{ "best_metric": 3.845926284790039, "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/rel-cl/transformer/1/checkpoints/checkpoint-915830", "epoch": 1.0250006060157382, "eval_steps": 10, "global_step": 2518550, "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": 10.9662, "step": 1 }, { "epoch": 0.0, "learning_rate": 4.999161405248948e-05, "loss": 6.8384, "step": 512 }, { "epoch": 0.0, "learning_rate": 4.998322810497896e-05, "loss": 6.2003, "step": 1024 }, { "epoch": 0.0, "learning_rate": 4.997484215746844e-05, "loss": 5.984, "step": 1536 }, { "epoch": 0.0, "learning_rate": 4.996645620995792e-05, "loss": 5.8361, "step": 2048 }, { "epoch": 0.0, "learning_rate": 4.99580702624474e-05, "loss": 5.7163, "step": 2560 }, { "epoch": 0.0, "learning_rate": 4.994968431493688e-05, "loss": 5.6151, "step": 3072 }, { "epoch": 0.0, "learning_rate": 4.994129836742636e-05, "loss": 5.549, "step": 3584 }, { "epoch": 0.0, "learning_rate": 4.993291241991584e-05, "loss": 5.4911, "step": 4096 }, { "epoch": 0.0, "learning_rate": 4.992452647240532e-05, "loss": 5.4148, "step": 4608 }, { "epoch": 0.0, "learning_rate": 4.99161405248948e-05, "loss": 5.3799, "step": 5120 }, { "epoch": 0.0, "learning_rate": 4.990775457738428e-05, "loss": 5.3402, "step": 5632 }, { "epoch": 0.0, "learning_rate": 4.989936862987376e-05, "loss": 5.2804, "step": 6144 }, { "epoch": 0.0, "learning_rate": 4.989098268236324e-05, "loss": 5.2292, "step": 6656 }, { "epoch": 0.0, "learning_rate": 4.988259673485272e-05, "loss": 5.2031, "step": 7168 }, { "epoch": 0.0, "learning_rate": 4.98742107873422e-05, "loss": 5.1705, "step": 7680 }, { "epoch": 0.0, "learning_rate": 4.986582483983168e-05, "loss": 5.1368, "step": 8192 }, { "epoch": 0.0, "learning_rate": 4.985745527112489e-05, "loss": 5.0909, "step": 8704 }, { "epoch": 0.0, "learning_rate": 4.984906932361437e-05, "loss": 5.0723, "step": 9216 }, { "epoch": 0.0, "learning_rate": 4.984068337610385e-05, "loss": 5.0415, "step": 9728 }, { "epoch": 0.0, "learning_rate": 4.983229742859333e-05, "loss": 5.0156, "step": 10240 }, { "epoch": 0.0, "learning_rate": 4.9823927859886547e-05, "loss": 4.9989, "step": 10752 }, { "epoch": 0.0, "learning_rate": 4.9815541912376026e-05, "loss": 4.9769, "step": 11264 }, { "epoch": 0.0, "learning_rate": 4.9807155964865506e-05, "loss": 4.9514, "step": 11776 }, { "epoch": 0.0, "learning_rate": 4.9798770017354986e-05, "loss": 4.9293, "step": 12288 }, { "epoch": 0.0, "learning_rate": 4.9790400448648195e-05, "loss": 4.9153, "step": 12800 }, { "epoch": 0.0, "learning_rate": 4.9782014501137675e-05, "loss": 4.89, "step": 13312 }, { "epoch": 0.0, "learning_rate": 4.9773628553627155e-05, "loss": 4.8802, "step": 13824 }, { "epoch": 0.0, "learning_rate": 4.9765242606116635e-05, "loss": 4.8445, "step": 14336 }, { "epoch": 0.0, "learning_rate": 4.9756873037409844e-05, "loss": 4.8481, "step": 14848 }, { "epoch": 0.01, "learning_rate": 4.9748487089899324e-05, "loss": 4.8142, "step": 15360 }, { "epoch": 0.01, "learning_rate": 4.9740101142388804e-05, "loss": 4.8057, "step": 15872 }, { "epoch": 0.01, "learning_rate": 4.9731715194878284e-05, "loss": 4.8064, "step": 16384 }, { "epoch": 0.01, "learning_rate": 4.9723329247367764e-05, "loss": 4.7902, "step": 16896 }, { "epoch": 0.01, "learning_rate": 4.971495967866098e-05, "loss": 4.7639, "step": 17408 }, { "epoch": 0.01, "learning_rate": 4.970657373115046e-05, "loss": 4.7501, "step": 17920 }, { "epoch": 0.01, "learning_rate": 4.969818778363994e-05, "loss": 4.7525, "step": 18432 }, { "epoch": 0.01, "learning_rate": 4.968980183612942e-05, "loss": 4.7349, "step": 18944 }, { "epoch": 0.01, "learning_rate": 4.96814158886189e-05, "loss": 4.7245, "step": 19456 }, { "epoch": 0.01, "learning_rate": 4.967302994110837e-05, "loss": 4.7072, "step": 19968 }, { "epoch": 0.01, "learning_rate": 4.966464399359785e-05, "loss": 4.6911, "step": 20480 }, { "epoch": 0.01, "learning_rate": 4.965625804608733e-05, "loss": 4.68, "step": 20992 }, { "epoch": 0.01, "learning_rate": 4.964788847738054e-05, "loss": 4.6665, "step": 21504 }, { "epoch": 0.01, "learning_rate": 4.963950252987002e-05, "loss": 4.667, "step": 22016 }, { "epoch": 0.01, "learning_rate": 4.96311165823595e-05, "loss": 4.6573, "step": 22528 }, { "epoch": 0.01, "learning_rate": 4.962273063484898e-05, "loss": 4.6531, "step": 23040 }, { "epoch": 0.01, "learning_rate": 4.961434468733847e-05, "loss": 4.637, "step": 23552 }, { "epoch": 0.01, "learning_rate": 4.960597511863168e-05, "loss": 4.6343, "step": 24064 }, { "epoch": 0.01, "learning_rate": 4.959758917112116e-05, "loss": 4.6367, "step": 24576 }, { "epoch": 0.01, "learning_rate": 4.958920322361064e-05, "loss": 4.6138, "step": 25088 }, { "epoch": 0.01, "learning_rate": 4.958081727610012e-05, "loss": 4.6078, "step": 25600 }, { "epoch": 0.01, "learning_rate": 4.957244770739333e-05, "loss": 4.5968, "step": 26112 }, { "epoch": 0.01, "learning_rate": 4.956406175988281e-05, "loss": 4.6061, "step": 26624 }, { "epoch": 0.01, "learning_rate": 4.955567581237229e-05, "loss": 4.5712, "step": 27136 }, { "epoch": 0.01, "learning_rate": 4.954728986486177e-05, "loss": 4.5898, "step": 27648 }, { "epoch": 0.01, "learning_rate": 4.9538920296154976e-05, "loss": 4.5639, "step": 28160 }, { "epoch": 0.01, "learning_rate": 4.9530534348644456e-05, "loss": 4.5614, "step": 28672 }, { "epoch": 0.01, "learning_rate": 4.9522148401133936e-05, "loss": 4.5622, "step": 29184 }, { "epoch": 0.01, "learning_rate": 4.951376245362342e-05, "loss": 4.5535, "step": 29696 }, { "epoch": 0.01, "learning_rate": 4.95053765061129e-05, "loss": 4.5372, "step": 30208 }, { "epoch": 0.01, "learning_rate": 4.949700693740611e-05, "loss": 4.5301, "step": 30720 }, { "epoch": 0.01, "learning_rate": 4.948862098989559e-05, "loss": 4.5188, "step": 31232 }, { "epoch": 0.01, "learning_rate": 4.948023504238507e-05, "loss": 4.5324, "step": 31744 }, { "epoch": 0.01, "learning_rate": 4.947184909487455e-05, "loss": 4.517, "step": 32256 }, { "epoch": 0.01, "learning_rate": 4.946347952616776e-05, "loss": 4.5067, "step": 32768 }, { "epoch": 0.01, "learning_rate": 4.945509357865724e-05, "loss": 4.5061, "step": 33280 }, { "epoch": 0.01, "learning_rate": 4.944670763114672e-05, "loss": 4.4966, "step": 33792 }, { "epoch": 0.01, "learning_rate": 4.94383216836362e-05, "loss": 4.4777, "step": 34304 }, { "epoch": 0.01, "learning_rate": 4.942995211492941e-05, "loss": 4.499, "step": 34816 }, { "epoch": 0.01, "learning_rate": 4.9421582546222625e-05, "loss": 4.4775, "step": 35328 }, { "epoch": 0.01, "learning_rate": 4.9413196598712105e-05, "loss": 4.4723, "step": 35840 }, { "epoch": 0.01, "learning_rate": 4.9404810651201585e-05, "loss": 4.4834, "step": 36352 }, { "epoch": 0.01, "learning_rate": 4.9396424703691065e-05, "loss": 4.4639, "step": 36864 }, { "epoch": 0.01, "learning_rate": 4.9388038756180545e-05, "loss": 4.4763, "step": 37376 }, { "epoch": 0.01, "learning_rate": 4.9379669187473754e-05, "loss": 4.473, "step": 37888 }, { "epoch": 0.01, "learning_rate": 4.9371283239963234e-05, "loss": 4.4608, "step": 38400 }, { "epoch": 0.01, "learning_rate": 4.9362897292452714e-05, "loss": 4.4655, "step": 38912 }, { "epoch": 0.01, "learning_rate": 4.9354511344942194e-05, "loss": 4.4382, "step": 39424 }, { "epoch": 0.01, "learning_rate": 4.9346125397431674e-05, "loss": 4.4353, "step": 39936 }, { "epoch": 0.01, "learning_rate": 4.9337739449921154e-05, "loss": 4.4392, "step": 40448 }, { "epoch": 0.01, "learning_rate": 4.9329353502410634e-05, "loss": 4.4381, "step": 40960 }, { "epoch": 0.01, "learning_rate": 4.9320967554900114e-05, "loss": 4.432, "step": 41472 }, { "epoch": 0.01, "learning_rate": 4.931259798619332e-05, "loss": 4.4173, "step": 41984 }, { "epoch": 0.01, "learning_rate": 4.930421203868281e-05, "loss": 4.4089, "step": 42496 }, { "epoch": 0.01, "learning_rate": 4.929582609117229e-05, "loss": 4.4109, "step": 43008 }, { "epoch": 0.01, "learning_rate": 4.92874565224655e-05, "loss": 4.4117, "step": 43520 }, { "epoch": 0.01, "learning_rate": 4.927907057495498e-05, "loss": 4.411, "step": 44032 }, { "epoch": 0.01, "learning_rate": 4.927068462744446e-05, "loss": 4.4136, "step": 44544 }, { "epoch": 0.01, "learning_rate": 4.926229867993394e-05, "loss": 4.4098, "step": 45056 }, { "epoch": 0.01, "learning_rate": 4.925391273242342e-05, "loss": 4.3971, "step": 45568 }, { "epoch": 0.02, "learning_rate": 4.924554316371663e-05, "loss": 4.3838, "step": 46080 }, { "epoch": 0.02, "learning_rate": 4.923715721620611e-05, "loss": 4.3817, "step": 46592 }, { "epoch": 0.02, "learning_rate": 4.922877126869559e-05, "loss": 4.3886, "step": 47104 }, { "epoch": 0.02, "learning_rate": 4.922038532118507e-05, "loss": 4.3844, "step": 47616 }, { "epoch": 0.02, "learning_rate": 4.921199937367455e-05, "loss": 4.3662, "step": 48128 }, { "epoch": 0.02, "learning_rate": 4.920361342616403e-05, "loss": 4.3722, "step": 48640 }, { "epoch": 0.02, "learning_rate": 4.919522747865351e-05, "loss": 4.3718, "step": 49152 }, { "epoch": 0.02, "learning_rate": 4.918685790994672e-05, "loss": 4.3761, "step": 49664 }, { "epoch": 0.02, "learning_rate": 4.91784719624362e-05, "loss": 4.3706, "step": 50176 }, { "epoch": 0.02, "learning_rate": 4.9170086014925676e-05, "loss": 4.3653, "step": 50688 }, { "epoch": 0.02, "learning_rate": 4.9161700067415156e-05, "loss": 4.3666, "step": 51200 }, { "epoch": 0.02, "learning_rate": 4.9153314119904636e-05, "loss": 4.3564, "step": 51712 }, { "epoch": 0.02, "learning_rate": 4.9144928172394116e-05, "loss": 4.3536, "step": 52224 }, { "epoch": 0.02, "learning_rate": 4.9136542224883596e-05, "loss": 4.3621, "step": 52736 }, { "epoch": 0.02, "learning_rate": 4.9128172656176805e-05, "loss": 4.3462, "step": 53248 }, { "epoch": 0.02, "learning_rate": 4.9119786708666285e-05, "loss": 4.3513, "step": 53760 }, { "epoch": 0.02, "learning_rate": 4.9111400761155765e-05, "loss": 4.332, "step": 54272 }, { "epoch": 0.02, "learning_rate": 4.9103014813645245e-05, "loss": 4.328, "step": 54784 }, { "epoch": 0.02, "learning_rate": 4.909462886613473e-05, "loss": 4.3271, "step": 55296 }, { "epoch": 0.02, "learning_rate": 4.908624291862421e-05, "loss": 4.3365, "step": 55808 }, { "epoch": 0.02, "learning_rate": 4.907787334991742e-05, "loss": 4.3306, "step": 56320 }, { "epoch": 0.02, "learning_rate": 4.90694874024069e-05, "loss": 4.3082, "step": 56832 }, { "epoch": 0.02, "learning_rate": 4.906110145489638e-05, "loss": 4.3125, "step": 57344 }, { "epoch": 0.02, "learning_rate": 4.905271550738586e-05, "loss": 4.3217, "step": 57856 }, { "epoch": 0.02, "learning_rate": 4.904432955987534e-05, "loss": 4.3302, "step": 58368 }, { "epoch": 0.02, "learning_rate": 4.903594361236482e-05, "loss": 4.313, "step": 58880 }, { "epoch": 0.02, "learning_rate": 4.902757404365803e-05, "loss": 4.3194, "step": 59392 }, { "epoch": 0.02, "learning_rate": 4.901918809614751e-05, "loss": 4.3112, "step": 59904 }, { "epoch": 0.02, "learning_rate": 4.901080214863699e-05, "loss": 4.3137, "step": 60416 }, { "epoch": 0.02, "learning_rate": 4.900241620112647e-05, "loss": 4.3042, "step": 60928 }, { "epoch": 0.02, "learning_rate": 4.899403025361595e-05, "loss": 4.3001, "step": 61440 }, { "epoch": 0.02, "learning_rate": 4.898564430610543e-05, "loss": 4.2937, "step": 61952 }, { "epoch": 0.02, "learning_rate": 4.897725835859491e-05, "loss": 4.3029, "step": 62464 }, { "epoch": 0.02, "learning_rate": 4.8968872411084396e-05, "loss": 4.2869, "step": 62976 }, { "epoch": 0.02, "learning_rate": 4.8960502842377605e-05, "loss": 4.295, "step": 63488 }, { "epoch": 0.02, "learning_rate": 4.8952116894867085e-05, "loss": 4.2879, "step": 64000 }, { "epoch": 0.02, "learning_rate": 4.8943730947356565e-05, "loss": 4.2975, "step": 64512 }, { "epoch": 0.02, "learning_rate": 4.893534499984604e-05, "loss": 4.2724, "step": 65024 }, { "epoch": 0.02, "learning_rate": 4.8926975431139254e-05, "loss": 4.2844, "step": 65536 }, { "epoch": 0.02, "learning_rate": 4.8918589483628734e-05, "loss": 4.2936, "step": 66048 }, { "epoch": 0.02, "learning_rate": 4.8910203536118214e-05, "loss": 4.2718, "step": 66560 }, { "epoch": 0.02, "learning_rate": 4.8901833967411423e-05, "loss": 4.2909, "step": 67072 }, { "epoch": 0.02, "learning_rate": 4.88934480199009e-05, "loss": 4.2763, "step": 67584 }, { "epoch": 0.02, "learning_rate": 4.888506207239038e-05, "loss": 4.2771, "step": 68096 }, { "epoch": 0.02, "learning_rate": 4.887667612487986e-05, "loss": 4.271, "step": 68608 }, { "epoch": 0.02, "learning_rate": 4.886830655617308e-05, "loss": 4.263, "step": 69120 }, { "epoch": 0.02, "learning_rate": 4.885992060866256e-05, "loss": 4.2664, "step": 69632 }, { "epoch": 0.02, "learning_rate": 4.885153466115204e-05, "loss": 4.2703, "step": 70144 }, { "epoch": 0.02, "learning_rate": 4.884316509244525e-05, "loss": 4.2761, "step": 70656 }, { "epoch": 0.02, "learning_rate": 4.883477914493473e-05, "loss": 4.2647, "step": 71168 }, { "epoch": 0.02, "learning_rate": 4.882639319742421e-05, "loss": 4.2683, "step": 71680 }, { "epoch": 0.02, "learning_rate": 4.881800724991369e-05, "loss": 4.2612, "step": 72192 }, { "epoch": 0.02, "learning_rate": 4.880962130240316e-05, "loss": 4.2484, "step": 72704 }, { "epoch": 0.02, "learning_rate": 4.880123535489264e-05, "loss": 4.2555, "step": 73216 }, { "epoch": 0.02, "learning_rate": 4.879284940738212e-05, "loss": 4.2427, "step": 73728 }, { "epoch": 0.02, "learning_rate": 4.878447983867534e-05, "loss": 4.2467, "step": 74240 }, { "epoch": 0.02, "learning_rate": 4.877609389116482e-05, "loss": 4.2466, "step": 74752 }, { "epoch": 0.02, "learning_rate": 4.87677079436543e-05, "loss": 4.2414, "step": 75264 }, { "epoch": 0.02, "learning_rate": 4.875932199614378e-05, "loss": 4.239, "step": 75776 }, { "epoch": 0.02, "learning_rate": 4.875093604863326e-05, "loss": 4.238, "step": 76288 }, { "epoch": 0.03, "eval_loss": 4.202739715576172, "eval_runtime": 573.4896, "eval_samples_per_second": 665.384, "eval_steps_per_second": 20.794, "step": 76319 }, { "epoch": 0.0, "learning_rate": 4.8742566479926466e-05, "loss": 4.2444, "step": 76800 }, { "epoch": 0.0, "learning_rate": 4.8734180532415946e-05, "loss": 4.2388, "step": 77312 }, { "epoch": 0.0, "learning_rate": 4.8725794584905426e-05, "loss": 4.2311, "step": 77824 }, { "epoch": 0.0, "learning_rate": 4.8717408637394906e-05, "loss": 4.2298, "step": 78336 }, { "epoch": 0.0, "learning_rate": 4.8709022689884386e-05, "loss": 4.2306, "step": 78848 }, { "epoch": 0.0, "learning_rate": 4.8700636742373866e-05, "loss": 4.2059, "step": 79360 }, { "epoch": 0.0, "learning_rate": 4.8692250794863346e-05, "loss": 4.2215, "step": 79872 }, { "epoch": 0.0, "learning_rate": 4.8683864847352826e-05, "loss": 4.2212, "step": 80384 }, { "epoch": 0.0, "learning_rate": 4.8675478899842306e-05, "loss": 4.2108, "step": 80896 }, { "epoch": 0.0, "learning_rate": 4.8667092952331785e-05, "loss": 4.2213, "step": 81408 }, { "epoch": 0.0, "learning_rate": 4.865870700482127e-05, "loss": 4.2224, "step": 81920 }, { "epoch": 0.0, "learning_rate": 4.865032105731075e-05, "loss": 4.2059, "step": 82432 }, { "epoch": 0.0, "learning_rate": 4.8641935109800225e-05, "loss": 4.2052, "step": 82944 }, { "epoch": 0.0, "learning_rate": 4.8633549162289705e-05, "loss": 4.2054, "step": 83456 }, { "epoch": 0.0, "learning_rate": 4.8625163214779185e-05, "loss": 4.2053, "step": 83968 }, { "epoch": 0.0, "learning_rate": 4.86167936460724e-05, "loss": 4.1927, "step": 84480 }, { "epoch": 0.0, "learning_rate": 4.8608407698561874e-05, "loss": 4.1961, "step": 84992 }, { "epoch": 0.0, "learning_rate": 4.8600021751051354e-05, "loss": 4.1975, "step": 85504 }, { "epoch": 0.0, "learning_rate": 4.8591635803540834e-05, "loss": 4.194, "step": 86016 }, { "epoch": 0.0, "learning_rate": 4.8583249856030314e-05, "loss": 4.1983, "step": 86528 }, { "epoch": 0.0, "learning_rate": 4.8574863908519794e-05, "loss": 4.1962, "step": 87040 }, { "epoch": 0.0, "learning_rate": 4.8566477961009274e-05, "loss": 4.1978, "step": 87552 }, { "epoch": 0.0, "learning_rate": 4.855810839230249e-05, "loss": 4.1915, "step": 88064 }, { "epoch": 0.0, "learning_rate": 4.854972244479197e-05, "loss": 4.1898, "step": 88576 }, { "epoch": 0.0, "learning_rate": 4.854133649728145e-05, "loss": 4.1876, "step": 89088 }, { "epoch": 0.0, "learning_rate": 4.853295054977093e-05, "loss": 4.184, "step": 89600 }, { "epoch": 0.0, "learning_rate": 4.852456460226041e-05, "loss": 4.1904, "step": 90112 }, { "epoch": 0.0, "learning_rate": 4.851617865474989e-05, "loss": 4.1699, "step": 90624 }, { "epoch": 0.0, "learning_rate": 4.85078090860431e-05, "loss": 4.1829, "step": 91136 }, { "epoch": 0.01, "learning_rate": 4.849942313853258e-05, "loss": 4.1675, "step": 91648 }, { "epoch": 0.01, "learning_rate": 4.849103719102206e-05, "loss": 4.1732, "step": 92160 }, { "epoch": 0.01, "learning_rate": 4.848265124351154e-05, "loss": 4.1822, "step": 92672 }, { "epoch": 0.01, "learning_rate": 4.847426529600102e-05, "loss": 4.1788, "step": 93184 }, { "epoch": 0.01, "learning_rate": 4.846589572729423e-05, "loss": 4.1677, "step": 93696 }, { "epoch": 0.01, "learning_rate": 4.845750977978371e-05, "loss": 4.1617, "step": 94208 }, { "epoch": 0.01, "learning_rate": 4.8449123832273194e-05, "loss": 4.1753, "step": 94720 }, { "epoch": 0.01, "learning_rate": 4.8440737884762674e-05, "loss": 4.1658, "step": 95232 }, { "epoch": 0.01, "learning_rate": 4.8432368316055884e-05, "loss": 4.1661, "step": 95744 }, { "epoch": 0.01, "learning_rate": 4.8423982368545363e-05, "loss": 4.1607, "step": 96256 }, { "epoch": 0.01, "learning_rate": 4.8415596421034843e-05, "loss": 4.1479, "step": 96768 }, { "epoch": 0.01, "learning_rate": 4.840721047352432e-05, "loss": 4.1464, "step": 97280 }, { "epoch": 0.01, "learning_rate": 4.83988245260138e-05, "loss": 4.1464, "step": 97792 }, { "epoch": 0.01, "learning_rate": 4.839043857850328e-05, "loss": 4.1559, "step": 98304 }, { "epoch": 0.01, "learning_rate": 4.838206900979649e-05, "loss": 4.1457, "step": 98816 }, { "epoch": 0.01, "learning_rate": 4.837368306228597e-05, "loss": 4.1492, "step": 99328 }, { "epoch": 0.01, "learning_rate": 4.836529711477545e-05, "loss": 4.1462, "step": 99840 }, { "epoch": 0.01, "learning_rate": 4.835691116726493e-05, "loss": 4.1477, "step": 100352 }, { "epoch": 0.01, "learning_rate": 4.834852521975441e-05, "loss": 4.1575, "step": 100864 }, { "epoch": 0.01, "learning_rate": 4.834013927224389e-05, "loss": 4.1374, "step": 101376 }, { "epoch": 0.01, "learning_rate": 4.833176970353711e-05, "loss": 4.1404, "step": 101888 }, { "epoch": 0.01, "learning_rate": 4.832338375602659e-05, "loss": 4.1316, "step": 102400 }, { "epoch": 0.01, "learning_rate": 4.831499780851606e-05, "loss": 4.1546, "step": 102912 }, { "epoch": 0.01, "learning_rate": 4.830661186100554e-05, "loss": 4.1243, "step": 103424 }, { "epoch": 0.01, "learning_rate": 4.829824229229876e-05, "loss": 4.142, "step": 103936 }, { "epoch": 0.01, "learning_rate": 4.828985634478824e-05, "loss": 4.1252, "step": 104448 }, { "epoch": 0.01, "learning_rate": 4.828147039727771e-05, "loss": 4.1316, "step": 104960 }, { "epoch": 0.01, "learning_rate": 4.827308444976719e-05, "loss": 4.1332, "step": 105472 }, { "epoch": 0.01, "learning_rate": 4.826469850225667e-05, "loss": 4.1308, "step": 105984 }, { "epoch": 0.01, "learning_rate": 4.8256328933549886e-05, "loss": 4.1197, "step": 106496 }, { "epoch": 0.01, "learning_rate": 4.8247942986039366e-05, "loss": 4.1241, "step": 107008 }, { "epoch": 0.01, "learning_rate": 4.8239557038528846e-05, "loss": 4.1099, "step": 107520 }, { "epoch": 0.01, "learning_rate": 4.8231171091018326e-05, "loss": 4.1266, "step": 108032 }, { "epoch": 0.01, "learning_rate": 4.8222801522311535e-05, "loss": 4.1223, "step": 108544 }, { "epoch": 0.01, "learning_rate": 4.8214415574801015e-05, "loss": 4.1161, "step": 109056 }, { "epoch": 0.01, "learning_rate": 4.8206029627290495e-05, "loss": 4.1143, "step": 109568 }, { "epoch": 0.01, "learning_rate": 4.8197643679779975e-05, "loss": 4.1158, "step": 110080 }, { "epoch": 0.01, "learning_rate": 4.8189257732269455e-05, "loss": 4.097, "step": 110592 }, { "epoch": 0.01, "learning_rate": 4.8180888163562664e-05, "loss": 4.121, "step": 111104 }, { "epoch": 0.01, "learning_rate": 4.8172502216052144e-05, "loss": 4.1049, "step": 111616 }, { "epoch": 0.01, "learning_rate": 4.8164116268541624e-05, "loss": 4.1074, "step": 112128 }, { "epoch": 0.01, "learning_rate": 4.8155730321031104e-05, "loss": 4.1163, "step": 112640 }, { "epoch": 0.01, "learning_rate": 4.814736075232432e-05, "loss": 4.1034, "step": 113152 }, { "epoch": 0.01, "learning_rate": 4.81389748048138e-05, "loss": 4.1161, "step": 113664 }, { "epoch": 0.01, "learning_rate": 4.813058885730328e-05, "loss": 4.1203, "step": 114176 }, { "epoch": 0.01, "learning_rate": 4.812220290979276e-05, "loss": 4.1136, "step": 114688 }, { "epoch": 0.01, "learning_rate": 4.811383334108597e-05, "loss": 4.1171, "step": 115200 }, { "epoch": 0.01, "learning_rate": 4.810544739357545e-05, "loss": 4.0976, "step": 115712 }, { "epoch": 0.01, "learning_rate": 4.809706144606493e-05, "loss": 4.0919, "step": 116224 }, { "epoch": 0.01, "learning_rate": 4.808867549855441e-05, "loss": 4.1001, "step": 116736 }, { "epoch": 0.01, "learning_rate": 4.808030592984762e-05, "loss": 4.1079, "step": 117248 }, { "epoch": 0.01, "learning_rate": 4.80719199823371e-05, "loss": 4.0998, "step": 117760 }, { "epoch": 0.01, "learning_rate": 4.806353403482658e-05, "loss": 4.0916, "step": 118272 }, { "epoch": 0.01, "learning_rate": 4.805514808731606e-05, "loss": 4.0819, "step": 118784 }, { "epoch": 0.01, "learning_rate": 4.804676213980554e-05, "loss": 4.0857, "step": 119296 }, { "epoch": 0.01, "learning_rate": 4.803839257109875e-05, "loss": 4.0879, "step": 119808 }, { "epoch": 0.01, "learning_rate": 4.803000662358823e-05, "loss": 4.091, "step": 120320 }, { "epoch": 0.01, "learning_rate": 4.802162067607771e-05, "loss": 4.1018, "step": 120832 }, { "epoch": 0.01, "learning_rate": 4.801323472856719e-05, "loss": 4.0975, "step": 121344 }, { "epoch": 0.01, "learning_rate": 4.80048651598604e-05, "loss": 4.0874, "step": 121856 }, { "epoch": 0.02, "learning_rate": 4.799647921234988e-05, "loss": 4.0827, "step": 122368 }, { "epoch": 0.02, "learning_rate": 4.798809326483936e-05, "loss": 4.0765, "step": 122880 }, { "epoch": 0.02, "learning_rate": 4.797970731732884e-05, "loss": 4.0835, "step": 123392 }, { "epoch": 0.02, "learning_rate": 4.797133774862205e-05, "loss": 4.0838, "step": 123904 }, { "epoch": 0.02, "learning_rate": 4.796295180111153e-05, "loss": 4.0765, "step": 124416 }, { "epoch": 0.02, "learning_rate": 4.795456585360101e-05, "loss": 4.0755, "step": 124928 }, { "epoch": 0.02, "learning_rate": 4.794619628489423e-05, "loss": 4.0813, "step": 125440 }, { "epoch": 0.02, "learning_rate": 4.793781033738371e-05, "loss": 4.0877, "step": 125952 }, { "epoch": 0.02, "learning_rate": 4.792942438987319e-05, "loss": 4.0814, "step": 126464 }, { "epoch": 0.02, "learning_rate": 4.792103844236267e-05, "loss": 4.0801, "step": 126976 }, { "epoch": 0.02, "learning_rate": 4.791265249485215e-05, "loss": 4.0857, "step": 127488 }, { "epoch": 0.02, "learning_rate": 4.7904282926145356e-05, "loss": 4.0773, "step": 128000 }, { "epoch": 0.02, "learning_rate": 4.7895896978634836e-05, "loss": 4.0733, "step": 128512 }, { "epoch": 0.02, "learning_rate": 4.7887511031124316e-05, "loss": 4.0864, "step": 129024 }, { "epoch": 0.02, "learning_rate": 4.7879141462417525e-05, "loss": 4.0715, "step": 129536 }, { "epoch": 0.02, "learning_rate": 4.7870755514907005e-05, "loss": 4.0832, "step": 130048 }, { "epoch": 0.02, "learning_rate": 4.7862369567396485e-05, "loss": 4.067, "step": 130560 }, { "epoch": 0.02, "learning_rate": 4.7853983619885965e-05, "loss": 4.0565, "step": 131072 }, { "epoch": 0.02, "learning_rate": 4.7845597672375445e-05, "loss": 4.0647, "step": 131584 }, { "epoch": 0.02, "learning_rate": 4.7837211724864925e-05, "loss": 4.0715, "step": 132096 }, { "epoch": 0.02, "learning_rate": 4.782882577735441e-05, "loss": 4.0653, "step": 132608 }, { "epoch": 0.02, "learning_rate": 4.782043982984389e-05, "loss": 4.0544, "step": 133120 }, { "epoch": 0.02, "learning_rate": 4.78120702611371e-05, "loss": 4.0502, "step": 133632 }, { "epoch": 0.02, "learning_rate": 4.780368431362658e-05, "loss": 4.0637, "step": 134144 }, { "epoch": 0.02, "learning_rate": 4.779529836611606e-05, "loss": 4.073, "step": 134656 }, { "epoch": 0.02, "learning_rate": 4.778691241860554e-05, "loss": 4.061, "step": 135168 }, { "epoch": 0.02, "learning_rate": 4.777854284989875e-05, "loss": 4.0729, "step": 135680 }, { "epoch": 0.02, "learning_rate": 4.777015690238823e-05, "loss": 4.0602, "step": 136192 }, { "epoch": 0.02, "learning_rate": 4.776177095487771e-05, "loss": 4.0618, "step": 136704 }, { "epoch": 0.02, "learning_rate": 4.775338500736719e-05, "loss": 4.0609, "step": 137216 }, { "epoch": 0.02, "learning_rate": 4.774499905985666e-05, "loss": 4.0534, "step": 137728 }, { "epoch": 0.02, "learning_rate": 4.773661311234615e-05, "loss": 4.0502, "step": 138240 }, { "epoch": 0.02, "learning_rate": 4.772822716483563e-05, "loss": 4.0615, "step": 138752 }, { "epoch": 0.02, "learning_rate": 4.771984121732511e-05, "loss": 4.0488, "step": 139264 }, { "epoch": 0.02, "learning_rate": 4.771147164861832e-05, "loss": 4.0523, "step": 139776 }, { "epoch": 0.02, "learning_rate": 4.77030857011078e-05, "loss": 4.0516, "step": 140288 }, { "epoch": 0.02, "learning_rate": 4.769469975359728e-05, "loss": 4.0635, "step": 140800 }, { "epoch": 0.02, "learning_rate": 4.768631380608676e-05, "loss": 4.0408, "step": 141312 }, { "epoch": 0.02, "learning_rate": 4.767794423737997e-05, "loss": 4.0455, "step": 141824 }, { "epoch": 0.02, "learning_rate": 4.766955828986945e-05, "loss": 4.0643, "step": 142336 }, { "epoch": 0.02, "learning_rate": 4.766117234235893e-05, "loss": 4.0427, "step": 142848 }, { "epoch": 0.02, "learning_rate": 4.765278639484841e-05, "loss": 4.0616, "step": 143360 }, { "epoch": 0.02, "learning_rate": 4.7644416826141616e-05, "loss": 4.046, "step": 143872 }, { "epoch": 0.02, "learning_rate": 4.7636030878631096e-05, "loss": 4.0535, "step": 144384 }, { "epoch": 0.02, "learning_rate": 4.762764493112058e-05, "loss": 4.0437, "step": 144896 }, { "epoch": 0.02, "learning_rate": 4.761925898361006e-05, "loss": 4.039, "step": 145408 }, { "epoch": 0.02, "learning_rate": 4.761088941490327e-05, "loss": 4.0437, "step": 145920 }, { "epoch": 0.02, "learning_rate": 4.760250346739275e-05, "loss": 4.0485, "step": 146432 }, { "epoch": 0.02, "learning_rate": 4.759411751988223e-05, "loss": 4.0583, "step": 146944 }, { "epoch": 0.02, "learning_rate": 4.758573157237171e-05, "loss": 4.0512, "step": 147456 }, { "epoch": 0.02, "learning_rate": 4.757736200366492e-05, "loss": 4.0492, "step": 147968 }, { "epoch": 0.02, "learning_rate": 4.75689760561544e-05, "loss": 4.0439, "step": 148480 }, { "epoch": 0.02, "learning_rate": 4.756059010864388e-05, "loss": 4.0309, "step": 148992 }, { "epoch": 0.02, "learning_rate": 4.755220416113336e-05, "loss": 4.0428, "step": 149504 }, { "epoch": 0.02, "learning_rate": 4.754383459242657e-05, "loss": 4.0314, "step": 150016 }, { "epoch": 0.02, "learning_rate": 4.7535465023719786e-05, "loss": 4.0343, "step": 150528 }, { "epoch": 0.02, "learning_rate": 4.7527079076209266e-05, "loss": 4.0394, "step": 151040 }, { "epoch": 0.02, "learning_rate": 4.7518693128698745e-05, "loss": 4.0269, "step": 151552 }, { "epoch": 0.02, "learning_rate": 4.7510307181188225e-05, "loss": 4.0353, "step": 152064 }, { "epoch": 0.02, "learning_rate": 4.7501921233677705e-05, "loss": 4.0312, "step": 152576 }, { "epoch": 0.03, "eval_loss": 4.032494068145752, "eval_runtime": 578.1785, "eval_samples_per_second": 659.988, "eval_steps_per_second": 20.625, "step": 152638 }, { "epoch": 0.0, "learning_rate": 4.7493551664970914e-05, "loss": 4.0392, "step": 153088 }, { "epoch": 0.0, "learning_rate": 4.7485165717460394e-05, "loss": 4.0357, "step": 153600 }, { "epoch": 0.0, "learning_rate": 4.7476779769949874e-05, "loss": 4.0304, "step": 154112 }, { "epoch": 0.0, "learning_rate": 4.7468393822439354e-05, "loss": 4.0282, "step": 154624 }, { "epoch": 0.0, "learning_rate": 4.7460007874928834e-05, "loss": 4.0321, "step": 155136 }, { "epoch": 0.0, "learning_rate": 4.7451621927418314e-05, "loss": 4.0123, "step": 155648 }, { "epoch": 0.0, "learning_rate": 4.7443235979907794e-05, "loss": 4.0277, "step": 156160 }, { "epoch": 0.0, "learning_rate": 4.7434850032397274e-05, "loss": 4.0227, "step": 156672 }, { "epoch": 0.0, "learning_rate": 4.7426464084886754e-05, "loss": 4.0134, "step": 157184 }, { "epoch": 0.0, "learning_rate": 4.741809451617997e-05, "loss": 4.0263, "step": 157696 }, { "epoch": 0.0, "learning_rate": 4.740970856866945e-05, "loss": 4.0318, "step": 158208 }, { "epoch": 0.0, "learning_rate": 4.740132262115893e-05, "loss": 4.015, "step": 158720 }, { "epoch": 0.0, "learning_rate": 4.739293667364841e-05, "loss": 4.0122, "step": 159232 }, { "epoch": 0.0, "learning_rate": 4.738455072613789e-05, "loss": 4.0157, "step": 159744 }, { "epoch": 0.0, "learning_rate": 4.737616477862737e-05, "loss": 4.0181, "step": 160256 }, { "epoch": 0.0, "learning_rate": 4.736777883111685e-05, "loss": 4.0077, "step": 160768 }, { "epoch": 0.0, "learning_rate": 4.735939288360632e-05, "loss": 4.0093, "step": 161280 }, { "epoch": 0.0, "learning_rate": 4.735102331489954e-05, "loss": 4.0118, "step": 161792 }, { "epoch": 0.0, "learning_rate": 4.734263736738902e-05, "loss": 4.014, "step": 162304 }, { "epoch": 0.0, "learning_rate": 4.73342514198785e-05, "loss": 4.0152, "step": 162816 }, { "epoch": 0.0, "learning_rate": 4.732586547236797e-05, "loss": 4.0131, "step": 163328 }, { "epoch": 0.0, "learning_rate": 4.731749590366119e-05, "loss": 4.0191, "step": 163840 }, { "epoch": 0.0, "learning_rate": 4.7309109956150674e-05, "loss": 4.0139, "step": 164352 }, { "epoch": 0.0, "learning_rate": 4.7300724008640154e-05, "loss": 4.0072, "step": 164864 }, { "epoch": 0.0, "learning_rate": 4.729233806112963e-05, "loss": 4.0109, "step": 165376 }, { "epoch": 0.0, "learning_rate": 4.7283968492422844e-05, "loss": 4.0092, "step": 165888 }, { "epoch": 0.0, "learning_rate": 4.7275582544912323e-05, "loss": 4.0132, "step": 166400 }, { "epoch": 0.0, "learning_rate": 4.72671965974018e-05, "loss": 3.9971, "step": 166912 }, { "epoch": 0.0, "learning_rate": 4.725882702869501e-05, "loss": 4.0074, "step": 167424 }, { "epoch": 0.01, "learning_rate": 4.725044108118449e-05, "loss": 3.996, "step": 167936 }, { "epoch": 0.01, "learning_rate": 4.724205513367397e-05, "loss": 4.0018, "step": 168448 }, { "epoch": 0.01, "learning_rate": 4.7233669186163446e-05, "loss": 4.0126, "step": 168960 }, { "epoch": 0.01, "learning_rate": 4.7225283238652926e-05, "loss": 4.0083, "step": 169472 }, { "epoch": 0.01, "learning_rate": 4.721689729114241e-05, "loss": 4.0004, "step": 169984 }, { "epoch": 0.01, "learning_rate": 4.720851134363189e-05, "loss": 3.9945, "step": 170496 }, { "epoch": 0.01, "learning_rate": 4.72001417749251e-05, "loss": 4.0107, "step": 171008 }, { "epoch": 0.01, "learning_rate": 4.719175582741458e-05, "loss": 3.9949, "step": 171520 }, { "epoch": 0.01, "learning_rate": 4.718336987990406e-05, "loss": 4.0012, "step": 172032 }, { "epoch": 0.01, "learning_rate": 4.717498393239354e-05, "loss": 3.9959, "step": 172544 }, { "epoch": 0.01, "learning_rate": 4.716659798488302e-05, "loss": 3.9813, "step": 173056 }, { "epoch": 0.01, "learning_rate": 4.71582120373725e-05, "loss": 3.9833, "step": 173568 }, { "epoch": 0.01, "learning_rate": 4.714982608986198e-05, "loss": 3.9804, "step": 174080 }, { "epoch": 0.01, "learning_rate": 4.714144014235146e-05, "loss": 3.9994, "step": 174592 }, { "epoch": 0.01, "learning_rate": 4.713307057364467e-05, "loss": 3.9874, "step": 175104 }, { "epoch": 0.01, "learning_rate": 4.712468462613415e-05, "loss": 3.9885, "step": 175616 }, { "epoch": 0.01, "learning_rate": 4.711629867862363e-05, "loss": 3.9852, "step": 176128 }, { "epoch": 0.01, "learning_rate": 4.710791273111311e-05, "loss": 3.9858, "step": 176640 }, { "epoch": 0.01, "learning_rate": 4.7099543162406326e-05, "loss": 4.0007, "step": 177152 }, { "epoch": 0.01, "learning_rate": 4.7091157214895806e-05, "loss": 3.9807, "step": 177664 }, { "epoch": 0.01, "learning_rate": 4.7082771267385286e-05, "loss": 3.9798, "step": 178176 }, { "epoch": 0.01, "learning_rate": 4.7074385319874766e-05, "loss": 3.9783, "step": 178688 }, { "epoch": 0.01, "learning_rate": 4.7066015751167975e-05, "loss": 3.9996, "step": 179200 }, { "epoch": 0.01, "learning_rate": 4.7057629803657455e-05, "loss": 3.9722, "step": 179712 }, { "epoch": 0.01, "learning_rate": 4.7049243856146935e-05, "loss": 3.9878, "step": 180224 }, { "epoch": 0.01, "learning_rate": 4.7040857908636415e-05, "loss": 3.9686, "step": 180736 }, { "epoch": 0.01, "learning_rate": 4.7032488339929624e-05, "loss": 3.9832, "step": 181248 }, { "epoch": 0.01, "learning_rate": 4.702411877122283e-05, "loss": 3.9849, "step": 181760 }, { "epoch": 0.01, "learning_rate": 4.701573282371232e-05, "loss": 3.9746, "step": 182272 }, { "epoch": 0.01, "learning_rate": 4.70073468762018e-05, "loss": 3.9794, "step": 182784 }, { "epoch": 0.01, "learning_rate": 4.699896092869128e-05, "loss": 3.9774, "step": 183296 }, { "epoch": 0.01, "learning_rate": 4.699057498118076e-05, "loss": 3.9566, "step": 183808 }, { "epoch": 0.01, "learning_rate": 4.698218903367024e-05, "loss": 3.9758, "step": 184320 }, { "epoch": 0.01, "learning_rate": 4.697381946496345e-05, "loss": 3.979, "step": 184832 }, { "epoch": 0.01, "learning_rate": 4.696543351745293e-05, "loss": 3.9712, "step": 185344 }, { "epoch": 0.01, "learning_rate": 4.695704756994241e-05, "loss": 3.9683, "step": 185856 }, { "epoch": 0.01, "learning_rate": 4.694866162243189e-05, "loss": 3.9718, "step": 186368 }, { "epoch": 0.01, "learning_rate": 4.694027567492137e-05, "loss": 3.956, "step": 186880 }, { "epoch": 0.01, "learning_rate": 4.693188972741085e-05, "loss": 3.9783, "step": 187392 }, { "epoch": 0.01, "learning_rate": 4.692350377990033e-05, "loss": 3.9575, "step": 187904 }, { "epoch": 0.01, "learning_rate": 4.691511783238981e-05, "loss": 3.9659, "step": 188416 }, { "epoch": 0.01, "learning_rate": 4.690674826368302e-05, "loss": 3.9741, "step": 188928 }, { "epoch": 0.01, "learning_rate": 4.68983623161725e-05, "loss": 3.9628, "step": 189440 }, { "epoch": 0.01, "learning_rate": 4.6889976368661984e-05, "loss": 3.9724, "step": 189952 }, { "epoch": 0.01, "learning_rate": 4.688159042115146e-05, "loss": 3.9833, "step": 190464 }, { "epoch": 0.01, "learning_rate": 4.687322085244467e-05, "loss": 3.9698, "step": 190976 }, { "epoch": 0.01, "learning_rate": 4.686483490493415e-05, "loss": 3.9803, "step": 191488 }, { "epoch": 0.01, "learning_rate": 4.685644895742363e-05, "loss": 3.9612, "step": 192000 }, { "epoch": 0.01, "learning_rate": 4.6848063009913106e-05, "loss": 3.9519, "step": 192512 }, { "epoch": 0.01, "learning_rate": 4.683969344120632e-05, "loss": 3.9628, "step": 193024 }, { "epoch": 0.01, "learning_rate": 4.68313074936958e-05, "loss": 3.9744, "step": 193536 }, { "epoch": 0.01, "learning_rate": 4.682292154618528e-05, "loss": 3.9625, "step": 194048 }, { "epoch": 0.01, "learning_rate": 4.6814535598674755e-05, "loss": 3.9531, "step": 194560 }, { "epoch": 0.01, "learning_rate": 4.680616602996797e-05, "loss": 3.949, "step": 195072 }, { "epoch": 0.01, "learning_rate": 4.679778008245745e-05, "loss": 3.9523, "step": 195584 }, { "epoch": 0.01, "learning_rate": 4.678939413494693e-05, "loss": 3.9512, "step": 196096 }, { "epoch": 0.01, "learning_rate": 4.678102456624015e-05, "loss": 3.9569, "step": 196608 }, { "epoch": 0.01, "learning_rate": 4.677263861872963e-05, "loss": 3.9662, "step": 197120 }, { "epoch": 0.01, "learning_rate": 4.676425267121911e-05, "loss": 3.9644, "step": 197632 }, { "epoch": 0.01, "learning_rate": 4.675586672370858e-05, "loss": 3.9562, "step": 198144 }, { "epoch": 0.02, "learning_rate": 4.674748077619806e-05, "loss": 3.9521, "step": 198656 }, { "epoch": 0.02, "learning_rate": 4.673909482868754e-05, "loss": 3.9452, "step": 199168 }, { "epoch": 0.02, "learning_rate": 4.673070888117702e-05, "loss": 3.954, "step": 199680 }, { "epoch": 0.02, "learning_rate": 4.672233931247023e-05, "loss": 3.9498, "step": 200192 }, { "epoch": 0.02, "learning_rate": 4.671395336495971e-05, "loss": 3.9514, "step": 200704 }, { "epoch": 0.02, "learning_rate": 4.670556741744919e-05, "loss": 3.9462, "step": 201216 }, { "epoch": 0.02, "learning_rate": 4.6697181469938675e-05, "loss": 3.9556, "step": 201728 }, { "epoch": 0.02, "learning_rate": 4.6688795522428155e-05, "loss": 3.9553, "step": 202240 }, { "epoch": 0.02, "learning_rate": 4.6680409574917635e-05, "loss": 3.9559, "step": 202752 }, { "epoch": 0.02, "learning_rate": 4.6672023627407115e-05, "loss": 3.9546, "step": 203264 }, { "epoch": 0.02, "learning_rate": 4.6663637679896595e-05, "loss": 3.9569, "step": 203776 }, { "epoch": 0.02, "learning_rate": 4.6655268111189804e-05, "loss": 3.9512, "step": 204288 }, { "epoch": 0.02, "learning_rate": 4.6646898542483013e-05, "loss": 3.9462, "step": 204800 }, { "epoch": 0.02, "learning_rate": 4.6638512594972493e-05, "loss": 3.9636, "step": 205312 }, { "epoch": 0.02, "learning_rate": 4.6630126647461973e-05, "loss": 3.9421, "step": 205824 }, { "epoch": 0.02, "learning_rate": 4.662174069995145e-05, "loss": 3.9638, "step": 206336 }, { "epoch": 0.02, "learning_rate": 4.661335475244093e-05, "loss": 3.9378, "step": 206848 }, { "epoch": 0.02, "learning_rate": 4.660496880493041e-05, "loss": 3.935, "step": 207360 }, { "epoch": 0.02, "learning_rate": 4.659658285741989e-05, "loss": 3.9403, "step": 207872 }, { "epoch": 0.02, "learning_rate": 4.658819690990937e-05, "loss": 3.9524, "step": 208384 }, { "epoch": 0.02, "learning_rate": 4.657982734120259e-05, "loss": 3.9441, "step": 208896 }, { "epoch": 0.02, "learning_rate": 4.657144139369207e-05, "loss": 3.9309, "step": 209408 }, { "epoch": 0.02, "learning_rate": 4.656305544618155e-05, "loss": 3.9299, "step": 209920 }, { "epoch": 0.02, "learning_rate": 4.655466949867103e-05, "loss": 3.94, "step": 210432 }, { "epoch": 0.02, "learning_rate": 4.654628355116051e-05, "loss": 3.9532, "step": 210944 }, { "epoch": 0.02, "learning_rate": 4.653791398245372e-05, "loss": 3.9388, "step": 211456 }, { "epoch": 0.02, "learning_rate": 4.65295280349432e-05, "loss": 3.9527, "step": 211968 }, { "epoch": 0.02, "learning_rate": 4.652114208743268e-05, "loss": 3.9397, "step": 212480 }, { "epoch": 0.02, "learning_rate": 4.651275613992216e-05, "loss": 3.9421, "step": 212992 }, { "epoch": 0.02, "learning_rate": 4.650438657121537e-05, "loss": 3.9473, "step": 213504 }, { "epoch": 0.02, "learning_rate": 4.649600062370485e-05, "loss": 3.9325, "step": 214016 }, { "epoch": 0.02, "learning_rate": 4.648761467619433e-05, "loss": 3.9349, "step": 214528 }, { "epoch": 0.02, "learning_rate": 4.647922872868381e-05, "loss": 3.9412, "step": 215040 }, { "epoch": 0.02, "learning_rate": 4.6470842781173294e-05, "loss": 3.932, "step": 215552 }, { "epoch": 0.02, "learning_rate": 4.646245683366277e-05, "loss": 3.9365, "step": 216064 }, { "epoch": 0.02, "learning_rate": 4.645407088615225e-05, "loss": 3.9363, "step": 216576 }, { "epoch": 0.02, "learning_rate": 4.644568493864173e-05, "loss": 3.9442, "step": 217088 }, { "epoch": 0.02, "learning_rate": 4.643731536993494e-05, "loss": 3.9275, "step": 217600 }, { "epoch": 0.02, "learning_rate": 4.642894580122815e-05, "loss": 3.9262, "step": 218112 }, { "epoch": 0.02, "learning_rate": 4.642055985371763e-05, "loss": 3.9516, "step": 218624 }, { "epoch": 0.02, "learning_rate": 4.641217390620711e-05, "loss": 3.9302, "step": 219136 }, { "epoch": 0.02, "learning_rate": 4.640378795869659e-05, "loss": 3.9444, "step": 219648 }, { "epoch": 0.02, "learning_rate": 4.6395402011186065e-05, "loss": 3.9349, "step": 220160 }, { "epoch": 0.02, "learning_rate": 4.6387016063675545e-05, "loss": 3.9392, "step": 220672 }, { "epoch": 0.02, "learning_rate": 4.637864649496876e-05, "loss": 3.9306, "step": 221184 }, { "epoch": 0.02, "learning_rate": 4.637026054745824e-05, "loss": 3.9261, "step": 221696 }, { "epoch": 0.02, "learning_rate": 4.636187459994772e-05, "loss": 3.9348, "step": 222208 }, { "epoch": 0.02, "learning_rate": 4.63534886524372e-05, "loss": 3.9347, "step": 222720 }, { "epoch": 0.02, "learning_rate": 4.634510270492668e-05, "loss": 3.9459, "step": 223232 }, { "epoch": 0.02, "learning_rate": 4.633671675741616e-05, "loss": 3.9412, "step": 223744 }, { "epoch": 0.02, "learning_rate": 4.632834718870937e-05, "loss": 3.937, "step": 224256 }, { "epoch": 0.02, "learning_rate": 4.631996124119885e-05, "loss": 3.9321, "step": 224768 }, { "epoch": 0.02, "learning_rate": 4.631157529368833e-05, "loss": 3.9226, "step": 225280 }, { "epoch": 0.02, "learning_rate": 4.630318934617781e-05, "loss": 3.9317, "step": 225792 }, { "epoch": 0.02, "learning_rate": 4.629480339866729e-05, "loss": 3.9221, "step": 226304 }, { "epoch": 0.02, "learning_rate": 4.62864338299605e-05, "loss": 3.9265, "step": 226816 }, { "epoch": 0.02, "learning_rate": 4.6278047882449985e-05, "loss": 3.9278, "step": 227328 }, { "epoch": 0.02, "learning_rate": 4.6269661934939465e-05, "loss": 3.9194, "step": 227840 }, { "epoch": 0.02, "learning_rate": 4.6261275987428945e-05, "loss": 3.9265, "step": 228352 }, { "epoch": 0.02, "learning_rate": 4.6252890039918425e-05, "loss": 3.9229, "step": 228864 }, { "epoch": 0.03, "eval_loss": 3.9574086666107178, "eval_runtime": 564.865, "eval_samples_per_second": 675.544, "eval_steps_per_second": 21.111, "step": 228957 }, { "epoch": 0.0, "learning_rate": 4.6244520471211634e-05, "loss": 3.9292, "step": 229376 }, { "epoch": 0.0, "learning_rate": 4.6236134523701114e-05, "loss": 3.932, "step": 229888 }, { "epoch": 0.0, "learning_rate": 4.6227748576190594e-05, "loss": 3.922, "step": 230400 }, { "epoch": 0.0, "learning_rate": 4.6219362628680074e-05, "loss": 3.9237, "step": 230912 }, { "epoch": 0.0, "learning_rate": 4.6210976681169554e-05, "loss": 3.926, "step": 231424 }, { "epoch": 0.0, "learning_rate": 4.6202590733659034e-05, "loss": 3.9066, "step": 231936 }, { "epoch": 0.0, "learning_rate": 4.6194204786148514e-05, "loss": 3.9215, "step": 232448 }, { "epoch": 0.0, "learning_rate": 4.6185818838637994e-05, "loss": 3.9211, "step": 232960 }, { "epoch": 0.0, "learning_rate": 4.6177432891127474e-05, "loss": 3.91, "step": 233472 }, { "epoch": 0.0, "learning_rate": 4.616906332242068e-05, "loss": 3.9218, "step": 233984 }, { "epoch": 0.0, "learning_rate": 4.616067737491017e-05, "loss": 3.9265, "step": 234496 }, { "epoch": 0.0, "learning_rate": 4.615229142739965e-05, "loss": 3.907, "step": 235008 }, { "epoch": 0.0, "learning_rate": 4.614390547988913e-05, "loss": 3.9101, "step": 235520 }, { "epoch": 0.0, "learning_rate": 4.613553591118234e-05, "loss": 3.9142, "step": 236032 }, { "epoch": 0.0, "learning_rate": 4.612714996367182e-05, "loss": 3.9161, "step": 236544 }, { "epoch": 0.0, "learning_rate": 4.61187640161613e-05, "loss": 3.9033, "step": 237056 }, { "epoch": 0.0, "learning_rate": 4.611037806865078e-05, "loss": 3.9057, "step": 237568 }, { "epoch": 0.0, "learning_rate": 4.610199212114025e-05, "loss": 3.9098, "step": 238080 }, { "epoch": 0.0, "learning_rate": 4.609362255243347e-05, "loss": 3.9105, "step": 238592 }, { "epoch": 0.0, "learning_rate": 4.608523660492295e-05, "loss": 3.9163, "step": 239104 }, { "epoch": 0.0, "learning_rate": 4.607685065741242e-05, "loss": 3.9086, "step": 239616 }, { "epoch": 0.0, "learning_rate": 4.606846470990191e-05, "loss": 3.9217, "step": 240128 }, { "epoch": 0.0, "learning_rate": 4.606007876239139e-05, "loss": 3.915, "step": 240640 }, { "epoch": 0.0, "learning_rate": 4.60517091936846e-05, "loss": 3.9098, "step": 241152 }, { "epoch": 0.0, "learning_rate": 4.6043323246174076e-05, "loss": 3.9087, "step": 241664 }, { "epoch": 0.0, "learning_rate": 4.6034937298663556e-05, "loss": 3.9087, "step": 242176 }, { "epoch": 0.0, "learning_rate": 4.6026551351153036e-05, "loss": 3.9156, "step": 242688 }, { "epoch": 0.0, "learning_rate": 4.6018165403642516e-05, "loss": 3.9022, "step": 243200 }, { "epoch": 0.0, "learning_rate": 4.6009795834935725e-05, "loss": 3.9102, "step": 243712 }, { "epoch": 0.01, "learning_rate": 4.6001409887425205e-05, "loss": 3.8993, "step": 244224 }, { "epoch": 0.01, "learning_rate": 4.5993023939914685e-05, "loss": 3.901, "step": 244736 }, { "epoch": 0.01, "learning_rate": 4.5984637992404165e-05, "loss": 3.9155, "step": 245248 }, { "epoch": 0.01, "learning_rate": 4.5976252044893645e-05, "loss": 3.9104, "step": 245760 }, { "epoch": 0.01, "learning_rate": 4.596788247618686e-05, "loss": 3.9049, "step": 246272 }, { "epoch": 0.01, "learning_rate": 4.595949652867634e-05, "loss": 3.9006, "step": 246784 }, { "epoch": 0.01, "learning_rate": 4.595111058116582e-05, "loss": 3.9107, "step": 247296 }, { "epoch": 0.01, "learning_rate": 4.59427246336553e-05, "loss": 3.8988, "step": 247808 }, { "epoch": 0.01, "learning_rate": 4.593435506494851e-05, "loss": 3.9094, "step": 248320 }, { "epoch": 0.01, "learning_rate": 4.592596911743799e-05, "loss": 3.9007, "step": 248832 }, { "epoch": 0.01, "learning_rate": 4.591758316992747e-05, "loss": 3.8862, "step": 249344 }, { "epoch": 0.01, "learning_rate": 4.590919722241695e-05, "loss": 3.8923, "step": 249856 }, { "epoch": 0.01, "learning_rate": 4.590081127490643e-05, "loss": 3.8889, "step": 250368 }, { "epoch": 0.01, "learning_rate": 4.589242532739591e-05, "loss": 3.9023, "step": 250880 }, { "epoch": 0.01, "learning_rate": 4.588405575868912e-05, "loss": 3.893, "step": 251392 }, { "epoch": 0.01, "learning_rate": 4.58756698111786e-05, "loss": 3.8934, "step": 251904 }, { "epoch": 0.01, "learning_rate": 4.586728386366808e-05, "loss": 3.8929, "step": 252416 }, { "epoch": 0.01, "learning_rate": 4.585889791615756e-05, "loss": 3.8963, "step": 252928 }, { "epoch": 0.01, "learning_rate": 4.5850528347450774e-05, "loss": 3.9066, "step": 253440 }, { "epoch": 0.01, "learning_rate": 4.5842142399940254e-05, "loss": 3.8879, "step": 253952 }, { "epoch": 0.01, "learning_rate": 4.5833756452429734e-05, "loss": 3.8866, "step": 254464 }, { "epoch": 0.01, "learning_rate": 4.5825370504919214e-05, "loss": 3.8932, "step": 254976 }, { "epoch": 0.01, "learning_rate": 4.5817000936212423e-05, "loss": 3.9029, "step": 255488 }, { "epoch": 0.01, "learning_rate": 4.58086149887019e-05, "loss": 3.8832, "step": 256000 }, { "epoch": 0.01, "learning_rate": 4.580022904119138e-05, "loss": 3.8951, "step": 256512 }, { "epoch": 0.01, "learning_rate": 4.579184309368086e-05, "loss": 3.8804, "step": 257024 }, { "epoch": 0.01, "learning_rate": 4.578345714617034e-05, "loss": 3.8885, "step": 257536 }, { "epoch": 0.01, "learning_rate": 4.577508757746355e-05, "loss": 3.8978, "step": 258048 }, { "epoch": 0.01, "learning_rate": 4.576670162995303e-05, "loss": 3.8815, "step": 258560 }, { "epoch": 0.01, "learning_rate": 4.575831568244251e-05, "loss": 3.8957, "step": 259072 }, { "epoch": 0.01, "learning_rate": 4.574992973493199e-05, "loss": 3.8903, "step": 259584 }, { "epoch": 0.01, "learning_rate": 4.574154378742148e-05, "loss": 3.8676, "step": 260096 }, { "epoch": 0.01, "learning_rate": 4.573315783991096e-05, "loss": 3.8853, "step": 260608 }, { "epoch": 0.01, "learning_rate": 4.572478827120417e-05, "loss": 3.8881, "step": 261120 }, { "epoch": 0.01, "learning_rate": 4.571640232369365e-05, "loss": 3.8891, "step": 261632 }, { "epoch": 0.01, "learning_rate": 4.570801637618313e-05, "loss": 3.8796, "step": 262144 }, { "epoch": 0.01, "learning_rate": 4.569963042867261e-05, "loss": 3.883, "step": 262656 }, { "epoch": 0.01, "learning_rate": 4.569126085996582e-05, "loss": 3.8679, "step": 263168 }, { "epoch": 0.01, "learning_rate": 4.56828749124553e-05, "loss": 3.8892, "step": 263680 }, { "epoch": 0.01, "learning_rate": 4.567448896494478e-05, "loss": 3.8693, "step": 264192 }, { "epoch": 0.01, "learning_rate": 4.566610301743426e-05, "loss": 3.8801, "step": 264704 }, { "epoch": 0.01, "learning_rate": 4.5657733448727466e-05, "loss": 3.8876, "step": 265216 }, { "epoch": 0.01, "learning_rate": 4.5649347501216946e-05, "loss": 3.8767, "step": 265728 }, { "epoch": 0.01, "learning_rate": 4.564096155370643e-05, "loss": 3.8867, "step": 266240 }, { "epoch": 0.01, "learning_rate": 4.563257560619591e-05, "loss": 3.8927, "step": 266752 }, { "epoch": 0.01, "learning_rate": 4.5624189658685386e-05, "loss": 3.8877, "step": 267264 }, { "epoch": 0.01, "learning_rate": 4.56158200899786e-05, "loss": 3.8956, "step": 267776 }, { "epoch": 0.01, "learning_rate": 4.560743414246808e-05, "loss": 3.8738, "step": 268288 }, { "epoch": 0.01, "learning_rate": 4.5599048194957555e-05, "loss": 3.87, "step": 268800 }, { "epoch": 0.01, "learning_rate": 4.5590662247447035e-05, "loss": 3.8741, "step": 269312 }, { "epoch": 0.01, "learning_rate": 4.5582276299936515e-05, "loss": 3.8926, "step": 269824 }, { "epoch": 0.01, "learning_rate": 4.557390673122973e-05, "loss": 3.8782, "step": 270336 }, { "epoch": 0.01, "learning_rate": 4.5565520783719204e-05, "loss": 3.8682, "step": 270848 }, { "epoch": 0.01, "learning_rate": 4.5557134836208684e-05, "loss": 3.8639, "step": 271360 }, { "epoch": 0.01, "learning_rate": 4.554874888869817e-05, "loss": 3.8725, "step": 271872 }, { "epoch": 0.01, "learning_rate": 4.554036294118765e-05, "loss": 3.8676, "step": 272384 }, { "epoch": 0.01, "learning_rate": 4.553199337248086e-05, "loss": 3.8709, "step": 272896 }, { "epoch": 0.01, "learning_rate": 4.552360742497034e-05, "loss": 3.8801, "step": 273408 }, { "epoch": 0.01, "learning_rate": 4.551522147745982e-05, "loss": 3.8832, "step": 273920 }, { "epoch": 0.01, "learning_rate": 4.55068355299493e-05, "loss": 3.873, "step": 274432 }, { "epoch": 0.02, "learning_rate": 4.549846596124251e-05, "loss": 3.8724, "step": 274944 }, { "epoch": 0.02, "learning_rate": 4.549008001373199e-05, "loss": 3.8614, "step": 275456 }, { "epoch": 0.02, "learning_rate": 4.548169406622147e-05, "loss": 3.8695, "step": 275968 }, { "epoch": 0.02, "learning_rate": 4.547330811871095e-05, "loss": 3.8708, "step": 276480 }, { "epoch": 0.02, "learning_rate": 4.546493855000416e-05, "loss": 3.8691, "step": 276992 }, { "epoch": 0.02, "learning_rate": 4.545655260249364e-05, "loss": 3.8634, "step": 277504 }, { "epoch": 0.02, "learning_rate": 4.5448166654983124e-05, "loss": 3.8761, "step": 278016 }, { "epoch": 0.02, "learning_rate": 4.5439780707472604e-05, "loss": 3.8694, "step": 278528 }, { "epoch": 0.02, "learning_rate": 4.543141113876581e-05, "loss": 3.8814, "step": 279040 }, { "epoch": 0.02, "learning_rate": 4.542302519125529e-05, "loss": 3.8713, "step": 279552 }, { "epoch": 0.02, "learning_rate": 4.541463924374477e-05, "loss": 3.8766, "step": 280064 }, { "epoch": 0.02, "learning_rate": 4.540625329623425e-05, "loss": 3.8706, "step": 280576 }, { "epoch": 0.02, "learning_rate": 4.539788372752746e-05, "loss": 3.8656, "step": 281088 }, { "epoch": 0.02, "learning_rate": 4.538949778001694e-05, "loss": 3.8841, "step": 281600 }, { "epoch": 0.02, "learning_rate": 4.538111183250642e-05, "loss": 3.8636, "step": 282112 }, { "epoch": 0.02, "learning_rate": 4.53727258849959e-05, "loss": 3.8837, "step": 282624 }, { "epoch": 0.02, "learning_rate": 4.536435631628911e-05, "loss": 3.8573, "step": 283136 }, { "epoch": 0.02, "learning_rate": 4.535597036877859e-05, "loss": 3.8587, "step": 283648 }, { "epoch": 0.02, "learning_rate": 4.534758442126808e-05, "loss": 3.8599, "step": 284160 }, { "epoch": 0.02, "learning_rate": 4.533919847375756e-05, "loss": 3.8747, "step": 284672 }, { "epoch": 0.02, "learning_rate": 4.533082890505077e-05, "loss": 3.8657, "step": 285184 }, { "epoch": 0.02, "learning_rate": 4.532244295754025e-05, "loss": 3.8524, "step": 285696 }, { "epoch": 0.02, "learning_rate": 4.531405701002973e-05, "loss": 3.8513, "step": 286208 }, { "epoch": 0.02, "learning_rate": 4.530567106251921e-05, "loss": 3.8615, "step": 286720 }, { "epoch": 0.02, "learning_rate": 4.529728511500869e-05, "loss": 3.8777, "step": 287232 }, { "epoch": 0.02, "learning_rate": 4.5288915546301896e-05, "loss": 3.8614, "step": 287744 }, { "epoch": 0.02, "learning_rate": 4.5280529598791376e-05, "loss": 3.8788, "step": 288256 }, { "epoch": 0.02, "learning_rate": 4.5272143651280856e-05, "loss": 3.8625, "step": 288768 }, { "epoch": 0.02, "learning_rate": 4.5263757703770336e-05, "loss": 3.8655, "step": 289280 }, { "epoch": 0.02, "learning_rate": 4.5255388135063545e-05, "loss": 3.8669, "step": 289792 }, { "epoch": 0.02, "learning_rate": 4.524700218755303e-05, "loss": 3.8565, "step": 290304 }, { "epoch": 0.02, "learning_rate": 4.523861624004251e-05, "loss": 3.8563, "step": 290816 }, { "epoch": 0.02, "learning_rate": 4.523023029253199e-05, "loss": 3.8607, "step": 291328 }, { "epoch": 0.02, "learning_rate": 4.522184434502147e-05, "loss": 3.8582, "step": 291840 }, { "epoch": 0.02, "learning_rate": 4.521347477631468e-05, "loss": 3.8598, "step": 292352 }, { "epoch": 0.02, "learning_rate": 4.520508882880416e-05, "loss": 3.8629, "step": 292864 }, { "epoch": 0.02, "learning_rate": 4.519670288129364e-05, "loss": 3.8645, "step": 293376 }, { "epoch": 0.02, "learning_rate": 4.518831693378312e-05, "loss": 3.852, "step": 293888 }, { "epoch": 0.02, "learning_rate": 4.517994736507633e-05, "loss": 3.8532, "step": 294400 }, { "epoch": 0.02, "learning_rate": 4.517156141756581e-05, "loss": 3.8748, "step": 294912 }, { "epoch": 0.02, "learning_rate": 4.516317547005529e-05, "loss": 3.8532, "step": 295424 }, { "epoch": 0.02, "learning_rate": 4.515478952254477e-05, "loss": 3.8684, "step": 295936 }, { "epoch": 0.02, "learning_rate": 4.514640357503425e-05, "loss": 3.8625, "step": 296448 }, { "epoch": 0.02, "learning_rate": 4.5138034006327465e-05, "loss": 3.8635, "step": 296960 }, { "epoch": 0.02, "learning_rate": 4.5129648058816945e-05, "loss": 3.8537, "step": 297472 }, { "epoch": 0.02, "learning_rate": 4.5121262111306425e-05, "loss": 3.8563, "step": 297984 }, { "epoch": 0.02, "learning_rate": 4.5112876163795905e-05, "loss": 3.8565, "step": 298496 }, { "epoch": 0.02, "learning_rate": 4.5104506595089114e-05, "loss": 3.8602, "step": 299008 }, { "epoch": 0.02, "learning_rate": 4.5096120647578594e-05, "loss": 3.8743, "step": 299520 }, { "epoch": 0.02, "learning_rate": 4.5087734700068074e-05, "loss": 3.8604, "step": 300032 }, { "epoch": 0.02, "learning_rate": 4.5079348752557554e-05, "loss": 3.8658, "step": 300544 }, { "epoch": 0.02, "learning_rate": 4.507097918385076e-05, "loss": 3.8636, "step": 301056 }, { "epoch": 0.02, "learning_rate": 4.506259323634024e-05, "loss": 3.8489, "step": 301568 }, { "epoch": 0.02, "learning_rate": 4.505420728882972e-05, "loss": 3.8572, "step": 302080 }, { "epoch": 0.02, "learning_rate": 4.50458213413192e-05, "loss": 3.8483, "step": 302592 }, { "epoch": 0.02, "learning_rate": 4.503745177261242e-05, "loss": 3.8531, "step": 303104 }, { "epoch": 0.02, "learning_rate": 4.50290658251019e-05, "loss": 3.8544, "step": 303616 }, { "epoch": 0.02, "learning_rate": 4.502067987759138e-05, "loss": 3.8501, "step": 304128 }, { "epoch": 0.02, "learning_rate": 4.501229393008086e-05, "loss": 3.848, "step": 304640 }, { "epoch": 0.02, "learning_rate": 4.500392436137407e-05, "loss": 3.8541, "step": 305152 }, { "epoch": 0.03, "eval_loss": 3.9159610271453857, "eval_runtime": 566.2921, "eval_samples_per_second": 673.841, "eval_steps_per_second": 21.058, "step": 305276 }, { "epoch": 0.0, "learning_rate": 4.499553841386355e-05, "loss": 3.8595, "step": 305664 }, { "epoch": 0.0, "learning_rate": 4.498715246635303e-05, "loss": 3.8573, "step": 306176 }, { "epoch": 0.0, "learning_rate": 4.497876651884251e-05, "loss": 3.853, "step": 306688 }, { "epoch": 0.0, "learning_rate": 4.497038057133199e-05, "loss": 3.8488, "step": 307200 }, { "epoch": 0.0, "learning_rate": 4.496199462382146e-05, "loss": 3.8587, "step": 307712 }, { "epoch": 0.0, "learning_rate": 4.495360867631094e-05, "loss": 3.8354, "step": 308224 }, { "epoch": 0.0, "learning_rate": 4.494522272880042e-05, "loss": 3.8544, "step": 308736 }, { "epoch": 0.0, "learning_rate": 4.49368367812899e-05, "loss": 3.8441, "step": 309248 }, { "epoch": 0.0, "learning_rate": 4.4928467212583116e-05, "loss": 3.8414, "step": 309760 }, { "epoch": 0.0, "learning_rate": 4.4920081265072596e-05, "loss": 3.8497, "step": 310272 }, { "epoch": 0.0, "learning_rate": 4.4911695317562076e-05, "loss": 3.8534, "step": 310784 }, { "epoch": 0.0, "learning_rate": 4.4903309370051556e-05, "loss": 3.8358, "step": 311296 }, { "epoch": 0.0, "learning_rate": 4.4894939801344765e-05, "loss": 3.8433, "step": 311808 }, { "epoch": 0.0, "learning_rate": 4.4886553853834245e-05, "loss": 3.8429, "step": 312320 }, { "epoch": 0.0, "learning_rate": 4.4878167906323725e-05, "loss": 3.8473, "step": 312832 }, { "epoch": 0.0, "learning_rate": 4.4869781958813205e-05, "loss": 3.8305, "step": 313344 }, { "epoch": 0.0, "learning_rate": 4.4861412390106414e-05, "loss": 3.835, "step": 313856 }, { "epoch": 0.0, "learning_rate": 4.4853026442595894e-05, "loss": 3.8385, "step": 314368 }, { "epoch": 0.0, "learning_rate": 4.4844640495085374e-05, "loss": 3.8391, "step": 314880 }, { "epoch": 0.0, "learning_rate": 4.4836254547574854e-05, "loss": 3.8492, "step": 315392 }, { "epoch": 0.0, "learning_rate": 4.482788497886807e-05, "loss": 3.8408, "step": 315904 }, { "epoch": 0.0, "learning_rate": 4.481949903135755e-05, "loss": 3.8554, "step": 316416 }, { "epoch": 0.0, "learning_rate": 4.481111308384703e-05, "loss": 3.849, "step": 316928 }, { "epoch": 0.0, "learning_rate": 4.480272713633651e-05, "loss": 3.8434, "step": 317440 }, { "epoch": 