diff --git "a/checkpoint-1907989/trainer_state.json" "b/checkpoint-1907989/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-1907989/trainer_state.json" @@ -0,0 +1,22581 @@ +{ + "best_metric": 3.8362677097320557, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/full/transformer/3/checkpoints/checkpoint-915829", + "epoch": 0.025000606015738065, + "eval_steps": 10, + "global_step": 1907989, + "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": 10.9262, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 6.8448, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 6.1978, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 5.9733, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 5.8185, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 5.6949, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 5.5933, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 5.5267, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 5.4739, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 5.3928, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 5.3519, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 5.3119, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989938500867749e-05, + "loss": 5.2679, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989099906116697e-05, + "loss": 5.2061, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988261311365645e-05, + "loss": 5.1775, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.987422716614593e-05, + "loss": 5.146, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986584121863541e-05, + "loss": 5.1069, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985745527112489e-05, + "loss": 5.0731, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984906932361437e-05, + "loss": 5.0519, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.0249, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 4.9946, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.9823927859886547e-05, + "loss": 4.966, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.9815541912376026e-05, + "loss": 4.9543, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.9807155964865506e-05, + "loss": 4.9242, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 4.9154, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790400448648195e-05, + "loss": 4.8875, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9782014501137675e-05, + "loss": 4.8765, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773628553627155e-05, + "loss": 4.8582, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 4.8245, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756873037409844e-05, + "loss": 4.8264, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748487089899324e-05, + "loss": 4.7969, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.9740101142388804e-05, + "loss": 4.7862, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731715194878284e-05, + "loss": 4.7754, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.97233456261715e-05, + "loss": 4.7678, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.971495967866098e-05, + "loss": 4.7425, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.970657373115046e-05, + "loss": 4.7337, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969818778363994e-05, + "loss": 4.7324, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968981821493315e-05, + "loss": 4.7159, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.968143226742263e-05, + "loss": 4.7065, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967304631991211e-05, + "loss": 4.6884, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966466037240159e-05, + "loss": 4.6721, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.96562908036948e-05, + "loss": 4.6661, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964790485618428e-05, + "loss": 4.6422, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963951890867376e-05, + "loss": 4.6601, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.963113296116324e-05, + "loss": 4.6347, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.9622763392456454e-05, + "loss": 4.635, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.9614377444945934e-05, + "loss": 4.6263, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.9605991497435414e-05, + "loss": 4.6213, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.9597605549924894e-05, + "loss": 4.6119, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.9589219602414374e-05, + "loss": 4.5893, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958085003370758e-05, + "loss": 4.5815, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957248046500079e-05, + "loss": 4.573, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956409451749027e-05, + "loss": 4.5807, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.955570856997975e-05, + "loss": 4.5585, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.954732262246923e-05, + "loss": 4.5691, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.953893667495871e-05, + "loss": 4.544, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.953055072744819e-05, + "loss": 4.5374, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.952216477993767e-05, + "loss": 4.5333, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951377883242715e-05, + "loss": 4.5289, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.950539288491663e-05, + "loss": 4.525, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949702331620985e-05, + "loss": 4.5084, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948863736869932e-05, + "loss": 4.5036, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.94802514211888e-05, + "loss": 4.5131, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947186547367828e-05, + "loss": 4.4943, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946347952616776e-05, + "loss": 4.4876, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945510995746097e-05, + "loss": 4.4876, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944672400995045e-05, + "loss": 4.4839, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.943833806243993e-05, + "loss": 4.466, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942995211492941e-05, + "loss": 4.4773, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.9421582546222625e-05, + "loss": 4.465, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.9413196598712105e-05, + "loss": 4.4566, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.9404810651201585e-05, + "loss": 4.4622, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396424703691065e-05, + "loss": 4.4488, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388055134984274e-05, + "loss": 4.4605, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379669187473754e-05, + "loss": 4.4615, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371283239963234e-05, + "loss": 4.4511, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.9362897292452714e-05, + "loss": 4.4344, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.9354511344942194e-05, + "loss": 4.4245, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.93461417762354e-05, + "loss": 4.4141, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.933775582872488e-05, + "loss": 4.4273, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.932936988121436e-05, + "loss": 4.4268, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.932098393370384e-05, + "loss": 4.4242, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.931259798619332e-05, + "loss": 4.3983, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.930421203868281e-05, + "loss": 4.396, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.929582609117229e-05, + "loss": 4.4027, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.92874565224655e-05, + "loss": 4.3904, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.927907057495498e-05, + "loss": 4.3958, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.927068462744446e-05, + "loss": 4.3909, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.926229867993394e-05, + "loss": 4.3938, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925392911122715e-05, + "loss": 4.3836, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.924554316371663e-05, + "loss": 4.3786, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923715721620611e-05, + "loss": 4.3672, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922877126869559e-05, + "loss": 4.3803, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.92204016999888e-05, + "loss": 4.3646, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921201575247828e-05, + "loss": 4.3498, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920362980496776e-05, + "loss": 4.3557, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919524385745724e-05, + "loss": 4.3683, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918685790994672e-05, + "loss": 4.3612, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.91784719624362e-05, + "loss": 4.3611, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.9170086014925676e-05, + "loss": 4.3394, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.9161700067415156e-05, + "loss": 4.3552, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.915333049870837e-05, + "loss": 4.3306, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.914494455119785e-05, + "loss": 4.3469, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.9136558603687325e-05, + "loss": 4.3517, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.912818903498054e-05, + "loss": 4.3334, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.911980308747002e-05, + "loss": 4.3284, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.91114171399595e-05, + "loss": 4.3044, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.910303119244898e-05, + "loss": 4.3163, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.909464524493846e-05, + "loss": 4.3181, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908625929742794e-05, + "loss": 4.3143, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907788972872115e-05, + "loss": 4.3215, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.906950378121063e-05, + "loss": 4.3028, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906111783370011e-05, + "loss": 4.3048, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.905273188618959e-05, + "loss": 4.3109, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.904434593867907e-05, + "loss": 4.3139, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903595999116855e-05, + "loss": 4.3002, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.902759042246176e-05, + "loss": 4.2986, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.901920447495124e-05, + "loss": 4.2944, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.901081852744072e-05, + "loss": 4.2939, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.90024325799302e-05, + "loss": 4.2981, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.8994063011223415e-05, + "loss": 4.285, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.8985677063712895e-05, + "loss": 4.2811, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.8977291116202375e-05, + "loss": 4.2789, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968905168691855e-05, + "loss": 4.2744, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.8960519221181335e-05, + "loss": 4.2793, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.8952133273670815e-05, + "loss": 4.279, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.8943747326160294e-05, + "loss": 4.2854, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.8935361378649774e-05, + "loss": 4.2605, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.8926991809942984e-05, + "loss": 4.2738, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.8918605862432463e-05, + "loss": 4.2752, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.8910219914921943e-05, + "loss": 4.2633, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.890185034621515e-05, + "loss": 4.2801, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.889346439870464e-05, + "loss": 4.2603, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888507845119412e-05, + "loss": 4.2722, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.88766925036836e-05, + "loss": 4.2644, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886830655617308e-05, + "loss": 4.2423, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885992060866256e-05, + "loss": 4.243, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.885153466115204e-05, + "loss": 4.2468, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884316509244525e-05, + "loss": 4.2545, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883477914493473e-05, + "loss": 4.2552, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882639319742421e-05, + "loss": 4.2537, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.881800724991369e-05, + "loss": 4.2437, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.880962130240316e-05, + "loss": 4.24, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.880123535489264e-05, + "loss": 4.2326, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.879284940738212e-05, + "loss": 4.2285, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.87844634598716e-05, + "loss": 4.2368, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877609389116482e-05, + "loss": 4.2482, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.87677079436543e-05, + "loss": 4.2388, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875932199614378e-05, + "loss": 4.221, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.875093604863326e-05, + "loss": 4.2233, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.19038724899292, + "eval_runtime": 610.1579, + "eval_samples_per_second": 625.397, + "eval_steps_per_second": 19.544, + "step": 76319 + }, + { + "epoch": 0.0, + "learning_rate": 4.8742566479926466e-05, + "loss": 4.2252, + "step": 76800 + }, + { + "epoch": 0.0, + "learning_rate": 4.8734180532415946e-05, + "loss": 4.2202, + "step": 77312 + }, + { + "epoch": 0.0, + "learning_rate": 4.8725794584905426e-05, + "loss": 4.2162, + "step": 77824 + }, + { + "epoch": 0.0, + "learning_rate": 4.8717408637394906e-05, + "loss": 4.2165, + "step": 78336 + }, + { + "epoch": 0.0, + "learning_rate": 4.8709022689884386e-05, + "loss": 4.2069, + "step": 78848 + }, + { + "epoch": 0.0, + "learning_rate": 4.8700636742373866e-05, + "loss": 4.1919, + "step": 79360 + }, + { + "epoch": 0.0, + "learning_rate": 4.8692250794863346e-05, + "loss": 4.1979, + "step": 79872 + }, + { + "epoch": 0.0, + "learning_rate": 4.8683864847352826e-05, + "loss": 4.2106, + "step": 80384 + }, + { + "epoch": 0.0, + "learning_rate": 4.8675478899842306e-05, + "loss": 4.1975, + "step": 80896 + }, + { + "epoch": 0.0, + "learning_rate": 4.866710933113552e-05, + "loss": 4.2019, + "step": 81408 + }, + { + "epoch": 0.0, + "learning_rate": 4.8658723383625e-05, + "loss": 4.2037, + "step": 81920 + }, + { + "epoch": 0.0, + "learning_rate": 4.865033743611448e-05, + "loss": 4.2043, + "step": 82432 + }, + { + "epoch": 0.0, + "learning_rate": 4.864195148860396e-05, + "loss": 4.1957, + "step": 82944 + }, + { + "epoch": 0.0, + "learning_rate": 4.863356554109344e-05, + "loss": 4.1966, + "step": 83456 + }, + { + "epoch": 0.0, + "learning_rate": 4.862517959358292e-05, + "loss": 4.189, + "step": 83968 + }, + { + "epoch": 0.0, + "learning_rate": 4.86167936460724e-05, + "loss": 4.175, + "step": 84480 + }, + { + "epoch": 0.0, + "learning_rate": 4.8608407698561874e-05, + "loss": 4.1831, + "step": 84992 + }, + { + "epoch": 0.0, + "learning_rate": 4.8600021751051354e-05, + "loss": 4.188, + "step": 85504 + }, + { + "epoch": 0.0, + "learning_rate": 4.8591635803540834e-05, + "loss": 4.1851, + "step": 86016 + }, + { + "epoch": 0.0, + "learning_rate": 4.8583249856030314e-05, + "loss": 4.1896, + "step": 86528 + }, + { + "epoch": 0.0, + "learning_rate": 4.8574863908519794e-05, + "loss": 4.1737, + "step": 87040 + }, + { + "epoch": 0.0, + "learning_rate": 4.856649433981301e-05, + "loss": 4.1826, + "step": 87552 + }, + { + "epoch": 0.0, + "learning_rate": 4.8558124771106226e-05, + "loss": 4.1728, + "step": 88064 + }, + { + "epoch": 0.0, + "learning_rate": 4.85497388235957e-05, + "loss": 4.182, + "step": 88576 + }, + { + "epoch": 0.0, + "learning_rate": 4.854135287608518e-05, + "loss": 4.1717, + "step": 89088 + }, + { + "epoch": 0.0, + "learning_rate": 4.853296692857466e-05, + "loss": 4.1693, + "step": 89600 + }, + { + "epoch": 0.0, + "learning_rate": 4.852458098106414e-05, + "loss": 4.1735, + "step": 90112 + }, + { + "epoch": 0.0, + "learning_rate": 4.851619503355362e-05, + "loss": 4.1559, + "step": 90624 + }, + { + "epoch": 0.0, + "learning_rate": 4.850782546484683e-05, + "loss": 4.1716, + "step": 91136 + }, + { + "epoch": 0.01, + "learning_rate": 4.849943951733631e-05, + "loss": 4.1541, + "step": 91648 + }, + { + "epoch": 0.01, + "learning_rate": 4.849105356982579e-05, + "loss": 4.1591, + "step": 92160 + }, + { + "epoch": 0.01, + "learning_rate": 4.848266762231527e-05, + "loss": 4.1601, + "step": 92672 + }, + { + "epoch": 0.01, + "learning_rate": 4.847428167480475e-05, + "loss": 4.1658, + "step": 93184 + }, + { + "epoch": 0.01, + "learning_rate": 4.846589572729423e-05, + "loss": 4.1537, + "step": 93696 + }, + { + "epoch": 0.01, + "learning_rate": 4.845750977978371e-05, + "loss": 4.1486, + "step": 94208 + }, + { + "epoch": 0.01, + "learning_rate": 4.8449140211076924e-05, + "loss": 4.1617, + "step": 94720 + }, + { + "epoch": 0.01, + "learning_rate": 4.8440754263566404e-05, + "loss": 4.1508, + "step": 95232 + }, + { + "epoch": 0.01, + "learning_rate": 4.8432368316055884e-05, + "loss": 4.1596, + "step": 95744 + }, + { + "epoch": 0.01, + "learning_rate": 4.8423982368545363e-05, + "loss": 4.1428, + "step": 96256 + }, + { + "epoch": 0.01, + "learning_rate": 4.8415596421034843e-05, + "loss": 4.134, + "step": 96768 + }, + { + "epoch": 0.01, + "learning_rate": 4.840722685232805e-05, + "loss": 4.1377, + "step": 97280 + }, + { + "epoch": 0.01, + "learning_rate": 4.839884090481753e-05, + "loss": 4.1325, + "step": 97792 + }, + { + "epoch": 0.01, + "learning_rate": 4.839045495730701e-05, + "loss": 4.1471, + "step": 98304 + }, + { + "epoch": 0.01, + "learning_rate": 4.838206900979649e-05, + "loss": 4.1337, + "step": 98816 + }, + { + "epoch": 0.01, + "learning_rate": 4.837368306228597e-05, + "loss": 4.1398, + "step": 99328 + }, + { + "epoch": 0.01, + "learning_rate": 4.836531349357918e-05, + "loss": 4.1356, + "step": 99840 + }, + { + "epoch": 0.01, + "learning_rate": 4.835692754606866e-05, + "loss": 4.1407, + "step": 100352 + }, + { + "epoch": 0.01, + "learning_rate": 4.834854159855814e-05, + "loss": 4.1386, + "step": 100864 + }, + { + "epoch": 0.01, + "learning_rate": 4.834015565104763e-05, + "loss": 4.1158, + "step": 101376 + }, + { + "epoch": 0.01, + "learning_rate": 4.833176970353711e-05, + "loss": 4.1228, + "step": 101888 + }, + { + "epoch": 0.01, + "learning_rate": 4.832340013483032e-05, + "loss": 4.1172, + "step": 102400 + }, + { + "epoch": 0.01, + "learning_rate": 4.83150141873198e-05, + "loss": 4.1337, + "step": 102912 + }, + { + "epoch": 0.01, + "learning_rate": 4.830662823980928e-05, + "loss": 4.1126, + "step": 103424 + }, + { + "epoch": 0.01, + "learning_rate": 4.829824229229876e-05, + "loss": 4.1327, + "step": 103936 + }, + { + "epoch": 0.01, + "learning_rate": 4.8289872723591966e-05, + "loss": 4.1079, + "step": 104448 + }, + { + "epoch": 0.01, + "learning_rate": 4.8281486776081446e-05, + "loss": 4.1093, + "step": 104960 + }, + { + "epoch": 0.01, + "learning_rate": 4.8273100828570926e-05, + "loss": 4.1178, + "step": 105472 + }, + { + "epoch": 0.01, + "learning_rate": 4.8264714881060406e-05, + "loss": 4.1109, + "step": 105984 + }, + { + "epoch": 0.01, + "learning_rate": 4.8256328933549886e-05, + "loss": 4.1103, + "step": 106496 + }, + { + "epoch": 0.01, + "learning_rate": 4.8247959364843095e-05, + "loss": 4.1066, + "step": 107008 + }, + { + "epoch": 0.01, + "learning_rate": 4.823957341733258e-05, + "loss": 4.1004, + "step": 107520 + }, + { + "epoch": 0.01, + "learning_rate": 4.823118746982206e-05, + "loss": 4.1145, + "step": 108032 + }, + { + "epoch": 0.01, + "learning_rate": 4.8222801522311535e-05, + "loss": 4.1023, + "step": 108544 + }, + { + "epoch": 0.01, + "learning_rate": 4.8214415574801015e-05, + "loss": 4.1001, + "step": 109056 + }, + { + "epoch": 0.01, + "learning_rate": 4.820604600609423e-05, + "loss": 4.1009, + "step": 109568 + }, + { + "epoch": 0.01, + "learning_rate": 4.819766005858371e-05, + "loss": 4.1048, + "step": 110080 + }, + { + "epoch": 0.01, + "learning_rate": 4.8189274111073184e-05, + "loss": 4.086, + "step": 110592 + }, + { + "epoch": 0.01, + "learning_rate": 4.8180888163562664e-05, + "loss": 4.1062, + "step": 111104 + }, + { + "epoch": 0.01, + "learning_rate": 4.8172502216052144e-05, + "loss": 4.0921, + "step": 111616 + }, + { + "epoch": 0.01, + "learning_rate": 4.816413264734535e-05, + "loss": 4.0949, + "step": 112128 + }, + { + "epoch": 0.01, + "learning_rate": 4.815574669983483e-05, + "loss": 4.1, + "step": 112640 + }, + { + "epoch": 0.01, + "learning_rate": 4.814736075232432e-05, + "loss": 4.0925, + "step": 113152 + }, + { + "epoch": 0.01, + "learning_rate": 4.81389748048138e-05, + "loss": 4.107, + "step": 113664 + }, + { + "epoch": 0.01, + "learning_rate": 4.813058885730328e-05, + "loss": 4.1115, + "step": 114176 + }, + { + "epoch": 0.01, + "learning_rate": 4.812221928859649e-05, + "loss": 4.1057, + "step": 114688 + }, + { + "epoch": 0.01, + "learning_rate": 4.811383334108597e-05, + "loss": 4.0896, + "step": 115200 + }, + { + "epoch": 0.01, + "learning_rate": 4.810544739357545e-05, + "loss": 4.0812, + "step": 115712 + }, + { + "epoch": 0.01, + "learning_rate": 4.809706144606493e-05, + "loss": 4.0788, + "step": 116224 + }, + { + "epoch": 0.01, + "learning_rate": 4.808869187735814e-05, + "loss": 4.0898, + "step": 116736 + }, + { + "epoch": 0.01, + "learning_rate": 4.808030592984762e-05, + "loss": 4.0992, + "step": 117248 + }, + { + "epoch": 0.01, + "learning_rate": 4.80719199823371e-05, + "loss": 4.0934, + "step": 117760 + }, + { + "epoch": 0.01, + "learning_rate": 4.806353403482658e-05, + "loss": 4.0767, + "step": 118272 + }, + { + "epoch": 0.01, + "learning_rate": 4.805514808731606e-05, + "loss": 4.0712, + "step": 118784 + }, + { + "epoch": 0.01, + "learning_rate": 4.804677851860927e-05, + "loss": 4.0837, + "step": 119296 + }, + { + "epoch": 0.01, + "learning_rate": 4.803839257109875e-05, + "loss": 4.0712, + "step": 119808 + }, + { + "epoch": 0.01, + "learning_rate": 4.803000662358823e-05, + "loss": 4.0787, + "step": 120320 + }, + { + "epoch": 0.01, + "learning_rate": 4.802162067607771e-05, + "loss": 4.0813, + "step": 120832 + }, + { + "epoch": 0.01, + "learning_rate": 4.801325110737092e-05, + "loss": 4.0864, + "step": 121344 + }, + { + "epoch": 0.01, + "learning_rate": 4.80048651598604e-05, + "loss": 4.0758, + "step": 121856 + }, + { + "epoch": 0.02, + "learning_rate": 4.799647921234988e-05, + "loss": 4.0739, + "step": 122368 + }, + { + "epoch": 0.02, + "learning_rate": 4.798809326483936e-05, + "loss": 4.0661, + "step": 122880 + }, + { + "epoch": 0.02, + "learning_rate": 4.797972369613257e-05, + "loss": 4.0764, + "step": 123392 + }, + { + "epoch": 0.02, + "learning_rate": 4.797133774862205e-05, + "loss": 4.0747, + "step": 123904 + }, + { + "epoch": 0.02, + "learning_rate": 4.796295180111153e-05, + "loss": 4.0553, + "step": 124416 + }, + { + "epoch": 0.02, + "learning_rate": 4.795456585360101e-05, + "loss": 4.0645, + "step": 124928 + }, + { + "epoch": 0.02, + "learning_rate": 4.794619628489423e-05, + "loss": 4.0748, + "step": 125440 + }, + { + "epoch": 0.02, + "learning_rate": 4.793781033738371e-05, + "loss": 4.0816, + "step": 125952 + }, + { + "epoch": 0.02, + "learning_rate": 4.792942438987319e-05, + "loss": 4.0709, + "step": 126464 + }, + { + "epoch": 0.02, + "learning_rate": 4.792103844236267e-05, + "loss": 4.0609, + "step": 126976 + }, + { + "epoch": 0.02, + "learning_rate": 4.7912668873655876e-05, + "loss": 4.0737, + "step": 127488 + }, + { + "epoch": 0.02, + "learning_rate": 4.7904282926145356e-05, + "loss": 4.0521, + "step": 128000 + }, + { + "epoch": 0.02, + "learning_rate": 