diff --git "a/checkpoint-1755360/trainer_state.json" "b/checkpoint-1755360/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-1755360/trainer_state.json" @@ -0,0 +1,20777 @@ +{ + "best_metric": 3.8423845767974854, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/binding-c-command/transformer/2/checkpoints/checkpoint-992160", + "epoch": 1.0250006060157382, + "eval_steps": 10, + "global_step": 1755360, + "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": 10.9766, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 6.8228, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 6.1813, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 5.9673, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 5.8024, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 5.6932, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 5.5963, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 5.5331, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 5.4421, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 5.4089, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 5.3501, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 5.3099, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989938500867749e-05, + "loss": 5.2682, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989099906116697e-05, + "loss": 5.2006, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988261311365645e-05, + "loss": 5.1813, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.987422716614593e-05, + "loss": 5.1334, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986584121863541e-05, + "loss": 5.1106, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985745527112489e-05, + "loss": 5.0804, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984906932361437e-05, + "loss": 5.0426, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.0182, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 5.0045, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.9823927859886547e-05, + "loss": 4.9756, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.9815541912376026e-05, + "loss": 4.9436, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.9807155964865506e-05, + "loss": 4.9246, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 4.9147, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790400448648195e-05, + "loss": 4.8895, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9782014501137675e-05, + "loss": 4.8614, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773628553627155e-05, + "loss": 4.8516, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 4.8314, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756856658606115e-05, + "loss": 4.8165, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748487089899324e-05, + "loss": 4.8007, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.9740101142388804e-05, + "loss": 4.788, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731715194878284e-05, + "loss": 4.7767, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.97233456261715e-05, + "loss": 4.7564, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.971495967866098e-05, + "loss": 4.754, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.970657373115046e-05, + "loss": 4.7528, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969818778363994e-05, + "loss": 4.7291, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968980183612942e-05, + "loss": 4.6918, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.96814158886189e-05, + "loss": 4.6965, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967302994110837e-05, + "loss": 4.6778, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966464399359785e-05, + "loss": 4.6813, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965627442489107e-05, + "loss": 4.6677, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964788847738054e-05, + "loss": 4.6605, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963950252987002e-05, + "loss": 4.6397, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.96311165823595e-05, + "loss": 4.6491, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962274701365272e-05, + "loss": 4.6317, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.96143610661422e-05, + "loss": 4.6303, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960597511863168e-05, + "loss": 4.6183, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.959758917112116e-05, + "loss": 4.5972, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.9589219602414374e-05, + "loss": 4.5981, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958083365490385e-05, + "loss": 4.6012, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957244770739333e-05, + "loss": 4.5797, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956406175988281e-05, + "loss": 4.5709, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.9555692191176016e-05, + "loss": 4.5617, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.9547306243665496e-05, + "loss": 4.5593, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.9538920296154976e-05, + "loss": 4.5431, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.9530534348644456e-05, + "loss": 4.5645, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.9522148401133936e-05, + "loss": 4.5313, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951376245362342e-05, + "loss": 4.5424, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.95053765061129e-05, + "loss": 4.533, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949699055860238e-05, + "loss": 4.5063, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948862098989559e-05, + "loss": 4.5142, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.948023504238507e-05, + "loss": 4.5051, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947184909487455e-05, + "loss": 4.4905, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946346314736403e-05, + "loss": 4.4835, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945509357865724e-05, + "loss": 4.4997, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944670763114672e-05, + "loss": 4.4766, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.94383216836362e-05, + "loss": 4.4716, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942993573612568e-05, + "loss": 4.4592, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.942154978861516e-05, + "loss": 4.4729, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.941318021990837e-05, + "loss": 4.4778, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.9404794272397856e-05, + "loss": 4.4629, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396408324887336e-05, + "loss": 4.4559, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388022377376816e-05, + "loss": 4.4615, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379652808670025e-05, + "loss": 4.457, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371266861159505e-05, + "loss": 4.4481, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.9362880913648985e-05, + "loss": 4.4302, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.9354494966138465e-05, + "loss": 4.4384, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.9346125397431674e-05, + "loss": 4.4257, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.9337739449921154e-05, + "loss": 4.4239, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.9329353502410634e-05, + "loss": 4.4129, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.9320967554900114e-05, + "loss": 4.4181, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.931259798619332e-05, + "loss": 4.4245, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.930421203868281e-05, + "loss": 4.4153, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.929582609117229e-05, + "loss": 4.3883, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.928744014366177e-05, + "loss": 4.3973, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.927907057495498e-05, + "loss": 4.3992, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.927068462744446e-05, + "loss": 4.3946, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.926229867993394e-05, + "loss": 4.3894, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925392911122715e-05, + "loss": 4.3856, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.924554316371663e-05, + "loss": 4.3814, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923715721620611e-05, + "loss": 4.3686, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922877126869559e-05, + "loss": 4.3744, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.922038532118507e-05, + "loss": 4.374, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921199937367455e-05, + "loss": 4.3642, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920362980496776e-05, + "loss": 4.3746, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919524385745724e-05, + "loss": 4.3525, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918685790994672e-05, + "loss": 4.3542, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.91784719624362e-05, + "loss": 4.3508, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.9170086014925676e-05, + "loss": 4.3512, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.9161700067415156e-05, + "loss": 4.3547, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.9153314119904636e-05, + "loss": 4.3397, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.9144928172394116e-05, + "loss": 4.3358, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.9136558603687325e-05, + "loss": 4.3329, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.9128172656176805e-05, + "loss": 4.3359, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.9119786708666285e-05, + "loss": 4.3184, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.91114171399595e-05, + "loss": 4.3116, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.910303119244898e-05, + "loss": 4.3205, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.909464524493846e-05, + "loss": 4.326, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908625929742794e-05, + "loss": 4.3166, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907787334991742e-05, + "loss": 4.3152, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.90694874024069e-05, + "loss": 4.3042, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906110145489638e-05, + "loss": 4.3147, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.905273188618959e-05, + "loss": 4.2992, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.904434593867907e-05, + "loss": 4.305, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903595999116855e-05, + "loss": 4.3068, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.902757404365803e-05, + "loss": 4.3051, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.901920447495124e-05, + "loss": 4.2954, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.901081852744072e-05, + "loss": 4.2938, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.90024325799302e-05, + "loss": 4.293, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.8994046632419686e-05, + "loss": 4.294, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.8985660684909166e-05, + "loss": 4.2822, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.8977274737398646e-05, + "loss": 4.2869, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968888789888125e-05, + "loss": 4.2839, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.8960519221181335e-05, + "loss": 4.2846, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.8952133273670815e-05, + "loss": 4.2676, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.8943747326160294e-05, + "loss": 4.2668, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.8935361378649774e-05, + "loss": 4.2698, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.8926991809942984e-05, + "loss": 4.2739, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.8918605862432463e-05, + "loss": 4.2631, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.8910219914921943e-05, + "loss": 4.276, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.8901833967411423e-05, + "loss": 4.2686, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.88934480199009e-05, + "loss": 4.2537, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888506207239038e-05, + "loss": 4.2592, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.88766925036836e-05, + "loss": 4.2701, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886830655617308e-05, + "loss": 4.2598, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885992060866256e-05, + "loss": 4.2564, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.885153466115204e-05, + "loss": 4.2464, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884314871364151e-05, + "loss": 4.2535, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883476276613099e-05, + "loss": 4.2591, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882637681862047e-05, + "loss": 4.2454, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.881799087110995e-05, + "loss": 4.2362, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.880962130240316e-05, + "loss": 4.2412, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.880123535489264e-05, + "loss": 4.2361, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.879286578618586e-05, + "loss": 4.233, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.878447983867534e-05, + "loss": 4.2422, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877609389116482e-05, + "loss": 4.231, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.87677079436543e-05, + "loss": 4.2325, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875932199614378e-05, + "loss": 4.2296, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.875093604863326e-05, + "loss": 4.2236, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.1937055587768555, + "eval_runtime": 307.9359, + "eval_samples_per_second": 1239.19, + "eval_steps_per_second": 38.726, + "step": 76320 + }, + { + "epoch": 1.0, + "learning_rate": 4.874255010112274e-05, + "loss": 4.2123, + "step": 76800 + }, + { + "epoch": 1.0, + "learning_rate": 4.873416415361222e-05, + "loss": 4.218, + "step": 77312 + }, + { + "epoch": 1.0, + "learning_rate": 4.8725794584905426e-05, + "loss": 4.2272, + "step": 77824 + }, + { + "epoch": 1.0, + "learning_rate": 4.8717408637394906e-05, + "loss": 4.2165, + "step": 78336 + }, + { + "epoch": 1.0, + "learning_rate": 4.8709022689884386e-05, + "loss": 4.217, + "step": 78848 + }, + { + "epoch": 1.0, + "learning_rate": 4.8700636742373866e-05, + "loss": 4.2124, + "step": 79360 + }, + { + "epoch": 1.0, + "learning_rate": 4.8692267173667075e-05, + "loss": 4.2076, + "step": 79872 + }, + { + "epoch": 1.0, + "learning_rate": 4.8683881226156555e-05, + "loss": 4.1962, + "step": 80384 + }, + { + "epoch": 1.0, + "learning_rate": 4.867551165744977e-05, + "loss": 4.2199, + "step": 80896 + }, + { + "epoch": 1.0, + "learning_rate": 4.866712570993925e-05, + "loss": 4.2037, + "step": 81408 + }, + { + "epoch": 1.0, + "learning_rate": 4.865873976242873e-05, + "loss": 4.2127, + "step": 81920 + }, + { + "epoch": 1.0, + "learning_rate": 4.865035381491821e-05, + "loss": 4.2119, + "step": 82432 + }, + { + "epoch": 1.0, + "learning_rate": 4.864198424621142e-05, + "loss": 4.1933, + "step": 82944 + }, + { + "epoch": 1.0, + "learning_rate": 4.86335982987009e-05, + "loss": 4.1923, + "step": 83456 + }, + { + "epoch": 1.0, + "learning_rate": 4.862521235119038e-05, + "loss": 4.1894, + "step": 83968 + }, + { + "epoch": 1.0, + "learning_rate": 4.861682640367986e-05, + "loss": 4.1826, + "step": 84480 + }, + { + "epoch": 1.0, + "learning_rate": 4.860844045616934e-05, + "loss": 4.1879, + "step": 84992 + }, + { + "epoch": 1.0, + "learning_rate": 4.860005450865882e-05, + "loss": 4.181, + "step": 85504 + }, + { + "epoch": 1.0, + "learning_rate": 4.85916685611483e-05, + "loss": 4.1765, + "step": 86016 + }, + { + "epoch": 1.0, + "learning_rate": 4.858328261363778e-05, + "loss": 4.1997, + "step": 86528 + }, + { + "epoch": 1.0, + "learning_rate": 4.857489666612726e-05, + "loss": 4.1823, + "step": 87040 + }, + { + "epoch": 1.0, + "learning_rate": 4.8566527097420475e-05, + "loss": 4.1752, + "step": 87552 + }, + { + "epoch": 1.0, + "learning_rate": 4.8558141149909955e-05, + "loss": 4.1722, + "step": 88064 + }, + { + "epoch": 1.0, + "learning_rate": 4.8549755202399435e-05, + "loss": 4.1875, + "step": 88576 + }, + { + "epoch": 1.0, + "learning_rate": 4.8541369254888915e-05, + "loss": 4.164, + "step": 89088 + }, + { + "epoch": 1.0, + "learning_rate": 4.8532983307378395e-05, + "loss": 4.1628, + "step": 89600 + }, + { + "epoch": 1.0, + "learning_rate": 4.8524597359867875e-05, + "loss": 4.1656, + "step": 90112 + }, + { + "epoch": 1.0, + "learning_rate": 4.8516227791161084e-05, + "loss": 4.1648, + "step": 90624 + }, + { + "epoch": 1.0, + "learning_rate": 4.8507841843650564e-05, + "loss": 4.1593, + "step": 91136 + }, + { + "epoch": 1.01, + "learning_rate": 4.8499455896140044e-05, + "loss": 4.1592, + "step": 91648 + }, + { + "epoch": 1.01, + "learning_rate": 4.8491069948629524e-05, + "loss": 4.1623, + "step": 92160 + }, + { + "epoch": 1.01, + "learning_rate": 4.8482684001119e-05, + "loss": 4.1653, + "step": 92672 + }, + { + "epoch": 1.01, + "learning_rate": 4.847429805360848e-05, + "loss": 4.1509, + "step": 93184 + }, + { + "epoch": 1.01, + "learning_rate": 4.8465912106097964e-05, + "loss": 4.1609, + "step": 93696 + }, + { + "epoch": 1.01, + "learning_rate": 4.845754253739117e-05, + "loss": 4.1647, + "step": 94208 + }, + { + "epoch": 1.01, + "learning_rate": 4.844915658988065e-05, + "loss": 4.1592, + "step": 94720 + }, + { + "epoch": 1.01, + "learning_rate": 4.844077064237013e-05, + "loss": 4.134, + "step": 95232 + }, + { + "epoch": 1.01, + "learning_rate": 4.843238469485961e-05, + "loss": 4.1402, + "step": 95744 + }, + { + "epoch": 1.01, + "learning_rate": 4.842399874734909e-05, + "loss": 4.1391, + "step": 96256 + }, + { + "epoch": 1.01, + "learning_rate": 4.841561279983857e-05, + "loss": 4.1446, + "step": 96768 + }, + { + "epoch": 1.01, + "learning_rate": 4.840722685232805e-05, + "loss": 4.1387, + "step": 97280 + }, + { + "epoch": 1.01, + "learning_rate": 4.839884090481753e-05, + "loss": 4.1453, + "step": 97792 + }, + { + "epoch": 1.01, + "learning_rate": 4.839047133611074e-05, + "loss": 4.1326, + "step": 98304 + }, + { + "epoch": 1.01, + "learning_rate": 4.838210176740395e-05, + "loss": 4.1426, + "step": 98816 + }, + { + "epoch": 1.01, + "learning_rate": 4.837371581989343e-05, + "loss": 4.141, + "step": 99328 + }, + { + "epoch": 1.01, + "learning_rate": 4.836532987238292e-05, + "loss": 4.1408, + "step": 99840 + }, + { + "epoch": 1.01, + "learning_rate": 4.83569439248724e-05, + "loss": 4.1368, + "step": 100352 + }, + { + "epoch": 1.01, + "learning_rate": 4.834855797736188e-05, + "loss": 4.1181, + "step": 100864 + }, + { + "epoch": 1.01, + "learning_rate": 4.8340188408655086e-05, + "loss": 4.1325, + "step": 101376 + }, + { + "epoch": 1.01, + "learning_rate": 4.8331802461144566e-05, + "loss": 4.1364, + "step": 101888 + }, + { + "epoch": 1.01, + "learning_rate": 4.8323416513634046e-05, + "loss": 4.1296, + "step": 102400 + }, + { + "epoch": 1.01, + "learning_rate": 4.8315030566123526e-05, + "loss": 4.1251, + "step": 102912 + }, + { + "epoch": 1.01, + "learning_rate": 4.8306644618613006e-05, + "loss": 4.1146, + "step": 103424 + }, + { + "epoch": 1.01, + "learning_rate": 4.8298275049906215e-05, + "loss": 4.1236, + "step": 103936 + }, + { + "epoch": 1.01, + "learning_rate": 4.8289889102395695e-05, + "loss": 4.1071, + "step": 104448 + }, + { + "epoch": 1.01, + "learning_rate": 4.8281503154885175e-05, + "loss": 4.1355, + "step": 104960 + }, + { + "epoch": 1.01, + "learning_rate": 4.8273117207374655e-05, + "loss": 4.1132, + "step": 105472 + }, + { + "epoch": 1.01, + "learning_rate": 4.8264731259864135e-05, + "loss": 4.1258, + "step": 105984 + }, + { + "epoch": 1.01, + "learning_rate": 4.825636169115735e-05, + "loss": 4.1239, + "step": 106496 + }, + { + "epoch": 1.01, + "learning_rate": 4.824797574364683e-05, + "loss": 4.097, + "step": 107008 + }, + { + "epoch": 1.01, + "learning_rate": 4.823958979613631e-05, + "loss": 4.1139, + "step": 107520 + }, + { + "epoch": 1.01, + "learning_rate": 4.823120384862579e-05, + "loss": 4.1078, + "step": 108032 + }, + { + "epoch": 1.01, + "learning_rate": 4.8222834279919e-05, + "loss": 4.0975, + "step": 108544 + }, + { + "epoch": 1.01, + "learning_rate": 4.821444833240848e-05, + "loss": 4.0948, + "step": 109056 + }, + { + "epoch": 1.01, + "learning_rate": 4.820606238489796e-05, + "loss": 4.1122, + "step": 109568 + }, + { + "epoch": 1.01, + "learning_rate": 4.819767643738744e-05, + "loss": 4.1014, + "step": 110080 + }, + { + "epoch": 1.01, + "learning_rate": 4.818929048987692e-05, + "loss": 4.0956, + "step": 110592 + }, + { + "epoch": 1.01, + "learning_rate": 4.818092092117013e-05, + "loss": 4.0869, + "step": 111104 + }, + { + "epoch": 1.01, + "learning_rate": 4.817253497365961e-05, + "loss": 4.1059, + "step": 111616 + }, + { + "epoch": 1.01, + "learning_rate": 4.816414902614909e-05, + "loss": 4.1085, + "step": 112128 + }, + { + "epoch": 1.01, + "learning_rate": 4.815576307863857e-05, + "loss": 4.1043, + "step": 112640 + }, + { + "epoch": 1.01, + "learning_rate": 4.814737713112805e-05, + "loss": 4.099, + "step": 113152 + }, + { + "epoch": 1.01, + "learning_rate": 4.8139007562421265e-05, + "loss": 4.1096, + "step": 113664 + }, + { + "epoch": 1.01, + "learning_rate": 4.8130621614910745e-05, + "loss": 4.1062, + "step": 114176 + }, + { + "epoch": 1.01, + "learning_rate": 4.8122235667400224e-05, + "loss": 4.1037, + "step": 114688 + }, + { + "epoch": 1.01, + "learning_rate": 4.8113849719889704e-05, + "loss": 4.0869, + "step": 115200 + }, + { + "epoch": 1.01, + "learning_rate": 4.8105480151182914e-05, + "loss": 4.0996, + "step": 115712 + }, + { + "epoch": 1.01, + "learning_rate": 4.8097094203672393e-05, + "loss": 4.092, + "step": 116224 + }, + { + "epoch": 1.01, + "learning_rate": 4.8088708256161873e-05, + "loss": 4.0908, + "step": 116736 + }, + { + "epoch": 1.01, + "learning_rate": 4.808032230865135e-05, + "loss": 4.088, + "step": 117248 + }, + { + "epoch": 1.01, + "learning_rate": 4.8071936361140827e-05, + "loss": 4.0895, + "step": 117760 + }, + { + "epoch": 1.01, + "learning_rate": 4.8063550413630307e-05, + "loss": 4.102, + "step": 118272 + }, + { + "epoch": 1.01, + "learning_rate": 4.805518084492352e-05, + "loss": 4.0946, + "step": 118784 + }, + { + "epoch": 1.01, + "learning_rate": 4.8046794897413e-05, + "loss": 4.0706, + "step": 119296 + }, + { + "epoch": 1.01, + "learning_rate": 4.803840894990248e-05, + "loss": 4.0776, + "step": 119808 + }, + { + "epoch": 1.01, + "learning_rate": 4.803002300239196e-05, + "loss": 4.0856, + "step": 120320 + }, + { + "epoch": 1.01, + "learning_rate": 4.802163705488144e-05, + "loss": 4.082, + "step": 120832 + }, + { + "epoch": 1.01, + "learning_rate": 4.801326748617466e-05, + "loss": 4.0813, + "step": 121344 + }, + { + "epoch": 1.01, + "learning_rate": 4.800488153866413e-05, + "loss": 4.0783, + "step": 121856 + }, + { + "epoch": 1.02, + "learning_rate": 4.799649559115361e-05, + "loss": 4.078, + "step": 122368 + }, + { + "epoch": 1.02, + "learning_rate": 4.798810964364309e-05, + "loss": 4.0673, + "step": 122880 + }, + { + "epoch": 1.02, + "learning_rate": 4.79797400749363e-05, + "loss": 4.0764, + "step": 123392 + }, + { + "epoch": 1.02, + "learning_rate": 4.797135412742578e-05, + "loss": 4.0744, + "step": 123904 + }, + { + "epoch": 1.02, + "learning_rate": 4.796296817991526e-05, + "loss": 4.0746, + "step": 124416 + }, + { + "epoch": 1.02, + "learning_rate": 4.795458223240474e-05, + "loss": 4.0814, + "step": 124928 + }, + { + "epoch": 1.02, + "learning_rate": 4.7946212663697956e-05, + "loss": 4.0723, + "step": 125440 + }, + { + "epoch": 1.02, + "learning_rate": 4.7937826716187436e-05, + "loss": 4.0653, + "step": 125952 + }, + { + "epoch": 1.02, + "learning_rate": 4.7929440768676916e-05, + "loss": 4.0692, + "step": 126464 + }, + { + "epoch": 1.02, + "learning_rate": 4.7921054821166396e-05, + "loss": 4.0707, + "step": 126976 + }, + { + "epoch": 1.02, + "learning_rate": 4.7912685252459605e-05, + "loss": 4.0736, + "step": 127488 + }, + { + "epoch": 1.02, + "learning_rate": 4.7904299304949085e-05, + "loss": 4.0641, + "step": 128000 + }, + { + "epoch": 1.02, + "learning_rate": 4.7895913357438565e-05, + "loss": 4.0608, + "step": 128512 + }, + { + "epoch": 1.02, + "learning_rate": 4.7887527409928045e-05, + "loss": 4.0588, + "step": 129024 + }, + { + "epoch": 1.02, + "learning_rate": 4.7879141462417525e-05, + "loss": 4.0672, + "step": 129536 + }, + { + "epoch": 1.02, + "learning_rate": 4.7870771893710734e-05, + "loss": 4.0524, + "step": 130048 + }, + { + "epoch": 1.02, + "learning_rate": 4.786240232500395e-05, + "loss": 4.0419, + "step": 130560 + }, + { + "epoch": 1.02, + "learning_rate": 4.785401637749343e-05, + "loss": 4.0595, + "step": 131072 + }, + { + "epoch": 1.02, + "learning_rate": 4.784563042998291e-05, + "loss": 4.0604, + "step": 131584 + }, + { + "epoch": 1.02, + "learning_rate": 4.783724448247239e-05, + "loss": 4.0533, + "step": 132096 + }, + { + "epoch": 1.02, + "learning_rate": 4.782885853496187e-05, + "loss": 4.0552, + "step": 132608 + }, + { + "epoch": 1.02, + "learning_rate": 4.782047258745135e-05, + "loss": 4.0496, + "step": 133120 + }, + { + "epoch": 1.02, + "learning_rate": 4.781208663994083e-05, + "loss": 4.0573, + "step": 133632 + }, + { + "epoch": 1.02, + "learning_rate": 4.780370069243031e-05, + "loss": 4.0451, + "step": 134144 + }, + { + "epoch": 1.02, + "learning_rate": 4.779533112372352e-05, + "loss": 4.0526, + "step": 134656 + }, + { + "epoch": 1.02, + "learning_rate": 4.7786945176213e-05, + "loss": 4.0599, + "step": 135168 + }, + { + "epoch": 1.02, + "learning_rate": 4.777855922870248e-05, + "loss": 4.0596, + "step": 135680 + }, + { + "epoch": 1.02, + "learning_rate": 4.777018965999569e-05, + "loss": 4.047, + "step": 136192 + }, + { + "epoch": 1.02, + "learning_rate": 4.776180371248517e-05, + "loss": 4.0467, + "step": 136704 + }, + { + "epoch": 1.02, + "learning_rate": 4.775341776497465e-05, + "loss": 4.0513, + "step": 137216 + }, + { + "epoch": 1.02, + "learning_rate": 4.7745031817464134e-05, + "loss": 4.0555, + "step": 137728 + }, + { + "epoch": 1.02, + "learning_rate": 4.7736645869953614e-05, + "loss": 4.0369, + "step": 138240 + }, + { + "epoch": 1.02, + "learning_rate": 4.7728259922443094e-05, + "loss": 4.0498, + "step": 138752 + }, + { + "epoch": 1.02, + "learning_rate": 4.7719873974932574e-05, + "loss": 4.0416, + "step": 139264 + }, + { + "epoch": 1.02, + "learning_rate": 4.7711488027422054e-05, + "loss": 4.053, + "step": 139776 + }, + { + "epoch": 1.02, + "learning_rate": 4.770311845871526e-05, + "loss": 4.0325, + "step": 140288 + }, + { + "epoch": 1.02, + "learning_rate": 4.769473251120474e-05, + "loss": 4.0343, + "step": 140800 + }, + { + "epoch": 1.02, + "learning_rate": 4.768634656369422e-05, + "loss": 4.038, + "step": 141312 + }, + { + "epoch": 1.02, + "learning_rate": 4.76779606161837e-05, + "loss": 4.0426, + "step": 141824 + }, + { + "epoch": 1.02, + "learning_rate": 4.766959104747691e-05, + "loss": 4.033, + "step": 142336 + }, + { + "epoch": 1.02, + "learning_rate": 4.766120509996639e-05, + "loss": 4.0532, + "step": 142848 + }, + { + "epoch": 1.02, + "learning_rate": 4.765281915245587e-05, + "loss": 4.0414, + "step": 143360 + }, + { + "epoch": 1.02, + "learning_rate": 4.764443320494535e-05, + "loss": 4.0314, + "step": 143872 + }, + { + "epoch": 1.02, + "learning_rate": 4.763606363623857e-05, + "loss": 4.032, + "step": 144384 + }, + { + "epoch": 1.02, + "learning_rate": 4.762767768872805e-05, + "loss": 4.0489, + "step": 144896 + }, + { + "epoch": 1.02, + "learning_rate": 4.761929174121753e-05, + "loss": 4.039, + "step": 145408 + }, + { + "epoch": 1.02, + "learning_rate": 4.761090579370701e-05, + "loss": 4.0369, + "step": 145920 + }, + { + "epoch": 1.02, + "learning_rate": 4.760253622500022e-05, + "loss": 4.0295, + "step": 146432 + }, + { + "epoch": 1.02, + "learning_rate": 4.75941502774897e-05, + "loss": 4.0375, + "step": 146944 + }, + { + "epoch": 1.02, + "learning_rate": 4.758576432997918e-05, + "loss": 4.0403, + "step": 147456 + }, + { + "epoch": 1.02, + "learning_rate": 4.757737838246866e-05, + "loss": 4.0317, + "step": 147968 + }, + { + "epoch": 1.02, + "learning_rate": 4.7569008813761866e-05, + "loss": 4.0237, + "step": 148480 + }, + { + "epoch": 1.02, + "learning_rate": 4.7560622866251346e-05, + "loss": 4.0284, + "step": 148992 + }, + { + "epoch": 1.02, + "learning_rate": 4.7552236918740826e-05, + "loss": 4.025, + "step": 149504 + }, + { + "epoch": 1.02, + "learning_rate": 4.7543867350034035e-05, + "loss": 4.0225, + "step": 150016 + }, + { + "epoch": 1.02, + "learning_rate": 4.753548140252352e-05, + "loss": 4.036, + "step": 150528 + }, + { + "epoch": 1.02, + "learning_rate": 4.7527095455013e-05, + "loss": 4.0231, + "step": 151040 + }, + { + "epoch": 1.02, + "learning_rate": 4.751870950750248e-05, + "loss": 4.026, + "step": 151552 + }, + { + "epoch": 1.02, + "learning_rate": 4.751032355999196e-05, + "loss": 4.0245, + "step": 152064 + }, + { + "epoch": 1.02, + "learning_rate": 4.7501937612481435e-05, + "loss": 4.0183, + "step": 152576 + }, + { + "epoch": 1.03, + "eval_loss": 4.024468898773193, + "eval_runtime": 306.7507, + "eval_samples_per_second": 1243.978, + "eval_steps_per_second": 38.875, + "step": 152640 + }, + { + "epoch": 0.0, + "learning_rate": 4.7493551664970914e-05, + "loss": 4.0077, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.7485165717460394e-05, + "loss": 4.0176, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.7476779769949874e-05, + "loss": 4.0298, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.7468393822439354e-05, + "loss": 4.0185, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.7460007874928834e-05, + "loss": 4.0228, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.7451621927418314e-05, + "loss": 4.0139, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.7443235979907794e-05, + "loss": 4.0162, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.7434850032397274e-05, + "loss": 4.0019, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.742648046369049e-05, + "loss": 4.0235, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.741809451617997e-05, + "loss": 4.0205, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.740970856866945e-05, + "loss": 4.0164, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.740132262115893e-05, + "loss": 4.0214, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.739293667364841e-05, + "loss": 4.0041, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.738455072613789e-05, + "loss": 4.0037, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.737616477862737e-05, + "loss": 4.0119, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.736777883111685e-05, + "loss": 3.9931, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.735940926241006e-05, + "loss": 4.0028, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.735102331489954e-05, + "loss": 3.9981, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.734263736738902e-05, + "loss": 3.9964, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.73342514198785e-05, + "loss": 4.0218, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.732588185117171e-05, + "loss": 4.0012, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.731749590366119e-05, + "loss": 4.0035, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.7309109956150674e-05, + "loss": 3.9932, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.7300724008640154e-05, + "loss": 4.0088, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.7292354439933364e-05, + "loss": 3.985, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.7283968492422844e-05, + "loss": 3.9911, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.7275582544912323e-05, + "loss": 3.9901, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.72671965974018e-05, + "loss": 3.9978, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.725882702869501e-05, + "loss": 3.9882, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.725044108118449e-05, + "loss": 3.9879, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.724205513367397e-05, + "loss": 3.9939, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.7233669186163446e-05, + "loss": 3.9988, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.722529961745666e-05, + "loss": 3.9788, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.721691366994614e-05, + "loss": 3.995, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.720852772243563e-05, + "loss": 3.994, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.72001417749251e-05, + "loss": 3.9902, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.719177220621832e-05, + "loss": 3.9705, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.71833862587078e-05, + "loss": 3.9802, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.717500031119727e-05, + "loss": 3.9701, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.716661436368675e-05, + "loss": 3.986, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.7158244794979966e-05, + "loss": 3.9789, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.7149858847469446e-05, + "loss": 3.9857, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.714147289995892e-05, + "loss": 3.9747, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.71330869524484e-05, + "loss": 3.9801, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.7124717383741615e-05, + "loss": 3.9845, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.7116331436231095e-05, + "loss": 3.986, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.7107945488720575e-05, + "loss": 3.9825, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.7099559541210055e-05, + "loss": 3.9604, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.709118997250327e-05, + "loss": 3.9744, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.7082804024992744e-05, + "loss": 3.9857, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.7074418077482224e-05, + "loss": 3.9709, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.7066032129971704e-05, + "loss": 3.9713, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.705766256126492e-05, + "loss": 3.9667, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.704929299255813e-05, + "loss": 3.972, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.704090704504761e-05, + "loss": 3.9578, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.703252109753709e-05, + "loss": 3.9788, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.702413515002657e-05, + "loss": 3.9676, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.701574920251605e-05, + "loss": 3.9726, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.700736325500553e-05, + "loss": 3.9803, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.699897730749501e-05, + "loss": 3.9486, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.699059135998449e-05, + "loss": 3.9669, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.69822217912777e-05, + "loss": 3.9598, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.697383584376718e-05, + "loss": 3.9557, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.696544989625666e-05, + "loss": 3.9501, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.695706394874614e-05, + "loss": 3.9673, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694869438003935e-05, + "loss": 3.9605, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.694030843252883e-05, + "loss": 3.9512, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.6931922485018307e-05, + "loss": 3.9442, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.6923536537507787e-05, + "loss": 3.9634, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.6915166968801e-05, + "loss": 3.9703, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.690678102129048e-05, + "loss": 3.9622, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.689839507377996e-05, + "loss": 3.961, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.689000912626944e-05, + "loss": 3.9707, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.688163955756265e-05, + "loss": 3.9658, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.687325361005213e-05, + "loss": 3.9683, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.686486766254161e-05, + "loss": 3.9458, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.685648171503109e-05, + "loss": 3.9625, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.6848128525128036e-05, + "loss": 3.9592, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.683974257761751e-05, + "loss": 3.9511, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.6831356630106996e-05, + "loss": 3.9559, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.6822970682596476e-05, + "loss": 3.9554, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.6814584735085956e-05, + "loss": 3.9671, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.6806198787575436e-05, + "loss": 3.9575, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.6797812840064916e-05, + "loss": 3.936, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.6789426892554396e-05, + "loss": 3.9413, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.6781057323847605e-05, + "loss": 3.9516, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.6772671376337085e-05, + "loss": 3.9537, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.6764285428826565e-05, + "loss": 3.9511, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.6755899481316045e-05, + "loss": 3.9441, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.6747529912609254e-05, + "loss": 3.9491, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.6739143965098734e-05, + "loss": 3.9368, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.6730758017588214e-05, + "loss": 3.9495, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.6722372070077694e-05, + "loss": 3.9423, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.6713986122567174e-05, + "loss": 3.9482, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.670561655386039e-05, + "loss": 3.9551, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.669723060634987e-05, + "loss": 3.9476, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.668884465883935e-05, + "loss": 3.9387, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.668045871132883e-05, + "loss": 3.9433, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.667207276381831e-05, + "loss": 3.9438, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.666368681630779e-05, + "loss": 3.9473, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.665530086879727e-05, + "loss": 3.9409, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.664691492128675e-05, + "loss": 3.9372, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.663854535257996e-05, + "loss": 3.9333, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.663015940506944e-05, + "loss": 3.9437, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.662177345755892e-05, + "loss": 3.9314, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.66133875100484e-05, + "loss": 3.9211, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.660503432014534e-05, + "loss": 3.9346, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.659664837263482e-05, + "loss": 3.938, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.65882624251243e-05, + "loss": 3.9287, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.657989285641751e-05, + "loss": 3.9393, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.657150690890699e-05, + "loss": 3.9246, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.656312096139647e-05, + "loss": 3.9396, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.655473501388595e-05, + "loss": 3.9262, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.654634906637543e-05, + "loss": 3.93, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.653797949766864e-05, + "loss": 3.9444, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.652959355015812e-05, + "loss": 3.9405, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.65212076026476e-05, + "loss": 3.9304, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.651282165513708e-05, + "loss": 3.9324, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.650443570762657e-05, + "loss": 3.9294, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.649604976011605e-05, + "loss": 3.9356, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.648768019140926e-05, + "loss": 3.9218, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.647929424389874e-05, + "loss": 3.9353, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.647090829638822e-05, + "loss": 3.9257, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.64625223488777e-05, + "loss": 3.9366, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.6454152780170906e-05, + "loss": 3.9146, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.6445766832660386e-05, + "loss": 3.9255, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.6437380885149866e-05, + "loss": 3.9209, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.6428994937639346e-05, + "loss": 3.926, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.642060899012882e-05, + "loss": 3.9195, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.6412223042618306e-05, + "loss": 3.9427, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.640385347391152e-05, + "loss": 3.9287, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.6395467526401e-05, + "loss": 3.922, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.6387081578890475e-05, + "loss": 3.9128, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.6378695631379955e-05, + "loss": 3.9355, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.637032606267317e-05, + "loss": 3.9287, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.636194011516265e-05, + "loss": 3.9275, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.6353554167652124e-05, + "loss": 3.9209, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.6345168220141604e-05, + "loss": 3.9251, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.633679865143482e-05, + "loss": 3.9301, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.632841270392429e-05, + "loss": 3.9212, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.632002675641377e-05, + "loss": 3.9171, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.631164080890326e-05, + "loss": 3.921, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.6303271240196475e-05, + "loss": 3.9181, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.629488529268595e-05, + "loss": 3.9116, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.628649934517543e-05, + "loss": 3.9242, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.627811339766491e-05, + "loss": 3.9235, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.626974382895812e-05, + "loss": 3.9168, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.62613578814476e-05, + "loss": 3.9151, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.625297193393708e-05, + "loss": 3.9082, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 3.949995279312134, + "eval_runtime": 303.7283, + "eval_samples_per_second": 1256.357, + "eval_steps_per_second": 39.262, + "step": 228960 + }, + { + "epoch": 1.0, + "learning_rate": 4.624458598642656e-05, + "loss": 3.9135, + "step": 229376 + }, + { + "epoch": 1.0, + "learning_rate": 4.6236216417719766e-05, + "loss": 3.9105, + "step": 229888 + }, + { + "epoch": 1.0, + "learning_rate": 4.6227830470209246e-05, + "loss": 3.9229, + "step": 230400 + }, + { + "epoch": 1.0, + "learning_rate": 4.6219444522698726e-05, + "loss": 3.912, + "step": 230912 + }, + { + "epoch": 1.0, + "learning_rate": 4.621105857518821e-05, + "loss": 3.9226, + "step": 231424 + }, + { + "epoch": 1.0, + "learning_rate": 4.620267262767769e-05, + "loss": 3.9082, + "step": 231936 + }, + { + "epoch": 1.0, + "learning_rate": 4.61943030589709e-05, + "loss": 3.9141, + "step": 232448 + }, + { + "epoch": 1.0, + "learning_rate": 4.618591711146038e-05, + "loss": 3.8987, + "step": 232960 + }, + { + "epoch": 1.0, + "learning_rate": 4.617753116394986e-05, + "loss": 3.9213, + "step": 233472 + }, + { + "epoch": 1.0, + "learning_rate": 4.616914521643934e-05, + "loss": 3.9151, + "step": 233984 + }, + { + "epoch": 1.0, + "learning_rate": 4.616077564773255e-05, + "loss": 3.9146, + "step": 234496 + }, + { + "epoch": 1.0, + "learning_rate": 4.615238970022203e-05, + "loss": 3.9177, + "step": 235008 + }, + { + "epoch": 1.0, + "learning_rate": 4.614402013151524e-05, + "loss": 3.8994, + "step": 235520 + }, + { + "epoch": 1.0, + "learning_rate": 4.613563418400472e-05, + "loss": 3.9042, + "step": 236032 + }, + { + "epoch": 1.0, + "learning_rate": 4.61272482364942e-05, + "loss": 3.9124, + "step": 236544 + }, + { + "epoch": 1.0, + "learning_rate": 4.611886228898368e-05, + "loss": 3.8972, + "step": 237056 + }, + { + "epoch": 1.0, + "learning_rate": 4.611047634147316e-05, + "loss": 3.8995, + "step": 237568 + }, + { + "epoch": 1.0, + "learning_rate": 4.610209039396265e-05, + "loss": 3.8963, + "step": 238080 + }, + { + "epoch": 1.0, + "learning_rate": 4.609370444645213e-05, + "loss": 3.8976, + "step": 238592 + }, + { + "epoch": 1.0, + "learning_rate": 4.6085318498941607e-05, + "loss": 3.924, + "step": 239104 + }, + { + "epoch": 1.0, + "learning_rate": 4.6076948930234816e-05, + "loss": 3.9012, + "step": 239616 + }, + { + "epoch": 1.0, + "learning_rate": 4.6068562982724296e-05, + "loss": 3.9014, + "step": 240128 + }, + { + "epoch": 1.0, + "learning_rate": 4.6060177035213776e-05, + "loss": 3.8984, + "step": 240640 + }, + { + "epoch": 1.0, + "learning_rate": 4.6051791087703256e-05, + "loss": 3.9053, + "step": 241152 + }, + { + "epoch": 1.0, + "learning_rate": 4.6043421518996465e-05, + "loss": 3.889, + "step": 241664 + }, + { + "epoch": 1.0, + "learning_rate": 4.6035035571485945e-05, + "loss": 3.8919, + "step": 242176 + }, + { + "epoch": 1.0, + "learning_rate": 4.6026649623975425e-05, + "loss": 3.8956, + "step": 242688 + }, + { + "epoch": 1.0, + "learning_rate": 4.6018263676464904e-05, + "loss": 3.9006, + "step": 243200 + }, + { + "epoch": 1.0, + "learning_rate": 4.6009877728954384e-05, + "loss": 3.8869, + "step": 243712 + }, + { + "epoch": 1.01, + "learning_rate": 4.60015081602476e-05, + "loss": 3.8936, + "step": 244224 + }, + { + "epoch": 1.01, + "learning_rate": 4.599312221273708e-05, + "loss": 3.8937, + "step": 244736 + }, + { + "epoch": 1.01, + "learning_rate": 4.598473626522656e-05, + "loss": 3.904, + "step": 245248 + }, + { + "epoch": 1.01, + "learning_rate": 4.597635031771604e-05, + "loss": 3.8906, + "step": 245760 + }, + { + "epoch": 1.01, + "learning_rate": 4.596796437020552e-05, + "loss": 3.8964, + "step": 246272 + }, + { + "epoch": 1.01, + "learning_rate": 4.595959480149873e-05, + "loss": 3.8971, + "step": 246784 + }, + { + "epoch": 1.01, + "learning_rate": 4.595120885398821e-05, + "loss": 3.8972, + "step": 247296 + }, + { + "epoch": 1.01, + "learning_rate": 4.594282290647769e-05, + "loss": 3.8775, + "step": 247808 + }, + { + "epoch": 1.01, + "learning_rate": 4.593443695896717e-05, + "loss": 3.8905, + "step": 248320 + }, + { + "epoch": 1.01, + "learning_rate": 4.592606739026038e-05, + "loss": 3.8748, + "step": 248832 + }, + { + "epoch": 1.01, + "learning_rate": 4.591768144274986e-05, + "loss": 3.8934, + "step": 249344 + }, + { + "epoch": 1.01, + "learning_rate": 4.590929549523934e-05, + "loss": 3.883, + "step": 249856 + }, + { + "epoch": 1.01, + "learning_rate": 4.590090954772882e-05, + "loss": 3.8948, + "step": 250368 + }, + { + "epoch": 1.01, + "learning_rate": 4.5892539979022034e-05, + "loss": 3.8853, + "step": 250880 + }, + { + "epoch": 1.01, + "learning_rate": 4.5884154031511514e-05, + "loss": 3.8848, + "step": 251392 + }, + { + "epoch": 1.01, + "learning_rate": 4.5875768084000994e-05, + "loss": 3.8936, + "step": 251904 + }, + { + "epoch": 1.01, + "learning_rate": 4.5867382136490474e-05, + "loss": 3.8911, + "step": 252416 + }, + { + "epoch": 1.01, + "learning_rate": 4.585901256778368e-05, + "loss": 3.8891, + "step": 252928 + }, + { + "epoch": 1.01, + "learning_rate": 4.585062662027316e-05, + "loss": 3.8746, + "step": 253440 + }, + { + "epoch": 1.01, + "learning_rate": 4.584224067276264e-05, + "loss": 3.8794, + "step": 253952 + }, + { + "epoch": 1.01, + "learning_rate": 4.583385472525212e-05, + "loss": 3.895, + "step": 254464 + }, + { + "epoch": 1.01, + "learning_rate": 4.582548515654533e-05, + "loss": 3.8808, + "step": 254976 + }, + { + "epoch": 1.01, + "learning_rate": 4.581709920903481e-05, + "loss": 3.8786, + "step": 255488 + }, + { + "epoch": 1.01, + "learning_rate": 4.580871326152429e-05, + "loss": 3.8778, + "step": 256000 + }, + { + "epoch": 1.01, + "learning_rate": 4.580032731401377e-05, + "loss": 3.8846, + "step": 256512 + }, + { + "epoch": 1.01, + "learning_rate": 4.579195774530699e-05, + "loss": 3.867, + "step": 257024 + }, + { + "epoch": 1.01, + "learning_rate": 4.578357179779647e-05, + "loss": 3.8864, + "step": 257536 + }, + { + "epoch": 1.01, + "learning_rate": 4.577518585028595e-05, + "loss": 3.879, + "step": 258048 + }, + { + "epoch": 1.01, + "learning_rate": 4.576679990277543e-05, + "loss": 3.8851, + "step": 258560 + }, + { + "epoch": 1.01, + "learning_rate": 4.5758430334068637e-05, + "loss": 3.8886, + "step": 259072 + }, + { + "epoch": 1.01, + "learning_rate": 4.5750044386558117e-05, + "loss": 3.8673, + "step": 259584 + }, + { + "epoch": 1.01, + "learning_rate": 4.5741658439047596e-05, + "loss": 3.8707, + "step": 260096 + }, + { + "epoch": 1.01, + "learning_rate": 4.5733272491537076e-05, + "loss": 3.8785, + "step": 260608 + }, + { + "epoch": 1.01, + "learning_rate": 4.5724902922830286e-05, + "loss": 3.8653, + "step": 261120 + }, + { + "epoch": 1.01, + "learning_rate": 4.5716516975319765e-05, + "loss": 3.8647, + "step": 261632 + }, + { + "epoch": 1.01, + "learning_rate": 4.5708131027809245e-05, + "loss": 3.8768, + "step": 262144 + }, + { + "epoch": 1.01, + "learning_rate": 4.5699745080298725e-05, + "loss": 3.8763, + "step": 262656 + }, + { + "epoch": 1.01, + "learning_rate": 4.569137551159194e-05, + "loss": 3.8635, + "step": 263168 + }, + { + "epoch": 1.01, + "learning_rate": 4.568298956408142e-05, + "loss": 3.8585, + "step": 263680 + }, + { + "epoch": 1.01, + "learning_rate": 4.56746036165709e-05, + "loss": 3.8752, + "step": 264192 + }, + { + "epoch": 1.01, + "learning_rate": 4.5666217669060374e-05, + "loss": 3.8823, + "step": 264704 + }, + { + "epoch": 1.01, + "learning_rate": 4.565784810035359e-05, + "loss": 3.8727, + "step": 265216 + }, + { + "epoch": 1.01, + "learning_rate": 4.564946215284307e-05, + "loss": 3.8807, + "step": 265728 + }, + { + "epoch": 1.01, + "learning_rate": 4.564107620533255e-05, + "loss": 3.8826, + "step": 266240 + }, + { + "epoch": 1.01, + "learning_rate": 4.563269025782202e-05, + "loss": 3.8816, + "step": 266752 + }, + { + "epoch": 1.01, + "learning_rate": 4.562432068911524e-05, + "loss": 3.8843, + "step": 267264 + }, + { + "epoch": 1.01, + "learning_rate": 4.561593474160472e-05, + "loss": 3.8606, + "step": 267776 + }, + { + "epoch": 1.01, + "learning_rate": 4.56075487940942e-05, + "loss": 3.8776, + "step": 268288 + }, + { + "epoch": 1.01, + "learning_rate": 4.559916284658368e-05, + "loss": 3.8793, + "step": 268800 + }, + { + "epoch": 1.01, + "learning_rate": 4.5590793277876895e-05, + "loss": 3.8643, + "step": 269312 + }, + { + "epoch": 1.01, + "learning_rate": 4.5582407330366375e-05, + "loss": 3.8765, + "step": 269824 + }, + { + "epoch": 1.01, + "learning_rate": 4.557402138285585e-05, + "loss": 3.8692, + "step": 270336 + }, + { + "epoch": 1.01, + "learning_rate": 4.556563543534533e-05, + "loss": 3.8815, + "step": 270848 + }, + { + "epoch": 1.01, + "learning_rate": 4.5557265866638544e-05, + "loss": 3.8758, + "step": 271360 + }, + { + "epoch": 1.01, + "learning_rate": 4.5548879919128024e-05, + "loss": 3.8514, + "step": 271872 + }, + { + "epoch": 1.01, + "learning_rate": 4.55404939716175e-05, + "loss": 3.8624, + "step": 272384 + }, + { + "epoch": 1.01, + "learning_rate": 4.553210802410698e-05, + "loss": 3.8664, + "step": 272896 + }, + { + "epoch": 1.01, + "learning_rate": 4.552372207659646e-05, + "loss": 3.8692, + "step": 273408 + }, + { + "epoch": 1.01, + "learning_rate": 4.5515352507889666e-05, + "loss": 3.8717, + "step": 273920 + }, + { + "epoch": 1.01, + "learning_rate": 4.550696656037915e-05, + "loss": 3.8621, + "step": 274432 + }, + { + "epoch": 1.02, + "learning_rate": 4.549858061286863e-05, + "loss": 3.8658, + "step": 274944 + }, + { + "epoch": 1.02, + "learning_rate": 4.549019466535811e-05, + "loss": 3.8574, + "step": 275456 + }, + { + "epoch": 1.02, + "learning_rate": 4.548182509665132e-05, + "loss": 3.8673, + "step": 275968 + }, + { + "epoch": 1.02, + "learning_rate": 4.54734391491408e-05, + "loss": 3.8596, + "step": 276480 + }, + { + "epoch": 1.02, + "learning_rate": 4.546505320163028e-05, + "loss": 3.8674, + "step": 276992 + }, + { + "epoch": 1.02, + "learning_rate": 4.545666725411976e-05, + "loss": 3.8769, + "step": 277504 + }, + { + "epoch": 1.02, + "learning_rate": 4.544829768541297e-05, + "loss": 3.8667, + "step": 278016 + }, + { + "epoch": 1.02, + "learning_rate": 4.543991173790245e-05, + "loss": 3.8571, + "step": 278528 + }, + { + "epoch": 1.02, + "learning_rate": 4.543152579039193e-05, + "loss": 3.8646, + "step": 279040 + }, + { + "epoch": 1.02, + "learning_rate": 4.542313984288141e-05, + "loss": 3.8627, + "step": 279552 + }, + { + "epoch": 1.02, + "learning_rate": 4.541477027417462e-05, + "loss": 3.8687, + "step": 280064 + }, + { + "epoch": 1.02, + "learning_rate": 4.5406384326664106e-05, + "loss": 3.8636, + "step": 280576 + }, + { + "epoch": 1.02, + "learning_rate": 4.5397998379153586e-05, + "loss": 3.8586, + "step": 281088 + }, + { + "epoch": 1.02, + "learning_rate": 4.5389612431643066e-05, + "loss": 3.8501, + "step": 281600 + }, + { + "epoch": 1.02, + "learning_rate": 4.5381242862936275e-05, + "loss": 3.8684, + "step": 282112 + }, + { + "epoch": 1.02, + "learning_rate": 4.5372856915425755e-05, + "loss": 3.8479, + "step": 282624 + }, + { + "epoch": 1.02, + "learning_rate": 4.5364470967915235e-05, + "loss": 3.8446, + "step": 283136 + }, + { + "epoch": 1.02, + "learning_rate": 4.5356085020404715e-05, + "loss": 3.8532, + "step": 283648 + }, + { + "epoch": 1.02, + "learning_rate": 4.5347715451697924e-05, + "loss": 3.8574, + "step": 284160 + }, + { + "epoch": 1.02, + "learning_rate": 4.5339329504187404e-05, + "loss": 3.8517, + "step": 284672 + }, + { + "epoch": 1.02, + "learning_rate": 4.5330943556676884e-05, + "loss": 3.8676, + "step": 285184 + }, + { + "epoch": 1.02, + "learning_rate": 4.5322557609166364e-05, + "loss": 3.8502, + "step": 285696 + }, + { + "epoch": 1.02, + "learning_rate": 4.5314188040459573e-05, + "loss": 3.854, + "step": 286208 + }, + { + "epoch": 1.02, + "learning_rate": 4.530580209294906e-05, + "loss": 3.8547, + "step": 286720 + }, + { + "epoch": 1.02, + "learning_rate": 4.529741614543854e-05, + "loss": 3.8466, + "step": 287232 + }, + { + "epoch": 1.02, + "learning_rate": 4.528904657673175e-05, + "loss": 3.8704, + "step": 287744 + }, + { + "epoch": 1.02, + "learning_rate": 4.528066062922123e-05, + "loss": 3.8631, + "step": 288256 + }, + { + "epoch": 1.02, + "learning_rate": 4.527227468171071e-05, + "loss": 3.8571, + "step": 288768 + }, + { + "epoch": 1.02, + "learning_rate": 4.526388873420019e-05, + "loss": 3.857, + "step": 289280 + }, + { + "epoch": 1.02, + "learning_rate": 4.52555191654934e-05, + "loss": 3.8477, + "step": 289792 + }, + { + "epoch": 1.02, + "learning_rate": 4.524713321798288e-05, + "loss": 3.8596, + "step": 290304 + }, + { + "epoch": 1.02, + "learning_rate": 4.523874727047236e-05, + "loss": 3.8466, + "step": 290816 + }, + { + "epoch": 1.02, + "learning_rate": 4.523036132296184e-05, + "loss": 3.864, + "step": 291328 + }, + { + "epoch": 1.02, + "learning_rate": 4.522199175425505e-05, + "loss": 3.8462, + "step": 291840 + }, + { + "epoch": 1.02, + "learning_rate": 4.521360580674453e-05, + "loss": 3.8574, + "step": 292352 + }, + { + "epoch": 1.02, + "learning_rate": 4.520521985923401e-05, + "loss": 3.8452, + "step": 292864 + }, + { + "epoch": 1.02, + "learning_rate": 4.5196833911723494e-05, + "loss": 3.8491, + "step": 293376 + }, + { + "epoch": 1.02, + "learning_rate": 4.5188447964212974e-05, + "loss": 3.8446, + "step": 293888 + }, + { + "epoch": 1.02, + "learning_rate": 4.518007839550618e-05, + "loss": 3.8513, + "step": 294400 + }, + { + "epoch": 1.02, + "learning_rate": 4.517169244799566e-05, + "loss": 3.8448, + "step": 294912 + }, + { + "epoch": 1.02, + "learning_rate": 4.516330650048514e-05, + "loss": 3.866, + "step": 295424 + }, + { + "epoch": 1.02, + "learning_rate": 4.515492055297462e-05, + "loss": 3.8569, + "step": 295936 + }, + { + "epoch": 1.02, + "learning_rate": 4.514655098426783e-05, + "loss": 3.8496, + "step": 296448 + }, + { + "epoch": 1.02, + "learning_rate": 4.513816503675731e-05, + "loss": 3.836, + "step": 296960 + }, + { + "epoch": 1.02, + "learning_rate": 4.512977908924679e-05, + "loss": 3.8601, + "step": 297472 + }, + { + "epoch": 1.02, + "learning_rate": 4.512139314173627e-05, + "loss": 3.8543, + "step": 297984 + }, + { + "epoch": 1.02, + "learning_rate": 4.511302357302948e-05, + "loss": 3.8575, + "step": 298496 + }, + { + "epoch": 1.02, + "learning_rate": 4.510463762551896e-05, + "loss": 3.8466, + "step": 299008 + }, + { + "epoch": 1.02, + "learning_rate": 4.509625167800845e-05, + "loss": 3.8492, + "step": 299520 + }, + { + "epoch": 1.02, + "learning_rate": 4.508786573049793e-05, + "loss": 3.8554, + "step": 300032 + }, + { + "epoch": 1.02, + "learning_rate": 4.5079496161791136e-05, + "loss": 3.8532, + "step": 300544 + }, + { + "epoch": 1.02, + "learning_rate": 4.5071110214280616e-05, + "loss": 3.8419, + "step": 301056 + }, + { + "epoch": 1.02, + "learning_rate": 4.5062724266770096e-05, + "loss": 3.8475, + "step": 301568 + }, + { + "epoch": 1.02, + "learning_rate": 4.5054338319259576e-05, + "loss": 3.8448, + "step": 302080 + }, + { + "epoch": 1.02, + "learning_rate": 4.5045968750552785e-05, + "loss": 3.8398, + "step": 302592 + }, + { + "epoch": 1.02, + "learning_rate": 4.5037582803042265e-05, + "loss": 3.8502, + "step": 303104 + }, + { + "epoch": 1.02, + "learning_rate": 4.5029196855531745e-05, + "loss": 3.8547, + "step": 303616 + }, + { + "epoch": 1.02, + "learning_rate": 4.5020827286824954e-05, + "loss": 3.8419, + "step": 304128 + }, + { + "epoch": 1.02, + "learning_rate": 4.5012441339314434e-05, + "loss": 3.8388, + "step": 304640 + }, + { + "epoch": 1.02, + "learning_rate": 4.5004055391803914e-05, + "loss": 3.8443, + "step": 305152 + }, + { + "epoch": 1.03, + "eval_loss": 3.9103078842163086, + "eval_runtime": 311.761, + "eval_samples_per_second": 1223.986, + "eval_steps_per_second": 38.25, + "step": 305280 + }, + { + "epoch": 0.0, + "learning_rate": 4.49956694442934e-05, + "loss": 3.8365, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.498728349678288e-05, + "loss": 3.8401, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.497889754927236e-05, + "loss": 3.8498, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.497051160176184e-05, + "loss": 3.8413, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.496212565425132e-05, + "loss": 3.8539, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.49537397067408e-05, + "loss": 3.8352, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.4945353759230274e-05, + "loss": 3.8426, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.4936967811719754e-05, + "loss": 3.8286, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.492859824301297e-05, + "loss": 3.8545, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.492021229550245e-05, + "loss": 3.8441, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.491184272679566e-05, + "loss": 3.8403, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.490345677928514e-05, + "loss": 3.8514, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.489507083177462e-05, + "loss": 3.8286, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.48866848842641e-05, + "loss": 3.8395, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.487829893675358e-05, + "loss": 3.8419, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.486991298924306e-05, + "loss": 3.8297, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.486152704173254e-05, + "loss": 3.8291, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.485314109422202e-05, + "loss": 3.8274, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.484477152551523e-05, + "loss": 3.8324, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.4836401956808444e-05, + "loss": 3.8515, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.4828016009297924e-05, + "loss": 3.833, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.48196300617874e-05, + "loss": 3.833, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.481124411427688e-05, + "loss": 3.8308, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.480285816676636e-05, + "loss": 3.8386, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.4794472219255837e-05, + "loss": 3.8254, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.478608627174532e-05, + "loss": 3.827, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.47777003242348e-05, + "loss": 3.8245, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.476933075552801e-05, + "loss": 3.8348, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.476094480801749e-05, + "loss": 3.8177, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.475255886050697e-05, + "loss": 3.8294, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.474418929180018e-05, + "loss": 3.8296, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.473580334428966e-05, + "loss": 3.837, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.472741739677914e-05, + "loss": 3.8249, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.471903144926862e-05, + "loss": 3.8299, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.471066188056183e-05, + "loss": 3.8296, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.470227593305131e-05, + "loss": 3.8316, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.469388998554079e-05, + "loss": 3.8153, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.468550403803028e-05, + "loss": 3.8208, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.4677134469323486e-05, + "loss": 3.8093, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.4668748521812966e-05, + "loss": 3.8265, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.4660362574302446e-05, + "loss": 3.8176, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.4651976626791926e-05, + "loss": 3.828, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.4643607058085135e-05, + "loss": 3.8192, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.4635221110574615e-05, + "loss": 3.8237, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.4626835163064095e-05, + "loss": 3.8268, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.4618449215553575e-05, + "loss": 3.825, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.4610079646846784e-05, + "loss": 3.8271, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.4601693699336264e-05, + "loss": 3.8145, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.4593307751825744e-05, + "loss": 3.8084, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.4584921804315224e-05, + "loss": 3.8316, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.457655223560844e-05, + "loss": 3.8186, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.456818266690165e-05, + "loss": 3.8163, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.455979671939113e-05, + "loss": 3.8153, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.455141077188061e-05, + "loss": 3.8232, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.454302482437009e-05, + "loss": 3.8025, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.453463887685957e-05, + "loss": 3.8243, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.452625292934905e-05, + "loss": 3.8168, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.451786698183853e-05, + "loss": 3.8195, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.450948103432801e-05, + "loss": 3.8269, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.450111146562122e-05, + "loss": 3.8097, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.44927255181107e-05, + "loss": 3.8049, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.448433957060018e-05, + "loss": 3.8214, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.4475953623089664e-05, + "loss": 3.7992, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.446758405438287e-05, + "loss": 3.803, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.445919810687235e-05, + "loss": 3.8157, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.445081215936183e-05, + "loss": 3.8149, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.444242621185131e-05, + "loss": 3.8019, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.443405664314452e-05, + "loss": 3.7984, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.4425670695634e-05, + "loss": 3.8116, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.441728474812348e-05, + "loss": 3.8186, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.440889880061296e-05, + "loss": 3.8149, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.440052923190617e-05, + "loss": 3.8136, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.439214328439565e-05, + "loss": 3.8234, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.438375733688513e-05, + "loss": 3.8166, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.437537138937462e-05, + "loss": 3.8272, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.436700182066783e-05, + "loss": 3.7997, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.435861587315731e-05, + "loss": 3.819, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.4350246304450516e-05, + "loss": 3.8165, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.4341860356939996e-05, + "loss": 3.8024, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.4333474409429476e-05, + "loss": 3.8199, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.4325088461918956e-05, + "loss": 3.8078, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.4316702514408436e-05, + "loss": 3.8181, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.4308316566897916e-05, + "loss": 3.8178, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.4299930619387396e-05, + "loss": 3.7925, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.4291544671876876e-05, + "loss": 3.804, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.4283175103170085e-05, + "loss": 3.8033, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.427478915565957e-05, + "loss": 3.8123, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.426640320814905e-05, + "loss": 3.8115, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.425801726063853e-05, + "loss": 3.801, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.424964769193174e-05, + "loss": 3.809, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.424126174442122e-05, + "loss": 3.8002, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.42328757969107e-05, + "loss": 3.8041, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.422448984940018e-05, + "loss": 3.8014, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.421612028069339e-05, + "loss": 3.8104, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.420773433318287e-05, + "loss": 3.818, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.419934838567235e-05, + "loss": 3.8083, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.419096243816182e-05, + "loss": 3.7983, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.418259286945504e-05, + "loss": 3.8027, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.4174206921944525e-05, + "loss": 3.807, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.4165820974434005e-05, + "loss": 3.813, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.415743502692348e-05, + "loss": 3.8063, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.4149065458216694e-05, + "loss": 3.8017, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.4140679510706174e-05, + "loss": 3.7919, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.4132293563195654e-05, + "loss": 3.8081, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.412390761568513e-05, + "loss": 3.7917, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.411555442578207e-05, + "loss": 3.7915, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.410716847827155e-05, + "loss": 3.7907, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.409878253076103e-05, + "loss": 3.8039, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.409039658325051e-05, + "loss": 3.7893, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.408201063573999e-05, + "loss": 3.8143, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.407362468822948e-05, + "loss": 3.7898, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.406523874071895e-05, + "loss": 3.8015, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.405685279320843e-05, + "loss": 3.7985, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.404848322450165e-05, + "loss": 3.7912, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.404009727699113e-05, + "loss": 3.813, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.40317113294806e-05, + "loss": 3.8066, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.402334176077382e-05, + "loss": 3.7978, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.40149558132633e-05, + "loss": 3.7998, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.400656986575277e-05, + "loss": 3.7943, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.399818391824225e-05, + "loss": 3.8021, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.398979797073173e-05, + "loss": 3.7849, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.398141202322122e-05, + "loss": 3.8085, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.39730260757107e-05, + "loss": 3.7947, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.396464012820018e-05, + "loss": 3.7978, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.3956270559493386e-05, + "loss": 3.7909, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.3947884611982866e-05, + "loss": 3.7945, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.3939515043276075e-05, + "loss": 3.7853, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.3931129095765555e-05, + "loss": 3.7986, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.3922743148255035e-05, + "loss": 3.7899, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.3914357200744515e-05, + "loss": 3.8073, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.3905971253233995e-05, + "loss": 3.8006, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.3897585305723475e-05, + "loss": 3.798, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.3889199358212955e-05, + "loss": 3.7795, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.3880813410702434e-05, + "loss": 3.8036, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.387246022079938e-05, + "loss": 3.7994, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.386407427328886e-05, + "loss": 3.8004, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.385568832577834e-05, + "loss": 3.7907, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.384730237826782e-05, + "loss": 3.7938, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.38389164307573e-05, + "loss": 3.797, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.383053048324678e-05, + "loss": 3.8024, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.382214453573626e-05, + "loss": 3.787, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.381375858822574e-05, + "loss": 3.7955, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.380538901951895e-05, + "loss": 3.7863, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.379700307200843e-05, + "loss": 3.788, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.378863350330164e-05, + "loss": 3.8005, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.3780247555791124e-05, + "loss": 3.7937, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.3771861608280604e-05, + "loss": 3.7918, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.3763475660770084e-05, + "loss": 3.7856, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.3755089713259564e-05, + "loss": 3.7908, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 3.8839731216430664, + "eval_runtime": 307.4054, + "eval_samples_per_second": 1241.328, + "eval_steps_per_second": 38.792, + "step": 381600 + }, + { + "epoch": 1.0, + "learning_rate": 4.3746703765749044e-05, + "loss": 3.7879, + "step": 381952 + }, + { + "epoch": 1.0, + "learning_rate": 4.3738317818238524e-05, + "loss": 3.7843, + "step": 382464 + }, + { + "epoch": 1.0, + "learning_rate": 4.3729931870728004e-05, + "loss": 3.7993, + "step": 382976 + }, + { + "epoch": 1.0, + "learning_rate": 4.372156230202121e-05, + "loss": 3.7915, + "step": 383488 + }, + { + "epoch": 1.0, + "learning_rate": 4.371317635451069e-05, + "loss": 3.7959, + "step": 384000 + }, + { + "epoch": 1.0, + "learning_rate": 4.370479040700017e-05, + "loss": 3.788, + "step": 384512 + }, + { + "epoch": 1.0, + "learning_rate": 4.369640445948965e-05, + "loss": 3.7845, + "step": 385024 + }, + { + "epoch": 1.0, + "learning_rate": 4.368803489078286e-05, + "loss": 3.7766, + "step": 385536 + }, + { + "epoch": 1.0, + "learning_rate": 4.367966532207607e-05, + "loss": 3.7961, + "step": 386048 + }, + { + "epoch": 1.0, + "learning_rate": 4.367127937456556e-05, + "loss": 3.796, + "step": 386560 + }, + { + "epoch": 1.0, + "learning_rate": 4.366289342705504e-05, + "loss": 3.789, + "step": 387072 + }, + { + "epoch": 1.0, + "learning_rate": 4.365450747954452e-05, + "loss": 3.7962, + "step": 387584 + }, + { + "epoch": 1.0, + "learning_rate": 4.364613791083773e-05, + "loss": 3.7753, + "step": 388096 + }, + { + "epoch": 1.0, + "learning_rate": 4.363775196332721e-05, + "loss": 3.7859, + "step": 388608 + }, + { + "epoch": 1.0, + "learning_rate": 4.3629366015816687e-05, + "loss": 3.7911, + "step": 389120 + }, + { + "epoch": 1.0, + "learning_rate": 4.3620980068306167e-05, + "loss": 3.7745, + "step": 389632 + }, + { + "epoch": 1.0, + "learning_rate": 4.3612594120795647e-05, + "loss": 3.7783, + "step": 390144 + }, + { + "epoch": 1.0, + "learning_rate": 4.3604224552088856e-05, + "loss": 3.7765, + "step": 390656 + }, + { + "epoch": 1.0, + "learning_rate": 4.3595838604578336e-05, + "loss": 3.7805, + "step": 391168 + }, + { + "epoch": 1.0, + "learning_rate": 4.3587452657067816e-05, + "loss": 3.7971, + "step": 391680 + }, + { + "epoch": 1.0, + "learning_rate": 4.3579066709557295e-05, + "loss": 3.7821, + "step": 392192 + }, + { + "epoch": 1.0, + "learning_rate": 4.3570680762046775e-05, + "loss": 3.7853, + "step": 392704 + }, + { + "epoch": 1.0, + "learning_rate": 4.3562294814536255e-05, + "loss": 3.7774, + "step": 393216 + }, + { + "epoch": 1.0, + "learning_rate": 4.3553908867025735e-05, + "loss": 3.7888, + "step": 393728 + }, + { + "epoch": 1.0, + "learning_rate": 4.3545522919515215e-05, + "loss": 3.772, + "step": 394240 + }, + { + "epoch": 1.0, + "learning_rate": 4.353715335080843e-05, + "loss": 3.7773, + "step": 394752 + }, + { + "epoch": 1.0, + "learning_rate": 4.3528767403297904e-05, + "loss": 3.7755, + "step": 395264 + }, + { + "epoch": 1.0, + "learning_rate": 4.3520381455787384e-05, + "loss": 3.7813, + "step": 395776 + }, + { + "epoch": 1.0, + "learning_rate": 4.35120118870806e-05, + "loss": 3.768, + "step": 396288 + }, + { + "epoch": 1.0, + "learning_rate": 4.350364231837381e-05, + "loss": 3.7774, + "step": 396800 + }, + { + "epoch": 1.01, + "learning_rate": 4.349525637086329e-05, + "loss": 3.7813, + "step": 397312 + }, + { + "epoch": 1.01, + "learning_rate": 4.348687042335277e-05, + "loss": 3.7832, + "step": 397824 + }, + { + "epoch": 1.01, + "learning_rate": 4.347848447584225e-05, + "loss": 3.7762, + "step": 398336 + }, + { + "epoch": 1.01, + "learning_rate": 4.347009852833173e-05, + "loss": 3.7775, + "step": 398848 + }, + { + "epoch": 1.01, + "learning_rate": 4.346171258082121e-05, + "loss": 3.7798, + "step": 399360 + }, + { + "epoch": 1.01, + "learning_rate": 4.345332663331069e-05, + "loss": 3.7762, + "step": 399872 + }, + { + "epoch": 1.01, + "learning_rate": 4.344494068580017e-05, + "loss": 3.7701, + "step": 400384 + }, + { + "epoch": 1.01, + "learning_rate": 4.343657111709338e-05, + "loss": 3.7683, + "step": 400896 + }, + { + "epoch": 1.01, + "learning_rate": 4.3428201548386594e-05, + "loss": 3.7624, + "step": 401408 + }, + { + "epoch": 1.01, + "learning_rate": 4.3419815600876074e-05, + "loss": 3.7748, + "step": 401920 + }, + { + "epoch": 1.01, + "learning_rate": 4.3411429653365554e-05, + "loss": 3.7705, + "step": 402432 + }, + { + "epoch": 1.01, + "learning_rate": 4.340304370585503e-05, + "loss": 3.7791, + "step": 402944 + }, + { + "epoch": 1.01, + "learning_rate": 4.339465775834451e-05, + "loss": 3.7701, + "step": 403456 + }, + { + "epoch": 1.01, + "learning_rate": 4.338627181083399e-05, + "loss": 3.7724, + "step": 403968 + }, + { + "epoch": 1.01, + "learning_rate": 4.33779022421272e-05, + "loss": 3.7808, + "step": 404480 + }, + { + "epoch": 1.01, + "learning_rate": 4.336951629461668e-05, + "loss": 3.7725, + "step": 404992 + }, + { + "epoch": 1.01, + "learning_rate": 4.336113034710616e-05, + "loss": 3.778, + "step": 405504 + }, + { + "epoch": 1.01, + "learning_rate": 4.335274439959564e-05, + "loss": 3.7636, + "step": 406016 + }, + { + "epoch": 1.01, + "learning_rate": 4.334435845208512e-05, + "loss": 3.759, + "step": 406528 + }, + { + "epoch": 1.01, + "learning_rate": 4.33359725045746e-05, + "loss": 3.7855, + "step": 407040 + }, + { + "epoch": 1.01, + "learning_rate": 4.332758655706408e-05, + "loss": 3.7691, + "step": 407552 + }, + { + "epoch": 1.01, + "learning_rate": 4.331920060955356e-05, + "loss": 3.7676, + "step": 408064 + }, + { + "epoch": 1.01, + "learning_rate": 4.331083104084677e-05, + "loss": 3.7654, + "step": 408576 + }, + { + "epoch": 1.01, + "learning_rate": 4.330244509333625e-05, + "loss": 3.7735, + "step": 409088 + }, + { + "epoch": 1.01, + "learning_rate": 4.329405914582573e-05, + "loss": 3.753, + "step": 409600 + }, + { + "epoch": 1.01, + "learning_rate": 4.328567319831521e-05, + "loss": 3.7742, + "step": 410112 + }, + { + "epoch": 1.01, + "learning_rate": 4.327728725080469e-05, + "loss": 3.7711, + "step": 410624 + }, + { + "epoch": 1.01, + "learning_rate": 4.326890130329417e-05, + "loss": 3.7651, + "step": 411136 + }, + { + "epoch": 1.01, + "learning_rate": 4.326051535578365e-05, + "loss": 3.7846, + "step": 411648 + }, + { + "epoch": 1.01, + "learning_rate": 4.325214578707687e-05, + "loss": 3.7592, + "step": 412160 + }, + { + "epoch": 1.01, + "learning_rate": 4.324375983956635e-05, + "loss": 3.7599, + "step": 412672 + }, + { + "epoch": 1.01, + "learning_rate": 4.323537389205583e-05, + "loss": 3.773, + "step": 413184 + }, + { + "epoch": 1.01, + "learning_rate": 4.3227004323349036e-05, + "loss": 3.7548, + "step": 413696 + }, + { + "epoch": 1.01, + "learning_rate": 4.3218618375838516e-05, + "loss": 3.7575, + "step": 414208 + }, + { + "epoch": 1.01, + "learning_rate": 4.3210232428327996e-05, + "loss": 3.7642, + "step": 414720 + }, + { + "epoch": 1.01, + "learning_rate": 4.3201846480817476e-05, + "loss": 3.7663, + "step": 415232 + }, + { + "epoch": 1.01, + "learning_rate": 4.3193460533306956e-05, + "loss": 3.7558, + "step": 415744 + }, + { + "epoch": 1.01, + "learning_rate": 4.3185090964600165e-05, + "loss": 3.7512, + "step": 416256 + }, + { + "epoch": 1.01, + "learning_rate": 4.3176705017089645e-05, + "loss": 3.7598, + "step": 416768 + }, + { + "epoch": 1.01, + "learning_rate": 4.3168319069579125e-05, + "loss": 3.7691, + "step": 417280 + }, + { + "epoch": 1.01, + "learning_rate": 4.3159933122068605e-05, + "loss": 3.7686, + "step": 417792 + }, + { + "epoch": 1.01, + "learning_rate": 4.3151547174558085e-05, + "loss": 3.7709, + "step": 418304 + }, + { + "epoch": 1.01, + "learning_rate": 4.3143161227047565e-05, + "loss": 3.7715, + "step": 418816 + }, + { + "epoch": 1.01, + "learning_rate": 4.3134775279537045e-05, + "loss": 3.7723, + "step": 419328 + }, + { + "epoch": 1.01, + "learning_rate": 4.3126389332026525e-05, + "loss": 3.7819, + "step": 419840 + }, + { + "epoch": 1.01, + "learning_rate": 4.311801976331974e-05, + "loss": 3.7506, + "step": 420352 + }, + { + "epoch": 1.01, + "learning_rate": 4.3109633815809214e-05, + "loss": 3.7756, + "step": 420864 + }, + { + "epoch": 1.01, + "learning_rate": 4.310126424710243e-05, + "loss": 3.7707, + "step": 421376 + }, + { + "epoch": 1.01, + "learning_rate": 4.309287829959191e-05, + "loss": 3.7497, + "step": 421888 + }, + { + "epoch": 1.01, + "learning_rate": 4.308449235208139e-05, + "loss": 3.7752, + "step": 422400 + }, + { + "epoch": 1.01, + "learning_rate": 4.307610640457086e-05, + "loss": 3.7611, + "step": 422912 + }, + { + "epoch": 1.01, + "learning_rate": 4.306772045706034e-05, + "loss": 3.7719, + "step": 423424 + }, + { + "epoch": 1.01, + "learning_rate": 4.305935088835356e-05, + "loss": 3.7728, + "step": 423936 + }, + { + "epoch": 1.01, + "learning_rate": 4.305096494084304e-05, + "loss": 3.7507, + "step": 424448 + }, + { + "epoch": 1.01, + "learning_rate": 4.304257899333252e-05, + "loss": 3.7536, + "step": 424960 + }, + { + "epoch": 1.01, + "learning_rate": 4.3034193045822e-05, + "loss": 3.7561, + "step": 425472 + }, + { + "epoch": 1.01, + "learning_rate": 4.302580709831148e-05, + "loss": 3.7656, + "step": 425984 + }, + { + "epoch": 1.01, + "learning_rate": 4.301743752960469e-05, + "loss": 3.7622, + "step": 426496 + }, + { + "epoch": 1.01, + "learning_rate": 4.300905158209417e-05, + "loss": 3.7577, + "step": 427008 + }, + { + "epoch": 1.02, + "learning_rate": 4.300066563458365e-05, + "loss": 3.7583, + "step": 427520 + }, + { + "epoch": 1.02, + "learning_rate": 4.299227968707313e-05, + "loss": 3.7582, + "step": 428032 + }, + { + "epoch": 1.02, + "learning_rate": 4.2983910118366337e-05, + "loss": 3.7585, + "step": 428544 + }, + { + "epoch": 1.02, + "learning_rate": 4.2975524170855817e-05, + "loss": 3.7525, + "step": 429056 + }, + { + "epoch": 1.02, + "learning_rate": 4.2967138223345296e-05, + "loss": 3.7691, + "step": 429568 + }, + { + "epoch": 1.02, + "learning_rate": 4.2958752275834776e-05, + "loss": 3.7685, + "step": 430080 + }, + { + "epoch": 1.02, + "learning_rate": 4.2950366328324256e-05, + "loss": 3.7678, + "step": 430592 + }, + { + "epoch": 1.02, + "learning_rate": 4.294199675961747e-05, + "loss": 3.7491, + "step": 431104 + }, + { + "epoch": 1.02, + "learning_rate": 4.293361081210695e-05, + "loss": 3.7588, + "step": 431616 + }, + { + "epoch": 1.02, + "learning_rate": 4.292522486459643e-05, + "loss": 3.7588, + "step": 432128 + }, + { + "epoch": 1.02, + "learning_rate": 4.291683891708591e-05, + "loss": 3.7631, + "step": 432640 + }, + { + "epoch": 1.02, + "learning_rate": 4.290845296957539e-05, + "loss": 3.7623, + "step": 433152 + }, + { + "epoch": 1.02, + "learning_rate": 4.29000834008686e-05, + "loss": 3.7574, + "step": 433664 + }, + { + "epoch": 1.02, + "learning_rate": 4.289169745335808e-05, + "loss": 3.7466, + "step": 434176 + }, + { + "epoch": 1.02, + "learning_rate": 4.288331150584756e-05, + "loss": 3.7617, + "step": 434688 + }, + { + "epoch": 1.02, + "learning_rate": 4.287492555833704e-05, + "loss": 3.7501, + "step": 435200 + }, + { + "epoch": 1.02, + "learning_rate": 4.286653961082652e-05, + "loss": 3.7458, + "step": 435712 + }, + { + "epoch": 1.02, + "learning_rate": 4.285817004211973e-05, + "loss": 3.742, + "step": 436224 + }, + { + "epoch": 1.02, + "learning_rate": 4.284978409460921e-05, + "loss": 3.7569, + "step": 436736 + }, + { + "epoch": 1.02, + "learning_rate": 4.28413981470987e-05, + "loss": 3.75, + "step": 437248 + }, + { + "epoch": 1.02, + "learning_rate": 4.283301219958818e-05, + "loss": 3.7657, + "step": 437760 + }, + { + "epoch": 1.02, + "learning_rate": 4.2824642630881386e-05, + "loss": 3.7473, + "step": 438272 + }, + { + "epoch": 1.02, + "learning_rate": 4.2816256683370866e-05, + "loss": 3.7575, + "step": 438784 + }, + { + "epoch": 1.02, + "learning_rate": 4.2807870735860346e-05, + "loss": 3.755, + "step": 439296 + }, + { + "epoch": 1.02, + "learning_rate": 4.2799484788349826e-05, + "loss": 3.7449, + "step": 439808 + }, + { + "epoch": 1.02, + "learning_rate": 4.2791115219643035e-05, + "loss": 3.7682, + "step": 440320 + }, + { + "epoch": 1.02, + "learning_rate": 4.2782729272132515e-05, + "loss": 3.7616, + "step": 440832 + }, + { + "epoch": 1.02, + "learning_rate": 4.2774343324621995e-05, + "loss": 3.7526, + "step": 441344 + }, + { + "epoch": 1.02, + "learning_rate": 4.2765957377111475e-05, + "loss": 3.7537, + "step": 441856 + }, + { + "epoch": 1.02, + "learning_rate": 4.2757571429600955e-05, + "loss": 3.7518, + "step": 442368 + }, + { + "epoch": 1.02, + "learning_rate": 4.2749185482090435e-05, + "loss": 3.7565, + "step": 442880 + }, + { + "epoch": 1.02, + "learning_rate": 4.274081591338365e-05, + "loss": 3.7377, + "step": 443392 + }, + { + "epoch": 1.02, + "learning_rate": 4.273242996587313e-05, + "loss": 3.7647, + "step": 443904 + }, + { + "epoch": 1.02, + "learning_rate": 4.272404401836261e-05, + "loss": 3.7479, + "step": 444416 + }, + { + "epoch": 1.02, + "learning_rate": 4.271565807085209e-05, + "loss": 3.7531, + "step": 444928 + }, + { + "epoch": 1.02, + "learning_rate": 4.27072885021453e-05, + "loss": 3.7519, + "step": 445440 + }, + { + "epoch": 1.02, + "learning_rate": 4.269890255463478e-05, + "loss": 3.7491, + "step": 445952 + }, + { + "epoch": 1.02, + "learning_rate": 4.269051660712426e-05, + "loss": 3.747, + "step": 446464 + }, + { + "epoch": 1.02, + "learning_rate": 4.268213065961374e-05, + "loss": 3.7512, + "step": 446976 + }, + { + "epoch": 1.02, + "learning_rate": 4.267374471210322e-05, + "loss": 3.7484, + "step": 447488 + }, + { + "epoch": 1.02, + "learning_rate": 4.26653587645927e-05, + "loss": 3.7617, + "step": 448000 + }, + { + "epoch": 1.02, + "learning_rate": 4.265698919588591e-05, + "loss": 3.7545, + "step": 448512 + }, + { + "epoch": 1.02, + "learning_rate": 4.264860324837539e-05, + "loss": 3.7565, + "step": 449024 + }, + { + "epoch": 1.02, + "learning_rate": 4.264021730086487e-05, + "loss": 3.7356, + "step": 449536 + }, + { + "epoch": 1.02, + "learning_rate": 4.263183135335435e-05, + "loss": 3.762, + "step": 450048 + }, + { + "epoch": 1.02, + "learning_rate": 4.2623461784647564e-05, + "loss": 3.7522, + "step": 450560 + }, + { + "epoch": 1.02, + "learning_rate": 4.2615075837137044e-05, + "loss": 3.7565, + "step": 451072 + }, + { + "epoch": 1.02, + "learning_rate": 4.2606689889626524e-05, + "loss": 3.7492, + "step": 451584 + }, + { + "epoch": 1.02, + "learning_rate": 4.2598303942116e-05, + "loss": 3.7493, + "step": 452096 + }, + { + "epoch": 1.02, + "learning_rate": 4.258991799460548e-05, + "loss": 3.7596, + "step": 452608 + }, + { + "epoch": 1.02, + "learning_rate": 4.258153204709496e-05, + "loss": 3.7594, + "step": 453120 + }, + { + "epoch": 1.02, + "learning_rate": 4.257314609958444e-05, + "loss": 3.743, + "step": 453632 + }, + { + "epoch": 1.02, + "learning_rate": 4.256476015207392e-05, + "loss": 3.75, + "step": 454144 + }, + { + "epoch": 1.02, + "learning_rate": 4.2556390583367126e-05, + "loss": 3.7477, + "step": 454656 + }, + { + "epoch": 1.02, + "learning_rate": 4.2548004635856606e-05, + "loss": 3.7441, + "step": 455168 + }, + { + "epoch": 1.02, + "learning_rate": 4.253963506714982e-05, + "loss": 3.7588, + "step": 455680 + }, + { + "epoch": 1.02, + "learning_rate": 4.25312491196393e-05, + "loss": 3.7505, + "step": 456192 + }, + { + "epoch": 1.02, + "learning_rate": 4.252286317212878e-05, + "loss": 3.7528, + "step": 456704 + }, + { + "epoch": 1.02, + "learning_rate": 4.251447722461826e-05, + "loss": 3.7378, + "step": 457216 + }, + { + "epoch": 1.02, + "learning_rate": 4.250609127710774e-05, + "loss": 3.7508, + "step": 457728 + }, + { + "epoch": 1.03, + "eval_loss": 3.8685173988342285, + "eval_runtime": 308.0819, + "eval_samples_per_second": 