diff --git "a/checkpoint-1602710/trainer_state.json" "b/checkpoint-1602710/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-1602710/trainer_state.json" @@ -0,0 +1,18973 @@ +{ + "best_metric": 3.845362424850464, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/rel-cl/transformer/3/checkpoints/checkpoint-915830", + "epoch": 0.025000606015738065, + "eval_steps": 10, + "global_step": 1602710, + "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": 10.9675, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 6.8442, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 6.2012, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 5.9806, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 5.8323, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 5.7129, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 5.6086, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 5.5465, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 5.4913, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 5.4143, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 5.3845, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 5.3436, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989936862987376e-05, + "loss": 5.2855, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989098268236324e-05, + "loss": 5.2356, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988259673485272e-05, + "loss": 5.2099, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.98742107873422e-05, + "loss": 5.179, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986582483983168e-05, + "loss": 5.1463, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985745527112489e-05, + "loss": 5.1011, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984906932361437e-05, + "loss": 5.0832, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.053, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 5.0275, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.982391148108281e-05, + "loss": 5.0107, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.981552553357229e-05, + "loss": 4.9884, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.9807155964865506e-05, + "loss": 4.9628, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 4.9434, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790384069844466e-05, + "loss": 4.9274, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9781998122333946e-05, + "loss": 4.9014, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773612174823426e-05, + "loss": 4.8911, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.97652262273129e-05, + "loss": 4.8564, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756856658606115e-05, + "loss": 4.86, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748470711095595e-05, + "loss": 4.8264, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.974008476358507e-05, + "loss": 4.8159, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.973169881607455e-05, + "loss": 4.8184, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.9723329247367764e-05, + "loss": 4.8007, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.9714943299857244e-05, + "loss": 4.7742, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.9706557352346724e-05, + "loss": 4.7608, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.9698171404836204e-05, + "loss": 4.7629, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968980183612942e-05, + "loss": 4.7439, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.968143226742263e-05, + "loss": 4.733, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967304631991211e-05, + "loss": 4.718, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966466037240159e-05, + "loss": 4.6988, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965627442489107e-05, + "loss": 4.6883, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964788847738054e-05, + "loss": 4.6767, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963950252987002e-05, + "loss": 4.6765, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.96311165823595e-05, + "loss": 4.6665, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962274701365272e-05, + "loss": 4.6614, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.96143610661422e-05, + "loss": 4.646, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960597511863168e-05, + "loss": 4.6418, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.959758917112116e-05, + "loss": 4.6451, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.958920322361064e-05, + "loss": 4.6211, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958083365490385e-05, + "loss": 4.615, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957244770739333e-05, + "loss": 4.6033, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956406175988281e-05, + "loss": 4.6149, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.955567581237229e-05, + "loss": 4.5787, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.9547306243665496e-05, + "loss": 4.5958, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.9538920296154976e-05, + "loss": 4.5704, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.9530534348644456e-05, + "loss": 4.5678, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.9522148401133936e-05, + "loss": 4.5701, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951376245362342e-05, + "loss": 4.5601, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.950539288491663e-05, + "loss": 4.5459, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949700693740611e-05, + "loss": 4.5362, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948862098989559e-05, + "loss": 4.5251, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.948023504238507e-05, + "loss": 4.5374, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947186547367828e-05, + "loss": 4.5237, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946347952616776e-05, + "loss": 4.5137, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945509357865724e-05, + "loss": 4.5123, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944670763114672e-05, + "loss": 4.5038, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.94383216836362e-05, + "loss": 4.4844, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942995211492941e-05, + "loss": 4.506, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.9421582546222625e-05, + "loss": 4.4831, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.9413196598712105e-05, + "loss": 4.4796, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.9404810651201585e-05, + "loss": 4.4907, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396424703691065e-05, + "loss": 4.4678, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388038756180545e-05, + "loss": 4.4832, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379652808670025e-05, + "loss": 4.4781, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371266861159505e-05, + "loss": 4.4666, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.9362897292452714e-05, + "loss": 4.4697, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.9354511344942194e-05, + "loss": 4.4446, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.9346125397431674e-05, + "loss": 4.4413, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.9337739449921154e-05, + "loss": 4.4438, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.9329353502410634e-05, + "loss": 4.446, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.9320967554900114e-05, + "loss": 4.4378, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.9312581607389594e-05, + "loss": 4.4216, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.9304195659879074e-05, + "loss": 4.4131, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.929582609117229e-05, + "loss": 4.4157, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.92874565224655e-05, + "loss": 4.418, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.927907057495498e-05, + "loss": 4.4178, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.927068462744446e-05, + "loss": 4.4195, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.926229867993394e-05, + "loss": 4.4155, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925391273242342e-05, + "loss": 4.4014, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.924554316371663e-05, + "loss": 4.3891, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923715721620611e-05, + "loss": 4.3868, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922877126869559e-05, + "loss": 4.3937, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.922038532118507e-05, + "loss": 4.3902, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921199937367455e-05, + "loss": 4.3725, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920361342616403e-05, + "loss": 4.3762, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919524385745724e-05, + "loss": 4.3777, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918685790994672e-05, + "loss": 4.3801, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.91784719624362e-05, + "loss": 4.3747, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.9170086014925676e-05, + "loss": 4.3714, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.9161700067415156e-05, + "loss": 4.3722, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.9153314119904636e-05, + "loss": 4.3612, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.9144928172394116e-05, + "loss": 4.361, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.9136542224883596e-05, + "loss": 4.3674, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.912818903498054e-05, + "loss": 4.3497, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.911980308747002e-05, + "loss": 4.3561, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.91114171399595e-05, + "loss": 4.3367, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.910303119244898e-05, + "loss": 4.3325, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.909464524493846e-05, + "loss": 4.333, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908625929742794e-05, + "loss": 4.34, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907788972872115e-05, + "loss": 4.3349, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.906950378121063e-05, + "loss": 4.3127, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906111783370011e-05, + "loss": 4.3165, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.905273188618959e-05, + "loss": 4.3257, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.904434593867907e-05, + "loss": 4.3343, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903597636997228e-05, + "loss": 4.3187, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.902759042246176e-05, + "loss": 4.3251, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.901920447495124e-05, + "loss": 4.3164, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.901081852744072e-05, + "loss": 4.318, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.90024325799302e-05, + "loss": 4.3093, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.8994046632419686e-05, + "loss": 4.304, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.8985660684909166e-05, + "loss": 4.2982, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.8977274737398646e-05, + "loss": 4.3054, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968905168691855e-05, + "loss": 4.2896, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.8960519221181335e-05, + "loss": 4.3007, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.8952133273670815e-05, + "loss": 4.2915, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.8943747326160294e-05, + "loss": 4.3014, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.8935377757453504e-05, + "loss": 4.2771, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.892700818874671e-05, + "loss": 4.2887, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.891862224123619e-05, + "loss": 4.2973, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.891023629372567e-05, + "loss": 4.2753, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.890185034621515e-05, + "loss": 4.2934, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.889346439870464e-05, + "loss": 4.2797, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888507845119412e-05, + "loss": 4.2806, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.88766925036836e-05, + "loss": 4.2737, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886832293497681e-05, + "loss": 4.2675, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885993698746629e-05, + "loss": 4.2702, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.885155103995577e-05, + "loss": 4.2759, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884318147124898e-05, + "loss": 4.2784, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883479552373846e-05, + "loss": 4.2678, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882640957622794e-05, + "loss": 4.2718, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.881802362871742e-05, + "loss": 4.2645, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.88096376812069e-05, + "loss": 4.252, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.880125173369638e-05, + "loss": 4.26, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.879286578618586e-05, + "loss": 4.2477, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.878449621747907e-05, + "loss": 4.2511, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877611026996855e-05, + "loss": 4.2488, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.876772432245803e-05, + "loss": 4.2454, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875933837494751e-05, + "loss": 4.2428, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.8750952427436986e-05, + "loss": 4.2434, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.205959320068359, + "eval_runtime": 565.7702, + "eval_samples_per_second": 674.463, + "eval_steps_per_second": 21.077, + "step": 76319 + }, + { + "epoch": 0.0, + "learning_rate": 4.87425828587302e-05, + "loss": 4.2475, + "step": 76800 + }, + { + "epoch": 0.0, + "learning_rate": 4.873419691121968e-05, + "loss": 4.2426, + "step": 77312 + }, + { + "epoch": 0.0, + "learning_rate": 4.872581096370916e-05, + "loss": 4.2332, + "step": 77824 + }, + { + "epoch": 0.0, + "learning_rate": 4.8717425016198635e-05, + "loss": 4.2346, + "step": 78336 + }, + { + "epoch": 0.0, + "learning_rate": 4.8709039068688115e-05, + "loss": 4.2327, + "step": 78848 + }, + { + "epoch": 0.0, + "learning_rate": 4.8700653121177595e-05, + "loss": 4.2101, + "step": 79360 + }, + { + "epoch": 0.0, + "learning_rate": 4.8692267173667075e-05, + "loss": 4.2252, + "step": 79872 + }, + { + "epoch": 0.0, + "learning_rate": 4.8683881226156555e-05, + "loss": 4.223, + "step": 80384 + }, + { + "epoch": 0.0, + "learning_rate": 4.867549527864604e-05, + "loss": 4.2142, + "step": 80896 + }, + { + "epoch": 0.0, + "learning_rate": 4.866712570993925e-05, + "loss": 4.2241, + "step": 81408 + }, + { + "epoch": 0.0, + "learning_rate": 4.865873976242873e-05, + "loss": 4.2248, + "step": 81920 + }, + { + "epoch": 0.0, + "learning_rate": 4.865035381491821e-05, + "loss": 4.2106, + "step": 82432 + }, + { + "epoch": 0.0, + "learning_rate": 4.864196786740769e-05, + "loss": 4.2068, + "step": 82944 + }, + { + "epoch": 0.0, + "learning_rate": 4.863358191989717e-05, + "loss": 4.2103, + "step": 83456 + }, + { + "epoch": 0.0, + "learning_rate": 4.862519597238665e-05, + "loss": 4.2078, + "step": 83968 + }, + { + "epoch": 0.0, + "learning_rate": 4.861681002487613e-05, + "loss": 4.1978, + "step": 84480 + }, + { + "epoch": 0.0, + "learning_rate": 4.860842407736561e-05, + "loss": 4.2011, + "step": 84992 + }, + { + "epoch": 0.0, + "learning_rate": 4.860003812985509e-05, + "loss": 4.2003, + "step": 85504 + }, + { + "epoch": 0.0, + "learning_rate": 4.859165218234457e-05, + "loss": 4.1976, + "step": 86016 + }, + { + "epoch": 0.0, + "learning_rate": 4.858326623483405e-05, + "loss": 4.2016, + "step": 86528 + }, + { + "epoch": 0.0, + "learning_rate": 4.857488028732352e-05, + "loss": 4.1995, + "step": 87040 + }, + { + "epoch": 0.0, + "learning_rate": 4.856651071861674e-05, + "loss": 4.1999, + "step": 87552 + }, + { + "epoch": 0.0, + "learning_rate": 4.8558124771106226e-05, + "loss": 4.1955, + "step": 88064 + }, + { + "epoch": 0.0, + "learning_rate": 4.8549755202399435e-05, + "loss": 4.1936, + "step": 88576 + }, + { + "epoch": 0.0, + "learning_rate": 4.8541369254888915e-05, + "loss": 4.1926, + "step": 89088 + }, + { + "epoch": 0.0, + "learning_rate": 4.8532983307378395e-05, + "loss": 4.1859, + "step": 89600 + }, + { + "epoch": 0.0, + "learning_rate": 4.8524597359867875e-05, + "loss": 4.1931, + "step": 90112 + }, + { + "epoch": 0.0, + "learning_rate": 4.851621141235735e-05, + "loss": 4.1735, + "step": 90624 + }, + { + "epoch": 0.0, + "learning_rate": 4.8507841843650564e-05, + "loss": 4.1868, + "step": 91136 + }, + { + "epoch": 0.01, + "learning_rate": 4.8499455896140044e-05, + "loss": 4.1705, + "step": 91648 + }, + { + "epoch": 0.01, + "learning_rate": 4.8491069948629524e-05, + "loss": 4.1747, + "step": 92160 + }, + { + "epoch": 0.01, + "learning_rate": 4.8482684001119e-05, + "loss": 4.1838, + "step": 92672 + }, + { + "epoch": 0.01, + "learning_rate": 4.847429805360848e-05, + "loss": 4.1834, + "step": 93184 + }, + { + "epoch": 0.01, + "learning_rate": 4.8465912106097964e-05, + "loss": 4.1698, + "step": 93696 + }, + { + "epoch": 0.01, + "learning_rate": 4.8457526158587444e-05, + "loss": 4.1657, + "step": 94208 + }, + { + "epoch": 0.01, + "learning_rate": 4.844915658988065e-05, + "loss": 4.178, + "step": 94720 + }, + { + "epoch": 0.01, + "learning_rate": 4.844077064237013e-05, + "loss": 4.1706, + "step": 95232 + }, + { + "epoch": 0.01, + "learning_rate": 4.843238469485961e-05, + "loss": 4.1692, + "step": 95744 + }, + { + "epoch": 0.01, + "learning_rate": 4.842399874734909e-05, + "loss": 4.1629, + "step": 96256 + }, + { + "epoch": 0.01, + "learning_rate": 4.841561279983857e-05, + "loss": 4.1518, + "step": 96768 + }, + { + "epoch": 0.01, + "learning_rate": 4.840722685232805e-05, + "loss": 4.1496, + "step": 97280 + }, + { + "epoch": 0.01, + "learning_rate": 4.839884090481753e-05, + "loss": 4.1509, + "step": 97792 + }, + { + "epoch": 0.01, + "learning_rate": 4.839045495730701e-05, + "loss": 4.1601, + "step": 98304 + }, + { + "epoch": 0.01, + "learning_rate": 4.838208538860022e-05, + "loss": 4.1478, + "step": 98816 + }, + { + "epoch": 0.01, + "learning_rate": 4.83736994410897e-05, + "loss": 4.1522, + "step": 99328 + }, + { + "epoch": 0.01, + "learning_rate": 4.836531349357918e-05, + "loss": 4.1496, + "step": 99840 + }, + { + "epoch": 0.01, + "learning_rate": 4.83569439248724e-05, + "loss": 4.1507, + "step": 100352 + }, + { + "epoch": 0.01, + "learning_rate": 4.834855797736188e-05, + "loss": 4.1597, + "step": 100864 + }, + { + "epoch": 0.01, + "learning_rate": 4.834017202985136e-05, + "loss": 4.1399, + "step": 101376 + }, + { + "epoch": 0.01, + "learning_rate": 4.833178608234084e-05, + "loss": 4.1442, + "step": 101888 + }, + { + "epoch": 0.01, + "learning_rate": 4.832340013483032e-05, + "loss": 4.1353, + "step": 102400 + }, + { + "epoch": 0.01, + "learning_rate": 4.8315030566123526e-05, + "loss": 4.1579, + "step": 102912 + }, + { + "epoch": 0.01, + "learning_rate": 4.8306644618613006e-05, + "loss": 4.1281, + "step": 103424 + }, + { + "epoch": 0.01, + "learning_rate": 4.8298258671102486e-05, + "loss": 4.1438, + "step": 103936 + }, + { + "epoch": 0.01, + "learning_rate": 4.8289872723591966e-05, + "loss": 4.1271, + "step": 104448 + }, + { + "epoch": 0.01, + "learning_rate": 4.8281503154885175e-05, + "loss": 4.1349, + "step": 104960 + }, + { + "epoch": 0.01, + "learning_rate": 4.8273117207374655e-05, + "loss": 4.1364, + "step": 105472 + }, + { + "epoch": 0.01, + "learning_rate": 4.8264731259864135e-05, + "loss": 4.1352, + "step": 105984 + }, + { + "epoch": 0.01, + "learning_rate": 4.8256345312353615e-05, + "loss": 4.1261, + "step": 106496 + }, + { + "epoch": 0.01, + "learning_rate": 4.8247959364843095e-05, + "loss": 4.1261, + "step": 107008 + }, + { + "epoch": 0.01, + "learning_rate": 4.823957341733258e-05, + "loss": 4.1123, + "step": 107520 + }, + { + "epoch": 0.01, + "learning_rate": 4.823118746982206e-05, + "loss": 4.1303, + "step": 108032 + }, + { + "epoch": 0.01, + "learning_rate": 4.822281790111527e-05, + "loss": 4.1252, + "step": 108544 + }, + { + "epoch": 0.01, + "learning_rate": 4.821443195360475e-05, + "loss": 4.1197, + "step": 109056 + }, + { + "epoch": 0.01, + "learning_rate": 4.820604600609423e-05, + "loss": 4.1174, + "step": 109568 + }, + { + "epoch": 0.01, + "learning_rate": 4.819766005858371e-05, + "loss": 4.1198, + "step": 110080 + }, + { + "epoch": 0.01, + "learning_rate": 4.8189274111073184e-05, + "loss": 4.1012, + "step": 110592 + }, + { + "epoch": 0.01, + "learning_rate": 4.81809045423664e-05, + "loss": 4.1235, + "step": 111104 + }, + { + "epoch": 0.01, + "learning_rate": 4.817251859485588e-05, + "loss": 4.107, + "step": 111616 + }, + { + "epoch": 0.01, + "learning_rate": 4.816413264734535e-05, + "loss": 4.111, + "step": 112128 + }, + { + "epoch": 0.01, + "learning_rate": 4.815574669983483e-05, + "loss": 4.1198, + "step": 112640 + }, + { + "epoch": 0.01, + "learning_rate": 4.814737713112805e-05, + "loss": 4.1071, + "step": 113152 + }, + { + "epoch": 0.01, + "learning_rate": 4.8138991183617535e-05, + "loss": 4.1186, + "step": 113664 + }, + { + "epoch": 0.01, + "learning_rate": 4.813060523610701e-05, + "loss": 4.1231, + "step": 114176 + }, + { + "epoch": 0.01, + "learning_rate": 4.812221928859649e-05, + "loss": 4.1154, + "step": 114688 + }, + { + "epoch": 0.01, + "learning_rate": 4.8113849719889704e-05, + "loss": 4.1182, + "step": 115200 + }, + { + "epoch": 0.01, + "learning_rate": 4.8105463772379184e-05, + "loss": 4.1007, + "step": 115712 + }, + { + "epoch": 0.01, + "learning_rate": 4.809707782486866e-05, + "loss": 4.0952, + "step": 116224 + }, + { + "epoch": 0.01, + "learning_rate": 4.808869187735814e-05, + "loss": 4.1051, + "step": 116736 + }, + { + "epoch": 0.01, + "learning_rate": 4.808032230865135e-05, + "loss": 4.1128, + "step": 117248 + }, + { + "epoch": 0.01, + "learning_rate": 4.8071936361140827e-05, + "loss": 4.102, + "step": 117760 + }, + { + "epoch": 0.01, + "learning_rate": 4.8063550413630307e-05, + "loss": 4.0963, + "step": 118272 + }, + { + "epoch": 0.01, + "learning_rate": 4.8055164466119786e-05, + "loss": 4.0846, + "step": 118784 + }, + { + "epoch": 0.01, + "learning_rate": 4.8046794897413e-05, + "loss": 4.0897, + "step": 119296 + }, + { + "epoch": 0.01, + "learning_rate": 4.803840894990248e-05, + "loss": 4.0916, + "step": 119808 + }, + { + "epoch": 0.01, + "learning_rate": 4.80300393811957e-05, + "loss": 4.0947, + "step": 120320 + }, + { + "epoch": 0.01, + "learning_rate": 4.802165343368518e-05, + "loss": 4.1023, + "step": 120832 + }, + { + "epoch": 0.01, + "learning_rate": 4.801326748617466e-05, + "loss": 4.1006, + "step": 121344 + }, + { + "epoch": 0.01, + "learning_rate": 4.800488153866413e-05, + "loss": 4.0898, + "step": 121856 + }, + { + "epoch": 0.02, + "learning_rate": 4.799651196995735e-05, + "loss": 4.0828, + "step": 122368 + }, + { + "epoch": 0.02, + "learning_rate": 4.798812602244683e-05, + "loss": 4.0794, + "step": 122880 + }, + { + "epoch": 0.02, + "learning_rate": 4.79797400749363e-05, + "loss": 4.0875, + "step": 123392 + }, + { + "epoch": 0.02, + "learning_rate": 4.797135412742578e-05, + "loss": 4.0872, + "step": 123904 + }, + { + "epoch": 0.02, + "learning_rate": 4.796296817991526e-05, + "loss": 4.0796, + "step": 124416 + }, + { + "epoch": 0.02, + "learning_rate": 4.795458223240474e-05, + "loss": 4.0793, + "step": 124928 + }, + { + "epoch": 0.02, + "learning_rate": 4.794619628489423e-05, + "loss": 4.0848, + "step": 125440 + }, + { + "epoch": 0.02, + "learning_rate": 4.793781033738371e-05, + "loss": 4.0899, + "step": 125952 + }, + { + "epoch": 0.02, + "learning_rate": 4.7929440768676916e-05, + "loss": 4.0816, + "step": 126464 + }, + { + "epoch": 0.02, + "learning_rate": 4.7921054821166396e-05, + "loss": 4.0838, + "step": 126976 + }, + { + "epoch": 0.02, + "learning_rate": 4.7912668873655876e-05, + "loss": 4.0908, + "step": 127488 + }, + { + "epoch": 0.02, + "learning_rate": 4.7904282926145356e-05, + "loss": 4.0791, + "step": 128000 + }, + { + "epoch": 0.02, + "learning_rate": 4.7895913357438565e-05, + "loss": 4.0765, + "step": 128512 + }, + { + "epoch": 0.02, + "learning_rate": 4.7887527409928045e-05, + "loss": 4.0892, + "step": 129024 + }, + { + "epoch": 0.02, + "learning_rate": 4.7879157841221254e-05, + "loss": 4.0735, + "step": 129536 + }, + { + "epoch": 0.02, + "learning_rate": 4.7870771893710734e-05, + "loss": 4.0849, + "step": 130048 + }, + { + "epoch": 0.02, + "learning_rate": 4.7862385946200214e-05, + "loss": 4.0702, + "step": 130560 + }, + { + "epoch": 0.02, + "learning_rate": 4.7853999998689694e-05, + "loss": 4.0594, + "step": 131072 + }, + { + "epoch": 0.02, + "learning_rate": 4.784561405117918e-05, + "loss": 4.0671, + "step": 131584 + }, + { + "epoch": 0.02, + "learning_rate": 4.783722810366866e-05, + "loss": 4.0748, + "step": 132096 + }, + { + "epoch": 0.02, + "learning_rate": 4.782885853496187e-05, + "loss": 4.0666, + "step": 132608 + }, + { + "epoch": 0.02, + "learning_rate": 4.782047258745135e-05, + "loss": 4.0558, + "step": 133120 + }, + { + "epoch": 0.02, + "learning_rate": 4.781208663994083e-05, + "loss": 4.0547, + "step": 133632 + }, + { + "epoch": 0.02, + "learning_rate": 4.780370069243031e-05, + "loss": 4.0654, + "step": 134144 + }, + { + "epoch": 0.02, + "learning_rate": 4.779531474491979e-05, + "loss": 4.0758, + "step": 134656 + }, + { + "epoch": 0.02, + "learning_rate": 4.778692879740927e-05, + "loss": 4.0633, + "step": 135168 + }, + { + "epoch": 0.02, + "learning_rate": 4.777855922870248e-05, + "loss": 4.0765, + "step": 135680 + }, + { + "epoch": 0.02, + "learning_rate": 4.777017328119196e-05, + "loss": 4.0637, + "step": 136192 + }, + { + "epoch": 0.02, + "learning_rate": 4.776178733368144e-05, + "loss": 4.0648, + "step": 136704 + }, + { + "epoch": 0.02, + "learning_rate": 4.775340138617092e-05, + "loss": 4.0633, + "step": 137216 + }, + { + "epoch": 0.02, + "learning_rate": 4.77450154386604e-05, + "loss": 4.0539, + "step": 137728 + }, + { + "epoch": 0.02, + "learning_rate": 4.773662949114988e-05, + "loss": 4.0509, + "step": 138240 + }, + { + "epoch": 0.02, + "learning_rate": 4.772824354363936e-05, + "loss": 4.0635, + "step": 138752 + }, + { + "epoch": 0.02, + "learning_rate": 4.7719857596128845e-05, + "loss": 4.0527, + "step": 139264 + }, + { + "epoch": 0.02, + "learning_rate": 4.7711488027422054e-05, + "loss": 4.0529, + "step": 139776 + }, + { + "epoch": 0.02, + "learning_rate": 4.7703102079911534e-05, + "loss": 4.0554, + "step": 140288 + }, + { + "epoch": 0.02, + "learning_rate": 4.7694716132401014e-05, + "loss": 4.0637, + "step": 140800 + }, + { + "epoch": 0.02, + "learning_rate": 4.7686330184890494e-05, + "loss": 4.0428, + "step": 141312 + }, + { + "epoch": 0.02, + "learning_rate": 4.76779606161837e-05, + "loss": 4.0467, + "step": 141824 + }, + { + "epoch": 0.02, + "learning_rate": 4.766957466867318e-05, + "loss": 4.0652, + "step": 142336 + }, + { + "epoch": 0.02, + "learning_rate": 4.766118872116266e-05, + "loss": 4.0449, + "step": 142848 + }, + { + "epoch": 0.02, + "learning_rate": 4.7652802773652136e-05, + "loss": 4.0646, + "step": 143360 + }, + { + "epoch": 0.02, + "learning_rate": 4.764443320494535e-05, + "loss": 4.0475, + "step": 143872 + }, + { + "epoch": 0.02, + "learning_rate": 4.763604725743483e-05, + "loss": 4.0569, + "step": 144384 + }, + { + "epoch": 0.02, + "learning_rate": 4.762766130992431e-05, + "loss": 4.0462, + "step": 144896 + }, + { + "epoch": 0.02, + "learning_rate": 4.761927536241379e-05, + "loss": 4.0408, + "step": 145408 + }, + { + "epoch": 0.02, + "learning_rate": 4.761090579370701e-05, + "loss": 4.0461, + "step": 145920 + }, + { + "epoch": 0.02, + "learning_rate": 4.760251984619649e-05, + "loss": 4.0514, + "step": 146432 + }, + { + "epoch": 0.02, + "learning_rate": 4.759413389868596e-05, + "loss": 4.0614, + "step": 146944 + }, + { + "epoch": 0.02, + "learning_rate": 4.758574795117544e-05, + "loss": 4.0508, + "step": 147456 + }, + { + "epoch": 0.02, + "learning_rate": 4.757737838246866e-05, + "loss": 4.0521, + "step": 147968 + }, + { + "epoch": 0.02, + "learning_rate": 4.7568992434958137e-05, + "loss": 4.0439, + "step": 148480 + }, + { + "epoch": 0.02, + "learning_rate": 4.756060648744761e-05, + "loss": 4.0352, + "step": 148992 + }, + { + "epoch": 0.02, + "learning_rate": 4.755222053993709e-05, + "loss": 4.0481, + "step": 149504 + }, + { + "epoch": 0.02, + "learning_rate": 4.7543850971230306e-05, + "loss": 4.0345, + "step": 150016 + }, + { + "epoch": 0.02, + "learning_rate": 4.7535465023719786e-05, + "loss": 4.0368, + "step": 150528 + }, + { + "epoch": 0.02, + "learning_rate": 4.7527079076209266e-05, + "loss": 4.0407, + "step": 151040 + }, + { + "epoch": 0.02, + "learning_rate": 4.7518693128698745e-05, + "loss": 4.0282, + "step": 151552 + }, + { + "epoch": 0.02, + "learning_rate": 4.751032355999196e-05, + "loss": 4.0357, + "step": 152064 + }, + { + "epoch": 0.02, + "learning_rate": 4.7501937612481435e-05, + "loss": 4.0345, + "step": 152576 + }, + { + "epoch": 0.03, + "eval_loss": 4.034010410308838, + "eval_runtime": 582.8384, + "eval_samples_per_second": 654.712, + "eval_steps_per_second": 20.46, + "step": 152638 + }, + { + "epoch": 0.0, + "learning_rate": 4.749356804377465e-05, + "loss": 4.0415, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.748518209626413e-05, + "loss": 4.0382, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.747679614875361e-05, + "loss": 4.0307, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.7468410201243084e-05, + "loss": 4.0307, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.7460024253732563e-05, + "loss": 4.0331, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.7451638306222043e-05, + "loss": 4.0119, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.744325235871152e-05, + "loss": 4.0289, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.7434866411201e-05, + "loss": 4.024, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.742648046369049e-05, + "loss": 4.0164, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.74181108949837e-05, + "loss": 4.0303, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.740972494747318e-05, + "loss": 4.033, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.740133899996266e-05, + "loss": 4.0179, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.739295305245214e-05, + "loss": 4.0138, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.738456710494162e-05, + "loss": 4.0195, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.73761811574311e-05, + "loss": 4.0197, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.736779520992058e-05, + "loss": 4.0116, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.735940926241006e-05, + "loss": 4.0119, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.735103969370327e-05, + "loss": 4.0117, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.734265374619275e-05, + "loss": 4.0149, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.733426779868223e-05, + "loss": 4.0168, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.732588185117171e-05, + "loss": 4.0169, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.7317512282464924e-05, + "loss": 4.0215, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.7309126334954404e-05, + "loss": 4.0178, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.7300740387443884e-05, + "loss": 4.0095, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.7292354439933364e-05, + "loss": 4.0147, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.728398487122657e-05, + "loss": 4.0099, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.727559892371605e-05, + "loss": 4.0132, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.726721297620553e-05, + "loss": 3.9993, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.725882702869501e-05, + "loss": 4.01, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.725045745998822e-05, + "loss": 3.9968, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.72420715124777e-05, + "loss": 4.0032, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.723368556496718e-05, + "loss": 4.0119, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.722529961745666e-05, + "loss": 4.011, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.721693004874988e-05, + "loss": 4.0004, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.720854410123936e-05, + "loss": 3.997, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.720015815372884e-05, + "loss": 4.0134, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.719177220621832e-05, + "loss": 3.9958, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.7183402637511526e-05, + "loss": 4.0028, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.7175016690001006e-05, + "loss": 3.9984, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.7166630742490486e-05, + "loss": 3.9849, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.7158244794979966e-05, + "loss": 3.9859, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.7149875226273175e-05, + "loss": 3.9844, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.7141489278762655e-05, + "loss": 4.0028, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.7133103331252135e-05, + "loss": 3.989, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.7124717383741615e-05, + "loss": 3.9883, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.711634781503483e-05, + "loss": 3.9893, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.710796186752431e-05, + "loss": 3.9892, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.709957592001379e-05, + "loss": 4.0043, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.709118997250327e-05, + "loss": 3.9816, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.708282040379648e-05, + "loss": 3.9816, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.707443445628596e-05, + "loss": 3.9801, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.706604850877544e-05, + "loss": 4.001, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.705766256126492e-05, + "loss": 3.9733, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.704929299255813e-05, + "loss": 3.9897, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.704090704504761e-05, + "loss": 3.9701, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.703252109753709e-05, + "loss": 3.9839, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.702413515002657e-05, + "loss": 3.9877, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.7015765581319785e-05, + "loss": 3.9776, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.7007379633809265e-05, + "loss": 3.9812, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.6998993686298745e-05, + "loss": 3.9764, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.699060773878822e-05, + "loss": 3.9587, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.6982238170081434e-05, + "loss": 3.9791, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.6973852222570914e-05, + "loss": 3.9811, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.6965466275060394e-05, + "loss": 3.9718, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.69570967063536e-05, + "loss": 3.9683, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694871075884308e-05, + "loss": 3.9738, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.694032481133256e-05, + "loss": 3.956, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.693193886382204e-05, + "loss": 3.9797, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.692355291631152e-05, + "loss": 3.9584, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.6915166968801e-05, + "loss": 3.9671, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.690678102129048e-05, + "loss": 3.9763, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.689841145258369e-05, + "loss": 3.966, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.689002550507317e-05, + "loss": 3.9731, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.688163955756265e-05, + "loss": 3.9859, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.687325361005213e-05, + "loss": 3.9709, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.686486766254161e-05, + "loss": 3.9794, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.685648171503109e-05, + "loss": 3.9633, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.684809576752057e-05, + "loss": 3.9544, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.683970982001005e-05, + "loss": 3.9646, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.683134025130326e-05, + "loss": 3.9767, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.682295430379274e-05, + "loss": 3.966, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.681456835628222e-05, + "loss": 3.9569, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.680618240877171e-05, + "loss": 3.951, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.6797812840064916e-05, + "loss": 3.954, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.6789426892554396e-05, + "loss": 3.9508, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.6781057323847605e-05, + "loss": 3.9597, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.6772671376337085e-05, + "loss": 3.9665, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.6764285428826565e-05, + "loss": 3.9647, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.6755899481316045e-05, + "loss": 3.957, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.6747529912609254e-05, + "loss": 3.9528, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.6739143965098734e-05, + "loss": 3.9483, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.6730758017588214e-05, + "loss": 3.9551, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.6722372070077694e-05, + "loss": 3.9528, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.6713986122567174e-05, + "loss": 3.9534, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.670560017505666e-05, + "loss": 3.9478, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.669721422754614e-05, + "loss": 3.9552, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.668882828003562e-05, + "loss": 3.9563, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.668045871132883e-05, + "loss": 3.9566, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.667207276381831e-05, + "loss": 3.9574, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.666368681630779e-05, + "loss": 3.961, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.665530086879727e-05, + "loss": 3.9551, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.664693130009048e-05, + "loss": 3.9484, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.663854535257996e-05, + "loss": 3.965, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.663017578387317e-05, + "loss": 3.9441, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.662178983636265e-05, + "loss": 3.9648, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.661340388885213e-05, + "loss": 3.9415, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.6605017941341614e-05, + "loss": 3.9359, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.659664837263482e-05, + "loss": 3.9419, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.65882624251243e-05, + "loss": 3.9554, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.657987647761378e-05, + "loss": 3.9464, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.657149053010326e-05, + "loss": 3.9343, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.656310458259274e-05, + "loss": 3.9333, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.655471863508222e-05, + "loss": 3.9414, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.65463326875717e-05, + "loss": 3.9547, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.6537946740061176e-05, + "loss": 3.9415, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.652957717135439e-05, + "loss": 3.9556, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.652119122384387e-05, + "loss": 