4.7895896978634836e-05, + "loss": 4.0692, + "step": 128512 + }, + { + "epoch": 0.02, + "learning_rate": 4.7887511031124316e-05, + "loss": 4.0745, + "step": 129024 + }, + { + "epoch": 0.02, + "learning_rate": 4.7879141462417525e-05, + "loss": 4.0638, + "step": 129536 + }, + { + "epoch": 0.02, + "learning_rate": 4.7870755514907005e-05, + "loss": 4.0642, + "step": 130048 + }, + { + "epoch": 0.02, + "learning_rate": 4.7862369567396485e-05, + "loss": 4.0422, + "step": 130560 + }, + { + "epoch": 0.02, + "learning_rate": 4.7853983619885965e-05, + "loss": 4.0443, + "step": 131072 + }, + { + "epoch": 0.02, + "learning_rate": 4.7845597672375445e-05, + "loss": 4.0523, + "step": 131584 + }, + { + "epoch": 0.02, + "learning_rate": 4.7837211724864925e-05, + "loss": 4.0529, + "step": 132096 + }, + { + "epoch": 0.02, + "learning_rate": 4.782882577735441e-05, + "loss": 4.0603, + "step": 132608 + }, + { + "epoch": 0.02, + "learning_rate": 4.782043982984389e-05, + "loss": 4.0472, + "step": 133120 + }, + { + "epoch": 0.02, + "learning_rate": 4.78120702611371e-05, + "loss": 4.0449, + "step": 133632 + }, + { + "epoch": 0.02, + "learning_rate": 4.780368431362658e-05, + "loss": 4.0553, + "step": 134144 + }, + { + "epoch": 0.02, + "learning_rate": 4.779529836611606e-05, + "loss": 4.0625, + "step": 134656 + }, + { + "epoch": 0.02, + "learning_rate": 4.778691241860554e-05, + "loss": 4.0489, + "step": 135168 + }, + { + "epoch": 0.02, + "learning_rate": 4.777852647109502e-05, + "loss": 4.0545, + "step": 135680 + }, + { + "epoch": 0.02, + "learning_rate": 4.777015690238823e-05, + "loss": 4.0463, + "step": 136192 + }, + { + "epoch": 0.02, + "learning_rate": 4.776177095487771e-05, + "loss": 4.0466, + "step": 136704 + }, + { + "epoch": 0.02, + "learning_rate": 4.775338500736719e-05, + "loss": 4.053, + "step": 137216 + }, + { + "epoch": 0.02, + "learning_rate": 4.77450154386604e-05, + "loss": 4.0388, + "step": 137728 + }, + { + "epoch": 0.02, + "learning_rate": 4.773662949114988e-05, + "loss": 4.0401, + "step": 138240 + }, + { + "epoch": 0.02, + "learning_rate": 4.772824354363936e-05, + "loss": 4.0383, + "step": 138752 + }, + { + "epoch": 0.02, + "learning_rate": 4.7719857596128845e-05, + "loss": 4.0374, + "step": 139264 + }, + { + "epoch": 0.02, + "learning_rate": 4.771147164861832e-05, + "loss": 4.0412, + "step": 139776 + }, + { + "epoch": 0.02, + "learning_rate": 4.77030857011078e-05, + "loss": 4.045, + "step": 140288 + }, + { + "epoch": 0.02, + "learning_rate": 4.769469975359728e-05, + "loss": 4.0507, + "step": 140800 + }, + { + "epoch": 0.02, + "learning_rate": 4.768631380608676e-05, + "loss": 4.0309, + "step": 141312 + }, + { + "epoch": 0.02, + "learning_rate": 4.767794423737997e-05, + "loss": 4.038, + "step": 141824 + }, + { + "epoch": 0.02, + "learning_rate": 4.766955828986945e-05, + "loss": 4.0499, + "step": 142336 + }, + { + "epoch": 0.02, + "learning_rate": 4.766117234235893e-05, + "loss": 4.0353, + "step": 142848 + }, + { + "epoch": 0.02, + "learning_rate": 4.765278639484841e-05, + "loss": 4.0483, + "step": 143360 + }, + { + "epoch": 0.02, + "learning_rate": 4.7644416826141616e-05, + "loss": 4.0335, + "step": 143872 + }, + { + "epoch": 0.02, + "learning_rate": 4.7636030878631096e-05, + "loss": 4.05, + "step": 144384 + }, + { + "epoch": 0.02, + "learning_rate": 4.762764493112058e-05, + "loss": 4.0397, + "step": 144896 + }, + { + "epoch": 0.02, + "learning_rate": 4.761925898361006e-05, + "loss": 4.023, + "step": 145408 + }, + { + "epoch": 0.02, + "learning_rate": 4.761088941490327e-05, + "loss": 4.023, + "step": 145920 + }, + { + "epoch": 0.02, + "learning_rate": 4.760250346739275e-05, + "loss": 4.0282, + "step": 146432 + }, + { + "epoch": 0.02, + "learning_rate": 4.759411751988223e-05, + "loss": 4.0403, + "step": 146944 + }, + { + "epoch": 0.02, + "learning_rate": 4.758573157237171e-05, + "loss": 4.0351, + "step": 147456 + }, + { + "epoch": 0.02, + "learning_rate": 4.757736200366492e-05, + "loss": 4.038, + "step": 147968 + }, + { + "epoch": 0.02, + "learning_rate": 4.75689760561544e-05, + "loss": 4.0311, + "step": 148480 + }, + { + "epoch": 0.02, + "learning_rate": 4.756059010864388e-05, + "loss": 4.0242, + "step": 148992 + }, + { + "epoch": 0.02, + "learning_rate": 4.755220416113336e-05, + "loss": 4.0243, + "step": 149504 + }, + { + "epoch": 0.02, + "learning_rate": 4.754383459242657e-05, + "loss": 4.0186, + "step": 150016 + }, + { + "epoch": 0.02, + "learning_rate": 4.753544864491605e-05, + "loss": 4.0264, + "step": 150528 + }, + { + "epoch": 0.02, + "learning_rate": 4.7527062697405536e-05, + "loss": 4.042, + "step": 151040 + }, + { + "epoch": 0.02, + "learning_rate": 4.7518676749895016e-05, + "loss": 4.0257, + "step": 151552 + }, + { + "epoch": 0.02, + "learning_rate": 4.7510307181188225e-05, + "loss": 4.02, + "step": 152064 + }, + { + "epoch": 0.02, + "learning_rate": 4.7501921233677705e-05, + "loss": 4.0164, + "step": 152576 + }, + { + "epoch": 0.03, + "eval_loss": 4.021358489990234, + "eval_runtime": 573.4841, + "eval_samples_per_second": 665.391, + "eval_steps_per_second": 20.794, + "step": 152638 + }, + { + "epoch": 0.0, + "learning_rate": 4.7493551664970914e-05, + "loss": 4.0235, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.7485165717460394e-05, + "loss": 4.0212, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.7476779769949874e-05, + "loss": 4.013, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.7468393822439354e-05, + "loss": 4.0163, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.7460007874928834e-05, + "loss": 4.014, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.7451621927418314e-05, + "loss": 3.9954, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.7443235979907794e-05, + "loss": 4.0035, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.7434850032397274e-05, + "loss": 4.0169, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.7426464084886754e-05, + "loss": 3.9997, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.741809451617997e-05, + "loss": 4.0077, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.740970856866945e-05, + "loss": 4.0156, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.740132262115893e-05, + "loss": 4.013, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.739295305245214e-05, + "loss": 4.0024, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.738456710494162e-05, + "loss": 4.0089, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.73761811574311e-05, + "loss": 4.0003, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.736779520992058e-05, + "loss": 3.9933, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.735940926241006e-05, + "loss": 3.9974, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.735102331489954e-05, + "loss": 4.0036, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.734263736738902e-05, + "loss": 4.0044, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.73342514198785e-05, + "loss": 4.0066, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.732586547236797e-05, + "loss": 3.9932, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.731747952485746e-05, + "loss": 4.0049, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.730909357734694e-05, + "loss": 3.9955, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.7300724008640154e-05, + "loss": 4.0007, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.729233806112963e-05, + "loss": 3.995, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.728395211361911e-05, + "loss": 3.9944, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.727556616610859e-05, + "loss": 4.0008, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.72671965974018e-05, + "loss": 3.9825, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.7258810649891277e-05, + "loss": 3.9961, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.7250424702380757e-05, + "loss": 3.9847, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.7242038754870237e-05, + "loss": 3.9875, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.7233669186163446e-05, + "loss": 3.9901, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.7225283238652926e-05, + "loss": 3.9941, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.721689729114241e-05, + "loss": 3.9878, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.720851134363189e-05, + "loss": 3.9793, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.72001417749251e-05, + "loss": 3.9938, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.719175582741458e-05, + "loss": 3.9839, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.718336987990406e-05, + "loss": 3.9973, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.717498393239354e-05, + "loss": 3.9811, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.716661436368675e-05, + "loss": 3.9697, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.715822841617623e-05, + "loss": 3.9731, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.714984246866571e-05, + "loss": 3.9746, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.714145652115519e-05, + "loss": 3.9902, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.71330869524484e-05, + "loss": 3.9687, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.712470100493788e-05, + "loss": 3.984, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.7116315057427366e-05, + "loss": 3.9794, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.7107929109916846e-05, + "loss": 3.9778, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.7099559541210055e-05, + "loss": 3.9846, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.7091173593699535e-05, + "loss": 3.9593, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.7082787646189015e-05, + "loss": 3.9662, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.7074401698678495e-05, + "loss": 3.9602, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.7066032129971704e-05, + "loss": 3.9814, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.7057646182461184e-05, + "loss": 3.9606, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.7049260234950664e-05, + "loss": 3.9795, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.7040874287440144e-05, + "loss": 3.9573, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.7032488339929624e-05, + "loss": 3.9583, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.7024102392419104e-05, + "loss": 3.9637, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.7015716444908584e-05, + "loss": 3.9584, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.70073468762018e-05, + "loss": 3.9656, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.699896092869128e-05, + "loss": 3.9626, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.699057498118076e-05, + "loss": 3.9481, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.698218903367024e-05, + "loss": 3.9645, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.697381946496345e-05, + "loss": 3.9562, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.696543351745293e-05, + "loss": 3.9607, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.695704756994241e-05, + "loss": 3.9531, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694866162243189e-05, + "loss": 3.9598, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.69402920537251e-05, + "loss": 3.9405, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.693190610621458e-05, + "loss": 3.9621, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.692352015870406e-05, + "loss": 3.9489, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.691513421119354e-05, + "loss": 3.9571, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.690676464248675e-05, + "loss": 3.9555, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.689837869497623e-05, + "loss": 3.9515, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.688999274746571e-05, + "loss": 3.965, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.688160679995519e-05, + "loss": 3.9718, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.68732372312484e-05, + "loss": 3.9671, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.686485128373788e-05, + "loss": 3.9559, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.685646533622736e-05, + "loss": 3.9443, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.684807938871684e-05, + "loss": 3.9369, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.683970982001005e-05, + "loss": 3.9566, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.683132387249953e-05, + "loss": 3.9623, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.682293792498901e-05, + "loss": 3.9598, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.681455197747849e-05, + "loss": 3.9423, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.680618240877171e-05, + "loss": 3.9382, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.679779646126119e-05, + "loss": 3.9468, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.678941051375067e-05, + "loss": 3.9368, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.678102456624015e-05, + "loss": 3.9441, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.6772654997533356e-05, + "loss": 3.9503, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.6764269050022836e-05, + "loss": 3.9515, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.6755883102512316e-05, + "loss": 3.9443, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.6747513533805525e-05, + "loss": 3.9466, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.6739127586295005e-05, + "loss": 3.9364, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.6730741638784485e-05, + "loss": 3.9473, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.6722355691273965e-05, + "loss": 3.9421, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.6713969743763445e-05, + "loss": 3.9311, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.6705583796252925e-05, + "loss": 3.9362, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.669721422754614e-05, + "loss": 3.9461, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.668882828003562e-05, + "loss": 3.9543, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.66804423325251e-05, + "loss": 3.9418, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.667205638501458e-05, + "loss": 3.9397, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.6663670437504054e-05, + "loss": 3.9464, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.6655284489993534e-05, + "loss": 3.9267, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.6646898542483013e-05, + "loss": 3.9445, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.6638512594972493e-05, + "loss": 3.9484, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.663015940506944e-05, + "loss": 3.9366, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.662177345755892e-05, + "loss": 3.9453, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.66133875100484e-05, + "loss": 3.9215, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.660500156253788e-05, + "loss": 3.919, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.659661561502736e-05, + "loss": 3.9327, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.658822966751684e-05, + "loss": 3.9315, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.657984372000632e-05, + "loss": 3.9407, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.65714577724958e-05, + "loss": 3.9262, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.656308820378901e-05, + "loss": 3.9234, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.655470225627849e-05, + "loss": 3.9304, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.654631630876797e-05, + "loss": 3.943, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.653793036125745e-05, + "loss": 3.9323, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.6529560792550656e-05, + "loss": 3.9396, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.6521174845040136e-05, + "loss": 3.9249, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.6512788897529616e-05, + "loss": 3.925, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.6504402950019096e-05, + "loss": 3.9398, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.649604976011605e-05, + "loss": 3.9217, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.648766381260553e-05, + "loss": 3.9232, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.6479277865095e-05, + "loss": 3.9222, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.647089191758448e-05, + "loss": 3.9193, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.646250597007396e-05, + "loss": 3.9248, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.645412002256344e-05, + "loss": 3.9264, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.644573407505292e-05, + "loss": 3.9381, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.64373481275424e-05, + "loss": 3.9164, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.642897855883561e-05, + "loss": 3.9204, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.642059261132509e-05, + "loss": 3.9392, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.641220666381457e-05, + "loss": 3.9199, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.6403837095107786e-05, + "loss": 3.9367, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.6395451147597266e-05, + "loss": 3.9232, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.6387065200086746e-05, + "loss": 3.9351, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.6378679252576226e-05, + "loss": 3.9274, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.6370293305065705e-05, + "loss": 3.9129, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.6361907357555185e-05, + "loss": 3.9144, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.6353521410044665e-05, + "loss": 3.9147, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.6345135462534145e-05, + "loss": 3.9261, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.6336765893827354e-05, + "loss": 3.9289, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.6328379946316834e-05, + "loss": 3.9246, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.6319993998806314e-05, + "loss": 3.9204, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.6311608051295794e-05, + "loss": 3.9152, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.6303238482589003e-05, + "loss": 3.916, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.629485253507848e-05, + "loss": 3.909, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.628646658756797e-05, + "loss": 3.9198, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.627808064005745e-05, + "loss": 3.9292, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.626971107135066e-05, + "loss": 3.9176, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.626132512384014e-05, + "loss": 3.9138, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.625295555513335e-05, + "loss": 3.9108, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 3.946960926055908, + "eval_runtime": 561.2521, + "eval_samples_per_second": 679.892, + "eval_steps_per_second": 21.247, + "step": 228957 + }, + { + "epoch": 0.0, + "learning_rate": 4.624456960762283e-05, + "loss": 3.9148, + "step": 229376 + }, + { + "epoch": 0.0, + "learning_rate": 4.623618366011231e-05, + "loss": 3.9194, + "step": 229888 + }, + { + "epoch": 0.0, + "learning_rate": 4.622779771260179e-05, + "loss": 3.9081, + "step": 230400 + }, + { + "epoch": 0.0, + "learning_rate": 4.621941176509127e-05, + "loss": 3.9091, + "step": 230912 + }, + { + "epoch": 0.0, + "learning_rate": 4.621102581758075e-05, + "loss": 3.9116, + "step": 231424 + }, + { + "epoch": 0.0, + "learning_rate": 4.620263987007023e-05, + "loss": 3.8901, + "step": 231936 + }, + { + "epoch": 0.0, + "learning_rate": 4.619425392255971e-05, + "loss": 3.8972, + "step": 232448 + }, + { + "epoch": 0.0, + "learning_rate": 4.618586797504919e-05, + "loss": 3.9123, + "step": 232960 + }, + { + "epoch": 0.0, + "learning_rate": 4.6177498406342404e-05, + "loss": 3.9026, + "step": 233472 + }, + { + "epoch": 0.0, + "learning_rate": 4.6169112458831884e-05, + "loss": 3.9083, + "step": 233984 + }, + { + "epoch": 0.0, + "learning_rate": 4.6160726511321364e-05, + "loss": 3.9097, + "step": 234496 + }, + { + "epoch": 0.0, + "learning_rate": 4.615234056381084e-05, + "loss": 3.9069, + "step": 235008 + }, + { + "epoch": 0.0, + "learning_rate": 4.614397099510405e-05, + "loss": 3.9001, + "step": 235520 + }, + { + "epoch": 0.0, + "learning_rate": 4.613558504759353e-05, + "loss": 3.9101, + "step": 236032 + }, + { + "epoch": 0.0, + "learning_rate": 4.6127199100083006e-05, + "loss": 3.8955, + "step": 236544 + }, + { + "epoch": 0.0, + "learning_rate": 4.6118813152572486e-05, + "loss": 3.8933, + "step": 237056 + }, + { + "epoch": 0.0, + "learning_rate": 4.6110427205061966e-05, + "loss": 3.8944, + "step": 237568 + }, + { + "epoch": 0.0, + "learning_rate": 4.6102041257551446e-05, + "loss": 3.9004, + "step": 238080 + }, + { + "epoch": 0.0, + "learning_rate": 4.6093655310040926e-05, + "loss": 3.9046, + "step": 238592 + }, + { + "epoch": 0.0, + "learning_rate": 4.6085269362530406e-05, + "loss": 3.9084, + "step": 239104 + }, + { + "epoch": 0.0, + "learning_rate": 4.607689979382362e-05, + "loss": 3.8949, + "step": 239616 + }, + { + "epoch": 0.0, + "learning_rate": 4.60685138463131e-05, + "loss": 3.9076, + "step": 240128 + }, + { + "epoch": 0.0, + "learning_rate": 4.606012789880258e-05, + "loss": 3.8985, + "step": 240640 + }, + { + "epoch": 0.0, + "learning_rate": 4.605174195129206e-05, + "loss": 3.8976, + "step": 241152 + }, + { + "epoch": 0.0, + "learning_rate": 4.604335600378154e-05, + "loss": 3.8984, + "step": 241664 + }, + { + "epoch": 0.0, + "learning_rate": 4.603497005627102e-05, + "loss": 3.8927, + "step": 242176 + }, + { + "epoch": 0.0, + "learning_rate": 4.60265841087605e-05, + "loss": 3.9022, + "step": 242688 + }, + { + "epoch": 0.0, + "learning_rate": 4.601819816124998e-05, + "loss": 3.8863, + "step": 243200 + }, + { + "epoch": 0.0, + "learning_rate": 4.600982859254319e-05, + "loss": 3.9018, + "step": 243712 + }, + { + "epoch": 0.01, + "learning_rate": 4.600144264503267e-05, + "loss": 3.8868, + "step": 244224 + }, + { + "epoch": 0.01, + "learning_rate": 4.599305669752215e-05, + "loss": 3.8888, + "step": 244736 + }, + { + "epoch": 0.01, + "learning_rate": 4.598467075001163e-05, + "loss": 3.895, + "step": 245248 + }, + { + "epoch": 0.01, + "learning_rate": 4.5976317560108575e-05, + "loss": 3.9025, + "step": 245760 + }, + { + "epoch": 0.01, + "learning_rate": 4.5967931612598055e-05, + "loss": 3.8881, + "step": 246272 + }, + { + "epoch": 0.01, + "learning_rate": 4.5959545665087535e-05, + "loss": 3.8911, + "step": 246784 + }, + { + "epoch": 0.01, + "learning_rate": 4.5951159717577015e-05, + "loss": 3.8944, + "step": 247296 + }, + { + "epoch": 0.01, + "learning_rate": 4.5942773770066495e-05, + "loss": 3.8894, + "step": 247808 + }, + { + "epoch": 0.01, + "learning_rate": 4.5934404201359704e-05, + "loss": 3.9076, + "step": 248320 + }, + { + "epoch": 0.01, + "learning_rate": 4.5926018253849184e-05, + "loss": 3.8868, + "step": 248832 + }, + { + "epoch": 0.01, + "learning_rate": 4.5917632306338664e-05, + "loss": 3.8762, + "step": 249344 + }, + { + "epoch": 0.01, + "learning_rate": 4.5909246358828144e-05, + "loss": 3.8819, + "step": 249856 + }, + { + "epoch": 0.01, + "learning_rate": 4.590087679012135e-05, + "loss": 3.8762, + "step": 250368 + }, + { + "epoch": 0.01, + "learning_rate": 4.589249084261083e-05, + "loss": 3.8977, + "step": 250880 + }, + { + "epoch": 0.01, + "learning_rate": 4.588410489510031e-05, + "loss": 3.8819, + "step": 251392 + }, + { + "epoch": 0.01, + "learning_rate": 4.58757189475898e-05, + "loss": 3.8898, + "step": 251904 + }, + { + "epoch": 0.01, + "learning_rate": 4.586733300007928e-05, + "loss": 3.8842, + "step": 252416 + }, + { + "epoch": 0.01, + "learning_rate": 4.585894705256876e-05, + "loss": 3.888, + "step": 252928 + }, + { + "epoch": 0.01, + "learning_rate": 4.585056110505824e-05, + "loss": 3.8913, + "step": 253440 + }, + { + "epoch": 0.01, + "learning_rate": 4.584217515754772e-05, + "loss": 3.8705, + "step": 253952 + }, + { + "epoch": 0.01, + "learning_rate": 4.583380558884093e-05, + "loss": 3.8703, + "step": 254464 + }, + { + "epoch": 0.01, + "learning_rate": 4.582541964133041e-05, + "loss": 3.8748, + "step": 254976 + }, + { + "epoch": 