0.0, "learning_rate": 4.479435756762972e-05, "loss": 3.8385, "step": 317952 }, { "epoch": 0.0, "learning_rate": 4.47859716201192e-05, "loss": 3.8404, "step": 318464 }, { "epoch": 0.0, "learning_rate": 4.477758567260868e-05, "loss": 3.8482, "step": 318976 }, { "epoch": 0.0, "learning_rate": 4.476919972509816e-05, "loss": 3.8368, "step": 319488 }, { "epoch": 0.0, "learning_rate": 4.476083015639137e-05, "loss": 3.8398, "step": 320000 }, { "epoch": 0.0, "learning_rate": 4.475244420888085e-05, "loss": 3.8395, "step": 320512 }, { "epoch": 0.01, "learning_rate": 4.474405826137033e-05, "loss": 3.8286, "step": 321024 }, { "epoch": 0.01, "learning_rate": 4.473567231385981e-05, "loss": 3.8452, "step": 321536 }, { "epoch": 0.01, "learning_rate": 4.4727302745153024e-05, "loss": 3.8499, "step": 322048 }, { "epoch": 0.01, "learning_rate": 4.4718916797642504e-05, "loss": 3.8394, "step": 322560 }, { "epoch": 0.01, "learning_rate": 4.4710530850131984e-05, "loss": 3.8344, "step": 323072 }, { "epoch": 0.01, "learning_rate": 4.4702144902621464e-05, "loss": 3.8415, "step": 323584 }, { "epoch": 0.01, "learning_rate": 4.469377533391467e-05, "loss": 3.8389, "step": 324096 }, { "epoch": 0.01, "learning_rate": 4.468538938640415e-05, "loss": 3.8383, "step": 324608 }, { "epoch": 0.01, "learning_rate": 4.467700343889363e-05, "loss": 3.8345, "step": 325120 }, { "epoch": 0.01, "learning_rate": 4.466861749138311e-05, "loss": 3.8209, "step": 325632 }, { "epoch": 0.01, "learning_rate": 4.466024792267632e-05, "loss": 3.8272, "step": 326144 }, { "epoch": 0.01, "learning_rate": 4.46518619751658e-05, "loss": 3.822, "step": 326656 }, { "epoch": 0.01, "learning_rate": 4.464347602765528e-05, "loss": 3.8379, "step": 327168 }, { "epoch": 0.01, "learning_rate": 4.463509008014476e-05, "loss": 3.8281, "step": 327680 }, { "epoch": 0.01, "learning_rate": 4.462672051143798e-05, "loss": 3.8294, "step": 328192 }, { "epoch": 0.01, "learning_rate": 4.461833456392746e-05, "loss": 3.8279, "step": 328704 }, { "epoch": 0.01, "learning_rate": 4.460994861641694e-05, "loss": 3.8307, "step": 329216 }, { "epoch": 0.01, "learning_rate": 4.460156266890642e-05, "loss": 3.8435, "step": 329728 }, { "epoch": 0.01, "learning_rate": 4.4593193100199626e-05, "loss": 3.8242, "step": 330240 }, { "epoch": 0.01, "learning_rate": 4.4584807152689106e-05, "loss": 3.8199, "step": 330752 }, { "epoch": 0.01, "learning_rate": 4.4576421205178586e-05, "loss": 3.8306, "step": 331264 }, { "epoch": 0.01, "learning_rate": 4.4568035257668066e-05, "loss": 3.8344, "step": 331776 }, { "epoch": 0.01, "learning_rate": 4.4559665688961275e-05, "loss": 3.8232, "step": 332288 }, { "epoch": 0.01, "learning_rate": 4.4551279741450755e-05, "loss": 3.8274, "step": 332800 }, { "epoch": 0.01, "learning_rate": 4.4542893793940235e-05, "loss": 3.8201, "step": 333312 }, { "epoch": 0.01, "learning_rate": 4.4534507846429715e-05, "loss": 3.8244, "step": 333824 }, { "epoch": 0.01, "learning_rate": 4.452613827772293e-05, "loss": 3.8328, "step": 334336 }, { "epoch": 0.01, "learning_rate": 4.451775233021241e-05, "loss": 3.8158, "step": 334848 }, { "epoch": 0.01, "learning_rate": 4.450936638270189e-05, "loss": 3.8347, "step": 335360 }, { "epoch": 0.01, "learning_rate": 4.450098043519137e-05, "loss": 3.8245, "step": 335872 }, { "epoch": 0.01, "learning_rate": 4.449261086648458e-05, "loss": 3.8085, "step": 336384 }, { "epoch": 0.01, "learning_rate": 4.448422491897406e-05, "loss": 3.8192, "step": 336896 }, { "epoch": 0.01, "learning_rate": 4.447583897146354e-05, "loss": 3.8259, "step": 337408 }, { "epoch": 0.01, "learning_rate": 4.446745302395302e-05, "loss": 3.8321, "step": 337920 }, { "epoch": 0.01, "learning_rate": 4.445908345524623e-05, "loss": 3.8159, "step": 338432 }, { "epoch": 0.01, "learning_rate": 4.445069750773571e-05, "loss": 3.8217, "step": 338944 }, { "epoch": 0.01, "learning_rate": 4.444231156022519e-05, "loss": 3.8022, "step": 339456 }, { "epoch": 0.01, "learning_rate": 4.443392561271467e-05, "loss": 3.8266, "step": 339968 }, { "epoch": 0.01, "learning_rate": 4.4425556044007885e-05, "loss": 3.8114, "step": 340480 }, { "epoch": 0.01, "learning_rate": 4.4417170096497365e-05, "loss": 3.8174, "step": 340992 }, { "epoch": 0.01, "learning_rate": 4.4408784148986845e-05, "loss": 3.8263, "step": 341504 }, { "epoch": 0.01, "learning_rate": 4.4400398201476325e-05, "loss": 3.8156, "step": 342016 }, { "epoch": 0.01, "learning_rate": 4.4392028632769534e-05, "loss": 3.8214, "step": 342528 }, { "epoch": 0.01, "learning_rate": 4.4383642685259014e-05, "loss": 3.8307, "step": 343040 }, { "epoch": 0.01, "learning_rate": 4.4375256737748494e-05, "loss": 3.826, "step": 343552 }, { "epoch": 0.01, "learning_rate": 4.4366870790237974e-05, "loss": 3.8312, "step": 344064 }, { "epoch": 0.01, "learning_rate": 4.435850122153118e-05, "loss": 3.816, "step": 344576 }, { "epoch": 0.01, "learning_rate": 4.435011527402066e-05, "loss": 3.8102, "step": 345088 }, { "epoch": 0.01, "learning_rate": 4.434172932651014e-05, "loss": 3.8146, "step": 345600 }, { "epoch": 0.01, "learning_rate": 4.433334337899962e-05, "loss": 3.8297, "step": 346112 }, { "epoch": 0.01, "learning_rate": 4.432497381029284e-05, "loss": 3.817, "step": 346624 }, { "epoch": 0.01, "learning_rate": 4.431658786278232e-05, "loss": 3.8097, "step": 347136 }, { "epoch": 0.01, "learning_rate": 4.43082019152718e-05, "loss": 3.801, "step": 347648 }, { "epoch": 0.01, "learning_rate": 4.429981596776128e-05, "loss": 3.8144, "step": 348160 }, { "epoch": 0.01, "learning_rate": 4.429144639905449e-05, "loss": 3.8046, "step": 348672 }, { "epoch": 0.01, "learning_rate": 4.428306045154397e-05, "loss": 3.8164, "step": 349184 }, { "epoch": 0.01, "learning_rate": 4.427467450403345e-05, "loss": 3.8152, "step": 349696 }, { "epoch": 0.01, "learning_rate": 4.426628855652293e-05, "loss": 3.8258, "step": 350208 }, { "epoch": 0.01, "learning_rate": 4.4257918987816136e-05, "loss": 3.8118, "step": 350720 }, { "epoch": 0.02, "learning_rate": 4.4249533040305616e-05, "loss": 3.8141, "step": 351232 }, { "epoch": 0.02, "learning_rate": 4.4241147092795096e-05, "loss": 3.8012, "step": 351744 }, { "epoch": 0.02, "learning_rate": 4.4232761145284576e-05, "loss": 3.8105, "step": 352256 }, { "epoch": 0.02, "learning_rate": 4.422439157657779e-05, "loss": 3.8145, "step": 352768 }, { "epoch": 0.02, "learning_rate": 4.421600562906727e-05, "loss": 3.8076, "step": 353280 }, { "epoch": 0.02, "learning_rate": 4.420761968155675e-05, "loss": 3.8059, "step": 353792 }, { "epoch": 0.02, "learning_rate": 4.419923373404623e-05, "loss": 3.819, "step": 354304 }, { "epoch": 0.02, "learning_rate": 4.419086416533944e-05, "loss": 3.8069, "step": 354816 }, { "epoch": 0.02, "learning_rate": 4.418247821782892e-05, "loss": 3.8285, "step": 355328 }, { "epoch": 0.02, "learning_rate": 4.41740922703184e-05, "loss": 3.8099, "step": 355840 }, { "epoch": 0.02, "learning_rate": 4.416570632280788e-05, "loss": 3.8172, "step": 356352 }, { "epoch": 0.02, "learning_rate": 4.415733675410109e-05, "loss": 3.8105, "step": 356864 }, { "epoch": 0.02, "learning_rate": 4.414895080659057e-05, "loss": 3.8067, "step": 357376 }, { "epoch": 0.02, "learning_rate": 4.414056485908005e-05, "loss": 3.8259, "step": 357888 }, { "epoch": 0.02, "learning_rate": 4.413217891156953e-05, "loss": 3.8043, "step": 358400 }, { "epoch": 0.02, "learning_rate": 4.4123809342862746e-05, "loss": 3.8233, "step": 358912 }, { "epoch": 0.02, "learning_rate": 4.4115423395352226e-05, "loss": 3.8015, "step": 359424 }, { "epoch": 0.02, "learning_rate": 4.4107037447841706e-05, "loss": 3.8036, "step": 359936 }, { "epoch": 0.02, "learning_rate": 4.4098651500331186e-05, "loss": 3.7995, "step": 360448 }, { "epoch": 0.02, "learning_rate": 4.4090281931624395e-05, "loss": 3.8133, "step": 360960 }, { "epoch": 0.02, "learning_rate": 4.4081895984113875e-05, "loss": 3.8119, "step": 361472 }, { "epoch": 0.02, "learning_rate": 4.4073510036603355e-05, "loss": 3.7984, "step": 361984 }, { "epoch": 0.02, "learning_rate": 4.4065124089092835e-05, "loss": 3.7902, "step": 362496 }, { "epoch": 0.02, "learning_rate": 4.4056754520386044e-05, "loss": 3.8034, "step": 363008 }, { "epoch": 0.02, "learning_rate": 4.4048368572875524e-05, "loss": 3.821, "step": 363520 }, { "epoch": 0.02, "learning_rate": 4.4039982625365004e-05, "loss": 3.8011, "step": 364032 }, { "epoch": 0.02, "learning_rate": 4.4031596677854484e-05, "loss": 3.8213, "step": 364544 }, { "epoch": 0.02, "learning_rate": 4.40232271091477e-05, "loss": 3.807, "step": 365056 }, { "epoch": 0.02, "learning_rate": 4.401484116163718e-05, "loss": 3.8092, "step": 365568 }, { "epoch": 0.02, "learning_rate": 4.400645521412666e-05, "loss": 3.8127, "step": 366080 }, { "epoch": 0.02, "learning_rate": 4.399806926661613e-05, "loss": 3.8004, "step": 366592 }, { "epoch": 0.02, "learning_rate": 4.398969969790935e-05, "loss": 3.7988, "step": 367104 }, { "epoch": 0.02, "learning_rate": 4.398131375039883e-05, "loss": 3.8038, "step": 367616 }, { "epoch": 0.02, "learning_rate": 4.397292780288831e-05, "loss": 3.8042, "step": 368128 }, { "epoch": 0.02, "learning_rate": 4.396454185537778e-05, "loss": 3.803, "step": 368640 }, { "epoch": 0.02, "learning_rate": 4.3956172286671e-05, "loss": 3.8049, "step": 369152 }, { "epoch": 0.02, "learning_rate": 4.394778633916048e-05, "loss": 3.8085, "step": 369664 }, { "epoch": 0.02, "learning_rate": 4.393940039164996e-05, "loss": 3.7962, "step": 370176 }, { "epoch": 0.02, "learning_rate": 4.393101444413944e-05, "loss": 3.7975, "step": 370688 }, { "epoch": 0.02, "learning_rate": 4.392264487543265e-05, "loss": 3.8143, "step": 371200 }, { "epoch": 0.02, "learning_rate": 4.391425892792213e-05, "loss": 3.7978, "step": 371712 }, { "epoch": 0.02, "learning_rate": 4.3905872980411606e-05, "loss": 3.8125, "step": 372224 }, { "epoch": 0.02, "learning_rate": 4.3897487032901086e-05, "loss": 3.8108, "step": 372736 }, { "epoch": 0.02, "learning_rate": 4.38891174641943e-05, "loss": 3.8048, "step": 373248 }, { "epoch": 0.02, "learning_rate": 4.388073151668378e-05, "loss": 3.8021, "step": 373760 }, { "epoch": 0.02, "learning_rate": 4.3872345569173255e-05, "loss": 3.8, "step": 374272 }, { "epoch": 0.02, "learning_rate": 4.3863959621662735e-05, "loss": 3.8015, "step": 374784 }, { "epoch": 0.02, "learning_rate": 4.385559005295595e-05, "loss": 3.8038, "step": 375296 }, { "epoch": 0.02, "learning_rate": 4.3847204105445424e-05, "loss": 3.817, "step": 375808 }, { "epoch": 0.02, "learning_rate": 4.383881815793491e-05, "loss": 3.8095, "step": 376320 }, { "epoch": 0.02, "learning_rate": 4.383043221042439e-05, "loss": 3.8093, "step": 376832 }, { "epoch": 0.02, "learning_rate": 4.382206264171761e-05, "loss": 3.8086, "step": 377344 }, { "epoch": 0.02, "learning_rate": 4.381367669420708e-05, "loss": 3.796, "step": 377856 }, { "epoch": 0.02, "learning_rate": 4.380529074669656e-05, "loss": 3.8015, "step": 378368 }, { "epoch": 0.02, "learning_rate": 4.379690479918604e-05, "loss": 3.7937, "step": 378880 }, { "epoch": 0.02, "learning_rate": 4.3788551609282985e-05, "loss": 3.7991, "step": 379392 }, { "epoch": 0.02, "learning_rate": 4.3780165661772465e-05, "loss": 3.8024, "step": 379904 }, { "epoch": 0.02, "learning_rate": 4.3771779714261945e-05, "loss": 3.7955, "step": 380416 }, { "epoch": 0.02, "learning_rate": 4.3763393766751425e-05, "loss": 3.7904, "step": 380928 }, { "epoch": 0.02, "learning_rate": 4.37550078192409e-05, "loss": 3.8015, "step": 381440 }, { "epoch": 0.03, "eval_loss": 3.891148805618286, "eval_runtime": 571.8978, "eval_samples_per_second": 667.236, "eval_steps_per_second": 20.852, "step": 381595 }, { "epoch": 0.0, "learning_rate": 4.374662187173038e-05, "loss": 3.8075, "step": 381952 }, { "epoch": 0.0, "learning_rate": 4.3738235924219865e-05, "loss": 3.8014, "step": 382464 }, { "epoch": 0.0, "learning_rate": 4.3729849976709345e-05, "loss": 3.8007, "step": 382976 }, { "epoch": 0.0, "learning_rate": 4.3721464029198824e-05, "loss": 3.7977, "step": 383488 }, { "epoch": 0.0, "learning_rate": 4.3713078081688304e-05, "loss": 3.8, "step": 384000 }, { "epoch": 0.0, "learning_rate": 4.3704692134177784e-05, "loss": 3.7856, "step": 384512 }, { "epoch": 0.0, "learning_rate": 4.3696306186667264e-05, "loss": 3.7983, "step": 385024 }, { "epoch": 0.0, "learning_rate": 4.3687920239156744e-05, "loss": 3.7881, "step": 385536 }, { "epoch": 0.0, "learning_rate": 4.3679550670449953e-05, "loss": 3.7936, "step": 386048 }, { "epoch": 0.0, "learning_rate": 4.367118110174316e-05, "loss": 3.7968, "step": 386560 }, { "epoch": 0.0, "learning_rate": 4.366279515423264e-05, "loss": 3.799, "step": 387072 }, { "epoch": 0.0, "learning_rate": 4.365440920672212e-05, "loss": 3.7827, "step": 387584 }, { "epoch": 0.0, "learning_rate": 4.36460232592116e-05, "loss": 3.7929, "step": 388096 }, { "epoch": 0.0, "learning_rate": 4.363763731170108e-05, "loss": 3.7875, "step": 388608 }, { "epoch": 0.0, "learning_rate": 4.362925136419056e-05, "loss": 3.794, "step": 389120 }, { "epoch": 0.0, "learning_rate": 4.362086541668005e-05, "loss": 3.781, "step": 389632 }, { "epoch": 0.0, "learning_rate": 4.361247946916953e-05, "loss": 3.7814, "step": 390144 }, { "epoch": 0.0, "learning_rate": 4.360410990046274e-05, "loss": 3.7854, "step": 390656 }, { "epoch": 0.0, "learning_rate": 4.359572395295222e-05, "loss": 3.7888, "step": 391168 }, { "epoch": 0.0, "learning_rate": 4.35873380054417e-05, "loss": 3.7982, "step": 391680 }, { "epoch": 0.0, "learning_rate": 4.357895205793118e-05, "loss": 3.7865, "step": 392192 }, { "epoch": 0.0, "learning_rate": 4.357058248922439e-05, "loss": 3.8057, "step": 392704 }, { "epoch": 0.0, "learning_rate": 4.356219654171387e-05, "loss": 3.7933, "step": 393216 }, { "epoch": 0.0, "learning_rate": 4.355381059420335e-05, "loss": 3.7938, "step": 393728 }, { "epoch": 0.0, "learning_rate": 4.354542464669283e-05, "loss": 3.7863, "step": 394240 }, { "epoch": 0.0, "learning_rate": 4.3537055077986036e-05, "loss": 3.7871, "step": 394752 }, { "epoch": 0.0, "learning_rate": 4.3528669130475516e-05, "loss": 3.7975, "step": 395264 }, { "epoch": 0.0, "learning_rate": 4.3520283182964996e-05, "loss": 3.7841, "step": 395776 }, { "epoch": 0.0, "learning_rate": 4.351189723545448e-05, "loss": 3.7895, "step": 396288 }, { "epoch": 0.0, "learning_rate": 4.350352766674769e-05, "loss": 3.7861, "step": 396800 }, { "epoch": 0.01, "learning_rate": 4.349514171923717e-05, "loss": 3.7761, "step": 397312 }, { "epoch": 0.01, "learning_rate": 4.348675577172665e-05, "loss": 3.7958, "step": 397824 }, { "epoch": 0.01, "learning_rate": 4.347836982421613e-05, "loss": 3.7949, "step": 398336 }, { "epoch": 0.01, "learning_rate": 4.347000025550934e-05, "loss": 3.792, "step": 398848 }, { "epoch": 0.01, "learning_rate": 4.346161430799882e-05, "loss": 3.7812, "step": 399360 }, { "epoch": 0.01, "learning_rate": 4.34532283604883e-05, "loss": 3.7924, "step": 399872 }, { "epoch": 0.01, "learning_rate": 4.344484241297778e-05, "loss": 3.7817, "step": 400384 }, { "epoch": 0.01, "learning_rate": 4.343647284427099e-05, "loss": 3.7917, "step": 400896 }, { "epoch": 0.01, "learning_rate": 4.342808689676047e-05, "loss": 3.7845, "step": 401408 }, { "epoch": 0.01, "learning_rate": 4.341970094924995e-05, "loss": 3.7697, "step": 401920 }, { "epoch": 0.01, "learning_rate": 4.3411315001739436e-05, "loss": 3.777, "step": 402432 }, { "epoch": 0.01, "learning_rate": 4.3402945433032645e-05, "loss": 3.7685, "step": 402944 }, { "epoch": 0.01, "learning_rate": 4.3394559485522125e-05, "loss": 3.791, "step": 403456 }, { "epoch": 0.01, "learning_rate": 4.3386173538011605e-05, "loss": 3.7781, "step": 403968 }, { "epoch": 0.01, "learning_rate": 4.3377787590501085e-05, "loss": 3.7735, "step": 404480 }, { "epoch": 0.01, "learning_rate": 4.3369418021794294e-05, "loss": 3.782, "step": 404992 }, { "epoch": 0.01, "learning_rate": 4.3361032074283774e-05, "loss": 3.7813, "step": 405504 }, { "epoch": 0.01, "learning_rate": 4.3352646126773254e-05, "loss": 3.7924, "step": 406016 }, { "epoch": 0.01, "learning_rate": 4.3344260179262734e-05, "loss": 3.7721, "step": 406528 }, { "epoch": 0.01, "learning_rate": 4.333589061055594e-05, "loss": 3.773, "step": 407040 }, { "epoch": 0.01, "learning_rate": 4.332750466304542e-05, "loss": 3.7822, "step": 407552 }, { "epoch": 0.01, "learning_rate": 4.33191187155349e-05, "loss": 3.7809, "step": 408064 }, { "epoch": 0.01, "learning_rate": 4.331073276802439e-05, "loss": 3.7742, "step": 408576 }, { "epoch": 0.01, "learning_rate": 4.33023631993176e-05, "loss": 3.7758, "step": 409088 }, { "epoch": 0.01, "learning_rate": 4.329397725180708e-05, "loss": 3.7718, "step": 409600 }, { "epoch": 0.01, "learning_rate": 4.328559130429656e-05, "loss": 3.7789, "step": 410112 }, { "epoch": 0.01, "learning_rate": 4.327720535678604e-05, "loss": 3.7797, "step": 410624 }, { "epoch": 0.01, "learning_rate": 4.326883578807925e-05, "loss": 3.7731, "step": 411136 }, { "epoch": 0.01, "learning_rate": 4.326044984056873e-05, "loss": 3.7849, "step": 411648 }, { "epoch": 0.01, "learning_rate": 4.325206389305821e-05, "loss": 3.7735, "step": 412160 }, { "epoch": 0.01, "learning_rate": 4.324367794554768e-05, "loss": 3.7643, "step": 412672 }, { "epoch": 0.01, "learning_rate": 4.32353083768409e-05, "loss": 3.7699, "step": 413184 }, { "epoch": 0.01, "learning_rate": 4.322692242933038e-05, "loss": 3.7698, "step": 413696 }, { "epoch": 0.01, "learning_rate": 4.321853648181986e-05, "loss": 3.7907, "step": 414208 }, { "epoch": 0.01, "learning_rate": 4.321015053430934e-05, "loss": 3.7675, "step": 414720 }, { "epoch": 0.01, "learning_rate": 4.320178096560255e-05, "loss": 3.7727, "step": 415232 }, { "epoch": 0.01, "learning_rate": 4.319339501809203e-05, "loss": 3.7568, "step": 415744 }, { "epoch": 0.01, "learning_rate": 4.3185009070581506e-05, "loss": 3.7747, "step": 416256 }, { "epoch": 0.01, "learning_rate": 4.3176623123070986e-05, "loss": 3.765, "step": 416768 }, { "epoch": 0.01, "learning_rate": 4.31682535543642e-05, "loss": 3.766, "step": 417280 }, { "epoch": 0.01, "learning_rate": 4.315986760685368e-05, "loss": 3.778, "step": 417792 }, { "epoch": 0.01, "learning_rate": 4.3151481659343155e-05, "loss": 3.7696, "step": 418304 }, { "epoch": 0.01, "learning_rate": 4.314311209063637e-05, "loss": 3.7726, "step": 418816 }, { "epoch": 0.01, "learning_rate": 4.313472614312585e-05, "loss": 3.7824, "step": 419328 }, { "epoch": 0.01, "learning_rate": 4.312634019561533e-05, "loss": 3.7763, "step": 419840 }, { "epoch": 0.01, "learning_rate": 4.3117970626908546e-05, "loss": 3.7864, "step": 420352 }, { "epoch": 0.01, "learning_rate": 4.3109584679398026e-05, "loss": 3.7691, "step": 420864 }, { "epoch": 0.01, "learning_rate": 4.3101198731887506e-05, "loss": 3.7608, "step": 421376 }, { "epoch": 0.01, "learning_rate": 4.309281278437698e-05, "loss": 3.767, "step": 421888 }, { "epoch": 0.01, "learning_rate": 4.308442683686646e-05, "loss": 3.7827, "step": 422400 }, { "epoch": 0.01, "learning_rate": 4.307604088935594e-05, "loss": 3.769, "step": 422912 }, { "epoch": 0.01, "learning_rate": 4.306765494184542e-05, "loss": 3.7642, "step": 423424 }, { "epoch": 0.01, "learning_rate": 4.30592689943349e-05, "loss": 3.7537, "step": 423936 }, { "epoch": 0.01, "learning_rate": 4.305089942562811e-05, "loss": 3.7683, "step": 424448 }, { "epoch": 0.01, "learning_rate": 4.3042529856921324e-05, "loss": 3.7536, "step": 424960 }, { "epoch": 0.01, "learning_rate": 4.3034143909410804e-05, "loss": 3.7687, "step": 425472 }, { "epoch": 0.01, "learning_rate": 4.3025757961900284e-05, "loss": 3.7705, "step": 425984 }, { "epoch": 0.01, "learning_rate": 4.3017372014389764e-05, "loss": 3.7755, "step": 426496 }, { "epoch": 0.01, "learning_rate": 4.3008986066879244e-05, "loss": 3.7691, "step": 427008 }, { "epoch": 0.02, "learning_rate": 4.3000600119368724e-05, "loss": 3.7681, "step": 427520 }, { "epoch": 0.02, "learning_rate": 4.2992214171858204e-05, "loss": 3.7549, "step": 428032 }, { "epoch": 0.02, "learning_rate": 4.2983828224347684e-05, "loss": 3.7652, "step": 428544 }, { "epoch": 0.02, "learning_rate": 4.297545865564089e-05, "loss": 3.7661, "step": 429056 }, { "epoch": 0.02, "learning_rate": 4.296707270813037e-05, "loss": 3.764, "step": 429568 }, { "epoch": 0.02, "learning_rate": 4.295868676061985e-05, "loss": 3.7585, "step": 430080 }, { "epoch": 0.02, "learning_rate": 4.295030081310933e-05, "loss": 3.7751, "step": 430592 }, { "epoch": 0.02, "learning_rate": 4.294193124440254e-05, "loss": 3.7603, "step": 431104 }, { "epoch": 0.02, "learning_rate": 4.293354529689202e-05, "loss": 3.7858, "step": 431616 }, { "epoch": 0.02, "learning_rate": 4.29251593493815e-05, "loss": 3.7587, "step": 432128 }, { "epoch": 0.02, "learning_rate": 4.291677340187099e-05, "loss": 3.7743, "step": 432640 }, { "epoch": 0.02, "learning_rate": 4.29084038331642e-05, "loss": 3.7624, "step": 433152 }, { "epoch": 0.02, "learning_rate": 4.290001788565368e-05, "loss": 3.7626, "step": 433664 }, { "epoch": 0.02, "learning_rate": 4.289163193814316e-05, "loss": 3.7819, "step": 434176 }, { "epoch": 0.02, "learning_rate": 4.288324599063264e-05, "loss": 3.7576, "step": 434688 }, { "epoch": 0.02, "learning_rate": 4.287487642192585e-05, "loss": 3.7778, "step": 435200 }, { "epoch": 0.02, "learning_rate": 4.286649047441533e-05, "loss": 3.7572, "step": 435712 }, { "epoch": 0.02, "learning_rate": 4.285810452690481e-05, "loss": 3.7577, "step": 436224 }, { "epoch": 0.02, "learning_rate": 4.284971857939429e-05, "loss": 3.7537, "step": 436736 }, { "epoch": 0.02, "learning_rate": 4.2841349010687496e-05, "loss": 3.7688, "step": 437248 }, { "epoch": 0.02, "learning_rate": 4.283297944198071e-05, "loss": 3.7664, "step": 437760 }, { "epoch": 0.02, "learning_rate": 4.282459349447019e-05, "loss": 3.7566, "step": 438272 }, { "epoch": 0.02, "learning_rate": 4.281620754695967e-05, "loss": 3.7426, "step": 438784 }, { "epoch": 0.02, "learning_rate": 4.280782159944915e-05, "loss": 3.7596, "step": 439296 }, { "epoch": 0.02, "learning_rate": 4.279943565193863e-05, "loss": 3.773, "step": 439808 }, { "epoch": 0.02, "learning_rate": 4.279104970442811e-05, "loss": 3.7652, "step": 440320 }, { "epoch": 0.02, "learning_rate": 4.278268013572132e-05, "loss": 3.7709, "step": 440832 }, { "epoch": 0.02, "learning_rate": 4.27742941882108e-05, "loss": 3.7632, "step": 441344 }, { "epoch": 0.02, "learning_rate": 4.276590824070028e-05, "loss": 3.7634, "step": 441856 }, { "epoch": 0.02, "learning_rate": 4.275752229318976e-05, "loss": 3.7674, "step": 442368 }, { "epoch": 0.02, "learning_rate": 4.274913634567924e-05, "loss": 3.7582, "step": 442880 }, { "epoch": 0.02, "learning_rate": 4.274075039816872e-05, "loss": 3.7529, "step": 443392 }, { "epoch": 0.02, "learning_rate": 4.27323644506582e-05, "loss": 3.758, "step": 443904 }, { "epoch": 0.02, "learning_rate": 4.272397850314768e-05, "loss": 3.7596, "step": 444416 }, { "epoch": 0.02, "learning_rate": 4.2715608934440896e-05, "loss": 3.7593, "step": 444928 }, { "epoch": 0.02, "learning_rate": 4.2707222986930376e-05, "loss": 3.7597, "step": 445440 }, { "epoch": 0.02, "learning_rate": 4.2698837039419856e-05, "loss": 3.764, "step": 445952 }, { "epoch": 0.02, "learning_rate": 4.2690451091909336e-05, "loss": 3.7573, "step": 446464 }, { "epoch": 0.02, "learning_rate": 4.2682081523202545e-05, "loss": 3.7513, "step": 446976 }, { "epoch": 0.02, "learning_rate": 4.2673695575692025e-05, "loss": 3.7685, "step": 447488 }, { "epoch": 0.02, "learning_rate": 4.2665309628181505e-05, "loss": 3.7541, "step": 448000 }, { "epoch": 0.02, "learning_rate": 4.2656923680670985e-05, "loss": 3.7676, "step": 448512 }, { "epoch": 0.02, "learning_rate": 4.2648554111964194e-05, "loss": 3.7697, "step": 449024 }, { "epoch": 0.02, "learning_rate": 4.2640168164453674e-05, "loss": 3.7592, "step": 449536 }, { "epoch": 0.02, "learning_rate": 4.2631782216943154e-05, "loss": 3.7603, "step": 450048 }, { "epoch": 0.02, "learning_rate": 4.2623396269432634e-05, "loss": 3.7584, "step": 450560 }, { "epoch": 0.02, "learning_rate": 4.261502670072584e-05, "loss": 3.7551, "step": 451072 }, { "epoch": 0.02, "learning_rate": 4.260664075321533e-05, "loss": 3.756, "step": 451584 }, { "epoch": 0.02, "learning_rate": 4.259825480570481e-05, "loss": 3.7718, "step": 452096 }, { "epoch": 0.02, "learning_rate": 4.258986885819429e-05, "loss": 3.7708, "step": 452608 }, { "epoch": 0.02, "learning_rate": 4.25814992894875e-05, "loss": 3.7615, "step": 453120 }, { "epoch": 0.02, "learning_rate": 4.257311334197698e-05, "loss": 3.7655, "step": 453632 }, { "epoch": 0.02, "learning_rate": 4.256472739446646e-05, "loss": 3.7561, "step": 454144 }, { "epoch": 0.02, "learning_rate": 4.255635782575967e-05, "loss": 3.7598, "step": 454656 }, { "epoch": 0.02, "learning_rate": 4.254797187824915e-05, "loss": 3.7538, "step": 455168 }, { "epoch": 0.02, "learning_rate": 4.253958593073863e-05, "loss": 3.7484, "step": 455680 }, { "epoch": 0.02, "learning_rate": 4.253119998322811e-05, "loss": 3.7618, "step": 456192 }, { "epoch": 0.02, "learning_rate": 4.252281403571758e-05, "loss": 3.7534, "step": 456704 }, { "epoch": 0.02, "learning_rate": 4.251442808820707e-05, "loss": 3.7467, "step": 457216 }, { "epoch": 0.02, "learning_rate": 4.250605851950028e-05, "loss": 3.7558, "step": 457728 }, { "epoch": 0.03, "eval_loss": 3.87520694732666, "eval_runtime": 669.5577, "eval_samples_per_second": 569.915, "eval_steps_per_second": 17.81, "step": 457914 }, { "epoch": 0.0, "learning_rate": 4.249767257198976e-05, "loss": 3.7637, "step": 458240 }, { "epoch": 0.0, "learning_rate": 4.2489286624479237e-05, "loss": 3.7592, "step": 458752 }, { "epoch": 0.0, "learning_rate": 4.2480900676968716e-05, "loss": 3.7573, "step": 459264 }, { "epoch": 0.0, "learning_rate": 4.2472514729458196e-05, "loss": 3.7559, "step": 459776 }, { "epoch": 0.0, "learning_rate": 4.2464128781947676e-05, "loss": 3.7586, "step": 460288 }, { "epoch": 0.0, "learning_rate": 4.2455759213240885e-05, "loss": 3.7441, "step": 460800 }, { "epoch": 0.0, "learning_rate": 4.2447373265730365e-05, "loss": 3.7573, "step": 461312 }, { "epoch": 0.0, "learning_rate": 4.2438987318219845e-05, "loss": 3.7437, "step": 461824 }, { "epoch": 0.0, "learning_rate": 4.2430601370709325e-05, "loss": 3.7495, "step": 462336 }, { "epoch": 0.0, "learning_rate": 4.2422215423198805e-05, "loss": 3.7532, "step": 462848 }, { "epoch": 0.0, "learning_rate": 4.241384585449202e-05, "loss": 3.7601, "step": 463360 }, { "epoch": 0.0, "learning_rate": 4.24054599069815e-05, "loss": 3.7355, "step": 463872 }, { "epoch": 0.0, "learning_rate": 4.239707395947098e-05, "loss": 3.7527, "step": 464384 }, { "epoch": 0.0, "learning_rate": 4.238868801196046e-05, "loss": 3.7445, "step": 464896 }, { "epoch": 0.0, "learning_rate": 4.238030206444994e-05, "loss": 3.7542, "step": 465408 }, { "epoch": 0.0, "learning_rate": 4.237191611693942e-05, "loss": 3.7366, "step": 465920 }, { "epoch": 0.0, "learning_rate": 4.23635301694289e-05, "loss": 3.7386, "step": 466432 }, { "epoch": 0.0, "learning_rate": 4.235516060072211e-05, "loss": 3.7467, "step": 466944 }, { "epoch": 0.0, "learning_rate": 4.234677465321159e-05, "loss": 3.745, "step": 467456 }, { "epoch": 0.0, "learning_rate": 4.233838870570107e-05, "loss": 3.7548, "step": 467968 }, { "epoch": 0.0, "learning_rate": 4.233000275819055e-05, "loss": 3.7477, "step": 468480 }, { "epoch": 0.0, "learning_rate": 4.232163318948376e-05, "loss": 3.7621, "step": 468992 }, { "epoch": 0.0, "learning_rate": 4.231324724197324e-05, "loss": 3.7538, "step": 469504 }, { "epoch": 0.0, "learning_rate": 4.230486129446272e-05, "loss": 3.7489, "step": 470016 }, { "epoch": 0.0, "learning_rate": 4.2296475346952206e-05, "loss": 3.7433, "step": 470528 }, { "epoch": 0.0, "learning_rate": 4.2288105778245415e-05, "loss": 3.7474, "step": 471040 }, { "epoch": 0.0, "learning_rate": 4.2279719830734895e-05, "loss": 3.7547, "step": 471552 }, { "epoch": 0.0, "learning_rate": 4.2271333883224375e-05, "loss": 3.7464, "step": 472064 }, { "epoch": 0.0, "learning_rate": 4.2262947935713855e-05, "loss": 3.7453, "step": 472576 }, { "epoch": 0.0, "learning_rate": 4.2254578367007064e-05, "loss": 3.7481, "step": 473088 }, { "epoch": 0.01, "learning_rate": 4.2246192419496544e-05, "loss": 3.736, "step": 473600 }, { "epoch": 0.01, "learning_rate": 4.2237806471986024e-05, "loss": 3.7519, "step": 474112 }, { "epoch": 0.01, "learning_rate": 4.2229420524475504e-05, "loss": 3.7558, "step": 474624 }, { "epoch": 0.01, "learning_rate": 4.222105095576871e-05, "loss": 3.7506, "step": 475136 }, { "epoch": 0.01, "learning_rate": 4.221266500825819e-05, "loss": 3.7386, "step": 475648 }, { "epoch": 0.01, "learning_rate": 4.220427906074767e-05, "loss": 3.7523, "step": 476160 }, { "epoch": 0.01, "learning_rate": 4.219589311323716e-05, "loss": 3.7422, "step": 476672 }, { "epoch": 0.01, "learning_rate": 4.218752354453037e-05, "loss": 3.7483, "step": 477184 }, { "epoch": 0.01, "learning_rate": 4.217913759701985e-05, "loss": 3.7469, "step": 477696 }, { "epoch": 0.01, "learning_rate": 4.217075164950933e-05, "loss": 3.7326, "step": 478208 }, { "epoch": 0.01, "learning_rate": 4.216236570199881e-05, "loss": 3.7326, "step": 478720 }, { "epoch": 0.01, "learning_rate": 4.215399613329202e-05, "loss": 3.7268, "step": 479232 }, { "epoch": 0.01, "learning_rate": 4.21456101857815e-05, "loss": 3.7559, "step": 479744 }, { "epoch": 0.01, "learning_rate": 4.213722423827098e-05, "loss": 3.7359, "step": 480256 }, { "epoch": 0.01, "learning_rate": 4.2128854669564186e-05, "loss": 3.7329, "step": 480768 }, { "epoch": 0.01, "learning_rate": 4.2120468722053666e-05, "loss": 3.7449, "step": 481280 }, { "epoch": 0.01, "learning_rate": 4.2112082774543146e-05, "loss": 3.7396, "step": 481792 }, { "epoch": 0.01, "learning_rate": 4.2103696827032626e-05, "loss": 3.7484, "step": 482304 }, { "epoch": 0.01, "learning_rate": 4.209531087952211e-05, "loss": 3.7329, "step": 482816 }, { "epoch": 0.01, "learning_rate": 4.208692493201159e-05, "loss": 3.7374, "step": 483328 }, { "epoch": 0.01, "learning_rate": 4.207853898450107e-05, "loss": 3.7382, "step": 483840 }, { "epoch": 0.01, "learning_rate": 4.2070153036990546e-05, "loss": 3.7429, "step": 484352 }, { "epoch": 0.01, "learning_rate": 4.206178346828376e-05, "loss": 3.7356, "step": 484864 }, { "epoch": 0.01, "learning_rate": 4.205339752077324e-05, "loss": 3.7319, "step": 485376 }, { "epoch": 0.01, "learning_rate": 4.204501157326272e-05, "loss": 3.7352, "step": 485888 }, { "epoch": 0.01, "learning_rate": 4.2036625625752195e-05, "loss": 3.74, "step": 486400 }, { "epoch": 0.01, "learning_rate": 4.202825605704541e-05, "loss": 3.7379, "step": 486912 }, { "epoch": 0.01, "learning_rate": 4.201988648833862e-05, "loss": 3.7325, "step": 487424 }, { "epoch": 0.01, "learning_rate": 4.20115005408281e-05, "loss": 3.7456, "step": 487936 }, { "epoch": 0.01, "learning_rate": 4.200311459331758e-05, "loss": 3.7343, "step": 488448 }, { "epoch": 0.01, "learning_rate": 4.199472864580707e-05, "loss": 3.7242, "step": 488960 }, { "epoch": 0.01, "learning_rate": 4.1986342698296547e-05, "loss": 3.7287, "step": 489472 }, { "epoch": 0.01, "learning_rate": 4.197795675078602e-05, "loss": 3.7311, "step": 489984 }, { "epoch": 0.01, "learning_rate": 4.19695708032755e-05, "loss": 3.7509, "step": 490496 }, { "epoch": 0.01, "learning_rate": 4.196118485576498e-05, "loss": 3.7303, "step": 491008 }, { "epoch": 0.01, "learning_rate": 4.195281528705819e-05, "loss": 3.7326, "step": 491520 }, { "epoch": 0.01, "learning_rate": 4.194442933954767e-05, "loss": 3.7194, "step": 492032 }, { "epoch": 0.01, "learning_rate": 4.193604339203715e-05, "loss": 3.7335, "step": 492544 }, { "epoch": 0.01, "learning_rate": 4.192765744452663e-05, "loss": 3.7273, "step": 493056 }, { "epoch": 0.01, "learning_rate": 4.191928787581984e-05, "loss": 3.7288, "step": 493568 }, { "epoch": 0.01, "learning_rate": 4.191090192830932e-05, "loss": 3.7358, "step": 494080 }, { "epoch": 0.01, "learning_rate": 4.1902515980798804e-05, "loss": 3.7289, "step": 494592 }, { "epoch": 0.01, "learning_rate": 4.1894130033288284e-05, "loss": 3.738, "step": 495104 }, { "epoch": 0.01, "learning_rate": 4.1885744085777764e-05, "loss": 3.7431, "step": 495616 }, { "epoch": 0.01, "learning_rate": 4.1877358138267244e-05, "loss": 3.7378, "step": 496128 }, { "epoch": 0.01, "learning_rate": 4.186898856956045e-05, "loss": 3.745, "step": 496640 }, { "epoch": 0.01, "learning_rate": 4.186060262204993e-05, "loss": 3.736, "step": 497152 }, { "epoch": 0.01, "learning_rate": 4.185221667453941e-05, "loss": 3.7204, "step": 497664 }, { "epoch": 0.01, "learning_rate": 4.184383072702889e-05, "loss": 3.7277, "step": 498176 }, { "epoch": 0.01, "learning_rate": 4.183544477951837e-05, "loss": 3.7387, "step": 498688 }, { "epoch": 0.01, "learning_rate": 4.182705883200785e-05, "loss": 3.7335, "step": 499200 }, { "epoch": 0.01, "learning_rate": 4.181867288449733e-05, "loss": 3.7295, "step": 499712 }, { "epoch": 0.01, "learning_rate": 4.181028693698681e-05, "loss": 3.7112, "step": 500224 }, { "epoch": 0.01, "learning_rate": 4.180191736828002e-05, "loss": 3.7324, "step": 500736 }, { "epoch": 0.01, "learning_rate": 4.179354779957324e-05, "loss": 3.7154, "step": 501248 }, { "epoch": 0.01, "learning_rate": 4.178516185206272e-05, "loss": 3.732, "step": 501760 }, { "epoch": 0.01, "learning_rate": 4.17767759045522e-05, "loss": 3.7286, "step": 502272 }, { "epoch": 0.01, "learning_rate": 4.176838995704168e-05, "loss": 3.739, "step": 502784 }, { "epoch": 0.01, "learning_rate": 4.176000400953116e-05, "loss": 3.7289, "step": 503296 }, { "epoch": 0.02, "learning_rate": 4.175161806202064e-05, "loss": 3.7295, "step": 503808 }, { "epoch": 0.02, "learning_rate": 4.174323211451012e-05, "loss": 3.7189, "step": 504320 }, { "epoch": 0.02, "learning_rate": 4.17348461669996e-05, "loss": 3.7325, "step": 504832 }, { "epoch": 0.02, "learning_rate": 4.172647659829281e-05, "loss": 3.7241, "step": 505344 }, { "epoch": 0.02, "learning_rate": 4.1718107029586016e-05, "loss": 3.7272, "step": 505856 }, { "epoch": 0.02, "learning_rate": 4.1709721082075496e-05, "loss": 3.7196, "step": 506368 }, { "epoch": 0.02, "learning_rate": 4.1701335134564976e-05, "loss": 3.7334, "step": 506880 }, { "epoch": 0.02, "learning_rate": 4.1692949187054456e-05, "loss": 3.7215, "step": 507392 }, { "epoch": 0.02, "learning_rate": 4.1684563239543936e-05, "loss": 3.7498, "step": 507904 }, { "epoch": 0.02, "learning_rate": 4.167617729203342e-05, "loss": 3.7221, "step": 508416 }, { "epoch": 0.02, "learning_rate": 4.166780772332663e-05, "loss": 3.7372, "step": 508928 }, { "epoch": 0.02, "learning_rate": 4.165942177581611e-05, "loss": 3.728, "step": 509440 }, { "epoch": 0.02, "learning_rate": 4.165103582830559e-05, "loss": 3.7224, "step": 509952 }, { "epoch": 0.02, "learning_rate": 4.164264988079507e-05, "loss": 3.7429, "step": 510464 }, { "epoch": 0.02, "learning_rate": 4.163426393328455e-05, "loss": 3.7239, "step": 510976 }, { "epoch": 0.02, "learning_rate": 4.1625877985774025e-05, "loss": 3.7373, "step": 511488 }, { "epoch": 0.02, "learning_rate": 4.1617492038263505e-05, "loss": 3.7236, "step": 512000 }, { "epoch": 0.02, "learning_rate": 4.1609106090752984e-05, "loss": 3.7183, "step": 512512 }, { "epoch": 0.02, "learning_rate": 4.16007365220462e-05, "loss": 3.718, "step": 513024 }, { "epoch": 0.02, "learning_rate": 4.159236695333941e-05, "loss": 3.7317, "step": 513536 }, { "epoch": 0.02, "learning_rate": 4.158398100582889e-05, "loss": 3.7297, "step": 514048 }, { "epoch": 0.02, "learning_rate": 4.1575595058318376e-05, "loss": 3.7233, "step": 514560 }, { "epoch": 0.02, "learning_rate": 4.1567209110807856e-05, "loss": 3.7003, "step": 515072 }, { "epoch": 0.02, "learning_rate": 4.155882316329733e-05, "loss": 3.7224, "step": 515584 }, { "epoch": 0.02, "learning_rate": 4.155043721578681e-05, "loss": 3.7362, "step": 516096 }, { "epoch": 0.02, "learning_rate": 4.1542067647080025e-05, "loss": 3.7273, "step": 516608 }, { "epoch": 0.02, "learning_rate": 4.15336816995695e-05, "loss": 3.7344, "step": 517120 }, { "epoch": 0.02, "learning_rate": 4.152529575205898e-05, "loss": 3.7267, "step": 517632 }, { "epoch": 0.02, "learning_rate": 4.151690980454846e-05, "loss": 3.7276, "step": 518144 }, { "epoch": 0.02, "learning_rate": 4.150852385703794e-05, "loss": 3.7303, "step": 518656 }, { "epoch": 0.02, "learning_rate": 4.150013790952742e-05, "loss": 3.723, "step": 519168 }, { "epoch": 0.02, "learning_rate": 4.14917519620169e-05, "loss": 3.7154, "step": 519680 }, { "epoch": 0.02, "learning_rate": 4.148336601450638e-05, "loss": 3.7203, "step": 520192 }, { "epoch": 0.02, "learning_rate": 4.1474996445799594e-05, "loss": 3.7226, "step": 520704 }, { "epoch": 0.02, "learning_rate": 4.1466610498289074e-05, "loss": 3.7231, "step": 521216 }, { "epoch": 0.02, "learning_rate": 4.1458224550778554e-05, "loss": 3.7228, "step": 521728 }, { "epoch": 0.02, "learning_rate": 4.144985498207176e-05, "loss": 3.7278, "step": 522240 }, { "epoch": 0.02, "learning_rate": 4.144146903456124e-05, "loss": 3.7186, "step": 522752 }, { "epoch": 0.02, "learning_rate": 4.143308308705072e-05, "loss": 3.7156, "step": 523264 }, { "epoch": 0.02, "learning_rate": 4.14246971395402e-05, "loss": 3.7316, "step": 523776 }, { "epoch": 0.02, "learning_rate": 4.141631119202968e-05, "loss": 3.7182, "step": 524288 }, { "epoch": 0.02, "learning_rate": 4.140792524451916e-05, "loss": 3.7324, "step": 524800 }, { "epoch": 0.02, "learning_rate": 4.139955567581237e-05, "loss": 3.7328, "step": 525312 }, { "epoch": 0.02, "learning_rate": 4.139116972830185e-05, "loss": 3.7229, "step": 525824 }, { "epoch": 0.02, "learning_rate": 4.138278378079133e-05, "loss": 3.724, "step": 526336 }, { "epoch": 0.02, "learning_rate": 4.137439783328081e-05, "loss": 3.7245, "step": 526848 }, { "epoch": 0.02, "learning_rate": 4.136601188577029e-05, "loss": 3.7178, "step": 527360 }, { "epoch": 0.02, "learning_rate": 4.135762593825978e-05, "loss": 3.7201, "step": 527872 }, { "epoch": 0.02, "learning_rate": 4.134923999074926e-05, "loss": 3.737, "step": 528384 }, { "epoch": 0.02, "learning_rate": 4.134087042204247e-05, "loss": 3.7335, "step": 528896 }, { "epoch": 0.02, "learning_rate": 4.133248447453195e-05, "loss": 3.728, "step": 529408 }, { "epoch": 0.02, "learning_rate": 4.132409852702143e-05, "loss": 3.7288, "step": 529920 }, { "epoch": 0.02, "learning_rate": 4.131571257951091e-05, "loss": 3.7185, "step": 530432 }, { "epoch": 0.02, "learning_rate": 4.1307343010804116e-05, "loss": 3.7238, "step": 530944 }, { "epoch": 0.02, "learning_rate": 4.1298957063293596e-05, "loss": 3.7174, "step": 531456 }, { "epoch": 0.02, "learning_rate": 4.1290571115783076e-05, "loss": 3.7115, "step": 531968 }, { "epoch": 0.02, "learning_rate": 4.1282185168272556e-05, "loss": 3.7295, "step": 532480 }, { "epoch": 0.02, "learning_rate": 4.1273799220762036e-05, "loss": 3.7167, "step": 532992 }, { "epoch": 0.02, "learning_rate": 4.1265413273251516e-05, "loss": 3.7119, "step": 533504 }, { "epoch": 0.02, "learning_rate": 4.1257027325740996e-05, "loss": 3.7219, "step": 534016 }, { "epoch": 0.03, "eval_loss": 3.865478992462158, "eval_runtime": 576.716, "eval_samples_per_second": 661.662, "eval_steps_per_second": 20.677, "step": 534233 }, { "epoch": 0.0, "learning_rate": 4.124865775703421e-05, "loss": 3.729, "step": 534528 }, { "epoch": 0.0, "learning_rate": 4.1240271809523685e-05, "loss": 3.7204, "step": 535040 }, { "epoch": 0.0, "learning_rate": 4.1231885862013165e-05, "loss": 3.7264, "step": 535552 }, { "epoch": 0.0, "learning_rate": 4.1223499914502645e-05, "loss": 3.721, "step": 536064 }, { "epoch": 0.0, "learning_rate": 4.1215113966992125e-05, "loss": 3.7189, "step": 536576 }, { "epoch": 0.0, "learning_rate": 4.1206728019481605e-05, "loss": 3.7126, "step": 537088 }, { "epoch": 0.0, "learning_rate": 4.1198358450774814e-05, "loss": 3.7201, "step": 537600 }, { "epoch": 0.0, "learning_rate": 4.1189972503264294e-05, "loss": 3.7094, "step": 538112 }, { "epoch": 0.0, "learning_rate": 4.1181586555753774e-05, "loss": 3.7138, "step": 538624 }, { "epoch": 0.0, "learning_rate": 4.1173200608243254e-05, "loss": 3.7124, "step": 539136 }, { "epoch": 0.0, "learning_rate": 4.116483103953647e-05, "loss": 3.7259, "step": 539648 }, { "epoch": 0.0, "learning_rate": 4.115644509202595e-05, "loss": 3.7051, "step": 540160 }, { "epoch": 0.0, "learning_rate": 4.114805914451543e-05, "loss": 3.7171, "step": 540672 }, { "epoch": 0.0, "learning_rate": 4.113967319700491e-05, "loss": 3.7062, "step": 541184 }, { "epoch": 0.0, "learning_rate": 4.113128724949439e-05, "loss": 3.721, "step": 541696 }, { "epoch": 0.0, "learning_rate": 4.112290130198387e-05, "loss": 3.7042, "step": 542208 }, { "epoch": 0.0, "learning_rate": 4.111451535447335e-05, "loss": 3.7047, "step": 542720 }, { "epoch": 0.0, "learning_rate": 4.110614578576656e-05, "loss": 3.7102, "step": 543232 }, { "epoch": 0.0, "learning_rate": 4.109775983825604e-05, "loss": 3.7094, "step": 543744 }, { "epoch": 0.0, "learning_rate": 4.108939026954925e-05, "loss": 3.719, "step": 544256 }, { "epoch": 0.0, "learning_rate": 4.108100432203873e-05, "loss": 3.7108, "step": 544768 }, { "epoch": 0.0, "learning_rate": 4.107261837452821e-05, "loss": 3.7283, "step": 545280 }, { "epoch": 0.0, "learning_rate": 4.106423242701769e-05, "loss": 3.7135, "step": 545792 }, { "epoch": 0.0, "learning_rate": 4.105584647950717e-05, "loss": 3.7167, "step": 546304 }, { "epoch": 0.0, "learning_rate": 4.1047460531996654e-05, "loss": 3.7123, "step": 546816 }, { "epoch": 0.0, "learning_rate": 4.1039074584486134e-05, "loss": 3.7119, "step": 547328 }, { "epoch": 0.0, "learning_rate": 4.103070501577934e-05, "loss": 3.7172, "step": 547840 }, { "epoch": 0.0, "learning_rate": 4.102231906826882e-05, "loss": 3.7111, "step": 548352 }, { "epoch": 0.0, "learning_rate": 4.10139331207583e-05, "loss": 3.7133, "step": 548864 }, { "epoch": 0.0, "learning_rate": 4.100554717324778e-05, "loss": 3.7102, "step": 549376 }, { "epoch": 0.01, "learning_rate": 4.099716122573726e-05, "loss": 3.7025, "step": 549888 }, { "epoch": 0.01, "learning_rate": 4.098879165703047e-05, "loss": 3.7152, "step": 550400 }, { "epoch": 0.01, "learning_rate": 4.098040570951995e-05, "loss": 3.7225, "step": 550912 }, { "epoch": 0.01, "learning_rate": 4.097201976200943e-05, "loss": 3.7142, "step": 551424 }, { "epoch": 0.01, "learning_rate": 4.096363381449891e-05, "loss": 3.7071, "step": 551936 }, { "epoch": 0.01, "learning_rate": 4.095526424579212e-05, "loss": 3.716, "step": 552448 }, { "epoch": 0.01, "learning_rate": 4.094687829828161e-05, "loss": 3.7094, "step": 552960 }, { "epoch": 0.01, "learning_rate": 4.093849235077109e-05, "loss": 3.7143, "step": 553472 }, { "epoch": 0.01, "learning_rate": 4.093010640326057e-05, "loss": 3.7103, "step": 553984 }, { "epoch": 0.01, "learning_rate": 4.092172045575005e-05, "loss": 3.7012, "step": 554496 }, { "epoch": 0.01, "learning_rate": 4.091335088704326e-05, "loss": 3.7006, "step": 555008 }, { "epoch": 0.01, "learning_rate": 4.090496493953274e-05, "loss": 3.6936, "step": 555520 }, { "epoch": 0.01, "learning_rate": 4.089657899202222e-05, "loss": 3.719, "step": 556032 }, { "epoch": 0.01, "learning_rate": 4.08881930445117e-05, "loss": 3.7035, "step": 556544 }, { "epoch": 0.01, "learning_rate": 4.0879823475804906e-05, "loss": 3.6999, "step": 557056 }, { "epoch": 0.01, "learning_rate": 4.0871437528294386e-05, "loss": 3.712, "step": 557568 }, { "epoch": 0.01, "learning_rate": 4.0863051580783866e-05, "loss": 3.705, "step": 558080 }, { "epoch": 0.01, "learning_rate": 4.0854665633273346e-05, "loss": 3.7136, "step": 558592 }, { "epoch": 0.01, "learning_rate": 4.0846279685762826e-05, "loss": 3.6993, "step": 559104 }, { "epoch": 0.01, "learning_rate": 4.083791011705604e-05, "loss": 3.7062, "step": 559616 }, { "epoch": 0.01, "learning_rate": 4.082952416954552e-05, "loss": 3.7024, "step": 560128 }, { "epoch": 0.01, "learning_rate": 4.0821138222034995e-05, "loss": 3.7068, "step": 560640 }, { "epoch": 0.01, "learning_rate": 4.0812752274524475e-05, "loss": 3.7055, "step": 561152 }, { "epoch": 0.01, "learning_rate": 4.080438270581769e-05, "loss": 3.6969, "step": 561664 }, { "epoch": 0.01, "learning_rate": 4.079599675830717e-05, "loss": 3.7039, "step": 562176 }, { "epoch": 0.01, "learning_rate": 4.0787610810796644e-05, "loss": 3.7057, "step": 562688 }, { "epoch": 0.01, "learning_rate": 4.0779224863286124e-05, "loss": 3.7056, "step": 563200 }, { "epoch": 0.01, "learning_rate": 4.0770838915775604e-05, "loss": 3.7014, "step": 563712 }, { "epoch": 0.01, "learning_rate": 4.076246934706881e-05, "loss": 3.7149, "step": 564224 }, { "epoch": 0.01, "learning_rate": 4.07540833995583e-05, "loss": 3.6943, "step": 564736 }, { "epoch": 0.01, "learning_rate": 4.074569745204778e-05, "loss": 3.6954, "step": 565248 }, { "epoch": 0.01, "learning_rate": 4.073731150453726e-05, "loss": 3.6957, "step": 565760 }, { "epoch": 0.01, "learning_rate": 4.072892555702674e-05, "loss": 3.7013, "step": 566272 }, { "epoch": 0.01, "learning_rate": 4.072053960951622e-05, "loss": 3.7149, "step": 566784 }, { "epoch": 0.01, "learning_rate": 4.07121536620057e-05, "loss": 3.6974, "step": 567296 }, { "epoch": 0.01, "learning_rate": 4.070376771449518e-05, "loss": 3.6993, "step": 567808 }, { "epoch": 0.01, "learning_rate": 4.069539814578839e-05, "loss": 3.6882, "step": 568320 }, { "epoch": 0.01, "learning_rate": 4.068701219827787e-05, "loss": 3.7, "step": 568832 }, { "epoch": 0.01, "learning_rate": 4.067864262957108e-05, "loss": 3.6924, "step": 569344 }, { "epoch": 0.01, "learning_rate": 4.067025668206056e-05, "loss": 3.6977, "step": 569856 }, { "epoch": 0.01, "learning_rate": 4.066187073455004e-05, "loss": 3.7038, "step": 570368 }, { "epoch": 0.01, "learning_rate": 4.065348478703952e-05, "loss": 3.6969, "step": 570880 }, { "epoch": 0.01, "learning_rate": 4.0645098839529e-05, "loss": 3.6993, "step": 571392 }, { "epoch": 0.01, "learning_rate": 4.063671289201848e-05, "loss": 3.7123, "step": 571904 }, { "epoch": 0.01, "learning_rate": 4.0628326944507964e-05, "loss": 3.7026, "step": 572416 }, { "epoch": 0.01, "learning_rate": 4.061995737580117e-05, "loss": 3.7106, "step": 572928 }, { "epoch": 0.01, "learning_rate": 4.061157142829065e-05, "loss": 3.7037, "step": 573440 }, { "epoch": 0.01, "learning_rate": 4.060318548078013e-05, "loss": 3.6909, "step": 573952 }, { "epoch": 0.01, "learning_rate": 4.059479953326961e-05, "loss": 3.6953, "step": 574464 }, { "epoch": 0.01, "learning_rate": 4.058642996456282e-05, "loss": 3.7064, "step": 574976 }, { "epoch": 0.01, "learning_rate": 4.05780440170523e-05, "loss": 3.7034, "step": 575488 }, { "epoch": 0.01, "learning_rate": 4.056965806954178e-05, "loss": 3.6924, "step": 576000 }, { "epoch": 0.01, "learning_rate": 4.056127212203126e-05, "loss": 3.6827, "step": 576512 }, { "epoch": 0.01, "learning_rate": 4.055288617452074e-05, "loss": 3.6963, "step": 577024 }, { "epoch": 0.01, "learning_rate": 4.054451660581395e-05, "loss": 3.6842, "step": 577536 }, { "epoch": 0.01, "learning_rate": 4.053613065830343e-05, "loss": 3.6995, "step": 578048 }, { "epoch": 0.01, "learning_rate": 4.052774471079292e-05, "loss": 3.6943, "step": 578560 }, { "epoch": 0.01, "learning_rate": 4.05193587632824e-05, "loss": 3.7053, "step": 579072 }, { "epoch": 0.01, "learning_rate": 4.051097281577188e-05, "loss": 3.7024, "step": 579584 }, { "epoch": 0.02, "learning_rate": 4.050258686826136e-05, "loss": 3.6942, "step": 580096 }, { "epoch": 0.02, "learning_rate": 4.049420092075083e-05, "loss": 3.6897, "step": 580608 }, { "epoch": 0.02, "learning_rate": 4.048581497324031e-05, "loss": 3.6994, "step": 581120 }, { "epoch": 0.02, "learning_rate": 4.0477445404533526e-05, "loss": 3.6883, "step": 581632 }, { "epoch": 0.02, "learning_rate": 4.0469075835826735e-05, "loss": 3.6944, "step": 582144 }, { "epoch": 0.02, "learning_rate": 4.0460689888316215e-05, "loss": 3.6906, "step": 582656 }, { "epoch": 0.02, "learning_rate": 4.0452303940805695e-05, "loss": 3.7004, "step": 583168 }, { "epoch": 0.02, "learning_rate": 4.0443917993295175e-05, "loss": 3.6927, "step": 583680 }, { "epoch": 0.02, "learning_rate": 4.0435532045784655e-05, "loss": 3.7186, "step": 584192 }, { "epoch": 0.02, "learning_rate": 4.042716247707787e-05, "loss": 3.687, "step": 584704 }, { "epoch": 0.02, "learning_rate": 4.041877652956735e-05, "loss": 3.7052, "step": 585216 }, { "epoch": 0.02, "learning_rate": 4.041039058205683e-05, "loss": 3.701, "step": 585728 }, { "epoch": 0.02, "learning_rate": 4.0402004634546304e-05, "loss": 3.6919, "step": 586240 }, { "epoch": 0.02, "learning_rate": 4.0393618687035784e-05, "loss": 3.706, "step": 586752 }, { "epoch": 0.02, "learning_rate": 4.0385232739525264e-05, "loss": 3.6983, "step": 587264 }, { "epoch": 0.02, "learning_rate": 4.037686317081848e-05, "loss": 3.7039, "step": 587776 }, { "epoch": 0.02, "learning_rate": 4.036847722330795e-05, "loss": 3.6935, "step": 588288 }, { "epoch": 0.02, "learning_rate": 4.036009127579743e-05, "loss": 3.6884, "step": 588800 }, { "epoch": 0.02, "learning_rate": 4.035170532828691e-05, "loss": 3.6873, "step": 589312 }, { "epoch": 0.02, "learning_rate": 4.034333575958012e-05, "loss": 3.6987, "step": 589824 }, { "epoch": 0.02, "learning_rate": 4.033494981206961e-05, "loss": 3.6984, "step": 590336 }, { "epoch": 0.02, "learning_rate": 4.032656386455909e-05, "loss": 3.6879, "step": 590848 }, { "epoch": 0.02, "learning_rate": 4.031817791704857e-05, "loss": 3.6694, "step": 591360 }, { "epoch": 0.02, "learning_rate": 4.030979196953805e-05, "loss": 3.6922, "step": 591872 }, { "epoch": 0.02, "learning_rate": 4.030142240083126e-05, "loss": 3.7034, "step": 592384 }, { "epoch": 0.02, "learning_rate": 4.029303645332074e-05, "loss": 3.695, "step": 592896 }, { "epoch": 0.02, "learning_rate": 4.028465050581022e-05, "loss": 3.705, "step": 593408 }, { "epoch": 0.02, "learning_rate": 4.02762645582997e-05, "loss": 3.6963, "step": 593920 }, { "epoch": 0.02, "learning_rate": 4.026787861078918e-05, "loss": 3.6893, "step": 594432 }, { "epoch": 0.02, "learning_rate": 4.025949266327866e-05, "loss": 3.7023, "step": 594944 }, { "epoch": 0.02, "learning_rate": 4.025112309457187e-05, "loss": 3.6936, "step": 595456 }, { "epoch": 0.02, "learning_rate": 4.024273714706135e-05, "loss": 3.6871, "step": 595968 }, { "epoch": 0.02, "learning_rate": 4.023435119955083e-05, "loss": 3.6878, "step": 596480 }, { "epoch": 0.02, "learning_rate": 4.0225965252040307e-05, "loss": 3.6941, "step": 596992 }, { "epoch": 0.02, "learning_rate": 4.021759568333352e-05, "loss": 3.6895, "step": 597504 }, { "epoch": 0.02, "learning_rate": 4.0209209735823e-05, "loss": 3.686, "step": 598016 }, { "epoch": 0.02, "learning_rate": 4.020082378831248e-05, "loss": 3.6993, "step": 598528 }, { "epoch": 0.02, "learning_rate": 4.019243784080196e-05, "loss": 3.6896, "step": 599040 }, { "epoch": 0.02, "learning_rate": 4.018405189329144e-05, "loss": 3.6825, "step": 599552 }, { "epoch": 0.02, "learning_rate": 4.017566594578092e-05, "loss": 3.7035, "step": 600064 }, { "epoch": 0.02, "learning_rate": 4.016729637707413e-05, "loss": 3.6839, "step": 600576 }, { "epoch": 0.02, "learning_rate": 4.015891042956361e-05, "loss": 3.6993, "step": 601088 }, { "epoch": 0.02, "learning_rate": 4.015052448205309e-05, "loss": 3.7047, "step": 601600 }, { "epoch": 0.02, "learning_rate": 4.014213853454257e-05, "loss": 3.6948, "step": 602112 }, { "epoch": 0.02, "learning_rate": 4.013375258703205e-05, "loss": 3.6906, "step": 602624 }, { "epoch": 0.02, "learning_rate": 4.012536663952153e-05, "loss": 3.6926, "step": 603136 }, { "epoch": 0.02, "learning_rate": 4.011698069201101e-05, "loss": 3.6895, "step": 603648 }, { "epoch": 0.02, "learning_rate": 4.010861112330423e-05, "loss": 3.6896, "step": 604160 }, { "epoch": 0.02, "learning_rate": 4.010022517579371e-05, "loss": 3.707, "step": 604672 }, { "epoch": 0.02, "learning_rate": 4.009183922828319e-05, "loss": 3.7004, "step": 605184 }, { "epoch": 0.02, "learning_rate": 4.008345328077267e-05, "loss": 3.6983, "step": 605696 }, { "epoch": 0.02, "learning_rate": 4.007506733326214e-05, "loss": 3.6977, "step": 606208 }, { "epoch": 0.02, "learning_rate": 4.0066697764555356e-05, "loss": 3.688, "step": 606720 }, { "epoch": 0.02, "learning_rate": 4.0058311817044836e-05, "loss": 3.6967, "step": 607232 }, { "epoch": 0.02, "learning_rate": 4.004992586953431e-05, "loss": 3.6842, "step": 607744 }, { "epoch": 0.02, "learning_rate": 4.004153992202379e-05, "loss": 3.6856, "step": 608256 }, { "epoch": 0.02, "learning_rate": 4.0033170353317005e-05, "loss": 3.6958, "step": 608768 }, { "epoch": 0.02, "learning_rate": 4.0024784405806485e-05, "loss": 3.6896, "step": 609280 }, { "epoch": 0.02, "learning_rate": 4.0016398458295965e-05, "loss": 3.6774, "step": 609792 }, { "epoch": 0.02, "learning_rate": 4.0008012510785445e-05, "loss": 3.6946, "step": 610304 }, { "epoch": 0.03, "eval_loss": 3.8578743934631348, "eval_runtime": 569.8526, "eval_samples_per_second": 669.631, "eval_steps_per_second": 20.926, "step": 610552 }, { "epoch": 0.0, "learning_rate": 3.999964294207866e-05, "loss": 3.6948, "step": 610816 }, { "epoch": 0.0, "learning_rate": 3.999125699456814e-05, "loss": 3.6962, "step": 611328 }, { "epoch": 0.0, "learning_rate": 3.9982871047057614e-05, "loss": 3.6946, "step": 611840 }, { "epoch": 0.0, "learning_rate": 3.9974485099547094e-05, "loss": 3.6889, "step": 612352 }, { "epoch": 0.0, "learning_rate": 3.996611553084031e-05, "loss": 3.6875, "step": 612864 }, { "epoch": 0.0, "learning_rate": 3.995772958332978e-05, "loss": 3.6829, "step": 613376 }, { "epoch": 0.0, "learning_rate": 3.994934363581926e-05, "loss": 3.6909, "step": 613888 }, { "epoch": 0.0, "learning_rate": 3.994095768830874e-05, "loss": 3.6785, "step": 614400 }, { "epoch": 0.0, "learning_rate": 3.993258811960196e-05, "loss": 3.6814, "step": 614912 }, { "epoch": 0.0, "learning_rate": 3.992420217209143e-05, "loss": 3.6843, "step": 615424 }, { "epoch": 0.0, "learning_rate": 3.991581622458092e-05, "loss": 3.6944, "step": 615936 }, { "epoch": 0.0, "learning_rate": 3.99074302770704e-05, "loss": 3.6766, "step": 616448 }, { "epoch": 0.0, "learning_rate": 3.989904432955988e-05, "loss": 3.6867, "step": 616960 }, { "epoch": 0.0, "learning_rate": 3.989067476085309e-05, "loss": 3.6742, "step": 617472 }, { "epoch": 0.0, "learning_rate": 3.988228881334257e-05, "loss": 3.6932, "step": 617984 }, { "epoch": 0.0, "learning_rate": 3.987390286583205e-05, "loss": 3.6714, "step": 618496 }, { "epoch": 0.0, "learning_rate": 3.986551691832153e-05, "loss": 3.6755, "step": 619008 }, { "epoch": 0.0, "learning_rate": 3.985713097081101e-05, "loss": 3.6811, "step": 619520 }, { "epoch": 0.0, "learning_rate": 3.9848761402104216e-05, "loss": 3.6807, "step": 620032 }, { "epoch": 0.0, "learning_rate": 3.9840375454593696e-05, "loss": 3.6873, "step": 620544 }, { "epoch": 0.0, "learning_rate": 3.9831989507083176e-05, "loss": 3.6828, "step": 621056 }, { "epoch": 0.0, "learning_rate": 3.9823603559572656e-05, "loss": 3.6995, "step": 621568 }, { "epoch": 0.0, "learning_rate": 3.9815217612062136e-05, "loss": 3.6828, "step": 622080 }, { "epoch": 0.0, "learning_rate": 3.980684804335535e-05, "loss": 3.6864, "step": 622592 }, { "epoch": 0.0, "learning_rate": 3.979846209584483e-05, "loss": 3.681, "step": 623104 }, { "epoch": 0.0, "learning_rate": 3.979007614833431e-05, "loss": 3.6861, "step": 623616 }, { "epoch": 0.0, "learning_rate": 3.978169020082379e-05, "loss": 3.6869, "step": 624128 }, { "epoch": 0.0, "learning_rate": 3.977330425331327e-05, "loss": 3.6831, "step": 624640 }, { "epoch": 0.0, "learning_rate": 3.976493468460648e-05, "loss": 3.6833, "step": 625152 }, { "epoch": 0.0, "learning_rate": 3.975654873709596e-05, "loss": 3.684, "step": 625664 }, { "epoch": 0.01, "learning_rate": 3.974816278958544e-05, "loss": 3.6716, "step": 626176 }, { "epoch": 0.01, "learning_rate": 3.973977684207492e-05, "loss": 3.6868, "step": 626688 }, { "epoch": 0.01, "learning_rate": 3.973140727336813e-05, "loss": 3.694, "step": 627200 }, { "epoch": 0.01, "learning_rate": 3.972302132585761e-05, "loss": 3.6823, "step": 627712 }, { "epoch": 0.01, "learning_rate": 3.971463537834709e-05, "loss": 3.6783, "step": 628224 }, { "epoch": 0.01, "learning_rate": 3.970624943083657e-05, "loss": 3.6883, "step": 628736 }, { "epoch": 0.01, "learning_rate": 3.9697863483326056e-05, "loss": 3.6779, "step": 629248 }, { "epoch": 0.01, "learning_rate": 3.9689477535815536e-05, "loss": 3.6829, "step": 629760 }, { "epoch": 0.01, "learning_rate": 3.9681107967108746e-05, "loss": 3.6835, "step": 630272 }, { "epoch": 0.01, "learning_rate": 3.9672722019598225e-05, "loss": 3.6723, "step": 630784 }, { "epoch": 0.01, "learning_rate": 3.9664336072087705e-05, "loss": 3.6728, "step": 631296 }, { "epoch": 0.01, "learning_rate": 3.9655950124577185e-05, "loss": 3.6643, "step": 631808 }, { "epoch": 0.01, "learning_rate": 3.9647564177066665e-05, "loss": 3.6893, "step": 632320 }, { "epoch": 0.01, "learning_rate": 3.9639194608359874e-05, "loss": 3.6773, "step": 632832 }, { "epoch": 0.01, "learning_rate": 3.9630808660849354e-05, "loss": 3.6712, "step": 633344 }, { "epoch": 0.01, "learning_rate": 3.9622422713338834e-05, "loss": 3.6831, "step": 633856 }, { "epoch": 0.01, "learning_rate": 3.9614036765828314e-05, "loss": 3.6709, "step": 634368 }, { "epoch": 0.01, "learning_rate": 3.9605667197121523e-05, "loss": 3.6876, "step": 634880 }, { "epoch": 0.01, "learning_rate": 3.959728124961101e-05, "loss": 3.6734, "step": 635392 }, { "epoch": 