1238.602, + "eval_steps_per_second": 38.707, + "step": 457920 + }, + { + "epoch": 0.0, + "learning_rate": 4.249770532959722e-05, + "loss": 3.7495, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.24893193820867e-05, + "loss": 3.7401, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.248093343457618e-05, + "loss": 3.7553, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.247254748706566e-05, + "loss": 3.7513, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.246416153955514e-05, + "loss": 3.7522, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.245577559204462e-05, + "loss": 3.7454, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.24473896445341e-05, + "loss": 3.7373, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.243900369702358e-05, + "loss": 3.7412, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.243065050712052e-05, + "loss": 3.7507, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.2422264559610006e-05, + "loss": 3.7585, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.2413878612099486e-05, + "loss": 3.7441, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.2405492664588966e-05, + "loss": 3.7558, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.2397123095882175e-05, + "loss": 3.738, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.2388737148371655e-05, + "loss": 3.7418, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.2380351200861135e-05, + "loss": 3.7518, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.2371965253350615e-05, + "loss": 3.7314, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.2363579305840095e-05, + "loss": 3.7372, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.2355209737133304e-05, + "loss": 3.7332, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.2346823789622784e-05, + "loss": 3.7406, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.2338437842112264e-05, + "loss": 3.7519, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.2330051894601744e-05, + "loss": 3.7443, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.2321665947091224e-05, + "loss": 3.7451, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.2313279999580704e-05, + "loss": 3.7331, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.2304894052070184e-05, + "loss": 3.7464, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.2296508104559664e-05, + "loss": 3.7342, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.228813853585288e-05, + "loss": 3.7367, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.227975258834236e-05, + "loss": 3.7316, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.227138301963557e-05, + "loss": 3.7372, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.226299707212505e-05, + "loss": 3.736, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.225461112461453e-05, + "loss": 3.7315, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.2246225177104e-05, + "loss": 3.7413, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.223785560839722e-05, + "loss": 3.7408, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.22294696608867e-05, + "loss": 3.7372, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.222108371337618e-05, + "loss": 3.7418, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.221269776586566e-05, + "loss": 3.7373, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.2204328197158874e-05, + "loss": 3.7375, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.2195942249648353e-05, + "loss": 3.7341, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.2187556302137833e-05, + "loss": 3.7216, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.217917035462731e-05, + "loss": 3.7213, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.2170784407116787e-05, + "loss": 3.7336, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.2162398459606267e-05, + "loss": 3.7298, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.2154012512095746e-05, + "loss": 3.7354, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.2145626564585226e-05, + "loss": 3.7317, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.2137256995878436e-05, + "loss": 3.733, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.212888742717165e-05, + "loss": 3.7405, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.212050147966113e-05, + "loss": 3.7351, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.211211553215061e-05, + "loss": 3.7397, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.210372958464009e-05, + "loss": 3.7234, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.209536001593331e-05, + "loss": 3.7151, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.208697406842278e-05, + "loss": 3.7478, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.207858812091226e-05, + "loss": 3.7321, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.207020217340174e-05, + "loss": 3.7265, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.206181622589122e-05, + "loss": 3.7284, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.205344665718443e-05, + "loss": 3.7315, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.204506070967391e-05, + "loss": 3.7167, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.203667476216339e-05, + "loss": 3.7325, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.202828881465287e-05, + "loss": 3.7327, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.201990286714235e-05, + "loss": 3.7294, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.2011516919631836e-05, + "loss": 3.743, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.2003130972121316e-05, + "loss": 3.7196, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.1994761403414525e-05, + "loss": 3.7223, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.1986375455904005e-05, + "loss": 3.7382, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.1977989508393485e-05, + "loss": 3.7153, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.1969603560882965e-05, + "loss": 3.7134, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.1961217613372445e-05, + "loss": 3.7263, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.1952848044665654e-05, + "loss": 3.7259, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.1944462097155134e-05, + "loss": 3.7167, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.1936076149644614e-05, + "loss": 3.7164, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.1927690202134094e-05, + "loss": 3.7168, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.1919304254623574e-05, + "loss": 3.7359, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.1910918307113054e-05, + "loss": 3.7298, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.1902532359602534e-05, + "loss": 3.7311, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.189416279089575e-05, + "loss": 3.733, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.188577684338523e-05, + "loss": 3.732, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.187739089587471e-05, + "loss": 3.7443, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.186900494836419e-05, + "loss": 3.7146, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.18606353796574e-05, + "loss": 3.7368, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.185224943214688e-05, + "loss": 3.7327, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.184386348463636e-05, + "loss": 3.7144, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.183547753712584e-05, + "loss": 3.7335, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.182710796841905e-05, + "loss": 3.7247, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.181872202090853e-05, + "loss": 3.7339, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.181033607339801e-05, + "loss": 3.7338, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.180195012588749e-05, + "loss": 3.7175, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.179356417837697e-05, + "loss": 3.7105, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.178519460967018e-05, + "loss": 3.7163, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.177680866215966e-05, + "loss": 3.7304, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.1768422714649136e-05, + "loss": 3.7234, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.1760036767138616e-05, + "loss": 3.72, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.175166719843183e-05, + "loss": 3.7237, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.174328125092131e-05, + "loss": 3.7174, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.1734895303410785e-05, + "loss": 3.7231, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.1726509355900265e-05, + "loss": 3.7163, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.1718123408389745e-05, + "loss": 3.73, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.1709737460879225e-05, + "loss": 3.7295, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.1701351513368705e-05, + "loss": 3.7284, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.169298194466192e-05, + "loss": 3.711, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.16845959971514e-05, + "loss": 3.7202, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.167621004964088e-05, + "loss": 3.7228, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.166782410213036e-05, + "loss": 3.7263, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.165943815461984e-05, + "loss": 3.7255, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.165106858591305e-05, + "loss": 3.7165, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.164268263840253e-05, + "loss": 3.7142, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.163429669089201e-05, + "loss": 3.7218, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.162591074338149e-05, + "loss": 3.7108, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.161752479587097e-05, + "loss": 3.7178, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.160915522716418e-05, + "loss": 3.698, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.160076927965366e-05, + "loss": 3.7238, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.1592383332143145e-05, + "loss": 3.7144, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.1583997384632625e-05, + "loss": 3.7242, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.1575611437122105e-05, + "loss": 3.7119, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.1567241868415314e-05, + "loss": 3.7211, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.1558855920904794e-05, + "loss": 3.7196, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.1550469973394274e-05, + "loss": 3.7045, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.1542084025883754e-05, + "loss": 3.733, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.153371445717696e-05, + "loss": 3.723, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.152532850966644e-05, + "loss": 3.7176, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.151694256215592e-05, + "loss": 3.7209, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.15085566146454e-05, + "loss": 3.7089, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.150018704593861e-05, + "loss": 3.7255, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.14918010984281e-05, + "loss": 3.7063, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.148341515091758e-05, + "loss": 3.7263, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.147502920340706e-05, + "loss": 3.7086, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.146665963470027e-05, + "loss": 3.718, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.145827368718975e-05, + "loss": 3.7109, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.144988773967923e-05, + "loss": 3.7141, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.144150179216871e-05, + "loss": 3.7132, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.143313222346192e-05, + "loss": 3.7121, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.14247462759514e-05, + "loss": 3.7154, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.141636032844088e-05, + "loss": 3.723, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.140797438093036e-05, + "loss": 3.715, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.1399604812223566e-05, + "loss": 3.7234, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.139121886471305e-05, + "loss": 3.6995, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.138283291720253e-05, + "loss": 3.7246, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.137444696969201e-05, + "loss": 3.7226, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.136606102218149e-05, + "loss": 3.7179, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.135767507467097e-05, + "loss": 3.7139, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.1349289127160446e-05, + "loss": 3.7157, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.134091955845366e-05, + "loss": 3.7183, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.133253361094314e-05, + "loss": 3.7266, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.132414766343262e-05, + "loss": 3.7063, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.1315761715922095e-05, + "loss": 3.7168, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.1307375768411575e-05, + "loss": 3.7128, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.129900619970479e-05, + "loss": 3.7093, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.129062025219427e-05, + "loss": 3.7181, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.128223430468375e-05, + "loss": 3.7168, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.127384835717323e-05, + "loss": 3.7172, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.1265478788466446e-05, + "loss": 3.703, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.125709284095592e-05, + "loss": 3.7217, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 3.858555793762207, + "eval_runtime": 302.8363, + "eval_samples_per_second": 1260.057, + "eval_steps_per_second": 39.378, + "step": 534240 + }, + { + "epoch": 1.0, + "learning_rate": 4.12487068934454e-05, + "loss": 3.7083, + "step": 534528 + }, + { + "epoch": 1.0, + "learning_rate": 4.124032094593488e-05, + "loss": 3.7053, + "step": 535040 + }, + { + "epoch": 1.0, + "learning_rate": 4.123193499842436e-05, + "loss": 3.7178, + "step": 535552 + }, + { + "epoch": 1.0, + "learning_rate": 4.122354905091384e-05, + "loss": 3.7166, + "step": 536064 + }, + { + "epoch": 1.0, + "learning_rate": 4.121517948220705e-05, + "loss": 3.7151, + "step": 536576 + }, + { + "epoch": 1.0, + "learning_rate": 4.120679353469653e-05, + "loss": 3.7132, + "step": 537088 + }, + { + "epoch": 1.0, + "learning_rate": 4.119840758718601e-05, + "loss": 3.7035, + "step": 537600 + }, + { + "epoch": 1.0, + "learning_rate": 4.119002163967549e-05, + "loss": 3.7057, + "step": 538112 + }, + { + "epoch": 1.0, + "learning_rate": 4.1181652070968704e-05, + "loss": 3.7176, + "step": 538624 + }, + { + "epoch": 1.0, + "learning_rate": 4.1173266123458184e-05, + "loss": 3.7206, + "step": 539136 + }, + { + "epoch": 1.0, + "learning_rate": 4.1164880175947664e-05, + "loss": 3.7122, + "step": 539648 + }, + { + "epoch": 1.0, + "learning_rate": 4.1156494228437144e-05, + "loss": 3.72, + "step": 540160 + }, + { + "epoch": 1.0, + "learning_rate": 4.114812465973035e-05, + "loss": 3.7092, + "step": 540672 + }, + { + "epoch": 1.0, + "learning_rate": 4.113973871221983e-05, + "loss": 3.7049, + "step": 541184 + }, + { + "epoch": 1.0, + "learning_rate": 4.113135276470931e-05, + "loss": 3.714, + "step": 541696 + }, + { + "epoch": 1.0, + "learning_rate": 4.112296681719879e-05, + "loss": 3.6969, + "step": 542208 + }, + { + "epoch": 1.0, + "learning_rate": 4.111458086968827e-05, + "loss": 3.7019, + "step": 542720 + }, + { + "epoch": 1.0, + "learning_rate": 4.110621130098148e-05, + "loss": 3.7003, + "step": 543232 + }, + { + "epoch": 1.0, + "learning_rate": 4.109782535347096e-05, + "loss": 3.7059, + "step": 543744 + }, + { + "epoch": 1.0, + "learning_rate": 4.108943940596044e-05, + "loss": 3.7146, + "step": 544256 + }, + { + "epoch": 1.0, + "learning_rate": 4.108105345844992e-05, + "loss": 3.7154, + "step": 544768 + }, + { + "epoch": 1.0, + "learning_rate": 4.107266751093941e-05, + "loss": 3.7076, + "step": 545280 + }, + { + "epoch": 1.0, + "learning_rate": 4.106429794223262e-05, + "loss": 3.6994, + "step": 545792 + }, + { + "epoch": 1.0, + "learning_rate": 4.10559119947221e-05, + "loss": 3.7122, + "step": 546304 + }, + { + "epoch": 1.0, + "learning_rate": 4.104752604721158e-05, + "loss": 3.6967, + "step": 546816 + }, + { + "epoch": 1.0, + "learning_rate": 4.103914009970106e-05, + "loss": 3.7058, + "step": 547328 + }, + { + "epoch": 1.0, + "learning_rate": 4.103075415219054e-05, + "loss": 3.6962, + "step": 547840 + }, + { + "epoch": 1.0, + "learning_rate": 4.1022384583483747e-05, + "loss": 3.7053, + "step": 548352 + }, + { + "epoch": 1.0, + "learning_rate": 4.1013998635973227e-05, + "loss": 3.6982, + "step": 548864 + }, + { + "epoch": 1.0, + "learning_rate": 4.1005612688462706e-05, + "loss": 3.7028, + "step": 549376 + }, + { + "epoch": 1.01, + "learning_rate": 4.0997226740952186e-05, + "loss": 3.7034, + "step": 549888 + }, + { + "epoch": 1.01, + "learning_rate": 4.0988857172245396e-05, + "loss": 3.7106, + "step": 550400 + }, + { + "epoch": 1.01, + "learning_rate": 4.0980471224734875e-05, + "loss": 3.7034, + "step": 550912 + }, + { + "epoch": 1.01, + "learning_rate": 4.097208527722436e-05, + "loss": 3.7018, + "step": 551424 + }, + { + "epoch": 1.01, + "learning_rate": 4.096369932971384e-05, + "loss": 3.7047, + "step": 551936 + }, + { + "epoch": 1.01, + "learning_rate": 4.095532976100705e-05, + "loss": 3.7011, + "step": 552448 + }, + { + "epoch": 1.01, + "learning_rate": 4.094694381349653e-05, + "loss": 3.7038, + "step": 552960 + }, + { + "epoch": 1.01, + "learning_rate": 4.093855786598601e-05, + "loss": 3.6851, + "step": 553472 + }, + { + "epoch": 1.01, + "learning_rate": 4.093017191847549e-05, + "loss": 3.69, + "step": 553984 + }, + { + "epoch": 1.01, + "learning_rate": 4.092178597096497e-05, + "loss": 3.6972, + "step": 554496 + }, + { + "epoch": 1.01, + "learning_rate": 4.091340002345445e-05, + "loss": 3.7025, + "step": 555008 + }, + { + "epoch": 1.01, + "learning_rate": 4.090503045474766e-05, + "loss": 3.7014, + "step": 555520 + }, + { + "epoch": 1.01, + "learning_rate": 4.089664450723714e-05, + "loss": 3.6982, + "step": 556032 + }, + { + "epoch": 1.01, + "learning_rate": 4.088825855972662e-05, + "loss": 3.6969, + "step": 556544 + }, + { + "epoch": 1.01, + "learning_rate": 4.08798726122161e-05, + "loss": 3.7091, + "step": 557056 + }, + { + "epoch": 1.01, + "learning_rate": 4.087148666470558e-05, + "loss": 3.696, + "step": 557568 + }, + { + "epoch": 1.01, + "learning_rate": 4.0863117095998796e-05, + "loss": 3.714, + "step": 558080 + }, + { + "epoch": 1.01, + "learning_rate": 4.0854731148488276e-05, + "loss": 3.6866, + "step": 558592 + }, + { + "epoch": 1.01, + "learning_rate": 4.0846345200977756e-05, + "loss": 3.6783, + "step": 559104 + }, + { + "epoch": 1.01, + "learning_rate": 4.083795925346723e-05, + "loss": 3.7175, + "step": 559616 + }, + { + "epoch": 1.01, + "learning_rate": 4.0829589684760445e-05, + "loss": 3.6964, + "step": 560128 + }, + { + "epoch": 1.01, + "learning_rate": 4.0821203737249925e-05, + "loss": 3.6986, + "step": 560640 + }, + { + "epoch": 1.01, + "learning_rate": 4.0812817789739405e-05, + "loss": 3.6954, + "step": 561152 + }, + { + "epoch": 1.01, + "learning_rate": 4.080443184222888e-05, + "loss": 3.6959, + "step": 561664 + }, + { + "epoch": 1.01, + "learning_rate": 4.079604589471836e-05, + "loss": 3.688, + "step": 562176 + }, + { + "epoch": 1.01, + "learning_rate": 4.0787676326011574e-05, + "loss": 3.6986, + "step": 562688 + }, + { + "epoch": 1.01, + "learning_rate": 4.0779290378501054e-05, + "loss": 3.6988, + "step": 563200 + }, + { + "epoch": 1.01, + "learning_rate": 4.0770904430990534e-05, + "loss": 3.6977, + "step": 563712 + }, + { + "epoch": 1.01, + "learning_rate": 4.0762518483480014e-05, + "loss": 3.7108, + "step": 564224 + }, + { + "epoch": 1.01, + "learning_rate": 4.075414891477323e-05, + "loss": 3.6899, + "step": 564736 + }, + { + "epoch": 1.01, + "learning_rate": 4.07457629672627e-05, + "loss": 3.6868, + "step": 565248 + }, + { + "epoch": 1.01, + "learning_rate": 4.073737701975218e-05, + "loss": 3.7068, + "step": 565760 + }, + { + "epoch": 1.01, + "learning_rate": 4.072899107224166e-05, + "loss": 3.68, + "step": 566272 + }, + { + "epoch": 1.01, + "learning_rate": 4.072062150353488e-05, + "loss": 3.6825, + "step": 566784 + }, + { + "epoch": 1.01, + "learning_rate": 4.071223555602435e-05, + "loss": 3.6914, + "step": 567296 + }, + { + "epoch": 1.01, + "learning_rate": 4.070384960851383e-05, + "loss": 3.6957, + "step": 567808 + }, + { + "epoch": 1.01, + "learning_rate": 4.069546366100331e-05, + "loss": 3.6813, + "step": 568320 + }, + { + "epoch": 1.01, + "learning_rate": 4.068709409229652e-05, + "loss": 3.6877, + "step": 568832 + }, + { + "epoch": 1.01, + "learning_rate": 4.067870814478601e-05, + "loss": 3.6836, + "step": 569344 + }, + { + "epoch": 1.01, + "learning_rate": 4.067032219727549e-05, + "loss": 3.6997, + "step": 569856 + }, + { + "epoch": 1.01, + "learning_rate": 4.066193624976497e-05, + "loss": 3.7002, + "step": 570368 + }, + { + "epoch": 1.01, + "learning_rate": 4.065355030225445e-05, + "loss": 3.6935, + "step": 570880 + }, + { + "epoch": 1.01, + "learning_rate": 4.0645180733547656e-05, + "loss": 3.6998, + "step": 571392 + }, + { + "epoch": 1.01, + "learning_rate": 4.0636794786037136e-05, + "loss": 3.7007, + "step": 571904 + }, + { + "epoch": 1.01, + "learning_rate": 4.0628408838526616e-05, + "loss": 3.7133, + "step": 572416 + }, + { + "epoch": 1.01, + "learning_rate": 4.0620022891016096e-05, + "loss": 3.6795, + "step": 572928 + }, + { + "epoch": 1.01, + "learning_rate": 4.0611653322309305e-05, + "loss": 3.7087, + "step": 573440 + }, + { + "epoch": 1.01, + "learning_rate": 4.0603267374798785e-05, + "loss": 3.6946, + "step": 573952 + }, + { + "epoch": 1.01, + "learning_rate": 4.0594881427288265e-05, + "loss": 3.6854, + "step": 574464 + }, + { + "epoch": 1.01, + "learning_rate": 4.0586495479777745e-05, + "loss": 3.6995, + "step": 574976 + }, + { + "epoch": 1.01, + "learning_rate": 4.057812591107096e-05, + "loss": 3.6952, + "step": 575488 + }, + { + "epoch": 1.01, + "learning_rate": 4.056973996356044e-05, + "loss": 3.6981, + "step": 576000 + }, + { + "epoch": 1.01, + "learning_rate": 4.056135401604992e-05, + "loss": 3.7043, + "step": 576512 + }, + { + "epoch": 1.01, + "learning_rate": 4.05529680685394e-05, + "loss": 3.6822, + "step": 577024 + }, + { + "epoch": 1.01, + "learning_rate": 4.054459849983261e-05, + "loss": 3.6773, + "step": 577536 + }, + { + "epoch": 1.01, + "learning_rate": 4.053621255232209e-05, + "loss": 3.6891, + "step": 578048 + }, + { + "epoch": 1.01, + "learning_rate": 4.052782660481157e-05, + "loss": 3.6996, + "step": 578560 + }, + { + "epoch": 1.01, + "learning_rate": 4.051944065730105e-05, + "loss": 3.6943, + "step": 579072 + }, + { + "epoch": 1.01, + "learning_rate": 4.051107108859426e-05, + "loss": 3.6864, + "step": 579584 + }, + { + "epoch": 1.02, + "learning_rate": 4.050268514108374e-05, + "loss": 3.6868, + "step": 580096 + }, + { + "epoch": 1.02, + "learning_rate": 4.049429919357322e-05, + "loss": 3.6901, + "step": 580608 + }, + { + "epoch": 1.02, + "learning_rate": 4.04859132460627e-05, + "loss": 3.6907, + "step": 581120 + }, + { + "epoch": 1.02, + "learning_rate": 4.0477543677355915e-05, + "loss": 3.6895, + "step": 581632 + }, + { + "epoch": 1.02, + "learning_rate": 4.0469157729845395e-05, + "loss": 3.695, + "step": 582144 + }, + { + "epoch": 1.02, + "learning_rate": 4.0460771782334875e-05, + "loss": 3.6988, + "step": 582656 + }, + { + "epoch": 1.02, + "learning_rate": 4.0452385834824355e-05, + "loss": 3.6964, + "step": 583168 + }, + { + "epoch": 1.02, + "learning_rate": 4.0443999887313835e-05, + "loss": 3.6823, + "step": 583680 + }, + { + "epoch": 1.02, + "learning_rate": 4.0435630318607044e-05, + "loss": 3.6915, + "step": 584192 + }, + { + "epoch": 1.02, + "learning_rate": 4.0427244371096524e-05, + "loss": 3.6866, + "step": 584704 + }, + { + "epoch": 1.02, + "learning_rate": 4.0418858423586004e-05, + "loss": 3.6952, + "step": 585216 + }, + { + "epoch": 1.02, + "learning_rate": 4.0410472476075483e-05, + "loss": 3.6948, + "step": 585728 + }, + { + "epoch": 1.02, + "learning_rate": 4.0402086528564963e-05, + "loss": 3.691, + "step": 586240 + }, + { + "epoch": 1.02, + "learning_rate": 4.039370058105444e-05, + "loss": 3.6783, + "step": 586752 + }, + { + "epoch": 1.02, + "learning_rate": 4.038533101234765e-05, + "loss": 3.6859, + "step": 587264 + }, + { + "epoch": 1.02, + "learning_rate": 4.037694506483713e-05, + "loss": 3.685, + "step": 587776 + }, + { + "epoch": 1.02, + "learning_rate": 4.036855911732661e-05, + "loss": 3.6822, + "step": 588288 + }, + { + "epoch": 1.02, + "learning_rate": 4.036017316981609e-05, + "loss": 3.6696, + "step": 588800 + }, + { + "epoch": 1.02, + "learning_rate": 4.035180360110931e-05, + "loss": 3.6919, + "step": 589312 + }, + { + "epoch": 1.02, + "learning_rate": 4.034341765359879e-05, + "loss": 3.6867, + "step": 589824 + }, + { + "epoch": 1.02, + "learning_rate": 4.033503170608827e-05, + "loss": 3.6885, + "step": 590336 + }, + { + "epoch": 1.02, + "learning_rate": 4.032664575857775e-05, + "loss": 3.6778, + "step": 590848 + }, + { + "epoch": 1.02, + "learning_rate": 4.031825981106723e-05, + "loss": 3.6959, + "step": 591360 + }, + { + "epoch": 1.02, + "learning_rate": 4.030989024236044e-05, + "loss": 3.6871, + "step": 591872 + }, + { + "epoch": 1.02, + "learning_rate": 4.030150429484992e-05, + "loss": 3.6775, + "step": 592384 + }, + { + "epoch": 1.02, + "learning_rate": 4.02931183473394e-05, + "loss": 3.6999, + "step": 592896 + }, + { + "epoch": 1.02, + "learning_rate": 4.028473239982888e-05, + "loss": 3.6921, + "step": 593408 + }, + { + "epoch": 1.02, + "learning_rate": 4.0276362831122086e-05, + "loss": 3.6835, + "step": 593920 + }, + { + "epoch": 1.02, + "learning_rate": 4.0267976883611566e-05, + "loss": 3.6946, + "step": 594432 + }, + { + "epoch": 1.02, + "learning_rate": 4.0259590936101046e-05, + "loss": 3.6786, + "step": 594944 + }, + { + "epoch": 1.02, + "learning_rate": 4.025120498859053e-05, + "loss": 3.6945, + "step": 595456 + }, + { + "epoch": 1.02, + "learning_rate": 4.024283541988374e-05, + "loss": 3.6789, + "step": 595968 + }, + { + "epoch": 1.02, + "learning_rate": 4.023444947237322e-05, + "loss": 3.6894, + "step": 596480 + }, + { + "epoch": 1.02, + "learning_rate": 4.02260635248627e-05, + "loss": 3.6799, + "step": 596992 + }, + { + "epoch": 1.02, + "learning_rate": 4.021767757735218e-05, + "loss": 3.6877, + "step": 597504 + }, + { + "epoch": 1.02, + "learning_rate": 4.020930800864539e-05, + "loss": 3.6807, + "step": 598016 + }, + { + "epoch": 1.02, + "learning_rate": 4.020092206113487e-05, + "loss": 3.6831, + "step": 598528 + }, + { + "epoch": 1.02, + "learning_rate": 4.019253611362435e-05, + "loss": 3.6787, + "step": 599040 + }, + { + "epoch": 1.02, + "learning_rate": 4.018415016611383e-05, + "loss": 3.6844, + "step": 599552 + }, + { + "epoch": 1.02, + "learning_rate": 4.017578059740704e-05, + "loss": 3.6858, + "step": 600064 + }, + { + "epoch": 1.02, + "learning_rate": 4.016739464989652e-05, + "loss": 3.6941, + "step": 600576 + }, + { + "epoch": 1.02, + "learning_rate": 4.0159008702386e-05, + "loss": 3.6797, + "step": 601088 + }, + { + "epoch": 1.02, + "learning_rate": 4.0150622754875486e-05, + "loss": 3.6971, + "step": 601600 + }, + { + "epoch": 1.02, + "learning_rate": 4.014223680736496e-05, + "loss": 3.6674, + "step": 602112 + }, + { + "epoch": 1.02, + "learning_rate": 4.0133867238658175e-05, + "loss": 3.6938, + "step": 602624 + }, + { + "epoch": 1.02, + "learning_rate": 4.0125481291147655e-05, + "loss": 3.6903, + "step": 603136 + }, + { + "epoch": 1.02, + "learning_rate": 4.011709534363713e-05, + "loss": 3.6871, + "step": 603648 + }, + { + "epoch": 1.02, + "learning_rate": 4.010870939612661e-05, + "loss": 3.6818, + "step": 604160 + }, + { + "epoch": 1.02, + "learning_rate": 4.010032344861609e-05, + "loss": 3.6877, + "step": 604672 + }, + { + "epoch": 1.02, + "learning_rate": 4.0091953879909304e-05, + "loss": 3.688, + "step": 605184 + }, + { + "epoch": 1.02, + "learning_rate": 4.008356793239878e-05, + "loss": 3.6985, + "step": 605696 + }, + { + "epoch": 1.02, + "learning_rate": 4.007518198488826e-05, + "loss": 3.6748, + "step": 606208 + }, + { + "epoch": 1.02, + "learning_rate": 4.006679603737774e-05, + "loss": 3.6838, + "step": 606720 + }, + { + "epoch": 1.02, + "learning_rate": 4.005842646867095e-05, + "loss": 3.6811, + "step": 607232 + }, + { + "epoch": 1.02, + "learning_rate": 4.005004052116043e-05, + "loss": 3.6837, + "step": 607744 + }, + { + "epoch": 1.02, + "learning_rate": 4.004165457364991e-05, + "loss": 3.6832, + "step": 608256 + }, + { + "epoch": 1.02, + "learning_rate": 4.003326862613939e-05, + "loss": 3.6856, + "step": 608768 + }, + { + "epoch": 1.02, + "learning_rate": 4.00248990574326e-05, + "loss": 3.6888, + "step": 609280 + }, + { + "epoch": 1.02, + "learning_rate": 4.001651310992208e-05, + "loss": 3.6717, + "step": 609792 + }, + { + "epoch": 1.02, + "learning_rate": 4.000812716241156e-05, + "loss": 3.6907, + "step": 610304 + }, + { + "epoch": 1.03, + "eval_loss": 3.851924180984497, + "eval_runtime": 302.4466, + "eval_samples_per_second": 1261.681, + "eval_steps_per_second": 39.428, + "step": 610560 + }, + { + "epoch": 0.0, + "learning_rate": 3.999974121490104e-05, + "loss": 3.6818, + "step": 610816 + }, + { + "epoch": 0.0, + "learning_rate": 3.999135526739052e-05, + "loss": 3.6785, + "step": 611328 + }, + { + "epoch": 0.0, + "learning_rate": 3.998296931988e-05, + "loss": 3.6831, + "step": 611840 + }, + { + "epoch": 0.0, + "learning_rate": 3.997458337236948e-05, + "loss": 3.6857, + "step": 612352 + }, + { + "epoch": 0.0, + "learning_rate": 3.996619742485896e-05, + "loss": 3.6892, + "step": 612864 + }, + { + "epoch": 0.0, + "learning_rate": 3.995782785615218e-05, + "loss": 3.6794, + "step": 613376 + }, + { + "epoch": 0.0, + "learning_rate": 3.994944190864166e-05, + "loss": 3.6764, + "step": 613888 + }, + { + "epoch": 0.0, + "learning_rate": 3.994105596113114e-05, + "loss": 3.6789, + "step": 614400 + }, + { + "epoch": 0.0, + "learning_rate": 3.993267001362062e-05, + "loss": 3.6849, + "step": 614912 + }, + { + "epoch": 0.0, + "learning_rate": 3.992430044491383e-05, + "loss": 3.6923, + "step": 615424 + }, + { + "epoch": 0.0, + "learning_rate": 3.991591449740331e-05, + "loss": 3.6844, + "step": 615936 + }, + { + "epoch": 0.0, + "learning_rate": 3.990752854989279e-05, + "loss": 3.6878, + "step": 616448 + }, + { + "epoch": 0.0, + "learning_rate": 3.9899158981185996e-05, + "loss": 3.6759, + "step": 616960 + }, + { + "epoch": 0.0, + "learning_rate": 3.9890773033675476e-05, + "loss": 3.6748, + "step": 617472 + }, + { + "epoch": 0.0, + "learning_rate": 3.9882387086164956e-05, + "loss": 3.6868, + "step": 617984 + }, + { + "epoch": 0.0, + "learning_rate": 3.9874001138654436e-05, + "loss": 3.6695, + "step": 618496 + }, + { + "epoch": 0.0, + "learning_rate": 3.9865615191143916e-05, + "loss": 3.6735, + "step": 619008 + }, + { + "epoch": 0.0, + "learning_rate": 3.9857229243633396e-05, + "loss": 3.6712, + "step": 619520 + }, + { + "epoch": 0.0, + "learning_rate": 3.9848843296122876e-05, + "loss": 3.6771, + "step": 620032 + }, + { + "epoch": 0.0, + "learning_rate": 3.9840457348612356e-05, + "loss": 3.6824, + "step": 620544 + }, + { + "epoch": 0.0, + "learning_rate": 3.983208777990557e-05, + "loss": 3.6891, + "step": 621056 + }, + { + "epoch": 0.0, + "learning_rate": 3.982370183239505e-05, + "loss": 3.6787, + "step": 621568 + }, + { + "epoch": 0.0, + "learning_rate": 3.981531588488453e-05, + "loss": 3.6706, + "step": 622080 + }, + { + "epoch": 0.0, + "learning_rate": 3.980692993737401e-05, + "loss": 3.6792, + "step": 622592 + }, + { + "epoch": 0.0, + "learning_rate": 3.979856036866722e-05, + "loss": 3.6729, + "step": 623104 + }, + { + "epoch": 0.0, + "learning_rate": 3.97901744211567e-05, + "loss": 3.6772, + "step": 623616 + }, + { + "epoch": 0.0, + "learning_rate": 3.978178847364618e-05, + "loss": 3.6641, + "step": 624128 + }, + { + "epoch": 0.0, + "learning_rate": 3.977340252613566e-05, + "loss": 3.6767, + "step": 624640 + }, + { + "epoch": 0.0, + "learning_rate": 3.976503295742887e-05, + "loss": 3.6732, + "step": 625152 + }, + { + "epoch": 0.0, + "learning_rate": 3.975664700991835e-05, + "loss": 3.6685, + "step": 625664 + }, + { + "epoch": 0.01, + "learning_rate": 3.974826106240783e-05, + "loss": 3.6728, + "step": 626176 + }, + { + "epoch": 0.01, + "learning_rate": 3.973987511489731e-05, + "loss": 3.6844, + "step": 626688 + }, + { + "epoch": 0.01, + "learning_rate": 3.973148916738679e-05, + "loss": 3.6723, + "step": 627200 + }, + { + "epoch": 0.01, + "learning_rate": 3.9723119598680005e-05, + "loss": 3.6729, + "step": 627712 + }, + { + "epoch": 0.01, + "learning_rate": 3.9714733651169485e-05, + "loss": 3.6752, + "step": 628224 + }, + { + "epoch": 0.01, + "learning_rate": 3.9706347703658965e-05, + "loss": 3.6769, + "step": 628736 + }, + { + "epoch": 0.01, + "learning_rate": 3.969796175614844e-05, + "loss": 3.6713, + "step": 629248 + }, + { + "epoch": 0.01, + "learning_rate": 3.9689592187441654e-05, + "loss": 3.6584, + "step": 629760 + }, + { + "epoch": 0.01, + "learning_rate": 3.9681206239931134e-05, + "loss": 3.6634, + "step": 630272 + }, + { + "epoch": 0.01, + "learning_rate": 3.9672820292420614e-05, + "loss": 3.6685, + "step": 630784 + }, + { + "epoch": 0.01, + "learning_rate": 3.966443434491009e-05, + "loss": 3.6719, + "step": 631296 + }, + { + "epoch": 0.01, + "learning_rate": 3.96560647762033e-05, + "loss": 3.6732, + "step": 631808 + }, + { + "epoch": 0.01, + "learning_rate": 3.964767882869278e-05, + "loss": 3.671, + "step": 632320 + }, + { + "epoch": 0.01, + "learning_rate": 3.963929288118226e-05, + "loss": 3.6692, + "step": 632832 + }, + { + "epoch": 0.01, + "learning_rate": 3.963090693367174e-05, + "loss": 3.6779, + "step": 633344 + }, + { + "epoch": 0.01, + "learning_rate": 3.962252098616122e-05, + "loss": 3.6688, + "step": 633856 + }, + { + "epoch": 0.01, + "learning_rate": 3.961415141745444e-05, + "loss": 3.6824, + "step": 634368 + }, + { + "epoch": 0.01, + "learning_rate": 3.960576546994391e-05, + "loss": 3.6629, + "step": 634880 + }, + { + "epoch": 0.01, + "learning_rate": 3.959737952243339e-05, + "loss": 3.6488, + "step": 635392 + }, + { + "epoch": 0.01, + "learning_rate": 3.958899357492287e-05, + "loss": 3.6889, + "step": 635904 + }, + { + "epoch": 0.01, + "learning_rate": 3.958062400621609e-05, + "loss": 3.6674, + "step": 636416 + }, + { + "epoch": 0.01, + "learning_rate": 3.957223805870556e-05, + "loss": 3.6737, + "step": 636928 + }, + { + "epoch": 0.01, + "learning_rate": 3.956385211119504e-05, + "loss": 3.6666, + "step": 637440 + }, + { + "epoch": 0.01, + "learning_rate": 3.955546616368452e-05, + "loss": 3.6647, + "step": 637952 + }, + { + "epoch": 0.01, + "learning_rate": 3.9547096594977737e-05, + "loss": 3.6609, + "step": 638464 + }, + { + "epoch": 0.01, + "learning_rate": 3.9538710647467217e-05, + "loss": 3.6673, + "step": 638976 + }, + { + "epoch": 0.01, + "learning_rate": 3.9530324699956696e-05, + "loss": 3.6734, + "step": 639488 + }, + { + "epoch": 0.01, + "learning_rate": 3.9521938752446176e-05, + "loss": 3.6703, + "step": 640000 + }, + { + "epoch": 0.01, + "learning_rate": 3.9513552804935656e-05, + "loss": 3.6828, + "step": 640512 + }, + { + "epoch": 0.01, + "learning_rate": 3.9505183236228865e-05, + "loss": 3.6604, + "step": 641024 + }, + { + "epoch": 0.01, + "learning_rate": 3.9496797288718345e-05, + "loss": 3.6583, + "step": 641536 + }, + { + "epoch": 0.01, + "learning_rate": 3.9488411341207825e-05, + "loss": 3.6799, + "step": 642048 + }, + { + "epoch": 0.01, + "learning_rate": 3.9480025393697305e-05, + "loss": 3.6509, + "step": 642560 + }, + { + "epoch": 0.01, + "learning_rate": 3.9471639446186785e-05, + "loss": 3.6524, + "step": 643072 + }, + { + "epoch": 0.01, + "learning_rate": 3.9463269877479994e-05, + "loss": 3.6666, + "step": 643584 + }, + { + "epoch": 0.01, + "learning_rate": 3.9454883929969474e-05, + "loss": 3.6655, + "step": 644096 + }, + { + "epoch": 0.01, + "learning_rate": 3.9446497982458954e-05, + "loss": 3.6551, + "step": 644608 + }, + { + "epoch": 0.01, + "learning_rate": 3.943811203494844e-05, + "loss": 3.6591, + "step": 645120 + }, + { + "epoch": 0.01, + "learning_rate": 3.942972608743792e-05, + "loss": 3.6571, + "step": 645632 + }, + { + "epoch": 0.01, + "learning_rate": 3.942135651873113e-05, + "loss": 3.6733, + "step": 646144 + }, + { + "epoch": 0.01, + "learning_rate": 3.941297057122061e-05, + "loss": 3.6685, + "step": 646656 + }, + { + "epoch": 0.01, + "learning_rate": 3.940458462371009e-05, + "loss": 3.6703, + "step": 647168 + }, + { + "epoch": 0.01, + "learning_rate": 3.939619867619957e-05, + "loss": 3.6733, + "step": 647680 + }, + { + "epoch": 0.01, + "learning_rate": 3.938781272868905e-05, + "loss": 3.6736, + "step": 648192 + }, + { + "epoch": 0.01, + "learning_rate": 3.937944315998226e-05, + "loss": 3.6841, + "step": 648704 + }, + { + "epoch": 0.01, + "learning_rate": 3.937105721247174e-05, + "loss": 3.6533, + "step": 649216 + }, + { + "epoch": 0.01, + "learning_rate": 3.936267126496122e-05, + "loss": 3.6804, + "step": 649728 + }, + { + "epoch": 0.01, + "learning_rate": 3.93542853174507e-05, + "loss": 3.6627, + "step": 650240 + }, + { + "epoch": 0.01, + "learning_rate": 3.934591574874391e-05, + "loss": 3.6591, + "step": 650752 + }, + { + "epoch": 0.01, + "learning_rate": 3.9337529801233395e-05, + "loss": 3.6734, + "step": 651264 + }, + { + "epoch": 0.01, + "learning_rate": 3.9329143853722875e-05, + "loss": 3.6695, + "step": 651776 + }, + { + "epoch": 0.01, + "learning_rate": 3.9320757906212355e-05, + "loss": 3.6701, + "step": 652288 + }, + { + "epoch": 0.01, + "learning_rate": 3.9312388337505564e-05, + "loss": 3.6801, + "step": 652800 + }, + { + "epoch": 0.01, + "learning_rate": 3.9304002389995044e-05, + "loss": 3.6552, + "step": 653312 + }, + { + "epoch": 0.01, + "learning_rate": 3.9295616442484524e-05, + "loss": 3.6453, + "step": 653824 + }, + { + "epoch": 0.01, + "learning_rate": 3.9287230494974004e-05, + "loss": 3.663, + "step": 654336 + }, + { + "epoch": 0.01, + "learning_rate": 3.927886092626721e-05, + "loss": 3.6723, + "step": 654848 + }, + { + "epoch": 0.01, + "learning_rate": 3.927047497875669e-05, + "loss": 3.6664, + "step": 655360 + }, + { + "epoch": 0.01, + "learning_rate": 3.926208903124617e-05, + "loss": 3.6624, + "step": 655872 + }, + { + "epoch": 0.02, + "learning_rate": 3.925370308373565e-05, + "loss": 3.6586, + "step": 656384 + }, + { + "epoch": 0.02, + "learning_rate": 3.924533351502886e-05, + "loss": 3.6604, + "step": 656896 + }, + { + "epoch": 0.02, + "learning_rate": 3.923694756751835e-05, + "loss": 3.6665, + "step": 657408 + }, + { + "epoch": 0.02, + "learning_rate": 3.922856162000783e-05, + "loss": 3.6613, + "step": 657920 + }, + { + "epoch": 0.02, + "learning_rate": 3.922017567249731e-05, + "loss": 3.6674, + "step": 658432 + }, + { + "epoch": 0.02, + "learning_rate": 3.921178972498679e-05, + "loss": 3.672, + "step": 658944 + }, + { + "epoch": 0.02, + "learning_rate": 3.920342015628e-05, + "loss": 3.6704, + "step": 659456 + }, + { + "epoch": 0.02, + "learning_rate": 3.919503420876948e-05, + "loss": 3.6574, + "step": 659968 + }, + { + "epoch": 0.02, + "learning_rate": 3.918664826125896e-05, + "loss": 3.6602, + "step": 660480 + }, + { + "epoch": 0.02, + "learning_rate": 3.917826231374844e-05, + "loss": 3.6609, + "step": 660992 + }, + { + "epoch": 0.02, + "learning_rate": 3.9169892745041646e-05, + "loss": 3.6658, + "step": 661504 + }, + { + "epoch": 0.02, + "learning_rate": 3.9161506797531126e-05, + "loss": 3.6693, + "step": 662016 + }, + { + "epoch": 0.02, + "learning_rate": 3.9153120850020606e-05, + "loss": 3.6641, + "step": 662528 + }, + { + "epoch": 0.02, + "learning_rate": 3.9144734902510086e-05, + "loss": 3.6552, + "step": 663040 + }, + { + "epoch": 0.02, + "learning_rate": 3.91363653338033e-05, + "loss": 3.6537, + "step": 663552 + }, + { + "epoch": 0.02, + "learning_rate": 3.912797938629278e-05, + "loss": 3.6603, + "step": 664064 + }, + { + "epoch": 0.02, + "learning_rate": 3.911959343878226e-05, + "loss": 3.6541, + "step": 664576 + }, + { + "epoch": 0.02, + "learning_rate": 3.911120749127174e-05, + "loss": 3.6411, + "step": 665088 + }, + { + "epoch": 0.02, + "learning_rate": 3.910283792256495e-05, + "loss": 3.6666, + "step": 665600 + }, + { + "epoch": 0.02, + "learning_rate": 3.909445197505443e-05, + "loss": 3.6573, + "step": 666112 + }, + { + "epoch": 0.02, + "learning_rate": 3.908606602754391e-05, + "loss": 3.6612, + "step": 666624 + }, + { + "epoch": 0.02, + "learning_rate": 3.907768008003339e-05, + "loss": 3.6489, + "step": 667136 + }, + { + "epoch": 0.02, + "learning_rate": 3.90693105113266e-05, + "loss": 3.667, + "step": 667648 + }, + { + "epoch": 0.02, + "learning_rate": 3.906092456381608e-05, + "loss": 3.6599, + "step": 668160 + }, + { + "epoch": 0.02, + "learning_rate": 3.905253861630556e-05, + "loss": 3.6491, + "step": 668672 + }, + { + "epoch": 0.02, + "learning_rate": 3.904415266879504e-05, + "loss": 3.6738, + "step": 669184 + }, + { + "epoch": 0.02, + "learning_rate": 3.9035783100088256e-05, + "loss": 3.6674, + "step": 669696 + }, + { + "epoch": 0.02, + "learning_rate": 3.9027397152577736e-05, + "loss": 3.66, + "step": 670208 + }, + { + "epoch": 0.02, + "learning_rate": 3.9019011205067216e-05, + "loss": 3.6645, + "step": 670720 + }, + { + "epoch": 0.02, + "learning_rate": 3.9010625257556696e-05, + "loss": 3.6495, + "step": 671232 + }, + { + "epoch": 0.02, + "learning_rate": 3.900223931004617e-05, + "loss": 3.6652, + "step": 671744 + }, + { + "epoch": 0.02, + "learning_rate": 3.8993869741339385e-05, + "loss": 3.6557, + "step": 672256 + }, + { + "epoch": 0.02, + "learning_rate": 3.8985483793828865e-05, + "loss": 3.6626, + "step": 672768 + }, + { + "epoch": 0.02, + "learning_rate": 3.897709784631834e-05, + "loss": 3.6523, + "step": 673280 + }, + { + "epoch": 0.02, + "learning_rate": 3.896871189880782e-05, + "loss": 3.6637, + "step": 673792 + }, + { + "epoch": 0.02, + "learning_rate": 3.8960342330101034e-05, + "loss": 3.6554, + "step": 674304 + }, + { + "epoch": 0.02, + "learning_rate": 3.8951956382590514e-05, + "loss": 3.6545, + "step": 674816 + }, + { + "epoch": 0.02, + "learning_rate": 3.8943570435079994e-05, + "loss": 3.651, + "step": 675328 + }, + { + "epoch": 0.02, + "learning_rate": 3.8935184487569473e-05, + "loss": 3.6584, + "step": 675840 + }, + { + "epoch": 0.02, + "learning_rate": 3.892681491886269e-05, + "loss": 3.6554, + "step": 676352 + }, + { + "epoch": 0.02, + "learning_rate": 3.891842897135217e-05, + "loss": 3.6649, + "step": 676864 + }, + { + "epoch": 0.02, + "learning_rate": 3.891004302384164e-05, + "loss": 3.6556, + "step": 677376 + }, + { + "epoch": 0.02, + "learning_rate": 3.890165707633112e-05, + "loss": 3.6724, + "step": 677888 + }, + { + "epoch": 0.02, + "learning_rate": 3.889328750762434e-05, + "loss": 3.6403, + "step": 678400 + }, + { + "epoch": 0.02, + "learning_rate": 3.888490156011381e-05, + "loss": 3.6649, + "step": 678912 + }, + { + "epoch": 0.02, + "learning_rate": 3.887651561260329e-05, + "loss": 3.665, + "step": 679424 + }, + { + "epoch": 0.02, + "learning_rate": 3.886812966509277e-05, + "loss": 3.6643, + "step": 679936 + }, + { + "epoch": 0.02, + "learning_rate": 3.885976009638599e-05, + "loss": 3.6539, + "step": 680448 + }, + { + "epoch": 0.02, + "learning_rate": 3.885137414887546e-05, + "loss": 3.659, + "step": 680960 + }, + { + "epoch": 0.02, + "learning_rate": 3.884298820136494e-05, + "loss": 3.6579, + "step": 681472 + }, + { + "epoch": 0.02, + "learning_rate": 3.883460225385443e-05, + "loss": 3.6762, + "step": 681984 + }, + { + "epoch": 0.02, + "learning_rate": 3.882621630634391e-05, + "loss": 3.649, + "step": 682496 + }, + { + "epoch": 0.02, + "learning_rate": 