0.01, + "learning_rate": 4.581705007262362e-05, + "loss": 3.8894, + "step": 255488 + }, + { + "epoch": 0.01, + "learning_rate": 4.58086641251131e-05, + "loss": 3.8717, + "step": 256000 + }, + { + "epoch": 0.01, + "learning_rate": 4.580027817760258e-05, + "loss": 3.8859, + "step": 256512 + }, + { + "epoch": 0.01, + "learning_rate": 4.579189223009206e-05, + "loss": 3.8689, + "step": 257024 + }, + { + "epoch": 0.01, + "learning_rate": 4.5783522661385267e-05, + "loss": 3.8667, + "step": 257536 + }, + { + "epoch": 0.01, + "learning_rate": 4.577513671387475e-05, + "loss": 3.8775, + "step": 258048 + }, + { + "epoch": 0.01, + "learning_rate": 4.576675076636423e-05, + "loss": 3.8652, + "step": 258560 + }, + { + "epoch": 0.01, + "learning_rate": 4.575836481885371e-05, + "loss": 3.8819, + "step": 259072 + }, + { + "epoch": 0.01, + "learning_rate": 4.574997887134319e-05, + "loss": 3.8763, + "step": 259584 + }, + { + "epoch": 0.01, + "learning_rate": 4.57416093026364e-05, + "loss": 3.8596, + "step": 260096 + }, + { + "epoch": 0.01, + "learning_rate": 4.573322335512588e-05, + "loss": 3.8747, + "step": 260608 + }, + { + "epoch": 0.01, + "learning_rate": 4.572483740761536e-05, + "loss": 3.8676, + "step": 261120 + }, + { + "epoch": 0.01, + "learning_rate": 4.571645146010484e-05, + "loss": 3.8756, + "step": 261632 + }, + { + "epoch": 0.01, + "learning_rate": 4.5708065512594315e-05, + "loss": 3.8635, + "step": 262144 + }, + { + "epoch": 0.01, + "learning_rate": 4.569969594388753e-05, + "loss": 3.8741, + "step": 262656 + }, + { + "epoch": 0.01, + "learning_rate": 4.569130999637701e-05, + "loss": 3.8572, + "step": 263168 + }, + { + "epoch": 0.01, + "learning_rate": 4.568292404886649e-05, + "loss": 3.872, + "step": 263680 + }, + { + "epoch": 0.01, + "learning_rate": 4.567453810135597e-05, + "loss": 3.8588, + "step": 264192 + }, + { + "epoch": 0.01, + "learning_rate": 4.566615215384545e-05, + "loss": 3.8674, + "step": 264704 + }, + { + "epoch": 0.01, + "learning_rate": 4.565776620633493e-05, + "loss": 3.8704, + "step": 265216 + }, + { + "epoch": 0.01, + "learning_rate": 4.564939663762814e-05, + "loss": 3.8704, + "step": 265728 + }, + { + "epoch": 0.01, + "learning_rate": 4.564101069011762e-05, + "loss": 3.8742, + "step": 266240 + }, + { + "epoch": 0.01, + "learning_rate": 4.56326247426071e-05, + "loss": 3.8881, + "step": 266752 + }, + { + "epoch": 0.01, + "learning_rate": 4.562423879509658e-05, + "loss": 3.8813, + "step": 267264 + }, + { + "epoch": 0.01, + "learning_rate": 4.561586922638979e-05, + "loss": 3.8695, + "step": 267776 + }, + { + "epoch": 0.01, + "learning_rate": 4.560748327887927e-05, + "loss": 3.8628, + "step": 268288 + }, + { + "epoch": 0.01, + "learning_rate": 4.559909733136875e-05, + "loss": 3.856, + "step": 268800 + }, + { + "epoch": 0.01, + "learning_rate": 4.559071138385823e-05, + "loss": 3.87, + "step": 269312 + }, + { + "epoch": 0.01, + "learning_rate": 4.5582341815151445e-05, + "loss": 3.8789, + "step": 269824 + }, + { + "epoch": 0.01, + "learning_rate": 4.5573955867640925e-05, + "loss": 3.8758, + "step": 270336 + }, + { + "epoch": 0.01, + "learning_rate": 4.5565569920130405e-05, + "loss": 3.8578, + "step": 270848 + }, + { + "epoch": 0.01, + "learning_rate": 4.5557183972619885e-05, + "loss": 3.8556, + "step": 271360 + }, + { + "epoch": 0.01, + "learning_rate": 4.5548798025109365e-05, + "loss": 3.8688, + "step": 271872 + }, + { + "epoch": 0.01, + "learning_rate": 4.5540428456402574e-05, + "loss": 3.8484, + "step": 272384 + }, + { + "epoch": 0.01, + "learning_rate": 4.5532042508892054e-05, + "loss": 3.8637, + "step": 272896 + }, + { + "epoch": 0.01, + "learning_rate": 4.5523656561381534e-05, + "loss": 3.8648, + "step": 273408 + }, + { + "epoch": 0.01, + "learning_rate": 4.5515270613871014e-05, + "loss": 3.868, + "step": 273920 + }, + { + "epoch": 0.01, + "learning_rate": 4.5506884666360494e-05, + "loss": 3.8651, + "step": 274432 + }, + { + "epoch": 0.02, + "learning_rate": 4.54985150976537e-05, + "loss": 3.8682, + "step": 274944 + }, + { + "epoch": 0.02, + "learning_rate": 4.549012915014318e-05, + "loss": 3.8534, + "step": 275456 + }, + { + "epoch": 0.02, + "learning_rate": 4.548174320263266e-05, + "loss": 3.8638, + "step": 275968 + }, + { + "epoch": 0.02, + "learning_rate": 4.547335725512214e-05, + "loss": 3.8587, + "step": 276480 + }, + { + "epoch": 0.02, + "learning_rate": 4.546498768641536e-05, + "loss": 3.8545, + "step": 276992 + }, + { + "epoch": 0.02, + "learning_rate": 4.545660173890484e-05, + "loss": 3.8546, + "step": 277504 + }, + { + "epoch": 0.02, + "learning_rate": 4.544821579139432e-05, + "loss": 3.8694, + "step": 278016 + }, + { + "epoch": 0.02, + "learning_rate": 4.54398298438838e-05, + "loss": 3.8694, + "step": 278528 + }, + { + "epoch": 0.02, + "learning_rate": 4.543144389637328e-05, + "loss": 3.8677, + "step": 279040 + }, + { + "epoch": 0.02, + "learning_rate": 4.542305794886276e-05, + "loss": 3.8574, + "step": 279552 + }, + { + "epoch": 0.02, + "learning_rate": 4.541467200135224e-05, + "loss": 3.8662, + "step": 280064 + }, + { + "epoch": 0.02, + "learning_rate": 4.540628605384172e-05, + "loss": 3.8499, + "step": 280576 + }, + { + "epoch": 0.02, + "learning_rate": 4.539791648513493e-05, + "loss": 3.8619, + "step": 281088 + }, + { + "epoch": 0.02, + "learning_rate": 4.5389546916428136e-05, + "loss": 3.8686, + "step": 281600 + }, + { + "epoch": 0.02, + "learning_rate": 4.5381160968917616e-05, + "loss": 3.8562, + "step": 282112 + }, + { + "epoch": 0.02, + "learning_rate": 4.5372775021407096e-05, + "loss": 3.869, + "step": 282624 + }, + { + "epoch": 0.02, + "learning_rate": 4.5364389073896576e-05, + "loss": 3.839, + "step": 283136 + }, + { + "epoch": 0.02, + "learning_rate": 4.535600312638606e-05, + "loss": 3.8419, + "step": 283648 + }, + { + "epoch": 0.02, + "learning_rate": 4.534763355767927e-05, + "loss": 3.854, + "step": 284160 + }, + { + "epoch": 0.02, + "learning_rate": 4.533924761016875e-05, + "loss": 3.8545, + "step": 284672 + }, + { + "epoch": 0.02, + "learning_rate": 4.533086166265823e-05, + "loss": 3.8618, + "step": 285184 + }, + { + "epoch": 0.02, + "learning_rate": 4.532247571514771e-05, + "loss": 3.8477, + "step": 285696 + }, + { + "epoch": 0.02, + "learning_rate": 4.531408976763719e-05, + "loss": 3.8448, + "step": 286208 + }, + { + "epoch": 0.02, + "learning_rate": 4.53057201989304e-05, + "loss": 3.853, + "step": 286720 + }, + { + "epoch": 0.02, + "learning_rate": 4.529733425141988e-05, + "loss": 3.8649, + "step": 287232 + }, + { + "epoch": 0.02, + "learning_rate": 4.528894830390936e-05, + "loss": 3.8569, + "step": 287744 + }, + { + "epoch": 0.02, + "learning_rate": 4.528056235639884e-05, + "loss": 3.8625, + "step": 288256 + }, + { + "epoch": 0.02, + "learning_rate": 4.527217640888832e-05, + "loss": 3.8478, + "step": 288768 + }, + { + "epoch": 0.02, + "learning_rate": 4.526380684018153e-05, + "loss": 3.8469, + "step": 289280 + }, + { + "epoch": 0.02, + "learning_rate": 4.5255420892671017e-05, + "loss": 3.8651, + "step": 289792 + }, + { + "epoch": 0.02, + "learning_rate": 4.5247034945160496e-05, + "loss": 3.8467, + "step": 290304 + }, + { + "epoch": 0.02, + "learning_rate": 4.5238648997649976e-05, + "loss": 3.8435, + "step": 290816 + }, + { + "epoch": 0.02, + "learning_rate": 4.5230279428943186e-05, + "loss": 3.8484, + "step": 291328 + }, + { + "epoch": 0.02, + "learning_rate": 4.5221893481432665e-05, + "loss": 3.8407, + "step": 291840 + }, + { + "epoch": 0.02, + "learning_rate": 4.5213507533922145e-05, + "loss": 3.8528, + "step": 292352 + }, + { + "epoch": 0.02, + "learning_rate": 4.5205121586411625e-05, + "loss": 3.8502, + "step": 292864 + }, + { + "epoch": 0.02, + "learning_rate": 4.51967356389011e-05, + "loss": 3.8643, + "step": 293376 + }, + { + "epoch": 0.02, + "learning_rate": 4.518834969139058e-05, + "loss": 3.8417, + "step": 293888 + }, + { + "epoch": 0.02, + "learning_rate": 4.5179980122683794e-05, + "loss": 3.8425, + "step": 294400 + }, + { + "epoch": 0.02, + "learning_rate": 4.5171594175173274e-05, + "loss": 3.8678, + "step": 294912 + }, + { + "epoch": 0.02, + "learning_rate": 4.5163208227662754e-05, + "loss": 3.8427, + "step": 295424 + }, + { + "epoch": 0.02, + "learning_rate": 4.5154822280152234e-05, + "loss": 3.8577, + "step": 295936 + }, + { + "epoch": 0.02, + "learning_rate": 4.5146436332641714e-05, + "loss": 3.8522, + "step": 296448 + }, + { + "epoch": 0.02, + "learning_rate": 4.5138050385131194e-05, + "loss": 3.8599, + "step": 296960 + }, + { + "epoch": 0.02, + "learning_rate": 4.51296808164244e-05, + "loss": 3.8515, + "step": 297472 + }, + { + "epoch": 0.02, + "learning_rate": 4.512129486891388e-05, + "loss": 3.8449, + "step": 297984 + }, + { + "epoch": 0.02, + "learning_rate": 4.511290892140336e-05, + "loss": 3.838, + "step": 298496 + }, + { + "epoch": 0.02, + "learning_rate": 4.510452297389284e-05, + "loss": 3.8403, + "step": 299008 + }, + { + "epoch": 0.02, + "learning_rate": 4.509615340518605e-05, + "loss": 3.8493, + "step": 299520 + }, + { + "epoch": 0.02, + "learning_rate": 4.508776745767553e-05, + "loss": 3.8571, + "step": 300032 + }, + { + "epoch": 0.02, + "learning_rate": 4.507938151016501e-05, + "loss": 3.8492, + "step": 300544 + }, + { + "epoch": 0.02, + "learning_rate": 4.507099556265449e-05, + "loss": 3.8521, + "step": 301056 + }, + { + "epoch": 0.02, + "learning_rate": 4.506262599394771e-05, + "loss": 3.8406, + "step": 301568 + }, + { + "epoch": 0.02, + "learning_rate": 4.505424004643719e-05, + "loss": 3.8453, + "step": 302080 + }, + { + "epoch": 0.02, + "learning_rate": 4.504585409892667e-05, + "loss": 3.8336, + "step": 302592 + }, + { + "epoch": 0.02, + "learning_rate": 4.503746815141615e-05, + "loss": 3.8493, + "step": 303104 + }, + { + "epoch": 0.02, + "learning_rate": 4.502908220390563e-05, + "loss": 3.8526, + "step": 303616 + }, + { + "epoch": 0.02, + "learning_rate": 4.502071263519884e-05, + "loss": 3.8532, + "step": 304128 + }, + { + "epoch": 0.02, + "learning_rate": 4.501232668768832e-05, + "loss": 3.8393, + "step": 304640 + }, + { + "epoch": 0.02, + "learning_rate": 4.50039407401778e-05, + "loss": 3.8387, + "step": 305152 + }, + { + "epoch": 0.03, + "eval_loss": 3.905977487564087, + "eval_runtime": 573.4819, + "eval_samples_per_second": 665.393, + "eval_steps_per_second": 20.794, + "step": 305276 + }, + { + "epoch": 0.0, + "learning_rate": 4.499555479266728e-05, + "loss": 3.847, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.498716884515676e-05, + "loss": 3.8433, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.497878289764624e-05, + "loss": 3.8395, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.497039695013572e-05, + "loss": 3.8392, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.4962011002625197e-05, + "loss": 3.839, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.4953625055114677e-05, + "loss": 3.8243, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.4945239107604156e-05, + "loss": 3.8286, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.4936853160093636e-05, + "loss": 3.8343, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.492848359138685e-05, + "loss": 3.8348, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.492009764387633e-05, + "loss": 3.8394, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.491171169636581e-05, + "loss": 3.8375, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.4903325748855285e-05, + "loss": 3.8331, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.48949561801485e-05, + "loss": 3.8319, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.488657023263798e-05, + "loss": 3.8403, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.487818428512746e-05, + "loss": 3.8297, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.4869798337616934e-05, + "loss": 3.8231, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.4861412390106414e-05, + "loss": 3.8245, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.4853026442595894e-05, + "loss": 3.8353, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.4844640495085374e-05, + "loss": 3.8323, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.4836254547574854e-05, + "loss": 3.8431, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.482788497886807e-05, + "loss": 3.8271, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.481949903135755e-05, + "loss": 3.8377, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.481111308384703e-05, + "loss": 3.8315, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.480272713633651e-05, + "loss": 3.8304, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.479435756762972e-05, + "loss": 3.8289, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.47859716201192e-05, + "loss": 3.8251, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.477758567260868e-05, + "loss": 3.8342, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.476919972509816e-05, + "loss": 3.8195, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.476083015639137e-05, + "loss": 3.8328, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.475244420888085e-05, + "loss": 3.8227, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.474405826137033e-05, + "loss": 3.8161, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.473567231385981e-05, + "loss": 3.83, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.4727302745153024e-05, + "loss": 3.8356, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.4718916797642504e-05, + "loss": 3.8257, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.4710530850131984e-05, + "loss": 3.8222, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.4702144902621464e-05, + "loss": 3.8279, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.469377533391467e-05, + "loss": 3.8257, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.468538938640415e-05, + "loss": 3.8402, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.467700343889363e-05, + "loss": 3.8216, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.466861749138311e-05, + "loss": 3.8096, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.466024792267632e-05, + "loss": 3.8167, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.46518619751658e-05, + "loss": 3.8132, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.464347602765528e-05, + "loss": 3.8292, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.463509008014476e-05, + "loss": 3.8173, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.462670413263425e-05, + "loss": 3.8277, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.461833456392746e-05, + "loss": 3.8221, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.460994861641694e-05, + "loss": 3.8203, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.460156266890642e-05, + "loss": 3.8297, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.45931767213959e-05, + "loss": 3.8084, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.4584807152689106e-05, + "loss": 3.8052, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.4576421205178586e-05, + "loss": 3.8157, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.4568035257668066e-05, + "loss": 3.8218, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.4559649310157546e-05, + "loss": 3.8068, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.4551279741450755e-05, + "loss": 3.8217, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.4542893793940235e-05, + "loss": 3.8063, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.4534507846429715e-05, + "loss": 3.8027, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.45261218989192e-05, + "loss": 3.814, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.451775233021241e-05, + "loss": 3.802, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.450936638270189e-05, + "loss": 3.8208, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.450098043519137e-05, + "loss": 3.8151, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.449259448768085e-05, + "loss": 3.7943, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.448422491897406e-05, + "loss": 3.8113, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.447583897146354e-05, + "loss": 3.8067, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.446745302395302e-05, + "loss": 3.8185, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.44590670764425e-05, + "loss": 3.8004, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.445069750773571e-05, + "loss": 3.8119, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.444231156022519e-05, + "loss": 3.7962, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.443392561271467e-05, + "loss": 3.809, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.4425539665204156e-05, + "loss": 3.7996, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.4417153717693636e-05, + "loss": 3.8029, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.4408767770183116e-05, + "loss": 3.8117, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.4400398201476325e-05, + "loss": 3.8048, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.4392012253965805e-05, + "loss": 3.8145, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.4383626306455285e-05, + "loss": 3.8245, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.4375240358944764e-05, + "loss": 3.8225, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.4366870790237974e-05, + "loss": 3.8094, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.4358484842727454e-05, + "loss": 3.8024, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.4350098895216933e-05, + "loss": 3.7957, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.4341712947706413e-05, + "loss": 3.8076, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.433334337899962e-05, + "loss": 3.8232, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.43249574314891e-05, + "loss": 3.8117, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.431657148397859e-05, + "loss": 3.7988, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.430818553646807e-05, + "loss": 3.7917, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.429981596776128e-05, + "loss": 3.8133, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.429143002025076e-05, + "loss": 3.7904, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.428304407274024e-05, + "loss": 3.8, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.427465812522971e-05, + "loss": 3.8016, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.426628855652293e-05, + "loss": 3.8067, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.425790260901241e-05, + "loss": 3.8081, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.424951666150189e-05, + "loss": 3.8105, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.424113071399136e-05, + "loss": 3.7965, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.4232761145284576e-05, + "loss": 3.8042, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.4224375197774056e-05, + "loss": 3.802, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.421598925026354e-05, + "loss": 3.7951, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.4207603302753016e-05, + "loss": 3.795, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.419925011284996e-05, + "loss": 3.8122, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.419086416533944e-05, + "loss": 3.8103, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.418247821782892e-05, + "loss": 3.811, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.41740922703184e-05, + "loss": 3.7999, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.416570632280788e-05, + "loss": 3.805, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.415732037529736e-05, + "loss": 3.7914, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.4148934427786834e-05, + "loss": 3.8078, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.4140548480276314e-05, + "loss": 3.8061, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.4132162532765794e-05, + "loss": 3.7993, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.412379296405901e-05, + "loss": 3.8131, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.411540701654849e-05, + "loss": 3.7846, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.410702106903797e-05, + "loss": 3.7861, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.409863512152745e-05, + "loss": 3.7937, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.409026555282066e-05, + "loss": 3.7955, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.408187960531014e-05, + "loss": 3.804, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.407349365779962e-05, + "loss": 3.7963, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.40651077102891e-05, + "loss": 3.7828, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.405673814158231e-05, + "loss": 3.7958, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.404835219407179e-05, + "loss": 3.808, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.403996624656127e-05, + "loss": 3.8007, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.403158029905075e-05, + "loss": 3.8075, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.4023210730343963e-05, + "loss": 3.7932, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.4014824782833443e-05, + "loss": 3.7899, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.4006438835322923e-05, + "loss": 3.8083, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.39980528878124e-05, + "loss": 3.7923, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.398968331910561e-05, + "loss": 3.7889, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.398129737159509e-05, + "loss": 3.7892, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.397291142408457e-05, + "loss": 3.7861, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.396452547657405e-05, + "loss": 3.7978, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.395615590786726e-05, + "loss": 3.7955, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.394776996035674e-05, + "loss": 3.8052, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.393938401284622e-05, + "loss": 3.7848, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.39309980653357e-05, + "loss": 3.7887, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.392262849662892e-05, + "loss": 3.8073, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.39142425491184e-05, + "loss": 3.791, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.390585660160788e-05, + "loss": 3.8004, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.389747065409736e-05, + "loss": 3.8009, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.3889101085390566e-05, + "loss": 3.8011, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.3880715137880046e-05, + "loss": 3.7997, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.3872329190369526e-05, + "loss": 3.786, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.3863943242859006e-05, + "loss": 3.7851, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.3855573674152215e-05, + "loss": 3.7895, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.3847187726641695e-05, + "loss": 3.7937, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.3838801779131175e-05, + "loss": 3.7989, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.3830415831620655e-05, + "loss": 3.7958, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.382204626291387e-05, + "loss": 3.798, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.381366031540335e-05, + "loss": 3.7895, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.380527436789283e-05, + "loss": 3.7906, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.379688842038231e-05, + "loss": 3.7778, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.378851885167552e-05, + "loss": 3.7967, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.3780132904165e-05, + "loss": 3.7984, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.377174695665448e-05, + "loss": 3.7979, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.376336100914396e-05, + "loss": 3.7826, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.375499144043717e-05, + "loss": 3.7867, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 3.881382703781128, + "eval_runtime": 571.5891, + "eval_samples_per_second": 667.597, + "eval_steps_per_second": 20.863, + "step": 381595 + }, + { + "epoch": 0.0, + "learning_rate": 4.374662187173038e-05, + "loss": 