3.9433, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.651280527633335e-05, + "loss": 3.9435, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.650441932882283e-05, + "loss": 3.9487, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.649603338131231e-05, + "loss": 3.933, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.648764743380179e-05, + "loss": 3.9353, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.647926148629127e-05, + "loss": 3.9428, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.647087553878075e-05, + "loss": 3.9333, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.646250597007396e-05, + "loss": 3.9382, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.645412002256344e-05, + "loss": 3.9394, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.644573407505292e-05, + "loss": 3.9457, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.64373481275424e-05, + "loss": 3.9276, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.642897855883561e-05, + "loss": 3.9287, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.642059261132509e-05, + "loss": 3.9529, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.641220666381457e-05, + "loss": 3.9312, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.640382071630405e-05, + "loss": 3.9459, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.6395451147597266e-05, + "loss": 3.9374, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.6387065200086746e-05, + "loss": 3.9409, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.6378679252576226e-05, + "loss": 3.9342, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.6370309683869435e-05, + "loss": 3.9312, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.636194011516265e-05, + "loss": 3.9355, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.6353554167652124e-05, + "loss": 3.9358, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.6345168220141604e-05, + "loss": 3.9485, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.6336782272631084e-05, + "loss": 3.942, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.6328396325120564e-05, + "loss": 3.9393, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.6320010377610043e-05, + "loss": 3.933, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.6311624430099523e-05, + "loss": 3.9262, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.6303238482589003e-05, + "loss": 3.9367, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.629486891388222e-05, + "loss": 3.9237, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.62864829663717e-05, + "loss": 3.9287, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.627809701886118e-05, + "loss": 3.9283, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.626971107135066e-05, + "loss": 3.9202, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.626134150264387e-05, + "loss": 3.9272, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.625295555513335e-05, + "loss": 3.9248, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 3.958523750305176, + "eval_runtime": 586.2687, + "eval_samples_per_second": 650.881, + "eval_steps_per_second": 20.341, + "step": 228957 + }, + { + "epoch": 0.0, + "learning_rate": 4.624458598642656e-05, + "loss": 3.9293, + "step": 229376 + }, + { + "epoch": 0.0, + "learning_rate": 4.623620003891604e-05, + "loss": 3.9353, + "step": 229888 + }, + { + "epoch": 0.0, + "learning_rate": 4.622781409140552e-05, + "loss": 3.9229, + "step": 230400 + }, + { + "epoch": 0.0, + "learning_rate": 4.6219428143895e-05, + "loss": 3.9239, + "step": 230912 + }, + { + "epoch": 0.0, + "learning_rate": 4.621104219638448e-05, + "loss": 3.9286, + "step": 231424 + }, + { + "epoch": 0.0, + "learning_rate": 4.620265624887396e-05, + "loss": 3.9071, + "step": 231936 + }, + { + "epoch": 0.0, + "learning_rate": 4.619427030136344e-05, + "loss": 3.9221, + "step": 232448 + }, + { + "epoch": 0.0, + "learning_rate": 4.6185884353852924e-05, + "loss": 3.9209, + "step": 232960 + }, + { + "epoch": 0.0, + "learning_rate": 4.6177498406342404e-05, + "loss": 3.9153, + "step": 233472 + }, + { + "epoch": 0.0, + "learning_rate": 4.616912883763561e-05, + "loss": 3.9258, + "step": 233984 + }, + { + "epoch": 0.0, + "learning_rate": 4.616074289012509e-05, + "loss": 3.9279, + "step": 234496 + }, + { + "epoch": 0.0, + "learning_rate": 4.615235694261457e-05, + "loss": 3.9105, + "step": 235008 + }, + { + "epoch": 0.0, + "learning_rate": 4.614397099510405e-05, + "loss": 3.9116, + "step": 235520 + }, + { + "epoch": 0.0, + "learning_rate": 4.613558504759353e-05, + "loss": 3.9167, + "step": 236032 + }, + { + "epoch": 0.0, + "learning_rate": 4.6127199100083006e-05, + "loss": 3.9178, + "step": 236544 + }, + { + "epoch": 0.0, + "learning_rate": 4.6118813152572486e-05, + "loss": 3.9056, + "step": 237056 + }, + { + "epoch": 0.0, + "learning_rate": 4.61104435838657e-05, + "loss": 3.9071, + "step": 237568 + }, + { + "epoch": 0.0, + "learning_rate": 4.610205763635518e-05, + "loss": 3.9114, + "step": 238080 + }, + { + "epoch": 0.0, + "learning_rate": 4.609367168884466e-05, + "loss": 3.9119, + "step": 238592 + }, + { + "epoch": 0.0, + "learning_rate": 4.608528574133414e-05, + "loss": 3.9188, + "step": 239104 + }, + { + "epoch": 0.0, + "learning_rate": 4.607689979382362e-05, + "loss": 3.9117, + "step": 239616 + }, + { + "epoch": 0.0, + "learning_rate": 4.60685138463131e-05, + "loss": 3.922, + "step": 240128 + }, + { + "epoch": 0.0, + "learning_rate": 4.606012789880258e-05, + "loss": 3.9161, + "step": 240640 + }, + { + "epoch": 0.0, + "learning_rate": 4.605174195129206e-05, + "loss": 3.9124, + "step": 241152 + }, + { + "epoch": 0.0, + "learning_rate": 4.604337238258527e-05, + "loss": 3.9114, + "step": 241664 + }, + { + "epoch": 0.0, + "learning_rate": 4.603498643507475e-05, + "loss": 3.9089, + "step": 242176 + }, + { + "epoch": 0.0, + "learning_rate": 4.602660048756423e-05, + "loss": 3.919, + "step": 242688 + }, + { + "epoch": 0.0, + "learning_rate": 4.601821454005371e-05, + "loss": 3.9051, + "step": 243200 + }, + { + "epoch": 0.0, + "learning_rate": 4.600984497134692e-05, + "loss": 3.912, + "step": 243712 + }, + { + "epoch": 0.01, + "learning_rate": 4.60014590238364e-05, + "loss": 3.9005, + "step": 244224 + }, + { + "epoch": 0.01, + "learning_rate": 4.599307307632588e-05, + "loss": 3.9014, + "step": 244736 + }, + { + "epoch": 0.01, + "learning_rate": 4.598468712881536e-05, + "loss": 3.9158, + "step": 245248 + }, + { + "epoch": 0.01, + "learning_rate": 4.5976301181304846e-05, + "loss": 3.9115, + "step": 245760 + }, + { + "epoch": 0.01, + "learning_rate": 4.5967915233794326e-05, + "loss": 3.9052, + "step": 246272 + }, + { + "epoch": 0.01, + "learning_rate": 4.5959529286283806e-05, + "loss": 3.9023, + "step": 246784 + }, + { + "epoch": 0.01, + "learning_rate": 4.5951143338773286e-05, + "loss": 3.9122, + "step": 247296 + }, + { + "epoch": 0.01, + "learning_rate": 4.5942773770066495e-05, + "loss": 3.9011, + "step": 247808 + }, + { + "epoch": 0.01, + "learning_rate": 4.5934404201359704e-05, + "loss": 3.9093, + "step": 248320 + }, + { + "epoch": 0.01, + "learning_rate": 4.5926018253849184e-05, + "loss": 3.9017, + "step": 248832 + }, + { + "epoch": 0.01, + "learning_rate": 4.5917632306338664e-05, + "loss": 3.8894, + "step": 249344 + }, + { + "epoch": 0.01, + "learning_rate": 4.5909246358828144e-05, + "loss": 3.8944, + "step": 249856 + }, + { + "epoch": 0.01, + "learning_rate": 4.5900860411317624e-05, + "loss": 3.893, + "step": 250368 + }, + { + "epoch": 0.01, + "learning_rate": 4.5892474463807104e-05, + "loss": 3.9069, + "step": 250880 + }, + { + "epoch": 0.01, + "learning_rate": 4.588410489510031e-05, + "loss": 3.8948, + "step": 251392 + }, + { + "epoch": 0.01, + "learning_rate": 4.58757189475898e-05, + "loss": 3.8936, + "step": 251904 + }, + { + "epoch": 0.01, + "learning_rate": 4.586733300007928e-05, + "loss": 3.8969, + "step": 252416 + }, + { + "epoch": 0.01, + "learning_rate": 4.585894705256876e-05, + "loss": 3.8996, + "step": 252928 + }, + { + "epoch": 0.01, + "learning_rate": 4.585056110505824e-05, + "loss": 3.9092, + "step": 253440 + }, + { + "epoch": 0.01, + "learning_rate": 4.584217515754772e-05, + "loss": 3.888, + "step": 253952 + }, + { + "epoch": 0.01, + "learning_rate": 4.58337892100372e-05, + "loss": 3.889, + "step": 254464 + }, + { + "epoch": 0.01, + "learning_rate": 4.582540326252667e-05, + "loss": 3.8937, + "step": 254976 + }, + { + "epoch": 0.01, + "learning_rate": 4.581703369381989e-05, + "loss": 3.9019, + "step": 255488 + }, + { + "epoch": 0.01, + "learning_rate": 4.580864774630937e-05, + "loss": 3.8839, + "step": 256000 + }, + { + "epoch": 0.01, + "learning_rate": 4.580026179879884e-05, + "loss": 3.8949, + "step": 256512 + }, + { + "epoch": 0.01, + "learning_rate": 4.579187585128832e-05, + "loss": 3.8812, + "step": 257024 + }, + { + "epoch": 0.01, + "learning_rate": 4.57834899037778e-05, + "loss": 3.8892, + "step": 257536 + }, + { + "epoch": 0.01, + "learning_rate": 4.577510395626728e-05, + "loss": 3.8985, + "step": 258048 + }, + { + "epoch": 0.01, + "learning_rate": 4.576671800875677e-05, + "loss": 3.8833, + "step": 258560 + }, + { + "epoch": 0.01, + "learning_rate": 4.575834844004998e-05, + "loss": 3.8984, + "step": 259072 + }, + { + "epoch": 0.01, + "learning_rate": 4.574996249253946e-05, + "loss": 3.8906, + "step": 259584 + }, + { + "epoch": 0.01, + "learning_rate": 4.574157654502894e-05, + "loss": 3.8679, + "step": 260096 + }, + { + "epoch": 0.01, + "learning_rate": 4.573319059751842e-05, + "loss": 3.887, + "step": 260608 + }, + { + "epoch": 0.01, + "learning_rate": 4.57248046500079e-05, + "loss": 3.8904, + "step": 261120 + }, + { + "epoch": 0.01, + "learning_rate": 4.571641870249738e-05, + "loss": 3.8887, + "step": 261632 + }, + { + "epoch": 0.01, + "learning_rate": 4.5708049133790586e-05, + "loss": 3.88, + "step": 262144 + }, + { + "epoch": 0.01, + "learning_rate": 4.5699663186280066e-05, + "loss": 3.8849, + "step": 262656 + }, + { + "epoch": 0.01, + "learning_rate": 4.5691277238769546e-05, + "loss": 3.8693, + "step": 263168 + }, + { + "epoch": 0.01, + "learning_rate": 4.5682891291259026e-05, + "loss": 3.8912, + "step": 263680 + }, + { + "epoch": 0.01, + "learning_rate": 4.5674505343748506e-05, + "loss": 3.8701, + "step": 264192 + }, + { + "epoch": 0.01, + "learning_rate": 4.5666119396237986e-05, + "loss": 3.8824, + "step": 264704 + }, + { + "epoch": 0.01, + "learning_rate": 4.5657733448727466e-05, + "loss": 3.8905, + "step": 265216 + }, + { + "epoch": 0.01, + "learning_rate": 4.564936388002068e-05, + "loss": 3.8783, + "step": 265728 + }, + { + "epoch": 0.01, + "learning_rate": 4.564097793251016e-05, + "loss": 3.8855, + "step": 266240 + }, + { + "epoch": 0.01, + "learning_rate": 4.563259198499964e-05, + "loss": 3.8967, + "step": 266752 + }, + { + "epoch": 0.01, + "learning_rate": 4.562420603748912e-05, + "loss": 3.8878, + "step": 267264 + }, + { + "epoch": 0.01, + "learning_rate": 4.561583646878233e-05, + "loss": 3.8947, + "step": 267776 + }, + { + "epoch": 0.01, + "learning_rate": 4.560745052127181e-05, + "loss": 3.8766, + "step": 268288 + }, + { + "epoch": 0.01, + "learning_rate": 4.559906457376129e-05, + "loss": 3.872, + "step": 268800 + }, + { + "epoch": 0.01, + "learning_rate": 4.559067862625077e-05, + "loss": 3.8754, + "step": 269312 + }, + { + "epoch": 0.01, + "learning_rate": 4.558229267874025e-05, + "loss": 3.8951, + "step": 269824 + }, + { + "epoch": 0.01, + "learning_rate": 4.557392311003346e-05, + "loss": 3.879, + "step": 270336 + }, + { + "epoch": 0.01, + "learning_rate": 4.556553716252294e-05, + "loss": 3.8708, + "step": 270848 + }, + { + "epoch": 0.01, + "learning_rate": 4.555715121501242e-05, + "loss": 3.8642, + "step": 271360 + }, + { + "epoch": 0.01, + "learning_rate": 4.55487652675019e-05, + "loss": 3.8742, + "step": 271872 + }, + { + "epoch": 0.01, + "learning_rate": 4.5540379319991386e-05, + "loss": 3.8686, + "step": 272384 + }, + { + "epoch": 0.01, + "learning_rate": 4.5532009751284595e-05, + "loss": 3.8727, + "step": 272896 + }, + { + "epoch": 0.01, + "learning_rate": 4.5523623803774075e-05, + "loss": 3.8803, + "step": 273408 + }, + { + "epoch": 0.01, + "learning_rate": 4.5515237856263555e-05, + "loss": 3.8844, + "step": 273920 + }, + { + "epoch": 0.01, + "learning_rate": 4.550685190875303e-05, + "loss": 3.8753, + "step": 274432 + }, + { + "epoch": 0.02, + "learning_rate": 4.5498482340046244e-05, + "loss": 3.8736, + "step": 274944 + }, + { + "epoch": 0.02, + "learning_rate": 4.5490096392535724e-05, + "loss": 3.8622, + "step": 275456 + }, + { + "epoch": 0.02, + "learning_rate": 4.5481710445025204e-05, + "loss": 3.8719, + "step": 275968 + }, + { + "epoch": 0.02, + "learning_rate": 4.547332449751468e-05, + "loss": 3.8736, + "step": 276480 + }, + { + "epoch": 0.02, + "learning_rate": 4.546493855000416e-05, + "loss": 3.8701, + "step": 276992 + }, + { + "epoch": 0.02, + "learning_rate": 4.545655260249364e-05, + "loss": 3.865, + "step": 277504 + }, + { + "epoch": 0.02, + "learning_rate": 4.544818303378685e-05, + "loss": 3.8746, + "step": 278016 + }, + { + "epoch": 0.02, + "learning_rate": 4.543979708627633e-05, + "loss": 3.8702, + "step": 278528 + }, + { + "epoch": 0.02, + "learning_rate": 4.543141113876581e-05, + "loss": 3.8826, + "step": 279040 + }, + { + "epoch": 0.02, + "learning_rate": 4.542302519125529e-05, + "loss": 3.8722, + "step": 279552 + }, + { + "epoch": 0.02, + "learning_rate": 4.541463924374477e-05, + "loss": 3.8794, + "step": 280064 + }, + { + "epoch": 0.02, + "learning_rate": 4.540626967503798e-05, + "loss": 3.8722, + "step": 280576 + }, + { + "epoch": 0.02, + "learning_rate": 4.539788372752746e-05, + "loss": 3.8675, + "step": 281088 + }, + { + "epoch": 0.02, + "learning_rate": 4.538949778001694e-05, + "loss": 3.885, + "step": 281600 + }, + { + "epoch": 0.02, + "learning_rate": 4.538111183250642e-05, + "loss": 3.8651, + "step": 282112 + }, + { + "epoch": 0.02, + "learning_rate": 4.537274226379963e-05, + "loss": 3.8861, + "step": 282624 + }, + { + "epoch": 0.02, + "learning_rate": 4.536435631628911e-05, + "loss": 3.86, + "step": 283136 + }, + { + "epoch": 0.02, + "learning_rate": 4.535597036877859e-05, + "loss": 3.8601, + "step": 283648 + }, + { + "epoch": 0.02, + "learning_rate": 4.534758442126808e-05, + "loss": 3.8625, + "step": 284160 + }, + { + "epoch": 0.02, + "learning_rate": 4.533921485256129e-05, + "loss": 3.8786, + "step": 284672 + }, + { + "epoch": 0.02, + "learning_rate": 4.53308452838545e-05, + "loss": 3.8673, + "step": 285184 + }, + { + "epoch": 0.02, + "learning_rate": 4.5322459336343976e-05, + "loss": 3.8538, + "step": 285696 + }, + { + "epoch": 0.02, + "learning_rate": 4.5314073388833456e-05, + "loss": 3.8516, + "step": 286208 + }, + { + "epoch": 0.02, + "learning_rate": 4.5305687441322936e-05, + "loss": 3.8614, + "step": 286720 + }, + { + "epoch": 0.02, + "learning_rate": 4.5297301493812416e-05, + "loss": 3.8792, + "step": 287232 + }, + { + "epoch": 0.02, + "learning_rate": 4.5288915546301896e-05, + "loss": 3.8627, + "step": 287744 + }, + { + "epoch": 0.02, + "learning_rate": 4.5280529598791376e-05, + "loss": 3.8788, + "step": 288256 + }, + { + "epoch": 0.02, + "learning_rate": 4.5272143651280856e-05, + "loss": 3.8648, + "step": 288768 + }, + { + "epoch": 0.02, + "learning_rate": 4.5263774082574065e-05, + "loss": 3.8687, + "step": 289280 + }, + { + "epoch": 0.02, + "learning_rate": 4.5255388135063545e-05, + "loss": 3.8704, + "step": 289792 + }, + { + "epoch": 0.02, + "learning_rate": 4.524700218755303e-05, + "loss": 3.8571, + "step": 290304 + }, + { + "epoch": 0.02, + "learning_rate": 4.523861624004251e-05, + "loss": 3.8576, + "step": 290816 + }, + { + "epoch": 0.02, + "learning_rate": 4.523024667133572e-05, + "loss": 3.8644, + "step": 291328 + }, + { + "epoch": 0.02, + "learning_rate": 4.52218607238252e-05, + "loss": 3.8585, + "step": 291840 + }, + { + "epoch": 0.02, + "learning_rate": 4.521347477631468e-05, + "loss": 3.8595, + "step": 292352 + }, + { + "epoch": 0.02, + "learning_rate": 4.520508882880416e-05, + "loss": 3.8644, + "step": 292864 + }, + { + "epoch": 0.02, + "learning_rate": 4.519670288129364e-05, + "loss": 3.8651, + "step": 293376 + }, + { + "epoch": 0.02, + "learning_rate": 4.518833331258685e-05, + "loss": 3.8526, + "step": 293888 + }, + { + "epoch": 0.02, + "learning_rate": 4.517994736507633e-05, + "loss": 3.8541, + "step": 294400 + }, + { + "epoch": 0.02, + "learning_rate": 4.517156141756581e-05, + "loss": 3.874, + "step": 294912 + }, + { + "epoch": 0.02, + "learning_rate": 4.516317547005529e-05, + "loss": 3.8548, + "step": 295424 + }, + { + "epoch": 0.02, + "learning_rate": 4.51548059013485e-05, + "loss": 3.87, + "step": 295936 + }, + { + "epoch": 0.02, + "learning_rate": 4.5146419953837985e-05, + "loss": 3.8629, + "step": 296448 + }, + { + "epoch": 0.02, + "learning_rate": 4.5138034006327465e-05, + "loss": 3.8646, + "step": 296960 + }, + { + "epoch": 0.02, + "learning_rate": 4.5129648058816945e-05, + "loss": 3.8566, + "step": 297472 + }, + { + "epoch": 0.02, + "learning_rate": 4.5121278490110154e-05, + "loss": 3.8614, + "step": 297984 + }, + { + "epoch": 0.02, + "learning_rate": 4.5112892542599634e-05, + "loss": 3.8582, + "step": 298496 + }, + { + "epoch": 0.02, + "learning_rate": 4.5104506595089114e-05, + "loss": 3.861, + "step": 299008 + }, + { + "epoch": 0.02, + "learning_rate": 4.5096120647578594e-05, + "loss": 3.8746, + "step": 299520 + }, + { + "epoch": 0.02, + "learning_rate": 4.50877510788718e-05, + "loss": 3.8621, + "step": 300032 + }, + { + "epoch": 0.02, + "learning_rate": 4.507936513136128e-05, + "loss": 3.8673, + "step": 300544 + }, + { + "epoch": 0.02, + "learning_rate": 4.507097918385076e-05, + "loss": 3.8653, + "step": 301056 + }, + { + "epoch": 0.02, + "learning_rate": 4.506259323634024e-05, + "loss": 3.8516, + "step": 301568 + }, + { + "epoch": 0.02, + "learning_rate": 4.505422366763345e-05, + "loss": 3.8617, + "step": 302080 + }, + { + "epoch": 0.02, + "learning_rate": 4.504583772012293e-05, + "loss": 3.8505, + "step": 302592 + }, + { + "epoch": 0.02, + "learning_rate": 4.503745177261242e-05, + "loss": 3.8553, + "step": 303104 + }, + { + "epoch": 0.02, + "learning_rate": 4.50290658251019e-05, + "loss": 3.8548, + "step": 303616 + }, + { + "epoch": 0.02, + "learning_rate": 4.502069625639511e-05, + "loss": 3.8523, + "step": 304128 + }, + { + "epoch": 0.02, + "learning_rate": 4.501231030888459e-05, + "loss": 3.8488, + "step": 304640 + }, + { + "epoch": 0.02, + "learning_rate": 4.500392436137407e-05, + "loss": 3.8562, + "step": 305152 + }, + { + "epoch": 0.03, + "eval_loss": 3.9172492027282715, + "eval_runtime": 566.0397, + "eval_samples_per_second": 674.142, + "eval_steps_per_second": 21.067, + "step": 305276 + }, + { + "epoch": 0.0, + "learning_rate": 4.499553841386355e-05, + "loss": 3.8596, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.498715246635303e-05, + "loss": 3.8605, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.497876651884251e-05, + "loss": 3.8541, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.497038057133199e-05, + "loss": 3.8513, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.496199462382146e-05, + "loss": 3.8602, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.495360867631094e-05, + "loss": 3.8344, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.494522272880042e-05, + "loss": 3.8536, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.49368367812899e-05, + "loss": 3.8453, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.4928467212583116e-05, + "loss": 3.8451, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.4920081265072596e-05, + "loss": 3.8546, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.4911695317562076e-05, + "loss": 3.8566, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.4903309370051556e-05, + "loss": 3.8398, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.4894939801344765e-05, + "loss": 3.8445, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.4886553853834245e-05, + "loss": 3.844, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.4878167906323725e-05, + "loss": 3.849, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.4869781958813205e-05, + "loss": 3.8325, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.4861412390106414e-05, + "loss": 3.838, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.4853026442595894e-05, + "loss": 3.8396, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.4844640495085374e-05, + "loss": 3.8416, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.4836254547574854e-05, + "loss": 3.8516, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.482788497886807e-05, + "loss": 3.8421, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.481949903135755e-05, + "loss": 3.8532, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.481111308384703e-05, + "loss": 3.8512, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.480272713633651e-05, + "loss": 3.8454, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.479434118882599e-05, + "loss": 3.8413, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.47859716201192e-05, + "loss": 3.8416, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.477758567260868e-05, + "loss": 3.8506, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.476919972509816e-05, + "loss": 3.8377, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.476081377758764e-05, + "loss": 3.8418, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.475244420888085e-05, + "loss": 3.8399, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.474405826137033e-05, + "loss": 3.8289, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.473567231385981e-05, + "loss": 3.8444, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.4727286366349295e-05, + "loss": 3.8495, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.4718916797642504e-05, + "loss": 3.8388, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.4710530850131984e-05, + "loss": 3.8358, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.4702144902621464e-05, + "loss": 3.8402, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.4693758955110944e-05, + "loss": 3.8388, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.468538938640415e-05, + "loss": 3.8392, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.467700343889363e-05, + "loss": 3.8358, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.466861749138311e-05, + "loss": 3.8241, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.466023154387259e-05, + "loss": 3.8289, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.46518619751658e-05, + "loss": 3.8241, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.464347602765528e-05, + "loss": 3.841, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.463509008014476e-05, + "loss": 3.8278, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.462670413263425e-05, + "loss": 3.8292, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.461833456392746e-05, + "loss": 3.8324, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.460994861641694e-05, + "loss": 3.8319, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.460156266890642e-05, + "loss": 3.8459, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.45931767213959e-05, + "loss": 3.8249, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.4584807152689106e-05, + "loss": 3.8217, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.4576421205178586e-05, + "loss": 3.8323, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.4568035257668066e-05, + "loss": 3.8333, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.4559649310157546e-05, + "loss": 3.8224, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.4551279741450755e-05, + "loss": 3.8282, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.4542893793940235e-05, + "loss": 3.8214, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.4534507846429715e-05, + "loss": 3.8262, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.45261218989192e-05, + "loss": 3.8342, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.451775233021241e-05, + "loss": 3.8174, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.450936638270189e-05, + "loss": 3.8359, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.450098043519137e-05, + "loss": 3.8243, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.449259448768085e-05, + "loss": 3.8086, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.448422491897406e-05, + "loss": 3.8213, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.447583897146354e-05, + "loss": 3.8265, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.446745302395302e-05, + "loss": 3.8303, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.44590670764425e-05, + "loss": 3.817, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.445069750773571e-05, + "loss": 3.8229, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.444231156022519e-05, + "loss": 3.8019, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.443392561271467e-05, + "loss": 3.8298, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.4425539665204156e-05, + "loss": 3.8113, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.4417170096497365e-05, + "loss": 3.819, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.4408784148986845e-05, + "loss": 3.8265, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.4400398201476325e-05, + "loss": 3.8167, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.4392012253965805e-05, + "loss": 3.8205, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.4383642685259014e-05, + "loss": 3.8332, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.4375256737748494e-05, + "loss": 3.8269, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.4366870790237974e-05, + "loss": 3.8303, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.4358484842727454e-05, + "loss": 3.8172, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.435011527402066e-05, + "loss": 3.8111, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.434172932651014e-05, + "loss": 3.8166, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.433334337899962e-05, + "loss": 3.8318, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.43249574314891e-05, + "loss": 3.8173, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.431658786278232e-05, + "loss": 3.8133, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.43082019152718e-05, + "loss": 3.802, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.429981596776128e-05, + "loss": 3.8138, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.429143002025076e-05, + "loss": 3.8047, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.428306045154397e-05, + "loss": 3.8168, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.427467450403345e-05, + "loss": 3.815, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.426628855652293e-05, + "loss": 3.8263, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.425790260901241e-05, + "loss": 3.8155, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.4249533040305616e-05, + "loss": 3.8149, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.4241147092795096e-05, + "loss": 3.8023, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.4232761145284576e-05, + "loss": 3.8122, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.4224375197774056e-05, + "loss": 3.8158, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.421600562906727e-05, + "loss": 3.8086, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.420761968155675e-05, + "loss": 3.8051, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.419923373404623e-05, + "loss": 3.8176, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.419084778653571e-05, + "loss": 3.8074, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.418247821782892e-05, + "loss": 3.8309, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.41740922703184e-05, + "loss": 3.8106, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.416570632280788e-05, + "loss": 3.8205, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.415732037529736e-05, + "loss": 3.812, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.414895080659057e-05, + "loss": 3.8089, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.414056485908005e-05, + "loss": 3.8271, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.413217891156953e-05, + "loss": 3.8068, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.412379296405901e-05, + "loss": 3.8246, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.4115423395352226e-05, + "loss": 3.8045, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.4107037447841706e-05, + "loss": 3.8038, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.4098651500331186e-05, + "loss": 3.8011, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.409026555282066e-05, + "loss": 3.8162, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.4081895984113875e-05, + "loss": 3.8141, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.4073510036603355e-05, + "loss": 3.8021, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.4065124089092835e-05, + "loss": 3.7906, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.405673814158231e-05, + "loss": 3.8034, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.4048368572875524e-05, + "loss": 3.8217, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.4039982625365004e-05, + "loss": 3.8024, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.4031596677854484e-05, + "loss": 3.8211, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.4023210730343963e-05, + "loss": 3.8087, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.401484116163718e-05, + "loss": 3.81, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.400645521412666e-05, + "loss": 3.8136, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.399806926661613e-05, + "loss": 3.8011, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.398968331910561e-05, + "loss": 3.7979, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.398131375039883e-05, + "loss": 3.8048, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.397292780288831e-05, + "loss": 3.8047, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.396454185537778e-05, + "loss": 3.8036, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.395615590786726e-05, + "loss": 3.8057, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.394778633916048e-05, + "loss": 3.8084, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.393940039164996e-05, + "loss": 3.7959, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.393101444413944e-05, + "loss": 3.799, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.392262849662892e-05, + "loss": 3.8152, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.391425892792213e-05, + "loss": 3.7996, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.3905872980411606e-05, + "loss": 3.8145, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.3897487032901086e-05, + "loss": 3.8104, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.3889101085390566e-05, + "loss": 3.8055, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.388073151668378e-05, + "loss": 3.8037, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.3872345569173255e-05, + "loss": 3.8057, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.3863959621662735e-05, + "loss": 3.8021, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.3855573674152215e-05, + "loss": 3.8037, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.3847204105445424e-05, + "loss": 3.8197, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.383881815793491e-05, + "loss": 3.8105, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.383043221042439e-05, + "loss": 3.8109, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.382204626291387e-05, + "loss": 3.8089, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.381367669420708e-05, + "loss": 3.7985, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.380529074669656e-05, + "loss": 3.804, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.379690479918604e-05, + "loss": 3.7947, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.378851885167552e-05, + "loss": 3.8001, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.378014928296873e-05, + "loss": 3.8032, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.377176333545821e-05, + "loss": 3.7973, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.376337738794769e-05, + "loss": 3.7917, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.37550078192409e-05, + "loss": 3.8037, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 3.890806198120117, + "eval_runtime": 570.4872, + "eval_samples_per_second": 668.886, + "eval_steps_per_second": 20.903, + "step": 381595 + }, + { + "epoch": 0.0, + "learning_rate": 4.374662187173038e-05, + "loss": 3.8088, + "step": 381952 + }, + { + "epoch": 0.0, + "learning_rate": 4.3738235924219865e-05, + "loss": 3.8028, + "step": 382464 + }, + { + "epoch": 0.0, + "learning_rate": 4.3729849976709345e-05, + "loss": 3.8016, + "step": 382976 + }, + { + "epoch": 0.0, + "learning_rate": 4.3721464029198824e-05, + "loss": 3.8007, + "step": 383488 + }, + { + "epoch": 0.0, + "learning_rate": 4.3713078081688304e-05, + "loss": 3.7992, + "step": 384000 + }, + { + "epoch": 0.0, + "learning_rate": 4.3704692134177784e-05, + "loss": 3.7863, + "step": 384512 + }, + { + "epoch": 0.0, + "learning_rate": 4.3696306186667264e-05, + "loss": 3.7969, + "step": 385024 + }, + { + "epoch": 0.0, + "learning_rate": 4.3687920239156744e-05, + "loss": 3.789, + "step": 385536 + }, + { + "epoch": 0.0, + "learning_rate": 4.3679550670449953e-05, + "loss": 3.7981, + "step": 386048 + }, + { + "epoch": 0.0, + "learning_rate": 4.367118110174316e-05, + "loss": 3.8001, + "step": 386560 + }, + { + "epoch": 0.0, + "learning_rate": 4.366279515423264e-05, + "loss": 3.801, + "step": 387072 + }, + { + "epoch": 0.0, + "learning_rate": 4.365440920672212e-05, + "loss": 3.7862, + "step": 387584 + }, + { + "epoch": 0.0, + "learning_rate": 4.36460232592116e-05, + "loss": 3.7922, + "step": 388096 + }, + { + "epoch": 0.0, + "learning_rate": 4.363763731170108e-05, + "loss": 3.7901, + "step": 388608 + }, + { + "epoch": 0.0, + "learning_rate": 4.362925136419056e-05, + "loss": 3.7955, + "step": 389120 + }, + { + "epoch": 0.0, + "learning_rate": 4.362086541668005e-05, + "loss": 3.7805, + "step": 389632 + }, + { + "epoch": 0.0, + "learning_rate": 4.361247946916953e-05, + "loss": 3.7823, + "step": 390144 + }, + { + "epoch": 0.0, + "learning_rate": 4.360410990046274e-05, + "loss": 3.7869, + "step": 390656 + }, + { + "epoch": 0.0, + "learning_rate": 4.359572395295222e-05, + "loss": 3.7897, + "step": 391168 + }, + { + "epoch": 0.0, + "learning_rate": 4.35873380054417e-05, + "loss": 3.7994, + "step": 391680 + }, + { + "epoch": 0.0, + "learning_rate": 4.357895205793118e-05, + "loss": 3.7864, + "step": 392192 + }, + { + "epoch": 0.0, + "learning_rate": 4.357058248922439e-05, + "loss": 3.8045, + "step": 392704 + }, + { + "epoch": 0.0, + "learning_rate": 4.356219654171387e-05, + "loss": 3.7947, + "step": 393216 + }, + { + "epoch": 0.0, + "learning_rate": 4.355381059420335e-05, + "loss": 3.7953, + "step": 393728 + }, + { + "epoch": 0.0, + "learning_rate": 4.354542464669283e-05, + "loss": 3.7882, + "step": 394240 + }, + { + "epoch": 0.0, + "learning_rate": 4.3537055077986036e-05, + "loss": 3.7888, + "step": 394752 + }, + { + "epoch": 0.0, + "learning_rate": 4.3528669130475516e-05, + "loss": 3.8017, + "step": 395264 + }, + { + "epoch": 0.0, + "learning_rate": 4.3520283182964996e-05, + "loss": 3.7864, + "step": 395776 + }, + { + "epoch": 0.0, + "learning_rate": 4.351189723545448e-05, + "loss": 3.7918, + "step": 396288 + }, + { + "epoch": 0.0, + "learning_rate": 4.350352766674769e-05, + "loss": 3.7885, + "step": 396800 + }, + { + "epoch": 0.01, + "learning_rate": 4.349514171923717e-05, + "loss": 3.775, + "step": 397312 + }, + { + "epoch": 0.01, + "learning_rate": 4.348675577172665e-05, + "loss": 3.7946, + "step": 397824 + }, + { + "epoch": 0.01, + "learning_rate": 4.347836982421613e-05, + "loss": 3.7954, + "step": 398336 + }, + { + "epoch": 0.01, + "learning_rate": 4.347000025550934e-05, + "loss": 3.7921, + "step": 398848 + }, + { + "epoch": 0.01, + "learning_rate": 4.346161430799882e-05, + "loss": 3.7817, + "step": 399360 + }, + { + "epoch": 0.01, + "learning_rate": 4.34532283604883e-05, + "loss": 3.7944, + "step": 399872 + }, + { + "epoch": 0.01, + "learning_rate": 4.344484241297778e-05, + "loss": 3.7821, + "step": 400384 + }, + { + "epoch": 0.01, + "learning_rate": 4.343647284427099e-05, + "loss": 3.7919, + "step": 400896 + }, + { + "epoch": 0.01, + "learning_rate": 4.342808689676047e-05, + "loss": 3.7858, + "step": 401408 + }, + { + "epoch": 0.01, + "learning_rate": 4.341970094924995e-05, + "loss": 3.7724, + "step": 401920 + }, + { + "epoch": 0.01, + "learning_rate": 4.3411315001739436e-05, + "loss": 3.7794, + "step": 402432 + }, + { + "epoch": 0.01, + "learning_rate": 4.3402945433032645e-05, + "loss": 3.7706, + "step": 402944 + }, + { + "epoch": 0.01, + "learning_rate": 4.3394559485522125e-05, + "loss": 3.7945, + "step": 403456 + }, + { + "epoch": 0.01, + "learning_rate": 4.3386173538011605e-05, + "loss": 3.7773, + "step": 403968 + }, + { + "epoch": 0.01, + "learning_rate": 4.3377787590501085e-05, + "loss": 3.7758, + "step": 404480 + }, + { + "epoch": 0.01, + "learning_rate": 4.3369418021794294e-05, + "loss": 3.7852, + "step": 404992 + }, + { + "epoch": 0.01, + "learning_rate": 4.3361032074283774e-05, + "loss": 3.7824, + "step": 405504 + }, + { + "epoch": 0.01, + "learning_rate": 4.3352646126773254e-05, + "loss": 3.7954, + "step": 406016 + }, + { + "epoch": 0.01, + "learning_rate": 4.3344260179262734e-05, + "loss": 3.7714, + "step": 406528 + }, + { + "epoch": 0.01, + "learning_rate": 4.333589061055594e-05, + "loss": 3.7746, + "step": 407040 + }, + { + "epoch": 0.01, + "learning_rate": 4.332750466304542e-05, + "loss": 3.7828, + "step": 407552 + }, + { + "epoch": 0.01, + "learning_rate": 4.33191187155349e-05, + "loss": 3.7818, + "step": 408064 + }, + { + "epoch": 0.01, + "learning_rate": 4.331073276802439e-05, + "loss": 3.7763, + "step": 408576 + }, + { + "epoch": 0.01, + "learning_rate": 4.33023631993176e-05, + "loss": 3.7749, + "step": 409088 + }, + { + "epoch": 0.01, + "learning_rate": 4.329397725180708e-05, + "loss": 3.7723, + "step": 409600 + }, + { + "epoch": 0.01, + "learning_rate": 4.328559130429656e-05, + "loss": 3.7777, + "step": 410112 + }, + { + "epoch": 0.01, + "learning_rate": 4.327720535678604e-05, + "loss": 3.7804, + "step": 410624 + }, + { + "epoch": 0.01, + "learning_rate": 4.326883578807925e-05, + "loss": 3.7743, + "step": 411136 + }, + { + "epoch": 0.01, + "learning_rate": 4.326044984056873e-05, + "loss": 3.787, + "step": 411648 + }, + { + "epoch": 0.01, + "learning_rate": 4.325206389305821e-05, + "loss": 3.7716, + "step": 412160 + }, + { + "epoch": 0.01, + "learning_rate": 4.324367794554768e-05, + "loss": 3.7645, + "step": 412672 + }, + { + "epoch": 0.01, + "learning_rate": 4.32353083768409e-05, + "loss": 3.7722, + "step": 413184 + }, + { + "epoch": 0.01, + "learning_rate": 4.322692242933038e-05, + "loss": 3.7716, + "step": 413696 + }, + { + "epoch": 0.01, + "learning_rate": 4.321853648181986e-05, + "loss": 3.7903, + "step": 414208 + }, + { + "epoch": 0.01, + "learning_rate": 4.321016691311307e-05, + "loss": 3.7673, + "step": 414720 + }, + { + "epoch": 0.01, + "learning_rate": 4.320178096560255e-05, + "loss": 3.7767, + "step": 415232 + }, + { + "epoch": 0.01, + "learning_rate": 4.319339501809203e-05, + "loss": 3.7578, + "step": 415744 + }, + { + "epoch": 0.01, + "learning_rate": 4.3185009070581506e-05, + "loss": 3.7763, + "step": 416256 + }, + { + "epoch": 0.01, + "learning_rate": 4.317663950187472e-05, + "loss": 3.7635, + "step": 416768 + }, + { + "epoch": 0.01, + "learning_rate": 4.31682535543642e-05, + "loss": 3.7689, + "step": 417280 + }, + { + "epoch": 0.01, + "learning_rate": 4.315986760685368e-05, + "loss": 3.7766, + "step": 417792 + }, + { + "epoch": 0.01, + "learning_rate": 4.3151481659343155e-05, + "loss": 3.7701, + "step": 418304 + }, + { + "epoch": 0.01, + "learning_rate": 4.314311209063637e-05, + "loss": 3.7724, + "step": 418816 + }, + { + "epoch": 0.01, + "learning_rate": 4.313472614312585e-05, + "loss": 