0.01, "learning_rate": 3.958889530210049e-05, "loss": 3.6769, "step": 635904 }, { "epoch": 0.01, "learning_rate": 3.958050935458997e-05, "loss": 3.674, "step": 636416 }, { "epoch": 0.01, "learning_rate": 3.957212340707945e-05, "loss": 3.674, "step": 636928 }, { "epoch": 0.01, "learning_rate": 3.956375383837266e-05, "loss": 3.6813, "step": 637440 }, { "epoch": 0.01, "learning_rate": 3.955536789086214e-05, "loss": 3.6646, "step": 637952 }, { "epoch": 0.01, "learning_rate": 3.954698194335162e-05, "loss": 3.6759, "step": 638464 }, { "epoch": 0.01, "learning_rate": 3.953859599584109e-05, "loss": 3.6736, "step": 638976 }, { "epoch": 0.01, "learning_rate": 3.953021004833057e-05, "loss": 3.6761, "step": 639488 }, { "epoch": 0.01, "learning_rate": 3.952184047962379e-05, "loss": 3.6751, "step": 640000 }, { "epoch": 0.01, "learning_rate": 3.951345453211327e-05, "loss": 3.6869, "step": 640512 }, { "epoch": 0.01, "learning_rate": 3.950506858460275e-05, "loss": 3.6637, "step": 641024 }, { "epoch": 0.01, "learning_rate": 3.949668263709223e-05, "loss": 3.671, "step": 641536 }, { "epoch": 0.01, "learning_rate": 3.948829668958171e-05, "loss": 3.6659, "step": 642048 }, { "epoch": 0.01, "learning_rate": 3.947992712087492e-05, "loss": 3.6719, "step": 642560 }, { "epoch": 0.01, "learning_rate": 3.94715411733644e-05, "loss": 3.6838, "step": 643072 }, { "epoch": 0.01, "learning_rate": 3.946315522585388e-05, "loss": 3.6713, "step": 643584 }, { "epoch": 0.01, "learning_rate": 3.945476927834336e-05, "loss": 3.6764, "step": 644096 }, { "epoch": 0.01, "learning_rate": 3.9446399709636566e-05, "loss": 3.6543, "step": 644608 }, { "epoch": 0.01, "learning_rate": 3.9438013762126046e-05, "loss": 3.6771, "step": 645120 }, { "epoch": 0.01, "learning_rate": 3.9429627814615526e-05, "loss": 3.6632, "step": 645632 }, { "epoch": 0.01, "learning_rate": 3.9421241867105006e-05, "loss": 3.6675, "step": 646144 }, { "epoch": 0.01, "learning_rate": 3.9412872298398215e-05, "loss": 3.6745, "step": 646656 }, { "epoch": 0.01, "learning_rate": 3.94044863508877e-05, "loss": 3.6723, "step": 647168 }, { "epoch": 0.01, "learning_rate": 3.939610040337718e-05, "loss": 3.6696, "step": 647680 }, { "epoch": 0.01, "learning_rate": 3.938771445586666e-05, "loss": 3.6883, "step": 648192 }, { "epoch": 0.01, "learning_rate": 3.937932850835614e-05, "loss": 3.6719, "step": 648704 }, { "epoch": 0.01, "learning_rate": 3.937095893964935e-05, "loss": 3.6816, "step": 649216 }, { "epoch": 0.01, "learning_rate": 3.936257299213883e-05, "loss": 3.6783, "step": 649728 }, { "epoch": 0.01, "learning_rate": 3.935418704462831e-05, "loss": 3.6625, "step": 650240 }, { "epoch": 0.01, "learning_rate": 3.934580109711779e-05, "loss": 3.6616, "step": 650752 }, { "epoch": 0.01, "learning_rate": 3.9337431528411e-05, "loss": 3.6769, "step": 651264 }, { "epoch": 0.01, "learning_rate": 3.932904558090048e-05, "loss": 3.6805, "step": 651776 }, { "epoch": 0.01, "learning_rate": 3.932065963338996e-05, "loss": 3.6717, "step": 652288 }, { "epoch": 0.01, "learning_rate": 3.931227368587944e-05, "loss": 3.6503, "step": 652800 }, { "epoch": 0.01, "learning_rate": 3.930388773836892e-05, "loss": 3.6644, "step": 653312 }, { "epoch": 0.01, "learning_rate": 3.9295518169662135e-05, "loss": 3.6608, "step": 653824 }, { "epoch": 0.01, "learning_rate": 3.9287132222151615e-05, "loss": 3.6699, "step": 654336 }, { "epoch": 0.01, "learning_rate": 3.9278746274641095e-05, "loss": 3.6717, "step": 654848 }, { "epoch": 0.01, "learning_rate": 3.9270360327130575e-05, "loss": 3.6763, "step": 655360 }, { "epoch": 0.01, "learning_rate": 3.9261974379620055e-05, "loss": 3.6724, "step": 655872 }, { "epoch": 0.02, "learning_rate": 3.9253604810913264e-05, "loss": 3.6649, "step": 656384 }, { "epoch": 0.02, "learning_rate": 3.9245218863402744e-05, "loss": 3.6654, "step": 656896 }, { "epoch": 0.02, "learning_rate": 3.9236832915892224e-05, "loss": 3.6668, "step": 657408 }, { "epoch": 0.02, "learning_rate": 3.9228446968381704e-05, "loss": 3.6598, "step": 657920 }, { "epoch": 0.02, "learning_rate": 3.922007739967491e-05, "loss": 3.673, "step": 658432 }, { "epoch": 0.02, "learning_rate": 3.921169145216439e-05, "loss": 3.6646, "step": 658944 }, { "epoch": 0.02, "learning_rate": 3.920330550465387e-05, "loss": 3.6703, "step": 659456 }, { "epoch": 0.02, "learning_rate": 3.919491955714335e-05, "loss": 3.6656, "step": 659968 }, { "epoch": 0.02, "learning_rate": 3.918653360963283e-05, "loss": 3.6872, "step": 660480 }, { "epoch": 0.02, "learning_rate": 3.917816404092605e-05, "loss": 3.6623, "step": 660992 }, { "epoch": 0.02, "learning_rate": 3.916977809341553e-05, "loss": 3.6762, "step": 661504 }, { "epoch": 0.02, "learning_rate": 3.916139214590501e-05, "loss": 3.6749, "step": 662016 }, { "epoch": 0.02, "learning_rate": 3.915300619839449e-05, "loss": 3.6655, "step": 662528 }, { "epoch": 0.02, "learning_rate": 3.914462025088397e-05, "loss": 3.6746, "step": 663040 }, { "epoch": 0.02, "learning_rate": 3.913625068217718e-05, "loss": 3.6708, "step": 663552 }, { "epoch": 0.02, "learning_rate": 3.912786473466666e-05, "loss": 3.6757, "step": 664064 }, { "epoch": 0.02, "learning_rate": 3.911947878715614e-05, "loss": 3.6636, "step": 664576 }, { "epoch": 0.02, "learning_rate": 3.911109283964562e-05, "loss": 3.661, "step": 665088 }, { "epoch": 0.02, "learning_rate": 3.91027068921351e-05, "loss": 3.6627, "step": 665600 }, { "epoch": 0.02, "learning_rate": 3.909433732342831e-05, "loss": 3.6692, "step": 666112 }, { "epoch": 0.02, "learning_rate": 3.9085951375917787e-05, "loss": 3.6697, "step": 666624 }, { "epoch": 0.02, "learning_rate": 3.907756542840727e-05, "loss": 3.665, "step": 667136 }, { "epoch": 0.02, "learning_rate": 3.906917948089675e-05, "loss": 3.6423, "step": 667648 }, { "epoch": 0.02, "learning_rate": 3.9060793533386226e-05, "loss": 3.6688, "step": 668160 }, { "epoch": 0.02, "learning_rate": 3.905242396467944e-05, "loss": 3.6713, "step": 668672 }, { "epoch": 0.02, "learning_rate": 3.904403801716892e-05, "loss": 3.6658, "step": 669184 }, { "epoch": 0.02, "learning_rate": 3.90356520696584e-05, "loss": 3.6748, "step": 669696 }, { "epoch": 0.02, "learning_rate": 3.9027266122147875e-05, "loss": 3.6731, "step": 670208 }, { "epoch": 0.02, "learning_rate": 3.901889655344109e-05, "loss": 3.6605, "step": 670720 }, { "epoch": 0.02, "learning_rate": 3.901051060593057e-05, "loss": 3.6766, "step": 671232 }, { "epoch": 0.02, "learning_rate": 3.900212465842005e-05, "loss": 3.6665, "step": 671744 }, { "epoch": 0.02, "learning_rate": 3.8993738710909524e-05, "loss": 3.6578, "step": 672256 }, { "epoch": 0.02, "learning_rate": 3.898536914220274e-05, "loss": 3.6617, "step": 672768 }, { "epoch": 0.02, "learning_rate": 3.897698319469223e-05, "loss": 3.6661, "step": 673280 }, { "epoch": 0.02, "learning_rate": 3.89685972471817e-05, "loss": 3.6629, "step": 673792 }, { "epoch": 0.02, "learning_rate": 3.896021129967118e-05, "loss": 3.6589, "step": 674304 }, { "epoch": 0.02, "learning_rate": 3.8951841730964396e-05, "loss": 3.6696, "step": 674816 }, { "epoch": 0.02, "learning_rate": 3.8943455783453876e-05, "loss": 3.6666, "step": 675328 }, { "epoch": 0.02, "learning_rate": 3.893506983594335e-05, "loss": 3.6554, "step": 675840 }, { "epoch": 0.02, "learning_rate": 3.892668388843283e-05, "loss": 3.673, "step": 676352 }, { "epoch": 0.02, "learning_rate": 3.891829794092231e-05, "loss": 3.6567, "step": 676864 }, { "epoch": 0.02, "learning_rate": 3.890992837221552e-05, "loss": 3.6731, "step": 677376 }, { "epoch": 0.02, "learning_rate": 3.8901542424705e-05, "loss": 3.6817, "step": 677888 }, { "epoch": 0.02, "learning_rate": 3.889315647719448e-05, "loss": 3.6635, "step": 678400 }, { "epoch": 0.02, "learning_rate": 3.8884770529683965e-05, "loss": 3.6652, "step": 678912 }, { "epoch": 0.02, "learning_rate": 3.8876400960977174e-05, "loss": 3.6638, "step": 679424 }, { "epoch": 0.02, "learning_rate": 3.8868015013466654e-05, "loss": 3.6617, "step": 679936 }, { "epoch": 0.02, "learning_rate": 3.8859629065956134e-05, "loss": 3.6639, "step": 680448 }, { "epoch": 0.02, "learning_rate": 3.8851243118445614e-05, "loss": 3.6788, "step": 680960 }, { "epoch": 0.02, "learning_rate": 3.884287354973882e-05, "loss": 3.6766, "step": 681472 }, { "epoch": 0.02, "learning_rate": 3.88344876022283e-05, "loss": 3.6673, "step": 681984 }, { "epoch": 0.02, "learning_rate": 3.882610165471778e-05, "loss": 3.6684, "step": 682496 }, { "epoch": 0.02, "learning_rate": 3.881771570720726e-05, "loss": 3.6686, "step": 683008 }, { "epoch": 0.02, "learning_rate": 3.880934613850047e-05, "loss": 3.6639, "step": 683520 }, { "epoch": 0.02, "learning_rate": 3.880096019098995e-05, "loss": 3.6616, "step": 684032 }, { "epoch": 0.02, "learning_rate": 3.879257424347943e-05, "loss": 3.6587, "step": 684544 }, { "epoch": 0.02, "learning_rate": 3.878418829596892e-05, "loss": 3.6672, "step": 685056 }, { "epoch": 0.02, "learning_rate": 3.877581872726213e-05, "loss": 3.6635, "step": 685568 }, { "epoch": 0.02, "learning_rate": 3.876743277975161e-05, "loss": 3.6511, "step": 686080 }, { "epoch": 0.02, "learning_rate": 3.875904683224109e-05, "loss": 3.6653, "step": 686592 }, { "epoch": 0.03, "eval_loss": 3.855044364929199, "eval_runtime": 318.203, "eval_samples_per_second": 1199.206, "eval_steps_per_second": 37.476, "step": 686871 }, { "epoch": 1.0, "learning_rate": 3.875066088473057e-05, "loss": 3.6617, "step": 687104 }, { "epoch": 1.0, "learning_rate": 3.8742291316023777e-05, "loss": 3.6723, "step": 687616 }, { "epoch": 1.0, "learning_rate": 3.8733905368513256e-05, "loss": 3.6687, "step": 688128 }, { "epoch": 1.0, "learning_rate": 3.8725519421002736e-05, "loss": 3.6603, "step": 688640 }, { "epoch": 1.0, "learning_rate": 3.8717133473492216e-05, "loss": 3.6669, "step": 689152 }, { "epoch": 1.0, "learning_rate": 3.8708763904785425e-05, "loss": 3.6599, "step": 689664 }, { "epoch": 1.0, "learning_rate": 3.8700377957274905e-05, "loss": 3.659, "step": 690176 }, { "epoch": 1.0, "learning_rate": 3.8691992009764385e-05, "loss": 3.6556, "step": 690688 }, { "epoch": 1.0, "learning_rate": 3.8683606062253865e-05, "loss": 3.654, "step": 691200 }, { "epoch": 1.0, "learning_rate": 3.867523649354708e-05, "loss": 3.6622, "step": 691712 }, { "epoch": 1.0, "learning_rate": 3.866685054603656e-05, "loss": 3.665, "step": 692224 }, { "epoch": 1.0, "learning_rate": 3.865846459852604e-05, "loss": 3.6509, "step": 692736 }, { "epoch": 1.0, "learning_rate": 3.865007865101552e-05, "loss": 3.662, "step": 693248 }, { "epoch": 1.0, "learning_rate": 3.864170908230873e-05, "loss": 3.6496, "step": 693760 }, { "epoch": 1.0, "learning_rate": 3.863332313479821e-05, "loss": 3.6618, "step": 694272 }, { "epoch": 1.0, "learning_rate": 3.862493718728769e-05, "loss": 3.6423, "step": 694784 }, { "epoch": 1.0, "learning_rate": 3.861655123977717e-05, "loss": 3.6533, "step": 695296 }, { "epoch": 1.0, "learning_rate": 3.860816529226665e-05, "loss": 3.6571, "step": 695808 }, { "epoch": 1.0, "learning_rate": 3.859979572355986e-05, "loss": 3.6537, "step": 696320 }, { "epoch": 1.0, "learning_rate": 3.859140977604934e-05, "loss": 3.6675, "step": 696832 }, { "epoch": 1.0, "learning_rate": 3.858302382853882e-05, "loss": 3.6494, "step": 697344 }, { "epoch": 1.0, "learning_rate": 3.8574637881028306e-05, "loss": 3.679, "step": 697856 }, { "epoch": 1.0, "learning_rate": 3.8566251933517786e-05, "loss": 3.6546, "step": 698368 }, { "epoch": 1.0, "learning_rate": 3.8557882364810995e-05, "loss": 3.6592, "step": 698880 }, { "epoch": 1.0, "learning_rate": 3.8549496417300475e-05, "loss": 3.6576, "step": 699392 }, { "epoch": 1.0, "learning_rate": 3.8541110469789955e-05, "loss": 3.6628, "step": 699904 }, { "epoch": 1.0, "learning_rate": 3.8532724522279435e-05, "loss": 3.6615, "step": 700416 }, { "epoch": 1.0, "learning_rate": 3.8524354953572644e-05, "loss": 3.6545, "step": 700928 }, { "epoch": 1.0, "learning_rate": 3.8515969006062124e-05, "loss": 3.6571, "step": 701440 }, { "epoch": 1.0, "learning_rate": 3.8507583058551604e-05, "loss": 3.6608, "step": 701952 }, { "epoch": 1.01, "learning_rate": 3.8499197111041084e-05, "loss": 3.6402, "step": 702464 }, { "epoch": 1.01, "learning_rate": 3.849082754233429e-05, "loss": 3.6629, "step": 702976 }, { "epoch": 1.01, "learning_rate": 3.848244159482377e-05, "loss": 3.666, "step": 703488 }, { "epoch": 1.01, "learning_rate": 3.847405564731326e-05, "loss": 3.6575, "step": 704000 }, { "epoch": 1.01, "learning_rate": 3.846566969980274e-05, "loss": 3.6511, "step": 704512 }, { "epoch": 1.01, "learning_rate": 3.845730013109595e-05, "loss": 3.6641, "step": 705024 }, { "epoch": 1.01, "learning_rate": 3.844891418358543e-05, "loss": 3.656, "step": 705536 }, { "epoch": 1.01, "learning_rate": 3.844052823607491e-05, "loss": 3.6578, "step": 706048 }, { "epoch": 1.01, "learning_rate": 3.843214228856439e-05, "loss": 3.6579, "step": 706560 }, { "epoch": 1.01, "learning_rate": 3.84237727198576e-05, "loss": 3.6447, "step": 707072 }, { "epoch": 1.01, "learning_rate": 3.841538677234708e-05, "loss": 3.6481, "step": 707584 }, { "epoch": 1.01, "learning_rate": 3.840700082483656e-05, "loss": 3.6384, "step": 708096 }, { "epoch": 1.01, "learning_rate": 3.839861487732604e-05, "loss": 3.6624, "step": 708608 }, { "epoch": 1.01, "learning_rate": 3.839022892981552e-05, "loss": 3.652, "step": 709120 }, { "epoch": 1.01, "learning_rate": 3.8381859361108726e-05, "loss": 3.6434, "step": 709632 }, { "epoch": 1.01, "learning_rate": 3.837347341359821e-05, "loss": 3.6586, "step": 710144 }, { "epoch": 1.01, "learning_rate": 3.836508746608769e-05, "loss": 3.6465, "step": 710656 }, { "epoch": 1.01, "learning_rate": 3.835670151857717e-05, "loss": 3.6603, "step": 711168 }, { "epoch": 1.01, "learning_rate": 3.834833194987038e-05, "loss": 3.6553, "step": 711680 }, { "epoch": 1.01, "learning_rate": 3.833994600235986e-05, "loss": 3.649, "step": 712192 }, { "epoch": 1.01, "learning_rate": 3.833156005484934e-05, "loss": 3.6496, "step": 712704 }, { "epoch": 1.01, "learning_rate": 3.832317410733882e-05, "loss": 3.6476, "step": 713216 }, { "epoch": 1.01, "learning_rate": 3.831480453863203e-05, "loss": 3.6553, "step": 713728 }, { "epoch": 1.01, "learning_rate": 3.830641859112151e-05, "loss": 3.6368, "step": 714240 }, { "epoch": 1.01, "learning_rate": 3.829803264361099e-05, "loss": 3.654, "step": 714752 }, { "epoch": 1.01, "learning_rate": 3.828964669610047e-05, "loss": 3.6448, "step": 715264 }, { "epoch": 1.01, "learning_rate": 3.828127712739368e-05, "loss": 3.6523, "step": 715776 }, { "epoch": 1.01, "learning_rate": 3.827289117988317e-05, "loss": 3.6463, "step": 716288 }, { "epoch": 1.01, "learning_rate": 3.826450523237265e-05, "loss": 3.6607, "step": 716800 }, { "epoch": 1.01, "learning_rate": 3.825611928486213e-05, "loss": 3.6469, "step": 717312 }, { "epoch": 1.01, "learning_rate": 3.8247749716155336e-05, "loss": 3.6402, "step": 717824 }, { "epoch": 1.01, "learning_rate": 3.8239363768644816e-05, "loss": 3.6475, "step": 718336 }, { "epoch": 1.01, "learning_rate": 3.8230977821134296e-05, "loss": 3.6394, "step": 718848 }, { "epoch": 1.01, "learning_rate": 3.8222591873623776e-05, "loss": 3.6569, "step": 719360 }, { "epoch": 1.01, "learning_rate": 3.821420592611325e-05, "loss": 3.652, "step": 719872 }, { "epoch": 1.01, "learning_rate": 3.8205836357406465e-05, "loss": 3.6495, "step": 720384 }, { "epoch": 1.01, "learning_rate": 3.8197450409895945e-05, "loss": 3.6324, "step": 720896 }, { "epoch": 1.01, "learning_rate": 3.8189064462385425e-05, "loss": 3.6501, "step": 721408 }, { "epoch": 1.01, "learning_rate": 3.8180678514874905e-05, "loss": 3.6399, "step": 721920 }, { "epoch": 1.01, "learning_rate": 3.817230894616812e-05, "loss": 3.641, "step": 722432 }, { "epoch": 1.01, "learning_rate": 3.81639229986576e-05, "loss": 3.6474, "step": 722944 }, { "epoch": 1.01, "learning_rate": 3.8155537051147074e-05, "loss": 3.6461, "step": 723456 }, { "epoch": 1.01, "learning_rate": 3.8147151103636554e-05, "loss": 3.646, "step": 723968 }, { "epoch": 1.01, "learning_rate": 3.8138765156126033e-05, "loss": 3.663, "step": 724480 }, { "epoch": 1.01, "learning_rate": 3.813039558741925e-05, "loss": 3.6494, "step": 724992 }, { "epoch": 1.01, "learning_rate": 3.812200963990872e-05, "loss": 3.6575, "step": 725504 }, { "epoch": 1.01, "learning_rate": 3.81136236923982e-05, "loss": 3.6489, "step": 726016 }, { "epoch": 1.01, "learning_rate": 3.810523774488768e-05, "loss": 3.6418, "step": 726528 }, { "epoch": 1.01, "learning_rate": 3.80968681761809e-05, "loss": 3.6377, "step": 727040 }, { "epoch": 1.01, "learning_rate": 3.808848222867037e-05, "loss": 3.6506, "step": 727552 }, { "epoch": 1.01, "learning_rate": 3.808009628115986e-05, "loss": 3.6524, "step": 728064 }, { "epoch": 1.01, "learning_rate": 3.807171033364934e-05, "loss": 3.6523, "step": 728576 }, { "epoch": 1.01, "learning_rate": 3.806334076494255e-05, "loss": 3.6272, "step": 729088 }, { "epoch": 1.01, "learning_rate": 3.805495481743203e-05, "loss": 3.6375, "step": 729600 }, { "epoch": 1.01, "learning_rate": 3.804656886992151e-05, "loss": 3.6348, "step": 730112 }, { "epoch": 1.01, "learning_rate": 3.803818292241099e-05, "loss": 3.6447, "step": 730624 }, { "epoch": 1.01, "learning_rate": 3.8029813353704196e-05, "loss": 3.6433, "step": 731136 }, { "epoch": 1.01, "learning_rate": 3.8021427406193676e-05, "loss": 3.6548, "step": 731648 }, { "epoch": 1.01, "learning_rate": 3.8013041458683156e-05, "loss": 3.6488, "step": 732160 }, { "epoch": 1.02, "learning_rate": 3.8004655511172636e-05, "loss": 3.6441, "step": 732672 }, { "epoch": 1.02, "learning_rate": 3.7996285942465845e-05, "loss": 3.6397, "step": 733184 }, { "epoch": 1.02, "learning_rate": 3.7987899994955325e-05, "loss": 3.6414, "step": 733696 }, { "epoch": 1.02, "learning_rate": 3.797951404744481e-05, "loss": 3.6345, "step": 734208 }, { "epoch": 1.02, "learning_rate": 3.797112809993429e-05, "loss": 3.6469, "step": 734720 }, { "epoch": 1.02, "learning_rate": 3.79627585312275e-05, "loss": 3.6434, "step": 735232 }, { "epoch": 1.02, "learning_rate": 3.795437258371698e-05, "loss": 3.6418, "step": 735744 }, { "epoch": 1.02, "learning_rate": 3.794598663620646e-05, "loss": 3.6444, "step": 736256 }, { "epoch": 1.02, "learning_rate": 3.793760068869594e-05, "loss": 3.6581, "step": 736768 }, { "epoch": 1.02, "learning_rate": 3.792923111998915e-05, "loss": 3.6412, "step": 737280 }, { "epoch": 1.02, "learning_rate": 3.792084517247863e-05, "loss": 3.6536, "step": 737792 }, { "epoch": 1.02, "learning_rate": 3.791245922496811e-05, "loss": 3.6489, "step": 738304 }, { "epoch": 1.02, "learning_rate": 3.790407327745759e-05, "loss": 3.645, "step": 738816 }, { "epoch": 1.02, "learning_rate": 3.789568732994707e-05, "loss": 3.6432, "step": 739328 }, { "epoch": 1.02, "learning_rate": 3.788731776124028e-05, "loss": 3.6506, "step": 739840 }, { "epoch": 1.02, "learning_rate": 3.7878931813729766e-05, "loss": 3.6492, "step": 740352 }, { "epoch": 1.02, "learning_rate": 3.7870545866219246e-05, "loss": 3.6398, "step": 740864 }, { "epoch": 1.02, "learning_rate": 3.7862159918708725e-05, "loss": 3.6386, "step": 741376 }, { "epoch": 1.02, "learning_rate": 3.7853790350001935e-05, "loss": 3.6348, "step": 741888 }, { "epoch": 1.02, "learning_rate": 3.7845404402491415e-05, "loss": 3.6423, "step": 742400 }, { "epoch": 1.02, "learning_rate": 3.7837018454980894e-05, "loss": 3.6483, "step": 742912 }, { "epoch": 1.02, "learning_rate": 3.7828632507470374e-05, "loss": 3.6423, "step": 743424 }, { "epoch": 1.02, "learning_rate": 3.7820262938763584e-05, "loss": 3.6219, "step": 743936 }, { "epoch": 1.02, "learning_rate": 3.7811876991253063e-05, "loss": 3.6379, "step": 744448 }, { "epoch": 1.02, "learning_rate": 3.7803491043742543e-05, "loss": 3.6453, "step": 744960 }, { "epoch": 1.02, "learning_rate": 3.7795105096232023e-05, "loss": 3.646, "step": 745472 }, { "epoch": 1.02, "learning_rate": 3.778673552752523e-05, "loss": 3.6526, "step": 745984 }, { "epoch": 1.02, "learning_rate": 3.777834958001471e-05, "loss": 3.648, "step": 746496 }, { "epoch": 1.02, "learning_rate": 3.77699636325042e-05, "loss": 3.6384, "step": 747008 }, { "epoch": 1.02, "learning_rate": 3.776157768499368e-05, "loss": 3.6476, "step": 747520 }, { "epoch": 1.02, "learning_rate": 3.775319173748316e-05, "loss": 3.6452, "step": 748032 }, { "epoch": 1.02, "learning_rate": 3.774482216877637e-05, "loss": 3.6382, "step": 748544 }, { "epoch": 1.02, "learning_rate": 3.773643622126585e-05, "loss": 3.6342, "step": 749056 }, { "epoch": 1.02, "learning_rate": 3.772805027375533e-05, "loss": 3.6453, "step": 749568 }, { "epoch": 1.02, "learning_rate": 3.771966432624481e-05, "loss": 3.635, "step": 750080 }, { "epoch": 1.02, "learning_rate": 3.771129475753802e-05, "loss": 3.6395, "step": 750592 }, { "epoch": 1.02, "learning_rate": 3.77029088100275e-05, "loss": 3.6433, "step": 751104 }, { "epoch": 1.02, "learning_rate": 3.769452286251698e-05, "loss": 3.6457, "step": 751616 }, { "epoch": 1.02, "learning_rate": 3.768613691500646e-05, "loss": 3.6314, "step": 752128 }, { "epoch": 1.02, "learning_rate": 3.767775096749594e-05, "loss": 3.6465, "step": 752640 }, { "epoch": 1.02, "learning_rate": 3.766938139878915e-05, "loss": 3.634, "step": 753152 }, { "epoch": 1.02, "learning_rate": 3.766099545127863e-05, "loss": 3.6499, "step": 753664 }, { "epoch": 1.02, "learning_rate": 3.765260950376811e-05, "loss": 3.6568, "step": 754176 }, { "epoch": 1.02, "learning_rate": 3.764422355625759e-05, "loss": 3.6392, "step": 754688 }, { "epoch": 1.02, "learning_rate": 3.76358539875508e-05, "loss": 3.6376, "step": 755200 }, { "epoch": 1.02, "learning_rate": 3.762746804004028e-05, "loss": 3.6445, "step": 755712 }, { "epoch": 1.02, "learning_rate": 3.761908209252976e-05, "loss": 3.6376, "step": 756224 }, { "epoch": 1.02, "learning_rate": 3.761069614501924e-05, "loss": 3.6409, "step": 756736 }, { "epoch": 1.02, "learning_rate": 3.760232657631245e-05, "loss": 3.6542, "step": 757248 }, { "epoch": 1.02, "learning_rate": 3.759394062880193e-05, "loss": 3.6482, "step": 757760 }, { "epoch": 1.02, "learning_rate": 3.758555468129141e-05, "loss": 3.6466, "step": 758272 }, { "epoch": 1.02, "learning_rate": 3.757716873378089e-05, "loss": 3.6463, "step": 758784 }, { "epoch": 1.02, "learning_rate": 3.7568799165074107e-05, "loss": 3.6469, "step": 759296 }, { "epoch": 1.02, "learning_rate": 3.7560413217563586e-05, "loss": 3.6374, "step": 759808 }, { "epoch": 1.02, "learning_rate": 3.7552027270053066e-05, "loss": 3.638, "step": 760320 }, { "epoch": 1.02, "learning_rate": 3.7543641322542546e-05, "loss": 3.6351, "step": 760832 }, { "epoch": 1.02, "learning_rate": 3.7535271753835755e-05, "loss": 3.6463, "step": 761344 }, { "epoch": 1.02, "learning_rate": 3.7526885806325235e-05, "loss": 3.6404, "step": 761856 }, { "epoch": 1.02, "learning_rate": 3.7518499858814715e-05, "loss": 3.6227, "step": 762368 }, { "epoch": 1.02, "learning_rate": 3.7510113911304195e-05, "loss": 3.6444, "step": 762880 }, { "epoch": 1.03, "eval_loss": 3.8525781631469727, "eval_runtime": 310.6369, "eval_samples_per_second": 1228.415, "eval_steps_per_second": 38.389, "step": 763190 }, { "epoch": 0.0, "learning_rate": 3.7501744342597404e-05, "loss": 3.6517, "step": 763392 }, { "epoch": 0.0, "learning_rate": 3.7493358395086884e-05, "loss": 3.6382, "step": 763904 }, { "epoch": 0.0, "learning_rate": 3.7484972447576364e-05, "loss": 3.6427, "step": 764416 }, { "epoch": 0.0, "learning_rate": 3.7476586500065844e-05, "loss": 3.6504, "step": 764928 }, { "epoch": 0.0, "learning_rate": 3.746821693135906e-05, "loss": 3.6575, "step": 765440 }, { "epoch": 0.0, "learning_rate": 3.745983098384854e-05, "loss": 3.6463, "step": 765952 }, { "epoch": 0.0, "learning_rate": 3.745144503633802e-05, "loss": 3.6475, "step": 766464 }, { "epoch": 0.0, "learning_rate": 3.74430590888275e-05, "loss": 3.6364, "step": 766976 }, { "epoch": 0.0, "learning_rate": 3.743468952012071e-05, "loss": 3.6347, "step": 767488 }, { "epoch": 0.0, "learning_rate": 3.742630357261019e-05, "loss": 3.6422, "step": 768000 }, { "epoch": 0.0, "learning_rate": 3.741791762509967e-05, "loss": 3.6499, "step": 768512 }, { "epoch": 0.0, "learning_rate": 3.740953167758915e-05, "loss": 3.6393, "step": 769024 }, { "epoch": 0.0, "learning_rate": 3.740114573007862e-05, "loss": 3.6429, "step": 769536 }, { "epoch": 0.0, "learning_rate": 3.739277616137184e-05, "loss": 3.6289, "step": 770048 }, { "epoch": 0.0, "learning_rate": 3.738439021386132e-05, "loss": 3.6366, "step": 770560 }, { "epoch": 0.0, "learning_rate": 3.73760042663508e-05, "loss": 3.6203, "step": 771072 }, { "epoch": 0.0, "learning_rate": 3.736761831884028e-05, "loss": 3.6376, "step": 771584 }, { "epoch": 0.0, "learning_rate": 3.7359248750133494e-05, "loss": 3.6398, "step": 772096 }, { "epoch": 0.0, "learning_rate": 3.7350862802622974e-05, "loss": 3.6294, "step": 772608 }, { "epoch": 0.0, "learning_rate": 3.7342476855112454e-05, "loss": 3.652, "step": 773120 }, { "epoch": 0.0, "learning_rate": 3.733409090760193e-05, "loss": 3.6488, "step": 773632 }, { "epoch": 0.0, "learning_rate": 3.732572133889514e-05, "loss": 3.6446, "step": 774144 }, { "epoch": 0.0, "learning_rate": 3.731733539138462e-05, "loss": 3.639, "step": 774656 }, { "epoch": 0.0, "learning_rate": 3.7308949443874096e-05, "loss": 3.6373, "step": 775168 }, { "epoch": 0.0, "learning_rate": 3.7300563496363576e-05, "loss": 3.6456, "step": 775680 }, { "epoch": 0.0, "learning_rate": 3.729219392765679e-05, "loss": 3.6496, "step": 776192 }, { "epoch": 0.0, "learning_rate": 3.728380798014627e-05, "loss": 3.6274, "step": 776704 }, { "epoch": 0.0, "learning_rate": 3.727542203263575e-05, "loss": 3.6418, "step": 777216 }, { "epoch": 0.0, "learning_rate": 3.726703608512523e-05, "loss": 3.6331, "step": 777728 }, { "epoch": 0.0, "learning_rate": 3.725866651641845e-05, "loss": 3.634, "step": 778240 }, { "epoch": 0.01, "learning_rate": 3.725028056890793e-05, "loss": 3.6398, "step": 778752 }, { "epoch": 0.01, "learning_rate": 3.72418946213974e-05, "loss": 3.6415, "step": 779264 }, { "epoch": 0.01, "learning_rate": 3.723350867388688e-05, "loss": 3.6381, "step": 779776 }, { "epoch": 0.01, "learning_rate": 3.7225139105180096e-05, "loss": 3.6539, "step": 780288 }, { "epoch": 0.01, "learning_rate": 3.721675315766957e-05, "loss": 3.6381, "step": 780800 }, { "epoch": 0.01, "learning_rate": 3.720836721015905e-05, "loss": 3.64, "step": 781312 }, { "epoch": 0.01, "learning_rate": 3.719998126264853e-05, "loss": 3.6454, "step": 781824 }, { "epoch": 0.01, "learning_rate": 3.719159531513801e-05, "loss": 3.626, "step": 782336 }, { "epoch": 0.01, "learning_rate": 3.718322574643122e-05, "loss": 3.6306, "step": 782848 }, { "epoch": 0.01, "learning_rate": 3.7174839798920705e-05, "loss": 3.6302, "step": 783360 }, { "epoch": 0.01, "learning_rate": 3.7166453851410185e-05, "loss": 3.6248, "step": 783872 }, { "epoch": 0.01, "learning_rate": 3.7158067903899665e-05, "loss": 3.6322, "step": 784384 }, { "epoch": 0.01, "learning_rate": 3.7149698335192874e-05, "loss": 3.6456, "step": 784896 }, { "epoch": 0.01, "learning_rate": 3.7141312387682354e-05, "loss": 3.6321, "step": 785408 }, { "epoch": 0.01, "learning_rate": 3.7132926440171834e-05, "loss": 3.6345, "step": 785920 }, { "epoch": 0.01, "learning_rate": 3.7124540492661314e-05, "loss": 3.6328, "step": 786432 }, { "epoch": 0.01, "learning_rate": 3.711617092395452e-05, "loss": 3.6374, "step": 786944 }, { "epoch": 0.01, "learning_rate": 3.7107784976444e-05, "loss": 3.6235, "step": 787456 }, { "epoch": 0.01, "learning_rate": 3.709939902893348e-05, "loss": 3.6153, "step": 787968 }, { "epoch": 0.01, "learning_rate": 3.709101308142296e-05, "loss": 3.6417, "step": 788480 }, { "epoch": 0.01, "learning_rate": 3.708264351271617e-05, "loss": 3.6397, "step": 788992 }, { "epoch": 0.01, "learning_rate": 3.707425756520566e-05, "loss": 3.6472, "step": 789504 }, { "epoch": 0.01, "learning_rate": 3.706587161769514e-05, "loss": 3.6354, "step": 790016 }, { "epoch": 0.01, "learning_rate": 3.705748567018462e-05, "loss": 3.6278, "step": 790528 }, { "epoch": 0.01, "learning_rate": 3.704911610147783e-05, "loss": 3.6262, "step": 791040 }, { "epoch": 0.01, "learning_rate": 3.704073015396731e-05, "loss": 3.6266, "step": 791552 }, { "epoch": 0.01, "learning_rate": 3.703234420645679e-05, "loss": 3.6457, "step": 792064 }, { "epoch": 0.01, "learning_rate": 3.702395825894627e-05, "loss": 3.6155, "step": 792576 }, { "epoch": 0.01, "learning_rate": 3.701558869023948e-05, "loss": 3.6566, "step": 793088 }, { "epoch": 0.01, "learning_rate": 3.700720274272896e-05, "loss": 3.6356, "step": 793600 }, { "epoch": 0.01, "learning_rate": 3.699881679521844e-05, "loss": 3.6102, "step": 794112 }, { "epoch": 0.01, "learning_rate": 3.699043084770792e-05, "loss": 3.6418, "step": 794624 }, { "epoch": 0.01, "learning_rate": 3.6982061279001126e-05, "loss": 3.6284, "step": 795136 }, { "epoch": 0.01, "learning_rate": 3.6973675331490606e-05, "loss": 3.6156, "step": 795648 }, { "epoch": 0.01, "learning_rate": 3.696528938398009e-05, "loss": 3.6356, "step": 796160 }, { "epoch": 0.01, "learning_rate": 3.695690343646957e-05, "loss": 3.6392, "step": 796672 }, { "epoch": 0.01, "learning_rate": 3.694853386776278e-05, "loss": 3.6199, "step": 797184 }, { "epoch": 0.01, "learning_rate": 3.694014792025226e-05, "loss": 3.6352, "step": 797696 }, { "epoch": 0.01, "learning_rate": 3.693176197274174e-05, "loss": 3.6111, "step": 798208 }, { "epoch": 0.01, "learning_rate": 3.692337602523122e-05, "loss": 3.6239, "step": 798720 }, { "epoch": 0.01, "learning_rate": 3.691500645652443e-05, "loss": 3.6319, "step": 799232 }, { "epoch": 0.01, "learning_rate": 3.690662050901391e-05, "loss": 3.6266, "step": 799744 }, { "epoch": 0.01, "learning_rate": 3.689823456150339e-05, "loss": 3.6326, "step": 800256 }, { "epoch": 0.01, "learning_rate": 3.688984861399287e-05, "loss": 3.6259, "step": 800768 }, { "epoch": 0.01, "learning_rate": 3.688147904528608e-05, "loss": 3.6425, "step": 801280 }, { "epoch": 0.01, "learning_rate": 3.687309309777556e-05, "loss": 3.6322, "step": 801792 }, { "epoch": 0.01, "learning_rate": 3.6864707150265046e-05, "loss": 3.6386, "step": 802304 }, { "epoch": 0.01, "learning_rate": 3.6856321202754526e-05, "loss": 3.6252, "step": 802816 }, { "epoch": 0.01, "learning_rate": 3.6847935255244006e-05, "loss": 3.6204, "step": 803328 }, { "epoch": 0.01, "learning_rate": 3.6839565686537215e-05, "loss": 3.6328, "step": 803840 }, { "epoch": 0.01, "learning_rate": 3.6831179739026695e-05, "loss": 3.6303, "step": 804352 }, { "epoch": 0.01, "learning_rate": 3.6822793791516175e-05, "loss": 3.6293, "step": 804864 }, { "epoch": 0.01, "learning_rate": 3.6814407844005655e-05, "loss": 3.6358, "step": 805376 }, { "epoch": 0.01, "learning_rate": 3.6806038275298864e-05, "loss": 3.619, "step": 805888 }, { "epoch": 0.01, "learning_rate": 3.6797652327788344e-05, "loss": 3.6147, "step": 806400 }, { "epoch": 0.01, "learning_rate": 3.6789266380277824e-05, "loss": 3.6272, "step": 806912 }, { "epoch": 0.01, "learning_rate": 3.6780880432767304e-05, "loss": 3.6346, "step": 807424 }, { "epoch": 0.01, "learning_rate": 3.677251086406051e-05, "loss": 3.62, "step": 807936 }, { "epoch": 0.01, "learning_rate": 3.676412491655e-05, "loss": 3.6311, "step": 808448 }, { "epoch": 0.01, "learning_rate": 3.675573896903948e-05, "loss": 3.6265, "step": 808960 }, { "epoch": 0.02, "learning_rate": 3.674735302152896e-05, "loss": 3.6226, "step": 809472 }, { "epoch": 0.02, "learning_rate": 3.673898345282217e-05, "loss": 3.6179, "step": 809984 }, { "epoch": 0.02, "learning_rate": 3.673059750531165e-05, "loss": 3.624, "step": 810496 }, { "epoch": 0.02, "learning_rate": 3.672221155780113e-05, "loss": 3.6392, "step": 811008 }, { "epoch": 0.02, "learning_rate": 3.671382561029061e-05, "loss": 3.6322, "step": 811520 }, { "epoch": 0.02, "learning_rate": 3.670545604158382e-05, "loss": 3.6319, "step": 812032 }, { "epoch": 0.02, "learning_rate": 3.66970700940733e-05, "loss": 3.6213, "step": 812544 }, { "epoch": 0.02, "learning_rate": 3.668868414656278e-05, "loss": 3.619, "step": 813056 }, { "epoch": 0.02, "learning_rate": 3.668029819905226e-05, "loss": 3.6264, "step": 813568 }, { "epoch": 0.02, "learning_rate": 3.667192863034547e-05, "loss": 3.6352, "step": 814080 }, { "epoch": 0.02, "learning_rate": 3.6663542682834954e-05, "loss": 3.6313, "step": 814592 }, { "epoch": 0.02, "learning_rate": 3.6655156735324434e-05, "loss": 3.6326, "step": 815104 }, { "epoch": 0.02, "learning_rate": 3.6646770787813914e-05, "loss": 3.6245, "step": 815616 }, { "epoch": 0.02, "learning_rate": 3.663840121910712e-05, "loss": 3.6245, "step": 816128 }, { "epoch": 0.02, "learning_rate": 3.66300152715966e-05, "loss": 3.6297, "step": 816640 }, { "epoch": 0.02, "learning_rate": 3.662162932408608e-05, "loss": 3.6255, "step": 817152 }, { "epoch": 0.02, "learning_rate": 3.661324337657556e-05, "loss": 3.6168, "step": 817664 }, { "epoch": 0.02, "learning_rate": 3.660487380786877e-05, "loss": 3.6293, "step": 818176 }, { "epoch": 0.02, "learning_rate": 3.659648786035825e-05, "loss": 3.6244, "step": 818688 }, { "epoch": 0.02, "learning_rate": 3.658810191284773e-05, "loss": 3.623, "step": 819200 }, { "epoch": 0.02, "learning_rate": 3.657971596533721e-05, "loss": 3.6176, "step": 819712 }, { "epoch": 0.02, "learning_rate": 3.657133001782669e-05, "loss": 3.6176, "step": 820224 }, { "epoch": 0.02, "learning_rate": 3.656296044911991e-05, "loss": 3.6273, "step": 820736 }, { "epoch": 0.02, "learning_rate": 3.655457450160939e-05, "loss": 3.6262, "step": 821248 }, { "epoch": 0.02, "learning_rate": 3.654618855409887e-05, "loss": 3.6268, "step": 821760 }, { "epoch": 0.02, "learning_rate": 3.653780260658835e-05, "loss": 3.6343, "step": 822272 }, { "epoch": 0.02, "learning_rate": 3.6529433037881556e-05, "loss": 3.6346, "step": 822784 }, { "epoch": 0.02, "learning_rate": 3.6521047090371036e-05, "loss": 3.6293, "step": 823296 }, { "epoch": 0.02, "learning_rate": 3.6512661142860516e-05, "loss": 3.6271, "step": 823808 }, { "epoch": 0.02, "learning_rate": 3.6504275195349996e-05, "loss": 3.6179, "step": 824320 }, { "epoch": 0.02, "learning_rate": 3.6495905626643205e-05, "loss": 3.6283, "step": 824832 }, { "epoch": 0.02, "learning_rate": 3.6487519679132685e-05, "loss": 3.6228, "step": 825344 }, { "epoch": 0.02, "learning_rate": 3.6479133731622165e-05, "loss": 3.6195, "step": 825856 }, { "epoch": 0.02, "learning_rate": 3.6470747784111645e-05, "loss": 3.6191, "step": 826368 }, { "epoch": 0.02, "learning_rate": 3.646237821540486e-05, "loss": 3.6268, "step": 826880 }, { "epoch": 0.02, "learning_rate": 3.645399226789434e-05, "loss": 3.626, "step": 827392 }, { "epoch": 0.02, "learning_rate": 3.644560632038382e-05, "loss": 3.6222, "step": 827904 }, { "epoch": 0.02, "learning_rate": 3.64372203728733e-05, "loss": 3.622, "step": 828416 }, { "epoch": 0.02, "learning_rate": 3.642885080416651e-05, "loss": 3.6207, "step": 828928 }, { "epoch": 0.02, "learning_rate": 3.642046485665599e-05, "loss": 3.6285, "step": 829440 }, { "epoch": 0.02, "learning_rate": 3.641207890914547e-05, "loss": 3.6258, "step": 829952 }, { "epoch": 0.02, "learning_rate": 3.640369296163495e-05, "loss": 3.6363, "step": 830464 }, { "epoch": 0.02, "learning_rate": 3.639532339292816e-05, "loss": 3.6178, "step": 830976 }, { "epoch": 0.02, "learning_rate": 3.638693744541764e-05, "loss": 3.6224, "step": 831488 }, { "epoch": 0.02, "learning_rate": 3.637855149790712e-05, "loss": 3.6306, "step": 832000 }, { "epoch": 0.02, "learning_rate": 3.63701655503966e-05, "loss": 3.6181, "step": 832512 }, { "epoch": 0.02, "learning_rate": 3.6361795981689815e-05, "loss": 3.6273, "step": 833024 }, { "epoch": 0.02, "learning_rate": 3.6353410034179295e-05, "loss": 3.6264, "step": 833536 }, { "epoch": 0.02, "learning_rate": 3.6345024086668775e-05, "loss": 3.6291, "step": 834048 }, { "epoch": 0.02, "learning_rate": 3.633663813915825e-05, "loss": 3.6379, "step": 834560 }, { "epoch": 0.02, "learning_rate": 3.6328268570451464e-05, "loss": 3.6267, "step": 835072 }, { "epoch": 0.02, "learning_rate": 3.6319882622940944e-05, "loss": 3.6243, "step": 835584 }, { "epoch": 0.02, "learning_rate": 3.631149667543042e-05, "loss": 3.6294, "step": 836096 }, { "epoch": 0.02, "learning_rate": 3.63031107279199e-05, "loss": 3.6204, "step": 836608 }, { "epoch": 0.02, "learning_rate": 3.629474115921311e-05, "loss": 3.6204, "step": 837120 }, { "epoch": 0.02, "learning_rate": 3.628635521170259e-05, "loss": 3.6221, "step": 837632 }, { "epoch": 0.02, "learning_rate": 3.6277969264192066e-05, "loss": 3.6193, "step": 838144 }, { "epoch": 0.02, "learning_rate": 3.626958331668155e-05, "loss": 3.6202, "step": 838656 }, { "epoch": 0.02, "learning_rate": 3.626121374797477e-05, "loss": 3.6189, "step": 839168 }, { "epoch": 0.03, "eval_loss": 3.8472540378570557, "eval_runtime": 304.628, "eval_samples_per_second": 1252.646, "eval_steps_per_second": 39.146, "step": 839510 }, { "epoch": 1.0, "learning_rate": 3.625282780046425e-05, "loss": 3.6221, "step": 839680 }, { "epoch": 1.0, "learning_rate": 3.624444185295372e-05, "loss": 3.6191, "step": 840192 }, { "epoch": 1.0, "learning_rate": 3.62360559054432e-05, "loss": 3.6226, "step": 840704 }, { "epoch": 1.0, "learning_rate": 3.622768633673642e-05, "loss": 3.625, "step": 841216 }, { "epoch": 1.0, "learning_rate": 3.621930038922589e-05, "loss": 3.6319, "step": 841728 }, { "epoch": 1.0, "learning_rate": 3.621091444171537e-05, "loss": 3.6239, "step": 842240 }, { "epoch": 1.0, "learning_rate": 3.620252849420485e-05, "loss": 3.6229, "step": 842752 }, { "epoch": 1.0, "learning_rate": 3.6194158925498066e-05, "loss": 3.6156, "step": 843264 }, { "epoch": 1.0, "learning_rate": 3.618577297798754e-05, "loss": 3.6096, "step": 843776 }, { "epoch": 1.0, "learning_rate": 3.617738703047702e-05, "loss": 3.6159, "step": 844288 }, { "epoch": 1.0, "learning_rate": 3.6169001082966506e-05, "loss": 3.6326, "step": 844800 }, { "epoch": 1.0, "learning_rate": 3.6160615135455986e-05, "loss": 3.6104, "step": 845312 }, { "epoch": 1.0, "learning_rate": 3.6152245566749195e-05, "loss": 3.6214, "step": 845824 }, { "epoch": 1.0, "learning_rate": 3.6143859619238675e-05, "loss": 3.6043, "step": 846336 }, { "epoch": 1.0, "learning_rate": 3.6135473671728155e-05, "loss": 3.6095, "step": 846848 }, { "epoch": 1.0, "learning_rate": 3.6127087724217635e-05, "loss": 3.6012, "step": 847360 }, { "epoch": 1.0, "learning_rate": 3.6118718155510844e-05, "loss": 3.6153, "step": 847872 }, { "epoch": 1.0, "learning_rate": 3.6110332208000324e-05, "loss": 3.6164, "step": 848384 }, { "epoch": 1.0, "learning_rate": 3.6101946260489804e-05, "loss": 3.6113, "step": 848896 }, { "epoch": 1.0, "learning_rate": 3.6093560312979284e-05, "loss": 3.6211, "step": 849408 }, { "epoch": 1.0, "learning_rate": 3.608519074427249e-05, "loss": 3.6298, "step": 849920 }, { "epoch": 1.0, "learning_rate": 3.607680479676197e-05, "loss": 3.6206, "step": 850432 }, { "epoch": 1.0, "learning_rate": 3.606841884925145e-05, "loss": 3.6141, "step": 850944 }, { "epoch": 1.0, "learning_rate": 3.606003290174094e-05, "loss": 3.6117, "step": 851456 }, { "epoch": 1.0, "learning_rate": 3.605166333303415e-05, "loss": 3.6253, "step": 851968 }, { "epoch": 1.0, "learning_rate": 3.604327738552363e-05, "loss": 3.6201, "step": 852480 }, { "epoch": 1.0, "learning_rate": 3.603489143801311e-05, "loss": 3.6086, "step": 852992 }, { "epoch": 1.0, "learning_rate": 3.602650549050259e-05, "loss": 3.6179, "step": 853504 }, { "epoch": 1.0, "learning_rate": 3.60181359217958e-05, "loss": 3.6134, "step": 854016 }, { "epoch": 1.0, "learning_rate": 3.600974997428528e-05, "loss": 3.6065, "step": 854528 }, { "epoch": 1.01, "learning_rate": 3.600136402677476e-05, "loss": 3.6193, "step": 855040 }, { "epoch": 1.01, "learning_rate": 3.599297807926424e-05, "loss": 3.6173, "step": 855552 }, { "epoch": 1.01, "learning_rate": 3.598460851055745e-05, "loss": 3.6213, "step": 856064 }, { "epoch": 1.01, "learning_rate": 3.597622256304693e-05, "loss": 3.6293, "step": 856576 }, { "epoch": 1.01, "learning_rate": 3.596783661553641e-05, "loss": 3.6109, "step": 857088 }, { "epoch": 1.01, "learning_rate": 3.595945066802589e-05, "loss": 3.6196, "step": 857600 }, { "epoch": 1.01, "learning_rate": 3.59510810993191e-05, "loss": 3.6213, "step": 858112 }, { "epoch": 1.01, "learning_rate": 3.594269515180858e-05, "loss": 3.6047, "step": 858624 }, { "epoch": 1.01, "learning_rate": 3.593430920429806e-05, "loss": 3.6119, "step": 859136 }, { "epoch": 1.01, "learning_rate": 3.592592325678754e-05, "loss": 3.6023, "step": 859648 }, { "epoch": 1.01, "learning_rate": 3.591755368808075e-05, "loss": 3.6039, "step": 860160 }, { "epoch": 1.01, "learning_rate": 3.590916774057023e-05, "loss": 3.6091, "step": 860672 }, { "epoch": 1.01, "learning_rate": 3.590078179305971e-05, "loss": 3.6227, "step": 861184 }, { "epoch": 1.01, "learning_rate": 3.589239584554919e-05, "loss": 3.6095, "step": 861696 }, { "epoch": 1.01, "learning_rate": 3.58840262768424e-05, "loss": 3.6072, "step": 862208 }, { "epoch": 1.01, "learning_rate": 3.587564032933188e-05, "loss": 3.6141, "step": 862720 }, { "epoch": 1.01, "learning_rate": 3.586725438182136e-05, "loss": 3.6131, "step": 863232 }, { "epoch": 1.01, "learning_rate": 3.585886843431085e-05, "loss": 3.6035, "step": 863744 }, { "epoch": 1.01, "learning_rate": 3.5850498865604056e-05, "loss": 3.5929, "step": 864256 }, { "epoch": 1.01, "learning_rate": 3.5842112918093536e-05, "loss": 3.6165, "step": 864768 }, { "epoch": 1.01, "learning_rate": 3.5833726970583016e-05, "loss": 3.6171, "step": 865280 }, { "epoch": 1.01, "learning_rate": 3.5825341023072496e-05, "loss": 3.6221, "step": 865792 }, { "epoch": 1.01, "learning_rate": 3.5816971454365705e-05, "loss": 3.6147, "step": 866304 }, { "epoch": 1.01, "learning_rate": 3.5808585506855185e-05, "loss": 3.6047, "step": 866816 }, { "epoch": 1.01, "learning_rate": 3.5800199559344665e-05, "loss": 3.6045, "step": 867328 }, { "epoch": 1.01, "learning_rate": 3.5791813611834145e-05, "loss": 3.6004, "step": 867840 }, { "epoch": 1.01, "learning_rate": 3.5783444043127354e-05, "loss": 3.6217, "step": 868352 }, { "epoch": 1.01, "learning_rate": 3.5775058095616834e-05, "loss": 3.5951, "step": 868864 }, { "epoch": 1.01, "learning_rate": 3.5766672148106314e-05, "loss": 3.6316, "step": 869376 }, { "epoch": 1.01, "learning_rate": 3.57582862005958e-05, "loss": 3.6146, "step": 869888 }, { "epoch": 1.01, "learning_rate": 3.574991663188901e-05, "loss": 3.5924, "step": 870400 }, { "epoch": 1.01, "learning_rate": 3.574153068437849e-05, "loss": 3.6138, "step": 870912 }, { "epoch": 1.01, "learning_rate": 3.573314473686797e-05, "loss": 3.6075, "step": 871424 }, { "epoch": 1.01, "learning_rate": 3.572475878935745e-05, "loss": 3.594, "step": 871936 }, { "epoch": 1.01, "learning_rate": 3.571638922065066e-05, "loss": 3.6102, "step": 872448 }, { "epoch": 1.01, "learning_rate": 3.570800327314014e-05, "loss": 3.6183, "step": 872960 }, { "epoch": 1.01, "learning_rate": 3.569961732562962e-05, "loss": 3.6031, "step": 873472 }, { "epoch": 1.01, "learning_rate": 3.56912313781191e-05, "loss": 3.6091, "step": 873984 }, { "epoch": 1.01, "learning_rate": 3.568286180941231e-05, "loss": 3.5892, "step": 874496 }, { "epoch": 1.01, "learning_rate": 3.567447586190179e-05, "loss": 3.6012, "step": 875008 }, { "epoch": 1.01, "learning_rate": 3.566608991439127e-05, "loss": 3.6079, "step": 875520 }, { "epoch": 1.01, "learning_rate": 3.5657703966880754e-05, "loss": 3.6091, "step": 876032 }, { "epoch": 1.01, "learning_rate": 3.5649334398173963e-05, "loss": 3.6088, "step": 876544 }, { "epoch": 1.01, "learning_rate": 3.5640948450663443e-05, "loss": 3.6031, "step": 877056 }, { "epoch": 1.01, "learning_rate": 3.563256250315292e-05, "loss": 3.6227, "step": 877568 }, { "epoch": 1.01, "learning_rate": 3.56241765556424e-05, "loss": 3.6089, "step": 878080 }, { "epoch": 1.01, "learning_rate": 3.561580698693561e-05, "loss": 3.6146, "step": 878592 }, { "epoch": 1.01, "learning_rate": 3.560742103942509e-05, "loss": 3.6042, "step": 879104 }, { "epoch": 1.01, "learning_rate": 3.559903509191457e-05, "loss": 3.6013, "step": 879616 }, { "epoch": 1.01, "learning_rate": 3.559064914440405e-05, "loss": 3.6113, "step": 880128 }, { "epoch": 1.01, "learning_rate": 3.558227957569726e-05, "loss": 3.6086, "step": 880640 }, { "epoch": 1.01, "learning_rate": 3.557389362818674e-05, "loss": 3.604, "step": 881152 }, { "epoch": 1.01, "learning_rate": 3.556550768067622e-05, "loss": 3.6132, "step": 881664 }, { "epoch": 1.01, "learning_rate": 3.555712173316571e-05, "loss": 3.5997, "step": 882176 }, { "epoch": 1.01, "learning_rate": 3.554873578565519e-05, "loss": 3.591, "step": 882688 }, { "epoch": 1.01, "learning_rate": 3.55403662169484e-05, "loss": 3.6028, "step": 883200 }, { "epoch": 1.01, "learning_rate": 3.553198026943788e-05, "loss": 3.6125, "step": 883712 }, { "epoch": 1.01, "learning_rate": 3.552359432192736e-05, "loss": 3.5999, "step": 884224 }, { "epoch": 1.01, "learning_rate": 3.551520837441684e-05, "loss": 3.6067, "step": 884736 }, { "epoch": 1.01, "learning_rate": 3.5506838805710046e-05, "loss": 3.6057, "step": 885248 }, { "epoch": 1.02, "learning_rate": 3.5498452858199526e-05, "loss": 3.5988, "step": 885760 }, { "epoch": 1.02, "learning_rate": 3.5490066910689006e-05, "loss": 3.6002, "step": 886272 }, { "epoch": 1.02, "learning_rate": 3.5481680963178486e-05, "loss": 3.5997, "step": 886784 }, { "epoch": 1.02, "learning_rate": 3.5473311394471695e-05, "loss": 3.6122, "step": 887296 }, { "epoch": 1.02, "learning_rate": 3.5464925446961175e-05, "loss": 3.614, "step": 887808 }, { "epoch": 1.02, "learning_rate": 3.545653949945066e-05, "loss": 3.6154, "step": 888320 }, { "epoch": 1.02, "learning_rate": 3.544815355194014e-05, "loss": 3.599, "step": 888832 }, { "epoch": 1.02, "learning_rate": 3.543978398323335e-05, "loss": 3.5965, "step": 889344 }, { "epoch": 1.02, "learning_rate": 3.543139803572283e-05, "loss": 3.6084, "step": 889856 }, { "epoch": 1.02, "learning_rate": 3.542301208821231e-05, "loss": 3.6126, "step": 890368 }, { "epoch": 1.02, "learning_rate": 3.541462614070179e-05, "loss": 3.6096, "step": 890880 }, { "epoch": 1.02, "learning_rate": 3.5406256571995e-05, "loss": 3.6116, "step": 891392 }, { "epoch": 1.02, "learning_rate": 3.539787062448448e-05, "loss": 3.6044, "step": 891904 }, { "epoch": 1.02, "learning_rate": 3.538948467697396e-05, "loss": 3.6, "step": 892416 }, { "epoch": 1.02, "learning_rate": 3.538109872946344e-05, "loss": 3.6108, "step": 892928 }, { "epoch": 1.02, "learning_rate": 3.537272916075665e-05, "loss": 3.5998, "step": 893440 }, { "epoch": 1.02, "learning_rate": 3.536434321324613e-05, "loss": 3.5996, "step": 893952 }, { "epoch": 1.02, "learning_rate": 3.535595726573561e-05, "loss": 3.6031, "step": 894464 }, { "epoch": 1.02, "learning_rate": 3.5347571318225095e-05, "loss": 3.6034, "step": 894976 }, { "epoch": 1.02, "learning_rate": 3.5339201749518304e-05, "loss": 3.6005, "step": 895488 }, { "epoch": 1.02, "learning_rate": 3.5330815802007784e-05, "loss": 3.5937, "step": 896000 }, { "epoch": 1.02, "learning_rate": 3.5322429854497264e-05, "loss": 3.5945, "step": 896512 }, { "epoch": 1.02, "learning_rate": 3.5314043906986744e-05, "loss": 3.6094, "step": 897024 }, { "epoch": 1.02, "learning_rate": 3.530567433827995e-05, "loss": 3.6042, "step": 897536 }, { "epoch": 1.02, "learning_rate": 3.529728839076943e-05, "loss": 3.6043, "step": 898048 }, { "epoch": 1.02, "learning_rate": 3.528890244325891e-05, "loss": 3.6093, "step": 898560 }, { "epoch": 1.02, "learning_rate": 3.5280516495748386e-05, "loss": 3.6166, "step": 899072 }, { "epoch": 1.02, "learning_rate": 3.52721469270416e-05, "loss": 3.6045, "step": 899584 }, { "epoch": 1.02, "learning_rate": 3.526376097953108e-05, "loss": 3.6058, "step": 900096 }, { "epoch": 1.02, "learning_rate": 3.525537503202056e-05, "loss": 3.5967, "step": 900608 }, { "epoch": 1.02, "learning_rate": 3.524698908451004e-05, "loss": 3.6017, "step": 901120 }, { "epoch": 1.02, "learning_rate": 3.523861951580326e-05, "loss": 3.6016, "step": 901632 }, { "epoch": 1.02, "learning_rate": 3.523023356829274e-05, "loss": 3.604, "step": 902144 }, { "epoch": 1.02, "learning_rate": 3.522184762078222e-05, "loss": 3.5979, "step": 902656 }, { "epoch": 1.02, "learning_rate": 3.521346167327169e-05, "loss": 3.6043, "step": 903168 }, { "epoch": 1.02, "learning_rate": 3.520509210456491e-05, "loss": 3.6029, "step": 903680 }, { "epoch": 1.02, "learning_rate": 3.519670615705439e-05, "loss": 3.5987, "step": 904192 }, { "epoch": 1.02, "learning_rate": 3.518832020954386e-05, "loss": 3.6046, "step": 904704 }, { "epoch": 1.02, "learning_rate": 3.517993426203334e-05, "loss": 3.6001, "step": 905216 }, { "epoch": 1.02, "learning_rate": 3.5171564693326556e-05, "loss": 3.6036, "step": 905728 }, { "epoch": 1.02, "learning_rate": 3.5163178745816036e-05, "loss": 3.6051, "step": 906240 }, { "epoch": 1.02, "learning_rate": 3.5154792798305516e-05, "loss": 3.6165, "step": 906752 }, { "epoch": 1.02, "learning_rate": 3.5146406850794996e-05, "loss": 3.5969, "step": 907264 }, { "epoch": 1.02, "learning_rate": 3.513803728208821e-05, "loss": 3.6028, "step": 907776 }, { "epoch": 1.02, "learning_rate": 3.512965133457769e-05, "loss": 3.6059, "step": 908288 }, { "epoch": 1.02, "learning_rate": 3.5121265387067165e-05, "loss": 3.5975, "step": 908800 }, { "epoch": 1.02, "learning_rate": 3.5112879439556645e-05, "loss": 3.6021, "step": 909312 }, { "epoch": 1.02, "learning_rate": 3.510450987084986e-05, "loss": 3.6033, "step": 909824 }, { "epoch": 1.02, "learning_rate": 3.5096123923339334e-05, "loss": 3.6147, "step": 910336 }, { "epoch": 1.02, "learning_rate": 3.5087737975828814e-05, "loss": 3.611, "step": 910848 }, { "epoch": 1.02, "learning_rate": 3.5079352028318294e-05, "loss": 3.6067, "step": 911360 }, { "epoch": 1.02, "learning_rate": 3.507098245961151e-05, "loss": 3.6042, "step": 911872 }, { "epoch": 1.02, "learning_rate": 3.506259651210099e-05, "loss": 3.6073, "step": 912384 }, { "epoch": 1.02, "learning_rate": 3.505421056459047e-05, "loss": 3.6022, "step": 912896 }, { "epoch": 1.02, "learning_rate": 3.5045840995883685e-05, "loss": 3.5968, "step": 913408 }, { "epoch": 1.02, "learning_rate": 3.5037455048373165e-05, "loss": 3.6022, "step": 913920 }, { "epoch": 1.02, "learning_rate": 3.502906910086264e-05, "loss": 3.5946, "step": 914432 }, { "epoch": 1.02, "learning_rate": 3.502068315335212e-05, "loss": 3.6005, "step": 914944 }, { "epoch": 1.02, "learning_rate": 3.50122972058416e-05, "loss": 3.5975, "step": 915456 }, { "epoch": 1.03, "eval_loss": 3.845926284790039, "eval_runtime": 304.0738, "eval_samples_per_second": 1254.929, "eval_steps_per_second": 39.217, "step": 915830 }, { "epoch": 0.0, "learning_rate": 3.500391125833108e-05, "loss": 3.616, "step": 915968 }, { "epoch": 0.0, "learning_rate": 3.499552531082056e-05, "loss": 3.5949, "step": 916480 }, { "epoch": 0.0, "learning_rate": 3.498713936331004e-05, "loss": 3.5995, "step": 916992 }, { "epoch": 0.0, "learning_rate": 3.497875341579952e-05, "loss": 3.6073, "step": 917504 }, { "epoch": 0.0, "learning_rate": 3.497038384709273e-05, "loss": 3.6081, "step": 918016 }, { "epoch": 0.0, "learning_rate": 3.496199789958221e-05, "loss": 3.6066, "step": 918528 }, { "epoch": 0.0, "learning_rate": 3.4953611952071694e-05, "loss": 3.6074, "step": 919040 }, { "epoch": 0.0, "learning_rate": 3.4945226004561174e-05, "loss": 3.5909, "step": 919552 }, { "epoch": 0.0, "learning_rate": 3.493685643585438e-05, "loss": 3.5894, "step": 920064 }, { "epoch": 0.0, "learning_rate": 3.492847048834386e-05, "loss": 3.6, "step": 920576 }, { "epoch": 0.0, "learning_rate": 3.492008454083334e-05, "loss": 3.6046, "step": 921088 }, { "epoch": 0.0, "learning_rate": 3.491169859332282e-05, "loss": 3.5946, "step": 921600 }, { "epoch": 0.0, "learning_rate": 3.490332902461603e-05, "loss": 3.6029, "step": 922112 }, { "epoch": 0.0, "learning_rate": 3.489494307710551e-05, "loss": 3.5844, "step": 922624 }, { "epoch": 0.0, "learning_rate": 3.488655712959499e-05, "loss": 3.5897, "step": 923136 }, { "epoch": 0.0, "learning_rate": 3.487817118208447e-05, "loss": 3.5793, "step": 923648 }, { "epoch": 0.0, "learning_rate": 3.486980161337768e-05, "loss": 3.5983, "step": 924160 }, { "epoch": 0.0, "learning_rate": 3.486141566586716e-05, "loss": 3.5943, "step": 924672 }, { "epoch": 0.0, "learning_rate": 3.485302971835665e-05, "loss": 3.5921, "step": 925184 }, { "epoch": 0.0, "learning_rate": 3.484464377084613e-05, "loss": 3.5994, "step": 925696 }, { "epoch": 0.0, "learning_rate": 3.483627420213934e-05, "loss": 3.6093, "step": 926208 }, { "epoch": 0.0, "learning_rate": 3.482788825462882e-05, "loss": 3.6002, "step": 926720 }, { "epoch": 0.0, "learning_rate": 3.48195023071183e-05, "loss": 3.596, "step": 927232 }, { "epoch": 0.0, "learning_rate": 3.481111635960778e-05, "loss": 3.5912, "step": 927744 }, { "epoch": 0.0, "learning_rate": 3.4802746790900986e-05, "loss": 3.608, "step": 928256 }, { "epoch": 0.0, "learning_rate": 3.4794360843390466e-05, "loss": 3.597, "step": 928768 }, { "epoch": 0.0, "learning_rate": 3.4785974895879946e-05, "loss": 3.5916, "step": 929280 }, { "epoch": 0.0, "learning_rate": 3.4777588948369426e-05, "loss": 3.5966, "step": 929792 }, { "epoch": 0.0, "learning_rate": 3.4769219379662635e-05, "loss": 3.5882, "step": 930304 }, { "epoch": 0.0, "learning_rate": 3.4760833432152115e-05, "loss": 3.5936, "step": 930816 }, { "epoch": 0.01, "learning_rate": 3.47524474846416e-05, "loss": 3.5985, "step": 931328 }, { "epoch": 0.01, "learning_rate": 3.474406153713108e-05, "loss": 3.5932, "step": 931840 }, { "epoch": 0.01, "learning_rate": 3.473569196842429e-05, "loss": 3.6006, "step": 932352 }, { "epoch": 0.01, "learning_rate": 3.472730602091377e-05, "loss": 3.6053, "step": 932864 }, { "epoch": 0.01, "learning_rate": 3.471892007340325e-05, "loss": 3.5936, "step": 933376 }, { "epoch": 0.01, "learning_rate": 3.471053412589273e-05, "loss": 3.5989, "step": 933888 }, { "epoch": 0.01, "learning_rate": 3.470216455718594e-05, "loss": 3.605, "step": 934400 }, { "epoch": 0.01, "learning_rate": 3.469377860967542e-05, "loss": 3.5838, "step": 934912 }, { "epoch": 0.01, "learning_rate": 3.46853926621649e-05, "loss": 3.5948, "step": 935424 }, { "epoch": 0.01, "learning_rate": 3.467700671465438e-05, "loss": 3.5807, "step": 935936 }, { "epoch": 0.01, "learning_rate": 3.466863714594759e-05, "loss": 3.583, "step": 936448 }, { "epoch": 0.01, "learning_rate": 3.466025119843707e-05, "loss": 3.5917, "step": 936960 }, { "epoch": 0.01, "learning_rate": 3.4651865250926555e-05, "loss": 3.602, "step": 937472 }, { "epoch": 0.01, "learning_rate": 3.4643479303416035e-05, "loss": 3.5872, "step": 937984 }, { "epoch": 0.01, "learning_rate": 3.4635109734709244e-05, "loss": 3.5919, "step": 938496 }, { "epoch": 0.01, "learning_rate": 3.4626723787198724e-05, "loss": 3.5905, "step": 939008 }, { "epoch": 0.01, "learning_rate": 3.4618337839688204e-05, "loss": 3.5945, "step": 939520 }, { "epoch": 0.01, "learning_rate": 3.4609951892177684e-05, "loss": 3.5822, "step": 940032 }, { "epoch": 0.01, "learning_rate": 3.460158232347089e-05, "loss": 3.5736, "step": 940544 }, { "epoch": 0.01, "learning_rate": 3.459319637596037e-05, "loss": 3.5949, "step": 941056 }, { "epoch": 0.01, "learning_rate": 3.458481042844985e-05, "loss": 3.6021, "step": 941568 }, { "epoch": 0.01, "learning_rate": 3.457642448093933e-05, "loss": 3.6014, "step": 942080 }, { "epoch": 0.01, "learning_rate": 3.456805491223254e-05, "loss": 3.5888, "step": 942592 }, { "epoch": 0.01, "learning_rate": 3.455966896472202e-05, "loss": 3.5885, "step": 943104 }, { "epoch": 0.01, "learning_rate": 3.455128301721151e-05, "loss": 3.5841, "step": 943616 }, { "epoch": 0.01, "learning_rate": 3.454289706970099e-05, "loss": 3.579, "step": 944128 }, { "epoch": 0.01, "learning_rate": 3.45345275009942e-05, "loss": 3.6053, "step": 944640 }, { "epoch": 0.01, "learning_rate": 3.452614155348368e-05, "loss": 3.5769, "step": 945152 }, { "epoch": 0.01, "learning_rate": 3.451775560597316e-05, "loss": 3.6103, "step": 945664 }, { "epoch": 0.01, "learning_rate": 3.450936965846264e-05, "loss": 3.5941, "step": 946176 }, { "epoch": 0.01, "learning_rate": 3.450100008975585e-05, "loss": 3.5744, "step": 946688 }, { "epoch": 0.01, "learning_rate": 3.449261414224533e-05, "loss": 3.5931, "step": 947200 }, { "epoch": 0.01, "learning_rate": 3.448422819473481e-05, "loss": 3.5877, "step": 947712 }, { "epoch": 0.01, "learning_rate": 3.447584224722429e-05, "loss": 3.5742, "step": 948224 }, { "epoch": 0.01, "learning_rate": 3.4467472678517496e-05, "loss": 3.5879, "step": 948736 }, { "epoch": 0.01, "learning_rate": 3.4459086731006976e-05, "loss": 3.5978, "step": 949248 }, { "epoch": 0.01, "learning_rate": 3.4450700783496456e-05, "loss": 3.5823, "step": 949760 }, { "epoch": 0.01, "learning_rate": 3.444231483598594e-05, "loss": 3.5908, "step": 950272 }, { "epoch": 0.01, "learning_rate": 3.443394526727915e-05, "loss": 3.5677, "step": 950784 }, { "epoch": 0.01, "learning_rate": 3.442555931976863e-05, "loss": 3.5833, "step": 951296 }, { "epoch": 0.01, "learning_rate": 3.441717337225811e-05, "loss": 3.5867, "step": 951808 }, { "epoch": 0.01, "learning_rate": 3.440878742474759e-05, "loss": 3.592, "step": 952320 }, { "epoch": 0.01, "learning_rate": 3.44004178560408e-05, "loss": 3.586, "step": 952832 }, { "epoch": 0.01, "learning_rate": 3.439203190853028e-05, "loss": 3.5861, "step": 953344 }, { "epoch": 