3.8817846737637116e-05, + "loss": 3.6557, + "step": 683008 + }, + { + "epoch": 0.02, + "learning_rate": 3.8809460790126596e-05, + "loss": 3.6536, + "step": 683520 + }, + { + "epoch": 0.02, + "learning_rate": 3.8801074842616076e-05, + "loss": 3.6609, + "step": 684032 + }, + { + "epoch": 0.02, + "learning_rate": 3.8792688895105556e-05, + "loss": 3.6504, + "step": 684544 + }, + { + "epoch": 0.02, + "learning_rate": 3.8784319326398765e-05, + "loss": 3.6614, + "step": 685056 + }, + { + "epoch": 0.02, + "learning_rate": 3.8775933378888245e-05, + "loss": 3.6578, + "step": 685568 + }, + { + "epoch": 0.02, + "learning_rate": 3.8767547431377725e-05, + "loss": 3.6536, + "step": 686080 + }, + { + "epoch": 0.02, + "learning_rate": 3.8759161483867205e-05, + "loss": 3.6607, + "step": 686592 + }, + { + "epoch": 0.03, + "eval_loss": 3.847529888153076, + "eval_runtime": 302.585, + "eval_samples_per_second": 1261.104, + "eval_steps_per_second": 39.41, + "step": 686880 + }, + { + "epoch": 1.0, + "learning_rate": 3.8750791915160414e-05, + "loss": 3.6506, + "step": 687104 + }, + { + "epoch": 1.0, + "learning_rate": 3.8742405967649894e-05, + "loss": 3.6503, + "step": 687616 + }, + { + "epoch": 1.0, + "learning_rate": 3.873402002013938e-05, + "loss": 3.6603, + "step": 688128 + }, + { + "epoch": 1.0, + "learning_rate": 3.872563407262886e-05, + "loss": 3.6598, + "step": 688640 + }, + { + "epoch": 1.0, + "learning_rate": 3.871726450392207e-05, + "loss": 3.6645, + "step": 689152 + }, + { + "epoch": 1.0, + "learning_rate": 3.870887855641155e-05, + "loss": 3.6554, + "step": 689664 + }, + { + "epoch": 1.0, + "learning_rate": 3.870049260890103e-05, + "loss": 3.651, + "step": 690176 + }, + { + "epoch": 1.0, + "learning_rate": 3.869210666139051e-05, + "loss": 3.6525, + "step": 690688 + }, + { + "epoch": 1.0, + "learning_rate": 3.868373709268372e-05, + "loss": 3.6528, + "step": 691200 + }, + { + "epoch": 1.0, + "learning_rate": 3.86753511451732e-05, + "loss": 3.6661, + "step": 691712 + }, + { + "epoch": 1.0, + "learning_rate": 3.866696519766268e-05, + "loss": 3.6588, + "step": 692224 + }, + { + "epoch": 1.0, + "learning_rate": 3.865857925015216e-05, + "loss": 3.66, + "step": 692736 + }, + { + "epoch": 1.0, + "learning_rate": 3.865020968144537e-05, + "loss": 3.6603, + "step": 693248 + }, + { + "epoch": 1.0, + "learning_rate": 3.864182373393485e-05, + "loss": 3.6427, + "step": 693760 + }, + { + "epoch": 1.0, + "learning_rate": 3.8633437786424334e-05, + "loss": 3.6597, + "step": 694272 + }, + { + "epoch": 1.0, + "learning_rate": 3.8625051838913814e-05, + "loss": 3.6448, + "step": 694784 + }, + { + "epoch": 1.0, + "learning_rate": 3.8616665891403294e-05, + "loss": 3.6454, + "step": 695296 + }, + { + "epoch": 1.0, + "learning_rate": 3.8608296322696503e-05, + "loss": 3.6487, + "step": 695808 + }, + { + "epoch": 1.0, + "learning_rate": 3.8599910375185983e-05, + "loss": 3.6467, + "step": 696320 + }, + { + "epoch": 1.0, + "learning_rate": 3.8591524427675463e-05, + "loss": 3.6547, + "step": 696832 + }, + { + "epoch": 1.0, + "learning_rate": 3.858313848016494e-05, + "loss": 3.6645, + "step": 697344 + }, + { + "epoch": 1.0, + "learning_rate": 3.857476891145815e-05, + "loss": 3.6573, + "step": 697856 + }, + { + "epoch": 1.0, + "learning_rate": 3.856638296394763e-05, + "loss": 3.6469, + "step": 698368 + }, + { + "epoch": 1.0, + "learning_rate": 3.855799701643711e-05, + "loss": 3.6506, + "step": 698880 + }, + { + "epoch": 1.0, + "learning_rate": 3.854961106892659e-05, + "loss": 3.6454, + "step": 699392 + }, + { + "epoch": 1.0, + "learning_rate": 3.85412415002198e-05, + "loss": 3.6508, + "step": 699904 + }, + { + "epoch": 1.0, + "learning_rate": 3.853285555270929e-05, + "loss": 3.6409, + "step": 700416 + }, + { + "epoch": 1.0, + "learning_rate": 3.852446960519877e-05, + "loss": 3.6566, + "step": 700928 + }, + { + "epoch": 1.0, + "learning_rate": 3.851608365768825e-05, + "loss": 3.6448, + "step": 701440 + }, + { + "epoch": 1.0, + "learning_rate": 3.850769771017773e-05, + "loss": 3.6454, + "step": 701952 + }, + { + "epoch": 1.01, + "learning_rate": 3.849932814147094e-05, + "loss": 3.6427, + "step": 702464 + }, + { + "epoch": 1.01, + "learning_rate": 3.849094219396042e-05, + "loss": 3.6593, + "step": 702976 + }, + { + "epoch": 1.01, + "learning_rate": 3.84825562464499e-05, + "loss": 3.6509, + "step": 703488 + }, + { + "epoch": 1.01, + "learning_rate": 3.847417029893938e-05, + "loss": 3.6483, + "step": 704000 + }, + { + "epoch": 1.01, + "learning_rate": 3.8465800730232586e-05, + "loss": 3.6495, + "step": 704512 + }, + { + "epoch": 1.01, + "learning_rate": 3.8457414782722066e-05, + "loss": 3.6458, + "step": 705024 + }, + { + "epoch": 1.01, + "learning_rate": 3.8449028835211546e-05, + "loss": 3.6514, + "step": 705536 + }, + { + "epoch": 1.01, + "learning_rate": 3.8440642887701026e-05, + "loss": 3.6361, + "step": 706048 + }, + { + "epoch": 1.01, + "learning_rate": 3.843227331899424e-05, + "loss": 3.6357, + "step": 706560 + }, + { + "epoch": 1.01, + "learning_rate": 3.842388737148372e-05, + "loss": 3.6421, + "step": 707072 + }, + { + "epoch": 1.01, + "learning_rate": 3.84155014239732e-05, + "loss": 3.642, + "step": 707584 + }, + { + "epoch": 1.01, + "learning_rate": 3.840711547646268e-05, + "loss": 3.6464, + "step": 708096 + }, + { + "epoch": 1.01, + "learning_rate": 3.839874590775589e-05, + "loss": 3.6454, + "step": 708608 + }, + { + "epoch": 1.01, + "learning_rate": 3.839035996024537e-05, + "loss": 3.6495, + "step": 709120 + }, + { + "epoch": 1.01, + "learning_rate": 3.838197401273485e-05, + "loss": 3.6459, + "step": 709632 + }, + { + "epoch": 1.01, + "learning_rate": 3.837358806522433e-05, + "loss": 3.6478, + "step": 710144 + }, + { + "epoch": 1.01, + "learning_rate": 3.836521849651754e-05, + "loss": 3.6545, + "step": 710656 + }, + { + "epoch": 1.01, + "learning_rate": 3.835683254900702e-05, + "loss": 3.64, + "step": 711168 + }, + { + "epoch": 1.01, + "learning_rate": 3.83484466014965e-05, + "loss": 3.6228, + "step": 711680 + }, + { + "epoch": 1.01, + "learning_rate": 3.834006065398598e-05, + "loss": 3.6584, + "step": 712192 + }, + { + "epoch": 1.01, + "learning_rate": 3.8331691085279195e-05, + "loss": 3.6413, + "step": 712704 + }, + { + "epoch": 1.01, + "learning_rate": 3.8323305137768675e-05, + "loss": 3.6488, + "step": 713216 + }, + { + "epoch": 1.01, + "learning_rate": 3.8314919190258155e-05, + "loss": 3.6467, + "step": 713728 + }, + { + "epoch": 1.01, + "learning_rate": 3.8306533242747635e-05, + "loss": 3.6378, + "step": 714240 + }, + { + "epoch": 1.01, + "learning_rate": 3.8298163674040844e-05, + "loss": 3.6347, + "step": 714752 + }, + { + "epoch": 1.01, + "learning_rate": 3.8289777726530324e-05, + "loss": 3.6421, + "step": 715264 + }, + { + "epoch": 1.01, + "learning_rate": 3.8281391779019804e-05, + "loss": 3.652, + "step": 715776 + }, + { + "epoch": 1.01, + "learning_rate": 3.8273005831509284e-05, + "loss": 3.6424, + "step": 716288 + }, + { + "epoch": 1.01, + "learning_rate": 3.8264619883998764e-05, + "loss": 3.6567, + "step": 716800 + }, + { + "epoch": 1.01, + "learning_rate": 3.825625031529197e-05, + "loss": 3.6411, + "step": 717312 + }, + { + "epoch": 1.01, + "learning_rate": 3.824786436778145e-05, + "loss": 3.6302, + "step": 717824 + }, + { + "epoch": 1.01, + "learning_rate": 3.823947842027093e-05, + "loss": 3.655, + "step": 718336 + }, + { + "epoch": 1.01, + "learning_rate": 3.823109247276041e-05, + "loss": 3.6297, + "step": 718848 + }, + { + "epoch": 1.01, + "learning_rate": 3.822272290405363e-05, + "loss": 3.6293, + "step": 719360 + }, + { + "epoch": 1.01, + "learning_rate": 3.821433695654311e-05, + "loss": 3.6418, + "step": 719872 + }, + { + "epoch": 1.01, + "learning_rate": 3.820595100903259e-05, + "loss": 3.6382, + "step": 720384 + }, + { + "epoch": 1.01, + "learning_rate": 3.819756506152207e-05, + "loss": 3.6327, + "step": 720896 + }, + { + "epoch": 1.01, + "learning_rate": 3.818919549281528e-05, + "loss": 3.6343, + "step": 721408 + }, + { + "epoch": 1.01, + "learning_rate": 3.818080954530476e-05, + "loss": 3.6337, + "step": 721920 + }, + { + "epoch": 1.01, + "learning_rate": 3.817242359779424e-05, + "loss": 3.6476, + "step": 722432 + }, + { + "epoch": 1.01, + "learning_rate": 3.816403765028371e-05, + "loss": 3.6466, + "step": 722944 + }, + { + "epoch": 1.01, + "learning_rate": 3.815566808157693e-05, + "loss": 3.6435, + "step": 723456 + }, + { + "epoch": 1.01, + "learning_rate": 3.814728213406641e-05, + "loss": 3.6484, + "step": 723968 + }, + { + "epoch": 1.01, + "learning_rate": 3.813889618655589e-05, + "loss": 3.6467, + "step": 724480 + }, + { + "epoch": 1.01, + "learning_rate": 3.813051023904537e-05, + "loss": 3.6574, + "step": 724992 + }, + { + "epoch": 1.01, + "learning_rate": 3.812214067033858e-05, + "loss": 3.632, + "step": 725504 + }, + { + "epoch": 1.01, + "learning_rate": 3.811375472282806e-05, + "loss": 3.6567, + "step": 726016 + }, + { + "epoch": 1.01, + "learning_rate": 3.810536877531754e-05, + "loss": 3.6369, + "step": 726528 + }, + { + "epoch": 1.01, + "learning_rate": 3.8096982827807016e-05, + "loss": 3.6371, + "step": 727040 + }, + { + "epoch": 1.01, + "learning_rate": 3.808861325910023e-05, + "loss": 3.6423, + "step": 727552 + }, + { + "epoch": 1.01, + "learning_rate": 3.808022731158971e-05, + "loss": 3.6454, + "step": 728064 + }, + { + "epoch": 1.01, + "learning_rate": 3.8071841364079185e-05, + "loss": 3.6485, + "step": 728576 + }, + { + "epoch": 1.01, + "learning_rate": 3.8063455416568665e-05, + "loss": 3.654, + "step": 729088 + }, + { + "epoch": 1.01, + "learning_rate": 3.805508584786188e-05, + "loss": 3.6295, + "step": 729600 + }, + { + "epoch": 1.01, + "learning_rate": 3.804669990035136e-05, + "loss": 3.6249, + "step": 730112 + }, + { + "epoch": 1.01, + "learning_rate": 3.8038313952840834e-05, + "loss": 3.6388, + "step": 730624 + }, + { + "epoch": 1.01, + "learning_rate": 3.802992800533032e-05, + "loss": 3.6473, + "step": 731136 + }, + { + "epoch": 1.01, + "learning_rate": 3.8021558436623536e-05, + "loss": 3.6387, + "step": 731648 + }, + { + "epoch": 1.01, + "learning_rate": 3.8013172489113016e-05, + "loss": 3.6383, + "step": 732160 + }, + { + "epoch": 1.02, + "learning_rate": 3.800478654160249e-05, + "loss": 3.638, + "step": 732672 + }, + { + "epoch": 1.02, + "learning_rate": 3.799640059409197e-05, + "loss": 3.6379, + "step": 733184 + }, + { + "epoch": 1.02, + "learning_rate": 3.7988031025385185e-05, + "loss": 3.6374, + "step": 733696 + }, + { + "epoch": 1.02, + "learning_rate": 3.797964507787466e-05, + "loss": 3.6372, + "step": 734208 + }, + { + "epoch": 1.02, + "learning_rate": 3.797125913036414e-05, + "loss": 3.645, + "step": 734720 + }, + { + "epoch": 1.02, + "learning_rate": 3.796287318285362e-05, + "loss": 3.6455, + "step": 735232 + }, + { + "epoch": 1.02, + "learning_rate": 3.7954503614146834e-05, + "loss": 3.6501, + "step": 735744 + }, + { + "epoch": 1.02, + "learning_rate": 3.794611766663631e-05, + "loss": 3.6344, + "step": 736256 + }, + { + "epoch": 1.02, + "learning_rate": 3.793773171912579e-05, + "loss": 3.6341, + "step": 736768 + }, + { + "epoch": 1.02, + "learning_rate": 3.7929345771615274e-05, + "loss": 3.6375, + "step": 737280 + }, + { + "epoch": 1.02, + "learning_rate": 3.792097620290849e-05, + "loss": 3.6392, + "step": 737792 + }, + { + "epoch": 1.02, + "learning_rate": 3.791259025539796e-05, + "loss": 3.6442, + "step": 738304 + }, + { + "epoch": 1.02, + "learning_rate": 3.790420430788744e-05, + "loss": 3.642, + "step": 738816 + }, + { + "epoch": 1.02, + "learning_rate": 3.789581836037692e-05, + "loss": 3.6295, + "step": 739328 + }, + { + "epoch": 1.02, + "learning_rate": 3.78874324128664e-05, + "loss": 3.6267, + "step": 739840 + }, + { + "epoch": 1.02, + "learning_rate": 3.787906284415961e-05, + "loss": 3.6391, + "step": 740352 + }, + { + "epoch": 1.02, + "learning_rate": 3.787067689664909e-05, + "loss": 3.6308, + "step": 740864 + }, + { + "epoch": 1.02, + "learning_rate": 3.786229094913857e-05, + "loss": 3.6171, + "step": 741376 + }, + { + "epoch": 1.02, + "learning_rate": 3.785390500162805e-05, + "loss": 3.6372, + "step": 741888 + }, + { + "epoch": 1.02, + "learning_rate": 3.784553543292126e-05, + "loss": 3.6435, + "step": 742400 + }, + { + "epoch": 1.02, + "learning_rate": 3.783714948541074e-05, + "loss": 3.6331, + "step": 742912 + }, + { + "epoch": 1.02, + "learning_rate": 3.782876353790023e-05, + "loss": 3.6276, + "step": 743424 + }, + { + "epoch": 1.02, + "learning_rate": 3.782037759038971e-05, + "loss": 3.638, + "step": 743936 + }, + { + "epoch": 1.02, + "learning_rate": 3.781200802168292e-05, + "loss": 3.6375, + "step": 744448 + }, + { + "epoch": 1.02, + "learning_rate": 3.78036220741724e-05, + "loss": 3.6266, + "step": 744960 + }, + { + "epoch": 1.02, + "learning_rate": 3.779523612666188e-05, + "loss": 3.651, + "step": 745472 + }, + { + "epoch": 1.02, + "learning_rate": 3.778685017915136e-05, + "loss": 3.6439, + "step": 745984 + }, + { + "epoch": 1.02, + "learning_rate": 3.7778480610444566e-05, + "loss": 3.6335, + "step": 746496 + }, + { + "epoch": 1.02, + "learning_rate": 3.7770094662934046e-05, + "loss": 3.639, + "step": 747008 + }, + { + "epoch": 1.02, + "learning_rate": 3.7761708715423526e-05, + "loss": 3.6313, + "step": 747520 + }, + { + "epoch": 1.02, + "learning_rate": 3.7753322767913006e-05, + "loss": 3.6404, + "step": 748032 + }, + { + "epoch": 1.02, + "learning_rate": 3.7744953199206215e-05, + "loss": 3.6336, + "step": 748544 + }, + { + "epoch": 1.02, + "learning_rate": 3.7736567251695695e-05, + "loss": 3.6353, + "step": 749056 + }, + { + "epoch": 1.02, + "learning_rate": 3.772818130418518e-05, + "loss": 3.6309, + "step": 749568 + }, + { + "epoch": 1.02, + "learning_rate": 3.771979535667466e-05, + "loss": 3.6423, + "step": 750080 + }, + { + "epoch": 1.02, + "learning_rate": 3.771142578796787e-05, + "loss": 3.6341, + "step": 750592 + }, + { + "epoch": 1.02, + "learning_rate": 3.770303984045735e-05, + "loss": 3.6308, + "step": 751104 + }, + { + "epoch": 1.02, + "learning_rate": 3.769465389294683e-05, + "loss": 3.6265, + "step": 751616 + }, + { + "epoch": 1.02, + "learning_rate": 3.768626794543631e-05, + "loss": 3.6358, + "step": 752128 + }, + { + "epoch": 1.02, + "learning_rate": 3.767789837672952e-05, + "loss": 3.6306, + "step": 752640 + }, + { + "epoch": 1.02, + "learning_rate": 3.7669512429219e-05, + "loss": 3.6427, + "step": 753152 + }, + { + "epoch": 1.02, + "learning_rate": 3.766112648170848e-05, + "loss": 3.6333, + "step": 753664 + }, + { + "epoch": 1.02, + "learning_rate": 3.765274053419796e-05, + "loss": 3.6468, + "step": 754176 + }, + { + "epoch": 1.02, + "learning_rate": 3.764435458668744e-05, + "loss": 3.6162, + "step": 754688 + }, + { + "epoch": 1.02, + "learning_rate": 3.763598501798065e-05, + "loss": 3.6439, + "step": 755200 + }, + { + "epoch": 1.02, + "learning_rate": 3.7627599070470135e-05, + "loss": 3.6389, + "step": 755712 + }, + { + "epoch": 1.02, + "learning_rate": 3.7619213122959615e-05, + "loss": 3.6392, + "step": 756224 + }, + { + "epoch": 1.02, + "learning_rate": 3.7610827175449095e-05, + "loss": 3.6346, + "step": 756736 + }, + { + "epoch": 1.02, + "learning_rate": 3.7602457606742304e-05, + "loss": 3.6353, + "step": 757248 + }, + { + "epoch": 1.02, + "learning_rate": 3.7594071659231784e-05, + "loss": 3.6347, + "step": 757760 + }, + { + "epoch": 1.02, + "learning_rate": 3.7585685711721264e-05, + "loss": 3.6557, + "step": 758272 + }, + { + "epoch": 1.02, + "learning_rate": 3.7577299764210744e-05, + "loss": 3.623, + "step": 758784 + }, + { + "epoch": 1.02, + "learning_rate": 3.7568913816700224e-05, + "loss": 3.634, + "step": 759296 + }, + { + "epoch": 1.02, + "learning_rate": 3.756054424799343e-05, + "loss": 3.6317, + "step": 759808 + }, + { + "epoch": 1.02, + "learning_rate": 3.755215830048291e-05, + "loss": 3.6342, + "step": 760320 + }, + { + "epoch": 1.02, + "learning_rate": 3.754377235297239e-05, + "loss": 3.6277, + "step": 760832 + }, + { + "epoch": 1.02, + "learning_rate": 3.753538640546187e-05, + "loss": 3.6408, + "step": 761344 + }, + { + "epoch": 1.02, + "learning_rate": 3.752701683675509e-05, + "loss": 3.6325, + "step": 761856 + }, + { + "epoch": 1.02, + "learning_rate": 3.751863088924457e-05, + "loss": 3.6346, + "step": 762368 + }, + { + "epoch": 1.02, + "learning_rate": 3.751024494173405e-05, + "loss": 3.6343, + "step": 762880 + }, + { + "epoch": 1.03, + "eval_loss": 3.8452465534210205, + "eval_runtime": 302.2657, + "eval_samples_per_second": 1262.436, + "eval_steps_per_second": 39.452, + "step": 763200 + }, + { + "epoch": 0.0, + "learning_rate": 3.750185899422353e-05, + "loss": 3.6315, + "step": 763392 + }, + { + "epoch": 0.0, + "learning_rate": 3.749347304671301e-05, + "loss": 3.626, + "step": 763904 + }, + { + "epoch": 0.0, + "learning_rate": 3.748508709920249e-05, + "loss": 3.6339, + "step": 764416 + }, + { + "epoch": 0.0, + "learning_rate": 3.747670115169197e-05, + "loss": 3.6403, + "step": 764928 + }, + { + "epoch": 0.0, + "learning_rate": 3.746831520418144e-05, + "loss": 3.6403, + "step": 765440 + }, + { + "epoch": 0.0, + "learning_rate": 3.745994563547466e-05, + "loss": 3.6303, + "step": 765952 + }, + { + "epoch": 0.0, + "learning_rate": 3.745155968796414e-05, + "loss": 3.6294, + "step": 766464 + }, + { + "epoch": 0.0, + "learning_rate": 3.744317374045362e-05, + "loss": 3.6273, + "step": 766976 + }, + { + "epoch": 0.0, + "learning_rate": 3.743478779294309e-05, + "loss": 3.6303, + "step": 767488 + }, + { + "epoch": 0.0, + "learning_rate": 3.742641822423631e-05, + "loss": 3.6438, + "step": 768000 + }, + { + "epoch": 0.0, + "learning_rate": 3.7418032276725787e-05, + "loss": 3.6349, + "step": 768512 + }, + { + "epoch": 0.0, + "learning_rate": 3.7409646329215267e-05, + "loss": 3.6364, + "step": 769024 + }, + { + "epoch": 0.0, + "learning_rate": 3.740127676050848e-05, + "loss": 3.6395, + "step": 769536 + }, + { + "epoch": 0.0, + "learning_rate": 3.739289081299796e-05, + "loss": 3.6171, + "step": 770048 + }, + { + "epoch": 0.0, + "learning_rate": 3.738450486548744e-05, + "loss": 3.6399, + "step": 770560 + }, + { + "epoch": 0.0, + "learning_rate": 3.7376118917976916e-05, + "loss": 3.6196, + "step": 771072 + }, + { + "epoch": 0.0, + "learning_rate": 3.7367732970466395e-05, + "loss": 3.6224, + "step": 771584 + }, + { + "epoch": 0.0, + "learning_rate": 3.7359347022955875e-05, + "loss": 3.6237, + "step": 772096 + }, + { + "epoch": 0.0, + "learning_rate": 3.7350961075445355e-05, + "loss": 3.6246, + "step": 772608 + }, + { + "epoch": 0.0, + "learning_rate": 3.7342575127934835e-05, + "loss": 3.6343, + "step": 773120 + }, + { + "epoch": 0.0, + "learning_rate": 3.7334205559228044e-05, + "loss": 3.639, + "step": 773632 + }, + { + "epoch": 0.0, + "learning_rate": 3.7325819611717524e-05, + "loss": 3.638, + "step": 774144 + }, + { + "epoch": 0.0, + "learning_rate": 3.7317433664207004e-05, + "loss": 3.6242, + "step": 774656 + }, + { + "epoch": 0.0, + "learning_rate": 3.730904771669649e-05, + "loss": 3.6238, + "step": 775168 + }, + { + "epoch": 0.0, + "learning_rate": 3.73006781479897e-05, + "loss": 3.6274, + "step": 775680 + }, + { + "epoch": 0.0, + "learning_rate": 3.729229220047918e-05, + "loss": 3.6258, + "step": 776192 + }, + { + "epoch": 0.0, + "learning_rate": 3.728390625296866e-05, + "loss": 3.6199, + "step": 776704 + }, + { + "epoch": 0.0, + "learning_rate": 3.727552030545814e-05, + "loss": 3.634, + "step": 777216 + }, + { + "epoch": 0.0, + "learning_rate": 3.726715073675135e-05, + "loss": 3.6166, + "step": 777728 + }, + { + "epoch": 0.0, + "learning_rate": 3.725876478924083e-05, + "loss": 3.6268, + "step": 778240 + }, + { + "epoch": 0.01, + "learning_rate": 3.725037884173031e-05, + "loss": 3.6168, + "step": 778752 + }, + { + "epoch": 0.01, + "learning_rate": 3.724199289421979e-05, + "loss": 3.6354, + "step": 779264 + }, + { + "epoch": 0.01, + "learning_rate": 3.7233623325513e-05, + "loss": 3.6315, + "step": 779776 + }, + { + "epoch": 0.01, + "learning_rate": 3.722523737800248e-05, + "loss": 3.6217, + "step": 780288 + }, + { + "epoch": 0.01, + "learning_rate": 3.721685143049196e-05, + "loss": 3.6301, + "step": 780800 + }, + { + "epoch": 0.01, + "learning_rate": 3.7208465482981445e-05, + "loss": 3.6181, + "step": 781312 + }, + { + "epoch": 0.01, + "learning_rate": 3.7200095914274654e-05, + "loss": 3.6324, + "step": 781824 + }, + { + "epoch": 0.01, + "learning_rate": 3.7191709966764134e-05, + "loss": 3.6183, + "step": 782336 + }, + { + "epoch": 0.01, + "learning_rate": 3.7183324019253614e-05, + "loss": 3.6125, + "step": 782848 + }, + { + "epoch": 0.01, + "learning_rate": 3.7174938071743094e-05, + "loss": 3.6157, + "step": 783360 + }, + { + "epoch": 0.01, + "learning_rate": 3.7166552124232574e-05, + "loss": 3.6244, + "step": 783872 + }, + { + "epoch": 0.01, + "learning_rate": 3.715818255552578e-05, + "loss": 3.6211, + "step": 784384 + }, + { + "epoch": 0.01, + "learning_rate": 3.714979660801526e-05, + "loss": 3.6225, + "step": 784896 + }, + { + "epoch": 0.01, + "learning_rate": 3.714141066050474e-05, + "loss": 3.6273, + "step": 785408 + }, + { + "epoch": 0.01, + "learning_rate": 3.713302471299422e-05, + "loss": 3.6247, + "step": 785920 + }, + { + "epoch": 0.01, + "learning_rate": 3.712465514428743e-05, + "loss": 3.6262, + "step": 786432 + }, + { + "epoch": 0.01, + "learning_rate": 3.711626919677691e-05, + "loss": 3.6374, + "step": 786944 + }, + { + "epoch": 0.01, + "learning_rate": 3.71078832492664e-05, + "loss": 3.6171, + "step": 787456 + }, + { + "epoch": 0.01, + "learning_rate": 3.709949730175588e-05, + "loss": 3.5979, + "step": 787968 + }, + { + "epoch": 0.01, + "learning_rate": 3.709112773304909e-05, + "loss": 3.6361, + "step": 788480 + }, + { + "epoch": 0.01, + "learning_rate": 3.708274178553857e-05, + "loss": 3.619, + "step": 788992 + }, + { + "epoch": 0.01, + "learning_rate": 3.707435583802805e-05, + "loss": 3.6285, + "step": 789504 + }, + { + "epoch": 0.01, + "learning_rate": 3.706596989051753e-05, + "loss": 3.6203, + "step": 790016 + }, + { + "epoch": 0.01, + "learning_rate": 3.7057600321810736e-05, + "loss": 3.6182, + "step": 790528 + }, + { + "epoch": 0.01, + "learning_rate": 3.7049214374300216e-05, + "loss": 3.6126, + "step": 791040 + }, + { + "epoch": 0.01, + "learning_rate": 3.7040828426789696e-05, + "loss": 3.6152, + "step": 791552 + }, + { + "epoch": 0.01, + "learning_rate": 3.7032442479279176e-05, + "loss": 3.6333, + "step": 792064 + }, + { + "epoch": 0.01, + "learning_rate": 3.7024072910572385e-05, + "loss": 3.6163, + "step": 792576 + }, + { + "epoch": 0.01, + "learning_rate": 3.7015686963061865e-05, + "loss": 3.6371, + "step": 793088 + }, + { + "epoch": 0.01, + "learning_rate": 3.700730101555135e-05, + "loss": 3.6182, + "step": 793600 + }, + { + "epoch": 0.01, + "learning_rate": 3.699891506804083e-05, + "loss": 3.605, + "step": 794112 + }, + { + "epoch": 0.01, + "learning_rate": 3.699054549933404e-05, + "loss": 3.6309, + "step": 794624 + }, + { + "epoch": 0.01, + "learning_rate": 3.698215955182352e-05, + "loss": 3.6156, + "step": 795136 + }, + { + "epoch": 0.01, + "learning_rate": 3.6973773604313e-05, + "loss": 3.6012, + "step": 795648 + }, + { + "epoch": 0.01, + "learning_rate": 3.696538765680248e-05, + "loss": 3.6192, + "step": 796160 + }, + { + "epoch": 0.01, + "learning_rate": 3.695701808809569e-05, + "loss": 3.6166, + "step": 796672 + }, + { + "epoch": 0.01, + "learning_rate": 3.694863214058517e-05, + "loss": 3.6105, + "step": 797184 + }, + { + "epoch": 0.01, + "learning_rate": 3.694024619307465e-05, + "loss": 3.6108, + "step": 797696 + }, + { + "epoch": 0.01, + "learning_rate": 3.693186024556413e-05, + "loss": 3.6101, + "step": 798208 + }, + { + "epoch": 0.01, + "learning_rate": 3.692347429805361e-05, + "loss": 3.6234, + "step": 798720 + }, + { + "epoch": 0.01, + "learning_rate": 3.691510472934682e-05, + "loss": 3.6291, + "step": 799232 + }, + { + "epoch": 0.01, + "learning_rate": 3.6906718781836306e-05, + "loss": 3.6161, + "step": 799744 + }, + { + "epoch": 0.01, + "learning_rate": 3.6898332834325786e-05, + "loss": 3.6288, + "step": 800256 + }, + { + "epoch": 0.01, + "learning_rate": 3.6889946886815266e-05, + "loss": 3.6241, + "step": 800768 + }, + { + "epoch": 0.01, + "learning_rate": 3.6881577318108475e-05, + "loss": 3.637, + "step": 801280 + }, + { + "epoch": 0.01, + "learning_rate": 3.6873191370597955e-05, + "loss": 3.6121, + "step": 801792 + }, + { + "epoch": 0.01, + "learning_rate": 3.6864805423087435e-05, + "loss": 3.6359, + "step": 802304 + }, + { + "epoch": 0.01, + "learning_rate": 3.6856419475576915e-05, + "loss": 3.6131, + "step": 802816 + }, + { + "epoch": 0.01, + "learning_rate": 3.6848049906870124e-05, + "loss": 3.613, + "step": 803328 + }, + { + "epoch": 0.01, + "learning_rate": 3.6839663959359604e-05, + "loss": 3.6265, + "step": 803840 + }, + { + "epoch": 0.01, + "learning_rate": 3.6831278011849084e-05, + "loss": 3.6199, + "step": 804352 + }, + { + "epoch": 0.01, + "learning_rate": 3.6822892064338564e-05, + "loss": 3.6268, + "step": 804864 + }, + { + "epoch": 0.01, + "learning_rate": 3.6814506116828044e-05, + "loss": 3.6318, + "step": 805376 + }, + { + "epoch": 0.01, + "learning_rate": 3.680613654812126e-05, + "loss": 3.6082, + "step": 805888 + }, + { + "epoch": 0.01, + "learning_rate": 3.679775060061074e-05, + "loss": 3.6025, + "step": 806400 + }, + { + "epoch": 0.01, + "learning_rate": 3.678936465310022e-05, + "loss": 3.6146, + "step": 806912 + }, + { + "epoch": 0.01, + "learning_rate": 3.67809787055897e-05, + "loss": 3.6298, + "step": 807424 + }, + { + "epoch": 0.01, + "learning_rate": 3.677260913688291e-05, + "loss": 3.6122, + "step": 807936 + }, + { + "epoch": 0.01, + "learning_rate": 3.676422318937239e-05, + "loss": 3.6147, + "step": 808448 + }, + { + "epoch": 0.01, + "learning_rate": 3.675583724186187e-05, + "loss": 3.6199, + "step": 808960 + }, + { + "epoch": 0.02, + "learning_rate": 3.674745129435134e-05, + "loss": 3.6112, + "step": 809472 + }, + { + "epoch": 0.02, + "learning_rate": 3.673908172564456e-05, + "loss": 3.6204, + "step": 809984 + }, + { + "epoch": 0.02, + "learning_rate": 3.673069577813404e-05, + "loss": 3.6125, + "step": 810496 + }, + { + "epoch": 0.02, + "learning_rate": 3.672230983062352e-05, + "loss": 3.6225, + "step": 811008 + }, + { + "epoch": 0.02, + "learning_rate": 3.6713923883113e-05, + "loss": 3.6207, + "step": 811520 + }, + { + "epoch": 0.02, + "learning_rate": 3.670555431440621e-05, + "loss": 3.6297, + "step": 812032 + }, + { + "epoch": 0.02, + "learning_rate": 3.669716836689569e-05, + "loss": 3.611, + "step": 812544 + }, + { + "epoch": 0.02, + "learning_rate": 3.668878241938517e-05, + "loss": 3.6174, + "step": 813056 + }, + { + "epoch": 0.02, + "learning_rate": 3.6680396471874646e-05, + "loss": 3.6128, + "step": 813568 + }, + { + "epoch": 0.02, + "learning_rate": 3.667202690316786e-05, + "loss": 3.6185, + "step": 814080 + }, + { + "epoch": 0.02, + "learning_rate": 3.666364095565734e-05, + "loss": 3.6245, + "step": 814592 + }, + { + "epoch": 0.02, + "learning_rate": 3.6655255008146815e-05, + "loss": 3.6153, + "step": 815104 + }, + { + "epoch": 0.02, + "learning_rate": 3.6646869060636295e-05, + "loss": 3.6132, + "step": 815616 + }, + { + "epoch": 0.02, + "learning_rate": 3.6638483113125775e-05, + "loss": 3.6074, + "step": 816128 + }, + { + "epoch": 0.02, + "learning_rate": 3.663011354441899e-05, + "loss": 3.6162, + "step": 816640 + }, + { + "epoch": 0.02, + "learning_rate": 3.6621727596908464e-05, + "loss": 3.6118, + "step": 817152 + }, + { + "epoch": 0.02, + "learning_rate": 3.661334164939795e-05, + "loss": 3.5955, + "step": 817664 + }, + { + "epoch": 0.02, + "learning_rate": 3.660495570188743e-05, + "loss": 3.6163, + "step": 818176 + }, + { + "epoch": 0.02, + "learning_rate": 3.659658613318065e-05, + "loss": 3.6181, + "step": 818688 + }, + { + "epoch": 0.02, + "learning_rate": 3.658820018567012e-05, + "loss": 3.6111, + "step": 819200 + }, + { + "epoch": 0.02, + "learning_rate": 3.65798142381596e-05, + "loss": 3.6092, + "step": 819712 + }, + { + "epoch": 0.02, + "learning_rate": 3.657142829064908e-05, + "loss": 3.6144, + "step": 820224 + }, + { + "epoch": 0.02, + "learning_rate": 3.656305872194229e-05, + "loss": 3.6183, + "step": 820736 + }, + { + "epoch": 0.02, + "learning_rate": 3.655467277443177e-05, + "loss": 3.6034, + "step": 821248 + }, + { + "epoch": 0.02, + "learning_rate": 3.654628682692125e-05, + "loss": 3.6321, + "step": 821760 + }, + { + "epoch": 0.02, + "learning_rate": 3.653790087941073e-05, + "loss": 3.6193, + "step": 822272 + }, + { + "epoch": 0.02, + "learning_rate": 3.652953131070394e-05, + "loss": 3.6139, + "step": 822784 + }, + { + "epoch": 0.02, + "learning_rate": 3.652114536319342e-05, + "loss": 3.62, + "step": 823296 + }, + { + "epoch": 0.02, + "learning_rate": 3.65127594156829e-05, + "loss": 3.6115, + "step": 823808 + }, + { + "epoch": 0.02, + "learning_rate": 3.6504373468172384e-05, + "loss": 3.619, + "step": 824320 + }, + { + "epoch": 0.02, + "learning_rate": 3.6496003899465594e-05, + "loss": 3.6135, + "step": 824832 + }, + { + "epoch": 0.02, + "learning_rate": 3.6487617951955074e-05, + "loss": 3.6095, + "step": 825344 + }, + { + "epoch": 0.02, + "learning_rate": 3.6479232004444554e-05, + "loss": 3.6119, + "step": 825856 + }, + { + "epoch": 0.02, + "learning_rate": 3.6470846056934033e-05, + "loss": 3.6165, + "step": 826368 + }, + { + "epoch": 0.02, + "learning_rate": 3.646247648822724e-05, + "loss": 3.6144, + "step": 826880 + }, + { + "epoch": 0.02, + "learning_rate": 3.645409054071672e-05, + "loss": 3.6072, + "step": 827392 + }, + { + "epoch": 0.02, + "learning_rate": 3.64457045932062e-05, + "loss": 3.6096, + "step": 827904 + }, + { + "epoch": 0.02, + "learning_rate": 3.643731864569568e-05, + "loss": 3.6089, + "step": 828416 + }, + { + "epoch": 0.02, + "learning_rate": 3.642894907698889e-05, + "loss": 3.6104, + "step": 828928 + }, + { + "epoch": 0.02, + "learning_rate": 3.642056312947837e-05, + "loss": 3.6216, + "step": 829440 + }, + { + "epoch": 0.02, + "learning_rate": 3.641217718196785e-05, + "loss": 3.6154, + "step": 829952 + }, + { + "epoch": 0.02, + "learning_rate": 3.640379123445734e-05, + "loss": 3.6246, + "step": 830464 + }, + { + "epoch": 0.02, + "learning_rate": 3.639542166575055e-05, + "loss": 3.5941, + "step": 830976 + }, + { + "epoch": 0.02, + "learning_rate": 3.638703571824003e-05, + "loss": 3.6265, + "step": 831488 + }, + { + "epoch": 0.02, + "learning_rate": 3.637864977072951e-05, + "loss": 3.6171, + "step": 832000 + }, + { + "epoch": 0.02, + "learning_rate": 3.637026382321899e-05, + "loss": 3.6181, + "step": 832512 + }, + { + "epoch": 0.02, + "learning_rate": 3.636187787570847e-05, + "loss": 3.614, + "step": 833024 + }, + { + "epoch": 0.02, + "learning_rate": 3.6353508307001676e-05, + "loss": 3.6082, + "step": 833536 + }, + { + "epoch": 0.02, + "learning_rate": 3.6345122359491156e-05, + "loss": 3.6125, + "step": 834048 + }, + { + "epoch": 0.02, + "learning_rate": 3.6336736411980636e-05, + "loss": 3.6309, + "step": 834560 + }, + { + "epoch": 0.02, + "learning_rate": 3.6328350464470116e-05, + "loss": 3.6045, + "step": 835072 + }, + { + "epoch": 0.02, + "learning_rate": 3.6319980895763325e-05, + "loss": 3.6142, + "step": 835584 + }, + { + "epoch": 0.02, + "learning_rate": 3.6311594948252805e-05, + "loss": 3.6094, + "step": 836096 + }, + { + "epoch": 0.02, + "learning_rate": 3.630320900074229e-05, + "loss": 3.6117, + "step": 836608 + }, + { + "epoch": 0.02, + "learning_rate": 3.629482305323177e-05, + "loss": 3.6093, + "step": 837120 + }, + { + "epoch": 0.02, + "learning_rate": 3.628645348452498e-05, + "loss": 3.6153, + "step": 837632 + }, + { + "epoch": 0.02, + "learning_rate": 3.627806753701446e-05, + "loss": 3.6124, + "step": 838144 + }, + { + "epoch": 0.02, + "learning_rate": 3.626968158950394e-05, + "loss": 3.6167, + "step": 838656 + }, + { + "epoch": 0.02, + "learning_rate": 3.626129564199342e-05, + "loss": 3.611, + "step": 839168 + }, + { + "epoch": 0.03, + "eval_loss": 3.8431830406188965, + "eval_runtime": 310.328, + "eval_samples_per_second": 1229.638, + "eval_steps_per_second": 38.427, + "step": 839520 + }, + { + "epoch": 1.0, + "learning_rate": 3.625292607328663e-05, + "loss": 3.6074, + "step": 839680 + }, + { + "epoch": 1.0, + "learning_rate": 3.624454012577611e-05, + "loss": 3.6059, + "step": 840192 + }, + { + "epoch": 1.0, + "learning_rate": 3.623615417826559e-05, + "loss": 3.6146, + "step": 840704 + }, + { + "epoch": 1.0, + "learning_rate": 3.622776823075507e-05, + "loss": 3.615, + "step": 841216 + }, + { + "epoch": 1.0, + "learning_rate": 3.621939866204828e-05, + "loss": 3.6209, + "step": 841728 + }, + { + "epoch": 1.0, + "learning_rate": 3.621101271453776e-05, + "loss": 3.6112, + "step": 842240 + }, + { + "epoch": 1.0, + "learning_rate": 3.6202626767027245e-05, + "loss": 3.6078, + "step": 842752 + }, + { + "epoch": 1.0, + "learning_rate": 3.6194240819516725e-05, + "loss": 3.6137, + "step": 843264 + }, + { + "epoch": 1.0, + "learning_rate": 3.6185871250809935e-05, + "loss": 3.606, + "step": 843776 + }, + { + "epoch": 1.0, + "learning_rate": 3.6177485303299415e-05, + "loss": 3.6191, + "step": 844288 + }, + { + "epoch": 1.0, + "learning_rate": 3.6169099355788894e-05, + "loss": 3.6159, + "step": 844800 + }, + { + "epoch": 1.0, + "learning_rate": 3.6160713408278374e-05, + "loss": 3.6198, + "step": 845312 + }, + { + "epoch": 1.0, + "learning_rate": 3.6152343839571584e-05, + "loss": 3.6156, + "step": 845824 + }, + { + "epoch": 1.0, + "learning_rate": 3.6143957892061063e-05, + "loss": 3.5984, + "step": 846336 + }, + { + "epoch": 1.0, + "learning_rate": 3.6135571944550543e-05, + "loss": 3.6174, + "step": 846848 + }, + { + "epoch": 1.0, + "learning_rate": 3.612718599704002e-05, + "loss": 3.5985, + "step": 847360 + }, + { + "epoch": 1.0, + "learning_rate": 3.611881642833323e-05, + "loss": 3.6044, + "step": 847872 + }, + { + "epoch": 1.0, + "learning_rate": 3.611043048082271e-05, + "loss": 3.6051, + "step": 848384 + }, + { + "epoch": 1.0, + "learning_rate": 3.61020445333122e-05, + "loss": 3.6005, + "step": 848896 + }, + { + "epoch": 1.0, + "learning_rate": 3.609365858580168e-05, + "loss": 3.6108, + "step": 849408 + }, + { + "epoch": 1.0, + "learning_rate": 3.608528901709489e-05, + "loss": 3.6233, + "step": 849920 + }, + { + "epoch": 1.0, + "learning_rate": 3.607690306958437e-05, + "loss": 3.6126, + "step": 850432 + }, + { + "epoch": 1.0, + "learning_rate": 3.606851712207385e-05, + "loss": 3.6079, + "step": 850944 + }, + { + "epoch": 1.0, + "learning_rate": 3.606013117456333e-05, + "loss": 3.6073, + "step": 851456 + }, + { + "epoch": 1.0, + "learning_rate": 3.605174522705281e-05, + "loss": 3.6069, + "step": 851968 + }, + { + "epoch": 1.0, + "learning_rate": 3.604337565834602e-05, + "loss": 3.6033, + "step": 852480 + }, + { + "epoch": 1.0, + "learning_rate": 3.60349897108355e-05, + "loss": 3.5982, + "step": 852992 + }, + { + "epoch": 1.0, + "learning_rate": 3.602660376332498e-05, + "loss": 3.612, + "step": 853504 + }, + { + "epoch": 1.0, + "learning_rate": 3.601821781581446e-05, + "loss": 3.5991, + "step": 854016 + }, + { + "epoch": 1.0, + "learning_rate": 3.6009848247107666e-05, + "loss": 3.6053, + "step": 854528 + }, + { + "epoch": 1.01, + "learning_rate": 3.600146229959715e-05, + "loss": 3.597, + "step": 855040 + }, + { + "epoch": 1.01, + "learning_rate": 3.599307635208663e-05, + "loss": 3.6135, + "step": 855552 + }, + { + "epoch": 1.01, + "learning_rate": 3.598469040457611e-05, + "loss": 3.6039, + "step": 856064 + }, + { + "epoch": 1.01, + "learning_rate": 3.597630445706559e-05, + "loss": 3.6078, + "step": 856576 + }, + { + "epoch": 1.01, + "learning_rate": 3.59679348883588e-05, + "loss": 3.6084, + "step": 857088 + }, + { + "epoch": 1.01, + "learning_rate": 3.595954894084828e-05, + "loss": 3.5994, + "step": 857600 + }, + { + "epoch": 1.01, + "learning_rate": 3.595116299333776e-05, + "loss": 3.6141, + "step": 858112 + }, + { + "epoch": 1.01, + "learning_rate": 3.594277704582724e-05, + "loss": 3.5921, + "step": 858624 + }, + { + "epoch": 1.01, + "learning_rate": 3.593440747712045e-05, + "loss": 3.5926, + "step": 859136 + }, + { + "epoch": 1.01, + "learning_rate": 3.592602152960993e-05, + "loss": 3.5975, + "step": 859648 + }, + { + "epoch": 1.01, + "learning_rate": 3.591763558209941e-05, + "loss": 3.6038, + "step": 860160 + }, + { + "epoch": 1.01, + "learning_rate": 3.590924963458889e-05, + "loss": 3.5992, + "step": 860672 + }, + { + "epoch": 1.01, + "learning_rate": 3.5900880065882106e-05, + "loss": 3.6042, + "step": 861184 + }, + { + "epoch": 1.01, + "learning_rate": 3.5892494118371586e-05, + "loss": 3.6042, + "step": 861696 + }, + { + "epoch": 1.01, + "learning_rate": 3.5884108170861066e-05, + "loss": 3.6045, + "step": 862208 + }, + { + "epoch": 1.01, + "learning_rate": 3.5875722223350546e-05, + "loss": 3.6063, + "step": 862720 + }, + { + "epoch": 1.01, + "learning_rate": 3.5867352654643755e-05, + "loss": 3.6124, + "step": 863232 + }, + { + "epoch": 1.01, + "learning_rate": 3.5858966707133235e-05, + "loss": 3.6006, + "step": 863744 + }, + { + "epoch": 1.01, + "learning_rate": 3.5850580759622715e-05, + "loss": 3.5793, + "step": 864256 + }, + { + "epoch": 1.01, + "learning_rate": 3.5842194812112195e-05, + "loss": 3.616, + "step": 864768 + }, + { + "epoch": 1.01, + "learning_rate": 3.5833825243405404e-05, + "loss": 3.6004, + "step": 865280 + }, + { + "epoch": 1.01, + "learning_rate": 3.5825439295894884e-05, + "loss": 3.6032, + "step": 865792 + }, + { + "epoch": 1.01, + "learning_rate": 3.5817053348384364e-05, + "loss": 3.5993, + "step": 866304 + }, + { + "epoch": 1.01, + "learning_rate": 3.5808667400873844e-05, + "loss": 3.5977, + "step": 866816 + }, + { + "epoch": 1.01, + "learning_rate": 3.580029783216706e-05, + "loss": 3.5942, + "step": 867328 + }, + { + "epoch": 1.01, + "learning_rate": 3.579191188465654e-05, + "loss": 3.5954, + "step": 867840 + }, + { + "epoch": 1.01, + "learning_rate": 3.578352593714602e-05, + "loss": 3.6178, + "step": 868352 + }, + { + "epoch": 1.01, + "learning_rate": 3.577513998963549e-05, + "loss": 3.596, + "step": 868864 + }, + { + "epoch": 1.01, + "learning_rate": 3.576677042092871e-05, + "loss": 3.6171, + "step": 869376 + }, + { + "epoch": 1.01, + "learning_rate": 3.575838447341819e-05, + "loss": 3.5988, + "step": 869888 + }, + { + "epoch": 1.01, + "learning_rate": 3.574999852590767e-05, + "loss": 3.5836, + "step": 870400 + }, + { + "epoch": 1.01, + "learning_rate": 3.574161257839714e-05, + "loss": 3.6112, + "step": 870912 + }, + { + "epoch": 1.01, + "learning_rate": 3.573324300969036e-05, + "loss": 3.5955, + "step": 871424 + }, + { + "epoch": 1.01, + "learning_rate": 3.572485706217984e-05, + "loss": 3.5848, + "step": 871936 + }, + { + "epoch": 1.01, + "learning_rate": 3.571647111466931e-05, + "loss": 3.5988, + "step": 872448 + }, + { + "epoch": 1.01, + "learning_rate": 3.57080851671588e-05, + "loss": 3.5958, + "step": 872960 + }, + { + "epoch": 1.01, + "learning_rate": 3.569971559845201e-05, + "loss": 3.5879, + "step": 873472 + }, + { + "epoch": 1.01, + "learning_rate": 3.5691329650941494e-05, + "loss": 3.5958, + "step": 873984 + }, + { + "epoch": 1.01, + "learning_rate": 3.568294370343097e-05, + "loss": 3.5923, + "step": 874496 + }, + { + "epoch": 1.01, + "learning_rate": 3.567455775592045e-05, + "loss": 3.6005, + "step": 875008 + }, + { + "epoch": 1.01, + "learning_rate": 3.566617180840993e-05, + "loss": 3.6067, + "step": 875520 + }, + { + "epoch": 1.01, + "learning_rate": 3.565780223970314e-05, + "loss": 3.6001, + "step": 876032 + }, + { + "epoch": 1.01, + "learning_rate": 3.5649416292192616e-05, + "loss": 3.6078, + "step": 876544 + }, + { + "epoch": 1.01, + "learning_rate": 3.5641030344682096e-05, + "loss": 3.604, + "step": 877056 + }, + { + "epoch": 1.01, + "learning_rate": 3.5632644397171576e-05, + "loss": 3.6175, + "step": 877568 + }, + { + "epoch": 1.01, + "learning_rate": 3.5624274828464785e-05, + "loss": 3.5946, + "step": 878080 + }, + { + "epoch": 1.01, + "learning_rate": 3.5615888880954265e-05, + "loss": 3.6152, + "step": 878592 + }, + { + "epoch": 1.01, + "learning_rate": 3.5607502933443745e-05, + "loss": 3.5935, + "step": 879104 + }, + { + "epoch": 1.01, + "learning_rate": 3.559911698593323e-05, + "loss": 3.5936, + "step": 879616 + }, + { + "epoch": 1.01, + "learning_rate": 3.559074741722644e-05, + "loss": 3.6007, + "step": 880128 + }, + { + "epoch": 1.01, + "learning_rate": 3.558236146971592e-05, + "loss": 3.6011, + "step": 880640 + }, + { + "epoch": 1.01, + "learning_rate": 3.55739755222054e-05, + "loss": 3.6067, + "step": 881152 + }, + { + "epoch": 1.01, + "learning_rate": 3.556558957469488e-05, + "loss": 3.6142, + "step": 881664 + }, + { + "epoch": 1.01, + "learning_rate": 3.555722000598809e-05, + "loss": 3.592, + "step": 882176 + }, + { + "epoch": 1.01, + "learning_rate": 3.554883405847757e-05, + "loss": 3.5821, + "step": 882688 + }, + { + "epoch": 1.01, + "learning_rate": 3.554044811096705e-05, + "loss": 3.5905, + "step": 883200 + }, + { + "epoch": 1.01, + "learning_rate": 3.553206216345653e-05, + "loss": 3.6115, + "step": 883712 + }, + { + "epoch": 1.01, + "learning_rate": 3.552369259474974e-05, + "loss": 3.5914, + "step": 884224 + }, + { + "epoch": 1.01, + "learning_rate": 3.551530664723922e-05, + "loss": 3.6004, + "step": 884736 + }, + { + "epoch": 1.01, + "learning_rate": 3.55069206997287e-05, + "loss": 3.6019, + "step": 885248 + }, + { + "epoch": 1.02, + "learning_rate": 3.5498534752218185e-05, + "loss": 3.5896, + "step": 885760 + }, + { + "epoch": 1.02, + "learning_rate": 3.5490165183511394e-05, + "loss": 3.5992, + "step": 886272 + }, + { + "epoch": 1.02, + "learning_rate": 3.5481779236000874e-05, + "loss": 3.5967, + "step": 886784 + }, + { + "epoch": 1.02, + "learning_rate": 3.5473393288490354e-05, + "loss": 3.5983, + "step": 887296 + }, + { + "epoch": 1.02, + "learning_rate": 3.5465007340979834e-05, + "loss": 3.6061, + "step": 887808 + }, + { + "epoch": 1.02, + "learning_rate": 3.545663777227304e-05, + "loss": 3.609, + "step": 888320 + }, + { + "epoch": 1.02, + "learning_rate": 3.544825182476252e-05, + "loss": 3.5932, + "step": 888832 + }, + { + "epoch": 1.02, + "learning_rate": 3.5439865877252e-05, + "loss": 3.5959, + "step": 889344 + }, + { + "epoch": 1.02, + "learning_rate": 3.543147992974148e-05, + "loss": 3.5928, + "step": 889856 + }, + { + "epoch": 1.02, + "learning_rate": 3.542311036103469e-05, + "loss": 3.6008, + "step": 890368 + }, + { + "epoch": 1.02, + "learning_rate": 3.541472441352417e-05, + "loss": 3.6027, + "step": 890880 + }, + { + "epoch": 1.02, + "learning_rate": 3.540633846601365e-05, + "loss": 3.5952, + "step": 891392 + }, + { + "epoch": 1.02, + "learning_rate": 3.539795251850314e-05, + "loss": 3.5933, + "step": 891904 + }, + { + "epoch": 1.02, + "learning_rate": 3.538958294979635e-05, + "loss": 3.5858, + "step": 892416 + }, + { + "epoch": 1.02, + "learning_rate": 3.538119700228583e-05, + "loss": 3.5983, + "step": 892928 + }, + { + "epoch": 1.02, + "learning_rate": 3.537281105477531e-05, + "loss": 3.5903, + "step": 893440 + }, + { + "epoch": 1.02, + "learning_rate": 3.536442510726479e-05, + "loss": 3.5761, + "step": 893952 + }, + { + "epoch": 1.02, + "learning_rate": 3.5356055538558e-05, + "loss": 3.5981, + "step": 894464 + }, + { + "epoch": 1.02, + "learning_rate": 3.534766959104748e-05, + "loss": 3.5983, + "step": 894976 + }, + { + "epoch": 1.02, + "learning_rate": 3.533928364353696e-05, + "loss": 3.5937, + "step": 895488 + }, + { + "epoch": 1.02, + "learning_rate": 3.533089769602644e-05, + "loss": 3.589, + "step": 896000 + }, + { + "epoch": 1.02, + "learning_rate": 3.532251174851592e-05, + "loss": 3.5945, + "step": 896512 + }, + { + "epoch": 1.02, + "learning_rate": 3.5314142179809126e-05, + "loss": 3.5991, + "step": 897024 + }, + { + "epoch": 1.02, + "learning_rate": 3.5305756232298606e-05, + "loss": 3.583, + "step": 897536 + }, + { + "epoch": 1.02, + "learning_rate": 3.529737028478809e-05, + "loss": 3.6078, + "step": 898048 + }, + { + "epoch": 1.02, + "learning_rate": 3.528898433727757e-05, + "loss": 3.6002, + "step": 898560 + }, + { + "epoch": 1.02, + "learning_rate": 3.528061476857078e-05, + "loss": 3.5953, + "step": 899072 + }, + { + "epoch": 1.02, + "learning_rate": 