3.7841, + "step": 419328 + }, + { + "epoch": 0.01, + "learning_rate": 4.312634019561533e-05, + "loss": 3.7755, + "step": 419840 + }, + { + "epoch": 0.01, + "learning_rate": 4.3117970626908546e-05, + "loss": 3.7847, + "step": 420352 + }, + { + "epoch": 0.01, + "learning_rate": 4.3109584679398026e-05, + "loss": 3.7702, + "step": 420864 + }, + { + "epoch": 0.01, + "learning_rate": 4.3101198731887506e-05, + "loss": 3.7626, + "step": 421376 + }, + { + "epoch": 0.01, + "learning_rate": 4.309281278437698e-05, + "loss": 3.7697, + "step": 421888 + }, + { + "epoch": 0.01, + "learning_rate": 4.308442683686646e-05, + "loss": 3.7848, + "step": 422400 + }, + { + "epoch": 0.01, + "learning_rate": 4.307604088935594e-05, + "loss": 3.7688, + "step": 422912 + }, + { + "epoch": 0.01, + "learning_rate": 4.306765494184542e-05, + "loss": 3.7665, + "step": 423424 + }, + { + "epoch": 0.01, + "learning_rate": 4.305928537313863e-05, + "loss": 3.7539, + "step": 423936 + }, + { + "epoch": 0.01, + "learning_rate": 4.305089942562811e-05, + "loss": 3.7691, + "step": 424448 + }, + { + "epoch": 0.01, + "learning_rate": 4.304251347811759e-05, + "loss": 3.7548, + "step": 424960 + }, + { + "epoch": 0.01, + "learning_rate": 4.303412753060707e-05, + "loss": 3.7696, + "step": 425472 + }, + { + "epoch": 0.01, + "learning_rate": 4.3025757961900284e-05, + "loss": 3.7712, + "step": 425984 + }, + { + "epoch": 0.01, + "learning_rate": 4.30173883931935e-05, + "loss": 3.7763, + "step": 426496 + }, + { + "epoch": 0.01, + "learning_rate": 4.300900244568298e-05, + "loss": 3.7692, + "step": 427008 + }, + { + "epoch": 0.02, + "learning_rate": 4.300061649817245e-05, + "loss": 3.7703, + "step": 427520 + }, + { + "epoch": 0.02, + "learning_rate": 4.299223055066193e-05, + "loss": 3.7542, + "step": 428032 + }, + { + "epoch": 0.02, + "learning_rate": 4.298384460315141e-05, + "loss": 3.7658, + "step": 428544 + }, + { + "epoch": 0.02, + "learning_rate": 4.297545865564089e-05, + "loss": 3.766, + "step": 429056 + }, + { + "epoch": 0.02, + "learning_rate": 4.296707270813037e-05, + "loss": 3.7644, + "step": 429568 + }, + { + "epoch": 0.02, + "learning_rate": 4.295868676061985e-05, + "loss": 3.7583, + "step": 430080 + }, + { + "epoch": 0.02, + "learning_rate": 4.295031719191306e-05, + "loss": 3.7728, + "step": 430592 + }, + { + "epoch": 0.02, + "learning_rate": 4.294193124440254e-05, + "loss": 3.7601, + "step": 431104 + }, + { + "epoch": 0.02, + "learning_rate": 4.293354529689202e-05, + "loss": 3.7872, + "step": 431616 + }, + { + "epoch": 0.02, + "learning_rate": 4.292517572818524e-05, + "loss": 3.7572, + "step": 432128 + }, + { + "epoch": 0.02, + "learning_rate": 4.291678978067472e-05, + "loss": 3.7763, + "step": 432640 + }, + { + "epoch": 0.02, + "learning_rate": 4.29084038331642e-05, + "loss": 3.7651, + "step": 433152 + }, + { + "epoch": 0.02, + "learning_rate": 4.290001788565368e-05, + "loss": 3.7629, + "step": 433664 + }, + { + "epoch": 0.02, + "learning_rate": 4.289163193814316e-05, + "loss": 3.7846, + "step": 434176 + }, + { + "epoch": 0.02, + "learning_rate": 4.288324599063264e-05, + "loss": 3.7578, + "step": 434688 + }, + { + "epoch": 0.02, + "learning_rate": 4.287486004312212e-05, + "loss": 3.779, + "step": 435200 + }, + { + "epoch": 0.02, + "learning_rate": 4.286649047441533e-05, + "loss": 3.7582, + "step": 435712 + }, + { + "epoch": 0.02, + "learning_rate": 4.285810452690481e-05, + "loss": 3.7596, + "step": 436224 + }, + { + "epoch": 0.02, + "learning_rate": 4.284971857939429e-05, + "loss": 3.7532, + "step": 436736 + }, + { + "epoch": 0.02, + "learning_rate": 4.284133263188377e-05, + "loss": 3.7699, + "step": 437248 + }, + { + "epoch": 0.02, + "learning_rate": 4.2832963063176976e-05, + "loss": 3.7682, + "step": 437760 + }, + { + "epoch": 0.02, + "learning_rate": 4.2824577115666456e-05, + "loss": 3.7587, + "step": 438272 + }, + { + "epoch": 0.02, + "learning_rate": 4.281619116815594e-05, + "loss": 3.7432, + "step": 438784 + }, + { + "epoch": 0.02, + "learning_rate": 4.280780522064542e-05, + "loss": 3.7596, + "step": 439296 + }, + { + "epoch": 0.02, + "learning_rate": 4.279943565193863e-05, + "loss": 3.7734, + "step": 439808 + }, + { + "epoch": 0.02, + "learning_rate": 4.279104970442811e-05, + "loss": 3.764, + "step": 440320 + }, + { + "epoch": 0.02, + "learning_rate": 4.278266375691759e-05, + "loss": 3.7729, + "step": 440832 + }, + { + "epoch": 0.02, + "learning_rate": 4.277427780940707e-05, + "loss": 3.7642, + "step": 441344 + }, + { + "epoch": 0.02, + "learning_rate": 4.276589186189655e-05, + "loss": 3.7642, + "step": 441856 + }, + { + "epoch": 0.02, + "learning_rate": 4.275750591438603e-05, + "loss": 3.7711, + "step": 442368 + }, + { + "epoch": 0.02, + "learning_rate": 4.274911996687551e-05, + "loss": 3.7591, + "step": 442880 + }, + { + "epoch": 0.02, + "learning_rate": 4.274075039816872e-05, + "loss": 3.7518, + "step": 443392 + }, + { + "epoch": 0.02, + "learning_rate": 4.27323644506582e-05, + "loss": 3.7584, + "step": 443904 + }, + { + "epoch": 0.02, + "learning_rate": 4.272397850314768e-05, + "loss": 3.7583, + "step": 444416 + }, + { + "epoch": 0.02, + "learning_rate": 4.271559255563716e-05, + "loss": 3.759, + "step": 444928 + }, + { + "epoch": 0.02, + "learning_rate": 4.2707222986930376e-05, + "loss": 3.7585, + "step": 445440 + }, + { + "epoch": 0.02, + "learning_rate": 4.2698853418223585e-05, + "loss": 3.7623, + "step": 445952 + }, + { + "epoch": 0.02, + "learning_rate": 4.2690467470713065e-05, + "loss": 3.7559, + "step": 446464 + }, + { + "epoch": 0.02, + "learning_rate": 4.2682081523202545e-05, + "loss": 3.7508, + "step": 446976 + }, + { + "epoch": 0.02, + "learning_rate": 4.2673695575692025e-05, + "loss": 3.7695, + "step": 447488 + }, + { + "epoch": 0.02, + "learning_rate": 4.2665309628181505e-05, + "loss": 3.7555, + "step": 448000 + }, + { + "epoch": 0.02, + "learning_rate": 4.2656923680670985e-05, + "loss": 3.7686, + "step": 448512 + }, + { + "epoch": 0.02, + "learning_rate": 4.2648537733160465e-05, + "loss": 3.7708, + "step": 449024 + }, + { + "epoch": 0.02, + "learning_rate": 4.264015178564994e-05, + "loss": 3.7606, + "step": 449536 + }, + { + "epoch": 0.02, + "learning_rate": 4.2631782216943154e-05, + "loss": 3.7618, + "step": 450048 + }, + { + "epoch": 0.02, + "learning_rate": 4.2623396269432634e-05, + "loss": 3.7614, + "step": 450560 + }, + { + "epoch": 0.02, + "learning_rate": 4.2615010321922114e-05, + "loss": 3.7576, + "step": 451072 + }, + { + "epoch": 0.02, + "learning_rate": 4.2606624374411594e-05, + "loss": 3.7561, + "step": 451584 + }, + { + "epoch": 0.02, + "learning_rate": 4.259825480570481e-05, + "loss": 3.7746, + "step": 452096 + }, + { + "epoch": 0.02, + "learning_rate": 4.258986885819429e-05, + "loss": 3.7706, + "step": 452608 + }, + { + "epoch": 0.02, + "learning_rate": 4.258148291068376e-05, + "loss": 3.7632, + "step": 453120 + }, + { + "epoch": 0.02, + "learning_rate": 4.257309696317324e-05, + "loss": 3.7649, + "step": 453632 + }, + { + "epoch": 0.02, + "learning_rate": 4.256472739446646e-05, + "loss": 3.757, + "step": 454144 + }, + { + "epoch": 0.02, + "learning_rate": 4.255634144695594e-05, + "loss": 3.7627, + "step": 454656 + }, + { + "epoch": 0.02, + "learning_rate": 4.254795549944541e-05, + "loss": 3.7535, + "step": 455168 + }, + { + "epoch": 0.02, + "learning_rate": 4.253958593073863e-05, + "loss": 3.7515, + "step": 455680 + }, + { + "epoch": 0.02, + "learning_rate": 4.253119998322811e-05, + "loss": 3.7623, + "step": 456192 + }, + { + "epoch": 0.02, + "learning_rate": 4.252281403571758e-05, + "loss": 3.7541, + "step": 456704 + }, + { + "epoch": 0.02, + "learning_rate": 4.251442808820707e-05, + "loss": 3.7488, + "step": 457216 + }, + { + "epoch": 0.02, + "learning_rate": 4.250604214069655e-05, + "loss": 3.7556, + "step": 457728 + }, + { + "epoch": 0.03, + "eval_loss": 3.874908685684204, + "eval_runtime": 556.2656, + "eval_samples_per_second": 685.987, + "eval_steps_per_second": 21.438, + "step": 457914 + }, + { + "epoch": 0.0, + "learning_rate": 4.249767257198976e-05, + "loss": 3.7647, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.2489286624479237e-05, + "loss": 3.7611, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.2480900676968716e-05, + "loss": 3.7564, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.2472514729458196e-05, + "loss": 3.7585, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.2464128781947676e-05, + "loss": 3.7582, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.2455742834437156e-05, + "loss": 3.7453, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.2447356886926636e-05, + "loss": 3.7554, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.2438970939416116e-05, + "loss": 3.7452, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.2430617749513054e-05, + "loss": 3.7538, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.2422231802002534e-05, + "loss": 3.7561, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.241384585449202e-05, + "loss": 3.7606, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.24054599069815e-05, + "loss": 3.7386, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.239707395947098e-05, + "loss": 3.753, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.238868801196046e-05, + "loss": 3.746, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.238030206444994e-05, + "loss": 3.7568, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.237191611693942e-05, + "loss": 3.7371, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.236354654823263e-05, + "loss": 3.7398, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.235516060072211e-05, + "loss": 3.7485, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.234677465321159e-05, + "loss": 3.745, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.233838870570107e-05, + "loss": 3.7567, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.233003551579801e-05, + "loss": 3.7473, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.232164956828749e-05, + "loss": 3.76, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.2313263620776975e-05, + "loss": 3.7545, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.2304877673266455e-05, + "loss": 3.7502, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.2296491725755935e-05, + "loss": 3.7445, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.2288105778245415e-05, + "loss": 3.7498, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.2279719830734895e-05, + "loss": 3.7571, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.2271333883224375e-05, + "loss": 3.7484, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.2262964314517584e-05, + "loss": 3.7465, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.2254578367007064e-05, + "loss": 3.7499, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.2246192419496544e-05, + "loss": 3.7364, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.2237806471986024e-05, + "loss": 3.753, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.222943690327923e-05, + "loss": 3.7555, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.222105095576871e-05, + "loss": 3.7514, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.221266500825819e-05, + "loss": 3.7402, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.220427906074767e-05, + "loss": 3.7533, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.219589311323716e-05, + "loss": 3.74, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.218750716572664e-05, + "loss": 3.75, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.217912121821612e-05, + "loss": 3.7481, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.21707352707056e-05, + "loss": 3.7343, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.216236570199881e-05, + "loss": 3.7346, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.215397975448829e-05, + "loss": 3.7291, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.214559380697777e-05, + "loss": 3.7579, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.213720785946725e-05, + "loss": 3.7359, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.212883829076046e-05, + "loss": 3.7345, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.212045234324994e-05, + "loss": 3.7464, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.211206639573942e-05, + "loss": 3.742, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.2103696827032626e-05, + "loss": 3.7517, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.209531087952211e-05, + "loss": 3.7343, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.208692493201159e-05, + "loss": 3.7377, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.207853898450107e-05, + "loss": 3.7373, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.2070153036990546e-05, + "loss": 3.743, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.206178346828376e-05, + "loss": 3.7364, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.205339752077324e-05, + "loss": 3.7324, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.204501157326272e-05, + "loss": 3.736, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.2036625625752195e-05, + "loss": 3.7419, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.2028239678241675e-05, + "loss": 3.7375, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.2019853730731155e-05, + "loss": 3.733, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.2011467783220635e-05, + "loss": 3.7462, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.200309821451385e-05, + "loss": 3.7322, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.199471226700333e-05, + "loss": 3.7238, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.1986342698296547e-05, + "loss": 3.7332, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.197795675078602e-05, + "loss": 3.7314, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.19695708032755e-05, + "loss": 3.7515, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.196118485576498e-05, + "loss": 3.7298, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.195279890825446e-05, + "loss": 3.7344, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.194441296074394e-05, + "loss": 3.7191, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.193604339203715e-05, + "loss": 3.7349, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.192765744452663e-05, + "loss": 3.724, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.191927149701611e-05, + "loss": 3.73, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.191088554950559e-05, + "loss": 3.7371, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.1902515980798804e-05, + "loss": 3.7311, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.1894130033288284e-05, + "loss": 3.735, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.1885744085777764e-05, + "loss": 3.7419, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.1877358138267244e-05, + "loss": 3.7381, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.1868972190756724e-05, + "loss": 3.7442, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.1860586243246204e-05, + "loss": 3.7371, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.1852200295735684e-05, + "loss": 3.7203, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.1843814348225164e-05, + "loss": 3.7283, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.183544477951837e-05, + "loss": 3.7402, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.182705883200785e-05, + "loss": 3.7357, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.181867288449733e-05, + "loss": 3.7305, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.181028693698681e-05, + "loss": 3.7126, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.180190098947629e-05, + "loss": 3.7328, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.17935314207695e-05, + "loss": 3.7157, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.178514547325898e-05, + "loss": 3.7331, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.177675952574847e-05, + "loss": 3.7296, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.176837357823795e-05, + "loss": 3.7376, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.175998763072743e-05, + "loss": 3.7318, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.175160168321691e-05, + "loss": 3.7298, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.174323211451012e-05, + "loss": 3.7186, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.17348461669996e-05, + "loss": 3.7324, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.172646021948908e-05, + "loss": 3.7239, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.171807427197855e-05, + "loss": 3.7274, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.170968832446803e-05, + "loss": 3.7188, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.170130237695751e-05, + "loss": 3.7306, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.169293280825073e-05, + "loss": 3.7231, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.1684546860740207e-05, + "loss": 3.748, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.1676160913229687e-05, + "loss": 3.7207, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.1667774965719167e-05, + "loss": 3.7384, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.1659389018208646e-05, + "loss": 3.7292, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.1651003070698126e-05, + "loss": 3.725, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.1642617123187606e-05, + "loss": 3.7425, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.1634231175677086e-05, + "loss": 3.7253, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.1625861606970295e-05, + "loss": 3.7395, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.1617475659459775e-05, + "loss": 3.7253, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.1609089711949255e-05, + "loss": 3.7179, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.1600703764438735e-05, + "loss": 3.716, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.1592334195731944e-05, + "loss": 3.7317, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.1583948248221424e-05, + "loss": 3.7304, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.1575562300710904e-05, + "loss": 3.7264, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.156717635320039e-05, + "loss": 3.7007, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.155879040568987e-05, + "loss": 3.7226, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.155040445817935e-05, + "loss": 3.7369, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.154203488947256e-05, + "loss": 3.7269, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.153364894196204e-05, + "loss": 3.7341, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.152526299445152e-05, + "loss": 3.7286, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.1516877046941e-05, + "loss": 3.7272, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.150849109943048e-05, + "loss": 3.7317, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.150012153072369e-05, + "loss": 3.7235, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.149173558321317e-05, + "loss": 3.7133, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.148334963570265e-05, + "loss": 3.7223, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.147496368819213e-05, + "loss": 3.7224, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.1466594119485345e-05, + "loss": 3.7234, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.1458208171974825e-05, + "loss": 3.7229, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.1449822224464305e-05, + "loss": 3.7276, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.1441436276953785e-05, + "loss": 3.7187, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.1433050329443265e-05, + "loss": 3.7159, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.1424680760736474e-05, + "loss": 3.7326, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.1416294813225954e-05, + "loss": 3.7173, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.1407908865715434e-05, + "loss": 3.7322, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.1399522918204913e-05, + "loss": 3.7324, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.139113697069439e-05, + "loss": 3.7253, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.138275102318387e-05, + "loss": 3.7249, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.137438145447708e-05, + "loss": 3.7265, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.136599550696656e-05, + "loss": 3.7194, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.135760955945604e-05, + "loss": 3.7211, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.134922361194552e-05, + "loss": 3.7381, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.1340837664435e-05, + "loss": 3.7329, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.133246809572821e-05, + "loss": 3.7305, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.132408214821769e-05, + "loss": 3.7292, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.131569620070717e-05, + "loss": 3.7181, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.130731025319665e-05, + "loss": 3.7248, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.129892430568613e-05, + "loss": 3.7177, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.129055473697934e-05, + "loss": 3.7135, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.128216878946882e-05, + "loss": 3.7305, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.12737828419583e-05, + "loss": 3.717, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.126539689444778e-05, + "loss": 3.7126, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.125701094693726e-05, + "loss": 3.7229, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 3.86488938331604, + "eval_runtime": 582.4563, + "eval_samples_per_second": 655.141, + "eval_steps_per_second": 20.474, + "step": 534233 + }, + { + "epoch": 0.0, + "learning_rate": 4.1248641378230476e-05, + "loss": 3.7296, + "step": 534528 + }, + { + "epoch": 0.0, + "learning_rate": 4.1240255430719956e-05, + "loss": 3.7221, + "step": 535040 + }, + { + "epoch": 0.0, + "learning_rate": 4.1231869483209436e-05, + "loss": 3.7265, + "step": 535552 + }, + { + "epoch": 0.0, + "learning_rate": 4.1223483535698916e-05, + "loss": 3.7224, + "step": 536064 + }, + { + "epoch": 0.0, + "learning_rate": 4.1215097588188396e-05, + "loss": 3.7183, + "step": 536576 + }, + { + "epoch": 0.0, + "learning_rate": 4.1206728019481605e-05, + "loss": 3.7136, + "step": 537088 + }, + { + "epoch": 0.0, + "learning_rate": 4.1198342071971085e-05, + "loss": 3.7185, + "step": 537600 + }, + { + "epoch": 0.0, + "learning_rate": 4.1189956124460565e-05, + "loss": 3.7115, + "step": 538112 + }, + { + "epoch": 0.0, + "learning_rate": 4.1181570176950045e-05, + "loss": 3.7164, + "step": 538624 + }, + { + "epoch": 0.0, + "learning_rate": 4.1173200608243254e-05, + "loss": 3.7162, + "step": 539136 + }, + { + "epoch": 0.0, + "learning_rate": 4.1164814660732734e-05, + "loss": 3.7286, + "step": 539648 + }, + { + "epoch": 0.0, + "learning_rate": 4.1156428713222214e-05, + "loss": 3.7068, + "step": 540160 + }, + { + "epoch": 0.0, + "learning_rate": 4.11480427657117e-05, + "loss": 3.7182, + "step": 540672 + }, + { + "epoch": 0.0, + "learning_rate": 4.113965681820118e-05, + "loss": 3.7077, + "step": 541184 + }, + { + "epoch": 0.0, + "learning_rate": 4.113128724949439e-05, + "loss": 3.7229, + "step": 541696 + }, + { + "epoch": 0.0, + "learning_rate": 4.112290130198387e-05, + "loss": 3.704, + "step": 542208 + }, + { + "epoch": 0.0, + "learning_rate": 4.111451535447335e-05, + "loss": 3.7064, + "step": 542720 + }, + { + "epoch": 0.0, + "learning_rate": 4.110612940696283e-05, + "loss": 3.7115, + "step": 543232 + }, + { + "epoch": 0.0, + "learning_rate": 4.109774345945231e-05, + "loss": 3.7107, + "step": 543744 + }, + { + "epoch": 0.0, + "learning_rate": 4.108935751194179e-05, + "loss": 3.722, + "step": 544256 + }, + { + "epoch": 0.0, + "learning_rate": 4.1080987943235e-05, + "loss": 3.712, + "step": 544768 + }, + { + "epoch": 0.0, + "learning_rate": 4.107260199572448e-05, + "loss": 3.7267, + "step": 545280 + }, + { + "epoch": 0.0, + "learning_rate": 4.106421604821396e-05, + "loss": 3.7164, + "step": 545792 + }, + { + "epoch": 0.0, + "learning_rate": 4.105583010070344e-05, + "loss": 3.7182, + "step": 546304 + }, + { + "epoch": 0.0, + "learning_rate": 4.104744415319292e-05, + "loss": 3.7134, + "step": 546816 + }, + { + "epoch": 0.0, + "learning_rate": 4.1039074584486134e-05, + "loss": 3.7142, + "step": 547328 + }, + { + "epoch": 0.0, + "learning_rate": 4.1030688636975614e-05, + "loss": 3.7177, + "step": 547840 + }, + { + "epoch": 0.0, + "learning_rate": 4.1022302689465094e-05, + "loss": 3.7141, + "step": 548352 + }, + { + "epoch": 0.0, + "learning_rate": 4.1013916741954574e-05, + "loss": 3.7148, + "step": 548864 + }, + { + "epoch": 0.0, + "learning_rate": 4.100553079444405e-05, + "loss": 3.7133, + "step": 549376 + }, + { + "epoch": 0.01, + "learning_rate": 4.099716122573726e-05, + "loss": 3.7032, + "step": 549888 + }, + { + "epoch": 0.01, + "learning_rate": 4.098877527822674e-05, + "loss": 3.7148, + "step": 550400 + }, + { + "epoch": 0.01, + "learning_rate": 4.098038933071622e-05, + "loss": 3.7235, + "step": 550912 + }, + { + "epoch": 0.01, + "learning_rate": 4.0972003383205696e-05, + "loss": 3.7136, + "step": 551424 + }, + { + "epoch": 0.01, + "learning_rate": 4.0963617435695176e-05, + "loss": 3.7075, + "step": 551936 + }, + { + "epoch": 0.01, + "learning_rate": 4.095524786698839e-05, + "loss": 3.7172, + "step": 552448 + }, + { + "epoch": 0.01, + "learning_rate": 4.094686191947787e-05, + "loss": 3.7076, + "step": 552960 + }, + { + "epoch": 0.01, + "learning_rate": 4.093847597196735e-05, + "loss": 3.7149, + "step": 553472 + }, + { + "epoch": 0.01, + "learning_rate": 4.093009002445683e-05, + "loss": 3.7101, + "step": 553984 + }, + { + "epoch": 0.01, + "learning_rate": 4.092172045575005e-05, + "loss": 3.7034, + "step": 554496 + }, + { + "epoch": 0.01, + "learning_rate": 4.091333450823952e-05, + "loss": 3.7011, + "step": 555008 + }, + { + "epoch": 0.01, + "learning_rate": 4.0904948560729e-05, + "loss": 3.696, + "step": 555520 + }, + { + "epoch": 0.01, + "learning_rate": 4.089656261321848e-05, + "loss": 3.7192, + "step": 556032 + }, + { + "epoch": 0.01, + "learning_rate": 4.088817666570796e-05, + "loss": 3.7021, + "step": 556544 + }, + { + "epoch": 0.01, + "learning_rate": 4.087980709700117e-05, + "loss": 3.7021, + "step": 557056 + }, + { + "epoch": 0.01, + "learning_rate": 4.087142114949065e-05, + "loss": 3.714, + "step": 557568 + }, + { + "epoch": 0.01, + "learning_rate": 4.086303520198013e-05, + "loss": 3.7055, + "step": 558080 + }, + { + "epoch": 0.01, + "learning_rate": 4.085464925446961e-05, + "loss": 3.716, + "step": 558592 + }, + { + "epoch": 0.01, + "learning_rate": 4.084626330695909e-05, + "loss": 3.6995, + "step": 559104 + }, + { + "epoch": 0.01, + "learning_rate": 4.0837893738252306e-05, + "loss": 3.706, + "step": 559616 + }, + { + "epoch": 0.01, + "learning_rate": 4.0829507790741786e-05, + "loss": 3.7016, + "step": 560128 + }, + { + "epoch": 0.01, + "learning_rate": 4.0821121843231265e-05, + "loss": 3.7072, + "step": 560640 + }, + { + "epoch": 0.01, + "learning_rate": 4.0812735895720745e-05, + "loss": 3.7074, + "step": 561152 + }, + { + "epoch": 0.01, + "learning_rate": 4.0804366327013955e-05, + "loss": 3.6971, + "step": 561664 + }, + { + "epoch": 0.01, + "learning_rate": 4.0795980379503435e-05, + "loss": 3.7043, + "step": 562176 + }, + { + "epoch": 0.01, + "learning_rate": 4.0787594431992914e-05, + "loss": 3.7072, + "step": 562688 + }, + { + "epoch": 0.01, + "learning_rate": 4.0779208484482394e-05, + "loss": 3.7049, + "step": 563200 + }, + { + "epoch": 0.01, + "learning_rate": 4.0770822536971874e-05, + "loss": 3.7023, + "step": 563712 + }, + { + "epoch": 0.01, + "learning_rate": 4.0762452968265083e-05, + "loss": 3.7144, + "step": 564224 + }, + { + "epoch": 0.01, + "learning_rate": 4.0754067020754563e-05, + "loss": 3.6941, + "step": 564736 + }, + { + "epoch": 0.01, + "learning_rate": 4.074568107324404e-05, + "loss": 3.697, + "step": 565248 + }, + { + "epoch": 0.01, + "learning_rate": 4.073729512573352e-05, + "loss": 3.6976, + "step": 565760 + }, + { + "epoch": 0.01, + "learning_rate": 4.072892555702674e-05, + "loss": 3.7029, + "step": 566272 + }, + { + "epoch": 0.01, + "learning_rate": 4.072053960951622e-05, + "loss": 3.7143, + "step": 566784 + }, + { + "epoch": 0.01, + "learning_rate": 4.07121536620057e-05, + "loss": 3.6977, + "step": 567296 + }, + { + "epoch": 0.01, + "learning_rate": 4.070376771449518e-05, + "loss": 3.7012, + "step": 567808 + }, + { + "epoch": 0.01, + "learning_rate": 4.069539814578839e-05, + "loss": 3.6888, + "step": 568320 + }, + { + "epoch": 0.01, + "learning_rate": 4.068701219827787e-05, + "loss": 3.7008, + "step": 568832 + }, + { + "epoch": 0.01, + "learning_rate": 4.067862625076735e-05, + "loss": 3.6925, + "step": 569344 + }, + { + "epoch": 0.01, + "learning_rate": 4.067024030325683e-05, + "loss": 3.6996, + "step": 569856 + }, + { + "epoch": 0.01, + "learning_rate": 4.066187073455004e-05, + "loss": 3.7044, + "step": 570368 + }, + { + "epoch": 0.01, + "learning_rate": 4.065348478703952e-05, + "loss": 3.6983, + "step": 570880 + }, + { + "epoch": 0.01, + "learning_rate": 4.0645098839529e-05, + "loss": 3.6999, + "step": 571392 + }, + { + "epoch": 0.01, + "learning_rate": 4.063671289201848e-05, + "loss": 3.7136, + "step": 571904 + }, + { + "epoch": 0.01, + "learning_rate": 4.062834332331169e-05, + "loss": 3.7041, + "step": 572416 + }, + { + "epoch": 0.01, + "learning_rate": 4.061995737580117e-05, + "loss": 3.7088, + "step": 572928 + }, + { + "epoch": 0.01, + "learning_rate": 4.061157142829065e-05, + "loss": 3.7031, + "step": 573440 + }, + { + "epoch": 0.01, + "learning_rate": 4.060318548078013e-05, + "loss": 3.6928, + "step": 573952 + }, + { + "epoch": 0.01, + "learning_rate": 4.059479953326961e-05, + "loss": 3.6957, + "step": 574464 + }, + { + "epoch": 0.01, + "learning_rate": 4.058642996456282e-05, + "loss": 3.7078, + "step": 574976 + }, + { + "epoch": 0.01, + "learning_rate": 4.05780440170523e-05, + "loss": 3.7032, + "step": 575488 + }, + { + "epoch": 0.01, + "learning_rate": 4.056965806954178e-05, + "loss": 3.6959, + "step": 576000 + }, + { + "epoch": 0.01, + "learning_rate": 4.056127212203126e-05, + "loss": 3.6819, + "step": 576512 + }, + { + "epoch": 0.01, + "learning_rate": 4.055288617452074e-05, + "loss": 3.6968, + "step": 577024 + }, + { + "epoch": 0.01, + "learning_rate": 4.054451660581395e-05, + "loss": 3.6867, + "step": 577536 + }, + { + "epoch": 0.01, + "learning_rate": 4.053613065830343e-05, + "loss": 3.7, + "step": 578048 + }, + { + "epoch": 0.01, + "learning_rate": 4.052774471079292e-05, + "loss": 3.6951, + "step": 578560 + }, + { + "epoch": 0.01, + "learning_rate": 4.05193587632824e-05, + "loss": 3.7064, + "step": 579072 + }, + { + "epoch": 0.01, + "learning_rate": 4.0510989194575606e-05, + "loss": 3.7038, + "step": 579584 + }, + { + "epoch": 0.02, + "learning_rate": 4.0502603247065086e-05, + "loss": 3.6938, + "step": 580096 + }, + { + "epoch": 0.02, + "learning_rate": 4.0494217299554566e-05, + "loss": 3.6912, + "step": 580608 + }, + { + "epoch": 0.02, + "learning_rate": 4.0485831352044046e-05, + "loss": 3.6983, + "step": 581120 + }, + { + "epoch": 0.02, + "learning_rate": 4.0477461783337255e-05, + "loss": 3.6904, + "step": 581632 + }, + { + "epoch": 0.02, + "learning_rate": 4.0469075835826735e-05, + "loss": 3.6958, + "step": 582144 + }, + { + "epoch": 0.02, + "learning_rate": 4.0460689888316215e-05, + "loss": 3.6889, + "step": 582656 + }, + { + "epoch": 0.02, + "learning_rate": 4.0452303940805695e-05, + "loss": 3.6985, + "step": 583168 + }, + { + "epoch": 0.02, + "learning_rate": 4.0443934372098904e-05, + "loss": 3.6929, + "step": 583680 + }, + { + "epoch": 0.02, + "learning_rate": 4.0435548424588384e-05, + "loss": 3.7182, + "step": 584192 + }, + { + "epoch": 0.02, + "learning_rate": 4.042716247707787e-05, + "loss": 3.6851, + "step": 584704 + }, + { + "epoch": 0.02, + "learning_rate": 4.041877652956735e-05, + "loss": 3.7063, + "step": 585216 + }, + { + "epoch": 0.02, + "learning_rate": 4.041039058205683e-05, + "loss": 3.7018, + "step": 585728 + }, + { + "epoch": 0.02, + "learning_rate": 4.040202101335004e-05, + "loss": 3.6937, + "step": 586240 + }, + { + "epoch": 0.02, + "learning_rate": 4.039363506583952e-05, + "loss": 3.7037, + "step": 586752 + }, + { + "epoch": 0.02, + "learning_rate": 4.0385249118329e-05, + "loss": 3.6978, + "step": 587264 + }, + { + "epoch": 0.02, + "learning_rate": 4.037686317081848e-05, + "loss": 3.7061, + "step": 587776 + }, + { + "epoch": 0.02, + "learning_rate": 4.036849360211169e-05, + "loss": 3.6925, + "step": 588288 + }, + { + "epoch": 0.02, + "learning_rate": 4.036010765460117e-05, + "loss": 3.6875, + "step": 588800 + }, + { + "epoch": 0.02, + "learning_rate": 4.035172170709065e-05, + "loss": 3.6847, + "step": 589312 + }, + { + "epoch": 0.02, + "learning_rate": 4.034333575958012e-05, + "loss": 3.701, + "step": 589824 + }, + { + "epoch": 0.02, + "learning_rate": 4.033494981206961e-05, + "loss": 3.6993, + "step": 590336 + }, + { + "epoch": 0.02, + "learning_rate": 4.0326580243362825e-05, + "loss": 3.6925, + "step": 590848 + }, + { + "epoch": 0.02, + "learning_rate": 4.0318194295852305e-05, + "loss": 3.6697, + "step": 591360 + }, + { + "epoch": 0.02, + "learning_rate": 4.030980834834178e-05, + "loss": 3.692, + "step": 591872 + }, + { + "epoch": 0.02, + "learning_rate": 4.030142240083126e-05, + "loss": 3.7048, + "step": 592384 + }, + { + "epoch": 0.02, + "learning_rate": 4.0293052832124474e-05, + "loss": 3.695, + "step": 592896 + }, + { + "epoch": 0.02, + "learning_rate": 4.0284666884613954e-05, + "loss": 3.7041, + "step": 593408 + }, + { + "epoch": 0.02, + "learning_rate": 4.027628093710343e-05, + "loss": 3.6948, + "step": 593920 + }, + { + "epoch": 0.02, + "learning_rate": 4.026789498959291e-05, + "loss": 3.6913, + "step": 594432 + }, + { + "epoch": 0.02, + "learning_rate": 4.025952542088612e-05, + "loss": 3.7019, + "step": 594944 + }, + { + "epoch": 0.02, + "learning_rate": 4.0251139473375596e-05, + "loss": 3.6927, + "step": 595456 + }, + { + "epoch": 0.02, + "learning_rate": 4.0242753525865076e-05, + "loss": 3.6857, + "step": 595968 + }, + { + "epoch": 0.02, + "learning_rate": 4.023436757835456e-05, + "loss": 3.6907, + "step": 596480 + }, + { + "epoch": 0.02, + "learning_rate": 4.022599800964778e-05, + "loss": 3.6917, + "step": 596992 + }, + { + "epoch": 0.02, + "learning_rate": 4.021761206213725e-05, + "loss": 3.6895, + "step": 597504 + }, + { + "epoch": 0.02, + "learning_rate": 4.020922611462673e-05, + "loss": 3.6865, + "step": 598016 + }, + { + "epoch": 0.02, + "learning_rate": 4.020084016711621e-05, + "loss": 3.6983, + "step": 598528 + }, + { + "epoch": 0.02, + "learning_rate": 4.019247059840943e-05, + "loss": 3.69, + "step": 599040 + }, + { + "epoch": 0.02, + "learning_rate": 4.01840846508989e-05, + "loss": 3.6808, + "step": 599552 + }, + { + "epoch": 0.02, + "learning_rate": 4.017569870338838e-05, + "loss": 3.7044, + "step": 600064 + }, + { + "epoch": 0.02, + "learning_rate": 4.016731275587786e-05, + "loss": 3.6842, + "step": 600576 + }, + { + "epoch": 0.02, + "learning_rate": 4.015894318717107e-05, + "loss": 3.6998, + "step": 601088 + }, + { + "epoch": 0.02, + "learning_rate": 4.015055723966055e-05, + "loss": 3.7035, + "step": 601600 + }, + { + "epoch": 0.02, + "learning_rate": 4.014217129215003e-05, + "loss": 3.6935, + "step": 602112 + }, + { + "epoch": 0.02, + "learning_rate": 4.0133785344639516e-05, + "loss": 3.6928, + "step": 602624 + }, + { + "epoch": 0.02, + "learning_rate": 4.0125415775932725e-05, + "loss": 3.6936, + "step": 603136 + }, + { + "epoch": 0.02, + "learning_rate": 4.0117029828422205e-05, + "loss": 3.6901, + "step": 603648 + }, + { + "epoch": 0.02, + "learning_rate": 4.0108643880911685e-05, + "loss": 3.6909, + "step": 604160 + }, + { + "epoch": 0.02, + "learning_rate": 4.0100257933401165e-05, + "loss": 3.7057, + "step": 604672 + }, + { + "epoch": 0.02, + "learning_rate": 4.0091888364694374e-05, + "loss": 3.7008, + "step": 605184 + }, + { + "epoch": 0.02, + "learning_rate": 4.0083502417183854e-05, + "loss": 3.6998, + "step": 605696 + }, + { + "epoch": 0.02, + "learning_rate": 4.0075116469673334e-05, + "loss": 3.6979, + "step": 606208 + }, + { + "epoch": 0.02, + "learning_rate": 4.0066730522162814e-05, + "loss": 3.6887, + "step": 606720 + }, + { + "epoch": 0.02, + "learning_rate": 4.005836095345602e-05, + "loss": 3.698, + "step": 607232 + }, + { + "epoch": 0.02, + "learning_rate": 4.00499750059455e-05, + "loss": 3.6841, + "step": 607744 + }, + { + "epoch": 0.02, + "learning_rate": 4.004158905843498e-05, + "loss": 3.6858, + "step": 608256 + }, + { + "epoch": 0.02, + "learning_rate": 4.003320311092447e-05, + "loss": 3.6961, + "step": 608768 + }, + { + "epoch": 0.02, + "learning_rate": 4.002483354221768e-05, + "loss": 3.689, + "step": 609280 + }, + { + "epoch": 0.02, + "learning_rate": 4.001644759470716e-05, + "loss": 3.6787, + "step": 609792 + }, + { + "epoch": 0.02, + "learning_rate": 4.000806164719664e-05, + "loss": 3.6965, + "step": 610304 + }, + { + "epoch": 0.03, + "eval_loss": 3.857670307159424, + "eval_runtime": 572.0419, + "eval_samples_per_second": 667.068, + "eval_steps_per_second": 20.846, + "step": 610552 + }, + { + "epoch": 0.0, + "learning_rate": 3.999967569968612e-05, + "loss": 3.6968, + "step": 610816 + }, + { + "epoch": 0.0, + "learning_rate": 3.99912897521756e-05, + "loss": 3.6977, + "step": 611328 + }, + { + "epoch": 0.0, + "learning_rate": 3.998290380466508e-05, + "loss": 3.694, + "step": 611840 + }, + { + "epoch": 0.0, + "learning_rate": 3.997451785715456e-05, + "loss": 3.6916, + "step": 612352 + }, + { + "epoch": 0.0, + "learning_rate": 3.996614828844777e-05, + "loss": 3.6885, + "step": 612864 + }, + { + "epoch": 0.0, + "learning_rate": 3.995776234093725e-05, + "loss": 3.6837, + "step": 613376 + }, + { + "epoch": 0.0, + "learning_rate": 3.994937639342673e-05, + "loss": 3.687, + "step": 613888 + }, + { + "epoch": 0.0, + "learning_rate": 3.994099044591621e-05, + "loss": 3.6799, + "step": 614400 + }, + { + "epoch": 0.0, + "learning_rate": 3.993262087720942e-05, + "loss": 3.6837, + "step": 614912 + }, + { + "epoch": 0.0, + "learning_rate": 3.9924234929698903e-05, + "loss": 3.6897, + "step": 615424 + }, + { + "epoch": 0.0, + "learning_rate": 3.9915848982188383e-05, + "loss": 3.6965, + "step": 615936 + }, + { + "epoch": 0.0, + "learning_rate": 3.9907463034677863e-05, + "loss": 3.6776, + "step": 616448 + }, + { + "epoch": 0.0, + "learning_rate": 3.989909346597107e-05, + "loss": 3.6889, + "step": 616960 + }, + { + "epoch": 0.0, + "learning_rate": 3.989070751846055e-05, + "loss": 3.6737, + "step": 617472 + }, + { + "epoch": 0.0, + "learning_rate": 3.988232157095003e-05, + "loss": 3.697, + "step": 617984 + }, + { + "epoch": 0.0, + "learning_rate": 3.987393562343951e-05, + "loss": 3.6687, + "step": 618496 + }, + { + "epoch": 0.0, + "learning_rate": 3.986554967592899e-05, + "loss": 3.6768, + "step": 619008 + }, + { + "epoch": 0.0, + "learning_rate": 3.98571801072222e-05, + "loss": 3.6849, + "step": 619520 + }, + { + "epoch": 0.0, + "learning_rate": 3.984879415971168e-05, + "loss": 3.6802, + "step": 620032 + }, + { + "epoch": 0.0, + "learning_rate": 3.984040821220116e-05, + "loss": 3.6903, + "step": 620544 + }, + { + "epoch": 0.0, + "learning_rate": 3.983202226469064e-05, + "loss": 3.683, + "step": 621056 + }, + { + "epoch": 0.0, + "learning_rate": 3.982365269598386e-05, + "loss": 3.6975, + "step": 621568 + }, + { + "epoch": 0.0, + "learning_rate": 3.981526674847334e-05, + "loss": 3.6847, + "step": 622080 + }, + { + "epoch": 0.0, + "learning_rate": 3.980688080096282e-05, + "loss": 3.6874, + "step": 622592 + }, + { + "epoch": 0.0, + "learning_rate": 3.97984948534523e-05, + "loss": 3.6815, + "step": 623104 + }, + { + "epoch": 0.0, + "learning_rate": 3.9790125284745506e-05, + "loss": 3.6894, + "step": 623616 + }, + { + "epoch": 0.0, + "learning_rate": 3.9781739337234986e-05, + "loss": 3.6887, + "step": 624128 + }, + { + "epoch": 0.0, + "learning_rate": 3.9773353389724466e-05, + "loss": 3.6855, + "step": 624640 + }, + { + "epoch": 0.0, + "learning_rate": 3.9764967442213946e-05, + "loss": 3.685, + "step": 625152 + }, + { + "epoch": 0.0, + "learning_rate": 3.9756581494703426e-05, + "loss": 3.6852, + "step": 625664 + }, + { + "epoch": 0.01, + "learning_rate": 3.9748211925996635e-05, + "loss": 3.6707, + "step": 626176 + }, + { + "epoch": 0.01, + "learning_rate": 3.9739825978486115e-05, + "loss": 3.6857, + "step": 626688 + }, + { + "epoch": 0.01, + "learning_rate": 3.9731440030975595e-05, + "loss": 3.6943, + "step": 627200 + }, + { + "epoch": 0.01, + "learning_rate": 3.9723054083465075e-05, + "loss": 3.6827, + "step": 627712 + }, + { + "epoch": 0.01, + "learning_rate": 3.971468451475829e-05, + "loss": 3.6781, + "step": 628224 + }, + { + "epoch": 0.01, + "learning_rate": 3.970629856724777e-05, + "loss": 3.6886, + "step": 628736 + }, + { + "epoch": 0.01, + "learning_rate": 3.969791261973725e-05, + "loss": 3.6778, + "step": 629248 + }, + { + "epoch": 0.01, + "learning_rate": 3.968952667222673e-05, + "loss": 3.6842, + "step": 629760 + }, + { + "epoch": 0.01, + "learning_rate": 3.968115710351994e-05, + "loss": 3.6838, + "step": 630272 + }, + { + "epoch": 0.01, + "learning_rate": 3.967277115600942e-05, + "loss": 3.6721, + "step": 630784 + }, + { + "epoch": 0.01, + "learning_rate": 3.96643852084989e-05, + "loss": 3.6753, + "step": 631296 + }, + { + "epoch": 0.01, + "learning_rate": 3.965599926098838e-05, + "loss": 3.6656, + "step": 631808 + }, + { + "epoch": 0.01, + "learning_rate": 3.964762969228159e-05, + "loss": 3.689, + "step": 632320 + }, + { + "epoch": 0.01, + "learning_rate": 3.963924374477107e-05, + "loss": 3.6772, + "step": 632832 + }, + { + "epoch": 0.01, + "learning_rate": 3.963085779726055e-05, + "loss": 3.6733, + "step": 633344 + }, + { + "epoch": 0.01, + "learning_rate": 3.962247184975003e-05, + "loss": 3.6846, + "step": 633856 + }, + { + "epoch": 0.01, + "learning_rate": 3.961408590223951e-05, + "loss": 3.6715, + "step": 634368 + }, + { + "epoch": 0.01, + "learning_rate": 3.9605716333532724e-05, + "loss": 3.6891, + "step": 634880 + }, + { + "epoch": 0.01, + "learning_rate": 3.9597330386022204e-05, + "loss": 3.6736, + "step": 635392 + }, + { + "epoch": 0.01, + "learning_rate": 3.958894443851168e-05, + "loss": 3.6778, + "step": 635904 + }, + { + "epoch": 0.01, + "learning_rate": 3.958055849100116e-05, + "loss": 3.6729, + "step": 636416 + }, + { + "epoch": 0.01, + "learning_rate": 3.957218892229437e-05, + "loss": 3.6754, + "step": 636928 + }, + { + "epoch": 0.01, + "learning_rate": 3.956380297478385e-05, + "loss": 3.6829, + "step": 637440 + }, + { + "epoch": 0.01, + "learning_rate": 3.9555417027273326e-05, + "loss": 3.6648, + "step": 637952 + }, + { + "epoch": 0.01, + "learning_rate": 3.9547031079762806e-05, + "loss": 3.6753, + "step": 638464 + }, + { + "epoch": 0.01, + "learning_rate": 3.953866151105602e-05, + "loss": 3.6745, + "step": 638976 + }, + { + "epoch": 0.01, + "learning_rate": 3.95302755635455e-05, + "loss": 3.6767, + "step": 639488 + }, + { + "epoch": 0.01, + "learning_rate": 3.952188961603498e-05, + "loss": 3.6729, + "step": 640000 + }, + { + "epoch": 0.01, + "learning_rate": 3.951350366852446e-05, + "loss": 3.686, + "step": 640512 + }, + { + "epoch": 0.01, + "learning_rate": 3.950513409981768e-05, + "loss": 3.6635, + "step": 641024 + }, + { + "epoch": 0.01, + "learning_rate": 3.949674815230715e-05, + "loss": 3.6711, + "step": 641536 + }, + { + "epoch": 0.01, + "learning_rate": 3.948836220479663e-05, + "loss": 3.669, + "step": 642048 + }, + { + "epoch": 0.01, + "learning_rate": 3.947997625728611e-05, + "loss": 3.6733, + "step": 642560 + }, + { + "epoch": 0.01, + "learning_rate": 3.947160668857933e-05, + "loss": 3.6832, + "step": 643072 + }, + { + "epoch": 0.01, + "learning_rate": 3.94632207410688e-05, + "loss": 3.6701, + "step": 643584 + }, + { + "epoch": 0.01, + "learning_rate": 3.945483479355828e-05, + "loss": 3.6786, + "step": 644096 + }, + { + "epoch": 0.01, + "learning_rate": 3.944644884604776e-05, + "loss": 3.6529, + "step": 644608 + }, + { + "epoch": 0.01, + "learning_rate": 3.943807927734097e-05, + "loss": 3.6766, + "step": 645120 + }, + { + "epoch": 0.01, + "learning_rate": 3.9429693329830456e-05, + "loss": 3.6626, + "step": 645632 + }, + { + "epoch": 0.01, + "learning_rate": 3.9421307382319936e-05, + "loss": 3.6706, + "step": 646144 + }, + { + "epoch": 0.01, + "learning_rate": 3.9412921434809416e-05, + "loss": 3.674, + "step": 646656 + }, + { + "epoch": 0.01, + "learning_rate": 3.9404551866102625e-05, + "loss": 3.6731, + "step": 647168 + }, + { + "epoch": 0.01, + "learning_rate": 3.9396165918592105e-05, + "loss": 3.6695, + "step": 647680 + }, + { + "epoch": 0.01, + "learning_rate": 3.9387779971081585e-05, + "loss": 3.6885, + "step": 648192 + }, + { + "epoch": 0.01, + "learning_rate": 3.9379394023571065e-05, + "loss": 3.6711, + "step": 648704 + }, + { + "epoch": 0.01, + "learning_rate": 3.9371024454864274e-05, + "loss": 3.6811, + "step": 649216 + }, + { + "epoch": 0.01, + "learning_rate": 3.9362638507353754e-05, + "loss": 3.6778, + "step": 649728 + }, + { + "epoch": 0.01, + "learning_rate": 3.9354252559843234e-05, + "loss": 3.663, + "step": 650240 + }, + { + "epoch": 0.01, + "learning_rate": 3.9345866612332714e-05, + "loss": 3.6625, + "step": 650752 + }, + { + "epoch": 0.01, + "learning_rate": 3.933749704362592e-05, + "loss": 3.6774, + "step": 651264 + }, + { + "epoch": 0.01, + "learning_rate": 3.932911109611541e-05, + "loss": 3.6805, + "step": 651776 + }, + { + "epoch": 0.01, + "learning_rate": 3.932072514860489e-05, + "loss": 3.6736, + "step": 652288 + }, + { + "epoch": 0.01, + "learning_rate": 3.931233920109437e-05, + "loss": 3.6515, + "step": 652800 + }, + { + "epoch": 0.01, + "learning_rate": 3.930395325358385e-05, + "loss": 3.6668, + "step": 653312 + }, + { + "epoch": 0.01, + "learning_rate": 3.929558368487706e-05, + "loss": 3.6601, + "step": 653824 + }, + { + "epoch": 0.01, + "learning_rate": 3.928719773736654e-05, + "loss": 3.6706, + "step": 654336 + }, + { + "epoch": 0.01, + "learning_rate": 3.927881178985602e-05, + "loss": 3.6714, + "step": 654848 + }, + { + "epoch": 0.01, + "learning_rate": 3.92704258423455e-05, + "loss": 3.6772, + "step": 655360 + }, + { + "epoch": 0.01, + "learning_rate": 3.926205627363871e-05, + "loss": 3.6719, + "step": 655872 + }, + { + "epoch": 0.02, + "learning_rate": 3.925367032612819e-05, + "loss": 3.6667, + "step": 656384 + }, + { + "epoch": 0.02, + "learning_rate": 3.924528437861767e-05, + "loss": 3.6653, + "step": 656896 + }, + { + "epoch": 0.02, + "learning_rate": 3.923689843110715e-05, + "loss": 3.6643, + "step": 657408 + }, + { + "epoch": 0.02, + "learning_rate": 3.922852886240036e-05, + "loss": 3.6593, + "step": 657920 + }, + { + "epoch": 0.02, + "learning_rate": 3.922014291488984e-05, + "loss": 3.6737, + "step": 658432 + }, + { + "epoch": 0.02, + "learning_rate": 3.921175696737932e-05, + "loss": 3.6629, + "step": 658944 + }, + { + "epoch": 0.02, + "learning_rate": 3.92033710198688e-05, + "loss": 3.6679, + "step": 659456 + }, + { + "epoch": 0.02, + "learning_rate": 3.919500145116201e-05, + "loss": 3.6665, + "step": 659968 + }, + { + "epoch": 0.02, + "learning_rate": 3.918661550365149e-05, + "loss": 3.6867, + "step": 660480 + }, + { + "epoch": 0.02, + "learning_rate": 3.917822955614097e-05, + "loss": 3.6614, + "step": 660992 + }, + { + "epoch": 0.02, + "learning_rate": 3.916984360863045e-05, + "loss": 3.677, + "step": 661504 + }, + { + "epoch": 0.02, + "learning_rate": 3.916147403992366e-05, + "loss": 3.675, + "step": 662016 + }, + { + "epoch": 0.02, + "learning_rate": 3.915308809241314e-05, + "loss": 3.6674, + "step": 662528 + }, + { + "epoch": 0.02, + "learning_rate": 3.914470214490262e-05, + "loss": 3.6746, + "step": 663040 + }, + { + "epoch": 0.02, + "learning_rate": 3.91363161973921e-05, + "loss": 3.6711, + "step": 663552 + }, + { + "epoch": 0.02, + "learning_rate": 3.912793024988158e-05, + "loss": 3.6786, + "step": 664064 + }, + { + "epoch": 0.02, + "learning_rate": 3.91195606811748e-05, + "loss": 3.663, + "step": 664576 + }, + { + "epoch": 0.02, + "learning_rate": 3.911117473366428e-05, + "loss": 3.6609, + "step": 665088 + }, + { + "epoch": 0.02, + "learning_rate": 3.910278878615376e-05, + "loss": 3.6613, + "step": 665600 + }, + { + "epoch": 0.02, + "learning_rate": 3.909440283864324e-05, + "loss": 3.6701, + "step": 666112 + }, + { + "epoch": 0.02, + "learning_rate": 3.9086033269936446e-05, + "loss": 3.6697, + "step": 666624 + }, + { + "epoch": 0.02, + "learning_rate": 3.9077647322425926e-05, + "loss": 3.6689, + "step": 667136 + }, + { + "epoch": 0.02, + "learning_rate": 3.9069261374915406e-05, + "loss": 3.6419, + "step": 667648 + }, + { + "epoch": 0.02, + "learning_rate": 3.9060875427404886e-05, + "loss": 3.6673, + "step": 668160 + }, + { + "epoch": 0.02, + "learning_rate": 3.9052505858698095e-05, + "loss": 3.6724, + "step": 668672 + }, + { + "epoch": 0.02, + "learning_rate": 3.9044119911187575e-05, + "loss": 3.6673, + "step": 669184 + }, + { + "epoch": 0.02, + "learning_rate": 3.9035733963677055e-05, + "loss": 3.6769, + "step": 669696 + }, + { + "epoch": 0.02, + "learning_rate": 3.9027348016166535e-05, + "loss": 3.6728, + "step": 670208 + }, + { + "epoch": 0.02, + "learning_rate": 3.901897844745975e-05, + "loss": 3.662, + "step": 670720 + }, + { + "epoch": 0.02, + "learning_rate": 3.901059249994923e-05, + "loss": 3.676, + "step": 671232 + }, + { + "epoch": 0.02, + "learning_rate": 3.900220655243871e-05, + "loss": 3.668, + "step": 671744 + }, + { + "epoch": 0.02, + "learning_rate": 3.899382060492819e-05, + "loss": 3.6558, + "step": 672256 + }, + { + "epoch": 0.02, + "learning_rate": 3.89854510362214e-05, + "loss": 3.664, + "step": 672768 + }, + { + "epoch": 0.02, + "learning_rate": 3.897706508871088e-05, + "loss": 3.6652, + "step": 673280 + }, + { + "epoch": 0.02, + "learning_rate": 3.896867914120036e-05, + "loss": 3.6637, + "step": 673792 + }, + { + "epoch": 0.02, + "learning_rate": 3.896029319368984e-05, + "loss": 3.6604, + "step": 674304 + }, + { + "epoch": 0.02, + "learning_rate": 3.895192362498305e-05, + "loss": 3.6677, + "step": 674816 + }, + { + "epoch": 0.02, + "learning_rate": 3.894353767747253e-05, + "loss": 3.668, + "step": 675328 + }, + { + "epoch": 0.02, + "learning_rate": 3.893515172996201e-05, + "loss": 3.653, + "step": 675840 + }, + { + "epoch": 0.02, + "learning_rate": 3.892676578245149e-05, + "loss": 3.6736, + "step": 676352 + }, + { + "epoch": 0.02, + "learning_rate": 3.8918396213744704e-05, + "loss": 3.6585, + "step": 676864 + }, + { + "epoch": 0.02, + "learning_rate": 3.8910010266234184e-05, + "loss": 3.6741, + "step": 677376 + }, + { + "epoch": 0.02, + "learning_rate": 3.8901624318723664e-05, + "loss": 3.6816, + "step": 677888 + }, + { + "epoch": 0.02, + "learning_rate": 3.8893238371213144e-05, + "loss": 3.6631, + "step": 678400 + }, + { + "epoch": 0.02, + "learning_rate": 3.888486880250635e-05, + "loss": 3.6653, + "step": 678912 + }, + { + "epoch": 0.02, + "learning_rate": 3.887648285499583e-05, + "loss": 3.666, + "step": 679424 + }, + { + "epoch": 0.02, + "learning_rate": 3.886809690748531e-05, + "loss": 3.664, + "step": 679936 + }, + { + "epoch": 0.02, + "learning_rate": 3.885971095997479e-05, + "loss": 3.664, + "step": 680448 + }, + { + "epoch": 0.02, + "learning_rate": 3.8851341391268e-05, + "loss": 3.6777, + "step": 680960 + }, + { + "epoch": 0.02, + "learning_rate": 3.884295544375748e-05, + "loss": 3.6761, + "step": 681472 + }, + { + "epoch": 0.02, + "learning_rate": 3.883456949624696e-05, + "loss": 3.6681, + "step": 681984 + }, + { + "epoch": 0.02, + "learning_rate": 3.882618354873644e-05, + "loss": 3.6702, + "step": 682496 + }, + { + "epoch": 0.02, + "learning_rate": 3.881781398002966e-05, + "loss": 3.6672, + "step": 683008 + }, + { + "epoch": 0.02, + "learning_rate": 3.880942803251914e-05, + "loss": 3.6673, + "step": 683520 + }, + { + "epoch": 0.02, + "learning_rate": 3.880104208500862e-05, + "loss": 3.6604, + "step": 684032 + }, + { + "epoch": 0.02, + "learning_rate": 3.87926561374981e-05, + "loss": 3.6575, + "step": 684544 + }, + { + "epoch": 0.02, + "learning_rate": 3.878428656879131e-05, + "loss": 3.6685, + "step": 685056 + }, + { + "epoch": 0.02, + "learning_rate": 3.877590062128079e-05, + "loss": 3.6665, + "step": 685568 + }, + { + "epoch": 0.02, + "learning_rate": 3.876751467377027e-05, + "loss": 3.6527, + "step": 686080 + }, + { + "epoch": 0.02, + "learning_rate": 3.875912872625975e-05, + "loss": 3.6655, + "step": 686592 + }, + { + "epoch": 0.03, + "eval_loss": 3.8533360958099365, + "eval_runtime": 312.8368, + "eval_samples_per_second": 1219.777, + "eval_steps_per_second": 38.119, + "step": 686871 + }, + { + "epoch": 1.0, + "learning_rate": 3.8750759157552956e-05, + "loss": 3.6634, + "step": 687104 + }, + { + "epoch": 1.0, + "learning_rate": 3.8742373210042436e-05, + "loss": 3.6718, + "step": 687616 + }, + { + "epoch": 1.0, + "learning_rate": 3.8733987262531916e-05, + "loss": 3.6686, + "step": 688128 + }, + { + "epoch": 1.0, + "learning_rate": 3.8725601315021396e-05, + "loss": 3.6607, + "step": 688640 + }, + { + "epoch": 1.0, + "learning_rate": 3.871723174631461e-05, + "loss": 3.6648, + "step": 689152 + }, + { + "epoch": 1.0, + "learning_rate": 3.870884579880409e-05, + "loss": 3.66, + "step": 689664 + }, + { + "epoch": 1.0, + "learning_rate": 3.870045985129357e-05, + "loss": 3.6583, + "step": 690176 + }, + { + "epoch": 1.0, + "learning_rate": 3.869207390378305e-05, + "loss": 3.656, + "step": 690688 + }, + { + "epoch": 1.0, + "learning_rate": 3.868370433507626e-05, + "loss": 3.656, + "step": 691200 + }, + { + "epoch": 1.0, + "learning_rate": 3.867531838756574e-05, + "loss": 3.6664, + "step": 691712 + }, + { + "epoch": 1.0, + "learning_rate": 3.866693244005522e-05, + "loss": 3.6668, + "step": 692224 + }, + { + "epoch": 1.0, + "learning_rate": 3.86585464925447e-05, + "loss": 3.6527, + "step": 692736 + }, + { + "epoch": 1.0, + "learning_rate": 3.865017692383791e-05, + "loss": 3.6639, + "step": 693248 + }, + { + "epoch": 1.0, + "learning_rate": 3.864179097632739e-05, + "loss": 3.6492, + "step": 693760 + }, + { + "epoch": 1.0, + "learning_rate": 3.863340502881687e-05, + "loss": 3.6647, + "step": 694272 + }, + { + "epoch": 1.0, + "learning_rate": 3.862501908130635e-05, + "loss": 3.6427, + "step": 694784 + }, + { + "epoch": 1.0, + "learning_rate": 3.861663313379583e-05, + "loss": 3.6547, + "step": 695296 + }, + { + "epoch": 1.0, + "learning_rate": 3.8608263565089045e-05, + "loss": 3.6602, + "step": 695808 + }, + { + "epoch": 1.0, + "learning_rate": 3.8599877617578525e-05, + "loss": 3.6533, + "step": 696320 + }, + { + "epoch": 1.0, + "learning_rate": 3.8591491670068e-05, + "loss": 3.6665, + "step": 696832 + }, + { + "epoch": 1.0, + "learning_rate": 3.858310572255748e-05, + "loss": 3.6503, + "step": 697344 + }, + { + "epoch": 1.0, + "learning_rate": 3.8574736153850694e-05, + "loss": 3.6766, + "step": 697856 + }, + { + "epoch": 1.0, + "learning_rate": 3.8566350206340174e-05, + "loss": 3.6569, + "step": 698368 + }, + { + "epoch": 1.0, + "learning_rate": 3.855796425882965e-05, + "loss": 3.6606, + "step": 698880 + }, + { + "epoch": 1.0, + "learning_rate": 3.854957831131913e-05, + "loss": 3.6568, + "step": 699392 + }, + { + "epoch": 1.0, + "learning_rate": 3.854120874261234e-05, + "loss": 3.6637, + "step": 699904 + }, + { + "epoch": 1.0, + "learning_rate": 3.853282279510182e-05, + "loss": 3.6626, + "step": 700416 + }, + { + "epoch": 1.0, + "learning_rate": 3.85244368475913e-05, + "loss": 3.6572, + "step": 700928 + }, + { + "epoch": 1.0, + "learning_rate": 3.851605090008078e-05, + "loss": 3.6577, + "step": 701440 + }, + { + "epoch": 1.0, + "learning_rate": 3.8507681331374e-05, + "loss": 3.6616, + "step": 701952 + }, + { + "epoch": 1.01, + "learning_rate": 3.849929538386347e-05, + "loss": 3.6399, + "step": 702464 + }, + { + "epoch": 1.01, + "learning_rate": 3.849090943635295e-05, + "loss": 3.6627, + "step": 702976 + }, + { + "epoch": 1.01, + "learning_rate": 3.848252348884243e-05, + "loss": 3.6666, + "step": 703488 + }, + { + "epoch": 1.01, + "learning_rate": 3.847415392013565e-05, + "loss": 3.6579, + "step": 704000 + }, + { + "epoch": 1.01, + "learning_rate": 3.846576797262512e-05, + "loss": 3.6504, + "step": 704512 + }, + { + "epoch": 1.01, + "learning_rate": 3.84573820251146e-05, + "loss": 3.6618, + "step": 705024 + }, + { + "epoch": 1.01, + "learning_rate": 3.844899607760408e-05, + "loss": 3.6561, + "step": 705536 + }, + { + "epoch": 1.01, + "learning_rate": 3.84406265088973e-05, + "loss": 3.6569, + "step": 706048 + }, + { + "epoch": 1.01, + "learning_rate": 3.843224056138677e-05, + "loss": 3.6569, + "step": 706560 + }, + { + "epoch": 1.01, + "learning_rate": 3.842385461387626e-05, + "loss": 3.6478, + "step": 707072 + }, + { + "epoch": 1.01, + "learning_rate": 3.841546866636574e-05, + "loss": 3.6524, + "step": 707584 + }, + { + "epoch": 1.01, + "learning_rate": 3.840708271885522e-05, + "loss": 3.6395, + "step": 708096 + }, + { + "epoch": 1.01, + "learning_rate": 3.8398713150148426e-05, + "loss": 3.6629, + "step": 708608 + }, + { + "epoch": 1.01, + "learning_rate": 3.8390327202637906e-05, + "loss": 3.6499, + "step": 709120 + }, + { + "epoch": 1.01, + "learning_rate": 3.8381941255127386e-05, + "loss": 3.6461, + "step": 709632 + }, + { + "epoch": 1.01, + "learning_rate": 3.8373555307616866e-05, + "loss": 3.659, + "step": 710144 + }, + { + "epoch": 1.01, + "learning_rate": 3.8365185738910075e-05, + "loss": 3.6487, + "step": 710656 + }, + { + "epoch": 1.01, + "learning_rate": 3.8356799791399555e-05, + "loss": 3.6621, + "step": 711168 + }, + { + "epoch": 1.01, + "learning_rate": 3.8348413843889035e-05, + "loss": 3.6529, + "step": 711680 + }, + { + "epoch": 1.01, + "learning_rate": 3.8340044275182244e-05, + "loss": 3.6517, + "step": 712192 + }, + { + "epoch": 1.01, + "learning_rate": 3.8331658327671724e-05, + "loss": 3.6498, + "step": 712704 + }, + { + "epoch": 1.01, + "learning_rate": 3.832327238016121e-05, + "loss": 3.6447, + "step": 713216 + }, + { + "epoch": 1.01, + "learning_rate": 3.831488643265069e-05, + "loss": 3.6589, + "step": 713728 + }, + { + "epoch": 1.01, + "learning_rate": 3.83065168639439e-05, + "loss": 3.6372, + "step": 714240 + }, + { + "epoch": 1.01, + "learning_rate": 3.829813091643338e-05, + "loss": 3.6547, + "step": 714752 + }, + { + "epoch": 1.01, + "learning_rate": 3.828974496892286e-05, + "loss": 3.6453, + "step": 715264 + }, + { + "epoch": 1.01, + "learning_rate": 3.828135902141234e-05, + "loss": 3.6521, + "step": 715776 + }, + { + "epoch": 1.01, + "learning_rate": 3.827297307390182e-05, + "loss": 3.6461, + "step": 716288 + }, + { + "epoch": 1.01, + "learning_rate": 3.826460350519503e-05, + "loss": 3.6604, + "step": 716800 + }, + { + "epoch": 1.01, + "learning_rate": 3.825621755768451e-05, + "loss": 3.6464, + "step": 717312 + }, + { + "epoch": 1.01, + "learning_rate": 3.824783161017399e-05, + "loss": 3.6403, + "step": 717824 + }, + { + "epoch": 1.01, + "learning_rate": 3.823944566266347e-05, + "loss": 3.6486, + "step": 718336 + }, + { + "epoch": 1.01, + "learning_rate": 3.823107609395668e-05, + "loss": 3.6408, + "step": 718848 + }, + { + "epoch": 1.01, + "learning_rate": 3.822269014644616e-05, + "loss": 3.6556, + "step": 719360 + }, + { + "epoch": 1.01, + "learning_rate": 3.8214304198935644e-05, + "loss": 3.6515, + "step": 719872 + }, + { + "epoch": 1.01, + "learning_rate": 3.8205918251425124e-05, + "loss": 3.6517, + "step": 720384 + }, + { + "epoch": 1.01, + "learning_rate": 3.819754868271833e-05, + "loss": 3.6296, + "step": 720896 + }, + { + "epoch": 1.01, + "learning_rate": 3.818916273520781e-05, + "loss": 3.6487, + "step": 721408 + }, + { + "epoch": 1.01, + "learning_rate": 3.818077678769729e-05, + "loss": 3.6403, + "step": 721920 + }, + { + "epoch": 1.01, + "learning_rate": 3.817239084018677e-05, + "loss": 3.6437, + "step": 722432 + }, + { + "epoch": 1.01, + "learning_rate": 3.816402127147998e-05, + "loss": 3.6467, + "step": 722944 + }, + { + "epoch": 1.01, + "learning_rate": 3.815563532396946e-05, + "loss": 3.6459, + "step": 723456 + }, + { + "epoch": 1.01, + "learning_rate": 3.814724937645894e-05, + "loss": 3.6431, + "step": 723968 + }, + { + "epoch": 1.01, + "learning_rate": 3.813886342894842e-05, + "loss": 3.6642, + "step": 724480 + }, + { + "epoch": 1.01, + "learning_rate": 3.813049386024163e-05, + "loss": 3.6473, + "step": 724992 + }, + { + "epoch": 1.01, + "learning_rate": 3.812210791273111e-05, + "loss": 3.6571, + "step": 725504 + }, + { + "epoch": 1.01, + "learning_rate": 3.81137219652206e-05, + "loss": 3.6487, + "step": 726016 + }, + { + "epoch": 1.01, + "learning_rate": 3.810533601771008e-05, + "loss": 3.6422, + "step": 726528 + }, + { + "epoch": 1.01, + "learning_rate": 3.809696644900329e-05, + "loss": 3.6391, + "step": 727040 + }, + { + "epoch": 1.01, + "learning_rate": 3.808858050149277e-05, + "loss": 3.6522, + "step": 727552 + }, + { + "epoch": 1.01, + "learning_rate": 3.808019455398225e-05, + "loss": 3.6513, + "step": 728064 + }, + { + "epoch": 1.01, + "learning_rate": 3.8071808606471727e-05, + "loss": 3.6529, + "step": 728576 + }, + { + "epoch": 1.01, + "learning_rate": 3.8063422658961207e-05, + "loss": 3.626, + "step": 729088 + }, + { + "epoch": 1.01, + "learning_rate": 3.8055053090254416e-05, + "loss": 3.638, + "step": 729600 + }, + { + "epoch": 1.01, + "learning_rate": 3.8046667142743896e-05, + "loss": 3.6348, + "step": 730112 + }, + { + "epoch": 1.01, + "learning_rate": 3.8038281195233376e-05, + "loss": 3.6461, + "step": 730624 + }, + { + "epoch": 1.01, + "learning_rate": 3.8029895247722855e-05, + "loss": 3.6442, + "step": 731136 + }, + { + "epoch": 1.01, + "learning_rate": 3.8021525679016065e-05, + "loss": 3.6553, + "step": 731648 + }, + { + "epoch": 1.01, + "learning_rate": 3.801313973150555e-05, + "loss": 3.6476, + "step": 732160 + }, + { + "epoch": 1.02, + "learning_rate": 3.800475378399503e-05, + "loss": 3.6445, + "step": 732672 + }, + { + "epoch": 1.02, + "learning_rate": 3.799636783648451e-05, + "loss": 3.6399, + "step": 733184 + }, + { + "epoch": 1.02, + "learning_rate": 3.798799826777772e-05, + "loss": 3.6401, + "step": 733696 + }, + { + "epoch": 1.02, + "learning_rate": 3.79796123202672e-05, + "loss": 3.6335, + "step": 734208 + }, + { + "epoch": 1.02, + "learning_rate": 3.797122637275668e-05, + "loss": 3.6469, + "step": 734720 + }, + { + "epoch": 1.02, + "learning_rate": 3.796284042524616e-05, + "loss": 3.6405, + "step": 735232 + }, + { + "epoch": 1.02, + "learning_rate": 3.795447085653937e-05, + "loss": 3.6421, + "step": 735744 + }, + { + "epoch": 1.02, + "learning_rate": 3.794608490902885e-05, + "loss": 3.6443, + "step": 736256 + }, + { + "epoch": 1.02, + "learning_rate": 3.793769896151833e-05, + "loss": 3.6589, + "step": 736768 + }, + { + "epoch": 1.02, + "learning_rate": 3.792932939281154e-05, + "loss": 3.637, + "step": 737280 + }, + { + "epoch": 1.02, + "learning_rate": 3.792094344530102e-05, + "loss": 3.6534, + "step": 737792 + }, + { + "epoch": 1.02, + "learning_rate": 3.7912557497790505e-05, + "loss": 3.6506, + "step": 738304 + }, + { + "epoch": 1.02, + "learning_rate": 3.7904171550279985e-05, + "loss": 3.6469, + "step": 738816 + }, + { + "epoch": 1.02, + "learning_rate": 3.7895801981573194e-05, + "loss": 3.6431, + "step": 739328 + }, + { + "epoch": 1.02, + "learning_rate": 3.7887416034062674e-05, + "loss": 3.6491, + "step": 739840 + }, + { + "epoch": 1.02, + "learning_rate": 3.7879030086552154e-05, + "loss": 3.651, + "step": 740352 + }, + { + "epoch": 1.02, + "learning_rate": 3.7870644139041634e-05, + "loss": 3.639, + "step": 740864 + }, + { + "epoch": 1.02, + "learning_rate": 3.786227457033484e-05, + "loss": 3.639, + "step": 741376 + }, + { + "epoch": 1.02, + "learning_rate": 3.785388862282432e-05, + "loss": 3.6324, + "step": 741888 + }, + { + "epoch": 1.02, + "learning_rate": 3.78455026753138e-05, + "loss": 3.642, + "step": 742400 + }, + { + "epoch": 1.02, + "learning_rate": 3.783711672780328e-05, + "loss": 3.6479, + "step": 742912 + }, + { + "epoch": 1.02, + "learning_rate": 3.782874715909649e-05, + "loss": 3.6448, + "step": 743424 + }, + { + "epoch": 1.02, + "learning_rate": 3.782036121158597e-05, + "loss": 3.6205, + "step": 743936 + }, + { + "epoch": 1.02, + "learning_rate": 3.781197526407546e-05, + "loss": 3.6372, + "step": 744448 + }, + { + "epoch": 1.02, + "learning_rate": 3.780358931656494e-05, + "loss": 3.6458, + "step": 744960 + }, + { + "epoch": 1.02, + "learning_rate": 3.779521974785815e-05, + "loss": 3.6461, + "step": 745472 + }, + { + "epoch": 1.02, + "learning_rate": 3.778683380034763e-05, + "loss": 3.6542, + "step": 745984 + }, + { + "epoch": 1.02, + "learning_rate": 3.777844785283711e-05, + "loss": 3.6474, + "step": 746496 + }, + { + "epoch": 1.02, + "learning_rate": 3.777006190532659e-05, + "loss": 3.6378, + "step": 747008 + }, + { + "epoch": 1.02, + "learning_rate": 3.776167595781607e-05, + "loss": 3.6497, + "step": 747520 + }, + { + "epoch": 1.02, + "learning_rate": 3.775330638910928e-05, + "loss": 3.6438, + "step": 748032 + }, + { + "epoch": 1.02, + "learning_rate": 3.7744920441598757e-05, + "loss": 3.6365, + "step": 748544 + }, + { + "epoch": 1.02, + "learning_rate": 3.7736534494088237e-05, + "loss": 3.6333, + "step": 749056 + }, + { + "epoch": 1.02, + "learning_rate": 3.7728148546577716e-05, + "loss": 3.6444, + "step": 749568 + }, + { + "epoch": 1.02, + "learning_rate": 3.7719778977870926e-05, + "loss": 3.6333, + "step": 750080 + }, + { + "epoch": 1.02, + "learning_rate": 3.771139303036041e-05, + "loss": 3.6408, + "step": 750592 + }, + { + "epoch": 1.02, + "learning_rate": 3.770300708284989e-05, + "loss": 3.6427, + "step": 751104 + }, + { + "epoch": 1.02, + "learning_rate": 3.76946375141431e-05, + "loss": 3.646, + "step": 751616 + }, + { + "epoch": 1.02, + "learning_rate": 3.768625156663258e-05, + "loss": 3.6296, + "step": 752128 + }, + { + "epoch": 1.02, + "learning_rate": 3.767786561912206e-05, + "loss": 3.6469, + "step": 752640 + }, + { + "epoch": 1.02, + "learning_rate": 3.766947967161154e-05, + "loss": 3.6344, + "step": 753152 + }, + { + "epoch": 1.02, + "learning_rate": 3.766111010290475e-05, + "loss": 3.6513, + "step": 753664 + }, + { + "epoch": 1.02, + "learning_rate": 3.765272415539423e-05, + "loss": 3.6562, + "step": 754176 + }, + { + "epoch": 1.02, + "learning_rate": 3.764433820788371e-05, + "loss": 3.6371, + "step": 754688 + }, + { + "epoch": 1.02, + "learning_rate": 3.763595226037319e-05, + "loss": 3.6375, + "step": 755200 + }, + { + "epoch": 1.02, + "learning_rate": 3.76275826916664e-05, + "loss": 3.6447, + "step": 755712 + }, + { + "epoch": 1.02, + "learning_rate": 3.761919674415588e-05, + "loss": 3.6398, + "step": 756224 + }, + { + "epoch": 1.02, + "learning_rate": 3.7610810796645366e-05, + "loss": 3.6416, + "step": 756736 + }, + { + "epoch": 1.02, + "learning_rate": 3.7602424849134846e-05, + "loss": 3.6534, + "step": 757248 + }, + { + "epoch": 1.02, + "learning_rate": 3.7594038901624326e-05, + "loss": 3.6479, + "step": 757760 + }, + { + "epoch": 1.02, + "learning_rate": 3.7585669332917535e-05, + "loss": 3.6466, + "step": 758272 + }, + { + "epoch": 1.02, + "learning_rate": 3.7577283385407015e-05, + "loss": 3.6458, + "step": 758784 + }, + { + "epoch": 1.02, + "learning_rate": 3.7568897437896495e-05, + "loss": 3.645, + "step": 759296 + }, + { + "epoch": 1.02, + "learning_rate": 3.756051149038597e-05, + "loss": 3.6388, + "step": 759808 + }, + { + "epoch": 1.02, + "learning_rate": 3.7552141921679184e-05, + "loss": 3.6359, + "step": 760320 + }, + { + "epoch": 1.02, + "learning_rate": 3.7543755974168664e-05, + "loss": 3.6352, + "step": 760832 + }, + { + "epoch": 1.02, + "learning_rate": 3.7535370026658144e-05, + "loss": 3.6469, + "step": 761344 + }, + { + "epoch": 1.02, + "learning_rate": 3.752698407914762e-05, + "loss": 3.6425, + "step": 761856 + }, + { + "epoch": 1.02, + "learning_rate": 3.751861451044083e-05, + "loss": 3.6247, + "step": 762368 + }, + { + "epoch": 1.02, + "learning_rate": 3.751022856293032e-05, + "loss": 3.6443, + "step": 762880 + }, + { + "epoch": 1.03, + "eval_loss": 3.8508858680725098, + "eval_runtime": 312.6022, + "eval_samples_per_second": 1220.692, + "eval_steps_per_second": 38.148, + "step": 763190 + }, + { + "epoch": 0.0, + "learning_rate": 3.750184261541979e-05, + "loss": 3.6512, + "step": 763392 + }, + { + "epoch": 0.0, + "learning_rate": 3.749345666790927e-05, + "loss": 3.6384, + "step": 763904 + }, + { + "epoch": 0.0, + "learning_rate": 3.748507072039875e-05, + "loss": 3.6417, + "step": 764416 + }, + { + "epoch": 0.0, + "learning_rate": 3.747668477288823e-05, + "loss": 3.6484, + "step": 764928 + }, + { + "epoch": 0.0, + "learning_rate": 3.746831520418144e-05, + "loss": 3.6576, + "step": 765440 + }, + { + "epoch": 0.0, + "learning_rate": 3.745992925667092e-05, + "loss": 3.6452, + "step": 765952 + }, + { + "epoch": 0.0, + "learning_rate": 3.74515433091604e-05, + "loss": 3.6493, + "step": 766464 + }, + { + "epoch": 0.0, + "learning_rate": 3.744315736164988e-05, + "loss": 3.6392, + "step": 766976 + }, + { + "epoch": 0.0, + "learning_rate": 3.743478779294309e-05, + "loss": 3.6353, + "step": 767488 + }, + { + "epoch": 0.0, + "learning_rate": 3.742640184543257e-05, + "loss": 3.6431, + "step": 768000 + }, + { + "epoch": 0.0, + "learning_rate": 3.741801589792206e-05, + "loss": 3.6494, + "step": 768512 + }, + { + "epoch": 0.0, + "learning_rate": 3.740962995041154e-05, + "loss": 3.6416, + "step": 769024 + }, + { + "epoch": 0.0, + "learning_rate": 3.7401260381704747e-05, + "loss": 3.6443, + "step": 769536 + }, + { + "epoch": 0.0, + "learning_rate": 3.7392874434194226e-05, + "loss": 3.6283, + "step": 770048 + }, + { + "epoch": 0.0, + "learning_rate": 3.7384488486683706e-05, + "loss": 3.6397, + "step": 770560 + }, + { + "epoch": 0.0, + "learning_rate": 3.7376102539173186e-05, + "loss": 3.6207, + "step": 771072 + }, + { + "epoch": 0.0, + "learning_rate": 3.7367732970466395e-05, + "loss": 3.6399, + "step": 771584 + }, + { + "epoch": 0.0, + "learning_rate": 3.7359347022955875e-05, + "loss": 3.6417, + "step": 772096 + }, + { + "epoch": 0.0, + "learning_rate": 3.7350961075445355e-05, + "loss": 3.6301, + "step": 772608 + }, + { + "epoch": 0.0, + "learning_rate": 3.7342575127934835e-05, + "loss": 3.6518, + "step": 773120 + }, + { + "epoch": 0.0, + "learning_rate": 3.7334205559228044e-05, + "loss": 3.6511, + "step": 773632 + }, + { + "epoch": 0.0, + "learning_rate": 3.7325819611717524e-05, + "loss": 3.6447, + "step": 774144 + }, + { + "epoch": 0.0, + "learning_rate": 3.7317433664207004e-05, + "loss": 3.6408, + "step": 774656 + }, + { + "epoch": 0.0, + "learning_rate": 3.730904771669649e-05, + "loss": 3.6389, + "step": 775168 + }, + { + "epoch": 0.0, + "learning_rate": 3.73006781479897e-05, + "loss": 3.6464, + "step": 775680 + }, + { + "epoch": 0.0, + "learning_rate": 3.729229220047918e-05, + "loss": 3.6503, + "step": 776192 + }, + { + "epoch": 0.0, + "learning_rate": 3.728390625296866e-05, + "loss": 3.6282, + "step": 776704 + }, + { + "epoch": 0.0, + "learning_rate": 3.727552030545814e-05, + "loss": 3.6442, + "step": 777216 + }, + { + "epoch": 0.0, + "learning_rate": 3.726715073675135e-05, + "loss": 3.6313, + "step": 777728 + }, + { + "epoch": 0.0, + "learning_rate": 3.725876478924083e-05, + "loss": 3.6361, + "step": 778240 + }, + { + "epoch": 0.01, + "learning_rate": 3.725037884173031e-05, + "loss": 3.6388, + "step": 778752 + }, + { + "epoch": 0.01, + "learning_rate": 3.724199289421979e-05, + "loss": 3.6438, + "step": 779264 + }, + { + "epoch": 0.01, + "learning_rate": 3.7233623325513e-05, + "loss": 3.6406, + "step": 779776 + }, + { + "epoch": 0.01, + "learning_rate": 3.722523737800248e-05, + "loss": 3.6506, + "step": 780288 + }, + { + "epoch": 0.01, + "learning_rate": 3.721685143049196e-05, + "loss": 3.6375, + "step": 780800 + }, + { + "epoch": 0.01, + "learning_rate": 3.7208465482981445e-05, + "loss": 3.6389, + "step": 781312 + }, + { + "epoch": 0.01, + "learning_rate": 3.7200095914274654e-05, + "loss": 3.6437, + "step": 781824 + }, + { + "epoch": 0.01, + "learning_rate": 3.7191709966764134e-05, + "loss": 3.6272, + "step": 782336 + }, + { + "epoch": 0.01, + "learning_rate": 3.7183324019253614e-05, + "loss": 3.6314, + "step": 782848 + }, + { + "epoch": 0.01, + "learning_rate": 3.7174938071743094e-05, + "loss": 3.6292, + "step": 783360 + }, + { + "epoch": 0.01, + "learning_rate": 3.7166552124232574e-05, + "loss": 3.6235, + "step": 783872 + }, + { + "epoch": 0.01, + "learning_rate": 3.715818255552578e-05, + "loss": 3.6354, + "step": 784384 + }, + { + "epoch": 0.01, + "learning_rate": 3.714979660801526e-05, + "loss": 3.6472, + "step": 784896 + }, + { + "epoch": 0.01, + "learning_rate": 3.714141066050474e-05, + "loss": 3.6333, + "step": 785408 + }, + { + "epoch": 0.01, + "learning_rate": 3.713302471299422e-05, + "loss": 3.6353, + "step": 785920 + }, + { + "epoch": 0.01, + "learning_rate": 3.712465514428743e-05, + "loss": 3.6321, + "step": 786432 + }, + { + "epoch": 0.01, + "learning_rate": 3.711626919677691e-05, + "loss": 3.6369, + "step": 786944 + }, + { + "epoch": 0.01, + "learning_rate": 3.71078832492664e-05, + "loss": 3.6243, + "step": 787456 + }, + { + "epoch": 0.01, + "learning_rate": 3.709949730175588e-05, + "loss": 3.6134, + "step": 787968 + }, + { + "epoch": 0.01, + "learning_rate": 3.709112773304909e-05, + "loss": 3.6418, + "step": 788480 + }, + { + "epoch": 0.01, + "learning_rate": 3.708274178553857e-05, + "loss": 3.6374, + "step": 788992 + }, + { + "epoch": 0.01, + "learning_rate": 3.707435583802805e-05, + "loss": 3.6454, + "step": 789504 + }, + { + "epoch": 0.01, + "learning_rate": 3.706596989051753e-05, + "loss": 3.6325, + "step": 790016 + }, + { + "epoch": 0.01, + "learning_rate": 3.7057600321810736e-05, + "loss": 3.6311, + "step": 790528 + }, + { + "epoch": 0.01, + "learning_rate": 3.7049214374300216e-05, + "loss": 3.6271, + "step": 791040 + }, + { + "epoch": 0.01, + "learning_rate": 3.7040828426789696e-05, + "loss": 3.6287, + "step": 791552 + }, + { + "epoch": 0.01, + "learning_rate": 3.7032442479279176e-05, + "loss": 3.6468, + "step": 792064 + }, + { + "epoch": 0.01, + "learning_rate": 3.7024072910572385e-05, + "loss": 3.616, + "step": 792576 + }, + { + "epoch": 0.01, + "learning_rate": 3.7015686963061865e-05, + "loss": 3.6576, + "step": 793088 + }, + { + "epoch": 0.01, + "learning_rate": 3.700730101555135e-05, + "loss": 3.6343, + "step": 793600 + }, + { + "epoch": 0.01, + "learning_rate": 3.699891506804083e-05, + "loss": 3.6134, + "step": 794112 + }, + { + "epoch": 0.01, + "learning_rate": 3.699054549933404e-05, + "loss": 3.6401, + "step": 794624 + }, + { + "epoch": 0.01, + "learning_rate": 3.698215955182352e-05, + "loss": 3.6264, + "step": 795136 + }, + { + "epoch": 0.01, + "learning_rate": 3.6973773604313e-05, + "loss": 3.6163, + "step": 795648 + }, + { + "epoch": 0.01, + "learning_rate": 3.696538765680248e-05, + "loss": 3.6388, + "step": 796160 + }, + { + "epoch": 0.01, + "learning_rate": 3.695701808809569e-05, + "loss": 3.638, + "step": 796672 + }, + { + "epoch": 0.01, + "learning_rate": 3.694863214058517e-05, + "loss": 3.6193, + "step": 797184 + }, + { + "epoch": 0.01, + "learning_rate": 3.694024619307465e-05, + "loss": 3.6339, + "step": 797696 + }, + { + "epoch": 0.01, + "learning_rate": 3.693186024556413e-05, + "loss": 3.6101, + "step": 798208 + }, + { + "epoch": 0.01, + "learning_rate": 3.692349067685734e-05, + "loss": 3.6218, + "step": 798720 + }, + { + "epoch": 0.01, + "learning_rate": 3.691510472934682e-05, + "loss": 3.6325, + "step": 799232 + }, + { + "epoch": 0.01, + "learning_rate": 3.6906718781836306e-05, + "loss": 3.6289, + "step": 799744 + }, + { + "epoch": 0.01, + "learning_rate": 3.6898332834325786e-05, + "loss": 3.6325, + "step": 800256 + }, + { + "epoch": 0.01, + "learning_rate": 3.6889963265618995e-05, + "loss": 3.6275, + "step": 800768 + }, + { + "epoch": 0.01, + "learning_rate": 3.6881577318108475e-05, + "loss": 3.6424, + "step": 801280 + }, + { + "epoch": 0.01, + "learning_rate": 3.6873191370597955e-05, + "loss": 3.6313, + "step": 801792 + }, + { + "epoch": 0.01, + "learning_rate": 3.6864805423087435e-05, + "loss": 3.639, + "step": 802304 + }, + { + "epoch": 0.01, + "learning_rate": 3.6856435854380644e-05, + "loss": 3.6268, + "step": 802816 + }, + { + "epoch": 0.01, + "learning_rate": 3.6848049906870124e-05, + "loss": 3.622, + "step": 803328 + }, + { + "epoch": 0.01, + "learning_rate": 3.6839663959359604e-05, + "loss": 3.6319, + "step": 803840 + }, + { + "epoch": 0.01, + "learning_rate": 3.6831278011849084e-05, + "loss": 3.6294, + "step": 804352 + }, + { + "epoch": 0.01, + "learning_rate": 3.682290844314229e-05, + "loss": 3.6315, + "step": 804864 + }, + { + "epoch": 0.01, + "learning_rate": 3.681452249563177e-05, + "loss": 3.635, + "step": 805376 + }, + { + "epoch": 0.01, + "learning_rate": 3.680613654812126e-05, + "loss": 3.6217, + "step": 805888 + }, + { + "epoch": 0.01, + "learning_rate": 3.679775060061074e-05, + "loss": 3.6146, + "step": 806400 + }, + { + "epoch": 0.01, + "learning_rate": 3.678938103190395e-05, + "loss": 3.6279, + "step": 806912 + }, + { + "epoch": 0.01, + "learning_rate": 3.678099508439343e-05, + "loss": 3.6333, + "step": 807424 + }, + { + "epoch": 0.01, + "learning_rate": 3.677260913688291e-05, + "loss": 3.6188, + "step": 807936 + }, + { + "epoch": 0.01, + "learning_rate": 3.676422318937239e-05, + "loss": 3.6309, + "step": 808448 + }, + { + "epoch": 0.01, + "learning_rate": 3.67558536206656e-05, + "loss": 3.6256, + "step": 808960 + }, + { + "epoch": 0.02, + "learning_rate": 3.674746767315508e-05, + "loss": 3.6208, + "step": 809472 + }, + { + "epoch": 0.02, + "learning_rate": 3.673908172564456e-05, + "loss": 3.6181, + "step": 809984 + }, + { + "epoch": 0.02, + "learning_rate": 3.673069577813404e-05, + "loss": 3.6236, + "step": 810496 + }, + { + "epoch": 0.02, + "learning_rate": 3.6722326209427246e-05, + "loss": 3.6391, + "step": 811008 + }, + { + "epoch": 0.02, + "learning_rate": 3.6713940261916726e-05, + "loss": 3.6325, + "step": 811520 + }, + { + "epoch": 0.02, + "learning_rate": 3.670555431440621e-05, + "loss": 3.6312, + "step": 812032 + }, + { + "epoch": 0.02, + "learning_rate": 3.669716836689569e-05, + "loss": 3.6211, + "step": 812544 + }, + { + "epoch": 0.02, + "learning_rate": 3.66887987981889e-05, + "loss": 3.6204, + "step": 813056 + }, + { + "epoch": 0.02, + "learning_rate": 3.668041285067838e-05, + "loss": 3.6242, + "step": 813568 + }, + { + "epoch": 0.02, + "learning_rate": 3.667202690316786e-05, + "loss": 3.6338, + "step": 814080 + }, + { + "epoch": 0.02, + "learning_rate": 3.666364095565734e-05, + "loss": 3.6329, + "step": 814592 + }, + { + "epoch": 0.02, + "learning_rate": 3.665527138695055e-05, + "loss": 3.6324, + "step": 815104 + }, + { + "epoch": 0.02, + "learning_rate": 3.664688543944003e-05, + "loss": 3.6255, + "step": 815616 + }, + { + "epoch": 0.02, + "learning_rate": 3.663849949192951e-05, + "loss": 3.6226, + "step": 816128 + }, + { + "epoch": 0.02, + "learning_rate": 3.663011354441899e-05, + "loss": 3.6309, + "step": 816640 + }, + { + "epoch": 0.02, + "learning_rate": 3.66217439757122e-05, + "loss": 3.6238, + "step": 817152 + }, + { + "epoch": 0.02, + "learning_rate": 3.661335802820168e-05, + "loss": 3.6163, + "step": 817664 + }, + { + "epoch": 0.02, + "learning_rate": 3.660497208069116e-05, + "loss": 3.6297, + "step": 818176 + }, + { + "epoch": 0.02, + "learning_rate": 3.659658613318065e-05, + "loss": 3.6243, + "step": 818688 + }, + { + "epoch": 0.02, + "learning_rate": 3.6588216564473856e-05, + "loss": 3.6241, + "step": 819200 + }, + { + "epoch": 0.02, + "learning_rate": 3.6579830616963336e-05, + "loss": 3.6161, + "step": 819712 + }, + { + "epoch": 0.02, + "learning_rate": 3.6571444669452816e-05, + "loss": 3.6166, + "step": 820224 + }, + { + "epoch": 0.02, + "learning_rate": 3.656305872194229e-05, + "loss": 3.6286, + "step": 820736 + }, + { + "epoch": 0.02, + "learning_rate": 3.6554689153235505e-05, + "loss": 3.6266, + "step": 821248 + }, + { + "epoch": 0.02, + "learning_rate": 3.6546303205724985e-05, + "loss": 3.6258, + "step": 821760 + }, + { + "epoch": 0.02, + "learning_rate": 