + "epoch": 0.02, + "learning_rate": 1.668900189535517e-05, + "loss": 3.3974, + "step": 2034688 + }, + { + "epoch": 0.02, + "learning_rate": 1.668061594784465e-05, + "loss": 3.4066, + "step": 2035200 + }, + { + "epoch": 0.02, + "learning_rate": 1.667223000033413e-05, + "loss": 3.41, + "step": 2035712 + }, + { + "epoch": 0.02, + "learning_rate": 1.666386043162734e-05, + "loss": 3.4046, + "step": 2036224 + }, + { + "epoch": 0.02, + "learning_rate": 1.665547448411682e-05, + "loss": 3.3995, + "step": 2036736 + }, + { + "epoch": 0.02, + "learning_rate": 1.66470885366063e-05, + "loss": 3.3927, + "step": 2037248 + }, + { + "epoch": 0.02, + "learning_rate": 1.663871896789951e-05, + "loss": 3.4071, + "step": 2037760 + }, + { + "epoch": 0.02, + "learning_rate": 1.663033302038899e-05, + "loss": 3.3998, + "step": 2038272 + }, + { + "epoch": 0.02, + "learning_rate": 1.662194707287847e-05, + "loss": 3.3836, + "step": 2038784 + }, + { + "epoch": 0.02, + "learning_rate": 1.661356112536795e-05, + "loss": 3.4075, + "step": 2039296 + }, + { + "epoch": 0.02, + "learning_rate": 1.660517517785743e-05, + "loss": 3.406, + "step": 2039808 + }, + { + "epoch": 0.02, + "learning_rate": 1.659678923034691e-05, + "loss": 3.4033, + "step": 2040320 + }, + { + "epoch": 0.02, + "learning_rate": 1.658840328283639e-05, + "loss": 3.3964, + "step": 2040832 + }, + { + "epoch": 0.02, + "learning_rate": 1.6580033714129603e-05, + "loss": 3.4035, + "step": 2041344 + }, + { + "epoch": 0.02, + "learning_rate": 1.657164776661908e-05, + "loss": 3.4034, + "step": 2041856 + }, + { + "epoch": 0.02, + "learning_rate": 1.6563261819108562e-05, + "loss": 3.3921, + "step": 2042368 + }, + { + "epoch": 0.02, + "learning_rate": 1.6554875871598042e-05, + "loss": 3.4178, + "step": 2042880 + }, + { + "epoch": 0.02, + "learning_rate": 1.654650630289125e-05, + "loss": 3.4094, + "step": 2043392 + }, + { + "epoch": 0.02, + "learning_rate": 1.653812035538073e-05, + "loss": 3.3989, + "step": 2043904 + }, + { + "epoch": 0.02, + "learning_rate": 1.652973440787021e-05, + "loss": 3.4073, + "step": 2044416 + }, + { + "epoch": 0.02, + "learning_rate": 1.652134846035969e-05, + "loss": 3.396, + "step": 2044928 + }, + { + "epoch": 0.02, + "learning_rate": 1.6512978891652904e-05, + "loss": 3.4063, + "step": 2045440 + }, + { + "epoch": 0.02, + "learning_rate": 1.6504592944142384e-05, + "loss": 3.3987, + "step": 2045952 + }, + { + "epoch": 0.02, + "learning_rate": 1.6496206996631864e-05, + "loss": 3.3993, + "step": 2046464 + }, + { + "epoch": 0.02, + "learning_rate": 1.6487821049121344e-05, + "loss": 3.4018, + "step": 2046976 + }, + { + "epoch": 0.02, + "learning_rate": 1.6479451480414553e-05, + "loss": 3.4024, + "step": 2047488 + }, + { + "epoch": 0.02, + "learning_rate": 1.6471065532904033e-05, + "loss": 3.4032, + "step": 2048000 + }, + { + "epoch": 0.02, + "learning_rate": 1.6462679585393516e-05, + "loss": 3.4013, + "step": 2048512 + }, + { + "epoch": 0.02, + "learning_rate": 1.6454293637882996e-05, + "loss": 3.4004, + "step": 2049024 + }, + { + "epoch": 0.02, + "learning_rate": 1.6445924069176205e-05, + "loss": 3.3969, + "step": 2049536 + }, + { + "epoch": 0.02, + "learning_rate": 1.6437538121665685e-05, + "loss": 3.4011, + "step": 2050048 + }, + { + "epoch": 0.02, + "learning_rate": 1.6429152174155165e-05, + "loss": 3.4112, + "step": 2050560 + }, + { + "epoch": 0.02, + "learning_rate": 1.6420766226644645e-05, + "loss": 3.4042, + "step": 2051072 + }, + { + "epoch": 0.02, + "learning_rate": 1.6412396657937858e-05, + "loss": 3.4147, + "step": 2051584 + }, + { + "epoch": 0.02, + "learning_rate": 1.6404010710427338e-05, + "loss": 3.3858, + "step": 2052096 + }, + { + "epoch": 0.02, + "learning_rate": 1.6395624762916817e-05, + "loss": 3.4152, + "step": 2052608 + }, + { + "epoch": 0.02, + "learning_rate": 1.6387238815406297e-05, + "loss": 3.4049, + "step": 2053120 + }, + { + "epoch": 0.02, + "learning_rate": 1.6378869246699507e-05, + "loss": 3.405, + "step": 2053632 + }, + { + "epoch": 0.02, + "learning_rate": 1.6370483299188986e-05, + "loss": 3.4041, + "step": 2054144 + }, + { + "epoch": 0.02, + "learning_rate": 1.636209735167847e-05, + "loss": 3.3969, + "step": 2054656 + }, + { + "epoch": 0.02, + "learning_rate": 1.635371140416795e-05, + "loss": 3.4062, + "step": 2055168 + }, + { + "epoch": 0.02, + "learning_rate": 1.634534183546116e-05, + "loss": 3.4222, + "step": 2055680 + }, + { + "epoch": 0.02, + "learning_rate": 1.633695588795064e-05, + "loss": 3.3925, + "step": 2056192 + }, + { + "epoch": 0.02, + "learning_rate": 1.632856994044012e-05, + "loss": 3.4055, + "step": 2056704 + }, + { + "epoch": 0.02, + "learning_rate": 1.63201839929296e-05, + "loss": 3.3984, + "step": 2057216 + }, + { + "epoch": 0.02, + "learning_rate": 1.631181442422281e-05, + "loss": 3.403, + "step": 2057728 + }, + { + "epoch": 0.02, + "learning_rate": 1.630342847671229e-05, + "loss": 3.3993, + "step": 2058240 + }, + { + "epoch": 0.02, + "learning_rate": 1.629504252920177e-05, + "loss": 3.4073, + "step": 2058752 + }, + { + "epoch": 0.02, + "learning_rate": 1.628665658169125e-05, + "loss": 3.4077, + "step": 2059264 + }, + { + "epoch": 0.02, + "learning_rate": 1.627828701298446e-05, + "loss": 3.4032, + "step": 2059776 + }, + { + "epoch": 0.02, + "learning_rate": 1.626990106547394e-05, + "loss": 3.4005, + "step": 2060288 + }, + { + "epoch": 0.03, + "eval_loss": 3.859920024871826, + "eval_runtime": 302.96, + "eval_samples_per_second": 1259.543, + "eval_steps_per_second": 39.362, + "step": 2060640 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 1.440177644408316e+18, + "trial_name": null, + "trial_params": null +}