0.01, "learning_rate": 3.438364596101976e-05, "loss": 3.6007, "step": 953856 }, { "epoch": 0.01, "learning_rate": 3.4375260013509234e-05, "loss": 3.5932, "step": 954368 }, { "epoch": 0.01, "learning_rate": 3.436689044480245e-05, "loss": 3.5904, "step": 954880 }, { "epoch": 0.01, "learning_rate": 3.435850449729193e-05, "loss": 3.5869, "step": 955392 }, { "epoch": 0.01, "learning_rate": 3.435011854978141e-05, "loss": 3.581, "step": 955904 }, { "epoch": 0.01, "learning_rate": 3.434173260227089e-05, "loss": 3.5928, "step": 956416 }, { "epoch": 0.01, "learning_rate": 3.4333363033564105e-05, "loss": 3.5866, "step": 956928 }, { "epoch": 0.01, "learning_rate": 3.4324977086053585e-05, "loss": 3.5879, "step": 957440 }, { "epoch": 0.01, "learning_rate": 3.4316591138543065e-05, "loss": 3.5914, "step": 957952 }, { "epoch": 0.01, "learning_rate": 3.430820519103254e-05, "loss": 3.5841, "step": 958464 }, { "epoch": 0.01, "learning_rate": 3.4299835622325754e-05, "loss": 3.5681, "step": 958976 }, { "epoch": 0.01, "learning_rate": 3.4291449674815234e-05, "loss": 3.5879, "step": 959488 }, { "epoch": 0.01, "learning_rate": 3.428306372730471e-05, "loss": 3.5913, "step": 960000 }, { "epoch": 0.01, "learning_rate": 3.427467777979419e-05, "loss": 3.58, "step": 960512 }, { "epoch": 0.01, "learning_rate": 3.42663082110874e-05, "loss": 3.5865, "step": 961024 }, { "epoch": 0.01, "learning_rate": 3.425792226357688e-05, "loss": 3.5863, "step": 961536 }, { "epoch": 0.02, "learning_rate": 3.424953631606636e-05, "loss": 3.5805, "step": 962048 }, { "epoch": 0.02, "learning_rate": 3.424115036855584e-05, "loss": 3.5798, "step": 962560 }, { "epoch": 0.02, "learning_rate": 3.423278079984906e-05, "loss": 3.5829, "step": 963072 }, { "epoch": 0.02, "learning_rate": 3.422439485233854e-05, "loss": 3.5896, "step": 963584 }, { "epoch": 0.02, "learning_rate": 3.421600890482801e-05, "loss": 3.5902, "step": 964096 }, { "epoch": 0.02, "learning_rate": 3.420762295731749e-05, "loss": 3.5971, "step": 964608 }, { "epoch": 0.02, "learning_rate": 3.419925338861071e-05, "loss": 3.5809, "step": 965120 }, { "epoch": 0.02, "learning_rate": 3.419086744110018e-05, "loss": 3.5785, "step": 965632 }, { "epoch": 0.02, "learning_rate": 3.418248149358966e-05, "loss": 3.5871, "step": 966144 }, { "epoch": 0.02, "learning_rate": 3.417409554607914e-05, "loss": 3.5964, "step": 966656 }, { "epoch": 0.02, "learning_rate": 3.416572597737236e-05, "loss": 3.5923, "step": 967168 }, { "epoch": 0.02, "learning_rate": 3.415734002986184e-05, "loss": 3.5894, "step": 967680 }, { "epoch": 0.02, "learning_rate": 3.414895408235132e-05, "loss": 3.5851, "step": 968192 }, { "epoch": 0.02, "learning_rate": 3.41405681348408e-05, "loss": 3.5843, "step": 968704 }, { "epoch": 0.02, "learning_rate": 3.413219856613401e-05, "loss": 3.5908, "step": 969216 }, { "epoch": 0.02, "learning_rate": 3.4123812618623486e-05, "loss": 3.582, "step": 969728 }, { "epoch": 0.02, "learning_rate": 3.4115426671112966e-05, "loss": 3.5835, "step": 970240 }, { "epoch": 0.02, "learning_rate": 3.4107040723602446e-05, "loss": 3.5877, "step": 970752 }, { "epoch": 0.02, "learning_rate": 3.4098671154895655e-05, "loss": 3.5806, "step": 971264 }, { "epoch": 0.02, "learning_rate": 3.4090285207385135e-05, "loss": 3.5826, "step": 971776 }, { "epoch": 0.02, "learning_rate": 3.4081899259874615e-05, "loss": 3.5778, "step": 972288 }, { "epoch": 0.02, "learning_rate": 3.4073513312364095e-05, "loss": 3.5751, "step": 972800 }, { "epoch": 0.02, "learning_rate": 3.406514374365731e-05, "loss": 3.5863, "step": 973312 }, { "epoch": 0.02, "learning_rate": 3.405675779614679e-05, "loss": 3.5895, "step": 973824 }, { "epoch": 0.02, "learning_rate": 3.404837184863627e-05, "loss": 3.5791, "step": 974336 }, { "epoch": 0.02, "learning_rate": 3.403998590112575e-05, "loss": 3.5925, "step": 974848 }, { "epoch": 0.02, "learning_rate": 3.403161633241896e-05, "loss": 3.5975, "step": 975360 }, { "epoch": 0.02, "learning_rate": 3.402323038490844e-05, "loss": 3.5842, "step": 975872 }, { "epoch": 0.02, "learning_rate": 3.401484443739792e-05, "loss": 3.5876, "step": 976384 }, { "epoch": 0.02, "learning_rate": 3.40064584898874e-05, "loss": 3.5795, "step": 976896 }, { "epoch": 0.02, "learning_rate": 3.399808892118061e-05, "loss": 3.5848, "step": 977408 }, { "epoch": 0.02, "learning_rate": 3.398970297367009e-05, "loss": 3.5803, "step": 977920 }, { "epoch": 0.02, "learning_rate": 3.398131702615957e-05, "loss": 3.5859, "step": 978432 }, { "epoch": 0.02, "learning_rate": 3.397293107864905e-05, "loss": 3.5801, "step": 978944 }, { "epoch": 0.02, "learning_rate": 3.396454513113853e-05, "loss": 3.5862, "step": 979456 }, { "epoch": 0.02, "learning_rate": 3.3956175562431744e-05, "loss": 3.5798, "step": 979968 }, { "epoch": 0.02, "learning_rate": 3.3947789614921224e-05, "loss": 3.5857, "step": 980480 }, { "epoch": 0.02, "learning_rate": 3.3939403667410704e-05, "loss": 3.5854, "step": 980992 }, { "epoch": 0.02, "learning_rate": 3.393103409870391e-05, "loss": 3.5807, "step": 981504 }, { "epoch": 0.02, "learning_rate": 3.392264815119339e-05, "loss": 3.5792, "step": 982016 }, { "epoch": 0.02, "learning_rate": 3.391426220368287e-05, "loss": 3.5905, "step": 982528 }, { "epoch": 0.02, "learning_rate": 3.390587625617235e-05, "loss": 3.595, "step": 983040 }, { "epoch": 0.02, "learning_rate": 3.389750668746556e-05, "loss": 3.5788, "step": 983552 }, { "epoch": 0.02, "learning_rate": 3.388912073995504e-05, "loss": 3.5805, "step": 984064 }, { "epoch": 0.02, "learning_rate": 3.388073479244452e-05, "loss": 3.5903, "step": 984576 }, { "epoch": 0.02, "learning_rate": 3.3872348844934e-05, "loss": 3.5765, "step": 985088 }, { "epoch": 0.02, "learning_rate": 3.386397927622722e-05, "loss": 3.5875, "step": 985600 }, { "epoch": 0.02, "learning_rate": 3.38555933287167e-05, "loss": 3.5851, "step": 986112 }, { "epoch": 0.02, "learning_rate": 3.384720738120618e-05, "loss": 3.5973, "step": 986624 }, { "epoch": 0.02, "learning_rate": 3.383882143369566e-05, "loss": 3.5883, "step": 987136 }, { "epoch": 0.02, "learning_rate": 3.383043548618514e-05, "loss": 3.5916, "step": 987648 }, { "epoch": 0.02, "learning_rate": 3.382206591747835e-05, "loss": 3.5825, "step": 988160 }, { "epoch": 0.02, "learning_rate": 3.381367996996783e-05, "loss": 3.5902, "step": 988672 }, { "epoch": 0.02, "learning_rate": 3.3805294022457307e-05, "loss": 3.5844, "step": 989184 }, { "epoch": 0.02, "learning_rate": 3.3796908074946787e-05, "loss": 3.5755, "step": 989696 }, { "epoch": 0.02, "learning_rate": 3.3788538506239996e-05, "loss": 3.5865, "step": 990208 }, { "epoch": 0.02, "learning_rate": 3.3780152558729476e-05, "loss": 3.5716, "step": 990720 }, { "epoch": 0.02, "learning_rate": 3.3771766611218956e-05, "loss": 3.5873, "step": 991232 }, { "epoch": 0.02, "learning_rate": 3.3763380663708435e-05, "loss": 3.5762, "step": 991744 }, { "epoch": 0.03, "eval_loss": 3.846428155899048, "eval_runtime": 304.6348, "eval_samples_per_second": 1252.618, "eval_steps_per_second": 39.145, "step": 992150 }, { "epoch": 1.0, "learning_rate": 3.375501109500165e-05, "loss": 3.5857, "step": 992256 }, { "epoch": 1.0, "learning_rate": 3.374662514749113e-05, "loss": 3.5765, "step": 992768 }, { "epoch": 1.0, "learning_rate": 3.373823919998061e-05, "loss": 3.5812, "step": 993280 }, { "epoch": 1.0, "learning_rate": 3.372985325247009e-05, "loss": 3.5919, "step": 993792 }, { "epoch": 1.0, "learning_rate": 3.37214836837633e-05, "loss": 3.5872, "step": 994304 }, { "epoch": 1.0, "learning_rate": 3.371309773625278e-05, "loss": 3.593, "step": 994816 }, { "epoch": 1.0, "learning_rate": 3.370471178874226e-05, "loss": 3.5841, "step": 995328 }, { "epoch": 1.0, "learning_rate": 3.369632584123174e-05, "loss": 3.5759, "step": 995840 }, { "epoch": 1.0, "learning_rate": 3.368795627252495e-05, "loss": 3.567, "step": 996352 }, { "epoch": 1.0, "learning_rate": 3.367957032501443e-05, "loss": 3.581, "step": 996864 }, { "epoch": 1.0, "learning_rate": 3.367118437750391e-05, "loss": 3.5847, "step": 997376 }, { "epoch": 1.0, "learning_rate": 3.366279842999339e-05, "loss": 3.5777, "step": 997888 }, { "epoch": 1.0, "learning_rate": 3.3654445240090334e-05, "loss": 3.5866, "step": 998400 }, { "epoch": 1.0, "learning_rate": 3.3646059292579814e-05, "loss": 3.5615, "step": 998912 }, { "epoch": 1.0, "learning_rate": 3.3637673345069294e-05, "loss": 3.5698, "step": 999424 }, { "epoch": 1.0, "learning_rate": 3.3629287397558774e-05, "loss": 3.5687, "step": 999936 }, { "epoch": 1.0, "learning_rate": 3.3620901450048254e-05, "loss": 3.5781, "step": 1000448 }, { "epoch": 1.0, "learning_rate": 3.3612515502537734e-05, "loss": 3.572, "step": 1000960 }, { "epoch": 1.0, "learning_rate": 3.3604129555027214e-05, "loss": 3.5755, "step": 1001472 }, { "epoch": 1.0, "learning_rate": 3.3595743607516694e-05, "loss": 3.5843, "step": 1001984 }, { "epoch": 1.0, "learning_rate": 3.35873740388099e-05, "loss": 3.5863, "step": 1002496 }, { "epoch": 1.0, "learning_rate": 3.357898809129938e-05, "loss": 3.5847, "step": 1003008 }, { "epoch": 1.0, "learning_rate": 3.357060214378886e-05, "loss": 3.5764, "step": 1003520 }, { "epoch": 1.0, "learning_rate": 3.356221619627834e-05, "loss": 3.5734, "step": 1004032 }, { "epoch": 1.0, "learning_rate": 3.355384662757156e-05, "loss": 3.5899, "step": 1004544 }, { "epoch": 1.0, "learning_rate": 3.354546068006104e-05, "loss": 3.5772, "step": 1005056 }, { "epoch": 1.0, "learning_rate": 3.353707473255052e-05, "loss": 3.5727, "step": 1005568 }, { "epoch": 1.0, "learning_rate": 3.352868878504e-05, "loss": 3.5814, "step": 1006080 }, { "epoch": 1.0, "learning_rate": 3.352031921633321e-05, "loss": 3.5669, "step": 1006592 }, { "epoch": 1.0, "learning_rate": 3.351193326882269e-05, "loss": 3.5754, "step": 1007104 }, { "epoch": 1.01, "learning_rate": 3.350354732131217e-05, "loss": 3.5807, "step": 1007616 }, { "epoch": 1.01, "learning_rate": 3.349516137380165e-05, "loss": 3.5762, "step": 1008128 }, { "epoch": 1.01, "learning_rate": 3.348679180509486e-05, "loss": 3.5816, "step": 1008640 }, { "epoch": 1.01, "learning_rate": 3.3478405857584337e-05, "loss": 3.59, "step": 1009152 }, { "epoch": 1.01, "learning_rate": 3.3470019910073817e-05, "loss": 3.5748, "step": 1009664 }, { "epoch": 1.01, "learning_rate": 3.3461633962563296e-05, "loss": 3.5811, "step": 1010176 }, { "epoch": 1.01, "learning_rate": 3.345326439385651e-05, "loss": 3.5883, "step": 1010688 }, { "epoch": 1.01, "learning_rate": 3.344487844634599e-05, "loss": 3.5623, "step": 1011200 }, { "epoch": 1.01, "learning_rate": 3.343649249883547e-05, "loss": 3.5757, "step": 1011712 }, { "epoch": 1.01, "learning_rate": 3.342810655132495e-05, "loss": 3.5615, "step": 1012224 }, { "epoch": 1.01, "learning_rate": 3.341973698261816e-05, "loss": 3.5681, "step": 1012736 }, { "epoch": 1.01, "learning_rate": 3.341135103510764e-05, "loss": 3.5684, "step": 1013248 }, { "epoch": 1.01, "learning_rate": 3.340296508759712e-05, "loss": 3.5883, "step": 1013760 }, { "epoch": 1.01, "learning_rate": 3.33945791400866e-05, "loss": 3.5682, "step": 1014272 }, { "epoch": 1.01, "learning_rate": 3.338620957137981e-05, "loss": 3.5747, "step": 1014784 }, { "epoch": 1.01, "learning_rate": 3.337782362386929e-05, "loss": 3.5718, "step": 1015296 }, { "epoch": 1.01, "learning_rate": 3.336943767635877e-05, "loss": 3.5776, "step": 1015808 }, { "epoch": 1.01, "learning_rate": 3.336105172884825e-05, "loss": 3.5671, "step": 1016320 }, { "epoch": 1.01, "learning_rate": 3.3352682160141466e-05, "loss": 3.5558, "step": 1016832 }, { "epoch": 1.01, "learning_rate": 3.3344296212630946e-05, "loss": 3.5763, "step": 1017344 }, { "epoch": 1.01, "learning_rate": 3.3335910265120426e-05, "loss": 3.5858, "step": 1017856 }, { "epoch": 1.01, "learning_rate": 3.3327524317609906e-05, "loss": 3.5765, "step": 1018368 }, { "epoch": 1.01, "learning_rate": 3.3319154748903115e-05, "loss": 3.5717, "step": 1018880 }, { "epoch": 1.01, "learning_rate": 3.3310768801392595e-05, "loss": 3.568, "step": 1019392 }, { "epoch": 1.01, "learning_rate": 3.3302382853882075e-05, "loss": 3.5719, "step": 1019904 }, { "epoch": 1.01, "learning_rate": 3.3293996906371555e-05, "loss": 3.5594, "step": 1020416 }, { "epoch": 1.01, "learning_rate": 3.3285627337664764e-05, "loss": 3.5905, "step": 1020928 }, { "epoch": 1.01, "learning_rate": 3.3277241390154244e-05, "loss": 3.5584, "step": 1021440 }, { "epoch": 1.01, "learning_rate": 3.3268855442643724e-05, "loss": 3.5908, "step": 1021952 }, { "epoch": 1.01, "learning_rate": 3.3260469495133204e-05, "loss": 3.5773, "step": 1022464 }, { "epoch": 1.01, "learning_rate": 3.325209992642642e-05, "loss": 3.5572, "step": 1022976 }, { "epoch": 1.01, "learning_rate": 3.32437139789159e-05, "loss": 3.5726, "step": 1023488 }, { "epoch": 1.01, "learning_rate": 3.323532803140538e-05, "loss": 3.5725, "step": 1024000 }, { "epoch": 1.01, "learning_rate": 3.322694208389486e-05, "loss": 3.5583, "step": 1024512 }, { "epoch": 1.01, "learning_rate": 3.321857251518807e-05, "loss": 3.565, "step": 1025024 }, { "epoch": 1.01, "learning_rate": 3.321018656767755e-05, "loss": 3.5843, "step": 1025536 }, { "epoch": 1.01, "learning_rate": 3.320180062016703e-05, "loss": 3.565, "step": 1026048 }, { "epoch": 1.01, "learning_rate": 3.319341467265651e-05, "loss": 3.5714, "step": 1026560 }, { "epoch": 1.01, "learning_rate": 3.318504510394972e-05, "loss": 3.5517, "step": 1027072 }, { "epoch": 1.01, "learning_rate": 3.31766591564392e-05, "loss": 3.5679, "step": 1027584 }, { "epoch": 1.01, "learning_rate": 3.316827320892868e-05, "loss": 3.5661, "step": 1028096 }, { "epoch": 1.01, "learning_rate": 3.315988726141816e-05, "loss": 3.5749, "step": 1028608 }, { "epoch": 1.01, "learning_rate": 3.315151769271137e-05, "loss": 3.5655, "step": 1029120 }, { "epoch": 1.01, "learning_rate": 3.314313174520085e-05, "loss": 3.5725, "step": 1029632 }, { "epoch": 1.01, "learning_rate": 3.313474579769033e-05, "loss": 3.5812, "step": 1030144 }, { "epoch": 1.01, "learning_rate": 3.3126359850179806e-05, "loss": 3.5725, "step": 1030656 }, { "epoch": 1.01, "learning_rate": 3.311799028147302e-05, "loss": 3.5731, "step": 1031168 }, { "epoch": 1.01, "learning_rate": 3.31096043339625e-05, "loss": 3.573, "step": 1031680 }, { "epoch": 1.01, "learning_rate": 3.310121838645198e-05, "loss": 3.5654, "step": 1032192 }, { "epoch": 1.01, "learning_rate": 3.3092832438941455e-05, "loss": 3.576, "step": 1032704 }, { "epoch": 1.01, "learning_rate": 3.308446287023467e-05, "loss": 3.5682, "step": 1033216 }, { "epoch": 1.01, "learning_rate": 3.307607692272415e-05, "loss": 3.5704, "step": 1033728 }, { "epoch": 1.01, "learning_rate": 3.3067690975213624e-05, "loss": 3.5781, "step": 1034240 }, { "epoch": 1.01, "learning_rate": 3.305930502770311e-05, "loss": 3.5644, "step": 1034752 }, { "epoch": 1.01, "learning_rate": 3.305091908019259e-05, "loss": 3.55, "step": 1035264 }, { "epoch": 1.01, "learning_rate": 3.304253313268207e-05, "loss": 3.5702, "step": 1035776 }, { "epoch": 1.01, "learning_rate": 3.303414718517155e-05, "loss": 3.5708, "step": 1036288 }, { "epoch": 1.01, "learning_rate": 3.302576123766103e-05, "loss": 3.5652, "step": 1036800 }, { "epoch": 1.01, "learning_rate": 3.301739166895424e-05, "loss": 3.568, "step": 1037312 }, { "epoch": 1.01, "learning_rate": 3.300900572144372e-05, "loss": 3.5715, "step": 1037824 }, { "epoch": 1.02, "learning_rate": 3.30006197739332e-05, "loss": 3.5602, "step": 1038336 }, { "epoch": 1.02, "learning_rate": 3.299223382642268e-05, "loss": 3.5621, "step": 1038848 }, { "epoch": 1.02, "learning_rate": 3.298386425771589e-05, "loss": 3.5652, "step": 1039360 }, { "epoch": 1.02, "learning_rate": 3.297547831020537e-05, "loss": 3.574, "step": 1039872 }, { "epoch": 1.02, "learning_rate": 3.296709236269485e-05, "loss": 3.5712, "step": 1040384 }, { "epoch": 1.02, "learning_rate": 3.295870641518433e-05, "loss": 3.5773, "step": 1040896 }, { "epoch": 1.02, "learning_rate": 3.2950336846477545e-05, "loss": 3.5614, "step": 1041408 }, { "epoch": 1.02, "learning_rate": 3.2941950898967025e-05, "loss": 3.5646, "step": 1041920 }, { "epoch": 1.02, "learning_rate": 3.2933564951456505e-05, "loss": 3.5699, "step": 1042432 }, { "epoch": 1.02, "learning_rate": 3.2925179003945985e-05, "loss": 3.5792, "step": 1042944 }, { "epoch": 1.02, "learning_rate": 3.2916809435239194e-05, "loss": 3.57, "step": 1043456 }, { "epoch": 1.02, "learning_rate": 3.2908423487728674e-05, "loss": 3.5741, "step": 1043968 }, { "epoch": 1.02, "learning_rate": 3.2900037540218154e-05, "loss": 3.5667, "step": 1044480 }, { "epoch": 1.02, "learning_rate": 3.2891651592707634e-05, "loss": 3.5634, "step": 1044992 }, { "epoch": 1.02, "learning_rate": 3.288328202400084e-05, "loss": 3.5756, "step": 1045504 }, { "epoch": 1.02, "learning_rate": 3.287489607649032e-05, "loss": 3.56, "step": 1046016 }, { "epoch": 1.02, "learning_rate": 3.28665101289798e-05, "loss": 3.5663, "step": 1046528 }, { "epoch": 1.02, "learning_rate": 3.285812418146928e-05, "loss": 3.5699, "step": 1047040 }, { "epoch": 1.02, "learning_rate": 3.28497546127625e-05, "loss": 3.5656, "step": 1047552 }, { "epoch": 1.02, "learning_rate": 3.284136866525198e-05, "loss": 3.5628, "step": 1048064 }, { "epoch": 1.02, "learning_rate": 3.283298271774146e-05, "loss": 3.5645, "step": 1048576 }, { "epoch": 1.02, "learning_rate": 3.282459677023094e-05, "loss": 3.5541, "step": 1049088 }, { "epoch": 1.02, "learning_rate": 3.281622720152415e-05, "loss": 3.5708, "step": 1049600 }, { "epoch": 1.02, "learning_rate": 3.280784125401363e-05, "loss": 3.571, "step": 1050112 }, { "epoch": 1.02, "learning_rate": 3.279945530650311e-05, "loss": 3.5608, "step": 1050624 }, { "epoch": 1.02, "learning_rate": 3.279106935899259e-05, "loss": 3.5763, "step": 1051136 }, { "epoch": 1.02, "learning_rate": 3.2782699790285796e-05, "loss": 3.583, "step": 1051648 }, { "epoch": 1.02, "learning_rate": 3.2774313842775276e-05, "loss": 3.567, "step": 1052160 }, { "epoch": 1.02, "learning_rate": 3.2765927895264756e-05, "loss": 3.5682, "step": 1052672 }, { "epoch": 1.02, "learning_rate": 3.2757541947754236e-05, "loss": 3.5647, "step": 1053184 }, { "epoch": 1.02, "learning_rate": 3.274917237904745e-05, "loss": 3.5653, "step": 1053696 }, { "epoch": 1.02, "learning_rate": 3.274078643153693e-05, "loss": 3.5602, "step": 1054208 }, { "epoch": 1.02, "learning_rate": 3.273240048402641e-05, "loss": 3.5677, "step": 1054720 }, { "epoch": 1.02, "learning_rate": 3.272401453651589e-05, "loss": 3.5642, "step": 1055232 }, { "epoch": 1.02, "learning_rate": 3.27156449678091e-05, "loss": 3.5699, "step": 1055744 }, { "epoch": 1.02, "learning_rate": 3.270725902029858e-05, "loss": 3.5659, "step": 1056256 }, { "epoch": 1.02, "learning_rate": 3.269887307278806e-05, "loss": 3.5672, "step": 1056768 }, { "epoch": 1.02, "learning_rate": 3.269048712527754e-05, "loss": 3.5682, "step": 1057280 }, { "epoch": 1.02, "learning_rate": 3.268211755657075e-05, "loss": 3.5632, "step": 1057792 }, { "epoch": 1.02, "learning_rate": 3.267373160906023e-05, "loss": 3.5617, "step": 1058304 }, { "epoch": 1.02, "learning_rate": 3.266534566154971e-05, "loss": 3.5747, "step": 1058816 }, { "epoch": 1.02, "learning_rate": 3.265695971403919e-05, "loss": 3.5776, "step": 1059328 }, { "epoch": 1.02, "learning_rate": 3.2648590145332406e-05, "loss": 3.5658, "step": 1059840 }, { "epoch": 1.02, "learning_rate": 3.2640204197821886e-05, "loss": 3.5603, "step": 1060352 }, { "epoch": 1.02, "learning_rate": 3.2631818250311366e-05, "loss": 3.571, "step": 1060864 }, { "epoch": 1.02, "learning_rate": 3.2623432302800846e-05, "loss": 3.5602, "step": 1061376 }, { "epoch": 1.02, "learning_rate": 3.2615062734094055e-05, "loss": 3.5681, "step": 1061888 }, { "epoch": 1.02, "learning_rate": 3.2606676786583535e-05, "loss": 3.5671, "step": 1062400 }, { "epoch": 1.02, "learning_rate": 3.2598290839073015e-05, "loss": 3.582, "step": 1062912 }, { "epoch": 1.02, "learning_rate": 3.2589921270366224e-05, "loss": 3.5698, "step": 1063424 }, { "epoch": 1.02, "learning_rate": 3.2581535322855704e-05, "loss": 3.5734, "step": 1063936 }, { "epoch": 1.02, "learning_rate": 3.2573149375345184e-05, "loss": 3.5658, "step": 1064448 }, { "epoch": 1.02, "learning_rate": 3.2564763427834664e-05, "loss": 3.575, "step": 1064960 }, { "epoch": 1.02, "learning_rate": 3.255639385912787e-05, "loss": 3.5637, "step": 1065472 }, { "epoch": 1.02, "learning_rate": 3.254802429042109e-05, "loss": 3.5585, "step": 1065984 }, { "epoch": 1.02, "learning_rate": 3.253963834291057e-05, "loss": 3.5692, "step": 1066496 }, { "epoch": 1.02, "learning_rate": 3.253125239540005e-05, "loss": 3.5545, "step": 1067008 }, { "epoch": 1.02, "learning_rate": 3.252286644788953e-05, "loss": 3.57, "step": 1067520 }, { "epoch": 1.02, "learning_rate": 3.251448050037901e-05, "loss": 3.5575, "step": 1068032 }, { "epoch": 1.03, "eval_loss": 3.8479952812194824, "eval_runtime": 304.1056, "eval_samples_per_second": 1254.798, "eval_steps_per_second": 39.213, "step": 1068470 }, { "epoch": 0.0, "learning_rate": 3.250609455286849e-05, "loss": 3.5778, "step": 1068544 }, { "epoch": 0.0, "learning_rate": 3.249770860535797e-05, "loss": 3.5611, "step": 1069056 }, { "epoch": 0.0, "learning_rate": 3.248932265784745e-05, "loss": 3.5625, "step": 1069568 }, { "epoch": 0.0, "learning_rate": 3.248093671033693e-05, "loss": 3.5767, "step": 1070080 }, { "epoch": 0.0, "learning_rate": 3.247256714163014e-05, "loss": 3.5675, "step": 1070592 }, { "epoch": 0.0, "learning_rate": 3.246418119411962e-05, "loss": 3.5796, "step": 1071104 }, { "epoch": 0.0, "learning_rate": 3.24557952466091e-05, "loss": 3.5628, "step": 1071616 }, { "epoch": 0.0, "learning_rate": 3.244740929909858e-05, "loss": 3.5569, "step": 1072128 }, { "epoch": 0.0, "learning_rate": 3.243903973039179e-05, "loss": 3.5549, "step": 1072640 }, { "epoch": 0.0, "learning_rate": 3.243065378288127e-05, "loss": 3.5665, "step": 1073152 }, { "epoch": 0.0, "learning_rate": 3.242226783537075e-05, "loss": 3.5622, "step": 1073664 }, { "epoch": 0.0, "learning_rate": 3.241388188786023e-05, "loss": 3.5617, "step": 1074176 }, { "epoch": 0.0, "learning_rate": 3.240551231915344e-05, "loss": 3.5698, "step": 1074688 }, { "epoch": 0.0, "learning_rate": 3.239712637164292e-05, "loss": 3.5484, "step": 1075200 }, { "epoch": 0.0, "learning_rate": 3.23887404241324e-05, "loss": 3.5515, "step": 1075712 }, { "epoch": 0.0, "learning_rate": 3.238035447662188e-05, "loss": 3.5513, "step": 1076224 }, { "epoch": 0.0, "learning_rate": 3.237198490791509e-05, "loss": 3.5572, "step": 1076736 }, { "epoch": 0.0, "learning_rate": 3.236359896040457e-05, "loss": 3.5576, "step": 1077248 }, { "epoch": 0.0, "learning_rate": 3.235521301289405e-05, "loss": 3.5582, "step": 1077760 }, { "epoch": 0.0, "learning_rate": 3.234682706538353e-05, "loss": 3.5649, "step": 1078272 }, { "epoch": 0.0, "learning_rate": 3.233845749667675e-05, "loss": 3.5718, "step": 1078784 }, { "epoch": 0.0, "learning_rate": 3.233007154916623e-05, "loss": 3.5626, "step": 1079296 }, { "epoch": 0.0, "learning_rate": 3.232168560165571e-05, "loss": 3.5627, "step": 1079808 }, { "epoch": 0.0, "learning_rate": 3.231329965414518e-05, "loss": 3.5564, "step": 1080320 }, { "epoch": 0.0, "learning_rate": 3.2304930085438396e-05, "loss": 3.5762, "step": 1080832 }, { "epoch": 0.0, "learning_rate": 3.2296544137927876e-05, "loss": 3.5593, "step": 1081344 }, { "epoch": 0.0, "learning_rate": 3.2288158190417356e-05, "loss": 3.5589, "step": 1081856 }, { "epoch": 0.0, "learning_rate": 3.227977224290683e-05, "loss": 3.559, "step": 1082368 }, { "epoch": 0.0, "learning_rate": 3.2271402674200045e-05, "loss": 3.551, "step": 1082880 }, { "epoch": 0.0, "learning_rate": 3.2263016726689525e-05, "loss": 3.5608, "step": 1083392 }, { "epoch": 0.01, "learning_rate": 3.2254630779179005e-05, "loss": 3.56, "step": 1083904 }, { "epoch": 0.01, "learning_rate": 3.2246244831668485e-05, "loss": 3.5625, "step": 1084416 }, { "epoch": 0.01, "learning_rate": 3.22378752629617e-05, "loss": 3.5643, "step": 1084928 }, { "epoch": 0.01, "learning_rate": 3.222948931545118e-05, "loss": 3.5687, "step": 1085440 }, { "epoch": 0.01, "learning_rate": 3.2221103367940654e-05, "loss": 3.5595, "step": 1085952 }, { "epoch": 0.01, "learning_rate": 3.2212717420430134e-05, "loss": 3.565, "step": 1086464 }, { "epoch": 0.01, "learning_rate": 3.220434785172335e-05, "loss": 3.5705, "step": 1086976 }, { "epoch": 0.01, "learning_rate": 3.219596190421283e-05, "loss": 3.5463, "step": 1087488 }, { "epoch": 0.01, "learning_rate": 3.21875759567023e-05, "loss": 3.559, "step": 1088000 }, { "epoch": 0.01, "learning_rate": 3.217919000919178e-05, "loss": 3.5444, "step": 1088512 }, { "epoch": 0.01, "learning_rate": 3.2170820440485e-05, "loss": 3.5566, "step": 1089024 }, { "epoch": 0.01, "learning_rate": 3.216243449297447e-05, "loss": 3.5504, "step": 1089536 }, { "epoch": 0.01, "learning_rate": 3.215404854546396e-05, "loss": 3.569, "step": 1090048 }, { "epoch": 0.01, "learning_rate": 3.214566259795344e-05, "loss": 3.5488, "step": 1090560 }, { "epoch": 0.01, "learning_rate": 3.2137293029246654e-05, "loss": 3.5557, "step": 1091072 }, { "epoch": 0.01, "learning_rate": 3.212890708173613e-05, "loss": 3.5602, "step": 1091584 }, { "epoch": 0.01, "learning_rate": 3.212052113422561e-05, "loss": 3.5555, "step": 1092096 }, { "epoch": 0.01, "learning_rate": 3.211213518671509e-05, "loss": 3.5542, "step": 1092608 }, { "epoch": 0.01, "learning_rate": 3.21037656180083e-05, "loss": 3.5336, "step": 1093120 }, { "epoch": 0.01, "learning_rate": 3.2095379670497776e-05, "loss": 3.5597, "step": 1093632 }, { "epoch": 0.01, "learning_rate": 3.2086993722987256e-05, "loss": 3.5679, "step": 1094144 }, { "epoch": 0.01, "learning_rate": 3.2078607775476736e-05, "loss": 3.5642, "step": 1094656 }, { "epoch": 0.01, "learning_rate": 3.2070238206769945e-05, "loss": 3.5582, "step": 1095168 }, { "epoch": 0.01, "learning_rate": 3.2061852259259425e-05, "loss": 3.5483, "step": 1095680 }, { "epoch": 0.01, "learning_rate": 3.205346631174891e-05, "loss": 3.5586, "step": 1096192 }, { "epoch": 0.01, "learning_rate": 3.204508036423839e-05, "loss": 3.5425, "step": 1096704 }, { "epoch": 0.01, "learning_rate": 3.20367107955316e-05, "loss": 3.5699, "step": 1097216 }, { "epoch": 0.01, "learning_rate": 3.202834122682482e-05, "loss": 3.5428, "step": 1097728 }, { "epoch": 0.01, "learning_rate": 3.20199552793143e-05, "loss": 3.5742, "step": 1098240 }, { "epoch": 0.01, "learning_rate": 3.201156933180378e-05, "loss": 3.563, "step": 1098752 }, { "epoch": 0.01, "learning_rate": 3.200318338429325e-05, "loss": 3.5373, "step": 1099264 }, { "epoch": 0.01, "learning_rate": 3.199479743678273e-05, "loss": 3.5551, "step": 1099776 }, { "epoch": 0.01, "learning_rate": 3.198641148927221e-05, "loss": 3.5591, "step": 1100288 }, { "epoch": 0.01, "learning_rate": 3.197802554176169e-05, "loss": 3.5435, "step": 1100800 }, { "epoch": 0.01, "learning_rate": 3.196963959425117e-05, "loss": 3.5446, "step": 1101312 }, { "epoch": 0.01, "learning_rate": 3.196127002554438e-05, "loss": 3.5653, "step": 1101824 }, { "epoch": 0.01, "learning_rate": 3.1952884078033866e-05, "loss": 3.5543, "step": 1102336 }, { "epoch": 0.01, "learning_rate": 3.1944498130523346e-05, "loss": 3.5546, "step": 1102848 }, { "epoch": 0.01, "learning_rate": 3.1936112183012825e-05, "loss": 3.5374, "step": 1103360 }, { "epoch": 0.01, "learning_rate": 3.1927742614306035e-05, "loss": 3.5512, "step": 1103872 }, { "epoch": 0.01, "learning_rate": 3.1919356666795515e-05, "loss": 3.5462, "step": 1104384 }, { "epoch": 0.01, "learning_rate": 3.1910970719284995e-05, "loss": 3.5616, "step": 1104896 }, { "epoch": 0.01, "learning_rate": 3.1902584771774474e-05, "loss": 3.5481, "step": 1105408 }, { "epoch": 0.01, "learning_rate": 3.1894215203067684e-05, "loss": 3.5578, "step": 1105920 }, { "epoch": 0.01, "learning_rate": 3.1885829255557164e-05, "loss": 3.5604, "step": 1106432 }, { "epoch": 0.01, "learning_rate": 3.1877443308046643e-05, "loss": 3.5585, "step": 1106944 }, { "epoch": 0.01, "learning_rate": 3.1869057360536123e-05, "loss": 3.5564, "step": 1107456 }, { "epoch": 0.01, "learning_rate": 3.186068779182933e-05, "loss": 3.5549, "step": 1107968 }, { "epoch": 0.01, "learning_rate": 3.185230184431882e-05, "loss": 3.5517, "step": 1108480 }, { "epoch": 0.01, "learning_rate": 3.18439158968083e-05, "loss": 3.5577, "step": 1108992 }, { "epoch": 0.01, "learning_rate": 3.183552994929778e-05, "loss": 3.5546, "step": 1109504 }, { "epoch": 0.01, "learning_rate": 3.182714400178726e-05, "loss": 3.5547, "step": 1110016 }, { "epoch": 0.01, "learning_rate": 3.181875805427674e-05, "loss": 3.5558, "step": 1110528 }, { "epoch": 0.01, "learning_rate": 3.181037210676622e-05, "loss": 3.5498, "step": 1111040 }, { "epoch": 0.01, "learning_rate": 3.18019861592557e-05, "loss": 3.5347, "step": 1111552 }, { "epoch": 0.01, "learning_rate": 3.179361659054891e-05, "loss": 3.5533, "step": 1112064 }, { "epoch": 0.01, "learning_rate": 3.178523064303839e-05, "loss": 3.5501, "step": 1112576 }, { "epoch": 0.01, "learning_rate": 3.177684469552787e-05, "loss": 3.5546, "step": 1113088 }, { "epoch": 0.01, "learning_rate": 3.176845874801735e-05, "loss": 3.5506, "step": 1113600 }, { "epoch": 0.01, "learning_rate": 3.176008917931056e-05, "loss": 3.5563, "step": 1114112 }, { "epoch": 0.02, "learning_rate": 3.175170323180004e-05, "loss": 3.5462, "step": 1114624 }, { "epoch": 0.02, "learning_rate": 3.174331728428952e-05, "loss": 3.5439, "step": 1115136 }, { "epoch": 0.02, "learning_rate": 3.1734931336779e-05, "loss": 3.5468, "step": 1115648 }, { "epoch": 0.02, "learning_rate": 3.172656176807221e-05, "loss": 3.5578, "step": 1116160 }, { "epoch": 0.02, "learning_rate": 3.171817582056169e-05, "loss": 3.554, "step": 1116672 }, { "epoch": 0.02, "learning_rate": 3.170978987305117e-05, "loss": 3.562, "step": 1117184 }, { "epoch": 0.02, "learning_rate": 3.170140392554065e-05, "loss": 3.5475, "step": 1117696 }, { "epoch": 0.02, "learning_rate": 3.169303435683386e-05, "loss": 3.5495, "step": 1118208 }, { "epoch": 0.02, "learning_rate": 3.168464840932334e-05, "loss": 3.5499, "step": 1118720 }, { "epoch": 0.02, "learning_rate": 3.167626246181282e-05, "loss": 3.5643, "step": 1119232 }, { "epoch": 0.02, "learning_rate": 3.16678765143023e-05, "loss": 3.5563, "step": 1119744 }, { "epoch": 0.02, "learning_rate": 3.165950694559551e-05, "loss": 3.5608, "step": 1120256 }, { "epoch": 0.02, "learning_rate": 3.165112099808499e-05, "loss": 3.5491, "step": 1120768 }, { "epoch": 0.02, "learning_rate": 3.164273505057447e-05, "loss": 3.5493, "step": 1121280 }, { "epoch": 0.02, "learning_rate": 3.163434910306395e-05, "loss": 3.5609, "step": 1121792 }, { "epoch": 0.02, "learning_rate": 3.1625979534357166e-05, "loss": 3.5414, "step": 1122304 }, { "epoch": 0.02, "learning_rate": 3.1617593586846646e-05, "loss": 3.5482, "step": 1122816 }, { "epoch": 0.02, "learning_rate": 3.1609207639336126e-05, "loss": 3.5523, "step": 1123328 }, { "epoch": 0.02, "learning_rate": 3.1600821691825606e-05, "loss": 3.5489, "step": 1123840 }, { "epoch": 0.02, "learning_rate": 3.1592452123118815e-05, "loss": 3.5491, "step": 1124352 }, { "epoch": 0.02, "learning_rate": 3.1584066175608295e-05, "loss": 3.5485, "step": 1124864 }, { "epoch": 0.02, "learning_rate": 3.1575680228097775e-05, "loss": 3.5386, "step": 1125376 }, { "epoch": 0.02, "learning_rate": 3.1567294280587255e-05, "loss": 3.5542, "step": 1125888 }, { "epoch": 0.02, "learning_rate": 3.1558924711880464e-05, "loss": 3.5501, "step": 1126400 }, { "epoch": 0.02, "learning_rate": 3.1550538764369944e-05, "loss": 3.5485, "step": 1126912 }, { "epoch": 0.02, "learning_rate": 3.1542152816859424e-05, "loss": 3.5586, "step": 1127424 }, { "epoch": 0.02, "learning_rate": 3.153378324815264e-05, "loss": 3.5661, "step": 1127936 }, { "epoch": 0.02, "learning_rate": 3.152539730064212e-05, "loss": 3.5534, "step": 1128448 }, { "epoch": 0.02, "learning_rate": 3.15170113531316e-05, "loss": 3.5533, "step": 1128960 }, { "epoch": 0.02, "learning_rate": 3.150862540562108e-05, "loss": 3.5441, "step": 1129472 }, { "epoch": 0.02, "learning_rate": 3.150025583691429e-05, "loss": 3.5514, "step": 1129984 }, { "epoch": 0.02, "learning_rate": 3.149186988940377e-05, "loss": 3.5419, "step": 1130496 }, { "epoch": 0.02, "learning_rate": 3.148348394189325e-05, "loss": 3.5532, "step": 1131008 }, { "epoch": 0.02, "learning_rate": 3.147509799438273e-05, "loss": 3.5452, "step": 1131520 }, { "epoch": 0.02, "learning_rate": 3.146672842567594e-05, "loss": 3.5551, "step": 1132032 }, { "epoch": 0.02, "learning_rate": 3.145834247816542e-05, "loss": 3.5477, "step": 1132544 }, { "epoch": 0.02, "learning_rate": 3.14499565306549e-05, "loss": 3.5497, "step": 1133056 }, { "epoch": 0.02, "learning_rate": 3.144157058314438e-05, "loss": 3.5556, "step": 1133568 }, { "epoch": 0.02, "learning_rate": 3.143318463563386e-05, "loss": 3.5458, "step": 1134080 }, { "epoch": 0.02, "learning_rate": 3.1424815066927074e-05, "loss": 3.5424, "step": 1134592 }, { "epoch": 0.02, "learning_rate": 3.1416429119416554e-05, "loss": 3.5569, "step": 1135104 }, { "epoch": 0.02, "learning_rate": 3.140804317190603e-05, "loss": 3.5619, "step": 1135616 }, { "epoch": 0.02, "learning_rate": 3.139965722439551e-05, "loss": 3.554, "step": 1136128 }, { "epoch": 0.02, "learning_rate": 3.139128765568872e-05, "loss": 3.543, "step": 1136640 }, { "epoch": 0.02, "learning_rate": 3.13829017081782e-05, "loss": 3.5515, "step": 1137152 }, { "epoch": 0.02, "learning_rate": 3.1374515760667676e-05, "loss": 3.5471, "step": 1137664 }, { "epoch": 0.02, "learning_rate": 3.136614619196089e-05, "loss": 3.5553, "step": 1138176 }, { "epoch": 0.02, "learning_rate": 3.135776024445037e-05, "loss": 3.5523, "step": 1138688 }, { "epoch": 0.02, "learning_rate": 3.134937429693985e-05, "loss": 3.5653, "step": 1139200 }, { "epoch": 0.02, "learning_rate": 3.134098834942933e-05, "loss": 3.5503, "step": 1139712 }, { "epoch": 0.02, "learning_rate": 3.133260240191881e-05, "loss": 3.562, "step": 1140224 }, { "epoch": 0.02, "learning_rate": 3.132423283321203e-05, "loss": 3.548, "step": 1140736 }, { "epoch": 0.02, "learning_rate": 3.13158468857015e-05, "loss": 3.557, "step": 1141248 }, { "epoch": 0.02, "learning_rate": 3.130746093819098e-05, "loss": 3.5467, "step": 1141760 }, { "epoch": 0.02, "learning_rate": 3.1299091369484196e-05, "loss": 3.5431, "step": 1142272 }, { "epoch": 0.02, "learning_rate": 3.1290705421973676e-05, "loss": 3.554, "step": 1142784 }, { "epoch": 0.02, "learning_rate": 3.128231947446315e-05, "loss": 3.539, "step": 1143296 }, { "epoch": 0.02, "learning_rate": 3.127393352695263e-05, "loss": 3.5527, "step": 1143808 }, { "epoch": 0.02, "learning_rate": 3.126554757944211e-05, "loss": 3.5455, "step": 1144320 }, { "epoch": 0.03, "eval_loss": 3.8496906757354736, "eval_runtime": 304.0346, "eval_samples_per_second": 1255.091, "eval_steps_per_second": 39.223, "step": 1144790 }, { "epoch": 0.0, "learning_rate": 3.125716163193159e-05, "loss": 3.5481, "step": 1144832 }, { "epoch": 0.0, "learning_rate": 3.124877568442107e-05, "loss": 3.5495, "step": 1145344 }, { "epoch": 0.0, "learning_rate": 3.124038973691055e-05, "loss": 3.5451, "step": 1145856 }, { "epoch": 0.0, "learning_rate": 3.1232003789400036e-05, "loss": 3.5547, "step": 1146368 }, { "epoch": 0.0, "learning_rate": 3.1223634220693245e-05, "loss": 3.5565, "step": 1146880 }, { "epoch": 0.0, "learning_rate": 3.1215248273182725e-05, "loss": 3.5609, "step": 1147392 }, { "epoch": 0.0, "learning_rate": 3.1206862325672205e-05, "loss": 3.5475, "step": 1147904 }, { "epoch": 0.0, "learning_rate": 3.1198476378161685e-05, "loss": 3.5457, "step": 1148416 }, { "epoch": 0.0, "learning_rate": 3.1190106809454894e-05, "loss": 3.5351, "step": 1148928 }, { "epoch": 0.0, "learning_rate": 3.1181720861944374e-05, "loss": 3.5531, "step": 1149440 }, { "epoch": 0.0, "learning_rate": 3.1173334914433854e-05, "loss": 3.5479, "step": 1149952 }, { "epoch": 0.0, "learning_rate": 3.1164948966923334e-05, "loss": 3.5471, "step": 1150464 }, { "epoch": 0.0, "learning_rate": 3.115657939821654e-05, "loss": 3.5491, "step": 1150976 }, { "epoch": 0.0, "learning_rate": 3.114819345070602e-05, "loss": 3.5383, "step": 1151488 }, { "epoch": 0.0, "learning_rate": 3.11398075031955e-05, "loss": 3.5362, "step": 1152000 }, { "epoch": 0.0, "learning_rate": 3.113142155568499e-05, "loss": 3.5365, "step": 1152512 }, { "epoch": 0.0, "learning_rate": 3.11230519869782e-05, "loss": 3.538, "step": 1153024 }, { "epoch": 0.0, "learning_rate": 3.111466603946768e-05, "loss": 3.5422, "step": 1153536 }, { "epoch": 0.0, "learning_rate": 3.110628009195716e-05, "loss": 3.547, "step": 1154048 }, { "epoch": 0.0, "learning_rate": 3.109789414444664e-05, "loss": 3.5429, "step": 1154560 }, { "epoch": 0.0, "learning_rate": 3.108952457573985e-05, "loss": 3.5621, "step": 1155072 }, { "epoch": 0.0, "learning_rate": 3.108113862822933e-05, "loss": 3.5463, "step": 1155584 }, { "epoch": 0.0, "learning_rate": 3.107275268071881e-05, "loss": 3.5462, "step": 1156096 }, { "epoch": 0.0, "learning_rate": 3.106436673320829e-05, "loss": 3.5422, "step": 1156608 }, { "epoch": 0.0, "learning_rate": 3.10559971645015e-05, "loss": 3.5595, "step": 1157120 }, { "epoch": 0.0, "learning_rate": 3.104761121699098e-05, "loss": 3.5422, "step": 1157632 }, { "epoch": 0.0, "learning_rate": 3.103922526948046e-05, "loss": 3.5453, "step": 1158144 }, { "epoch": 0.0, "learning_rate": 3.103083932196994e-05, "loss": 3.5398, "step": 1158656 }, { "epoch": 0.0, "learning_rate": 3.102246975326315e-05, "loss": 3.5421, "step": 1159168 }, { "epoch": 0.0, "learning_rate": 3.101408380575263e-05, "loss": 3.542, "step": 1159680 }, { "epoch": 0.01, "learning_rate": 3.100569785824211e-05, "loss": 3.5429, "step": 1160192 }, { "epoch": 0.01, "learning_rate": 3.099731191073159e-05, "loss": 3.5484, "step": 1160704 }, { "epoch": 0.01, "learning_rate": 3.09889423420248e-05, "loss": 3.5507, "step": 1161216 }, { "epoch": 0.01, "learning_rate": 3.098055639451428e-05, "loss": 3.5507, "step": 1161728 }, { "epoch": 0.01, "learning_rate": 3.097217044700376e-05, "loss": 3.5462, "step": 1162240 }, { "epoch": 0.01, "learning_rate": 3.096378449949324e-05, "loss": 3.551, "step": 1162752 }, { "epoch": 0.01, "learning_rate": 3.095541493078645e-05, "loss": 3.5506, "step": 1163264 }, { "epoch": 0.01, "learning_rate": 3.094702898327593e-05, "loss": 3.537, "step": 1163776 }, { "epoch": 0.01, "learning_rate": 3.0938659414569146e-05, "loss": 3.5407, "step": 1164288 }, { "epoch": 0.01, "learning_rate": 3.0930273467058626e-05, "loss": 3.5298, "step": 1164800 }, { "epoch": 0.01, "learning_rate": 3.0921887519548106e-05, "loss": 3.54, "step": 1165312 }, { "epoch": 0.01, "learning_rate": 3.0913501572037586e-05, "loss": 3.5343, "step": 1165824 }, { "epoch": 0.01, "learning_rate": 3.0905115624527066e-05, "loss": 3.5546, "step": 1166336 }, { "epoch": 0.01, "learning_rate": 3.0896729677016546e-05, "loss": 3.5396, "step": 1166848 }, { "epoch": 0.01, "learning_rate": 3.0888343729506026e-05, "loss": 3.5386, "step": 1167360 }, { "epoch": 0.01, "learning_rate": 3.0879957781995506e-05, "loss": 3.5426, "step": 1167872 }, { "epoch": 0.01, "learning_rate": 3.0871588213288715e-05, "loss": 3.5456, "step": 1168384 }, { "epoch": 0.01, "learning_rate": 3.0863202265778195e-05, "loss": 3.5406, "step": 1168896 }, { "epoch": 0.01, "learning_rate": 3.0854816318267675e-05, "loss": 3.5212, "step": 1169408 }, { "epoch": 0.01, "learning_rate": 3.0846430370757155e-05, "loss": 3.5398, "step": 1169920 }, { "epoch": 0.01, "learning_rate": 3.0838060802050364e-05, "loss": 3.5534, "step": 1170432 }, { "epoch": 0.01, "learning_rate": 3.0829674854539844e-05, "loss": 3.5477, "step": 1170944 }, { "epoch": 0.01, "learning_rate": 3.082128890702933e-05, "loss": 3.5439, "step": 1171456 }, { "epoch": 0.01, "learning_rate": 3.081290295951881e-05, "loss": 3.531, "step": 1171968 }, { "epoch": 0.01, "learning_rate": 3.080453339081202e-05, "loss": 3.5439, "step": 1172480 }, { "epoch": 0.01, "learning_rate": 3.07961474433015e-05, "loss": 3.5291, "step": 1172992 }, { "epoch": 0.01, "learning_rate": 3.078776149579098e-05, "loss": 3.5519, "step": 1173504 }, { "epoch": 0.01, "learning_rate": 3.077939192708419e-05, "loss": 3.5289, "step": 1174016 }, { "epoch": 0.01, "learning_rate": 3.077100597957367e-05, "loss": 3.5567, "step": 1174528 }, { "epoch": 0.01, "learning_rate": 3.076262003206315e-05, "loss": 3.5489, "step": 1175040 }, { "epoch": 0.01, "learning_rate": 3.075423408455263e-05, "loss": 3.525, "step": 1175552 }, { "epoch": 0.01, "learning_rate": 3.07458481370421e-05, "loss": 3.5403, "step": 1176064 }, { "epoch": 0.01, "learning_rate": 3.073746218953158e-05, "loss": 3.5473, "step": 1176576 }, { "epoch": 0.01, "learning_rate": 3.072907624202107e-05, "loss": 3.5234, "step": 1177088 }, { "epoch": 0.01, "learning_rate": 3.072069029451055e-05, "loss": 3.5299, "step": 1177600 }, { "epoch": 0.01, "learning_rate": 3.071232072580376e-05, "loss": 3.5516, "step": 1178112 }, { "epoch": 0.01, "learning_rate": 3.070393477829324e-05, "loss": 3.5392, "step": 1178624 }, { "epoch": 0.01, "learning_rate": 3.069554883078272e-05, "loss": 3.5359, "step": 1179136 }, { "epoch": 0.01, "learning_rate": 3.06871628832722e-05, "loss": 3.5227, "step": 1179648 }, { "epoch": 0.01, "learning_rate": 3.0678793314565407e-05, "loss": 3.5365, "step": 1180160 }, { "epoch": 0.01, "learning_rate": 3.0670407367054886e-05, "loss": 3.5276, "step": 1180672 }, { "epoch": 0.01, "learning_rate": 3.0662021419544366e-05, "loss": 3.5459, "step": 1181184 }, { "epoch": 0.01, "learning_rate": 3.0653635472033846e-05, "loss": 3.5312, "step": 1181696 }, { "epoch": 0.01, "learning_rate": 3.0645265903327056e-05, "loss": 3.5434, "step": 1182208 }, { "epoch": 0.01, "learning_rate": 3.0636879955816535e-05, "loss": 3.5434, "step": 1182720 }, { "epoch": 0.01, "learning_rate": 3.062849400830602e-05, "loss": 3.5434, "step": 1183232 }, { "epoch": 0.01, "learning_rate": 3.06201080607955e-05, "loss": 3.5406, "step": 1183744 }, { "epoch": 0.01, "learning_rate": 3.061173849208871e-05, "loss": 3.5388, "step": 1184256 }, { "epoch": 0.01, "learning_rate": 3.060335254457819e-05, "loss": 3.5413, "step": 1184768 }, { "epoch": 0.01, "learning_rate": 3.059496659706767e-05, "loss": 3.5423, "step": 1185280 }, { "epoch": 0.01, "learning_rate": 3.058658064955715e-05, "loss": 3.5379, "step": 1185792 }, { "epoch": 0.01, "learning_rate": 3.057819470204663e-05, "loss": 3.5379, "step": 1186304 }, { "epoch": 0.01, "learning_rate": 3.056982513333984e-05, "loss": 3.5392, "step": 1186816 }, { "epoch": 0.01, "learning_rate": 3.056143918582932e-05, "loss": 3.5369, "step": 1187328 }, { "epoch": 0.01, "learning_rate": 3.05530532383188e-05, "loss": 3.522, "step": 1187840 }, { "epoch": 0.01, "learning_rate": 3.054466729080828e-05, "loss": 3.5363, "step": 1188352 }, { "epoch": 0.01, "learning_rate": 3.053628134329776e-05, "loss": 3.5384, "step": 1188864 }, { "epoch": 0.01, "learning_rate": 3.052789539578724e-05, "loss": 3.5378, "step": 1189376 }, { "epoch": 0.01, "learning_rate": 3.051950944827672e-05, "loss": 3.5353, "step": 1189888 }, { "epoch": 0.01, "learning_rate": 3.0511123500766203e-05, "loss": 3.5376, "step": 1190400 }, { "epoch": 0.02, "learning_rate": 3.0502753932059412e-05, "loss": 3.533, "step": 1190912 }, { "epoch": 0.02, "learning_rate": 3.0494367984548892e-05, "loss": 3.5275, "step": 1191424 }, { "epoch": 0.02, "learning_rate": 3.0485982037038376e-05, "loss": 3.5323, "step": 1191936 }, { "epoch": 0.02, "learning_rate": 3.0477596089527856e-05, "loss": 3.5415, "step": 1192448 }, { "epoch": 0.02, "learning_rate": 3.0469226520821065e-05, "loss": 3.539, "step": 1192960 }, { "epoch": 0.02, "learning_rate": 3.0460840573310545e-05, "loss": 3.547, "step": 1193472 }, { "epoch": 0.02, "learning_rate": 3.0452454625800025e-05, "loss": 3.5328, "step": 1193984 }, { "epoch": 0.02, "learning_rate": 3.0444068678289505e-05, "loss": 3.5349, "step": 1194496 }, { "epoch": 0.02, "learning_rate": 3.0435699109582717e-05, "loss": 3.5329, "step": 1195008 }, { "epoch": 0.02, "learning_rate": 3.0427313162072197e-05, "loss": 3.5484, "step": 1195520 }, { "epoch": 0.02, "learning_rate": 3.0418927214561677e-05, "loss": 3.5384, "step": 1196032 }, { "epoch": 0.02, "learning_rate": 3.0410541267051157e-05, "loss": 3.5485, "step": 1196544 }, { "epoch": 0.02, "learning_rate": 3.0402171698344366e-05, "loss": 3.5331, "step": 1197056 }, { "epoch": 0.02, "learning_rate": 3.0393785750833846e-05, "loss": 3.5305, "step": 1197568 }, { "epoch": 0.02, "learning_rate": 3.038539980332333e-05, "loss": 3.5498, "step": 1198080 }, { "epoch": 0.02, "learning_rate": 3.037701385581281e-05, "loss": 3.529, "step": 1198592 }, { "epoch": 0.02, "learning_rate": 3.036864428710602e-05, "loss": 3.5302, "step": 1199104 }, { "epoch": 0.02, "learning_rate": 3.03602583395955e-05, "loss": 3.5408, "step": 1199616 }, { "epoch": 0.02, "learning_rate": 3.0351872392084978e-05, "loss": 3.5376, "step": 1200128 }, { "epoch": 0.02, "learning_rate": 3.034350282337819e-05, "loss": 3.5293, "step": 1200640 }, { "epoch": 0.02, "learning_rate": 3.033511687586767e-05, "loss": 3.5373, "step": 1201152 }, { "epoch": 0.02, "learning_rate": 3.032673092835715e-05, "loss": 3.5235, "step": 1201664 }, { "epoch": 0.02, "learning_rate": 3.031834498084663e-05, "loss": 3.5394, "step": 1202176 }, { "epoch": 0.02, "learning_rate": 3.030997541213984e-05, "loss": 3.5328, "step": 1202688 }, { "epoch": 0.02, "learning_rate": 3.030158946462932e-05, "loss": 3.5362, "step": 1203200 }, { "epoch": 0.02, "learning_rate": 3.02932035171188e-05, "loss": 3.5416, "step": 1203712 }, { "epoch": 0.02, "learning_rate": 3.0284817569608283e-05, "loss": 3.5523, "step": 1204224 }, { "epoch": 0.02, "learning_rate": 3.0276448000901492e-05, "loss": 3.5395, "step": 1204736 }, { "epoch": 0.02, "learning_rate": 3.0268062053390972e-05, "loss": 3.5348, "step": 1205248 }, { "epoch": 0.02, "learning_rate": 3.0259676105880452e-05, "loss": 3.533, "step": 1205760 }, { "epoch": 0.02, "learning_rate": 3.0251290158369932e-05, "loss": 3.5321, "step": 1206272 }, { "epoch": 0.02, "learning_rate": 3.0242920589663144e-05, "loss": 3.5315, "step": 1206784 }, { "epoch": 0.02, "learning_rate": 3.0234534642152624e-05, "loss": 3.5381, "step": 1207296 }, { "epoch": 0.02, "learning_rate": 3.0226148694642104e-05, "loss": 3.5322, "step": 1207808 }, { "epoch": 0.02, "learning_rate": 3.0217762747131584e-05, "loss": 3.5396, "step": 1208320 }, { "epoch": 0.02, "learning_rate": 3.0209393178424793e-05, "loss": 3.5326, "step": 1208832 }, { "epoch": 0.02, "learning_rate": 3.0201007230914273e-05, "loss": 3.5402, "step": 1209344 }, { "epoch": 0.02, "learning_rate": 3.0192621283403753e-05, "loss": 3.5346, "step": 1209856 }, { "epoch": 0.02, "learning_rate": 3.0184235335893237e-05, "loss": 3.5313, "step": 1210368 }, { "epoch": 0.02, "learning_rate": 3.0175865767186446e-05, "loss": 3.5297, "step": 1210880 }, { "epoch": 0.02, "learning_rate": 3.0167479819675926e-05, "loss": 3.5431, "step": 1211392 }, { "epoch": 0.02, "learning_rate": 3.0159093872165406e-05, "loss": 3.5495, "step": 1211904 }, { "epoch": 0.02, "learning_rate": 3.0150707924654886e-05, "loss": 3.5404, "step": 1212416 }, { "epoch": 0.02, "learning_rate": 3.0142338355948098e-05, "loss": 3.5254, "step": 1212928 }, { "epoch": 0.02, "learning_rate": 3.0133952408437578e-05, "loss": 3.5334, "step": 1213440 }, { "epoch": 0.02, "learning_rate": 3.0125566460927058e-05, "loss": 3.5358, "step": 1213952 }, { "epoch": 0.02, "learning_rate": 3.0117180513416538e-05, "loss": 3.539, "step": 1214464 }, { "epoch": 0.02, "learning_rate": 3.0108810944709747e-05, "loss": 3.5378, "step": 1214976 }, { "epoch": 0.02, "learning_rate": 3.0100424997199227e-05, "loss": 3.5478, "step": 1215488 }, { "epoch": 0.02, "learning_rate": 3.0092039049688707e-05, "loss": 3.5344, "step": 1216000 }, { "epoch": 0.02, "learning_rate": 3.0083653102178184e-05, "loss": 3.5475, "step": 1216512 }, { "epoch": 0.02, "learning_rate": 3.00752835334714e-05, "loss": 3.5325, "step": 1217024 }, { "epoch": 0.02, "learning_rate": 3.006689758596088e-05, "loss": 3.542, "step": 1217536 }, { "epoch": 0.02, "learning_rate": 3.005851163845036e-05, "loss": 3.5359, "step": 1218048 }, { "epoch": 0.02, "learning_rate": 3.0050125690939836e-05, "loss": 3.5257, "step": 1218560 }, { "epoch": 0.02, "learning_rate": 3.0041756122233052e-05, "loss": 3.5438, "step": 1219072 }, { "epoch": 0.02, "learning_rate": 3.0033370174722532e-05, "loss": 3.5242, "step": 1219584 }, { "epoch": 0.02, "learning_rate": 3.002498422721201e-05, "loss": 3.5344, "step": 1220096 }, { "epoch": 0.02, "learning_rate": 3.0016598279701485e-05, "loss": 3.5318, "step": 1220608 }, { "epoch": 0.03, "eval_loss": 3.8517608642578125, "eval_runtime": 302.9543, "eval_samples_per_second": 1259.566, "eval_steps_per_second": 39.362, "step": 1221110 }, { "epoch": 1.0, "learning_rate": 3.0008212332190965e-05, "loss": 3.5317, "step": 1221120 }, { "epoch": 1.0, "learning_rate": 2.9999826384680445e-05, "loss": 3.5338, "step": 1221632 }, { "epoch": 1.0, "learning_rate": 2.9991440437169928e-05, "loss": 3.5318, "step": 1222144 }, { "epoch": 1.0, "learning_rate": 2.9983070868463137e-05, "loss": 3.541, "step": 1222656 }, { "epoch": 1.0, "learning_rate": 2.9974684920952617e-05, "loss": 3.5393, "step": 1223168 }, { "epoch": 1.0, "learning_rate": 2.9966298973442097e-05, "loss": 3.5485, "step": 1223680 }, { "epoch": 1.0, "learning_rate": 2.9957913025931577e-05, "loss": 3.5312, "step": 1224192 }, { "epoch": 1.0, "learning_rate": 2.994954345722479e-05, "loss": 3.5296, "step": 1224704 }, { "epoch": 1.0, "learning_rate": 2.994115750971427e-05, "loss": 3.523, "step": 1225216 }, { "epoch": 1.0, "learning_rate": 2.993277156220375e-05, "loss": 3.5374, "step": 1225728 }, { "epoch": 1.0, "learning_rate": 2.992438561469323e-05, "loss": 3.5319, "step": 1226240 }, { "epoch": 1.0, "learning_rate": 2.991601604598644e-05, "loss": 3.5341, "step": 1226752 }, { "epoch": 1.0, "learning_rate": 2.990763009847592e-05, "loss": 3.5297, "step": 1227264 }, { "epoch": 1.0, "learning_rate": 2.98992441509654e-05, "loss": 3.5224, "step": 1227776 }, { "epoch": 1.0, "learning_rate": 2.9890858203454882e-05, "loss": 3.526, "step": 1228288 }, { "epoch": 1.0, "learning_rate": 2.988248863474809e-05, "loss": 3.5252, "step": 1228800 }, { "epoch": 1.0, "learning_rate": 2.987410268723757e-05, "loss": 3.5191, "step": 1229312 }, { "epoch": 1.0, "learning_rate": 2.986571673972705e-05, "loss": 3.5311, "step": 1229824 }, { "epoch": 1.0, "learning_rate": 2.985733079221653e-05, "loss": 3.5284, "step": 1230336 }, { "epoch": 1.0, "learning_rate": 2.9848961223509743e-05, "loss": 3.5316, "step": 1230848 }, { "epoch": 1.0, "learning_rate": 2.9840575275999223e-05, "loss": 3.5487, "step": 1231360 }, { "epoch": 1.0, "learning_rate": 2.9832189328488703e-05, "loss": 3.528, "step": 1231872 }, { "epoch": 1.0, "learning_rate": 2.9823803380978183e-05, "loss": 3.5367, "step": 1232384 }, { "epoch": 1.0, "learning_rate": 2.9815433812271392e-05, "loss": 3.5251, "step": 1232896 }, { "epoch": 1.0, "learning_rate": 2.9807047864760872e-05, "loss": 3.543, "step": 1233408 }, { "epoch": 1.0, "learning_rate": 2.9798661917250352e-05, "loss": 3.5279, "step": 1233920 }, { "epoch": 1.0, "learning_rate": 2.9790275969739832e-05, "loss": 3.5318, "step": 1234432 }, { "epoch": 1.0, "learning_rate": 2.9781906401033045e-05, "loss": 3.5254, "step": 1234944 }, { "epoch": 1.0, "learning_rate": 2.9773520453522524e-05, "loss": 3.5291, "step": 1235456 }, { "epoch": 1.0, "learning_rate": 2.9765134506012004e-05, "loss": 3.5273, "step": 1235968 }, { "epoch": 1.01, "learning_rate": 2.9756748558501484e-05, "loss": 3.529, "step": 1236480 }, { "epoch": 1.01, "learning_rate": 2.9748378989794693e-05, "loss": 3.5362, "step": 1236992 }, { "epoch": 1.01, "learning_rate": 2.9739993042284177e-05, "loss": 3.5325, "step": 1237504 }, { "epoch": 1.01, "learning_rate": 2.9731607094773657e-05, "loss": 3.5356, "step": 1238016 }, { "epoch": 1.01, "learning_rate": 2.9723221147263137e-05, "loss": 3.5354, "step": 1238528 }, { "epoch": 1.01, "learning_rate": 2.9714851578556346e-05, "loss": 3.529, "step": 1239040 }, { "epoch": 1.01, "learning_rate": 2.9706465631045826e-05, "loss": 3.5409, "step": 1239552 }, { "epoch": 1.01, "learning_rate": 2.9698079683535306e-05, "loss": 3.5191, "step": 1240064 }, { "epoch": 1.01, "learning_rate": 2.9689710114828518e-05, "loss": 3.5295, "step": 1240576 }, { "epoch": 1.01, "learning_rate": 2.9681324167317998e-05, "loss": 3.5151, "step": 1241088 }, { "epoch": 1.01, "learning_rate": 2.9672938219807478e-05, "loss": 3.5239, "step": 1241600 }, { "epoch": 1.01, "learning_rate": 2.9664552272296958e-05, "loss": 3.5222, "step": 1242112 }, { "epoch": 1.01, "learning_rate": 2.9656166324786438e-05, "loss": 3.5375, "step": 1242624 }, { "epoch": 1.01, "learning_rate": 2.9647780377275918e-05, "loss": 3.5271, "step": 1243136 }, { "epoch": 1.01, "learning_rate": 2.9639394429765398e-05, "loss": 3.5228, "step": 1243648 }, { "epoch": 1.01, "learning_rate": 2.9631008482254878e-05, "loss": 3.5308, "step": 1244160 }, { "epoch": 1.01, "learning_rate": 2.962263891354809e-05, "loss": 3.5295, "step": 1244672 }, { "epoch": 1.01, "learning_rate": 2.961425296603757e-05, "loss": 3.5235, "step": 1245184 }, { "epoch": 1.01, "learning_rate": 2.960586701852705e-05, "loss": 3.5124, "step": 1245696 }, { "epoch": 1.01, "learning_rate": 2.959748107101653e-05, "loss": 3.52, "step": 1246208 }, { "epoch": 1.01, "learning_rate": 2.958911150230974e-05, "loss": 3.5377, "step": 1246720 }, { "epoch": 1.01, "learning_rate": 2.9580725554799223e-05, "loss": 3.5389, "step": 1247232 }, { "epoch": 1.01, "learning_rate": 2.9572339607288703e-05, "loss": 3.527, "step": 1247744 }, { "epoch": 1.01, "learning_rate": 2.9563970038581912e-05, "loss": 3.5205, "step": 1248256 }, { "epoch": 1.01, "learning_rate": 2.9555584091071392e-05, "loss": 3.5327, "step": 1248768 }, { "epoch": 1.01, "learning_rate": 2.954719814356087e-05, "loss": 3.5145, "step": 1249280 }, { "epoch": 1.01, "learning_rate": 2.953881219605035e-05, "loss": 3.5344, "step": 1249792 }, { "epoch": 1.01, "learning_rate": 2.953042624853983e-05, "loss": 3.5134, "step": 1250304 }, { "epoch": 1.01, "learning_rate": 2.9522056679833044e-05, "loss": 3.5399, "step": 1250816 }, { "epoch": 1.01, "learning_rate": 2.9513670732322524e-05, "loss": 3.5345, "step": 1251328 }, { "epoch": 1.01, "learning_rate": 2.9505284784812004e-05, "loss": 3.5139, "step": 1251840 }, { "epoch": 1.01, "learning_rate": 2.9496898837301484e-05, "loss": 3.5224, "step": 1252352 }, { "epoch": 1.01, "learning_rate": 2.9488512889790964e-05, "loss": 3.5338, "step": 1252864 }, { "epoch": 1.01, "learning_rate": 2.948012694228044e-05, "loss": 3.5098, "step": 1253376 }, { "epoch": 1.01, "learning_rate": 2.947174099476992e-05, "loss": 3.5126, "step": 1253888 }, { "epoch": 1.01, "learning_rate": 2.9463371426063136e-05, "loss": 3.5376, "step": 1254400 }, { "epoch": 1.01, "learning_rate": 2.9454985478552616e-05, "loss": 3.5271, "step": 1254912 }, { "epoch": 1.01, "learning_rate": 2.944659953104209e-05, "loss": 3.5215, "step": 1255424 }, { "epoch": 1.01, "learning_rate": 2.943821358353157e-05, "loss": 3.5116, "step": 1255936 }, { "epoch": 1.01, "learning_rate": 2.9429844014824785e-05, "loss": 3.5197, "step": 1256448 }, { "epoch": 1.01, "learning_rate": 2.9421458067314262e-05, "loss": 3.514, "step": 1256960 }, { "epoch": 1.01, "learning_rate": 2.9413072119803742e-05, "loss": 3.5352, "step": 1257472 }, { "epoch": 1.01, "learning_rate": 2.9404686172293222e-05, "loss": 3.5151, "step": 1257984 }, { "epoch": 1.01, "learning_rate": 2.9396316603586438e-05, "loss": 3.5314, "step": 1258496 }, { "epoch": 1.01, "learning_rate": 2.9387930656075914e-05, "loss": 3.5264, "step": 1259008 }, { "epoch": 1.01, "learning_rate": 2.9379544708565394e-05, "loss": 3.5324, "step": 1259520 }, { "epoch": 1.01, "learning_rate": 2.9371158761054874e-05, "loss": 3.5218, "step": 1260032 }, { "epoch": 1.01, "learning_rate": 2.936278919234809e-05, "loss": 3.5259, "step": 1260544 }, { "epoch": 1.01, "learning_rate": 2.9354403244837563e-05, "loss": 3.5292, "step": 1261056 }, { "epoch": 1.01, "learning_rate": 2.9346017297327043e-05, "loss": 3.5257, "step": 1261568 }, { "epoch": 1.01, "learning_rate": 2.9337631349816523e-05, "loss": 3.525, "step": 1262080 }, { "epoch": 1.01, "learning_rate": 2.9329245402306006e-05, "loss": 3.5222, "step": 1262592 }, { "epoch": 1.01, "learning_rate": 2.9320875833599215e-05, "loss": 3.5279, "step": 1263104 }, { "epoch": 1.01, "learning_rate": 2.9312489886088695e-05, "loss": 3.5208, "step": 1263616 }, { "epoch": 1.01, "learning_rate": 2.9304103938578175e-05, "loss": 3.5123, "step": 1264128 }, { "epoch": 1.01, "learning_rate": 2.9295717991067655e-05, "loss": 3.5168, "step": 1264640 }, { "epoch": 1.01, "learning_rate": 2.9287332043557135e-05, "loss": 3.5252, "step": 1265152 }, { "epoch": 1.01, "learning_rate": 2.9278946096046615e-05, "loss": 3.5239, "step": 1265664 }, { "epoch": 1.01, "learning_rate": 2.92705601485361e-05, "loss": 3.5198, "step": 1266176 }, { "epoch": 1.01, "learning_rate": 2.926217420102558e-05, "loss": 3.5267, "step": 1266688 }, { "epoch": 1.02, "learning_rate": 2.9253804632318788e-05, "loss": 3.518, "step": 1267200 }, { "epoch": 1.02, "learning_rate": 2.9245418684808268e-05, "loss": 3.5129, "step": 1267712 }, { "epoch": 1.02, "learning_rate": 2.9237032737297748e-05, "loss": 