3.6537917258214465e-05, + "loss": 3.6306, + "step": 822272 + }, + { + "epoch": 0.02, + "learning_rate": 3.652953131070394e-05, + "loss": 3.6378, + "step": 822784 + }, + { + "epoch": 0.02, + "learning_rate": 3.6521161741997154e-05, + "loss": 3.6279, + "step": 823296 + }, + { + "epoch": 0.02, + "learning_rate": 3.6512775794486634e-05, + "loss": 3.6259, + "step": 823808 + }, + { + "epoch": 0.02, + "learning_rate": 3.6504389846976114e-05, + "loss": 3.6136, + "step": 824320 + }, + { + "epoch": 0.02, + "learning_rate": 3.6496003899465594e-05, + "loss": 3.6282, + "step": 824832 + }, + { + "epoch": 0.02, + "learning_rate": 3.648763433075881e-05, + "loss": 3.6228, + "step": 825344 + }, + { + "epoch": 0.02, + "learning_rate": 3.647924838324829e-05, + "loss": 3.6161, + "step": 825856 + }, + { + "epoch": 0.02, + "learning_rate": 3.647086243573776e-05, + "loss": 3.62, + "step": 826368 + }, + { + "epoch": 0.02, + "learning_rate": 3.646247648822724e-05, + "loss": 3.6273, + "step": 826880 + }, + { + "epoch": 0.02, + "learning_rate": 3.645410691952046e-05, + "loss": 3.6271, + "step": 827392 + }, + { + "epoch": 0.02, + "learning_rate": 3.644572097200994e-05, + "loss": 3.6205, + "step": 827904 + }, + { + "epoch": 0.02, + "learning_rate": 3.643733502449941e-05, + "loss": 3.6222, + "step": 828416 + }, + { + "epoch": 0.02, + "learning_rate": 3.642894907698889e-05, + "loss": 3.6202, + "step": 828928 + }, + { + "epoch": 0.02, + "learning_rate": 3.642057950828211e-05, + "loss": 3.6291, + "step": 829440 + }, + { + "epoch": 0.02, + "learning_rate": 3.641219356077159e-05, + "loss": 3.6269, + "step": 829952 + }, + { + "epoch": 0.02, + "learning_rate": 3.640380761326107e-05, + "loss": 3.6382, + "step": 830464 + }, + { + "epoch": 0.02, + "learning_rate": 3.639542166575055e-05, + "loss": 3.6177, + "step": 830976 + }, + { + "epoch": 0.02, + "learning_rate": 3.638705209704376e-05, + "loss": 3.6217, + "step": 831488 + }, + { + "epoch": 0.02, + "learning_rate": 3.6378666149533236e-05, + "loss": 3.631, + "step": 832000 + }, + { + "epoch": 0.02, + "learning_rate": 3.6370280202022716e-05, + "loss": 3.6201, + "step": 832512 + }, + { + "epoch": 0.02, + "learning_rate": 3.6361894254512196e-05, + "loss": 3.6288, + "step": 833024 + }, + { + "epoch": 0.02, + "learning_rate": 3.635352468580541e-05, + "loss": 3.6263, + "step": 833536 + }, + { + "epoch": 0.02, + "learning_rate": 3.6345138738294885e-05, + "loss": 3.6294, + "step": 834048 + }, + { + "epoch": 0.02, + "learning_rate": 3.6336752790784365e-05, + "loss": 3.6376, + "step": 834560 + }, + { + "epoch": 0.02, + "learning_rate": 3.6328366843273845e-05, + "loss": 3.6247, + "step": 835072 + }, + { + "epoch": 0.02, + "learning_rate": 3.631999727456706e-05, + "loss": 3.625, + "step": 835584 + }, + { + "epoch": 0.02, + "learning_rate": 3.631161132705654e-05, + "loss": 3.6278, + "step": 836096 + }, + { + "epoch": 0.02, + "learning_rate": 3.630322537954602e-05, + "loss": 3.6187, + "step": 836608 + }, + { + "epoch": 0.02, + "learning_rate": 3.62948394320355e-05, + "loss": 3.619, + "step": 837120 + }, + { + "epoch": 0.02, + "learning_rate": 3.628646986332871e-05, + "loss": 3.6223, + "step": 837632 + }, + { + "epoch": 0.02, + "learning_rate": 3.627808391581819e-05, + "loss": 3.6202, + "step": 838144 + }, + { + "epoch": 0.02, + "learning_rate": 3.626969796830767e-05, + "loss": 3.62, + "step": 838656 + }, + { + "epoch": 0.02, + "learning_rate": 3.626131202079715e-05, + "loss": 3.6177, + "step": 839168 + }, + { + "epoch": 0.03, + "eval_loss": 3.8456246852874756, + "eval_runtime": 314.534, + "eval_samples_per_second": 1213.195, + "eval_steps_per_second": 37.913, + "step": 839510 + }, + { + "epoch": 1.0, + "learning_rate": 3.625294245209036e-05, + "loss": 3.6226, + "step": 839680 + }, + { + "epoch": 1.0, + "learning_rate": 3.624455650457984e-05, + "loss": 3.618, + "step": 840192 + }, + { + "epoch": 1.0, + "learning_rate": 3.623617055706932e-05, + "loss": 3.6214, + "step": 840704 + }, + { + "epoch": 1.0, + "learning_rate": 3.62277846095588e-05, + "loss": 3.6243, + "step": 841216 + }, + { + "epoch": 1.0, + "learning_rate": 3.6219415040852015e-05, + "loss": 3.631, + "step": 841728 + }, + { + "epoch": 1.0, + "learning_rate": 3.6211029093341495e-05, + "loss": 3.6241, + "step": 842240 + }, + { + "epoch": 1.0, + "learning_rate": 3.6202643145830975e-05, + "loss": 3.6254, + "step": 842752 + }, + { + "epoch": 1.0, + "learning_rate": 3.6194257198320455e-05, + "loss": 3.6158, + "step": 843264 + }, + { + "epoch": 1.0, + "learning_rate": 3.6185887629613664e-05, + "loss": 3.6099, + "step": 843776 + }, + { + "epoch": 1.0, + "learning_rate": 3.6177501682103144e-05, + "loss": 3.6162, + "step": 844288 + }, + { + "epoch": 1.0, + "learning_rate": 3.6169115734592624e-05, + "loss": 3.6317, + "step": 844800 + }, + { + "epoch": 1.0, + "learning_rate": 3.6160729787082104e-05, + "loss": 3.6131, + "step": 845312 + }, + { + "epoch": 1.0, + "learning_rate": 3.615236021837531e-05, + "loss": 3.6231, + "step": 845824 + }, + { + "epoch": 1.0, + "learning_rate": 3.614397427086479e-05, + "loss": 3.6037, + "step": 846336 + }, + { + "epoch": 1.0, + "learning_rate": 3.613558832335427e-05, + "loss": 3.6116, + "step": 846848 + }, + { + "epoch": 1.0, + "learning_rate": 3.612720237584375e-05, + "loss": 3.6015, + "step": 847360 + }, + { + "epoch": 1.0, + "learning_rate": 3.611883280713697e-05, + "loss": 3.6169, + "step": 847872 + }, + { + "epoch": 1.0, + "learning_rate": 3.611044685962645e-05, + "loss": 3.6161, + "step": 848384 + }, + { + "epoch": 1.0, + "learning_rate": 3.610206091211593e-05, + "loss": 3.6106, + "step": 848896 + }, + { + "epoch": 1.0, + "learning_rate": 3.609367496460541e-05, + "loss": 3.6179, + "step": 849408 + }, + { + "epoch": 1.0, + "learning_rate": 3.608530539589862e-05, + "loss": 3.6284, + "step": 849920 + }, + { + "epoch": 1.0, + "learning_rate": 3.60769194483881e-05, + "loss": 3.6217, + "step": 850432 + }, + { + "epoch": 1.0, + "learning_rate": 3.606853350087758e-05, + "loss": 3.6151, + "step": 850944 + }, + { + "epoch": 1.0, + "learning_rate": 3.606014755336706e-05, + "loss": 3.6139, + "step": 851456 + }, + { + "epoch": 1.0, + "learning_rate": 3.6051777984660266e-05, + "loss": 3.6282, + "step": 851968 + }, + { + "epoch": 1.0, + "learning_rate": 3.6043392037149746e-05, + "loss": 3.6211, + "step": 852480 + }, + { + "epoch": 1.0, + "learning_rate": 3.6035006089639226e-05, + "loss": 3.6106, + "step": 852992 + }, + { + "epoch": 1.0, + "learning_rate": 3.6026636520932435e-05, + "loss": 3.6182, + "step": 853504 + }, + { + "epoch": 1.0, + "learning_rate": 3.601825057342192e-05, + "loss": 3.6093, + "step": 854016 + }, + { + "epoch": 1.0, + "learning_rate": 3.60098646259114e-05, + "loss": 3.608, + "step": 854528 + }, + { + "epoch": 1.01, + "learning_rate": 3.600147867840088e-05, + "loss": 3.6192, + "step": 855040 + }, + { + "epoch": 1.01, + "learning_rate": 3.599310910969409e-05, + "loss": 3.6176, + "step": 855552 + }, + { + "epoch": 1.01, + "learning_rate": 3.598472316218357e-05, + "loss": 3.62, + "step": 856064 + }, + { + "epoch": 1.01, + "learning_rate": 3.597633721467305e-05, + "loss": 3.6287, + "step": 856576 + }, + { + "epoch": 1.01, + "learning_rate": 3.596795126716253e-05, + "loss": 3.6102, + "step": 857088 + }, + { + "epoch": 1.01, + "learning_rate": 3.595958169845574e-05, + "loss": 3.6199, + "step": 857600 + }, + { + "epoch": 1.01, + "learning_rate": 3.595119575094522e-05, + "loss": 3.6206, + "step": 858112 + }, + { + "epoch": 1.01, + "learning_rate": 3.59428098034347e-05, + "loss": 3.6051, + "step": 858624 + }, + { + "epoch": 1.01, + "learning_rate": 3.593442385592418e-05, + "loss": 3.6123, + "step": 859136 + }, + { + "epoch": 1.01, + "learning_rate": 3.592605428721739e-05, + "loss": 3.6026, + "step": 859648 + }, + { + "epoch": 1.01, + "learning_rate": 3.5917668339706876e-05, + "loss": 3.6013, + "step": 860160 + }, + { + "epoch": 1.01, + "learning_rate": 3.5909282392196356e-05, + "loss": 3.6112, + "step": 860672 + }, + { + "epoch": 1.01, + "learning_rate": 3.5900896444685836e-05, + "loss": 3.6243, + "step": 861184 + }, + { + "epoch": 1.01, + "learning_rate": 3.5892526875979045e-05, + "loss": 3.6123, + "step": 861696 + }, + { + "epoch": 1.01, + "learning_rate": 3.5884140928468525e-05, + "loss": 3.6069, + "step": 862208 + }, + { + "epoch": 1.01, + "learning_rate": 3.5875754980958005e-05, + "loss": 3.6145, + "step": 862720 + }, + { + "epoch": 1.01, + "learning_rate": 3.5867369033447485e-05, + "loss": 3.6129, + "step": 863232 + }, + { + "epoch": 1.01, + "learning_rate": 3.5858999464740694e-05, + "loss": 3.6067, + "step": 863744 + }, + { + "epoch": 1.01, + "learning_rate": 3.5850613517230174e-05, + "loss": 3.5905, + "step": 864256 + }, + { + "epoch": 1.01, + "learning_rate": 3.5842227569719654e-05, + "loss": 3.6175, + "step": 864768 + }, + { + "epoch": 1.01, + "learning_rate": 3.5833841622209134e-05, + "loss": 3.6155, + "step": 865280 + }, + { + "epoch": 1.01, + "learning_rate": 3.582547205350234e-05, + "loss": 3.6212, + "step": 865792 + }, + { + "epoch": 1.01, + "learning_rate": 3.581708610599183e-05, + "loss": 3.6128, + "step": 866304 + }, + { + "epoch": 1.01, + "learning_rate": 3.580871653728504e-05, + "loss": 3.6076, + "step": 866816 + }, + { + "epoch": 1.01, + "learning_rate": 3.580033058977452e-05, + "loss": 3.6029, + "step": 867328 + }, + { + "epoch": 1.01, + "learning_rate": 3.5791944642264e-05, + "loss": 3.6022, + "step": 867840 + }, + { + "epoch": 1.01, + "learning_rate": 3.578355869475348e-05, + "loss": 3.624, + "step": 868352 + }, + { + "epoch": 1.01, + "learning_rate": 3.577517274724296e-05, + "loss": 3.5953, + "step": 868864 + }, + { + "epoch": 1.01, + "learning_rate": 3.576678679973244e-05, + "loss": 3.6313, + "step": 869376 + }, + { + "epoch": 1.01, + "learning_rate": 3.575840085222192e-05, + "loss": 3.6121, + "step": 869888 + }, + { + "epoch": 1.01, + "learning_rate": 3.57500149047114e-05, + "loss": 3.5949, + "step": 870400 + }, + { + "epoch": 1.01, + "learning_rate": 3.574164533600461e-05, + "loss": 3.6136, + "step": 870912 + }, + { + "epoch": 1.01, + "learning_rate": 3.573325938849409e-05, + "loss": 3.6066, + "step": 871424 + }, + { + "epoch": 1.01, + "learning_rate": 3.572487344098357e-05, + "loss": 3.5961, + "step": 871936 + }, + { + "epoch": 1.01, + "learning_rate": 3.571648749347305e-05, + "loss": 3.6112, + "step": 872448 + }, + { + "epoch": 1.01, + "learning_rate": 3.570811792476626e-05, + "loss": 3.6175, + "step": 872960 + }, + { + "epoch": 1.01, + "learning_rate": 3.569973197725574e-05, + "loss": 3.6016, + "step": 873472 + }, + { + "epoch": 1.01, + "learning_rate": 3.569134602974522e-05, + "loss": 3.6087, + "step": 873984 + }, + { + "epoch": 1.01, + "learning_rate": 3.56829600822347e-05, + "loss": 3.5858, + "step": 874496 + }, + { + "epoch": 1.01, + "learning_rate": 3.567459051352791e-05, + "loss": 3.6015, + "step": 875008 + }, + { + "epoch": 1.01, + "learning_rate": 3.566620456601739e-05, + "loss": 3.6058, + "step": 875520 + }, + { + "epoch": 1.01, + "learning_rate": 3.565781861850687e-05, + "loss": 3.6096, + "step": 876032 + }, + { + "epoch": 1.01, + "learning_rate": 3.564943267099635e-05, + "loss": 3.6071, + "step": 876544 + }, + { + "epoch": 1.01, + "learning_rate": 3.564106310228956e-05, + "loss": 3.6053, + "step": 877056 + }, + { + "epoch": 1.01, + "learning_rate": 3.563267715477904e-05, + "loss": 3.6223, + "step": 877568 + }, + { + "epoch": 1.01, + "learning_rate": 3.562429120726852e-05, + "loss": 3.6087, + "step": 878080 + }, + { + "epoch": 1.01, + "learning_rate": 3.5615905259758e-05, + "loss": 3.6162, + "step": 878592 + }, + { + "epoch": 1.01, + "learning_rate": 3.560753569105122e-05, + "loss": 3.6046, + "step": 879104 + }, + { + "epoch": 1.01, + "learning_rate": 3.55991497435407e-05, + "loss": 3.6019, + "step": 879616 + }, + { + "epoch": 1.01, + "learning_rate": 3.5590763796030177e-05, + "loss": 3.6102, + "step": 880128 + }, + { + "epoch": 1.01, + "learning_rate": 3.5582377848519657e-05, + "loss": 3.6086, + "step": 880640 + }, + { + "epoch": 1.01, + "learning_rate": 3.5574008279812866e-05, + "loss": 3.6053, + "step": 881152 + }, + { + "epoch": 1.01, + "learning_rate": 3.5565622332302346e-05, + "loss": 3.6133, + "step": 881664 + }, + { + "epoch": 1.01, + "learning_rate": 3.5557236384791826e-05, + "loss": 3.6027, + "step": 882176 + }, + { + "epoch": 1.01, + "learning_rate": 3.5548850437281306e-05, + "loss": 3.5901, + "step": 882688 + }, + { + "epoch": 1.01, + "learning_rate": 3.5540480868574515e-05, + "loss": 3.6044, + "step": 883200 + }, + { + "epoch": 1.01, + "learning_rate": 3.5532094921063995e-05, + "loss": 3.6103, + "step": 883712 + }, + { + "epoch": 1.01, + "learning_rate": 3.5523708973553475e-05, + "loss": 3.5978, + "step": 884224 + }, + { + "epoch": 1.01, + "learning_rate": 3.5515323026042954e-05, + "loss": 3.6082, + "step": 884736 + }, + { + "epoch": 1.01, + "learning_rate": 3.550695345733617e-05, + "loss": 3.6049, + "step": 885248 + }, + { + "epoch": 1.02, + "learning_rate": 3.549856750982565e-05, + "loss": 3.5975, + "step": 885760 + }, + { + "epoch": 1.02, + "learning_rate": 3.549018156231513e-05, + "loss": 3.5985, + "step": 886272 + }, + { + "epoch": 1.02, + "learning_rate": 3.548179561480461e-05, + "loss": 3.5991, + "step": 886784 + }, + { + "epoch": 1.02, + "learning_rate": 3.547342604609782e-05, + "loss": 3.6141, + "step": 887296 + }, + { + "epoch": 1.02, + "learning_rate": 3.54650400985873e-05, + "loss": 3.6115, + "step": 887808 + }, + { + "epoch": 1.02, + "learning_rate": 3.545665415107678e-05, + "loss": 3.6121, + "step": 888320 + }, + { + "epoch": 1.02, + "learning_rate": 3.544826820356626e-05, + "loss": 3.5979, + "step": 888832 + }, + { + "epoch": 1.02, + "learning_rate": 3.543989863485947e-05, + "loss": 3.596, + "step": 889344 + }, + { + "epoch": 1.02, + "learning_rate": 3.543151268734895e-05, + "loss": 3.6056, + "step": 889856 + }, + { + "epoch": 1.02, + "learning_rate": 3.542312673983843e-05, + "loss": 3.6105, + "step": 890368 + }, + { + "epoch": 1.02, + "learning_rate": 3.541474079232791e-05, + "loss": 3.6098, + "step": 890880 + }, + { + "epoch": 1.02, + "learning_rate": 3.5406371223621124e-05, + "loss": 3.6113, + "step": 891392 + }, + { + "epoch": 1.02, + "learning_rate": 3.5397985276110604e-05, + "loss": 3.6024, + "step": 891904 + }, + { + "epoch": 1.02, + "learning_rate": 3.5389599328600084e-05, + "loss": 3.5992, + "step": 892416 + }, + { + "epoch": 1.02, + "learning_rate": 3.538121338108956e-05, + "loss": 3.6135, + "step": 892928 + }, + { + "epoch": 1.02, + "learning_rate": 3.537284381238277e-05, + "loss": 3.5998, + "step": 893440 + }, + { + "epoch": 1.02, + "learning_rate": 3.536445786487225e-05, + "loss": 3.5983, + "step": 893952 + }, + { + "epoch": 1.02, + "learning_rate": 3.535607191736173e-05, + "loss": 3.6046, + "step": 894464 + }, + { + "epoch": 1.02, + "learning_rate": 3.5347685969851206e-05, + "loss": 3.6032, + "step": 894976 + }, + { + "epoch": 1.02, + "learning_rate": 3.533931640114442e-05, + "loss": 3.6004, + "step": 895488 + }, + { + "epoch": 1.02, + "learning_rate": 3.53309304536339e-05, + "loss": 3.5928, + "step": 896000 + }, + { + "epoch": 1.02, + "learning_rate": 3.532254450612338e-05, + "loss": 3.5952, + "step": 896512 + }, + { + "epoch": 1.02, + "learning_rate": 3.531415855861286e-05, + "loss": 3.6085, + "step": 897024 + }, + { + "epoch": 1.02, + "learning_rate": 3.530578898990608e-05, + "loss": 3.6065, + "step": 897536 + }, + { + "epoch": 1.02, + "learning_rate": 3.529740304239556e-05, + "loss": 3.6021, + "step": 898048 + }, + { + "epoch": 1.02, + "learning_rate": 3.528901709488503e-05, + "loss": 3.6077, + "step": 898560 + }, + { + "epoch": 1.02, + "learning_rate": 3.528063114737451e-05, + "loss": 3.6167, + "step": 899072 + }, + { + "epoch": 1.02, + "learning_rate": 3.527226157866773e-05, + "loss": 3.604, + "step": 899584 + }, + { + "epoch": 1.02, + "learning_rate": 3.5263875631157207e-05, + "loss": 3.6039, + "step": 900096 + }, + { + "epoch": 1.02, + "learning_rate": 3.525548968364668e-05, + "loss": 3.5949, + "step": 900608 + }, + { + "epoch": 1.02, + "learning_rate": 3.524710373613616e-05, + "loss": 3.6003, + "step": 901120 + }, + { + "epoch": 1.02, + "learning_rate": 3.5238734167429376e-05, + "loss": 3.6023, + "step": 901632 + }, + { + "epoch": 1.02, + "learning_rate": 3.5230348219918856e-05, + "loss": 3.6003, + "step": 902144 + }, + { + "epoch": 1.02, + "learning_rate": 3.522196227240833e-05, + "loss": 3.5963, + "step": 902656 + }, + { + "epoch": 1.02, + "learning_rate": 3.5213576324897815e-05, + "loss": 3.6047, + "step": 903168 + }, + { + "epoch": 1.02, + "learning_rate": 3.520520675619103e-05, + "loss": 3.6042, + "step": 903680 + }, + { + "epoch": 1.02, + "learning_rate": 3.5196820808680505e-05, + "loss": 3.5976, + "step": 904192 + }, + { + "epoch": 1.02, + "learning_rate": 3.5188434861169984e-05, + "loss": 3.6048, + "step": 904704 + }, + { + "epoch": 1.02, + "learning_rate": 3.5180048913659464e-05, + "loss": 3.6017, + "step": 905216 + }, + { + "epoch": 1.02, + "learning_rate": 3.517167934495268e-05, + "loss": 3.6031, + "step": 905728 + }, + { + "epoch": 1.02, + "learning_rate": 3.5163293397442153e-05, + "loss": 3.6057, + "step": 906240 + }, + { + "epoch": 1.02, + "learning_rate": 3.5154907449931633e-05, + "loss": 3.616, + "step": 906752 + }, + { + "epoch": 1.02, + "learning_rate": 3.5146521502421113e-05, + "loss": 3.5956, + "step": 907264 + }, + { + "epoch": 1.02, + "learning_rate": 3.513815193371433e-05, + "loss": 3.6046, + "step": 907776 + }, + { + "epoch": 1.02, + "learning_rate": 3.51297659862038e-05, + "loss": 3.606, + "step": 908288 + }, + { + "epoch": 1.02, + "learning_rate": 3.512138003869328e-05, + "loss": 3.6006, + "step": 908800 + }, + { + "epoch": 1.02, + "learning_rate": 3.511299409118277e-05, + "loss": 3.6029, + "step": 909312 + }, + { + "epoch": 1.02, + "learning_rate": 3.510462452247598e-05, + "loss": 3.604, + "step": 909824 + }, + { + "epoch": 1.02, + "learning_rate": 3.509623857496546e-05, + "loss": 3.6156, + "step": 910336 + }, + { + "epoch": 1.02, + "learning_rate": 3.508785262745494e-05, + "loss": 3.6122, + "step": 910848 + }, + { + "epoch": 1.02, + "learning_rate": 3.507946667994442e-05, + "loss": 3.6038, + "step": 911360 + }, + { + "epoch": 1.02, + "learning_rate": 3.507109711123763e-05, + "loss": 3.6049, + "step": 911872 + }, + { + "epoch": 1.02, + "learning_rate": 3.506271116372711e-05, + "loss": 3.607, + "step": 912384 + }, + { + "epoch": 1.02, + "learning_rate": 3.505432521621659e-05, + "loss": 3.6004, + "step": 912896 + }, + { + "epoch": 1.02, + "learning_rate": 3.504593926870607e-05, + "loss": 3.5969, + "step": 913408 + }, + { + "epoch": 1.02, + "learning_rate": 3.5037569699999276e-05, + "loss": 3.6041, + "step": 913920 + }, + { + "epoch": 1.02, + "learning_rate": 3.5029183752488756e-05, + "loss": 3.5946, + "step": 914432 + }, + { + "epoch": 1.02, + "learning_rate": 3.5020797804978236e-05, + "loss": 3.601, + "step": 914944 + }, + { + "epoch": 1.02, + "learning_rate": 3.501242823627145e-05, + "loss": 3.5968, + "step": 915456 + }, + { + "epoch": 1.03, + "eval_loss": 3.845362424850464, + "eval_runtime": 316.1049, + "eval_samples_per_second": 1207.166, + "eval_steps_per_second": 37.725, + "step": 915830 + }, + { + "epoch": 0.0, + "learning_rate": 3.500404228876093e-05, + "loss": 3.6138, + "step": 915968 + }, + { + "epoch": 0.0, + "learning_rate": 3.499565634125041e-05, + "loss": 3.5962, + "step": 916480 + }, + { + "epoch": 0.0, + "learning_rate": 3.498727039373989e-05, + "loss": 3.5977, + "step": 916992 + }, + { + "epoch": 0.0, + "learning_rate": 3.497888444622937e-05, + "loss": 3.6063, + "step": 917504 + }, + { + "epoch": 0.0, + "learning_rate": 3.497051487752258e-05, + "loss": 3.6079, + "step": 918016 + }, + { + "epoch": 0.0, + "learning_rate": 3.496212893001206e-05, + "loss": 3.6057, + "step": 918528 + }, + { + "epoch": 0.0, + "learning_rate": 3.495374298250154e-05, + "loss": 3.6079, + "step": 919040 + }, + { + "epoch": 0.0, + "learning_rate": 3.494535703499102e-05, + "loss": 3.5938, + "step": 919552 + }, + { + "epoch": 0.0, + "learning_rate": 3.493698746628423e-05, + "loss": 3.5893, + "step": 920064 + }, + { + "epoch": 0.0, + "learning_rate": 3.492860151877371e-05, + "loss": 3.5999, + "step": 920576 + }, + { + "epoch": 0.0, + "learning_rate": 3.492021557126319e-05, + "loss": 3.6023, + "step": 921088 + }, + { + "epoch": 0.0, + "learning_rate": 3.4911829623752676e-05, + "loss": 3.5978, + "step": 921600 + }, + { + "epoch": 0.0, + "learning_rate": 3.4903460055045886e-05, + "loss": 3.6042, + "step": 922112 + }, + { + "epoch": 0.0, + "learning_rate": 3.4895074107535366e-05, + "loss": 3.5813, + "step": 922624 + }, + { + "epoch": 0.0, + "learning_rate": 3.4886688160024845e-05, + "loss": 3.5919, + "step": 923136 + }, + { + "epoch": 0.0, + "learning_rate": 3.4878302212514325e-05, + "loss": 3.5794, + "step": 923648 + }, + { + "epoch": 0.0, + "learning_rate": 3.4869932643807535e-05, + "loss": 3.5995, + "step": 924160 + }, + { + "epoch": 0.0, + "learning_rate": 3.4861546696297014e-05, + "loss": 3.5943, + "step": 924672 + }, + { + "epoch": 0.0, + "learning_rate": 3.4853160748786494e-05, + "loss": 3.5925, + "step": 925184 + }, + { + "epoch": 0.0, + "learning_rate": 3.4844774801275974e-05, + "loss": 3.5963, + "step": 925696 + }, + { + "epoch": 0.0, + "learning_rate": 3.4836405232569184e-05, + "loss": 3.6093, + "step": 926208 + }, + { + "epoch": 0.0, + "learning_rate": 3.4828019285058663e-05, + "loss": 3.6, + "step": 926720 + }, + { + "epoch": 0.0, + "learning_rate": 3.4819633337548143e-05, + "loss": 3.5964, + "step": 927232 + }, + { + "epoch": 0.0, + "learning_rate": 3.481124739003763e-05, + "loss": 3.5935, + "step": 927744 + }, + { + "epoch": 0.0, + "learning_rate": 3.480287782133084e-05, + "loss": 3.6091, + "step": 928256 + }, + { + "epoch": 0.0, + "learning_rate": 3.479449187382032e-05, + "loss": 3.5997, + "step": 928768 + }, + { + "epoch": 0.0, + "learning_rate": 3.47861059263098e-05, + "loss": 3.5912, + "step": 929280 + }, + { + "epoch": 0.0, + "learning_rate": 3.477771997879928e-05, + "loss": 3.6006, + "step": 929792 + }, + { + "epoch": 0.0, + "learning_rate": 3.476935041009249e-05, + "loss": 3.5854, + "step": 930304 + }, + { + "epoch": 0.0, + "learning_rate": 3.476096446258197e-05, + "loss": 3.5934, + "step": 930816 + }, + { + "epoch": 0.01, + "learning_rate": 3.475257851507145e-05, + "loss": 3.5994, + "step": 931328 + }, + { + "epoch": 0.01, + "learning_rate": 3.474419256756093e-05, + "loss": 3.596, + "step": 931840 + }, + { + "epoch": 0.01, + "learning_rate": 3.473582299885414e-05, + "loss": 3.5995, + "step": 932352 + }, + { + "epoch": 0.01, + "learning_rate": 3.472743705134362e-05, + "loss": 3.6055, + "step": 932864 + }, + { + "epoch": 0.01, + "learning_rate": 3.47190511038331e-05, + "loss": 3.5912, + "step": 933376 + }, + { + "epoch": 0.01, + "learning_rate": 3.471066515632258e-05, + "loss": 3.5992, + "step": 933888 + }, + { + "epoch": 0.01, + "learning_rate": 3.470229558761579e-05, + "loss": 3.6021, + "step": 934400 + }, + { + "epoch": 0.01, + "learning_rate": 3.469390964010527e-05, + "loss": 3.5834, + "step": 934912 + }, + { + "epoch": 0.01, + "learning_rate": 3.468552369259475e-05, + "loss": 3.5932, + "step": 935424 + }, + { + "epoch": 0.01, + "learning_rate": 3.467713774508423e-05, + "loss": 3.5832, + "step": 935936 + }, + { + "epoch": 0.01, + "learning_rate": 3.466876817637744e-05, + "loss": 3.5794, + "step": 936448 + }, + { + "epoch": 0.01, + "learning_rate": 3.466038222886692e-05, + "loss": 3.5939, + "step": 936960 + }, + { + "epoch": 0.01, + "learning_rate": 3.46519962813564e-05, + "loss": 3.6048, + "step": 937472 + }, + { + "epoch": 0.01, + "learning_rate": 3.464361033384588e-05, + "loss": 3.5903, + "step": 937984 + }, + { + "epoch": 0.01, + "learning_rate": 3.463524076513909e-05, + "loss": 3.591, + "step": 938496 + }, + { + "epoch": 0.01, + "learning_rate": 3.462685481762857e-05, + "loss": 3.5909, + "step": 939008 + }, + { + "epoch": 0.01, + "learning_rate": 3.461846887011805e-05, + "loss": 3.5941, + "step": 939520 + }, + { + "epoch": 0.01, + "learning_rate": 3.461008292260753e-05, + "loss": 3.5832, + "step": 940032 + }, + { + "epoch": 0.01, + "learning_rate": 3.4601713353900747e-05, + "loss": 3.5732, + "step": 940544 + }, + { + "epoch": 0.01, + "learning_rate": 3.4593327406390227e-05, + "loss": 3.5941, + "step": 941056 + }, + { + "epoch": 0.01, + "learning_rate": 3.4584941458879706e-05, + "loss": 3.601, + "step": 941568 + }, + { + "epoch": 0.01, + "learning_rate": 3.4576555511369186e-05, + "loss": 3.601, + "step": 942080 + }, + { + "epoch": 0.01, + "learning_rate": 3.4568185942662396e-05, + "loss": 3.5869, + "step": 942592 + }, + { + "epoch": 0.01, + "learning_rate": 3.4559816373955605e-05, + "loss": 3.5922, + "step": 943104 + }, + { + "epoch": 0.01, + "learning_rate": 3.4551430426445085e-05, + "loss": 3.5815, + "step": 943616 + }, + { + "epoch": 0.01, + "learning_rate": 3.4543044478934565e-05, + "loss": 3.5809, + "step": 944128 + }, + { + "epoch": 0.01, + "learning_rate": 3.4534658531424045e-05, + "loss": 3.6063, + "step": 944640 + }, + { + "epoch": 0.01, + "learning_rate": 3.4526272583913524e-05, + "loss": 3.5771, + "step": 945152 + }, + { + "epoch": 0.01, + "learning_rate": 3.4517886636403004e-05, + "loss": 3.6091, + "step": 945664 + }, + { + "epoch": 0.01, + "learning_rate": 3.4509500688892484e-05, + "loss": 3.5916, + "step": 946176 + }, + { + "epoch": 0.01, + "learning_rate": 3.450111474138197e-05, + "loss": 3.577, + "step": 946688 + }, + { + "epoch": 0.01, + "learning_rate": 3.449274517267518e-05, + "loss": 3.5932, + "step": 947200 + }, + { + "epoch": 0.01, + "learning_rate": 3.448435922516466e-05, + "loss": 3.5887, + "step": 947712 + }, + { + "epoch": 0.01, + "learning_rate": 3.447597327765414e-05, + "loss": 3.5733, + "step": 948224 + }, + { + "epoch": 0.01, + "learning_rate": 3.446758733014362e-05, + "loss": 3.5892, + "step": 948736 + }, + { + "epoch": 0.01, + "learning_rate": 3.445921776143683e-05, + "loss": 3.5964, + "step": 949248 + }, + { + "epoch": 0.01, + "learning_rate": 3.445083181392631e-05, + "loss": 3.5809, + "step": 949760 + }, + { + "epoch": 0.01, + "learning_rate": 3.444244586641579e-05, + "loss": 3.5909, + "step": 950272 + }, + { + "epoch": 0.01, + "learning_rate": 3.443405991890527e-05, + "loss": 3.5684, + "step": 950784 + }, + { + "epoch": 0.01, + "learning_rate": 3.442569035019848e-05, + "loss": 3.5836, + "step": 951296 + }, + { + "epoch": 0.01, + "learning_rate": 3.441730440268796e-05, + "loss": 3.5878, + "step": 951808 + }, + { + "epoch": 0.01, + "learning_rate": 3.440891845517744e-05, + "loss": 3.5911, + "step": 952320 + }, + { + "epoch": 0.01, + "learning_rate": 3.4400532507666925e-05, + "loss": 3.5828, + "step": 952832 + }, + { + "epoch": 0.01, + "learning_rate": 3.4392162938960134e-05, + "loss": 3.5871, + "step": 953344 + }, + { + "epoch": 0.01, + "learning_rate": 3.4383776991449614e-05, + "loss": 3.6011, + "step": 953856 + }, + { + "epoch": 0.01, + "learning_rate": 3.4375391043939094e-05, + "loss": 3.5924, + "step": 954368 + }, + { + "epoch": 0.01, + "learning_rate": 3.4367005096428574e-05, + "loss": 3.5924, + "step": 954880 + }, + { + "epoch": 0.01, + "learning_rate": 3.435863552772178e-05, + "loss": 3.5869, + "step": 955392 + }, + { + "epoch": 0.01, + "learning_rate": 3.435024958021126e-05, + "loss": 3.5813, + "step": 955904 + }, + { + "epoch": 0.01, + "learning_rate": 3.434186363270074e-05, + "loss": 3.5926, + "step": 956416 + }, + { + "epoch": 0.01, + "learning_rate": 3.433347768519022e-05, + "loss": 3.5852, + "step": 956928 + }, + { + "epoch": 0.01, + "learning_rate": 3.432510811648343e-05, + "loss": 3.5891, + "step": 957440 + }, + { + "epoch": 0.01, + "learning_rate": 3.431672216897291e-05, + "loss": 3.5916, + "step": 957952 + }, + { + "epoch": 0.01, + "learning_rate": 3.430833622146239e-05, + "loss": 3.5859, + "step": 958464 + }, + { + "epoch": 0.01, + "learning_rate": 3.429995027395188e-05, + "loss": 3.5682, + "step": 958976 + }, + { + "epoch": 0.01, + "learning_rate": 3.429158070524509e-05, + "loss": 3.5886, + "step": 959488 + }, + { + "epoch": 0.01, + "learning_rate": 3.428319475773457e-05, + "loss": 3.5878, + "step": 960000 + }, + { + "epoch": 0.01, + "learning_rate": 3.427480881022405e-05, + "loss": 3.5785, + "step": 960512 + }, + { + "epoch": 0.01, + "learning_rate": 3.426642286271353e-05, + "loss": 3.5858, + "step": 961024 + }, + { + "epoch": 0.01, + "learning_rate": 3.4258053294006736e-05, + "loss": 3.5852, + "step": 961536 + }, + { + "epoch": 0.02, + "learning_rate": 3.4249667346496216e-05, + "loss": 3.5785, + "step": 962048 + }, + { + "epoch": 0.02, + "learning_rate": 3.4241281398985696e-05, + "loss": 3.5778, + "step": 962560 + }, + { + "epoch": 0.02, + "learning_rate": 3.4232895451475176e-05, + "loss": 3.5842, + "step": 963072 + }, + { + "epoch": 0.02, + "learning_rate": 3.4224525882768385e-05, + "loss": 3.5905, + "step": 963584 + }, + { + "epoch": 0.02, + "learning_rate": 3.4216139935257865e-05, + "loss": 3.5904, + "step": 964096 + }, + { + "epoch": 0.02, + "learning_rate": 3.4207753987747345e-05, + "loss": 3.5946, + "step": 964608 + }, + { + "epoch": 0.02, + "learning_rate": 3.4199368040236825e-05, + "loss": 3.578, + "step": 965120 + }, + { + "epoch": 0.02, + "learning_rate": 3.419099847153004e-05, + "loss": 3.5799, + "step": 965632 + }, + { + "epoch": 0.02, + "learning_rate": 3.418261252401952e-05, + "loss": 3.5847, + "step": 966144 + }, + { + "epoch": 0.02, + "learning_rate": 3.4174226576509e-05, + "loss": 3.5925, + "step": 966656 + }, + { + "epoch": 0.02, + "learning_rate": 3.4165840628998474e-05, + "loss": 3.5899, + "step": 967168 + }, + { + "epoch": 0.02, + "learning_rate": 3.415747106029169e-05, + "loss": 3.5877, + "step": 967680 + }, + { + "epoch": 0.02, + "learning_rate": 3.414908511278117e-05, + "loss": 3.5826, + "step": 968192 + }, + { + "epoch": 0.02, + "learning_rate": 3.414069916527065e-05, + "loss": 3.5829, + "step": 968704 + }, + { + "epoch": 0.02, + "learning_rate": 3.413231321776012e-05, + "loss": 3.5912, + "step": 969216 + }, + { + "epoch": 0.02, + "learning_rate": 3.412394364905334e-05, + "loss": 3.5829, + "step": 969728 + }, + { + "epoch": 0.02, + "learning_rate": 3.411555770154282e-05, + "loss": 3.5807, + "step": 970240 + }, + { + "epoch": 0.02, + "learning_rate": 3.41071717540323e-05, + "loss": 3.5866, + "step": 970752 + }, + { + "epoch": 0.02, + "learning_rate": 3.409878580652178e-05, + "loss": 3.5813, + "step": 971264 + }, + { + "epoch": 0.02, + "learning_rate": 3.4090416237814995e-05, + "loss": 3.5806, + "step": 971776 + }, + { + "epoch": 0.02, + "learning_rate": 3.4082030290304475e-05, + "loss": 3.5788, + "step": 972288 + }, + { + "epoch": 0.02, + "learning_rate": 3.407364434279395e-05, + "loss": 3.5733, + "step": 972800 + }, + { + "epoch": 0.02, + "learning_rate": 3.406525839528343e-05, + "loss": 3.5871, + "step": 973312 + }, + { + "epoch": 0.02, + "learning_rate": 3.4056888826576644e-05, + "loss": 3.5892, + "step": 973824 + }, + { + "epoch": 0.02, + "learning_rate": 3.4048502879066124e-05, + "loss": 3.5785, + "step": 974336 + }, + { + "epoch": 0.02, + "learning_rate": 3.40401169315556e-05, + "loss": 3.5904, + "step": 974848 + }, + { + "epoch": 0.02, + "learning_rate": 3.403173098404508e-05, + "loss": 3.5969, + "step": 975360 + }, + { + "epoch": 0.02, + "learning_rate": 3.402336141533829e-05, + "loss": 3.5839, + "step": 975872 + }, + { + "epoch": 0.02, + "learning_rate": 3.401497546782777e-05, + "loss": 3.5849, + "step": 976384 + }, + { + "epoch": 0.02, + "learning_rate": 3.400658952031725e-05, + "loss": 3.5769, + "step": 976896 + }, + { + "epoch": 0.02, + "learning_rate": 3.399820357280673e-05, + "loss": 3.5841, + "step": 977408 + }, + { + "epoch": 0.02, + "learning_rate": 3.398983400409995e-05, + "loss": 3.5795, + "step": 977920 + }, + { + "epoch": 0.02, + "learning_rate": 3.398144805658942e-05, + "loss": 3.5815, + "step": 978432 + }, + { + "epoch": 0.02, + "learning_rate": 3.39730621090789e-05, + "loss": 3.5799, + "step": 978944 + }, + { + "epoch": 0.02, + "learning_rate": 3.396467616156838e-05, + "loss": 3.5873, + "step": 979456 + }, + { + "epoch": 0.02, + "learning_rate": 3.39563065928616e-05, + "loss": 3.5818, + "step": 979968 + }, + { + "epoch": 0.02, + "learning_rate": 3.394792064535107e-05, + "loss": 3.5834, + "step": 980480 + }, + { + "epoch": 0.02, + "learning_rate": 3.393953469784055e-05, + "loss": 3.5854, + "step": 980992 + }, + { + "epoch": 0.02, + "learning_rate": 3.393114875033003e-05, + "loss": 3.5815, + "step": 981504 + }, + { + "epoch": 0.02, + "learning_rate": 3.3922779181623246e-05, + "loss": 3.5812, + "step": 982016 + }, + { + "epoch": 0.02, + "learning_rate": 3.3914393234112726e-05, + "loss": 3.593, + "step": 982528 + }, + { + "epoch": 0.02, + "learning_rate": 3.3906007286602206e-05, + "loss": 3.5938, + "step": 983040 + }, + { + "epoch": 0.02, + "learning_rate": 3.3897621339091686e-05, + "loss": 3.5804, + "step": 983552 + }, + { + "epoch": 0.02, + "learning_rate": 3.3889251770384895e-05, + "loss": 3.5804, + "step": 984064 + }, + { + "epoch": 0.02, + "learning_rate": 3.3880865822874375e-05, + "loss": 3.5896, + "step": 984576 + }, + { + "epoch": 0.02, + "learning_rate": 3.3872479875363855e-05, + "loss": 3.5778, + "step": 985088 + }, + { + "epoch": 0.02, + "learning_rate": 3.3864093927853335e-05, + "loss": 3.5856, + "step": 985600 + }, + { + "epoch": 0.02, + "learning_rate": 3.3855724359146544e-05, + "loss": 3.586, + "step": 986112 + }, + { + "epoch": 0.02, + "learning_rate": 3.3847338411636024e-05, + "loss": 3.5953, + "step": 986624 + }, + { + "epoch": 0.02, + "learning_rate": 3.3838952464125504e-05, + "loss": 3.5884, + "step": 987136 + }, + { + "epoch": 0.02, + "learning_rate": 3.3830566516614984e-05, + "loss": 3.5906, + "step": 987648 + }, + { + "epoch": 0.02, + "learning_rate": 3.38221969479082e-05, + "loss": 3.5815, + "step": 988160 + }, + { + "epoch": 0.02, + "learning_rate": 3.381381100039768e-05, + "loss": 3.5896, + "step": 988672 + }, + { + "epoch": 0.02, + "learning_rate": 3.380542505288716e-05, + "loss": 3.5836, + "step": 989184 + }, + { + "epoch": 0.02, + "learning_rate": 3.379703910537664e-05, + "loss": 3.5761, + "step": 989696 + }, + { + "epoch": 0.02, + "learning_rate": 3.378866953666985e-05, + "loss": 3.5858, + "step": 990208 + }, + { + "epoch": 0.02, + "learning_rate": 3.378028358915933e-05, + "loss": 3.5723, + "step": 990720 + }, + { + "epoch": 0.02, + "learning_rate": 3.377189764164881e-05, + "loss": 3.5878, + "step": 991232 + }, + { + "epoch": 0.02, + "learning_rate": 3.376351169413829e-05, + "loss": 3.5746, + "step": 991744 + }, + { + "epoch": 0.03, + "eval_loss": 3.845794439315796, + "eval_runtime": 305.5552, + "eval_samples_per_second": 1248.845, + "eval_steps_per_second": 39.027, + "step": 992150 + }, + { + "epoch": 1.0, + "learning_rate": 3.37551421254315e-05, + "loss": 3.5865, + "step": 992256 + }, + { + "epoch": 1.0, + "learning_rate": 3.374675617792098e-05, + "loss": 3.5778, + "step": 992768 + }, + { + "epoch": 1.0, + "learning_rate": 3.373837023041046e-05, + "loss": 3.5798, + "step": 993280 + }, + { + "epoch": 1.0, + "learning_rate": 3.373000066170367e-05, + "loss": 3.5918, + "step": 993792 + }, + { + "epoch": 1.0, + "learning_rate": 3.3721614714193154e-05, + "loss": 3.5853, + "step": 994304 + }, + { + "epoch": 1.0, + "learning_rate": 3.3713228766682634e-05, + "loss": 3.5933, + "step": 994816 + }, + { + "epoch": 1.0, + "learning_rate": 3.3704842819172114e-05, + "loss": 3.5831, + "step": 995328 + }, + { + "epoch": 1.0, + "learning_rate": 3.369647325046532e-05, + "loss": 3.5783, + "step": 995840 + }, + { + "epoch": 1.0, + "learning_rate": 3.36880873029548e-05, + "loss": 3.5681, + "step": 996352 + }, + { + "epoch": 1.0, + "learning_rate": 3.367970135544428e-05, + "loss": 3.5817, + "step": 996864 + }, + { + "epoch": 1.0, + "learning_rate": 3.367131540793376e-05, + "loss": 3.5837, + "step": 997376 + }, + { + "epoch": 1.0, + "learning_rate": 3.366292946042324e-05, + "loss": 3.5812, + "step": 997888 + }, + { + "epoch": 1.0, + "learning_rate": 3.365455989171645e-05, + "loss": 3.5876, + "step": 998400 + }, + { + "epoch": 1.0, + "learning_rate": 3.364617394420593e-05, + "loss": 3.561, + "step": 998912 + }, + { + "epoch": 1.0, + "learning_rate": 3.363778799669541e-05, + "loss": 3.573, + "step": 999424 + }, + { + "epoch": 1.0, + "learning_rate": 3.362940204918489e-05, + "loss": 3.5685, + "step": 999936 + }, + { + "epoch": 1.0, + "learning_rate": 3.36210324804781e-05, + "loss": 3.5787, + "step": 1000448 + }, + { + "epoch": 1.0, + "learning_rate": 3.361264653296759e-05, + "loss": 3.5736, + "step": 1000960 + }, + { + "epoch": 1.0, + "learning_rate": 3.360426058545707e-05, + "loss": 3.5751, + "step": 1001472 + }, + { + "epoch": 1.0, + "learning_rate": 3.359587463794655e-05, + "loss": 3.582, + "step": 1001984 + }, + { + "epoch": 1.0, + "learning_rate": 3.3587505069239756e-05, + "loss": 3.5859, + "step": 1002496 + }, + { + "epoch": 1.0, + "learning_rate": 3.3579119121729236e-05, + "loss": 3.5857, + "step": 1003008 + }, + { + "epoch": 1.0, + "learning_rate": 3.3570733174218716e-05, + "loss": 3.5766, + "step": 1003520 + }, + { + "epoch": 1.0, + "learning_rate": 3.3562363605511925e-05, + "loss": 3.5769, + "step": 1004032 + }, + { + "epoch": 1.0, + "learning_rate": 3.3553977658001405e-05, + "loss": 3.5914, + "step": 1004544 + }, + { + "epoch": 1.0, + "learning_rate": 3.3545591710490885e-05, + "loss": 3.5787, + "step": 1005056 + }, + { + "epoch": 1.0, + "learning_rate": 3.3537205762980365e-05, + "loss": 3.572, + "step": 1005568 + }, + { + "epoch": 1.0, + "learning_rate": 3.3528836194273574e-05, + "loss": 3.5821, + "step": 1006080 + }, + { + "epoch": 1.0, + "learning_rate": 3.3520450246763054e-05, + "loss": 3.566, + "step": 1006592 + }, + { + "epoch": 1.0, + "learning_rate": 3.351206429925254e-05, + "loss": 3.5761, + "step": 1007104 + }, + { + "epoch": 1.01, + "learning_rate": 3.350367835174202e-05, + "loss": 3.5821, + "step": 1007616 + }, + { + "epoch": 1.01, + "learning_rate": 3.349530878303523e-05, + "loss": 3.5779, + "step": 1008128 + }, + { + "epoch": 1.01, + "learning_rate": 3.348692283552471e-05, + "loss": 3.5805, + "step": 1008640 + }, + { + "epoch": 1.01, + "learning_rate": 3.347853688801419e-05, + "loss": 3.5871, + "step": 1009152 + }, + { + "epoch": 1.01, + "learning_rate": 3.347015094050367e-05, + "loss": 3.5735, + "step": 1009664 + }, + { + "epoch": 1.01, + "learning_rate": 3.346178137179688e-05, + "loss": 3.5825, + "step": 1010176 + }, + { + "epoch": 1.01, + "learning_rate": 3.345339542428636e-05, + "loss": 3.5836, + "step": 1010688 + }, + { + "epoch": 1.01, + "learning_rate": 3.344500947677584e-05, + "loss": 3.5636, + "step": 1011200 + }, + { + "epoch": 1.01, + "learning_rate": 3.343662352926532e-05, + "loss": 3.5754, + "step": 1011712 + }, + { + "epoch": 1.01, + "learning_rate": 3.342825396055853e-05, + "loss": 3.5623, + "step": 1012224 + }, + { + "epoch": 1.01, + "learning_rate": 3.341986801304801e-05, + "loss": 3.568, + "step": 1012736 + }, + { + "epoch": 1.01, + "learning_rate": 3.3411482065537495e-05, + "loss": 3.5738, + "step": 1013248 + }, + { + "epoch": 1.01, + "learning_rate": 3.3403096118026975e-05, + "loss": 3.5879, + "step": 1013760 + }, + { + "epoch": 1.01, + "learning_rate": 3.3394726549320184e-05, + "loss": 3.5711, + "step": 1014272 + }, + { + "epoch": 1.01, + "learning_rate": 3.3386340601809664e-05, + "loss": 3.5763, + "step": 1014784 + }, + { + "epoch": 1.01, + "learning_rate": 3.3377954654299144e-05, + "loss": 3.5714, + "step": 1015296 + }, + { + "epoch": 1.01, + "learning_rate": 3.3369568706788624e-05, + "loss": 3.5744, + "step": 1015808 + }, + { + "epoch": 1.01, + "learning_rate": 3.336119913808183e-05, + "loss": 3.5695, + "step": 1016320 + }, + { + "epoch": 1.01, + "learning_rate": 3.335281319057131e-05, + "loss": 3.5566, + "step": 1016832 + }, + { + "epoch": 1.01, + "learning_rate": 3.334442724306079e-05, + "loss": 3.5736, + "step": 1017344 + }, + { + "epoch": 1.01, + "learning_rate": 3.333604129555027e-05, + "loss": 3.5852, + "step": 1017856 + }, + { + "epoch": 1.01, + "learning_rate": 3.332767172684348e-05, + "loss": 3.5754, + "step": 1018368 + }, + { + "epoch": 1.01, + "learning_rate": 3.331928577933296e-05, + "loss": 