3.8034, + "step": 381952 + }, + { + "epoch": 0.0, + "learning_rate": 4.3738235924219865e-05, + "loss": 3.7859, + "step": 382464 + }, + { + "epoch": 0.0, + "learning_rate": 4.3729849976709345e-05, + "loss": 3.7868, + "step": 382976 + }, + { + "epoch": 0.0, + "learning_rate": 4.3721464029198824e-05, + "loss": 3.7839, + "step": 383488 + }, + { + "epoch": 0.0, + "learning_rate": 4.3713078081688304e-05, + "loss": 3.7856, + "step": 384000 + }, + { + "epoch": 0.0, + "learning_rate": 4.3704692134177784e-05, + "loss": 3.7733, + "step": 384512 + }, + { + "epoch": 0.0, + "learning_rate": 4.3696306186667264e-05, + "loss": 3.7772, + "step": 385024 + }, + { + "epoch": 0.0, + "learning_rate": 4.3687920239156744e-05, + "loss": 3.7763, + "step": 385536 + }, + { + "epoch": 0.0, + "learning_rate": 4.3679550670449953e-05, + "loss": 3.7843, + "step": 386048 + }, + { + "epoch": 0.0, + "learning_rate": 4.367118110174316e-05, + "loss": 3.7897, + "step": 386560 + }, + { + "epoch": 0.0, + "learning_rate": 4.366279515423264e-05, + "loss": 3.7821, + "step": 387072 + }, + { + "epoch": 0.0, + "learning_rate": 4.365440920672212e-05, + "loss": 3.7816, + "step": 387584 + }, + { + "epoch": 0.0, + "learning_rate": 4.36460232592116e-05, + "loss": 3.7853, + "step": 388096 + }, + { + "epoch": 0.0, + "learning_rate": 4.363763731170108e-05, + "loss": 3.787, + "step": 388608 + }, + { + "epoch": 0.0, + "learning_rate": 4.362925136419056e-05, + "loss": 3.7774, + "step": 389120 + }, + { + "epoch": 0.0, + "learning_rate": 4.362086541668005e-05, + "loss": 3.771, + "step": 389632 + }, + { + "epoch": 0.0, + "learning_rate": 4.361247946916953e-05, + "loss": 3.773, + "step": 390144 + }, + { + "epoch": 0.0, + "learning_rate": 4.360410990046274e-05, + "loss": 3.7812, + "step": 390656 + }, + { + "epoch": 0.0, + "learning_rate": 4.359572395295222e-05, + "loss": 3.7807, + "step": 391168 + }, + { + "epoch": 0.0, + "learning_rate": 4.35873380054417e-05, + "loss": 3.7918, + "step": 391680 + }, + { + "epoch": 0.0, + "learning_rate": 4.357895205793118e-05, + "loss": 3.7765, + "step": 392192 + }, + { + "epoch": 0.0, + "learning_rate": 4.357058248922439e-05, + "loss": 3.7856, + "step": 392704 + }, + { + "epoch": 0.0, + "learning_rate": 4.356219654171387e-05, + "loss": 3.783, + "step": 393216 + }, + { + "epoch": 0.0, + "learning_rate": 4.355381059420335e-05, + "loss": 3.7788, + "step": 393728 + }, + { + "epoch": 0.0, + "learning_rate": 4.354542464669283e-05, + "loss": 3.7771, + "step": 394240 + }, + { + "epoch": 0.0, + "learning_rate": 4.3537055077986036e-05, + "loss": 3.7762, + "step": 394752 + }, + { + "epoch": 0.0, + "learning_rate": 4.3528669130475516e-05, + "loss": 3.7844, + "step": 395264 + }, + { + "epoch": 0.0, + "learning_rate": 4.3520283182964996e-05, + "loss": 3.7666, + "step": 395776 + }, + { + "epoch": 0.0, + "learning_rate": 4.351189723545448e-05, + "loss": 3.7852, + "step": 396288 + }, + { + "epoch": 0.0, + "learning_rate": 4.350352766674769e-05, + "loss": 3.771, + "step": 396800 + }, + { + "epoch": 0.01, + "learning_rate": 4.349514171923717e-05, + "loss": 3.7642, + "step": 397312 + }, + { + "epoch": 0.01, + "learning_rate": 4.348675577172665e-05, + "loss": 3.7807, + "step": 397824 + }, + { + "epoch": 0.01, + "learning_rate": 4.347836982421613e-05, + "loss": 3.7819, + "step": 398336 + }, + { + "epoch": 0.01, + "learning_rate": 4.347000025550934e-05, + "loss": 3.7805, + "step": 398848 + }, + { + "epoch": 0.01, + "learning_rate": 4.346161430799882e-05, + "loss": 3.7737, + "step": 399360 + }, + { + "epoch": 0.01, + "learning_rate": 4.34532283604883e-05, + "loss": 3.7733, + "step": 399872 + }, + { + "epoch": 0.01, + "learning_rate": 4.344484241297778e-05, + "loss": 3.7733, + "step": 400384 + }, + { + "epoch": 0.01, + "learning_rate": 4.343647284427099e-05, + "loss": 3.7905, + "step": 400896 + }, + { + "epoch": 0.01, + "learning_rate": 4.342808689676047e-05, + "loss": 3.7733, + "step": 401408 + }, + { + "epoch": 0.01, + "learning_rate": 4.341970094924995e-05, + "loss": 3.7604, + "step": 401920 + }, + { + "epoch": 0.01, + "learning_rate": 4.3411315001739436e-05, + "loss": 3.7673, + "step": 402432 + }, + { + "epoch": 0.01, + "learning_rate": 4.3402945433032645e-05, + "loss": 3.7621, + "step": 402944 + }, + { + "epoch": 0.01, + "learning_rate": 4.3394559485522125e-05, + "loss": 3.7779, + "step": 403456 + }, + { + "epoch": 0.01, + "learning_rate": 4.3386173538011605e-05, + "loss": 3.7728, + "step": 403968 + }, + { + "epoch": 0.01, + "learning_rate": 4.3377787590501085e-05, + "loss": 3.7736, + "step": 404480 + }, + { + "epoch": 0.01, + "learning_rate": 4.3369418021794294e-05, + "loss": 3.7765, + "step": 404992 + }, + { + "epoch": 0.01, + "learning_rate": 4.3361032074283774e-05, + "loss": 3.7722, + "step": 405504 + }, + { + "epoch": 0.01, + "learning_rate": 4.3352646126773254e-05, + "loss": 3.7818, + "step": 406016 + }, + { + "epoch": 0.01, + "learning_rate": 4.3344260179262734e-05, + "loss": 3.7601, + "step": 406528 + }, + { + "epoch": 0.01, + "learning_rate": 4.333589061055594e-05, + "loss": 3.7541, + "step": 407040 + }, + { + "epoch": 0.01, + "learning_rate": 4.332750466304542e-05, + "loss": 3.7702, + "step": 407552 + }, + { + "epoch": 0.01, + "learning_rate": 4.33191187155349e-05, + "loss": 3.7656, + "step": 408064 + }, + { + "epoch": 0.01, + "learning_rate": 4.331073276802439e-05, + "loss": 3.762, + "step": 408576 + }, + { + "epoch": 0.01, + "learning_rate": 4.33023631993176e-05, + "loss": 3.7734, + "step": 409088 + }, + { + "epoch": 0.01, + "learning_rate": 4.329397725180708e-05, + "loss": 3.7563, + "step": 409600 + }, + { + "epoch": 0.01, + "learning_rate": 4.328559130429656e-05, + "loss": 3.757, + "step": 410112 + }, + { + "epoch": 0.01, + "learning_rate": 4.327720535678604e-05, + "loss": 3.7649, + "step": 410624 + }, + { + "epoch": 0.01, + "learning_rate": 4.326883578807925e-05, + "loss": 3.755, + "step": 411136 + }, + { + "epoch": 0.01, + "learning_rate": 4.326044984056873e-05, + "loss": 3.7709, + "step": 411648 + }, + { + "epoch": 0.01, + "learning_rate": 4.325206389305821e-05, + "loss": 3.7634, + "step": 412160 + }, + { + "epoch": 0.01, + "learning_rate": 4.324367794554768e-05, + "loss": 3.7553, + "step": 412672 + }, + { + "epoch": 0.01, + "learning_rate": 4.32353083768409e-05, + "loss": 3.7596, + "step": 413184 + }, + { + "epoch": 0.01, + "learning_rate": 4.322692242933038e-05, + "loss": 3.7542, + "step": 413696 + }, + { + "epoch": 0.01, + "learning_rate": 4.321853648181986e-05, + "loss": 3.7739, + "step": 414208 + }, + { + "epoch": 0.01, + "learning_rate": 4.321015053430934e-05, + "loss": 3.7559, + "step": 414720 + }, + { + "epoch": 0.01, + "learning_rate": 4.320178096560255e-05, + "loss": 3.7674, + "step": 415232 + }, + { + "epoch": 0.01, + "learning_rate": 4.319339501809203e-05, + "loss": 3.7481, + "step": 415744 + }, + { + "epoch": 0.01, + "learning_rate": 4.3185009070581506e-05, + "loss": 3.759, + "step": 416256 + }, + { + "epoch": 0.01, + "learning_rate": 4.3176623123070986e-05, + "loss": 3.7527, + "step": 416768 + }, + { + "epoch": 0.01, + "learning_rate": 4.31682535543642e-05, + "loss": 3.7543, + "step": 417280 + }, + { + "epoch": 0.01, + "learning_rate": 4.315986760685368e-05, + "loss": 3.7613, + "step": 417792 + }, + { + "epoch": 0.01, + "learning_rate": 4.3151481659343155e-05, + "loss": 3.7593, + "step": 418304 + }, + { + "epoch": 0.01, + "learning_rate": 4.3143095711832635e-05, + "loss": 3.7654, + "step": 418816 + }, + { + "epoch": 0.01, + "learning_rate": 4.313472614312585e-05, + "loss": 3.7764, + "step": 419328 + }, + { + "epoch": 0.01, + "learning_rate": 4.312634019561533e-05, + "loss": 3.775, + "step": 419840 + }, + { + "epoch": 0.01, + "learning_rate": 4.311795424810481e-05, + "loss": 3.7658, + "step": 420352 + }, + { + "epoch": 0.01, + "learning_rate": 4.310956830059429e-05, + "loss": 3.757, + "step": 420864 + }, + { + "epoch": 0.01, + "learning_rate": 4.3101198731887506e-05, + "loss": 3.7521, + "step": 421376 + }, + { + "epoch": 0.01, + "learning_rate": 4.309281278437698e-05, + "loss": 3.7585, + "step": 421888 + }, + { + "epoch": 0.01, + "learning_rate": 4.308442683686646e-05, + "loss": 3.7756, + "step": 422400 + }, + { + "epoch": 0.01, + "learning_rate": 4.307604088935594e-05, + "loss": 3.765, + "step": 422912 + }, + { + "epoch": 0.01, + "learning_rate": 4.3067671320649155e-05, + "loss": 3.7542, + "step": 423424 + }, + { + "epoch": 0.01, + "learning_rate": 4.305928537313863e-05, + "loss": 3.7435, + "step": 423936 + }, + { + "epoch": 0.01, + "learning_rate": 4.305089942562811e-05, + "loss": 3.7705, + "step": 424448 + }, + { + "epoch": 0.01, + "learning_rate": 4.304251347811759e-05, + "loss": 3.7387, + "step": 424960 + }, + { + "epoch": 0.01, + "learning_rate": 4.3034143909410804e-05, + "loss": 3.7571, + "step": 425472 + }, + { + "epoch": 0.01, + "learning_rate": 4.3025757961900284e-05, + "loss": 3.7569, + "step": 425984 + }, + { + "epoch": 0.01, + "learning_rate": 4.3017372014389764e-05, + "loss": 3.761, + "step": 426496 + }, + { + "epoch": 0.01, + "learning_rate": 4.3008986066879244e-05, + "loss": 3.7606, + "step": 427008 + }, + { + "epoch": 0.02, + "learning_rate": 4.300061649817245e-05, + "loss": 3.7668, + "step": 427520 + }, + { + "epoch": 0.02, + "learning_rate": 4.299223055066193e-05, + "loss": 3.7472, + "step": 428032 + }, + { + "epoch": 0.02, + "learning_rate": 4.298384460315141e-05, + "loss": 3.7564, + "step": 428544 + }, + { + "epoch": 0.02, + "learning_rate": 4.297545865564089e-05, + "loss": 3.7587, + "step": 429056 + }, + { + "epoch": 0.02, + "learning_rate": 4.29670890869341e-05, + "loss": 3.7495, + "step": 429568 + }, + { + "epoch": 0.02, + "learning_rate": 4.295870313942358e-05, + "loss": 3.7502, + "step": 430080 + }, + { + "epoch": 0.02, + "learning_rate": 4.29503335707168e-05, + "loss": 3.766, + "step": 430592 + }, + { + "epoch": 0.02, + "learning_rate": 4.294194762320628e-05, + "loss": 3.7622, + "step": 431104 + }, + { + "epoch": 0.02, + "learning_rate": 4.293356167569576e-05, + "loss": 3.7706, + "step": 431616 + }, + { + "epoch": 0.02, + "learning_rate": 4.292517572818524e-05, + "loss": 3.7538, + "step": 432128 + }, + { + "epoch": 0.02, + "learning_rate": 4.291678978067472e-05, + "loss": 3.7575, + "step": 432640 + }, + { + "epoch": 0.02, + "learning_rate": 4.29084038331642e-05, + "loss": 3.7447, + "step": 433152 + }, + { + "epoch": 0.02, + "learning_rate": 4.290001788565368e-05, + "loss": 3.7605, + "step": 433664 + }, + { + "epoch": 0.02, + "learning_rate": 4.289163193814316e-05, + "loss": 3.7633, + "step": 434176 + }, + { + "epoch": 0.02, + "learning_rate": 4.288326236943637e-05, + "loss": 3.7513, + "step": 434688 + }, + { + "epoch": 0.02, + "learning_rate": 4.287487642192585e-05, + "loss": 3.7657, + "step": 435200 + }, + { + "epoch": 0.02, + "learning_rate": 4.286649047441533e-05, + "loss": 3.7388, + "step": 435712 + }, + { + "epoch": 0.02, + "learning_rate": 4.285810452690481e-05, + "loss": 3.7447, + "step": 436224 + }, + { + "epoch": 0.02, + "learning_rate": 4.2849734958198016e-05, + "loss": 3.7443, + "step": 436736 + }, + { + "epoch": 0.02, + "learning_rate": 4.2841349010687496e-05, + "loss": 3.7521, + "step": 437248 + }, + { + "epoch": 0.02, + "learning_rate": 4.2832963063176976e-05, + "loss": 3.7602, + "step": 437760 + }, + { + "epoch": 0.02, + "learning_rate": 4.2824577115666456e-05, + "loss": 3.7554, + "step": 438272 + }, + { + "epoch": 0.02, + "learning_rate": 4.281620754695967e-05, + "loss": 3.7306, + "step": 438784 + }, + { + "epoch": 0.02, + "learning_rate": 4.280782159944915e-05, + "loss": 3.7568, + "step": 439296 + }, + { + "epoch": 0.02, + "learning_rate": 4.279943565193863e-05, + "loss": 3.7611, + "step": 439808 + }, + { + "epoch": 0.02, + "learning_rate": 4.279104970442811e-05, + "loss": 3.7597, + "step": 440320 + }, + { + "epoch": 0.02, + "learning_rate": 4.278268013572132e-05, + "loss": 3.7582, + "step": 440832 + }, + { + "epoch": 0.02, + "learning_rate": 4.27742941882108e-05, + "loss": 3.7497, + "step": 441344 + }, + { + "epoch": 0.02, + "learning_rate": 4.276590824070028e-05, + "loss": 3.7457, + "step": 441856 + }, + { + "epoch": 0.02, + "learning_rate": 4.275752229318976e-05, + "loss": 3.7659, + "step": 442368 + }, + { + "epoch": 0.02, + "learning_rate": 4.274915272448297e-05, + "loss": 3.7481, + "step": 442880 + }, + { + "epoch": 0.02, + "learning_rate": 4.274076677697245e-05, + "loss": 3.7476, + "step": 443392 + }, + { + "epoch": 0.02, + "learning_rate": 4.273238082946193e-05, + "loss": 3.7426, + "step": 443904 + }, + { + "epoch": 0.02, + "learning_rate": 4.272399488195141e-05, + "loss": 3.7462, + "step": 444416 + }, + { + "epoch": 0.02, + "learning_rate": 4.2715625313244625e-05, + "loss": 3.7547, + "step": 444928 + }, + { + "epoch": 0.02, + "learning_rate": 4.2707239365734105e-05, + "loss": 3.7526, + "step": 445440 + }, + { + "epoch": 0.02, + "learning_rate": 4.2698853418223585e-05, + "loss": 3.761, + "step": 445952 + }, + { + "epoch": 0.02, + "learning_rate": 4.2690467470713065e-05, + "loss": 3.7459, + "step": 446464 + }, + { + "epoch": 0.02, + "learning_rate": 4.2682097902006274e-05, + "loss": 3.7435, + "step": 446976 + }, + { + "epoch": 0.02, + "learning_rate": 4.2673711954495754e-05, + "loss": 3.7613, + "step": 447488 + }, + { + "epoch": 0.02, + "learning_rate": 4.2665326006985234e-05, + "loss": 3.7457, + "step": 448000 + }, + { + "epoch": 0.02, + "learning_rate": 4.2656940059474714e-05, + "loss": 3.7557, + "step": 448512 + }, + { + "epoch": 0.02, + "learning_rate": 4.264857049076792e-05, + "loss": 3.7595, + "step": 449024 + }, + { + "epoch": 0.02, + "learning_rate": 4.26401845432574e-05, + "loss": 3.7588, + "step": 449536 + }, + { + "epoch": 0.02, + "learning_rate": 4.263179859574688e-05, + "loss": 3.7558, + "step": 450048 + }, + { + "epoch": 0.02, + "learning_rate": 4.262341264823636e-05, + "loss": 3.7446, + "step": 450560 + }, + { + "epoch": 0.02, + "learning_rate": 4.261504307952958e-05, + "loss": 3.7372, + "step": 451072 + }, + { + "epoch": 0.02, + "learning_rate": 4.260665713201906e-05, + "loss": 3.7473, + "step": 451584 + }, + { + "epoch": 0.02, + "learning_rate": 4.259827118450854e-05, + "loss": 3.7511, + "step": 452096 + }, + { + "epoch": 0.02, + "learning_rate": 4.258988523699802e-05, + "loss": 3.7601, + "step": 452608 + }, + { + "epoch": 0.02, + "learning_rate": 4.258151566829123e-05, + "loss": 3.7517, + "step": 453120 + }, + { + "epoch": 0.02, + "learning_rate": 4.257312972078071e-05, + "loss": 3.7515, + "step": 453632 + }, + { + "epoch": 0.02, + "learning_rate": 4.256474377327019e-05, + "loss": 3.75, + "step": 454144 + }, + { + "epoch": 0.02, + "learning_rate": 4.255635782575967e-05, + "loss": 3.751, + "step": 454656 + }, + { + "epoch": 0.02, + "learning_rate": 4.254798825705288e-05, + "loss": 3.7387, + "step": 455168 + }, + { + "epoch": 0.02, + "learning_rate": 4.253960230954236e-05, + "loss": 3.7456, + "step": 455680 + }, + { + "epoch": 0.02, + "learning_rate": 4.253121636203184e-05, + "loss": 3.7587, + "step": 456192 + }, + { + "epoch": 0.02, + "learning_rate": 4.252283041452132e-05, + "loss": 3.7568, + "step": 456704 + }, + { + "epoch": 0.02, + "learning_rate": 4.251446084581453e-05, + "loss": 3.741, + "step": 457216 + }, + { + "epoch": 0.02, + "learning_rate": 4.250607489830401e-05, + "loss": 3.7413, + "step": 457728 + }, + { + "epoch": 0.03, + "eval_loss": 3.8656201362609863, + "eval_runtime": 575.9172, + "eval_samples_per_second": 662.58, + "eval_steps_per_second": 20.706, + "step": 457914 + }, + { + "epoch": 0.0, + "learning_rate": 4.249770532959722e-05, + "loss": 3.7627, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.24893193820867e-05, + "loss": 3.7451, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.248093343457618e-05, + "loss": 3.7414, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.247254748706566e-05, + "loss": 3.7452, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.246416153955514e-05, + "loss": 3.7387, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.245577559204462e-05, + "loss": 3.7331, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.24473896445341e-05, + "loss": 3.7332, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.243900369702358e-05, + "loss": 3.7367, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.243063412831679e-05, + "loss": 3.744, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.242224818080627e-05, + "loss": 3.7451, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.2413878612099486e-05, + "loss": 3.742, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.2405492664588966e-05, + "loss": 3.7348, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.2397106717078446e-05, + "loss": 3.7491, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.2388720769567926e-05, + "loss": 3.7428, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.2380351200861135e-05, + "loss": 3.7408, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.2371965253350615e-05, + "loss": 3.7267, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.2363579305840095e-05, + "loss": 3.7297, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.2355193358329575e-05, + "loss": 3.744, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.2346807410819055e-05, + "loss": 3.7381, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.233842146330853e-05, + "loss": 3.7505, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.233003551579801e-05, + "loss": 3.7341, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.232164956828749e-05, + "loss": 3.7466, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.2313279999580704e-05, + "loss": 3.741, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.230491043087392e-05, + "loss": 3.7371, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.22965244833634e-05, + "loss": 3.7358, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.228813853585288e-05, + "loss": 3.7349, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.227975258834236e-05, + "loss": 3.7427, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.227136664083183e-05, + "loss": 3.7295, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.226298069332131e-05, + "loss": 3.7434, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.225459474581079e-05, + "loss": 3.7341, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.224620879830027e-05, + "loss": 3.7217, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.223783922959348e-05, + "loss": 3.7395, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.222945328208296e-05, + "loss": 3.7409, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.222106733457244e-05, + "loss": 3.7443, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.221268138706193e-05, + "loss": 3.7306, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.220431181835514e-05, + "loss": 3.7363, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.219592587084462e-05, + "loss": 3.7323, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.21875399233341e-05, + "loss": 3.7464, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.217915397582358e-05, + "loss": 3.7361, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.2170784407116787e-05, + "loss": 3.7209, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.2162398459606267e-05, + "loss": 3.7262, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.2154012512095746e-05, + "loss": 3.7204, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.2145626564585226e-05, + "loss": 3.7414, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.2137256995878436e-05, + "loss": 3.7319, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.2128871048367915e-05, + "loss": 3.7329, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.2120485100857395e-05, + "loss": 3.7392, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.211209915334688e-05, + "loss": 3.7291, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.210372958464009e-05, + "loss": 3.7416, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.209534363712957e-05, + "loss": 3.7214, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.208695768961905e-05, + "loss": 3.7159, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.207858812091226e-05, + "loss": 3.729, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.207020217340174e-05, + "loss": 3.7234, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.206181622589122e-05, + "loss": 3.7273, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.20534302783807e-05, + "loss": 3.7303, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.204506070967391e-05, + "loss": 3.7229, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.203667476216339e-05, + "loss": 3.718, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.202828881465287e-05, + "loss": 3.7232, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.201990286714235e-05, + "loss": 3.7201, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.2011533298435565e-05, + "loss": 3.7302, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.2003147350925045e-05, + "loss": 3.7247, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.1994761403414525e-05, + "loss": 3.7147, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.1986391834707734e-05, + "loss": 3.722, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.1978005887197214e-05, + "loss": 3.7098, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.1969619939686694e-05, + "loss": 3.7386, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.1961233992176174e-05, + "loss": 3.7192, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.1952848044665654e-05, + "loss": 3.7254, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.1944462097155134e-05, + "loss": 3.7144, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.1936076149644614e-05, + "loss": 3.7136, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.1927690202134094e-05, + "loss": 3.7175, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.19193206334273e-05, + "loss": 3.7162, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.191093468591679e-05, + "loss": 3.7251, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.190254873840627e-05, + "loss": 3.7203, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.189416279089575e-05, + "loss": 3.7282, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.188579322218896e-05, + "loss": 3.7372, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.187740727467844e-05, + "loss": 3.7332, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.186902132716792e-05, + "loss": 3.7309, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.18606353796574e-05, + "loss": 3.7191, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.185226581095061e-05, + "loss": 3.7137, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.184387986344009e-05, + "loss": 3.7209, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.1835510294733297e-05, + "loss": 3.7353, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.1827124347222776e-05, + "loss": 3.727, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.1818738399712256e-05, + "loss": 3.7168, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.181035245220174e-05, + "loss": 3.7037, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.180196650469122e-05, + "loss": 3.7347, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.17935805571807e-05, + "loss": 3.6986, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.178519460967018e-05, + "loss": 3.7181, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.177682504096339e-05, + "loss": 3.7224, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.176843909345287e-05, + "loss": 3.721, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.176005314594235e-05, + "loss": 3.7277, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.175166719843183e-05, + "loss": 3.7311, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.174329762972504e-05, + "loss": 3.7067, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.173491168221452e-05, + "loss": 3.7214, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.1726525734704e-05, + "loss": 3.7223, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.171813978719348e-05, + "loss": 3.7136, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.170977021848669e-05, + "loss": 3.7107, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.1701400649779906e-05, + "loss": 