3.5157, "step": 1268224 }, { "epoch": 1.02, "learning_rate": 2.9228646789787228e-05, "loss": 3.5278, "step": 1268736 }, { "epoch": 1.02, "learning_rate": 2.922027722108044e-05, "loss": 3.525, "step": 1269248 }, { "epoch": 1.02, "learning_rate": 2.921189127356992e-05, "loss": 3.5319, "step": 1269760 }, { "epoch": 1.02, "learning_rate": 2.92035053260594e-05, "loss": 3.5246, "step": 1270272 }, { "epoch": 1.02, "learning_rate": 2.919511937854888e-05, "loss": 3.5156, "step": 1270784 }, { "epoch": 1.02, "learning_rate": 2.918674980984209e-05, "loss": 3.5217, "step": 1271296 }, { "epoch": 1.02, "learning_rate": 2.917836386233157e-05, "loss": 3.5327, "step": 1271808 }, { "epoch": 1.02, "learning_rate": 2.916997791482105e-05, "loss": 3.5272, "step": 1272320 }, { "epoch": 1.02, "learning_rate": 2.9161591967310532e-05, "loss": 3.5342, "step": 1272832 }, { "epoch": 1.02, "learning_rate": 2.915322239860374e-05, "loss": 3.5177, "step": 1273344 }, { "epoch": 1.02, "learning_rate": 2.914483645109322e-05, "loss": 3.5131, "step": 1273856 }, { "epoch": 1.02, "learning_rate": 2.91364505035827e-05, "loss": 3.5383, "step": 1274368 }, { "epoch": 1.02, "learning_rate": 2.912806455607218e-05, "loss": 3.5112, "step": 1274880 }, { "epoch": 1.02, "learning_rate": 2.9119694987365394e-05, "loss": 3.5168, "step": 1275392 }, { "epoch": 1.02, "learning_rate": 2.9111309039854874e-05, "loss": 3.5249, "step": 1275904 }, { "epoch": 1.02, "learning_rate": 2.9102923092344354e-05, "loss": 3.5246, "step": 1276416 }, { "epoch": 1.02, "learning_rate": 2.9094553523637563e-05, "loss": 3.515, "step": 1276928 }, { "epoch": 1.02, "learning_rate": 2.9086167576127043e-05, "loss": 3.5182, "step": 1277440 }, { "epoch": 1.02, "learning_rate": 2.9077781628616523e-05, "loss": 3.5147, "step": 1277952 }, { "epoch": 1.02, "learning_rate": 2.9069395681106003e-05, "loss": 3.5243, "step": 1278464 }, { "epoch": 1.02, "learning_rate": 2.9061009733595486e-05, "loss": 3.5207, "step": 1278976 }, { "epoch": 1.02, "learning_rate": 2.9052623786084966e-05, "loss": 3.52, "step": 1279488 }, { "epoch": 1.02, "learning_rate": 2.9044237838574446e-05, "loss": 3.5303, "step": 1280000 }, { "epoch": 1.02, "learning_rate": 2.903585189106392e-05, "loss": 3.5358, "step": 1280512 }, { "epoch": 1.02, "learning_rate": 2.9027482322357135e-05, "loss": 3.53, "step": 1281024 }, { "epoch": 1.02, "learning_rate": 2.9019096374846615e-05, "loss": 3.5222, "step": 1281536 }, { "epoch": 1.02, "learning_rate": 2.9010710427336095e-05, "loss": 3.5181, "step": 1282048 }, { "epoch": 1.02, "learning_rate": 2.900232447982557e-05, "loss": 3.5143, "step": 1282560 }, { "epoch": 1.02, "learning_rate": 2.8993954911118787e-05, "loss": 3.5189, "step": 1283072 }, { "epoch": 1.02, "learning_rate": 2.8985568963608267e-05, "loss": 3.5243, "step": 1283584 }, { "epoch": 1.02, "learning_rate": 2.8977183016097747e-05, "loss": 3.5179, "step": 1284096 }, { "epoch": 1.02, "learning_rate": 2.8968797068587224e-05, "loss": 3.5217, "step": 1284608 }, { "epoch": 1.02, "learning_rate": 2.896042749988044e-05, "loss": 3.5214, "step": 1285120 }, { "epoch": 1.02, "learning_rate": 2.895204155236992e-05, "loss": 3.5234, "step": 1285632 }, { "epoch": 1.02, "learning_rate": 2.8943655604859393e-05, "loss": 3.5235, "step": 1286144 }, { "epoch": 1.02, "learning_rate": 2.8935269657348873e-05, "loss": 3.5177, "step": 1286656 }, { "epoch": 1.02, "learning_rate": 2.892690008864209e-05, "loss": 3.5146, "step": 1287168 }, { "epoch": 1.02, "learning_rate": 2.891851414113157e-05, "loss": 3.5272, "step": 1287680 }, { "epoch": 1.02, "learning_rate": 2.8910128193621045e-05, "loss": 3.533, "step": 1288192 }, { "epoch": 1.02, "learning_rate": 2.8901742246110525e-05, "loss": 3.5294, "step": 1288704 }, { "epoch": 1.02, "learning_rate": 2.889337267740374e-05, "loss": 3.51, "step": 1289216 }, { "epoch": 1.02, "learning_rate": 2.888498672989322e-05, "loss": 3.5217, "step": 1289728 }, { "epoch": 1.02, "learning_rate": 2.8876600782382694e-05, "loss": 3.5208, "step": 1290240 }, { "epoch": 1.02, "learning_rate": 2.8868214834872177e-05, "loss": 3.5276, "step": 1290752 }, { "epoch": 1.02, "learning_rate": 2.8859845266165393e-05, "loss": 3.5179, "step": 1291264 }, { "epoch": 1.02, "learning_rate": 2.8851459318654866e-05, "loss": 3.5352, "step": 1291776 }, { "epoch": 1.02, "learning_rate": 2.8843073371144346e-05, "loss": 3.5202, "step": 1292288 }, { "epoch": 1.02, "learning_rate": 2.8834687423633826e-05, "loss": 3.538, "step": 1292800 }, { "epoch": 1.02, "learning_rate": 2.8826317854927042e-05, "loss": 3.5164, "step": 1293312 }, { "epoch": 1.02, "learning_rate": 2.881793190741652e-05, "loss": 3.53, "step": 1293824 }, { "epoch": 1.02, "learning_rate": 2.8809545959906e-05, "loss": 3.5186, "step": 1294336 }, { "epoch": 1.02, "learning_rate": 2.880116001239548e-05, "loss": 3.5116, "step": 1294848 }, { "epoch": 1.02, "learning_rate": 2.8792806822492424e-05, "loss": 3.5287, "step": 1295360 }, { "epoch": 1.02, "learning_rate": 2.8784420874981904e-05, "loss": 3.5104, "step": 1295872 }, { "epoch": 1.02, "learning_rate": 2.8776034927471384e-05, "loss": 3.5221, "step": 1296384 }, { "epoch": 1.02, "learning_rate": 2.8767648979960864e-05, "loss": 3.5176, "step": 1296896 }, { "epoch": 1.02, "learning_rate": 2.875926303245034e-05, "loss": 3.517, "step": 1297408 }, { "epoch": 1.03, "eval_loss": 3.8526835441589355, "eval_runtime": 303.1466, "eval_samples_per_second": 1258.767, "eval_steps_per_second": 39.337, "step": 1297430 }, { "epoch": 0.0, "learning_rate": 2.875087708493982e-05, "loss": 3.5194, "step": 1297920 }, { "epoch": 0.0, "learning_rate": 2.87424911374293e-05, "loss": 3.5209, "step": 1298432 }, { "epoch": 0.0, "learning_rate": 2.873410518991878e-05, "loss": 3.5276, "step": 1298944 }, { "epoch": 0.0, "learning_rate": 2.8725735621211992e-05, "loss": 3.5241, "step": 1299456 }, { "epoch": 0.0, "learning_rate": 2.8717349673701472e-05, "loss": 3.5395, "step": 1299968 }, { "epoch": 0.0, "learning_rate": 2.8708963726190952e-05, "loss": 3.5161, "step": 1300480 }, { "epoch": 0.0, "learning_rate": 2.8700577778680432e-05, "loss": 3.5171, "step": 1300992 }, { "epoch": 0.0, "learning_rate": 2.869220820997364e-05, "loss": 3.5109, "step": 1301504 }, { "epoch": 0.0, "learning_rate": 2.868382226246312e-05, "loss": 3.5227, "step": 1302016 }, { "epoch": 0.0, "learning_rate": 2.86754363149526e-05, "loss": 3.5206, "step": 1302528 }, { "epoch": 0.0, "learning_rate": 2.8667050367442085e-05, "loss": 3.516, "step": 1303040 }, { "epoch": 0.0, "learning_rate": 2.8658680798735294e-05, "loss": 3.5189, "step": 1303552 }, { "epoch": 0.0, "learning_rate": 2.8650294851224774e-05, "loss": 3.5041, "step": 1304064 }, { "epoch": 0.0, "learning_rate": 2.8641908903714254e-05, "loss": 3.517, "step": 1304576 }, { "epoch": 0.0, "learning_rate": 2.8633522956203734e-05, "loss": 3.5096, "step": 1305088 }, { "epoch": 0.0, "learning_rate": 2.8625153387496946e-05, "loss": 3.5095, "step": 1305600 }, { "epoch": 0.0, "learning_rate": 2.8616767439986426e-05, "loss": 3.5124, "step": 1306112 }, { "epoch": 0.0, "learning_rate": 2.8608381492475906e-05, "loss": 3.5137, "step": 1306624 }, { "epoch": 0.0, "learning_rate": 2.8599995544965386e-05, "loss": 3.5155, "step": 1307136 }, { "epoch": 0.0, "learning_rate": 2.8591625976258595e-05, "loss": 3.5379, "step": 1307648 }, { "epoch": 0.0, "learning_rate": 2.8583240028748075e-05, "loss": 3.5142, "step": 1308160 }, { "epoch": 0.0, "learning_rate": 2.8574854081237555e-05, "loss": 3.5185, "step": 1308672 }, { "epoch": 0.0, "learning_rate": 2.856646813372704e-05, "loss": 3.5154, "step": 1309184 }, { "epoch": 0.0, "learning_rate": 2.8558098565020247e-05, "loss": 3.5248, "step": 1309696 }, { "epoch": 0.0, "learning_rate": 2.8549712617509727e-05, "loss": 3.517, "step": 1310208 }, { "epoch": 0.0, "learning_rate": 2.8541326669999207e-05, "loss": 3.5224, "step": 1310720 }, { "epoch": 0.0, "learning_rate": 2.8532940722488687e-05, "loss": 3.5127, "step": 1311232 }, { "epoch": 0.0, "learning_rate": 2.85245711537819e-05, "loss": 3.5174, "step": 1311744 }, { "epoch": 0.0, "learning_rate": 2.851618520627138e-05, "loss": 3.5082, "step": 1312256 }, { "epoch": 0.01, "learning_rate": 2.850779925876086e-05, "loss": 3.5171, "step": 1312768 }, { "epoch": 0.01, "learning_rate": 2.849941331125034e-05, "loss": 3.5214, "step": 1313280 }, { "epoch": 0.01, "learning_rate": 2.849104374254355e-05, "loss": 3.5182, "step": 1313792 }, { "epoch": 0.01, "learning_rate": 2.848265779503303e-05, "loss": 3.5238, "step": 1314304 }, { "epoch": 0.01, "learning_rate": 2.847427184752251e-05, "loss": 3.5187, "step": 1314816 }, { "epoch": 0.01, "learning_rate": 2.8465885900011992e-05, "loss": 3.5153, "step": 1315328 }, { "epoch": 0.01, "learning_rate": 2.84575163313052e-05, "loss": 3.525, "step": 1315840 }, { "epoch": 0.01, "learning_rate": 2.844913038379468e-05, "loss": 3.5108, "step": 1316352 }, { "epoch": 0.01, "learning_rate": 2.844076081508789e-05, "loss": 3.5118, "step": 1316864 }, { "epoch": 0.01, "learning_rate": 2.843237486757737e-05, "loss": 3.5019, "step": 1317376 }, { "epoch": 0.01, "learning_rate": 2.8423988920066853e-05, "loss": 3.5106, "step": 1317888 }, { "epoch": 0.01, "learning_rate": 2.8415602972556333e-05, "loss": 3.5105, "step": 1318400 }, { "epoch": 0.01, "learning_rate": 2.8407217025045813e-05, "loss": 3.5211, "step": 1318912 }, { "epoch": 0.01, "learning_rate": 2.8398831077535293e-05, "loss": 3.5157, "step": 1319424 }, { "epoch": 0.01, "learning_rate": 2.8390445130024773e-05, "loss": 3.5089, "step": 1319936 }, { "epoch": 0.01, "learning_rate": 2.8382059182514253e-05, "loss": 3.5168, "step": 1320448 }, { "epoch": 0.01, "learning_rate": 2.8373689613807462e-05, "loss": 3.5133, "step": 1320960 }, { "epoch": 0.01, "learning_rate": 2.8365303666296946e-05, "loss": 3.511, "step": 1321472 }, { "epoch": 0.01, "learning_rate": 2.8356917718786426e-05, "loss": 3.4987, "step": 1321984 }, { "epoch": 0.01, "learning_rate": 2.8348531771275906e-05, "loss": 3.5061, "step": 1322496 }, { "epoch": 0.01, "learning_rate": 2.8340162202569115e-05, "loss": 3.5238, "step": 1323008 }, { "epoch": 0.01, "learning_rate": 2.8331776255058595e-05, "loss": 3.5255, "step": 1323520 }, { "epoch": 0.01, "learning_rate": 2.8323390307548075e-05, "loss": 3.5085, "step": 1324032 }, { "epoch": 0.01, "learning_rate": 2.8315004360037555e-05, "loss": 3.5107, "step": 1324544 }, { "epoch": 0.01, "learning_rate": 2.8306634791330767e-05, "loss": 3.5158, "step": 1325056 }, { "epoch": 0.01, "learning_rate": 2.8298248843820247e-05, "loss": 3.5012, "step": 1325568 }, { "epoch": 0.01, "learning_rate": 2.8289862896309727e-05, "loss": 3.521, "step": 1326080 }, { "epoch": 0.01, "learning_rate": 2.8281476948799207e-05, "loss": 3.503, "step": 1326592 }, { "epoch": 0.01, "learning_rate": 2.8273107380092416e-05, "loss": 3.5256, "step": 1327104 }, { "epoch": 0.01, "learning_rate": 2.8264721432581896e-05, "loss": 3.5216, "step": 1327616 }, { "epoch": 0.01, "learning_rate": 2.825633548507138e-05, "loss": 3.5066, "step": 1328128 }, { "epoch": 0.01, "learning_rate": 2.824794953756086e-05, "loss": 3.5016, "step": 1328640 }, { "epoch": 0.01, "learning_rate": 2.823956359005034e-05, "loss": 3.5206, "step": 1329152 }, { "epoch": 0.01, "learning_rate": 2.823117764253982e-05, "loss": 3.4943, "step": 1329664 }, { "epoch": 0.01, "learning_rate": 2.82227916950293e-05, "loss": 3.501, "step": 1330176 }, { "epoch": 0.01, "learning_rate": 2.8214422126322508e-05, "loss": 3.5217, "step": 1330688 }, { "epoch": 0.01, "learning_rate": 2.8206036178811988e-05, "loss": 3.5143, "step": 1331200 }, { "epoch": 0.01, "learning_rate": 2.819765023130147e-05, "loss": 3.5071, "step": 1331712 }, { "epoch": 0.01, "learning_rate": 2.8189264283790945e-05, "loss": 3.497, "step": 1332224 }, { "epoch": 0.01, "learning_rate": 2.818089471508416e-05, "loss": 3.5083, "step": 1332736 }, { "epoch": 0.01, "learning_rate": 2.817250876757364e-05, "loss": 3.5021, "step": 1333248 }, { "epoch": 0.01, "learning_rate": 2.816412282006312e-05, "loss": 3.5157, "step": 1333760 }, { "epoch": 0.01, "learning_rate": 2.8155736872552597e-05, "loss": 3.5034, "step": 1334272 }, { "epoch": 0.01, "learning_rate": 2.8147367303845813e-05, "loss": 3.5172, "step": 1334784 }, { "epoch": 0.01, "learning_rate": 2.8138981356335293e-05, "loss": 3.5133, "step": 1335296 }, { "epoch": 0.01, "learning_rate": 2.8130595408824773e-05, "loss": 3.5208, "step": 1335808 }, { "epoch": 0.01, "learning_rate": 2.8122209461314246e-05, "loss": 3.5067, "step": 1336320 }, { "epoch": 0.01, "learning_rate": 2.8113839892607462e-05, "loss": 3.5116, "step": 1336832 }, { "epoch": 0.01, "learning_rate": 2.8105453945096942e-05, "loss": 3.5137, "step": 1337344 }, { "epoch": 0.01, "learning_rate": 2.809706799758642e-05, "loss": 3.5125, "step": 1337856 }, { "epoch": 0.01, "learning_rate": 2.80886820500759e-05, "loss": 3.513, "step": 1338368 }, { "epoch": 0.01, "learning_rate": 2.808029610256538e-05, "loss": 3.5102, "step": 1338880 }, { "epoch": 0.01, "learning_rate": 2.8071926533858594e-05, "loss": 3.5141, "step": 1339392 }, { "epoch": 0.01, "learning_rate": 2.806354058634807e-05, "loss": 3.5066, "step": 1339904 }, { "epoch": 0.01, "learning_rate": 2.805515463883755e-05, "loss": 3.4965, "step": 1340416 }, { "epoch": 0.01, "learning_rate": 2.804676869132703e-05, "loss": 3.5024, "step": 1340928 }, { "epoch": 0.01, "learning_rate": 2.803838274381651e-05, "loss": 3.513, "step": 1341440 }, { "epoch": 0.01, "learning_rate": 2.802999679630599e-05, "loss": 3.5138, "step": 1341952 }, { "epoch": 0.01, "learning_rate": 2.80216272275992e-05, "loss": 3.5062, "step": 1342464 }, { "epoch": 0.01, "learning_rate": 2.801324128008868e-05, "loss": 3.5107, "step": 1342976 }, { "epoch": 0.02, "learning_rate": 2.8004855332578163e-05, "loss": 3.5031, "step": 1343488 }, { "epoch": 0.02, "learning_rate": 2.7996469385067643e-05, "loss": 3.4994, "step": 1344000 }, { "epoch": 0.02, "learning_rate": 2.7988083437557123e-05, "loss": 3.5029, "step": 1344512 }, { "epoch": 0.02, "learning_rate": 2.7979713868850332e-05, "loss": 3.5118, "step": 1345024 }, { "epoch": 0.02, "learning_rate": 2.7971327921339812e-05, "loss": 3.5132, "step": 1345536 }, { "epoch": 0.02, "learning_rate": 2.7962941973829292e-05, "loss": 3.5182, "step": 1346048 }, { "epoch": 0.02, "learning_rate": 2.7954556026318772e-05, "loss": 3.513, "step": 1346560 }, { "epoch": 0.02, "learning_rate": 2.7946170078808255e-05, "loss": 3.5015, "step": 1347072 }, { "epoch": 0.02, "learning_rate": 2.7937784131297735e-05, "loss": 3.5093, "step": 1347584 }, { "epoch": 0.02, "learning_rate": 2.7929398183787215e-05, "loss": 3.512, "step": 1348096 }, { "epoch": 0.02, "learning_rate": 2.7921012236276695e-05, "loss": 3.5162, "step": 1348608 }, { "epoch": 0.02, "learning_rate": 2.7912642667569904e-05, "loss": 3.5189, "step": 1349120 }, { "epoch": 0.02, "learning_rate": 2.7904256720059384e-05, "loss": 3.5074, "step": 1349632 }, { "epoch": 0.02, "learning_rate": 2.7895870772548864e-05, "loss": 3.5005, "step": 1350144 }, { "epoch": 0.02, "learning_rate": 2.7887484825038347e-05, "loss": 3.5243, "step": 1350656 }, { "epoch": 0.02, "learning_rate": 2.7879115256331557e-05, "loss": 3.4975, "step": 1351168 }, { "epoch": 0.02, "learning_rate": 2.7870729308821036e-05, "loss": 3.5088, "step": 1351680 }, { "epoch": 0.02, "learning_rate": 2.7862343361310516e-05, "loss": 3.5085, "step": 1352192 }, { "epoch": 0.02, "learning_rate": 2.7853957413799996e-05, "loss": 3.5112, "step": 1352704 }, { "epoch": 0.02, "learning_rate": 2.784558784509321e-05, "loss": 3.4971, "step": 1353216 }, { "epoch": 0.02, "learning_rate": 2.783720189758269e-05, "loss": 3.5085, "step": 1353728 }, { "epoch": 0.02, "learning_rate": 2.782881595007217e-05, "loss": 3.5003, "step": 1354240 }, { "epoch": 0.02, "learning_rate": 2.782043000256165e-05, "loss": 3.5083, "step": 1354752 }, { "epoch": 0.02, "learning_rate": 2.7812060433854858e-05, "loss": 3.5092, "step": 1355264 }, { "epoch": 0.02, "learning_rate": 2.7803674486344338e-05, "loss": 3.5015, "step": 1355776 }, { "epoch": 0.02, "learning_rate": 2.7795288538833818e-05, "loss": 3.5183, "step": 1356288 }, { "epoch": 0.02, "learning_rate": 2.77869025913233e-05, "loss": 3.5235, "step": 1356800 }, { "epoch": 0.02, "learning_rate": 2.777853302261651e-05, "loss": 3.5147, "step": 1357312 }, { "epoch": 0.02, "learning_rate": 2.777014707510599e-05, "loss": 3.5093, "step": 1357824 }, { "epoch": 0.02, "learning_rate": 2.776176112759547e-05, "loss": 3.5045, "step": 1358336 }, { "epoch": 0.02, "learning_rate": 2.775337518008495e-05, "loss": 3.5038, "step": 1358848 }, { "epoch": 0.02, "learning_rate": 2.7745005611378163e-05, "loss": 3.5012, "step": 1359360 }, { "epoch": 0.02, "learning_rate": 2.7736619663867643e-05, "loss": 3.515, "step": 1359872 }, { "epoch": 0.02, "learning_rate": 2.7728233716357122e-05, "loss": 3.5025, "step": 1360384 }, { "epoch": 0.02, "learning_rate": 2.7719847768846602e-05, "loss": 3.5065, "step": 1360896 }, { "epoch": 0.02, "learning_rate": 2.771147820013981e-05, "loss": 3.5103, "step": 1361408 }, { "epoch": 0.02, "learning_rate": 2.770309225262929e-05, "loss": 3.5128, "step": 1361920 }, { "epoch": 0.02, "learning_rate": 2.769470630511877e-05, "loss": 3.5051, "step": 1362432 }, { "epoch": 0.02, "learning_rate": 2.768632035760825e-05, "loss": 3.5027, "step": 1362944 }, { "epoch": 0.02, "learning_rate": 2.7677950788901464e-05, "loss": 3.5085, "step": 1363456 }, { "epoch": 0.02, "learning_rate": 2.7669564841390944e-05, "loss": 3.5076, "step": 1363968 }, { "epoch": 0.02, "learning_rate": 2.7661178893880424e-05, "loss": 3.5204, "step": 1364480 }, { "epoch": 0.02, "learning_rate": 2.7652792946369904e-05, "loss": 3.5175, "step": 1364992 }, { "epoch": 0.02, "learning_rate": 2.7644423377663113e-05, "loss": 3.4997, "step": 1365504 }, { "epoch": 0.02, "learning_rate": 2.7636037430152596e-05, "loss": 3.5089, "step": 1366016 }, { "epoch": 0.02, "learning_rate": 2.7627651482642076e-05, "loss": 3.509, "step": 1366528 }, { "epoch": 0.02, "learning_rate": 2.761926553513155e-05, "loss": 3.5105, "step": 1367040 }, { "epoch": 0.02, "learning_rate": 2.7610895966424765e-05, "loss": 3.5083, "step": 1367552 }, { "epoch": 0.02, "learning_rate": 2.7602510018914245e-05, "loss": 3.5166, "step": 1368064 }, { "epoch": 0.02, "learning_rate": 2.7594124071403725e-05, "loss": 3.5077, "step": 1368576 }, { "epoch": 0.02, "learning_rate": 2.75857381238932e-05, "loss": 3.5249, "step": 1369088 }, { "epoch": 0.02, "learning_rate": 2.7577368555186418e-05, "loss": 3.5027, "step": 1369600 }, { "epoch": 0.02, "learning_rate": 2.7568982607675897e-05, "loss": 3.5135, "step": 1370112 }, { "epoch": 0.02, "learning_rate": 2.7560596660165377e-05, "loss": 3.5081, "step": 1370624 }, { "epoch": 0.02, "learning_rate": 2.7552210712654854e-05, "loss": 3.5013, "step": 1371136 }, { "epoch": 0.02, "learning_rate": 2.7543841143948066e-05, "loss": 3.5135, "step": 1371648 }, { "epoch": 0.02, "learning_rate": 2.753545519643755e-05, "loss": 3.5039, "step": 1372160 }, { "epoch": 0.02, "learning_rate": 2.7527069248927023e-05, "loss": 3.5065, "step": 1372672 }, { "epoch": 0.02, "learning_rate": 2.7518683301416503e-05, "loss": 3.5002, "step": 1373184 }, { "epoch": 0.02, "learning_rate": 2.7510297353905983e-05, "loss": 3.5041, "step": 1373696 }, { "epoch": 0.03, "eval_loss": 3.854726791381836, "eval_runtime": 302.1926, "eval_samples_per_second": 1262.741, "eval_steps_per_second": 39.462, "step": 1373750 }, { "epoch": 1.0, "learning_rate": 2.7501911406395463e-05, "loss": 3.5058, "step": 1374208 }, { "epoch": 1.0, "learning_rate": 2.7493525458884943e-05, "loss": 3.5042, "step": 1374720 }, { "epoch": 1.0, "learning_rate": 2.7485139511374426e-05, "loss": 3.5172, "step": 1375232 }, { "epoch": 1.0, "learning_rate": 2.7476769942667635e-05, "loss": 3.5078, "step": 1375744 }, { "epoch": 1.0, "learning_rate": 2.7468383995157115e-05, "loss": 3.5253, "step": 1376256 }, { "epoch": 1.0, "learning_rate": 2.7459998047646595e-05, "loss": 3.5032, "step": 1376768 }, { "epoch": 1.0, "learning_rate": 2.7451612100136075e-05, "loss": 3.5065, "step": 1377280 }, { "epoch": 1.0, "learning_rate": 2.7443242531429288e-05, "loss": 3.4919, "step": 1377792 }, { "epoch": 1.0, "learning_rate": 2.7434856583918768e-05, "loss": 3.5101, "step": 1378304 }, { "epoch": 1.0, "learning_rate": 2.7426470636408248e-05, "loss": 3.5061, "step": 1378816 }, { "epoch": 1.0, "learning_rate": 2.7418101067701457e-05, "loss": 3.4998, "step": 1379328 }, { "epoch": 1.0, "learning_rate": 2.7409715120190937e-05, "loss": 3.5138, "step": 1379840 }, { "epoch": 1.0, "learning_rate": 2.7401329172680417e-05, "loss": 3.4902, "step": 1380352 }, { "epoch": 1.0, "learning_rate": 2.7392943225169897e-05, "loss": 3.5067, "step": 1380864 }, { "epoch": 1.0, "learning_rate": 2.738457365646311e-05, "loss": 3.4901, "step": 1381376 }, { "epoch": 1.0, "learning_rate": 2.737618770895259e-05, "loss": 3.4976, "step": 1381888 }, { "epoch": 1.0, "learning_rate": 2.736780176144207e-05, "loss": 3.4984, "step": 1382400 }, { "epoch": 1.0, "learning_rate": 2.735941581393155e-05, "loss": 3.5021, "step": 1382912 }, { "epoch": 1.0, "learning_rate": 2.7351046245224758e-05, "loss": 3.499, "step": 1383424 }, { "epoch": 1.0, "learning_rate": 2.734266029771424e-05, "loss": 3.5234, "step": 1383936 }, { "epoch": 1.0, "learning_rate": 2.733427435020372e-05, "loss": 3.5011, "step": 1384448 }, { "epoch": 1.0, "learning_rate": 2.73258884026932e-05, "loss": 3.508, "step": 1384960 }, { "epoch": 1.0, "learning_rate": 2.731751883398641e-05, "loss": 3.5011, "step": 1385472 }, { "epoch": 1.0, "learning_rate": 2.730913288647589e-05, "loss": 3.5137, "step": 1385984 }, { "epoch": 1.0, "learning_rate": 2.730074693896537e-05, "loss": 3.5014, "step": 1386496 }, { "epoch": 1.0, "learning_rate": 2.7292377370258583e-05, "loss": 3.5105, "step": 1387008 }, { "epoch": 1.0, "learning_rate": 2.7283991422748063e-05, "loss": 3.4949, "step": 1387520 }, { "epoch": 1.0, "learning_rate": 2.7275605475237543e-05, "loss": 3.5047, "step": 1388032 }, { "epoch": 1.0, "learning_rate": 2.7267219527727023e-05, "loss": 3.4952, "step": 1388544 }, { "epoch": 1.01, "learning_rate": 2.7258833580216503e-05, "loss": 3.5065, "step": 1389056 }, { "epoch": 1.01, "learning_rate": 2.7250447632705982e-05, "loss": 3.5041, "step": 1389568 }, { "epoch": 1.01, "learning_rate": 2.7242078063999195e-05, "loss": 3.5038, "step": 1390080 }, { "epoch": 1.01, "learning_rate": 2.7233692116488675e-05, "loss": 3.5156, "step": 1390592 }, { "epoch": 1.01, "learning_rate": 2.7225306168978155e-05, "loss": 3.5044, "step": 1391104 }, { "epoch": 1.01, "learning_rate": 2.7216920221467635e-05, "loss": 3.5011, "step": 1391616 }, { "epoch": 1.01, "learning_rate": 2.7208534273957115e-05, "loss": 3.5114, "step": 1392128 }, { "epoch": 1.01, "learning_rate": 2.7200148326446595e-05, "loss": 3.5008, "step": 1392640 }, { "epoch": 1.01, "learning_rate": 2.7191778757739804e-05, "loss": 3.4952, "step": 1393152 }, { "epoch": 1.01, "learning_rate": 2.7183392810229287e-05, "loss": 3.4899, "step": 1393664 }, { "epoch": 1.01, "learning_rate": 2.7175006862718767e-05, "loss": 3.4958, "step": 1394176 }, { "epoch": 1.01, "learning_rate": 2.7166620915208247e-05, "loss": 3.496, "step": 1394688 }, { "epoch": 1.01, "learning_rate": 2.7158234967697727e-05, "loss": 3.5063, "step": 1395200 }, { "epoch": 1.01, "learning_rate": 2.7149849020187207e-05, "loss": 3.5047, "step": 1395712 }, { "epoch": 1.01, "learning_rate": 2.714146307267668e-05, "loss": 3.4937, "step": 1396224 }, { "epoch": 1.01, "learning_rate": 2.7133077125166164e-05, "loss": 3.5064, "step": 1396736 }, { "epoch": 1.01, "learning_rate": 2.712470755645938e-05, "loss": 3.4999, "step": 1397248 }, { "epoch": 1.01, "learning_rate": 2.711632160894886e-05, "loss": 3.4957, "step": 1397760 }, { "epoch": 1.01, "learning_rate": 2.7107935661438333e-05, "loss": 3.4892, "step": 1398272 }, { "epoch": 1.01, "learning_rate": 2.7099549713927812e-05, "loss": 3.4877, "step": 1398784 }, { "epoch": 1.01, "learning_rate": 2.709118014522103e-05, "loss": 3.511, "step": 1399296 }, { "epoch": 1.01, "learning_rate": 2.708279419771051e-05, "loss": 3.5115, "step": 1399808 }, { "epoch": 1.01, "learning_rate": 2.7074408250199985e-05, "loss": 3.4981, "step": 1400320 }, { "epoch": 1.01, "learning_rate": 2.7066022302689465e-05, "loss": 3.4968, "step": 1400832 }, { "epoch": 1.01, "learning_rate": 2.705765273398268e-05, "loss": 3.5044, "step": 1401344 }, { "epoch": 1.01, "learning_rate": 2.7049266786472154e-05, "loss": 3.4856, "step": 1401856 }, { "epoch": 1.01, "learning_rate": 2.7040880838961634e-05, "loss": 3.5044, "step": 1402368 }, { "epoch": 1.01, "learning_rate": 2.7032494891451117e-05, "loss": 3.4908, "step": 1402880 }, { "epoch": 1.01, "learning_rate": 2.7024125322744333e-05, "loss": 3.508, "step": 1403392 }, { "epoch": 1.01, "learning_rate": 2.7015739375233806e-05, "loss": 3.5114, "step": 1403904 }, { "epoch": 1.01, "learning_rate": 2.7007353427723286e-05, "loss": 3.4943, "step": 1404416 }, { "epoch": 1.01, "learning_rate": 2.6998967480212766e-05, "loss": 3.4873, "step": 1404928 }, { "epoch": 1.01, "learning_rate": 2.6990581532702246e-05, "loss": 3.5092, "step": 1405440 }, { "epoch": 1.01, "learning_rate": 2.6982195585191726e-05, "loss": 3.4818, "step": 1405952 }, { "epoch": 1.01, "learning_rate": 2.6973809637681206e-05, "loss": 3.4931, "step": 1406464 }, { "epoch": 1.01, "learning_rate": 2.696544006897442e-05, "loss": 3.5043, "step": 1406976 }, { "epoch": 1.01, "learning_rate": 2.69570541214639e-05, "loss": 3.5028, "step": 1407488 }, { "epoch": 1.01, "learning_rate": 2.694866817395338e-05, "loss": 3.4929, "step": 1408000 }, { "epoch": 1.01, "learning_rate": 2.694028222644286e-05, "loss": 3.4843, "step": 1408512 }, { "epoch": 1.01, "learning_rate": 2.693191265773607e-05, "loss": 3.4911, "step": 1409024 }, { "epoch": 1.01, "learning_rate": 2.692352671022555e-05, "loss": 3.4892, "step": 1409536 }, { "epoch": 1.01, "learning_rate": 2.691514076271503e-05, "loss": 3.5032, "step": 1410048 }, { "epoch": 1.01, "learning_rate": 2.690675481520451e-05, "loss": 3.491, "step": 1410560 }, { "epoch": 1.01, "learning_rate": 2.689838524649772e-05, "loss": 3.5039, "step": 1411072 }, { "epoch": 1.01, "learning_rate": 2.68899992989872e-05, "loss": 3.502, "step": 1411584 }, { "epoch": 1.01, "learning_rate": 2.688161335147668e-05, "loss": 3.5046, "step": 1412096 }, { "epoch": 1.01, "learning_rate": 2.687322740396616e-05, "loss": 3.495, "step": 1412608 }, { "epoch": 1.01, "learning_rate": 2.6864857835259372e-05, "loss": 3.5009, "step": 1413120 }, { "epoch": 1.01, "learning_rate": 2.6856471887748852e-05, "loss": 3.5016, "step": 1413632 }, { "epoch": 1.01, "learning_rate": 2.6848085940238332e-05, "loss": 3.4953, "step": 1414144 }, { "epoch": 1.01, "learning_rate": 2.6839699992727812e-05, "loss": 3.5017, "step": 1414656 }, { "epoch": 1.01, "learning_rate": 2.6831314045217292e-05, "loss": 3.4984, "step": 1415168 }, { "epoch": 1.01, "learning_rate": 2.6822944476510504e-05, "loss": 3.4971, "step": 1415680 }, { "epoch": 1.01, "learning_rate": 2.6814558528999984e-05, "loss": 3.4946, "step": 1416192 }, { "epoch": 1.01, "learning_rate": 2.6806172581489464e-05, "loss": 3.4825, "step": 1416704 }, { "epoch": 1.01, "learning_rate": 2.6797786633978944e-05, "loss": 3.4932, "step": 1417216 }, { "epoch": 1.01, "learning_rate": 2.6789400686468424e-05, "loss": 3.4939, "step": 1417728 }, { "epoch": 1.01, "learning_rate": 2.6781014738957904e-05, "loss": 3.5005, "step": 1418240 }, { "epoch": 1.01, "learning_rate": 2.6772645170251113e-05, "loss": 3.4931, "step": 1418752 }, { "epoch": 1.01, "learning_rate": 2.6764259222740597e-05, "loss": 3.4979, "step": 1419264 }, { "epoch": 1.02, "learning_rate": 2.6755873275230077e-05, "loss": 3.4916, "step": 1419776 }, { "epoch": 1.02, "learning_rate": 2.6747487327719557e-05, "loss": 3.4865, "step": 1420288 }, { "epoch": 1.02, "learning_rate": 2.6739101380209037e-05, "loss": 3.4883, "step": 1420800 }, { "epoch": 1.02, "learning_rate": 2.6730715432698517e-05, "loss": 3.4949, "step": 1421312 }, { "epoch": 1.02, "learning_rate": 2.6722345863991726e-05, "loss": 3.5042, "step": 1421824 }, { "epoch": 1.02, "learning_rate": 2.6713959916481206e-05, "loss": 3.5051, "step": 1422336 }, { "epoch": 1.02, "learning_rate": 2.670557396897069e-05, "loss": 3.4962, "step": 1422848 }, { "epoch": 1.02, "learning_rate": 2.669718802146017e-05, "loss": 3.4915, "step": 1423360 }, { "epoch": 1.02, "learning_rate": 2.6688802073949642e-05, "loss": 3.4943, "step": 1423872 }, { "epoch": 1.02, "learning_rate": 2.6680416126439122e-05, "loss": 3.4962, "step": 1424384 }, { "epoch": 1.02, "learning_rate": 2.6672030178928602e-05, "loss": 3.5065, "step": 1424896 }, { "epoch": 1.02, "learning_rate": 2.6663660610221814e-05, "loss": 3.507, "step": 1425408 }, { "epoch": 1.02, "learning_rate": 2.6655274662711294e-05, "loss": 3.4933, "step": 1425920 }, { "epoch": 1.02, "learning_rate": 2.6646888715200774e-05, "loss": 3.4856, "step": 1426432 }, { "epoch": 1.02, "learning_rate": 2.6638502767690254e-05, "loss": 3.5099, "step": 1426944 }, { "epoch": 1.02, "learning_rate": 2.6630133198983463e-05, "loss": 3.4863, "step": 1427456 }, { "epoch": 1.02, "learning_rate": 2.6621747251472943e-05, "loss": 3.4986, "step": 1427968 }, { "epoch": 1.02, "learning_rate": 2.6613361303962427e-05, "loss": 3.4931, "step": 1428480 }, { "epoch": 1.02, "learning_rate": 2.6604975356451907e-05, "loss": 3.495, "step": 1428992 }, { "epoch": 1.02, "learning_rate": 2.6596605787745116e-05, "loss": 3.4889, "step": 1429504 }, { "epoch": 1.02, "learning_rate": 2.6588219840234596e-05, "loss": 3.5008, "step": 1430016 }, { "epoch": 1.02, "learning_rate": 2.6579833892724076e-05, "loss": 3.4846, "step": 1430528 }, { "epoch": 1.02, "learning_rate": 2.6571447945213556e-05, "loss": 3.4917, "step": 1431040 }, { "epoch": 1.02, "learning_rate": 2.6563078376506768e-05, "loss": 3.5017, "step": 1431552 }, { "epoch": 1.02, "learning_rate": 2.6554692428996248e-05, "loss": 3.4872, "step": 1432064 }, { "epoch": 1.02, "learning_rate": 2.6546306481485728e-05, "loss": 3.5084, "step": 1432576 }, { "epoch": 1.02, "learning_rate": 2.6537920533975208e-05, "loss": 3.5093, "step": 1433088 }, { "epoch": 1.02, "learning_rate": 2.6529550965268417e-05, "loss": 3.502, "step": 1433600 }, { "epoch": 1.02, "learning_rate": 2.6521165017757897e-05, "loss": 3.4951, "step": 1434112 }, { "epoch": 1.02, "learning_rate": 2.651277907024738e-05, "loss": 3.4938, "step": 1434624 }, { "epoch": 1.02, "learning_rate": 2.650439312273686e-05, "loss": 3.4927, "step": 1435136 }, { "epoch": 1.02, "learning_rate": 2.649602355403007e-05, "loss": 3.4842, "step": 1435648 }, { "epoch": 1.02, "learning_rate": 2.648763760651955e-05, "loss": 3.5043, "step": 1436160 }, { "epoch": 1.02, "learning_rate": 2.647925165900903e-05, "loss": 3.4889, "step": 1436672 }, { "epoch": 1.02, "learning_rate": 2.647086571149851e-05, "loss": 3.4965, "step": 1437184 }, { "epoch": 1.02, "learning_rate": 2.6462496142791722e-05, "loss": 3.4988, "step": 1437696 }, { "epoch": 1.02, "learning_rate": 2.6454110195281202e-05, "loss": 3.4974, "step": 1438208 }, { "epoch": 1.02, "learning_rate": 2.6445724247770682e-05, "loss": 3.4914, "step": 1438720 }, { "epoch": 1.02, "learning_rate": 2.643733830026016e-05, "loss": 3.4905, "step": 1439232 }, { "epoch": 1.02, "learning_rate": 2.642896873155337e-05, "loss": 3.496, "step": 1439744 }, { "epoch": 1.02, "learning_rate": 2.642058278404285e-05, "loss": 3.4959, "step": 1440256 }, { "epoch": 1.02, "learning_rate": 2.6412196836532334e-05, "loss": 3.5007, "step": 1440768 }, { "epoch": 1.02, "learning_rate": 2.6403810889021814e-05, "loss": 3.5079, "step": 1441280 }, { "epoch": 1.02, "learning_rate": 2.6395441320315023e-05, "loss": 3.4861, "step": 1441792 }, { "epoch": 1.02, "learning_rate": 2.6387055372804503e-05, "loss": 3.4954, "step": 1442304 }, { "epoch": 1.02, "learning_rate": 2.6378669425293983e-05, "loss": 3.4983, "step": 1442816 }, { "epoch": 1.02, "learning_rate": 2.6370283477783463e-05, "loss": 3.4968, "step": 1443328 }, { "epoch": 1.02, "learning_rate": 2.6361913909076675e-05, "loss": 3.4935, "step": 1443840 }, { "epoch": 1.02, "learning_rate": 2.6353527961566155e-05, "loss": 3.5056, "step": 1444352 }, { "epoch": 1.02, "learning_rate": 2.6345142014055635e-05, "loss": 3.4965, "step": 1444864 }, { "epoch": 1.02, "learning_rate": 2.6336756066545115e-05, "loss": 3.512, "step": 1445376 }, { "epoch": 1.02, "learning_rate": 2.6328386497838324e-05, "loss": 3.4935, "step": 1445888 }, { "epoch": 1.02, "learning_rate": 2.6320000550327804e-05, "loss": 3.5004, "step": 1446400 }, { "epoch": 1.02, "learning_rate": 2.6311614602817288e-05, "loss": 3.4959, "step": 1446912 }, { "epoch": 1.02, "learning_rate": 2.6303228655306768e-05, "loss": 3.4896, "step": 1447424 }, { "epoch": 1.02, "learning_rate": 2.6294875465403706e-05, "loss": 3.4968, "step": 1447936 }, { "epoch": 1.02, "learning_rate": 2.6286489517893186e-05, "loss": 3.4933, "step": 1448448 }, { "epoch": 1.02, "learning_rate": 2.6278103570382666e-05, "loss": 3.492, "step": 1448960 }, { "epoch": 1.02, "learning_rate": 2.626971762287215e-05, "loss": 3.4896, "step": 1449472 }, { "epoch": 1.02, "learning_rate": 2.626133167536163e-05, "loss": 3.4888, "step": 1449984 }, { "epoch": 1.03, "eval_loss": 3.855644464492798, "eval_runtime": 301.9558, "eval_samples_per_second": 1263.731, "eval_steps_per_second": 39.493, "step": 1450070 }, { "epoch": 0.0, "learning_rate": 2.625294572785111e-05, "loss": 3.4936, "step": 1450496 }, { "epoch": 0.0, "learning_rate": 2.624455978034059e-05, "loss": 3.4927, "step": 1451008 }, { "epoch": 0.0, "learning_rate": 2.623617383283007e-05, "loss": 3.5047, "step": 1451520 }, { "epoch": 0.0, "learning_rate": 2.622778788531955e-05, "loss": 3.4925, "step": 1452032 }, { "epoch": 0.0, "learning_rate": 2.6219418316612758e-05, "loss": 3.5185, "step": 1452544 }, { "epoch": 0.0, "learning_rate": 2.621103236910224e-05, "loss": 3.49, "step": 1453056 }, { "epoch": 0.0, "learning_rate": 2.620264642159172e-05, "loss": 3.4914, "step": 1453568 }, { "epoch": 0.0, "learning_rate": 2.619427685288493e-05, "loss": 3.4805, "step": 1454080 }, { "epoch": 0.0, "learning_rate": 2.618589090537441e-05, "loss": 3.4956, "step": 1454592 }, { "epoch": 0.0, "learning_rate": 2.617750495786389e-05, "loss": 3.4953, "step": 1455104 }, { "epoch": 0.0, "learning_rate": 2.616911901035337e-05, "loss": 3.4871, "step": 1455616 }, { "epoch": 0.0, "learning_rate": 2.6160749441646583e-05, "loss": 3.4976, "step": 1456128 }, { "epoch": 0.0, "learning_rate": 2.6152363494136063e-05, "loss": 3.4791, "step": 1456640 }, { "epoch": 0.0, "learning_rate": 2.6143977546625543e-05, "loss": 3.4914, "step": 1457152 }, { "epoch": 0.0, "learning_rate": 2.6135591599115023e-05, "loss": 3.4846, "step": 1457664 }, { "epoch": 0.0, "learning_rate": 2.6127222030408232e-05, "loss": 3.4819, "step": 1458176 }, { "epoch": 0.0, "learning_rate": 2.6118836082897712e-05, "loss": 3.4821, "step": 1458688 }, { "epoch": 0.0, "learning_rate": 2.611045013538719e-05, "loss": 3.4894, "step": 1459200 }, { "epoch": 0.0, "learning_rate": 2.6102064187876675e-05, "loss": 3.4911, "step": 1459712 }, { "epoch": 0.0, "learning_rate": 2.6093694619169884e-05, "loss": 3.5089, "step": 1460224 }, { "epoch": 0.0, "learning_rate": 2.6085308671659364e-05, "loss": 3.4892, "step": 1460736 }, { "epoch": 0.0, "learning_rate": 2.6076922724148844e-05, "loss": 3.4984, "step": 1461248 }, { "epoch": 0.0, "learning_rate": 2.6068536776638324e-05, "loss": 3.4871, "step": 1461760 }, { "epoch": 0.0, "learning_rate": 2.6060167207931536e-05, "loss": 3.4993, "step": 1462272 }, { "epoch": 0.0, "learning_rate": 2.6051781260421016e-05, "loss": 3.4885, "step": 1462784 }, { "epoch": 0.0, "learning_rate": 2.6043411691714226e-05, "loss": 3.4971, "step": 1463296 }, { "epoch": 0.0, "learning_rate": 2.6035025744203705e-05, "loss": 3.4913, "step": 1463808 }, { "epoch": 0.0, "learning_rate": 2.6026639796693185e-05, "loss": 3.4872, "step": 1464320 }, { "epoch": 0.0, "learning_rate": 2.6018253849182665e-05, "loss": 3.4791, "step": 1464832 }, { "epoch": 0.01, "learning_rate": 2.6009867901672145e-05, "loss": 3.4929, "step": 1465344 }, { "epoch": 0.01, "learning_rate": 2.600148195416163e-05, "loss": 3.4988, "step": 1465856 }, { "epoch": 0.01, "learning_rate": 2.5993112385454838e-05, "loss": 3.4909, "step": 1466368 }, { "epoch": 0.01, "learning_rate": 2.5984726437944318e-05, "loss": 3.505, "step": 1466880 }, { "epoch": 0.01, "learning_rate": 2.5976340490433798e-05, "loss": 3.4936, "step": 1467392 }, { "epoch": 0.01, "learning_rate": 2.5967954542923278e-05, "loss": 3.4858, "step": 1467904 }, { "epoch": 0.01, "learning_rate": 2.5959568595412758e-05, "loss": 3.4981, "step": 1468416 }, { "epoch": 0.01, "learning_rate": 2.5951182647902238e-05, "loss": 3.4905, "step": 1468928 }, { "epoch": 0.01, "learning_rate": 2.594281307919545e-05, "loss": 3.4824, "step": 1469440 }, { "epoch": 0.01, "learning_rate": 2.593442713168493e-05, "loss": 3.4794, "step": 1469952 }, { "epoch": 0.01, "learning_rate": 2.592604118417441e-05, "loss": 3.4818, "step": 1470464 }, { "epoch": 0.01, "learning_rate": 2.591765523666389e-05, "loss": 3.4889, "step": 1470976 }, { "epoch": 0.01, "learning_rate": 2.5909269289153366e-05, "loss": 3.4895, "step": 1471488 }, { "epoch": 0.01, "learning_rate": 2.5900883341642846e-05, "loss": 3.4917, "step": 1472000 }, { "epoch": 0.01, "learning_rate": 2.5892497394132326e-05, "loss": 3.4785, "step": 1472512 }, { "epoch": 0.01, "learning_rate": 2.5884111446621806e-05, "loss": 3.4972, "step": 1473024 }, { "epoch": 0.01, "learning_rate": 2.5875741877915015e-05, "loss": 3.4851, "step": 1473536 }, { "epoch": 0.01, "learning_rate": 2.5867355930404495e-05, "loss": 3.4862, "step": 1474048 }, { "epoch": 0.01, "learning_rate": 2.5858969982893975e-05, "loss": 3.4755, "step": 1474560 }, { "epoch": 0.01, "learning_rate": 2.585058403538346e-05, "loss": 3.4706, "step": 1475072 }, { "epoch": 0.01, "learning_rate": 2.5842214466676668e-05, "loss": 3.5025, "step": 1475584 }, { "epoch": 0.01, "learning_rate": 2.5833828519166148e-05, "loss": 3.497, "step": 1476096 }, { "epoch": 0.01, "learning_rate": 2.5825442571655628e-05, "loss": 3.4879, "step": 1476608 }, { "epoch": 0.01, "learning_rate": 2.5817056624145108e-05, "loss": 3.4879, "step": 1477120 }, { "epoch": 0.01, "learning_rate": 2.580868705543832e-05, "loss": 3.4863, "step": 1477632 }, { "epoch": 0.01, "learning_rate": 2.58003011079278e-05, "loss": 3.4744, "step": 1478144 }, { "epoch": 0.01, "learning_rate": 2.579191516041728e-05, "loss": 3.4909, "step": 1478656 }, { "epoch": 0.01, "learning_rate": 2.578352921290676e-05, "loss": 3.4811, "step": 1479168 }, { "epoch": 0.01, "learning_rate": 2.577515964419997e-05, "loss": 3.4892, "step": 1479680 }, { "epoch": 0.01, "learning_rate": 2.576677369668945e-05, "loss": 3.5041, "step": 1480192 }, { "epoch": 0.01, "learning_rate": 2.575838774917893e-05, "loss": 3.4828, "step": 1480704 }, { "epoch": 0.01, "learning_rate": 2.5750001801668412e-05, "loss": 3.474, "step": 1481216 }, { "epoch": 0.01, "learning_rate": 2.5741615854157892e-05, "loss": 3.4995, "step": 1481728 }, { "epoch": 0.01, "learning_rate": 2.5733229906647372e-05, "loss": 3.4691, "step": 1482240 }, { "epoch": 0.01, "learning_rate": 2.5724843959136852e-05, "loss": 3.4762, "step": 1482752 }, { "epoch": 0.01, "learning_rate": 2.5716458011626332e-05, "loss": 3.4954, "step": 1483264 }, { "epoch": 0.01, "learning_rate": 2.570808844291954e-05, "loss": 3.491, "step": 1483776 }, { "epoch": 0.01, "learning_rate": 2.569970249540902e-05, "loss": 3.4836, "step": 1484288 }, { "epoch": 0.01, "learning_rate": 2.5691316547898505e-05, "loss": 3.4754, "step": 1484800 }, { "epoch": 0.01, "learning_rate": 2.5682946979191714e-05, "loss": 3.4728, "step": 1485312 }, { "epoch": 0.01, "learning_rate": 2.5674561031681194e-05, "loss": 3.4741, "step": 1485824 }, { "epoch": 0.01, "learning_rate": 2.5666175084170674e-05, "loss": 3.4955, "step": 1486336 }, { "epoch": 0.01, "learning_rate": 2.5657789136660154e-05, "loss": 3.4761, "step": 1486848 }, { "epoch": 0.01, "learning_rate": 2.5649419567953366e-05, "loss": 3.4929, "step": 1487360 }, { "epoch": 0.01, "learning_rate": 2.5641033620442846e-05, "loss": 3.4889, "step": 1487872 }, { "epoch": 0.01, "learning_rate": 2.5632647672932326e-05, "loss": 3.4956, "step": 1488384 }, { "epoch": 0.01, "learning_rate": 2.5624261725421806e-05, "loss": 3.4824, "step": 1488896 }, { "epoch": 0.01, "learning_rate": 2.5615892156715015e-05, "loss": 3.4828, "step": 1489408 }, { "epoch": 0.01, "learning_rate": 2.5607506209204495e-05, "loss": 3.4905, "step": 1489920 }, { "epoch": 0.01, "learning_rate": 2.5599120261693975e-05, "loss": 3.4836, "step": 1490432 }, { "epoch": 0.01, "learning_rate": 2.5590734314183458e-05, "loss": 3.4915, "step": 1490944 }, { "epoch": 0.01, "learning_rate": 2.5582348366672938e-05, "loss": 3.4862, "step": 1491456 }, { "epoch": 0.01, "learning_rate": 2.5573978797966147e-05, "loss": 3.4827, "step": 1491968 }, { "epoch": 0.01, "learning_rate": 2.5565592850455627e-05, "loss": 3.4853, "step": 1492480 }, { "epoch": 0.01, "learning_rate": 2.5557206902945107e-05, "loss": 3.4682, "step": 1492992 }, { "epoch": 0.01, "learning_rate": 2.5548820955434587e-05, "loss": 3.4822, "step": 1493504 }, { "epoch": 0.01, "learning_rate": 2.5540435007924067e-05, "loss": 3.4853, "step": 1494016 }, { "epoch": 0.01, "learning_rate": 2.5532049060413547e-05, "loss": 3.4899, "step": 1494528 }, { "epoch": 0.01, "learning_rate": 2.552367949170676e-05, "loss": 3.4772, "step": 1495040 }, { "epoch": 0.01, "learning_rate": 2.551529354419624e-05, "loss": 3.4858, "step": 1495552 }, { "epoch": 0.02, "learning_rate": 2.550690759668572e-05, "loss": 3.4779, "step": 1496064 }, { "epoch": 0.02, "learning_rate": 2.54985216491752e-05, "loss": 3.478, "step": 1496576 }, { "epoch": 0.02, "learning_rate": 2.5490135701664676e-05, "loss": 3.474, "step": 1497088 }, { "epoch": 0.02, "learning_rate": 2.5481749754154156e-05, "loss": 3.4826, "step": 1497600 }, { "epoch": 0.02, "learning_rate": 2.5473380185447372e-05, "loss": 3.4944, "step": 1498112 }, { "epoch": 0.02, "learning_rate": 2.5464994237936852e-05, "loss": 3.4943, "step": 1498624 }, { "epoch": 0.02, "learning_rate": 2.5456608290426325e-05, "loss": 3.4854, "step": 1499136 }, { "epoch": 0.02, "learning_rate": 2.5448222342915805e-05, "loss": 3.4729, "step": 1499648 }, { "epoch": 0.02, "learning_rate": 2.5439836395405285e-05, "loss": 3.4832, "step": 1500160 }, { "epoch": 0.02, "learning_rate": 2.5431450447894768e-05, "loss": 3.4882, "step": 1500672 }, { "epoch": 0.02, "learning_rate": 2.5423064500384248e-05, "loss": 3.4888, "step": 1501184 }, { "epoch": 0.02, "learning_rate": 2.5414694931677457e-05, "loss": 3.4957, "step": 1501696 }, { "epoch": 0.02, "learning_rate": 2.5406308984166937e-05, "loss": 3.4822, "step": 1502208 }, { "epoch": 0.02, "learning_rate": 2.5397923036656417e-05, "loss": 3.4742, "step": 1502720 }, { "epoch": 0.02, "learning_rate": 2.5389537089145897e-05, "loss": 3.5001, "step": 1503232 }, { "epoch": 0.02, "learning_rate": 2.538116752043911e-05, "loss": 3.4724, "step": 1503744 }, { "epoch": 0.02, "learning_rate": 2.537278157292859e-05, "loss": 3.486, "step": 1504256 }, { "epoch": 0.02, "learning_rate": 2.536439562541807e-05, "loss": 3.4753, "step": 1504768 }, { "epoch": 0.02, "learning_rate": 2.535600967790755e-05, "loss": 3.4883, "step": 1505280 }, { "epoch": 0.02, "learning_rate": 2.534764010920076e-05, "loss": 3.4752, "step": 1505792 }, { "epoch": 0.02, "learning_rate": 2.533925416169024e-05, "loss": 3.4861, "step": 1506304 }, { "epoch": 0.02, "learning_rate": 2.5330868214179722e-05, "loss": 3.4772, "step": 1506816 }, { "epoch": 0.02, "learning_rate": 2.5322482266669202e-05, "loss": 3.4762, "step": 1507328 }, { "epoch": 0.02, "learning_rate": 2.531411269796241e-05, "loss": 3.4851, "step": 1507840 }, { "epoch": 0.02, "learning_rate": 2.530572675045189e-05, "loss": 3.4744, "step": 1508352 }, { "epoch": 0.02, "learning_rate": 2.529734080294137e-05, "loss": 3.4924, "step": 1508864 }, { "epoch": 0.02, "learning_rate": 2.528895485543085e-05, "loss": 3.4982, "step": 1509376 }, { "epoch": 0.02, "learning_rate": 2.5280585286724063e-05, "loss": 3.4911, "step": 1509888 }, { "epoch": 0.02, "learning_rate": 2.5272199339213543e-05, "loss": 3.4819, "step": 1510400 }, { "epoch": 0.02, "learning_rate": 2.5263813391703023e-05, "loss": 3.4803, "step": 1510912 }, { "epoch": 0.02, "learning_rate": 2.5255427444192503e-05, "loss": 3.4777, "step": 1511424 }, { "epoch": 0.02, "learning_rate": 2.5247057875485712e-05, "loss": 3.4769, "step": 1511936 }, { "epoch": 0.02, "learning_rate": 2.5238671927975192e-05, "loss": 3.4897, "step": 1512448 }, { "epoch": 0.02, "learning_rate": 2.5230285980464676e-05, "loss": 3.4738, "step": 1512960 }, { "epoch": 0.02, "learning_rate": 2.5221900032954155e-05, "loss": 3.4854, "step": 1513472 }, { "epoch": 0.02, "learning_rate": 2.5213546843051094e-05, "loss": 3.4824, "step": 1513984 }, { "epoch": 0.02, "learning_rate": 2.5205160895540574e-05, "loss": 3.4879, "step": 1514496 }, { "epoch": 0.02, "learning_rate": 2.5196774948030054e-05, "loss": 3.482, "step": 1515008 }, { "epoch": 0.02, "learning_rate": 2.5188389000519537e-05, "loss": 3.48, "step": 1515520 }, { "epoch": 0.02, "learning_rate": 2.5180003053009017e-05, "loss": 3.4809, "step": 1516032 }, { "epoch": 0.02, "learning_rate": 2.5171617105498497e-05, "loss": 3.4864, "step": 1516544 }, { "epoch": 0.02, "learning_rate": 2.5163231157987977e-05, "loss": 3.4856, "step": 1517056 }, { "epoch": 0.02, "learning_rate": 2.5154845210477457e-05, "loss": 3.4966, "step": 1517568 }, { "epoch": 0.02, "learning_rate": 2.5146475641770666e-05, "loss": 3.4715, "step": 1518080 }, { "epoch": 0.02, "learning_rate": 2.5138089694260146e-05, "loss": 3.4857, "step": 1518592 }, { "epoch": 0.02, "learning_rate": 2.512970374674963e-05, "loss": 3.4845, "step": 1519104 }, { "epoch": 0.02, "learning_rate": 2.512131779923911e-05, "loss": 3.4825, "step": 1519616 }, { "epoch": 0.02, "learning_rate": 2.5112948230532318e-05, "loss": 3.4827, "step": 1520128 }, { "epoch": 0.02, "learning_rate": 2.5104562283021798e-05, "loss": 3.493, "step": 1520640 }, { "epoch": 0.02, "learning_rate": 2.5096176335511278e-05, "loss": 3.4848, "step": 1521152 }, { "epoch": 0.02, "learning_rate": 2.5087790388000758e-05, "loss": 3.5006, "step": 1521664 }, { "epoch": 0.02, "learning_rate": 2.507942081929397e-05, "loss": 3.4795, "step": 1522176 }, { "epoch": 0.02, "learning_rate": 2.507103487178345e-05, "loss": 3.4888, "step": 1522688 }, { "epoch": 0.02, "learning_rate": 2.506264892427293e-05, "loss": 3.4804, "step": 1523200 }, { "epoch": 0.02, "learning_rate": 2.505426297676241e-05, "loss": 3.4795, "step": 1523712 }, { "epoch": 0.02, "learning_rate": 2.5045909786859352e-05, "loss": 3.4807, "step": 1524224 }, { "epoch": 0.02, "learning_rate": 2.5037523839348832e-05, "loss": 3.4837, "step": 1524736 }, { "epoch": 0.02, "learning_rate": 2.5029137891838312e-05, "loss": 3.4812, "step": 1525248 }, { "epoch": 0.02, "learning_rate": 2.5020751944327792e-05, "loss": 3.4752, "step": 1525760 }, { "epoch": 0.02, "learning_rate": 2.5012365996817272e-05, "loss": 3.4806, "step": 1526272 }, { "epoch": 0.03, "eval_loss": 3.857754707336426, "eval_runtime": 312.0408, "eval_samples_per_second": 1222.888, "eval_steps_per_second": 38.216, "step": 1526390 }, { "epoch": 1.0, "learning_rate": 2.5003980049306752e-05, "loss": 3.484, "step": 1526784 }, { "epoch": 1.0, "learning_rate": 2.4995594101796232e-05, "loss": 3.4795, "step": 1527296 }, { "epoch": 1.0, "learning_rate": 2.4987208154285712e-05, "loss": 3.4896, "step": 1527808 }, { "epoch": 1.0, "learning_rate": 2.4978838585578924e-05, "loss": 3.4844, "step": 1528320 }, { "epoch": 1.0, "learning_rate": 2.4970452638068404e-05, "loss": 3.5036, "step": 1528832 }, { "epoch": 1.0, "learning_rate": 2.4962066690557884e-05, "loss": 3.482, "step": 1529344 }, { "epoch": 1.0, "learning_rate": 2.4953680743047364e-05, "loss": 3.4795, "step": 1529856 }, { "epoch": 1.0, "learning_rate": 2.4945311174340573e-05, "loss": 3.4667, "step": 1530368 }, { "epoch": 1.0, "learning_rate": 2.4936925226830053e-05, "loss": 3.4821, "step": 1530880 }, { "epoch": 1.0, "learning_rate": 2.4928539279319537e-05, "loss": 3.4827, "step": 1531392 }, { "epoch": 1.0, "learning_rate": 2.4920153331809016e-05, "loss": 3.4779, "step": 1531904 }, { "epoch": 1.0, "learning_rate": 2.4911783763102226e-05, "loss": 3.4823, "step": 1532416 }, { "epoch": 1.0, "learning_rate": 2.4903397815591706e-05, "loss": 3.4686, "step": 1532928 }, { "epoch": 1.0, "learning_rate": 2.4895011868081186e-05, "loss": 3.4791, "step": 1533440 }, { "epoch": 1.0, "learning_rate": 2.4886642299374398e-05, "loss": 3.4709, "step": 1533952 }, { "epoch": 1.0, "learning_rate": 2.4878256351863878e-05, "loss": 3.4705, "step": 1534464 }, { "epoch": 1.0, "learning_rate": 2.4869870404353358e-05, "loss": 3.4701, "step": 1534976 }, { "epoch": 1.0, "learning_rate": 2.4861484456842838e-05, "loss": 3.4804, "step": 1535488 }, { "epoch": 1.0, "learning_rate": 2.4853114888136047e-05, "loss": 3.4741, "step": 1536000 }, { "epoch": 1.0, "learning_rate": 2.4844728940625527e-05, "loss": 3.4951, "step": 1536512 }, { "epoch": 1.0, "learning_rate": 2.4836342993115007e-05, "loss": 3.4775, "step": 1537024 }, { "epoch": 1.0, "learning_rate": 2.4827957045604487e-05, "loss": 3.4858, "step": 1537536 }, { "epoch": 1.0, "learning_rate": 2.48195874768977e-05, "loss": 3.4749, "step": 1538048 }, { "epoch": 1.0, "learning_rate": 2.481120152938718e-05, "loss": 3.4847, "step": 1538560 }, { "epoch": 1.0, "learning_rate": 2.480281558187666e-05, "loss": 3.4769, "step": 1539072 }, { "epoch": 1.0, "learning_rate": 2.479444601316987e-05, "loss": 3.4884, "step": 1539584 }, { "epoch": 1.0, "learning_rate": 2.478606006565935e-05, "loss": 3.4755, "step": 1540096 }, { "epoch": 1.0, "learning_rate": 2.477767411814883e-05, "loss": 3.4774, "step": 1540608 }, { "epoch": 1.0, "learning_rate": 2.476928817063831e-05, "loss": 3.4689, "step": 1541120 }, { "epoch": 1.0, "learning_rate": 2.4760902223127788e-05, "loss": 3.4791, "step": 1541632 }, { "epoch": 1.01, "learning_rate": 2.4752516275617268e-05, "loss": 3.4858, "step": 1542144 }, { "epoch": 1.01, "learning_rate": 2.4744130328106748e-05, "loss": 3.4778, "step": 1542656 }, { "epoch": 1.01, "learning_rate": 2.473576075939996e-05, "loss": 3.4911, "step": 1543168 }, { "epoch": 1.01, "learning_rate": 2.472737481188944e-05, "loss": 3.4803, "step": 1543680 }, { "epoch": 1.01, "learning_rate": 2.471898886437892e-05, "loss": 3.4765, "step": 1544192 }, { "epoch": 1.01, "learning_rate": 2.47106029168684e-05, "loss": 3.4864, "step": 1544704 }, { "epoch": 1.01, "learning_rate": 2.470221696935788e-05, "loss": 3.4801, "step": 1545216 }, { "epoch": 1.01, "learning_rate": 2.469384740065109e-05, "loss": 3.4668, "step": 1545728 }, { "epoch": 1.01, "learning_rate": 2.468546145314057e-05, "loss": 3.4662, "step": 1546240 }, { "epoch": 1.01, "learning_rate": 2.4677075505630053e-05, "loss": 3.4702, "step": 1546752 }, { "epoch": 1.01, "learning_rate": 2.4668689558119533e-05, "loss": 3.4754, "step": 1547264 }, { "epoch": 1.01, "learning_rate": 2.4660303610609013e-05, "loss": 3.4791, "step": 1547776 }, { "epoch": 1.01, "learning_rate": 2.4651917663098493e-05, "loss": 3.4765, "step": 1548288 }, { "epoch": 1.01, "learning_rate": 2.464353171558797e-05, "loss": 3.4713, "step": 1548800 }, { "epoch": 1.01, "learning_rate": 2.463514576807745e-05, "loss": 3.4796, "step": 1549312 }, { "epoch": 1.01, "learning_rate": 2.462677619937066e-05, "loss": 3.4752, "step": 1549824 }, { "epoch": 1.01, "learning_rate": 2.461839025186014e-05, "loss": 3.4755, "step": 1550336 }, { "epoch": 1.01, "learning_rate": 2.461000430434962e-05, "loss": 3.466, "step": 1550848 }, { "epoch": 1.01, "learning_rate": 2.46016183568391e-05, "loss": 3.4542, "step": 1551360 }, { "epoch": 1.01, "learning_rate": 2.4593248788132314e-05, "loss": 3.4935, "step": 1551872 }, { "epoch": 1.01, "learning_rate": 2.458486284062179e-05, "loss": 3.4813, "step": 1552384 }, { "epoch": 1.01, "learning_rate": 2.457647689311127e-05, "loss": 3.4801, "step": 1552896 }, { "epoch": 1.01, "learning_rate": 2.4568090945600754e-05, "loss": 3.4775, "step": 1553408 }, { "epoch": 1.01, "learning_rate": 2.4559721376893966e-05, "loss": 3.4727, "step": 1553920 }, { "epoch": 1.01, "learning_rate": 2.4551335429383443e-05, "loss": 3.465, "step": 1554432 }, { "epoch": 1.01, "learning_rate": 2.4542949481872923e-05, "loss": 3.476, "step": 1554944 }, { "epoch": 1.01, "learning_rate": 2.4534563534362403e-05, "loss": 3.4737, "step": 1555456 }, { "epoch": 1.01, "learning_rate": 2.4526193965655615e-05, "loss": 3.4755, "step": 1555968 }, { "epoch": 1.01, "learning_rate": 2.4517808018145095e-05, "loss": 3.4929, "step": 1556480 }, { "epoch": 1.01, "learning_rate": 2.4509422070634575e-05, "loss": 3.4695, "step": 1556992 }, { "epoch": 1.01, "learning_rate": 2.4501036123124055e-05, "loss": 3.4623, "step": 1557504 }, { "epoch": 1.01, "learning_rate": 2.4492650175613535e-05, "loss": 3.4856, "step": 1558016 }, { "epoch": 1.01, "learning_rate": 2.4484264228103015e-05, "loss": 3.4611, "step": 1558528 }, { "epoch": 1.01, "learning_rate": 2.4475878280592495e-05, "loss": 3.4634, "step": 1559040 }, { "epoch": 1.01, "learning_rate": 2.4467492333081975e-05, "loss": 3.4825, "step": 1559552 }, { "epoch": 1.01, "learning_rate": 2.4459139143178917e-05, "loss": 3.4767, "step": 1560064 }, { "epoch": 1.01, "learning_rate": 2.4450753195668397e-05, "loss": 3.4708, "step": 1560576 }, { "epoch": 1.01, "learning_rate": 2.4442367248157877e-05, "loss": 3.4628, "step": 1561088 }, { "epoch": 1.01, "learning_rate": 2.4433981300647356e-05, "loss": 3.4597, "step": 1561600 }, { "epoch": 1.01, "learning_rate": 2.4425595353136836e-05, "loss": 3.4637, "step": 1562112 }, { "epoch": 1.01, "learning_rate": 2.4417209405626316e-05, "loss": 3.4823, "step": 1562624 }, { "epoch": 1.01, "learning_rate": 2.4408823458115796e-05, "loss": 3.4639, "step": 1563136 }, { "epoch": 1.01, "learning_rate": 2.4400437510605276e-05, "loss": 3.479, "step": 1563648 }, { "epoch": 1.01, "learning_rate": 2.439206794189849e-05, "loss": 3.477, "step": 1564160 }, { "epoch": 1.01, "learning_rate": 2.438368199438797e-05, "loss": 3.4872, "step": 1564672 }, { "epoch": 1.01, "learning_rate": 2.4375296046877445e-05, "loss": 3.4707, "step": 1565184 }, { "epoch": 1.01, "learning_rate": 2.436692647817066e-05, "loss": 3.4707, "step": 1565696 }, { "epoch": 1.01, "learning_rate": 2.435854053066014e-05, "loss": 3.4785, "step": 1566208 }, { "epoch": 1.01, "learning_rate": 2.435015458314962e-05, "loss": 3.4679, "step": 1566720 }, { "epoch": 1.01, "learning_rate": 2.4341768635639098e-05, "loss": 3.4842, "step": 1567232 }, { "epoch": 1.01, "learning_rate": 2.4333382688128578e-05, "loss": 3.4735, "step": 1567744 }, { "epoch": 1.01, "learning_rate": 2.432501311942179e-05, "loss": 3.471, "step": 1568256 }, { "epoch": 1.01, "learning_rate": 2.431662717191127e-05, "loss": 3.474, "step": 1568768 }, { "epoch": 1.01, "learning_rate": 2.430824122440075e-05, "loss": 3.4569, "step": 1569280 }, { "epoch": 1.01, "learning_rate": 2.429985527689023e-05, "loss": 3.4659, "step": 1569792 }, { "epoch": 1.01, "learning_rate": 2.429146932937971e-05, "loss": 3.4721, "step": 1570304 }, { "epoch": 1.01, "learning_rate": 2.428308338186919e-05, "loss": 3.4771, "step": 1570816 }, { "epoch": 1.01, "learning_rate": 2.42747138131624e-05, "loss": 3.4643, "step": 1571328 }, { "epoch": 1.01, "learning_rate": 2.426632786565188e-05, "loss": 3.4729, "step": 1571840 }, { "epoch": 1.02, "learning_rate": 2.4257941918141362e-05, "loss": 3.4638, "step": 1572352 }, { "epoch": 1.02, "learning_rate": 2.4249555970630842e-05, "loss": 3.4697, "step": 1572864 }, { "epoch": 1.02, "learning_rate": 2.4241170023120322e-05, "loss": 3.4611, "step": 1573376 }, { "epoch": 1.02, "learning_rate": 2.42327840756098e-05, "loss": 3.471, "step": 1573888 }, { "epoch": 1.02, "learning_rate": 2.422441450690301e-05, "loss": 3.4796, "step": 1574400 }, { "epoch": 1.02, "learning_rate": 2.421602855939249e-05, "loss": 3.4812, "step": 1574912 }, { "epoch": 1.02, "learning_rate": 2.420764261188197e-05, "loss": 3.4744, "step": 1575424 }, { "epoch": 1.02, "learning_rate": 2.419925666437145e-05, "loss": 3.4645, "step": 1575936 }, { "epoch": 1.02, "learning_rate": 2.419087071686093e-05, "loss": 3.4724, "step": 1576448 }, { "epoch": 1.02, "learning_rate": 2.418248476935041e-05, "loss": 3.4731, "step": 1576960 }, { "epoch": 1.02, "learning_rate": 2.417409882183989e-05, "loss": 3.479, "step": 1577472 }, { "epoch": 1.02, "learning_rate": 2.41657292531331e-05, "loss": 3.482, "step": 1577984 }, { "epoch": 1.02, "learning_rate": 2.4157343305622583e-05, "loss": 3.4714, "step": 1578496 }, { "epoch": 1.02, "learning_rate": 2.4148957358112063e-05, "loss": 3.4656, "step": 1579008 }, { "epoch": 1.02, "learning_rate": 2.4140571410601543e-05, "loss": 3.4851, "step": 1579520 }, { "epoch": 1.02, "learning_rate": 2.4132201841894752e-05, "loss": 3.4619, "step": 1580032 }, { "epoch": 1.02, "learning_rate": 2.4123815894384232e-05, "loss": 3.4755, "step": 1580544 }, { "epoch": 1.02, "learning_rate": 2.4115429946873712e-05, "loss": 3.4642, "step": 1581056 }, { "epoch": 