3.527222882106026e-05, + "loss": 3.5996, + "step": 899584 + }, + { + "epoch": 1.02, + "learning_rate": 3.526384287354974e-05, + "loss": 3.592, + "step": 900096 + }, + { + "epoch": 1.02, + "learning_rate": 3.525545692603922e-05, + "loss": 3.5967, + "step": 900608 + }, + { + "epoch": 1.02, + "learning_rate": 3.524708735733243e-05, + "loss": 3.5963, + "step": 901120 + }, + { + "epoch": 1.02, + "learning_rate": 3.523870140982191e-05, + "loss": 3.5901, + "step": 901632 + }, + { + "epoch": 1.02, + "learning_rate": 3.523031546231139e-05, + "loss": 3.5952, + "step": 902144 + }, + { + "epoch": 1.02, + "learning_rate": 3.522192951480087e-05, + "loss": 3.5958, + "step": 902656 + }, + { + "epoch": 1.02, + "learning_rate": 3.521355994609408e-05, + "loss": 3.5949, + "step": 903168 + }, + { + "epoch": 1.02, + "learning_rate": 3.520517399858356e-05, + "loss": 3.5868, + "step": 903680 + }, + { + "epoch": 1.02, + "learning_rate": 3.5196788051073046e-05, + "loss": 3.5873, + "step": 904192 + }, + { + "epoch": 1.02, + "learning_rate": 3.5188402103562526e-05, + "loss": 3.5929, + "step": 904704 + }, + { + "epoch": 1.02, + "learning_rate": 3.5180032534855735e-05, + "loss": 3.5894, + "step": 905216 + }, + { + "epoch": 1.02, + "learning_rate": 3.5171646587345215e-05, + "loss": 3.605, + "step": 905728 + }, + { + "epoch": 1.02, + "learning_rate": 3.5163260639834695e-05, + "loss": 3.5928, + "step": 906240 + }, + { + "epoch": 1.02, + "learning_rate": 3.5154874692324175e-05, + "loss": 3.6085, + "step": 906752 + }, + { + "epoch": 1.02, + "learning_rate": 3.5146505123617384e-05, + "loss": 3.5738, + "step": 907264 + }, + { + "epoch": 1.02, + "learning_rate": 3.5138119176106864e-05, + "loss": 3.6061, + "step": 907776 + }, + { + "epoch": 1.02, + "learning_rate": 3.5129733228596344e-05, + "loss": 3.5941, + "step": 908288 + }, + { + "epoch": 1.02, + "learning_rate": 3.5121347281085824e-05, + "loss": 3.6041, + "step": 908800 + }, + { + "epoch": 1.02, + "learning_rate": 3.511297771237903e-05, + "loss": 3.5941, + "step": 909312 + }, + { + "epoch": 1.02, + "learning_rate": 3.510459176486851e-05, + "loss": 3.5854, + "step": 909824 + }, + { + "epoch": 1.02, + "learning_rate": 3.5096205817358e-05, + "loss": 3.5974, + "step": 910336 + }, + { + "epoch": 1.02, + "learning_rate": 3.508781986984748e-05, + "loss": 3.6181, + "step": 910848 + }, + { + "epoch": 1.02, + "learning_rate": 3.507943392233696e-05, + "loss": 3.5791, + "step": 911360 + }, + { + "epoch": 1.02, + "learning_rate": 3.507106435363017e-05, + "loss": 3.5957, + "step": 911872 + }, + { + "epoch": 1.02, + "learning_rate": 3.506267840611965e-05, + "loss": 3.5922, + "step": 912384 + }, + { + "epoch": 1.02, + "learning_rate": 3.505429245860913e-05, + "loss": 3.5918, + "step": 912896 + }, + { + "epoch": 1.02, + "learning_rate": 3.504590651109861e-05, + "loss": 3.5915, + "step": 913408 + }, + { + "epoch": 1.02, + "learning_rate": 3.503753694239182e-05, + "loss": 3.5974, + "step": 913920 + }, + { + "epoch": 1.02, + "learning_rate": 3.50291509948813e-05, + "loss": 3.5884, + "step": 914432 + }, + { + "epoch": 1.02, + "learning_rate": 3.502076504737078e-05, + "loss": 3.5987, + "step": 914944 + }, + { + "epoch": 1.02, + "learning_rate": 3.501237909986026e-05, + "loss": 3.5893, + "step": 915456 + }, + { + "epoch": 1.03, + "eval_loss": 3.842714309692383, + "eval_runtime": 304.6669, + "eval_samples_per_second": 1252.486, + "eval_steps_per_second": 39.141, + "step": 915840 + }, + { + "epoch": 0.0, + "learning_rate": 3.500400953115347e-05, + "loss": 3.6029, + "step": 915968 + }, + { + "epoch": 0.0, + "learning_rate": 3.4995623583642954e-05, + "loss": 3.5817, + "step": 916480 + }, + { + "epoch": 0.0, + "learning_rate": 3.4987237636132434e-05, + "loss": 3.5971, + "step": 916992 + }, + { + "epoch": 0.0, + "learning_rate": 3.4978851688621913e-05, + "loss": 3.5989, + "step": 917504 + }, + { + "epoch": 0.0, + "learning_rate": 3.4970465741111393e-05, + "loss": 3.5966, + "step": 918016 + }, + { + "epoch": 0.0, + "learning_rate": 3.49620961724046e-05, + "loss": 3.5918, + "step": 918528 + }, + { + "epoch": 0.0, + "learning_rate": 3.495371022489408e-05, + "loss": 3.5952, + "step": 919040 + }, + { + "epoch": 0.0, + "learning_rate": 3.494532427738356e-05, + "loss": 3.592, + "step": 919552 + }, + { + "epoch": 0.0, + "learning_rate": 3.493693832987304e-05, + "loss": 3.5878, + "step": 920064 + }, + { + "epoch": 0.0, + "learning_rate": 3.492856876116625e-05, + "loss": 3.5956, + "step": 920576 + }, + { + "epoch": 0.0, + "learning_rate": 3.492018281365573e-05, + "loss": 3.6038, + "step": 921088 + }, + { + "epoch": 0.0, + "learning_rate": 3.491179686614521e-05, + "loss": 3.5977, + "step": 921600 + }, + { + "epoch": 0.0, + "learning_rate": 3.490342729743842e-05, + "loss": 3.5995, + "step": 922112 + }, + { + "epoch": 0.0, + "learning_rate": 3.48950413499279e-05, + "loss": 3.578, + "step": 922624 + }, + { + "epoch": 0.0, + "learning_rate": 3.488665540241739e-05, + "loss": 3.5979, + "step": 923136 + }, + { + "epoch": 0.0, + "learning_rate": 3.487826945490687e-05, + "loss": 3.5812, + "step": 923648 + }, + { + "epoch": 0.0, + "learning_rate": 3.486988350739634e-05, + "loss": 3.5886, + "step": 924160 + }, + { + "epoch": 0.0, + "learning_rate": 3.486149755988582e-05, + "loss": 3.5833, + "step": 924672 + }, + { + "epoch": 0.0, + "learning_rate": 3.48531116123753e-05, + "loss": 3.5809, + "step": 925184 + }, + { + "epoch": 0.0, + "learning_rate": 3.484472566486478e-05, + "loss": 3.5901, + "step": 925696 + }, + { + "epoch": 0.0, + "learning_rate": 3.483633971735426e-05, + "loss": 3.6023, + "step": 926208 + }, + { + "epoch": 0.0, + "learning_rate": 3.482797014864747e-05, + "loss": 3.5938, + "step": 926720 + }, + { + "epoch": 0.0, + "learning_rate": 3.481958420113695e-05, + "loss": 3.5897, + "step": 927232 + }, + { + "epoch": 0.0, + "learning_rate": 3.481119825362643e-05, + "loss": 3.5867, + "step": 927744 + }, + { + "epoch": 0.0, + "learning_rate": 3.480281230611591e-05, + "loss": 3.59, + "step": 928256 + }, + { + "epoch": 0.0, + "learning_rate": 3.4794442737409125e-05, + "loss": 3.585, + "step": 928768 + }, + { + "epoch": 0.0, + "learning_rate": 3.4786056789898605e-05, + "loss": 3.5765, + "step": 929280 + }, + { + "epoch": 0.0, + "learning_rate": 3.4777670842388085e-05, + "loss": 3.5947, + "step": 929792 + }, + { + "epoch": 0.0, + "learning_rate": 3.4769284894877565e-05, + "loss": 3.5805, + "step": 930304 + }, + { + "epoch": 0.0, + "learning_rate": 3.4760915326170774e-05, + "loss": 3.588, + "step": 930816 + }, + { + "epoch": 0.01, + "learning_rate": 3.4752529378660254e-05, + "loss": 3.582, + "step": 931328 + }, + { + "epoch": 0.01, + "learning_rate": 3.4744143431149734e-05, + "loss": 3.5912, + "step": 931840 + }, + { + "epoch": 0.01, + "learning_rate": 3.4735757483639214e-05, + "loss": 3.5839, + "step": 932352 + }, + { + "epoch": 0.01, + "learning_rate": 3.472738791493242e-05, + "loss": 3.5898, + "step": 932864 + }, + { + "epoch": 0.01, + "learning_rate": 3.47190019674219e-05, + "loss": 3.5873, + "step": 933376 + }, + { + "epoch": 0.01, + "learning_rate": 3.471061601991138e-05, + "loss": 3.581, + "step": 933888 + }, + { + "epoch": 0.01, + "learning_rate": 3.470223007240086e-05, + "loss": 3.5956, + "step": 934400 + }, + { + "epoch": 0.01, + "learning_rate": 3.469386050369408e-05, + "loss": 3.5716, + "step": 934912 + }, + { + "epoch": 0.01, + "learning_rate": 3.468547455618356e-05, + "loss": 3.5782, + "step": 935424 + }, + { + "epoch": 0.01, + "learning_rate": 3.467708860867304e-05, + "loss": 3.5786, + "step": 935936 + }, + { + "epoch": 0.01, + "learning_rate": 3.466870266116252e-05, + "loss": 3.5818, + "step": 936448 + }, + { + "epoch": 0.01, + "learning_rate": 3.466033309245573e-05, + "loss": 3.5801, + "step": 936960 + }, + { + "epoch": 0.01, + "learning_rate": 3.465194714494521e-05, + "loss": 3.5877, + "step": 937472 + }, + { + "epoch": 0.01, + "learning_rate": 3.464356119743469e-05, + "loss": 3.5852, + "step": 937984 + }, + { + "epoch": 0.01, + "learning_rate": 3.463517524992417e-05, + "loss": 3.5862, + "step": 938496 + }, + { + "epoch": 0.01, + "learning_rate": 3.462678930241365e-05, + "loss": 3.5856, + "step": 939008 + }, + { + "epoch": 0.01, + "learning_rate": 3.4618419733706857e-05, + "loss": 3.5938, + "step": 939520 + }, + { + "epoch": 0.01, + "learning_rate": 3.4610033786196337e-05, + "loss": 3.5801, + "step": 940032 + }, + { + "epoch": 0.01, + "learning_rate": 3.4601647838685816e-05, + "loss": 3.5646, + "step": 940544 + }, + { + "epoch": 0.01, + "learning_rate": 3.4593261891175296e-05, + "loss": 3.595, + "step": 941056 + }, + { + "epoch": 0.01, + "learning_rate": 3.458489232246851e-05, + "loss": 3.5863, + "step": 941568 + }, + { + "epoch": 0.01, + "learning_rate": 3.457650637495799e-05, + "loss": 3.5832, + "step": 942080 + }, + { + "epoch": 0.01, + "learning_rate": 3.456812042744747e-05, + "loss": 3.5849, + "step": 942592 + }, + { + "epoch": 0.01, + "learning_rate": 3.455973447993695e-05, + "loss": 3.5788, + "step": 943104 + }, + { + "epoch": 0.01, + "learning_rate": 3.455136491123016e-05, + "loss": 3.5749, + "step": 943616 + }, + { + "epoch": 0.01, + "learning_rate": 3.454297896371964e-05, + "loss": 3.574, + "step": 944128 + }, + { + "epoch": 0.01, + "learning_rate": 3.453459301620912e-05, + "loss": 3.5979, + "step": 944640 + }, + { + "epoch": 0.01, + "learning_rate": 3.45262070686986e-05, + "loss": 3.5769, + "step": 945152 + }, + { + "epoch": 0.01, + "learning_rate": 3.451783749999181e-05, + "loss": 3.5984, + "step": 945664 + }, + { + "epoch": 0.01, + "learning_rate": 3.450945155248129e-05, + "loss": 3.5827, + "step": 946176 + }, + { + "epoch": 0.01, + "learning_rate": 3.450106560497077e-05, + "loss": 3.5635, + "step": 946688 + }, + { + "epoch": 0.01, + "learning_rate": 3.449267965746025e-05, + "loss": 3.591, + "step": 947200 + }, + { + "epoch": 0.01, + "learning_rate": 3.4484310088753466e-05, + "loss": 3.5755, + "step": 947712 + }, + { + "epoch": 0.01, + "learning_rate": 3.4475924141242946e-05, + "loss": 3.5686, + "step": 948224 + }, + { + "epoch": 0.01, + "learning_rate": 3.4467538193732426e-05, + "loss": 3.575, + "step": 948736 + }, + { + "epoch": 0.01, + "learning_rate": 3.4459152246221906e-05, + "loss": 3.5803, + "step": 949248 + }, + { + "epoch": 0.01, + "learning_rate": 3.4450782677515115e-05, + "loss": 3.5714, + "step": 949760 + }, + { + "epoch": 0.01, + "learning_rate": 3.4442396730004595e-05, + "loss": 3.5791, + "step": 950272 + }, + { + "epoch": 0.01, + "learning_rate": 3.4434010782494075e-05, + "loss": 3.569, + "step": 950784 + }, + { + "epoch": 0.01, + "learning_rate": 3.4425624834983555e-05, + "loss": 3.5822, + "step": 951296 + }, + { + "epoch": 0.01, + "learning_rate": 3.4417255266276764e-05, + "loss": 3.5877, + "step": 951808 + }, + { + "epoch": 0.01, + "learning_rate": 3.4408869318766244e-05, + "loss": 3.5805, + "step": 952320 + }, + { + "epoch": 0.01, + "learning_rate": 3.4400483371255724e-05, + "loss": 3.5898, + "step": 952832 + }, + { + "epoch": 0.01, + "learning_rate": 3.4392097423745204e-05, + "loss": 3.5844, + "step": 953344 + }, + { + "epoch": 0.01, + "learning_rate": 3.438372785503842e-05, + "loss": 3.596, + "step": 953856 + }, + { + "epoch": 0.01, + "learning_rate": 3.43753419075279e-05, + "loss": 3.5764, + "step": 954368 + }, + { + "epoch": 0.01, + "learning_rate": 3.436695596001738e-05, + "loss": 3.5923, + "step": 954880 + }, + { + "epoch": 0.01, + "learning_rate": 3.435857001250686e-05, + "loss": 3.578, + "step": 955392 + }, + { + "epoch": 0.01, + "learning_rate": 3.435020044380007e-05, + "loss": 3.5757, + "step": 955904 + }, + { + "epoch": 0.01, + "learning_rate": 3.434181449628955e-05, + "loss": 3.5884, + "step": 956416 + }, + { + "epoch": 0.01, + "learning_rate": 3.433342854877903e-05, + "loss": 3.5765, + "step": 956928 + }, + { + "epoch": 0.01, + "learning_rate": 3.432504260126851e-05, + "loss": 3.5887, + "step": 957440 + }, + { + "epoch": 0.01, + "learning_rate": 3.431667303256172e-05, + "loss": 3.5977, + "step": 957952 + }, + { + "epoch": 0.01, + "learning_rate": 3.43082870850512e-05, + "loss": 3.5792, + "step": 958464 + }, + { + "epoch": 0.01, + "learning_rate": 3.429990113754068e-05, + "loss": 3.5588, + "step": 958976 + }, + { + "epoch": 0.01, + "learning_rate": 3.429151519003016e-05, + "loss": 3.5747, + "step": 959488 + }, + { + "epoch": 0.01, + "learning_rate": 3.428314562132337e-05, + "loss": 3.5872, + "step": 960000 + }, + { + "epoch": 0.01, + "learning_rate": 3.427475967381285e-05, + "loss": 3.5758, + "step": 960512 + }, + { + "epoch": 0.01, + "learning_rate": 3.426637372630233e-05, + "loss": 3.5786, + "step": 961024 + }, + { + "epoch": 0.01, + "learning_rate": 3.425798777879181e-05, + "loss": 3.5825, + "step": 961536 + }, + { + "epoch": 0.02, + "learning_rate": 3.424961821008502e-05, + "loss": 3.5711, + "step": 962048 + }, + { + "epoch": 0.02, + "learning_rate": 3.42412322625745e-05, + "loss": 3.5837, + "step": 962560 + }, + { + "epoch": 0.02, + "learning_rate": 3.423284631506398e-05, + "loss": 3.5747, + "step": 963072 + }, + { + "epoch": 0.02, + "learning_rate": 3.422446036755346e-05, + "loss": 3.585, + "step": 963584 + }, + { + "epoch": 0.02, + "learning_rate": 3.421609079884667e-05, + "loss": 3.585, + "step": 964096 + }, + { + "epoch": 0.02, + "learning_rate": 3.420770485133615e-05, + "loss": 3.5901, + "step": 964608 + }, + { + "epoch": 0.02, + "learning_rate": 3.419931890382563e-05, + "loss": 3.5707, + "step": 965120 + }, + { + "epoch": 0.02, + "learning_rate": 3.419093295631511e-05, + "loss": 3.578, + "step": 965632 + }, + { + "epoch": 0.02, + "learning_rate": 3.418256338760833e-05, + "loss": 3.5816, + "step": 966144 + }, + { + "epoch": 0.02, + "learning_rate": 3.417417744009781e-05, + "loss": 3.578, + "step": 966656 + }, + { + "epoch": 0.02, + "learning_rate": 3.416579149258729e-05, + "loss": 3.5854, + "step": 967168 + }, + { + "epoch": 0.02, + "learning_rate": 3.415740554507677e-05, + "loss": 3.5765, + "step": 967680 + }, + { + "epoch": 0.02, + "learning_rate": 3.414901959756624e-05, + "loss": 3.5749, + "step": 968192 + }, + { + "epoch": 0.02, + "learning_rate": 3.4140650028859456e-05, + "loss": 3.5715, + "step": 968704 + }, + { + "epoch": 0.02, + "learning_rate": 3.4132264081348936e-05, + "loss": 3.5794, + "step": 969216 + }, + { + "epoch": 0.02, + "learning_rate": 3.4123878133838416e-05, + "loss": 3.5722, + "step": 969728 + }, + { + "epoch": 0.02, + "learning_rate": 3.411549218632789e-05, + "loss": 3.5615, + "step": 970240 + }, + { + "epoch": 0.02, + "learning_rate": 3.4107122617621105e-05, + "loss": 3.5763, + "step": 970752 + }, + { + "epoch": 0.02, + "learning_rate": 3.4098736670110585e-05, + "loss": 3.5826, + "step": 971264 + }, + { + "epoch": 0.02, + "learning_rate": 3.4090350722600065e-05, + "loss": 3.5713, + "step": 971776 + }, + { + "epoch": 0.02, + "learning_rate": 3.4081964775089545e-05, + "loss": 3.5762, + "step": 972288 + }, + { + "epoch": 0.02, + "learning_rate": 3.407359520638276e-05, + "loss": 3.5723, + "step": 972800 + }, + { + "epoch": 0.02, + "learning_rate": 3.406520925887224e-05, + "loss": 3.5836, + "step": 973312 + }, + { + "epoch": 0.02, + "learning_rate": 3.4056823311361714e-05, + "loss": 3.5709, + "step": 973824 + }, + { + "epoch": 0.02, + "learning_rate": 3.4048437363851194e-05, + "loss": 3.5846, + "step": 974336 + }, + { + "epoch": 0.02, + "learning_rate": 3.404006779514441e-05, + "loss": 3.5788, + "step": 974848 + }, + { + "epoch": 0.02, + "learning_rate": 3.403168184763389e-05, + "loss": 3.5829, + "step": 975360 + }, + { + "epoch": 0.02, + "learning_rate": 3.402329590012336e-05, + "loss": 3.5815, + "step": 975872 + }, + { + "epoch": 0.02, + "learning_rate": 3.401490995261284e-05, + "loss": 3.5749, + "step": 976384 + }, + { + "epoch": 0.02, + "learning_rate": 3.400654038390606e-05, + "loss": 3.5787, + "step": 976896 + }, + { + "epoch": 0.02, + "learning_rate": 3.399815443639554e-05, + "loss": 3.5789, + "step": 977408 + }, + { + "epoch": 0.02, + "learning_rate": 3.398976848888502e-05, + "loss": 3.5755, + "step": 977920 + }, + { + "epoch": 0.02, + "learning_rate": 3.39813825413745e-05, + "loss": 3.575, + "step": 978432 + }, + { + "epoch": 0.02, + "learning_rate": 3.3973012972667714e-05, + "loss": 3.5748, + "step": 978944 + }, + { + "epoch": 0.02, + "learning_rate": 3.396462702515719e-05, + "loss": 3.5811, + "step": 979456 + }, + { + "epoch": 0.02, + "learning_rate": 3.395624107764667e-05, + "loss": 3.5714, + "step": 979968 + }, + { + "epoch": 0.02, + "learning_rate": 3.394785513013615e-05, + "loss": 3.571, + "step": 980480 + }, + { + "epoch": 0.02, + "learning_rate": 3.393948556142936e-05, + "loss": 3.5681, + "step": 980992 + }, + { + "epoch": 0.02, + "learning_rate": 3.3931099613918836e-05, + "loss": 3.5718, + "step": 981504 + }, + { + "epoch": 0.02, + "learning_rate": 3.3922713666408316e-05, + "loss": 3.587, + "step": 982016 + }, + { + "epoch": 0.02, + "learning_rate": 3.3914327718897796e-05, + "loss": 3.5737, + "step": 982528 + }, + { + "epoch": 0.02, + "learning_rate": 3.390595815019101e-05, + "loss": 3.5931, + "step": 983040 + }, + { + "epoch": 0.02, + "learning_rate": 3.3897572202680485e-05, + "loss": 3.5591, + "step": 983552 + }, + { + "epoch": 0.02, + "learning_rate": 3.388918625516997e-05, + "loss": 3.5815, + "step": 984064 + }, + { + "epoch": 0.02, + "learning_rate": 3.388080030765945e-05, + "loss": 3.5818, + "step": 984576 + }, + { + "epoch": 0.02, + "learning_rate": 3.387243073895266e-05, + "loss": 3.5843, + "step": 985088 + }, + { + "epoch": 0.02, + "learning_rate": 3.386404479144214e-05, + "loss": 3.5796, + "step": 985600 + }, + { + "epoch": 0.02, + "learning_rate": 3.385565884393162e-05, + "loss": 3.5688, + "step": 986112 + }, + { + "epoch": 0.02, + "learning_rate": 3.38472728964211e-05, + "loss": 3.5799, + "step": 986624 + }, + { + "epoch": 0.02, + "learning_rate": 3.383890332771431e-05, + "loss": 3.5933, + "step": 987136 + }, + { + "epoch": 0.02, + "learning_rate": 3.383051738020379e-05, + "loss": 3.5667, + "step": 987648 + }, + { + "epoch": 0.02, + "learning_rate": 3.382213143269327e-05, + "loss": 3.5764, + "step": 988160 + }, + { + "epoch": 0.02, + "learning_rate": 3.381374548518275e-05, + "loss": 3.5761, + "step": 988672 + }, + { + "epoch": 0.02, + "learning_rate": 3.380535953767223e-05, + "loss": 3.574, + "step": 989184 + }, + { + "epoch": 0.02, + "learning_rate": 3.379698996896544e-05, + "loss": 3.5755, + "step": 989696 + }, + { + "epoch": 0.02, + "learning_rate": 3.3788604021454926e-05, + "loss": 3.5796, + "step": 990208 + }, + { + "epoch": 0.02, + "learning_rate": 3.3780218073944406e-05, + "loss": 3.5699, + "step": 990720 + }, + { + "epoch": 0.02, + "learning_rate": 3.3771832126433886e-05, + "loss": 3.5812, + "step": 991232 + }, + { + "epoch": 0.02, + "learning_rate": 3.3763462557727095e-05, + "loss": 3.5719, + "step": 991744 + }, + { + "epoch": 0.03, + "eval_loss": 3.8423845767974854, + "eval_runtime": 316.7151, + "eval_samples_per_second": 1204.84, + "eval_steps_per_second": 37.652, + "step": 992160 + }, + { + "epoch": 0.0, + "learning_rate": 3.3755076610216575e-05, + "loss": 3.5869, + "step": 992256 + }, + { + "epoch": 0.0, + "learning_rate": 3.3746690662706055e-05, + "loss": 3.5643, + "step": 992768 + }, + { + "epoch": 0.0, + "learning_rate": 3.3738304715195535e-05, + "loss": 3.5792, + "step": 993280 + }, + { + "epoch": 0.0, + "learning_rate": 3.3729918767685015e-05, + "loss": 3.5839, + "step": 993792 + }, + { + "epoch": 0.0, + "learning_rate": 3.3721549198978224e-05, + "loss": 3.5772, + "step": 994304 + }, + { + "epoch": 0.0, + "learning_rate": 3.3713163251467704e-05, + "loss": 3.5759, + "step": 994816 + }, + { + "epoch": 0.0, + "learning_rate": 3.3704777303957184e-05, + "loss": 3.5749, + "step": 995328 + }, + { + "epoch": 0.0, + "learning_rate": 3.3696391356446664e-05, + "loss": 3.5774, + "step": 995840 + }, + { + "epoch": 0.0, + "learning_rate": 3.368802178773988e-05, + "loss": 3.567, + "step": 996352 + }, + { + "epoch": 0.0, + "learning_rate": 3.367963584022936e-05, + "loss": 3.5818, + "step": 996864 + }, + { + "epoch": 0.0, + "learning_rate": 3.367124989271884e-05, + "loss": 3.5828, + "step": 997376 + }, + { + "epoch": 0.0, + "learning_rate": 3.366286394520832e-05, + "loss": 3.5789, + "step": 997888 + }, + { + "epoch": 0.0, + "learning_rate": 3.365449437650153e-05, + "loss": 3.5875, + "step": 998400 + }, + { + "epoch": 0.0, + "learning_rate": 3.364610842899101e-05, + "loss": 3.5567, + "step": 998912 + }, + { + "epoch": 0.0, + "learning_rate": 3.363772248148049e-05, + "loss": 3.5747, + "step": 999424 + }, + { + "epoch": 0.0, + "learning_rate": 3.362933653396997e-05, + "loss": 3.5648, + "step": 999936 + }, + { + "epoch": 0.0, + "learning_rate": 3.362095058645945e-05, + "loss": 3.5724, + "step": 1000448 + }, + { + "epoch": 0.0, + "learning_rate": 3.361258101775266e-05, + "loss": 3.5673, + "step": 1000960 + }, + { + "epoch": 0.0, + "learning_rate": 3.360419507024214e-05, + "loss": 3.5636, + "step": 1001472 + }, + { + "epoch": 0.0, + "learning_rate": 3.359580912273162e-05, + "loss": 3.567, + "step": 1001984 + }, + { + "epoch": 0.0, + "learning_rate": 3.35874231752211e-05, + "loss": 3.5891, + "step": 1002496 + }, + { + "epoch": 0.0, + "learning_rate": 3.357905360651431e-05, + "loss": 3.5757, + "step": 1003008 + }, + { + "epoch": 0.0, + "learning_rate": 3.357066765900379e-05, + "loss": 3.5707, + "step": 1003520 + }, + { + "epoch": 0.0, + "learning_rate": 3.356228171149327e-05, + "loss": 3.5712, + "step": 1004032 + }, + { + "epoch": 0.0, + "learning_rate": 3.355389576398275e-05, + "loss": 3.5765, + "step": 1004544 + }, + { + "epoch": 0.0, + "learning_rate": 3.354552619527596e-05, + "loss": 3.5642, + "step": 1005056 + }, + { + "epoch": 0.0, + "learning_rate": 3.353714024776544e-05, + "loss": 3.5594, + "step": 1005568 + }, + { + "epoch": 0.0, + "learning_rate": 3.352875430025492e-05, + "loss": 3.5754, + "step": 1006080 + }, + { + "epoch": 0.0, + "learning_rate": 3.35203683527444e-05, + "loss": 3.5637, + "step": 1006592 + }, + { + "epoch": 0.0, + "learning_rate": 3.351199878403761e-05, + "loss": 3.5661, + "step": 1007104 + }, + { + "epoch": 0.01, + "learning_rate": 3.350361283652709e-05, + "loss": 3.5672, + "step": 1007616 + }, + { + "epoch": 0.01, + "learning_rate": 3.349522688901657e-05, + "loss": 3.5722, + "step": 1008128 + }, + { + "epoch": 0.01, + "learning_rate": 3.348684094150605e-05, + "loss": 3.5696, + "step": 1008640 + }, + { + "epoch": 0.01, + "learning_rate": 3.347845499399553e-05, + "loss": 3.5703, + "step": 1009152 + }, + { + "epoch": 0.01, + "learning_rate": 3.347008542528875e-05, + "loss": 3.5705, + "step": 1009664 + }, + { + "epoch": 0.01, + "learning_rate": 3.346169947777823e-05, + "loss": 3.5706, + "step": 1010176 + }, + { + "epoch": 0.01, + "learning_rate": 3.3453313530267707e-05, + "loss": 3.579, + "step": 1010688 + }, + { + "epoch": 0.01, + "learning_rate": 3.3444943961560916e-05, + "loss": 3.5509, + "step": 1011200 + }, + { + "epoch": 0.01, + "learning_rate": 3.3436558014050396e-05, + "loss": 3.5614, + "step": 1011712 + }, + { + "epoch": 0.01, + "learning_rate": 3.3428172066539876e-05, + "loss": 3.5631, + "step": 1012224 + }, + { + "epoch": 0.01, + "learning_rate": 3.3419786119029356e-05, + "loss": 3.5642, + "step": 1012736 + }, + { + "epoch": 0.01, + "learning_rate": 3.3411400171518835e-05, + "loss": 3.5643, + "step": 1013248 + }, + { + "epoch": 0.01, + "learning_rate": 3.3403030602812045e-05, + "loss": 3.5715, + "step": 1013760 + }, + { + "epoch": 0.01, + "learning_rate": 3.3394644655301525e-05, + "loss": 3.5656, + "step": 1014272 + }, + { + "epoch": 0.01, + "learning_rate": 3.3386258707791004e-05, + "loss": 3.5701, + "step": 1014784 + }, + { + "epoch": 0.01, + "learning_rate": 3.3377872760280484e-05, + "loss": 3.5698, + "step": 1015296 + }, + { + "epoch": 0.01, + "learning_rate": 3.33695031915737e-05, + "loss": 3.5745, + "step": 1015808 + }, + { + "epoch": 0.01, + "learning_rate": 3.336111724406318e-05, + "loss": 3.5652, + "step": 1016320 + }, + { + "epoch": 0.01, + "learning_rate": 3.335273129655266e-05, + "loss": 3.5458, + "step": 1016832 + }, + { + "epoch": 0.01, + "learning_rate": 3.334434534904214e-05, + "loss": 3.5763, + "step": 1017344 + }, + { + "epoch": 0.01, + "learning_rate": 3.333597578033535e-05, + "loss": 3.569, + "step": 1017856 + }, + { + "epoch": 0.01, + "learning_rate": 3.332758983282483e-05, + "loss": 3.5675, + "step": 1018368 + }, + { + "epoch": 0.01, + "learning_rate": 3.331920388531431e-05, + "loss": 3.5642, + "step": 1018880 + }, + { + "epoch": 0.01, + "learning_rate": 3.331081793780379e-05, + "loss": 3.561, + "step": 1019392 + }, + { + "epoch": 0.01, + "learning_rate": 3.3302448369097e-05, + "loss": 3.5569, + "step": 1019904 + }, + { + "epoch": 0.01, + "learning_rate": 3.329406242158648e-05, + "loss": 3.5585, + "step": 1020416 + }, + { + "epoch": 0.01, + "learning_rate": 3.328567647407596e-05, + "loss": 3.5781, + "step": 1020928 + }, + { + "epoch": 0.01, + "learning_rate": 3.327729052656544e-05, + "loss": 3.558, + "step": 1021440 + }, + { + "epoch": 0.01, + "learning_rate": 3.3268920957858654e-05, + "loss": 3.5829, + "step": 1021952 + }, + { + "epoch": 0.01, + "learning_rate": 3.3260535010348134e-05, + "loss": 3.5711, + "step": 1022464 + }, + { + "epoch": 0.01, + "learning_rate": 3.3252149062837614e-05, + "loss": 3.5471, + "step": 1022976 + }, + { + "epoch": 0.01, + "learning_rate": 3.3243763115327094e-05, + "loss": 3.5725, + "step": 1023488 + }, + { + "epoch": 0.01, + "learning_rate": 3.32353935466203e-05, + "loss": 3.5573, + "step": 1024000 + }, + { + "epoch": 0.01, + "learning_rate": 3.322700759910978e-05, + "loss": 3.5534, + "step": 1024512 + }, + { + "epoch": 0.01, + "learning_rate": 3.321862165159926e-05, + "loss": 3.5568, + "step": 1025024 + }, + { + "epoch": 0.01, + "learning_rate": 3.3210235704088736e-05, + "loss": 3.56, + "step": 1025536 + }, + { + "epoch": 0.01, + "learning_rate": 3.320186613538195e-05, + "loss": 3.5598, + "step": 1026048 + }, + { + "epoch": 0.01, + "learning_rate": 3.319348018787143e-05, + "loss": 3.5628, + "step": 1026560 + }, + { + "epoch": 0.01, + "learning_rate": 3.318509424036091e-05, + "loss": 3.5503, + "step": 1027072 + }, + { + "epoch": 0.01, + "learning_rate": 3.317670829285039e-05, + "loss": 3.566, + "step": 1027584 + }, + { + "epoch": 0.01, + "learning_rate": 3.316832234533987e-05, + "loss": 3.5715, + "step": 1028096 + }, + { + "epoch": 0.01, + "learning_rate": 3.315995277663309e-05, + "loss": 3.566, + "step": 1028608 + }, + { + "epoch": 0.01, + "learning_rate": 3.315156682912257e-05, + "loss": 3.5716, + "step": 1029120 + }, + { + "epoch": 0.01, + "learning_rate": 3.314318088161204e-05, + "loss": 3.568, + "step": 1029632 + }, + { + "epoch": 0.01, + "learning_rate": 3.313479493410152e-05, + "loss": 3.5808, + "step": 1030144 + }, + { + "epoch": 0.01, + "learning_rate": 3.3126425365394737e-05, + "loss": 3.5589, + "step": 1030656 + }, + { + "epoch": 0.01, + "learning_rate": 3.311803941788421e-05, + "loss": 3.5722, + "step": 1031168 + }, + { + "epoch": 0.01, + "learning_rate": 3.310965347037369e-05, + "loss": 3.5666, + "step": 1031680 + }, + { + "epoch": 0.01, + "learning_rate": 3.310126752286317e-05, + "loss": 3.5607, + "step": 1032192 + }, + { + "epoch": 0.01, + "learning_rate": 3.3092897954156386e-05, + "loss": 3.5694, + "step": 1032704 + }, + { + "epoch": 0.01, + "learning_rate": 3.3084512006645866e-05, + "loss": 3.5611, + "step": 1033216 + }, + { + "epoch": 0.01, + "learning_rate": 3.3076126059135345e-05, + "loss": 3.5717, + "step": 1033728 + }, + { + "epoch": 0.01, + "learning_rate": 3.3067740111624825e-05, + "loss": 3.5798, + "step": 1034240 + }, + { + "epoch": 0.01, + "learning_rate": 3.305937054291804e-05, + "loss": 3.5649, + "step": 1034752 + }, + { + "epoch": 0.01, + "learning_rate": 3.3050984595407514e-05, + "loss": 3.5442, + "step": 1035264 + }, + { + "epoch": 0.01, + "learning_rate": 3.3042598647896994e-05, + "loss": 3.5547, + "step": 1035776 + }, + { + "epoch": 0.01, + "learning_rate": 3.3034212700386474e-05, + "loss": 3.5672, + "step": 1036288 + }, + { + "epoch": 0.01, + "learning_rate": 3.3025843131679683e-05, + "loss": 3.5652, + "step": 1036800 + }, + { + "epoch": 0.01, + "learning_rate": 3.3017457184169163e-05, + "loss": 3.5593, + "step": 1037312 + }, + { + "epoch": 0.01, + "learning_rate": 3.300907123665864e-05, + "loss": 3.565, + "step": 1037824 + }, + { + "epoch": 0.02, + "learning_rate": 3.300068528914812e-05, + "loss": 3.5582, + "step": 1038336 + }, + { + "epoch": 0.02, + "learning_rate": 3.299231572044133e-05, + "loss": 3.5613, + "step": 1038848 + }, + { + "epoch": 0.02, + "learning_rate": 3.298392977293082e-05, + "loss": 3.5623, + "step": 1039360 + }, + { + "epoch": 0.02, + "learning_rate": 3.29755438254203e-05, + "loss": 3.5662, + "step": 1039872 + }, + { + "epoch": 0.02, + "learning_rate": 3.296715787790978e-05, + "loss": 3.5697, + "step": 1040384 + }, + { + "epoch": 0.02, + "learning_rate": 3.295878830920299e-05, + "loss": 3.5745, + "step": 1040896 + }, + { + "epoch": 0.02, + "learning_rate": 3.295040236169247e-05, + "loss": 3.5542, + "step": 1041408 + }, + { + "epoch": 0.02, + "learning_rate": 3.294201641418195e-05, + "loss": 3.5601, + "step": 1041920 + }, + { + "epoch": 0.02, + "learning_rate": 3.293363046667143e-05, + "loss": 3.5662, + "step": 1042432 + }, + { + "epoch": 0.02, + "learning_rate": 3.292526089796464e-05, + "loss": 3.5597, + "step": 1042944 + }, + { + "epoch": 0.02, + "learning_rate": 3.291687495045412e-05, + "loss": 3.5718, + "step": 1043456 + }, + { + "epoch": 0.02, + "learning_rate": 3.29084890029436e-05, + "loss": 3.5608, + "step": 1043968 + }, + { + "epoch": 0.02, + "learning_rate": 3.290010305543308e-05, + "loss": 3.5553, + "step": 1044480 + }, + { + "epoch": 0.02, + "learning_rate": 3.2891733486726286e-05, + "loss": 3.5538, + "step": 1044992 + }, + { + "epoch": 0.02, + "learning_rate": 3.288334753921577e-05, + "loss": 3.5668, + "step": 1045504 + }, + { + "epoch": 0.02, + "learning_rate": 3.287496159170525e-05, + "loss": 3.5568, + "step": 1046016 + }, + { + "epoch": 0.02, + "learning_rate": 3.286657564419473e-05, + "loss": 3.5424, + "step": 1046528 + }, + { + "epoch": 0.02, + "learning_rate": 3.285820607548794e-05, + "loss": 3.5613, + "step": 1047040 + }, + { + "epoch": 0.02, + "learning_rate": 3.284982012797742e-05, + "loss": 3.5652, + "step": 1047552 + }, + { + "epoch": 0.02, + "learning_rate": 3.28414341804669e-05, + "loss": 3.5563, + "step": 1048064 + }, + { + "epoch": 0.02, + "learning_rate": 3.283304823295638e-05, + "loss": 3.5554, + "step": 1048576 + }, + { + "epoch": 0.02, + "learning_rate": 3.282467866424959e-05, + "loss": 3.5555, + "step": 1049088 + }, + { + "epoch": 0.02, + "learning_rate": 3.281629271673907e-05, + "loss": 3.5666, + "step": 1049600 + }, + { + "epoch": 0.02, + "learning_rate": 3.280790676922855e-05, + "loss": 3.5555, + "step": 1050112 + }, + { + "epoch": 0.02, + "learning_rate": 3.279952082171803e-05, + "loss": 3.5641, + "step": 1050624 + }, + { + "epoch": 0.02, + "learning_rate": 3.279115125301124e-05, + "loss": 3.5684, + "step": 1051136 + }, + { + "epoch": 0.02, + "learning_rate": 3.2782765305500727e-05, + "loss": 3.5673, + "step": 1051648 + }, + { + "epoch": 0.02, + "learning_rate": 3.2774379357990206e-05, + "loss": 3.5629, + "step": 1052160 + }, + { + "epoch": 0.02, + "learning_rate": 3.2765993410479686e-05, + "loss": 3.5587, + "step": 1052672 + }, + { + "epoch": 0.02, + "learning_rate": 3.2757623841772896e-05, + "loss": 3.5609, + "step": 1053184 + }, + { + "epoch": 0.02, + "learning_rate": 3.2749237894262375e-05, + "loss": 3.5608, + "step": 1053696 + }, + { + "epoch": 0.02, + "learning_rate": 3.2740851946751855e-05, + "loss": 3.5554, + "step": 1054208 + }, + { + "epoch": 0.02, + "learning_rate": 3.2732465999241335e-05, + "loss": 3.5621, + "step": 1054720 + }, + { + "epoch": 0.02, + "learning_rate": 3.2724096430534544e-05, + "loss": 3.5564, + "step": 1055232 + }, + { + "epoch": 0.02, + "learning_rate": 3.2715710483024024e-05, + "loss": 3.5613, + "step": 1055744 + }, + { + "epoch": 0.02, + "learning_rate": 3.2707324535513504e-05, + "loss": 3.5548, + "step": 1056256 + }, + { + "epoch": 0.02, + "learning_rate": 3.2698938588002984e-05, + "loss": 3.5575, + "step": 1056768 + }, + { + "epoch": 0.02, + "learning_rate": 3.2690569019296193e-05, + "loss": 3.5488, + "step": 1057280 + }, + { + "epoch": 0.02, + "learning_rate": 3.268218307178568e-05, + "loss": 3.5574, + "step": 1057792 + }, + { + "epoch": 0.02, + "learning_rate": 3.267379712427516e-05, + "loss": 3.5715, + "step": 1058304 + }, + { + "epoch": 0.02, + "learning_rate": 3.266541117676464e-05, + "loss": 3.5583, + "step": 1058816 + }, + { + "epoch": 0.02, + "learning_rate": 3.265704160805785e-05, + "loss": 3.5736, + "step": 1059328 + }, + { + "epoch": 0.02, + "learning_rate": 3.264865566054733e-05, + "loss": 3.5411, + "step": 1059840 + }, + { + "epoch": 0.02, + "learning_rate": 3.264026971303681e-05, + "loss": 3.5661, + "step": 1060352 + }, + { + "epoch": 0.02, + "learning_rate": 3.263188376552629e-05, + "loss": 3.5669, + "step": 1060864 + }, + { + "epoch": 0.02, + "learning_rate": 3.26235141968195e-05, + "loss": 3.5645, + "step": 1061376 + }, + { + "epoch": 0.02, + "learning_rate": 3.261512824930898e-05, + "loss": 3.564, + "step": 1061888 + }, + { + "epoch": 0.02, + "learning_rate": 3.260674230179846e-05, + "loss": 3.5501, + "step": 1062400 + }, + { + "epoch": 0.02, + "learning_rate": 3.259835635428794e-05, + "loss": 3.566, + "step": 1062912 + }, + { + "epoch": 0.02, + "learning_rate": 3.258998678558115e-05, + "loss": 3.5762, + "step": 1063424 + }, + { + "epoch": 0.02, + "learning_rate": 3.2581600838070634e-05, + "loss": 3.5515, + "step": 1063936 + }, + { + "epoch": 0.02, + "learning_rate": 3.2573214890560114e-05, + "loss": 3.5564, + "step": 1064448 + }, + { + "epoch": 0.02, + "learning_rate": 3.2564828943049594e-05, + "loss": 3.5643, + "step": 1064960 + }, + { + "epoch": 0.02, + "learning_rate": 3.2556442995539074e-05, + "loss": 3.5566, + "step": 1065472 + }, + { + "epoch": 0.02, + "learning_rate": 3.254807342683228e-05, + "loss": 3.5557, + "step": 1065984 + }, + { + "epoch": 0.02, + "learning_rate": 3.253968747932176e-05, + "loss": 3.5658, + "step": 1066496 + }, + { + "epoch": 0.02, + "learning_rate": 3.253130153181124e-05, + "loss": 3.5514, + "step": 1067008 + }, + { + "epoch": 0.02, + "learning_rate": 3.252293196310445e-05, + "loss": 3.5692, + "step": 1067520 + }, + { + "epoch": 0.02, + "learning_rate": 3.251454601559393e-05, + "loss": 3.5509, + "step": 1068032 + }, + { + "epoch": 0.03, + "eval_loss": 3.842683792114258, + "eval_runtime": 304.2114, + "eval_samples_per_second": 1254.361, + "eval_steps_per_second": 39.2, + "step": 1068480 + }, + { + "epoch": 1.0, + "learning_rate": 3.250616006808341e-05, + "loss": 3.5587, + "step": 1068544 + }, + { + "epoch": 1.0, + "learning_rate": 3.249777412057289e-05, + "loss": 3.5488, + "step": 1069056 + }, + { + "epoch": 1.0, + "learning_rate": 3.24894045518661e-05, + "loss": 3.5615, + "step": 1069568 + }, + { + "epoch": 1.0, + "learning_rate": 3.248101860435559e-05, + "loss": 3.5699, + "step": 1070080 + }, + { + "epoch": 1.0, + "learning_rate": 3.247263265684507e-05, + "loss": 3.5612, + "step": 1070592 + }, + { + "epoch": 1.0, + "learning_rate": 3.246424670933455e-05, + "loss": 3.559, + "step": 1071104 + }, + { + "epoch": 1.0, + "learning_rate": 3.2455877140627757e-05, + "loss": 3.5573, + "step": 1071616 + }, + { + "epoch": 1.0, + "learning_rate": 3.2447491193117236e-05, + "loss": 3.5587, + "step": 1072128 + }, + { + "epoch": 1.0, + "learning_rate": 3.2439105245606716e-05, + "loss": 3.5488, + "step": 1072640 + }, + { + "epoch": 1.0, + "learning_rate": 3.2430719298096196e-05, + "loss": 3.5699, + "step": 1073152 + }, + { + "epoch": 1.0, + "learning_rate": 3.2422349729389405e-05, + "loss": 3.5638, + "step": 1073664 + }, + { + "epoch": 1.0, + "learning_rate": 3.2413963781878885e-05, + "loss": 3.5644, + "step": 1074176 + }, + { + "epoch": 1.0, + "learning_rate": 3.2405594213172095e-05, + "loss": 3.572, + "step": 1074688 + }, + { + "epoch": 1.0, + "learning_rate": 3.2397208265661574e-05, + "loss": 3.5415, + "step": 1075200 + }, + { + "epoch": 1.0, + "learning_rate": 3.2388822318151054e-05, + "loss": 3.5598, + "step": 1075712 + }, + { + "epoch": 1.0, + "learning_rate": 3.238043637064054e-05, + "loss": 3.5482, + "step": 1076224 + }, + { + "epoch": 1.0, + "learning_rate": 3.237205042313002e-05, + "loss": 3.5578, + "step": 1076736 + }, + { + "epoch": 1.0, + "learning_rate": 3.23636644756195e-05, + "loss": 3.5475, + "step": 1077248 + }, + { + "epoch": 1.0, + "learning_rate": 3.235527852810898e-05, + "loss": 3.5533, + "step": 1077760 + }, + { + "epoch": 1.0, + "learning_rate": 3.234689258059846e-05, + "loss": 3.5483, + "step": 1078272 + }, + { + "epoch": 1.0, + "learning_rate": 3.233852301189167e-05, + "loss": 3.5738, + "step": 1078784 + }, + { + "epoch": 1.0, + "learning_rate": 3.233013706438115e-05, + "loss": 3.5603, + "step": 1079296 + }, + { + "epoch": 1.0, + "learning_rate": 3.232175111687063e-05, + "loss": 3.5569, + "step": 1079808 + }, + { + "epoch": 1.0, + "learning_rate": 3.231336516936011e-05, + "loss": 3.555, + "step": 1080320 + }, + { + "epoch": 1.0, + "learning_rate": 3.230499560065332e-05, + "loss": 3.5617, + "step": 1080832 + }, + { + "epoch": 1.0, + "learning_rate": 3.22966096531428e-05, + "loss": 3.5453, + "step": 1081344 + }, + { + "epoch": 1.0, + "learning_rate": 3.228822370563228e-05, + "loss": 3.5473, + "step": 1081856 + }, + { + "epoch": 1.0, + "learning_rate": 3.227983775812176e-05, + "loss": 3.5582, + "step": 1082368 + }, + { + "epoch": 1.0, + "learning_rate": 3.2271468189414975e-05, + "loss": 3.5483, + "step": 1082880 + }, + { + "epoch": 1.0, + "learning_rate": 3.2263082241904455e-05, + "loss": 3.5487, + "step": 1083392 + }, + { + "epoch": 1.01, + "learning_rate": 3.2254696294393935e-05, + "loss": 3.5519, + "step": 1083904 + }, + { + "epoch": 1.01, + "learning_rate": 3.2246310346883415e-05, + "loss": 3.5538, + "step": 1084416 + }, + { + "epoch": 1.01, + "learning_rate": 3.2237940778176624e-05, + "loss": 3.5582, + "step": 1084928 + }, + { + "epoch": 1.01, + "learning_rate": 3.2229554830666104e-05, + "loss": 3.5515, + "step": 1085440 + }, + { + "epoch": 1.01, + "learning_rate": 3.2221168883155584e-05, + "loss": 3.5484, + "step": 1085952 + }, + { + "epoch": 1.01, + "learning_rate": 3.221278293564506e-05, + "loss": 3.5618, + "step": 1086464 + }, + { + "epoch": 1.01, + "learning_rate": 3.220441336693827e-05, + "loss": 3.559, + "step": 1086976 + }, + { + "epoch": 1.01, + "learning_rate": 3.219602741942775e-05, + "loss": 3.5361, + "step": 1087488 + }, + { + "epoch": 1.01, + "learning_rate": 3.218764147191723e-05, + "loss": 3.5477, + "step": 1088000 + }, + { + "epoch": 1.01, + "learning_rate": 3.217925552440671e-05, + "loss": 3.5457, + "step": 1088512 + }, + { + "epoch": 1.01, + "learning_rate": 3.217086957689619e-05, + "loss": 3.5455, + "step": 1089024 + }, + { + "epoch": 1.01, + "learning_rate": 3.216250000818941e-05, + "loss": 3.5497, + "step": 1089536 + }, + { + "epoch": 1.01, + "learning_rate": 3.215411406067889e-05, + "loss": 3.5582, + "step": 1090048 + }, + { + "epoch": 1.01, + "learning_rate": 3.214572811316836e-05, + "loss": 3.5461, + "step": 1090560 + }, + { + "epoch": 1.01, + "learning_rate": 3.213734216565784e-05, + "loss": 3.5517, + "step": 1091072 + }, + { + "epoch": 1.01, + "learning_rate": 3.212897259695106e-05, + "loss": 3.5586, + "step": 1091584 + }, + { + "epoch": 1.01, + "learning_rate": 3.212058664944053e-05, + "loss": 3.5539, + "step": 1092096 + }, + { + "epoch": 1.01, + "learning_rate": 3.211220070193001e-05, + "loss": 3.5527, + "step": 1092608 + }, + { + "epoch": 1.01, + "learning_rate": 3.210381475441949e-05, + "loss": 3.5308, + "step": 1093120 + }, + { + "epoch": 1.01, + "learning_rate": 3.2095445185712706e-05, + "loss": 3.5571, + "step": 1093632 + }, + { + "epoch": 1.01, + "learning_rate": 3.208705923820218e-05, + "loss": 3.5557, + "step": 1094144 + }, + { + "epoch": 1.01, + "learning_rate": 3.2078673290691666e-05, + "loss": 3.5504, + "step": 1094656 + }, + { + "epoch": 1.01, + "learning_rate": 3.2070287343181146e-05, + "loss": 3.5473, + "step": 1095168 + }, + { + "epoch": 1.01, + "learning_rate": 3.206191777447436e-05, + "loss": 3.5486, + "step": 1095680 + }, + { + "epoch": 1.01, + "learning_rate": 3.2053531826963835e-05, + "loss": 3.534, + "step": 1096192 + }, + { + "epoch": 1.01, + "learning_rate": 3.2045145879453315e-05, + "loss": 3.5454, + "step": 1096704 + }, + { + "epoch": 1.01, + "learning_rate": 3.2036759931942795e-05, + "loss": 3.5626, + "step": 1097216 + }, + { + "epoch": 1.01, + "learning_rate": 3.2028390363236004e-05, + "loss": 3.5448, + "step": 1097728 + }, + { + "epoch": 1.01, + "learning_rate": 3.2020004415725484e-05, + "loss": 3.563, + "step": 1098240 + }, + { + "epoch": 1.01, + "learning_rate": 3.2011618468214964e-05, + "loss": 3.5557, + "step": 1098752 + }, + { + "epoch": 1.01, + "learning_rate": 3.2003232520704444e-05, + "loss": 3.5339, + "step": 1099264 + }, + { + "epoch": 1.01, + "learning_rate": 3.199486295199765e-05, + "loss": 3.5565, + "step": 1099776 + }, + { + "epoch": 1.01, + "learning_rate": 3.198647700448713e-05, + "loss": 3.5394, + "step": 1100288 + }, + { + "epoch": 1.01, + "learning_rate": 3.197809105697662e-05, + "loss": 3.5363, + "step": 1100800 + }, + { + "epoch": 1.01, + "learning_rate": 3.19697051094661e-05, + "loss": 3.5385, + "step": 1101312 + }, + { + "epoch": 1.01, + "learning_rate": 3.196133554075931e-05, + "loss": 3.5503, + "step": 1101824 + }, + { + "epoch": 1.01, + "learning_rate": 3.195294959324879e-05, + "loss": 3.5418, + "step": 1102336 + }, + { + "epoch": 1.01, + "learning_rate": 3.194456364573827e-05, + "loss": 3.5402, + "step": 1102848 + }, + { + "epoch": 1.01, + "learning_rate": 3.193617769822775e-05, + "loss": 3.5351, + "step": 1103360 + }, + { + "epoch": 1.01, + "learning_rate": 3.192780812952096e-05, + "loss": 3.5509, + "step": 1103872 + }, + { + "epoch": 1.01, + "learning_rate": 3.191942218201044e-05, + "loss": 3.5557, + "step": 1104384 + }, + { + "epoch": 1.01, + "learning_rate": 3.191103623449992e-05, + "loss": 3.5527, + "step": 1104896 + }, + { + "epoch": 1.01, + "learning_rate": 3.19026502869894e-05, + "loss": 3.5538, + "step": 1105408 + }, + { + "epoch": 1.01, + "learning_rate": 3.189428071828261e-05, + "loss": 3.5547, + "step": 1105920 + }, + { + "epoch": 1.01, + "learning_rate": 3.188589477077209e-05, + "loss": 3.5602, + "step": 1106432 + }, + { + "epoch": 1.01, + "learning_rate": 3.1877508823261574e-05, + "loss": 3.5509, + "step": 1106944 + }, + { + "epoch": 1.01, + "learning_rate": 3.1869122875751054e-05, + "loss": 3.5511, + "step": 1107456 + }, + { + "epoch": 1.01, + "learning_rate": 3.186075330704426e-05, + "loss": 3.55, + "step": 1107968 + }, + { + "epoch": 1.01, + "learning_rate": 3.185236735953374e-05, + "loss": 3.5463, + "step": 1108480 + }, + { + "epoch": 1.01, + "learning_rate": 3.184398141202322e-05, + "loss": 3.5526, + "step": 1108992 + }, + { + "epoch": 1.01, + "learning_rate": 3.18355954645127e-05, + "loss": 3.5458, + "step": 1109504 + }, + { + "epoch": 1.01, + "learning_rate": 3.182720951700218e-05, + "loss": 3.5555, + "step": 1110016 + }, + { + "epoch": 1.01, + "learning_rate": 3.181883994829539e-05, + "loss": 3.5653, + "step": 1110528 + }, + { + "epoch": 1.01, + "learning_rate": 3.181045400078487e-05, + "loss": 3.5489, + "step": 1111040 + }, + { + "epoch": 1.01, + "learning_rate": 3.180206805327435e-05, + "loss": 3.5258, + "step": 1111552 + }, + { + "epoch": 1.01, + "learning_rate": 3.179368210576383e-05, + "loss": 3.5426, + "step": 1112064 + }, + { + "epoch": 1.01, + "learning_rate": 3.178531253705704e-05, + "loss": 3.5519, + "step": 1112576 + }, + { + "epoch": 1.01, + "learning_rate": 3.177692658954653e-05, + "loss": 3.548, + "step": 1113088 + }, + { + "epoch": 1.01, + "learning_rate": 3.176854064203601e-05, + "loss": 3.545, + "step": 1113600 + }, + { + "epoch": 1.01, + "learning_rate": 3.1760171073329216e-05, + "loss": 3.5537, + "step": 1114112 + }, + { + "epoch": 1.02, + "learning_rate": 3.1751785125818696e-05, + "loss": 3.538, + "step": 1114624 + }, + { + "epoch": 