3.7301, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.1693014702269386e-05, + "loss": 3.7258, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.1684628754758866e-05, + "loss": 3.7361, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.1676242807248346e-05, + "loss": 3.7139, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.1667856859737826e-05, + "loss": 3.7231, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.1659470912227306e-05, + "loss": 3.7084, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.1651084964716786e-05, + "loss": 3.7231, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.164269901720626e-05, + "loss": 3.7265, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.1634329448499475e-05, + "loss": 3.7221, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.1625943500988955e-05, + "loss": 3.7266, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.1617557553478435e-05, + "loss": 3.7045, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.1609171605967915e-05, + "loss": 3.7043, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.160081841606486e-05, + "loss": 3.7048, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.159243246855434e-05, + "loss": 3.7151, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.158404652104382e-05, + "loss": 3.7233, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.15756605735333e-05, + "loss": 3.7228, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.156727462602278e-05, + "loss": 3.6953, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.155888867851226e-05, + "loss": 3.7186, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.155050273100173e-05, + "loss": 3.7249, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.154211678349121e-05, + "loss": 3.7234, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.153374721478443e-05, + "loss": 3.7213, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.152536126727391e-05, + "loss": 3.7136, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.151697531976338e-05, + "loss": 3.7129, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.150858937225287e-05, + "loss": 3.7248, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.1500219803546084e-05, + "loss": 3.7154, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.149183385603556e-05, + "loss": 3.711, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.148344790852504e-05, + "loss": 3.705, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.147506196101452e-05, + "loss": 3.708, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.146669239230773e-05, + "loss": 3.7181, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.1458306444797206e-05, + "loss": 3.7164, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.1449920497286686e-05, + "loss": 3.7226, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.1441534549776166e-05, + "loss": 3.7111, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.143316498106938e-05, + "loss": 3.707, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.1424779033558855e-05, + "loss": 3.7268, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.1416393086048335e-05, + "loss": 3.7067, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.140800713853782e-05, + "loss": 3.7212, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.139963756983103e-05, + "loss": 3.7271, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.139125162232051e-05, + "loss": 3.7193, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.138286567480999e-05, + "loss": 3.7203, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.137449610610321e-05, + "loss": 3.7142, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.136611015859268e-05, + "loss": 3.7005, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.135772421108216e-05, + "loss": 3.7094, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.134933826357164e-05, + "loss": 3.7126, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.134095231606112e-05, + "loss": 3.7254, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.13325663685506e-05, + "loss": 3.7126, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.132418042104008e-05, + "loss": 3.7205, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.131581085233329e-05, + "loss": 3.712, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.1307424904822776e-05, + "loss": 3.7162, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.1299038957312256e-05, + "loss": 3.7015, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.1290653009801736e-05, + "loss": 3.7106, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.1282283441094945e-05, + "loss": 3.7248, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.1273897493584425e-05, + "loss": 3.722, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.1265511546073905e-05, + "loss": 3.7041, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.1257125598563384e-05, + "loss": 3.7107, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 3.855581283569336, + "eval_runtime": 571.6992, + "eval_samples_per_second": 667.468, + "eval_steps_per_second": 20.859, + "step": 534233 + }, + { + "epoch": 0.0, + "learning_rate": 4.1248756029856594e-05, + "loss": 3.7299, + "step": 534528 + }, + { + "epoch": 0.0, + "learning_rate": 4.1240370082346074e-05, + "loss": 3.7082, + "step": 535040 + }, + { + "epoch": 0.0, + "learning_rate": 4.1231984134835553e-05, + "loss": 3.7068, + "step": 535552 + }, + { + "epoch": 0.0, + "learning_rate": 4.1223598187325033e-05, + "loss": 3.7139, + "step": 536064 + }, + { + "epoch": 0.0, + "learning_rate": 4.1215212239814513e-05, + "loss": 3.6996, + "step": 536576 + }, + { + "epoch": 0.0, + "learning_rate": 4.120682629230399e-05, + "loss": 3.7022, + "step": 537088 + }, + { + "epoch": 0.0, + "learning_rate": 4.119844034479347e-05, + "loss": 3.695, + "step": 537600 + }, + { + "epoch": 0.0, + "learning_rate": 4.119005439728296e-05, + "loss": 3.7054, + "step": 538112 + }, + { + "epoch": 0.0, + "learning_rate": 4.118168482857617e-05, + "loss": 3.7056, + "step": 538624 + }, + { + "epoch": 0.0, + "learning_rate": 4.117329888106565e-05, + "loss": 3.7119, + "step": 539136 + }, + { + "epoch": 0.0, + "learning_rate": 4.116492931235886e-05, + "loss": 3.7072, + "step": 539648 + }, + { + "epoch": 0.0, + "learning_rate": 4.115654336484834e-05, + "loss": 3.7021, + "step": 540160 + }, + { + "epoch": 0.0, + "learning_rate": 4.114815741733782e-05, + "loss": 3.7143, + "step": 540672 + }, + { + "epoch": 0.0, + "learning_rate": 4.11397714698273e-05, + "loss": 3.7049, + "step": 541184 + }, + { + "epoch": 0.0, + "learning_rate": 4.113138552231678e-05, + "loss": 3.7114, + "step": 541696 + }, + { + "epoch": 0.0, + "learning_rate": 4.112299957480626e-05, + "loss": 3.6888, + "step": 542208 + }, + { + "epoch": 0.0, + "learning_rate": 4.111461362729574e-05, + "loss": 3.6973, + "step": 542720 + }, + { + "epoch": 0.0, + "learning_rate": 4.110624405858895e-05, + "loss": 3.7072, + "step": 543232 + }, + { + "epoch": 0.0, + "learning_rate": 4.109785811107843e-05, + "loss": 3.7016, + "step": 543744 + }, + { + "epoch": 0.0, + "learning_rate": 4.108947216356791e-05, + "loss": 3.7179, + "step": 544256 + }, + { + "epoch": 0.0, + "learning_rate": 4.1081086216057394e-05, + "loss": 3.703, + "step": 544768 + }, + { + "epoch": 0.0, + "learning_rate": 4.10727166473506e-05, + "loss": 3.7086, + "step": 545280 + }, + { + "epoch": 0.0, + "learning_rate": 4.106433069984008e-05, + "loss": 3.707, + "step": 545792 + }, + { + "epoch": 0.0, + "learning_rate": 4.105596113113329e-05, + "loss": 3.6998, + "step": 546304 + }, + { + "epoch": 0.0, + "learning_rate": 4.104757518362277e-05, + "loss": 3.7058, + "step": 546816 + }, + { + "epoch": 0.0, + "learning_rate": 4.103918923611225e-05, + "loss": 3.6975, + "step": 547328 + }, + { + "epoch": 0.0, + "learning_rate": 4.103080328860173e-05, + "loss": 3.7112, + "step": 547840 + }, + { + "epoch": 0.0, + "learning_rate": 4.102241734109121e-05, + "loss": 3.6992, + "step": 548352 + }, + { + "epoch": 0.0, + "learning_rate": 4.1014031393580685e-05, + "loss": 3.7066, + "step": 548864 + }, + { + "epoch": 0.0, + "learning_rate": 4.1005645446070165e-05, + "loss": 3.6982, + "step": 549376 + }, + { + "epoch": 0.01, + "learning_rate": 4.0997259498559645e-05, + "loss": 3.6905, + "step": 549888 + }, + { + "epoch": 0.01, + "learning_rate": 4.098888992985286e-05, + "loss": 3.7056, + "step": 550400 + }, + { + "epoch": 0.01, + "learning_rate": 4.098050398234234e-05, + "loss": 3.7067, + "step": 550912 + }, + { + "epoch": 0.01, + "learning_rate": 4.097211803483182e-05, + "loss": 3.7073, + "step": 551424 + }, + { + "epoch": 0.01, + "learning_rate": 4.09637320873213e-05, + "loss": 3.7026, + "step": 551936 + }, + { + "epoch": 0.01, + "learning_rate": 4.0955378897418245e-05, + "loss": 3.6981, + "step": 552448 + }, + { + "epoch": 0.01, + "learning_rate": 4.0946992949907725e-05, + "loss": 3.7002, + "step": 552960 + }, + { + "epoch": 0.01, + "learning_rate": 4.0938607002397205e-05, + "loss": 3.7119, + "step": 553472 + }, + { + "epoch": 0.01, + "learning_rate": 4.0930221054886685e-05, + "loss": 3.705, + "step": 553984 + }, + { + "epoch": 0.01, + "learning_rate": 4.092183510737616e-05, + "loss": 3.6911, + "step": 554496 + }, + { + "epoch": 0.01, + "learning_rate": 4.0913465538669374e-05, + "loss": 3.691, + "step": 555008 + }, + { + "epoch": 0.01, + "learning_rate": 4.0905079591158854e-05, + "loss": 3.6878, + "step": 555520 + }, + { + "epoch": 0.01, + "learning_rate": 4.0896693643648334e-05, + "loss": 3.7067, + "step": 556032 + }, + { + "epoch": 0.01, + "learning_rate": 4.0888307696137814e-05, + "loss": 3.7005, + "step": 556544 + }, + { + "epoch": 0.01, + "learning_rate": 4.0879921748627294e-05, + "loss": 3.6946, + "step": 557056 + }, + { + "epoch": 0.01, + "learning_rate": 4.0871535801116774e-05, + "loss": 3.7096, + "step": 557568 + }, + { + "epoch": 0.01, + "learning_rate": 4.0863149853606254e-05, + "loss": 3.6965, + "step": 558080 + }, + { + "epoch": 0.01, + "learning_rate": 4.085478028489946e-05, + "loss": 3.709, + "step": 558592 + }, + { + "epoch": 0.01, + "learning_rate": 4.084639433738894e-05, + "loss": 3.6883, + "step": 559104 + }, + { + "epoch": 0.01, + "learning_rate": 4.083800838987842e-05, + "loss": 3.6839, + "step": 559616 + }, + { + "epoch": 0.01, + "learning_rate": 4.08296224423679e-05, + "loss": 3.6935, + "step": 560128 + }, + { + "epoch": 0.01, + "learning_rate": 4.082123649485738e-05, + "loss": 3.6947, + "step": 560640 + }, + { + "epoch": 0.01, + "learning_rate": 4.081285054734686e-05, + "loss": 3.6897, + "step": 561152 + }, + { + "epoch": 0.01, + "learning_rate": 4.080446459983634e-05, + "loss": 3.6985, + "step": 561664 + }, + { + "epoch": 0.01, + "learning_rate": 4.079609503112955e-05, + "loss": 3.6922, + "step": 562176 + }, + { + "epoch": 0.01, + "learning_rate": 4.078770908361904e-05, + "loss": 3.6843, + "step": 562688 + }, + { + "epoch": 0.01, + "learning_rate": 4.077932313610852e-05, + "loss": 3.6953, + "step": 563200 + }, + { + "epoch": 0.01, + "learning_rate": 4.0770937188598e-05, + "loss": 3.6816, + "step": 563712 + }, + { + "epoch": 0.01, + "learning_rate": 4.076255124108748e-05, + "loss": 3.6976, + "step": 564224 + }, + { + "epoch": 0.01, + "learning_rate": 4.075416529357696e-05, + "loss": 3.6923, + "step": 564736 + }, + { + "epoch": 0.01, + "learning_rate": 4.074579572487017e-05, + "loss": 3.6854, + "step": 565248 + }, + { + "epoch": 0.01, + "learning_rate": 4.073740977735965e-05, + "loss": 3.6889, + "step": 565760 + }, + { + "epoch": 0.01, + "learning_rate": 4.072902382984913e-05, + "loss": 3.6797, + "step": 566272 + }, + { + "epoch": 0.01, + "learning_rate": 4.072063788233861e-05, + "loss": 3.7038, + "step": 566784 + }, + { + "epoch": 0.01, + "learning_rate": 4.071225193482809e-05, + "loss": 3.685, + "step": 567296 + }, + { + "epoch": 0.01, + "learning_rate": 4.07038823661213e-05, + "loss": 3.6932, + "step": 567808 + }, + { + "epoch": 0.01, + "learning_rate": 4.0695496418610777e-05, + "loss": 3.6853, + "step": 568320 + }, + { + "epoch": 0.01, + "learning_rate": 4.0687110471100257e-05, + "loss": 3.6819, + "step": 568832 + }, + { + "epoch": 0.01, + "learning_rate": 4.0678724523589736e-05, + "loss": 3.6842, + "step": 569344 + }, + { + "epoch": 0.01, + "learning_rate": 4.067033857607922e-05, + "loss": 3.6862, + "step": 569856 + }, + { + "epoch": 0.01, + "learning_rate": 4.06619526285687e-05, + "loss": 3.69, + "step": 570368 + }, + { + "epoch": 0.01, + "learning_rate": 4.0653566681058176e-05, + "loss": 3.6902, + "step": 570880 + }, + { + "epoch": 0.01, + "learning_rate": 4.0645180733547656e-05, + "loss": 3.6969, + "step": 571392 + }, + { + "epoch": 0.01, + "learning_rate": 4.063681116484087e-05, + "loss": 3.7039, + "step": 571904 + }, + { + "epoch": 0.01, + "learning_rate": 4.0628425217330345e-05, + "loss": 3.7026, + "step": 572416 + }, + { + "epoch": 0.01, + "learning_rate": 4.0620039269819825e-05, + "loss": 3.6939, + "step": 572928 + }, + { + "epoch": 0.01, + "learning_rate": 4.0611653322309305e-05, + "loss": 3.6928, + "step": 573440 + }, + { + "epoch": 0.01, + "learning_rate": 4.060328375360252e-05, + "loss": 3.6766, + "step": 573952 + }, + { + "epoch": 0.01, + "learning_rate": 4.0594897806091994e-05, + "loss": 3.6892, + "step": 574464 + }, + { + "epoch": 0.01, + "learning_rate": 4.058652823738521e-05, + "loss": 3.7039, + "step": 574976 + }, + { + "epoch": 0.01, + "learning_rate": 4.057814228987469e-05, + "loss": 3.6939, + "step": 575488 + }, + { + "epoch": 0.01, + "learning_rate": 4.056975634236418e-05, + "loss": 3.6911, + "step": 576000 + }, + { + "epoch": 0.01, + "learning_rate": 4.056137039485365e-05, + "loss": 3.6723, + "step": 576512 + }, + { + "epoch": 0.01, + "learning_rate": 4.055298444734313e-05, + "loss": 3.6968, + "step": 577024 + }, + { + "epoch": 0.01, + "learning_rate": 4.0544614878636346e-05, + "loss": 3.6713, + "step": 577536 + }, + { + "epoch": 0.01, + "learning_rate": 4.053622893112582e-05, + "loss": 3.6852, + "step": 578048 + }, + { + "epoch": 0.01, + "learning_rate": 4.05278429836153e-05, + "loss": 3.686, + "step": 578560 + }, + { + "epoch": 0.01, + "learning_rate": 4.051945703610478e-05, + "loss": 3.6894, + "step": 579072 + }, + { + "epoch": 0.01, + "learning_rate": 4.051107108859426e-05, + "loss": 3.6969, + "step": 579584 + }, + { + "epoch": 0.02, + "learning_rate": 4.050268514108374e-05, + "loss": 3.6948, + "step": 580096 + }, + { + "epoch": 0.02, + "learning_rate": 4.049429919357322e-05, + "loss": 3.6804, + "step": 580608 + }, + { + "epoch": 0.02, + "learning_rate": 4.04859132460627e-05, + "loss": 3.6917, + "step": 581120 + }, + { + "epoch": 0.02, + "learning_rate": 4.0477543677355915e-05, + "loss": 3.686, + "step": 581632 + }, + { + "epoch": 0.02, + "learning_rate": 4.0469157729845395e-05, + "loss": 3.683, + "step": 582144 + }, + { + "epoch": 0.02, + "learning_rate": 4.0460771782334875e-05, + "loss": 3.6798, + "step": 582656 + }, + { + "epoch": 0.02, + "learning_rate": 4.0452385834824355e-05, + "loss": 3.6942, + "step": 583168 + }, + { + "epoch": 0.02, + "learning_rate": 4.0444016266117564e-05, + "loss": 3.6947, + "step": 583680 + }, + { + "epoch": 0.02, + "learning_rate": 4.0435630318607044e-05, + "loss": 3.7025, + "step": 584192 + }, + { + "epoch": 0.02, + "learning_rate": 4.0427244371096524e-05, + "loss": 3.6895, + "step": 584704 + }, + { + "epoch": 0.02, + "learning_rate": 4.0418858423586004e-05, + "loss": 3.6901, + "step": 585216 + }, + { + "epoch": 0.02, + "learning_rate": 4.0410472476075483e-05, + "loss": 3.6771, + "step": 585728 + }, + { + "epoch": 0.02, + "learning_rate": 4.0402086528564963e-05, + "loss": 3.695, + "step": 586240 + }, + { + "epoch": 0.02, + "learning_rate": 4.039370058105444e-05, + "loss": 3.6927, + "step": 586752 + }, + { + "epoch": 0.02, + "learning_rate": 4.038533101234765e-05, + "loss": 3.6912, + "step": 587264 + }, + { + "epoch": 0.02, + "learning_rate": 4.037694506483713e-05, + "loss": 3.6936, + "step": 587776 + }, + { + "epoch": 0.02, + "learning_rate": 4.036855911732661e-05, + "loss": 3.6764, + "step": 588288 + }, + { + "epoch": 0.02, + "learning_rate": 4.036017316981609e-05, + "loss": 3.6736, + "step": 588800 + }, + { + "epoch": 0.02, + "learning_rate": 4.035180360110931e-05, + "loss": 3.6766, + "step": 589312 + }, + { + "epoch": 0.02, + "learning_rate": 4.034341765359879e-05, + "loss": 3.6826, + "step": 589824 + }, + { + "epoch": 0.02, + "learning_rate": 4.033503170608827e-05, + "loss": 3.6927, + "step": 590336 + }, + { + "epoch": 0.02, + "learning_rate": 4.032664575857775e-05, + "loss": 3.6918, + "step": 590848 + }, + { + "epoch": 0.02, + "learning_rate": 4.031825981106723e-05, + "loss": 3.6615, + "step": 591360 + }, + { + "epoch": 0.02, + "learning_rate": 4.030989024236044e-05, + "loss": 3.691, + "step": 591872 + }, + { + "epoch": 0.02, + "learning_rate": 4.030150429484992e-05, + "loss": 3.6942, + "step": 592384 + }, + { + "epoch": 0.02, + "learning_rate": 4.02931183473394e-05, + "loss": 3.6914, + "step": 592896 + }, + { + "epoch": 0.02, + "learning_rate": 4.028473239982888e-05, + "loss": 3.69, + "step": 593408 + }, + { + "epoch": 0.02, + "learning_rate": 4.027634645231836e-05, + "loss": 3.6878, + "step": 593920 + }, + { + "epoch": 0.02, + "learning_rate": 4.026796050480783e-05, + "loss": 3.6764, + "step": 594432 + }, + { + "epoch": 0.02, + "learning_rate": 4.025957455729732e-05, + "loss": 3.6955, + "step": 594944 + }, + { + "epoch": 0.02, + "learning_rate": 4.025120498859053e-05, + "loss": 3.6855, + "step": 595456 + }, + { + "epoch": 0.02, + "learning_rate": 4.024281904108001e-05, + "loss": 3.6784, + "step": 595968 + }, + { + "epoch": 0.02, + "learning_rate": 4.0234433093569486e-05, + "loss": 3.6718, + "step": 596480 + }, + { + "epoch": 0.02, + "learning_rate": 4.0226047146058966e-05, + "loss": 3.6816, + "step": 596992 + }, + { + "epoch": 0.02, + "learning_rate": 4.0217661198548446e-05, + "loss": 3.6864, + "step": 597504 + }, + { + "epoch": 0.02, + "learning_rate": 4.0209275251037926e-05, + "loss": 3.6825, + "step": 598016 + }, + { + "epoch": 0.02, + "learning_rate": 4.0200889303527406e-05, + "loss": 3.6933, + "step": 598528 + }, + { + "epoch": 0.02, + "learning_rate": 4.0192519734820615e-05, + "loss": 3.6812, + "step": 599040 + }, + { + "epoch": 0.02, + "learning_rate": 4.018415016611383e-05, + "loss": 3.6776, + "step": 599552 + }, + { + "epoch": 0.02, + "learning_rate": 4.0175764218603304e-05, + "loss": 3.6972, + "step": 600064 + }, + { + "epoch": 0.02, + "learning_rate": 4.0167378271092784e-05, + "loss": 3.6737, + "step": 600576 + }, + { + "epoch": 0.02, + "learning_rate": 4.015899232358227e-05, + "loss": 3.6905, + "step": 601088 + }, + { + "epoch": 0.02, + "learning_rate": 4.015060637607175e-05, + "loss": 3.6965, + "step": 601600 + }, + { + "epoch": 0.02, + "learning_rate": 4.014222042856123e-05, + "loss": 3.6853, + "step": 602112 + }, + { + "epoch": 0.02, + "learning_rate": 4.013383448105071e-05, + "loss": 3.6914, + "step": 602624 + }, + { + "epoch": 0.02, + "learning_rate": 4.012546491234392e-05, + "loss": 3.6833, + "step": 603136 + }, + { + "epoch": 0.02, + "learning_rate": 4.01170789648334e-05, + "loss": 3.6711, + "step": 603648 + }, + { + "epoch": 0.02, + "learning_rate": 4.010869301732288e-05, + "loss": 3.6777, + "step": 604160 + }, + { + "epoch": 0.02, + "learning_rate": 4.010030706981236e-05, + "loss": 3.6853, + "step": 604672 + }, + { + "epoch": 0.02, + "learning_rate": 4.009192112230184e-05, + "loss": 3.6918, + "step": 605184 + }, + { + "epoch": 0.02, + "learning_rate": 4.008353517479132e-05, + "loss": 3.6859, + "step": 605696 + }, + { + "epoch": 0.02, + "learning_rate": 4.007516560608453e-05, + "loss": 3.6903, + "step": 606208 + }, + { + "epoch": 0.02, + "learning_rate": 4.006677965857401e-05, + "loss": 3.6797, + "step": 606720 + }, + { + "epoch": 0.02, + "learning_rate": 4.005839371106349e-05, + "loss": 3.6867, + "step": 607232 + }, + { + "epoch": 0.02, + "learning_rate": 4.005000776355297e-05, + "loss": 3.6718, + "step": 607744 + }, + { + "epoch": 0.02, + "learning_rate": 4.0041621816042455e-05, + "loss": 3.6812, + "step": 608256 + }, + { + "epoch": 0.02, + "learning_rate": 4.0033235868531935e-05, + "loss": 3.693, + "step": 608768 + }, + { + "epoch": 0.02, + "learning_rate": 4.0024849921021415e-05, + "loss": 3.6941, + "step": 609280 + }, + { + "epoch": 0.02, + "learning_rate": 4.0016463973510895e-05, + "loss": 3.6723, + "step": 609792 + }, + { + "epoch": 0.02, + "learning_rate": 4.0008094404804104e-05, + "loss": 3.6837, + "step": 610304 + }, + { + "epoch": 0.03, + "eval_loss": 3.8487296104431152, + "eval_runtime": 589.3545, + "eval_samples_per_second": 647.473, + "eval_steps_per_second": 20.234, + "step": 610552 + }, + { + "epoch": 0.0, + "learning_rate": 3.999972483609731e-05, + "loss": 3.7002, + "step": 610816 + }, + { + "epoch": 0.0, + "learning_rate": 3.999133888858679e-05, + "loss": 3.682, + "step": 611328 + }, + { + "epoch": 0.0, + "learning_rate": 3.998295294107627e-05, + "loss": 3.6762, + "step": 611840 + }, + { + "epoch": 0.0, + "learning_rate": 3.997456699356575e-05, + "loss": 3.6839, + "step": 612352 + }, + { + "epoch": 0.0, + "learning_rate": 3.996618104605523e-05, + "loss": 3.6691, + "step": 612864 + }, + { + "epoch": 0.0, + "learning_rate": 3.995779509854471e-05, + "loss": 3.6716, + "step": 613376 + }, + { + "epoch": 0.0, + "learning_rate": 3.994940915103419e-05, + "loss": 3.6717, + "step": 613888 + }, + { + "epoch": 0.0, + "learning_rate": 3.994102320352367e-05, + "loss": 3.6711, + "step": 614400 + }, + { + "epoch": 0.0, + "learning_rate": 3.993265363481689e-05, + "loss": 3.6742, + "step": 614912 + }, + { + "epoch": 0.0, + "learning_rate": 3.99242840661101e-05, + "loss": 3.6829, + "step": 615424 + }, + { + "epoch": 0.0, + "learning_rate": 3.991589811859958e-05, + "loss": 3.6762, + "step": 615936 + }, + { + "epoch": 0.0, + "learning_rate": 3.990751217108906e-05, + "loss": 3.6748, + "step": 616448 + }, + { + "epoch": 0.0, + "learning_rate": 3.989912622357854e-05, + "loss": 3.6858, + "step": 616960 + }, + { + "epoch": 0.0, + "learning_rate": 3.989074027606802e-05, + "loss": 3.6709, + "step": 617472 + }, + { + "epoch": 0.0, + "learning_rate": 3.9882370707361227e-05, + "loss": 3.6852, + "step": 617984 + }, + { + "epoch": 0.0, + "learning_rate": 3.9873984759850707e-05, + "loss": 3.6605, + "step": 618496 + }, + { + "epoch": 0.0, + "learning_rate": 3.9865598812340187e-05, + "loss": 3.6675, + "step": 619008 + }, + { + "epoch": 0.0, + "learning_rate": 3.9857212864829666e-05, + "loss": 3.6787, + "step": 619520 + }, + { + "epoch": 0.0, + "learning_rate": 3.9848826917319146e-05, + "loss": 3.6727, + "step": 620032 + }, + { + "epoch": 0.0, + "learning_rate": 3.9840440969808626e-05, + "loss": 3.6884, + "step": 620544 + }, + { + "epoch": 0.0, + "learning_rate": 3.9832055022298106e-05, + "loss": 3.6756, + "step": 621056 + }, + { + "epoch": 0.0, + "learning_rate": 3.9823669074787586e-05, + "loss": 3.6763, + "step": 621568 + }, + { + "epoch": 0.0, + "learning_rate": 3.9815299506080795e-05, + "loss": 3.6804, + "step": 622080 + }, + { + "epoch": 0.0, + "learning_rate": 3.980692993737401e-05, + "loss": 3.6703, + "step": 622592 + }, + { + "epoch": 0.0, + "learning_rate": 3.979854398986349e-05, + "loss": 3.6773, + "step": 623104 + }, + { + "epoch": 0.0, + "learning_rate": 3.9790158042352964e-05, + "loss": 3.6684, + "step": 623616 + }, + { + "epoch": 0.0, + "learning_rate": 3.9781772094842444e-05, + "loss": 3.6809, + "step": 624128 + }, + { + "epoch": 0.0, + "learning_rate": 3.9773386147331924e-05, + "loss": 3.6698, + "step": 624640 + }, + { + "epoch": 0.0, + "learning_rate": 3.9765000199821404e-05, + "loss": 3.6798, + "step": 625152 + }, + { + "epoch": 0.0, + "learning_rate": 3.9756614252310884e-05, + "loss": 3.6678, + "step": 625664 + }, + { + "epoch": 0.01, + "learning_rate": 3.9748228304800364e-05, + "loss": 3.6599, + "step": 626176 + }, + { + "epoch": 0.01, + "learning_rate": 3.973985873609358e-05, + "loss": 3.6778, + "step": 626688 + }, + { + "epoch": 0.01, + "learning_rate": 3.973147278858306e-05, + "loss": 3.6788, + "step": 627200 + }, + { + "epoch": 0.01, + "learning_rate": 3.972308684107254e-05, + "loss": 3.678, + "step": 627712 + }, + { + "epoch": 0.01, + "learning_rate": 3.971471727236575e-05, + "loss": 3.6717, + "step": 628224 + }, + { + "epoch": 0.01, + "learning_rate": 