3.5701, + "step": 1018880 + }, + { + "epoch": 1.01, + "learning_rate": 3.331089983182245e-05, + "loss": 3.5707, + "step": 1019392 + }, + { + "epoch": 1.01, + "learning_rate": 3.330251388431193e-05, + "loss": 3.5697, + "step": 1019904 + }, + { + "epoch": 1.01, + "learning_rate": 3.329414431560514e-05, + "loss": 3.5581, + "step": 1020416 + }, + { + "epoch": 1.01, + "learning_rate": 3.328575836809462e-05, + "loss": 3.5915, + "step": 1020928 + }, + { + "epoch": 1.01, + "learning_rate": 3.32773724205841e-05, + "loss": 3.5576, + "step": 1021440 + }, + { + "epoch": 1.01, + "learning_rate": 3.326898647307358e-05, + "loss": 3.5903, + "step": 1021952 + }, + { + "epoch": 1.01, + "learning_rate": 3.3260616904366786e-05, + "loss": 3.5758, + "step": 1022464 + }, + { + "epoch": 1.01, + "learning_rate": 3.3252230956856266e-05, + "loss": 3.5589, + "step": 1022976 + }, + { + "epoch": 1.01, + "learning_rate": 3.3243845009345746e-05, + "loss": 3.5728, + "step": 1023488 + }, + { + "epoch": 1.01, + "learning_rate": 3.3235459061835226e-05, + "loss": 3.5734, + "step": 1024000 + }, + { + "epoch": 1.01, + "learning_rate": 3.3227089493128435e-05, + "loss": 3.5573, + "step": 1024512 + }, + { + "epoch": 1.01, + "learning_rate": 3.3218703545617915e-05, + "loss": 3.5653, + "step": 1025024 + }, + { + "epoch": 1.01, + "learning_rate": 3.32103175981074e-05, + "loss": 3.5831, + "step": 1025536 + }, + { + "epoch": 1.01, + "learning_rate": 3.320193165059688e-05, + "loss": 3.564, + "step": 1026048 + }, + { + "epoch": 1.01, + "learning_rate": 3.319356208189009e-05, + "loss": 3.5693, + "step": 1026560 + }, + { + "epoch": 1.01, + "learning_rate": 3.318517613437957e-05, + "loss": 3.5512, + "step": 1027072 + }, + { + "epoch": 1.01, + "learning_rate": 3.317679018686905e-05, + "loss": 3.5652, + "step": 1027584 + }, + { + "epoch": 1.01, + "learning_rate": 3.316840423935853e-05, + "loss": 3.5671, + "step": 1028096 + }, + { + "epoch": 1.01, + "learning_rate": 3.316003467065174e-05, + "loss": 3.5726, + "step": 1028608 + }, + { + "epoch": 1.01, + "learning_rate": 3.315164872314122e-05, + "loss": 3.5657, + "step": 1029120 + }, + { + "epoch": 1.01, + "learning_rate": 3.31432627756307e-05, + "loss": 3.5741, + "step": 1029632 + }, + { + "epoch": 1.01, + "learning_rate": 3.313487682812018e-05, + "loss": 3.5817, + "step": 1030144 + }, + { + "epoch": 1.01, + "learning_rate": 3.312650725941339e-05, + "loss": 3.5691, + "step": 1030656 + }, + { + "epoch": 1.01, + "learning_rate": 3.311812131190287e-05, + "loss": 3.5748, + "step": 1031168 + }, + { + "epoch": 1.01, + "learning_rate": 3.3109735364392356e-05, + "loss": 3.5708, + "step": 1031680 + }, + { + "epoch": 1.01, + "learning_rate": 3.3101349416881836e-05, + "loss": 3.5638, + "step": 1032192 + }, + { + "epoch": 1.01, + "learning_rate": 3.3092979848175045e-05, + "loss": 3.573, + "step": 1032704 + }, + { + "epoch": 1.01, + "learning_rate": 3.3084593900664525e-05, + "loss": 3.5673, + "step": 1033216 + }, + { + "epoch": 1.01, + "learning_rate": 3.3076207953154005e-05, + "loss": 3.5716, + "step": 1033728 + }, + { + "epoch": 1.01, + "learning_rate": 3.3067822005643485e-05, + "loss": 3.5795, + "step": 1034240 + }, + { + "epoch": 1.01, + "learning_rate": 3.3059452436936694e-05, + "loss": 3.5668, + "step": 1034752 + }, + { + "epoch": 1.01, + "learning_rate": 3.3051066489426174e-05, + "loss": 3.5492, + "step": 1035264 + }, + { + "epoch": 1.01, + "learning_rate": 3.3042680541915654e-05, + "loss": 3.5718, + "step": 1035776 + }, + { + "epoch": 1.01, + "learning_rate": 3.3034294594405134e-05, + "loss": 3.5684, + "step": 1036288 + }, + { + "epoch": 1.01, + "learning_rate": 3.302592502569834e-05, + "loss": 3.5664, + "step": 1036800 + }, + { + "epoch": 1.01, + "learning_rate": 3.301753907818782e-05, + "loss": 3.5676, + "step": 1037312 + }, + { + "epoch": 1.01, + "learning_rate": 3.300915313067731e-05, + "loss": 3.5706, + "step": 1037824 + }, + { + "epoch": 1.02, + "learning_rate": 3.300076718316679e-05, + "loss": 3.5581, + "step": 1038336 + }, + { + "epoch": 1.02, + "learning_rate": 3.299239761446e-05, + "loss": 3.5611, + "step": 1038848 + }, + { + "epoch": 1.02, + "learning_rate": 3.298401166694948e-05, + "loss": 3.5644, + "step": 1039360 + }, + { + "epoch": 1.02, + "learning_rate": 3.297562571943896e-05, + "loss": 3.5752, + "step": 1039872 + }, + { + "epoch": 1.02, + "learning_rate": 3.296723977192844e-05, + "loss": 3.5728, + "step": 1040384 + }, + { + "epoch": 1.02, + "learning_rate": 3.295887020322165e-05, + "loss": 3.5763, + "step": 1040896 + }, + { + "epoch": 1.02, + "learning_rate": 3.295048425571113e-05, + "loss": 3.5592, + "step": 1041408 + }, + { + "epoch": 1.02, + "learning_rate": 3.294209830820061e-05, + "loss": 3.5646, + "step": 1041920 + }, + { + "epoch": 1.02, + "learning_rate": 3.293371236069009e-05, + "loss": 3.5662, + "step": 1042432 + }, + { + "epoch": 1.02, + "learning_rate": 3.2925342791983296e-05, + "loss": 3.5789, + "step": 1042944 + }, + { + "epoch": 1.02, + "learning_rate": 3.2916956844472776e-05, + "loss": 3.5669, + "step": 1043456 + }, + { + "epoch": 1.02, + "learning_rate": 3.2908570896962256e-05, + "loss": 3.5742, + "step": 1043968 + }, + { + "epoch": 1.02, + "learning_rate": 3.290018494945174e-05, + "loss": 3.567, + "step": 1044480 + }, + { + "epoch": 1.02, + "learning_rate": 3.289181538074495e-05, + "loss": 3.5635, + "step": 1044992 + }, + { + "epoch": 1.02, + "learning_rate": 3.288342943323443e-05, + "loss": 3.5763, + "step": 1045504 + }, + { + "epoch": 1.02, + "learning_rate": 3.287504348572391e-05, + "loss": 3.5614, + "step": 1046016 + }, + { + "epoch": 1.02, + "learning_rate": 3.286665753821339e-05, + "loss": 3.5643, + "step": 1046528 + }, + { + "epoch": 1.02, + "learning_rate": 3.28582879695066e-05, + "loss": 3.5688, + "step": 1047040 + }, + { + "epoch": 1.02, + "learning_rate": 3.284990202199608e-05, + "loss": 3.5647, + "step": 1047552 + }, + { + "epoch": 1.02, + "learning_rate": 3.284151607448556e-05, + "loss": 3.562, + "step": 1048064 + }, + { + "epoch": 1.02, + "learning_rate": 3.2833130126975034e-05, + "loss": 3.563, + "step": 1048576 + }, + { + "epoch": 1.02, + "learning_rate": 3.282476055826825e-05, + "loss": 3.5528, + "step": 1049088 + }, + { + "epoch": 1.02, + "learning_rate": 3.281637461075773e-05, + "loss": 3.5708, + "step": 1049600 + }, + { + "epoch": 1.02, + "learning_rate": 3.280798866324721e-05, + "loss": 3.5706, + "step": 1050112 + }, + { + "epoch": 1.02, + "learning_rate": 3.279960271573669e-05, + "loss": 3.5617, + "step": 1050624 + }, + { + "epoch": 1.02, + "learning_rate": 3.2791233147029906e-05, + "loss": 3.5725, + "step": 1051136 + }, + { + "epoch": 1.02, + "learning_rate": 3.2782847199519386e-05, + "loss": 3.5809, + "step": 1051648 + }, + { + "epoch": 1.02, + "learning_rate": 3.2774461252008866e-05, + "loss": 3.5662, + "step": 1052160 + }, + { + "epoch": 1.02, + "learning_rate": 3.276607530449834e-05, + "loss": 3.5685, + "step": 1052672 + }, + { + "epoch": 1.02, + "learning_rate": 3.2757705735791555e-05, + "loss": 3.5641, + "step": 1053184 + }, + { + "epoch": 1.02, + "learning_rate": 3.2749319788281035e-05, + "loss": 3.5643, + "step": 1053696 + }, + { + "epoch": 1.02, + "learning_rate": 3.274093384077051e-05, + "loss": 3.5599, + "step": 1054208 + }, + { + "epoch": 1.02, + "learning_rate": 3.273254789325999e-05, + "loss": 3.5626, + "step": 1054720 + }, + { + "epoch": 1.02, + "learning_rate": 3.2724178324553204e-05, + "loss": 3.5632, + "step": 1055232 + }, + { + "epoch": 1.02, + "learning_rate": 3.2715792377042684e-05, + "loss": 3.5688, + "step": 1055744 + }, + { + "epoch": 1.02, + "learning_rate": 3.2707406429532164e-05, + "loss": 3.5653, + "step": 1056256 + }, + { + "epoch": 1.02, + "learning_rate": 3.2699020482021644e-05, + "loss": 3.5658, + "step": 1056768 + }, + { + "epoch": 1.02, + "learning_rate": 3.269065091331486e-05, + "loss": 3.567, + "step": 1057280 + }, + { + "epoch": 1.02, + "learning_rate": 3.268226496580434e-05, + "loss": 3.5636, + "step": 1057792 + }, + { + "epoch": 1.02, + "learning_rate": 3.267387901829381e-05, + "loss": 3.5618, + "step": 1058304 + }, + { + "epoch": 1.02, + "learning_rate": 3.266549307078329e-05, + "loss": 3.5745, + "step": 1058816 + }, + { + "epoch": 1.02, + "learning_rate": 3.265712350207651e-05, + "loss": 3.5786, + "step": 1059328 + }, + { + "epoch": 1.02, + "learning_rate": 3.264873755456598e-05, + "loss": 3.5657, + "step": 1059840 + }, + { + "epoch": 1.02, + "learning_rate": 3.264035160705546e-05, + "loss": 3.5618, + "step": 1060352 + }, + { + "epoch": 1.02, + "learning_rate": 3.263196565954494e-05, + "loss": 3.5684, + "step": 1060864 + }, + { + "epoch": 1.02, + "learning_rate": 3.262359609083816e-05, + "loss": 3.5636, + "step": 1061376 + }, + { + "epoch": 1.02, + "learning_rate": 3.261521014332764e-05, + "loss": 3.5672, + "step": 1061888 + }, + { + "epoch": 1.02, + "learning_rate": 3.260682419581712e-05, + "loss": 3.5697, + "step": 1062400 + }, + { + "epoch": 1.02, + "learning_rate": 3.25984382483066e-05, + "loss": 3.5821, + "step": 1062912 + }, + { + "epoch": 1.02, + "learning_rate": 3.259006867959981e-05, + "loss": 3.57, + "step": 1063424 + }, + { + "epoch": 1.02, + "learning_rate": 3.2581682732089286e-05, + "loss": 3.5721, + "step": 1063936 + }, + { + "epoch": 1.02, + "learning_rate": 3.2573296784578766e-05, + "loss": 3.5664, + "step": 1064448 + }, + { + "epoch": 1.02, + "learning_rate": 3.2564910837068246e-05, + "loss": 3.5754, + "step": 1064960 + }, + { + "epoch": 1.02, + "learning_rate": 3.2556541268361455e-05, + "loss": 3.5626, + "step": 1065472 + }, + { + "epoch": 1.02, + "learning_rate": 3.2548155320850935e-05, + "loss": 3.5561, + "step": 1065984 + }, + { + "epoch": 1.02, + "learning_rate": 3.2539769373340415e-05, + "loss": 3.5701, + "step": 1066496 + }, + { + "epoch": 1.02, + "learning_rate": 3.2531383425829895e-05, + "loss": 3.5561, + "step": 1067008 + }, + { + "epoch": 1.02, + "learning_rate": 3.252301385712311e-05, + "loss": 3.5704, + "step": 1067520 + }, + { + "epoch": 1.02, + "learning_rate": 3.251462790961259e-05, + "loss": 3.5558, + "step": 1068032 + }, + { + "epoch": 1.03, + "eval_loss": 3.8476247787475586, + "eval_runtime": 306.3492, + "eval_samples_per_second": 1245.608, + "eval_steps_per_second": 38.926, + "step": 1068470 + }, + { + "epoch": 0.0, + "learning_rate": 3.250624196210207e-05, + "loss": 3.5774, + "step": 1068544 + }, + { + "epoch": 0.0, + "learning_rate": 3.249785601459155e-05, + "loss": 3.5637, + "step": 1069056 + }, + { + "epoch": 0.0, + "learning_rate": 3.248947006708103e-05, + "loss": 3.5618, + "step": 1069568 + }, + { + "epoch": 0.0, + "learning_rate": 3.248108411957051e-05, + "loss": 3.5763, + "step": 1070080 + }, + { + "epoch": 0.0, + "learning_rate": 3.247271455086372e-05, + "loss": 3.5664, + "step": 1070592 + }, + { + "epoch": 0.0, + "learning_rate": 3.24643286033532e-05, + "loss": 3.5778, + "step": 1071104 + }, + { + "epoch": 0.0, + "learning_rate": 3.245594265584268e-05, + "loss": 3.5614, + "step": 1071616 + }, + { + "epoch": 0.0, + "learning_rate": 3.244755670833216e-05, + "loss": 3.5612, + "step": 1072128 + }, + { + "epoch": 0.0, + "learning_rate": 3.243918713962537e-05, + "loss": 3.554, + "step": 1072640 + }, + { + "epoch": 0.0, + "learning_rate": 3.243080119211485e-05, + "loss": 3.5667, + "step": 1073152 + }, + { + "epoch": 0.0, + "learning_rate": 3.242241524460433e-05, + "loss": 3.5625, + "step": 1073664 + }, + { + "epoch": 0.0, + "learning_rate": 3.241402929709381e-05, + "loss": 3.5637, + "step": 1074176 + }, + { + "epoch": 0.0, + "learning_rate": 3.2405659728387025e-05, + "loss": 3.5707, + "step": 1074688 + }, + { + "epoch": 0.0, + "learning_rate": 3.2397273780876505e-05, + "loss": 3.5465, + "step": 1075200 + }, + { + "epoch": 0.0, + "learning_rate": 3.2388887833365985e-05, + "loss": 3.552, + "step": 1075712 + }, + { + "epoch": 0.0, + "learning_rate": 3.2380501885855465e-05, + "loss": 3.5517, + "step": 1076224 + }, + { + "epoch": 0.0, + "learning_rate": 3.2372132317148674e-05, + "loss": 3.5581, + "step": 1076736 + }, + { + "epoch": 0.0, + "learning_rate": 3.2363746369638154e-05, + "loss": 3.5599, + "step": 1077248 + }, + { + "epoch": 0.0, + "learning_rate": 3.2355360422127634e-05, + "loss": 3.558, + "step": 1077760 + }, + { + "epoch": 0.0, + "learning_rate": 3.2346974474617113e-05, + "loss": 3.562, + "step": 1078272 + }, + { + "epoch": 0.0, + "learning_rate": 3.233860490591032e-05, + "loss": 3.5692, + "step": 1078784 + }, + { + "epoch": 0.0, + "learning_rate": 3.23302189583998e-05, + "loss": 3.5632, + "step": 1079296 + }, + { + "epoch": 0.0, + "learning_rate": 3.232183301088928e-05, + "loss": 3.5631, + "step": 1079808 + }, + { + "epoch": 0.0, + "learning_rate": 3.231344706337876e-05, + "loss": 3.5575, + "step": 1080320 + }, + { + "epoch": 0.0, + "learning_rate": 3.230507749467198e-05, + "loss": 3.5748, + "step": 1080832 + }, + { + "epoch": 0.0, + "learning_rate": 3.229669154716146e-05, + "loss": 3.5616, + "step": 1081344 + }, + { + "epoch": 0.0, + "learning_rate": 3.228830559965094e-05, + "loss": 3.5602, + "step": 1081856 + }, + { + "epoch": 0.0, + "learning_rate": 3.227991965214042e-05, + "loss": 3.5608, + "step": 1082368 + }, + { + "epoch": 0.0, + "learning_rate": 3.227155008343363e-05, + "loss": 3.5527, + "step": 1082880 + }, + { + "epoch": 0.0, + "learning_rate": 3.226316413592311e-05, + "loss": 3.5589, + "step": 1083392 + }, + { + "epoch": 0.01, + "learning_rate": 3.225477818841259e-05, + "loss": 3.5589, + "step": 1083904 + }, + { + "epoch": 0.01, + "learning_rate": 3.224639224090207e-05, + "loss": 3.563, + "step": 1084416 + }, + { + "epoch": 0.01, + "learning_rate": 3.2238022672195276e-05, + "loss": 3.5625, + "step": 1084928 + }, + { + "epoch": 0.01, + "learning_rate": 3.2229636724684756e-05, + "loss": 3.5691, + "step": 1085440 + }, + { + "epoch": 0.01, + "learning_rate": 3.2221250777174236e-05, + "loss": 3.5583, + "step": 1085952 + }, + { + "epoch": 0.01, + "learning_rate": 3.2212864829663716e-05, + "loss": 3.5652, + "step": 1086464 + }, + { + "epoch": 0.01, + "learning_rate": 3.220449526095693e-05, + "loss": 3.5665, + "step": 1086976 + }, + { + "epoch": 0.01, + "learning_rate": 3.219610931344641e-05, + "loss": 3.5479, + "step": 1087488 + }, + { + "epoch": 0.01, + "learning_rate": 3.218772336593589e-05, + "loss": 3.5596, + "step": 1088000 + }, + { + "epoch": 0.01, + "learning_rate": 3.217933741842537e-05, + "loss": 3.5434, + "step": 1088512 + }, + { + "epoch": 0.01, + "learning_rate": 3.217096784971858e-05, + "loss": 3.5532, + "step": 1089024 + }, + { + "epoch": 0.01, + "learning_rate": 3.216258190220806e-05, + "loss": 3.5549, + "step": 1089536 + }, + { + "epoch": 0.01, + "learning_rate": 3.215419595469754e-05, + "loss": 3.5691, + "step": 1090048 + }, + { + "epoch": 0.01, + "learning_rate": 3.214581000718702e-05, + "loss": 3.5525, + "step": 1090560 + }, + { + "epoch": 0.01, + "learning_rate": 3.213744043848023e-05, + "loss": 3.5567, + "step": 1091072 + }, + { + "epoch": 0.01, + "learning_rate": 3.212905449096971e-05, + "loss": 3.5597, + "step": 1091584 + }, + { + "epoch": 0.01, + "learning_rate": 3.212066854345919e-05, + "loss": 3.5572, + "step": 1092096 + }, + { + "epoch": 0.01, + "learning_rate": 3.211228259594867e-05, + "loss": 3.5553, + "step": 1092608 + }, + { + "epoch": 0.01, + "learning_rate": 3.2103913027241886e-05, + "loss": 3.5356, + "step": 1093120 + }, + { + "epoch": 0.01, + "learning_rate": 3.2095527079731366e-05, + "loss": 3.5581, + "step": 1093632 + }, + { + "epoch": 0.01, + "learning_rate": 3.2087141132220846e-05, + "loss": 3.5668, + "step": 1094144 + }, + { + "epoch": 0.01, + "learning_rate": 3.2078755184710326e-05, + "loss": 3.5623, + "step": 1094656 + }, + { + "epoch": 0.01, + "learning_rate": 3.2070385616003535e-05, + "loss": 3.5555, + "step": 1095168 + }, + { + "epoch": 0.01, + "learning_rate": 3.2062016047296744e-05, + "loss": 3.5491, + "step": 1095680 + }, + { + "epoch": 0.01, + "learning_rate": 3.2053630099786224e-05, + "loss": 3.5591, + "step": 1096192 + }, + { + "epoch": 0.01, + "learning_rate": 3.2045244152275704e-05, + "loss": 3.5436, + "step": 1096704 + }, + { + "epoch": 0.01, + "learning_rate": 3.2036858204765184e-05, + "loss": 3.5718, + "step": 1097216 + }, + { + "epoch": 0.01, + "learning_rate": 3.2028472257254664e-05, + "loss": 3.5429, + "step": 1097728 + }, + { + "epoch": 0.01, + "learning_rate": 3.2020086309744143e-05, + "loss": 3.5736, + "step": 1098240 + }, + { + "epoch": 0.01, + "learning_rate": 3.2011700362233623e-05, + "loss": 3.5608, + "step": 1098752 + }, + { + "epoch": 0.01, + "learning_rate": 3.2003314414723103e-05, + "loss": 3.541, + "step": 1099264 + }, + { + "epoch": 0.01, + "learning_rate": 3.199494484601632e-05, + "loss": 3.5562, + "step": 1099776 + }, + { + "epoch": 0.01, + "learning_rate": 3.19865588985058e-05, + "loss": 3.5588, + "step": 1100288 + }, + { + "epoch": 0.01, + "learning_rate": 3.197817295099528e-05, + "loss": 3.5421, + "step": 1100800 + }, + { + "epoch": 0.01, + "learning_rate": 3.196978700348476e-05, + "loss": 3.5464, + "step": 1101312 + }, + { + "epoch": 0.01, + "learning_rate": 3.196141743477797e-05, + "loss": 3.5648, + "step": 1101824 + }, + { + "epoch": 0.01, + "learning_rate": 3.195303148726745e-05, + "loss": 3.5517, + "step": 1102336 + }, + { + "epoch": 0.01, + "learning_rate": 3.194464553975693e-05, + "loss": 3.5514, + "step": 1102848 + }, + { + "epoch": 0.01, + "learning_rate": 3.193625959224641e-05, + "loss": 3.5372, + "step": 1103360 + }, + { + "epoch": 0.01, + "learning_rate": 3.192789002353962e-05, + "loss": 3.5504, + "step": 1103872 + }, + { + "epoch": 0.01, + "learning_rate": 3.19195040760291e-05, + "loss": 3.5479, + "step": 1104384 + }, + { + "epoch": 0.01, + "learning_rate": 3.191111812851858e-05, + "loss": 3.5613, + "step": 1104896 + }, + { + "epoch": 0.01, + "learning_rate": 3.190273218100806e-05, + "loss": 3.5465, + "step": 1105408 + }, + { + "epoch": 0.01, + "learning_rate": 3.189436261230127e-05, + "loss": 3.5583, + "step": 1105920 + }, + { + "epoch": 0.01, + "learning_rate": 3.188597666479075e-05, + "loss": 3.5599, + "step": 1106432 + }, + { + "epoch": 0.01, + "learning_rate": 3.187759071728023e-05, + "loss": 3.5554, + "step": 1106944 + }, + { + "epoch": 0.01, + "learning_rate": 3.186920476976971e-05, + "loss": 3.5571, + "step": 1107456 + }, + { + "epoch": 0.01, + "learning_rate": 3.186083520106292e-05, + "loss": 3.5539, + "step": 1107968 + }, + { + "epoch": 0.01, + "learning_rate": 3.18524492535524e-05, + "loss": 3.5516, + "step": 1108480 + }, + { + "epoch": 0.01, + "learning_rate": 3.184406330604188e-05, + "loss": 3.555, + "step": 1108992 + }, + { + "epoch": 0.01, + "learning_rate": 3.183567735853136e-05, + "loss": 3.5532, + "step": 1109504 + }, + { + "epoch": 0.01, + "learning_rate": 3.182730778982457e-05, + "loss": 3.5538, + "step": 1110016 + }, + { + "epoch": 0.01, + "learning_rate": 3.181892184231405e-05, + "loss": 3.5548, + "step": 1110528 + }, + { + "epoch": 0.01, + "learning_rate": 3.181053589480353e-05, + "loss": 3.5521, + "step": 1111040 + }, + { + "epoch": 0.01, + "learning_rate": 3.180214994729301e-05, + "loss": 3.5365, + "step": 1111552 + }, + { + "epoch": 0.01, + "learning_rate": 3.1793780378586227e-05, + "loss": 3.5562, + "step": 1112064 + }, + { + "epoch": 0.01, + "learning_rate": 3.1785394431075707e-05, + "loss": 3.5465, + "step": 1112576 + }, + { + "epoch": 0.01, + "learning_rate": 3.1777008483565187e-05, + "loss": 3.5548, + "step": 1113088 + }, + { + "epoch": 0.01, + "learning_rate": 3.176862253605466e-05, + "loss": 3.5499, + "step": 1113600 + }, + { + "epoch": 0.01, + "learning_rate": 3.1760252967347876e-05, + "loss": 3.5553, + "step": 1114112 + }, + { + "epoch": 0.02, + "learning_rate": 3.1751867019837356e-05, + "loss": 3.5452, + "step": 1114624 + }, + { + "epoch": 0.02, + "learning_rate": 3.1743481072326835e-05, + "loss": 3.5415, + "step": 1115136 + }, + { + "epoch": 0.02, + "learning_rate": 3.173509512481631e-05, + "loss": 3.5459, + "step": 1115648 + }, + { + "epoch": 0.02, + "learning_rate": 3.1726725556109525e-05, + "loss": 3.5581, + "step": 1116160 + }, + { + "epoch": 0.02, + "learning_rate": 3.1718339608599004e-05, + "loss": 3.5553, + "step": 1116672 + }, + { + "epoch": 0.02, + "learning_rate": 3.1709953661088484e-05, + "loss": 3.5605, + "step": 1117184 + }, + { + "epoch": 0.02, + "learning_rate": 3.1701567713577964e-05, + "loss": 3.5436, + "step": 1117696 + }, + { + "epoch": 0.02, + "learning_rate": 3.169319814487118e-05, + "loss": 3.5501, + "step": 1118208 + }, + { + "epoch": 0.02, + "learning_rate": 3.168481219736066e-05, + "loss": 3.546, + "step": 1118720 + }, + { + "epoch": 0.02, + "learning_rate": 3.1676426249850133e-05, + "loss": 3.5625, + "step": 1119232 + }, + { + "epoch": 0.02, + "learning_rate": 3.166804030233961e-05, + "loss": 3.5523, + "step": 1119744 + }, + { + "epoch": 0.02, + "learning_rate": 3.165967073363283e-05, + "loss": 3.5609, + "step": 1120256 + }, + { + "epoch": 0.02, + "learning_rate": 3.16512847861223e-05, + "loss": 3.5482, + "step": 1120768 + }, + { + "epoch": 0.02, + "learning_rate": 3.164289883861178e-05, + "loss": 3.549, + "step": 1121280 + }, + { + "epoch": 0.02, + "learning_rate": 3.163451289110126e-05, + "loss": 3.5611, + "step": 1121792 + }, + { + "epoch": 0.02, + "learning_rate": 3.162614332239448e-05, + "loss": 3.5424, + "step": 1122304 + }, + { + "epoch": 0.02, + "learning_rate": 3.161775737488396e-05, + "loss": 3.5459, + "step": 1122816 + }, + { + "epoch": 0.02, + "learning_rate": 3.160937142737344e-05, + "loss": 3.55, + "step": 1123328 + }, + { + "epoch": 0.02, + "learning_rate": 3.160098547986292e-05, + "loss": 3.5479, + "step": 1123840 + }, + { + "epoch": 0.02, + "learning_rate": 3.1592615911156134e-05, + "loss": 3.5496, + "step": 1124352 + }, + { + "epoch": 0.02, + "learning_rate": 3.158422996364561e-05, + "loss": 3.5486, + "step": 1124864 + }, + { + "epoch": 0.02, + "learning_rate": 3.157584401613509e-05, + "loss": 3.5371, + "step": 1125376 + }, + { + "epoch": 0.02, + "learning_rate": 3.156745806862457e-05, + "loss": 3.5552, + "step": 1125888 + }, + { + "epoch": 0.02, + "learning_rate": 3.1559088499917776e-05, + "loss": 3.5529, + "step": 1126400 + }, + { + "epoch": 0.02, + "learning_rate": 3.1550702552407256e-05, + "loss": 3.5481, + "step": 1126912 + }, + { + "epoch": 0.02, + "learning_rate": 3.1542316604896736e-05, + "loss": 3.557, + "step": 1127424 + }, + { + "epoch": 0.02, + "learning_rate": 3.1533930657386216e-05, + "loss": 3.5639, + "step": 1127936 + }, + { + "epoch": 0.02, + "learning_rate": 3.1525561088679425e-05, + "loss": 3.5525, + "step": 1128448 + }, + { + "epoch": 0.02, + "learning_rate": 3.151717514116891e-05, + "loss": 3.5515, + "step": 1128960 + }, + { + "epoch": 0.02, + "learning_rate": 3.150878919365839e-05, + "loss": 3.5444, + "step": 1129472 + }, + { + "epoch": 0.02, + "learning_rate": 3.150040324614787e-05, + "loss": 3.5508, + "step": 1129984 + }, + { + "epoch": 0.02, + "learning_rate": 3.149203367744108e-05, + "loss": 3.5408, + "step": 1130496 + }, + { + "epoch": 0.02, + "learning_rate": 3.148364772993056e-05, + "loss": 3.5497, + "step": 1131008 + }, + { + "epoch": 0.02, + "learning_rate": 3.147526178242004e-05, + "loss": 3.5456, + "step": 1131520 + }, + { + "epoch": 0.02, + "learning_rate": 3.146687583490952e-05, + "loss": 3.5551, + "step": 1132032 + }, + { + "epoch": 0.02, + "learning_rate": 3.145850626620273e-05, + "loss": 3.5502, + "step": 1132544 + }, + { + "epoch": 0.02, + "learning_rate": 3.145012031869221e-05, + "loss": 3.5498, + "step": 1133056 + }, + { + "epoch": 0.02, + "learning_rate": 3.144173437118169e-05, + "loss": 3.5527, + "step": 1133568 + }, + { + "epoch": 0.02, + "learning_rate": 3.143334842367117e-05, + "loss": 3.5469, + "step": 1134080 + }, + { + "epoch": 0.02, + "learning_rate": 3.142497885496438e-05, + "loss": 3.5431, + "step": 1134592 + }, + { + "epoch": 0.02, + "learning_rate": 3.1416592907453865e-05, + "loss": 3.5572, + "step": 1135104 + }, + { + "epoch": 0.02, + "learning_rate": 3.1408206959943345e-05, + "loss": 3.5624, + "step": 1135616 + }, + { + "epoch": 0.02, + "learning_rate": 3.1399821012432825e-05, + "loss": 3.5535, + "step": 1136128 + }, + { + "epoch": 0.02, + "learning_rate": 3.1391451443726034e-05, + "loss": 3.5433, + "step": 1136640 + }, + { + "epoch": 0.02, + "learning_rate": 3.1383065496215514e-05, + "loss": 3.5499, + "step": 1137152 + }, + { + "epoch": 0.02, + "learning_rate": 3.1374679548704994e-05, + "loss": 3.5488, + "step": 1137664 + }, + { + "epoch": 0.02, + "learning_rate": 3.1366293601194474e-05, + "loss": 3.5549, + "step": 1138176 + }, + { + "epoch": 0.02, + "learning_rate": 3.1357924032487683e-05, + "loss": 3.5539, + "step": 1138688 + }, + { + "epoch": 0.02, + "learning_rate": 3.1349538084977163e-05, + "loss": 3.5637, + "step": 1139200 + }, + { + "epoch": 0.02, + "learning_rate": 3.134115213746664e-05, + "loss": 3.5508, + "step": 1139712 + }, + { + "epoch": 0.02, + "learning_rate": 3.133276618995612e-05, + "loss": 3.5596, + "step": 1140224 + }, + { + "epoch": 0.02, + "learning_rate": 3.132439662124933e-05, + "loss": 3.5503, + "step": 1140736 + }, + { + "epoch": 0.02, + "learning_rate": 3.131601067373882e-05, + "loss": 3.5574, + "step": 1141248 + }, + { + "epoch": 0.02, + "learning_rate": 3.13076247262283e-05, + "loss": 3.5456, + "step": 1141760 + }, + { + "epoch": 0.02, + "learning_rate": 3.129923877871778e-05, + "loss": 3.5446, + "step": 1142272 + }, + { + "epoch": 0.02, + "learning_rate": 3.129086921001099e-05, + "loss": 3.5567, + "step": 1142784 + }, + { + "epoch": 0.02, + "learning_rate": 3.128248326250047e-05, + "loss": 3.5391, + "step": 1143296 + }, + { + "epoch": 0.02, + "learning_rate": 3.127409731498995e-05, + "loss": 3.5534, + "step": 1143808 + }, + { + "epoch": 0.02, + "learning_rate": 3.126571136747943e-05, + "loss": 3.5439, + "step": 1144320 + }, + { + "epoch": 0.03, + "eval_loss": 3.8481285572052, + "eval_runtime": 310.9157, + "eval_samples_per_second": 1227.313, + "eval_steps_per_second": 38.354, + "step": 1144790 + }, + { + "epoch": 1.0, + "learning_rate": 3.125734179877264e-05, + "loss": 3.5505, + "step": 1144832 + }, + { + "epoch": 1.0, + "learning_rate": 3.124895585126212e-05, + "loss": 3.5488, + "step": 1145344 + }, + { + "epoch": 1.0, + "learning_rate": 3.12405699037516e-05, + "loss": 3.5442, + "step": 1145856 + }, + { + "epoch": 1.0, + "learning_rate": 3.123218395624108e-05, + "loss": 3.5566, + "step": 1146368 + }, + { + "epoch": 1.0, + "learning_rate": 3.1223814387534286e-05, + "loss": 3.5537, + "step": 1146880 + }, + { + "epoch": 1.0, + "learning_rate": 3.121542844002377e-05, + "loss": 3.5611, + "step": 1147392 + }, + { + "epoch": 1.0, + "learning_rate": 3.120704249251325e-05, + "loss": 3.5464, + "step": 1147904 + }, + { + "epoch": 1.0, + "learning_rate": 3.119865654500273e-05, + "loss": 3.5487, + "step": 1148416 + }, + { + "epoch": 1.0, + "learning_rate": 3.119028697629594e-05, + "loss": 3.5348, + "step": 1148928 + }, + { + "epoch": 1.0, + "learning_rate": 3.118190102878542e-05, + "loss": 3.5514, + "step": 1149440 + }, + { + "epoch": 1.0, + "learning_rate": 3.11735150812749e-05, + "loss": 3.5474, + "step": 1149952 + }, + { + "epoch": 1.0, + "learning_rate": 3.116512913376438e-05, + "loss": 3.5489, + "step": 1150464 + }, + { + "epoch": 1.0, + "learning_rate": 3.115675956505759e-05, + "loss": 3.5501, + "step": 1150976 + }, + { + "epoch": 1.0, + "learning_rate": 3.114837361754707e-05, + "loss": 3.5353, + "step": 1151488 + }, + { + "epoch": 1.0, + "learning_rate": 3.113998767003655e-05, + "loss": 3.5379, + "step": 1152000 + }, + { + "epoch": 1.0, + "learning_rate": 3.113160172252603e-05, + "loss": 3.536, + "step": 1152512 + }, + { + "epoch": 1.0, + "learning_rate": 3.112323215381924e-05, + "loss": 3.5374, + "step": 1153024 + }, + { + "epoch": 1.0, + "learning_rate": 3.1114846206308726e-05, + "loss": 3.5443, + "step": 1153536 + }, + { + "epoch": 1.0, + "learning_rate": 3.1106460258798206e-05, + "loss": 3.5468, + "step": 1154048 + }, + { + "epoch": 1.0, + "learning_rate": 3.1098090690091416e-05, + "loss": 3.5393, + "step": 1154560 + }, + { + "epoch": 1.0, + "learning_rate": 3.1089704742580895e-05, + "loss": 3.5606, + "step": 1155072 + }, + { + "epoch": 1.0, + "learning_rate": 3.1081318795070375e-05, + "loss": 3.5463, + "step": 1155584 + }, + { + "epoch": 1.0, + "learning_rate": 3.1072932847559855e-05, + "loss": 3.5477, + "step": 1156096 + }, + { + "epoch": 1.0, + "learning_rate": 3.1064563278853065e-05, + "loss": 3.5442, + "step": 1156608 + }, + { + "epoch": 1.0, + "learning_rate": 3.1056177331342544e-05, + "loss": 3.5602, + "step": 1157120 + }, + { + "epoch": 1.0, + "learning_rate": 3.1047791383832024e-05, + "loss": 3.5439, + "step": 1157632 + }, + { + "epoch": 1.0, + "learning_rate": 3.1039405436321504e-05, + "loss": 3.5477, + "step": 1158144 + }, + { + "epoch": 1.0, + "learning_rate": 3.1031035867614713e-05, + "loss": 3.5426, + "step": 1158656 + }, + { + "epoch": 1.0, + "learning_rate": 3.1022649920104193e-05, + "loss": 3.5441, + "step": 1159168 + }, + { + "epoch": 1.0, + "learning_rate": 3.101426397259368e-05, + "loss": 3.5443, + "step": 1159680 + }, + { + "epoch": 1.01, + "learning_rate": 3.100587802508316e-05, + "loss": 3.5422, + "step": 1160192 + }, + { + "epoch": 1.01, + "learning_rate": 3.099750845637637e-05, + "loss": 3.5508, + "step": 1160704 + }, + { + "epoch": 1.01, + "learning_rate": 3.098912250886585e-05, + "loss": 3.5501, + "step": 1161216 + }, + { + "epoch": 1.01, + "learning_rate": 3.098073656135533e-05, + "loss": 3.5499, + "step": 1161728 + }, + { + "epoch": 1.01, + "learning_rate": 3.097235061384481e-05, + "loss": 3.5434, + "step": 1162240 + }, + { + "epoch": 1.01, + "learning_rate": 3.096398104513802e-05, + "loss": 3.5517, + "step": 1162752 + }, + { + "epoch": 1.01, + "learning_rate": 3.09555950976275e-05, + "loss": 3.5472, + "step": 1163264 + }, + { + "epoch": 1.01, + "learning_rate": 3.094720915011698e-05, + "loss": 3.5349, + "step": 1163776 + }, + { + "epoch": 1.01, + "learning_rate": 3.093882320260646e-05, + "loss": 3.5411, + "step": 1164288 + }, + { + "epoch": 1.01, + "learning_rate": 3.093045363389967e-05, + "loss": 3.5311, + "step": 1164800 + }, + { + "epoch": 1.01, + "learning_rate": 3.092206768638915e-05, + "loss": 3.5388, + "step": 1165312 + }, + { + "epoch": 1.01, + "learning_rate": 3.091368173887863e-05, + "loss": 3.538, + "step": 1165824 + }, + { + "epoch": 1.01, + "learning_rate": 3.0905295791368114e-05, + "loss": 3.5548, + "step": 1166336 + }, + { + "epoch": 1.01, + "learning_rate": 3.089692622266132e-05, + "loss": 3.5422, + "step": 1166848 + }, + { + "epoch": 1.01, + "learning_rate": 3.08885402751508e-05, + "loss": 3.5387, + "step": 1167360 + }, + { + "epoch": 1.01, + "learning_rate": 3.088015432764028e-05, + "loss": 3.5429, + "step": 1167872 + }, + { + "epoch": 1.01, + "learning_rate": 3.087176838012976e-05, + "loss": 3.5436, + "step": 1168384 + }, + { + "epoch": 1.01, + "learning_rate": 3.086339881142297e-05, + "loss": 3.5398, + "step": 1168896 + }, + { + "epoch": 1.01, + "learning_rate": 3.085501286391245e-05, + "loss": 3.5231, + "step": 1169408 + }, + { + "epoch": 1.01, + "learning_rate": 3.084662691640193e-05, + "loss": 3.5383, + "step": 1169920 + }, + { + "epoch": 1.01, + "learning_rate": 3.083824096889141e-05, + "loss": 3.5527, + "step": 1170432 + }, + { + "epoch": 1.01, + "learning_rate": 3.082987140018462e-05, + "loss": 3.5454, + "step": 1170944 + }, + { + "epoch": 1.01, + "learning_rate": 3.08214854526741e-05, + "loss": 3.5421, + "step": 1171456 + }, + { + "epoch": 1.01, + "learning_rate": 3.081309950516358e-05, + "loss": 3.5322, + "step": 1171968 + }, + { + "epoch": 1.01, + "learning_rate": 3.080471355765307e-05, + "loss": 3.5441, + "step": 1172480 + }, + { + "epoch": 1.01, + "learning_rate": 3.0796343988946277e-05, + "loss": 3.5278, + "step": 1172992 + }, + { + "epoch": 1.01, + "learning_rate": 3.0787958041435756e-05, + "loss": 3.5527, + "step": 1173504 + }, + { + "epoch": 1.01, + "learning_rate": 3.0779572093925236e-05, + "loss": 3.5291, + "step": 1174016 + }, + { + "epoch": 1.01, + "learning_rate": 3.0771186146414716e-05, + "loss": 3.5558, + "step": 1174528 + }, + { + "epoch": 1.01, + "learning_rate": 3.0762816577707926e-05, + "loss": 3.5472, + "step": 1175040 + }, + { + "epoch": 1.01, + "learning_rate": 3.0754430630197405e-05, + "loss": 3.5274, + "step": 1175552 + }, + { + "epoch": 1.01, + "learning_rate": 3.0746044682686885e-05, + "loss": 3.5403, + "step": 1176064 + }, + { + "epoch": 1.01, + "learning_rate": 3.0737658735176365e-05, + "loss": 3.547, + "step": 1176576 + }, + { + "epoch": 1.01, + "learning_rate": 3.0729289166469574e-05, + "loss": 3.523, + "step": 1177088 + }, + { + "epoch": 1.01, + "learning_rate": 3.0720903218959054e-05, + "loss": 3.5306, + "step": 1177600 + }, + { + "epoch": 1.01, + "learning_rate": 3.0712517271448534e-05, + "loss": 3.5508, + "step": 1178112 + }, + { + "epoch": 1.01, + "learning_rate": 3.070413132393802e-05, + "loss": 3.5362, + "step": 1178624 + }, + { + "epoch": 1.01, + "learning_rate": 3.069576175523123e-05, + "loss": 3.5343, + "step": 1179136 + }, + { + "epoch": 1.01, + "learning_rate": 3.068737580772071e-05, + "loss": 3.5213, + "step": 1179648 + }, + { + "epoch": 1.01, + "learning_rate": 3.067898986021019e-05, + "loss": 3.5364, + "step": 1180160 + }, + { + "epoch": 1.01, + "learning_rate": 3.067060391269967e-05, + "loss": 3.5292, + "step": 1180672 + }, + { + "epoch": 1.01, + "learning_rate": 3.066223434399288e-05, + "loss": 3.5475, + "step": 1181184 + }, + { + "epoch": 1.01, + "learning_rate": 3.065384839648236e-05, + "loss": 3.5304, + "step": 1181696 + }, + { + "epoch": 1.01, + "learning_rate": 3.064546244897184e-05, + "loss": 3.5441, + "step": 1182208 + }, + { + "epoch": 1.01, + "learning_rate": 3.063707650146132e-05, + "loss": 3.5434, + "step": 1182720 + }, + { + "epoch": 1.01, + "learning_rate": 3.062870693275453e-05, + "loss": 3.5411, + "step": 1183232 + }, + { + "epoch": 1.01, + "learning_rate": 3.062032098524401e-05, + "loss": 3.5406, + "step": 1183744 + }, + { + "epoch": 1.01, + "learning_rate": 3.061193503773349e-05, + "loss": 3.5386, + "step": 1184256 + }, + { + "epoch": 1.01, + "learning_rate": 3.0603549090222975e-05, + "loss": 3.5391, + "step": 1184768 + }, + { + "epoch": 1.01, + "learning_rate": 3.0595179521516184e-05, + "loss": 3.5403, + "step": 1185280 + }, + { + "epoch": 1.01, + "learning_rate": 3.0586793574005664e-05, + "loss": 3.538, + "step": 1185792 + }, + { + "epoch": 1.01, + "learning_rate": 3.0578407626495144e-05, + "loss": 3.5374, + "step": 1186304 + }, + { + "epoch": 1.01, + "learning_rate": 3.0570021678984624e-05, + "loss": 3.5375, + "step": 1186816 + }, + { + "epoch": 1.01, + "learning_rate": 3.056165211027783e-05, + "loss": 3.5385, + "step": 1187328 + }, + { + "epoch": 1.01, + "learning_rate": 3.055326616276731e-05, + "loss": 3.5191, + "step": 1187840 + }, + { + "epoch": 1.01, + "learning_rate": 3.054488021525679e-05, + "loss": 3.5396, + "step": 1188352 + }, + { + "epoch": 1.01, + "learning_rate": 3.053649426774627e-05, + "loss": 3.5341, + "step": 1188864 + }, + { + "epoch": 1.01, + "learning_rate": 3.052812469903948e-05, + "loss": 3.5396, + "step": 1189376 + }, + { + "epoch": 1.01, + "learning_rate": 3.051973875152896e-05, + "loss": 3.5384, + "step": 1189888 + }, + { + "epoch": 1.01, + "learning_rate": 3.0511352804018445e-05, + "loss": 3.5359, + "step": 1190400 + }, + { + "epoch": 1.02, + "learning_rate": 3.0502966856507925e-05, + "loss": 3.5314, + "step": 1190912 + }, + { + "epoch": 1.02, + "learning_rate": 3.0494597287801134e-05, + "loss": 3.5252, + "step": 1191424 + }, + { + "epoch": 1.02, + "learning_rate": 3.0486211340290614e-05, + "loss": 3.5314, + "step": 1191936 + }, + { + "epoch": 1.02, + "learning_rate": 3.0477825392780097e-05, + "loss": 3.5431, + "step": 1192448 + }, + { + "epoch": 1.02, + "learning_rate": 3.0469439445269577e-05, + "loss": 3.5378, + "step": 1192960 + }, + { + "epoch": 1.02, + "learning_rate": 3.0461069876562787e-05, + "loss": 3.5456, + "step": 1193472 + }, + { + "epoch": 1.02, + "learning_rate": 3.0452683929052266e-05, + "loss": 3.5318, + "step": 1193984 + }, + { + "epoch": 1.02, + "learning_rate": 3.0444297981541746e-05, + "loss": 3.5347, + "step": 1194496 + }, + { + "epoch": 1.02, + "learning_rate": 3.0435912034031223e-05, + "loss": 3.53, + "step": 1195008 + }, + { + "epoch": 1.02, + "learning_rate": 3.042754246532444e-05, + "loss": 3.5471, + "step": 1195520 + }, + { + "epoch": 1.02, + "learning_rate": 3.041915651781392e-05, + "loss": 3.5354, + "step": 1196032 + }, + { + "epoch": 1.02, + "learning_rate": 3.04107705703034e-05, + "loss": 3.5481, + "step": 1196544 + }, + { + "epoch": 1.02, + "learning_rate": 3.0402384622792872e-05, + "loss": 3.53, + "step": 1197056 + }, + { + "epoch": 1.02, + "learning_rate": 3.0394015054086088e-05, + "loss": 3.5312, + "step": 1197568 + }, + { + "epoch": 1.02, + "learning_rate": 3.0385629106575568e-05, + "loss": 3.5489, + "step": 1198080 + }, + { + "epoch": 1.02, + "learning_rate": 3.037724315906505e-05, + "loss": 3.5299, + "step": 1198592 + }, + { + "epoch": 1.02, + "learning_rate": 3.0368857211554524e-05, + "loss": 3.5285, + "step": 1199104 + }, + { + "epoch": 1.02, + "learning_rate": 3.036048764284774e-05, + "loss": 3.5363, + "step": 1199616 + }, + { + "epoch": 1.02, + "learning_rate": 3.035210169533722e-05, + "loss": 3.5366, + "step": 1200128 + }, + { + "epoch": 1.02, + "learning_rate": 3.0343715747826697e-05, + "loss": 3.5272, + "step": 1200640 + }, + { + "epoch": 1.02, + "learning_rate": 3.0335329800316177e-05, + "loss": 3.5356, + "step": 1201152 + }, + { + "epoch": 1.02, + "learning_rate": 3.0326960231609393e-05, + "loss": 3.5212, + "step": 1201664 + }, + { + "epoch": 1.02, + "learning_rate": 3.0318574284098872e-05, + "loss": 3.5387, + "step": 1202176 + }, + { + "epoch": 1.02, + "learning_rate": 3.0310188336588346e-05, + "loss": 3.5342, + "step": 1202688 + }, + { + "epoch": 1.02, + "learning_rate": 3.0301802389077826e-05, + "loss": 3.5351, + "step": 1203200 + }, + { + "epoch": 1.02, + "learning_rate": 3.029343282037104e-05, + "loss": 3.54, + "step": 1203712 + }, + { + "epoch": 1.02, + "learning_rate": 3.0285046872860518e-05, + "loss": 3.5479, + "step": 1204224 + }, + { + "epoch": 1.02, + "learning_rate": 3.0276660925349998e-05, + "loss": 3.5388, + "step": 1204736 + }, + { + "epoch": 1.02, + "learning_rate": 3.0268274977839478e-05, + "loss": 3.5349, + "step": 1205248 + }, + { + "epoch": 1.02, + "learning_rate": 3.0259905409132694e-05, + "loss": 3.531, + "step": 1205760 + }, + { + "epoch": 1.02, + "learning_rate": 3.0251519461622167e-05, + "loss": 3.529, + "step": 1206272 + }, + { + "epoch": 1.02, + "learning_rate": 3.024313351411165e-05, + "loss": 3.5311, + "step": 1206784 + }, + { + "epoch": 1.02, + "learning_rate": 3.023474756660113e-05, + "loss": 3.532, + "step": 1207296 + }, + { + "epoch": 1.02, + "learning_rate": 3.0226377997894346e-05, + "loss": 3.5324, + "step": 1207808 + }, + { + "epoch": 1.02, + "learning_rate": 3.021799205038382e-05, + "loss": 3.5388, + "step": 1208320 + }, + { + "epoch": 1.02, + "learning_rate": 3.02096061028733e-05, + "loss": 3.5337, + "step": 1208832 + }, + { + "epoch": 1.02, + "learning_rate": 3.020122015536278e-05, + "loss": 3.5381, + "step": 1209344 + }, + { + "epoch": 1.02, + "learning_rate": 3.0192850586655992e-05, + "loss": 3.5348, + "step": 1209856 + }, + { + "epoch": 1.02, + "learning_rate": 3.0184464639145472e-05, + "loss": 3.5305, + "step": 1210368 + }, + { + "epoch": 1.02, + "learning_rate": 3.017607869163495e-05, + "loss": 3.528, + "step": 1210880 + }, + { + "epoch": 1.02, + "learning_rate": 3.016769274412443e-05, + "loss": 3.5409, + "step": 1211392 + }, + { + "epoch": 1.02, + "learning_rate": 3.015932317541764e-05, + "loss": 3.5495, + "step": 1211904 + }, + { + "epoch": 1.02, + "learning_rate": 3.015093722790712e-05, + "loss": 3.5414, + "step": 1212416 + }, + { + "epoch": 1.02, + "learning_rate": 3.0142551280396604e-05, + "loss": 3.5266, + "step": 1212928 + }, + { + "epoch": 1.02, + "learning_rate": 3.0134165332886084e-05, + "loss": 3.5321, + "step": 1213440 + }, + { + "epoch": 1.02, + "learning_rate": 3.0125795764179293e-05, + "loss": 3.5399, + "step": 1213952 + }, + { + "epoch": 1.02, + "learning_rate": 3.0117409816668773e-05, + "loss": 3.5381, + "step": 