1.02, + "learning_rate": 3.1743399178308176e-05, + "loss": 3.5455, + "step": 1115136 + }, + { + "epoch": 1.02, + "learning_rate": 3.1735013230797656e-05, + "loss": 3.5486, + "step": 1115648 + }, + { + "epoch": 1.02, + "learning_rate": 3.1726627283287136e-05, + "loss": 3.5532, + "step": 1116160 + }, + { + "epoch": 1.02, + "learning_rate": 3.1718257714580345e-05, + "loss": 3.5495, + "step": 1116672 + }, + { + "epoch": 1.02, + "learning_rate": 3.1709871767069825e-05, + "loss": 3.562, + "step": 1117184 + }, + { + "epoch": 1.02, + "learning_rate": 3.1701485819559305e-05, + "loss": 3.5352, + "step": 1117696 + }, + { + "epoch": 1.02, + "learning_rate": 3.1693099872048785e-05, + "loss": 3.5464, + "step": 1118208 + }, + { + "epoch": 1.02, + "learning_rate": 3.1684730303341994e-05, + "loss": 3.5528, + "step": 1118720 + }, + { + "epoch": 1.02, + "learning_rate": 3.167634435583148e-05, + "loss": 3.5455, + "step": 1119232 + }, + { + "epoch": 1.02, + "learning_rate": 3.166795840832096e-05, + "loss": 3.5587, + "step": 1119744 + }, + { + "epoch": 1.02, + "learning_rate": 3.165957246081044e-05, + "loss": 3.5396, + "step": 1120256 + }, + { + "epoch": 1.02, + "learning_rate": 3.165120289210365e-05, + "loss": 3.5406, + "step": 1120768 + }, + { + "epoch": 1.02, + "learning_rate": 3.164281694459313e-05, + "loss": 3.5383, + "step": 1121280 + }, + { + "epoch": 1.02, + "learning_rate": 3.163443099708261e-05, + "loss": 3.5526, + "step": 1121792 + }, + { + "epoch": 1.02, + "learning_rate": 3.162604504957209e-05, + "loss": 3.5389, + "step": 1122304 + }, + { + "epoch": 1.02, + "learning_rate": 3.16176754808653e-05, + "loss": 3.5286, + "step": 1122816 + }, + { + "epoch": 1.02, + "learning_rate": 3.160928953335478e-05, + "loss": 3.5446, + "step": 1123328 + }, + { + "epoch": 1.02, + "learning_rate": 3.160090358584426e-05, + "loss": 3.5466, + "step": 1123840 + }, + { + "epoch": 1.02, + "learning_rate": 3.159251763833374e-05, + "loss": 3.5417, + "step": 1124352 + }, + { + "epoch": 1.02, + "learning_rate": 3.158414806962695e-05, + "loss": 3.5467, + "step": 1124864 + }, + { + "epoch": 1.02, + "learning_rate": 3.1575762122116435e-05, + "loss": 3.5352, + "step": 1125376 + }, + { + "epoch": 1.02, + "learning_rate": 3.1567376174605915e-05, + "loss": 3.5533, + "step": 1125888 + }, + { + "epoch": 1.02, + "learning_rate": 3.1558990227095394e-05, + "loss": 3.5387, + "step": 1126400 + }, + { + "epoch": 1.02, + "learning_rate": 3.1550620658388604e-05, + "loss": 3.5464, + "step": 1126912 + }, + { + "epoch": 1.02, + "learning_rate": 3.1542234710878084e-05, + "loss": 3.555, + "step": 1127424 + }, + { + "epoch": 1.02, + "learning_rate": 3.1533848763367564e-05, + "loss": 3.554, + "step": 1127936 + }, + { + "epoch": 1.02, + "learning_rate": 3.1525462815857043e-05, + "loss": 3.5448, + "step": 1128448 + }, + { + "epoch": 1.02, + "learning_rate": 3.151709324715025e-05, + "loss": 3.5421, + "step": 1128960 + }, + { + "epoch": 1.02, + "learning_rate": 3.150870729963973e-05, + "loss": 3.5478, + "step": 1129472 + }, + { + "epoch": 1.02, + "learning_rate": 3.150032135212921e-05, + "loss": 3.5462, + "step": 1129984 + }, + { + "epoch": 1.02, + "learning_rate": 3.149193540461869e-05, + "loss": 3.5388, + "step": 1130496 + }, + { + "epoch": 1.02, + "learning_rate": 3.14835658359119e-05, + "loss": 3.5513, + "step": 1131008 + }, + { + "epoch": 1.02, + "learning_rate": 3.147517988840139e-05, + "loss": 3.5419, + "step": 1131520 + }, + { + "epoch": 1.02, + "learning_rate": 3.146679394089087e-05, + "loss": 3.5424, + "step": 1132032 + }, + { + "epoch": 1.02, + "learning_rate": 3.145840799338035e-05, + "loss": 3.538, + "step": 1132544 + }, + { + "epoch": 1.02, + "learning_rate": 3.145003842467356e-05, + "loss": 3.5423, + "step": 1133056 + }, + { + "epoch": 1.02, + "learning_rate": 3.144165247716304e-05, + "loss": 3.5382, + "step": 1133568 + }, + { + "epoch": 1.02, + "learning_rate": 3.143326652965252e-05, + "loss": 3.541, + "step": 1134080 + }, + { + "epoch": 1.02, + "learning_rate": 3.1424880582142e-05, + "loss": 3.553, + "step": 1134592 + }, + { + "epoch": 1.02, + "learning_rate": 3.1416511013435206e-05, + "loss": 3.5467, + "step": 1135104 + }, + { + "epoch": 1.02, + "learning_rate": 3.1408125065924686e-05, + "loss": 3.555, + "step": 1135616 + }, + { + "epoch": 1.02, + "learning_rate": 3.1399739118414166e-05, + "loss": 3.5312, + "step": 1136128 + }, + { + "epoch": 1.02, + "learning_rate": 3.1391353170903646e-05, + "loss": 3.5464, + "step": 1136640 + }, + { + "epoch": 1.02, + "learning_rate": 3.1382983602196855e-05, + "loss": 3.5507, + "step": 1137152 + }, + { + "epoch": 1.02, + "learning_rate": 3.1374597654686335e-05, + "loss": 3.551, + "step": 1137664 + }, + { + "epoch": 1.02, + "learning_rate": 3.136621170717582e-05, + "loss": 3.5433, + "step": 1138176 + }, + { + "epoch": 1.02, + "learning_rate": 3.13578257596653e-05, + "loss": 3.5384, + "step": 1138688 + }, + { + "epoch": 1.02, + "learning_rate": 3.134945619095851e-05, + "loss": 3.5524, + "step": 1139200 + }, + { + "epoch": 1.02, + "learning_rate": 3.134107024344799e-05, + "loss": 3.5604, + "step": 1139712 + }, + { + "epoch": 1.02, + "learning_rate": 3.133268429593747e-05, + "loss": 3.5399, + "step": 1140224 + }, + { + "epoch": 1.02, + "learning_rate": 3.132429834842695e-05, + "loss": 3.5396, + "step": 1140736 + }, + { + "epoch": 1.02, + "learning_rate": 3.131592877972016e-05, + "loss": 3.5477, + "step": 1141248 + }, + { + "epoch": 1.02, + "learning_rate": 3.130754283220964e-05, + "loss": 3.5408, + "step": 1141760 + }, + { + "epoch": 1.02, + "learning_rate": 3.129915688469912e-05, + "loss": 3.5403, + "step": 1142272 + }, + { + "epoch": 1.02, + "learning_rate": 3.12907709371886e-05, + "loss": 3.5494, + "step": 1142784 + }, + { + "epoch": 1.02, + "learning_rate": 3.128238498967808e-05, + "loss": 3.5357, + "step": 1143296 + }, + { + "epoch": 1.02, + "learning_rate": 3.127401542097129e-05, + "loss": 3.5537, + "step": 1143808 + }, + { + "epoch": 1.02, + "learning_rate": 3.1265629473460776e-05, + "loss": 3.5351, + "step": 1144320 + }, + { + "epoch": 1.03, + "eval_loss": 3.8427441120147705, + "eval_runtime": 306.727, + "eval_samples_per_second": 1244.074, + "eval_steps_per_second": 38.878, + "step": 1144800 + }, + { + "epoch": 0.0, + "learning_rate": 3.1257243525950256e-05, + "loss": 3.5113, + "step": 1144832 + }, + { + "epoch": 0.0, + "learning_rate": 3.1248857578439735e-05, + "loss": 3.5384, + "step": 1145344 + }, + { + "epoch": 0.0, + "learning_rate": 3.124047163092921e-05, + "loss": 3.5441, + "step": 1145856 + }, + { + "epoch": 0.0, + "learning_rate": 3.123208568341869e-05, + "loss": 3.553, + "step": 1146368 + }, + { + "epoch": 0.0, + "learning_rate": 3.1223716114711904e-05, + "loss": 3.5451, + "step": 1146880 + }, + { + "epoch": 0.0, + "learning_rate": 3.1215330167201384e-05, + "loss": 3.5451, + "step": 1147392 + }, + { + "epoch": 0.0, + "learning_rate": 3.120694421969086e-05, + "loss": 3.542, + "step": 1147904 + }, + { + "epoch": 0.0, + "learning_rate": 3.119855827218034e-05, + "loss": 3.5408, + "step": 1148416 + }, + { + "epoch": 0.0, + "learning_rate": 3.1190188703473553e-05, + "loss": 3.5375, + "step": 1148928 + }, + { + "epoch": 0.0, + "learning_rate": 3.1181802755963027e-05, + "loss": 3.5499, + "step": 1149440 + }, + { + "epoch": 0.0, + "learning_rate": 3.117341680845251e-05, + "loss": 3.5491, + "step": 1149952 + }, + { + "epoch": 0.0, + "learning_rate": 3.116503086094199e-05, + "loss": 3.5498, + "step": 1150464 + }, + { + "epoch": 0.0, + "learning_rate": 3.115666129223521e-05, + "loss": 3.5573, + "step": 1150976 + }, + { + "epoch": 0.0, + "learning_rate": 3.114827534472468e-05, + "loss": 3.5258, + "step": 1151488 + }, + { + "epoch": 0.0, + "learning_rate": 3.113988939721416e-05, + "loss": 3.5436, + "step": 1152000 + }, + { + "epoch": 0.0, + "learning_rate": 3.113150344970364e-05, + "loss": 3.5338, + "step": 1152512 + }, + { + "epoch": 0.0, + "learning_rate": 3.112313388099686e-05, + "loss": 3.5449, + "step": 1153024 + }, + { + "epoch": 0.0, + "learning_rate": 3.111474793348633e-05, + "loss": 3.5292, + "step": 1153536 + }, + { + "epoch": 0.0, + "learning_rate": 3.110636198597581e-05, + "loss": 3.5362, + "step": 1154048 + }, + { + "epoch": 0.0, + "learning_rate": 3.109797603846529e-05, + "loss": 3.5369, + "step": 1154560 + }, + { + "epoch": 0.0, + "learning_rate": 3.10896064697585e-05, + "loss": 3.5562, + "step": 1155072 + }, + { + "epoch": 0.0, + "learning_rate": 3.108122052224798e-05, + "loss": 3.5482, + "step": 1155584 + }, + { + "epoch": 0.0, + "learning_rate": 3.107283457473747e-05, + "loss": 3.5352, + "step": 1156096 + }, + { + "epoch": 0.0, + "learning_rate": 3.106444862722695e-05, + "loss": 3.5379, + "step": 1156608 + }, + { + "epoch": 0.0, + "learning_rate": 3.1056079058520156e-05, + "loss": 3.5483, + "step": 1157120 + }, + { + "epoch": 0.0, + "learning_rate": 3.1047693111009636e-05, + "loss": 3.53, + "step": 1157632 + }, + { + "epoch": 0.0, + "learning_rate": 3.1039307163499116e-05, + "loss": 3.5297, + "step": 1158144 + }, + { + "epoch": 0.0, + "learning_rate": 3.1030921215988596e-05, + "loss": 3.5441, + "step": 1158656 + }, + { + "epoch": 0.0, + "learning_rate": 3.1022551647281805e-05, + "loss": 3.5302, + "step": 1159168 + }, + { + "epoch": 0.0, + "learning_rate": 3.1014165699771285e-05, + "loss": 3.5355, + "step": 1159680 + }, + { + "epoch": 0.01, + "learning_rate": 3.1005779752260765e-05, + "loss": 3.5377, + "step": 1160192 + }, + { + "epoch": 0.01, + "learning_rate": 3.0997393804750245e-05, + "loss": 3.5363, + "step": 1160704 + }, + { + "epoch": 0.01, + "learning_rate": 3.0989024236043454e-05, + "loss": 3.5454, + "step": 1161216 + }, + { + "epoch": 0.01, + "learning_rate": 3.0980638288532934e-05, + "loss": 3.5327, + "step": 1161728 + }, + { + "epoch": 0.01, + "learning_rate": 3.097225234102242e-05, + "loss": 3.5374, + "step": 1162240 + }, + { + "epoch": 0.01, + "learning_rate": 3.09638663935119e-05, + "loss": 3.5457, + "step": 1162752 + }, + { + "epoch": 0.01, + "learning_rate": 3.095549682480511e-05, + "loss": 3.5466, + "step": 1163264 + }, + { + "epoch": 0.01, + "learning_rate": 3.094711087729459e-05, + "loss": 3.5202, + "step": 1163776 + }, + { + "epoch": 0.01, + "learning_rate": 3.093872492978407e-05, + "loss": 3.5338, + "step": 1164288 + }, + { + "epoch": 0.01, + "learning_rate": 3.093033898227355e-05, + "loss": 3.5258, + "step": 1164800 + }, + { + "epoch": 0.01, + "learning_rate": 3.092196941356676e-05, + "loss": 3.5316, + "step": 1165312 + }, + { + "epoch": 0.01, + "learning_rate": 3.091358346605624e-05, + "loss": 3.5335, + "step": 1165824 + }, + { + "epoch": 0.01, + "learning_rate": 3.090519751854572e-05, + "loss": 3.5451, + "step": 1166336 + }, + { + "epoch": 0.01, + "learning_rate": 3.08968115710352e-05, + "loss": 3.532, + "step": 1166848 + }, + { + "epoch": 0.01, + "learning_rate": 3.088844200232841e-05, + "loss": 3.5349, + "step": 1167360 + }, + { + "epoch": 0.01, + "learning_rate": 3.088005605481789e-05, + "loss": 3.5452, + "step": 1167872 + }, + { + "epoch": 0.01, + "learning_rate": 3.0871670107307374e-05, + "loss": 3.5415, + "step": 1168384 + }, + { + "epoch": 0.01, + "learning_rate": 3.0863284159796854e-05, + "loss": 3.5338, + "step": 1168896 + }, + { + "epoch": 0.01, + "learning_rate": 3.0854898212286334e-05, + "loss": 3.5186, + "step": 1169408 + }, + { + "epoch": 0.01, + "learning_rate": 3.084652864357954e-05, + "loss": 3.5409, + "step": 1169920 + }, + { + "epoch": 0.01, + "learning_rate": 3.083814269606902e-05, + "loss": 3.543, + "step": 1170432 + }, + { + "epoch": 0.01, + "learning_rate": 3.08297567485585e-05, + "loss": 3.5364, + "step": 1170944 + }, + { + "epoch": 0.01, + "learning_rate": 3.082137080104798e-05, + "loss": 3.5306, + "step": 1171456 + }, + { + "epoch": 0.01, + "learning_rate": 3.081300123234119e-05, + "loss": 3.5335, + "step": 1171968 + }, + { + "epoch": 0.01, + "learning_rate": 3.080461528483067e-05, + "loss": 3.5292, + "step": 1172480 + }, + { + "epoch": 0.01, + "learning_rate": 3.079622933732015e-05, + "loss": 3.5234, + "step": 1172992 + }, + { + "epoch": 0.01, + "learning_rate": 3.078784338980963e-05, + "loss": 3.5476, + "step": 1173504 + }, + { + "epoch": 0.01, + "learning_rate": 3.077947382110284e-05, + "loss": 3.5305, + "step": 1174016 + }, + { + "epoch": 0.01, + "learning_rate": 3.077108787359233e-05, + "loss": 3.5429, + "step": 1174528 + }, + { + "epoch": 0.01, + "learning_rate": 3.076270192608181e-05, + "loss": 3.5427, + "step": 1175040 + }, + { + "epoch": 0.01, + "learning_rate": 3.075431597857129e-05, + "loss": 3.517, + "step": 1175552 + }, + { + "epoch": 0.01, + "learning_rate": 3.07459464098645e-05, + "loss": 3.5365, + "step": 1176064 + }, + { + "epoch": 0.01, + "learning_rate": 3.073756046235398e-05, + "loss": 3.5305, + "step": 1176576 + }, + { + "epoch": 0.01, + "learning_rate": 3.072917451484346e-05, + "loss": 3.5264, + "step": 1177088 + }, + { + "epoch": 0.01, + "learning_rate": 3.072078856733294e-05, + "loss": 3.5191, + "step": 1177600 + }, + { + "epoch": 0.01, + "learning_rate": 3.0712418998626146e-05, + "loss": 3.5369, + "step": 1178112 + }, + { + "epoch": 0.01, + "learning_rate": 3.0704033051115626e-05, + "loss": 3.5288, + "step": 1178624 + }, + { + "epoch": 0.01, + "learning_rate": 3.0695647103605106e-05, + "loss": 3.5208, + "step": 1179136 + }, + { + "epoch": 0.01, + "learning_rate": 3.0687261156094586e-05, + "loss": 3.5226, + "step": 1179648 + }, + { + "epoch": 0.01, + "learning_rate": 3.0678891587387795e-05, + "loss": 3.5351, + "step": 1180160 + }, + { + "epoch": 0.01, + "learning_rate": 3.067050563987728e-05, + "loss": 3.5397, + "step": 1180672 + }, + { + "epoch": 0.01, + "learning_rate": 3.066211969236676e-05, + "loss": 3.5345, + "step": 1181184 + }, + { + "epoch": 0.01, + "learning_rate": 3.065373374485624e-05, + "loss": 3.5375, + "step": 1181696 + }, + { + "epoch": 0.01, + "learning_rate": 3.064536417614945e-05, + "loss": 3.5387, + "step": 1182208 + }, + { + "epoch": 0.01, + "learning_rate": 3.063697822863893e-05, + "loss": 3.5435, + "step": 1182720 + }, + { + "epoch": 0.01, + "learning_rate": 3.062859228112841e-05, + "loss": 3.5384, + "step": 1183232 + }, + { + "epoch": 0.01, + "learning_rate": 3.062020633361789e-05, + "loss": 3.5378, + "step": 1183744 + }, + { + "epoch": 0.01, + "learning_rate": 3.06118367649111e-05, + "loss": 3.537, + "step": 1184256 + }, + { + "epoch": 0.01, + "learning_rate": 3.060345081740058e-05, + "loss": 3.5328, + "step": 1184768 + }, + { + "epoch": 0.01, + "learning_rate": 3.059506486989006e-05, + "loss": 3.5373, + "step": 1185280 + }, + { + "epoch": 0.01, + "learning_rate": 3.058667892237954e-05, + "loss": 3.5288, + "step": 1185792 + }, + { + "epoch": 0.01, + "learning_rate": 3.057829297486902e-05, + "loss": 3.5412, + "step": 1186304 + }, + { + "epoch": 0.01, + "learning_rate": 3.056992340616223e-05, + "loss": 3.5448, + "step": 1186816 + }, + { + "epoch": 0.01, + "learning_rate": 3.0561537458651715e-05, + "loss": 3.5394, + "step": 1187328 + }, + { + "epoch": 0.01, + "learning_rate": 3.0553151511141195e-05, + "loss": 3.513, + "step": 1187840 + }, + { + "epoch": 0.01, + "learning_rate": 3.0544765563630675e-05, + "loss": 3.5247, + "step": 1188352 + }, + { + "epoch": 0.01, + "learning_rate": 3.0536395994923884e-05, + "loss": 3.5358, + "step": 1188864 + }, + { + "epoch": 0.01, + "learning_rate": 3.0528010047413364e-05, + "loss": 3.5349, + "step": 1189376 + }, + { + "epoch": 0.01, + "learning_rate": 3.0519624099902844e-05, + "loss": 3.5314, + "step": 1189888 + }, + { + "epoch": 0.01, + "learning_rate": 3.0511254531196053e-05, + "loss": 3.5389, + "step": 1190400 + }, + { + "epoch": 0.02, + "learning_rate": 3.0502868583685533e-05, + "loss": 3.5285, + "step": 1190912 + }, + { + "epoch": 0.02, + "learning_rate": 3.0494482636175013e-05, + "loss": 3.5253, + "step": 1191424 + }, + { + "epoch": 0.02, + "learning_rate": 3.0486096688664497e-05, + "loss": 3.5313, + "step": 1191936 + }, + { + "epoch": 0.02, + "learning_rate": 3.0477710741153977e-05, + "loss": 3.5376, + "step": 1192448 + }, + { + "epoch": 0.02, + "learning_rate": 3.0469341172447186e-05, + "loss": 3.5329, + "step": 1192960 + }, + { + "epoch": 0.02, + "learning_rate": 3.0460955224936666e-05, + "loss": 3.5455, + "step": 1193472 + }, + { + "epoch": 0.02, + "learning_rate": 3.0452569277426146e-05, + "loss": 3.5237, + "step": 1193984 + }, + { + "epoch": 0.02, + "learning_rate": 3.0444199708719358e-05, + "loss": 3.5305, + "step": 1194496 + }, + { + "epoch": 0.02, + "learning_rate": 3.0435813761208838e-05, + "loss": 3.5387, + "step": 1195008 + }, + { + "epoch": 0.02, + "learning_rate": 3.0427427813698318e-05, + "loss": 3.5308, + "step": 1195520 + }, + { + "epoch": 0.02, + "learning_rate": 3.0419041866187798e-05, + "loss": 3.5397, + "step": 1196032 + }, + { + "epoch": 0.02, + "learning_rate": 3.0410655918677278e-05, + "loss": 3.5302, + "step": 1196544 + }, + { + "epoch": 0.02, + "learning_rate": 3.0402286349970487e-05, + "loss": 3.5233, + "step": 1197056 + }, + { + "epoch": 0.02, + "learning_rate": 3.0393900402459967e-05, + "loss": 3.524, + "step": 1197568 + }, + { + "epoch": 0.02, + "learning_rate": 3.038551445494945e-05, + "loss": 3.5391, + "step": 1198080 + }, + { + "epoch": 0.02, + "learning_rate": 3.037712850743893e-05, + "loss": 3.5206, + "step": 1198592 + }, + { + "epoch": 0.02, + "learning_rate": 3.036875893873214e-05, + "loss": 3.5132, + "step": 1199104 + }, + { + "epoch": 0.02, + "learning_rate": 3.036037299122162e-05, + "loss": 3.5339, + "step": 1199616 + }, + { + "epoch": 0.02, + "learning_rate": 3.03519870437111e-05, + "loss": 3.5299, + "step": 1200128 + }, + { + "epoch": 0.02, + "learning_rate": 3.034360109620058e-05, + "loss": 3.5267, + "step": 1200640 + }, + { + "epoch": 0.02, + "learning_rate": 3.033523152749379e-05, + "loss": 3.5303, + "step": 1201152 + }, + { + "epoch": 0.02, + "learning_rate": 3.032684557998327e-05, + "loss": 3.522, + "step": 1201664 + }, + { + "epoch": 0.02, + "learning_rate": 3.031845963247275e-05, + "loss": 3.5386, + "step": 1202176 + }, + { + "epoch": 0.02, + "learning_rate": 3.031007368496223e-05, + "loss": 3.5206, + "step": 1202688 + }, + { + "epoch": 0.02, + "learning_rate": 3.0301687737451705e-05, + "loss": 3.5328, + "step": 1203200 + }, + { + "epoch": 0.02, + "learning_rate": 3.029331816874492e-05, + "loss": 3.5396, + "step": 1203712 + }, + { + "epoch": 0.02, + "learning_rate": 3.0284932221234404e-05, + "loss": 3.5406, + "step": 1204224 + }, + { + "epoch": 0.02, + "learning_rate": 3.0276546273723877e-05, + "loss": 3.5299, + "step": 1204736 + }, + { + "epoch": 0.02, + "learning_rate": 3.0268160326213357e-05, + "loss": 3.5271, + "step": 1205248 + }, + { + "epoch": 0.02, + "learning_rate": 3.0259790757506573e-05, + "loss": 3.5349, + "step": 1205760 + }, + { + "epoch": 0.02, + "learning_rate": 3.0251404809996053e-05, + "loss": 3.5305, + "step": 1206272 + }, + { + "epoch": 0.02, + "learning_rate": 3.024301886248553e-05, + "loss": 3.5234, + "step": 1206784 + }, + { + "epoch": 0.02, + "learning_rate": 3.023463291497501e-05, + "loss": 3.5362, + "step": 1207296 + }, + { + "epoch": 0.02, + "learning_rate": 3.0226263346268225e-05, + "loss": 3.528, + "step": 1207808 + }, + { + "epoch": 0.02, + "learning_rate": 3.0217877398757705e-05, + "loss": 3.5281, + "step": 1208320 + }, + { + "epoch": 0.02, + "learning_rate": 3.020949145124718e-05, + "loss": 3.5258, + "step": 1208832 + }, + { + "epoch": 0.02, + "learning_rate": 3.020110550373666e-05, + "loss": 3.5236, + "step": 1209344 + }, + { + "epoch": 0.02, + "learning_rate": 3.0192719556226142e-05, + "loss": 3.5281, + "step": 1209856 + }, + { + "epoch": 0.02, + "learning_rate": 3.018434998751935e-05, + "loss": 3.524, + "step": 1210368 + }, + { + "epoch": 0.02, + "learning_rate": 3.017596404000883e-05, + "loss": 3.5331, + "step": 1210880 + }, + { + "epoch": 0.02, + "learning_rate": 3.016757809249831e-05, + "loss": 3.5377, + "step": 1211392 + }, + { + "epoch": 0.02, + "learning_rate": 3.015919214498779e-05, + "loss": 3.5387, + "step": 1211904 + }, + { + "epoch": 0.02, + "learning_rate": 3.0150822576281003e-05, + "loss": 3.5167, + "step": 1212416 + }, + { + "epoch": 0.02, + "learning_rate": 3.0142436628770483e-05, + "loss": 3.5323, + "step": 1212928 + }, + { + "epoch": 0.02, + "learning_rate": 3.0134050681259963e-05, + "loss": 3.5372, + "step": 1213440 + }, + { + "epoch": 0.02, + "learning_rate": 3.0125664733749443e-05, + "loss": 3.5351, + "step": 1213952 + }, + { + "epoch": 0.02, + "learning_rate": 3.0117295165042652e-05, + "loss": 3.5276, + "step": 1214464 + }, + { + "epoch": 0.02, + "learning_rate": 3.0108909217532132e-05, + "loss": 3.5241, + "step": 1214976 + }, + { + "epoch": 0.02, + "learning_rate": 3.0100523270021612e-05, + "loss": 3.5363, + "step": 1215488 + }, + { + "epoch": 0.02, + "learning_rate": 3.0092137322511092e-05, + "loss": 3.5437, + "step": 1216000 + }, + { + "epoch": 0.02, + "learning_rate": 3.0083767753804304e-05, + "loss": 3.5276, + "step": 1216512 + }, + { + "epoch": 0.02, + "learning_rate": 3.0075381806293784e-05, + "loss": 3.5229, + "step": 1217024 + }, + { + "epoch": 0.02, + "learning_rate": 3.0066995858783264e-05, + "loss": 3.533, + "step": 1217536 + }, + { + "epoch": 0.02, + "learning_rate": 3.0058609911272744e-05, + "loss": 3.5236, + "step": 1218048 + }, + { + "epoch": 0.02, + "learning_rate": 3.0050240342565953e-05, + "loss": 3.5265, + "step": 1218560 + }, + { + "epoch": 0.02, + "learning_rate": 3.0041854395055437e-05, + "loss": 3.5383, + "step": 1219072 + }, + { + "epoch": 0.02, + "learning_rate": 3.0033468447544917e-05, + "loss": 3.5208, + "step": 1219584 + }, + { + "epoch": 0.02, + "learning_rate": 3.0025082500034397e-05, + "loss": 3.5402, + "step": 1220096 + }, + { + "epoch": 0.02, + "learning_rate": 3.0016712931327606e-05, + "loss": 3.5218, + "step": 1220608 + }, + { + "epoch": 0.03, + "learning_rate": 3.0008326983817086e-05, + "loss": 3.5269, + "step": 1221120 + }, + { + "epoch": 0.03, + "eval_loss": 3.844106912612915, + "eval_runtime": 312.1993, + "eval_samples_per_second": 1222.268, + "eval_steps_per_second": 38.197, + "step": 1221120 + }, + { + "epoch": 1.0, + "learning_rate": 2.9999941036306566e-05, + "loss": 3.5229, + "step": 1221632 + }, + { + "epoch": 1.0, + "learning_rate": 2.9991555088796046e-05, + "loss": 3.5274, + "step": 1222144 + }, + { + "epoch": 1.0, + "learning_rate": 2.998316914128553e-05, + "loss": 3.5387, + "step": 1222656 + }, + { + "epoch": 1.0, + "learning_rate": 2.9974799572578738e-05, + "loss": 3.5314, + "step": 1223168 + }, + { + "epoch": 1.0, + "learning_rate": 2.9966413625068218e-05, + "loss": 3.5329, + "step": 1223680 + }, + { + "epoch": 1.0, + "learning_rate": 2.9958027677557698e-05, + "loss": 3.529, + "step": 1224192 + }, + { + "epoch": 1.0, + "learning_rate": 2.9949641730047178e-05, + "loss": 3.5286, + "step": 1224704 + }, + { + "epoch": 1.0, + "learning_rate": 2.994127216134039e-05, + "loss": 3.516, + "step": 1225216 + }, + { + "epoch": 1.0, + "learning_rate": 2.993288621382987e-05, + "loss": 3.5443, + "step": 1225728 + }, + { + "epoch": 1.0, + "learning_rate": 2.992450026631935e-05, + "loss": 3.5284, + "step": 1226240 + }, + { + "epoch": 1.0, + "learning_rate": 2.991611431880883e-05, + "loss": 3.5407, + "step": 1226752 + }, + { + "epoch": 1.0, + "learning_rate": 2.990776112890577e-05, + "loss": 3.5415, + "step": 1227264 + }, + { + "epoch": 1.0, + "learning_rate": 2.9899375181395252e-05, + "loss": 3.5143, + "step": 1227776 + }, + { + "epoch": 1.0, + "learning_rate": 2.9890989233884732e-05, + "loss": 3.5251, + "step": 1228288 + }, + { + "epoch": 1.0, + "learning_rate": 2.9882603286374212e-05, + "loss": 3.5221, + "step": 1228800 + }, + { + "epoch": 1.0, + "learning_rate": 2.9874217338863692e-05, + "loss": 3.5234, + "step": 1229312 + }, + { + "epoch": 1.0, + "learning_rate": 2.9865831391353172e-05, + "loss": 3.5237, + "step": 1229824 + }, + { + "epoch": 1.0, + "learning_rate": 2.985744544384265e-05, + "loss": 3.5196, + "step": 1230336 + }, + { + "epoch": 1.0, + "learning_rate": 2.984905949633213e-05, + "loss": 3.5198, + "step": 1230848 + }, + { + "epoch": 1.0, + "learning_rate": 2.984067354882161e-05, + "loss": 3.5388, + "step": 1231360 + }, + { + "epoch": 1.0, + "learning_rate": 2.9832303980114824e-05, + "loss": 3.5332, + "step": 1231872 + }, + { + "epoch": 1.0, + "learning_rate": 2.9823918032604304e-05, + "loss": 3.5226, + "step": 1232384 + }, + { + "epoch": 1.0, + "learning_rate": 2.9815532085093784e-05, + "loss": 3.5239, + "step": 1232896 + }, + { + "epoch": 1.0, + "learning_rate": 2.9807146137583264e-05, + "loss": 3.5368, + "step": 1233408 + }, + { + "epoch": 1.0, + "learning_rate": 2.9798776568876473e-05, + "loss": 3.5157, + "step": 1233920 + }, + { + "epoch": 1.0, + "learning_rate": 2.9790390621365953e-05, + "loss": 3.5145, + "step": 1234432 + }, + { + "epoch": 1.0, + "learning_rate": 2.9782004673855436e-05, + "loss": 3.5282, + "step": 1234944 + }, + { + "epoch": 1.0, + "learning_rate": 2.9773618726344916e-05, + "loss": 3.5187, + "step": 1235456 + }, + { + "epoch": 1.0, + "learning_rate": 2.9765249157638125e-05, + "loss": 3.5195, + "step": 1235968 + }, + { + "epoch": 1.01, + "learning_rate": 2.9756863210127605e-05, + "loss": 3.5198, + "step": 1236480 + }, + { + "epoch": 1.01, + "learning_rate": 2.9748477262617085e-05, + "loss": 3.5236, + "step": 1236992 + }, + { + "epoch": 1.01, + "learning_rate": 2.9740091315106565e-05, + "loss": 3.5289, + "step": 1237504 + }, + { + "epoch": 1.01, + "learning_rate": 2.9731721746399778e-05, + "loss": 3.5185, + "step": 1238016 + }, + { + "epoch": 1.01, + "learning_rate": 2.9723335798889258e-05, + "loss": 3.5236, + "step": 1238528 + }, + { + "epoch": 1.01, + "learning_rate": 2.9714949851378738e-05, + "loss": 3.5334, + "step": 1239040 + }, + { + "epoch": 1.01, + "learning_rate": 2.9706563903868218e-05, + "loss": 3.5295, + "step": 1239552 + }, + { + "epoch": 1.01, + "learning_rate": 2.9698194335161427e-05, + "loss": 3.5092, + "step": 1240064 + }, + { + "epoch": 1.01, + "learning_rate": 2.9689808387650907e-05, + "loss": 3.5215, + "step": 1240576 + }, + { + "epoch": 1.01, + "learning_rate": 2.968142244014039e-05, + "loss": 3.5093, + "step": 1241088 + }, + { + "epoch": 1.01, + "learning_rate": 2.967303649262987e-05, + "loss": 3.5236, + "step": 1241600 + }, + { + "epoch": 1.01, + "learning_rate": 2.966466692392308e-05, + "loss": 3.5184, + "step": 1242112 + }, + { + "epoch": 1.01, + "learning_rate": 2.965628097641256e-05, + "loss": 3.5282, + "step": 1242624 + }, + { + "epoch": 1.01, + "learning_rate": 2.964789502890204e-05, + "loss": 3.5169, + "step": 1243136 + }, + { + "epoch": 1.01, + "learning_rate": 2.963950908139152e-05, + "loss": 3.5239, + "step": 1243648 + }, + { + "epoch": 1.01, + "learning_rate": 2.963113951268473e-05, + "loss": 3.5249, + "step": 1244160 + }, + { + "epoch": 1.01, + "learning_rate": 2.962275356517421e-05, + "loss": 3.5293, + "step": 1244672 + }, + { + "epoch": 1.01, + "learning_rate": 2.961436761766369e-05, + "loss": 3.5187, + "step": 1245184 + }, + { + "epoch": 1.01, + "learning_rate": 2.960598167015317e-05, + "loss": 3.5063, + "step": 1245696 + }, + { + "epoch": 1.01, + "learning_rate": 2.959761210144638e-05, + "loss": 3.527, + "step": 1246208 + }, + { + "epoch": 1.01, + "learning_rate": 2.958922615393586e-05, + "loss": 3.5322, + "step": 1246720 + }, + { + "epoch": 1.01, + "learning_rate": 2.9580840206425344e-05, + "loss": 3.5201, + "step": 1247232 + }, + { + "epoch": 1.01, + "learning_rate": 2.9572454258914824e-05, + "loss": 3.5169, + "step": 1247744 + }, + { + "epoch": 1.01, + "learning_rate": 2.9564084690208033e-05, + "loss": 3.5155, + "step": 1248256 + }, + { + "epoch": 1.01, + "learning_rate": 2.9555698742697513e-05, + "loss": 3.5174, + "step": 1248768 + }, + { + "epoch": 1.01, + "learning_rate": 2.9547312795186993e-05, + "loss": 3.5075, + "step": 1249280 + }, + { + "epoch": 1.01, + "learning_rate": 2.9538926847676473e-05, + "loss": 3.5352, + "step": 1249792 + }, + { + "epoch": 1.01, + "learning_rate": 2.9530557278969685e-05, + "loss": 3.5171, + "step": 1250304 + }, + { + "epoch": 1.01, + "learning_rate": 2.9522171331459165e-05, + "loss": 3.5309, + "step": 1250816 + }, + { + "epoch": 1.01, + "learning_rate": 2.9513785383948645e-05, + "loss": 3.5258, + "step": 1251328 + }, + { + "epoch": 1.01, + "learning_rate": 2.9505399436438125e-05, + "loss": 3.5068, + "step": 1251840 + }, + { + "epoch": 1.01, + "learning_rate": 2.9497029867731334e-05, + "loss": 3.5219, + "step": 1252352 + }, + { + "epoch": 1.01, + "learning_rate": 2.9488643920220814e-05, + "loss": 3.5186, + "step": 1252864 + }, + { + "epoch": 1.01, + "learning_rate": 2.9480257972710297e-05, + "loss": 3.5092, + "step": 1253376 + }, + { + "epoch": 1.01, + "learning_rate": 2.9471872025199777e-05, + "loss": 3.5069, + "step": 1253888 + }, + { + "epoch": 1.01, + "learning_rate": 2.9463502456492986e-05, + "loss": 3.5237, + "step": 1254400 + }, + { + "epoch": 1.01, + "learning_rate": 2.9455116508982466e-05, + "loss": 3.5098, + "step": 1254912 + }, + { + "epoch": 1.01, + "learning_rate": 2.9446730561471946e-05, + "loss": 3.5105, + "step": 1255424 + }, + { + "epoch": 1.01, + "learning_rate": 2.9438344613961426e-05, + "loss": 3.5049, + "step": 1255936 + }, + { + "epoch": 1.01, + "learning_rate": 2.9429958666450903e-05, + "loss": 3.5227, + "step": 1256448 + }, + { + "epoch": 1.01, + "learning_rate": 2.942158909774412e-05, + "loss": 3.5257, + "step": 1256960 + }, + { + "epoch": 1.01, + "learning_rate": 2.94132031502336e-05, + "loss": 3.5206, + "step": 1257472 + }, + { + "epoch": 1.01, + "learning_rate": 2.940481720272308e-05, + "loss": 3.5224, + "step": 1257984 + }, + { + "epoch": 1.01, + "learning_rate": 2.9396431255212552e-05, + "loss": 3.5279, + "step": 1258496 + }, + { + "epoch": 1.01, + "learning_rate": 2.9388061686505768e-05, + "loss": 3.5269, + "step": 1259008 + }, + { + "epoch": 1.01, + "learning_rate": 2.9379675738995248e-05, + "loss": 3.5265, + "step": 1259520 + }, + { + "epoch": 1.01, + "learning_rate": 2.937128979148473e-05, + "loss": 3.5159, + "step": 1260032 + }, + { + "epoch": 1.01, + "learning_rate": 2.9362903843974204e-05, + "loss": 3.5268, + "step": 1260544 + }, + { + "epoch": 1.01, + "learning_rate": 2.935453427526742e-05, + "loss": 3.5203, + "step": 1261056 + }, + { + "epoch": 1.01, + "learning_rate": 2.93461483277569e-05, + "loss": 3.5207, + "step": 1261568 + }, + { + "epoch": 1.01, + "learning_rate": 2.9337762380246377e-05, + "loss": 3.5163, + "step": 1262080 + }, + { + "epoch": 1.01, + "learning_rate": 2.9329376432735856e-05, + "loss": 3.5234, + "step": 1262592 + }, + { + "epoch": 1.01, + "learning_rate": 2.9321006864029072e-05, + "loss": 3.5319, + "step": 1263104 + }, + { + "epoch": 1.01, + "learning_rate": 2.9312620916518552e-05, + "loss": 3.5233, + "step": 1263616 + }, + { + "epoch": 1.01, + "learning_rate": 2.9304234969008025e-05, + "loss": 3.499, + "step": 1264128 + }, + { + "epoch": 1.01, + "learning_rate": 2.9295849021497505e-05, + "loss": 3.5109, + "step": 1264640 + }, + { + "epoch": 1.01, + "learning_rate": 2.9287463073986985e-05, + "loss": 3.5239, + "step": 1265152 + }, + { + "epoch": 1.01, + "learning_rate": 2.92790935052802e-05, + "loss": 3.5195, + "step": 1265664 + }, + { + "epoch": 1.01, + "learning_rate": 2.9270707557769678e-05, + "loss": 3.5191, + "step": 1266176 + }, + { + "epoch": 1.01, + "learning_rate": 2.9262321610259158e-05, + "loss": 3.5203, + "step": 1266688 + }, + { + "epoch": 1.02, + "learning_rate": 2.9253935662748638e-05, + "loss": 3.519, + "step": 1267200 + }, + { + "epoch": 1.02, + "learning_rate": 2.924556609404185e-05, + "loss": 3.51, + "step": 1267712 + }, + { + "epoch": 1.02, + "learning_rate": 2.923718014653133e-05, + "loss": 3.5166, + "step": 1268224 + }, + { + "epoch": 1.02, + "learning_rate": 2.922879419902081e-05, + "loss": 3.5241, + "step": 1268736 + }, + { + "epoch": 1.02, + "learning_rate": 2.922040825151029e-05, + "loss": 3.519, + "step": 1269248 + }, + { + "epoch": 1.02, + "learning_rate": 2.92120386828035e-05, + "loss": 3.5318, + "step": 1269760 + }, + { + "epoch": 1.02, + "learning_rate": 2.920365273529298e-05, + "loss": 3.5135, + "step": 1270272 + }, + { + "epoch": 1.02, + "learning_rate": 2.919526678778246e-05, + "loss": 3.5151, + "step": 1270784 + }, + { + "epoch": 1.02, + "learning_rate": 2.918688084027194e-05, + "loss": 3.5216, + "step": 1271296 + }, + { + "epoch": 1.02, + "learning_rate": 2.917851127156515e-05, + "loss": 3.518, + "step": 1271808 + }, + { + "epoch": 1.02, + "learning_rate": 2.917012532405463e-05, + "loss": 3.5267, + "step": 1272320 + }, + { + "epoch": 1.02, + "learning_rate": 2.916173937654411e-05, + "loss": 3.5159, + "step": 1272832 + }, + { + "epoch": 1.02, + "learning_rate": 2.915335342903359e-05, + "loss": 3.5099, + "step": 1273344 + }, + { + "epoch": 1.02, + "learning_rate": 2.91449838603268e-05, + "loss": 3.5116, + "step": 1273856 + }, + { + "epoch": 1.02, + "learning_rate": 2.9136597912816284e-05, + "loss": 3.5239, + "step": 1274368 + }, + { + "epoch": 1.02, + "learning_rate": 2.9128211965305764e-05, + "loss": 3.507, + "step": 1274880 + }, + { + "epoch": 1.02, + "learning_rate": 2.9119826017795244e-05, + "loss": 3.5016, + "step": 1275392 + }, + { + "epoch": 1.02, + "learning_rate": 2.9111456449088453e-05, + "loss": 3.5147, + "step": 1275904 + }, + { + "epoch": 1.02, + "learning_rate": 2.9103070501577933e-05, + "loss": 3.5196, + "step": 1276416 + }, + { + "epoch": 1.02, + "learning_rate": 2.9094684554067413e-05, + "loss": 3.5089, + "step": 1276928 + }, + { + "epoch": 1.02, + "learning_rate": 2.9086298606556893e-05, + "loss": 3.5182, + "step": 1277440 + }, + { + "epoch": 1.02, + "learning_rate": 2.9077929037850105e-05, + "loss": 3.5077, + "step": 1277952 + }, + { + "epoch": 1.02, + "learning_rate": 2.9069543090339585e-05, + "loss": 3.5249, + "step": 1278464 + }, + { + "epoch": 1.02, + "learning_rate": 2.9061157142829065e-05, + "loss": 3.5064, + "step": 1278976 + }, + { + "epoch": 1.02, + "learning_rate": 2.9052771195318545e-05, + "loss": 3.5187, + "step": 1279488 + }, + { + "epoch": 1.02, + "learning_rate": 2.9044401626611754e-05, + "loss": 3.5265, + "step": 1280000 + }, + { + "epoch": 1.02, + "learning_rate": 2.9036015679101238e-05, + "loss": 3.5279, + "step": 1280512 + }, + { + "epoch": 1.02, + "learning_rate": 2.9027629731590717e-05, + "loss": 3.5136, + "step": 1281024 + }, + { + "epoch": 1.02, + "learning_rate": 2.9019243784080197e-05, + "loss": 3.5169, + "step": 1281536 + }, + { + "epoch": 1.02, + "learning_rate": 2.9010874215373407e-05, + "loss": 3.5182, + "step": 1282048 + }, + { + "epoch": 1.02, + "learning_rate": 2.9002488267862886e-05, + "loss": 3.5178, + "step": 1282560 + }, + { + "epoch": 1.02, + "learning_rate": 2.8994102320352366e-05, + "loss": 3.5094, + "step": 1283072 + }, + { + "epoch": 1.02, + "learning_rate": 2.8985716372841846e-05, + "loss": 3.5175, + "step": 1283584 + }, + { + "epoch": 1.02, + "learning_rate": 2.897734680413506e-05, + "loss": 3.5174, + "step": 1284096 + }, + { + "epoch": 1.02, + "learning_rate": 2.896896085662454e-05, + "loss": 3.5204, + "step": 1284608 + }, + { + "epoch": 1.02, + "learning_rate": 2.896057490911402e-05, + "loss": 3.5086, + "step": 1285120 + }, + { + "epoch": 1.02, + "learning_rate": 2.89521889616035e-05, + "loss": 3.507, + "step": 1285632 + }, + { + "epoch": 1.02, + "learning_rate": 2.8943819392896708e-05, + "loss": 3.514, + "step": 1286144 + }, + { + "epoch": 1.02, + "learning_rate": 2.893543344538619e-05, + "loss": 3.5158, + "step": 1286656 + }, + { + "epoch": 1.02, + "learning_rate": 2.892704749787567e-05, + "loss": 3.5132, + "step": 1287168 + }, + { + "epoch": 1.02, + "learning_rate": 2.891866155036515e-05, + "loss": 3.526, + "step": 1287680 + }, + { + "epoch": 1.02, + "learning_rate": 2.891029198165836e-05, + "loss": 3.524, + "step": 1288192 + }, + { + "epoch": 1.02, + "learning_rate": 2.890190603414784e-05, + "loss": 3.5063, + "step": 1288704 + }, + { + "epoch": 1.02, + "learning_rate": 2.889352008663732e-05, + "loss": 3.5128, + "step": 1289216 + }, + { + "epoch": 1.02, + "learning_rate": 2.88851341391268e-05, + "loss": 3.5254, + "step": 1289728 + }, + { + "epoch": 1.02, + "learning_rate": 2.8876764570420013e-05, + "loss": 3.5188, + "step": 1290240 + }, + { + "epoch": 1.02, + "learning_rate": 2.8868378622909493e-05, + "loss": 3.5158, + "step": 1290752 + }, + { + "epoch": 1.02, + "learning_rate": 2.8859992675398972e-05, + "loss": 3.5118, + "step": 1291264 + }, + { + "epoch": 1.02, + "learning_rate": 2.8851606727888452e-05, + "loss": 3.5256, + "step": 1291776 + }, + { + "epoch": 1.02, + "learning_rate": 2.884323715918166e-05, + "loss": 3.5235, + "step": 1292288 + }, + { + "epoch": 1.02, + "learning_rate": 2.8834851211671145e-05, + "loss": 3.5164, + "step": 1292800 + }, + { + "epoch": 1.02, + "learning_rate": 2.8826465264160625e-05, + "loss": 3.5108, + "step": 1293312 + }, + { + "epoch": 1.02, + "learning_rate": 2.8818079316650105e-05, + "loss": 3.5162, + "step": 1293824 + }, + { + "epoch": 1.02, + "learning_rate": 2.8809709747943314e-05, + "loss": 3.5122, + "step": 1294336 + }, + { + "epoch": 1.02, + "learning_rate": 2.8801323800432794e-05, + "loss": 3.5114, + "step": 1294848 + }, + { + "epoch": 1.02, + "learning_rate": 2.8792937852922274e-05, + "loss": 3.5242, + "step": 1295360 + }, + { + "epoch": 1.02, + "learning_rate": 2.8784551905411754e-05, + "loss": 3.5142, + "step": 1295872 + }, + { + "epoch": 1.02, + "learning_rate": 2.8776182336704966e-05, + "loss": 3.5212, + "step": 1296384 + }, + { + "epoch": 1.02, + "learning_rate": 2.8767796389194446e-05, + "loss": 3.5104, + "step": 1296896 + }, + { + "epoch": 1.02, + "learning_rate": 2.8759410441683926e-05, + "loss": 3.5066, + "step": 1297408 + }, + { + "epoch": 1.03, + "eval_loss": 3.8453078269958496, + "eval_runtime": 315.9187, + "eval_samples_per_second": 1207.877, + "eval_steps_per_second": 37.747, + "step": 1297440 + }, + { + "epoch": 0.0, + "learning_rate": 2.8751024494173406e-05, + "loss": 3.5068, + "step": 1297920 + }, + { + "epoch": 0.0, + "learning_rate": 2.8742638546662886e-05, + "loss": 3.5181, + "step": 1298432 + }, + { + "epoch": 0.0, + "learning_rate": 2.8734252599152366e-05, + "loss": 3.5231, + "step": 1298944 + }, + { + "epoch": 0.0, + "learning_rate": 2.8725866651641846e-05, + "loss": 3.5145, + "step": 1299456 + }, + { + "epoch": 0.0, + "learning_rate": 2.871749708293506e-05, + "loss": 3.5224, + "step": 1299968 + }, + { + "epoch": 0.0, + "learning_rate": 2.870911113542454e-05, + "loss": 3.5143, + "step": 1300480 + }, + { + "epoch": 0.0, + "learning_rate": 2.870072518791402e-05, + "loss": 3.5108, + "step": 1300992 + }, + { + "epoch": 0.0, + "learning_rate": 2.8692339240403498e-05, + "loss": 3.5049, + "step": 1301504 + }, + { + "epoch": 0.0, + "learning_rate": 2.8683969671696707e-05, + "loss": 3.529, + "step": 1302016 + }, + { + "epoch": 0.0, + "learning_rate": 2.867558372418619e-05, + "loss": 3.5147, + "step": 1302528 + }, + { + "epoch": 0.0, + "learning_rate": 2.866719777667567e-05, + "loss": 3.5279, + "step": 1303040 + }, + { + "epoch": 0.0, + "learning_rate": 2.865881182916515e-05, + "loss": 3.522, + "step": 1303552 + }, + { + "epoch": 0.0, + "learning_rate": 2.865044226045836e-05, + "loss": 3.5097, + "step": 1304064 + }, + { + "epoch": 0.0, + "learning_rate": 2.864205631294784e-05, + "loss": 3.5089, + "step": 1304576 + }, + { + "epoch": 0.0, + "learning_rate": 2.863367036543732e-05, + "loss": 3.5129, + "step": 1305088 + }, + { + "epoch": 0.0, + "learning_rate": 2.86252844179268e-05, + "loss": 3.5056, + "step": 1305600 + }, + { + "epoch": 0.0, + "learning_rate": 2.8616914849220012e-05, + "loss": 3.5109, + "step": 1306112 + }, + { + "epoch": 0.0, + "learning_rate": 2.8608528901709492e-05, + "loss": 3.5065, + "step": 1306624 + }, + { + "epoch": 0.0, + "learning_rate": 2.8600142954198972e-05, + "loss": 3.503, + "step": 1307136 + }, + { + "epoch": 0.0, + "learning_rate": 2.8591757006688452e-05, + "loss": 3.5305, + "step": 1307648 + }, + { + "epoch": 0.0, + "learning_rate": 2.858338743798166e-05, + "loss": 3.5164, + "step": 1308160 + }, + { + "epoch": 0.0, + "learning_rate": 2.8575001490471144e-05, + "loss": 3.5122, + "step": 1308672 + }, + { + "epoch": 0.0, + "learning_rate": 2.8566615542960624e-05, + "loss": 3.5084, + "step": 1309184 + }, + { + "epoch": 0.0, + "learning_rate": 2.8558229595450104e-05, + "loss": 3.5227, + "step": 1309696 + }, + { + "epoch": 0.0, + "learning_rate": 2.8549860026743313e-05, + "loss": 3.5004, + "step": 1310208 + }, + { + "epoch": 0.0, + "learning_rate": 2.8541474079232793e-05, + "loss": 3.5042, + "step": 1310720 + }, + { + "epoch": 0.0, + "learning_rate": 2.8533088131722273e-05, + "loss": 3.509, + "step": 1311232 + }, + { + "epoch": 0.0, + "learning_rate": 2.8524702184211753e-05, + "loss": 3.5095, + "step": 1311744 + }, + { + "epoch": 0.0, + "learning_rate": 2.8516332615504966e-05, + "loss": 3.5042, + "step": 1312256 + }, + { + "epoch": 0.01, + "learning_rate": 2.8507946667994446e-05, + "loss": 3.5073, + "step": 1312768 + }, + { + "epoch": 0.01, + "learning_rate": 2.8499560720483926e-05, + "loss": 3.5091, + "step": 1313280 + }, + { + "epoch": 0.01, + "learning_rate": 2.84911747729734e-05, + "loss": 3.5166, + "step": 1313792 + }, + { + "epoch": 0.01, + "learning_rate": 2.8482805204266615e-05, + "loss": 3.5044, + "step": 1314304 + }, + { + "epoch": 0.01, + "learning_rate": 2.8474419256756095e-05, + "loss": 3.5122, + "step": 1314816 + }, + { + "epoch": 0.01, + "learning_rate": 2.8466033309245578e-05, + "loss": 3.5168, + "step": 1315328 + }, + { + "epoch": 0.01, + "learning_rate": 2.845764736173505e-05, + "loss": 3.5161, + "step": 1315840 + }, + { + "epoch": 0.01, + "learning_rate": 2.8449277793028267e-05, + "loss": 3.497, + "step": 1316352 + }, + { + "epoch": 0.01, + "learning_rate": 2.8440891845517747e-05, + "loss": 3.5043, + "step": 1316864 + }, + { + "epoch": 0.01, + "learning_rate": 2.8432505898007224e-05, + "loss": 3.5009, + "step": 1317376 + }, + { + "epoch": 0.01, + "learning_rate": 2.8424119950496704e-05, + "loss": 3.5083, + "step": 1317888 + }, + { + "epoch": 0.01, + "learning_rate": 2.841575038178992e-05, + "loss": 3.5033, + "step": 1318400 + }, + { + "epoch": 0.01, + "learning_rate": 2.84073644342794e-05, + "loss": 3.5133, + "step": 1318912 + }, + { + "epoch": 0.01, + "learning_rate": 2.8398978486768873e-05, + "loss": 3.5018, + "step": 1319424 + }, + { + "epoch": 0.01, + "learning_rate": 2.8390592539258353e-05, + "loss": 3.5087, + "step": 1319936 + }, + { + "epoch": 0.01, + "learning_rate": 2.838222297055157e-05, + "loss": 3.5145, + "step": 1320448 + }, + { + "epoch": 0.01, + "learning_rate": 2.837383702304105e-05, + "loss": 3.5118, + "step": 1320960 + }, + { + "epoch": 0.01, + "learning_rate": 2.8365451075530525e-05, + "loss": 3.5093, + "step": 1321472 + }, + { + "epoch": 0.01, + "learning_rate": 2.8357065128020005e-05, + "loss": 3.4898, + "step": 1321984 + }, + { + "epoch": 0.01, + "learning_rate": 2.834869555931322e-05, + "loss": 3.512, + "step": 1322496 + }, + { + "epoch": 0.01, + "learning_rate": 2.8340309611802694e-05, + "loss": 3.5134, + "step": 1323008 + }, + { + "epoch": 0.01, + "learning_rate": 2.8331923664292177e-05, + "loss": 3.5101, + "step": 1323520 + }, + { + "epoch": 0.01, + "learning_rate": 2.8323537716781657e-05, + "loss": 3.5093, + "step": 1324032 + }, + { + "epoch": 0.01, + "learning_rate": 2.8315168148074873e-05, + "loss": 3.4966, + "step": 1324544 + }, + { + "epoch": 0.01, + "learning_rate": 2.8306782200564346e-05, + "loss": 3.5049, + "step": 1325056 + }, + { + "epoch": 0.01, + "learning_rate": 2.8298396253053826e-05, + "loss": 3.4904, + "step": 1325568 + }, + { + "epoch": 0.01, + "learning_rate": 2.8290010305543306e-05, + "loss": 3.5232, + "step": 1326080 + }, + { + "epoch": 0.01, + "learning_rate": 2.8281640736836522e-05, + "loss": 3.5047, + "step": 1326592 + }, + { + "epoch": 0.01, + "learning_rate": 2.8273254789326e-05, + "loss": 3.5172, + "step": 1327104 + }, + { + "epoch": 0.01, + "learning_rate": 2.826486884181548e-05, + "loss": 3.5136, + "step": 1327616 + }, + { + "epoch": 0.01, + "learning_rate": 2.825648289430496e-05, + "loss": 3.4914, + "step": 1328128 + }, + { + "epoch": 0.01, + "learning_rate": 2.8248113325598168e-05, + "loss": 3.5072, + "step": 1328640 + }, + { + "epoch": 0.01, + "learning_rate": 2.8239727378087648e-05, + "loss": 3.5062, + "step": 1329152 + }, + { + "epoch": 0.01, + "learning_rate": 2.823134143057713e-05, + "loss": 3.493, + "step": 1329664 + }, + { + "epoch": 0.01, + "learning_rate": 2.822295548306661e-05, + "loss": 3.49, + "step": 1330176 + }, + { + "epoch": 0.01, + "learning_rate": 2.821458591435982e-05, + "loss": 3.5105, + "step": 1330688 + }, + { + "epoch": 0.01, + "learning_rate": 2.82061999668493e-05, + "loss": 3.5011, + "step": 1331200 + }, + { + "epoch": 0.01, + "learning_rate": 2.819781401933878e-05, + "loss": 3.4959, + "step": 1331712 + }, + { + "epoch": 0.01, + "learning_rate": 2.818942807182826e-05, + "loss": 3.4899, + "step": 1332224 + }, + { + "epoch": 0.01, + "learning_rate": 2.8181058503121472e-05, + "loss": 3.5099, + "step": 1332736 + }, + { + "epoch": 0.01, + "learning_rate": 2.8172672555610952e-05, + "loss": 3.5103, + "step": 1333248 + }, + { + "epoch": 0.01, + "learning_rate": 2.8164286608100432e-05, + "loss": 3.5068, + "step": 1333760 + }, + { + "epoch": 0.01, + "learning_rate": 2.8155900660589912e-05, + "loss": 3.5075, + "step": 1334272 + }, + { + "epoch": 0.01, + "learning_rate": 2.814753109188312e-05, + "loss": 3.5207, + "step": 1334784 + }, + { + "epoch": 0.01, + "learning_rate": 2.81391451443726e-05, + "loss": 3.5122, + "step": 1335296 + }, + { + "epoch": 0.01, + "learning_rate": 2.8130759196862085e-05, + "loss": 3.516, + "step": 1335808 + }, + { + "epoch": 0.01, + "learning_rate": 2.8122373249351565e-05, + "loss": 3.5008, + "step": 1336320 + }, + { + "epoch": 0.01, + "learning_rate": 2.8114003680644774e-05, + "loss": 3.5133, + "step": 1336832 + }, + { + "epoch": 0.01, + "learning_rate": 2.8105617733134254e-05, + "loss": 3.5071, + "step": 1337344 + }, + { + "epoch": 0.01, + "learning_rate": 2.8097231785623734e-05, + "loss": 3.5056, + "step": 1337856 + }, + { + "epoch": 0.01, + "learning_rate": 2.8088845838113214e-05, + "loss": 3.5051, + "step": 1338368 + }, + { + "epoch": 0.01, + "learning_rate": 2.8080476269406426e-05, + "loss": 3.5063, + "step": 1338880 + }, + { + "epoch": 0.01, + "learning_rate": 2.8072090321895906e-05, + "loss": 3.5203, + "step": 1339392 + }, + { + "epoch": 0.01, + "learning_rate": 2.8063704374385386e-05, + "loss": 3.5109, + "step": 1339904 + }, + { + "epoch": 0.01, + "learning_rate": 2.8055318426874866e-05, + "loss": 3.4882, + "step": 1340416 + }, + { + "epoch": 0.01, + "learning_rate": 2.8046948858168075e-05, + "loss": 3.4956, + "step": 1340928 + }, + { + "epoch": 0.01, + "learning_rate": 2.8038562910657555e-05, + "loss": 3.5075, + "step": 1341440 + }, + { + "epoch": 0.01, + "learning_rate": 2.8030176963147038e-05, + "loss": 3.5075, + "step": 1341952 + }, + { + "epoch": 0.01, + "learning_rate": 2.8021791015636518e-05, + "loss": 3.5073, + "step": 1342464 + }, + { + "epoch": 0.01, + "learning_rate": 2.8013421446929727e-05, + "loss": 3.5082, + "step": 1342976 + }, + { + "epoch": 0.02, + "learning_rate": 2.8005035499419207e-05, + "loss": 3.5017, + "step": 1343488 + }, + { + "epoch": 0.02, + "learning_rate": 2.7996649551908687e-05, + "loss": 3.4964, + "step": 1344000 + }, + { + "epoch": 0.02, + "learning_rate": 2.7988263604398167e-05, + "loss": 3.5064, + "step": 1344512 + }, + { + "epoch": 0.02, + "learning_rate": 2.797989403569138e-05, + "loss": 3.5072, + "step": 1345024 + }, + { + "epoch": 0.02, + "learning_rate": 2.797150808818086e-05, + "loss": 3.5071, + "step": 1345536 + }, + { + "epoch": 0.02, + "learning_rate": 2.796312214067034e-05, + "loss": 3.5145, + "step": 1346048 + }, + { + "epoch": 0.02, + "learning_rate": 2.795473619315982e-05, + "loss": 3.5083, + "step": 1346560 + }, + { + "epoch": 0.02, + "learning_rate": 2.79463502456493e-05, + "loss": 3.4987, + "step": 1347072 + }, + { + "epoch": 0.02, + "learning_rate": 2.793798067694251e-05, + "loss": 3.5075, + "step": 1347584 + }, + { + "epoch": 0.02, + "learning_rate": 2.7929594729431992e-05, + "loss": 3.5058, + "step": 1348096 + }, + { + "epoch": 0.02, + "learning_rate": 2.7921208781921472e-05, + "loss": 3.5138, + "step": 1348608 + }, + { + "epoch": 0.02, + "learning_rate": 2.791283921321468e-05, + "loss": 3.5022, + "step": 1349120 + }, + { + "epoch": 0.02, + "learning_rate": 2.790445326570416e-05, + "loss": 3.4986, + "step": 1349632 + }, + { + "epoch": 0.02, + "learning_rate": 2.789606731819364e-05, + "loss": 3.498, + "step": 1350144 + }, + { + "epoch": 0.02, + "learning_rate": 2.788768137068312e-05, + "loss": 3.5119, + "step": 1350656 + }, + { + "epoch": 0.02, + "learning_rate": 2.7879311801976333e-05, + "loss": 3.4965, + "step": 1351168 + }, + { + "epoch": 0.02, + "learning_rate": 2.7870925854465813e-05, + "loss": 3.4853, + "step": 1351680 + }, + { + "epoch": 0.02, + "learning_rate": 2.7862539906955293e-05, + "loss": 3.5028, + "step": 1352192 + }, + { + "epoch": 0.02, + "learning_rate": 2.7854153959444773e-05, + "loss": 3.5049, + "step": 1352704 + }, + { + "epoch": 0.02, + "learning_rate": 2.7845768011934253e-05, + "loss": 3.4963, + "step": 1353216 + }, + { + "epoch": 0.02, + "learning_rate": 2.7837398443227462e-05, + "loss": 3.5045, + "step": 1353728 + }, + { + "epoch": 0.02, + "learning_rate": 2.7829012495716946e-05, + "loss": 3.4984, + "step": 1354240 + }, + { + "epoch": 0.02, + "learning_rate": 2.7820626548206426e-05, + "loss": 3.5079, + "step": 1354752 + }, + { + "epoch": 0.02, + "learning_rate": 2.7812240600695906e-05, + "loss": 3.4965, + "step": 1355264 + }, + { + "epoch": 0.02, + "learning_rate": 2.7803871031989115e-05, + "loss": 3.5049, + "step": 1355776 + }, + { + "epoch": 0.02, + "learning_rate": 2.7795485084478595e-05, + "loss": 3.5121, + "step": 1356288 + }, + { + "epoch": 0.02, + "learning_rate": 2.7787099136968075e-05, + "loss": 3.5164, + "step": 1356800 + }, + { + "epoch": 0.02, + "learning_rate": 2.7778713189457554e-05, + "loss": 3.4974, + "step": 1357312 + }, + { + "epoch": 0.02, + "learning_rate": 2.7770343620750767e-05, + "loss": 3.5034, + "step": 1357824 + }, + { + "epoch": 0.02, + "learning_rate": 2.7761957673240247e-05, + "loss": 3.5073, + "step": 1358336 + }, + { + "epoch": 0.02, + "learning_rate": 2.7753571725729727e-05, + "loss": 3.5052, + "step": 1358848 + }, + { + "epoch": 0.02, + "learning_rate": 2.7745185778219207e-05, + "loss": 3.4937, + "step": 1359360 + }, + { + "epoch": 0.02, + "learning_rate": 2.7736816209512416e-05, + "loss": 3.5051, + "step": 1359872 + }, + { + "epoch": 0.02, + "learning_rate": 2.77284302620019e-05, + "loss": 3.5009, + "step": 1360384 + }, + { + "epoch": 0.02, + "learning_rate": 2.772004431449138e-05, + "loss": 3.5097, + "step": 1360896 + }, + { + "epoch": 0.02, + "learning_rate": 2.771165836698086e-05, + "loss": 3.4944, + "step": 1361408 + }, + { + "epoch": 0.02, + "learning_rate": 2.7703288798274068e-05, + "loss": 3.4958, + "step": 1361920 + }, + { + "epoch": 0.02, + "learning_rate": 2.7694902850763548e-05, + "loss": 3.4978, + "step": 1362432 + }, + { + "epoch": 0.02, + "learning_rate": 2.7686516903253028e-05, + "loss": 3.5019, + "step": 1362944 + }, + { + "epoch": 0.02, + "learning_rate": 2.7678130955742508e-05, + "loss": 3.4979, + "step": 1363456 + }, + { + "epoch": 0.02, + "learning_rate": 2.766976138703572e-05, + "loss": 3.5159, + "step": 1363968 + }, + { + "epoch": 0.02, + "learning_rate": 2.76613754395252e-05, + "loss": 3.5072, + "step": 1364480 + }, + { + "epoch": 0.02, + "learning_rate": 2.765298949201468e-05, + "loss": 3.4965, + "step": 1364992 + }, + { + "epoch": 0.02, + "learning_rate": 2.764460354450416e-05, + "loss": 3.496, + "step": 1365504 + }, + { + "epoch": 0.02, + "learning_rate": 2.763623397579737e-05, + "loss": 3.5122, + "step": 1366016 + }, + { + "epoch": 0.02, + "learning_rate": 2.7627848028286853e-05, + "loss": 3.5072, + "step": 1366528 + }, + { + "epoch": 0.02, + "learning_rate": 2.7619462080776333e-05, + "loss": 3.5024, + "step": 1367040 + }, + { + "epoch": 0.02, + "learning_rate": 2.7611076133265813e-05, + "loss": 3.4981, + "step": 1367552 + }, + { + "epoch": 0.02, + "learning_rate": 2.7602706564559022e-05, + "loss": 3.5118, + "step": 1368064 + }, + { + "epoch": 0.02, + "learning_rate": 2.7594320617048502e-05, + "loss": 3.5102, + "step": 1368576 + }, + { + "epoch": 0.02, + "learning_rate": 2.7585934669537982e-05, + "loss": 3.5038, + "step": 1369088 + }, + { + "epoch": 0.02, + "learning_rate": 2.7577548722027462e-05, + "loss": 3.5013, + "step": 1369600 + }, + { + "epoch": 0.02, + "learning_rate": 2.7569179153320674e-05, + "loss": 3.5039, + "step": 1370112 + }, + { + "epoch": 0.02, + "learning_rate": 2.7560793205810154e-05, + "loss": 3.4999, + "step": 1370624 + }, + { + "epoch": 0.02, + "learning_rate": 2.7552407258299634e-05, + "loss": 3.4968, + "step": 1371136 + }, + { + "epoch": 0.02, + "learning_rate": 2.7544021310789114e-05, + "loss": 3.5146, + "step": 1371648 + }, + { + "epoch": 0.02, + "learning_rate": 2.7535651742082323e-05, + "loss": 3.5006, + "step": 1372160 + }, + { + "epoch": 0.02, + "learning_rate": 2.7527265794571803e-05, + "loss": 3.5059, + "step": 1372672 + }, + { + "epoch": 0.02, + "learning_rate": 2.7518879847061287e-05, + "loss": 3.4989, + "step": 1373184 + }, + { + "epoch": 0.02, + "learning_rate": 2.7510493899550767e-05, + "loss": 3.4967, + "step": 1373696 + }, + { + "epoch": 0.03, + "eval_loss": 3.845757007598877, + "eval_runtime": 349.5863, + "eval_samples_per_second": 1091.55, + "eval_steps_per_second": 34.112, + "step": 1373760 + }, + { + "epoch": 1.0, + "learning_rate": 2.7502107952040246e-05, + "loss": 3.4953, + "step": 1374208 + }, + { + "epoch": 1.0, + "learning_rate": 2.7493738383333456e-05, + "loss": 3.5038, + "step": 1374720 + }, + { + "epoch": 1.0, + "learning_rate": 2.7485352435822936e-05, + "loss": 3.5118, + "step": 1375232 + }, + { + "epoch": 1.0, + "learning_rate": 2.7476966488312415e-05, + "loss": 3.5024, + "step": 1375744 + }, + { + "epoch": 1.0, + "learning_rate": 2.7468580540801895e-05, + "loss": 3.51, + "step": 1376256 + }, + { + "epoch": 1.0, + "learning_rate": 2.7460210972095108e-05, + "loss": 3.5004, + "step": 1376768 + }, + { + "epoch": 1.0, + "learning_rate": 2.7451825024584588e-05, + "loss": 3.5023, + "step": 1377280 + }, + { + "epoch": 1.0, + "learning_rate": 2.7443439077074068e-05, + "loss": 3.4908, + "step": 1377792 + }, + { + "epoch": 1.0, + "learning_rate": 2.7435053129563548e-05, + "loss": 3.5116, + "step": 1378304 + }, + { + "epoch": 1.0, + "learning_rate": 2.7426683560856757e-05, + "loss": 3.5084, + "step": 1378816 + }, + { + "epoch": 1.0, + "learning_rate": 2.741829761334624e-05, + "loss": 3.5055, + "step": 1379328 + }, + { + "epoch": 1.0, + "learning_rate": 2.740991166583572e-05, + "loss": 3.5101, + "step": 1379840 + }, + { + "epoch": 1.0, + "learning_rate": 2.740154209712893e-05, + "loss": 3.4962, + "step": 1380352 + }, + { + "epoch": 1.0, + "learning_rate": 2.739315614961841e-05, + "loss": 3.4945, + "step": 1380864 + }, + { + "epoch": 1.0, + "learning_rate": 2.738477020210789e-05, + "loss": 3.5067, + "step": 1381376 + }, + { + "epoch": 1.0, + "learning_rate": 2.737638425459737e-05, + "loss": 3.4906, + "step": 1381888 + }, + { + "epoch": 1.0, + "learning_rate": 2.7367998307086846e-05, + "loss": 3.4969, + "step": 1382400 + }, + { + "epoch": 1.0, + "learning_rate": 2.7359612359576326e-05, + "loss": 3.4919, + "step": 1382912 + }, + { + "epoch": 1.0, + "learning_rate": 2.7351226412065806e-05, + "loss": 3.4925, + "step": 1383424 + }, + { + "epoch": 1.0, + "learning_rate": 2.734285684335902e-05, + "loss": 3.5184, + "step": 1383936 + }, + { + "epoch": 1.0, + "learning_rate": 2.7334470895848495e-05, + "loss": 3.5008, + "step": 1384448 + }, + { + "epoch": 1.0, + "learning_rate": 2.7326084948337978e-05, + "loss": 3.5043, + "step": 1384960 + }, + { + "epoch": 1.0, + "learning_rate": 2.7317699000827458e-05, + "loss": 3.4946, + "step": 1385472 + }, + { + "epoch": 1.0, + "learning_rate": 2.7309313053316938e-05, + "loss": 3.5101, + "step": 1385984 + }, + { + "epoch": 1.0, + "learning_rate": 2.7300943484610147e-05, + "loss": 3.4836, + "step": 1386496 + }, + { + "epoch": 1.0, + "learning_rate": 2.7292557537099627e-05, + "loss": 3.4943, + "step": 1387008 + }, + { + "epoch": 1.0, + "learning_rate": 2.7284171589589107e-05, + "loss": 3.4922, + "step": 1387520 + }, + { + "epoch": 1.0, + "learning_rate": 2.7275785642078587e-05, + "loss": 3.4994, + "step": 1388032 + }, + { + "epoch": 1.0, + "learning_rate": 2.72674160733718e-05, + "loss": 3.4932, + "step": 1388544 + }, + { + "epoch": 1.01, + "learning_rate": 2.725903012586128e-05, + "loss": 3.4911, + "step": 1389056 + }, + { + "epoch": 1.01, + "learning_rate": 2.725064417835076e-05, + "loss": 3.499, + "step": 1389568 + }, + { + "epoch": 1.01, + "learning_rate": 2.724225823084024e-05, + "loss": 3.5043, + "step": 1390080 + }, + { + "epoch": 1.01, + "learning_rate": 2.723388866213345e-05, + "loss": 3.4878, + "step": 1390592 + }, + { + "epoch": 1.01, + "learning_rate": 2.722550271462293e-05, + "loss": 3.5018, + "step": 1391104 + }, + { + "epoch": 1.01, + "learning_rate": 2.721711676711241e-05, + "loss": 3.5049, + "step": 1391616 + }, + { + "epoch": 1.01, + "learning_rate": 2.720873081960189e-05, + "loss": 3.5006, + "step": 1392128 + }, + { + "epoch": 1.01, + "learning_rate": 2.72003612508951e-05, + "loss": 3.4841, + "step": 1392640 + }, + { + "epoch": 1.01, + "learning_rate": 2.719197530338458e-05, + "loss": 3.4944, + "step": 1393152 + }, + { + "epoch": 1.01, + "learning_rate": 2.718358935587406e-05, + "loss": 3.4835, + "step": 1393664 + }, + { + "epoch": 1.01, + "learning_rate": 2.717520340836354e-05, + "loss": 3.4972, + "step": 1394176 + }, + { + "epoch": 1.01, + "learning_rate": 2.7166817460853024e-05, + "loss": 3.4927, + "step": 1394688 + }, + { + "epoch": 1.01, + "learning_rate": 2.7158447892146233e-05, + "loss": 3.5019, + "step": 1395200 + }, + { + "epoch": 1.01, + "learning_rate": 2.7150061944635713e-05, + "loss": 3.4901, + "step": 1395712 + }, + { + "epoch": 1.01, + "learning_rate": 2.7141675997125193e-05, + "loss": 3.4937, + "step": 1396224 + }, + { + "epoch": 1.01, + "learning_rate": 2.7133290049614673e-05, + "loss": 3.5005, + "step": 1396736 + }, + { + "epoch": 1.01, + "learning_rate": 2.7124920480907885e-05, + "loss": 3.5036, + "step": 1397248 + }, + { + "epoch": 1.01, + "learning_rate": 2.7116534533397365e-05, + "loss": 3.4975, + "step": 1397760 + }, + { + "epoch": 1.01, + "learning_rate": 2.7108148585886845e-05, + "loss": 3.4779, + "step": 1398272 + }, + { + "epoch": 1.01, + "learning_rate": 2.7099762638376325e-05, + "loss": 3.4937, + "step": 1398784 + }, + { + "epoch": 1.01, + "learning_rate": 2.7091393069669534e-05, + "loss": 3.5038, + "step": 1399296 + }, + { + "epoch": 1.01, + "learning_rate": 2.7083007122159014e-05, + "loss": 3.4941, + "step": 1399808 + }, + { + "epoch": 1.01, + "learning_rate": 2.7074621174648494e-05, + "loss": 3.4938, + "step": 1400320 + }, + { + "epoch": 1.01, + "learning_rate": 2.7066235227137978e-05, + "loss": 3.4877, + "step": 1400832 + }, + { + "epoch": 1.01, + "learning_rate": 2.7057865658431187e-05, + "loss": 3.4921, + "step": 1401344 + }, + { + "epoch": 1.01, + "learning_rate": 2.7049479710920667e-05, + "loss": 3.4783, + "step": 1401856 + }, + { + "epoch": 1.01, + "learning_rate": 2.7041093763410147e-05, + "loss": 3.5054, + "step": 1402368 + }, + { + "epoch": 1.01, + "learning_rate": 2.7032707815899627e-05, + "loss": 3.4973, + "step": 1402880 + }, + { + "epoch": 1.01, + "learning_rate": 2.702433824719284e-05, + "loss": 3.5006, + "step": 1403392 + }, + { + "epoch": 1.01, + "learning_rate": 2.701595229968232e-05, + "loss": 3.5072, + "step": 1403904 + }, + { + "epoch": 1.01, + "learning_rate": 2.70075663521718e-05, + "loss": 3.4801, + "step": 1404416 + }, + { + "epoch": 1.01, + "learning_rate": 2.699918040466128e-05, + "loss": 3.4947, + "step": 1404928 + }, + { + "epoch": 1.01, + "learning_rate": 2.6990810835954488e-05, + "loss": 3.4915, + "step": 1405440 + }, + { + "epoch": 1.01, + "learning_rate": 2.6982424888443968e-05, + "loss": 3.4847, + "step": 1405952 + }, + { + "epoch": 1.01, + "learning_rate": 2.6974038940933448e-05, + "loss": 3.4797, + "step": 1406464 + }, + { + "epoch": 1.01, + "learning_rate": 2.696565299342293e-05, + "loss": 3.4946, + "step": 1406976 + }, + { + "epoch": 1.01, + "learning_rate": 2.695728342471614e-05, + "loss": 3.4905, + "step": 1407488 + }, + { + "epoch": 1.01, + "learning_rate": 2.694889747720562e-05, + "loss": 3.4835, + "step": 1408000 + }, + { + "epoch": 1.01, + "learning_rate": 2.69405115296951e-05, + "loss": 3.4755, + "step": 1408512 + }, + { + "epoch": 1.01, + "learning_rate": 2.693212558218458e-05, + "loss": 3.4963, + "step": 1409024 + }, + { + "epoch": 1.01, + "learning_rate": 2.6923756013477793e-05, + "loss": 3.5007, + "step": 1409536 + }, + { + "epoch": 1.01, + "learning_rate": 2.6915370065967273e-05, + "loss": 3.493, + "step": 1410048 + }, + { + "epoch": 1.01, + "learning_rate": 2.6906984118456753e-05, + "loss": 3.4944, + "step": 1410560 + }, + { + "epoch": 1.01, + "learning_rate": 2.6898598170946233e-05, + "loss": 3.5067, + "step": 1411072 + }, + { + "epoch": 1.01, + "learning_rate": 2.689022860223944e-05, + "loss": 3.4992, + "step": 1411584 + }, + { + "epoch": 1.01, + "learning_rate": 2.688184265472892e-05, + "loss": 3.5055, + "step": 1412096 + }, + { + "epoch": 1.01, + "learning_rate": 2.68734567072184e-05, + "loss": 3.4839, + "step": 1412608 + }, + { + "epoch": 1.01, + "learning_rate": 2.6865070759707885e-05, + "loss": 3.5005, + "step": 1413120 + }, + { + "epoch": 1.01, + "learning_rate": 2.6856701191001094e-05, + "loss": 3.4971, + "step": 1413632 + }, + { + "epoch": 1.01, + "learning_rate": 2.6848315243490574e-05, + "loss": 3.4917, + "step": 1414144 + }, + { + "epoch": 1.01, + "learning_rate": 2.6839929295980054e-05, + "loss": 3.4971, + "step": 1414656 + }, + { + "epoch": 1.01, + "learning_rate": 2.6831543348469534e-05, + "loss": 3.4944, + "step": 1415168 + }, + { + "epoch": 1.01, + "learning_rate": 2.6823173779762746e-05, + "loss": 3.5075, + "step": 1415680 + }, + { + "epoch": 1.01, + "learning_rate": 2.6814787832252226e-05, + "loss": 3.4973, + "step": 1416192 + }, + { + "epoch": 1.01, + "learning_rate": 2.6806401884741706e-05, + "loss": 3.4755, + "step": 1416704 + }, + { + "epoch": 1.01, + "learning_rate": 2.6798015937231186e-05, + "loss": 3.4827, + "step": 1417216 + }, + { + "epoch": 1.01, + "learning_rate": 2.6789629989720666e-05, + "loss": 3.4942, + "step": 1417728 + }, + { + "epoch": 1.01, + "learning_rate": 2.6781260421013875e-05, + "loss": 3.4963, + "step": 1418240 + }, + { + "epoch": 1.01, + "learning_rate": 2.6772874473503355e-05, + "loss": 3.4961, + "step": 1418752 + }, + { + "epoch": 1.01, + "learning_rate": 2.6764488525992835e-05, + "loss": 3.4921, + "step": 1419264 + }, + { + "epoch": 1.02, + "learning_rate": 2.675610257848232e-05, + "loss": 3.4912, + "step": 1419776 + }, + { + "epoch": 1.02, + "learning_rate": 2.6747733009775528e-05, + "loss": 3.4833, + "step": 1420288 + }, + { + "epoch": 1.02, + "learning_rate": 2.6739347062265008e-05, + "loss": 3.4949, + "step": 1420800 + }, + { + "epoch": 1.02, + "learning_rate": 2.6730961114754488e-05, + "loss": 3.4886, + "step": 1421312 + }, + { + "epoch": 1.02, + "learning_rate": 2.6722575167243967e-05, + "loss": 3.497, + "step": 1421824 + }, + { + "epoch": 1.02, + "learning_rate": 2.671420559853718e-05, + "loss": 3.5018, + "step": 1422336 + }, + { + "epoch": 1.02, + "learning_rate": 2.670581965102666e-05, + "loss": 3.4975, + "step": 1422848 + }, + { + "epoch": 1.02, + "learning_rate": 2.669743370351614e-05, + "loss": 3.4874, + "step": 1423360 + }, + { + "epoch": 1.02, + "learning_rate": 2.668904775600562e-05, + "loss": 3.4958, + "step": 1423872 + }, + { + "epoch": 1.02, + "learning_rate": 2.668067818729883e-05, + "loss": 3.4901, + "step": 1424384 + }, + { + "epoch": 1.02, + "learning_rate": 2.667229223978831e-05, + "loss": 3.4998, + "step": 1424896 + }, + { + "epoch": 1.02, + "learning_rate": 2.666390629227779e-05, + "loss": 3.4916, + "step": 1425408 + }, + { + "epoch": 1.02, + "learning_rate": 2.6655520344767272e-05, + "loss": 3.4887, + "step": 1425920 + }, + { + "epoch": 1.02, + "learning_rate": 2.664715077606048e-05, + "loss": 3.4818, + "step": 1426432 + }, + { + "epoch": 1.02, + "learning_rate": 2.663876482854996e-05, + "loss": 3.4986, + "step": 1426944 + }, + { + "epoch": 1.02, + "learning_rate": 2.663037888103944e-05, + "loss": 3.4857, + "step": 1427456 + }, + { + "epoch": 1.02, + "learning_rate": 2.662199293352892e-05, + "loss": 3.4767, + "step": 1427968 + }, + { + "epoch": 1.02, + "learning_rate": 2.6613623364822134e-05, + "loss": 3.4862, + "step": 1428480 + }, + { + "epoch": 1.02, + "learning_rate": 2.6605237417311614e-05, + "loss": 3.4925, + "step": 1428992 + }, + { + "epoch": 1.02, + "learning_rate": 2.6596851469801094e-05, + "loss": 3.4826, + "step": 1429504 + }, + { + "epoch": 1.02, + "learning_rate": 2.6588465522290574e-05, + "loss": 3.4962, + "step": 1430016 + }, + { + "epoch": 1.02, + "learning_rate": 2.6580095953583783e-05, + "loss": 3.4811, + "step": 1430528 + }, + { + "epoch": 1.02, + "learning_rate": 2.6571710006073263e-05, + "loss": 3.4963, + "step": 1431040 + }, + { + "epoch": 1.02, + "learning_rate": 2.6563324058562743e-05, + "loss": 3.4834, + "step": 1431552 + }, + { + "epoch": 1.02, + "learning_rate": 2.655493811105222e-05, + "loss": 3.4861, + "step": 1432064 + }, + { + "epoch": 1.02, + "learning_rate": 2.6546568542345435e-05, + "loss": 3.5039, + "step": 1432576 + }, + { + "epoch": 1.02, + "learning_rate": 2.6538182594834915e-05, + "loss": 3.5018, + "step": 1433088 + }, + { + "epoch": 1.02, + "learning_rate": 2.6529796647324395e-05, + "loss": 3.486, + "step": 1433600 + }, + { + "epoch": 1.02, + "learning_rate": 2.652141069981387e-05, + "loss": 3.4917, + "step": 1434112 + }, + { + "epoch": 1.02, + "learning_rate": 2.6513041131107087e-05, + "loss": 3.489, + "step": 1434624 + }, + { + "epoch": 1.02, + "learning_rate": 2.6504655183596567e-05, + "loss": 3.493, + "step": 1435136 + }, + { + "epoch": 1.02, + "learning_rate": 2.649626923608604e-05, + "loss": 3.4823, + "step": 1435648 + }, + { + "epoch": 1.02, + "learning_rate": 2.648788328857552e-05, + "loss": 3.4944, + "step": 1436160 + }, + { + "epoch": 1.02, + "learning_rate": 2.6479513719868736e-05, + "loss": 3.4887, + "step": 1436672 + }, + { + "epoch": 1.02, + "learning_rate": 2.6471127772358216e-05, + "loss": 3.4956, + "step": 1437184 + }, + { + "epoch": 1.02, + "learning_rate": 2.6462741824847693e-05, + "loss": 3.4784, + "step": 1437696 + }, + { + "epoch": 1.02, + "learning_rate": 2.6454355877337173e-05, + "loss": 3.4883, + "step": 1438208 + }, + { + "epoch": 1.02, + "learning_rate": 2.644598630863039e-05, + "loss": 3.4821, + "step": 1438720 + }, + { + "epoch": 1.02, + "learning_rate": 2.643760036111987e-05, + "loss": 3.4888, + "step": 1439232 + }, + { + "epoch": 1.02, + "learning_rate": 2.6429214413609342e-05, + "loss": 3.4873, + "step": 1439744 + }, + { + "epoch": 1.02, + "learning_rate": 2.6420828466098825e-05, + "loss": 3.5061, + "step": 1440256 + }, + { + "epoch": 1.02, + "learning_rate": 2.641245889739204e-05, + "loss": 3.4932, + "step": 1440768 + }, + { + "epoch": 1.02, + "learning_rate": 2.6404072949881514e-05, + "loss": 3.488, + "step": 1441280 + }, + { + "epoch": 1.02, + "learning_rate": 2.6395687002370994e-05, + "loss": 3.4787, + "step": 1441792 + }, + { + "epoch": 1.02, + "learning_rate": 2.6387301054860474e-05, + "loss": 3.4988, + "step": 1442304 + }, + { + "epoch": 1.02, + "learning_rate": 2.637893148615369e-05, + "loss": 3.4958, + "step": 1442816 + }, + { + "epoch": 1.02, + "learning_rate": 2.6370545538643167e-05, + "loss": 3.492, + "step": 1443328 + }, + { + "epoch": 1.02, + "learning_rate": 2.6362159591132646e-05, + "loss": 3.4874, + "step": 1443840 + }, + { + "epoch": 1.02, + "learning_rate": 2.6353773643622126e-05, + "loss": 3.4967, + "step": 1444352 + }, + { + "epoch": 1.02, + "learning_rate": 2.6345404074915342e-05, + "loss": 3.4962, + "step": 1444864 + }, + { + "epoch": 1.02, + "learning_rate": 2.6337018127404815e-05, + "loss": 3.4928, + "step": 1445376 + }, + { + "epoch": 1.02, + "learning_rate": 2.6328632179894295e-05, + "loss": 3.4884, + "step": 1445888 + }, + { + "epoch": 1.02, + "learning_rate": 2.632024623238378e-05, + "loss": 3.4923, + "step": 1446400 + }, + { + "epoch": 1.02, + "learning_rate": 2.6311876663676988e-05, + "loss": 3.4878, + "step": 1446912 + }, + { + "epoch": 1.02, + "learning_rate": 2.6303490716166468e-05, + "loss": 3.4816, + "step": 1447424 + }, + { + "epoch": 1.02, + "learning_rate": 2.6295104768655948e-05, + "loss": 3.4951, + "step": 1447936 + }, + { + "epoch": 1.02, + "learning_rate": 2.6286718821145428e-05, + "loss": 3.4956, + "step": 1448448 + }, + { + "epoch": 1.02, + "learning_rate": 2.627834925243864e-05, + "loss": 3.4906, + "step": 1448960 + }, + { + "epoch": 1.02, + "learning_rate": 2.626996330492812e-05, + "loss": 3.4838, + "step": 1449472 + }, + { + "epoch": 1.02, + "learning_rate": 2.62615773574176e-05, + "loss": 3.4799, + "step": 1449984 + }, + { + "epoch": 1.03, + "eval_loss": 3.847550868988037, + "eval_runtime": 506.4073, + "eval_samples_per_second": 753.526, + "eval_steps_per_second": 23.548, + "step": 1450080 + }, + { + "epoch": 0.0, + "learning_rate": 2.625319140990708e-05, + "loss": 3.4844, + "step": 1450496 + }, + { + "epoch": 0.0, + "learning_rate": 2.624480546239656e-05, + "loss": 3.4889, + "step": 1451008 + }, + { + "epoch": 0.0, + "learning_rate": 2.623641951488604e-05, + "loss": 3.4978, + "step": 1451520 + }, + { + "epoch": 0.0, + "learning_rate": 2.622803356737552e-05, + "loss": 3.4887, + "step": 1452032 + }, + { + "epoch": 0.0, + "learning_rate": 2.6219663998668732e-05, + "loss": 3.4992, + "step": 1452544 + }, + { + "epoch": 0.0, + "learning_rate": 2.6211278051158212e-05, + "loss": 3.4866, + "step": 1453056 + }, + { + "epoch": 0.0, + "learning_rate": 2.6202892103647692e-05, + "loss": 3.4903, + "step": 1453568 + }, + { + "epoch": 0.0, + "learning_rate": 2.6194506156137172e-05, + "loss": 3.477, + "step": 1454080 + }, + { + "epoch": 0.0, + "learning_rate": 2.618613658743038e-05, + "loss": 3.5001, + "step": 1454592 + }, + { + "epoch": 0.0, + "learning_rate": 2.617775063991986e-05, + "loss": 3.4953, + "step": 1455104 + }, + { + "epoch": 0.0, + "learning_rate": 2.616936469240934e-05, + "loss": 3.4963, + "step": 1455616 + }, + { + "epoch": 0.0, + "learning_rate": 2.6160978744898825e-05, + "loss": 3.4982, + "step": 1456128 + }, + { + "epoch": 0.0, + "learning_rate": 2.6152609176192034e-05, + "loss": 3.4812, + "step": 1456640 + }, + { + "epoch": 0.0, + "learning_rate": 2.6144223228681514e-05, + "loss": 3.4831, + "step": 1457152 + }, + { + "epoch": 0.0, + "learning_rate": 2.6135837281170994e-05, + "loss": 3.4945, + "step": 1457664 + }, + { + "epoch": 0.0, + "learning_rate": 2.6127451333660474e-05, + "loss": 3.4819, + "step": 1458176 + }, + { + "epoch": 0.0, + "learning_rate": 2.6119081764953686e-05, + "loss": 3.4807, + "step": 1458688 + }, + { + "epoch": 0.0, + "learning_rate": 2.6110695817443166e-05, + "loss": 3.4756, + "step": 1459200 + }, + { + "epoch": 0.0, + "learning_rate": 2.6102309869932646e-05, + "loss": 3.4815, + "step": 1459712 + }, + { + "epoch": 0.0, + "learning_rate": 2.6093923922422126e-05, + "loss": 3.5079, + "step": 1460224 + }, + { + "epoch": 0.0, + "learning_rate": 2.6085554353715335e-05, + "loss": 3.4887, + "step": 1460736 + }, + { + "epoch": 0.0, + "learning_rate": 2.6077168406204815e-05, + "loss": 3.4895, + "step": 1461248 + }, + { + "epoch": 0.0, + "learning_rate": 2.6068782458694295e-05, + "loss": 3.4861, + "step": 1461760 + }, + { + "epoch": 0.0, + "learning_rate": 2.606039651118378e-05, + "loss": 3.4927, + "step": 1462272 + }, + { + "epoch": 0.0, + "learning_rate": 2.6052026942476987e-05, + "loss": 3.4771, + "step": 1462784 + }, + { + "epoch": 0.0, + "learning_rate": 2.6043640994966467e-05, + "loss": 3.4814, + "step": 1463296 + }, + { + "epoch": 0.0, + "learning_rate": 2.6035255047455947e-05, + "loss": 3.4838, + "step": 1463808 + }, + { + "epoch": 0.0, + "learning_rate": 2.6026869099945427e-05, + "loss": 3.4891, + "step": 1464320 + }, + { + "epoch": 0.0, + "learning_rate": 2.601849953123864e-05, + "loss": 3.4759, + "step": 1464832 + }, + { + "epoch": 0.01, + "learning_rate": 2.601011358372812e-05, + "loss": 3.4819, + "step": 1465344 + }, + { + "epoch": 0.01, + "learning_rate": 2.60017276362176e-05, + "loss": 3.4831, + "step": 1465856 + }, + { + "epoch": 0.01, + "learning_rate": 2.599334168870708e-05, + "loss": 3.4906, + "step": 1466368 + }, + { + "epoch": 0.01, + "learning_rate": 2.598497212000029e-05, + "loss": 3.4802, + "step": 1466880 + }, + { + "epoch": 0.01, + "learning_rate": 2.597658617248977e-05, + "loss": 3.4875, + "step": 1467392 + }, + { + "epoch": 0.01, + "learning_rate": 2.596820022497925e-05, + "loss": 3.4883, + "step": 1467904 + }, + { + "epoch": 0.01, + "learning_rate": 2.595981427746873e-05, + "loss": 3.4887, + "step": 1468416 + }, + { + "epoch": 0.01, + "learning_rate": 2.595144470876194e-05, + "loss": 3.4718, + "step": 1468928 + }, + { + "epoch": 0.01, + "learning_rate": 2.594305876125142e-05, + "loss": 3.4836, + "step": 1469440 + }, + { + "epoch": 0.01, + "learning_rate": 2.59346728137409e-05, + "loss": 3.4708, + "step": 1469952 + }, + { + "epoch": 0.01, + "learning_rate": 2.592628686623038e-05, + "loss": 3.4851, + "step": 1470464 + }, + { + "epoch": 0.01, + "learning_rate": 2.5917917297523593e-05, + "loss": 3.4758, + "step": 1470976 + }, + { + "epoch": 0.01, + "learning_rate": 2.5909531350013073e-05, + "loss": 3.4907, + "step": 1471488 + }, + { + "epoch": 0.01, + "learning_rate": 2.5901145402502553e-05, + "loss": 3.4799, + "step": 1472000 + }, + { + "epoch": 0.01, + "learning_rate": 2.5892759454992033e-05, + "loss": 3.4793, + "step": 1472512 + }, + { + "epoch": 0.01, + "learning_rate": 2.5884389886285242e-05, + "loss": 3.4902, + "step": 1473024 + }, + { + "epoch": 0.01, + "learning_rate": 2.5876003938774722e-05, + "loss": 3.4871, + "step": 1473536 + }, + { + "epoch": 0.01, + "learning_rate": 2.5867617991264202e-05, + "loss": 3.484, + "step": 1474048 + }, + { + "epoch": 0.01, + "learning_rate": 2.5859232043753682e-05, + "loss": 3.471, + "step": 1474560 + }, + { + "epoch": 0.01, + "learning_rate": 2.5850862475046895e-05, + "loss": 3.4804, + "step": 1475072 + }, + { + "epoch": 0.01, + "learning_rate": 2.5842476527536375e-05, + "loss": 3.4914, + "step": 1475584 + }, + { + "epoch": 0.01, + "learning_rate": 2.5834090580025855e-05, + "loss": 3.4821, + "step": 1476096 + }, + { + "epoch": 0.01, + "learning_rate": 2.5825704632515335e-05, + "loss": 3.4781, + "step": 1476608 + }, + { + "epoch": 0.01, + "learning_rate": 2.5817335063808544e-05, + "loss": 3.477, + "step": 1477120 + }, + { + "epoch": 0.01, + "learning_rate": 2.5808949116298027e-05, + "loss": 3.4819, + "step": 1477632 + }, + { + "epoch": 0.01, + "learning_rate": 2.5800563168787507e-05, + "loss": 3.4661, + "step": 1478144 + }, + { + "epoch": 0.01, + "learning_rate": 2.5792177221276987e-05, + "loss": 3.4875, + "step": 1478656 + }, + { + "epoch": 0.01, + "learning_rate": 2.5783807652570196e-05, + "loss": 3.4848, + "step": 1479168 + }, + { + "epoch": 0.01, + "learning_rate": 2.5775421705059676e-05, + "loss": 3.4882, + "step": 1479680 + }, + { + "epoch": 0.01, + "learning_rate": 2.5767035757549156e-05, + "loss": 3.4892, + "step": 1480192 + }, + { + "epoch": 0.01, + "learning_rate": 2.5758649810038636e-05, + "loss": 3.4727, + "step": 1480704 + }, + { + "epoch": 0.01, + "learning_rate": 2.575028024133185e-05, + "loss": 3.476, + "step": 1481216 + }, + { + "epoch": 0.01, + "learning_rate": 2.574189429382133e-05, + "loss": 3.4821, + "step": 1481728 + }, + { + "epoch": 0.01, + "learning_rate": 2.573350834631081e-05, + "loss": 3.4716, + "step": 1482240 + }, + { + "epoch": 0.01, + "learning_rate": 2.5725122398800288e-05, + "loss": 3.4706, + "step": 1482752 + }, + { + "epoch": 0.01, + "learning_rate": 2.5716752830093497e-05, + "loss": 3.4796, + "step": 1483264 + }, + { + "epoch": 0.01, + "learning_rate": 2.570836688258298e-05, + "loss": 3.4815, + "step": 1483776 + }, + { + "epoch": 0.01, + "learning_rate": 2.569998093507246e-05, + "loss": 3.4708, + "step": 1484288 + }, + { + "epoch": 0.01, + "learning_rate": 2.569159498756194e-05, + "loss": 3.465, + "step": 1484800 + }, + { + "epoch": 0.01, + "learning_rate": 2.568320904005142e-05, + "loss": 3.4816, + "step": 1485312 + }, + { + "epoch": 0.01, + "learning_rate": 2.567483947134463e-05, + "loss": 3.4863, + "step": 1485824 + }, + { + "epoch": 0.01, + "learning_rate": 2.566645352383411e-05, + "loss": 3.4768, + "step": 1486336 + }, + { + "epoch": 0.01, + "learning_rate": 2.565806757632359e-05, + "loss": 3.4857, + "step": 1486848 + }, + { + "epoch": 0.01, + "learning_rate": 2.5649681628813066e-05, + "loss": 3.4943, + "step": 1487360 + }, + { + "epoch": 0.01, + "learning_rate": 2.5641312060106282e-05, + "loss": 3.4892, + "step": 1487872 + }, + { + "epoch": 0.01, + "learning_rate": 2.5632926112595762e-05, + "loss": 3.4965, + "step": 1488384 + }, + { + "epoch": 0.01, + "learning_rate": 2.5624540165085242e-05, + "loss": 3.4687, + "step": 1488896 + }, + { + "epoch": 0.01, + "learning_rate": 2.561617059637845e-05, + "loss": 3.4862, + "step": 1489408 + }, + { + "epoch": 0.01, + "learning_rate": 2.5607784648867934e-05, + "loss": 3.4892, + "step": 1489920 + }, + { + "epoch": 0.01, + "learning_rate": 2.5599398701357414e-05, + "loss": 3.4748, + "step": 1490432 + }, + { + "epoch": 0.01, + "learning_rate": 2.5591012753846894e-05, + "loss": 3.4892, + "step": 1490944 + }, + { + "epoch": 0.01, + "learning_rate": 2.5582643185140103e-05, + "loss": 3.4786, + "step": 1491456 + }, + { + "epoch": 0.01, + "learning_rate": 2.5574257237629583e-05, + "loss": 3.4944, + "step": 1491968 + }, + { + "epoch": 0.01, + "learning_rate": 2.5565871290119063e-05, + "loss": 3.4859, + "step": 1492480 + }, + { + "epoch": 0.01, + "learning_rate": 2.555748534260854e-05, + "loss": 3.4639, + "step": 1492992 + }, + { + "epoch": 0.01, + "learning_rate": 2.5549115773901756e-05, + "loss": 3.473, + "step": 1493504 + }, + { + "epoch": 0.01, + "learning_rate": 2.5540729826391236e-05, + "loss": 3.4778, + "step": 1494016 + }, + { + "epoch": 0.01, + "learning_rate": 2.5532343878880716e-05, + "loss": 3.4824, + "step": 1494528 + }, + { + "epoch": 0.01, + "learning_rate": 2.552395793137019e-05, + "loss": 3.4871, + "step": 1495040 + }, + { + "epoch": 0.01, + "learning_rate": 2.5515571983859672e-05, + "loss": 3.4796, + "step": 1495552 + }, + { + "epoch": 0.02, + "learning_rate": 2.5507202415152888e-05, + "loss": 3.4791, + "step": 1496064 + }, + { + "epoch": 0.02, + "learning_rate": 2.5498816467642368e-05, + "loss": 3.4722, + "step": 1496576 + }, + { + "epoch": 0.02, + "learning_rate": 2.549043052013184e-05, + "loss": 3.4818, + "step": 1497088 + }, + { + "epoch": 0.02, + "learning_rate": 2.5482060951425057e-05, + "loss": 3.4749, + "step": 1497600 + }, + { + "epoch": 0.02, + "learning_rate": 2.5473675003914537e-05, + "loss": 3.4855, + "step": 1498112 + }, + { + "epoch": 0.02, + "learning_rate": 2.5465289056404014e-05, + "loss": 3.492, + "step": 1498624 + }, + { + "epoch": 0.02, + "learning_rate": 2.5456903108893494e-05, + "loss": 3.4856, + "step": 1499136 + }, + { + "epoch": 0.02, + "learning_rate": 2.5448517161382974e-05, + "loss": 3.4735, + "step": 1499648 + }, + { + "epoch": 0.02, + "learning_rate": 2.544014759267619e-05, + "loss": 3.4825, + "step": 1500160 + }, + { + "epoch": 0.02, + "learning_rate": 2.5431761645165663e-05, + "loss": 3.4777, + "step": 1500672 + }, + { + "epoch": 0.02, + "learning_rate": 2.5423375697655143e-05, + "loss": 3.4883, + "step": 1501184 + }, + { + "epoch": 0.02, + "learning_rate": 2.5414989750144626e-05, + "loss": 3.4801, + "step": 1501696 + }, + { + "epoch": 0.02, + "learning_rate": 2.5406620181437842e-05, + "loss": 3.4765, + "step": 1502208 + }, + { + "epoch": 0.02, + "learning_rate": 2.5398234233927315e-05, + "loss": 3.4693, + "step": 1502720 + }, + { + "epoch": 0.02, + "learning_rate": 2.5389848286416795e-05, + "loss": 3.4875, + "step": 1503232 + }, + { + "epoch": 0.02, + "learning_rate": 2.5381462338906275e-05, + "loss": 3.4705, + "step": 1503744 + }, + { + "epoch": 0.02, + "learning_rate": 2.5373092770199487e-05, + "loss": 3.468, + "step": 1504256 + }, + { + "epoch": 0.02, + "learning_rate": 2.5364706822688967e-05, + "loss": 3.4725, + "step": 1504768 + }, + { + "epoch": 0.02, + "learning_rate": 2.5356320875178447e-05, + "loss": 3.4801, + "step": 1505280 + }, + { + "epoch": 0.02, + "learning_rate": 2.5347934927667927e-05, + "loss": 3.4725, + "step": 1505792 + }, + { + "epoch": 0.02, + "learning_rate": 2.5339565358961136e-05, + "loss": 3.4847, + "step": 1506304 + }, + { + "epoch": 0.02, + "learning_rate": 2.5331179411450616e-05, + "loss": 3.4731, + "step": 1506816 + }, + { + "epoch": 0.02, + "learning_rate": 2.5322793463940096e-05, + "loss": 3.4778, + "step": 1507328 + }, + { + "epoch": 0.02, + "learning_rate": 2.531440751642958e-05, + "loss": 3.477, + "step": 1507840 + }, + { + "epoch": 0.02, + "learning_rate": 2.530603794772279e-05, + "loss": 3.4692, + "step": 1508352 + }, + { + "epoch": 0.02, + "learning_rate": 2.529765200021227e-05, + "loss": 3.493, + "step": 1508864 + }, + { + "epoch": 0.02, + "learning_rate": 2.528926605270175e-05, + "loss": 3.4896, + "step": 1509376 + }, + { + "epoch": 0.02, + "learning_rate": 2.528088010519123e-05, + "loss": 3.4761, + "step": 1509888 + }, + { + "epoch": 0.02, + "learning_rate": 2.527251053648444e-05, + "loss": 3.4811, + "step": 1510400 + }, + { + "epoch": 0.02, + "learning_rate": 2.526412458897392e-05, + "loss": 3.4726, + "step": 1510912 + }, + { + "epoch": 0.02, + "learning_rate": 2.52557386414634e-05, + "loss": 3.4821, + "step": 1511424 + }, + { + "epoch": 0.02, + "learning_rate": 2.524735269395288e-05, + "loss": 3.4699, + "step": 1511936 + }, + { + "epoch": 0.02, + "learning_rate": 2.523898312524609e-05, + "loss": 3.4849, + "step": 1512448 + }, + { + "epoch": 0.02, + "learning_rate": 2.523059717773557e-05, + "loss": 3.4744, + "step": 1512960 + }, + { + "epoch": 0.02, + "learning_rate": 2.522221123022505e-05, + "loss": 3.48, + "step": 1513472 + }, + { + "epoch": 0.02, + "learning_rate": 2.5213825282714533e-05, + "loss": 3.4713, + "step": 1513984 + }, + { + "epoch": 0.02, + "learning_rate": 2.5205455714007742e-05, + "loss": 3.4754, + "step": 1514496 + }, + { + "epoch": 0.02, + "learning_rate": 2.5197069766497222e-05, + "loss": 3.4696, + "step": 1515008 + }, + { + "epoch": 0.02, + "learning_rate": 2.5188683818986702e-05, + "loss": 3.4772, + "step": 1515520 + }, + { + "epoch": 0.02, + "learning_rate": 2.5180297871476182e-05, + "loss": 3.4713, + "step": 1516032 + }, + { + "epoch": 0.02, + "learning_rate": 2.5171928302769395e-05, + "loss": 3.494, + "step": 1516544 + }, + { + "epoch": 0.02, + "learning_rate": 2.5163542355258875e-05, + "loss": 3.4847, + "step": 1517056 + }, + { + "epoch": 0.02, + "learning_rate": 2.5155156407748355e-05, + "loss": 3.4779, + "step": 1517568 + }, + { + "epoch": 0.02, + "learning_rate": 2.5146770460237835e-05, + "loss": 3.4626, + "step": 1518080 + }, + { + "epoch": 0.02, + "learning_rate": 2.5138400891531044e-05, + "loss": 3.4863, + "step": 1518592 + }, + { + "epoch": 0.02, + "learning_rate": 2.5130014944020524e-05, + "loss": 3.4796, + "step": 1519104 + }, + { + "epoch": 0.02, + "learning_rate": 2.5121628996510004e-05, + "loss": 3.4832, + "step": 1519616 + }, + { + "epoch": 0.02, + "learning_rate": 2.5113243048999487e-05, + "loss": 3.4747, + "step": 1520128 + }, + { + "epoch": 0.02, + "learning_rate": 2.5104873480292696e-05, + "loss": 3.4796, + "step": 1520640 + }, + { + "epoch": 0.02, + "learning_rate": 2.5096487532782176e-05, + "loss": 3.4838, + "step": 1521152 + }, + { + "epoch": 0.02, + "learning_rate": 2.5088101585271656e-05, + "loss": 3.4836, + "step": 1521664 + }, + { + "epoch": 0.02, + "learning_rate": 2.5079715637761136e-05, + "loss": 3.4742, + "step": 1522176 + }, + { + "epoch": 0.02, + "learning_rate": 2.507134606905435e-05, + "loss": 3.4802, + "step": 1522688 + }, + { + "epoch": 0.02, + "learning_rate": 2.5062960121543828e-05, + "loss": 3.4738, + "step": 1523200 + }, + { + "epoch": 0.02, + "learning_rate": 2.5054574174033308e-05, + "loss": 3.4705, + "step": 1523712 + }, + { + "epoch": 0.02, + "learning_rate": 2.5046188226522788e-05, + "loss": 3.4831, + "step": 1524224 + }, + { + "epoch": 0.02, + "learning_rate": 2.5037818657815997e-05, + "loss": 3.4872, + "step": 1524736 + }, + { + "epoch": 0.02, + "learning_rate": 2.5029432710305477e-05, + "loss": 3.4768, + "step": 1525248 + }, + { + "epoch": 0.02, + "learning_rate": 2.5021046762794957e-05, + "loss": 3.4691, + "step": 1525760 + }, + { + "epoch": 0.02, + "learning_rate": 2.5012660815284437e-05, + "loss": 3.4756, + "step": 1526272 + }, + { + "epoch": 0.03, + "eval_loss": 3.849992036819458, + "eval_runtime": 308.4992, + "eval_samples_per_second": 1236.927, + "eval_steps_per_second": 38.655, + "step": 1526400 + }, + { + "epoch": 1.0, + "learning_rate": 2.500429124657765e-05, + "loss": 3.4745, + "step": 1526784 + }, + { + "epoch": 1.0, + "learning_rate": 2.499590529906713e-05, + "loss": 3.4765, + "step": 1527296 + }, + { + "epoch": 1.0, + "learning_rate": 2.498751935155661e-05, + "loss": 3.4828, + "step": 1527808 + }, + { + "epoch": 1.0, + "learning_rate": 2.497913340404609e-05, + "loss": 3.476, + "step": 1528320 + }, + { + "epoch": 1.0, + "learning_rate": 2.4970763835339302e-05, + "loss": 3.4891, + "step": 1528832 + }, + { + "epoch": 1.0, + "learning_rate": 2.4962377887828782e-05, + "loss": 3.4756, + "step": 1529344 + }, + { + "epoch": 1.0, + "learning_rate": 2.4953991940318262e-05, + "loss": 3.4766, + "step": 1529856 + }, + { + "epoch": 1.0, + "learning_rate": 2.4945605992807742e-05, + "loss": 3.4671, + "step": 1530368 + }, + { + "epoch": 1.0, + "learning_rate": 2.493723642410095e-05, + "loss": 3.489, + "step": 1530880 + }, + { + "epoch": 1.0, + "learning_rate": 2.492885047659043e-05, + "loss": 3.4811, + "step": 1531392 + }, + { + "epoch": 1.0, + "learning_rate": 2.492046452907991e-05, + "loss": 3.4793, + "step": 1531904 + }, + { + "epoch": 1.0, + "learning_rate": 2.491207858156939e-05, + "loss": 3.4879, + "step": 1532416 + }, + { + "epoch": 1.0, + "learning_rate": 2.4903709012862603e-05, + "loss": 3.4688, + "step": 1532928 + }, + { + "epoch": 1.0, + "learning_rate": 2.4895323065352083e-05, + "loss": 3.4756, + "step": 1533440 + }, + { + "epoch": 1.0, + "learning_rate": 2.4886937117841563e-05, + "loss": 3.4804, + "step": 1533952 + }, + { + "epoch": 1.0, + "learning_rate": 2.4878551170331043e-05, + "loss": 3.4694, + "step": 1534464 + }, + { + "epoch": 1.0, + "learning_rate": 2.4870165222820523e-05, + "loss": 3.4692, + "step": 1534976 + }, + { + "epoch": 1.0, + "learning_rate": 2.4861779275310003e-05, + "loss": 3.4646, + "step": 1535488 + }, + { + "epoch": 1.0, + "learning_rate": 2.4853393327799483e-05, + "loss": 3.4706, + "step": 1536000 + }, + { + "epoch": 1.0, + "learning_rate": 2.4845007380288963e-05, + "loss": 3.4925, + "step": 1536512 + }, + { + "epoch": 1.0, + "learning_rate": 2.4836637811582175e-05, + "loss": 3.4755, + "step": 1537024 + }, + { + "epoch": 1.0, + "learning_rate": 2.4828251864071652e-05, + "loss": 3.4751, + "step": 1537536 + }, + { + "epoch": 1.0, + "learning_rate": 2.4819865916561132e-05, + "loss": 3.4739, + "step": 1538048 + }, + { + "epoch": 1.0, + "learning_rate": 2.4811479969050612e-05, + "loss": 3.4801, + "step": 1538560 + }, + { + "epoch": 1.0, + "learning_rate": 2.4803110400343828e-05, + "loss": 3.4677, + "step": 1539072 + }, + { + "epoch": 1.0, + "learning_rate": 2.4794724452833304e-05, + "loss": 3.47, + "step": 1539584 + }, + { + "epoch": 1.0, + "learning_rate": 2.4786338505322784e-05, + "loss": 3.4661, + "step": 1540096 + }, + { + "epoch": 1.0, + "learning_rate": 2.4777968936615997e-05, + "loss": 3.4779, + "step": 1540608 + }, + { + "epoch": 1.0, + "learning_rate": 2.4769582989105473e-05, + "loss": 3.4629, + "step": 1541120 + }, + { + "epoch": 1.0, + "learning_rate": 2.4761197041594957e-05, + "loss": 3.4711, + "step": 1541632 + }, + { + "epoch": 1.01, + "learning_rate": 2.4752811094084437e-05, + "loss": 3.4737, + "step": 1542144 + }, + { + "epoch": 