3.970633132485523e-05, + "loss": 3.6746, + "step": 628736 + }, + { + "epoch": 0.01, + "learning_rate": 3.969794537734471e-05, + "loss": 3.669, + "step": 629248 + }, + { + "epoch": 0.01, + "learning_rate": 3.968955942983419e-05, + "loss": 3.6816, + "step": 629760 + }, + { + "epoch": 0.01, + "learning_rate": 3.968117348232367e-05, + "loss": 3.6764, + "step": 630272 + }, + { + "epoch": 0.01, + "learning_rate": 3.967278753481315e-05, + "loss": 3.6616, + "step": 630784 + }, + { + "epoch": 0.01, + "learning_rate": 3.966440158730263e-05, + "loss": 3.6638, + "step": 631296 + }, + { + "epoch": 0.01, + "learning_rate": 3.965601563979211e-05, + "loss": 3.6597, + "step": 631808 + }, + { + "epoch": 0.01, + "learning_rate": 3.964766244988905e-05, + "loss": 3.6777, + "step": 632320 + }, + { + "epoch": 0.01, + "learning_rate": 3.9639276502378534e-05, + "loss": 3.676, + "step": 632832 + }, + { + "epoch": 0.01, + "learning_rate": 3.9630890554868014e-05, + "loss": 3.6625, + "step": 633344 + }, + { + "epoch": 0.01, + "learning_rate": 3.9622504607357494e-05, + "loss": 3.6826, + "step": 633856 + }, + { + "epoch": 0.01, + "learning_rate": 3.9614118659846974e-05, + "loss": 3.666, + "step": 634368 + }, + { + "epoch": 0.01, + "learning_rate": 3.960574909114018e-05, + "loss": 3.6794, + "step": 634880 + }, + { + "epoch": 0.01, + "learning_rate": 3.959736314362966e-05, + "loss": 3.6647, + "step": 635392 + }, + { + "epoch": 0.01, + "learning_rate": 3.958897719611914e-05, + "loss": 3.6577, + "step": 635904 + }, + { + "epoch": 0.01, + "learning_rate": 3.958059124860862e-05, + "loss": 3.6637, + "step": 636416 + }, + { + "epoch": 0.01, + "learning_rate": 3.95722053010981e-05, + "loss": 3.6622, + "step": 636928 + }, + { + "epoch": 0.01, + "learning_rate": 3.956381935358758e-05, + "loss": 3.6692, + "step": 637440 + }, + { + "epoch": 0.01, + "learning_rate": 3.955543340607706e-05, + "loss": 3.6632, + "step": 637952 + }, + { + "epoch": 0.01, + "learning_rate": 3.954706383737027e-05, + "loss": 3.6658, + "step": 638464 + }, + { + "epoch": 0.01, + "learning_rate": 3.953867788985975e-05, + "loss": 3.6525, + "step": 638976 + }, + { + "epoch": 0.01, + "learning_rate": 3.953029194234923e-05, + "loss": 3.6669, + "step": 639488 + }, + { + "epoch": 0.01, + "learning_rate": 3.952190599483872e-05, + "loss": 3.6558, + "step": 640000 + }, + { + "epoch": 0.01, + "learning_rate": 3.95135200473282e-05, + "loss": 3.6678, + "step": 640512 + }, + { + "epoch": 0.01, + "learning_rate": 3.950513409981768e-05, + "loss": 3.6586, + "step": 641024 + }, + { + "epoch": 0.01, + "learning_rate": 3.949676453111089e-05, + "loss": 3.6631, + "step": 641536 + }, + { + "epoch": 0.01, + "learning_rate": 3.948837858360037e-05, + "loss": 3.6612, + "step": 642048 + }, + { + "epoch": 0.01, + "learning_rate": 3.947999263608985e-05, + "loss": 3.6513, + "step": 642560 + }, + { + "epoch": 0.01, + "learning_rate": 3.947160668857933e-05, + "loss": 3.6729, + "step": 643072 + }, + { + "epoch": 0.01, + "learning_rate": 3.94632207410688e-05, + "loss": 3.6579, + "step": 643584 + }, + { + "epoch": 0.01, + "learning_rate": 3.9454851172362016e-05, + "loss": 3.6656, + "step": 644096 + }, + { + "epoch": 0.01, + "learning_rate": 3.9446465224851496e-05, + "loss": 3.6601, + "step": 644608 + }, + { + "epoch": 0.01, + "learning_rate": 3.943807927734097e-05, + "loss": 3.6517, + "step": 645120 + }, + { + "epoch": 0.01, + "learning_rate": 3.9429693329830456e-05, + "loss": 3.6554, + "step": 645632 + }, + { + "epoch": 0.01, + "learning_rate": 3.9421307382319936e-05, + "loss": 3.659, + "step": 646144 + }, + { + "epoch": 0.01, + "learning_rate": 3.941293781361315e-05, + "loss": 3.6627, + "step": 646656 + }, + { + "epoch": 0.01, + "learning_rate": 3.9404551866102625e-05, + "loss": 3.6617, + "step": 647168 + }, + { + "epoch": 0.01, + "learning_rate": 3.9396165918592105e-05, + "loss": 3.6658, + "step": 647680 + }, + { + "epoch": 0.01, + "learning_rate": 3.9387779971081585e-05, + "loss": 3.6819, + "step": 648192 + }, + { + "epoch": 0.01, + "learning_rate": 3.9379394023571065e-05, + "loss": 3.6745, + "step": 648704 + }, + { + "epoch": 0.01, + "learning_rate": 3.9371008076060545e-05, + "loss": 3.6653, + "step": 649216 + }, + { + "epoch": 0.01, + "learning_rate": 3.9362638507353754e-05, + "loss": 3.665, + "step": 649728 + }, + { + "epoch": 0.01, + "learning_rate": 3.9354252559843234e-05, + "loss": 3.6517, + "step": 650240 + }, + { + "epoch": 0.01, + "learning_rate": 3.9345866612332714e-05, + "loss": 3.6594, + "step": 650752 + }, + { + "epoch": 0.01, + "learning_rate": 3.9337480664822194e-05, + "loss": 3.6729, + "step": 651264 + }, + { + "epoch": 0.01, + "learning_rate": 3.9329094717311674e-05, + "loss": 3.6706, + "step": 651776 + }, + { + "epoch": 0.01, + "learning_rate": 3.932072514860489e-05, + "loss": 3.6595, + "step": 652288 + }, + { + "epoch": 0.01, + "learning_rate": 3.931233920109437e-05, + "loss": 3.6482, + "step": 652800 + }, + { + "epoch": 0.01, + "learning_rate": 3.930395325358385e-05, + "loss": 3.6688, + "step": 653312 + }, + { + "epoch": 0.01, + "learning_rate": 3.929556730607333e-05, + "loss": 3.6405, + "step": 653824 + }, + { + "epoch": 0.01, + "learning_rate": 3.928718135856281e-05, + "loss": 3.6606, + "step": 654336 + }, + { + "epoch": 0.01, + "learning_rate": 3.927879541105229e-05, + "loss": 3.6604, + "step": 654848 + }, + { + "epoch": 0.01, + "learning_rate": 3.927040946354177e-05, + "loss": 3.6593, + "step": 655360 + }, + { + "epoch": 0.01, + "learning_rate": 3.926203989483498e-05, + "loss": 3.6715, + "step": 655872 + }, + { + "epoch": 0.02, + "learning_rate": 3.925365394732446e-05, + "loss": 3.6668, + "step": 656384 + }, + { + "epoch": 0.02, + "learning_rate": 3.924526799981394e-05, + "loss": 3.6551, + "step": 656896 + }, + { + "epoch": 0.02, + "learning_rate": 3.923688205230342e-05, + "loss": 3.6588, + "step": 657408 + }, + { + "epoch": 0.02, + "learning_rate": 3.92284961047929e-05, + "loss": 3.6591, + "step": 657920 + }, + { + "epoch": 0.02, + "learning_rate": 3.922011015728238e-05, + "loss": 3.6562, + "step": 658432 + }, + { + "epoch": 0.02, + "learning_rate": 3.921172420977186e-05, + "loss": 3.6535, + "step": 658944 + }, + { + "epoch": 0.02, + "learning_rate": 3.920333826226134e-05, + "loss": 3.6648, + "step": 659456 + }, + { + "epoch": 0.02, + "learning_rate": 3.9194968693554554e-05, + "loss": 3.6706, + "step": 659968 + }, + { + "epoch": 0.02, + "learning_rate": 3.9186582746044034e-05, + "loss": 3.678, + "step": 660480 + }, + { + "epoch": 0.02, + "learning_rate": 3.9178196798533514e-05, + "loss": 3.6577, + "step": 660992 + }, + { + "epoch": 0.02, + "learning_rate": 3.916981085102299e-05, + "loss": 3.6639, + "step": 661504 + }, + { + "epoch": 0.02, + "learning_rate": 3.916142490351247e-05, + "loss": 3.653, + "step": 662016 + }, + { + "epoch": 0.02, + "learning_rate": 3.915303895600195e-05, + "loss": 3.6622, + "step": 662528 + }, + { + "epoch": 0.02, + "learning_rate": 3.914466938729516e-05, + "loss": 3.6693, + "step": 663040 + }, + { + "epoch": 0.02, + "learning_rate": 3.9136283439784636e-05, + "loss": 3.6659, + "step": 663552 + }, + { + "epoch": 0.02, + "learning_rate": 3.9127897492274116e-05, + "loss": 3.6681, + "step": 664064 + }, + { + "epoch": 0.02, + "learning_rate": 3.9119511544763596e-05, + "loss": 3.6478, + "step": 664576 + }, + { + "epoch": 0.02, + "learning_rate": 3.9111125597253076e-05, + "loss": 3.6489, + "step": 665088 + }, + { + "epoch": 0.02, + "learning_rate": 3.9102739649742556e-05, + "loss": 3.6502, + "step": 665600 + }, + { + "epoch": 0.02, + "learning_rate": 3.909437008103577e-05, + "loss": 3.6585, + "step": 666112 + }, + { + "epoch": 0.02, + "learning_rate": 3.908598413352525e-05, + "loss": 3.6595, + "step": 666624 + }, + { + "epoch": 0.02, + "learning_rate": 3.907759818601473e-05, + "loss": 3.6648, + "step": 667136 + }, + { + "epoch": 0.02, + "learning_rate": 3.906921223850421e-05, + "loss": 3.6338, + "step": 667648 + }, + { + "epoch": 0.02, + "learning_rate": 3.906084266979742e-05, + "loss": 3.6639, + "step": 668160 + }, + { + "epoch": 0.02, + "learning_rate": 3.90524567222869e-05, + "loss": 3.6689, + "step": 668672 + }, + { + "epoch": 0.02, + "learning_rate": 3.904407077477638e-05, + "loss": 3.6605, + "step": 669184 + }, + { + "epoch": 0.02, + "learning_rate": 3.903568482726586e-05, + "loss": 3.664, + "step": 669696 + }, + { + "epoch": 0.02, + "learning_rate": 3.902729887975534e-05, + "loss": 3.6617, + "step": 670208 + }, + { + "epoch": 0.02, + "learning_rate": 3.901891293224482e-05, + "loss": 3.648, + "step": 670720 + }, + { + "epoch": 0.02, + "learning_rate": 3.90105269847343e-05, + "loss": 3.667, + "step": 671232 + }, + { + "epoch": 0.02, + "learning_rate": 3.900215741602751e-05, + "loss": 3.6636, + "step": 671744 + }, + { + "epoch": 0.02, + "learning_rate": 3.8993771468516996e-05, + "loss": 3.6495, + "step": 672256 + }, + { + "epoch": 0.02, + "learning_rate": 3.8985385521006476e-05, + "loss": 3.6476, + "step": 672768 + }, + { + "epoch": 0.02, + "learning_rate": 3.8976999573495956e-05, + "loss": 3.6547, + "step": 673280 + }, + { + "epoch": 0.02, + "learning_rate": 3.8968613625985436e-05, + "loss": 3.6569, + "step": 673792 + }, + { + "epoch": 0.02, + "learning_rate": 3.8960227678474916e-05, + "loss": 3.6554, + "step": 674304 + }, + { + "epoch": 0.02, + "learning_rate": 3.8951858109768125e-05, + "loss": 3.664, + "step": 674816 + }, + { + "epoch": 0.02, + "learning_rate": 3.8943472162257605e-05, + "loss": 3.6575, + "step": 675328 + }, + { + "epoch": 0.02, + "learning_rate": 3.8935086214747085e-05, + "loss": 3.6492, + "step": 675840 + }, + { + "epoch": 0.02, + "learning_rate": 3.8926700267236565e-05, + "loss": 3.672, + "step": 676352 + }, + { + "epoch": 0.02, + "learning_rate": 3.8918314319726045e-05, + "loss": 3.6479, + "step": 676864 + }, + { + "epoch": 0.02, + "learning_rate": 3.890992837221552e-05, + "loss": 3.6652, + "step": 677376 + }, + { + "epoch": 0.02, + "learning_rate": 3.8901558803508734e-05, + "loss": 3.6714, + "step": 677888 + }, + { + "epoch": 0.02, + "learning_rate": 3.8893172855998214e-05, + "loss": 3.6594, + "step": 678400 + }, + { + "epoch": 0.02, + "learning_rate": 3.8884786908487694e-05, + "loss": 3.6646, + "step": 678912 + }, + { + "epoch": 0.02, + "learning_rate": 3.8876400960977174e-05, + "loss": 3.6584, + "step": 679424 + }, + { + "epoch": 0.02, + "learning_rate": 3.886803139227039e-05, + "loss": 3.6438, + "step": 679936 + }, + { + "epoch": 0.02, + "learning_rate": 3.885964544475987e-05, + "loss": 3.6546, + "step": 680448 + }, + { + "epoch": 0.02, + "learning_rate": 3.885125949724935e-05, + "loss": 3.6548, + "step": 680960 + }, + { + "epoch": 0.02, + "learning_rate": 3.884287354973882e-05, + "loss": 3.6671, + "step": 681472 + }, + { + "epoch": 0.02, + "learning_rate": 3.88344876022283e-05, + "loss": 3.6602, + "step": 681984 + }, + { + "epoch": 0.02, + "learning_rate": 3.882610165471778e-05, + "loss": 3.6594, + "step": 682496 + }, + { + "epoch": 0.02, + "learning_rate": 3.881771570720726e-05, + "loss": 3.6586, + "step": 683008 + }, + { + "epoch": 0.02, + "learning_rate": 3.880932975969674e-05, + "loss": 3.6579, + "step": 683520 + }, + { + "epoch": 0.02, + "learning_rate": 3.880096019098995e-05, + "loss": 3.6442, + "step": 684032 + }, + { + "epoch": 0.02, + "learning_rate": 3.879257424347943e-05, + "loss": 3.6553, + "step": 684544 + }, + { + "epoch": 0.02, + "learning_rate": 3.878418829596892e-05, + "loss": 3.6654, + "step": 685056 + }, + { + "epoch": 0.02, + "learning_rate": 3.87758023484584e-05, + "loss": 3.6665, + "step": 685568 + }, + { + "epoch": 0.02, + "learning_rate": 3.876743277975161e-05, + "loss": 3.6479, + "step": 686080 + }, + { + "epoch": 0.02, + "learning_rate": 3.875904683224109e-05, + "loss": 3.6531, + "step": 686592 + }, + { + "epoch": 0.03, + "eval_loss": 3.844803810119629, + "eval_runtime": 573.814, + "eval_samples_per_second": 665.008, + "eval_steps_per_second": 20.782, + "step": 686871 + }, + { + "epoch": 0.0, + "learning_rate": 3.8750677263534297e-05, + "loss": 3.6743, + "step": 687104 + }, + { + "epoch": 0.0, + "learning_rate": 3.8742291316023777e-05, + "loss": 3.6552, + "step": 687616 + }, + { + "epoch": 0.0, + "learning_rate": 3.8733905368513256e-05, + "loss": 3.6528, + "step": 688128 + }, + { + "epoch": 0.0, + "learning_rate": 3.8725519421002736e-05, + "loss": 3.6571, + "step": 688640 + }, + { + "epoch": 0.0, + "learning_rate": 3.8717133473492216e-05, + "loss": 3.6482, + "step": 689152 + }, + { + "epoch": 0.0, + "learning_rate": 3.8708747525981696e-05, + "loss": 3.6444, + "step": 689664 + }, + { + "epoch": 0.0, + "learning_rate": 3.8700377957274905e-05, + "loss": 3.6448, + "step": 690176 + }, + { + "epoch": 0.0, + "learning_rate": 3.8691992009764385e-05, + "loss": 3.6448, + "step": 690688 + }, + { + "epoch": 0.0, + "learning_rate": 3.8683606062253865e-05, + "loss": 3.6466, + "step": 691200 + }, + { + "epoch": 0.0, + "learning_rate": 3.867522011474335e-05, + "loss": 3.6586, + "step": 691712 + }, + { + "epoch": 0.0, + "learning_rate": 3.866685054603656e-05, + "loss": 3.6481, + "step": 692224 + }, + { + "epoch": 0.0, + "learning_rate": 3.865846459852604e-05, + "loss": 3.6498, + "step": 692736 + }, + { + "epoch": 0.0, + "learning_rate": 3.865007865101552e-05, + "loss": 3.6594, + "step": 693248 + }, + { + "epoch": 0.0, + "learning_rate": 3.8641692703505e-05, + "loss": 3.6468, + "step": 693760 + }, + { + "epoch": 0.0, + "learning_rate": 3.863332313479821e-05, + "loss": 3.6553, + "step": 694272 + }, + { + "epoch": 0.0, + "learning_rate": 3.862493718728769e-05, + "loss": 3.6344, + "step": 694784 + }, + { + "epoch": 0.0, + "learning_rate": 3.861655123977717e-05, + "loss": 3.6404, + "step": 695296 + }, + { + "epoch": 0.0, + "learning_rate": 3.860816529226665e-05, + "loss": 3.6556, + "step": 695808 + }, + { + "epoch": 0.0, + "learning_rate": 3.859977934475613e-05, + "loss": 3.649, + "step": 696320 + }, + { + "epoch": 0.0, + "learning_rate": 3.859140977604934e-05, + "loss": 3.6616, + "step": 696832 + }, + { + "epoch": 0.0, + "learning_rate": 3.858302382853882e-05, + "loss": 3.6448, + "step": 697344 + }, + { + "epoch": 0.0, + "learning_rate": 3.8574637881028306e-05, + "loss": 3.6601, + "step": 697856 + }, + { + "epoch": 0.0, + "learning_rate": 3.8566251933517786e-05, + "loss": 3.6478, + "step": 698368 + }, + { + "epoch": 0.0, + "learning_rate": 3.8557882364810995e-05, + "loss": 3.645, + "step": 698880 + }, + { + "epoch": 0.0, + "learning_rate": 3.8549496417300475e-05, + "loss": 3.6521, + "step": 699392 + }, + { + "epoch": 0.0, + "learning_rate": 3.8541110469789955e-05, + "loss": 3.6472, + "step": 699904 + }, + { + "epoch": 0.0, + "learning_rate": 3.8532724522279435e-05, + "loss": 3.6543, + "step": 700416 + }, + { + "epoch": 0.0, + "learning_rate": 3.8524338574768915e-05, + "loss": 3.6451, + "step": 700928 + }, + { + "epoch": 0.0, + "learning_rate": 3.8515952627258395e-05, + "loss": 3.6539, + "step": 701440 + }, + { + "epoch": 0.0, + "learning_rate": 3.8507566679747875e-05, + "loss": 3.6454, + "step": 701952 + }, + { + "epoch": 0.01, + "learning_rate": 3.8499180732237354e-05, + "loss": 3.6276, + "step": 702464 + }, + { + "epoch": 0.01, + "learning_rate": 3.8490811163530564e-05, + "loss": 3.6552, + "step": 702976 + }, + { + "epoch": 0.01, + "learning_rate": 3.8482425216020044e-05, + "loss": 3.6543, + "step": 703488 + }, + { + "epoch": 0.01, + "learning_rate": 3.8474039268509524e-05, + "loss": 3.6523, + "step": 704000 + }, + { + "epoch": 0.01, + "learning_rate": 3.8465653320999003e-05, + "loss": 3.6487, + "step": 704512 + }, + { + "epoch": 0.01, + "learning_rate": 3.845728375229222e-05, + "loss": 3.6451, + "step": 705024 + }, + { + "epoch": 0.01, + "learning_rate": 3.84488978047817e-05, + "loss": 3.6459, + "step": 705536 + }, + { + "epoch": 0.01, + "learning_rate": 3.844052823607491e-05, + "loss": 3.6539, + "step": 706048 + }, + { + "epoch": 0.01, + "learning_rate": 3.843214228856439e-05, + "loss": 3.6529, + "step": 706560 + }, + { + "epoch": 0.01, + "learning_rate": 3.842375634105387e-05, + "loss": 3.6338, + "step": 707072 + }, + { + "epoch": 0.01, + "learning_rate": 3.841537039354335e-05, + "loss": 3.6424, + "step": 707584 + }, + { + "epoch": 0.01, + "learning_rate": 3.840700082483656e-05, + "loss": 3.637, + "step": 708096 + }, + { + "epoch": 0.01, + "learning_rate": 3.839861487732604e-05, + "loss": 3.6469, + "step": 708608 + }, + { + "epoch": 0.01, + "learning_rate": 3.839022892981552e-05, + "loss": 3.6515, + "step": 709120 + }, + { + "epoch": 0.01, + "learning_rate": 3.8381842982305e-05, + "loss": 3.6397, + "step": 709632 + }, + { + "epoch": 0.01, + "learning_rate": 3.837347341359821e-05, + "loss": 3.6552, + "step": 710144 + }, + { + "epoch": 0.01, + "learning_rate": 3.836508746608769e-05, + "loss": 3.6396, + "step": 710656 + }, + { + "epoch": 0.01, + "learning_rate": 3.835670151857717e-05, + "loss": 3.6563, + "step": 711168 + }, + { + "epoch": 0.01, + "learning_rate": 3.834831557106665e-05, + "loss": 3.64, + "step": 711680 + }, + { + "epoch": 0.01, + "learning_rate": 3.833992962355613e-05, + "loss": 3.6325, + "step": 712192 + }, + { + "epoch": 0.01, + "learning_rate": 3.8331543676045606e-05, + "loss": 3.6413, + "step": 712704 + }, + { + "epoch": 0.01, + "learning_rate": 3.8323157728535086e-05, + "loss": 3.6332, + "step": 713216 + }, + { + "epoch": 0.01, + "learning_rate": 3.8314771781024566e-05, + "loss": 3.6476, + "step": 713728 + }, + { + "epoch": 0.01, + "learning_rate": 3.8306402212317775e-05, + "loss": 3.6369, + "step": 714240 + }, + { + "epoch": 0.01, + "learning_rate": 3.829803264361099e-05, + "loss": 3.6453, + "step": 714752 + }, + { + "epoch": 0.01, + "learning_rate": 3.828964669610047e-05, + "loss": 3.6281, + "step": 715264 + }, + { + "epoch": 0.01, + "learning_rate": 3.828126074858995e-05, + "loss": 3.6417, + "step": 715776 + }, + { + "epoch": 0.01, + "learning_rate": 3.827287480107943e-05, + "loss": 3.6283, + "step": 716288 + }, + { + "epoch": 0.01, + "learning_rate": 3.826448885356891e-05, + "loss": 3.6468, + "step": 716800 + }, + { + "epoch": 0.01, + "learning_rate": 3.825610290605839e-05, + "loss": 3.6348, + "step": 717312 + }, + { + "epoch": 0.01, + "learning_rate": 3.82477333373516e-05, + "loss": 3.6371, + "step": 717824 + }, + { + "epoch": 0.01, + "learning_rate": 3.823934738984108e-05, + "loss": 3.6369, + "step": 718336 + }, + { + "epoch": 0.01, + "learning_rate": 3.823096144233056e-05, + "loss": 3.6266, + "step": 718848 + }, + { + "epoch": 0.01, + "learning_rate": 3.822257549482004e-05, + "loss": 3.6456, + "step": 719360 + }, + { + "epoch": 0.01, + "learning_rate": 3.821420592611325e-05, + "loss": 3.6372, + "step": 719872 + }, + { + "epoch": 0.01, + "learning_rate": 3.820581997860273e-05, + "loss": 3.6442, + "step": 720384 + }, + { + "epoch": 0.01, + "learning_rate": 3.819743403109221e-05, + "loss": 3.6311, + "step": 720896 + }, + { + "epoch": 0.01, + "learning_rate": 3.818904808358169e-05, + "loss": 3.6305, + "step": 721408 + }, + { + "epoch": 0.01, + "learning_rate": 3.818066213607117e-05, + "loss": 3.6299, + "step": 721920 + }, + { + "epoch": 0.01, + "learning_rate": 3.817227618856065e-05, + "loss": 3.6375, + "step": 722432 + }, + { + "epoch": 0.01, + "learning_rate": 3.8163890241050135e-05, + "loss": 3.6337, + "step": 722944 + }, + { + "epoch": 0.01, + "learning_rate": 3.8155504293539615e-05, + "loss": 3.6393, + "step": 723456 + }, + { + "epoch": 0.01, + "learning_rate": 3.8147134724832824e-05, + "loss": 3.6412, + "step": 723968 + }, + { + "epoch": 0.01, + "learning_rate": 3.8138748777322304e-05, + "loss": 3.6585, + "step": 724480 + }, + { + "epoch": 0.01, + "learning_rate": 3.8130362829811784e-05, + "loss": 3.6463, + "step": 724992 + }, + { + "epoch": 0.01, + "learning_rate": 3.8121976882301264e-05, + "loss": 3.6435, + "step": 725504 + }, + { + "epoch": 0.01, + "learning_rate": 3.811360731359447e-05, + "loss": 3.6397, + "step": 726016 + }, + { + "epoch": 0.01, + "learning_rate": 3.810522136608395e-05, + "loss": 3.6299, + "step": 726528 + }, + { + "epoch": 0.01, + "learning_rate": 3.809683541857343e-05, + "loss": 3.6305, + "step": 727040 + }, + { + "epoch": 0.01, + "learning_rate": 3.808844947106291e-05, + "loss": 3.6492, + "step": 727552 + }, + { + "epoch": 0.01, + "learning_rate": 3.808007990235612e-05, + "loss": 3.6496, + "step": 728064 + }, + { + "epoch": 0.01, + "learning_rate": 3.80716939548456e-05, + "loss": 3.6399, + "step": 728576 + }, + { + "epoch": 0.01, + "learning_rate": 3.806330800733509e-05, + "loss": 3.6226, + "step": 729088 + }, + { + "epoch": 0.01, + "learning_rate": 3.805492205982457e-05, + "loss": 3.6378, + "step": 729600 + }, + { + "epoch": 0.01, + "learning_rate": 3.804655249111778e-05, + "loss": 3.6199, + "step": 730112 + }, + { + "epoch": 0.01, + "learning_rate": 3.803816654360726e-05, + "loss": 3.6369, + "step": 730624 + }, + { + "epoch": 0.01, + "learning_rate": 3.802978059609674e-05, + "loss": 3.6359, + "step": 731136 + }, + { + "epoch": 0.01, + "learning_rate": 3.802139464858622e-05, + "loss": 3.6342, + "step": 731648 + }, + { + "epoch": 0.01, + "learning_rate": 3.80130087010757e-05, + "loss": 3.646, + "step": 732160 + }, + { + "epoch": 0.02, + "learning_rate": 3.800462275356518e-05, + "loss": 3.6411, + "step": 732672 + }, + { + "epoch": 0.02, + "learning_rate": 3.799625318485839e-05, + "loss": 3.6344, + "step": 733184 + }, + { + "epoch": 0.02, + "learning_rate": 3.798786723734787e-05, + "loss": 3.6355, + "step": 733696 + }, + { + "epoch": 0.02, + "learning_rate": 3.797948128983735e-05, + "loss": 3.6369, + "step": 734208 + }, + { + "epoch": 0.02, + "learning_rate": 3.797109534232683e-05, + "loss": 3.629, + "step": 734720 + }, + { + "epoch": 0.02, + "learning_rate": 3.796270939481631e-05, + "loss": 3.6315, + "step": 735232 + }, + { + "epoch": 0.02, + "learning_rate": 3.795432344730579e-05, + "loss": 3.638, + "step": 735744 + }, + { + "epoch": 0.02, + "learning_rate": 3.7945953878599e-05, + "loss": 3.6466, + "step": 736256 + }, + { + "epoch": 0.02, + "learning_rate": 3.793756793108848e-05, + "loss": 3.6525, + "step": 736768 + }, + { + "epoch": 0.02, + "learning_rate": 3.792918198357796e-05, + "loss": 3.6327, + "step": 737280 + }, + { + "epoch": 0.02, + "learning_rate": 3.7920796036067436e-05, + "loss": 3.6417, + "step": 737792 + }, + { + "epoch": 0.02, + "learning_rate": 3.7912410088556916e-05, + "loss": 3.6315, + "step": 738304 + }, + { + "epoch": 0.02, + "learning_rate": 3.7904024141046396e-05, + "loss": 3.6395, + "step": 738816 + }, + { + "epoch": 0.02, + "learning_rate": 3.789565457233961e-05, + "loss": 3.6382, + "step": 739328 + }, + { + "epoch": 0.02, + "learning_rate": 3.7887268624829085e-05, + "loss": 3.6448, + "step": 739840 + }, + { + "epoch": 0.02, + "learning_rate": 3.7878882677318565e-05, + "loss": 3.6447, + "step": 740352 + }, + { + "epoch": 0.02, + "learning_rate": 3.7870496729808045e-05, + "loss": 3.6243, + "step": 740864 + }, + { + "epoch": 0.02, + "learning_rate": 3.786212716110126e-05, + "loss": 3.6264, + "step": 741376 + }, + { + "epoch": 0.02, + "learning_rate": 3.785374121359074e-05, + "loss": 3.6254, + "step": 741888 + }, + { + "epoch": 0.02, + "learning_rate": 3.784535526608022e-05, + "loss": 3.6302, + "step": 742400 + }, + { + "epoch": 0.02, + "learning_rate": 3.78369693185697e-05, + "loss": 3.638, + "step": 742912 + }, + { + "epoch": 0.02, + "learning_rate": 3.782858337105918e-05, + "loss": 3.641, + "step": 743424 + }, + { + "epoch": 0.02, + "learning_rate": 3.782021380235239e-05, + "loss": 3.616, + "step": 743936 + }, + { + "epoch": 0.02, + "learning_rate": 3.781182785484187e-05, + "loss": 3.6379, + "step": 744448 + }, + { + "epoch": 0.02, + "learning_rate": 3.780344190733135e-05, + "loss": 3.6429, + "step": 744960 + }, + { + "epoch": 0.02, + "learning_rate": 3.779505595982083e-05, + "loss": 3.6384, + "step": 745472 + }, + { + "epoch": 0.02, + "learning_rate": 3.778667001231031e-05, + "loss": 3.64, + "step": 745984 + }, + { + "epoch": 0.02, + "learning_rate": 3.777828406479979e-05, + "loss": 3.6367, + "step": 746496 + }, + { + "epoch": 0.02, + "learning_rate": 3.7769914496093e-05, + "loss": 3.6265, + "step": 747008 + }, + { + "epoch": 0.02, + "learning_rate": 3.776152854858248e-05, + "loss": 3.6412, + "step": 747520 + }, + { + "epoch": 0.02, + "learning_rate": 3.775314260107196e-05, + "loss": 3.6397, + "step": 748032 + }, + { + "epoch": 