1214464 + }, + { + "epoch": 1.02, + "learning_rate": 3.0109023869158253e-05, + "loss": 3.5406, + "step": 1214976 + }, + { + "epoch": 1.02, + "learning_rate": 3.0100637921647733e-05, + "loss": 3.547, + "step": 1215488 + }, + { + "epoch": 1.02, + "learning_rate": 3.0092268352940945e-05, + "loss": 3.5346, + "step": 1216000 + }, + { + "epoch": 1.02, + "learning_rate": 3.0083882405430425e-05, + "loss": 3.5474, + "step": 1216512 + }, + { + "epoch": 1.02, + "learning_rate": 3.0075496457919905e-05, + "loss": 3.5327, + "step": 1217024 + }, + { + "epoch": 1.02, + "learning_rate": 3.0067110510409385e-05, + "loss": 3.5414, + "step": 1217536 + }, + { + "epoch": 1.02, + "learning_rate": 3.0058740941702594e-05, + "loss": 3.5324, + "step": 1218048 + }, + { + "epoch": 1.02, + "learning_rate": 3.0050354994192074e-05, + "loss": 3.5231, + "step": 1218560 + }, + { + "epoch": 1.02, + "learning_rate": 3.004198542548529e-05, + "loss": 3.5437, + "step": 1219072 + }, + { + "epoch": 1.02, + "learning_rate": 3.0033599477974767e-05, + "loss": 3.5245, + "step": 1219584 + }, + { + "epoch": 1.02, + "learning_rate": 3.0025213530464247e-05, + "loss": 3.5364, + "step": 1220096 + }, + { + "epoch": 1.02, + "learning_rate": 3.0016827582953727e-05, + "loss": 3.5306, + "step": 1220608 + }, + { + "epoch": 1.03, + "eval_loss": 3.8491084575653076, + "eval_runtime": 309.7145, + "eval_samples_per_second": 1232.073, + "eval_steps_per_second": 38.503, + "step": 1221110 + }, + { + "epoch": 0.0, + "learning_rate": 3.0008441635443207e-05, + "loss": 3.5467, + "step": 1221120 + }, + { + "epoch": 0.0, + "learning_rate": 3.0000055687932687e-05, + "loss": 3.5335, + "step": 1221632 + }, + { + "epoch": 0.0, + "learning_rate": 2.9991669740422167e-05, + "loss": 3.5296, + "step": 1222144 + }, + { + "epoch": 0.0, + "learning_rate": 2.998328379291165e-05, + "loss": 3.5416, + "step": 1222656 + }, + { + "epoch": 0.0, + "learning_rate": 2.997491422420486e-05, + "loss": 3.54, + "step": 1223168 + }, + { + "epoch": 0.0, + "learning_rate": 2.996652827669434e-05, + "loss": 3.5484, + "step": 1223680 + }, + { + "epoch": 0.0, + "learning_rate": 2.995814232918382e-05, + "loss": 3.5297, + "step": 1224192 + }, + { + "epoch": 0.0, + "learning_rate": 2.99497563816733e-05, + "loss": 3.5292, + "step": 1224704 + }, + { + "epoch": 0.0, + "learning_rate": 2.994138681296651e-05, + "loss": 3.5262, + "step": 1225216 + }, + { + "epoch": 0.0, + "learning_rate": 2.993300086545599e-05, + "loss": 3.5366, + "step": 1225728 + }, + { + "epoch": 0.0, + "learning_rate": 2.992461491794547e-05, + "loss": 3.5319, + "step": 1226240 + }, + { + "epoch": 0.0, + "learning_rate": 2.991622897043495e-05, + "loss": 3.5338, + "step": 1226752 + }, + { + "epoch": 0.0, + "learning_rate": 2.990785940172816e-05, + "loss": 3.5311, + "step": 1227264 + }, + { + "epoch": 0.0, + "learning_rate": 2.989947345421764e-05, + "loss": 3.5214, + "step": 1227776 + }, + { + "epoch": 0.0, + "learning_rate": 2.989108750670712e-05, + "loss": 3.5262, + "step": 1228288 + }, + { + "epoch": 0.0, + "learning_rate": 2.9882701559196604e-05, + "loss": 3.5234, + "step": 1228800 + }, + { + "epoch": 0.0, + "learning_rate": 2.9874315611686084e-05, + "loss": 3.5186, + "step": 1229312 + }, + { + "epoch": 0.0, + "learning_rate": 2.9865946042979293e-05, + "loss": 3.532, + "step": 1229824 + }, + { + "epoch": 0.0, + "learning_rate": 2.9857560095468773e-05, + "loss": 3.5251, + "step": 1230336 + }, + { + "epoch": 0.0, + "learning_rate": 2.9849174147958253e-05, + "loss": 3.5273, + "step": 1230848 + }, + { + "epoch": 0.0, + "learning_rate": 2.9840788200447733e-05, + "loss": 3.5499, + "step": 1231360 + }, + { + "epoch": 0.0, + "learning_rate": 2.9832418631740945e-05, + "loss": 3.5272, + "step": 1231872 + }, + { + "epoch": 0.0, + "learning_rate": 2.9824032684230425e-05, + "loss": 3.5361, + "step": 1232384 + }, + { + "epoch": 0.0, + "learning_rate": 2.9815646736719905e-05, + "loss": 3.5285, + "step": 1232896 + }, + { + "epoch": 0.0, + "learning_rate": 2.9807260789209385e-05, + "loss": 3.5429, + "step": 1233408 + }, + { + "epoch": 0.0, + "learning_rate": 2.9798891220502594e-05, + "loss": 3.5288, + "step": 1233920 + }, + { + "epoch": 0.0, + "learning_rate": 2.9790505272992074e-05, + "loss": 3.5321, + "step": 1234432 + }, + { + "epoch": 0.0, + "learning_rate": 2.9782119325481557e-05, + "loss": 3.5254, + "step": 1234944 + }, + { + "epoch": 0.0, + "learning_rate": 2.9773733377971037e-05, + "loss": 3.5303, + "step": 1235456 + }, + { + "epoch": 0.0, + "learning_rate": 2.9765363809264246e-05, + "loss": 3.5256, + "step": 1235968 + }, + { + "epoch": 0.01, + "learning_rate": 2.9756977861753726e-05, + "loss": 3.5269, + "step": 1236480 + }, + { + "epoch": 0.01, + "learning_rate": 2.9748591914243206e-05, + "loss": 3.539, + "step": 1236992 + }, + { + "epoch": 0.01, + "learning_rate": 2.9740205966732686e-05, + "loss": 3.5298, + "step": 1237504 + }, + { + "epoch": 0.01, + "learning_rate": 2.97318363980259e-05, + "loss": 3.5355, + "step": 1238016 + }, + { + "epoch": 0.01, + "learning_rate": 2.972345045051538e-05, + "loss": 3.5311, + "step": 1238528 + }, + { + "epoch": 0.01, + "learning_rate": 2.971506450300486e-05, + "loss": 3.53, + "step": 1239040 + }, + { + "epoch": 0.01, + "learning_rate": 2.970667855549434e-05, + "loss": 3.5394, + "step": 1239552 + }, + { + "epoch": 0.01, + "learning_rate": 2.9698308986787548e-05, + "loss": 3.5192, + "step": 1240064 + }, + { + "epoch": 0.01, + "learning_rate": 2.9689923039277028e-05, + "loss": 3.5288, + "step": 1240576 + }, + { + "epoch": 0.01, + "learning_rate": 2.9681537091766508e-05, + "loss": 3.5147, + "step": 1241088 + }, + { + "epoch": 0.01, + "learning_rate": 2.967315114425599e-05, + "loss": 3.5212, + "step": 1241600 + }, + { + "epoch": 0.01, + "learning_rate": 2.96647815755492e-05, + "loss": 3.5234, + "step": 1242112 + }, + { + "epoch": 0.01, + "learning_rate": 2.965639562803868e-05, + "loss": 3.5382, + "step": 1242624 + }, + { + "epoch": 0.01, + "learning_rate": 2.964800968052816e-05, + "loss": 3.5284, + "step": 1243136 + }, + { + "epoch": 0.01, + "learning_rate": 2.963962373301764e-05, + "loss": 3.5213, + "step": 1243648 + }, + { + "epoch": 0.01, + "learning_rate": 2.9631254164310852e-05, + "loss": 3.5302, + "step": 1244160 + }, + { + "epoch": 0.01, + "learning_rate": 2.9622868216800332e-05, + "loss": 3.5275, + "step": 1244672 + }, + { + "epoch": 0.01, + "learning_rate": 2.9614482269289812e-05, + "loss": 3.5229, + "step": 1245184 + }, + { + "epoch": 0.01, + "learning_rate": 2.9606096321779292e-05, + "loss": 3.512, + "step": 1245696 + }, + { + "epoch": 0.01, + "learning_rate": 2.95977267530725e-05, + "loss": 3.5207, + "step": 1246208 + }, + { + "epoch": 0.01, + "learning_rate": 2.958934080556198e-05, + "loss": 3.5356, + "step": 1246720 + }, + { + "epoch": 0.01, + "learning_rate": 2.958095485805146e-05, + "loss": 3.5334, + "step": 1247232 + }, + { + "epoch": 0.01, + "learning_rate": 2.9572585289344674e-05, + "loss": 3.5241, + "step": 1247744 + }, + { + "epoch": 0.01, + "learning_rate": 2.9564199341834154e-05, + "loss": 3.5197, + "step": 1248256 + }, + { + "epoch": 0.01, + "learning_rate": 2.9555813394323634e-05, + "loss": 3.5317, + "step": 1248768 + }, + { + "epoch": 0.01, + "learning_rate": 2.9547427446813114e-05, + "loss": 3.514, + "step": 1249280 + }, + { + "epoch": 0.01, + "learning_rate": 2.9539057878106323e-05, + "loss": 3.5359, + "step": 1249792 + }, + { + "epoch": 0.01, + "learning_rate": 2.9530671930595806e-05, + "loss": 3.5145, + "step": 1250304 + }, + { + "epoch": 0.01, + "learning_rate": 2.9522285983085286e-05, + "loss": 3.5395, + "step": 1250816 + }, + { + "epoch": 0.01, + "learning_rate": 2.9513900035574766e-05, + "loss": 3.5335, + "step": 1251328 + }, + { + "epoch": 0.01, + "learning_rate": 2.9505530466867975e-05, + "loss": 3.515, + "step": 1251840 + }, + { + "epoch": 0.01, + "learning_rate": 2.9497144519357455e-05, + "loss": 3.5214, + "step": 1252352 + }, + { + "epoch": 0.01, + "learning_rate": 2.9488758571846935e-05, + "loss": 3.5332, + "step": 1252864 + }, + { + "epoch": 0.01, + "learning_rate": 2.9480372624336415e-05, + "loss": 3.5088, + "step": 1253376 + }, + { + "epoch": 0.01, + "learning_rate": 2.9472003055629627e-05, + "loss": 3.5136, + "step": 1253888 + }, + { + "epoch": 0.01, + "learning_rate": 2.9463617108119107e-05, + "loss": 3.5358, + "step": 1254400 + }, + { + "epoch": 0.01, + "learning_rate": 2.9455231160608587e-05, + "loss": 3.5226, + "step": 1254912 + }, + { + "epoch": 0.01, + "learning_rate": 2.9446845213098067e-05, + "loss": 3.5212, + "step": 1255424 + }, + { + "epoch": 0.01, + "learning_rate": 2.9438475644391276e-05, + "loss": 3.5094, + "step": 1255936 + }, + { + "epoch": 0.01, + "learning_rate": 2.943008969688076e-05, + "loss": 3.5184, + "step": 1256448 + }, + { + "epoch": 0.01, + "learning_rate": 2.942170374937024e-05, + "loss": 3.5135, + "step": 1256960 + }, + { + "epoch": 0.01, + "learning_rate": 2.941331780185972e-05, + "loss": 3.5339, + "step": 1257472 + }, + { + "epoch": 0.01, + "learning_rate": 2.940494823315293e-05, + "loss": 3.5138, + "step": 1257984 + }, + { + "epoch": 0.01, + "learning_rate": 2.939656228564241e-05, + "loss": 3.5301, + "step": 1258496 + }, + { + "epoch": 0.01, + "learning_rate": 2.938817633813189e-05, + "loss": 3.5268, + "step": 1259008 + }, + { + "epoch": 0.01, + "learning_rate": 2.937979039062137e-05, + "loss": 3.5332, + "step": 1259520 + }, + { + "epoch": 0.01, + "learning_rate": 2.937142082191458e-05, + "loss": 3.5226, + "step": 1260032 + }, + { + "epoch": 0.01, + "learning_rate": 2.936303487440406e-05, + "loss": 3.5258, + "step": 1260544 + }, + { + "epoch": 0.01, + "learning_rate": 2.935464892689354e-05, + "loss": 3.5259, + "step": 1261056 + }, + { + "epoch": 0.01, + "learning_rate": 2.9346262979383014e-05, + "loss": 3.5255, + "step": 1261568 + }, + { + "epoch": 0.01, + "learning_rate": 2.933789341067623e-05, + "loss": 3.5241, + "step": 1262080 + }, + { + "epoch": 0.01, + "learning_rate": 2.9329507463165713e-05, + "loss": 3.5219, + "step": 1262592 + }, + { + "epoch": 0.01, + "learning_rate": 2.9321121515655193e-05, + "loss": 3.5275, + "step": 1263104 + }, + { + "epoch": 0.01, + "learning_rate": 2.9312735568144666e-05, + "loss": 3.5209, + "step": 1263616 + }, + { + "epoch": 0.01, + "learning_rate": 2.9304365999437882e-05, + "loss": 3.509, + "step": 1264128 + }, + { + "epoch": 0.01, + "learning_rate": 2.9295980051927362e-05, + "loss": 3.5185, + "step": 1264640 + }, + { + "epoch": 0.01, + "learning_rate": 2.9287594104416842e-05, + "loss": 3.5209, + "step": 1265152 + }, + { + "epoch": 0.01, + "learning_rate": 2.927920815690632e-05, + "loss": 3.5262, + "step": 1265664 + }, + { + "epoch": 0.01, + "learning_rate": 2.9270838588199535e-05, + "loss": 3.5198, + "step": 1266176 + }, + { + "epoch": 0.01, + "learning_rate": 2.9262452640689015e-05, + "loss": 3.5256, + "step": 1266688 + }, + { + "epoch": 0.02, + "learning_rate": 2.9254066693178488e-05, + "loss": 3.5192, + "step": 1267200 + }, + { + "epoch": 0.02, + "learning_rate": 2.9245680745667968e-05, + "loss": 3.5099, + "step": 1267712 + }, + { + "epoch": 0.02, + "learning_rate": 2.9237311176961184e-05, + "loss": 3.514, + "step": 1268224 + }, + { + "epoch": 0.02, + "learning_rate": 2.9228925229450667e-05, + "loss": 3.5265, + "step": 1268736 + }, + { + "epoch": 0.02, + "learning_rate": 2.922053928194014e-05, + "loss": 3.5241, + "step": 1269248 + }, + { + "epoch": 0.02, + "learning_rate": 2.921215333442962e-05, + "loss": 3.5301, + "step": 1269760 + }, + { + "epoch": 0.02, + "learning_rate": 2.9203783765722836e-05, + "loss": 3.5223, + "step": 1270272 + }, + { + "epoch": 0.02, + "learning_rate": 2.9195397818212316e-05, + "loss": 3.5159, + "step": 1270784 + }, + { + "epoch": 0.02, + "learning_rate": 2.9187011870701793e-05, + "loss": 3.5162, + "step": 1271296 + }, + { + "epoch": 0.02, + "learning_rate": 2.9178625923191272e-05, + "loss": 3.5318, + "step": 1271808 + }, + { + "epoch": 0.02, + "learning_rate": 2.917025635448449e-05, + "loss": 3.5212, + "step": 1272320 + }, + { + "epoch": 0.02, + "learning_rate": 2.916187040697396e-05, + "loss": 3.535, + "step": 1272832 + }, + { + "epoch": 0.02, + "learning_rate": 2.915348445946344e-05, + "loss": 3.5164, + "step": 1273344 + }, + { + "epoch": 0.02, + "learning_rate": 2.914509851195292e-05, + "loss": 3.5134, + "step": 1273856 + }, + { + "epoch": 0.02, + "learning_rate": 2.9136728943246137e-05, + "loss": 3.5356, + "step": 1274368 + }, + { + "epoch": 0.02, + "learning_rate": 2.9128342995735614e-05, + "loss": 3.5115, + "step": 1274880 + }, + { + "epoch": 0.02, + "learning_rate": 2.9119957048225094e-05, + "loss": 3.5188, + "step": 1275392 + }, + { + "epoch": 0.02, + "learning_rate": 2.9111571100714574e-05, + "loss": 3.5209, + "step": 1275904 + }, + { + "epoch": 0.02, + "learning_rate": 2.910320153200779e-05, + "loss": 3.5234, + "step": 1276416 + }, + { + "epoch": 0.02, + "learning_rate": 2.9094815584497266e-05, + "loss": 3.5119, + "step": 1276928 + }, + { + "epoch": 0.02, + "learning_rate": 2.9086429636986746e-05, + "loss": 3.5164, + "step": 1277440 + }, + { + "epoch": 0.02, + "learning_rate": 2.9078043689476226e-05, + "loss": 3.5121, + "step": 1277952 + }, + { + "epoch": 0.02, + "learning_rate": 2.9069674120769435e-05, + "loss": 3.523, + "step": 1278464 + }, + { + "epoch": 0.02, + "learning_rate": 2.9061288173258915e-05, + "loss": 3.5211, + "step": 1278976 + }, + { + "epoch": 0.02, + "learning_rate": 2.9052902225748395e-05, + "loss": 3.5198, + "step": 1279488 + }, + { + "epoch": 0.02, + "learning_rate": 2.9044516278237875e-05, + "loss": 3.5287, + "step": 1280000 + }, + { + "epoch": 0.02, + "learning_rate": 2.9036146709531088e-05, + "loss": 3.534, + "step": 1280512 + }, + { + "epoch": 0.02, + "learning_rate": 2.9027760762020568e-05, + "loss": 3.5275, + "step": 1281024 + }, + { + "epoch": 0.02, + "learning_rate": 2.9019374814510048e-05, + "loss": 3.5209, + "step": 1281536 + }, + { + "epoch": 0.02, + "learning_rate": 2.9010988866999527e-05, + "loss": 3.5163, + "step": 1282048 + }, + { + "epoch": 0.02, + "learning_rate": 2.9002619298292737e-05, + "loss": 3.5129, + "step": 1282560 + }, + { + "epoch": 0.02, + "learning_rate": 2.899423335078222e-05, + "loss": 3.5218, + "step": 1283072 + }, + { + "epoch": 0.02, + "learning_rate": 2.89858474032717e-05, + "loss": 3.5176, + "step": 1283584 + }, + { + "epoch": 0.02, + "learning_rate": 2.897746145576118e-05, + "loss": 3.5158, + "step": 1284096 + }, + { + "epoch": 0.02, + "learning_rate": 2.896909188705439e-05, + "loss": 3.5205, + "step": 1284608 + }, + { + "epoch": 0.02, + "learning_rate": 2.896070593954387e-05, + "loss": 3.5207, + "step": 1285120 + }, + { + "epoch": 0.02, + "learning_rate": 2.895231999203335e-05, + "loss": 3.5224, + "step": 1285632 + }, + { + "epoch": 0.02, + "learning_rate": 2.894393404452283e-05, + "loss": 3.52, + "step": 1286144 + }, + { + "epoch": 0.02, + "learning_rate": 2.893556447581604e-05, + "loss": 3.517, + "step": 1286656 + }, + { + "epoch": 0.02, + "learning_rate": 2.892717852830552e-05, + "loss": 3.5137, + "step": 1287168 + }, + { + "epoch": 0.02, + "learning_rate": 2.8918792580795e-05, + "loss": 3.5268, + "step": 1287680 + }, + { + "epoch": 0.02, + "learning_rate": 2.891040663328448e-05, + "loss": 3.5334, + "step": 1288192 + }, + { + "epoch": 0.02, + "learning_rate": 2.890203706457769e-05, + "loss": 3.53, + "step": 1288704 + }, + { + "epoch": 0.02, + "learning_rate": 2.8893651117067174e-05, + "loss": 3.509, + "step": 1289216 + }, + { + "epoch": 0.02, + "learning_rate": 2.8885265169556654e-05, + "loss": 3.5192, + "step": 1289728 + }, + { + "epoch": 0.02, + "learning_rate": 2.8876879222046133e-05, + "loss": 3.5232, + "step": 1290240 + }, + { + "epoch": 0.02, + "learning_rate": 2.8868509653339343e-05, + "loss": 3.5252, + "step": 1290752 + }, + { + "epoch": 0.02, + "learning_rate": 2.8860123705828823e-05, + "loss": 3.5189, + "step": 1291264 + }, + { + "epoch": 0.02, + "learning_rate": 2.8851737758318302e-05, + "loss": 3.5347, + "step": 1291776 + }, + { + "epoch": 0.02, + "learning_rate": 2.8843351810807782e-05, + "loss": 3.518, + "step": 1292288 + }, + { + "epoch": 0.02, + "learning_rate": 2.8834982242100995e-05, + "loss": 3.5369, + "step": 1292800 + }, + { + "epoch": 0.02, + "learning_rate": 2.8826596294590475e-05, + "loss": 3.517, + "step": 1293312 + }, + { + "epoch": 0.02, + "learning_rate": 2.8818210347079955e-05, + "loss": 3.5301, + "step": 1293824 + }, + { + "epoch": 0.02, + "learning_rate": 2.8809824399569435e-05, + "loss": 3.5157, + "step": 1294336 + }, + { + "epoch": 0.02, + "learning_rate": 2.8801454830862644e-05, + "loss": 3.5112, + "step": 1294848 + }, + { + "epoch": 0.02, + "learning_rate": 2.8793085262155856e-05, + "loss": 3.5295, + "step": 1295360 + }, + { + "epoch": 0.02, + "learning_rate": 2.8784699314645336e-05, + "loss": 3.5129, + "step": 1295872 + }, + { + "epoch": 0.02, + "learning_rate": 2.8776313367134816e-05, + "loss": 3.5215, + "step": 1296384 + }, + { + "epoch": 0.02, + "learning_rate": 2.8767927419624296e-05, + "loss": 3.5156, + "step": 1296896 + }, + { + "epoch": 0.02, + "learning_rate": 2.8759541472113776e-05, + "loss": 3.5166, + "step": 1297408 + }, + { + "epoch": 0.03, + "eval_loss": 3.8516039848327637, + "eval_runtime": 418.9851, + "eval_samples_per_second": 910.751, + "eval_steps_per_second": 28.462, + "step": 1297430 + }, + { + "epoch": 1.0, + "learning_rate": 2.8751155524603256e-05, + "loss": 3.5192, + "step": 1297920 + }, + { + "epoch": 1.0, + "learning_rate": 2.8742769577092736e-05, + "loss": 3.5184, + "step": 1298432 + }, + { + "epoch": 1.0, + "learning_rate": 2.8734383629582216e-05, + "loss": 3.5259, + "step": 1298944 + }, + { + "epoch": 1.0, + "learning_rate": 2.872601406087543e-05, + "loss": 3.5221, + "step": 1299456 + }, + { + "epoch": 1.0, + "learning_rate": 2.871762811336491e-05, + "loss": 3.534, + "step": 1299968 + }, + { + "epoch": 1.0, + "learning_rate": 2.870924216585439e-05, + "loss": 3.5151, + "step": 1300480 + }, + { + "epoch": 1.0, + "learning_rate": 2.8700872597147598e-05, + "loss": 3.5168, + "step": 1300992 + }, + { + "epoch": 1.0, + "learning_rate": 2.869248664963708e-05, + "loss": 3.5107, + "step": 1301504 + }, + { + "epoch": 1.0, + "learning_rate": 2.868410070212656e-05, + "loss": 3.5218, + "step": 1302016 + }, + { + "epoch": 1.0, + "learning_rate": 2.867571475461604e-05, + "loss": 3.5198, + "step": 1302528 + }, + { + "epoch": 1.0, + "learning_rate": 2.866734518590925e-05, + "loss": 3.5159, + "step": 1303040 + }, + { + "epoch": 1.0, + "learning_rate": 2.865895923839873e-05, + "loss": 3.5194, + "step": 1303552 + }, + { + "epoch": 1.0, + "learning_rate": 2.865057329088821e-05, + "loss": 3.5026, + "step": 1304064 + }, + { + "epoch": 1.0, + "learning_rate": 2.864218734337769e-05, + "loss": 3.5138, + "step": 1304576 + }, + { + "epoch": 1.0, + "learning_rate": 2.8633817774670902e-05, + "loss": 3.5088, + "step": 1305088 + }, + { + "epoch": 1.0, + "learning_rate": 2.8625431827160382e-05, + "loss": 3.5095, + "step": 1305600 + }, + { + "epoch": 1.0, + "learning_rate": 2.8617045879649862e-05, + "loss": 3.5107, + "step": 1306112 + }, + { + "epoch": 1.0, + "learning_rate": 2.8608659932139342e-05, + "loss": 3.5126, + "step": 1306624 + }, + { + "epoch": 1.0, + "learning_rate": 2.860029036343255e-05, + "loss": 3.5108, + "step": 1307136 + }, + { + "epoch": 1.0, + "learning_rate": 2.859190441592203e-05, + "loss": 3.5361, + "step": 1307648 + }, + { + "epoch": 1.0, + "learning_rate": 2.8583518468411515e-05, + "loss": 3.5139, + "step": 1308160 + }, + { + "epoch": 1.0, + "learning_rate": 2.8575132520900994e-05, + "loss": 3.5187, + "step": 1308672 + }, + { + "epoch": 1.0, + "learning_rate": 2.8566762952194204e-05, + "loss": 3.5153, + "step": 1309184 + }, + { + "epoch": 1.0, + "learning_rate": 2.8558377004683684e-05, + "loss": 3.5248, + "step": 1309696 + }, + { + "epoch": 1.0, + "learning_rate": 2.8549991057173163e-05, + "loss": 3.5173, + "step": 1310208 + }, + { + "epoch": 1.0, + "learning_rate": 2.8541605109662643e-05, + "loss": 3.5219, + "step": 1310720 + }, + { + "epoch": 1.0, + "learning_rate": 2.8533235540955856e-05, + "loss": 3.5107, + "step": 1311232 + }, + { + "epoch": 1.0, + "learning_rate": 2.8524849593445336e-05, + "loss": 3.5161, + "step": 1311744 + }, + { + "epoch": 1.0, + "learning_rate": 2.8516463645934816e-05, + "loss": 3.5061, + "step": 1312256 + }, + { + "epoch": 1.01, + "learning_rate": 2.8508077698424296e-05, + "loss": 3.518, + "step": 1312768 + }, + { + "epoch": 1.01, + "learning_rate": 2.8499708129717505e-05, + "loss": 3.5208, + "step": 1313280 + }, + { + "epoch": 1.01, + "learning_rate": 2.8491322182206985e-05, + "loss": 3.5171, + "step": 1313792 + }, + { + "epoch": 1.01, + "learning_rate": 2.8482936234696468e-05, + "loss": 3.5236, + "step": 1314304 + }, + { + "epoch": 1.01, + "learning_rate": 2.8474550287185948e-05, + "loss": 3.5164, + "step": 1314816 + }, + { + "epoch": 1.01, + "learning_rate": 2.8466180718479157e-05, + "loss": 3.5183, + "step": 1315328 + }, + { + "epoch": 1.01, + "learning_rate": 2.8457794770968637e-05, + "loss": 3.5211, + "step": 1315840 + }, + { + "epoch": 1.01, + "learning_rate": 2.8449408823458117e-05, + "loss": 3.5099, + "step": 1316352 + }, + { + "epoch": 1.01, + "learning_rate": 2.8441022875947597e-05, + "loss": 3.5107, + "step": 1316864 + }, + { + "epoch": 1.01, + "learning_rate": 2.843265330724081e-05, + "loss": 3.5022, + "step": 1317376 + }, + { + "epoch": 1.01, + "learning_rate": 2.842426735973029e-05, + "loss": 3.507, + "step": 1317888 + }, + { + "epoch": 1.01, + "learning_rate": 2.841588141221977e-05, + "loss": 3.5121, + "step": 1318400 + }, + { + "epoch": 1.01, + "learning_rate": 2.840749546470925e-05, + "loss": 3.5226, + "step": 1318912 + }, + { + "epoch": 1.01, + "learning_rate": 2.839912589600246e-05, + "loss": 3.5143, + "step": 1319424 + }, + { + "epoch": 1.01, + "learning_rate": 2.839073994849194e-05, + "loss": 3.5096, + "step": 1319936 + }, + { + "epoch": 1.01, + "learning_rate": 2.8382354000981422e-05, + "loss": 3.5168, + "step": 1320448 + }, + { + "epoch": 1.01, + "learning_rate": 2.8373968053470902e-05, + "loss": 3.512, + "step": 1320960 + }, + { + "epoch": 1.01, + "learning_rate": 2.836559848476411e-05, + "loss": 3.5088, + "step": 1321472 + }, + { + "epoch": 1.01, + "learning_rate": 2.835721253725359e-05, + "loss": 3.5002, + "step": 1321984 + }, + { + "epoch": 1.01, + "learning_rate": 2.834882658974307e-05, + "loss": 3.5036, + "step": 1322496 + }, + { + "epoch": 1.01, + "learning_rate": 2.834044064223255e-05, + "loss": 3.5224, + "step": 1323008 + }, + { + "epoch": 1.01, + "learning_rate": 2.8332071073525763e-05, + "loss": 3.5193, + "step": 1323520 + }, + { + "epoch": 1.01, + "learning_rate": 2.8323685126015243e-05, + "loss": 3.5076, + "step": 1324032 + }, + { + "epoch": 1.01, + "learning_rate": 2.8315299178504723e-05, + "loss": 3.5108, + "step": 1324544 + }, + { + "epoch": 1.01, + "learning_rate": 2.8306913230994203e-05, + "loss": 3.5158, + "step": 1325056 + }, + { + "epoch": 1.01, + "learning_rate": 2.8298543662287412e-05, + "loss": 3.4996, + "step": 1325568 + }, + { + "epoch": 1.01, + "learning_rate": 2.8290157714776892e-05, + "loss": 3.5202, + "step": 1326080 + }, + { + "epoch": 1.01, + "learning_rate": 2.8281771767266376e-05, + "loss": 3.5045, + "step": 1326592 + }, + { + "epoch": 1.01, + "learning_rate": 2.8273385819755855e-05, + "loss": 3.5222, + "step": 1327104 + }, + { + "epoch": 1.01, + "learning_rate": 2.8265016251049065e-05, + "loss": 3.5191, + "step": 1327616 + }, + { + "epoch": 1.01, + "learning_rate": 2.8256630303538545e-05, + "loss": 3.5061, + "step": 1328128 + }, + { + "epoch": 1.01, + "learning_rate": 2.8248244356028024e-05, + "loss": 3.5043, + "step": 1328640 + }, + { + "epoch": 1.01, + "learning_rate": 2.8239858408517504e-05, + "loss": 3.5201, + "step": 1329152 + }, + { + "epoch": 1.01, + "learning_rate": 2.8231488839810717e-05, + "loss": 3.4946, + "step": 1329664 + }, + { + "epoch": 1.01, + "learning_rate": 2.8223102892300197e-05, + "loss": 3.5023, + "step": 1330176 + }, + { + "epoch": 1.01, + "learning_rate": 2.8214716944789677e-05, + "loss": 3.5193, + "step": 1330688 + }, + { + "epoch": 1.01, + "learning_rate": 2.8206330997279157e-05, + "loss": 3.5098, + "step": 1331200 + }, + { + "epoch": 1.01, + "learning_rate": 2.8197961428572366e-05, + "loss": 3.5067, + "step": 1331712 + }, + { + "epoch": 1.01, + "learning_rate": 2.8189575481061846e-05, + "loss": 3.4936, + "step": 1332224 + }, + { + "epoch": 1.01, + "learning_rate": 2.818118953355133e-05, + "loss": 3.5064, + "step": 1332736 + }, + { + "epoch": 1.01, + "learning_rate": 2.817280358604081e-05, + "loss": 3.5018, + "step": 1333248 + }, + { + "epoch": 1.01, + "learning_rate": 2.8164434017334018e-05, + "loss": 3.5138, + "step": 1333760 + }, + { + "epoch": 1.01, + "learning_rate": 2.8156048069823498e-05, + "loss": 3.506, + "step": 1334272 + }, + { + "epoch": 1.01, + "learning_rate": 2.8147662122312978e-05, + "loss": 3.5173, + "step": 1334784 + }, + { + "epoch": 1.01, + "learning_rate": 2.8139276174802458e-05, + "loss": 3.5138, + "step": 1335296 + }, + { + "epoch": 1.01, + "learning_rate": 2.813090660609567e-05, + "loss": 3.5179, + "step": 1335808 + }, + { + "epoch": 1.01, + "learning_rate": 2.812252065858515e-05, + "loss": 3.5065, + "step": 1336320 + }, + { + "epoch": 1.01, + "learning_rate": 2.811413471107463e-05, + "loss": 3.5113, + "step": 1336832 + }, + { + "epoch": 1.01, + "learning_rate": 2.810574876356411e-05, + "loss": 3.5111, + "step": 1337344 + }, + { + "epoch": 1.01, + "learning_rate": 2.809737919485732e-05, + "loss": 3.5094, + "step": 1337856 + }, + { + "epoch": 1.01, + "learning_rate": 2.80889932473468e-05, + "loss": 3.5119, + "step": 1338368 + }, + { + "epoch": 1.01, + "learning_rate": 2.8080607299836283e-05, + "loss": 3.5073, + "step": 1338880 + }, + { + "epoch": 1.01, + "learning_rate": 2.8072221352325756e-05, + "loss": 3.5143, + "step": 1339392 + }, + { + "epoch": 1.01, + "learning_rate": 2.8063851783618972e-05, + "loss": 3.5055, + "step": 1339904 + }, + { + "epoch": 1.01, + "learning_rate": 2.8055465836108452e-05, + "loss": 3.4956, + "step": 1340416 + }, + { + "epoch": 1.01, + "learning_rate": 2.8047079888597932e-05, + "loss": 3.5025, + "step": 1340928 + }, + { + "epoch": 1.01, + "learning_rate": 2.803869394108741e-05, + "loss": 3.5088, + "step": 1341440 + }, + { + "epoch": 1.01, + "learning_rate": 2.8030324372380624e-05, + "loss": 3.5144, + "step": 1341952 + }, + { + "epoch": 1.01, + "learning_rate": 2.8021938424870104e-05, + "loss": 3.5087, + "step": 1342464 + }, + { + "epoch": 1.01, + "learning_rate": 2.8013552477359584e-05, + "loss": 3.5082, + "step": 1342976 + }, + { + "epoch": 1.02, + "learning_rate": 2.8005182908652793e-05, + "loss": 3.5035, + "step": 1343488 + }, + { + "epoch": 1.02, + "learning_rate": 2.7996796961142273e-05, + "loss": 3.4965, + "step": 1344000 + }, + { + "epoch": 1.02, + "learning_rate": 2.7988411013631753e-05, + "loss": 3.5001, + "step": 1344512 + }, + { + "epoch": 1.02, + "learning_rate": 2.798002506612123e-05, + "loss": 3.5093, + "step": 1345024 + }, + { + "epoch": 1.02, + "learning_rate": 2.7971655497414446e-05, + "loss": 3.5115, + "step": 1345536 + }, + { + "epoch": 1.02, + "learning_rate": 2.7963269549903926e-05, + "loss": 3.5167, + "step": 1346048 + }, + { + "epoch": 1.02, + "learning_rate": 2.7954883602393406e-05, + "loss": 3.512, + "step": 1346560 + }, + { + "epoch": 1.02, + "learning_rate": 2.7946497654882882e-05, + "loss": 3.5021, + "step": 1347072 + }, + { + "epoch": 1.02, + "learning_rate": 2.7938128086176098e-05, + "loss": 3.5049, + "step": 1347584 + }, + { + "epoch": 1.02, + "learning_rate": 2.7929742138665578e-05, + "loss": 3.5134, + "step": 1348096 + }, + { + "epoch": 1.02, + "learning_rate": 2.7921356191155058e-05, + "loss": 3.512, + "step": 1348608 + }, + { + "epoch": 1.02, + "learning_rate": 2.791297024364453e-05, + "loss": 3.5184, + "step": 1349120 + }, + { + "epoch": 1.02, + "learning_rate": 2.7904600674937747e-05, + "loss": 3.5047, + "step": 1349632 + }, + { + "epoch": 1.02, + "learning_rate": 2.7896214727427227e-05, + "loss": 3.4999, + "step": 1350144 + }, + { + "epoch": 1.02, + "learning_rate": 2.7887828779916703e-05, + "loss": 3.5236, + "step": 1350656 + }, + { + "epoch": 1.02, + "learning_rate": 2.7879442832406183e-05, + "loss": 3.496, + "step": 1351168 + }, + { + "epoch": 1.02, + "learning_rate": 2.78710732636994e-05, + "loss": 3.5069, + "step": 1351680 + }, + { + "epoch": 1.02, + "learning_rate": 2.786268731618888e-05, + "loss": 3.5058, + "step": 1352192 + }, + { + "epoch": 1.02, + "learning_rate": 2.7854301368678352e-05, + "loss": 3.5108, + "step": 1352704 + }, + { + "epoch": 1.02, + "learning_rate": 2.7845915421167836e-05, + "loss": 3.498, + "step": 1353216 + }, + { + "epoch": 1.02, + "learning_rate": 2.783754585246105e-05, + "loss": 3.5057, + "step": 1353728 + }, + { + "epoch": 1.02, + "learning_rate": 2.782915990495053e-05, + "loss": 3.496, + "step": 1354240 + }, + { + "epoch": 1.02, + "learning_rate": 2.7820773957440005e-05, + "loss": 3.5069, + "step": 1354752 + }, + { + "epoch": 1.02, + "learning_rate": 2.7812388009929485e-05, + "loss": 3.5088, + "step": 1355264 + }, + { + "epoch": 1.02, + "learning_rate": 2.78040184412227e-05, + "loss": 3.5024, + "step": 1355776 + }, + { + "epoch": 1.02, + "learning_rate": 2.7795632493712177e-05, + "loss": 3.5148, + "step": 1356288 + }, + { + "epoch": 1.02, + "learning_rate": 2.7787246546201657e-05, + "loss": 3.5221, + "step": 1356800 + }, + { + "epoch": 1.02, + "learning_rate": 2.7778860598691137e-05, + "loss": 3.5102, + "step": 1357312 + }, + { + "epoch": 1.02, + "learning_rate": 2.7770491029984353e-05, + "loss": 3.5077, + "step": 1357824 + }, + { + "epoch": 1.02, + "learning_rate": 2.7762105082473826e-05, + "loss": 3.5023, + "step": 1358336 + }, + { + "epoch": 1.02, + "learning_rate": 2.7753719134963306e-05, + "loss": 3.5013, + "step": 1358848 + }, + { + "epoch": 1.02, + "learning_rate": 2.774533318745279e-05, + "loss": 3.5024, + "step": 1359360 + }, + { + "epoch": 1.02, + "learning_rate": 2.7736963618746002e-05, + "loss": 3.5098, + "step": 1359872 + }, + { + "epoch": 1.02, + "learning_rate": 2.772857767123548e-05, + "loss": 3.5021, + "step": 1360384 + }, + { + "epoch": 1.02, + "learning_rate": 2.772019172372496e-05, + "loss": 3.5043, + "step": 1360896 + }, + { + "epoch": 1.02, + "learning_rate": 2.771180577621444e-05, + "loss": 3.5098, + "step": 1361408 + }, + { + "epoch": 1.02, + "learning_rate": 2.770343620750765e-05, + "loss": 3.5111, + "step": 1361920 + }, + { + "epoch": 1.02, + "learning_rate": 2.769505025999713e-05, + "loss": 3.5015, + "step": 1362432 + }, + { + "epoch": 1.02, + "learning_rate": 2.768666431248661e-05, + "loss": 3.502, + "step": 1362944 + }, + { + "epoch": 1.02, + "learning_rate": 2.767827836497609e-05, + "loss": 3.5081, + "step": 1363456 + }, + { + "epoch": 1.02, + "learning_rate": 2.76699087962693e-05, + "loss": 3.506, + "step": 1363968 + }, + { + "epoch": 1.02, + "learning_rate": 2.766152284875878e-05, + "loss": 3.5207, + "step": 1364480 + }, + { + "epoch": 1.02, + "learning_rate": 2.765313690124826e-05, + "loss": 3.5175, + "step": 1364992 + }, + { + "epoch": 1.02, + "learning_rate": 2.764475095373774e-05, + "loss": 3.4986, + "step": 1365504 + }, + { + "epoch": 1.02, + "learning_rate": 2.7636381385030952e-05, + "loss": 3.5071, + "step": 1366016 + }, + { + "epoch": 1.02, + "learning_rate": 2.7627995437520432e-05, + "loss": 3.5089, + "step": 1366528 + }, + { + "epoch": 1.02, + "learning_rate": 2.7619609490009912e-05, + "loss": 3.5085, + "step": 1367040 + }, + { + "epoch": 1.02, + "learning_rate": 2.7611223542499392e-05, + "loss": 3.5083, + "step": 1367552 + }, + { + "epoch": 1.02, + "learning_rate": 2.76028539737926e-05, + "loss": 3.5161, + "step": 1368064 + }, + { + "epoch": 1.02, + "learning_rate": 2.7594468026282085e-05, + "loss": 3.5072, + "step": 1368576 + }, + { + "epoch": 1.02, + "learning_rate": 2.7586082078771564e-05, + "loss": 3.5225, + "step": 1369088 + }, + { + "epoch": 1.02, + "learning_rate": 2.7577696131261044e-05, + "loss": 3.504, + "step": 1369600 + }, + { + "epoch": 1.02, + "learning_rate": 2.7569326562554254e-05, + "loss": 3.5157, + "step": 1370112 + }, + { + "epoch": 1.02, + "learning_rate": 2.7560940615043733e-05, + "loss": 3.5082, + "step": 1370624 + }, + { + "epoch": 1.02, + "learning_rate": 2.7552554667533213e-05, + "loss": 3.4991, + "step": 1371136 + }, + { + "epoch": 1.02, + "learning_rate": 2.7544185098826426e-05, + "loss": 3.5129, + "step": 1371648 + }, + { + "epoch": 1.02, + "learning_rate": 2.7535799151315906e-05, + "loss": 3.5039, + "step": 1372160 + }, + { + "epoch": 1.02, + "learning_rate": 2.7527413203805386e-05, + "loss": 3.5061, + "step": 1372672 + }, + { + "epoch": 1.02, + "learning_rate": 2.7519027256294866e-05, + "loss": 3.5015, + "step": 1373184 + }, + { + "epoch": 1.02, + "learning_rate": 2.7510641308784346e-05, + "loss": 3.5037, + "step": 1373696 + }, + { + "epoch": 1.03, + "eval_loss": 3.853032350540161, + "eval_runtime": 402.8239, + "eval_samples_per_second": 947.29, + "eval_steps_per_second": 29.604, + "step": 1373750 + }, + { + "epoch": 0.0, + "learning_rate": 2.7502255361273826e-05, + "loss": 3.5066, + "step": 1374208 + }, + { + "epoch": 0.0, + "learning_rate": 2.7493869413763306e-05, + "loss": 3.5019, + "step": 1374720 + }, + { + "epoch": 0.0, + "learning_rate": 2.7485483466252786e-05, + "loss": 3.5141, + "step": 1375232 + }, + { + "epoch": 0.0, + "learning_rate": 2.747709751874227e-05, + "loss": 3.5069, + "step": 1375744 + }, + { + "epoch": 0.0, + "learning_rate": 2.7468727950035478e-05, + "loss": 3.5235, + "step": 1376256 + }, + { + "epoch": 0.0, + "learning_rate": 2.7460342002524958e-05, + "loss": 3.5009, + "step": 1376768 + }, + { + "epoch": 0.0, + "learning_rate": 2.7451956055014438e-05, + "loss": 3.5068, + "step": 1377280 + }, + { + "epoch": 0.0, + "learning_rate": 2.7443586486307647e-05, + "loss": 3.4927, + "step": 1377792 + }, + { + "epoch": 0.0, + "learning_rate": 2.743520053879713e-05, + "loss": 3.5122, + "step": 1378304 + }, + { + "epoch": 0.0, + "learning_rate": 2.742681459128661e-05, + "loss": 3.5042, + "step": 1378816 + }, + { + "epoch": 0.0, + "learning_rate": 2.741842864377609e-05, + "loss": 3.4991, + "step": 1379328 + }, + { + "epoch": 0.0, + "learning_rate": 2.741004269626557e-05, + "loss": 3.516, + "step": 1379840 + }, + { + "epoch": 0.0, + "learning_rate": 2.740167312755878e-05, + "loss": 3.488, + "step": 1380352 + }, + { + "epoch": 0.0, + "learning_rate": 2.739328718004826e-05, + "loss": 3.5038, + "step": 1380864 + }, + { + "epoch": 0.0, + "learning_rate": 2.738490123253774e-05, + "loss": 3.4914, + "step": 1381376 + }, + { + "epoch": 0.0, + "learning_rate": 2.7376515285027223e-05, + "loss": 3.4987, + "step": 1381888 + }, + { + "epoch": 0.0, + "learning_rate": 2.7368145716320432e-05, + "loss": 3.4961, + "step": 1382400 + }, + { + "epoch": 0.0, + "learning_rate": 2.735975976880991e-05, + "loss": 3.5027, + "step": 1382912 + }, + { + "epoch": 0.0, + "learning_rate": 2.735137382129939e-05, + "loss": 3.4975, + "step": 1383424 + }, + { + "epoch": 0.0, + "learning_rate": 2.73430042525926e-05, + "loss": 3.522, + "step": 1383936 + }, + { + "epoch": 0.0, + "learning_rate": 2.7334618305082084e-05, + "loss": 3.5007, + "step": 1384448 + }, + { + "epoch": 0.0, + "learning_rate": 2.7326232357571564e-05, + "loss": 3.5048, + "step": 1384960 + }, + { + "epoch": 0.0, + "learning_rate": 2.7317846410061044e-05, + "loss": 3.5015, + "step": 1385472 + }, + { + "epoch": 0.0, + "learning_rate": 2.7309476841354253e-05, + "loss": 3.5146, + "step": 1385984 + }, + { + "epoch": 0.0, + "learning_rate": 2.7301090893843733e-05, + "loss": 3.5024, + "step": 1386496 + }, + { + "epoch": 0.0, + "learning_rate": 2.7292704946333213e-05, + "loss": 3.512, + "step": 1387008 + }, + { + "epoch": 0.0, + "learning_rate": 2.7284318998822693e-05, + "loss": 3.4932, + "step": 1387520 + }, + { + "epoch": 0.0, + "learning_rate": 2.7275949430115905e-05, + "loss": 3.5022, + "step": 1388032 + }, + { + "epoch": 0.0, + "learning_rate": 2.7267563482605385e-05, + "loss": 3.4945, + "step": 1388544 + }, + { + "epoch": 0.01, + "learning_rate": 2.7259177535094865e-05, + "loss": 3.5059, + "step": 1389056 + }, + { + "epoch": 0.01, + "learning_rate": 2.7250791587584345e-05, + "loss": 3.5072, + "step": 1389568 + }, + { + "epoch": 0.01, + "learning_rate": 2.7242422018877554e-05, + "loss": 3.5034, + "step": 1390080 + }, + { + "epoch": 0.01, + "learning_rate": 2.7234036071367038e-05, + "loss": 3.5149, + "step": 1390592 + }, + { + "epoch": 0.01, + "learning_rate": 2.7225650123856518e-05, + "loss": 3.5002, + "step": 1391104 + }, + { + "epoch": 0.01, + "learning_rate": 2.7217264176345998e-05, + "loss": 3.502, + "step": 1391616 + }, + { + "epoch": 0.01, + "learning_rate": 2.7208894607639207e-05, + "loss": 3.5072, + "step": 1392128 + }, + { + "epoch": 0.01, + "learning_rate": 2.7200508660128687e-05, + "loss": 3.4988, + "step": 1392640 + }, + { + "epoch": 0.01, + "learning_rate": 2.7192122712618167e-05, + "loss": 3.495, + "step": 1393152 + }, + { + "epoch": 0.01, + "learning_rate": 2.7183736765107647e-05, + "loss": 3.4908, + "step": 1393664 + }, + { + "epoch": 0.01, + "learning_rate": 2.717536719640086e-05, + "loss": 3.493, + "step": 1394176 + }, + { + "epoch": 0.01, + "learning_rate": 2.716698124889034e-05, + "loss": 3.4969, + "step": 1394688 + }, + { + "epoch": 0.01, + "learning_rate": 2.715859530137982e-05, + "loss": 3.509, + "step": 1395200 + }, + { + "epoch": 0.01, + "learning_rate": 2.71502093538693e-05, + "loss": 3.5044, + "step": 1395712 + }, + { + "epoch": 0.01, + "learning_rate": 2.7141839785162508e-05, + "loss": 3.4928, + "step": 1396224 + }, + { + "epoch": 0.01, + "learning_rate": 2.713345383765199e-05, + "loss": 3.5067, + "step": 1396736 + }, + { + "epoch": 0.01, + "learning_rate": 2.712506789014147e-05, + "loss": 3.499, + "step": 1397248 + }, + { + "epoch": 0.01, + "learning_rate": 2.711668194263095e-05, + "loss": 3.4937, + "step": 1397760 + }, + { + "epoch": 0.01, + "learning_rate": 2.710831237392416e-05, + "loss": 3.492, + "step": 1398272 + }, + { + "epoch": 0.01, + "learning_rate": 2.709992642641364e-05, + "loss": 3.4851, + "step": 1398784 + }, + { + "epoch": 0.01, + "learning_rate": 2.709154047890312e-05, + "loss": 3.51, + "step": 1399296 + }, + { + "epoch": 0.01, + "learning_rate": 2.70831545313926e-05, + "loss": 3.507, + "step": 1399808 + }, + { + "epoch": 0.01, + "learning_rate": 2.7074784962685813e-05, + "loss": 3.497, + "step": 1400320 + }, + { + "epoch": 0.01, + "learning_rate": 2.7066399015175293e-05, + "loss": 3.4943, + "step": 1400832 + }, + { + "epoch": 0.01, + "learning_rate": 2.7058013067664773e-05, + "loss": 3.5044, + "step": 1401344 + }, + { + "epoch": 0.01, + "learning_rate": 2.7049627120154253e-05, + "loss": 3.4854, + "step": 1401856 + }, + { + "epoch": 0.01, + "learning_rate": 2.7041257551447462e-05, + "loss": 3.5066, + "step": 1402368 + }, + { + "epoch": 0.01, + "learning_rate": 2.7032871603936945e-05, + "loss": 3.4916, + "step": 1402880 + }, + { + "epoch": 0.01, + "learning_rate": 2.7024485656426425e-05, + "loss": 3.5081, + "step": 1403392 + }, + { + "epoch": 0.01, + "learning_rate": 2.7016099708915905e-05, + "loss": 3.5073, + "step": 1403904 + }, + { + "epoch": 0.01, + "learning_rate": 2.7007730140209114e-05, + "loss": 3.495, + "step": 1404416 + }, + { + "epoch": 0.01, + "learning_rate": 2.6999344192698594e-05, + "loss": 3.4883, + "step": 1404928 + }, + { + "epoch": 0.01, + "learning_rate": 2.6990958245188074e-05, + "loss": 3.5075, + "step": 1405440 + }, + { + "epoch": 0.01, + "learning_rate": 2.698257229767755e-05, + "loss": 3.4824, + "step": 1405952 + }, + { + "epoch": 0.01, + "learning_rate": 2.6974202728970766e-05, + "loss": 3.4952, + "step": 1406464 + }, + { + "epoch": 0.01, + "learning_rate": 2.6965816781460246e-05, + "loss": 3.5034, + "step": 1406976 + }, + { + "epoch": 0.01, + "learning_rate": 2.6957430833949726e-05, + "loss": 3.5006, + "step": 1407488 + }, + { + "epoch": 0.01, + "learning_rate": 2.69490448864392e-05, + "loss": 3.4917, + "step": 1408000 + }, + { + "epoch": 0.01, + "learning_rate": 2.6940675317732415e-05, + "loss": 3.4817, + "step": 1408512 + }, + { + "epoch": 0.01, + "learning_rate": 2.6932289370221895e-05, + "loss": 