1.01, + "learning_rate": 2.474444152537765e-05, + "loss": 3.4778, + "step": 1542656 + }, + { + "epoch": 1.01, + "learning_rate": 2.4736055577867126e-05, + "loss": 3.4694, + "step": 1543168 + }, + { + "epoch": 1.01, + "learning_rate": 2.4727669630356606e-05, + "loss": 3.4742, + "step": 1543680 + }, + { + "epoch": 1.01, + "learning_rate": 2.4719283682846086e-05, + "loss": 3.4745, + "step": 1544192 + }, + { + "epoch": 1.01, + "learning_rate": 2.4710914114139298e-05, + "loss": 3.4773, + "step": 1544704 + }, + { + "epoch": 1.01, + "learning_rate": 2.4702528166628778e-05, + "loss": 3.4653, + "step": 1545216 + }, + { + "epoch": 1.01, + "learning_rate": 2.4694142219118258e-05, + "loss": 3.4688, + "step": 1545728 + }, + { + "epoch": 1.01, + "learning_rate": 2.4685756271607738e-05, + "loss": 3.4583, + "step": 1546240 + }, + { + "epoch": 1.01, + "learning_rate": 2.4677370324097218e-05, + "loss": 3.4707, + "step": 1546752 + }, + { + "epoch": 1.01, + "learning_rate": 2.4669000755390427e-05, + "loss": 3.4642, + "step": 1547264 + }, + { + "epoch": 1.01, + "learning_rate": 2.466061480787991e-05, + "loss": 3.4771, + "step": 1547776 + }, + { + "epoch": 1.01, + "learning_rate": 2.465222886036939e-05, + "loss": 3.4685, + "step": 1548288 + }, + { + "epoch": 1.01, + "learning_rate": 2.464384291285887e-05, + "loss": 3.4724, + "step": 1548800 + }, + { + "epoch": 1.01, + "learning_rate": 2.463547334415208e-05, + "loss": 3.4768, + "step": 1549312 + }, + { + "epoch": 1.01, + "learning_rate": 2.462708739664156e-05, + "loss": 3.474, + "step": 1549824 + }, + { + "epoch": 1.01, + "learning_rate": 2.461870144913104e-05, + "loss": 3.4749, + "step": 1550336 + }, + { + "epoch": 1.01, + "learning_rate": 2.461031550162052e-05, + "loss": 3.463, + "step": 1550848 + }, + { + "epoch": 1.01, + "learning_rate": 2.4601945932913732e-05, + "loss": 3.4588, + "step": 1551360 + }, + { + "epoch": 1.01, + "learning_rate": 2.4593559985403212e-05, + "loss": 3.4801, + "step": 1551872 + }, + { + "epoch": 1.01, + "learning_rate": 2.458517403789269e-05, + "loss": 3.4701, + "step": 1552384 + }, + { + "epoch": 1.01, + "learning_rate": 2.45768044691859e-05, + "loss": 3.4679, + "step": 1552896 + }, + { + "epoch": 1.01, + "learning_rate": 2.456841852167538e-05, + "loss": 3.4654, + "step": 1553408 + }, + { + "epoch": 1.01, + "learning_rate": 2.456003257416486e-05, + "loss": 3.4709, + "step": 1553920 + }, + { + "epoch": 1.01, + "learning_rate": 2.4551646626654344e-05, + "loss": 3.4558, + "step": 1554432 + }, + { + "epoch": 1.01, + "learning_rate": 2.4543277057947553e-05, + "loss": 3.4762, + "step": 1554944 + }, + { + "epoch": 1.01, + "learning_rate": 2.4534891110437033e-05, + "loss": 3.473, + "step": 1555456 + }, + { + "epoch": 1.01, + "learning_rate": 2.4526505162926513e-05, + "loss": 3.4737, + "step": 1555968 + }, + { + "epoch": 1.01, + "learning_rate": 2.4518119215415993e-05, + "loss": 3.4804, + "step": 1556480 + }, + { + "epoch": 1.01, + "learning_rate": 2.4509749646709205e-05, + "loss": 3.4639, + "step": 1556992 + }, + { + "epoch": 1.01, + "learning_rate": 2.4501363699198685e-05, + "loss": 3.4626, + "step": 1557504 + }, + { + "epoch": 1.01, + "learning_rate": 2.4492977751688165e-05, + "loss": 3.4759, + "step": 1558016 + }, + { + "epoch": 1.01, + "learning_rate": 2.4484591804177645e-05, + "loss": 3.454, + "step": 1558528 + }, + { + "epoch": 1.01, + "learning_rate": 2.4476222235470854e-05, + "loss": 3.4589, + "step": 1559040 + }, + { + "epoch": 1.01, + "learning_rate": 2.4467836287960334e-05, + "loss": 3.4677, + "step": 1559552 + }, + { + "epoch": 1.01, + "learning_rate": 2.4459450340449814e-05, + "loss": 3.4695, + "step": 1560064 + }, + { + "epoch": 1.01, + "learning_rate": 2.4451064392939298e-05, + "loss": 3.4583, + "step": 1560576 + }, + { + "epoch": 1.01, + "learning_rate": 2.4442694824232507e-05, + "loss": 3.456, + "step": 1561088 + }, + { + "epoch": 1.01, + "learning_rate": 2.4434308876721987e-05, + "loss": 3.4675, + "step": 1561600 + }, + { + "epoch": 1.01, + "learning_rate": 2.4425922929211467e-05, + "loss": 3.4727, + "step": 1562112 + }, + { + "epoch": 1.01, + "learning_rate": 2.4417536981700947e-05, + "loss": 3.4689, + "step": 1562624 + }, + { + "epoch": 1.01, + "learning_rate": 2.440916741299416e-05, + "loss": 3.4703, + "step": 1563136 + }, + { + "epoch": 1.01, + "learning_rate": 2.440078146548364e-05, + "loss": 3.4827, + "step": 1563648 + }, + { + "epoch": 1.01, + "learning_rate": 2.439239551797312e-05, + "loss": 3.4746, + "step": 1564160 + }, + { + "epoch": 1.01, + "learning_rate": 2.43840095704626e-05, + "loss": 3.4883, + "step": 1564672 + }, + { + "epoch": 1.01, + "learning_rate": 2.4375640001755808e-05, + "loss": 3.4582, + "step": 1565184 + }, + { + "epoch": 1.01, + "learning_rate": 2.4367254054245288e-05, + "loss": 3.4747, + "step": 1565696 + }, + { + "epoch": 1.01, + "learning_rate": 2.4358868106734768e-05, + "loss": 3.4751, + "step": 1566208 + }, + { + "epoch": 1.01, + "learning_rate": 2.435048215922425e-05, + "loss": 3.4624, + "step": 1566720 + }, + { + "epoch": 1.01, + "learning_rate": 2.434211259051746e-05, + "loss": 3.4808, + "step": 1567232 + }, + { + "epoch": 1.01, + "learning_rate": 2.433372664300694e-05, + "loss": 3.4664, + "step": 1567744 + }, + { + "epoch": 1.01, + "learning_rate": 2.432534069549642e-05, + "loss": 3.4799, + "step": 1568256 + }, + { + "epoch": 1.01, + "learning_rate": 2.4316954747985897e-05, + "loss": 3.4781, + "step": 1568768 + }, + { + "epoch": 1.01, + "learning_rate": 2.430856880047538e-05, + "loss": 3.4518, + "step": 1569280 + }, + { + "epoch": 1.01, + "learning_rate": 2.4300199231768593e-05, + "loss": 3.462, + "step": 1569792 + }, + { + "epoch": 1.01, + "learning_rate": 2.4291813284258073e-05, + "loss": 3.463, + "step": 1570304 + }, + { + "epoch": 1.01, + "learning_rate": 2.428342733674755e-05, + "loss": 3.4709, + "step": 1570816 + }, + { + "epoch": 1.01, + "learning_rate": 2.427504138923703e-05, + "loss": 3.4732, + "step": 1571328 + }, + { + "epoch": 1.01, + "learning_rate": 2.4266671820530242e-05, + "loss": 3.4651, + "step": 1571840 + }, + { + "epoch": 1.02, + "learning_rate": 2.425828587301972e-05, + "loss": 3.4686, + "step": 1572352 + }, + { + "epoch": 1.02, + "learning_rate": 2.42498999255092e-05, + "loss": 3.4639, + "step": 1572864 + }, + { + "epoch": 1.02, + "learning_rate": 2.4241530356802414e-05, + "loss": 3.4654, + "step": 1573376 + }, + { + "epoch": 1.02, + "learning_rate": 2.4233144409291894e-05, + "loss": 3.4642, + "step": 1573888 + }, + { + "epoch": 1.02, + "learning_rate": 2.422475846178137e-05, + "loss": 3.4766, + "step": 1574400 + }, + { + "epoch": 1.02, + "learning_rate": 2.421637251427085e-05, + "loss": 3.4791, + "step": 1574912 + }, + { + "epoch": 1.02, + "learning_rate": 2.4207986566760334e-05, + "loss": 3.4713, + "step": 1575424 + }, + { + "epoch": 1.02, + "learning_rate": 2.4199616998053546e-05, + "loss": 3.4605, + "step": 1575936 + }, + { + "epoch": 1.02, + "learning_rate": 2.4191231050543023e-05, + "loss": 3.47, + "step": 1576448 + }, + { + "epoch": 1.02, + "learning_rate": 2.4182845103032503e-05, + "loss": 3.4681, + "step": 1576960 + }, + { + "epoch": 1.02, + "learning_rate": 2.4174459155521983e-05, + "loss": 3.4772, + "step": 1577472 + }, + { + "epoch": 1.02, + "learning_rate": 2.4166089586815195e-05, + "loss": 3.4698, + "step": 1577984 + }, + { + "epoch": 1.02, + "learning_rate": 2.4157703639304675e-05, + "loss": 3.4654, + "step": 1578496 + }, + { + "epoch": 1.02, + "learning_rate": 2.4149317691794155e-05, + "loss": 3.4579, + "step": 1579008 + }, + { + "epoch": 1.02, + "learning_rate": 2.4140931744283635e-05, + "loss": 3.4718, + "step": 1579520 + }, + { + "epoch": 1.02, + "learning_rate": 2.4132562175576844e-05, + "loss": 3.4601, + "step": 1580032 + }, + { + "epoch": 1.02, + "learning_rate": 2.4124176228066324e-05, + "loss": 3.4562, + "step": 1580544 + }, + { + "epoch": 1.02, + "learning_rate": 2.4115790280555804e-05, + "loss": 3.454, + "step": 1581056 + }, + { + "epoch": 1.02, + "learning_rate": 2.4107404333045284e-05, + "loss": 3.4686, + "step": 1581568 + }, + { + "epoch": 1.02, + "learning_rate": 2.4099034764338497e-05, + "loss": 3.4547, + "step": 1582080 + }, + { + "epoch": 1.02, + "learning_rate": 2.4090648816827977e-05, + "loss": 3.4778, + "step": 1582592 + }, + { + "epoch": 1.02, + "learning_rate": 2.4082262869317457e-05, + "loss": 3.4582, + "step": 1583104 + }, + { + "epoch": 1.02, + "learning_rate": 2.4073876921806937e-05, + "loss": 3.4704, + "step": 1583616 + }, + { + "epoch": 1.02, + "learning_rate": 2.406550735310015e-05, + "loss": 3.4664, + "step": 1584128 + }, + { + "epoch": 1.02, + "learning_rate": 2.405712140558963e-05, + "loss": 3.4587, + "step": 1584640 + }, + { + "epoch": 1.02, + "learning_rate": 2.404873545807911e-05, + "loss": 3.4806, + "step": 1585152 + }, + { + "epoch": 1.02, + "learning_rate": 2.404034951056859e-05, + "loss": 3.48, + "step": 1585664 + }, + { + "epoch": 1.02, + "learning_rate": 2.4031979941861798e-05, + "loss": 3.4648, + "step": 1586176 + }, + { + "epoch": 1.02, + "learning_rate": 2.4023593994351278e-05, + "loss": 3.4695, + "step": 1586688 + }, + { + "epoch": 1.02, + "learning_rate": 2.4015208046840758e-05, + "loss": 3.4629, + "step": 1587200 + }, + { + "epoch": 1.02, + "learning_rate": 2.400683847813397e-05, + "loss": 3.4697, + "step": 1587712 + }, + { + "epoch": 1.02, + "learning_rate": 2.399845253062345e-05, + "loss": 3.454, + "step": 1588224 + }, + { + "epoch": 1.02, + "learning_rate": 2.399006658311293e-05, + "loss": 3.474, + "step": 1588736 + }, + { + "epoch": 1.02, + "learning_rate": 2.398168063560241e-05, + "loss": 3.466, + "step": 1589248 + }, + { + "epoch": 1.02, + "learning_rate": 2.397331106689562e-05, + "loss": 3.4666, + "step": 1589760 + }, + { + "epoch": 1.02, + "learning_rate": 2.39649251193851e-05, + "loss": 3.4615, + "step": 1590272 + }, + { + "epoch": 1.02, + "learning_rate": 2.3956539171874583e-05, + "loss": 3.4646, + "step": 1590784 + }, + { + "epoch": 1.02, + "learning_rate": 2.3948153224364063e-05, + "loss": 3.4567, + "step": 1591296 + }, + { + "epoch": 1.02, + "learning_rate": 2.3939783655657272e-05, + "loss": 3.4659, + "step": 1591808 + }, + { + "epoch": 1.02, + "learning_rate": 2.393139770814675e-05, + "loss": 3.4613, + "step": 1592320 + }, + { + "epoch": 1.02, + "learning_rate": 2.392301176063623e-05, + "loss": 3.4774, + "step": 1592832 + }, + { + "epoch": 1.02, + "learning_rate": 2.391462581312571e-05, + "loss": 3.4735, + "step": 1593344 + }, + { + "epoch": 1.02, + "learning_rate": 2.3906256244418924e-05, + "loss": 3.4693, + "step": 1593856 + }, + { + "epoch": 1.02, + "learning_rate": 2.3897870296908404e-05, + "loss": 3.451, + "step": 1594368 + }, + { + "epoch": 1.02, + "learning_rate": 2.3889484349397884e-05, + "loss": 3.475, + "step": 1594880 + }, + { + "epoch": 1.02, + "learning_rate": 2.3881098401887364e-05, + "loss": 3.4688, + "step": 1595392 + }, + { + "epoch": 1.02, + "learning_rate": 2.3872728833180573e-05, + "loss": 3.4721, + "step": 1595904 + }, + { + "epoch": 1.02, + "learning_rate": 2.3864342885670053e-05, + "loss": 3.4627, + "step": 1596416 + }, + { + "epoch": 1.02, + "learning_rate": 2.3855956938159536e-05, + "loss": 3.4698, + "step": 1596928 + }, + { + "epoch": 1.02, + "learning_rate": 2.3847570990649016e-05, + "loss": 3.4708, + "step": 1597440 + }, + { + "epoch": 1.02, + "learning_rate": 2.3839201421942225e-05, + "loss": 3.4775, + "step": 1597952 + }, + { + "epoch": 1.02, + "learning_rate": 2.3830815474431705e-05, + "loss": 3.4597, + "step": 1598464 + }, + { + "epoch": 1.02, + "learning_rate": 2.3822429526921185e-05, + "loss": 3.4709, + "step": 1598976 + }, + { + "epoch": 1.02, + "learning_rate": 2.3814043579410665e-05, + "loss": 3.4599, + "step": 1599488 + }, + { + "epoch": 1.02, + "learning_rate": 2.3805674010703878e-05, + "loss": 3.4608, + "step": 1600000 + }, + { + "epoch": 1.02, + "learning_rate": 2.3797288063193358e-05, + "loss": 3.4739, + "step": 1600512 + }, + { + "epoch": 1.02, + "learning_rate": 2.3788902115682838e-05, + "loss": 3.4705, + "step": 1601024 + }, + { + "epoch": 1.02, + "learning_rate": 2.3780516168172318e-05, + "loss": 3.4675, + "step": 1601536 + }, + { + "epoch": 1.02, + "learning_rate": 2.3772146599465527e-05, + "loss": 3.4572, + "step": 1602048 + }, + { + "epoch": 1.02, + "learning_rate": 2.3763760651955007e-05, + "loss": 3.4629, + "step": 1602560 + }, + { + "epoch": 1.03, + "eval_loss": 3.8509905338287354, + "eval_runtime": 308.1843, + "eval_samples_per_second": 1238.191, + "eval_steps_per_second": 38.694, + "step": 1602720 + }, + { + "epoch": 0.0, + "learning_rate": 2.375537470444449e-05, + "loss": 3.4622, + "step": 1603072 + }, + { + "epoch": 0.0, + "learning_rate": 2.374698875693397e-05, + "loss": 3.4617, + "step": 1603584 + }, + { + "epoch": 0.0, + "learning_rate": 2.3738602809423447e-05, + "loss": 3.4731, + "step": 1604096 + }, + { + "epoch": 0.0, + "learning_rate": 2.3730216861912926e-05, + "loss": 3.4675, + "step": 1604608 + }, + { + "epoch": 0.0, + "learning_rate": 2.372184729320614e-05, + "loss": 3.4725, + "step": 1605120 + }, + { + "epoch": 0.0, + "learning_rate": 2.371346134569562e-05, + "loss": 3.4683, + "step": 1605632 + }, + { + "epoch": 0.0, + "learning_rate": 2.37050753981851e-05, + "loss": 3.4622, + "step": 1606144 + }, + { + "epoch": 0.0, + "learning_rate": 2.369668945067458e-05, + "loss": 3.4551, + "step": 1606656 + }, + { + "epoch": 0.0, + "learning_rate": 2.368831988196779e-05, + "loss": 3.4713, + "step": 1607168 + }, + { + "epoch": 0.0, + "learning_rate": 2.3679933934457268e-05, + "loss": 3.4734, + "step": 1607680 + }, + { + "epoch": 0.0, + "learning_rate": 2.3671547986946748e-05, + "loss": 3.4669, + "step": 1608192 + }, + { + "epoch": 0.0, + "learning_rate": 2.3663162039436228e-05, + "loss": 3.4762, + "step": 1608704 + }, + { + "epoch": 0.0, + "learning_rate": 2.3654808849533173e-05, + "loss": 3.4561, + "step": 1609216 + }, + { + "epoch": 0.0, + "learning_rate": 2.3646422902022653e-05, + "loss": 3.4632, + "step": 1609728 + }, + { + "epoch": 0.0, + "learning_rate": 2.3638036954512133e-05, + "loss": 3.4715, + "step": 1610240 + }, + { + "epoch": 0.0, + "learning_rate": 2.3629651007001613e-05, + "loss": 3.4578, + "step": 1610752 + }, + { + "epoch": 0.0, + "learning_rate": 2.3621265059491093e-05, + "loss": 3.4582, + "step": 1611264 + }, + { + "epoch": 0.0, + "learning_rate": 2.361287911198057e-05, + "loss": 3.4556, + "step": 1611776 + }, + { + "epoch": 0.0, + "learning_rate": 2.3604493164470053e-05, + "loss": 3.4573, + "step": 1612288 + }, + { + "epoch": 0.0, + "learning_rate": 2.3596107216959533e-05, + "loss": 3.4802, + "step": 1612800 + }, + { + "epoch": 0.0, + "learning_rate": 2.358773764825274e-05, + "loss": 3.4663, + "step": 1613312 + }, + { + "epoch": 0.0, + "learning_rate": 2.3579368079545954e-05, + "loss": 3.4681, + "step": 1613824 + }, + { + "epoch": 0.0, + "learning_rate": 2.3570982132035434e-05, + "loss": 3.4592, + "step": 1614336 + }, + { + "epoch": 0.0, + "learning_rate": 2.3562596184524914e-05, + "loss": 3.4704, + "step": 1614848 + }, + { + "epoch": 0.0, + "learning_rate": 2.3554210237014394e-05, + "loss": 3.4552, + "step": 1615360 + }, + { + "epoch": 0.0, + "learning_rate": 2.3545824289503874e-05, + "loss": 3.4587, + "step": 1615872 + }, + { + "epoch": 0.0, + "learning_rate": 2.3537438341993354e-05, + "loss": 3.4574, + "step": 1616384 + }, + { + "epoch": 0.0, + "learning_rate": 2.3529052394482834e-05, + "loss": 3.463, + "step": 1616896 + }, + { + "epoch": 0.0, + "learning_rate": 2.3520666446972314e-05, + "loss": 3.4518, + "step": 1617408 + }, + { + "epoch": 0.0, + "learning_rate": 2.3512296878265523e-05, + "loss": 3.46, + "step": 1617920 + }, + { + "epoch": 0.01, + "learning_rate": 2.3503910930755006e-05, + "loss": 3.4653, + "step": 1618432 + }, + { + "epoch": 0.01, + "learning_rate": 2.3495524983244486e-05, + "loss": 3.4666, + "step": 1618944 + }, + { + "epoch": 0.01, + "learning_rate": 2.3487139035733966e-05, + "loss": 3.4603, + "step": 1619456 + }, + { + "epoch": 0.01, + "learning_rate": 2.3478769467027175e-05, + "loss": 3.4614, + "step": 1619968 + }, + { + "epoch": 0.01, + "learning_rate": 2.3470383519516655e-05, + "loss": 3.463, + "step": 1620480 + }, + { + "epoch": 0.01, + "learning_rate": 2.3461997572006135e-05, + "loss": 3.4603, + "step": 1620992 + }, + { + "epoch": 0.01, + "learning_rate": 2.3453611624495615e-05, + "loss": 3.4571, + "step": 1621504 + }, + { + "epoch": 0.01, + "learning_rate": 2.3445242055788828e-05, + "loss": 3.4562, + "step": 1622016 + }, + { + "epoch": 0.01, + "learning_rate": 2.3436856108278308e-05, + "loss": 3.4497, + "step": 1622528 + }, + { + "epoch": 0.01, + "learning_rate": 2.3428470160767787e-05, + "loss": 3.4569, + "step": 1623040 + }, + { + "epoch": 0.01, + "learning_rate": 2.3420084213257267e-05, + "loss": 3.4549, + "step": 1623552 + }, + { + "epoch": 0.01, + "learning_rate": 2.3411714644550477e-05, + "loss": 3.4664, + "step": 1624064 + }, + { + "epoch": 0.01, + "learning_rate": 2.340332869703996e-05, + "loss": 3.4566, + "step": 1624576 + }, + { + "epoch": 0.01, + "learning_rate": 2.339494274952944e-05, + "loss": 3.4578, + "step": 1625088 + }, + { + "epoch": 0.01, + "learning_rate": 2.338655680201892e-05, + "loss": 3.4687, + "step": 1625600 + }, + { + "epoch": 0.01, + "learning_rate": 2.337818723331213e-05, + "loss": 3.4623, + "step": 1626112 + }, + { + "epoch": 0.01, + "learning_rate": 2.336980128580161e-05, + "loss": 3.463, + "step": 1626624 + }, + { + "epoch": 0.01, + "learning_rate": 2.336141533829109e-05, + "loss": 3.4492, + "step": 1627136 + }, + { + "epoch": 0.01, + "learning_rate": 2.335302939078057e-05, + "loss": 3.4481, + "step": 1627648 + }, + { + "epoch": 0.01, + "learning_rate": 2.334465982207378e-05, + "loss": 3.4713, + "step": 1628160 + }, + { + "epoch": 0.01, + "learning_rate": 2.333627387456326e-05, + "loss": 3.4595, + "step": 1628672 + }, + { + "epoch": 0.01, + "learning_rate": 2.332788792705274e-05, + "loss": 3.4555, + "step": 1629184 + }, + { + "epoch": 0.01, + "learning_rate": 2.331950197954222e-05, + "loss": 3.4535, + "step": 1629696 + }, + { + "epoch": 0.01, + "learning_rate": 2.331113241083543e-05, + "loss": 3.4596, + "step": 1630208 + }, + { + "epoch": 0.01, + "learning_rate": 2.3302746463324914e-05, + "loss": 3.4421, + "step": 1630720 + }, + { + "epoch": 0.01, + "learning_rate": 2.3294360515814394e-05, + "loss": 3.4639, + "step": 1631232 + }, + { + "epoch": 0.01, + "learning_rate": 2.328597456830387e-05, + "loss": 3.4601, + "step": 1631744 + }, + { + "epoch": 0.01, + "learning_rate": 2.3277604999597083e-05, + "loss": 3.4579, + "step": 1632256 + }, + { + "epoch": 0.01, + "learning_rate": 2.3269219052086563e-05, + "loss": 3.4733, + "step": 1632768 + }, + { + "epoch": 0.01, + "learning_rate": 2.3260833104576042e-05, + "loss": 3.4487, + "step": 1633280 + }, + { + "epoch": 0.01, + "learning_rate": 2.3252447157065522e-05, + "loss": 3.4521, + "step": 1633792 + }, + { + "epoch": 0.01, + "learning_rate": 2.3244077588358735e-05, + "loss": 3.4654, + "step": 1634304 + }, + { + "epoch": 0.01, + "learning_rate": 2.3235691640848215e-05, + "loss": 3.4458, + "step": 1634816 + }, + { + "epoch": 0.01, + "learning_rate": 2.322730569333769e-05, + "loss": 3.4487, + "step": 1635328 + }, + { + "epoch": 0.01, + "learning_rate": 2.321891974582717e-05, + "loss": 3.4542, + "step": 1635840 + }, + { + "epoch": 0.01, + "learning_rate": 2.3210550177120384e-05, + "loss": 3.4573, + "step": 1636352 + }, + { + "epoch": 0.01, + "learning_rate": 2.3202164229609867e-05, + "loss": 3.4502, + "step": 1636864 + }, + { + "epoch": 0.01, + "learning_rate": 2.3193778282099344e-05, + "loss": 3.4462, + "step": 1637376 + }, + { + "epoch": 0.01, + "learning_rate": 2.3185392334588824e-05, + "loss": 3.4518, + "step": 1637888 + }, + { + "epoch": 0.01, + "learning_rate": 2.3177022765882036e-05, + "loss": 3.4601, + "step": 1638400 + }, + { + "epoch": 0.01, + "learning_rate": 2.3168636818371516e-05, + "loss": 3.4578, + "step": 1638912 + }, + { + "epoch": 0.01, + "learning_rate": 2.3160250870860993e-05, + "loss": 3.4608, + "step": 1639424 + }, + { + "epoch": 0.01, + "learning_rate": 2.3151864923350476e-05, + "loss": 3.4673, + "step": 1639936 + }, + { + "epoch": 0.01, + "learning_rate": 2.314349535464369e-05, + "loss": 3.4647, + "step": 1640448 + }, + { + "epoch": 0.01, + "learning_rate": 2.3135109407133165e-05, + "loss": 3.4775, + "step": 1640960 + }, + { + "epoch": 0.01, + "learning_rate": 2.3126723459622645e-05, + "loss": 3.445, + "step": 1641472 + }, + { + "epoch": 0.01, + "learning_rate": 2.3118337512112125e-05, + "loss": 3.4682, + "step": 1641984 + }, + { + "epoch": 0.01, + "learning_rate": 2.3109967943405338e-05, + "loss": 3.4645, + "step": 1642496 + }, + { + "epoch": 0.01, + "learning_rate": 2.3101581995894818e-05, + "loss": 3.4457, + "step": 1643008 + }, + { + "epoch": 0.01, + "learning_rate": 2.3093196048384297e-05, + "loss": 3.4712, + "step": 1643520 + }, + { + "epoch": 0.01, + "learning_rate": 2.3084810100873777e-05, + "loss": 3.4542, + "step": 1644032 + }, + { + "epoch": 0.01, + "learning_rate": 2.307644053216699e-05, + "loss": 3.4674, + "step": 1644544 + }, + { + "epoch": 0.01, + "learning_rate": 2.3068054584656466e-05, + "loss": 3.4673, + "step": 1645056 + }, + { + "epoch": 0.01, + "learning_rate": 2.3059668637145946e-05, + "loss": 3.4448, + "step": 1645568 + }, + { + "epoch": 0.01, + "learning_rate": 2.305128268963543e-05, + "loss": 3.4492, + "step": 1646080 + }, + { + "epoch": 0.01, + "learning_rate": 2.304291312092864e-05, + "loss": 3.4523, + "step": 1646592 + }, + { + "epoch": 0.01, + "learning_rate": 2.303452717341812e-05, + "loss": 3.4606, + "step": 1647104 + }, + { + "epoch": 0.01, + "learning_rate": 2.30261412259076e-05, + "loss": 3.4613, + "step": 1647616 + }, + { + "epoch": 0.01, + "learning_rate": 2.301775527839708e-05, + "loss": 3.4585, + "step": 1648128 + }, + { + "epoch": 0.02, + "learning_rate": 2.300938570969029e-05, + "loss": 3.4536, + "step": 1648640 + }, + { + "epoch": 0.02, + "learning_rate": 2.300099976217977e-05, + "loss": 3.4543, + "step": 1649152 + }, + { + "epoch": 0.02, + "learning_rate": 2.299261381466925e-05, + "loss": 3.456, + "step": 1649664 + }, + { + "epoch": 0.02, + "learning_rate": 2.298422786715873e-05, + "loss": 3.4501, + "step": 1650176 + }, + { + "epoch": 0.02, + "learning_rate": 2.297585829845194e-05, + "loss": 3.4693, + "step": 1650688 + }, + { + "epoch": 0.02, + "learning_rate": 2.296747235094142e-05, + "loss": 3.4646, + "step": 1651200 + }, + { + "epoch": 0.02, + "learning_rate": 2.29590864034309e-05, + "loss": 3.4641, + "step": 1651712 + }, + { + "epoch": 0.02, + "learning_rate": 2.2950716834724113e-05, + "loss": 3.4491, + "step": 1652224 + }, + { + "epoch": 0.02, + "learning_rate": 2.2942330887213593e-05, + "loss": 3.4598, + "step": 1652736 + }, + { + "epoch": 0.02, + "learning_rate": 2.2933944939703072e-05, + "loss": 3.4535, + "step": 1653248 + }, + { + "epoch": 0.02, + "learning_rate": 2.2925558992192552e-05, + "loss": 3.4624, + "step": 1653760 + }, + { + "epoch": 0.02, + "learning_rate": 2.2917173044682032e-05, + "loss": 3.4604, + "step": 1654272 + }, + { + "epoch": 0.02, + "learning_rate": 2.2908803475975245e-05, + "loss": 3.4565, + "step": 1654784 + }, + { + "epoch": 0.02, + "learning_rate": 2.2900417528464725e-05, + "loss": 3.4464, + "step": 1655296 + }, + { + "epoch": 0.02, + "learning_rate": 2.2892031580954205e-05, + "loss": 3.4599, + "step": 1655808 + }, + { + "epoch": 0.02, + "learning_rate": 2.2883645633443685e-05, + "loss": 3.451, + "step": 1656320 + }, + { + "epoch": 0.02, + "learning_rate": 2.2875276064736894e-05, + "loss": 3.4436, + "step": 1656832 + }, + { + "epoch": 0.02, + "learning_rate": 2.2866890117226374e-05, + "loss": 3.4389, + "step": 1657344 + }, + { + "epoch": 0.02, + "learning_rate": 2.2858504169715854e-05, + "loss": 3.4572, + "step": 1657856 + }, + { + "epoch": 0.02, + "learning_rate": 2.2850118222205337e-05, + "loss": 3.4498, + "step": 1658368 + }, + { + "epoch": 0.02, + "learning_rate": 2.2841748653498546e-05, + "loss": 3.4632, + "step": 1658880 + }, + { + "epoch": 0.02, + "learning_rate": 2.2833362705988026e-05, + "loss": 3.4473, + "step": 1659392 + }, + { + "epoch": 0.02, + "learning_rate": 2.2824976758477506e-05, + "loss": 3.4598, + "step": 1659904 + }, + { + "epoch": 0.02, + "learning_rate": 2.2816590810966986e-05, + "loss": 3.4564, + "step": 1660416 + }, + { + "epoch": 0.02, + "learning_rate": 2.28082212422602e-05, + "loss": 3.4477, + "step": 1660928 + }, + { + "epoch": 0.02, + "learning_rate": 2.279983529474968e-05, + "loss": 3.4681, + "step": 1661440 + }, + { + "epoch": 0.02, + "learning_rate": 2.279144934723916e-05, + "loss": 3.466, + "step": 1661952 + }, + { + "epoch": 0.02, + "learning_rate": 2.278306339972864e-05, + "loss": 3.4537, + "step": 1662464 + }, + { + "epoch": 0.02, + "learning_rate": 2.2774693831021848e-05, + "loss": 3.4574, + "step": 1662976 + }, + { + "epoch": 0.02, + "learning_rate": 2.2766307883511327e-05, + "loss": 3.4537, + "step": 1663488 + }, + { + "epoch": 0.02, + "learning_rate": 2.2757921936000807e-05, + "loss": 3.4606, + "step": 1664000 + }, + { + "epoch": 0.02, + "learning_rate": 2.274953598849029e-05, + "loss": 3.439, + "step": 1664512 + }, + { + "epoch": 0.02, + "learning_rate": 2.27411664197835e-05, + "loss": 3.4648, + "step": 1665024 + }, + { + "epoch": 0.02, + "learning_rate": 2.273278047227298e-05, + "loss": 3.4514, + "step": 1665536 + }, + { + "epoch": 0.02, + "learning_rate": 2.272439452476246e-05, + "loss": 3.4545, + "step": 1666048 + }, + { + "epoch": 0.02, + "learning_rate": 2.271600857725194e-05, + "loss": 3.4528, + "step": 1666560 + }, + { + "epoch": 0.02, + "learning_rate": 2.2707639008545152e-05, + "loss": 3.4517, + "step": 1667072 + }, + { + "epoch": 0.02, + "learning_rate": 2.2699253061034632e-05, + "loss": 3.4512, + "step": 1667584 + }, + { + "epoch": 0.02, + "learning_rate": 2.2690867113524112e-05, + "loss": 3.4542, + "step": 1668096 + }, + { + "epoch": 0.02, + "learning_rate": 2.2682481166013592e-05, + "loss": 3.4537, + "step": 1668608 + }, + { + "epoch": 0.02, + "learning_rate": 2.26741115973068e-05, + "loss": 3.4647, + "step": 1669120 + }, + { + "epoch": 0.02, + "learning_rate": 2.266572564979628e-05, + "loss": 3.458, + "step": 1669632 + }, + { + "epoch": 0.02, + "learning_rate": 2.265733970228576e-05, + "loss": 3.4617, + "step": 1670144 + }, + { + "epoch": 0.02, + "learning_rate": 2.2648970133578974e-05, + "loss": 3.4389, + "step": 1670656 + }, + { + "epoch": 0.02, + "learning_rate": 2.2640584186068454e-05, + "loss": 3.4663, + "step": 1671168 + }, + { + "epoch": 0.02, + "learning_rate": 2.2632198238557933e-05, + "loss": 3.4562, + "step": 1671680 + }, + { + "epoch": 0.02, + "learning_rate": 2.2623812291047413e-05, + "loss": 3.4597, + "step": 1672192 + }, + { + "epoch": 0.02, + "learning_rate": 2.261542634353689e-05, + "loss": 3.454, + "step": 1672704 + }, + { + "epoch": 0.02, + "learning_rate": 2.2607056774830106e-05, + "loss": 3.4564, + "step": 1673216 + }, + { + "epoch": 0.02, + "learning_rate": 2.2598670827319586e-05, + "loss": 3.4611, + "step": 1673728 + }, + { + "epoch": 0.02, + "learning_rate": 2.2590284879809062e-05, + "loss": 3.4634, + "step": 1674240 + }, + { + "epoch": 0.02, + "learning_rate": 2.2581898932298542e-05, + "loss": 3.4488, + "step": 1674752 + }, + { + "epoch": 0.02, + "learning_rate": 2.2573529363591755e-05, + "loss": 3.4561, + "step": 1675264 + }, + { + "epoch": 0.02, + "learning_rate": 2.2565143416081235e-05, + "loss": 3.4543, + "step": 1675776 + }, + { + "epoch": 0.02, + "learning_rate": 2.2556757468570715e-05, + "loss": 3.4495, + "step": 1676288 + }, + { + "epoch": 0.02, + "learning_rate": 2.2548371521060195e-05, + "loss": 3.4619, + "step": 1676800 + }, + { + "epoch": 0.02, + "learning_rate": 2.2540001952353407e-05, + "loss": 3.4593, + "step": 1677312 + }, + { + "epoch": 0.02, + "learning_rate": 2.2531616004842887e-05, + "loss": 3.4605, + "step": 1677824 + }, + { + "epoch": 0.02, + "learning_rate": 2.2523230057332364e-05, + "loss": 3.4416, + "step": 1678336 + }, + { + "epoch": 0.02, + "learning_rate": 2.2514860488625576e-05, + "loss": 3.4559, + "step": 1678848 + }, + { + "epoch": 0.03, + "eval_loss": 3.8535525798797607, + "eval_runtime": 302.5146, + "eval_samples_per_second": 1261.397, + "eval_steps_per_second": 39.42, + "step": 1679040 + }, + { + "epoch": 1.0, + "learning_rate": 2.250647454111506e-05, + "loss": 3.4564, + "step": 1679360 + }, + { + "epoch": 1.0, + "learning_rate": 2.2498088593604536e-05, + "loss": 3.4502, + "step": 1679872 + }, + { + "epoch": 1.0, + "learning_rate": 2.2489702646094016e-05, + "loss": 3.4612, + "step": 1680384 + }, + { + "epoch": 1.0, + "learning_rate": 2.2481316698583496e-05, + "loss": 3.4594, + "step": 1680896 + }, + { + "epoch": 1.0, + "learning_rate": 2.247294712987671e-05, + "loss": 3.462, + "step": 1681408 + }, + { + "epoch": 1.0, + "learning_rate": 2.2464561182366185e-05, + "loss": 3.4551, + "step": 1681920 + }, + { + "epoch": 1.0, + "learning_rate": 2.245617523485567e-05, + "loss": 3.4471, + "step": 1682432 + }, + { + "epoch": 1.0, + "learning_rate": 2.244780566614888e-05, + "loss": 3.4492, + "step": 1682944 + }, + { + "epoch": 1.0, + "learning_rate": 2.243941971863836e-05, + "loss": 3.4591, + "step": 1683456 + }, + { + "epoch": 1.0, + "learning_rate": 2.2431033771127837e-05, + "loss": 3.465, + "step": 1683968 + }, + { + "epoch": 1.0, + "learning_rate": 2.2422647823617317e-05, + "loss": 3.4566, + "step": 1684480 + }, + { + "epoch": 1.0, + "learning_rate": 2.241427825491053e-05, + "loss": 3.4641, + "step": 1684992 + }, + { + "epoch": 1.0, + "learning_rate": 2.2405908686203742e-05, + "loss": 3.4479, + "step": 1685504 + }, + { + "epoch": 1.0, + "learning_rate": 2.2397522738693222e-05, + "loss": 3.4462, + "step": 1686016 + }, + { + "epoch": 1.0, + "learning_rate": 2.2389136791182702e-05, + "loss": 3.4624, + "step": 1686528 + }, + { + "epoch": 1.0, + "learning_rate": 2.2380750843672182e-05, + "loss": 3.4474, + "step": 1687040 + }, + { + "epoch": 1.0, + "learning_rate": 2.237236489616166e-05, + "loss": 3.447, + "step": 1687552 + }, + { + "epoch": 1.0, + "learning_rate": 2.236397894865114e-05, + "loss": 3.4434, + "step": 1688064 + }, + { + "epoch": 1.0, + "learning_rate": 2.2355593001140622e-05, + "loss": 3.4502, + "step": 1688576 + }, + { + "epoch": 1.0, + "learning_rate": 2.2347207053630102e-05, + "loss": 3.463, + "step": 1689088 + }, + { + "epoch": 1.0, + "learning_rate": 2.233883748492331e-05, + "loss": 3.4564, + "step": 1689600 + }, + { + "epoch": 1.0, + "learning_rate": 2.2330467916216524e-05, + "loss": 3.4582, + "step": 1690112 + }, + { + "epoch": 1.0, + "learning_rate": 2.2322081968706004e-05, + "loss": 3.446, + "step": 1690624 + }, + { + "epoch": 1.0, + "learning_rate": 2.2313696021195484e-05, + "loss": 3.4593, + "step": 1691136 + }, + { + "epoch": 1.0, + "learning_rate": 2.2305310073684963e-05, + "loss": 3.4462, + "step": 1691648 + }, + { + "epoch": 1.0, + "learning_rate": 2.2296924126174443e-05, + "loss": 3.4492, + "step": 1692160 + }, + { + "epoch": 1.0, + "learning_rate": 2.2288538178663923e-05, + "loss": 3.4431, + "step": 1692672 + }, + { + "epoch": 1.0, + "learning_rate": 2.2280152231153403e-05, + "loss": 3.4481, + "step": 1693184 + }, + { + "epoch": 1.0, + "learning_rate": 2.2271766283642883e-05, + "loss": 3.4479, + "step": 1693696 + }, + { + "epoch": 1.0, + "learning_rate": 2.2263396714936092e-05, + "loss": 3.4441, + "step": 1694208 + }, + { + "epoch": 1.01, + "learning_rate": 2.2255010767425576e-05, + "loss": 3.454, + "step": 1694720 + }, + { + "epoch": 1.01, + "learning_rate": 2.2246624819915056e-05, + "loss": 3.4532, + "step": 1695232 + }, + { + "epoch": 1.01, + "learning_rate": 2.2238238872404536e-05, + "loss": 3.4499, + "step": 1695744 + }, + { + "epoch": 1.01, + "learning_rate": 2.2229869303697745e-05, + "loss": 3.4529, + "step": 1696256 + }, + { + "epoch": 1.01, + "learning_rate": 2.2221483356187225e-05, + "loss": 3.4503, + "step": 1696768 + }, + { + "epoch": 1.01, + "learning_rate": 2.2213097408676705e-05, + "loss": 3.4497, + "step": 1697280 + }, + { + "epoch": 1.01, + "learning_rate": 2.2204711461166185e-05, + "loss": 3.4493, + "step": 1697792 + }, + { + "epoch": 1.01, + "learning_rate": 2.2196341892459397e-05, + "loss": 3.4386, + "step": 1698304 + }, + { + "epoch": 1.01, + "learning_rate": 2.2187955944948877e-05, + "loss": 3.4388, + "step": 1698816 + }, + { + "epoch": 1.01, + "learning_rate": 2.2179569997438357e-05, + "loss": 3.4469, + "step": 1699328 + }, + { + "epoch": 1.01, + "learning_rate": 2.2171184049927837e-05, + "loss": 3.4467, + "step": 1699840 + }, + { + "epoch": 1.01, + "learning_rate": 2.2162814481221046e-05, + "loss": 3.4517, + "step": 1700352 + }, + { + "epoch": 1.01, + "learning_rate": 2.215442853371053e-05, + "loss": 3.4478, + "step": 1700864 + }, + { + "epoch": 1.01, + "learning_rate": 2.214604258620001e-05, + "loss": 3.4464, + "step": 1701376 + }, + { + "epoch": 1.01, + "learning_rate": 2.213765663868949e-05, + "loss": 3.4564, + "step": 1701888 + }, + { + "epoch": 1.01, + "learning_rate": 2.21292870699827e-05, + "loss": 3.4513, + "step": 1702400 + }, + { + "epoch": 1.01, + "learning_rate": 2.212090112247218e-05, + "loss": 3.4536, + "step": 1702912 + }, + { + "epoch": 1.01, + "learning_rate": 2.211251517496166e-05, + "loss": 3.438, + "step": 1703424 + }, + { + "epoch": 1.01, + "learning_rate": 2.2104129227451138e-05, + "loss": 3.4314, + "step": 1703936 + }, + { + "epoch": 1.01, + "learning_rate": 2.209575965874435e-05, + "loss": 3.4626, + "step": 1704448 + }, + { + "epoch": 1.01, + "learning_rate": 2.208737371123383e-05, + "loss": 3.4498, + "step": 1704960 + }, + { + "epoch": 1.01, + "learning_rate": 2.207898776372331e-05, + "loss": 3.4442, + "step": 1705472 + }, + { + "epoch": 1.01, + "learning_rate": 2.2070601816212787e-05, + "loss": 3.4436, + "step": 1705984 + }, + { + "epoch": 1.01, + "learning_rate": 2.2062232247506e-05, + "loss": 3.4456, + "step": 1706496 + }, + { + "epoch": 1.01, + "learning_rate": 2.2053846299995483e-05, + "loss": 3.4368, + "step": 1707008 + }, + { + "epoch": 1.01, + "learning_rate": 2.2045460352484963e-05, + "loss": 3.4503, + "step": 1707520 + }, + { + "epoch": 1.01, + "learning_rate": 2.203707440497444e-05, + "loss": 3.4511, + "step": 1708032 + }, + { + "epoch": 1.01, + "learning_rate": 2.2028704836267652e-05, + "loss": 3.4488, + "step": 1708544 + }, + { + "epoch": 1.01, + "learning_rate": 2.2020318888757132e-05, + "loss": 3.4586, + "step": 1709056 + }, + { + "epoch": 1.01, + "learning_rate": 2.201193294124661e-05, + "loss": 3.4396, + "step": 1709568 + }, + { + "epoch": 1.01, + "learning_rate": 2.2003546993736092e-05, + "loss": 3.4442, + "step": 1710080 + }, + { + "epoch": 1.01, + "learning_rate": 2.1995177425029304e-05, + "loss": 3.4562, + "step": 1710592 + }, + { + "epoch": 1.01, + "learning_rate": 2.1986791477518784e-05, + "loss": 3.4347, + "step": 1711104 + }, + { + "epoch": 1.01, + "learning_rate": 2.197840553000826e-05, + "loss": 3.4349, + "step": 1711616 + }, + { + "epoch": 1.01, + "learning_rate": 2.197001958249774e-05, + "loss": 3.4438, + "step": 1712128 + }, + { + "epoch": 1.01, + "learning_rate": 2.1961650013790953e-05, + "loss": 3.4453, + "step": 1712640 + }, + { + "epoch": 1.01, + "learning_rate": 2.1953264066280433e-05, + "loss": 3.4366, + "step": 1713152 + }, + { + "epoch": 1.01, + "learning_rate": 2.1944878118769913e-05, + "loss": 3.4387, + "step": 1713664 + }, + { + "epoch": 1.01, + "learning_rate": 2.1936492171259393e-05, + "loss": 3.4363, + "step": 1714176 + }, + { + "epoch": 1.01, + "learning_rate": 2.1928122602552606e-05, + "loss": 3.4542, + "step": 1714688 + }, + { + "epoch": 1.01, + "learning_rate": 2.1919736655042082e-05, + "loss": 3.4456, + "step": 1715200 + }, + { + "epoch": 1.01, + "learning_rate": 2.1911350707531562e-05, + "loss": 3.4482, + "step": 1715712 + }, + { + "epoch": 1.01, + "learning_rate": 2.1902964760021046e-05, + "loss": 3.4552, + "step": 1716224 + }, + { + "epoch": 1.01, + "learning_rate": 2.1894595191314258e-05, + "loss": 3.4514, + "step": 1716736 + }, + { + "epoch": 1.01, + "learning_rate": 2.1886209243803735e-05, + "loss": 3.4655, + "step": 1717248 + }, + { + "epoch": 1.01, + "learning_rate": 2.1877823296293215e-05, + "loss": 3.4358, + "step": 1717760 + }, + { + "epoch": 1.01, + "learning_rate": 2.1869437348782695e-05, + "loss": 3.4579, + "step": 1718272 + }, + { + "epoch": 1.01, + "learning_rate": 2.1861067780075907e-05, + "loss": 3.4535, + "step": 1718784 + }, + { + "epoch": 1.01, + "learning_rate": 2.1852681832565387e-05, + "loss": 3.4361, + "step": 1719296 + }, + { + "epoch": 1.01, + "learning_rate": 2.1844295885054867e-05, + "loss": 3.4578, + "step": 1719808 + }, + { + "epoch": 1.01, + "learning_rate": 2.1835909937544347e-05, + "loss": 3.446, + "step": 1720320 + }, + { + "epoch": 1.01, + "learning_rate": 2.1827540368837556e-05, + "loss": 3.4555, + "step": 1720832 + }, + { + "epoch": 1.01, + "learning_rate": 2.1819154421327036e-05, + "loss": 3.4557, + "step": 1721344 + }, + { + "epoch": 1.01, + "learning_rate": 2.1810768473816516e-05, + "loss": 3.4361, + "step": 1721856 + }, + { + "epoch": 1.01, + "learning_rate": 2.1802382526306e-05, + "loss": 3.4334, + "step": 1722368 + }, + { + "epoch": 1.01, + "learning_rate": 2.179401295759921e-05, + "loss": 3.4401, + "step": 1722880 + }, + { + "epoch": 1.01, + "learning_rate": 2.178564338889242e-05, + "loss": 3.452, + "step": 1723392 + }, + { + "epoch": 1.01, + "learning_rate": 2.17772574413819e-05, + "loss": 3.4473, + "step": 1723904 + }, + { + "epoch": 1.01, + "learning_rate": 2.1768871493871377e-05, + "loss": 3.4457, + "step": 1724416 + }, + { + "epoch": 1.02, + "learning_rate": 2.176048554636086e-05, + "loss": 3.4422, + "step": 1724928 + }, + { + "epoch": 1.02, + "learning_rate": 2.175209959885034e-05, + "loss": 3.4438, + "step": 1725440 + }, + { + "epoch": 1.02, + "learning_rate": 2.174371365133982e-05, + "loss": 3.4474, + "step": 1725952 + }, + { + "epoch": 1.02, + "learning_rate": 2.17353277038293e-05, + "loss": 3.4408, + "step": 1726464 + }, + { + "epoch": 1.02, + "learning_rate": 2.172694175631878e-05, + "loss": 3.4543, + "step": 1726976 + }, + { + "epoch": 1.02, + "learning_rate": 2.171857218761199e-05, + "loss": 3.4535, + "step": 1727488 + }, + { + "epoch": 1.02, + "learning_rate": 2.171018624010147e-05, + "loss": 3.4533, + "step": 1728000 + }, + { + "epoch": 1.02, + "learning_rate": 2.1701800292590953e-05, + "loss": 3.4372, + "step": 1728512 + }, + { + "epoch": 1.02, + "learning_rate": 2.1693414345080433e-05, + "loss": 3.4468, + "step": 1729024 + }, + { + "epoch": 1.02, + "learning_rate": 2.1685044776373642e-05, + "loss": 3.446, + "step": 1729536 + }, + { + "epoch": 1.02, + "learning_rate": 2.1676658828863122e-05, + "loss": 3.4505, + "step": 1730048 + }, + { + "epoch": 1.02, + "learning_rate": 2.1668272881352602e-05, + "loss": 3.4486, + "step": 1730560 + }, + { + "epoch": 1.02, + "learning_rate": 2.1659886933842082e-05, + "loss": 3.4411, + "step": 1731072 + }, + { + "epoch": 1.02, + "learning_rate": 2.1651517365135294e-05, + "loss": 3.4395, + "step": 1731584 + }, + { + "epoch": 1.02, + "learning_rate": 2.1643131417624774e-05, + "loss": 3.4459, + "step": 1732096 + }, + { + "epoch": 1.02, + "learning_rate": 2.1634745470114254e-05, + "loss": 3.4377, + "step": 1732608 + }, + { + "epoch": 1.02, + "learning_rate": 2.1626359522603734e-05, + "loss": 3.4427, + "step": 1733120 + }, + { + "epoch": 1.02, + "learning_rate": 2.1617989953896943e-05, + "loss": 3.4208, + "step": 1733632 + }, + { + "epoch": 1.02, + "learning_rate": 2.1609604006386423e-05, + "loss": 3.4494, + "step": 1734144 + }, + { + "epoch": 1.02, + "learning_rate": 2.1601218058875907e-05, + "loss": 3.4396, + "step": 1734656 + }, + { + "epoch": 1.02, + "learning_rate": 2.1592832111365387e-05, + "loss": 3.4481, + "step": 1735168 + }, + { + "epoch": 1.02, + "learning_rate": 2.1584462542658596e-05, + "loss": 3.4357, + "step": 1735680 + }, + { + "epoch": 1.02, + "learning_rate": 2.1576076595148076e-05, + "loss": 3.45, + "step": 1736192 + }, + { + "epoch": 1.02, + "learning_rate": 2.1567690647637556e-05, + "loss": 3.4483, + "step": 1736704 + }, + { + "epoch": 1.02, + "learning_rate": 2.1559304700127032e-05, + "loss": 3.4325, + "step": 1737216 + }, + { + "epoch": 1.02, + "learning_rate": 2.1550935131420248e-05, + "loss": 3.4574, + "step": 1737728 + }, + { + "epoch": 1.02, + "learning_rate": 2.1542549183909728e-05, + "loss": 3.4538, + "step": 1738240 + }, + { + "epoch": 1.02, + "learning_rate": 2.1534163236399208e-05, + "loss": 3.4432, + "step": 1738752 + }, + { + "epoch": 1.02, + "learning_rate": 2.1525793667692417e-05, + "loss": 3.4503, + "step": 1739264 + }, + { + "epoch": 1.02, + "learning_rate": 2.1517407720181897e-05, + "loss": 3.4371, + "step": 1739776 + }, + { + "epoch": 1.02, + "learning_rate": 2.1509021772671377e-05, + "loss": 3.4522, + "step": 1740288 + }, + { + "epoch": 1.02, + "learning_rate": 2.150063582516086e-05, + "loss": 3.4337, + "step": 1740800 + }, + { + "epoch": 1.02, + "learning_rate": 2.1492249877650337e-05, + "loss": 3.4518, + "step": 1741312 + }, + { + "epoch": 1.02, + "learning_rate": 2.1483863930139817e-05, + "loss": 3.4382, + "step": 1741824 + }, + { + "epoch": 1.02, + "learning_rate": 2.1475477982629297e-05, + "loss": 3.4453, + "step": 1742336 + }, + { + "epoch": 1.02, + "learning_rate": 2.1467092035118777e-05, + "loss": 3.4392, + "step": 1742848 + }, + { + "epoch": 1.02, + "learning_rate": 2.1458722466411986e-05, + "loss": 3.4409, + "step": 1743360 + }, + { + "epoch": 1.02, + "learning_rate": 2.145033651890147e-05, + "loss": 3.4413, + "step": 1743872 + }, + { + "epoch": 1.02, + "learning_rate": 2.144195057139095e-05, + "loss": 3.4388, + "step": 1744384 + }, + { + "epoch": 1.02, + "learning_rate": 2.143356462388043e-05, + "loss": 3.4439, + "step": 1744896 + }, + { + "epoch": 1.02, + "learning_rate": 2.1425195055173638e-05, + "loss": 3.4531, + "step": 1745408 + }, + { + "epoch": 1.02, + "learning_rate": 2.1416809107663118e-05, + "loss": 3.4429, + "step": 1745920 + }, + { + "epoch": 1.02, + "learning_rate": 2.1408423160152598e-05, + "loss": 3.4552, + "step": 1746432 + }, + { + "epoch": 1.02, + "learning_rate": 2.1400037212642078e-05, + "loss": 3.4294, + "step": 1746944 + }, + { + "epoch": 1.02, + "learning_rate": 2.139166764393529e-05, + "loss": 3.4526, + "step": 1747456 + }, + { + "epoch": 1.02, + "learning_rate": 2.138328169642477e-05, + "loss": 3.4481, + "step": 1747968 + }, + { + "epoch": 1.02, + "learning_rate": 2.137489574891425e-05, + "loss": 3.446, + "step": 1748480 + }, + { + "epoch": 1.02, + "learning_rate": 2.136652618020746e-05, + "loss": 3.4427, + "step": 1748992 + }, + { + "epoch": 1.02, + "learning_rate": 2.135814023269694e-05, + "loss": 3.4457, + "step": 1749504 + }, + { + "epoch": 1.02, + "learning_rate": 2.1349754285186423e-05, + "loss": 3.4473, + "step": 1750016 + }, + { + "epoch": 1.02, + "learning_rate": 2.1341368337675903e-05, + "loss": 3.457, + "step": 1750528 + }, + { + "epoch": 1.02, + "learning_rate": 2.1332998768969112e-05, + "loss": 3.437, + "step": 1751040 + }, + { + "epoch": 1.02, + "learning_rate": 2.1324612821458592e-05, + "loss": 3.4462, + "step": 1751552 + }, + { + "epoch": 1.02, + "learning_rate": 2.1316226873948072e-05, + "loss": 3.4413, + "step": 1752064 + }, + { + "epoch": 1.02, + "learning_rate": 2.1307840926437552e-05, + "loss": 3.4375, + "step": 1752576 + }, + { + "epoch": 1.02, + "learning_rate": 2.1299471357730764e-05, + "loss": 3.4474, + "step": 1753088 + }, + { + "epoch": 1.02, + "learning_rate": 2.1291085410220244e-05, + "loss": 3.4481, + "step": 1753600 + }, + { + "epoch": 1.02, + "learning_rate": 2.1282699462709724e-05, + "loss": 3.4479, + "step": 1754112 + }, + { + "epoch": 1.02, + "learning_rate": 2.1274313515199204e-05, + "loss": 3.4344, + "step": 1754624 + }, + { + "epoch": 1.02, + "learning_rate": 2.1265943946492413e-05, + "loss": 3.4494, + "step": 1755136 + }, + { + "epoch": 1.03, + "eval_loss": 3.8533949851989746, + "eval_runtime": 301.578, + "eval_samples_per_second": 1265.315, + "eval_steps_per_second": 39.542, + "step": 1755360 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 1.2268179933848617e+18, + "trial_name": null, + "trial_params": null +}