0.02, + "learning_rate": 3.7744756653561445e-05, + "loss": 3.6333, + "step": 748544 + }, + { + "epoch": 0.02, + "learning_rate": 3.7736370706050925e-05, + "loss": 3.6185, + "step": 749056 + }, + { + "epoch": 0.02, + "learning_rate": 3.7728001137344134e-05, + "loss": 3.6341, + "step": 749568 + }, + { + "epoch": 0.02, + "learning_rate": 3.7719615189833614e-05, + "loss": 3.6313, + "step": 750080 + }, + { + "epoch": 0.02, + "learning_rate": 3.7711229242323094e-05, + "loss": 3.6352, + "step": 750592 + }, + { + "epoch": 0.02, + "learning_rate": 3.7702843294812574e-05, + "loss": 3.6336, + "step": 751104 + }, + { + "epoch": 0.02, + "learning_rate": 3.7694457347302054e-05, + "loss": 3.6404, + "step": 751616 + }, + { + "epoch": 0.02, + "learning_rate": 3.768608777859526e-05, + "loss": 3.6264, + "step": 752128 + }, + { + "epoch": 0.02, + "learning_rate": 3.767770183108474e-05, + "loss": 3.6469, + "step": 752640 + }, + { + "epoch": 0.02, + "learning_rate": 3.766931588357422e-05, + "loss": 3.6256, + "step": 753152 + }, + { + "epoch": 0.02, + "learning_rate": 3.76609299360637e-05, + "loss": 3.6414, + "step": 753664 + }, + { + "epoch": 0.02, + "learning_rate": 3.765256036735691e-05, + "loss": 3.6487, + "step": 754176 + }, + { + "epoch": 0.02, + "learning_rate": 3.76441744198464e-05, + "loss": 3.6347, + "step": 754688 + }, + { + "epoch": 0.02, + "learning_rate": 3.763578847233588e-05, + "loss": 3.6412, + "step": 755200 + }, + { + "epoch": 0.02, + "learning_rate": 3.762740252482536e-05, + "loss": 3.6372, + "step": 755712 + }, + { + "epoch": 0.02, + "learning_rate": 3.761903295611857e-05, + "loss": 3.6213, + "step": 756224 + }, + { + "epoch": 0.02, + "learning_rate": 3.761064700860805e-05, + "loss": 3.6304, + "step": 756736 + }, + { + "epoch": 0.02, + "learning_rate": 3.760226106109753e-05, + "loss": 3.6274, + "step": 757248 + }, + { + "epoch": 0.02, + "learning_rate": 3.759387511358701e-05, + "loss": 3.6425, + "step": 757760 + }, + { + "epoch": 0.02, + "learning_rate": 3.758548916607649e-05, + "loss": 3.638, + "step": 758272 + }, + { + "epoch": 0.02, + "learning_rate": 3.757710321856597e-05, + "loss": 3.6375, + "step": 758784 + }, + { + "epoch": 0.02, + "learning_rate": 3.7568733649859176e-05, + "loss": 3.6406, + "step": 759296 + }, + { + "epoch": 0.02, + "learning_rate": 3.7560347702348656e-05, + "loss": 3.6317, + "step": 759808 + }, + { + "epoch": 0.02, + "learning_rate": 3.7551961754838136e-05, + "loss": 3.6212, + "step": 760320 + }, + { + "epoch": 0.02, + "learning_rate": 3.7543575807327616e-05, + "loss": 3.6319, + "step": 760832 + }, + { + "epoch": 0.02, + "learning_rate": 3.7535189859817096e-05, + "loss": 3.6441, + "step": 761344 + }, + { + "epoch": 0.02, + "learning_rate": 3.7526803912306576e-05, + "loss": 3.6409, + "step": 761856 + }, + { + "epoch": 0.02, + "learning_rate": 3.7518417964796056e-05, + "loss": 3.6242, + "step": 762368 + }, + { + "epoch": 0.02, + "learning_rate": 3.751004839608927e-05, + "loss": 3.6291, + "step": 762880 + }, + { + "epoch": 0.03, + "eval_loss": 3.8420088291168213, + "eval_runtime": 320.9317, + "eval_samples_per_second": 1189.01, + "eval_steps_per_second": 37.157, + "step": 763190 + }, + { + "epoch": 1.0, + "learning_rate": 3.750169520618621e-05, + "loss": 3.647, + "step": 763392 + }, + { + "epoch": 1.0, + "learning_rate": 3.749330925867569e-05, + "loss": 3.6286, + "step": 763904 + }, + { + "epoch": 1.0, + "learning_rate": 3.748492331116517e-05, + "loss": 3.6318, + "step": 764416 + }, + { + "epoch": 1.0, + "learning_rate": 3.747653736365465e-05, + "loss": 3.6288, + "step": 764928 + }, + { + "epoch": 1.0, + "learning_rate": 3.746815141614413e-05, + "loss": 3.6307, + "step": 765440 + }, + { + "epoch": 1.0, + "learning_rate": 3.745976546863361e-05, + "loss": 3.6182, + "step": 765952 + }, + { + "epoch": 1.0, + "learning_rate": 3.745137952112309e-05, + "loss": 3.6235, + "step": 766464 + }, + { + "epoch": 1.0, + "learning_rate": 3.744299357361257e-05, + "loss": 3.6168, + "step": 766976 + }, + { + "epoch": 1.0, + "learning_rate": 3.743460762610205e-05, + "loss": 3.6265, + "step": 767488 + }, + { + "epoch": 1.0, + "learning_rate": 3.7426238057395266e-05, + "loss": 3.6335, + "step": 768000 + }, + { + "epoch": 1.0, + "learning_rate": 3.7417852109884746e-05, + "loss": 3.6302, + "step": 768512 + }, + { + "epoch": 1.0, + "learning_rate": 3.740946616237422e-05, + "loss": 3.6247, + "step": 769024 + }, + { + "epoch": 1.0, + "learning_rate": 3.74010802148637e-05, + "loss": 3.635, + "step": 769536 + }, + { + "epoch": 1.0, + "learning_rate": 3.7392710646156915e-05, + "loss": 3.6246, + "step": 770048 + }, + { + "epoch": 1.0, + "learning_rate": 3.7384324698646395e-05, + "loss": 3.633, + "step": 770560 + }, + { + "epoch": 1.0, + "learning_rate": 3.737593875113587e-05, + "loss": 3.612, + "step": 771072 + }, + { + "epoch": 1.0, + "learning_rate": 3.736755280362535e-05, + "loss": 3.6151, + "step": 771584 + }, + { + "epoch": 1.0, + "learning_rate": 3.735916685611483e-05, + "loss": 3.636, + "step": 772096 + }, + { + "epoch": 1.0, + "learning_rate": 3.735078090860431e-05, + "loss": 3.6259, + "step": 772608 + }, + { + "epoch": 1.0, + "learning_rate": 3.7342411339897524e-05, + "loss": 3.6383, + "step": 773120 + }, + { + "epoch": 1.0, + "learning_rate": 3.7334025392387004e-05, + "loss": 3.619, + "step": 773632 + }, + { + "epoch": 1.0, + "learning_rate": 3.7325639444876483e-05, + "loss": 3.6388, + "step": 774144 + }, + { + "epoch": 1.0, + "learning_rate": 3.7317253497365963e-05, + "loss": 3.6266, + "step": 774656 + }, + { + "epoch": 1.0, + "learning_rate": 3.730888392865917e-05, + "loss": 3.623, + "step": 775168 + }, + { + "epoch": 1.0, + "learning_rate": 3.730049798114865e-05, + "loss": 3.6276, + "step": 775680 + }, + { + "epoch": 1.0, + "learning_rate": 3.729211203363813e-05, + "loss": 3.6243, + "step": 776192 + }, + { + "epoch": 1.0, + "learning_rate": 3.728372608612761e-05, + "loss": 3.6316, + "step": 776704 + }, + { + "epoch": 1.0, + "learning_rate": 3.727534013861709e-05, + "loss": 3.6204, + "step": 777216 + }, + { + "epoch": 1.0, + "learning_rate": 3.726695419110657e-05, + "loss": 3.6292, + "step": 777728 + }, + { + "epoch": 1.0, + "learning_rate": 3.725856824359605e-05, + "loss": 3.6273, + "step": 778240 + }, + { + "epoch": 1.01, + "learning_rate": 3.725018229608553e-05, + "loss": 3.6066, + "step": 778752 + }, + { + "epoch": 1.01, + "learning_rate": 3.724182910618248e-05, + "loss": 3.6287, + "step": 779264 + }, + { + "epoch": 1.01, + "learning_rate": 3.723344315867196e-05, + "loss": 3.6305, + "step": 779776 + }, + { + "epoch": 1.01, + "learning_rate": 3.722505721116144e-05, + "loss": 3.6274, + "step": 780288 + }, + { + "epoch": 1.01, + "learning_rate": 3.721667126365092e-05, + "loss": 3.6251, + "step": 780800 + }, + { + "epoch": 1.01, + "learning_rate": 3.72082853161404e-05, + "loss": 3.6263, + "step": 781312 + }, + { + "epoch": 1.01, + "learning_rate": 3.7199915747433606e-05, + "loss": 3.6248, + "step": 781824 + }, + { + "epoch": 1.01, + "learning_rate": 3.7191529799923086e-05, + "loss": 3.6292, + "step": 782336 + }, + { + "epoch": 1.01, + "learning_rate": 3.7183143852412566e-05, + "loss": 3.6343, + "step": 782848 + }, + { + "epoch": 1.01, + "learning_rate": 3.7174757904902046e-05, + "loss": 3.6122, + "step": 783360 + }, + { + "epoch": 1.01, + "learning_rate": 3.7166388336195255e-05, + "loss": 3.6199, + "step": 783872 + }, + { + "epoch": 1.01, + "learning_rate": 3.7158002388684735e-05, + "loss": 3.6126, + "step": 784384 + }, + { + "epoch": 1.01, + "learning_rate": 3.7149616441174215e-05, + "loss": 3.6235, + "step": 784896 + }, + { + "epoch": 1.01, + "learning_rate": 3.7141230493663695e-05, + "loss": 3.6276, + "step": 785408 + }, + { + "epoch": 1.01, + "learning_rate": 3.713286092495691e-05, + "loss": 3.6158, + "step": 785920 + }, + { + "epoch": 1.01, + "learning_rate": 3.712447497744639e-05, + "loss": 3.6343, + "step": 786432 + }, + { + "epoch": 1.01, + "learning_rate": 3.711608902993587e-05, + "loss": 3.6195, + "step": 786944 + }, + { + "epoch": 1.01, + "learning_rate": 3.710770308242535e-05, + "loss": 3.6321, + "step": 787456 + }, + { + "epoch": 1.01, + "learning_rate": 3.709931713491483e-05, + "loss": 3.6225, + "step": 787968 + }, + { + "epoch": 1.01, + "learning_rate": 3.709094756620804e-05, + "loss": 3.6064, + "step": 788480 + }, + { + "epoch": 1.01, + "learning_rate": 3.708256161869752e-05, + "loss": 3.6192, + "step": 788992 + }, + { + "epoch": 1.01, + "learning_rate": 3.7074175671187e-05, + "loss": 3.6103, + "step": 789504 + }, + { + "epoch": 1.01, + "learning_rate": 3.706578972367648e-05, + "loss": 3.6262, + "step": 790016 + }, + { + "epoch": 1.01, + "learning_rate": 3.705740377616596e-05, + "loss": 3.6171, + "step": 790528 + }, + { + "epoch": 1.01, + "learning_rate": 3.704903420745917e-05, + "loss": 3.6179, + "step": 791040 + }, + { + "epoch": 1.01, + "learning_rate": 3.704064825994865e-05, + "loss": 3.6045, + "step": 791552 + }, + { + "epoch": 1.01, + "learning_rate": 3.703226231243813e-05, + "loss": 3.6198, + "step": 792064 + }, + { + "epoch": 1.01, + "learning_rate": 3.7023876364927615e-05, + "loss": 3.6081, + "step": 792576 + }, + { + "epoch": 1.01, + "learning_rate": 3.7015506796220824e-05, + "loss": 3.6231, + "step": 793088 + }, + { + "epoch": 1.01, + "learning_rate": 3.7007120848710304e-05, + "loss": 3.615, + "step": 793600 + }, + { + "epoch": 1.01, + "learning_rate": 3.6998734901199784e-05, + "loss": 3.613, + "step": 794112 + }, + { + "epoch": 1.01, + "learning_rate": 3.6990348953689264e-05, + "loss": 3.6178, + "step": 794624 + }, + { + "epoch": 1.01, + "learning_rate": 3.6981963006178744e-05, + "loss": 3.6033, + "step": 795136 + }, + { + "epoch": 1.01, + "learning_rate": 3.697359343747195e-05, + "loss": 3.6227, + "step": 795648 + }, + { + "epoch": 1.01, + "learning_rate": 3.696520748996143e-05, + "loss": 3.6162, + "step": 796160 + }, + { + "epoch": 1.01, + "learning_rate": 3.695682154245091e-05, + "loss": 3.6223, + "step": 796672 + }, + { + "epoch": 1.01, + "learning_rate": 3.694843559494039e-05, + "loss": 3.6112, + "step": 797184 + }, + { + "epoch": 1.01, + "learning_rate": 3.694004964742987e-05, + "loss": 3.6066, + "step": 797696 + }, + { + "epoch": 1.01, + "learning_rate": 3.693166369991935e-05, + "loss": 3.6074, + "step": 798208 + }, + { + "epoch": 1.01, + "learning_rate": 3.692327775240883e-05, + "loss": 3.614, + "step": 798720 + }, + { + "epoch": 1.01, + "learning_rate": 3.691489180489831e-05, + "loss": 3.6115, + "step": 799232 + }, + { + "epoch": 1.01, + "learning_rate": 3.690652223619153e-05, + "loss": 3.6173, + "step": 799744 + }, + { + "epoch": 1.01, + "learning_rate": 3.689815266748474e-05, + "loss": 3.6164, + "step": 800256 + }, + { + "epoch": 1.01, + "learning_rate": 3.688976671997422e-05, + "loss": 3.6352, + "step": 800768 + }, + { + "epoch": 1.01, + "learning_rate": 3.68813807724637e-05, + "loss": 3.6278, + "step": 801280 + }, + { + "epoch": 1.01, + "learning_rate": 3.687299482495317e-05, + "loss": 3.6188, + "step": 801792 + }, + { + "epoch": 1.01, + "learning_rate": 3.686462525624639e-05, + "loss": 3.6195, + "step": 802304 + }, + { + "epoch": 1.01, + "learning_rate": 3.685623930873587e-05, + "loss": 3.6097, + "step": 802816 + }, + { + "epoch": 1.01, + "learning_rate": 3.684785336122535e-05, + "loss": 3.6144, + "step": 803328 + }, + { + "epoch": 1.01, + "learning_rate": 3.683946741371482e-05, + "loss": 3.6179, + "step": 803840 + }, + { + "epoch": 1.01, + "learning_rate": 3.6831097845008036e-05, + "loss": 3.6261, + "step": 804352 + }, + { + "epoch": 1.01, + "learning_rate": 3.682271189749752e-05, + "loss": 3.6199, + "step": 804864 + }, + { + "epoch": 1.01, + "learning_rate": 3.6814325949987e-05, + "loss": 3.6046, + "step": 805376 + }, + { + "epoch": 1.01, + "learning_rate": 3.6805940002476476e-05, + "loss": 3.6148, + "step": 805888 + }, + { + "epoch": 1.01, + "learning_rate": 3.679757043376969e-05, + "loss": 3.5996, + "step": 806400 + }, + { + "epoch": 1.01, + "learning_rate": 3.678918448625917e-05, + "loss": 3.6147, + "step": 806912 + }, + { + "epoch": 1.01, + "learning_rate": 3.6780798538748645e-05, + "loss": 3.6099, + "step": 807424 + }, + { + "epoch": 1.01, + "learning_rate": 3.6772412591238125e-05, + "loss": 3.616, + "step": 807936 + }, + { + "epoch": 1.01, + "learning_rate": 3.6764026643727605e-05, + "loss": 3.627, + "step": 808448 + }, + { + "epoch": 1.01, + "learning_rate": 3.675565707502082e-05, + "loss": 3.6196, + "step": 808960 + }, + { + "epoch": 1.02, + "learning_rate": 3.6747271127510294e-05, + "loss": 3.6094, + "step": 809472 + }, + { + "epoch": 1.02, + "learning_rate": 3.6738885179999774e-05, + "loss": 3.6128, + "step": 809984 + }, + { + "epoch": 1.02, + "learning_rate": 3.673049923248926e-05, + "loss": 3.6152, + "step": 810496 + }, + { + "epoch": 1.02, + "learning_rate": 3.672211328497874e-05, + "loss": 3.6087, + "step": 811008 + }, + { + "epoch": 1.02, + "learning_rate": 3.671372733746822e-05, + "loss": 3.6083, + "step": 811520 + }, + { + "epoch": 1.02, + "learning_rate": 3.67053413899577e-05, + "loss": 3.6168, + "step": 812032 + }, + { + "epoch": 1.02, + "learning_rate": 3.669697182125091e-05, + "loss": 3.6253, + "step": 812544 + }, + { + "epoch": 1.02, + "learning_rate": 3.668858587374039e-05, + "loss": 3.6294, + "step": 813056 + }, + { + "epoch": 1.02, + "learning_rate": 3.668019992622987e-05, + "loss": 3.6124, + "step": 813568 + }, + { + "epoch": 1.02, + "learning_rate": 3.667181397871935e-05, + "loss": 3.6189, + "step": 814080 + }, + { + "epoch": 1.02, + "learning_rate": 3.666342803120883e-05, + "loss": 3.6112, + "step": 814592 + }, + { + "epoch": 1.02, + "learning_rate": 3.665504208369831e-05, + "loss": 3.6186, + "step": 815104 + }, + { + "epoch": 1.02, + "learning_rate": 3.664665613618779e-05, + "loss": 3.6124, + "step": 815616 + }, + { + "epoch": 1.02, + "learning_rate": 3.6638286567481e-05, + "loss": 3.6288, + "step": 816128 + }, + { + "epoch": 1.02, + "learning_rate": 3.662990061997048e-05, + "loss": 3.6194, + "step": 816640 + }, + { + "epoch": 1.02, + "learning_rate": 3.662151467245996e-05, + "loss": 3.6015, + "step": 817152 + }, + { + "epoch": 1.02, + "learning_rate": 3.661312872494944e-05, + "loss": 3.6075, + "step": 817664 + }, + { + "epoch": 1.02, + "learning_rate": 3.6604742777438925e-05, + "loss": 3.6053, + "step": 818176 + }, + { + "epoch": 1.02, + "learning_rate": 3.6596373208732134e-05, + "loss": 3.6082, + "step": 818688 + }, + { + "epoch": 1.02, + "learning_rate": 3.6587987261221614e-05, + "loss": 3.6125, + "step": 819200 + }, + { + "epoch": 1.02, + "learning_rate": 3.6579601313711094e-05, + "loss": 3.6223, + "step": 819712 + }, + { + "epoch": 1.02, + "learning_rate": 3.6571215366200574e-05, + "loss": 3.5951, + "step": 820224 + }, + { + "epoch": 1.02, + "learning_rate": 3.656284579749378e-05, + "loss": 3.6101, + "step": 820736 + }, + { + "epoch": 1.02, + "learning_rate": 3.655445984998326e-05, + "loss": 3.6225, + "step": 821248 + }, + { + "epoch": 1.02, + "learning_rate": 3.654607390247274e-05, + "loss": 3.6197, + "step": 821760 + }, + { + "epoch": 1.02, + "learning_rate": 3.653768795496222e-05, + "loss": 3.6214, + "step": 822272 + }, + { + "epoch": 1.02, + "learning_rate": 3.65293020074517e-05, + "loss": 3.6178, + "step": 822784 + }, + { + "epoch": 1.02, + "learning_rate": 3.652093243874491e-05, + "loss": 3.5996, + "step": 823296 + }, + { + "epoch": 1.02, + "learning_rate": 3.651254649123439e-05, + "loss": 3.6194, + "step": 823808 + }, + { + "epoch": 1.02, + "learning_rate": 3.650416054372388e-05, + "loss": 3.6212, + "step": 824320 + }, + { + "epoch": 1.02, + "learning_rate": 3.649577459621336e-05, + "loss": 3.6105, + "step": 824832 + }, + { + "epoch": 1.02, + "learning_rate": 3.648738864870284e-05, + "loss": 3.5987, + "step": 825344 + }, + { + "epoch": 1.02, + "learning_rate": 3.647901907999605e-05, + "loss": 3.6101, + "step": 825856 + }, + { + "epoch": 1.02, + "learning_rate": 3.647063313248553e-05, + "loss": 3.6111, + "step": 826368 + }, + { + "epoch": 1.02, + "learning_rate": 3.646224718497501e-05, + "loss": 3.6164, + "step": 826880 + }, + { + "epoch": 1.02, + "learning_rate": 3.645386123746448e-05, + "loss": 3.611, + "step": 827392 + }, + { + "epoch": 1.02, + "learning_rate": 3.644547528995396e-05, + "loss": 3.6199, + "step": 827904 + }, + { + "epoch": 1.02, + "learning_rate": 3.6437105721247176e-05, + "loss": 3.6029, + "step": 828416 + }, + { + "epoch": 1.02, + "learning_rate": 3.6428719773736656e-05, + "loss": 3.622, + "step": 828928 + }, + { + "epoch": 1.02, + "learning_rate": 3.642033382622613e-05, + "loss": 3.6067, + "step": 829440 + }, + { + "epoch": 1.02, + "learning_rate": 3.6411947878715616e-05, + "loss": 3.6195, + "step": 829952 + }, + { + "epoch": 1.02, + "learning_rate": 3.640357831000883e-05, + "loss": 3.6323, + "step": 830464 + }, + { + "epoch": 1.02, + "learning_rate": 3.6395192362498305e-05, + "loss": 3.6108, + "step": 830976 + }, + { + "epoch": 1.02, + "learning_rate": 3.6386806414987785e-05, + "loss": 3.6165, + "step": 831488 + }, + { + "epoch": 1.02, + "learning_rate": 3.6378420467477265e-05, + "loss": 3.6181, + "step": 832000 + }, + { + "epoch": 1.02, + "learning_rate": 3.637005089877048e-05, + "loss": 3.6021, + "step": 832512 + }, + { + "epoch": 1.02, + "learning_rate": 3.6361664951259954e-05, + "loss": 3.6064, + "step": 833024 + }, + { + "epoch": 1.02, + "learning_rate": 3.6353279003749434e-05, + "loss": 3.61, + "step": 833536 + }, + { + "epoch": 1.02, + "learning_rate": 3.6344893056238914e-05, + "loss": 3.6187, + "step": 834048 + }, + { + "epoch": 1.02, + "learning_rate": 3.6336507108728394e-05, + "loss": 3.6163, + "step": 834560 + }, + { + "epoch": 1.02, + "learning_rate": 3.63281375400216e-05, + "loss": 3.617, + "step": 835072 + }, + { + "epoch": 1.02, + "learning_rate": 3.631975159251108e-05, + "loss": 3.6189, + "step": 835584 + }, + { + "epoch": 1.02, + "learning_rate": 3.631136564500057e-05, + "loss": 3.6105, + "step": 836096 + }, + { + "epoch": 1.02, + "learning_rate": 3.630297969749005e-05, + "loss": 3.6029, + "step": 836608 + }, + { + "epoch": 1.02, + "learning_rate": 3.629459374997953e-05, + "loss": 3.6116, + "step": 837120 + }, + { + "epoch": 1.02, + "learning_rate": 3.628620780246901e-05, + "loss": 3.6222, + "step": 837632 + }, + { + "epoch": 1.02, + "learning_rate": 3.627782185495849e-05, + "loss": 3.6207, + "step": 838144 + }, + { + "epoch": 1.02, + "learning_rate": 3.626943590744797e-05, + "loss": 3.6047, + "step": 838656 + }, + { + "epoch": 1.02, + "learning_rate": 3.626106633874118e-05, + "loss": 3.6101, + "step": 839168 + }, + { + "epoch": 1.03, + "eval_loss": 3.8408679962158203, + "eval_runtime": 316.2085, + "eval_samples_per_second": 1206.77, + "eval_steps_per_second": 37.712, + "step": 839509 + }, + { + "epoch": 0.0, + "learning_rate": 3.625269677003439e-05, + "loss": 3.5989, + "step": 839680 + }, + { + "epoch": 0.0, + "learning_rate": 3.624431082252387e-05, + "loss": 3.6106, + "step": 840192 + }, + { + "epoch": 0.0, + "learning_rate": 3.623592487501335e-05, + "loss": 3.6132, + "step": 840704 + }, + { + "epoch": 0.0, + "learning_rate": 3.622753892750283e-05, + "loss": 3.6167, + "step": 841216 + }, + { + "epoch": 0.0, + "learning_rate": 3.621916935879604e-05, + "loss": 3.6265, + "step": 841728 + }, + { + "epoch": 0.0, + "learning_rate": 3.6210783411285524e-05, + "loss": 3.6098, + "step": 842240 + }, + { + "epoch": 0.0, + "learning_rate": 3.6202397463775004e-05, + "loss": 3.6159, + "step": 842752 + }, + { + "epoch": 0.0, + "learning_rate": 3.6194011516264484e-05, + "loss": 3.6139, + "step": 843264 + }, + { + "epoch": 0.0, + "learning_rate": 3.6185625568753964e-05, + "loss": 3.6058, + "step": 843776 + }, + { + "epoch": 0.0, + "learning_rate": 3.617725600004717e-05, + "loss": 3.6059, + "step": 844288 + }, + { + "epoch": 0.0, + "learning_rate": 3.616887005253665e-05, + "loss": 3.6184, + "step": 844800 + }, + { + "epoch": 0.0, + "learning_rate": 3.616048410502613e-05, + "loss": 3.6248, + "step": 845312 + }, + { + "epoch": 0.0, + "learning_rate": 3.615211453631934e-05, + "loss": 3.6171, + "step": 845824 + }, + { + "epoch": 0.0, + "learning_rate": 3.614372858880882e-05, + "loss": 3.5941, + "step": 846336 + }, + { + "epoch": 0.0, + "learning_rate": 3.61353426412983e-05, + "loss": 3.6152, + "step": 846848 + }, + { + "epoch": 0.0, + "learning_rate": 3.612695669378778e-05, + "loss": 3.6002, + "step": 847360 + }, + { + "epoch": 0.0, + "learning_rate": 3.611857074627726e-05, + "loss": 3.61, + "step": 847872 + }, + { + "epoch": 0.0, + "learning_rate": 3.611018479876674e-05, + "loss": 3.6086, + "step": 848384 + }, + { + "epoch": 0.0, + "learning_rate": 3.610179885125622e-05, + "loss": 3.6089, + "step": 848896 + }, + { + "epoch": 0.0, + "learning_rate": 3.609341290374571e-05, + "loss": 3.6174, + "step": 849408 + }, + { + "epoch": 0.0, + "learning_rate": 3.608502695623519e-05, + "loss": 3.6222, + "step": 849920 + }, + { + "epoch": 0.0, + "learning_rate": 3.60766573875284e-05, + "loss": 3.6138, + "step": 850432 + }, + { + "epoch": 0.0, + "learning_rate": 3.606827144001788e-05, + "loss": 3.6099, + "step": 850944 + }, + { + "epoch": 0.0, + "learning_rate": 3.605988549250736e-05, + "loss": 3.6004, + "step": 851456 + }, + { + "epoch": 0.0, + "learning_rate": 3.605149954499684e-05, + "loss": 3.6172, + "step": 851968 + }, + { + "epoch": 0.0, + "learning_rate": 3.604311359748632e-05, + "loss": 3.615, + "step": 852480 + }, + { + "epoch": 0.0, + "learning_rate": 3.6034744028779526e-05, + "loss": 3.6058, + "step": 852992 + }, + { + "epoch": 0.0, + "learning_rate": 3.6026358081269006e-05, + "loss": 3.6085, + "step": 853504 + }, + { + "epoch": 0.0, + "learning_rate": 3.6017972133758486e-05, + "loss": 3.6038, + "step": 854016 + }, + { + "epoch": 0.0, + "learning_rate": 3.6009586186247966e-05, + "loss": 3.6117, + "step": 854528 + }, + { + "epoch": 0.01, + "learning_rate": 3.6001216617541175e-05, + "loss": 3.6015, + "step": 855040 + }, + { + "epoch": 0.01, + "learning_rate": 3.5992830670030655e-05, + "loss": 3.6122, + "step": 855552 + }, + { + "epoch": 0.01, + "learning_rate": 3.598444472252014e-05, + "loss": 3.6169, + "step": 856064 + }, + { + "epoch": 0.01, + "learning_rate": 3.5976058775009615e-05, + "loss": 3.6151, + "step": 856576 + }, + { + "epoch": 0.01, + "learning_rate": 3.596768920630283e-05, + "loss": 3.6105, + "step": 857088 + }, + { + "epoch": 0.01, + "learning_rate": 3.595930325879231e-05, + "loss": 3.6065, + "step": 857600 + }, + { + "epoch": 0.01, + "learning_rate": 3.595091731128179e-05, + "loss": 3.6162, + "step": 858112 + }, + { + "epoch": 0.01, + "learning_rate": 3.5942531363771264e-05, + "loss": 3.606, + "step": 858624 + }, + { + "epoch": 0.01, + "learning_rate": 3.5934145416260744e-05, + "loss": 3.6008, + "step": 859136 + }, + { + "epoch": 0.01, + "learning_rate": 3.5925759468750224e-05, + "loss": 3.6061, + "step": 859648 + }, + { + "epoch": 0.01, + "learning_rate": 3.591738990004344e-05, + "loss": 3.5978, + "step": 860160 + }, + { + "epoch": 0.01, + "learning_rate": 3.590900395253291e-05, + "loss": 3.6054, + "step": 860672 + }, + { + "epoch": 0.01, + "learning_rate": 3.590061800502239e-05, + "loss": 3.6028, + "step": 861184 + }, + { + "epoch": 0.01, + "learning_rate": 3.589223205751188e-05, + "loss": 3.6093, + "step": 861696 + }, + { + "epoch": 0.01, + "learning_rate": 3.588384611000136e-05, + "loss": 3.6114, + "step": 862208 + }, + { + "epoch": 0.01, + "learning_rate": 3.587546016249084e-05, + "loss": 3.6147, + "step": 862720 + }, + { + "epoch": 0.01, + "learning_rate": 3.586707421498032e-05, + "loss": 3.6131, + "step": 863232 + }, + { + "epoch": 0.01, + "learning_rate": 3.58586882674698e-05, + "loss": 3.6078, + "step": 863744 + }, + { + "epoch": 0.01, + "learning_rate": 3.585031869876301e-05, + "loss": 3.5855, + "step": 864256 + }, + { + "epoch": 0.01, + "learning_rate": 3.584193275125249e-05, + "loss": 3.6147, + "step": 864768 + }, + { + "epoch": 0.01, + "learning_rate": 3.583354680374197e-05, + "loss": 3.5993, + "step": 865280 + }, + { + "epoch": 0.01, + "learning_rate": 3.582516085623145e-05, + "loss": 3.6066, + "step": 865792 + }, + { + "epoch": 0.01, + "learning_rate": 3.581677490872093e-05, + "loss": 3.612, + "step": 866304 + }, + { + "epoch": 0.01, + "learning_rate": 3.580840534001414e-05, + "loss": 3.6041, + "step": 866816 + }, + { + "epoch": 0.01, + "learning_rate": 