3.4895, + "step": 1409024 + }, + { + "epoch": 0.01, + "learning_rate": 2.692390342271138e-05, + "loss": 3.4895, + "step": 1409536 + }, + { + "epoch": 0.01, + "learning_rate": 2.6915517475200852e-05, + "loss": 3.5032, + "step": 1410048 + }, + { + "epoch": 0.01, + "learning_rate": 2.6907147906494068e-05, + "loss": 3.4893, + "step": 1410560 + }, + { + "epoch": 0.01, + "learning_rate": 2.6898761958983548e-05, + "loss": 3.5052, + "step": 1411072 + }, + { + "epoch": 0.01, + "learning_rate": 2.6890376011473024e-05, + "loss": 3.5015, + "step": 1411584 + }, + { + "epoch": 0.01, + "learning_rate": 2.6881990063962504e-05, + "loss": 3.5044, + "step": 1412096 + }, + { + "epoch": 0.01, + "learning_rate": 2.687362049525572e-05, + "loss": 3.4938, + "step": 1412608 + }, + { + "epoch": 0.01, + "learning_rate": 2.686525092654893e-05, + "loss": 3.4979, + "step": 1413120 + }, + { + "epoch": 0.01, + "learning_rate": 2.685686497903841e-05, + "loss": 3.4997, + "step": 1413632 + }, + { + "epoch": 0.01, + "learning_rate": 2.684847903152789e-05, + "loss": 3.4939, + "step": 1414144 + }, + { + "epoch": 0.01, + "learning_rate": 2.684009308401737e-05, + "loss": 3.501, + "step": 1414656 + }, + { + "epoch": 0.01, + "learning_rate": 2.683170713650685e-05, + "loss": 3.4959, + "step": 1415168 + }, + { + "epoch": 0.01, + "learning_rate": 2.6823321188996326e-05, + "loss": 3.4965, + "step": 1415680 + }, + { + "epoch": 0.01, + "learning_rate": 2.6814935241485806e-05, + "loss": 3.4957, + "step": 1416192 + }, + { + "epoch": 0.01, + "learning_rate": 2.6806549293975285e-05, + "loss": 3.4818, + "step": 1416704 + }, + { + "epoch": 0.01, + "learning_rate": 2.6798179725268498e-05, + "loss": 3.4935, + "step": 1417216 + }, + { + "epoch": 0.01, + "learning_rate": 2.6789793777757978e-05, + "loss": 3.4925, + "step": 1417728 + }, + { + "epoch": 0.01, + "learning_rate": 2.6781407830247458e-05, + "loss": 3.5026, + "step": 1418240 + }, + { + "epoch": 0.01, + "learning_rate": 2.6773021882736938e-05, + "loss": 3.4956, + "step": 1418752 + }, + { + "epoch": 0.01, + "learning_rate": 2.6764652314030147e-05, + "loss": 3.4954, + "step": 1419264 + }, + { + "epoch": 0.02, + "learning_rate": 2.6756266366519627e-05, + "loss": 3.4902, + "step": 1419776 + }, + { + "epoch": 0.02, + "learning_rate": 2.6747880419009107e-05, + "loss": 3.4843, + "step": 1420288 + }, + { + "epoch": 0.02, + "learning_rate": 2.6739494471498587e-05, + "loss": 3.4876, + "step": 1420800 + }, + { + "epoch": 0.02, + "learning_rate": 2.67311249027918e-05, + "loss": 3.4924, + "step": 1421312 + }, + { + "epoch": 0.02, + "learning_rate": 2.672273895528128e-05, + "loss": 3.5028, + "step": 1421824 + }, + { + "epoch": 0.02, + "learning_rate": 2.671435300777076e-05, + "loss": 3.5034, + "step": 1422336 + }, + { + "epoch": 0.02, + "learning_rate": 2.670596706026024e-05, + "loss": 3.4959, + "step": 1422848 + }, + { + "epoch": 0.02, + "learning_rate": 2.6697597491553448e-05, + "loss": 3.4927, + "step": 1423360 + }, + { + "epoch": 0.02, + "learning_rate": 2.668921154404293e-05, + "loss": 3.4933, + "step": 1423872 + }, + { + "epoch": 0.02, + "learning_rate": 2.668082559653241e-05, + "loss": 3.4975, + "step": 1424384 + }, + { + "epoch": 0.02, + "learning_rate": 2.667243964902189e-05, + "loss": 3.5023, + "step": 1424896 + }, + { + "epoch": 0.02, + "learning_rate": 2.66640700803151e-05, + "loss": 3.5039, + "step": 1425408 + }, + { + "epoch": 0.02, + "learning_rate": 2.665568413280458e-05, + "loss": 3.4924, + "step": 1425920 + }, + { + "epoch": 0.02, + "learning_rate": 2.664729818529406e-05, + "loss": 3.4853, + "step": 1426432 + }, + { + "epoch": 0.02, + "learning_rate": 2.663891223778354e-05, + "loss": 3.5088, + "step": 1426944 + }, + { + "epoch": 0.02, + "learning_rate": 2.6630542669076753e-05, + "loss": 3.4856, + "step": 1427456 + }, + { + "epoch": 0.02, + "learning_rate": 2.6622156721566233e-05, + "loss": 3.4971, + "step": 1427968 + }, + { + "epoch": 0.02, + "learning_rate": 2.6613770774055713e-05, + "loss": 3.4907, + "step": 1428480 + }, + { + "epoch": 0.02, + "learning_rate": 2.6605384826545193e-05, + "loss": 3.4946, + "step": 1428992 + }, + { + "epoch": 0.02, + "learning_rate": 2.6597015257838402e-05, + "loss": 3.4873, + "step": 1429504 + }, + { + "epoch": 0.02, + "learning_rate": 2.6588629310327885e-05, + "loss": 3.4952, + "step": 1430016 + }, + { + "epoch": 0.02, + "learning_rate": 2.6580243362817365e-05, + "loss": 3.4826, + "step": 1430528 + }, + { + "epoch": 0.02, + "learning_rate": 2.6571857415306845e-05, + "loss": 3.4905, + "step": 1431040 + }, + { + "epoch": 0.02, + "learning_rate": 2.6563487846600054e-05, + "loss": 3.4989, + "step": 1431552 + }, + { + "epoch": 0.02, + "learning_rate": 2.6555101899089534e-05, + "loss": 3.4857, + "step": 1432064 + }, + { + "epoch": 0.02, + "learning_rate": 2.6546715951579014e-05, + "loss": 3.5053, + "step": 1432576 + }, + { + "epoch": 0.02, + "learning_rate": 2.6538330004068494e-05, + "loss": 3.5068, + "step": 1433088 + }, + { + "epoch": 0.02, + "learning_rate": 2.6529960435361707e-05, + "loss": 3.4996, + "step": 1433600 + }, + { + "epoch": 0.02, + "learning_rate": 2.6521574487851187e-05, + "loss": 3.4934, + "step": 1434112 + }, + { + "epoch": 0.02, + "learning_rate": 2.6513188540340667e-05, + "loss": 3.4911, + "step": 1434624 + }, + { + "epoch": 0.02, + "learning_rate": 2.6504802592830146e-05, + "loss": 3.491, + "step": 1435136 + }, + { + "epoch": 0.02, + "learning_rate": 2.6496433024123356e-05, + "loss": 3.4845, + "step": 1435648 + }, + { + "epoch": 0.02, + "learning_rate": 2.648804707661284e-05, + "loss": 3.5005, + "step": 1436160 + }, + { + "epoch": 0.02, + "learning_rate": 2.647966112910232e-05, + "loss": 3.4872, + "step": 1436672 + }, + { + "epoch": 0.02, + "learning_rate": 2.64712751815918e-05, + "loss": 3.4936, + "step": 1437184 + }, + { + "epoch": 0.02, + "learning_rate": 2.6462905612885008e-05, + "loss": 3.498, + "step": 1437696 + }, + { + "epoch": 0.02, + "learning_rate": 2.6454519665374488e-05, + "loss": 3.4972, + "step": 1438208 + }, + { + "epoch": 0.02, + "learning_rate": 2.6446133717863968e-05, + "loss": 3.487, + "step": 1438720 + }, + { + "epoch": 0.02, + "learning_rate": 2.6437747770353448e-05, + "loss": 3.49, + "step": 1439232 + }, + { + "epoch": 0.02, + "learning_rate": 2.642937820164666e-05, + "loss": 3.4974, + "step": 1439744 + }, + { + "epoch": 0.02, + "learning_rate": 2.642099225413614e-05, + "loss": 3.4932, + "step": 1440256 + }, + { + "epoch": 0.02, + "learning_rate": 2.641260630662562e-05, + "loss": 3.5008, + "step": 1440768 + }, + { + "epoch": 0.02, + "learning_rate": 2.64042203591151e-05, + "loss": 3.5071, + "step": 1441280 + }, + { + "epoch": 0.02, + "learning_rate": 2.639585079040831e-05, + "loss": 3.4845, + "step": 1441792 + }, + { + "epoch": 0.02, + "learning_rate": 2.6387464842897793e-05, + "loss": 3.4917, + "step": 1442304 + }, + { + "epoch": 0.02, + "learning_rate": 2.6379078895387273e-05, + "loss": 3.4997, + "step": 1442816 + }, + { + "epoch": 0.02, + "learning_rate": 2.6370692947876753e-05, + "loss": 3.4952, + "step": 1443328 + }, + { + "epoch": 0.02, + "learning_rate": 2.636232337916996e-05, + "loss": 3.4945, + "step": 1443840 + }, + { + "epoch": 0.02, + "learning_rate": 2.635393743165944e-05, + "loss": 3.5049, + "step": 1444352 + }, + { + "epoch": 0.02, + "learning_rate": 2.634555148414892e-05, + "loss": 3.494, + "step": 1444864 + }, + { + "epoch": 0.02, + "learning_rate": 2.63371655366384e-05, + "loss": 3.5098, + "step": 1445376 + }, + { + "epoch": 0.02, + "learning_rate": 2.6328795967931614e-05, + "loss": 3.4924, + "step": 1445888 + }, + { + "epoch": 0.02, + "learning_rate": 2.6320410020421094e-05, + "loss": 3.4988, + "step": 1446400 + }, + { + "epoch": 0.02, + "learning_rate": 2.6312024072910574e-05, + "loss": 3.4952, + "step": 1446912 + }, + { + "epoch": 0.02, + "learning_rate": 2.6303638125400054e-05, + "loss": 3.488, + "step": 1447424 + }, + { + "epoch": 0.02, + "learning_rate": 2.6295284935496995e-05, + "loss": 3.4969, + "step": 1447936 + }, + { + "epoch": 0.02, + "learning_rate": 2.6286898987986475e-05, + "loss": 3.4922, + "step": 1448448 + }, + { + "epoch": 0.02, + "learning_rate": 2.6278513040475955e-05, + "loss": 3.4902, + "step": 1448960 + }, + { + "epoch": 0.02, + "learning_rate": 2.6270127092965435e-05, + "loss": 3.4896, + "step": 1449472 + }, + { + "epoch": 0.02, + "learning_rate": 2.6261741145454915e-05, + "loss": 3.4876, + "step": 1449984 + }, + { + "epoch": 0.03, + "eval_loss": 3.854522943496704, + "eval_runtime": 301.8826, + "eval_samples_per_second": 1264.038, + "eval_steps_per_second": 39.502, + "step": 1450070 + }, + { + "epoch": 1.0, + "learning_rate": 2.6253355197944395e-05, + "loss": 3.497, + "step": 1450496 + }, + { + "epoch": 1.0, + "learning_rate": 2.6244969250433875e-05, + "loss": 3.4902, + "step": 1451008 + }, + { + "epoch": 1.0, + "learning_rate": 2.6236583302923355e-05, + "loss": 3.5033, + "step": 1451520 + }, + { + "epoch": 1.0, + "learning_rate": 2.6228213734216568e-05, + "loss": 3.4923, + "step": 1452032 + }, + { + "epoch": 1.0, + "learning_rate": 2.6219827786706048e-05, + "loss": 3.5141, + "step": 1452544 + }, + { + "epoch": 1.0, + "learning_rate": 2.6211441839195528e-05, + "loss": 3.4876, + "step": 1453056 + }, + { + "epoch": 1.0, + "learning_rate": 2.6203055891685007e-05, + "loss": 3.4925, + "step": 1453568 + }, + { + "epoch": 1.0, + "learning_rate": 2.6194686322978217e-05, + "loss": 3.4804, + "step": 1454080 + }, + { + "epoch": 1.0, + "learning_rate": 2.61863003754677e-05, + "loss": 3.4943, + "step": 1454592 + }, + { + "epoch": 1.0, + "learning_rate": 2.617791442795718e-05, + "loss": 3.4936, + "step": 1455104 + }, + { + "epoch": 1.0, + "learning_rate": 2.616952848044666e-05, + "loss": 3.4859, + "step": 1455616 + }, + { + "epoch": 1.0, + "learning_rate": 2.616115891173987e-05, + "loss": 3.4989, + "step": 1456128 + }, + { + "epoch": 1.0, + "learning_rate": 2.615277296422935e-05, + "loss": 3.4774, + "step": 1456640 + }, + { + "epoch": 1.0, + "learning_rate": 2.614438701671883e-05, + "loss": 3.4892, + "step": 1457152 + }, + { + "epoch": 1.0, + "learning_rate": 2.613600106920831e-05, + "loss": 3.4868, + "step": 1457664 + }, + { + "epoch": 1.0, + "learning_rate": 2.612763150050152e-05, + "loss": 3.4838, + "step": 1458176 + }, + { + "epoch": 1.0, + "learning_rate": 2.6119245552991e-05, + "loss": 3.4818, + "step": 1458688 + }, + { + "epoch": 1.0, + "learning_rate": 2.611085960548048e-05, + "loss": 3.4893, + "step": 1459200 + }, + { + "epoch": 1.0, + "learning_rate": 2.610247365796996e-05, + "loss": 3.4874, + "step": 1459712 + }, + { + "epoch": 1.0, + "learning_rate": 2.609410408926317e-05, + "loss": 3.5073, + "step": 1460224 + }, + { + "epoch": 1.0, + "learning_rate": 2.6085718141752654e-05, + "loss": 3.4876, + "step": 1460736 + }, + { + "epoch": 1.0, + "learning_rate": 2.6077332194242134e-05, + "loss": 3.4979, + "step": 1461248 + }, + { + "epoch": 1.0, + "learning_rate": 2.6068946246731614e-05, + "loss": 3.4894, + "step": 1461760 + }, + { + "epoch": 1.0, + "learning_rate": 2.6060576678024823e-05, + "loss": 3.4989, + "step": 1462272 + }, + { + "epoch": 1.0, + "learning_rate": 2.6052190730514303e-05, + "loss": 3.4895, + "step": 1462784 + }, + { + "epoch": 1.0, + "learning_rate": 2.6043804783003783e-05, + "loss": 3.4966, + "step": 1463296 + }, + { + "epoch": 1.0, + "learning_rate": 2.6035418835493262e-05, + "loss": 3.488, + "step": 1463808 + }, + { + "epoch": 1.0, + "learning_rate": 2.6027049266786475e-05, + "loss": 3.4868, + "step": 1464320 + }, + { + "epoch": 1.0, + "learning_rate": 2.6018663319275955e-05, + "loss": 3.4785, + "step": 1464832 + }, + { + "epoch": 1.01, + "learning_rate": 2.6010277371765435e-05, + "loss": 3.493, + "step": 1465344 + }, + { + "epoch": 1.01, + "learning_rate": 2.6001891424254915e-05, + "loss": 3.4974, + "step": 1465856 + }, + { + "epoch": 1.01, + "learning_rate": 2.5993521855548124e-05, + "loss": 3.4901, + "step": 1466368 + }, + { + "epoch": 1.01, + "learning_rate": 2.5985135908037604e-05, + "loss": 3.5042, + "step": 1466880 + }, + { + "epoch": 1.01, + "learning_rate": 2.5976749960527087e-05, + "loss": 3.489, + "step": 1467392 + }, + { + "epoch": 1.01, + "learning_rate": 2.5968364013016567e-05, + "loss": 3.4842, + "step": 1467904 + }, + { + "epoch": 1.01, + "learning_rate": 2.5959994444309776e-05, + "loss": 3.4948, + "step": 1468416 + }, + { + "epoch": 1.01, + "learning_rate": 2.5951608496799256e-05, + "loss": 3.4881, + "step": 1468928 + }, + { + "epoch": 1.01, + "learning_rate": 2.5943222549288736e-05, + "loss": 3.4795, + "step": 1469440 + }, + { + "epoch": 1.01, + "learning_rate": 2.5934836601778216e-05, + "loss": 3.4805, + "step": 1469952 + }, + { + "epoch": 1.01, + "learning_rate": 2.592646703307143e-05, + "loss": 3.4789, + "step": 1470464 + }, + { + "epoch": 1.01, + "learning_rate": 2.591808108556091e-05, + "loss": 3.4903, + "step": 1470976 + }, + { + "epoch": 1.01, + "learning_rate": 2.590969513805039e-05, + "loss": 3.4917, + "step": 1471488 + }, + { + "epoch": 1.01, + "learning_rate": 2.590130919053987e-05, + "loss": 3.4905, + "step": 1472000 + }, + { + "epoch": 1.01, + "learning_rate": 2.5892939621833078e-05, + "loss": 3.4789, + "step": 1472512 + }, + { + "epoch": 1.01, + "learning_rate": 2.5884553674322558e-05, + "loss": 3.4941, + "step": 1473024 + }, + { + "epoch": 1.01, + "learning_rate": 2.587616772681204e-05, + "loss": 3.4863, + "step": 1473536 + }, + { + "epoch": 1.01, + "learning_rate": 2.586778177930152e-05, + "loss": 3.4843, + "step": 1474048 + }, + { + "epoch": 1.01, + "learning_rate": 2.585941221059473e-05, + "loss": 3.479, + "step": 1474560 + }, + { + "epoch": 1.01, + "learning_rate": 2.585102626308421e-05, + "loss": 3.4699, + "step": 1475072 + }, + { + "epoch": 1.01, + "learning_rate": 2.584264031557369e-05, + "loss": 3.5013, + "step": 1475584 + }, + { + "epoch": 1.01, + "learning_rate": 2.583425436806317e-05, + "loss": 3.4934, + "step": 1476096 + }, + { + "epoch": 1.01, + "learning_rate": 2.5825884799356382e-05, + "loss": 3.4837, + "step": 1476608 + }, + { + "epoch": 1.01, + "learning_rate": 2.5817498851845862e-05, + "loss": 3.4853, + "step": 1477120 + }, + { + "epoch": 1.01, + "learning_rate": 2.5809112904335342e-05, + "loss": 3.4857, + "step": 1477632 + }, + { + "epoch": 1.01, + "learning_rate": 2.5800726956824822e-05, + "loss": 3.4729, + "step": 1478144 + }, + { + "epoch": 1.01, + "learning_rate": 2.579235738811803e-05, + "loss": 3.4921, + "step": 1478656 + }, + { + "epoch": 1.01, + "learning_rate": 2.578397144060751e-05, + "loss": 3.4823, + "step": 1479168 + }, + { + "epoch": 1.01, + "learning_rate": 2.5775585493096995e-05, + "loss": 3.4876, + "step": 1479680 + }, + { + "epoch": 1.01, + "learning_rate": 2.5767199545586468e-05, + "loss": 3.5027, + "step": 1480192 + }, + { + "epoch": 1.01, + "learning_rate": 2.5758829976879684e-05, + "loss": 3.482, + "step": 1480704 + }, + { + "epoch": 1.01, + "learning_rate": 2.5750444029369164e-05, + "loss": 3.474, + "step": 1481216 + }, + { + "epoch": 1.01, + "learning_rate": 2.5742058081858644e-05, + "loss": 3.4989, + "step": 1481728 + }, + { + "epoch": 1.01, + "learning_rate": 2.573367213434812e-05, + "loss": 3.4687, + "step": 1482240 + }, + { + "epoch": 1.01, + "learning_rate": 2.5725302565641336e-05, + "loss": 3.4781, + "step": 1482752 + }, + { + "epoch": 1.01, + "learning_rate": 2.5716916618130816e-05, + "loss": 3.4942, + "step": 1483264 + }, + { + "epoch": 1.01, + "learning_rate": 2.570853067062029e-05, + "loss": 3.4855, + "step": 1483776 + }, + { + "epoch": 1.01, + "learning_rate": 2.570014472310977e-05, + "loss": 3.481, + "step": 1484288 + }, + { + "epoch": 1.01, + "learning_rate": 2.5691775154402985e-05, + "loss": 3.4729, + "step": 1484800 + }, + { + "epoch": 1.01, + "learning_rate": 2.5683389206892465e-05, + "loss": 3.4728, + "step": 1485312 + }, + { + "epoch": 1.01, + "learning_rate": 2.567500325938194e-05, + "loss": 3.4749, + "step": 1485824 + }, + { + "epoch": 1.01, + "learning_rate": 2.5666633690675157e-05, + "loss": 3.4952, + "step": 1486336 + }, + { + "epoch": 1.01, + "learning_rate": 2.5658247743164637e-05, + "loss": 3.4706, + "step": 1486848 + }, + { + "epoch": 1.01, + "learning_rate": 2.5649861795654117e-05, + "loss": 3.4927, + "step": 1487360 + }, + { + "epoch": 1.01, + "learning_rate": 2.5641475848143594e-05, + "loss": 3.4875, + "step": 1487872 + }, + { + "epoch": 1.01, + "learning_rate": 2.563310627943681e-05, + "loss": 3.4953, + "step": 1488384 + }, + { + "epoch": 1.01, + "learning_rate": 2.562472033192629e-05, + "loss": 3.4813, + "step": 1488896 + }, + { + "epoch": 1.01, + "learning_rate": 2.5616334384415763e-05, + "loss": 3.4798, + "step": 1489408 + }, + { + "epoch": 1.01, + "learning_rate": 2.5607948436905243e-05, + "loss": 3.4899, + "step": 1489920 + }, + { + "epoch": 1.01, + "learning_rate": 2.559957886819846e-05, + "loss": 3.4797, + "step": 1490432 + }, + { + "epoch": 1.01, + "learning_rate": 2.559119292068794e-05, + "loss": 3.4929, + "step": 1490944 + }, + { + "epoch": 1.01, + "learning_rate": 2.5582806973177415e-05, + "loss": 3.482, + "step": 1491456 + }, + { + "epoch": 1.01, + "learning_rate": 2.5574421025666895e-05, + "loss": 3.4806, + "step": 1491968 + }, + { + "epoch": 1.01, + "learning_rate": 2.556605145696011e-05, + "loss": 3.4841, + "step": 1492480 + }, + { + "epoch": 1.01, + "learning_rate": 2.555766550944959e-05, + "loss": 3.4665, + "step": 1492992 + }, + { + "epoch": 1.01, + "learning_rate": 2.5549279561939064e-05, + "loss": 3.4808, + "step": 1493504 + }, + { + "epoch": 1.01, + "learning_rate": 2.5540893614428547e-05, + "loss": 3.4831, + "step": 1494016 + }, + { + "epoch": 1.01, + "learning_rate": 2.5532524045721763e-05, + "loss": 3.4887, + "step": 1494528 + }, + { + "epoch": 1.01, + "learning_rate": 2.5524138098211237e-05, + "loss": 3.4804, + "step": 1495040 + }, + { + "epoch": 1.01, + "learning_rate": 2.5515752150700716e-05, + "loss": 3.4845, + "step": 1495552 + }, + { + "epoch": 1.02, + "learning_rate": 2.5507366203190196e-05, + "loss": 3.4764, + "step": 1496064 + }, + { + "epoch": 1.02, + "learning_rate": 2.5498996634483412e-05, + "loss": 3.4732, + "step": 1496576 + }, + { + "epoch": 1.02, + "learning_rate": 2.549061068697289e-05, + "loss": 3.4734, + "step": 1497088 + }, + { + "epoch": 1.02, + "learning_rate": 2.548222473946237e-05, + "loss": 3.4782, + "step": 1497600 + }, + { + "epoch": 1.02, + "learning_rate": 2.547383879195185e-05, + "loss": 3.4948, + "step": 1498112 + }, + { + "epoch": 1.02, + "learning_rate": 2.5465469223245065e-05, + "loss": 3.4917, + "step": 1498624 + }, + { + "epoch": 1.02, + "learning_rate": 2.5457083275734538e-05, + "loss": 3.4847, + "step": 1499136 + }, + { + "epoch": 1.02, + "learning_rate": 2.5448697328224018e-05, + "loss": 3.4742, + "step": 1499648 + }, + { + "epoch": 1.02, + "learning_rate": 2.54403113807135e-05, + "loss": 3.4788, + "step": 1500160 + }, + { + "epoch": 1.02, + "learning_rate": 2.543194181200671e-05, + "loss": 3.4868, + "step": 1500672 + }, + { + "epoch": 1.02, + "learning_rate": 2.542355586449619e-05, + "loss": 3.4843, + "step": 1501184 + }, + { + "epoch": 1.02, + "learning_rate": 2.541516991698567e-05, + "loss": 3.4924, + "step": 1501696 + }, + { + "epoch": 1.02, + "learning_rate": 2.540678396947515e-05, + "loss": 3.4815, + "step": 1502208 + }, + { + "epoch": 1.02, + "learning_rate": 2.5398414400768363e-05, + "loss": 3.4738, + "step": 1502720 + }, + { + "epoch": 1.02, + "learning_rate": 2.5390028453257843e-05, + "loss": 3.4968, + "step": 1503232 + }, + { + "epoch": 1.02, + "learning_rate": 2.5381642505747322e-05, + "loss": 3.4729, + "step": 1503744 + }, + { + "epoch": 1.02, + "learning_rate": 2.5373256558236802e-05, + "loss": 3.4824, + "step": 1504256 + }, + { + "epoch": 1.02, + "learning_rate": 2.536488698953001e-05, + "loss": 3.4742, + "step": 1504768 + }, + { + "epoch": 1.02, + "learning_rate": 2.535650104201949e-05, + "loss": 3.4868, + "step": 1505280 + }, + { + "epoch": 1.02, + "learning_rate": 2.534811509450897e-05, + "loss": 3.4749, + "step": 1505792 + }, + { + "epoch": 1.02, + "learning_rate": 2.5339729146998455e-05, + "loss": 3.4824, + "step": 1506304 + }, + { + "epoch": 1.02, + "learning_rate": 2.5331359578291664e-05, + "loss": 3.4767, + "step": 1506816 + }, + { + "epoch": 1.02, + "learning_rate": 2.5322973630781144e-05, + "loss": 3.474, + "step": 1507328 + }, + { + "epoch": 1.02, + "learning_rate": 2.5314587683270624e-05, + "loss": 3.486, + "step": 1507840 + }, + { + "epoch": 1.02, + "learning_rate": 2.5306201735760104e-05, + "loss": 3.4763, + "step": 1508352 + }, + { + "epoch": 1.02, + "learning_rate": 2.5297832167053316e-05, + "loss": 3.4909, + "step": 1508864 + }, + { + "epoch": 1.02, + "learning_rate": 2.5289446219542796e-05, + "loss": 3.496, + "step": 1509376 + }, + { + "epoch": 1.02, + "learning_rate": 2.5281060272032276e-05, + "loss": 3.4867, + "step": 1509888 + }, + { + "epoch": 1.02, + "learning_rate": 2.5272674324521756e-05, + "loss": 3.4783, + "step": 1510400 + }, + { + "epoch": 1.02, + "learning_rate": 2.5264304755814965e-05, + "loss": 3.4789, + "step": 1510912 + }, + { + "epoch": 1.02, + "learning_rate": 2.5255918808304445e-05, + "loss": 3.4757, + "step": 1511424 + }, + { + "epoch": 1.02, + "learning_rate": 2.5247532860793925e-05, + "loss": 3.4779, + "step": 1511936 + }, + { + "epoch": 1.02, + "learning_rate": 2.523914691328341e-05, + "loss": 3.4858, + "step": 1512448 + }, + { + "epoch": 1.02, + "learning_rate": 2.5230777344576618e-05, + "loss": 3.47, + "step": 1512960 + }, + { + "epoch": 1.02, + "learning_rate": 2.5222391397066098e-05, + "loss": 3.4852, + "step": 1513472 + }, + { + "epoch": 1.02, + "learning_rate": 2.5214005449555577e-05, + "loss": 3.4821, + "step": 1513984 + }, + { + "epoch": 1.02, + "learning_rate": 2.5205619502045057e-05, + "loss": 3.4879, + "step": 1514496 + }, + { + "epoch": 1.02, + "learning_rate": 2.519724993333827e-05, + "loss": 3.4788, + "step": 1515008 + }, + { + "epoch": 1.02, + "learning_rate": 2.518886398582775e-05, + "loss": 3.48, + "step": 1515520 + }, + { + "epoch": 1.02, + "learning_rate": 2.518047803831723e-05, + "loss": 3.4826, + "step": 1516032 + }, + { + "epoch": 1.02, + "learning_rate": 2.517209209080671e-05, + "loss": 3.4859, + "step": 1516544 + }, + { + "epoch": 1.02, + "learning_rate": 2.516372252209992e-05, + "loss": 3.4854, + "step": 1517056 + }, + { + "epoch": 1.02, + "learning_rate": 2.51553365745894e-05, + "loss": 3.4953, + "step": 1517568 + }, + { + "epoch": 1.02, + "learning_rate": 2.514695062707888e-05, + "loss": 3.4712, + "step": 1518080 + }, + { + "epoch": 1.02, + "learning_rate": 2.5138564679568362e-05, + "loss": 3.4825, + "step": 1518592 + }, + { + "epoch": 1.02, + "learning_rate": 2.513019511086157e-05, + "loss": 3.4839, + "step": 1519104 + }, + { + "epoch": 1.02, + "learning_rate": 2.512180916335105e-05, + "loss": 3.4814, + "step": 1519616 + }, + { + "epoch": 1.02, + "learning_rate": 2.511342321584053e-05, + "loss": 3.4821, + "step": 1520128 + }, + { + "epoch": 1.02, + "learning_rate": 2.510503726833001e-05, + "loss": 3.4942, + "step": 1520640 + }, + { + "epoch": 1.02, + "learning_rate": 2.5096667699623224e-05, + "loss": 3.4801, + "step": 1521152 + }, + { + "epoch": 1.02, + "learning_rate": 2.5088281752112704e-05, + "loss": 3.4985, + "step": 1521664 + }, + { + "epoch": 1.02, + "learning_rate": 2.5079895804602183e-05, + "loss": 3.4797, + "step": 1522176 + }, + { + "epoch": 1.02, + "learning_rate": 2.5071509857091663e-05, + "loss": 3.4863, + "step": 1522688 + }, + { + "epoch": 1.02, + "learning_rate": 2.5063140288384873e-05, + "loss": 3.48, + "step": 1523200 + }, + { + "epoch": 1.02, + "learning_rate": 2.5054754340874352e-05, + "loss": 3.4798, + "step": 1523712 + }, + { + "epoch": 1.02, + "learning_rate": 2.5046384772167565e-05, + "loss": 3.4805, + "step": 1524224 + }, + { + "epoch": 1.02, + "learning_rate": 2.5037998824657045e-05, + "loss": 3.4838, + "step": 1524736 + }, + { + "epoch": 1.02, + "learning_rate": 2.5029612877146525e-05, + "loss": 3.4787, + "step": 1525248 + }, + { + "epoch": 1.02, + "learning_rate": 2.5021226929636005e-05, + "loss": 3.4741, + "step": 1525760 + }, + { + "epoch": 1.02, + "learning_rate": 2.5012840982125485e-05, + "loss": 3.478, + "step": 1526272 + }, + { + "epoch": 1.03, + "eval_loss": 3.856762409210205, + "eval_runtime": 302.7182, + "eval_samples_per_second": 1260.549, + "eval_steps_per_second": 39.393, + "step": 1526390 + }, + { + "epoch": 0.0, + "learning_rate": 2.5004455034614965e-05, + "loss": 3.4829, + "step": 1526784 + }, + { + "epoch": 0.0, + "learning_rate": 2.4996069087104445e-05, + "loss": 3.4767, + "step": 1527296 + }, + { + "epoch": 0.0, + "learning_rate": 2.4987683139593925e-05, + "loss": 3.4873, + "step": 1527808 + }, + { + "epoch": 0.0, + "learning_rate": 2.4979297192083405e-05, + "loss": 3.4814, + "step": 1528320 + }, + { + "epoch": 0.0, + "learning_rate": 2.4970927623376617e-05, + "loss": 3.4977, + "step": 1528832 + }, + { + "epoch": 0.0, + "learning_rate": 2.4962541675866097e-05, + "loss": 3.4806, + "step": 1529344 + }, + { + "epoch": 0.0, + "learning_rate": 2.4954155728355577e-05, + "loss": 3.4806, + "step": 1529856 + }, + { + "epoch": 0.0, + "learning_rate": 2.4945769780845054e-05, + "loss": 3.4657, + "step": 1530368 + }, + { + "epoch": 0.0, + "learning_rate": 2.4937400212138266e-05, + "loss": 3.4825, + "step": 1530880 + }, + { + "epoch": 0.0, + "learning_rate": 2.492901426462775e-05, + "loss": 3.4803, + "step": 1531392 + }, + { + "epoch": 0.0, + "learning_rate": 2.4920628317117226e-05, + "loss": 3.4772, + "step": 1531904 + }, + { + "epoch": 0.0, + "learning_rate": 2.4912242369606706e-05, + "loss": 3.4823, + "step": 1532416 + }, + { + "epoch": 0.0, + "learning_rate": 2.490387280089992e-05, + "loss": 3.4667, + "step": 1532928 + }, + { + "epoch": 0.0, + "learning_rate": 2.48954868533894e-05, + "loss": 3.4763, + "step": 1533440 + }, + { + "epoch": 0.0, + "learning_rate": 2.488710090587888e-05, + "loss": 3.4723, + "step": 1533952 + }, + { + "epoch": 0.0, + "learning_rate": 2.4878714958368358e-05, + "loss": 3.4697, + "step": 1534464 + }, + { + "epoch": 0.0, + "learning_rate": 2.487034538966157e-05, + "loss": 3.4695, + "step": 1534976 + }, + { + "epoch": 0.0, + "learning_rate": 2.486195944215105e-05, + "loss": 3.4792, + "step": 1535488 + }, + { + "epoch": 0.0, + "learning_rate": 2.4853573494640527e-05, + "loss": 3.4722, + "step": 1536000 + }, + { + "epoch": 0.0, + "learning_rate": 2.4845187547130007e-05, + "loss": 3.4955, + "step": 1536512 + }, + { + "epoch": 0.0, + "learning_rate": 2.483681797842322e-05, + "loss": 3.476, + "step": 1537024 + }, + { + "epoch": 0.0, + "learning_rate": 2.48284320309127e-05, + "loss": 3.486, + "step": 1537536 + }, + { + "epoch": 0.0, + "learning_rate": 2.482004608340218e-05, + "loss": 3.4754, + "step": 1538048 + }, + { + "epoch": 0.0, + "learning_rate": 2.4811676514695392e-05, + "loss": 3.4829, + "step": 1538560 + }, + { + "epoch": 0.0, + "learning_rate": 2.4803290567184872e-05, + "loss": 3.4754, + "step": 1539072 + }, + { + "epoch": 0.0, + "learning_rate": 2.479490461967435e-05, + "loss": 3.4856, + "step": 1539584 + }, + { + "epoch": 0.0, + "learning_rate": 2.4786518672163832e-05, + "loss": 3.4732, + "step": 1540096 + }, + { + "epoch": 0.0, + "learning_rate": 2.4778149103457044e-05, + "loss": 3.4786, + "step": 1540608 + }, + { + "epoch": 0.0, + "learning_rate": 2.4769763155946524e-05, + "loss": 3.4665, + "step": 1541120 + }, + { + "epoch": 0.0, + "learning_rate": 2.4761377208436e-05, + "loss": 3.4779, + "step": 1541632 + }, + { + "epoch": 0.01, + "learning_rate": 2.475299126092548e-05, + "loss": 3.4856, + "step": 1542144 + }, + { + "epoch": 0.01, + "learning_rate": 2.4744621692218693e-05, + "loss": 3.4784, + "step": 1542656 + }, + { + "epoch": 0.01, + "learning_rate": 2.4736235744708173e-05, + "loss": 3.4889, + "step": 1543168 + }, + { + "epoch": 0.01, + "learning_rate": 2.4727849797197653e-05, + "loss": 3.476, + "step": 1543680 + }, + { + "epoch": 0.01, + "learning_rate": 2.4719463849687133e-05, + "loss": 3.4753, + "step": 1544192 + }, + { + "epoch": 0.01, + "learning_rate": 2.4711094280980346e-05, + "loss": 3.4829, + "step": 1544704 + }, + { + "epoch": 0.01, + "learning_rate": 2.4702708333469822e-05, + "loss": 3.4778, + "step": 1545216 + }, + { + "epoch": 0.01, + "learning_rate": 2.4694322385959302e-05, + "loss": 3.4661, + "step": 1545728 + }, + { + "epoch": 0.01, + "learning_rate": 2.4685936438448786e-05, + "loss": 3.4693, + "step": 1546240 + }, + { + "epoch": 0.01, + "learning_rate": 2.4677566869741998e-05, + "loss": 3.4659, + "step": 1546752 + }, + { + "epoch": 0.01, + "learning_rate": 2.4669180922231475e-05, + "loss": 3.475, + "step": 1547264 + }, + { + "epoch": 0.01, + "learning_rate": 2.4660794974720955e-05, + "loss": 3.4807, + "step": 1547776 + }, + { + "epoch": 0.01, + "learning_rate": 2.4652409027210435e-05, + "loss": 3.4798, + "step": 1548288 + }, + { + "epoch": 0.01, + "learning_rate": 2.4644039458503647e-05, + "loss": 3.4706, + "step": 1548800 + }, + { + "epoch": 0.01, + "learning_rate": 2.4635653510993127e-05, + "loss": 3.4772, + "step": 1549312 + }, + { + "epoch": 0.01, + "learning_rate": 2.4627267563482607e-05, + "loss": 3.4746, + "step": 1549824 + }, + { + "epoch": 0.01, + "learning_rate": 2.4618881615972087e-05, + "loss": 3.4727, + "step": 1550336 + }, + { + "epoch": 0.01, + "learning_rate": 2.4610512047265296e-05, + "loss": 3.4671, + "step": 1550848 + }, + { + "epoch": 0.01, + "learning_rate": 2.4602126099754776e-05, + "loss": 3.4531, + "step": 1551360 + }, + { + "epoch": 0.01, + "learning_rate": 2.4593740152244256e-05, + "loss": 3.4916, + "step": 1551872 + }, + { + "epoch": 0.01, + "learning_rate": 2.4585354204733736e-05, + "loss": 3.4767, + "step": 1552384 + }, + { + "epoch": 0.01, + "learning_rate": 2.457698463602695e-05, + "loss": 3.4769, + "step": 1552896 + }, + { + "epoch": 0.01, + "learning_rate": 2.456859868851643e-05, + "loss": 3.4741, + "step": 1553408 + }, + { + "epoch": 0.01, + "learning_rate": 2.456021274100591e-05, + "loss": 3.4721, + "step": 1553920 + }, + { + "epoch": 0.01, + "learning_rate": 2.4551826793495388e-05, + "loss": 3.4629, + "step": 1554432 + }, + { + "epoch": 0.01, + "learning_rate": 2.45434572247886e-05, + "loss": 3.4777, + "step": 1554944 + }, + { + "epoch": 0.01, + "learning_rate": 2.453507127727808e-05, + "loss": 3.4734, + "step": 1555456 + }, + { + "epoch": 0.01, + "learning_rate": 2.452668532976756e-05, + "loss": 3.4757, + "step": 1555968 + }, + { + "epoch": 0.01, + "learning_rate": 2.451829938225704e-05, + "loss": 3.4923, + "step": 1556480 + }, + { + "epoch": 0.01, + "learning_rate": 2.450992981355025e-05, + "loss": 3.4671, + "step": 1556992 + }, + { + "epoch": 0.01, + "learning_rate": 2.450154386603973e-05, + "loss": 3.4627, + "step": 1557504 + }, + { + "epoch": 0.01, + "learning_rate": 2.449315791852921e-05, + "loss": 3.4889, + "step": 1558016 + }, + { + "epoch": 0.01, + "learning_rate": 2.448477197101869e-05, + "loss": 3.4589, + "step": 1558528 + }, + { + "epoch": 0.01, + "learning_rate": 2.4476402402311902e-05, + "loss": 3.4652, + "step": 1559040 + }, + { + "epoch": 0.01, + "learning_rate": 2.4468016454801382e-05, + "loss": 3.4783, + "step": 1559552 + }, + { + "epoch": 0.01, + "learning_rate": 2.4459630507290862e-05, + "loss": 3.4731, + "step": 1560064 + }, + { + "epoch": 0.01, + "learning_rate": 2.4451244559780342e-05, + "loss": 3.4678, + "step": 1560576 + }, + { + "epoch": 0.01, + "learning_rate": 2.444287499107355e-05, + "loss": 3.4626, + "step": 1561088 + }, + { + "epoch": 0.01, + "learning_rate": 2.4434489043563034e-05, + "loss": 3.459, + "step": 1561600 + }, + { + "epoch": 0.01, + "learning_rate": 2.4426103096052514e-05, + "loss": 3.4649, + "step": 1562112 + }, + { + "epoch": 0.01, + "learning_rate": 2.4417717148541994e-05, + "loss": 3.4794, + "step": 1562624 + }, + { + "epoch": 0.01, + "learning_rate": 2.4409347579835203e-05, + "loss": 3.4618, + "step": 1563136 + }, + { + "epoch": 0.01, + "learning_rate": 2.4400961632324683e-05, + "loss": 3.4774, + "step": 1563648 + }, + { + "epoch": 0.01, + "learning_rate": 2.4392575684814163e-05, + "loss": 3.4758, + "step": 1564160 + }, + { + "epoch": 0.01, + "learning_rate": 2.4384189737303643e-05, + "loss": 3.4861, + "step": 1564672 + }, + { + "epoch": 0.01, + "learning_rate": 2.4375820168596856e-05, + "loss": 3.4691, + "step": 1565184 + }, + { + "epoch": 0.01, + "learning_rate": 2.4367434221086336e-05, + "loss": 3.4658, + "step": 1565696 + }, + { + "epoch": 0.01, + "learning_rate": 2.4359048273575816e-05, + "loss": 3.4769, + "step": 1566208 + }, + { + "epoch": 0.01, + "learning_rate": 2.4350662326065296e-05, + "loss": 3.4667, + "step": 1566720 + }, + { + "epoch": 0.01, + "learning_rate": 2.4342292757358505e-05, + "loss": 3.4842, + "step": 1567232 + }, + { + "epoch": 0.01, + "learning_rate": 2.4333906809847988e-05, + "loss": 3.4716, + "step": 1567744 + }, + { + "epoch": 0.01, + "learning_rate": 2.4325520862337468e-05, + "loss": 3.4698, + "step": 1568256 + }, + { + "epoch": 0.01, + "learning_rate": 2.4317134914826948e-05, + "loss": 3.4746, + "step": 1568768 + }, + { + "epoch": 0.01, + "learning_rate": 2.4308765346120157e-05, + "loss": 3.4564, + "step": 1569280 + }, + { + "epoch": 0.01, + "learning_rate": 2.4300379398609637e-05, + "loss": 3.464, + "step": 1569792 + }, + { + "epoch": 0.01, + "learning_rate": 2.4291993451099117e-05, + "loss": 3.4707, + "step": 1570304 + }, + { + "epoch": 0.01, + "learning_rate": 2.4283607503588597e-05, + "loss": 3.4791, + "step": 1570816 + }, + { + "epoch": 0.01, + "learning_rate": 2.427523793488181e-05, + "loss": 3.4661, + "step": 1571328 + }, + { + "epoch": 0.01, + "learning_rate": 2.426685198737129e-05, + "loss": 3.4755, + "step": 1571840 + }, + { + "epoch": 0.02, + "learning_rate": 2.425846603986077e-05, + "loss": 3.4632, + "step": 1572352 + }, + { + "epoch": 0.02, + "learning_rate": 2.4250080092350246e-05, + "loss": 3.4665, + "step": 1572864 + }, + { + "epoch": 0.02, + "learning_rate": 2.424171052364346e-05, + "loss": 3.4591, + "step": 1573376 + }, + { + "epoch": 0.02, + "learning_rate": 2.4233324576132942e-05, + "loss": 3.4678, + "step": 1573888 + }, + { + "epoch": 0.02, + "learning_rate": 2.4224938628622422e-05, + "loss": 3.4812, + "step": 1574400 + }, + { + "epoch": 0.02, + "learning_rate": 2.421656905991563e-05, + "loss": 3.4784, + "step": 1574912 + }, + { + "epoch": 0.02, + "learning_rate": 2.420818311240511e-05, + "loss": 3.4748, + "step": 1575424 + }, + { + "epoch": 0.02, + "learning_rate": 2.419979716489459e-05, + "loss": 3.4631, + "step": 1575936 + }, + { + "epoch": 0.02, + "learning_rate": 2.419141121738407e-05, + "loss": 3.4683, + "step": 1576448 + }, + { + "epoch": 0.02, + "learning_rate": 2.418302526987355e-05, + "loss": 3.4717, + "step": 1576960 + }, + { + "epoch": 0.02, + "learning_rate": 2.4174655701166763e-05, + "loss": 3.4758, + "step": 1577472 + }, + { + "epoch": 0.02, + "learning_rate": 2.4166269753656243e-05, + "loss": 3.4775, + "step": 1577984 + }, + { + "epoch": 0.02, + "learning_rate": 2.415788380614572e-05, + "loss": 3.4686, + "step": 1578496 + }, + { + "epoch": 0.02, + "learning_rate": 2.41494978586352e-05, + "loss": 3.463, + "step": 1579008 + }, + { + "epoch": 0.02, + "learning_rate": 2.4141128289928412e-05, + "loss": 3.4825, + "step": 1579520 + }, + { + "epoch": 0.02, + "learning_rate": 2.4132742342417895e-05, + "loss": 3.4613, + "step": 1580032 + }, + { + "epoch": 0.02, + "learning_rate": 2.4124356394907372e-05, + "loss": 3.4713, + "step": 1580544 + }, + { + "epoch": 0.02, + "learning_rate": 2.4115970447396852e-05, + "loss": 3.4645, + "step": 1581056 + }, + { + "epoch": 0.02, + "learning_rate": 2.4107600878690064e-05, + "loss": 3.4735, + "step": 1581568 + }, + { + "epoch": 0.02, + "learning_rate": 2.409921493117954e-05, + "loss": 3.459, + "step": 1582080 + }, + { + "epoch": 0.02, + "learning_rate": 2.409082898366902e-05, + "loss": 3.4736, + "step": 1582592 + }, + { + "epoch": 0.02, + "learning_rate": 2.4082443036158504e-05, + "loss": 3.4606, + "step": 1583104 + }, + { + "epoch": 0.02, + "learning_rate": 2.4074073467451717e-05, + "loss": 3.4659, + "step": 1583616 + }, + { + "epoch": 0.02, + "learning_rate": 2.4065687519941193e-05, + "loss": 3.4726, + "step": 1584128 + }, + { + "epoch": 0.02, + "learning_rate": 2.4057301572430673e-05, + "loss": 3.4673, + "step": 1584640 + }, + { + "epoch": 0.02, + "learning_rate": 2.4048915624920153e-05, + "loss": 3.4739, + "step": 1585152 + }, + { + "epoch": 0.02, + "learning_rate": 2.4040546056213366e-05, + "loss": 3.4837, + "step": 1585664 + }, + { + "epoch": 0.02, + "learning_rate": 2.4032160108702846e-05, + "loss": 3.4719, + "step": 1586176 + }, + { + "epoch": 0.02, + "learning_rate": 2.4023774161192326e-05, + "loss": 3.4722, + "step": 1586688 + }, + { + "epoch": 0.02, + "learning_rate": 2.4015388213681806e-05, + "loss": 3.4679, + "step": 1587200 + }, + { + "epoch": 0.02, + "learning_rate": 2.4007018644975015e-05, + "loss": 3.4645, + "step": 1587712 + }, + { + "epoch": 0.02, + "learning_rate": 2.3998632697464495e-05, + "loss": 3.4621, + "step": 1588224 + }, + { + "epoch": 0.02, + "learning_rate": 2.3990246749953975e-05, + "loss": 3.4766, + "step": 1588736 + }, + { + "epoch": 0.02, + "learning_rate": 2.398187718124719e-05, + "loss": 3.4558, + "step": 1589248 + }, + { + "epoch": 0.02, + "learning_rate": 2.3973491233736667e-05, + "loss": 3.4721, + "step": 1589760 + }, + { + "epoch": 0.02, + "learning_rate": 2.3965105286226147e-05, + "loss": 3.4682, + "step": 1590272 + }, + { + "epoch": 0.02, + "learning_rate": 2.3956719338715627e-05, + "loss": 3.4771, + "step": 1590784 + }, + { + "epoch": 0.02, + "learning_rate": 2.394834977000884e-05, + "loss": 3.4649, + "step": 1591296 + }, + { + "epoch": 0.02, + "learning_rate": 2.393996382249832e-05, + "loss": 3.469, + "step": 1591808 + }, + { + "epoch": 0.02, + "learning_rate": 2.39315778749878e-05, + "loss": 3.4658, + "step": 1592320 + }, + { + "epoch": 0.02, + "learning_rate": 2.392319192747728e-05, + "loss": 3.4757, + "step": 1592832 + }, + { + "epoch": 0.02, + "learning_rate": 2.391482235877049e-05, + "loss": 3.4739, + "step": 1593344 + }, + { + "epoch": 0.02, + "learning_rate": 2.390643641125997e-05, + "loss": 3.4837, + "step": 1593856 + }, + { + "epoch": 0.02, + "learning_rate": 2.389805046374945e-05, + "loss": 3.4608, + "step": 1594368 + }, + { + "epoch": 0.02, + "learning_rate": 2.3889664516238928e-05, + "loss": 3.4716, + "step": 1594880 + }, + { + "epoch": 0.02, + "learning_rate": 2.388129494753214e-05, + "loss": 3.4762, + "step": 1595392 + }, + { + "epoch": 0.02, + "learning_rate": 2.387290900002162e-05, + "loss": 3.4705, + "step": 1595904 + }, + { + "epoch": 0.02, + "learning_rate": 2.38645230525111e-05, + "loss": 3.4701, + "step": 1596416 + }, + { + "epoch": 0.02, + "learning_rate": 2.385613710500058e-05, + "loss": 3.477, + "step": 1596928 + }, + { + "epoch": 0.02, + "learning_rate": 2.384776753629379e-05, + "loss": 3.4701, + "step": 1597440 + }, + { + "epoch": 0.02, + "learning_rate": 2.3839381588783273e-05, + "loss": 3.4901, + "step": 1597952 + }, + { + "epoch": 0.02, + "learning_rate": 2.3830995641272753e-05, + "loss": 3.4659, + "step": 1598464 + }, + { + "epoch": 0.02, + "learning_rate": 2.3822609693762233e-05, + "loss": 3.4736, + "step": 1598976 + }, + { + "epoch": 0.02, + "learning_rate": 2.3814240125055442e-05, + "loss": 3.4661, + "step": 1599488 + }, + { + "epoch": 0.02, + "learning_rate": 2.3805854177544922e-05, + "loss": 3.4668, + "step": 1600000 + }, + { + "epoch": 0.02, + "learning_rate": 2.3797484608838135e-05, + "loss": 3.4742, + "step": 1600512 + }, + { + "epoch": 0.02, + "learning_rate": 2.3789098661327614e-05, + "loss": 3.4654, + "step": 1601024 + }, + { + "epoch": 0.02, + "learning_rate": 2.3780712713817094e-05, + "loss": 3.4697, + "step": 1601536 + }, + { + "epoch": 0.02, + "learning_rate": 2.3772326766306574e-05, + "loss": 3.4565, + "step": 1602048 + }, + { + "epoch": 0.02, + "learning_rate": 2.3763940818796054e-05, + "loss": 3.4703, + "step": 1602560 + }, + { + "epoch": 0.03, + "eval_loss": 3.857863426208496, + "eval_runtime": 304.561, + "eval_samples_per_second": 1252.921, + "eval_steps_per_second": 39.155, + "step": 1602710 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 1.0939165831194532e+18, + "trial_name": null, + "trial_params": null +}