1.02, "learning_rate": 2.4107043999363192e-05, "loss": 3.4758, "step": 1581568 }, { "epoch": 1.02, "learning_rate": 2.4098674430656405e-05, "loss": 3.4611, "step": 1582080 }, { "epoch": 1.02, "learning_rate": 2.4090288483145885e-05, "loss": 3.4764, "step": 1582592 }, { "epoch": 1.02, "learning_rate": 2.4081902535635365e-05, "loss": 3.4622, "step": 1583104 }, { "epoch": 1.02, "learning_rate": 2.4073516588124845e-05, "loss": 3.4685, "step": 1583616 }, { "epoch": 1.02, "learning_rate": 2.4065147019418054e-05, "loss": 3.4723, "step": 1584128 }, { "epoch": 1.02, "learning_rate": 2.4056761071907534e-05, "loss": 3.4665, "step": 1584640 }, { "epoch": 1.02, "learning_rate": 2.4048375124397017e-05, "loss": 3.4786, "step": 1585152 }, { "epoch": 1.02, "learning_rate": 2.4039989176886497e-05, "loss": 3.486, "step": 1585664 }, { "epoch": 1.02, "learning_rate": 2.4031619608179706e-05, "loss": 3.4746, "step": 1586176 }, { "epoch": 1.02, "learning_rate": 2.4023233660669186e-05, "loss": 3.4727, "step": 1586688 }, { "epoch": 1.02, "learning_rate": 2.4014847713158666e-05, "loss": 3.4703, "step": 1587200 }, { "epoch": 1.02, "learning_rate": 2.4006461765648146e-05, "loss": 3.466, "step": 1587712 }, { "epoch": 1.02, "learning_rate": 2.399809219694136e-05, "loss": 3.4634, "step": 1588224 }, { "epoch": 1.02, "learning_rate": 2.398970624943084e-05, "loss": 3.4803, "step": 1588736 }, { "epoch": 1.02, "learning_rate": 2.398132030192032e-05, "loss": 3.4582, "step": 1589248 }, { "epoch": 1.02, "learning_rate": 2.3972934354409798e-05, "loss": 3.4764, "step": 1589760 }, { "epoch": 1.02, "learning_rate": 2.396458116450674e-05, "loss": 3.4663, "step": 1590272 }, { "epoch": 1.02, "learning_rate": 2.395619521699622e-05, "loss": 3.4777, "step": 1590784 }, { "epoch": 1.02, "learning_rate": 2.39478092694857e-05, "loss": 3.4695, "step": 1591296 }, { "epoch": 1.02, "learning_rate": 2.393942332197518e-05, "loss": 3.4707, "step": 1591808 }, { "epoch": 1.02, "learning_rate": 2.393103737446466e-05, "loss": 3.4646, "step": 1592320 }, { "epoch": 1.02, "learning_rate": 2.392265142695414e-05, "loss": 3.478, "step": 1592832 }, { "epoch": 1.02, "learning_rate": 2.391426547944362e-05, "loss": 3.4728, "step": 1593344 }, { "epoch": 1.02, "learning_rate": 2.39058795319331e-05, "loss": 3.4845, "step": 1593856 }, { "epoch": 1.02, "learning_rate": 2.3897509963226312e-05, "loss": 3.46, "step": 1594368 }, { "epoch": 1.02, "learning_rate": 2.3889124015715792e-05, "loss": 3.4738, "step": 1594880 }, { "epoch": 1.02, "learning_rate": 2.3880738068205272e-05, "loss": 3.4741, "step": 1595392 }, { "epoch": 1.02, "learning_rate": 2.3872352120694752e-05, "loss": 3.4716, "step": 1595904 }, { "epoch": 1.02, "learning_rate": 2.386398255198796e-05, "loss": 3.472, "step": 1596416 }, { "epoch": 1.02, "learning_rate": 2.385559660447744e-05, "loss": 3.4784, "step": 1596928 }, { "epoch": 1.02, "learning_rate": 2.3847210656966924e-05, "loss": 3.47, "step": 1597440 }, { "epoch": 1.02, "learning_rate": 2.38388247094564e-05, "loss": 3.4927, "step": 1597952 }, { "epoch": 1.02, "learning_rate": 2.3830455140749613e-05, "loss": 3.4656, "step": 1598464 }, { "epoch": 1.02, "learning_rate": 2.3822069193239093e-05, "loss": 3.4767, "step": 1598976 }, { "epoch": 1.02, "learning_rate": 2.3813683245728573e-05, "loss": 3.4665, "step": 1599488 }, { "epoch": 1.02, "learning_rate": 2.3805297298218053e-05, "loss": 3.4694, "step": 1600000 }, { "epoch": 1.02, "learning_rate": 2.3796944108314995e-05, "loss": 3.475, "step": 1600512 }, { "epoch": 1.02, "learning_rate": 2.3788558160804475e-05, "loss": 3.4663, "step": 1601024 }, { "epoch": 1.02, "learning_rate": 2.3780172213293955e-05, "loss": 3.4715, "step": 1601536 }, { "epoch": 1.02, "learning_rate": 2.3771786265783435e-05, "loss": 3.4554, "step": 1602048 }, { "epoch": 1.02, "learning_rate": 2.3763400318272915e-05, "loss": 3.4712, "step": 1602560 }, { "epoch": 1.03, "eval_loss": 3.8586251735687256, "eval_runtime": 307.8076, "eval_samples_per_second": 1239.706, "eval_steps_per_second": 38.742, "step": 1602710 }, { "epoch": 0.0, "learning_rate": 2.3755014370762395e-05, "loss": 3.4741, "step": 1603072 }, { "epoch": 0.0, "learning_rate": 2.3746628423251875e-05, "loss": 3.4682, "step": 1603584 }, { "epoch": 0.0, "learning_rate": 2.3738242475741355e-05, "loss": 3.4751, "step": 1604096 }, { "epoch": 0.0, "learning_rate": 2.3729856528230835e-05, "loss": 3.4762, "step": 1604608 }, { "epoch": 0.0, "learning_rate": 2.3721486959524047e-05, "loss": 3.4858, "step": 1605120 }, { "epoch": 0.0, "learning_rate": 2.3713101012013524e-05, "loss": 3.4717, "step": 1605632 }, { "epoch": 0.0, "learning_rate": 2.3704715064503007e-05, "loss": 3.4671, "step": 1606144 }, { "epoch": 0.0, "learning_rate": 2.3696329116992487e-05, "loss": 3.4581, "step": 1606656 }, { "epoch": 0.0, "learning_rate": 2.36879595482857e-05, "loss": 3.4695, "step": 1607168 }, { "epoch": 0.0, "learning_rate": 2.367958997957891e-05, "loss": 3.4721, "step": 1607680 }, { "epoch": 0.0, "learning_rate": 2.367120403206839e-05, "loss": 3.4698, "step": 1608192 }, { "epoch": 0.0, "learning_rate": 2.366281808455787e-05, "loss": 3.4658, "step": 1608704 }, { "epoch": 0.0, "learning_rate": 2.365443213704735e-05, "loss": 3.4614, "step": 1609216 }, { "epoch": 0.0, "learning_rate": 2.364604618953683e-05, "loss": 3.4629, "step": 1609728 }, { "epoch": 0.0, "learning_rate": 2.3637660242026308e-05, "loss": 3.4625, "step": 1610240 }, { "epoch": 0.0, "learning_rate": 2.3629274294515788e-05, "loss": 3.4556, "step": 1610752 }, { "epoch": 0.0, "learning_rate": 2.3620888347005268e-05, "loss": 3.4607, "step": 1611264 }, { "epoch": 0.0, "learning_rate": 2.3612518778298477e-05, "loss": 3.4658, "step": 1611776 }, { "epoch": 0.0, "learning_rate": 2.3604132830787957e-05, "loss": 3.4648, "step": 1612288 }, { "epoch": 0.0, "learning_rate": 2.359574688327744e-05, "loss": 3.484, "step": 1612800 }, { "epoch": 0.0, "learning_rate": 2.358736093576692e-05, "loss": 3.4694, "step": 1613312 }, { "epoch": 0.0, "learning_rate": 2.357899136706013e-05, "loss": 3.4758, "step": 1613824 }, { "epoch": 0.0, "learning_rate": 2.357060541954961e-05, "loss": 3.4605, "step": 1614336 }, { "epoch": 0.0, "learning_rate": 2.356221947203909e-05, "loss": 3.471, "step": 1614848 }, { "epoch": 0.0, "learning_rate": 2.3553849903332302e-05, "loss": 3.4639, "step": 1615360 }, { "epoch": 0.0, "learning_rate": 2.3545480334625515e-05, "loss": 3.4768, "step": 1615872 }, { "epoch": 0.0, "learning_rate": 2.3537094387114994e-05, "loss": 3.4646, "step": 1616384 }, { "epoch": 0.0, "learning_rate": 2.352870843960447e-05, "loss": 3.4625, "step": 1616896 }, { "epoch": 0.0, "learning_rate": 2.352032249209395e-05, "loss": 3.4593, "step": 1617408 }, { "epoch": 0.0, "learning_rate": 2.351193654458343e-05, "loss": 3.467, "step": 1617920 }, { "epoch": 0.01, "learning_rate": 2.350355059707291e-05, "loss": 3.473, "step": 1618432 }, { "epoch": 0.01, "learning_rate": 2.3495181028366123e-05, "loss": 3.4708, "step": 1618944 }, { "epoch": 0.01, "learning_rate": 2.3486795080855603e-05, "loss": 3.4749, "step": 1619456 }, { "epoch": 0.01, "learning_rate": 2.3478409133345083e-05, "loss": 3.4707, "step": 1619968 }, { "epoch": 0.01, "learning_rate": 2.3470023185834563e-05, "loss": 3.4632, "step": 1620480 }, { "epoch": 0.01, "learning_rate": 2.3461637238324043e-05, "loss": 3.4767, "step": 1620992 }, { "epoch": 0.01, "learning_rate": 2.3453251290813523e-05, "loss": 3.4695, "step": 1621504 }, { "epoch": 0.01, "learning_rate": 2.3444865343303003e-05, "loss": 3.4552, "step": 1622016 }, { "epoch": 0.01, "learning_rate": 2.3436495774596216e-05, "loss": 3.459, "step": 1622528 }, { "epoch": 0.01, "learning_rate": 2.3428109827085696e-05, "loss": 3.4549, "step": 1623040 }, { "epoch": 0.01, "learning_rate": 2.3419723879575176e-05, "loss": 3.4599, "step": 1623552 }, { "epoch": 0.01, "learning_rate": 2.3411337932064652e-05, "loss": 3.4711, "step": 1624064 }, { "epoch": 0.01, "learning_rate": 2.3402951984554132e-05, "loss": 3.4666, "step": 1624576 }, { "epoch": 0.01, "learning_rate": 2.3394566037043615e-05, "loss": 3.4573, "step": 1625088 }, { "epoch": 0.01, "learning_rate": 2.3386180089533095e-05, "loss": 3.4702, "step": 1625600 }, { "epoch": 0.01, "learning_rate": 2.3377810520826304e-05, "loss": 3.4608, "step": 1626112 }, { "epoch": 0.01, "learning_rate": 2.3369424573315784e-05, "loss": 3.4646, "step": 1626624 }, { "epoch": 0.01, "learning_rate": 2.3361038625805264e-05, "loss": 3.4519, "step": 1627136 }, { "epoch": 0.01, "learning_rate": 2.3352652678294744e-05, "loss": 3.4404, "step": 1627648 }, { "epoch": 0.01, "learning_rate": 2.3344283109587957e-05, "loss": 3.4852, "step": 1628160 }, { "epoch": 0.01, "learning_rate": 2.3335897162077437e-05, "loss": 3.468, "step": 1628672 }, { "epoch": 0.01, "learning_rate": 2.3327511214566917e-05, "loss": 3.4721, "step": 1629184 }, { "epoch": 0.01, "learning_rate": 2.3319125267056397e-05, "loss": 3.4589, "step": 1629696 }, { "epoch": 0.01, "learning_rate": 2.3310755698349606e-05, "loss": 3.4652, "step": 1630208 }, { "epoch": 0.01, "learning_rate": 2.3302369750839086e-05, "loss": 3.4524, "step": 1630720 }, { "epoch": 0.01, "learning_rate": 2.3293983803328566e-05, "loss": 3.463, "step": 1631232 }, { "epoch": 0.01, "learning_rate": 2.328559785581805e-05, "loss": 3.4655, "step": 1631744 }, { "epoch": 0.01, "learning_rate": 2.3277228287111258e-05, "loss": 3.4629, "step": 1632256 }, { "epoch": 0.01, "learning_rate": 2.3268842339600738e-05, "loss": 3.4809, "step": 1632768 }, { "epoch": 0.01, "learning_rate": 2.3260456392090218e-05, "loss": 3.4585, "step": 1633280 }, { "epoch": 0.01, "learning_rate": 2.3252070444579698e-05, "loss": 3.4507, "step": 1633792 }, { "epoch": 0.01, "learning_rate": 2.3243684497069178e-05, "loss": 3.4763, "step": 1634304 }, { "epoch": 0.01, "learning_rate": 2.3235298549558658e-05, "loss": 3.4465, "step": 1634816 }, { "epoch": 0.01, "learning_rate": 2.3226912602048138e-05, "loss": 3.4506, "step": 1635328 }, { "epoch": 0.01, "learning_rate": 2.3218526654537618e-05, "loss": 3.4703, "step": 1635840 }, { "epoch": 0.01, "learning_rate": 2.321015708583083e-05, "loss": 3.4702, "step": 1636352 }, { "epoch": 0.01, "learning_rate": 2.3201771138320307e-05, "loss": 3.4554, "step": 1636864 }, { "epoch": 0.01, "learning_rate": 2.3193385190809787e-05, "loss": 3.4586, "step": 1637376 }, { "epoch": 0.01, "learning_rate": 2.318499924329927e-05, "loss": 3.4438, "step": 1637888 }, { "epoch": 0.01, "learning_rate": 2.317662967459248e-05, "loss": 3.4561, "step": 1638400 }, { "epoch": 0.01, "learning_rate": 2.316824372708196e-05, "loss": 3.4679, "step": 1638912 }, { "epoch": 0.01, "learning_rate": 2.315985777957144e-05, "loss": 3.4517, "step": 1639424 }, { "epoch": 0.01, "learning_rate": 2.315148821086465e-05, "loss": 3.4674, "step": 1639936 }, { "epoch": 0.01, "learning_rate": 2.314310226335413e-05, "loss": 3.4637, "step": 1640448 }, { "epoch": 0.01, "learning_rate": 2.313471631584361e-05, "loss": 3.475, "step": 1640960 }, { "epoch": 0.01, "learning_rate": 2.312633036833309e-05, "loss": 3.4577, "step": 1641472 }, { "epoch": 0.01, "learning_rate": 2.3117960799626304e-05, "loss": 3.4626, "step": 1641984 }, { "epoch": 0.01, "learning_rate": 2.310957485211578e-05, "loss": 3.4639, "step": 1642496 }, { "epoch": 0.01, "learning_rate": 2.310118890460526e-05, "loss": 3.456, "step": 1643008 }, { "epoch": 0.01, "learning_rate": 2.309280295709474e-05, "loss": 3.4667, "step": 1643520 }, { "epoch": 0.01, "learning_rate": 2.3084417009584224e-05, "loss": 3.463, "step": 1644032 }, { "epoch": 0.01, "learning_rate": 2.3076047440877433e-05, "loss": 3.4615, "step": 1644544 }, { "epoch": 0.01, "learning_rate": 2.3067661493366913e-05, "loss": 3.4611, "step": 1645056 }, { "epoch": 0.01, "learning_rate": 2.3059275545856393e-05, "loss": 3.4461, "step": 1645568 }, { "epoch": 0.01, "learning_rate": 2.3050889598345873e-05, "loss": 3.4514, "step": 1646080 }, { "epoch": 0.01, "learning_rate": 2.3042503650835353e-05, "loss": 3.4607, "step": 1646592 }, { "epoch": 0.01, "learning_rate": 2.3034117703324833e-05, "loss": 3.4647, "step": 1647104 }, { "epoch": 0.01, "learning_rate": 2.3025748134618045e-05, "loss": 3.4522, "step": 1647616 }, { "epoch": 0.01, "learning_rate": 2.3017362187107525e-05, "loss": 3.4631, "step": 1648128 }, { "epoch": 0.02, "learning_rate": 2.3008976239597005e-05, "loss": 3.4511, "step": 1648640 }, { "epoch": 0.02, "learning_rate": 2.3000590292086485e-05, "loss": 3.4567, "step": 1649152 }, { "epoch": 0.02, "learning_rate": 2.299220434457596e-05, "loss": 3.4508, "step": 1649664 }, { "epoch": 0.02, "learning_rate": 2.298381839706544e-05, "loss": 3.4598, "step": 1650176 }, { "epoch": 0.02, "learning_rate": 2.2975448828358657e-05, "loss": 3.4688, "step": 1650688 }, { "epoch": 0.02, "learning_rate": 2.2967062880848134e-05, "loss": 3.4661, "step": 1651200 }, { "epoch": 0.02, "learning_rate": 2.2958676933337614e-05, "loss": 3.464, "step": 1651712 }, { "epoch": 0.02, "learning_rate": 2.2950290985827094e-05, "loss": 3.4521, "step": 1652224 }, { "epoch": 0.02, "learning_rate": 2.2941905038316574e-05, "loss": 3.4589, "step": 1652736 }, { "epoch": 0.02, "learning_rate": 2.2933519090806054e-05, "loss": 3.4608, "step": 1653248 }, { "epoch": 0.02, "learning_rate": 2.2925133143295534e-05, "loss": 3.469, "step": 1653760 }, { "epoch": 0.02, "learning_rate": 2.2916747195785017e-05, "loss": 3.4644, "step": 1654272 }, { "epoch": 0.02, "learning_rate": 2.2908377627078226e-05, "loss": 3.4611, "step": 1654784 }, { "epoch": 0.02, "learning_rate": 2.2899991679567706e-05, "loss": 3.4551, "step": 1655296 }, { "epoch": 0.02, "learning_rate": 2.2891605732057186e-05, "loss": 3.4736, "step": 1655808 }, { "epoch": 0.02, "learning_rate": 2.2883236163350395e-05, "loss": 3.45, "step": 1656320 }, { "epoch": 0.02, "learning_rate": 2.287485021583988e-05, "loss": 3.4635, "step": 1656832 }, { "epoch": 0.02, "learning_rate": 2.286646426832936e-05, "loss": 3.4488, "step": 1657344 }, { "epoch": 0.02, "learning_rate": 2.285807832081884e-05, "loss": 3.4664, "step": 1657856 }, { "epoch": 0.02, "learning_rate": 2.2849708752112048e-05, "loss": 3.4517, "step": 1658368 }, { "epoch": 0.02, "learning_rate": 2.2841322804601528e-05, "loss": 3.4622, "step": 1658880 }, { "epoch": 0.02, "learning_rate": 2.2832936857091007e-05, "loss": 3.4531, "step": 1659392 }, { "epoch": 0.02, "learning_rate": 2.2824550909580487e-05, "loss": 3.4552, "step": 1659904 }, { "epoch": 0.02, "learning_rate": 2.28161813408737e-05, "loss": 3.4582, "step": 1660416 }, { "epoch": 0.02, "learning_rate": 2.280779539336318e-05, "loss": 3.4557, "step": 1660928 }, { "epoch": 0.02, "learning_rate": 2.279942582465639e-05, "loss": 3.4665, "step": 1661440 }, { "epoch": 0.02, "learning_rate": 2.279103987714587e-05, "loss": 3.4745, "step": 1661952 }, { "epoch": 0.02, "learning_rate": 2.278265392963535e-05, "loss": 3.4633, "step": 1662464 }, { "epoch": 0.02, "learning_rate": 2.2774267982124832e-05, "loss": 3.4645, "step": 1662976 }, { "epoch": 0.02, "learning_rate": 2.2765882034614312e-05, "loss": 3.4554, "step": 1663488 }, { "epoch": 0.02, "learning_rate": 2.275749608710379e-05, "loss": 3.4545, "step": 1664000 }, { "epoch": 0.02, "learning_rate": 2.274911013959327e-05, "loss": 3.4579, "step": 1664512 }, { "epoch": 0.02, "learning_rate": 2.274072419208275e-05, "loss": 3.4701, "step": 1665024 }, { "epoch": 0.02, "learning_rate": 2.273235462337596e-05, "loss": 3.4458, "step": 1665536 }, { "epoch": 0.02, "learning_rate": 2.272396867586544e-05, "loss": 3.4607, "step": 1666048 }, { "epoch": 0.02, "learning_rate": 2.2715599107158654e-05, "loss": 3.4597, "step": 1666560 }, { "epoch": 0.02, "learning_rate": 2.2707213159648134e-05, "loss": 3.4614, "step": 1667072 }, { "epoch": 0.02, "learning_rate": 2.269882721213761e-05, "loss": 3.4591, "step": 1667584 }, { "epoch": 0.02, "learning_rate": 2.269044126462709e-05, "loss": 3.456, "step": 1668096 }, { "epoch": 0.02, "learning_rate": 2.268205531711657e-05, "loss": 3.4548, "step": 1668608 }, { "epoch": 0.02, "learning_rate": 2.267366936960605e-05, "loss": 3.4656, "step": 1669120 }, { "epoch": 0.02, "learning_rate": 2.2665283422095533e-05, "loss": 3.4638, "step": 1669632 }, { "epoch": 0.02, "learning_rate": 2.2656897474585013e-05, "loss": 3.4747, "step": 1670144 }, { "epoch": 0.02, "learning_rate": 2.2648527905878222e-05, "loss": 3.4486, "step": 1670656 }, { "epoch": 0.02, "learning_rate": 2.2640141958367702e-05, "loss": 3.4604, "step": 1671168 }, { "epoch": 0.02, "learning_rate": 2.2631756010857182e-05, "loss": 3.4631, "step": 1671680 }, { "epoch": 0.02, "learning_rate": 2.2623370063346662e-05, "loss": 3.4588, "step": 1672192 }, { "epoch": 0.02, "learning_rate": 2.2615000494639875e-05, "loss": 3.4607, "step": 1672704 }, { "epoch": 0.02, "learning_rate": 2.2606614547129355e-05, "loss": 3.4665, "step": 1673216 }, { "epoch": 0.02, "learning_rate": 2.2598228599618835e-05, "loss": 3.4612, "step": 1673728 }, { "epoch": 0.02, "learning_rate": 2.2589842652108315e-05, "loss": 3.4804, "step": 1674240 }, { "epoch": 0.02, "learning_rate": 2.2581473083401524e-05, "loss": 3.4578, "step": 1674752 }, { "epoch": 0.02, "learning_rate": 2.2573087135891004e-05, "loss": 3.4618, "step": 1675264 }, { "epoch": 0.02, "learning_rate": 2.2564701188380487e-05, "loss": 3.4561, "step": 1675776 }, { "epoch": 0.02, "learning_rate": 2.2556315240869967e-05, "loss": 3.4633, "step": 1676288 }, { "epoch": 0.02, "learning_rate": 2.254796205096691e-05, "loss": 3.4556, "step": 1676800 }, { "epoch": 0.02, "learning_rate": 2.2539576103456385e-05, "loss": 3.4584, "step": 1677312 }, { "epoch": 0.02, "learning_rate": 2.2531190155945865e-05, "loss": 3.4615, "step": 1677824 }, { "epoch": 0.02, "learning_rate": 2.252280420843535e-05, "loss": 3.4432, "step": 1678336 }, { "epoch": 0.02, "learning_rate": 2.251441826092483e-05, "loss": 3.4613, "step": 1678848 }, { "epoch": 0.03, "eval_loss": 3.8605756759643555, "eval_runtime": 306.4165, "eval_samples_per_second": 1245.335, "eval_steps_per_second": 38.918, "step": 1679030 }, { "epoch": 1.0, "learning_rate": 2.250603231341431e-05, "loss": 3.4621, "step": 1679360 }, { "epoch": 1.0, "learning_rate": 2.2497646365903788e-05, "loss": 3.4578, "step": 1679872 }, { "epoch": 1.0, "learning_rate": 2.2489260418393265e-05, "loss": 3.4597, "step": 1680384 }, { "epoch": 1.0, "learning_rate": 2.2480890849686477e-05, "loss": 3.4633, "step": 1680896 }, { "epoch": 1.0, "learning_rate": 2.2472504902175957e-05, "loss": 3.4748, "step": 1681408 }, { "epoch": 1.0, "learning_rate": 2.246411895466544e-05, "loss": 3.4585, "step": 1681920 }, { "epoch": 1.0, "learning_rate": 2.2455733007154917e-05, "loss": 3.4588, "step": 1682432 }, { "epoch": 1.0, "learning_rate": 2.244736343844813e-05, "loss": 3.4458, "step": 1682944 }, { "epoch": 1.0, "learning_rate": 2.243897749093761e-05, "loss": 3.4571, "step": 1683456 }, { "epoch": 1.0, "learning_rate": 2.243059154342709e-05, "loss": 3.4592, "step": 1683968 }, { "epoch": 1.0, "learning_rate": 2.2422205595916566e-05, "loss": 3.4575, "step": 1684480 }, { "epoch": 1.0, "learning_rate": 2.2413836027209782e-05, "loss": 3.4553, "step": 1684992 }, { "epoch": 1.0, "learning_rate": 2.2405450079699262e-05, "loss": 3.4491, "step": 1685504 }, { "epoch": 1.0, "learning_rate": 2.239706413218874e-05, "loss": 3.4524, "step": 1686016 }, { "epoch": 1.0, "learning_rate": 2.238867818467822e-05, "loss": 3.4543, "step": 1686528 }, { "epoch": 1.0, "learning_rate": 2.238030861597143e-05, "loss": 3.4439, "step": 1687040 }, { "epoch": 1.0, "learning_rate": 2.237192266846091e-05, "loss": 3.4498, "step": 1687552 }, { "epoch": 1.0, "learning_rate": 2.236353672095039e-05, "loss": 3.4516, "step": 1688064 }, { "epoch": 1.0, "learning_rate": 2.235515077343987e-05, "loss": 3.4534, "step": 1688576 }, { "epoch": 1.0, "learning_rate": 2.2346781204733083e-05, "loss": 3.4702, "step": 1689088 }, { "epoch": 1.0, "learning_rate": 2.2338411636026292e-05, "loss": 3.4582, "step": 1689600 }, { "epoch": 1.0, "learning_rate": 2.2330025688515772e-05, "loss": 3.4681, "step": 1690112 }, { "epoch": 1.0, "learning_rate": 2.2321639741005256e-05, "loss": 3.448, "step": 1690624 }, { "epoch": 1.0, "learning_rate": 2.2313253793494736e-05, "loss": 3.4564, "step": 1691136 }, { "epoch": 1.0, "learning_rate": 2.2304867845984212e-05, "loss": 3.4535, "step": 1691648 }, { "epoch": 1.0, "learning_rate": 2.2296498277277425e-05, "loss": 3.4651, "step": 1692160 }, { "epoch": 1.0, "learning_rate": 2.2288112329766905e-05, "loss": 3.4519, "step": 1692672 }, { "epoch": 1.0, "learning_rate": 2.2279726382256385e-05, "loss": 3.4538, "step": 1693184 }, { "epoch": 1.0, "learning_rate": 2.2271340434745865e-05, "loss": 3.4477, "step": 1693696 }, { "epoch": 1.0, "learning_rate": 2.2262954487235345e-05, "loss": 3.4546, "step": 1694208 }, { "epoch": 1.01, "learning_rate": 2.2254568539724825e-05, "loss": 3.4547, "step": 1694720 }, { "epoch": 1.01, "learning_rate": 2.2246182592214305e-05, "loss": 3.4651, "step": 1695232 }, { "epoch": 1.01, "learning_rate": 2.2237796644703784e-05, "loss": 3.4608, "step": 1695744 }, { "epoch": 1.01, "learning_rate": 2.2229427075996994e-05, "loss": 3.464, "step": 1696256 }, { "epoch": 1.01, "learning_rate": 2.2221041128486474e-05, "loss": 3.4517, "step": 1696768 }, { "epoch": 1.01, "learning_rate": 2.2212655180975957e-05, "loss": 3.4582, "step": 1697280 }, { "epoch": 1.01, "learning_rate": 2.2204269233465437e-05, "loss": 3.4567, "step": 1697792 }, { "epoch": 1.01, "learning_rate": 2.2195899664758646e-05, "loss": 3.4454, "step": 1698304 }, { "epoch": 1.01, "learning_rate": 2.218753009605186e-05, "loss": 3.4482, "step": 1698816 }, { "epoch": 1.01, "learning_rate": 2.2179144148541335e-05, "loss": 3.4418, "step": 1699328 }, { "epoch": 1.01, "learning_rate": 2.217075820103082e-05, "loss": 3.4509, "step": 1699840 }, { "epoch": 1.01, "learning_rate": 2.2162372253520298e-05, "loss": 3.457, "step": 1700352 }, { "epoch": 1.01, "learning_rate": 2.2153986306009778e-05, "loss": 3.4568, "step": 1700864 }, { "epoch": 1.01, "learning_rate": 2.2145600358499258e-05, "loss": 3.4487, "step": 1701376 }, { "epoch": 1.01, "learning_rate": 2.2137214410988738e-05, "loss": 3.457, "step": 1701888 }, { "epoch": 1.01, "learning_rate": 2.2128844842281947e-05, "loss": 3.4525, "step": 1702400 }, { "epoch": 1.01, "learning_rate": 2.2120458894771427e-05, "loss": 3.4535, "step": 1702912 }, { "epoch": 1.01, "learning_rate": 2.211207294726091e-05, "loss": 3.4419, "step": 1703424 }, { "epoch": 1.01, "learning_rate": 2.210368699975039e-05, "loss": 3.4283, "step": 1703936 }, { "epoch": 1.01, "learning_rate": 2.20953174310436e-05, "loss": 3.4719, "step": 1704448 }, { "epoch": 1.01, "learning_rate": 2.208693148353308e-05, "loss": 3.4556, "step": 1704960 }, { "epoch": 1.01, "learning_rate": 2.207854553602256e-05, "loss": 3.4638, "step": 1705472 }, { "epoch": 1.01, "learning_rate": 2.207015958851204e-05, "loss": 3.4508, "step": 1705984 }, { "epoch": 1.01, "learning_rate": 2.2061790019805252e-05, "loss": 3.4507, "step": 1706496 }, { "epoch": 1.01, "learning_rate": 2.2053404072294732e-05, "loss": 3.4422, "step": 1707008 }, { "epoch": 1.01, "learning_rate": 2.2045018124784212e-05, "loss": 3.4517, "step": 1707520 }, { "epoch": 1.01, "learning_rate": 2.203663217727369e-05, "loss": 3.4564, "step": 1708032 }, { "epoch": 1.01, "learning_rate": 2.20282626085669e-05, "loss": 3.4474, "step": 1708544 }, { "epoch": 1.01, "learning_rate": 2.201987666105638e-05, "loss": 3.4721, "step": 1709056 }, { "epoch": 1.01, "learning_rate": 2.2011490713545864e-05, "loss": 3.4464, "step": 1709568 }, { "epoch": 1.01, "learning_rate": 2.200310476603534e-05, "loss": 3.4404, "step": 1710080 }, { "epoch": 1.01, "learning_rate": 2.199471881852482e-05, "loss": 3.4634, "step": 1710592 }, { "epoch": 1.01, "learning_rate": 2.19863328710143e-05, "loss": 3.4377, "step": 1711104 }, { "epoch": 1.01, "learning_rate": 2.197794692350378e-05, "loss": 3.4344, "step": 1711616 }, { "epoch": 1.01, "learning_rate": 2.196956097599326e-05, "loss": 3.4628, "step": 1712128 }, { "epoch": 1.01, "learning_rate": 2.1961191407286473e-05, "loss": 3.4577, "step": 1712640 }, { "epoch": 1.01, "learning_rate": 2.1952805459775953e-05, "loss": 3.443, "step": 1713152 }, { "epoch": 1.01, "learning_rate": 2.1944419512265433e-05, "loss": 3.4499, "step": 1713664 }, { "epoch": 1.01, "learning_rate": 2.1936033564754913e-05, "loss": 3.4329, "step": 1714176 }, { "epoch": 1.01, "learning_rate": 2.1927663996048122e-05, "loss": 3.4477, "step": 1714688 }, { "epoch": 1.01, "learning_rate": 2.1919278048537602e-05, "loss": 3.4538, "step": 1715200 }, { "epoch": 1.01, "learning_rate": 2.1910892101027082e-05, "loss": 3.4413, "step": 1715712 }, { "epoch": 1.01, "learning_rate": 2.1902506153516565e-05, "loss": 3.4546, "step": 1716224 }, { "epoch": 1.01, "learning_rate": 2.1894136584809774e-05, "loss": 3.4544, "step": 1716736 }, { "epoch": 1.01, "learning_rate": 2.1885750637299254e-05, "loss": 3.4629, "step": 1717248 }, { "epoch": 1.01, "learning_rate": 2.1877364689788734e-05, "loss": 3.4483, "step": 1717760 }, { "epoch": 1.01, "learning_rate": 2.1868995121081943e-05, "loss": 3.4519, "step": 1718272 }, { "epoch": 1.01, "learning_rate": 2.1860609173571427e-05, "loss": 3.4559, "step": 1718784 }, { "epoch": 1.01, "learning_rate": 2.1852223226060907e-05, "loss": 3.4455, "step": 1719296 }, { "epoch": 1.01, "learning_rate": 2.1843837278550387e-05, "loss": 3.4555, "step": 1719808 }, { "epoch": 1.01, "learning_rate": 2.1835451331039867e-05, "loss": 3.4536, "step": 1720320 }, { "epoch": 1.01, "learning_rate": 2.1827081762333076e-05, "loss": 3.4474, "step": 1720832 }, { "epoch": 1.01, "learning_rate": 2.1818695814822556e-05, "loss": 3.455, "step": 1721344 }, { "epoch": 1.01, "learning_rate": 2.1810309867312036e-05, "loss": 3.4334, "step": 1721856 }, { "epoch": 1.01, "learning_rate": 2.180192391980152e-05, "loss": 3.4414, "step": 1722368 }, { "epoch": 1.01, "learning_rate": 2.1793537972290996e-05, "loss": 3.4496, "step": 1722880 }, { "epoch": 1.01, "learning_rate": 2.1785152024780475e-05, "loss": 3.4531, "step": 1723392 }, { "epoch": 1.01, "learning_rate": 2.1776782456073688e-05, "loss": 3.4446, "step": 1723904 }, { "epoch": 1.01, "learning_rate": 2.1768396508563168e-05, "loss": 3.4519, "step": 1724416 }, { "epoch": 1.02, "learning_rate": 2.1760010561052644e-05, "loss": 3.4353, "step": 1724928 }, { "epoch": 1.02, "learning_rate": 2.1751624613542128e-05, "loss": 3.4496, "step": 1725440 }, { "epoch": 1.02, "learning_rate": 2.1743238666031608e-05, "loss": 3.4384, "step": 1725952 }, { "epoch": 1.02, "learning_rate": 2.1734852718521088e-05, "loss": 3.4482, "step": 1726464 }, { "epoch": 1.02, "learning_rate": 2.1726483149814297e-05, "loss": 3.4612, "step": 1726976 }, { "epoch": 1.02, "learning_rate": 2.1718097202303777e-05, "loss": 3.4524, "step": 1727488 }, { "epoch": 1.02, "learning_rate": 2.1709711254793257e-05, "loss": 3.4537, "step": 1728000 }, { "epoch": 1.02, "learning_rate": 2.1701325307282737e-05, "loss": 3.4405, "step": 1728512 }, { "epoch": 1.02, "learning_rate": 2.169293935977222e-05, "loss": 3.4465, "step": 1729024 }, { "epoch": 1.02, "learning_rate": 2.16845534122617e-05, "loss": 3.4502, "step": 1729536 }, { "epoch": 1.02, "learning_rate": 2.1676167464751177e-05, "loss": 3.4587, "step": 1730048 }, { "epoch": 1.02, "learning_rate": 2.1667781517240657e-05, "loss": 3.4557, "step": 1730560 }, { "epoch": 1.02, "learning_rate": 2.165941194853387e-05, "loss": 3.4562, "step": 1731072 }, { "epoch": 1.02, "learning_rate": 2.165102600102335e-05, "loss": 3.4412, "step": 1731584 }, { "epoch": 1.02, "learning_rate": 2.164264005351283e-05, "loss": 3.4586, "step": 1732096 }, { "epoch": 1.02, "learning_rate": 2.163425410600231e-05, "loss": 3.4422, "step": 1732608 }, { "epoch": 1.02, "learning_rate": 2.162588453729552e-05, "loss": 3.4553, "step": 1733120 }, { "epoch": 1.02, "learning_rate": 2.1617498589784998e-05, "loss": 3.4338, "step": 1733632 }, { "epoch": 1.02, "learning_rate": 2.1609112642274478e-05, "loss": 3.4552, "step": 1734144 }, { "epoch": 1.02, "learning_rate": 2.160074307356769e-05, "loss": 3.4383, "step": 1734656 }, { "epoch": 1.02, "learning_rate": 2.1592357126057174e-05, "loss": 3.4498, "step": 1735168 }, { "epoch": 1.02, "learning_rate": 2.158397117854665e-05, "loss": 3.4395, "step": 1735680 }, { "epoch": 1.02, "learning_rate": 2.157558523103613e-05, "loss": 3.4504, "step": 1736192 }, { "epoch": 1.02, "learning_rate": 2.1567215662329343e-05, "loss": 3.4433, "step": 1736704 }, { "epoch": 1.02, "learning_rate": 2.155882971481882e-05, "loss": 3.4435, "step": 1737216 }, { "epoch": 1.02, "learning_rate": 2.1550460146112035e-05, "loss": 3.4577, "step": 1737728 }, { "epoch": 1.02, "learning_rate": 2.1542074198601515e-05, "loss": 3.4595, "step": 1738240 }, { "epoch": 1.02, "learning_rate": 2.1533688251090995e-05, "loss": 3.4557, "step": 1738752 }, { "epoch": 1.02, "learning_rate": 2.152530230358047e-05, "loss": 3.4535, "step": 1739264 }, { "epoch": 1.02, "learning_rate": 2.151691635606995e-05, "loss": 3.4463, "step": 1739776 }, { "epoch": 1.02, "learning_rate": 2.150853040855943e-05, "loss": 3.445, "step": 1740288 }, { "epoch": 1.02, "learning_rate": 2.1500160839852644e-05, "loss": 3.4444, "step": 1740800 }, { "epoch": 1.02, "learning_rate": 2.1491774892342124e-05, "loss": 3.452, "step": 1741312 }, { "epoch": 1.02, "learning_rate": 2.1483388944831604e-05, "loss": 3.4373, "step": 1741824 }, { "epoch": 1.02, "learning_rate": 2.1475002997321084e-05, "loss": 3.4502, "step": 1742336 }, { "epoch": 1.02, "learning_rate": 2.1466633428614293e-05, "loss": 3.4488, "step": 1742848 }, { "epoch": 1.02, "learning_rate": 2.1458247481103773e-05, "loss": 3.4523, "step": 1743360 }, { "epoch": 1.02, "learning_rate": 2.1449861533593253e-05, "loss": 3.447, "step": 1743872 }, { "epoch": 1.02, "learning_rate": 2.1441475586082736e-05, "loss": 3.4462, "step": 1744384 }, { "epoch": 1.02, "learning_rate": 2.1433089638572216e-05, "loss": 3.4421, "step": 1744896 }, { "epoch": 1.02, "learning_rate": 2.1424703691061696e-05, "loss": 3.4562, "step": 1745408 }, { "epoch": 1.02, "learning_rate": 2.1416317743551176e-05, "loss": 3.4514, "step": 1745920 }, { "epoch": 1.02, "learning_rate": 2.1407931796040653e-05, "loss": 3.4579, "step": 1746432 }, { "epoch": 1.02, "learning_rate": 2.1399562227333865e-05, "loss": 3.44, "step": 1746944 }, { "epoch": 1.02, "learning_rate": 2.1391176279823345e-05, "loss": 3.4538, "step": 1747456 }, { "epoch": 1.02, "learning_rate": 2.138279033231283e-05, "loss": 3.4508, "step": 1747968 }, { "epoch": 1.02, "learning_rate": 2.1374404384802305e-05, "loss": 3.4467, "step": 1748480 }, { "epoch": 1.02, "learning_rate": 2.1366034816095518e-05, "loss": 3.45, "step": 1748992 }, { "epoch": 1.02, "learning_rate": 2.1357648868584997e-05, "loss": 3.4528, "step": 1749504 }, { "epoch": 1.02, "learning_rate": 2.1349262921074474e-05, "loss": 3.4506, "step": 1750016 }, { "epoch": 1.02, "learning_rate": 2.1340876973563957e-05, "loss": 3.4642, "step": 1750528 }, { "epoch": 1.02, "learning_rate": 2.133250740485717e-05, "loss": 3.4446, "step": 1751040 }, { "epoch": 1.02, "learning_rate": 2.132412145734665e-05, "loss": 3.4525, "step": 1751552 }, { "epoch": 1.02, "learning_rate": 2.1315735509836126e-05, "loss": 3.4464, "step": 1752064 }, { "epoch": 1.02, "learning_rate": 2.1307349562325606e-05, "loss": 3.4513, "step": 1752576 }, { "epoch": 1.02, "learning_rate": 2.129899637242255e-05, "loss": 3.4454, "step": 1753088 }, { "epoch": 1.02, "learning_rate": 2.129061042491203e-05, "loss": 3.4425, "step": 1753600 }, { "epoch": 1.02, "learning_rate": 2.128222447740151e-05, "loss": 3.4503, "step": 1754112 }, { "epoch": 1.02, "learning_rate": 2.127383852989099e-05, "loss": 3.4333, "step": 1754624 }, { "epoch": 1.02, "learning_rate": 2.126545258238047e-05, "loss": 3.4536, "step": 1755136 }, { "epoch": 1.03, "eval_loss": 3.862443447113037, "eval_runtime": 306.7713, "eval_samples_per_second": 1243.894, "eval_steps_per_second": 38.873, "step": 1755350 }, { "epoch": 0.0, "learning_rate": 2.1257066634869948e-05, "loss": 3.4538, "step": 1755648 }, { "epoch": 0.0, "learning_rate": 2.1248680687359428e-05, "loss": 3.4442, "step": 1756160 }, { "epoch": 0.0, "learning_rate": 2.124029473984891e-05, "loss": 3.4522, "step": 1756672 }, { "epoch": 0.0, "learning_rate": 2.123190879233839e-05, "loss": 3.4529, "step": 1757184 }, { "epoch": 0.0, "learning_rate": 2.12235392236316e-05, "loss": 3.4609, "step": 1757696 }, { "epoch": 0.0, "learning_rate": 2.1215169654924813e-05, "loss": 3.4474, "step": 1758208 }, { "epoch": 0.0, "learning_rate": 2.1206783707414293e-05, "loss": 3.4497, "step": 1758720 }, { "epoch": 0.0, "learning_rate": 2.1198397759903773e-05, "loss": 3.4403, "step": 1759232 }, { "epoch": 0.0, "learning_rate": 2.1190011812393252e-05, "loss": 3.4422, "step": 1759744 }, { "epoch": 0.0, "learning_rate": 2.1181625864882732e-05, "loss": 3.4497, "step": 1760256 }, { "epoch": 0.0, "learning_rate": 2.1173239917372212e-05, "loss": 3.449, "step": 1760768 }, { "epoch": 0.0, "learning_rate": 2.1164853969861692e-05, "loss": 3.4417, "step": 1761280 }, { "epoch": 0.0, "learning_rate": 2.1156468022351172e-05, "loss": 3.4439, "step": 1761792 }, { "epoch": 0.0, "learning_rate": 2.114809845364438e-05, "loss": 3.4361, "step": 1762304 }, { "epoch": 0.0, "learning_rate": 2.113971250613386e-05, "loss": 3.4389, "step": 1762816 }, { "epoch": 0.0, "learning_rate": 2.1131326558623345e-05, "loss": 3.4354, "step": 1763328 }, { "epoch": 0.0, "learning_rate": 2.1122940611112825e-05, "loss": 3.4349, "step": 1763840 }, { "epoch": 0.0, "learning_rate": 2.1114571042406034e-05, "loss": 3.4482, "step": 1764352 }, { "epoch": 0.0, "learning_rate": 2.1106185094895514e-05, "loss": 3.4372, "step": 1764864 }, { "epoch": 0.0, "learning_rate": 2.1097799147384994e-05, "loss": 3.4598, "step": 1765376 }, { "epoch": 0.0, "learning_rate": 2.1089413199874474e-05, "loss": 3.4514, "step": 1765888 }, { "epoch": 0.0, "learning_rate": 2.1081043631167686e-05, "loss": 3.4545, "step": 1766400 }, { "epoch": 0.0, "learning_rate": 2.1072657683657166e-05, "loss": 3.4391, "step": 1766912 }, { "epoch": 0.0, "learning_rate": 2.1064271736146646e-05, "loss": 3.443, "step": 1767424 }, { "epoch": 0.0, "learning_rate": 2.1055885788636126e-05, "loss": 3.4452, "step": 1767936 }, { "epoch": 0.0, "learning_rate": 2.1047532598733068e-05, "loss": 3.4541, "step": 1768448 }, { "epoch": 0.0, "learning_rate": 2.1039146651222548e-05, "loss": 3.4413, "step": 1768960 }, { "epoch": 0.0, "learning_rate": 2.1030760703712027e-05, "loss": 3.4441, "step": 1769472 }, { "epoch": 0.0, "learning_rate": 2.1022374756201507e-05, "loss": 3.4364, "step": 1769984 }, { "epoch": 0.0, "learning_rate": 2.1013988808690987e-05, "loss": 3.4434, "step": 1770496 }, { "epoch": 0.01, "learning_rate": 2.1005602861180467e-05, "loss": 3.4441, "step": 1771008 }, { "epoch": 0.01, "learning_rate": 2.0997233292473676e-05, "loss": 3.4516, "step": 1771520 }, { "epoch": 0.01, "learning_rate": 2.098884734496316e-05, "loss": 3.4486, "step": 1772032 }, { "epoch": 0.01, "learning_rate": 2.098046139745264e-05, "loss": 3.451, "step": 1772544 }, { "epoch": 0.01, "learning_rate": 2.097207544994212e-05, "loss": 3.4441, "step": 1773056 }, { "epoch": 0.01, "learning_rate": 2.09636895024316e-05, "loss": 3.4471, "step": 1773568 }, { "epoch": 0.01, "learning_rate": 2.0955303554921076e-05, "loss": 3.4509, "step": 1774080 }, { "epoch": 0.01, "learning_rate": 2.0946917607410556e-05, "loss": 3.4379, "step": 1774592 }, { "epoch": 0.01, "learning_rate": 2.093854803870377e-05, "loss": 3.4353, "step": 1775104 }, { "epoch": 0.01, "learning_rate": 2.0930162091193252e-05, "loss": 3.428, "step": 1775616 }, { "epoch": 0.01, "learning_rate": 2.092177614368273e-05, "loss": 3.4415, "step": 1776128 }, { "epoch": 0.01, "learning_rate": 2.091339019617221e-05, "loss": 3.4422, "step": 1776640 }, { "epoch": 0.01, "learning_rate": 2.090500424866169e-05, "loss": 3.4467, "step": 1777152 }, { "epoch": 0.01, "learning_rate": 2.089661830115117e-05, "loss": 3.4422, "step": 1777664 }, { "epoch": 0.01, "learning_rate": 2.088823235364065e-05, "loss": 3.4408, "step": 1778176 }, { "epoch": 0.01, "learning_rate": 2.087986278493386e-05, "loss": 3.4421, "step": 1778688 }, { "epoch": 0.01, "learning_rate": 2.087147683742334e-05, "loss": 3.4456, "step": 1779200 }, { "epoch": 0.01, "learning_rate": 2.086309088991282e-05, "loss": 3.4304, "step": 1779712 }, { "epoch": 0.01, "learning_rate": 2.08547049424023e-05, "loss": 3.4186, "step": 1780224 }, { "epoch": 0.01, "learning_rate": 2.084633537369551e-05, "loss": 3.4539, "step": 1780736 }, { "epoch": 0.01, "learning_rate": 2.083794942618499e-05, "loss": 3.446, "step": 1781248 }, { "epoch": 0.01, "learning_rate": 2.082956347867447e-05, "loss": 3.4541, "step": 1781760 }, { "epoch": 0.01, "learning_rate": 2.0821177531163953e-05, "loss": 3.4375, "step": 1782272 }, { "epoch": 0.01, "learning_rate": 2.0812807962457162e-05, "loss": 3.4381, "step": 1782784 }, { "epoch": 0.01, "learning_rate": 2.0804422014946642e-05, "loss": 3.4326, "step": 1783296 }, { "epoch": 0.01, "learning_rate": 2.0796036067436122e-05, "loss": 3.4395, "step": 1783808 }, { "epoch": 0.01, "learning_rate": 2.0787650119925602e-05, "loss": 3.4462, "step": 1784320 }, { "epoch": 0.01, "learning_rate": 2.0779280551218815e-05, "loss": 3.433, "step": 1784832 }, { "epoch": 0.01, "learning_rate": 2.0770894603708295e-05, "loss": 3.4635, "step": 1785344 }, { "epoch": 0.01, "learning_rate": 2.0762508656197774e-05, "loss": 3.4404, "step": 1785856 }, { "epoch": 0.01, "learning_rate": 2.0754122708687254e-05, "loss": 3.4251, "step": 1786368 }, { "epoch": 0.01, "learning_rate": 2.074573676117673e-05, "loss": 3.453, "step": 1786880 }, { "epoch": 0.01, "learning_rate": 2.073735081366621e-05, "loss": 3.4298, "step": 1787392 }, { "epoch": 0.01, "learning_rate": 2.072896486615569e-05, "loss": 3.4238, "step": 1787904 }, { "epoch": 0.01, "learning_rate": 2.0720578918645174e-05, "loss": 3.4514, "step": 1788416 }, { "epoch": 0.01, "learning_rate": 2.0712225728742116e-05, "loss": 3.4451, "step": 1788928 }, { "epoch": 0.01, "learning_rate": 2.0703839781231596e-05, "loss": 3.4318, "step": 1789440 }, { "epoch": 0.01, "learning_rate": 2.0695453833721076e-05, "loss": 3.4385, "step": 1789952 }, { "epoch": 0.01, "learning_rate": 2.0687067886210552e-05, "loss": 3.4226, "step": 1790464 }, { "epoch": 0.01, "learning_rate": 2.0678681938700036e-05, "loss": 3.4371, "step": 1790976 }, { "epoch": 0.01, "learning_rate": 2.0670295991189516e-05, "loss": 3.441, "step": 1791488 }, { "epoch": 0.01, "learning_rate": 2.0661910043678996e-05, "loss": 3.4333, "step": 1792000 }, { "epoch": 0.01, "learning_rate": 2.0653524096168476e-05, "loss": 3.4457, "step": 1792512 }, { "epoch": 0.01, "learning_rate": 2.0645154527461685e-05, "loss": 3.4416, "step": 1793024 }, { "epoch": 0.01, "learning_rate": 2.0636768579951165e-05, "loss": 3.4483, "step": 1793536 }, { "epoch": 0.01, "learning_rate": 2.0628382632440645e-05, "loss": 3.4375, "step": 1794048 }, { "epoch": 0.01, "learning_rate": 2.0620013063733857e-05, "loss": 3.4441, "step": 1794560 }, { "epoch": 0.01, "learning_rate": 2.0611627116223337e-05, "loss": 3.4411, "step": 1795072 }, { "epoch": 0.01, "learning_rate": 2.0603241168712817e-05, "loss": 3.4357, "step": 1795584 }, { "epoch": 0.01, "learning_rate": 2.0594855221202297e-05, "loss": 3.4458, "step": 1796096 }, { "epoch": 0.01, "learning_rate": 2.0586469273691777e-05, "loss": 3.4434, "step": 1796608 }, { "epoch": 0.01, "learning_rate": 2.057809970498499e-05, "loss": 3.4365, "step": 1797120 }, { "epoch": 0.01, "learning_rate": 2.056971375747447e-05, "loss": 3.4446, "step": 1797632 }, { "epoch": 0.01, "learning_rate": 2.056132780996395e-05, "loss": 3.4213, "step": 1798144 }, { "epoch": 0.01, "learning_rate": 2.055294186245343e-05, "loss": 3.429, "step": 1798656 }, { "epoch": 0.01, "learning_rate": 2.054455591494291e-05, "loss": 3.4415, "step": 1799168 }, { "epoch": 0.01, "learning_rate": 2.0536169967432386e-05, "loss": 3.4455, "step": 1799680 }, { "epoch": 0.01, "learning_rate": 2.0527784019921866e-05, "loss": 3.4321, "step": 1800192 }, { "epoch": 0.01, "learning_rate": 2.0519414451215078e-05, "loss": 3.4407, "step": 1800704 }, { "epoch": 0.02, "learning_rate": 2.051102850370456e-05, "loss": 3.4241, "step": 1801216 }, { "epoch": 0.02, "learning_rate": 2.0502642556194038e-05, "loss": 3.4353, "step": 1801728 }, { "epoch": 0.02, "learning_rate": 2.0494256608683518e-05, "loss": 3.4299, "step": 1802240 }, { "epoch": 0.02, "learning_rate": 2.0485870661172998e-05, "loss": 3.4374, "step": 1802752 }, { "epoch": 0.02, "learning_rate": 2.0477501092466207e-05, "loss": 3.4472, "step": 1803264 }, { "epoch": 0.02, "learning_rate": 2.046911514495569e-05, "loss": 3.4397, "step": 1803776 }, { "epoch": 0.02, "learning_rate": 2.046072919744517e-05, "loss": 3.4452, "step": 1804288 }, { "epoch": 0.02, "learning_rate": 2.045234324993465e-05, "loss": 3.4296, "step": 1804800 }, { "epoch": 0.02, "learning_rate": 2.044395730242413e-05, "loss": 3.4374, "step": 1805312 }, { "epoch": 0.02, "learning_rate": 2.043557135491361e-05, "loss": 3.4371, "step": 1805824 }, { "epoch": 0.02, "learning_rate": 2.042718540740309e-05, "loss": 3.4463, "step": 1806336 }, { "epoch": 0.02, "learning_rate": 2.0418799459892567e-05, "loss": 3.444, "step": 1806848 }, { "epoch": 0.02, "learning_rate": 2.0410429891185783e-05, "loss": 3.4473, "step": 1807360 }, { "epoch": 0.02, "learning_rate": 2.0402043943675263e-05, "loss": 3.4314, "step": 1807872 }, { "epoch": 0.02, "learning_rate": 2.039365799616474e-05, "loss": 3.4427, "step": 1808384 }, { "epoch": 0.02, "learning_rate": 2.038527204865422e-05, "loss": 3.4346, "step": 1808896 }, { "epoch": 0.02, "learning_rate": 2.037690247994743e-05, "loss": 3.4422, "step": 1809408 }, { "epoch": 0.02, "learning_rate": 2.036851653243691e-05, "loss": 3.4263, "step": 1809920 }, { "epoch": 0.02, "learning_rate": 2.036013058492639e-05, "loss": 3.4463, "step": 1810432 }, { "epoch": 0.02, "learning_rate": 2.035174463741587e-05, "loss": 3.4284, "step": 1810944 }, { "epoch": 0.02, "learning_rate": 2.0343375068709084e-05, "loss": 3.4402, "step": 1811456 }, { "epoch": 0.02, "learning_rate": 2.0334989121198564e-05, "loss": 3.4266, "step": 1811968 }, { "epoch": 0.02, "learning_rate": 2.032660317368804e-05, "loss": 3.4396, "step": 1812480 }, { "epoch": 0.02, "learning_rate": 2.0318233604981253e-05, "loss": 3.4361, "step": 1812992 }, { "epoch": 0.02, "learning_rate": 2.0309847657470736e-05, "loss": 3.4309, "step": 1813504 }, { "epoch": 0.02, "learning_rate": 2.0301478088763945e-05, "loss": 3.4468, "step": 1814016 }, { "epoch": 0.02, "learning_rate": 2.0293092141253425e-05, "loss": 3.4504, "step": 1814528 }, { "epoch": 0.02, "learning_rate": 2.0284706193742905e-05, "loss": 3.4486, "step": 1815040 }, { "epoch": 0.02, "learning_rate": 2.0276320246232385e-05, "loss": 3.4411, "step": 1815552 }, { "epoch": 0.02, "learning_rate": 2.0267934298721862e-05, "loss": 3.4344, "step": 1816064 }, { "epoch": 0.02, "learning_rate": 2.0259548351211345e-05, "loss": 3.4326, "step": 1816576 }, { "epoch": 0.02, "learning_rate": 2.0251162403700825e-05, "loss": 3.4363, "step": 1817088 }, { "epoch": 0.02, "learning_rate": 2.0242776456190305e-05, "loss": 3.438, "step": 1817600 }, { "epoch": 0.02, "learning_rate": 2.0234406887483514e-05, "loss": 3.4266, "step": 1818112 }, { "epoch": 0.02, "learning_rate": 2.0226020939972994e-05, "loss": 3.4412, "step": 1818624 }, { "epoch": 0.02, "learning_rate": 2.0217651371266207e-05, "loss": 3.4403, "step": 1819136 }, { "epoch": 0.02, "learning_rate": 2.0209265423755687e-05, "loss": 3.4383, "step": 1819648 }, { "epoch": 0.02, "learning_rate": 2.0200879476245167e-05, "loss": 3.4368, "step": 1820160 }, { "epoch": 0.02, "learning_rate": 2.0192493528734647e-05, "loss": 3.4346, "step": 1820672 }, { "epoch": 0.02, "learning_rate": 2.0184107581224126e-05, "loss": 3.4307, "step": 1821184 }, { "epoch": 0.02, "learning_rate": 2.0175721633713606e-05, "loss": 3.4452, "step": 1821696 }, { "epoch": 0.02, "learning_rate": 2.0167335686203086e-05, "loss": 3.4417, "step": 1822208 }, { "epoch": 0.02, "learning_rate": 2.0158949738692566e-05, "loss": 3.4474, "step": 1822720 }, { "epoch": 0.02, "learning_rate": 2.015058016998578e-05, "loss": 3.4277, "step": 1823232 }, { "epoch": 0.02, "learning_rate": 2.014219422247526e-05, "loss": 3.4435, "step": 1823744 }, { "epoch": 0.02, "learning_rate": 2.013380827496474e-05, "loss": 3.4395, "step": 1824256 }, { "epoch": 0.02, "learning_rate": 2.012542232745422e-05, "loss": 3.4369, "step": 1824768 }, { "epoch": 0.02, "learning_rate": 2.0117052758747428e-05, "loss": 3.4417, "step": 1825280 }, { "epoch": 0.02, "learning_rate": 2.0108666811236908e-05, "loss": 3.4363, "step": 1825792 }, { "epoch": 0.02, "learning_rate": 2.010028086372639e-05, "loss": 3.4441, "step": 1826304 }, { "epoch": 0.02, "learning_rate": 2.0091894916215868e-05, "loss": 3.4564, "step": 1826816 }, { "epoch": 0.02, "learning_rate": 2.008352534750908e-05, "loss": 3.4324, "step": 1827328 }, { "epoch": 0.02, "learning_rate": 2.007513939999856e-05, "loss": 3.4416, "step": 1827840 }, { "epoch": 0.02, "learning_rate": 2.006675345248804e-05, "loss": 3.442, "step": 1828352 }, { "epoch": 0.02, "learning_rate": 2.0058367504977517e-05, "loss": 3.4363, "step": 1828864 }, { "epoch": 0.02, "learning_rate": 2.005001431507446e-05, "loss": 3.4344, "step": 1829376 }, { "epoch": 0.02, "learning_rate": 2.004162836756394e-05, "loss": 3.4313, "step": 1829888 }, { "epoch": 0.02, "learning_rate": 2.003324242005342e-05, "loss": 3.4394, "step": 1830400 }, { "epoch": 0.02, "learning_rate": 2.00248564725429e-05, "loss": 3.4229, "step": 1830912 }, { "epoch": 0.02, "learning_rate": 2.001647052503238e-05, "loss": 3.4406, "step": 1831424 }, { "epoch": 0.03, "eval_loss": 3.863980293273926, "eval_runtime": 303.9516, "eval_samples_per_second": 1255.433, "eval_steps_per_second": 39.233, "step": 1831670 }, { "epoch": 1.0, "learning_rate": 2.000808457752186e-05, "loss": 3.4391, "step": 1831936 }, { "epoch": 1.0, "learning_rate": 1.999969863001134e-05, "loss": 3.4351, "step": 1832448 }, { "epoch": 1.0, "learning_rate": 1.999131268250082e-05, "loss": 3.4371, "step": 1832960 }, { "epoch": 1.0, "learning_rate": 1.9982943113794034e-05, "loss": 3.4429, "step": 1833472 }, { "epoch": 1.0, "learning_rate": 1.9974557166283514e-05, "loss": 3.4503, "step": 1833984 }, { "epoch": 1.0, "learning_rate": 1.9966187597576723e-05, "loss": 3.4371, "step": 1834496 }, { "epoch": 1.0, "learning_rate": 1.9957801650066206e-05, "loss": 3.4393, "step": 1835008 }, { "epoch": 1.0, "learning_rate": 1.9949415702555686e-05, "loss": 3.4293, "step": 1835520 }, { "epoch": 1.0, "learning_rate": 1.9941029755045166e-05, "loss": 3.4286, "step": 1836032 }, { "epoch": 1.0, "learning_rate": 1.9932660186338375e-05, "loss": 3.4425, "step": 1836544 }, { "epoch": 1.0, "learning_rate": 1.9924274238827855e-05, "loss": 3.4361, "step": 1837056 }, { "epoch": 1.0, "learning_rate": 1.9915888291317335e-05, "loss": 3.4285, "step": 1837568 }, { "epoch": 1.0, "learning_rate": 1.9907502343806815e-05, "loss": 3.4361, "step": 1838080 }, { "epoch": 1.0, "learning_rate": 1.9899116396296295e-05, "loss": 3.4225, "step": 1838592 }, { "epoch": 1.0, "learning_rate": 1.9890730448785775e-05, "loss": 3.4255, "step": 1839104 }, { "epoch": 1.0, "learning_rate": 1.9882344501275255e-05, "loss": 3.4239, "step": 1839616 }, { "epoch": 1.0, "learning_rate": 1.9873958553764735e-05, "loss": 3.4281, "step": 1840128 }, { "epoch": 1.0, "learning_rate": 1.9865588985057944e-05, "loss": 3.4341, "step": 1840640 }, { "epoch": 1.0, "learning_rate": 1.9857203037547424e-05, "loss": 3.4288, "step": 1841152 }, { "epoch": 1.0, "learning_rate": 1.9848817090036907e-05, "loss": 3.4462, "step": 1841664 }, { "epoch": 1.0, "learning_rate": 1.9840431142526387e-05, "loss": 3.4432, "step": 1842176 }, { "epoch": 1.0, "learning_rate": 1.9832061573819596e-05, "loss": 3.4427, "step": 1842688 }, { "epoch": 1.0, "learning_rate": 1.9823675626309076e-05, "loss": 3.4323, "step": 1843200 }, { "epoch": 1.0, "learning_rate": 1.9815289678798556e-05, "loss": 3.4341, "step": 1843712 }, { "epoch": 1.0, "learning_rate": 1.9806903731288036e-05, "loss": 3.4366, "step": 1844224 }, { "epoch": 1.0, "learning_rate": 1.979855054138498e-05, "loss": 3.4425, "step": 1844736 }, { "epoch": 1.0, "learning_rate": 1.979016459387446e-05, "loss": 3.4291, "step": 1845248 }, { "epoch": 1.0, "learning_rate": 1.9781778646363938e-05, "loss": 3.4369, "step": 1845760 }, { "epoch": 1.0, "learning_rate": 1.9773392698853418e-05, "loss": 3.4208, "step": 1846272 }, { "epoch": 1.0, "learning_rate": 1.9765006751342898e-05, "loss": 3.4343, "step": 1846784 }, { "epoch": 1.01, "learning_rate": 1.9756620803832378e-05, "loss": 3.4318, "step": 1847296 }, { "epoch": 1.01, "learning_rate": 1.974825123512559e-05, "loss": 3.4392, "step": 1847808 }, { "epoch": 1.01, "learning_rate": 1.973986528761507e-05, "loss": 3.4415, "step": 1848320 }, { "epoch": 1.01, "learning_rate": 1.973147934010455e-05, "loss": 3.4441, "step": 1848832 }, { "epoch": 1.01, "learning_rate": 1.972309339259403e-05, "loss": 3.4284, "step": 1849344 }, { "epoch": 1.01, "learning_rate": 1.971470744508351e-05, "loss": 3.4355, "step": 1849856 }, { "epoch": 1.01, "learning_rate": 1.970632149757299e-05, "loss": 3.4404, "step": 1850368 }, { "epoch": 1.01, "learning_rate": 1.969793555006247e-05, "loss": 3.4246, "step": 1850880 }, { "epoch": 1.01, "learning_rate": 1.9689565981355682e-05, "loss": 3.428, "step": 1851392 }, { "epoch": 1.01, "learning_rate": 1.9681180033845162e-05, "loss": 3.42, "step": 1851904 }, { "epoch": 1.01, "learning_rate": 1.9672794086334642e-05, "loss": 3.4273, "step": 1852416 }, { "epoch": 1.01, "learning_rate": 1.966440813882412e-05, "loss": 3.4281, "step": 1852928 }, { "epoch": 1.01, "learning_rate": 1.96560221913136e-05, "loss": 3.4381, "step": 1853440 }, { "epoch": 1.01, "learning_rate": 1.964763624380308e-05, "loss": 3.4321, "step": 1853952 }, { "epoch": 1.01, "learning_rate": 1.9639250296292562e-05, "loss": 3.428, "step": 1854464 }, { "epoch": 1.01, "learning_rate": 1.9630864348782042e-05, "loss": 3.4304, "step": 1854976 }, { "epoch": 1.01, "learning_rate": 1.962249478007525e-05, "loss": 3.4356, "step": 1855488 }, { "epoch": 1.01, "learning_rate": 1.961410883256473e-05, "loss": 3.4192, "step": 1856000 }, { "epoch": 1.01, "learning_rate": 1.960572288505421e-05, "loss": 3.4077, "step": 1856512 }, { "epoch": 1.01, "learning_rate": 1.9597353316347424e-05, "loss": 3.4413, "step": 1857024 }, { "epoch": 1.01, "learning_rate": 1.9588967368836903e-05, "loss": 3.4369, "step": 1857536 }, { "epoch": 1.01, "learning_rate": 1.9580581421326383e-05, "loss": 3.4401, "step": 1858048 }, { "epoch": 1.01, "learning_rate": 1.9572195473815863e-05, "loss": 3.43, "step": 1858560 }, { "epoch": 1.01, "learning_rate": 1.9563825905109072e-05, "loss": 3.4293, "step": 1859072 }, { "epoch": 1.01, "learning_rate": 1.9555439957598552e-05, "loss": 3.4236, "step": 1859584 }, { "epoch": 1.01, "learning_rate": 1.9547054010088032e-05, "loss": 3.4276, "step": 1860096 }, { "epoch": 1.01, "learning_rate": 1.9538668062577516e-05, "loss": 3.4382, "step": 1860608 }, { "epoch": 1.01, "learning_rate": 1.9530298493870725e-05, "loss": 3.4197, "step": 1861120 }, { "epoch": 1.01, "learning_rate": 1.9521912546360205e-05, "loss": 3.4515, "step": 1861632 }, { "epoch": 1.01, "learning_rate": 1.9513526598849685e-05, "loss": 3.4292, "step": 1862144 }, { "epoch": 1.01, "learning_rate": 1.9505140651339165e-05, "loss": 3.4127, "step": 1862656 }, { "epoch": 1.01, "learning_rate": 1.9496754703828645e-05, "loss": 3.4401, "step": 1863168 }, { "epoch": 1.01, "learning_rate": 1.9488368756318125e-05, "loss": 3.4242, "step": 1863680 }, { "epoch": 1.01, "learning_rate": 1.9479982808807605e-05, "loss": 3.4102, "step": 1864192 }, { "epoch": 1.01, "learning_rate": 1.9471596861297085e-05, "loss": 3.4407, "step": 1864704 }, { "epoch": 1.01, "learning_rate": 1.9463243671394026e-05, "loss": 3.4365, "step": 1865216 }, { "epoch": 1.01, "learning_rate": 1.9454857723883506e-05, "loss": 3.4212, "step": 1865728 }, { "epoch": 1.01, "learning_rate": 1.9446471776372986e-05, "loss": 3.4247, "step": 1866240 }, { "epoch": 1.01, "learning_rate": 1.943808582886247e-05, "loss": 3.4134, "step": 1866752 }, { "epoch": 1.01, "learning_rate": 1.9429699881351946e-05, "loss": 3.4236, "step": 1867264 }, { "epoch": 1.01, "learning_rate": 1.9421313933841426e-05, "loss": 3.4348, "step": 1867776 }, { "epoch": 1.01, "learning_rate": 1.9412927986330906e-05, "loss": 3.4217, "step": 1868288 }, { "epoch": 1.01, "learning_rate": 1.9404542038820386e-05, "loss": 3.4343, "step": 1868800 }, { "epoch": 1.01, "learning_rate": 1.9396172470113595e-05, "loss": 3.426, "step": 1869312 }, { "epoch": 1.01, "learning_rate": 1.9387786522603078e-05, "loss": 3.4383, "step": 1869824 }, { "epoch": 1.01, "learning_rate": 1.9379400575092558e-05, "loss": 3.4285, "step": 1870336 }, { "epoch": 1.01, "learning_rate": 1.937103100638577e-05, "loss": 3.4357, "step": 1870848 }, { "epoch": 1.01, "learning_rate": 1.9362645058875247e-05, "loss": 3.4268, "step": 1871360 }, { "epoch": 1.01, "learning_rate": 1.9354259111364727e-05, "loss": 3.4237, "step": 1871872 }, { "epoch": 1.01, "learning_rate": 1.9345873163854207e-05, "loss": 3.4373, "step": 1872384 }, { "epoch": 1.01, "learning_rate": 1.9337487216343687e-05, "loss": 3.4296, "step": 1872896 }, { "epoch": 1.01, "learning_rate": 1.93291176476369e-05, "loss": 3.428, "step": 1873408 }, { "epoch": 1.01, "learning_rate": 1.932073170012638e-05, "loss": 3.4339, "step": 1873920 }, { "epoch": 1.01, "learning_rate": 1.931234575261586e-05, "loss": 3.4114, "step": 1874432 }, { "epoch": 1.01, "learning_rate": 1.930395980510534e-05, "loss": 3.4212, "step": 1874944 }, { "epoch": 1.01, "learning_rate": 1.929557385759482e-05, "loss": 3.4275, "step": 1875456 }, { "epoch": 1.01, "learning_rate": 1.92871879100843e-05, "loss": 3.4336, "step": 1875968 }, { "epoch": 1.01, "learning_rate": 1.927880196257378e-05, "loss": 3.4187, "step": 1876480 }, { "epoch": 1.01, "learning_rate": 1.9270432393866992e-05, "loss": 3.4336, "step": 1876992 }, { "epoch": 1.02, "learning_rate": 1.9262046446356472e-05, "loss": 3.4168, "step": 1877504 }, { "epoch": 1.02, "learning_rate": 1.925366049884595e-05, "loss": 3.4246, "step": 1878016 }, { "epoch": 1.02, "learning_rate": 1.924527455133543e-05, "loss": 3.4182, "step": 1878528 }, { "epoch": 1.02, "learning_rate": 1.9236888603824908e-05, "loss": 3.4229, "step": 1879040 }, { "epoch": 1.02, "learning_rate": 1.9228519035118124e-05, "loss": 3.4377, "step": 1879552 }, { "epoch": 1.02, "learning_rate": 1.92201330876076e-05, "loss": 3.4313, "step": 1880064 }, { "epoch": 1.02, "learning_rate": 1.921174714009708e-05, "loss": 3.4334, "step": 1880576 }, { "epoch": 1.02, "learning_rate": 1.920336119258656e-05, "loss": 3.4214, "step": 1881088 }, { "epoch": 1.02, "learning_rate": 1.919497524507604e-05, "loss": 3.4231, "step": 1881600 }, { "epoch": 1.02, "learning_rate": 1.918658929756552e-05, "loss": 3.4283, "step": 1882112 }, { "epoch": 1.02, "learning_rate": 1.9178203350055e-05, "loss": 3.4335, "step": 1882624 }, { "epoch": 1.02, "learning_rate": 1.916981740254448e-05, "loss": 3.429, "step": 1883136 }, { "epoch": 1.02, "learning_rate": 1.9161447833837693e-05, "loss": 3.4356, "step": 1883648 }, { "epoch": 1.02, "learning_rate": 1.9153061886327173e-05, "loss": 3.4255, "step": 1884160 }, { "epoch": 1.02, "learning_rate": 1.9144675938816653e-05, "loss": 3.4266, "step": 1884672 }, { "epoch": 1.02, "learning_rate": 1.913628999130613e-05, "loss": 3.4298, "step": 1885184 }, { "epoch": 1.02, "learning_rate": 1.9127920422599342e-05, "loss": 3.4289, "step": 1885696 }, { "epoch": 1.02, "learning_rate": 1.9119534475088825e-05, "loss": 3.414, "step": 1886208 }, { "epoch": 1.02, "learning_rate": 1.9111148527578305e-05, "loss": 3.4378, "step": 1886720 }, { "epoch": 1.02, "learning_rate": 1.9102762580067782e-05, "loss": 3.4163, "step": 1887232 }, { "epoch": 1.02, "learning_rate": 1.9094393011360994e-05, "loss": 3.4254, "step": 1887744 }, { "epoch": 1.02, "learning_rate": 1.9086007063850474e-05, "loss": 3.4224, "step": 1888256 }, { "epoch": 1.02, "learning_rate": 1.9077621116339954e-05, "loss": 3.4233, "step": 1888768 }, { "epoch": 1.02, "learning_rate": 1.9069235168829434e-05, "loss": 3.425, "step": 1889280 }, { "epoch": 1.02, "learning_rate": 1.9060865600122647e-05, "loss": 3.4219, "step": 1889792 }, { "epoch": 1.02, "learning_rate": 1.9052496031415856e-05, "loss": 3.4339, "step": 1890304 }, { "epoch": 1.02, "learning_rate": 1.9044110083905336e-05, "loss": 3.4397, "step": 1890816 }, { "epoch": 1.02, "learning_rate": 1.9035724136394816e-05, "loss": 3.4351, "step": 1891328 }, { "epoch": 1.02, "learning_rate": 1.9027338188884296e-05, "loss": 3.4301, "step": 1891840 }, { "epoch": 1.02, "learning_rate": 1.901895224137378e-05, "loss": 3.4267, "step": 1892352 }, { "epoch": 1.02, "learning_rate": 1.9010566293863255e-05, "loss": 3.4211, "step": 1892864 }, { "epoch": 1.02, "learning_rate": 1.9002196725156468e-05, "loss": 3.4271, "step": 1893376 }, { "epoch": 1.02, "learning_rate": 1.8993810777645948e-05, "loss": 3.4279, "step": 1893888 }, { "epoch": 1.02, "learning_rate": 1.8985424830135428e-05, "loss": 3.4206, "step": 1894400 }, { "epoch": 1.02, "learning_rate": 1.8977038882624908e-05, "loss": 3.4264, "step": 1894912 }, { "epoch": 1.02, "learning_rate": 1.896866931391812e-05, "loss": 3.4299, "step": 1895424 }, { "epoch": 1.02, "learning_rate": 1.89602833664076e-05, "loss": 3.4267, "step": 1895936 }, { "epoch": 1.02, "learning_rate": 1.8951897418897077e-05, "loss": 3.4269, "step": 1896448 }, { "epoch": 1.02, "learning_rate": 1.8943511471386557e-05, "loss": 3.4244, "step": 1896960 }, { "epoch": 1.02, "learning_rate": 1.8935125523876037e-05, "loss": 3.4218, "step": 1897472 }, { "epoch": 1.02, "learning_rate": 1.8926739576365517e-05, "loss": 3.4333, "step": 1897984 }, { "epoch": 1.02, "learning_rate": 1.8918353628855e-05, "loss": 3.4271, "step": 1898496 }, { "epoch": 1.02, "learning_rate": 1.890996768134448e-05, "loss": 3.4427, "step": 1899008 }, { "epoch": 1.02, "learning_rate": 1.890159811263769e-05, "loss": 3.4169, "step": 1899520 }, { "epoch": 1.02, "learning_rate": 1.889321216512717e-05, "loss": 3.4275, "step": 1900032 }, { "epoch": 1.02, "learning_rate": 1.888482621761665e-05, "loss": 3.4295, "step": 1900544 }, { "epoch": 1.02, "learning_rate": 1.887644027010613e-05, "loss": 3.4271, "step": 1901056 }, { "epoch": 1.02, "learning_rate": 1.886807070139934e-05, "loss": 3.4278, "step": 1901568 }, { "epoch": 1.02, "learning_rate": 1.885968475388882e-05, "loss": 3.4289, "step": 1902080 }, { "epoch": 1.02, "learning_rate": 1.88512988063783e-05, "loss": 3.4309, "step": 1902592 }, { "epoch": 1.02, "learning_rate": 1.884291285886778e-05, "loss": 3.445, "step": 1903104 }, { "epoch": 1.02, "learning_rate": 1.883454329016099e-05, "loss": 3.4243, "step": 1903616 }, { "epoch": 1.02, "learning_rate": 1.882615734265047e-05, "loss": 3.4296, "step": 1904128 }, { "epoch": 1.02, "learning_rate": 1.881777139513995e-05, "loss": 3.4326, "step": 1904640 }, { "epoch": 1.02, "learning_rate": 1.8809385447629434e-05, "loss": 3.4233, "step": 1905152 }, { "epoch": 1.02, "learning_rate": 1.8801032257726375e-05, "loss": 3.4248, "step": 1905664 }, { "epoch": 1.02, "learning_rate": 1.8792646310215852e-05, "loss": 3.4214, "step": 1906176 }, { "epoch": 1.02, "learning_rate": 1.8784260362705332e-05, "loss": 3.4262, "step": 1906688 }, { "epoch": 1.02, "learning_rate": 1.8775874415194815e-05, "loss": 3.4187, "step": 1907200 }, { "epoch": 1.02, "learning_rate": 1.8767488467684295e-05, "loss": 3.4269, "step": 1907712 }, { "epoch": 1.03, "eval_loss": 3.8642468452453613, "eval_runtime": 302.8639, "eval_samples_per_second": 1259.942, "eval_steps_per_second": 39.374, "step": 1907990 }, { "epoch": 0.0, "learning_rate": 1.8759102520173775e-05, "loss": 3.4331, "step": 1908224 }, { "epoch": 0.0, "learning_rate": 1.8750716572663255e-05, "loss": 3.4225, "step": 1908736 }, { "epoch": 0.0, "learning_rate": 1.874233062515273e-05, "loss": 3.4274, "step": 1909248 }, { "epoch": 0.0, "learning_rate": 1.8733961056445944e-05, "loss": 3.434, "step": 1909760 }, { "epoch": 0.0, "learning_rate": 1.8725575108935424e-05, "loss": 3.4401, "step": 1910272 }, { "epoch": 0.0, "learning_rate": 1.8717189161424904e-05, "loss": 3.4295, "step": 1910784 }, { "epoch": 0.0, "learning_rate": 1.8708803213914384e-05, "loss": 3.4282, "step": 1911296 }, { "epoch": 0.0, "learning_rate": 1.8700417266403864e-05, "loss": 3.418, "step": 1911808 }, { "epoch": 0.0, "learning_rate": 1.8692047697697076e-05, "loss": 3.4179, "step": 1912320 }, { "epoch": 0.0, "learning_rate": 1.8683661750186556e-05, "loss": 3.4323, "step": 1912832 }, { "epoch": 0.0, "learning_rate": 1.8675275802676033e-05, "loss": 3.4266, "step": 1913344 }, { "epoch": 0.0, "learning_rate": 1.8666889855165516e-05, "loss": 3.4208, "step": 1913856 }, { "epoch": 0.0, "learning_rate": 1.8658503907654996e-05, "loss": 3.4261, "step": 1914368 }, { "epoch": 0.0, "learning_rate": 1.8650117960144476e-05, "loss": 3.412, "step": 1914880 }, { "epoch": 0.0, "learning_rate": 1.8641732012633956e-05, "loss": 3.4171, "step": 1915392 }, { "epoch": 0.0, "learning_rate": 1.8633362443927165e-05, "loss": 3.4089, "step": 1915904 }, { "epoch": 0.0, "learning_rate": 1.8624976496416645e-05, "loss": 3.4215, "step": 1916416 }, { "epoch": 0.0, "learning_rate": 1.8616590548906125e-05, "loss": 3.4256, "step": 1916928 }, { "epoch": 0.0, "learning_rate": 1.860820460139561e-05, "loss": 3.4148, "step": 1917440 }, { "epoch": 0.0, "learning_rate": 1.8599835032688818e-05, "loss": 3.4331, "step": 1917952 }, { "epoch": 0.0, "learning_rate": 1.8591449085178298e-05, "loss": 3.4335, "step": 1918464 }, { "epoch": 0.0, "learning_rate": 1.8583079516471507e-05, "loss": 3.4305, "step": 1918976 }, { "epoch": 0.0, "learning_rate": 1.8574693568960987e-05, "loss": 3.4223, "step": 1919488 }, { "epoch": 0.0, "learning_rate": 1.856630762145047e-05, "loss": 3.422, "step": 1920000 }, { "epoch": 0.0, "learning_rate": 1.855792167393995e-05, "loss": 3.4273, "step": 1920512 }, { "epoch": 0.0, "learning_rate": 1.854953572642943e-05, "loss": 3.432, "step": 1921024 }, { "epoch": 0.0, "learning_rate": 1.854114977891891e-05, "loss": 3.4144, "step": 1921536 }, { "epoch": 0.0, "learning_rate": 1.8532763831408386e-05, "loss": 3.4255, "step": 1922048 }, { "epoch": 0.0, "learning_rate": 1.85243942627016e-05, "loss": 3.413, "step": 1922560 }, { "epoch": 0.0, "learning_rate": 1.851600831519108e-05, "loss": 3.4236, "step": 1923072 }, { "epoch": 0.01, "learning_rate": 1.8507622367680562e-05, "loss": 3.4239, "step": 1923584 }, { "epoch": 0.01, "learning_rate": 1.849923642017004e-05, "loss": 3.4276, "step": 1924096 }, { "epoch": 0.01, "learning_rate": 1.849086685146325e-05, "loss": 3.4244, "step": 1924608 }, { "epoch": 0.01, "learning_rate": 1.848248090395273e-05, "loss": 3.4358, "step": 1925120 }, { "epoch": 0.01, "learning_rate": 1.8474094956442208e-05, "loss": 3.4197, "step": 1925632 }, { "epoch": 0.01, "learning_rate": 1.8465709008931688e-05, "loss": 3.4224, "step": 1926144 }, { "epoch": 0.01, "learning_rate": 1.845732306142117e-05, "loss": 3.4302, "step": 1926656 }, { "epoch": 0.01, "learning_rate": 1.844893711391065e-05, "loss": 3.4111, "step": 1927168 }, { "epoch": 0.01, "learning_rate": 1.844056754520386e-05, "loss": 3.4168, "step": 1927680 }, { "epoch": 0.01, "learning_rate": 1.843218159769334e-05, "loss": 3.4131, "step": 1928192 }, { "epoch": 0.01, "learning_rate": 1.842379565018282e-05, "loss": 3.4133, "step": 1928704 }, { "epoch": 0.01, "learning_rate": 1.84154097026723e-05, "loss": 3.4161, "step": 1929216 }, { "epoch": 0.01, "learning_rate": 1.840702375516178e-05, "loss": 3.4329, "step": 1929728 }, { "epoch": 0.01, "learning_rate": 1.8398637807651263e-05, "loss": 3.4185, "step": 1930240 }, { "epoch": 0.01, "learning_rate": 1.8390251860140743e-05, "loss": 3.4184, "step": 1930752 }, { "epoch": 0.01, "learning_rate": 1.838186591263022e-05, "loss": 3.4175, "step": 1931264 }, { "epoch": 0.01, "learning_rate": 1.8373496343923432e-05, "loss": 3.4258, "step": 1931776 }, { "epoch": 0.01, "learning_rate": 1.8365110396412912e-05, "loss": 3.4077, "step": 1932288 }, { "epoch": 0.01, "learning_rate": 1.835672444890239e-05, "loss": 3.4018, "step": 1932800 }, { "epoch": 0.01, "learning_rate": 1.8348338501391872e-05, "loss": 3.4296, "step": 1933312 }, { "epoch": 0.01, "learning_rate": 1.8339968932685085e-05, "loss": 3.4263, "step": 1933824 }, { "epoch": 0.01, "learning_rate": 1.8331582985174565e-05, "loss": 3.4339, "step": 1934336 }, { "epoch": 0.01, "learning_rate": 1.832319703766404e-05, "loss": 3.4163, "step": 1934848 }, { "epoch": 0.01, "learning_rate": 1.8314827468957254e-05, "loss": 3.4155, "step": 1935360 }, { "epoch": 0.01, "learning_rate": 1.8306441521446734e-05, "loss": 3.4134, "step": 1935872 }, { "epoch": 0.01, "learning_rate": 1.8298055573936217e-05, "loss": 3.4153, "step": 1936384 }, { "epoch": 0.01, "learning_rate": 1.8289669626425693e-05, "loss": 3.4304, "step": 1936896 }, { "epoch": 0.01, "learning_rate": 1.8281300057718906e-05, "loss": 3.4075, "step": 1937408 }, { "epoch": 0.01, "learning_rate": 1.8272914110208386e-05, "loss": 3.4408, "step": 1937920 }, { "epoch": 0.01, "learning_rate": 1.8264528162697862e-05, "loss": 3.4241, "step": 1938432 }, { "epoch": 0.01, "learning_rate": 1.8256142215187342e-05, "loss": 3.3963, "step": 1938944 }, { "epoch": 0.01, "learning_rate": 1.8247756267676826e-05, "loss": 3.4297, "step": 1939456 }, { "epoch": 0.01, "learning_rate": 1.8239370320166306e-05, "loss": 3.4167, "step": 1939968 }, { "epoch": 0.01, "learning_rate": 1.8230984372655786e-05, "loss": 3.3971, "step": 1940480 }, { "epoch": 0.01, "learning_rate": 1.8222598425145266e-05, "loss": 3.4261, "step": 1940992 }, { "epoch": 0.01, "learning_rate": 1.8214228856438475e-05, "loss": 3.426, "step": 1941504 }, { "epoch": 0.01, "learning_rate": 1.8205842908927955e-05, "loss": 3.4114, "step": 1942016 }, { "epoch": 0.01, "learning_rate": 1.8197456961417435e-05, "loss": 3.4153, "step": 1942528 }, { "epoch": 0.01, "learning_rate": 1.8189071013906918e-05, "loss": 3.4009, "step": 1943040 }, { "epoch": 0.01, "learning_rate": 1.8180701445200127e-05, "loss": 3.4118, "step": 1943552 }, { "epoch": 0.01, "learning_rate": 1.8172315497689607e-05, "loss": 3.4206, "step": 1944064 }, { "epoch": 0.01, "learning_rate": 1.8163929550179087e-05, "loss": 3.4101, "step": 1944576 }, { "epoch": 0.01, "learning_rate": 1.8155543602668567e-05, "loss": 3.4251, "step": 1945088 }, { "epoch": 0.01, "learning_rate": 1.814717403396178e-05, "loss": 3.4143, "step": 1945600 }, { "epoch": 0.01, "learning_rate": 1.813878808645126e-05, "loss": 3.4301, "step": 1946112 }, { "epoch": 0.01, "learning_rate": 1.813040213894074e-05, "loss": 3.4219, "step": 1946624 }, { "epoch": 0.01, "learning_rate": 1.812203257023395e-05, "loss": 3.424, "step": 1947136 }, { "epoch": 0.01, "learning_rate": 1.811364662272343e-05, "loss": 3.4133, "step": 1947648 }, { "epoch": 0.01, "learning_rate": 1.810526067521291e-05, "loss": 3.4143, "step": 1948160 }, { "epoch": 0.01, "learning_rate": 1.809687472770239e-05, "loss": 3.425, "step": 1948672 }, { "epoch": 0.01, "learning_rate": 1.808848878019187e-05, "loss": 3.4201, "step": 1949184 }, { "epoch": 0.01, "learning_rate": 1.808011921148508e-05, "loss": 3.4202, "step": 1949696 }, { "epoch": 0.01, "learning_rate": 1.807173326397456e-05, "loss": 3.422, "step": 1950208 }, { "epoch": 0.01, "learning_rate": 1.806334731646404e-05, "loss": 3.4053, "step": 1950720 }, { "epoch": 0.01, "learning_rate": 1.8054961368953517e-05, "loss": 3.405, "step": 1951232 }, { "epoch": 0.01, "learning_rate": 1.8046575421442997e-05, "loss": 3.4171, "step": 1951744 }, { "epoch": 0.01, "learning_rate": 1.803818947393248e-05, "loss": 3.4234, "step": 1952256 }, { "epoch": 0.01, "learning_rate": 1.802980352642196e-05, "loss": 3.4099, "step": 1952768 }, { "epoch": 0.01, "learning_rate": 1.802143395771517e-05, "loss": 3.4197, "step": 1953280 }, { "epoch": 0.02, "learning_rate": 1.801304801020465e-05, "loss": 3.4102, "step": 1953792 }, { "epoch": 0.02, "learning_rate": 1.800466206269413e-05, "loss": 3.4121, "step": 1954304 }, { "epoch": 0.02, "learning_rate": 1.799627611518361e-05, "loss": 3.4109, "step": 1954816 }, { "epoch": 0.02, "learning_rate": 1.798789016767309e-05, "loss": 3.4121, "step": 1955328 }, { "epoch": 0.02, "learning_rate": 1.7979520598966302e-05, "loss": 3.4264, "step": 1955840 }, { "epoch": 0.02, "learning_rate": 1.7971134651455782e-05, "loss": 3.4187, "step": 1956352 }, { "epoch": 0.02, "learning_rate": 1.7962748703945262e-05, "loss": 3.4235, "step": 1956864 }, { "epoch": 0.02, "learning_rate": 1.7954362756434742e-05, "loss": 3.4091, "step": 1957376 }, { "epoch": 0.02, "learning_rate": 1.7945976808924222e-05, "loss": 3.4136, "step": 1957888 }, { "epoch": 0.02, "learning_rate": 1.79375908614137e-05, "loss": 3.4174, "step": 1958400 }, { "epoch": 0.02, "learning_rate": 1.792920491390318e-05, "loss": 3.4269, "step": 1958912 }, { "epoch": 0.02, "learning_rate": 1.792081896639266e-05, "loss": 3.4209, "step": 1959424 }, { "epoch": 0.02, "learning_rate": 1.7912449397685874e-05, "loss": 3.4257, "step": 1959936 }, { "epoch": 0.02, "learning_rate": 1.790406345017535e-05, "loss": 3.4142, "step": 1960448 }, { "epoch": 0.02, "learning_rate": 1.789567750266483e-05, "loss": 3.4147, "step": 1960960 }, { "epoch": 0.02, "learning_rate": 1.788729155515431e-05, "loss": 3.4213, "step": 1961472 }, { "epoch": 0.02, "learning_rate": 1.7878921986447523e-05, "loss": 3.4182, "step": 1961984 }, { "epoch": 0.02, "learning_rate": 1.7870536038937003e-05, "loss": 3.406, "step": 1962496 }, { "epoch": 0.02, "learning_rate": 1.7862150091426483e-05, "loss": 3.4224, "step": 1963008 }, { "epoch": 0.02, "learning_rate": 1.7853764143915963e-05, "loss": 3.4103, "step": 1963520 }, { "epoch": 0.02, "learning_rate": 1.7845394575209172e-05, "loss": 3.4126, "step": 1964032 }, { "epoch": 0.02, "learning_rate": 1.7837008627698655e-05, "loss": 3.4145, "step": 1964544 }, { "epoch": 0.02, "learning_rate": 1.7828622680188135e-05, "loss": 3.4088, "step": 1965056 }, { "epoch": 0.02, "learning_rate": 1.7820236732677615e-05, "loss": 3.4194, "step": 1965568 }, { "epoch": 0.02, "learning_rate": 1.7811867163970824e-05, "loss": 3.4106, "step": 1966080 }, { "epoch": 0.02, "learning_rate": 1.7803481216460304e-05, "loss": 3.4236, "step": 1966592 }, { "epoch": 0.02, "learning_rate": 1.7795095268949784e-05, "loss": 3.4273, "step": 1967104 }, { "epoch": 0.02, "learning_rate": 1.7786709321439264e-05, "loss": 3.4256, "step": 1967616 }, { "epoch": 0.02, "learning_rate": 1.7778339752732477e-05, "loss": 3.4194, "step": 1968128 }, { "epoch": 0.02, "learning_rate": 1.7769953805221957e-05, "loss": 3.4159, "step": 1968640 }, { "epoch": 0.02, "learning_rate": 1.7761567857711437e-05, "loss": 3.4103, "step": 1969152 }, { "epoch": 0.02, "learning_rate": 1.7753214667808378e-05, "loss": 3.4184, "step": 1969664 }, { "epoch": 0.02, "learning_rate": 1.7744828720297858e-05, "loss": 3.4196, "step": 1970176 }, { "epoch": 0.02, "learning_rate": 1.773644277278734e-05, "loss": 3.4068, "step": 1970688 }, { "epoch": 0.02, "learning_rate": 1.772805682527682e-05, "loss": 3.4172, "step": 1971200 }, { "epoch": 0.02, "learning_rate": 1.771968725657003e-05, "loss": 3.4169, "step": 1971712 }, { "epoch": 0.02, "learning_rate": 1.771130130905951e-05, "loss": 3.4223, "step": 1972224 }, { "epoch": 0.02, "learning_rate": 1.770291536154899e-05, "loss": 3.4154, "step": 1972736 }, { "epoch": 0.02, "learning_rate": 1.7694529414038467e-05, "loss": 3.4101, "step": 1973248 }, { "epoch": 0.02, "learning_rate": 1.768614346652795e-05, "loss": 3.4101, "step": 1973760 }, { "epoch": 0.02, "learning_rate": 1.767775751901743e-05, "loss": 3.4257, "step": 1974272 }, { "epoch": 0.02, "learning_rate": 1.766937157150691e-05, "loss": 3.4158, "step": 1974784 }, { "epoch": 0.02, "learning_rate": 1.766098562399639e-05, "loss": 3.433, "step": 1975296 }, { "epoch": 0.02, "learning_rate": 1.76526160552896e-05, "loss": 3.4075, "step": 1975808 }, { "epoch": 0.02, "learning_rate": 1.764423010777908e-05, "loss": 3.4162, "step": 1976320 }, { "epoch": 0.02, "learning_rate": 1.763584416026856e-05, "loss": 3.422, "step": 1976832 }, { "epoch": 0.02, "learning_rate": 1.7627458212758043e-05, "loss": 3.4128, "step": 1977344 }, { "epoch": 0.02, "learning_rate": 1.7619088644051252e-05, "loss": 3.4207, "step": 1977856 }, { "epoch": 0.02, "learning_rate": 1.761070269654073e-05, "loss": 3.415, "step": 1978368 }, { "epoch": 0.02, "learning_rate": 1.760231674903021e-05, "loss": 3.4238, "step": 1978880 }, { "epoch": 0.02, "learning_rate": 1.759393080151969e-05, "loss": 3.4292, "step": 1979392 }, { "epoch": 0.02, "learning_rate": 1.7585561232812904e-05, "loss": 3.4186, "step": 1979904 }, { "epoch": 0.02, "learning_rate": 1.7577175285302384e-05, "loss": 3.4198, "step": 1980416 }, { "epoch": 0.02, "learning_rate": 1.7568789337791864e-05, "loss": 3.4202, "step": 1980928 }, { "epoch": 0.02, "learning_rate": 1.7560403390281344e-05, "loss": 3.4153, "step": 1981440 }, { "epoch": 0.02, "learning_rate": 1.7552050200378286e-05, "loss": 3.4137, "step": 1981952 }, { "epoch": 0.02, "learning_rate": 1.7543664252867766e-05, "loss": 3.4096, "step": 1982464 }, { "epoch": 0.02, "learning_rate": 1.7535278305357245e-05, "loss": 3.4158, "step": 1982976 }, { "epoch": 0.02, "learning_rate": 1.7526892357846725e-05, "loss": 3.4095, "step": 1983488 }, { "epoch": 0.02, "learning_rate": 1.7518506410336205e-05, "loss": 3.4133, "step": 1984000 }, { "epoch": 0.03, "eval_loss": 3.8660171031951904, "eval_runtime": 303.146, "eval_samples_per_second": 1258.77, "eval_steps_per_second": 39.337, "step": 1984310 }, { "epoch": 1.0, "learning_rate": 1.7510120462825685e-05, "loss": 3.4161, "step": 1984512 }, { "epoch": 1.0, "learning_rate": 1.7501734515315165e-05, "loss": 3.4102, "step": 1985024 }, { "epoch": 1.0, "learning_rate": 1.7493348567804645e-05, "loss": 3.4166, "step": 1985536 }, { "epoch": 1.0, "learning_rate": 1.7484978999097858e-05, "loss": 3.4232, "step": 1986048 }, { "epoch": 1.0, "learning_rate": 1.7476593051587338e-05, "loss": 3.4315, "step": 1986560 }, { "epoch": 1.0, "learning_rate": 1.7468223482880547e-05, "loss": 3.4161, "step": 1987072 }, { "epoch": 1.0, "learning_rate": 1.7459837535370027e-05, "loss": 3.4187, "step": 1987584 }, { "epoch": 1.0, "learning_rate": 1.7451451587859507e-05, "loss": 3.4108, "step": 1988096 }, { "epoch": 1.0, "learning_rate": 1.7443065640348987e-05, "loss": 3.4069, "step": 1988608 }, { "epoch": 1.0, "learning_rate": 1.74346960716422e-05, "loss": 3.4166, "step": 1989120 }, { "epoch": 1.0, "learning_rate": 1.742631012413168e-05, "loss": 3.4193, "step": 1989632 }, { "epoch": 1.0, "learning_rate": 1.741792417662116e-05, "loss": 3.4112, "step": 1990144 }, { "epoch": 1.0, "learning_rate": 1.740953822911064e-05, "loss": 3.4131, "step": 1990656 }, { "epoch": 1.0, "learning_rate": 1.740115228160012e-05, "loss": 3.3999, "step": 1991168 }, { "epoch": 1.0, "learning_rate": 1.7392766334089596e-05, "loss": 3.4063, "step": 1991680 }, { "epoch": 1.0, "learning_rate": 1.7384380386579076e-05, "loss": 3.3948, "step": 1992192 }, { "epoch": 1.0, "learning_rate": 1.737599443906856e-05, "loss": 3.4139, "step": 1992704 }, { "epoch": 1.0, "learning_rate": 1.736762487036177e-05, "loss": 3.4141, "step": 1993216 }, { "epoch": 1.0, "learning_rate": 1.7359238922851248e-05, "loss": 3.4051, "step": 1993728 }, { "epoch": 1.0, "learning_rate": 1.7350852975340728e-05, "loss": 3.4236, "step": 1994240 }, { "epoch": 1.0, "learning_rate": 1.734248340663394e-05, "loss": 3.4232, "step": 1994752 }, { "epoch": 1.0, "learning_rate": 1.733409745912342e-05, "loss": 3.4182, "step": 1995264 }, { "epoch": 1.0, "learning_rate": 1.73257115116129e-05, "loss": 3.4123, "step": 1995776 }, { "epoch": 1.0, "learning_rate": 1.731732556410238e-05, "loss": 3.409, "step": 1996288 }, { "epoch": 1.0, "learning_rate": 1.730893961659186e-05, "loss": 3.4177, "step": 1996800 }, { "epoch": 1.0, "learning_rate": 1.730057004788507e-05, "loss": 3.4231, "step": 1997312 }, { "epoch": 1.0, "learning_rate": 1.729218410037455e-05, "loss": 3.4019, "step": 1997824 }, { "epoch": 1.0, "learning_rate": 1.728379815286403e-05, "loss": 3.4155, "step": 1998336 }, { "epoch": 1.0, "learning_rate": 1.7275412205353513e-05, "loss": 3.4062, "step": 1998848 }, { "epoch": 1.0, "learning_rate": 1.7267026257842992e-05, "loss": 3.4078, "step": 1999360 }, { "epoch": 1.01, "learning_rate": 1.7258640310332472e-05, "loss": 3.4135, "step": 1999872 }, { "epoch": 1.01, "learning_rate": 1.7250254362821952e-05, "loss": 3.4165, "step": 2000384 }, { "epoch": 1.01, "learning_rate": 1.724188479411516e-05, "loss": 3.4138, "step": 2000896 }, { "epoch": 1.01, "learning_rate": 1.723349884660464e-05, "loss": 3.4264, "step": 2001408 }, { "epoch": 1.01, "learning_rate": 1.722511289909412e-05, "loss": 3.4121, "step": 2001920 }, { "epoch": 1.01, "learning_rate": 1.72167269515836e-05, "loss": 3.4141, "step": 2002432 }, { "epoch": 1.01, "learning_rate": 1.720834100407308e-05, "loss": 3.4206, "step": 2002944 }, { "epoch": 1.01, "learning_rate": 1.719995505656256e-05, "loss": 3.399, "step": 2003456 }, { "epoch": 1.01, "learning_rate": 1.7191585487855774e-05, "loss": 3.4054, "step": 2003968 }, { "epoch": 1.01, "learning_rate": 1.718319954034525e-05, "loss": 3.4063, "step": 2004480 }, { "epoch": 1.01, "learning_rate": 1.7174813592834734e-05, "loss": 3.4014, "step": 2004992 }, { "epoch": 1.01, "learning_rate": 1.7166427645324214e-05, "loss": 3.4078, "step": 2005504 }, { "epoch": 1.01, "learning_rate": 1.7158041697813694e-05, "loss": 3.4206, "step": 2006016 }, { "epoch": 1.01, "learning_rate": 1.7149655750303174e-05, "loss": 3.4058, "step": 2006528 }, { "epoch": 1.01, "learning_rate": 1.7141269802792653e-05, "loss": 3.4094, "step": 2007040 }, { "epoch": 1.01, "learning_rate": 1.7132883855282133e-05, "loss": 3.4112, "step": 2007552 }, { "epoch": 1.01, "learning_rate": 1.7124514286575343e-05, "loss": 3.4158, "step": 2008064 }, { "epoch": 1.01, "learning_rate": 1.7116128339064822e-05, "loss": 3.3946, "step": 2008576 }, { "epoch": 1.01, "learning_rate": 1.7107742391554306e-05, "loss": 3.3915, "step": 2009088 }, { "epoch": 1.01, "learning_rate": 1.7099356444043782e-05, "loss": 3.4185, "step": 2009600 }, { "epoch": 1.01, "learning_rate": 1.7090986875336995e-05, "loss": 3.4167, "step": 2010112 }, { "epoch": 1.01, "learning_rate": 1.7082600927826475e-05, "loss": 3.4219, "step": 2010624 }, { "epoch": 1.01, "learning_rate": 1.7074214980315955e-05, "loss": 3.4068, "step": 2011136 }, { "epoch": 1.01, "learning_rate": 1.7065845411609167e-05, "loss": 3.4039, "step": 2011648 }, { "epoch": 1.01, "learning_rate": 1.7057459464098647e-05, "loss": 3.4041, "step": 2012160 }, { "epoch": 1.01, "learning_rate": 1.7049073516588127e-05, "loss": 3.4048, "step": 2012672 }, { "epoch": 1.01, "learning_rate": 1.7040687569077607e-05, "loss": 3.4228, "step": 2013184 }, { "epoch": 1.01, "learning_rate": 1.7032318000370816e-05, "loss": 3.3926, "step": 2013696 }, { "epoch": 1.01, "learning_rate": 1.7023932052860296e-05, "loss": 3.4347, "step": 2014208 }, { "epoch": 1.01, "learning_rate": 1.7015546105349776e-05, "loss": 3.4125, "step": 2014720 }, { "epoch": 1.01, "learning_rate": 1.7007160157839256e-05, "loss": 3.3907, "step": 2015232 }, { "epoch": 1.01, "learning_rate": 1.6998774210328736e-05, "loss": 3.4147, "step": 2015744 }, { "epoch": 1.01, "learning_rate": 1.6990388262818216e-05, "loss": 3.4042, "step": 2016256 }, { "epoch": 1.01, "learning_rate": 1.6982002315307696e-05, "loss": 3.3934, "step": 2016768 }, { "epoch": 1.01, "learning_rate": 1.6973616367797176e-05, "loss": 3.4138, "step": 2017280 }, { "epoch": 1.01, "learning_rate": 1.696524679909039e-05, "loss": 3.4172, "step": 2017792 }, { "epoch": 1.01, "learning_rate": 1.695686085157987e-05, "loss": 3.3948, "step": 2018304 }, { "epoch": 1.01, "learning_rate": 1.694847490406935e-05, "loss": 3.4127, "step": 2018816 }, { "epoch": 1.01, "learning_rate": 1.6940088956558828e-05, "loss": 3.3898, "step": 2019328 }, { "epoch": 1.01, "learning_rate": 1.6931719387852037e-05, "loss": 3.4038, "step": 2019840 }, { "epoch": 1.01, "learning_rate": 1.6923333440341517e-05, "loss": 3.4099, "step": 2020352 }, { "epoch": 1.01, "learning_rate": 1.6914947492830997e-05, "loss": 3.4057, "step": 2020864 }, { "epoch": 1.01, "learning_rate": 1.690656154532048e-05, "loss": 3.4124, "step": 2021376 }, { "epoch": 1.01, "learning_rate": 1.689819197661369e-05, "loss": 3.4061, "step": 2021888 }, { "epoch": 1.01, "learning_rate": 1.688980602910317e-05, "loss": 3.4197, "step": 2022400 }, { "epoch": 1.01, "learning_rate": 1.688142008159265e-05, "loss": 3.4088, "step": 2022912 }, { "epoch": 1.01, "learning_rate": 1.687303413408213e-05, "loss": 3.4189, "step": 2023424 }, { "epoch": 1.01, "learning_rate": 1.6864664565375342e-05, "loss": 3.4044, "step": 2023936 }, { "epoch": 1.01, "learning_rate": 1.6856278617864822e-05, "loss": 3.4013, "step": 2024448 }, { "epoch": 1.01, "learning_rate": 1.6847892670354302e-05, "loss": 3.4119, "step": 2024960 }, { "epoch": 1.01, "learning_rate": 1.6839506722843782e-05, "loss": 3.4094, "step": 2025472 }, { "epoch": 1.01, "learning_rate": 1.6831120775333262e-05, "loss": 3.4078, "step": 2025984 }, { "epoch": 1.01, "learning_rate": 1.682275120662647e-05, "loss": 3.415, "step": 2026496 }, { "epoch": 1.01, "learning_rate": 1.681436525911595e-05, "loss": 3.3982, "step": 2027008 }, { "epoch": 1.01, "learning_rate": 1.680597931160543e-05, "loss": 3.3919, "step": 2027520 }, { "epoch": 1.01, "learning_rate": 1.679759336409491e-05, "loss": 3.4062, "step": 2028032 }, { "epoch": 1.01, "learning_rate": 1.678920741658439e-05, "loss": 3.4128, "step": 2028544 }, { "epoch": 1.01, "learning_rate": 1.678082146907387e-05, "loss": 3.3995, "step": 2029056 }, { "epoch": 1.01, "learning_rate": 1.6772451900367083e-05, "loss": 3.4092, "step": 2029568 }, { "epoch": 1.01, "learning_rate": 1.676406595285656e-05, "loss": 3.4026, "step": 2030080 }, { "epoch": 1.02, "learning_rate": 1.6755680005346043e-05, "loss": 3.3996, "step": 2030592 }, { "epoch": 1.02, "learning_rate": 1.6747294057835523e-05, "loss": 3.3985, "step": 2031104 }, { "epoch": 1.02, "learning_rate": 1.6738908110325003e-05, "loss": 3.4028, "step": 2031616 }, { "epoch": 1.02, "learning_rate": 1.6730538541618212e-05, "loss": 3.4172, "step": 2032128 }, { "epoch": 1.02, "learning_rate": 1.6722152594107692e-05, "loss": 3.41, "step": 2032640 }, { "epoch": 1.02, "learning_rate": 1.6713766646597172e-05, "loss": 3.4124, "step": 2033152 }, { "epoch": 1.02, "learning_rate": 1.6705380699086652e-05, "loss": 3.4013, "step": 2033664 }, { "epoch": 1.02, "learning_rate": 1.6696994751576135e-05, "loss": 3.4012, "step": 2034176 }, { "epoch": 1.02, "learning_rate": 1.6688608804065615e-05, "loss": 3.4043, "step": 2034688 }, { "epoch": 1.02, "learning_rate": 1.6680222856555092e-05, "loss": 3.4141, "step": 2035200 }, { "epoch": 1.02, "learning_rate": 1.6671836909044572e-05, "loss": 3.4113, "step": 2035712 }, { "epoch": 1.02, "learning_rate": 1.6663467340337784e-05, "loss": 3.4136, "step": 2036224 }, { "epoch": 1.02, "learning_rate": 1.6655081392827264e-05, "loss": 3.4069, "step": 2036736 }, { "epoch": 1.02, "learning_rate": 1.6646695445316744e-05, "loss": 3.4005, "step": 2037248 }, { "epoch": 1.02, "learning_rate": 1.6638309497806224e-05, "loss": 3.4111, "step": 2037760 }, { "epoch": 1.02, "learning_rate": 1.6629939929099437e-05, "loss": 3.4074, "step": 2038272 }, { "epoch": 1.02, "learning_rate": 1.6621553981588913e-05, "loss": 3.3958, "step": 2038784 }, { "epoch": 1.02, "learning_rate": 1.6613168034078393e-05, "loss": 3.4096, "step": 2039296 }, { "epoch": 1.02, "learning_rate": 1.6604782086567873e-05, "loss": 3.4042, "step": 2039808 }, { "epoch": 1.02, "learning_rate": 1.659641251786109e-05, "loss": 3.4051, "step": 2040320 }, { "epoch": 1.02, "learning_rate": 1.6588026570350566e-05, "loss": 3.4012, "step": 2040832 }, { "epoch": 1.02, "learning_rate": 1.6579640622840046e-05, "loss": 3.4004, "step": 2041344 }, { "epoch": 1.02, "learning_rate": 1.6571254675329526e-05, "loss": 3.4089, "step": 2041856 }, { "epoch": 1.02, "learning_rate": 1.6562885106622738e-05, "loss": 3.4061, "step": 2042368 }, { "epoch": 1.02, "learning_rate": 1.655451553791595e-05, "loss": 3.4077, "step": 2042880 }, { "epoch": 1.02, "learning_rate": 1.654612959040543e-05, "loss": 3.4151, "step": 2043392 }, { "epoch": 1.02, "learning_rate": 1.653774364289491e-05, "loss": 3.4186, "step": 2043904 }, { "epoch": 1.02, "learning_rate": 1.6529357695384387e-05, "loss": 3.4081, "step": 2044416 }, { "epoch": 1.02, "learning_rate": 1.6520971747873867e-05, "loss": 3.4103, "step": 2044928 }, { "epoch": 1.02, "learning_rate": 1.6512585800363347e-05, "loss": 3.3983, "step": 2045440 }, { "epoch": 1.02, "learning_rate": 1.6504199852852827e-05, "loss": 3.4095, "step": 2045952 }, { "epoch": 1.02, "learning_rate": 1.6495813905342307e-05, "loss": 3.4056, "step": 2046464 }, { "epoch": 1.02, "learning_rate": 1.648744433663552e-05, "loss": 3.4006, "step": 2046976 }, { "epoch": 1.02, "learning_rate": 1.6479058389125e-05, "loss": 3.4027, "step": 2047488 }, { "epoch": 1.02, "learning_rate": 1.647067244161448e-05, "loss": 3.4099, "step": 2048000 }, { "epoch": 1.02, "learning_rate": 1.6462302872907688e-05, "loss": 3.4092, "step": 2048512 }, { "epoch": 1.02, "learning_rate": 1.6453916925397168e-05, "loss": 3.4021, "step": 2049024 }, { "epoch": 1.02, "learning_rate": 1.644553097788665e-05, "loss": 3.4012, "step": 2049536 }, { "epoch": 1.02, "learning_rate": 1.643714503037613e-05, "loss": 3.4043, "step": 2050048 }, { "epoch": 1.02, "learning_rate": 1.642875908286561e-05, "loss": 3.4114, "step": 2050560 }, { "epoch": 1.02, "learning_rate": 1.642037313535509e-05, "loss": 3.4073, "step": 2051072 }, { "epoch": 1.02, "learning_rate": 1.6411987187844568e-05, "loss": 3.4193, "step": 2051584 }, { "epoch": 1.02, "learning_rate": 1.640361761913778e-05, "loss": 3.3991, "step": 2052096 }, { "epoch": 1.02, "learning_rate": 1.639523167162726e-05, "loss": 3.4068, "step": 2052608 }, { "epoch": 1.02, "learning_rate": 1.6386845724116744e-05, "loss": 3.4107, "step": 2053120 }, { "epoch": 1.02, "learning_rate": 1.637845977660622e-05, "loss": 3.401, "step": 2053632 }, { "epoch": 1.02, "learning_rate": 1.6370090207899433e-05, "loss": 3.4103, "step": 2054144 }, { "epoch": 1.02, "learning_rate": 1.6361704260388913e-05, "loss": 3.4071, "step": 2054656 }, { "epoch": 1.02, "learning_rate": 1.6353318312878393e-05, "loss": 3.4109, "step": 2055168 }, { "epoch": 1.02, "learning_rate": 1.634493236536787e-05, "loss": 3.4199, "step": 2055680 }, { "epoch": 1.02, "learning_rate": 1.6336562796661085e-05, "loss": 3.4093, "step": 2056192 }, { "epoch": 1.02, "learning_rate": 1.6328176849150565e-05, "loss": 3.4063, "step": 2056704 }, { "epoch": 1.02, "learning_rate": 1.6319790901640042e-05, "loss": 3.411, "step": 2057216 }, { "epoch": 1.02, "learning_rate": 1.6311404954129522e-05, "loss": 3.4032, "step": 2057728 }, { "epoch": 1.02, "learning_rate": 1.6303051764226467e-05, "loss": 3.4039, "step": 2058240 }, { "epoch": 1.02, "learning_rate": 1.6294665816715947e-05, "loss": 3.4033, "step": 2058752 }, { "epoch": 1.02, "learning_rate": 1.6286279869205427e-05, "loss": 3.4029, "step": 2059264 }, { "epoch": 1.02, "learning_rate": 1.6277893921694907e-05, "loss": 3.4061, "step": 2059776 }, { "epoch": 1.02, "learning_rate": 1.6269507974184387e-05, "loss": 3.4003, "step": 2060288 }, { "epoch": 1.03, "eval_loss": 3.8679862022399902, "eval_runtime": 303.118, "eval_samples_per_second": 1258.886, "eval_steps_per_second": 39.341, "step": 2060630 }, { "epoch": 0.0, "learning_rate": 1.6261122026673866e-05, "loss": 3.4084, "step": 2060800 }, { "epoch": 0.0, "learning_rate": 1.6252736079163343e-05, "loss": 3.4039, "step": 2061312 }, { "epoch": 0.0, "learning_rate": 1.6244350131652823e-05, "loss": 3.408, "step": 2061824 }, { "epoch": 0.0, "learning_rate": 1.6235964184142306e-05, "loss": 3.413, "step": 2062336 }, { "epoch": 0.0, "learning_rate": 1.6227594615435515e-05, "loss": 3.4192, "step": 2062848 }, { "epoch": 0.0, "learning_rate": 1.6219208667924995e-05, "loss": 3.4095, "step": 2063360 }, { "epoch": 0.0, "learning_rate": 1.6210822720414475e-05, "loss": 3.4099, "step": 2063872 }, { "epoch": 0.0, "learning_rate": 1.6202436772903955e-05, "loss": 3.401, "step": 2064384 }, { "epoch": 0.0, "learning_rate": 1.6194067204197168e-05, "loss": 3.395, "step": 2064896 }, { "epoch": 0.0, "learning_rate": 1.6185681256686648e-05, "loss": 3.4019, "step": 2065408 }, { "epoch": 0.0, "learning_rate": 1.6177295309176128e-05, "loss": 3.4161, "step": 2065920 }, { "epoch": 0.0, "learning_rate": 1.6168909361665608e-05, "loss": 3.3971, "step": 2066432 }, { "epoch": 0.0, "learning_rate": 1.6160523414155088e-05, "loss": 3.4063, "step": 2066944 }, { "epoch": 0.0, "learning_rate": 1.6152137466644568e-05, "loss": 3.3892, "step": 2067456 }, { "epoch": 0.0, "learning_rate": 1.6143751519134044e-05, "loss": 3.3953, "step": 2067968 }, { "epoch": 0.0, "learning_rate": 1.6135365571623527e-05, "loss": 3.3885, "step": 2068480 }, { "epoch": 0.0, "learning_rate": 1.612699600291674e-05, "loss": 3.4024, "step": 2068992 }, { "epoch": 0.0, "learning_rate": 1.611861005540622e-05, "loss": 3.4037, "step": 2069504 }, { "epoch": 0.0, "learning_rate": 1.6110224107895697e-05, "loss": 3.3994, "step": 2070016 }, { "epoch": 0.0, "learning_rate": 1.610185453918891e-05, "loss": 3.4061, "step": 2070528 }, { "epoch": 0.0, "learning_rate": 1.609346859167839e-05, "loss": 3.4145, "step": 2071040 }, { "epoch": 0.0, "learning_rate": 1.608508264416787e-05, "loss": 3.4077, "step": 2071552 }, { "epoch": 0.0, "learning_rate": 1.607671307546108e-05, "loss": 3.4023, "step": 2072064 }, { "epoch": 0.0, "learning_rate": 1.606832712795056e-05, "loss": 3.3996, "step": 2072576 }, { "epoch": 0.0, "learning_rate": 1.605994118044004e-05, "loss": 3.4117, "step": 2073088 }, { "epoch": 0.0, "learning_rate": 1.6051555232929518e-05, "loss": 3.4072, "step": 2073600 }, { "epoch": 0.0, "learning_rate": 1.6043169285418998e-05, "loss": 3.3972, "step": 2074112 }, { "epoch": 0.0, "learning_rate": 1.6034783337908478e-05, "loss": 3.4029, "step": 2074624 }, { "epoch": 0.0, "learning_rate": 1.602639739039796e-05, "loss": 3.3993, "step": 2075136 }, { "epoch": 0.0, "learning_rate": 1.601802782169117e-05, "loss": 3.3933, "step": 2075648 }, { "epoch": 0.01, "learning_rate": 1.600964187418065e-05, "loss": 3.4056, "step": 2076160 }, { "epoch": 0.01, "learning_rate": 1.6001272305473863e-05, "loss": 3.4043, "step": 2076672 }, { "epoch": 0.01, "learning_rate": 1.5992886357963343e-05, "loss": 3.4085, "step": 2077184 }, { "epoch": 0.01, "learning_rate": 1.5984500410452823e-05, "loss": 3.415, "step": 2077696 }, { "epoch": 0.01, "learning_rate": 1.5976114462942303e-05, "loss": 3.3987, "step": 2078208 }, { "epoch": 0.01, "learning_rate": 1.5967728515431782e-05, "loss": 3.406, "step": 2078720 }, { "epoch": 0.01, "learning_rate": 1.5959342567921262e-05, "loss": 3.4094, "step": 2079232 }, { "epoch": 0.01, "learning_rate": 1.5950956620410742e-05, "loss": 3.3937, "step": 2079744 }, { "epoch": 0.01, "learning_rate": 1.594258705170395e-05, "loss": 3.3991, "step": 2080256 }, { "epoch": 0.01, "learning_rate": 1.593420110419343e-05, "loss": 3.3883, "step": 2080768 }, { "epoch": 0.01, "learning_rate": 1.5925815156682915e-05, "loss": 3.392, "step": 2081280 }, { "epoch": 0.01, "learning_rate": 1.5917429209172395e-05, "loss": 3.3965, "step": 2081792 }, { "epoch": 0.01, "learning_rate": 1.5909043261661875e-05, "loss": 3.4129, "step": 2082304 }, { "epoch": 0.01, "learning_rate": 1.590065731415135e-05, "loss": 3.3986, "step": 2082816 }, { "epoch": 0.01, "learning_rate": 1.589227136664083e-05, "loss": 3.3953, "step": 2083328 }, { "epoch": 0.01, "learning_rate": 1.588388541913031e-05, "loss": 3.4029, "step": 2083840 }, { "epoch": 0.01, "learning_rate": 1.5875515850423524e-05, "loss": 3.4032, "step": 2084352 }, { "epoch": 0.01, "learning_rate": 1.5867129902913004e-05, "loss": 3.3883, "step": 2084864 }, { "epoch": 0.01, "learning_rate": 1.5858743955402484e-05, "loss": 3.38, "step": 2085376 }, { "epoch": 0.01, "learning_rate": 1.5850358007891964e-05, "loss": 3.4052, "step": 2085888 }, { "epoch": 0.01, "learning_rate": 1.5842004817988905e-05, "loss": 3.4062, "step": 2086400 }, { "epoch": 0.01, "learning_rate": 1.5833618870478385e-05, "loss": 3.4111, "step": 2086912 }, { "epoch": 0.01, "learning_rate": 1.582523292296787e-05, "loss": 3.4006, "step": 2087424 }, { "epoch": 0.01, "learning_rate": 1.581684697545735e-05, "loss": 3.3946, "step": 2087936 }, { "epoch": 0.01, "learning_rate": 1.5808461027946825e-05, "loss": 3.393, "step": 2088448 }, { "epoch": 0.01, "learning_rate": 1.5800075080436305e-05, "loss": 3.3918, "step": 2088960 }, { "epoch": 0.01, "learning_rate": 1.5791689132925785e-05, "loss": 3.4122, "step": 2089472 }, { "epoch": 0.01, "learning_rate": 1.5783319564218997e-05, "loss": 3.3844, "step": 2089984 }, { "epoch": 0.01, "learning_rate": 1.5774933616708477e-05, "loss": 3.4214, "step": 2090496 }, { "epoch": 0.01, "learning_rate": 1.5766547669197957e-05, "loss": 3.4028, "step": 2091008 }, { "epoch": 0.01, "learning_rate": 1.5758161721687437e-05, "loss": 3.3848, "step": 2091520 }, { "epoch": 0.01, "learning_rate": 1.5749775774176917e-05, "loss": 3.4016, "step": 2092032 }, { "epoch": 0.01, "learning_rate": 1.5741389826666397e-05, "loss": 3.3954, "step": 2092544 }, { "epoch": 0.01, "learning_rate": 1.5733003879155877e-05, "loss": 3.3833, "step": 2093056 }, { "epoch": 0.01, "learning_rate": 1.5724617931645354e-05, "loss": 3.3994, "step": 2093568 }, { "epoch": 0.01, "learning_rate": 1.571624836293857e-05, "loss": 3.4075, "step": 2094080 }, { "epoch": 0.01, "learning_rate": 1.570786241542805e-05, "loss": 3.391, "step": 2094592 }, { "epoch": 0.01, "learning_rate": 1.569947646791753e-05, "loss": 3.3984, "step": 2095104 }, { "epoch": 0.01, "learning_rate": 1.5691090520407006e-05, "loss": 3.3794, "step": 2095616 }, { "epoch": 0.01, "learning_rate": 1.568272095170022e-05, "loss": 3.3924, "step": 2096128 }, { "epoch": 0.01, "learning_rate": 1.56743350041897e-05, "loss": 3.3952, "step": 2096640 }, { "epoch": 0.01, "learning_rate": 1.566594905667918e-05, "loss": 3.3994, "step": 2097152 }, { "epoch": 0.01, "learning_rate": 1.565756310916866e-05, "loss": 3.3981, "step": 2097664 }, { "epoch": 0.01, "learning_rate": 1.564919354046187e-05, "loss": 3.395, "step": 2098176 }, { "epoch": 0.01, "learning_rate": 1.564080759295135e-05, "loss": 3.4131, "step": 2098688 }, { "epoch": 0.01, "learning_rate": 1.5632421645440827e-05, "loss": 3.4009, "step": 2099200 }, { "epoch": 0.01, "learning_rate": 1.5624035697930307e-05, "loss": 3.4063, "step": 2099712 }, { "epoch": 0.01, "learning_rate": 1.5615666129223523e-05, "loss": 3.3958, "step": 2100224 }, { "epoch": 0.01, "learning_rate": 1.5607280181713003e-05, "loss": 3.3931, "step": 2100736 }, { "epoch": 0.01, "learning_rate": 1.559889423420248e-05, "loss": 3.403, "step": 2101248 }, { "epoch": 0.01, "learning_rate": 1.559050828669196e-05, "loss": 3.3999, "step": 2101760 }, { "epoch": 0.01, "learning_rate": 1.558212233918144e-05, "loss": 3.3966, "step": 2102272 }, { "epoch": 0.01, "learning_rate": 1.5573752770474652e-05, "loss": 3.4046, "step": 2102784 }, { "epoch": 0.01, "learning_rate": 1.5565366822964132e-05, "loss": 3.3889, "step": 2103296 }, { "epoch": 0.01, "learning_rate": 1.5556980875453612e-05, "loss": 3.379, "step": 2103808 }, { "epoch": 0.01, "learning_rate": 1.5548594927943092e-05, "loss": 3.392, "step": 2104320 }, { "epoch": 0.01, "learning_rate": 1.5540208980432572e-05, "loss": 3.404, "step": 2104832 }, { "epoch": 0.01, "learning_rate": 1.5531823032922052e-05, "loss": 3.3914, "step": 2105344 }, { "epoch": 0.01, "learning_rate": 1.552345346421526e-05, "loss": 3.3979, "step": 2105856 }, { "epoch": 0.01, "learning_rate": 1.5515067516704744e-05, "loss": 3.3941, "step": 2106368 }, { "epoch": 0.02, "learning_rate": 1.5506681569194224e-05, "loss": 3.3871, "step": 2106880 }, { "epoch": 0.02, "learning_rate": 1.5498295621683704e-05, "loss": 3.3918, "step": 2107392 }, { "epoch": 0.02, "learning_rate": 1.5489909674173184e-05, "loss": 3.3906, "step": 2107904 }, { "epoch": 0.02, "learning_rate": 1.5481540105466393e-05, "loss": 3.4038, "step": 2108416 }, { "epoch": 0.02, "learning_rate": 1.5473154157955873e-05, "loss": 3.4016, "step": 2108928 }, { "epoch": 0.02, "learning_rate": 1.5464768210445353e-05, "loss": 3.4034, "step": 2109440 }, { "epoch": 0.02, "learning_rate": 1.5456382262934833e-05, "loss": 3.3888, "step": 2109952 }, { "epoch": 0.02, "learning_rate": 1.5447996315424313e-05, "loss": 3.3903, "step": 2110464 }, { "epoch": 0.02, "learning_rate": 1.5439610367913793e-05, "loss": 3.3999, "step": 2110976 }, { "epoch": 0.02, "learning_rate": 1.5431224420403273e-05, "loss": 3.4012, "step": 2111488 }, { "epoch": 0.02, "learning_rate": 1.5422838472892753e-05, "loss": 3.4026, "step": 2112000 }, { "epoch": 0.02, "learning_rate": 1.5414468904185962e-05, "loss": 3.4046, "step": 2112512 }, { "epoch": 0.02, "learning_rate": 1.5406082956675445e-05, "loss": 3.3946, "step": 2113024 }, { "epoch": 0.02, "learning_rate": 1.5397697009164925e-05, "loss": 3.3895, "step": 2113536 }, { "epoch": 0.02, "learning_rate": 1.5389311061654405e-05, "loss": 3.403, "step": 2114048 }, { "epoch": 0.02, "learning_rate": 1.5380941492947614e-05, "loss": 3.3961, "step": 2114560 }, { "epoch": 0.02, "learning_rate": 1.5372571924240827e-05, "loss": 3.3904, "step": 2115072 }, { "epoch": 0.02, "learning_rate": 1.5364185976730307e-05, "loss": 3.3968, "step": 2115584 }, { "epoch": 0.02, "learning_rate": 1.5355800029219787e-05, "loss": 3.3952, "step": 2116096 }, { "epoch": 0.02, "learning_rate": 1.5347414081709267e-05, "loss": 3.3932, "step": 2116608 }, { "epoch": 0.02, "learning_rate": 1.5339028134198747e-05, "loss": 3.388, "step": 2117120 }, { "epoch": 0.02, "learning_rate": 1.5330642186688227e-05, "loss": 3.3896, "step": 2117632 }, { "epoch": 0.02, "learning_rate": 1.5322256239177707e-05, "loss": 3.3988, "step": 2118144 }, { "epoch": 0.02, "learning_rate": 1.5313870291667187e-05, "loss": 3.3971, "step": 2118656 }, { "epoch": 0.02, "learning_rate": 1.53055007229604e-05, "loss": 3.3977, "step": 2119168 }, { "epoch": 0.02, "learning_rate": 1.529711477544988e-05, "loss": 3.4033, "step": 2119680 }, { "epoch": 0.02, "learning_rate": 1.528872882793936e-05, "loss": 3.4139, "step": 2120192 }, { "epoch": 0.02, "learning_rate": 1.528034288042884e-05, "loss": 3.3953, "step": 2120704 }, { "epoch": 0.02, "learning_rate": 1.5271973311722048e-05, "loss": 3.3986, "step": 2121216 }, { "epoch": 0.02, "learning_rate": 1.5263587364211528e-05, "loss": 3.3902, "step": 2121728 }, { "epoch": 0.02, "learning_rate": 1.525520141670101e-05, "loss": 3.3945, "step": 2122240 }, { "epoch": 0.02, "learning_rate": 1.5246815469190486e-05, "loss": 3.3954, "step": 2122752 }, { "epoch": 0.02, "learning_rate": 1.52384459004837e-05, "loss": 3.3953, "step": 2123264 }, { "epoch": 0.02, "learning_rate": 1.523005995297318e-05, "loss": 3.3924, "step": 2123776 }, { "epoch": 0.02, "learning_rate": 1.522167400546266e-05, "loss": 3.3976, "step": 2124288 }, { "epoch": 0.02, "learning_rate": 1.5213304436755871e-05, "loss": 3.3981, "step": 2124800 }, { "epoch": 0.02, "learning_rate": 1.5204918489245351e-05, "loss": 3.3921, "step": 2125312 }, { "epoch": 0.02, "learning_rate": 1.5196532541734831e-05, "loss": 3.3937, "step": 2125824 }, { "epoch": 0.02, "learning_rate": 1.5188146594224311e-05, "loss": 3.3962, "step": 2126336 }, { "epoch": 0.02, "learning_rate": 1.517976064671379e-05, "loss": 3.396, "step": 2126848 }, { "epoch": 0.02, "learning_rate": 1.517137469920327e-05, "loss": 3.3979, "step": 2127360 }, { "epoch": 0.02, "learning_rate": 1.516298875169275e-05, "loss": 3.4111, "step": 2127872 }, { "epoch": 0.02, "learning_rate": 1.515461918298596e-05, "loss": 3.3918, "step": 2128384 }, { "epoch": 0.02, "learning_rate": 1.514623323547544e-05, "loss": 3.3989, "step": 2128896 }, { "epoch": 0.02, "learning_rate": 1.5137847287964922e-05, "loss": 3.3973, "step": 2129408 }, { "epoch": 0.02, "learning_rate": 1.5129461340454402e-05, "loss": 3.3933, "step": 2129920 }, { "epoch": 0.02, "learning_rate": 1.512109177174761e-05, "loss": 3.3949, "step": 2130432 }, { "epoch": 0.02, "learning_rate": 1.5112705824237092e-05, "loss": 3.397, "step": 2130944 }, { "epoch": 0.02, "learning_rate": 1.5104319876726572e-05, "loss": 3.4082, "step": 2131456 }, { "epoch": 0.02, "learning_rate": 1.5095933929216052e-05, "loss": 3.4059, "step": 2131968 }, { "epoch": 0.02, "learning_rate": 1.5087564360509263e-05, "loss": 3.3995, "step": 2132480 }, { "epoch": 0.02, "learning_rate": 1.5079178412998743e-05, "loss": 3.3973, "step": 2132992 }, { "epoch": 0.02, "learning_rate": 1.5070792465488223e-05, "loss": 3.4019, "step": 2133504 }, { "epoch": 0.02, "learning_rate": 1.5062406517977703e-05, "loss": 3.3942, "step": 2134016 }, { "epoch": 0.02, "learning_rate": 1.5054053328074646e-05, "loss": 3.3918, "step": 2134528 }, { "epoch": 0.02, "learning_rate": 1.5045667380564126e-05, "loss": 3.3945, "step": 2135040 }, { "epoch": 0.02, "learning_rate": 1.5037281433053608e-05, "loss": 3.3882, "step": 2135552 }, { "epoch": 0.02, "learning_rate": 1.5028895485543084e-05, "loss": 3.3945, "step": 2136064 }, { "epoch": 0.02, "learning_rate": 1.5020509538032564e-05, "loss": 3.3918, "step": 2136576 }, { "epoch": 0.03, "eval_loss": 3.8685483932495117, "eval_runtime": 304.3266, "eval_samples_per_second": 1253.887, "eval_steps_per_second": 39.185, "step": 2136950 }, { "epoch": 1.0, "learning_rate": 1.5012123590522046e-05, "loss": 3.3991, "step": 2137088 }, { "epoch": 1.0, "learning_rate": 1.5003737643011526e-05, "loss": 3.3916, "step": 2137600 }, { "epoch": 1.0, "learning_rate": 1.4995351695501006e-05, "loss": 3.3949, "step": 2138112 }, { "epoch": 1.0, "learning_rate": 1.4986982126794217e-05, "loss": 3.4048, "step": 2138624 }, { "epoch": 1.0, "learning_rate": 1.4978596179283697e-05, "loss": 3.4058, "step": 2139136 }, { "epoch": 1.0, "learning_rate": 1.4970210231773177e-05, "loss": 3.3999, "step": 2139648 }, { "epoch": 1.0, "learning_rate": 1.4961824284262656e-05, "loss": 3.4032, "step": 2140160 }, { "epoch": 1.0, "learning_rate": 1.4953438336752138e-05, "loss": 3.3872, "step": 2140672 }, { "epoch": 1.0, "learning_rate": 1.4945068768045347e-05, "loss": 3.3851, "step": 2141184 }, { "epoch": 1.0, "learning_rate": 1.4936682820534827e-05, "loss": 3.3974, "step": 2141696 }, { "epoch": 1.0, "learning_rate": 1.4928296873024309e-05, "loss": 3.3972, "step": 2142208 }, { "epoch": 1.0, "learning_rate": 1.4919910925513789e-05, "loss": 3.391, "step": 2142720 }, { "epoch": 1.0, "learning_rate": 1.4911524978003265e-05, "loss": 3.398, "step": 2143232 }, { "epoch": 1.0, "learning_rate": 1.4903139030492747e-05, "loss": 3.3776, "step": 2143744 }, { "epoch": 1.0, "learning_rate": 1.4894753082982227e-05, "loss": 3.3845, "step": 2144256 }, { "epoch": 1.0, "learning_rate": 1.4886367135471707e-05, "loss": 3.3758, "step": 2144768 }, { "epoch": 1.0, "learning_rate": 1.4877997566764918e-05, "loss": 3.3968, "step": 2145280 }, { "epoch": 1.0, "learning_rate": 1.4869611619254398e-05, "loss": 3.3903, "step": 2145792 }, { "epoch": 1.0, "learning_rate": 1.4861225671743878e-05, "loss": 3.3895, "step": 2146304 }, { "epoch": 1.0, "learning_rate": 1.4852856103037088e-05, "loss": 3.3959, "step": 2146816 }, { "epoch": 1.0, "learning_rate": 1.4844486534330301e-05, "loss": 3.4061, "step": 2147328 }, { "epoch": 1.0, "learning_rate": 1.4836100586819781e-05, "loss": 3.3978, "step": 2147840 }, { "epoch": 1.0, "learning_rate": 1.4827714639309263e-05, "loss": 3.3936, "step": 2148352 }, { "epoch": 1.0, "learning_rate": 1.4819328691798739e-05, "loss": 3.3888, "step": 2148864 }, { "epoch": 1.0, "learning_rate": 1.4810942744288219e-05, "loss": 3.4037, "step": 2149376 }, { "epoch": 1.0, "learning_rate": 1.4802573175581433e-05, "loss": 3.3959, "step": 2149888 }, { "epoch": 1.0, "learning_rate": 1.479418722807091e-05, "loss": 3.3883, "step": 2150400 }, { "epoch": 1.0, "learning_rate": 1.4785801280560391e-05, "loss": 3.3938, "step": 2150912 }, { "epoch": 1.0, "learning_rate": 1.4777415333049871e-05, "loss": 3.3819, "step": 2151424 }, { "epoch": 1.0, "learning_rate": 1.4769029385539351e-05, "loss": 3.3884, "step": 2151936 }, { "epoch": 1.01, "learning_rate": 1.4760643438028831e-05, "loss": 3.3933, "step": 2152448 }, { "epoch": 1.01, "learning_rate": 1.4752273869322042e-05, "loss": 3.3899, "step": 2152960 }, { "epoch": 1.01, "learning_rate": 1.4743887921811522e-05, "loss": 3.3983, "step": 2153472 }, { "epoch": 1.01, "learning_rate": 1.4735501974301002e-05, "loss": 3.3998, "step": 2153984 }, { "epoch": 1.01, "learning_rate": 1.4727116026790484e-05, "loss": 3.3899, "step": 2154496 }, { "epoch": 1.01, "learning_rate": 1.4718730079279964e-05, "loss": 3.3954, "step": 2155008 }, { "epoch": 1.01, "learning_rate": 1.4710344131769444e-05, "loss": 3.4017, "step": 2155520 }, { "epoch": 1.01, "learning_rate": 1.4701958184258922e-05, "loss": 3.3837, "step": 2156032 }, { "epoch": 1.01, "learning_rate": 1.4693588615552134e-05, "loss": 3.3914, "step": 2156544 }, { "epoch": 1.01, "learning_rate": 1.4685202668041614e-05, "loss": 3.3777, "step": 2157056 }, { "epoch": 1.01, "learning_rate": 1.4676816720531093e-05, "loss": 3.3835, "step": 2157568 }, { "epoch": 1.01, "learning_rate": 1.4668430773020572e-05, "loss": 3.388, "step": 2158080 }, { "epoch": 1.01, "learning_rate": 1.4660044825510052e-05, "loss": 3.4019, "step": 2158592 }, { "epoch": 1.01, "learning_rate": 1.4651658877999532e-05, "loss": 3.384, "step": 2159104 }, { "epoch": 1.01, "learning_rate": 1.4643272930489012e-05, "loss": 3.3877, "step": 2159616 }, { "epoch": 1.01, "learning_rate": 1.4634886982978494e-05, "loss": 3.3908, "step": 2160128 }, { "epoch": 1.01, "learning_rate": 1.4626517414271703e-05, "loss": 3.3954, "step": 2160640 }, { "epoch": 1.01, "learning_rate": 1.4618147845564917e-05, "loss": 3.3764, "step": 2161152 }, { "epoch": 1.01, "learning_rate": 1.4609761898054394e-05, "loss": 3.3689, "step": 2161664 }, { "epoch": 1.01, "learning_rate": 1.4601375950543874e-05, "loss": 3.3915, "step": 2162176 }, { "epoch": 1.01, "learning_rate": 1.4592990003033355e-05, "loss": 3.4007, "step": 2162688 }, { "epoch": 1.01, "learning_rate": 1.4584604055522835e-05, "loss": 3.4011, "step": 2163200 }, { "epoch": 1.01, "learning_rate": 1.4576218108012315e-05, "loss": 3.3861, "step": 2163712 }, { "epoch": 1.01, "learning_rate": 1.4567832160501795e-05, "loss": 3.3875, "step": 2164224 }, { "epoch": 1.01, "learning_rate": 1.4559446212991274e-05, "loss": 3.3821, "step": 2164736 }, { "epoch": 1.01, "learning_rate": 1.4551076644284486e-05, "loss": 3.3783, "step": 2165248 }, { "epoch": 1.01, "learning_rate": 1.4542690696773966e-05, "loss": 3.4044, "step": 2165760 }, { "epoch": 1.01, "learning_rate": 1.4534321128067177e-05, "loss": 3.3777, "step": 2166272 }, { "epoch": 1.01, "learning_rate": 1.4525935180556657e-05, "loss": 3.4102, "step": 2166784 }, { "epoch": 1.01, "learning_rate": 1.4517549233046138e-05, "loss": 3.3925, "step": 2167296 }, { "epoch": 1.01, "learning_rate": 1.4509163285535618e-05, "loss": 3.3752, "step": 2167808 }, { "epoch": 1.01, "learning_rate": 1.4500777338025098e-05, "loss": 3.3911, "step": 2168320 }, { "epoch": 1.01, "learning_rate": 1.4492391390514577e-05, "loss": 3.3849, "step": 2168832 }, { "epoch": 1.01, "learning_rate": 1.4484005443004057e-05, "loss": 3.3742, "step": 2169344 }, { "epoch": 1.01, "learning_rate": 1.4475619495493536e-05, "loss": 3.3883, "step": 2169856 }, { "epoch": 1.01, "learning_rate": 1.4467249926786747e-05, "loss": 3.3991, "step": 2170368 }, { "epoch": 1.01, "learning_rate": 1.445888035807996e-05, "loss": 3.3788, "step": 2170880 }, { "epoch": 1.01, "learning_rate": 1.445049441056944e-05, "loss": 3.3896, "step": 2171392 }, { "epoch": 1.01, "learning_rate": 1.444210846305892e-05, "loss": 3.3689, "step": 2171904 }, { "epoch": 1.01, "learning_rate": 1.4433722515548398e-05, "loss": 3.3855, "step": 2172416 }, { "epoch": 1.01, "learning_rate": 1.4425336568037878e-05, "loss": 3.3843, "step": 2172928 }, { "epoch": 1.01, "learning_rate": 1.4416950620527358e-05, "loss": 3.3899, "step": 2173440 }, { "epoch": 1.01, "learning_rate": 1.440856467301684e-05, "loss": 3.385, "step": 2173952 }, { "epoch": 1.01, "learning_rate": 1.4400195104310049e-05, "loss": 3.3888, "step": 2174464 }, { "epoch": 1.01, "learning_rate": 1.439180915679953e-05, "loss": 3.4002, "step": 2174976 }, { "epoch": 1.01, "learning_rate": 1.438342320928901e-05, "loss": 3.395, "step": 2175488 }, { "epoch": 1.01, "learning_rate": 1.437503726177849e-05, "loss": 3.3912, "step": 2176000 }, { "epoch": 1.01, "learning_rate": 1.4366667693071701e-05, "loss": 3.3878, "step": 2176512 }, { "epoch": 1.01, "learning_rate": 1.4358281745561181e-05, "loss": 3.3831, "step": 2177024 }, { "epoch": 1.01, "learning_rate": 1.4349895798050661e-05, "loss": 3.3952, "step": 2177536 }, { "epoch": 1.01, "learning_rate": 1.434150985054014e-05, "loss": 3.3868, "step": 2178048 }, { "epoch": 1.01, "learning_rate": 1.4333140281833352e-05, "loss": 3.3894, "step": 2178560 }, { "epoch": 1.01, "learning_rate": 1.4324754334322832e-05, "loss": 3.3924, "step": 2179072 }, { "epoch": 1.01, "learning_rate": 1.4316368386812312e-05, "loss": 3.384, "step": 2179584 }, { "epoch": 1.01, "learning_rate": 1.4307982439301793e-05, "loss": 3.3683, "step": 2180096 }, { "epoch": 1.01, "learning_rate": 1.4299596491791273e-05, "loss": 3.3881, "step": 2180608 }, { "epoch": 1.01, "learning_rate": 1.429121054428075e-05, "loss": 3.3915, "step": 2181120 }, { "epoch": 1.01, "learning_rate": 1.4282824596770231e-05, "loss": 3.3805, "step": 2181632 }, { "epoch": 1.01, "learning_rate": 1.4274455028063444e-05, "loss": 3.3874, "step": 2182144 }, { "epoch": 1.01, "learning_rate": 1.4266069080552924e-05, "loss": 3.3835, "step": 2182656 }, { "epoch": 1.02, "learning_rate": 1.4257683133042402e-05, "loss": 3.3804, "step": 2183168 }, { "epoch": 1.02, "learning_rate": 1.4249297185531882e-05, "loss": 3.3797, "step": 2183680 }, { "epoch": 1.02, "learning_rate": 1.4240911238021362e-05, "loss": 3.3843, "step": 2184192 }, { "epoch": 1.02, "learning_rate": 1.4232541669314574e-05, "loss": 3.3907, "step": 2184704 }, { "epoch": 1.02, "learning_rate": 1.4224155721804053e-05, "loss": 3.3893, "step": 2185216 }, { "epoch": 1.02, "learning_rate": 1.4215769774293533e-05, "loss": 3.3967, "step": 2185728 }, { "epoch": 1.02, "learning_rate": 1.4207383826783013e-05, "loss": 3.3815, "step": 2186240 }, { "epoch": 1.02, "learning_rate": 1.4198997879272494e-05, "loss": 3.3818, "step": 2186752 }, { "epoch": 1.02, "learning_rate": 1.4190611931761974e-05, "loss": 3.3877, "step": 2187264 }, { "epoch": 1.02, "learning_rate": 1.4182225984251454e-05, "loss": 3.3935, "step": 2187776 }, { "epoch": 1.02, "learning_rate": 1.4173840036740932e-05, "loss": 3.3911, "step": 2188288 }, { "epoch": 1.02, "learning_rate": 1.4165470468034145e-05, "loss": 3.3914, "step": 2188800 }, { "epoch": 1.02, "learning_rate": 1.4157084520523625e-05, "loss": 3.3838, "step": 2189312 }, { "epoch": 1.02, "learning_rate": 1.4148698573013105e-05, "loss": 3.3839, "step": 2189824 }, { "epoch": 1.02, "learning_rate": 1.4140312625502583e-05, "loss": 3.3919, "step": 2190336 }, { "epoch": 1.02, "learning_rate": 1.4131943056795796e-05, "loss": 3.3845, "step": 2190848 }, { "epoch": 1.02, "learning_rate": 1.4123557109285277e-05, "loss": 3.3832, "step": 2191360 }, { "epoch": 1.02, "learning_rate": 1.4115171161774757e-05, "loss": 3.389, "step": 2191872 }, { "epoch": 1.02, "learning_rate": 1.4106785214264234e-05, "loss": 3.3801, "step": 2192384 }, { "epoch": 1.02, "learning_rate": 1.4098415645557448e-05, "loss": 3.3818, "step": 2192896 }, { "epoch": 1.02, "learning_rate": 1.4090029698046928e-05, "loss": 3.3805, "step": 2193408 }, { "epoch": 1.02, "learning_rate": 1.4081643750536404e-05, "loss": 3.3777, "step": 2193920 }, { "epoch": 1.02, "learning_rate": 1.4073257803025886e-05, "loss": 3.3893, "step": 2194432 }, { "epoch": 1.02, "learning_rate": 1.4064888234319099e-05, "loss": 3.3892, "step": 2194944 }, { "epoch": 1.02, "learning_rate": 1.405651866561231e-05, "loss": 3.3823, "step": 2195456 }, { "epoch": 1.02, "learning_rate": 1.404813271810179e-05, "loss": 3.3946, "step": 2195968 }, { "epoch": 1.02, "learning_rate": 1.403974677059127e-05, "loss": 3.401, "step": 2196480 }, { "epoch": 1.02, "learning_rate": 1.403136082308075e-05, "loss": 3.3849, "step": 2196992 }, { "epoch": 1.02, "learning_rate": 1.402297487557023e-05, "loss": 3.3872, "step": 2197504 }, { "epoch": 1.02, "learning_rate": 1.4014588928059707e-05, "loss": 3.3809, "step": 2198016 }, { "epoch": 1.02, "learning_rate": 1.4006202980549187e-05, "loss": 3.3852, "step": 2198528 }, { "epoch": 1.02, "learning_rate": 1.3997833411842402e-05, "loss": 3.3828, "step": 2199040 }, { "epoch": 1.02, "learning_rate": 1.3989447464331878e-05, "loss": 3.3848, "step": 2199552 }, { "epoch": 1.02, "learning_rate": 1.3981061516821358e-05, "loss": 3.3827, "step": 2200064 }, { "epoch": 1.02, "learning_rate": 1.397267556931084e-05, "loss": 3.3901, "step": 2200576 }, { "epoch": 1.02, "learning_rate": 1.3964306000604052e-05, "loss": 3.3845, "step": 2201088 }, { "epoch": 1.02, "learning_rate": 1.395592005309353e-05, "loss": 3.3869, "step": 2201600 }, { "epoch": 1.02, "learning_rate": 1.394753410558301e-05, "loss": 3.3847, "step": 2202112 }, { "epoch": 1.02, "learning_rate": 1.393914815807249e-05, "loss": 3.3833, "step": 2202624 }, { "epoch": 1.02, "learning_rate": 1.393076221056197e-05, "loss": 3.3835, "step": 2203136 }, { "epoch": 1.02, "learning_rate": 1.392237626305145e-05, "loss": 3.3926, "step": 2203648 }, { "epoch": 1.02, "learning_rate": 1.3913990315540932e-05, "loss": 3.3941, "step": 2204160 }, { "epoch": 1.02, "learning_rate": 1.3905620746834141e-05, "loss": 3.3837, "step": 2204672 }, { "epoch": 1.02, "learning_rate": 1.3897234799323621e-05, "loss": 3.3846, "step": 2205184 }, { "epoch": 1.02, "learning_rate": 1.3888848851813103e-05, "loss": 3.3916, "step": 2205696 }, { "epoch": 1.02, "learning_rate": 1.3880462904302583e-05, "loss": 3.3786, "step": 2206208 }, { "epoch": 1.02, "learning_rate": 1.3872093335595793e-05, "loss": 3.3898, "step": 2206720 }, { "epoch": 1.02, "learning_rate": 1.3863707388085273e-05, "loss": 3.3877, "step": 2207232 }, { "epoch": 1.02, "learning_rate": 1.3855321440574753e-05, "loss": 3.3993, "step": 2207744 }, { "epoch": 1.02, "learning_rate": 1.3846935493064233e-05, "loss": 3.3919, "step": 2208256 }, { "epoch": 1.02, "learning_rate": 1.3838565924357444e-05, "loss": 3.3941, "step": 2208768 }, { "epoch": 1.02, "learning_rate": 1.3830179976846924e-05, "loss": 3.3838, "step": 2209280 }, { "epoch": 1.02, "learning_rate": 1.3821794029336404e-05, "loss": 3.3911, "step": 2209792 }, { "epoch": 1.02, "learning_rate": 1.3813408081825886e-05, "loss": 3.3868, "step": 2210304 }, { "epoch": 1.02, "learning_rate": 1.3805054891922826e-05, "loss": 3.3812, "step": 2210816 }, { "epoch": 1.02, "learning_rate": 1.3796668944412306e-05, "loss": 3.3859, "step": 2211328 }, { "epoch": 1.02, "learning_rate": 1.3788282996901785e-05, "loss": 3.3764, "step": 2211840 }, { "epoch": 1.02, "learning_rate": 1.3779897049391265e-05, "loss": 3.3897, "step": 2212352 }, { "epoch": 1.02, "learning_rate": 1.3771511101880747e-05, "loss": 3.3794, "step": 2212864 }, { "epoch": 1.03, "eval_loss": 3.8699846267700195, "eval_runtime": 304.8376, "eval_samples_per_second": 1251.785, "eval_steps_per_second": 39.119, "step": 2213270 }, { "epoch": 0.0, "learning_rate": 1.3763125154370227e-05, "loss": 3.3969, "step": 2213376 }, { "epoch": 0.0, "learning_rate": 1.3754739206859707e-05, "loss": 3.3827, "step": 2213888 }, { "epoch": 0.0, "learning_rate": 1.3746353259349185e-05, "loss": 3.3855, "step": 2214400 }, { "epoch": 0.0, "learning_rate": 1.3737983690642398e-05, "loss": 3.3986, "step": 2214912 }, { "epoch": 0.0, "learning_rate": 1.3729597743131878e-05, "loss": 3.3905, "step": 2215424 }, { "epoch": 0.0, "learning_rate": 1.3721211795621358e-05, "loss": 3.3974, "step": 2215936 }, { "epoch": 0.0, "learning_rate": 1.3712825848110836e-05, "loss": 3.3879, "step": 2216448 }, { "epoch": 0.0, "learning_rate": 1.3704439900600316e-05, "loss": 3.3815, "step": 2216960 }, { "epoch": 0.0, "learning_rate": 1.3696070331893528e-05, "loss": 3.3732, "step": 2217472 }, { "epoch": 0.0, "learning_rate": 1.3687684384383007e-05, "loss": 3.3881, "step": 2217984 }, { "epoch": 0.0, "learning_rate": 1.3679298436872487e-05, "loss": 3.3849, "step": 2218496 }, { "epoch": 0.0, "learning_rate": 1.3670912489361967e-05, "loss": 3.3827, "step": 2219008 }, { "epoch": 0.0, "learning_rate": 1.3662526541851448e-05, "loss": 3.39, "step": 2219520 }, { "epoch": 0.0, "learning_rate": 1.3654140594340928e-05, "loss": 3.3643, "step": 2220032 }, { "epoch": 0.0, "learning_rate": 1.3645754646830408e-05, "loss": 3.3742, "step": 2220544 }, { "epoch": 0.0, "learning_rate": 1.3637368699319888e-05, "loss": 3.372, "step": 2221056 }, { "epoch": 0.0, "learning_rate": 1.3628999130613099e-05, "loss": 3.3826, "step": 2221568 }, { "epoch": 0.0, "learning_rate": 1.3620613183102579e-05, "loss": 3.3767, "step": 2222080 }, { "epoch": 0.0, "learning_rate": 1.3612227235592059e-05, "loss": 3.3796, "step": 2222592 }, { "epoch": 0.0, "learning_rate": 1.3603841288081537e-05, "loss": 3.3881, "step": 2223104 }, { "epoch": 0.0, "learning_rate": 1.359547171937475e-05, "loss": 3.3915, "step": 2223616 }, { "epoch": 0.0, "learning_rate": 1.358708577186423e-05, "loss": 3.39, "step": 2224128 }, { "epoch": 0.0, "learning_rate": 1.357871620315744e-05, "loss": 3.3831, "step": 2224640 }, { "epoch": 0.0, "learning_rate": 1.357033025564692e-05, "loss": 3.3806, "step": 2225152 }, { "epoch": 0.0, "learning_rate": 1.3561944308136402e-05, "loss": 3.3949, "step": 2225664 }, { "epoch": 0.0, "learning_rate": 1.3553558360625882e-05, "loss": 3.3841, "step": 2226176 }, { "epoch": 0.0, "learning_rate": 1.3545172413115362e-05, "loss": 3.3795, "step": 2226688 }, { "epoch": 0.0, "learning_rate": 1.353678646560484e-05, "loss": 3.3863, "step": 2227200 }, { "epoch": 0.0, "learning_rate": 1.3528416896898053e-05, "loss": 3.3713, "step": 2227712 }, { "epoch": 0.0, "learning_rate": 1.3520030949387532e-05, "loss": 3.3795, "step": 2228224 }, { "epoch": 0.01, "learning_rate": 1.351164500187701e-05, "loss": 3.3869, "step": 2228736 }, { "epoch": 0.01, "learning_rate": 1.350325905436649e-05, "loss": 3.3812, "step": 2229248 }, { "epoch": 0.01, "learning_rate": 1.3494889485659703e-05, "loss": 3.3869, "step": 2229760 }, { "epoch": 0.01, "learning_rate": 1.3486503538149183e-05, "loss": 3.3937, "step": 2230272 }, { "epoch": 0.01, "learning_rate": 1.3478117590638661e-05, "loss": 3.3804, "step": 2230784 }, { "epoch": 0.01, "learning_rate": 1.3469731643128141e-05, "loss": 3.3857, "step": 2231296 }, { "epoch": 0.01, "learning_rate": 1.3461345695617621e-05, "loss": 3.3949, "step": 2231808 }, { "epoch": 0.01, "learning_rate": 1.3452959748107103e-05, "loss": 3.3697, "step": 2232320 }, { "epoch": 0.01, "learning_rate": 1.3444590179400312e-05, "loss": 3.3816, "step": 2232832 }, { "epoch": 0.01, "learning_rate": 1.3436204231889794e-05, "loss": 3.3669, "step": 2233344 }, { "epoch": 0.01, "learning_rate": 1.3427818284379274e-05, "loss": 3.3764, "step": 2233856 }, { "epoch": 0.01, "learning_rate": 1.3419432336868754e-05, "loss": 3.3747, "step": 2234368 }, { "epoch": 0.01, "learning_rate": 1.3411046389358234e-05, "loss": 3.396, "step": 2234880 }, { "epoch": 0.01, "learning_rate": 1.3402660441847714e-05, "loss": 3.3726, "step": 2235392 }, { "epoch": 0.01, "learning_rate": 1.3394274494337192e-05, "loss": 3.3799, "step": 2235904 }, { "epoch": 0.01, "learning_rate": 1.3385888546826672e-05, "loss": 3.3807, "step": 2236416 }, { "epoch": 0.01, "learning_rate": 1.3377518978119886e-05, "loss": 3.3822, "step": 2236928 }, { "epoch": 0.01, "learning_rate": 1.3369133030609366e-05, "loss": 3.3715, "step": 2237440 }, { "epoch": 0.01, "learning_rate": 1.3360747083098842e-05, "loss": 3.3594, "step": 2237952 }, { "epoch": 0.01, "learning_rate": 1.3352361135588322e-05, "loss": 3.3825, "step": 2238464 }, { "epoch": 0.01, "learning_rate": 1.3343991566881537e-05, "loss": 3.3923, "step": 2238976 }, { "epoch": 0.01, "learning_rate": 1.3335605619371017e-05, "loss": 3.3858, "step": 2239488 }, { "epoch": 0.01, "learning_rate": 1.3327219671860495e-05, "loss": 3.377, "step": 2240000 }, { "epoch": 0.01, "learning_rate": 1.3318850103153707e-05, "loss": 3.3743, "step": 2240512 }, { "epoch": 0.01, "learning_rate": 1.3310464155643187e-05, "loss": 3.3785, "step": 2241024 }, { "epoch": 0.01, "learning_rate": 1.3302078208132665e-05, "loss": 3.3676, "step": 2241536 }, { "epoch": 0.01, "learning_rate": 1.3293692260622145e-05, "loss": 3.3971, "step": 2242048 }, { "epoch": 0.01, "learning_rate": 1.3285322691915358e-05, "loss": 3.3664, "step": 2242560 }, { "epoch": 0.01, "learning_rate": 1.3276936744404838e-05, "loss": 3.3996, "step": 2243072 }, { "epoch": 0.01, "learning_rate": 1.3268550796894316e-05, "loss": 3.3823, "step": 2243584 }, { "epoch": 0.01, "learning_rate": 1.3260164849383796e-05, "loss": 3.3663, "step": 2244096 }, { "epoch": 0.01, "learning_rate": 1.3251778901873276e-05, "loss": 3.3812, "step": 2244608 }, { "epoch": 0.01, "learning_rate": 1.3243392954362758e-05, "loss": 3.3787, "step": 2245120 }, { "epoch": 0.01, "learning_rate": 1.3235007006852238e-05, "loss": 3.3662, "step": 2245632 }, { "epoch": 0.01, "learning_rate": 1.3226621059341718e-05, "loss": 3.3712, "step": 2246144 }, { "epoch": 0.01, "learning_rate": 1.3218251490634928e-05, "loss": 3.3938, "step": 2246656 }, { "epoch": 0.01, "learning_rate": 1.3209881921928138e-05, "loss": 3.3718, "step": 2247168 }, { "epoch": 0.01, "learning_rate": 1.320149597441762e-05, "loss": 3.377, "step": 2247680 }, { "epoch": 0.01, "learning_rate": 1.3193110026907099e-05, "loss": 3.36, "step": 2248192 }, { "epoch": 0.01, "learning_rate": 1.3184724079396579e-05, "loss": 3.3763, "step": 2248704 }, { "epoch": 0.01, "learning_rate": 1.3176338131886059e-05, "loss": 3.3749, "step": 2249216 }, { "epoch": 0.01, "learning_rate": 1.316795218437554e-05, "loss": 3.3785, "step": 2249728 }, { "epoch": 0.01, "learning_rate": 1.315956623686502e-05, "loss": 3.3737, "step": 2250240 }, { "epoch": 0.01, "learning_rate": 1.3151180289354497e-05, "loss": 3.3814, "step": 2250752 }, { "epoch": 0.01, "learning_rate": 1.3142810720647711e-05, "loss": 3.3885, "step": 2251264 }, { "epoch": 0.01, "learning_rate": 1.3134424773137191e-05, "loss": 3.3808, "step": 2251776 }, { "epoch": 0.01, "learning_rate": 1.3126038825626671e-05, "loss": 3.3836, "step": 2252288 }, { "epoch": 0.01, "learning_rate": 1.3117669256919882e-05, "loss": 3.3801, "step": 2252800 }, { "epoch": 0.01, "learning_rate": 1.3109283309409362e-05, "loss": 3.3756, "step": 2253312 }, { "epoch": 0.01, "learning_rate": 1.3100897361898842e-05, "loss": 3.3819, "step": 2253824 }, { "epoch": 0.01, "learning_rate": 1.309251141438832e-05, "loss": 3.3757, "step": 2254336 }, { "epoch": 0.01, "learning_rate": 1.3084141845681533e-05, "loss": 3.3789, "step": 2254848 }, { "epoch": 0.01, "learning_rate": 1.3075755898171013e-05, "loss": 3.3889, "step": 2255360 }, { "epoch": 0.01, "learning_rate": 1.3067369950660494e-05, "loss": 3.3717, "step": 2255872 }, { "epoch": 0.01, "learning_rate": 1.3058984003149971e-05, "loss": 3.3577, "step": 2256384 }, { "epoch": 0.01, "learning_rate": 1.3050598055639451e-05, "loss": 3.3782, "step": 2256896 }, { "epoch": 0.01, "learning_rate": 1.3042212108128933e-05, "loss": 3.3774, "step": 2257408 }, { "epoch": 0.01, "learning_rate": 1.3033842539422142e-05, "loss": 3.3758, "step": 2257920 }, { "epoch": 0.01, "learning_rate": 1.3025456591911622e-05, "loss": 3.3753, "step": 2258432 }, { "epoch": 0.01, "learning_rate": 1.3017070644401103e-05, "loss": 3.3787, "step": 2258944 }, { "epoch": 0.02, "learning_rate": 1.3008684696890583e-05, "loss": 3.3674, "step": 2259456 }, { "epoch": 0.02, "learning_rate": 1.3000298749380063e-05, "loss": 3.3712, "step": 2259968 }, { "epoch": 0.02, "learning_rate": 1.2991912801869543e-05, "loss": 3.3721, "step": 2260480 }, { "epoch": 0.02, "learning_rate": 1.2983543233162754e-05, "loss": 3.3828, "step": 2260992 }, { "epoch": 0.02, "learning_rate": 1.2975157285652234e-05, "loss": 3.3779, "step": 2261504 }, { "epoch": 0.02, "learning_rate": 1.2966771338141714e-05, "loss": 3.384, "step": 2262016 }, { "epoch": 0.02, "learning_rate": 1.2958385390631195e-05, "loss": 3.3697, "step": 2262528 }, { "epoch": 0.02, "learning_rate": 1.2949999443120675e-05, "loss": 3.3736, "step": 2263040 }, { "epoch": 0.02, "learning_rate": 1.2941613495610152e-05, "loss": 3.3788, "step": 2263552 }, { "epoch": 0.02, "learning_rate": 1.2933227548099634e-05, "loss": 3.3854, "step": 2264064 }, { "epoch": 0.02, "learning_rate": 1.2924841600589114e-05, "loss": 3.3768, "step": 2264576 }, { "epoch": 0.02, "learning_rate": 1.2916472031882323e-05, "loss": 3.3847, "step": 2265088 }, { "epoch": 0.02, "learning_rate": 1.2908086084371804e-05, "loss": 3.377, "step": 2265600 }, { "epoch": 0.02, "learning_rate": 1.2899700136861284e-05, "loss": 3.3739, "step": 2266112 }, { "epoch": 0.02, "learning_rate": 1.2891314189350764e-05, "loss": 3.3832, "step": 2266624 }, { "epoch": 0.02, "learning_rate": 1.2882928241840244e-05, "loss": 3.3711, "step": 2267136 }, { "epoch": 0.02, "learning_rate": 1.2874542294329726e-05, "loss": 3.3735, "step": 2267648 }, { "epoch": 0.02, "learning_rate": 1.2866156346819206e-05, "loss": 3.3789, "step": 2268160 }, { "epoch": 0.02, "learning_rate": 1.2857770399308682e-05, "loss": 3.3711, "step": 2268672 }, { "epoch": 0.02, "learning_rate": 1.2849400830601897e-05, "loss": 3.3702, "step": 2269184 }, { "epoch": 0.02, "learning_rate": 1.2841014883091376e-05, "loss": 3.3727, "step": 2269696 }, { "epoch": 0.02, "learning_rate": 1.2832628935580856e-05, "loss": 3.3673, "step": 2270208 }, { "epoch": 0.02, "learning_rate": 1.2824242988070335e-05, "loss": 3.3773, "step": 2270720 }, { "epoch": 0.02, "learning_rate": 1.2815873419363547e-05, "loss": 3.3793, "step": 2271232 }, { "epoch": 0.02, "learning_rate": 1.2807487471853027e-05, "loss": 3.371, "step": 2271744 }, { "epoch": 0.02, "learning_rate": 1.2799101524342505e-05, "loss": 3.3855, "step": 2272256 }, { "epoch": 0.02, "learning_rate": 1.2790715576831985e-05, "loss": 3.3933, "step": 2272768 }, { "epoch": 0.02, "learning_rate": 1.2782346008125198e-05, "loss": 3.3751, "step": 2273280 }, { "epoch": 0.02, "learning_rate": 1.2773960060614678e-05, "loss": 3.38, "step": 2273792 }, { "epoch": 0.02, "learning_rate": 1.2765574113104156e-05, "loss": 3.3728, "step": 2274304 }, { "epoch": 0.02, "learning_rate": 1.2757204544397369e-05, "loss": 3.3734, "step": 2274816 }, { "epoch": 0.02, "learning_rate": 1.274883497569058e-05, "loss": 3.3701, "step": 2275328 }, { "epoch": 0.02, "learning_rate": 1.274044902818006e-05, "loss": 3.3756, "step": 2275840 }, { "epoch": 0.02, "learning_rate": 1.2732063080669541e-05, "loss": 3.374, "step": 2276352 }, { "epoch": 0.02, "learning_rate": 1.2723677133159021e-05, "loss": 3.3804, "step": 2276864 }, { "epoch": 0.02, "learning_rate": 1.2715291185648501e-05, "loss": 3.3763, "step": 2277376 }, { "epoch": 0.02, "learning_rate": 1.2706905238137979e-05, "loss": 3.3772, "step": 2277888 }, { "epoch": 0.02, "learning_rate": 1.2698519290627459e-05, "loss": 3.3753, "step": 2278400 }, { "epoch": 0.02, "learning_rate": 1.2690133343116939e-05, "loss": 3.3727, "step": 2278912 }, { "epoch": 0.02, "learning_rate": 1.2681763774410152e-05, "loss": 3.3728, "step": 2279424 }, { "epoch": 0.02, "learning_rate": 1.267337782689963e-05, "loss": 3.3839, "step": 2279936 }, { "epoch": 0.02, "learning_rate": 1.266499187938911e-05, "loss": 3.3863, "step": 2280448 }, { "epoch": 0.02, "learning_rate": 1.265660593187859e-05, "loss": 3.3754, "step": 2280960 }, { "epoch": 0.02, "learning_rate": 1.2648236363171804e-05, "loss": 3.3732, "step": 2281472 }, { "epoch": 0.02, "learning_rate": 1.263985041566128e-05, "loss": 3.3802, "step": 2281984 }, { "epoch": 0.02, "learning_rate": 1.263146446815076e-05, "loss": 3.3713, "step": 2282496 }, { "epoch": 0.02, "learning_rate": 1.2623078520640242e-05, "loss": 3.378, "step": 2283008 }, { "epoch": 0.02, "learning_rate": 1.2614708951933451e-05, "loss": 3.3776, "step": 2283520 }, { "epoch": 0.02, "learning_rate": 1.2606323004422931e-05, "loss": 3.3922, "step": 2284032 }, { "epoch": 0.02, "learning_rate": 1.2597937056912413e-05, "loss": 3.3776, "step": 2284544 }, { "epoch": 0.02, "learning_rate": 1.2589567488205625e-05, "loss": 3.3835, "step": 2285056 }, { "epoch": 0.02, "learning_rate": 1.2581181540695103e-05, "loss": 3.3745, "step": 2285568 }, { "epoch": 0.02, "learning_rate": 1.2572795593184583e-05, "loss": 3.3848, "step": 2286080 }, { "epoch": 0.02, "learning_rate": 1.2564409645674063e-05, "loss": 3.3724, "step": 2286592 }, { "epoch": 0.02, "learning_rate": 1.2556056455771007e-05, "loss": 3.37, "step": 2287104 }, { "epoch": 0.02, "learning_rate": 1.2547670508260487e-05, "loss": 3.3787, "step": 2287616 }, { "epoch": 0.02, "learning_rate": 1.2539284560749967e-05, "loss": 3.3649, "step": 2288128 }, { "epoch": 0.02, "learning_rate": 1.2530898613239447e-05, "loss": 3.381, "step": 2288640 }, { "epoch": 0.02, "learning_rate": 1.2522512665728925e-05, "loss": 3.3659, "step": 2289152 }, { "epoch": 0.03, "eval_loss": 3.871690273284912, "eval_runtime": 305.9963, "eval_samples_per_second": 1247.045, "eval_steps_per_second": 38.971, "step": 2289590 }, { "epoch": 1.0, "learning_rate": 1.2514126718218405e-05, "loss": 3.3778, "step": 2289664 }, { "epoch": 1.0, "learning_rate": 1.2505740770707885e-05, "loss": 3.3753, "step": 2290176 }, { "epoch": 1.0, "learning_rate": 1.2497354823197366e-05, "loss": 3.3733, "step": 2290688 }, { "epoch": 1.0, "learning_rate": 1.2488985254490577e-05, "loss": 3.3896, "step": 2291200 }, { "epoch": 1.0, "learning_rate": 1.248061568578379e-05, "loss": 3.3799, "step": 2291712 }, { "epoch": 1.0, "learning_rate": 1.2472229738273268e-05, "loss": 3.3899, "step": 2292224 }, { "epoch": 1.0, "learning_rate": 1.2463843790762748e-05, "loss": 3.3745, "step": 2292736 }, { "epoch": 1.0, "learning_rate": 1.2455457843252228e-05, "loss": 3.3695, "step": 2293248 }, { "epoch": 1.0, "learning_rate": 1.2447088274545439e-05, "loss": 3.3671, "step": 2293760 }, { "epoch": 1.0, "learning_rate": 1.2438702327034919e-05, "loss": 3.3802, "step": 2294272 }, { "epoch": 1.0, "learning_rate": 1.24303163795244e-05, "loss": 3.371, "step": 2294784 }, { "epoch": 1.0, "learning_rate": 1.242193043201388e-05, "loss": 3.3729, "step": 2295296 }, { "epoch": 1.0, "learning_rate": 1.2413544484503358e-05, "loss": 3.3794, "step": 2295808 }, { "epoch": 1.0, "learning_rate": 1.2405158536992838e-05, "loss": 3.3608, "step": 2296320 }, { "epoch": 1.0, "learning_rate": 1.239677258948232e-05, "loss": 3.3619, "step": 2296832 }, { "epoch": 1.0, "learning_rate": 1.2388386641971798e-05, "loss": 3.3637, "step": 2297344 }, { "epoch": 1.0, "learning_rate": 1.238001707326501e-05, "loss": 3.3701, "step": 2297856 }, { "epoch": 1.0, "learning_rate": 1.237163112575449e-05, "loss": 3.3704, "step": 2298368 }, { "epoch": 1.0, "learning_rate": 1.236324517824397e-05, "loss": 3.3709, "step": 2298880 }, { "epoch": 1.0, "learning_rate": 1.2354859230733449e-05, "loss": 3.3764, "step": 2299392 }, { "epoch": 1.0, "learning_rate": 1.2346489662026661e-05, "loss": 3.3825, "step": 2299904 }, { "epoch": 1.0, "learning_rate": 1.2338103714516141e-05, "loss": 3.3751, "step": 2300416 }, { "epoch": 1.0, "learning_rate": 1.2329734145809354e-05, "loss": 3.3771, "step": 2300928 }, { "epoch": 1.0, "learning_rate": 1.2321348198298832e-05, "loss": 3.3697, "step": 2301440 }, { "epoch": 1.0, "learning_rate": 1.2312962250788312e-05, "loss": 3.3867, "step": 2301952 }, { "epoch": 1.0, "learning_rate": 1.2304576303277792e-05, "loss": 3.3707, "step": 2302464 }, { "epoch": 1.0, "learning_rate": 1.2296190355767272e-05, "loss": 3.3717, "step": 2302976 }, { "epoch": 1.0, "learning_rate": 1.2287804408256752e-05, "loss": 3.3722, "step": 2303488 }, { "epoch": 1.0, "learning_rate": 1.2279434839549964e-05, "loss": 3.3658, "step": 2304000 }, { "epoch": 1.0, "learning_rate": 1.2271048892039444e-05, "loss": 3.371, "step": 2304512 }, { "epoch": 1.01, "learning_rate": 1.2262662944528923e-05, "loss": 3.3714, "step": 2305024 }, { "epoch": 1.01, "learning_rate": 1.2254276997018403e-05, "loss": 3.3748, "step": 2305536 }, { "epoch": 1.01, "learning_rate": 1.2245907428311615e-05, "loss": 3.3772, "step": 2306048 }, { "epoch": 1.01, "learning_rate": 1.2237521480801093e-05, "loss": 3.3806, "step": 2306560 }, { "epoch": 1.01, "learning_rate": 1.2229135533290573e-05, "loss": 3.3732, "step": 2307072 }, { "epoch": 1.01, "learning_rate": 1.2220749585780055e-05, "loss": 3.375, "step": 2307584 }, { "epoch": 1.01, "learning_rate": 1.2212363638269535e-05, "loss": 3.3829, "step": 2308096 }, { "epoch": 1.01, "learning_rate": 1.2203977690759013e-05, "loss": 3.36, "step": 2308608 }, { "epoch": 1.01, "learning_rate": 1.2195608122052226e-05, "loss": 3.3719, "step": 2309120 }, { "epoch": 1.01, "learning_rate": 1.2187222174541706e-05, "loss": 3.3573, "step": 2309632 }, { "epoch": 1.01, "learning_rate": 1.2178836227031184e-05, "loss": 3.3694, "step": 2310144 }, { "epoch": 1.01, "learning_rate": 1.2170450279520666e-05, "loss": 3.3639, "step": 2310656 }, { "epoch": 1.01, "learning_rate": 1.2162064332010146e-05, "loss": 3.3837, "step": 2311168 }, { "epoch": 1.01, "learning_rate": 1.2153678384499625e-05, "loss": 3.3634, "step": 2311680 }, { "epoch": 1.01, "learning_rate": 1.2145292436989104e-05, "loss": 3.3662, "step": 2312192 }, { "epoch": 1.01, "learning_rate": 1.2136906489478585e-05, "loss": 3.3752, "step": 2312704 }, { "epoch": 1.01, "learning_rate": 1.2128536920771796e-05, "loss": 3.3707, "step": 2313216 }, { "epoch": 1.01, "learning_rate": 1.2120150973261274e-05, "loss": 3.3662, "step": 2313728 }, { "epoch": 1.01, "learning_rate": 1.2111765025750756e-05, "loss": 3.3467, "step": 2314240 }, { "epoch": 1.01, "learning_rate": 1.2103379078240236e-05, "loss": 3.3738, "step": 2314752 }, { "epoch": 1.01, "learning_rate": 1.2095009509533447e-05, "loss": 3.3807, "step": 2315264 }, { "epoch": 1.01, "learning_rate": 1.2086623562022927e-05, "loss": 3.3786, "step": 2315776 }, { "epoch": 1.01, "learning_rate": 1.2078237614512407e-05, "loss": 3.3707, "step": 2316288 }, { "epoch": 1.01, "learning_rate": 1.206986804580562e-05, "loss": 3.3611, "step": 2316800 }, { "epoch": 1.01, "learning_rate": 1.20614820982951e-05, "loss": 3.3707, "step": 2317312 }, { "epoch": 1.01, "learning_rate": 1.2053096150784577e-05, "loss": 3.3583, "step": 2317824 }, { "epoch": 1.01, "learning_rate": 1.2044710203274057e-05, "loss": 3.3847, "step": 2318336 }, { "epoch": 1.01, "learning_rate": 1.203634063456727e-05, "loss": 3.3585, "step": 2318848 }, { "epoch": 1.01, "learning_rate": 1.2027954687056748e-05, "loss": 3.3876, "step": 2319360 }, { "epoch": 1.01, "learning_rate": 1.2019568739546228e-05, "loss": 3.3763, "step": 2319872 }, { "epoch": 1.01, "learning_rate": 1.201118279203571e-05, "loss": 3.3533, "step": 2320384 }, { "epoch": 1.01, "learning_rate": 1.200279684452519e-05, "loss": 3.3692, "step": 2320896 }, { "epoch": 1.01, "learning_rate": 1.1994410897014668e-05, "loss": 3.3707, "step": 2321408 }, { "epoch": 1.01, "learning_rate": 1.1986024949504148e-05, "loss": 3.3577, "step": 2321920 }, { "epoch": 1.01, "learning_rate": 1.197763900199363e-05, "loss": 3.3584, "step": 2322432 }, { "epoch": 1.01, "learning_rate": 1.1969269433286839e-05, "loss": 3.3819, "step": 2322944 }, { "epoch": 1.01, "learning_rate": 1.1960899864580051e-05, "loss": 3.3672, "step": 2323456 }, { "epoch": 1.01, "learning_rate": 1.1952513917069531e-05, "loss": 3.3656, "step": 2323968 }, { "epoch": 1.01, "learning_rate": 1.1944127969559011e-05, "loss": 3.3525, "step": 2324480 }, { "epoch": 1.01, "learning_rate": 1.1935742022048491e-05, "loss": 3.3652, "step": 2324992 }, { "epoch": 1.01, "learning_rate": 1.1927356074537971e-05, "loss": 3.3612, "step": 2325504 }, { "epoch": 1.01, "learning_rate": 1.1918970127027451e-05, "loss": 3.3734, "step": 2326016 }, { "epoch": 1.01, "learning_rate": 1.1910584179516931e-05, "loss": 3.3619, "step": 2326528 }, { "epoch": 1.01, "learning_rate": 1.1902198232006411e-05, "loss": 3.3739, "step": 2327040 }, { "epoch": 1.01, "learning_rate": 1.1893828663299622e-05, "loss": 3.3744, "step": 2327552 }, { "epoch": 1.01, "learning_rate": 1.1885442715789102e-05, "loss": 3.3709, "step": 2328064 }, { "epoch": 1.01, "learning_rate": 1.1877056768278582e-05, "loss": 3.3696, "step": 2328576 }, { "epoch": 1.01, "learning_rate": 1.1868687199571792e-05, "loss": 3.3696, "step": 2329088 }, { "epoch": 1.01, "learning_rate": 1.1860301252061274e-05, "loss": 3.3682, "step": 2329600 }, { "epoch": 1.01, "learning_rate": 1.1851915304550752e-05, "loss": 3.371, "step": 2330112 }, { "epoch": 1.01, "learning_rate": 1.1843529357040232e-05, "loss": 3.368, "step": 2330624 }, { "epoch": 1.01, "learning_rate": 1.1835159788333445e-05, "loss": 3.3684, "step": 2331136 }, { "epoch": 1.01, "learning_rate": 1.1826773840822925e-05, "loss": 3.3706, "step": 2331648 }, { "epoch": 1.01, "learning_rate": 1.1818387893312403e-05, "loss": 3.3651, "step": 2332160 }, { "epoch": 1.01, "learning_rate": 1.1810001945801885e-05, "loss": 3.3495, "step": 2332672 }, { "epoch": 1.01, "learning_rate": 1.1801615998291365e-05, "loss": 3.3677, "step": 2333184 }, { "epoch": 1.01, "learning_rate": 1.1793230050780843e-05, "loss": 3.3641, "step": 2333696 }, { "epoch": 1.01, "learning_rate": 1.1784844103270323e-05, "loss": 3.3693, "step": 2334208 }, { "epoch": 1.01, "learning_rate": 1.1776474534563535e-05, "loss": 3.3662, "step": 2334720 }, { "epoch": 1.01, "learning_rate": 1.1768088587053015e-05, "loss": 3.3698, "step": 2335232 }, { "epoch": 1.02, "learning_rate": 1.1759702639542493e-05, "loss": 3.3596, "step": 2335744 }, { "epoch": 1.02, "learning_rate": 1.1751316692031975e-05, "loss": 3.3573, "step": 2336256 }, { "epoch": 1.02, "learning_rate": 1.1742930744521455e-05, "loss": 3.3602, "step": 2336768 }, { "epoch": 1.02, "learning_rate": 1.1734561175814666e-05, "loss": 3.3745, "step": 2337280 }, { "epoch": 1.02, "learning_rate": 1.1726175228304146e-05, "loss": 3.3656, "step": 2337792 }, { "epoch": 1.02, "learning_rate": 1.1717789280793626e-05, "loss": 3.3763, "step": 2338304 }, { "epoch": 1.02, "learning_rate": 1.1709403333283106e-05, "loss": 3.3611, "step": 2338816 }, { "epoch": 1.02, "learning_rate": 1.1701017385772586e-05, "loss": 3.3657, "step": 2339328 }, { "epoch": 1.02, "learning_rate": 1.1692631438262066e-05, "loss": 3.3666, "step": 2339840 }, { "epoch": 1.02, "learning_rate": 1.1684245490751546e-05, "loss": 3.3754, "step": 2340352 }, { "epoch": 1.02, "learning_rate": 1.1675859543241024e-05, "loss": 3.3688, "step": 2340864 }, { "epoch": 1.02, "learning_rate": 1.1667489974534236e-05, "loss": 3.3761, "step": 2341376 }, { "epoch": 1.02, "learning_rate": 1.1659104027023716e-05, "loss": 3.3639, "step": 2341888 }, { "epoch": 1.02, "learning_rate": 1.1650718079513196e-05, "loss": 3.3624, "step": 2342400 }, { "epoch": 1.02, "learning_rate": 1.1642332132002676e-05, "loss": 3.3759, "step": 2342912 }, { "epoch": 1.02, "learning_rate": 1.1633962563295887e-05, "loss": 3.3603, "step": 2343424 }, { "epoch": 1.02, "learning_rate": 1.1625576615785367e-05, "loss": 3.362, "step": 2343936 }, { "epoch": 1.02, "learning_rate": 1.1617190668274849e-05, "loss": 3.3672, "step": 2344448 }, { "epoch": 1.02, "learning_rate": 1.1608804720764327e-05, "loss": 3.3625, "step": 2344960 }, { "epoch": 1.02, "learning_rate": 1.160043515205754e-05, "loss": 3.3652, "step": 2345472 }, { "epoch": 1.02, "learning_rate": 1.159204920454702e-05, "loss": 3.3641, "step": 2345984 }, { "epoch": 1.02, "learning_rate": 1.1583663257036498e-05, "loss": 3.3553, "step": 2346496 }, { "epoch": 1.02, "learning_rate": 1.1575277309525978e-05, "loss": 3.3708, "step": 2347008 }, { "epoch": 1.02, "learning_rate": 1.156690774081919e-05, "loss": 3.3662, "step": 2347520 }, { "epoch": 1.02, "learning_rate": 1.155852179330867e-05, "loss": 3.3632, "step": 2348032 }, { "epoch": 1.02, "learning_rate": 1.1550135845798148e-05, "loss": 3.372, "step": 2348544 }, { "epoch": 1.02, "learning_rate": 1.154174989828763e-05, "loss": 3.3828, "step": 2349056 }, { "epoch": 1.02, "learning_rate": 1.153338032958084e-05, "loss": 3.3695, "step": 2349568 }, { "epoch": 1.02, "learning_rate": 1.152499438207032e-05, "loss": 3.3682, "step": 2350080 }, { "epoch": 1.02, "learning_rate": 1.15166084345598e-05, "loss": 3.3621, "step": 2350592 }, { "epoch": 1.02, "learning_rate": 1.150822248704928e-05, "loss": 3.3675, "step": 2351104 }, { "epoch": 1.02, "learning_rate": 1.1499869297146224e-05, "loss": 3.3575, "step": 2351616 }, { "epoch": 1.02, "learning_rate": 1.1491483349635704e-05, "loss": 3.3681, "step": 2352128 }, { "epoch": 1.02, "learning_rate": 1.1483097402125182e-05, "loss": 3.3612, "step": 2352640 }, { "epoch": 1.02, "learning_rate": 1.1474711454614664e-05, "loss": 3.3705, "step": 2353152 }, { "epoch": 1.02, "learning_rate": 1.1466341885907874e-05, "loss": 3.3638, "step": 2353664 }, { "epoch": 1.02, "learning_rate": 1.1457955938397354e-05, "loss": 3.3663, "step": 2354176 }, { "epoch": 1.02, "learning_rate": 1.1449569990886834e-05, "loss": 3.3686, "step": 2354688 }, { "epoch": 1.02, "learning_rate": 1.1441184043376314e-05, "loss": 3.3642, "step": 2355200 }, { "epoch": 1.02, "learning_rate": 1.1432798095865794e-05, "loss": 3.3595, "step": 2355712 }, { "epoch": 1.02, "learning_rate": 1.1424412148355274e-05, "loss": 3.374, "step": 2356224 }, { "epoch": 1.02, "learning_rate": 1.1416026200844754e-05, "loss": 3.378, "step": 2356736 }, { "epoch": 1.02, "learning_rate": 1.1407640253334234e-05, "loss": 3.3727, "step": 2357248 }, { "epoch": 1.02, "learning_rate": 1.1399270684627445e-05, "loss": 3.3623, "step": 2357760 }, { "epoch": 1.02, "learning_rate": 1.1390884737116925e-05, "loss": 3.3677, "step": 2358272 }, { "epoch": 1.02, "learning_rate": 1.1382498789606405e-05, "loss": 3.3614, "step": 2358784 }, { "epoch": 1.02, "learning_rate": 1.1374129220899617e-05, "loss": 3.3714, "step": 2359296 }, { "epoch": 1.02, "learning_rate": 1.1365743273389096e-05, "loss": 3.3683, "step": 2359808 }, { "epoch": 1.02, "learning_rate": 1.1357357325878576e-05, "loss": 3.3827, "step": 2360320 }, { "epoch": 1.02, "learning_rate": 1.1348971378368056e-05, "loss": 3.3668, "step": 2360832 }, { "epoch": 1.02, "learning_rate": 1.1340601809661268e-05, "loss": 3.3778, "step": 2361344 }, { "epoch": 1.02, "learning_rate": 1.1332215862150746e-05, "loss": 3.3657, "step": 2361856 }, { "epoch": 1.02, "learning_rate": 1.1323829914640228e-05, "loss": 3.3711, "step": 2362368 }, { "epoch": 1.02, "learning_rate": 1.1315443967129708e-05, "loss": 3.3606, "step": 2362880 }, { "epoch": 1.02, "learning_rate": 1.1307090777226651e-05, "loss": 3.3625, "step": 2363392 }, { "epoch": 1.02, "learning_rate": 1.129870482971613e-05, "loss": 3.3693, "step": 2363904 }, { "epoch": 1.02, "learning_rate": 1.129031888220561e-05, "loss": 3.3565, "step": 2364416 }, { "epoch": 1.02, "learning_rate": 1.128193293469509e-05, "loss": 3.3708, "step": 2364928 }, { "epoch": 1.02, "learning_rate": 1.127354698718457e-05, "loss": 3.3609, "step": 2365440 }, { "epoch": 1.03, "eval_loss": 3.8720974922180176, "eval_runtime": 303.2602, "eval_samples_per_second": 1258.296, "eval_steps_per_second": 39.323, "step": 2365910 }, { "epoch": 0.0, "learning_rate": 1.126516103967405e-05, "loss": 3.3573, "step": 2365952 }, { "epoch": 0.0, "learning_rate": 1.125677509216353e-05, "loss": 3.3666, "step": 2366464 }, { "epoch": 0.0, "learning_rate": 1.124838914465301e-05, "loss": 3.3628, "step": 2366976 }, { "epoch": 0.0, "learning_rate": 1.124001957594622e-05, "loss": 3.375, "step": 2367488 }, { "epoch": 0.0, "learning_rate": 1.12316336284357e-05, "loss": 3.3743, "step": 2368000 }, { "epoch": 0.0, "learning_rate": 1.122324768092518e-05, "loss": 3.3773, "step": 2368512 }, { "epoch": 0.0, "learning_rate": 1.121486173341466e-05, "loss": 3.3655, "step": 2369024 }, { "epoch": 0.0, "learning_rate": 1.120647578590414e-05, "loss": 3.3629, "step": 2369536 }, { "epoch": 0.0, "learning_rate": 1.1198106217197352e-05, "loss": 3.3513, "step": 2370048 }, { "epoch": 0.0, "learning_rate": 1.118972026968683e-05, "loss": 3.37, "step": 2370560 }, { "epoch": 0.0, "learning_rate": 1.118133432217631e-05, "loss": 3.3641, "step": 2371072 }, { "epoch": 0.0, "learning_rate": 1.117294837466579e-05, "loss": 3.3648, "step": 2371584 }, { "epoch": 0.0, "learning_rate": 1.1164562427155272e-05, "loss": 3.3667, "step": 2372096 }, { "epoch": 0.0, "learning_rate": 1.115617647964475e-05, "loss": 3.3543, "step": 2372608 }, { "epoch": 0.0, "learning_rate": 1.114779053213423e-05, "loss": 3.3524, "step": 2373120 }, { "epoch": 0.0, "learning_rate": 1.113940458462371e-05, "loss": 3.3551, "step": 2373632 }, { "epoch": 0.0, "learning_rate": 1.1131035015916921e-05, "loss": 3.3565, "step": 2374144 }, { "epoch": 0.0, "learning_rate": 1.1122649068406401e-05, "loss": 3.36, "step": 2374656 }, { "epoch": 0.0, "learning_rate": 1.1114263120895883e-05, "loss": 3.3637, "step": 2375168 }, { "epoch": 0.0, "learning_rate": 1.1105877173385363e-05, "loss": 3.3606, "step": 2375680 }, { "epoch": 0.0, "learning_rate": 1.1097507604678572e-05, "loss": 3.3772, "step": 2376192 }, { "epoch": 0.0, "learning_rate": 1.1089121657168053e-05, "loss": 3.3654, "step": 2376704 }, { "epoch": 0.0, "learning_rate": 1.1080752088461264e-05, "loss": 3.3662, "step": 2377216 }, { "epoch": 0.0, "learning_rate": 1.1072366140950744e-05, "loss": 3.3616, "step": 2377728 }, { "epoch": 0.0, "learning_rate": 1.1063980193440224e-05, "loss": 3.374, "step": 2378240 }, { "epoch": 0.0, "learning_rate": 1.1055594245929704e-05, "loss": 3.3587, "step": 2378752 }, { "epoch": 0.0, "learning_rate": 1.1047208298419184e-05, "loss": 3.3647, "step": 2379264 }, { "epoch": 0.0, "learning_rate": 1.1038838729712395e-05, "loss": 3.3588, "step": 2379776 }, { "epoch": 0.0, "learning_rate": 1.1030452782201875e-05, "loss": 3.3599, "step": 2380288 }, { "epoch": 0.0, "learning_rate": 1.1022066834691355e-05, "loss": 3.3625, "step": 2380800 }, { "epoch": 0.01, "learning_rate": 1.1013680887180836e-05, "loss": 3.3584, "step": 2381312 }, { "epoch": 0.01, "learning_rate": 1.1005294939670315e-05, "loss": 3.3677, "step": 2381824 }, { "epoch": 0.01, "learning_rate": 1.0996925370963525e-05, "loss": 3.3696, "step": 2382336 }, { "epoch": 0.01, "learning_rate": 1.0988539423453007e-05, "loss": 3.3671, "step": 2382848 }, { "epoch": 0.01, "learning_rate": 1.0980153475942485e-05, "loss": 3.3624, "step": 2383360 }, { "epoch": 0.01, "learning_rate": 1.0971767528431965e-05, "loss": 3.3674, "step": 2383872 }, { "epoch": 0.01, "learning_rate": 1.0963381580921445e-05, "loss": 3.3679, "step": 2384384 }, { "epoch": 0.01, "learning_rate": 1.0954995633410927e-05, "loss": 3.354, "step": 2384896 }, { "epoch": 0.01, "learning_rate": 1.0946626064704136e-05, "loss": 3.3587, "step": 2385408 }, { "epoch": 0.01, "learning_rate": 1.0938240117193618e-05, "loss": 3.348, "step": 2385920 }, { "epoch": 0.01, "learning_rate": 1.0929854169683098e-05, "loss": 3.3585, "step": 2386432 }, { "epoch": 0.01, "learning_rate": 1.0921468222172576e-05, "loss": 3.3535, "step": 2386944 }, { "epoch": 0.01, "learning_rate": 1.0913082274662056e-05, "loss": 3.3758, "step": 2387456 }, { "epoch": 0.01, "learning_rate": 1.0904696327151537e-05, "loss": 3.3584, "step": 2387968 }, { "epoch": 0.01, "learning_rate": 1.0896310379641017e-05, "loss": 3.3551, "step": 2388480 }, { "epoch": 0.01, "learning_rate": 1.0887924432130496e-05, "loss": 3.3642, "step": 2388992 }, { "epoch": 0.01, "learning_rate": 1.0879554863423708e-05, "loss": 3.3633, "step": 2389504 }, { "epoch": 0.01, "learning_rate": 1.0871168915913188e-05, "loss": 3.3572, "step": 2390016 }, { "epoch": 0.01, "learning_rate": 1.0862782968402666e-05, "loss": 3.3384, "step": 2390528 }, { "epoch": 0.01, "learning_rate": 1.0854397020892148e-05, "loss": 3.3582, "step": 2391040 }, { "epoch": 0.01, "learning_rate": 1.0846027452185359e-05, "loss": 3.3722, "step": 2391552 }, { "epoch": 0.01, "learning_rate": 1.0837641504674839e-05, "loss": 3.3688, "step": 2392064 }, { "epoch": 0.01, "learning_rate": 1.0829255557164319e-05, "loss": 3.3607, "step": 2392576 }, { "epoch": 0.01, "learning_rate": 1.082088598845753e-05, "loss": 3.3491, "step": 2393088 }, { "epoch": 0.01, "learning_rate": 1.081250004094701e-05, "loss": 3.3642, "step": 2393600 }, { "epoch": 0.01, "learning_rate": 1.0804114093436491e-05, "loss": 3.3494, "step": 2394112 }, { "epoch": 0.01, "learning_rate": 1.079572814592597e-05, "loss": 3.3707, "step": 2394624 }, { "epoch": 0.01, "learning_rate": 1.078735857721918e-05, "loss": 3.3504, "step": 2395136 }, { "epoch": 0.01, "learning_rate": 1.0778972629708662e-05, "loss": 3.3762, "step": 2395648 }, { "epoch": 0.01, "learning_rate": 1.077058668219814e-05, "loss": 3.3683, "step": 2396160 }, { "epoch": 0.01, "learning_rate": 1.076220073468762e-05, "loss": 3.3472, "step": 2396672 }, { "epoch": 0.01, "learning_rate": 1.07538147871771e-05, "loss": 3.3575, "step": 2397184 }, { "epoch": 0.01, "learning_rate": 1.0745428839666582e-05, "loss": 3.3645, "step": 2397696 }, { "epoch": 0.01, "learning_rate": 1.073704289215606e-05, "loss": 3.3436, "step": 2398208 }, { "epoch": 0.01, "learning_rate": 1.072865694464554e-05, "loss": 3.3494, "step": 2398720 }, { "epoch": 0.01, "learning_rate": 1.0720287375938752e-05, "loss": 3.3737, "step": 2399232 }, { "epoch": 0.01, "learning_rate": 1.071190142842823e-05, "loss": 3.3562, "step": 2399744 }, { "epoch": 0.01, "learning_rate": 1.070351548091771e-05, "loss": 3.3534, "step": 2400256 }, { "epoch": 0.01, "learning_rate": 1.0695129533407192e-05, "loss": 3.3451, "step": 2400768 }, { "epoch": 0.01, "learning_rate": 1.0686759964700403e-05, "loss": 3.3583, "step": 2401280 }, { "epoch": 0.01, "learning_rate": 1.0678374017189883e-05, "loss": 3.3487, "step": 2401792 }, { "epoch": 0.01, "learning_rate": 1.0669988069679363e-05, "loss": 3.3664, "step": 2402304 }, { "epoch": 0.01, "learning_rate": 1.0661602122168843e-05, "loss": 3.3529, "step": 2402816 }, { "epoch": 0.01, "learning_rate": 1.0653232553462054e-05, "loss": 3.3641, "step": 2403328 }, { "epoch": 0.01, "learning_rate": 1.0644846605951534e-05, "loss": 3.3635, "step": 2403840 }, { "epoch": 0.01, "learning_rate": 1.0636460658441014e-05, "loss": 3.3647, "step": 2404352 }, { "epoch": 0.01, "learning_rate": 1.0628074710930494e-05, "loss": 3.359, "step": 2404864 }, { "epoch": 0.01, "learning_rate": 1.0619705142223704e-05, "loss": 3.3575, "step": 2405376 }, { "epoch": 0.01, "learning_rate": 1.0611319194713184e-05, "loss": 3.3608, "step": 2405888 }, { "epoch": 0.01, "learning_rate": 1.0602933247202664e-05, "loss": 3.3635, "step": 2406400 }, { "epoch": 0.01, "learning_rate": 1.0594547299692144e-05, "loss": 3.3577, "step": 2406912 }, { "epoch": 0.01, "learning_rate": 1.0586161352181624e-05, "loss": 3.3581, "step": 2407424 }, { "epoch": 0.01, "learning_rate": 1.0577791783474837e-05, "loss": 3.3599, "step": 2407936 }, { "epoch": 0.01, "learning_rate": 1.0569405835964317e-05, "loss": 3.357, "step": 2408448 }, { "epoch": 0.01, "learning_rate": 1.0561019888453795e-05, "loss": 3.3411, "step": 2408960 }, { "epoch": 0.01, "learning_rate": 1.0552633940943275e-05, "loss": 3.3553, "step": 2409472 }, { "epoch": 0.01, "learning_rate": 1.0544247993432756e-05, "loss": 3.3571, "step": 2409984 }, { "epoch": 0.01, "learning_rate": 1.0535862045922235e-05, "loss": 3.3614, "step": 2410496 }, { "epoch": 0.01, "learning_rate": 1.0527492477215446e-05, "loss": 3.3584, "step": 2411008 }, { "epoch": 0.01, "learning_rate": 1.0519106529704927e-05, "loss": 3.3578, "step": 2411520 }, { "epoch": 0.02, "learning_rate": 1.0510720582194407e-05, "loss": 3.3505, "step": 2412032 }, { "epoch": 0.02, "learning_rate": 1.0502334634683885e-05, "loss": 3.347, "step": 2412544 }, { "epoch": 0.02, "learning_rate": 1.0493948687173365e-05, "loss": 3.3522, "step": 2413056 }, { "epoch": 0.02, "learning_rate": 1.0485579118466578e-05, "loss": 3.3636, "step": 2413568 }, { "epoch": 0.02, "learning_rate": 1.0477193170956058e-05, "loss": 3.3566, "step": 2414080 }, { "epoch": 0.02, "learning_rate": 1.0468807223445538e-05, "loss": 3.3639, "step": 2414592 }, { "epoch": 0.02, "learning_rate": 1.0460421275935018e-05, "loss": 3.3527, "step": 2415104 }, { "epoch": 0.02, "learning_rate": 1.0452035328424498e-05, "loss": 3.3553, "step": 2415616 }, { "epoch": 0.02, "learning_rate": 1.0443665759717708e-05, "loss": 3.3546, "step": 2416128 }, { "epoch": 0.02, "learning_rate": 1.0435279812207188e-05, "loss": 3.3658, "step": 2416640 }, { "epoch": 0.02, "learning_rate": 1.0426893864696668e-05, "loss": 3.3576, "step": 2417152 }, { "epoch": 0.02, "learning_rate": 1.0418507917186148e-05, "loss": 3.3703, "step": 2417664 }, { "epoch": 0.02, "learning_rate": 1.0410121969675628e-05, "loss": 3.352, "step": 2418176 }, { "epoch": 0.02, "learning_rate": 1.0401736022165108e-05, "loss": 3.3528, "step": 2418688 }, { "epoch": 0.02, "learning_rate": 1.0393350074654588e-05, "loss": 3.3689, "step": 2419200 }, { "epoch": 0.02, "learning_rate": 1.0384964127144068e-05, "loss": 3.3495, "step": 2419712 }, { "epoch": 0.02, "learning_rate": 1.037661093724101e-05, "loss": 3.3493, "step": 2420224 }, { "epoch": 0.02, "learning_rate": 1.0368224989730491e-05, "loss": 3.3596, "step": 2420736 }, { "epoch": 0.02, "learning_rate": 1.0359839042219971e-05, "loss": 3.3578, "step": 2421248 }, { "epoch": 0.02, "learning_rate": 1.035145309470945e-05, "loss": 3.35, "step": 2421760 }, { "epoch": 0.02, "learning_rate": 1.034306714719893e-05, "loss": 3.3574, "step": 2422272 }, { "epoch": 0.02, "learning_rate": 1.0334681199688411e-05, "loss": 3.3447, "step": 2422784 }, { "epoch": 0.02, "learning_rate": 1.032629525217789e-05, "loss": 3.357, "step": 2423296 }, { "epoch": 0.02, "learning_rate": 1.031790930466737e-05, "loss": 3.3548, "step": 2423808 }, { "epoch": 0.02, "learning_rate": 1.0309539735960582e-05, "loss": 3.3558, "step": 2424320 }, { "epoch": 0.02, "learning_rate": 1.0301153788450062e-05, "loss": 3.3636, "step": 2424832 }, { "epoch": 0.02, "learning_rate": 1.029276784093954e-05, "loss": 3.3741, "step": 2425344 }, { "epoch": 0.02, "learning_rate": 1.028438189342902e-05, "loss": 3.3607, "step": 2425856 }, { "epoch": 0.02, "learning_rate": 1.0276012324722233e-05, "loss": 3.3568, "step": 2426368 }, { "epoch": 0.02, "learning_rate": 1.0267626377211713e-05, "loss": 3.3534, "step": 2426880 }, { "epoch": 0.02, "learning_rate": 1.0259240429701192e-05, "loss": 3.3531, "step": 2427392 }, { "epoch": 0.02, "learning_rate": 1.0250870860994403e-05, "loss": 3.3554, "step": 2427904 }, { "epoch": 0.02, "learning_rate": 1.0242484913483883e-05, "loss": 3.3559, "step": 2428416 }, { "epoch": 0.02, "learning_rate": 1.0234098965973363e-05, "loss": 3.3526, "step": 2428928 }, { "epoch": 0.02, "learning_rate": 1.0225713018462843e-05, "loss": 3.3623, "step": 2429440 }, { "epoch": 0.02, "learning_rate": 1.0217343449756054e-05, "loss": 3.3538, "step": 2429952 }, { "epoch": 0.02, "learning_rate": 1.0208957502245536e-05, "loss": 3.3587, "step": 2430464 }, { "epoch": 0.02, "learning_rate": 1.0200571554735014e-05, "loss": 3.3537, "step": 2430976 }, { "epoch": 0.02, "learning_rate": 1.0192185607224494e-05, "loss": 3.3511, "step": 2431488 }, { "epoch": 0.02, "learning_rate": 1.0183799659713974e-05, "loss": 3.3495, "step": 2432000 }, { "epoch": 0.02, "learning_rate": 1.0175413712203454e-05, "loss": 3.363, "step": 2432512 }, { "epoch": 0.02, "learning_rate": 1.0167027764692934e-05, "loss": 3.3701, "step": 2433024 }, { "epoch": 0.02, "learning_rate": 1.0158641817182414e-05, "loss": 3.3639, "step": 2433536 }, { "epoch": 0.02, "learning_rate": 1.0150272248475626e-05, "loss": 3.3509, "step": 2434048 }, { "epoch": 0.02, "learning_rate": 1.0141886300965104e-05, "loss": 3.3531, "step": 2434560 }, { "epoch": 0.02, "learning_rate": 1.0133500353454584e-05, "loss": 3.3568, "step": 2435072 }, { "epoch": 0.02, "learning_rate": 1.0125114405944066e-05, "loss": 3.3604, "step": 2435584 }, { "epoch": 0.02, "learning_rate": 1.0116744837237277e-05, "loss": 3.3623, "step": 2436096 }, { "epoch": 0.02, "learning_rate": 1.0108358889726757e-05, "loss": 3.369, "step": 2436608 }, { "epoch": 0.02, "learning_rate": 1.0099972942216237e-05, "loss": 3.3553, "step": 2437120 }, { "epoch": 0.02, "learning_rate": 1.0091586994705717e-05, "loss": 3.3699, "step": 2437632 }, { "epoch": 0.02, "learning_rate": 1.0083217425998927e-05, "loss": 3.3534, "step": 2438144 }, { "epoch": 0.02, "learning_rate": 1.0074831478488407e-05, "loss": 3.3632, "step": 2438656 }, { "epoch": 0.02, "learning_rate": 1.0066445530977887e-05, "loss": 3.3571, "step": 2439168 }, { "epoch": 0.02, "learning_rate": 1.00580759622711e-05, "loss": 3.3509, "step": 2439680 }, { "epoch": 0.02, "learning_rate": 1.0049706393564309e-05, "loss": 3.3637, "step": 2440192 }, { "epoch": 0.02, "learning_rate": 1.0041320446053789e-05, "loss": 3.3471, "step": 2440704 }, { "epoch": 0.02, "learning_rate": 1.003293449854327e-05, "loss": 3.3571, "step": 2441216 }, { "epoch": 0.02, "learning_rate": 1.002454855103275e-05, "loss": 3.3533, "step": 2441728 }, { "epoch": 0.03, "eval_loss": 3.873310089111328, "eval_runtime": 451.8098, "eval_samples_per_second": 844.583, "eval_steps_per_second": 26.394, "step": 2442230 }, { "epoch": 1.0, "learning_rate": 1.0016162603522229e-05, "loss": 3.3529, "step": 2442240 }, { "epoch": 1.0, "learning_rate": 1.0007776656011709e-05, "loss": 3.3547, "step": 2442752 }, { "epoch": 1.0, "learning_rate": 9.99939070850119e-06, "loss": 3.3536, "step": 2443264 }, { "epoch": 1.0, "learning_rate": 9.9910211397944e-06, "loss": 3.3657, "step": 2443776 }, { "epoch": 1.0, "learning_rate": 9.982635192283881e-06, "loss": 3.3659, "step": 2444288 }, { "epoch": 1.0, "learning_rate": 9.974249244773361e-06, "loss": 3.3717, "step": 2444800 }, { "epoch": 1.0, "learning_rate": 9.96586329726284e-06, "loss": 3.3564, "step": 2445312 }, { "epoch": 1.0, "learning_rate": 9.95747734975232e-06, "loss": 3.3502, "step": 2445824 }, { "epoch": 1.0, "learning_rate": 9.949107781045532e-06, "loss": 3.3467, "step": 2446336 }, { "epoch": 1.0, "learning_rate": 9.940721833535012e-06, "loss": 3.3618, "step": 2446848 }, { "epoch": 1.0, "learning_rate": 9.932335886024492e-06, "loss": 3.3534, "step": 2447360 }, { "epoch": 1.0, "learning_rate": 9.923949938513972e-06, "loss": 3.3575, "step": 2447872 }, { "epoch": 1.0, "learning_rate": 9.915563991003452e-06, "loss": 3.3516, "step": 2448384 }, { "epoch": 1.0, "learning_rate": 9.90717804349293e-06, "loss": 3.3451, "step": 2448896 }, { "epoch": 1.0, "learning_rate": 9.898792095982411e-06, "loss": 3.3487, "step": 2449408 }, { "epoch": 1.0, "learning_rate": 9.890406148471891e-06, "loss": 3.346, "step": 2449920 }, { "epoch": 1.0, "learning_rate": 9.882036579765102e-06, "loss": 3.3411, "step": 2450432 }, { "epoch": 1.0, "learning_rate": 9.873650632254582e-06, "loss": 3.3553, "step": 2450944 }, { "epoch": 1.0, "learning_rate": 9.865264684744062e-06, "loss": 3.3512, "step": 2451456 }, { "epoch": 1.0, "learning_rate": 9.856878737233542e-06, "loss": 3.3524, "step": 2451968 }, { "epoch": 1.0, "learning_rate": 9.848509168526755e-06, "loss": 3.3718, "step": 2452480 }, { "epoch": 1.0, "learning_rate": 9.840123221016233e-06, "loss": 3.3522, "step": 2452992 }, { "epoch": 1.0, "learning_rate": 9.831753652309444e-06, "loss": 3.3602, "step": 2453504 }, { "epoch": 1.0, "learning_rate": 9.823367704798925e-06, "loss": 3.3501, "step": 2454016 }, { "epoch": 1.0, "learning_rate": 9.814981757288404e-06, "loss": 3.3638, "step": 2454528 }, { "epoch": 1.0, "learning_rate": 9.806595809777883e-06, "loss": 3.3503, "step": 2455040 }, { "epoch": 1.0, "learning_rate": 9.798209862267365e-06, "loss": 3.3553, "step": 2455552 }, { "epoch": 1.0, "learning_rate": 9.789823914756845e-06, "loss": 3.349, "step": 2456064 }, { "epoch": 1.0, "learning_rate": 9.781454346050054e-06, "loss": 3.3521, "step": 2456576 }, { "epoch": 1.0, "learning_rate": 9.773068398539536e-06, "loss": 3.3499, "step": 2457088 }, { "epoch": 1.01, "learning_rate": 9.764682451029016e-06, "loss": 3.3505, "step": 2457600 }, { "epoch": 1.01, "learning_rate": 9.756296503518494e-06, "loss": 3.3604, "step": 2458112 }, { "epoch": 1.01, "learning_rate": 9.747926934811707e-06, "loss": 3.354, "step": 2458624 }, { "epoch": 1.01, "learning_rate": 9.739540987301187e-06, "loss": 3.3591, "step": 2459136 }, { "epoch": 1.01, "learning_rate": 9.731155039790666e-06, "loss": 3.3595, "step": 2459648 }, { "epoch": 1.01, "learning_rate": 9.722769092280146e-06, "loss": 3.3498, "step": 2460160 }, { "epoch": 1.01, "learning_rate": 9.714383144769626e-06, "loss": 3.3644, "step": 2460672 }, { "epoch": 1.01, "learning_rate": 9.705997197259106e-06, "loss": 3.3421, "step": 2461184 }, { "epoch": 1.01, "learning_rate": 9.697627628552317e-06, "loss": 3.3537, "step": 2461696 }, { "epoch": 1.01, "learning_rate": 9.689241681041797e-06, "loss": 3.339, "step": 2462208 }, { "epoch": 1.01, "learning_rate": 9.680855733531277e-06, "loss": 3.3486, "step": 2462720 }, { "epoch": 1.01, "learning_rate": 9.672469786020757e-06, "loss": 3.3461, "step": 2463232 }, { "epoch": 1.01, "learning_rate": 9.664083838510237e-06, "loss": 3.3631, "step": 2463744 }, { "epoch": 1.01, "learning_rate": 9.655714269803448e-06, "loss": 3.3497, "step": 2464256 }, { "epoch": 1.01, "learning_rate": 9.647328322292928e-06, "loss": 3.3441, "step": 2464768 }, { "epoch": 1.01, "learning_rate": 9.63894237478241e-06, "loss": 3.3565, "step": 2465280 }, { "epoch": 1.01, "learning_rate": 9.630556427271888e-06, "loss": 3.3547, "step": 2465792 }, { "epoch": 1.01, "learning_rate": 9.622170479761368e-06, "loss": 3.3481, "step": 2466304 }, { "epoch": 1.01, "learning_rate": 9.613784532250848e-06, "loss": 3.3336, "step": 2466816 }, { "epoch": 1.01, "learning_rate": 9.605398584740327e-06, "loss": 3.3458, "step": 2467328 }, { "epoch": 1.01, "learning_rate": 9.597012637229807e-06, "loss": 3.359, "step": 2467840 }, { "epoch": 1.01, "learning_rate": 9.58864306852302e-06, "loss": 3.362, "step": 2468352 }, { "epoch": 1.01, "learning_rate": 9.5802571210125e-06, "loss": 3.3488, "step": 2468864 }, { "epoch": 1.01, "learning_rate": 9.571887552305709e-06, "loss": 3.3433, "step": 2469376 }, { "epoch": 1.01, "learning_rate": 9.56350160479519e-06, "loss": 3.3542, "step": 2469888 }, { "epoch": 1.01, "learning_rate": 9.55511565728467e-06, "loss": 3.3408, "step": 2470400 }, { "epoch": 1.01, "learning_rate": 9.546729709774149e-06, "loss": 3.3583, "step": 2470912 }, { "epoch": 1.01, "learning_rate": 9.538343762263629e-06, "loss": 3.3371, "step": 2471424 }, { "epoch": 1.01, "learning_rate": 9.529974193556841e-06, "loss": 3.3674, "step": 2471936 }, { "epoch": 1.01, "learning_rate": 9.521588246046321e-06, "loss": 3.3605, "step": 2472448 }, { "epoch": 1.01, "learning_rate": 9.513202298535801e-06, "loss": 3.3399, "step": 2472960 }, { "epoch": 1.01, "learning_rate": 9.504816351025281e-06, "loss": 3.347, "step": 2473472 }, { "epoch": 1.01, "learning_rate": 9.496430403514761e-06, "loss": 3.3579, "step": 2473984 }, { "epoch": 1.01, "learning_rate": 9.48804445600424e-06, "loss": 3.3349, "step": 2474496 }, { "epoch": 1.01, "learning_rate": 9.479658508493721e-06, "loss": 3.3376, "step": 2475008 }, { "epoch": 1.01, "learning_rate": 9.471288939786932e-06, "loss": 3.3637, "step": 2475520 }, { "epoch": 1.01, "learning_rate": 9.462902992276412e-06, "loss": 3.351, "step": 2476032 }, { "epoch": 1.01, "learning_rate": 9.454517044765892e-06, "loss": 3.3453, "step": 2476544 }, { "epoch": 1.01, "learning_rate": 9.446131097255372e-06, "loss": 3.3363, "step": 2477056 }, { "epoch": 1.01, "learning_rate": 9.437761528548582e-06, "loss": 3.3462, "step": 2477568 }, { "epoch": 1.01, "learning_rate": 9.429375581038064e-06, "loss": 3.3379, "step": 2478080 }, { "epoch": 1.01, "learning_rate": 9.420989633527542e-06, "loss": 3.3577, "step": 2478592 }, { "epoch": 1.01, "learning_rate": 9.412603686017022e-06, "loss": 3.3405, "step": 2479104 }, { "epoch": 1.01, "learning_rate": 9.404234117310235e-06, "loss": 3.3564, "step": 2479616 }, { "epoch": 1.01, "learning_rate": 9.395848169799713e-06, "loss": 3.3528, "step": 2480128 }, { "epoch": 1.01, "learning_rate": 9.387462222289193e-06, "loss": 3.3588, "step": 2480640 }, { "epoch": 1.01, "learning_rate": 9.379076274778675e-06, "loss": 3.345, "step": 2481152 }, { "epoch": 1.01, "learning_rate": 9.370706706071885e-06, "loss": 3.3496, "step": 2481664 }, { "epoch": 1.01, "learning_rate": 9.362320758561364e-06, "loss": 3.353, "step": 2482176 }, { "epoch": 1.01, "learning_rate": 9.353934811050845e-06, "loss": 3.3503, "step": 2482688 }, { "epoch": 1.01, "learning_rate": 9.345548863540325e-06, "loss": 3.3507, "step": 2483200 }, { "epoch": 1.01, "learning_rate": 9.337179294833536e-06, "loss": 3.3476, "step": 2483712 }, { "epoch": 1.01, "learning_rate": 9.328793347323016e-06, "loss": 3.3531, "step": 2484224 }, { "epoch": 1.01, "learning_rate": 9.320407399812496e-06, "loss": 3.3464, "step": 2484736 }, { "epoch": 1.01, "learning_rate": 9.312021452301976e-06, "loss": 3.3361, "step": 2485248 }, { "epoch": 1.01, "learning_rate": 9.303635504791456e-06, "loss": 3.3408, "step": 2485760 }, { "epoch": 1.01, "learning_rate": 9.295249557280936e-06, "loss": 3.3475, "step": 2486272 }, { "epoch": 1.01, "learning_rate": 9.286879988574147e-06, "loss": 3.3497, "step": 2486784 }, { "epoch": 1.01, "learning_rate": 9.278494041063627e-06, "loss": 3.3431, "step": 2487296 }, { "epoch": 1.01, "learning_rate": 9.270108093553107e-06, "loss": 3.3513, "step": 2487808 }, { "epoch": 1.02, "learning_rate": 9.261722146042587e-06, "loss": 3.342, "step": 2488320 }, { "epoch": 1.02, "learning_rate": 9.253352577335799e-06, "loss": 3.3358, "step": 2488832 }, { "epoch": 1.02, "learning_rate": 9.244966629825277e-06, "loss": 3.339, "step": 2489344 }, { "epoch": 1.02, "learning_rate": 9.236580682314757e-06, "loss": 3.3521, "step": 2489856 }, { "epoch": 1.02, "learning_rate": 9.228194734804237e-06, "loss": 3.3467, "step": 2490368 }, { "epoch": 1.02, "learning_rate": 9.219808787293717e-06, "loss": 3.3557, "step": 2490880 }, { "epoch": 1.02, "learning_rate": 9.211422839783197e-06, "loss": 3.3498, "step": 2491392 }, { "epoch": 1.02, "learning_rate": 9.203036892272677e-06, "loss": 3.3415, "step": 2491904 }, { "epoch": 1.02, "learning_rate": 9.194650944762159e-06, "loss": 3.3482, "step": 2492416 }, { "epoch": 1.02, "learning_rate": 9.186281376055368e-06, "loss": 3.3549, "step": 2492928 }, { "epoch": 1.02, "learning_rate": 9.177895428544848e-06, "loss": 3.3509, "step": 2493440 }, { "epoch": 1.02, "learning_rate": 9.16950948103433e-06, "loss": 3.3599, "step": 2493952 }, { "epoch": 1.02, "learning_rate": 9.161123533523808e-06, "loss": 3.3436, "step": 2494464 }, { "epoch": 1.02, "learning_rate": 9.15275396481702e-06, "loss": 3.3382, "step": 2494976 }, { "epoch": 1.02, "learning_rate": 9.1443680173065e-06, "loss": 3.3624, "step": 2495488 }, { "epoch": 1.02, "learning_rate": 9.13598206979598e-06, "loss": 3.3369, "step": 2496000 }, { "epoch": 1.02, "learning_rate": 9.127596122285458e-06, "loss": 3.3445, "step": 2496512 }, { "epoch": 1.02, "learning_rate": 9.11922655357867e-06, "loss": 3.3481, "step": 2497024 }, { "epoch": 1.02, "learning_rate": 9.11084060606815e-06, "loss": 3.3485, "step": 2497536 }, { "epoch": 1.02, "learning_rate": 9.10245465855763e-06, "loss": 3.3399, "step": 2498048 }, { "epoch": 1.02, "learning_rate": 9.09406871104711e-06, "loss": 3.3421, "step": 2498560 }, { "epoch": 1.02, "learning_rate": 9.085699142340321e-06, "loss": 3.3403, "step": 2499072 }, { "epoch": 1.02, "learning_rate": 9.077313194829801e-06, "loss": 3.3495, "step": 2499584 }, { "epoch": 1.02, "learning_rate": 9.068927247319281e-06, "loss": 3.3453, "step": 2500096 }, { "epoch": 1.02, "learning_rate": 9.060541299808761e-06, "loss": 3.3443, "step": 2500608 }, { "epoch": 1.02, "learning_rate": 9.052171731101972e-06, "loss": 3.3559, "step": 2501120 }, { "epoch": 1.02, "learning_rate": 9.043785783591454e-06, "loss": 3.3618, "step": 2501632 }, { "epoch": 1.02, "learning_rate": 9.035399836080932e-06, "loss": 3.3534, "step": 2502144 }, { "epoch": 1.02, "learning_rate": 9.027030267374145e-06, "loss": 3.3487, "step": 2502656 }, { "epoch": 1.02, "learning_rate": 9.018644319863624e-06, "loss": 3.344, "step": 2503168 }, { "epoch": 1.02, "learning_rate": 9.010258372353104e-06, "loss": 3.341, "step": 2503680 }, { "epoch": 1.02, "learning_rate": 9.001872424842583e-06, "loss": 3.3461, "step": 2504192 }, { "epoch": 1.02, "learning_rate": 8.993502856135795e-06, "loss": 3.3469, "step": 2504704 }, { "epoch": 1.02, "learning_rate": 8.985116908625275e-06, "loss": 3.3433, "step": 2505216 }, { "epoch": 1.02, "learning_rate": 8.976730961114755e-06, "loss": 3.3501, "step": 2505728 }, { "epoch": 1.02, "learning_rate": 8.968361392407966e-06, "loss": 3.3481, "step": 2506240 }, { "epoch": 1.02, "learning_rate": 8.959975444897446e-06, "loss": 3.3487, "step": 2506752 }, { "epoch": 1.02, "learning_rate": 8.951589497386926e-06, "loss": 3.3449, "step": 2507264 }, { "epoch": 1.02, "learning_rate": 8.943203549876406e-06, "loss": 3.3424, "step": 2507776 }, { "epoch": 1.02, "learning_rate": 8.934817602365886e-06, "loss": 3.3415, "step": 2508288 }, { "epoch": 1.02, "learning_rate": 8.926431654855366e-06, "loss": 3.357, "step": 2508800 }, { "epoch": 1.02, "learning_rate": 8.918045707344846e-06, "loss": 3.3588, "step": 2509312 }, { "epoch": 1.02, "learning_rate": 8.909659759834326e-06, "loss": 3.3563, "step": 2509824 }, { "epoch": 1.02, "learning_rate": 8.901290191127536e-06, "loss": 3.3405, "step": 2510336 }, { "epoch": 1.02, "learning_rate": 8.892904243617018e-06, "loss": 3.3464, "step": 2510848 }, { "epoch": 1.02, "learning_rate": 8.884518296106496e-06, "loss": 3.3463, "step": 2511360 }, { "epoch": 1.02, "learning_rate": 8.876132348595976e-06, "loss": 3.3527, "step": 2511872 }, { "epoch": 1.02, "learning_rate": 8.867762779889189e-06, "loss": 3.3455, "step": 2512384 }, { "epoch": 1.02, "learning_rate": 8.859376832378669e-06, "loss": 3.3619, "step": 2512896 }, { "epoch": 1.02, "learning_rate": 8.850990884868147e-06, "loss": 3.3432, "step": 2513408 }, { "epoch": 1.02, "learning_rate": 8.842604937357629e-06, "loss": 3.3645, "step": 2513920 }, { "epoch": 1.02, "learning_rate": 8.83423536865084e-06, "loss": 3.3438, "step": 2514432 }, { "epoch": 1.02, "learning_rate": 8.825849421140318e-06, "loss": 3.3559, "step": 2514944 }, { "epoch": 1.02, "learning_rate": 8.81747985243353e-06, "loss": 3.3434, "step": 2515456 }, { "epoch": 1.02, "learning_rate": 8.80909390492301e-06, "loss": 3.34, "step": 2515968 }, { "epoch": 1.02, "learning_rate": 8.80070795741249e-06, "loss": 3.3549, "step": 2516480 }, { "epoch": 1.02, "learning_rate": 8.79232200990197e-06, "loss": 3.3388, "step": 2516992 }, { "epoch": 1.02, "learning_rate": 8.78393606239145e-06, "loss": 3.3497, "step": 2517504 }, { "epoch": 1.02, "learning_rate": 8.77555011488093e-06, "loss": 3.3437, "step": 2518016 }, { "epoch": 1.02, "learning_rate": 8.76716416737041e-06, "loss": 3.3415, "step": 2518528 }, { "epoch": 1.03, "eval_loss": 3.8731186389923096, "eval_runtime": 525.4231, "eval_samples_per_second": 726.255, "eval_steps_per_second": 22.696, "step": 2518550 } ], "logging_steps": 512, "max_steps": 3052726, "num_train_epochs": 9223372036854775807, "save_steps": 10, "total_flos": 1.7193227683529964e+18, "trial_name": null, "trial_params": null }