3.580001939250362e-05, + "loss": 3.5886, + "step": 867328 + }, + { + "epoch": 0.01, + "learning_rate": 3.57916334449931e-05, + "loss": 3.5954, + "step": 867840 + }, + { + "epoch": 0.01, + "learning_rate": 3.578324749748258e-05, + "loss": 3.6045, + "step": 868352 + }, + { + "epoch": 0.01, + "learning_rate": 3.577487792877579e-05, + "loss": 3.5977, + "step": 868864 + }, + { + "epoch": 0.01, + "learning_rate": 3.576649198126527e-05, + "loss": 3.6136, + "step": 869376 + }, + { + "epoch": 0.01, + "learning_rate": 3.575810603375475e-05, + "loss": 3.6014, + "step": 869888 + }, + { + "epoch": 0.01, + "learning_rate": 3.574972008624423e-05, + "loss": 3.5911, + "step": 870400 + }, + { + "epoch": 0.01, + "learning_rate": 3.574133413873371e-05, + "loss": 3.6209, + "step": 870912 + }, + { + "epoch": 0.01, + "learning_rate": 3.573294819122319e-05, + "loss": 3.597, + "step": 871424 + }, + { + "epoch": 0.01, + "learning_rate": 3.57245786225164e-05, + "loss": 3.5894, + "step": 871936 + }, + { + "epoch": 0.01, + "learning_rate": 3.571619267500588e-05, + "loss": 3.6032, + "step": 872448 + }, + { + "epoch": 0.01, + "learning_rate": 3.570780672749536e-05, + "loss": 3.5989, + "step": 872960 + }, + { + "epoch": 0.01, + "learning_rate": 3.569942077998484e-05, + "loss": 3.5932, + "step": 873472 + }, + { + "epoch": 0.01, + "learning_rate": 3.569105121127805e-05, + "loss": 3.6007, + "step": 873984 + }, + { + "epoch": 0.01, + "learning_rate": 3.568266526376753e-05, + "loss": 3.5841, + "step": 874496 + }, + { + "epoch": 0.01, + "learning_rate": 3.567427931625702e-05, + "loss": 3.5969, + "step": 875008 + }, + { + "epoch": 0.01, + "learning_rate": 3.56658933687465e-05, + "loss": 3.6098, + "step": 875520 + }, + { + "epoch": 0.01, + "learning_rate": 3.565752380003971e-05, + "loss": 3.6014, + "step": 876032 + }, + { + "epoch": 0.01, + "learning_rate": 3.564913785252919e-05, + "loss": 3.608, + "step": 876544 + }, + { + "epoch": 0.01, + "learning_rate": 3.5640751905018667e-05, + "loss": 3.6007, + "step": 877056 + }, + { + "epoch": 0.01, + "learning_rate": 3.5632365957508147e-05, + "loss": 3.6189, + "step": 877568 + }, + { + "epoch": 0.01, + "learning_rate": 3.5623996388801356e-05, + "loss": 3.5944, + "step": 878080 + }, + { + "epoch": 0.01, + "learning_rate": 3.5615610441290836e-05, + "loss": 3.6111, + "step": 878592 + }, + { + "epoch": 0.01, + "learning_rate": 3.5607224493780316e-05, + "loss": 3.6021, + "step": 879104 + }, + { + "epoch": 0.01, + "learning_rate": 3.5598838546269796e-05, + "loss": 3.5888, + "step": 879616 + }, + { + "epoch": 0.01, + "learning_rate": 3.559045259875927e-05, + "loss": 3.61, + "step": 880128 + }, + { + "epoch": 0.01, + "learning_rate": 3.5582083030052485e-05, + "loss": 3.6105, + "step": 880640 + }, + { + "epoch": 0.01, + "learning_rate": 3.557369708254197e-05, + "loss": 3.6055, + "step": 881152 + }, + { + "epoch": 0.01, + "learning_rate": 3.556531113503145e-05, + "loss": 3.609, + "step": 881664 + }, + { + "epoch": 0.01, + "learning_rate": 3.5556925187520924e-05, + "loss": 3.5871, + "step": 882176 + }, + { + "epoch": 0.01, + "learning_rate": 3.5548539240010404e-05, + "loss": 3.5854, + "step": 882688 + }, + { + "epoch": 0.01, + "learning_rate": 3.554016967130362e-05, + "loss": 3.6004, + "step": 883200 + }, + { + "epoch": 0.01, + "learning_rate": 3.55317837237931e-05, + "loss": 3.6068, + "step": 883712 + }, + { + "epoch": 0.01, + "learning_rate": 3.5523397776282573e-05, + "loss": 3.5953, + "step": 884224 + }, + { + "epoch": 0.01, + "learning_rate": 3.551501182877205e-05, + "loss": 3.592, + "step": 884736 + }, + { + "epoch": 0.01, + "learning_rate": 3.550664226006527e-05, + "loss": 3.6005, + "step": 885248 + }, + { + "epoch": 0.02, + "learning_rate": 3.549825631255474e-05, + "loss": 3.6013, + "step": 885760 + }, + { + "epoch": 0.02, + "learning_rate": 3.548987036504422e-05, + "loss": 3.5962, + "step": 886272 + }, + { + "epoch": 0.02, + "learning_rate": 3.548148441753371e-05, + "loss": 3.596, + "step": 886784 + }, + { + "epoch": 0.02, + "learning_rate": 3.547309847002319e-05, + "loss": 3.6082, + "step": 887296 + }, + { + "epoch": 0.02, + "learning_rate": 3.54647289013164e-05, + "loss": 3.6196, + "step": 887808 + }, + { + "epoch": 0.02, + "learning_rate": 3.545634295380588e-05, + "loss": 3.607, + "step": 888320 + }, + { + "epoch": 0.02, + "learning_rate": 3.544795700629536e-05, + "loss": 3.593, + "step": 888832 + }, + { + "epoch": 0.02, + "learning_rate": 3.543957105878484e-05, + "loss": 3.5948, + "step": 889344 + }, + { + "epoch": 0.02, + "learning_rate": 3.543120149007805e-05, + "loss": 3.5985, + "step": 889856 + }, + { + "epoch": 0.02, + "learning_rate": 3.542281554256753e-05, + "loss": 3.6096, + "step": 890368 + }, + { + "epoch": 0.02, + "learning_rate": 3.541442959505701e-05, + "loss": 3.5998, + "step": 890880 + }, + { + "epoch": 0.02, + "learning_rate": 3.540604364754649e-05, + "loss": 3.5989, + "step": 891392 + }, + { + "epoch": 0.02, + "learning_rate": 3.5397674078839696e-05, + "loss": 3.5951, + "step": 891904 + }, + { + "epoch": 0.02, + "learning_rate": 3.5389288131329176e-05, + "loss": 3.6059, + "step": 892416 + }, + { + "epoch": 0.02, + "learning_rate": 3.538090218381866e-05, + "loss": 3.6027, + "step": 892928 + }, + { + "epoch": 0.02, + "learning_rate": 3.537251623630814e-05, + "loss": 3.5961, + "step": 893440 + }, + { + "epoch": 0.02, + "learning_rate": 3.536414666760135e-05, + "loss": 3.5907, + "step": 893952 + }, + { + "epoch": 0.02, + "learning_rate": 3.535576072009083e-05, + "loss": 3.5925, + "step": 894464 + }, + { + "epoch": 0.02, + "learning_rate": 3.534737477258031e-05, + "loss": 3.5971, + "step": 894976 + }, + { + "epoch": 0.02, + "learning_rate": 3.533898882506979e-05, + "loss": 3.591, + "step": 895488 + }, + { + "epoch": 0.02, + "learning_rate": 3.5330619256363e-05, + "loss": 3.5973, + "step": 896000 + }, + { + "epoch": 0.02, + "learning_rate": 3.532223330885248e-05, + "loss": 3.592, + "step": 896512 + }, + { + "epoch": 0.02, + "learning_rate": 3.531384736134196e-05, + "loss": 3.601, + "step": 897024 + }, + { + "epoch": 0.02, + "learning_rate": 3.530546141383144e-05, + "loss": 3.5924, + "step": 897536 + }, + { + "epoch": 0.02, + "learning_rate": 3.529707546632092e-05, + "loss": 3.6077, + "step": 898048 + }, + { + "epoch": 0.02, + "learning_rate": 3.528870589761413e-05, + "loss": 3.6098, + "step": 898560 + }, + { + "epoch": 0.02, + "learning_rate": 3.528031995010361e-05, + "loss": 3.5997, + "step": 899072 + }, + { + "epoch": 0.02, + "learning_rate": 3.5271934002593096e-05, + "loss": 3.6098, + "step": 899584 + }, + { + "epoch": 0.02, + "learning_rate": 3.5263548055082576e-05, + "loss": 3.5979, + "step": 900096 + }, + { + "epoch": 0.02, + "learning_rate": 3.5255178486375785e-05, + "loss": 3.5948, + "step": 900608 + }, + { + "epoch": 0.02, + "learning_rate": 3.5246792538865265e-05, + "loss": 3.5948, + "step": 901120 + }, + { + "epoch": 0.02, + "learning_rate": 3.5238406591354745e-05, + "loss": 3.5859, + "step": 901632 + }, + { + "epoch": 0.02, + "learning_rate": 3.5230020643844225e-05, + "loss": 3.5998, + "step": 902144 + }, + { + "epoch": 0.02, + "learning_rate": 3.5221634696333705e-05, + "loss": 3.5981, + "step": 902656 + }, + { + "epoch": 0.02, + "learning_rate": 3.5213248748823185e-05, + "loss": 3.6006, + "step": 903168 + }, + { + "epoch": 0.02, + "learning_rate": 3.5204879180116394e-05, + "loss": 3.5938, + "step": 903680 + }, + { + "epoch": 0.02, + "learning_rate": 3.5196493232605874e-05, + "loss": 3.6023, + "step": 904192 + }, + { + "epoch": 0.02, + "learning_rate": 3.5188107285095354e-05, + "loss": 3.5975, + "step": 904704 + }, + { + "epoch": 0.02, + "learning_rate": 3.5179721337584834e-05, + "loss": 3.5919, + "step": 905216 + }, + { + "epoch": 0.02, + "learning_rate": 3.517135176887805e-05, + "loss": 3.5988, + "step": 905728 + }, + { + "epoch": 0.02, + "learning_rate": 3.516296582136753e-05, + "loss": 3.6003, + "step": 906240 + }, + { + "epoch": 0.02, + "learning_rate": 3.515457987385701e-05, + "loss": 3.6076, + "step": 906752 + }, + { + "epoch": 0.02, + "learning_rate": 3.514619392634649e-05, + "loss": 3.5887, + "step": 907264 + }, + { + "epoch": 0.02, + "learning_rate": 3.51378243576397e-05, + "loss": 3.6103, + "step": 907776 + }, + { + "epoch": 0.02, + "learning_rate": 3.512943841012918e-05, + "loss": 3.5923, + "step": 908288 + }, + { + "epoch": 0.02, + "learning_rate": 3.512105246261866e-05, + "loss": 3.6046, + "step": 908800 + }, + { + "epoch": 0.02, + "learning_rate": 3.511266651510814e-05, + "loss": 3.6034, + "step": 909312 + }, + { + "epoch": 0.02, + "learning_rate": 3.510428056759762e-05, + "loss": 3.5942, + "step": 909824 + }, + { + "epoch": 0.02, + "learning_rate": 3.50958946200871e-05, + "loss": 3.5906, + "step": 910336 + }, + { + "epoch": 0.02, + "learning_rate": 3.508752505138031e-05, + "loss": 3.6115, + "step": 910848 + }, + { + "epoch": 0.02, + "learning_rate": 3.507913910386979e-05, + "loss": 3.5859, + "step": 911360 + }, + { + "epoch": 0.02, + "learning_rate": 3.507075315635927e-05, + "loss": 3.6024, + "step": 911872 + }, + { + "epoch": 0.02, + "learning_rate": 3.506236720884875e-05, + "loss": 3.597, + "step": 912384 + }, + { + "epoch": 0.02, + "learning_rate": 3.5053981261338234e-05, + "loss": 3.5987, + "step": 912896 + }, + { + "epoch": 0.02, + "learning_rate": 3.5045611692631444e-05, + "loss": 3.5922, + "step": 913408 + }, + { + "epoch": 0.02, + "learning_rate": 3.5037225745120924e-05, + "loss": 3.6014, + "step": 913920 + }, + { + "epoch": 0.02, + "learning_rate": 3.5028839797610403e-05, + "loss": 3.599, + "step": 914432 + }, + { + "epoch": 0.02, + "learning_rate": 3.502045385009988e-05, + "loss": 3.6099, + "step": 914944 + }, + { + "epoch": 0.02, + "learning_rate": 3.501208428139309e-05, + "loss": 3.5963, + "step": 915456 + }, + { + "epoch": 0.03, + "eval_loss": 3.8362677097320557, + "eval_runtime": 305.5683, + "eval_samples_per_second": 1248.791, + "eval_steps_per_second": 39.026, + "step": 915829 + }, + { + "epoch": 1.0, + "learning_rate": 3.500369833388257e-05, + "loss": 3.589, + "step": 915968 + }, + { + "epoch": 1.0, + "learning_rate": 3.499531238637205e-05, + "loss": 3.5888, + "step": 916480 + }, + { + "epoch": 1.0, + "learning_rate": 3.4986926438861526e-05, + "loss": 3.5935, + "step": 916992 + }, + { + "epoch": 1.0, + "learning_rate": 3.4978540491351006e-05, + "loss": 3.5988, + "step": 917504 + }, + { + "epoch": 1.0, + "learning_rate": 3.497017092264422e-05, + "loss": 3.6002, + "step": 918016 + }, + { + "epoch": 1.0, + "learning_rate": 3.49617849751337e-05, + "loss": 3.591, + "step": 918528 + }, + { + "epoch": 1.0, + "learning_rate": 3.495339902762318e-05, + "loss": 3.5984, + "step": 919040 + }, + { + "epoch": 1.0, + "learning_rate": 3.494501308011266e-05, + "loss": 3.5921, + "step": 919552 + }, + { + "epoch": 1.0, + "learning_rate": 3.493662713260214e-05, + "loss": 3.5857, + "step": 920064 + }, + { + "epoch": 1.0, + "learning_rate": 3.492825756389535e-05, + "loss": 3.5793, + "step": 920576 + }, + { + "epoch": 1.0, + "learning_rate": 3.491987161638483e-05, + "loss": 3.6034, + "step": 921088 + }, + { + "epoch": 1.0, + "learning_rate": 3.491148566887431e-05, + "loss": 3.6032, + "step": 921600 + }, + { + "epoch": 1.0, + "learning_rate": 3.4903116100167526e-05, + "loss": 3.5952, + "step": 922112 + }, + { + "epoch": 1.0, + "learning_rate": 3.4894730152657e-05, + "loss": 3.5735, + "step": 922624 + }, + { + "epoch": 1.0, + "learning_rate": 3.488634420514648e-05, + "loss": 3.5921, + "step": 923136 + }, + { + "epoch": 1.0, + "learning_rate": 3.487795825763596e-05, + "loss": 3.5789, + "step": 923648 + }, + { + "epoch": 1.0, + "learning_rate": 3.486957231012544e-05, + "loss": 3.5932, + "step": 924160 + }, + { + "epoch": 1.0, + "learning_rate": 3.4861186362614926e-05, + "loss": 3.5877, + "step": 924672 + }, + { + "epoch": 1.0, + "learning_rate": 3.4852800415104406e-05, + "loss": 3.587, + "step": 925184 + }, + { + "epoch": 1.0, + "learning_rate": 3.4844414467593886e-05, + "loss": 3.5952, + "step": 925696 + }, + { + "epoch": 1.0, + "learning_rate": 3.4836044898887095e-05, + "loss": 3.6014, + "step": 926208 + }, + { + "epoch": 1.0, + "learning_rate": 3.4827658951376575e-05, + "loss": 3.5898, + "step": 926720 + }, + { + "epoch": 1.0, + "learning_rate": 3.4819273003866055e-05, + "loss": 3.59, + "step": 927232 + }, + { + "epoch": 1.0, + "learning_rate": 3.4810887056355535e-05, + "loss": 3.5846, + "step": 927744 + }, + { + "epoch": 1.0, + "learning_rate": 3.4802517487648744e-05, + "loss": 3.5953, + "step": 928256 + }, + { + "epoch": 1.0, + "learning_rate": 3.4794131540138224e-05, + "loss": 3.5935, + "step": 928768 + }, + { + "epoch": 1.0, + "learning_rate": 3.4785745592627704e-05, + "loss": 3.5813, + "step": 929280 + }, + { + "epoch": 1.0, + "learning_rate": 3.4777359645117184e-05, + "loss": 3.5877, + "step": 929792 + }, + { + "epoch": 1.0, + "learning_rate": 3.4768973697606664e-05, + "loss": 3.5874, + "step": 930304 + }, + { + "epoch": 1.0, + "learning_rate": 3.476060412889988e-05, + "loss": 3.5874, + "step": 930816 + }, + { + "epoch": 1.01, + "learning_rate": 3.475221818138936e-05, + "loss": 3.5851, + "step": 931328 + }, + { + "epoch": 1.01, + "learning_rate": 3.474383223387884e-05, + "loss": 3.5915, + "step": 931840 + }, + { + "epoch": 1.01, + "learning_rate": 3.473544628636832e-05, + "loss": 3.5901, + "step": 932352 + }, + { + "epoch": 1.01, + "learning_rate": 3.472707671766153e-05, + "loss": 3.5998, + "step": 932864 + }, + { + "epoch": 1.01, + "learning_rate": 3.471869077015101e-05, + "loss": 3.5886, + "step": 933376 + }, + { + "epoch": 1.01, + "learning_rate": 3.471030482264049e-05, + "loss": 3.5848, + "step": 933888 + }, + { + "epoch": 1.01, + "learning_rate": 3.470191887512997e-05, + "loss": 3.5969, + "step": 934400 + }, + { + "epoch": 1.01, + "learning_rate": 3.469354930642318e-05, + "loss": 3.5807, + "step": 934912 + }, + { + "epoch": 1.01, + "learning_rate": 3.468516335891266e-05, + "loss": 3.5811, + "step": 935424 + }, + { + "epoch": 1.01, + "learning_rate": 3.467677741140214e-05, + "loss": 3.5846, + "step": 935936 + }, + { + "epoch": 1.01, + "learning_rate": 3.466839146389162e-05, + "loss": 3.5796, + "step": 936448 + }, + { + "epoch": 1.01, + "learning_rate": 3.46600055163811e-05, + "loss": 3.5838, + "step": 936960 + }, + { + "epoch": 1.01, + "learning_rate": 3.465161956887058e-05, + "loss": 3.5842, + "step": 937472 + }, + { + "epoch": 1.01, + "learning_rate": 3.464325000016379e-05, + "loss": 3.5881, + "step": 937984 + }, + { + "epoch": 1.01, + "learning_rate": 3.463486405265327e-05, + "loss": 3.5903, + "step": 938496 + }, + { + "epoch": 1.01, + "learning_rate": 3.462647810514275e-05, + "loss": 3.5947, + "step": 939008 + }, + { + "epoch": 1.01, + "learning_rate": 3.461809215763223e-05, + "loss": 3.5883, + "step": 939520 + }, + { + "epoch": 1.01, + "learning_rate": 3.460972258892544e-05, + "loss": 3.5896, + "step": 940032 + }, + { + "epoch": 1.01, + "learning_rate": 3.460133664141492e-05, + "loss": 3.5697, + "step": 940544 + }, + { + "epoch": 1.01, + "learning_rate": 3.45929506939044e-05, + "loss": 3.5933, + "step": 941056 + }, + { + "epoch": 1.01, + "learning_rate": 3.458456474639388e-05, + "loss": 3.5777, + "step": 941568 + }, + { + "epoch": 1.01, + "learning_rate": 3.457619517768709e-05, + "loss": 3.5852, + "step": 942080 + }, + { + "epoch": 1.01, + "learning_rate": 3.456780923017657e-05, + "loss": 3.5889, + "step": 942592 + }, + { + "epoch": 1.01, + "learning_rate": 3.455942328266605e-05, + "loss": 3.5834, + "step": 943104 + }, + { + "epoch": 1.01, + "learning_rate": 3.455103733515553e-05, + "loss": 3.569, + "step": 943616 + }, + { + "epoch": 1.01, + "learning_rate": 3.454266776644875e-05, + "loss": 3.5773, + "step": 944128 + }, + { + "epoch": 1.01, + "learning_rate": 3.453428181893823e-05, + "loss": 3.5838, + "step": 944640 + }, + { + "epoch": 1.01, + "learning_rate": 3.452589587142771e-05, + "loss": 3.575, + "step": 945152 + }, + { + "epoch": 1.01, + "learning_rate": 3.451750992391719e-05, + "loss": 3.5944, + "step": 945664 + }, + { + "epoch": 1.01, + "learning_rate": 3.4509140355210396e-05, + "loss": 3.5822, + "step": 946176 + }, + { + "epoch": 1.01, + "learning_rate": 3.4500754407699876e-05, + "loss": 3.5686, + "step": 946688 + }, + { + "epoch": 1.01, + "learning_rate": 3.4492368460189356e-05, + "loss": 3.5993, + "step": 947200 + }, + { + "epoch": 1.01, + "learning_rate": 3.4483982512678836e-05, + "loss": 3.5763, + "step": 947712 + }, + { + "epoch": 1.01, + "learning_rate": 3.4475612943972045e-05, + "loss": 3.5698, + "step": 948224 + }, + { + "epoch": 1.01, + "learning_rate": 3.4467226996461525e-05, + "loss": 3.5838, + "step": 948736 + }, + { + "epoch": 1.01, + "learning_rate": 3.4458841048951005e-05, + "loss": 3.578, + "step": 949248 + }, + { + "epoch": 1.01, + "learning_rate": 3.4450455101440485e-05, + "loss": 3.5719, + "step": 949760 + }, + { + "epoch": 1.01, + "learning_rate": 3.4442069153929965e-05, + "loss": 3.5815, + "step": 950272 + }, + { + "epoch": 1.01, + "learning_rate": 3.443369958522318e-05, + "loss": 3.5674, + "step": 950784 + }, + { + "epoch": 1.01, + "learning_rate": 3.442531363771266e-05, + "loss": 3.5708, + "step": 951296 + }, + { + "epoch": 1.01, + "learning_rate": 3.4416927690202134e-05, + "loss": 3.5913, + "step": 951808 + }, + { + "epoch": 1.01, + "learning_rate": 3.4408541742691614e-05, + "loss": 3.5818, + "step": 952320 + }, + { + "epoch": 1.01, + "learning_rate": 3.440017217398483e-05, + "loss": 3.586, + "step": 952832 + }, + { + "epoch": 1.01, + "learning_rate": 3.439178622647431e-05, + "loss": 3.5842, + "step": 953344 + }, + { + "epoch": 1.01, + "learning_rate": 3.438340027896378e-05, + "loss": 3.5971, + "step": 953856 + }, + { + "epoch": 1.01, + "learning_rate": 3.437501433145326e-05, + "loss": 3.574, + "step": 954368 + }, + { + "epoch": 1.01, + "learning_rate": 3.436664476274648e-05, + "loss": 3.5939, + "step": 954880 + }, + { + "epoch": 1.01, + "learning_rate": 3.435825881523596e-05, + "loss": 3.5799, + "step": 955392 + }, + { + "epoch": 1.01, + "learning_rate": 3.434987286772544e-05, + "loss": 3.572, + "step": 955904 + }, + { + "epoch": 1.01, + "learning_rate": 3.434148692021492e-05, + "loss": 3.5849, + "step": 956416 + }, + { + "epoch": 1.01, + "learning_rate": 3.4333117351508134e-05, + "loss": 3.5927, + "step": 956928 + }, + { + "epoch": 1.01, + "learning_rate": 3.432473140399761e-05, + "loss": 3.5827, + "step": 957440 + }, + { + "epoch": 1.01, + "learning_rate": 3.431634545648709e-05, + "loss": 3.5927, + "step": 957952 + }, + { + "epoch": 1.01, + "learning_rate": 3.430795950897657e-05, + "loss": 3.5679, + "step": 958464 + }, + { + "epoch": 1.01, + "learning_rate": 3.429957356146605e-05, + "loss": 3.5645, + "step": 958976 + }, + { + "epoch": 1.01, + "learning_rate": 3.4291203992759256e-05, + "loss": 3.5792, + "step": 959488 + }, + { + "epoch": 1.01, + "learning_rate": 3.4282818045248736e-05, + "loss": 3.585, + "step": 960000 + }, + { + "epoch": 1.01, + "learning_rate": 3.4274432097738216e-05, + "loss": 3.5767, + "step": 960512 + }, + { + "epoch": 1.01, + "learning_rate": 3.4266046150227696e-05, + "loss": 3.5736, + "step": 961024 + }, + { + "epoch": 1.01, + "learning_rate": 3.425767658152091e-05, + "loss": 3.5814, + "step": 961536 + }, + { + "epoch": 1.02, + "learning_rate": 3.424929063401039e-05, + "loss": 3.5819, + "step": 962048 + }, + { + "epoch": 1.02, + "learning_rate": 3.424090468649987e-05, + "loss": 3.574, + "step": 962560 + }, + { + "epoch": 1.02, + "learning_rate": 3.423251873898935e-05, + "loss": 3.5753, + "step": 963072 + }, + { + "epoch": 1.02, + "learning_rate": 3.422414917028256e-05, + "loss": 3.5864, + "step": 963584 + }, + { + "epoch": 1.02, + "learning_rate": 3.421576322277204e-05, + "loss": 3.5994, + "step": 964096 + }, + { + "epoch": 1.02, + "learning_rate": 3.420737727526152e-05, + "loss": 3.5875, + "step": 964608 + }, + { + "epoch": 1.02, + "learning_rate": 3.4198991327751e-05, + "loss": 3.5721, + "step": 965120 + }, + { + "epoch": 1.02, + "learning_rate": 3.419060538024048e-05, + "loss": 3.5783, + "step": 965632 + }, + { + "epoch": 1.02, + "learning_rate": 3.418223581153369e-05, + "loss": 3.5787, + "step": 966144 + }, + { + "epoch": 1.02, + "learning_rate": 3.417384986402317e-05, + "loss": 3.5868, + "step": 966656 + }, + { + "epoch": 1.02, + "learning_rate": 3.416546391651265e-05, + "loss": 3.5826, + "step": 967168 + }, + { + "epoch": 1.02, + "learning_rate": 3.415707796900213e-05, + "loss": 3.5771, + "step": 967680 + }, + { + "epoch": 1.02, + "learning_rate": 3.4148708400295346e-05, + "loss": 3.5772, + "step": 968192 + }, + { + "epoch": 1.02, + "learning_rate": 3.4140322452784826e-05, + "loss": 3.5816, + "step": 968704 + }, + { + "epoch": 1.02, + "learning_rate": 3.4131936505274306e-05, + "loss": 3.5848, + "step": 969216 + }, + { + "epoch": 1.02, + "learning_rate": 3.4123550557763786e-05, + "loss": 3.5765, + "step": 969728 + }, + { + "epoch": 1.02, + "learning_rate": 3.4115180989056995e-05, + "loss": 3.5737, + "step": 970240 + }, + { + "epoch": 1.02, + "learning_rate": 3.4106795041546475e-05, + "loss": 3.5714, + "step": 970752 + }, + { + "epoch": 1.02, + "learning_rate": 3.4098409094035955e-05, + "loss": 3.5785, + "step": 971264 + }, + { + "epoch": 1.02, + "learning_rate": 3.4090023146525434e-05, + "loss": 3.5739, + "step": 971776 + }, + { + "epoch": 1.02, + "learning_rate": 3.4081653577818644e-05, + "loss": 3.5749, + "step": 972288 + }, + { + "epoch": 1.02, + "learning_rate": 3.4073267630308124e-05, + "loss": 3.5735, + "step": 972800 + }, + { + "epoch": 1.02, + "learning_rate": 3.4064881682797603e-05, + "loss": 3.5792, + "step": 973312 + }, + { + "epoch": 1.02, + "learning_rate": 3.4056495735287083e-05, + "loss": 3.5734, + "step": 973824 + }, + { + "epoch": 1.02, + "learning_rate": 3.4048109787776563e-05, + "loss": 3.5866, + "step": 974336 + }, + { + "epoch": 1.02, + "learning_rate": 3.403974021906978e-05, + "loss": 3.5929, + "step": 974848 + }, + { + "epoch": 1.02, + "learning_rate": 3.403135427155926e-05, + "loss": 3.5802, + "step": 975360 + }, + { + "epoch": 1.02, + "learning_rate": 3.402296832404874e-05, + "loss": 3.5869, + "step": 975872 + }, + { + "epoch": 1.02, + "learning_rate": 3.401458237653822e-05, + "loss": 3.5818, + "step": 976384 + }, + { + "epoch": 1.02, + "learning_rate": 3.400621280783143e-05, + "loss": 3.5751, + "step": 976896 + }, + { + "epoch": 1.02, + "learning_rate": 3.399782686032091e-05, + "loss": 3.5786, + "step": 977408 + }, + { + "epoch": 1.02, + "learning_rate": 3.398944091281039e-05, + "loss": 3.5608, + "step": 977920 + }, + { + "epoch": 1.02, + "learning_rate": 3.398105496529987e-05, + "loss": 3.5822, + "step": 978432 + }, + { + "epoch": 1.02, + "learning_rate": 3.397266901778935e-05, + "loss": 3.5774, + "step": 978944 + }, + { + "epoch": 1.02, + "learning_rate": 3.396429944908256e-05, + "loss": 3.5826, + "step": 979456 + }, + { + "epoch": 1.02, + "learning_rate": 3.395591350157204e-05, + "loss": 3.5745, + "step": 979968 + }, + { + "epoch": 1.02, + "learning_rate": 3.394752755406152e-05, + "loss": 3.5873, + "step": 980480 + }, + { + "epoch": 1.02, + "learning_rate": 3.3939141606551e-05, + "loss": 3.5762, + "step": 980992 + }, + { + "epoch": 1.02, + "learning_rate": 3.393077203784421e-05, + "loss": 3.5712, + "step": 981504 + }, + { + "epoch": 1.02, + "learning_rate": 3.392238609033369e-05, + "loss": 3.5835, + "step": 982016 + }, + { + "epoch": 1.02, + "learning_rate": 3.391400014282317e-05, + "loss": 3.5787, + "step": 982528 + }, + { + "epoch": 1.02, + "learning_rate": 3.390561419531265e-05, + "loss": 3.5891, + "step": 983040 + }, + { + "epoch": 1.02, + "learning_rate": 3.389724462660586e-05, + "loss": 3.5742, + "step": 983552 + }, + { + "epoch": 1.02, + "learning_rate": 3.388885867909534e-05, + "loss": 3.5865, + "step": 984064 + }, + { + "epoch": 1.02, + "learning_rate": 3.388047273158482e-05, + "loss": 3.5766, + "step": 984576 + }, + { + "epoch": 1.02, + "learning_rate": 3.38720867840743e-05, + "loss": 3.5822, + "step": 985088 + }, + { + "epoch": 1.02, + "learning_rate": 3.386371721536751e-05, + "loss": 3.5844, + "step": 985600 + }, + { + "epoch": 1.02, + "learning_rate": 3.385533126785699e-05, + "loss": 3.5744, + "step": 986112 + }, + { + "epoch": 1.02, + "learning_rate": 3.384694532034647e-05, + "loss": 3.5718, + "step": 986624 + }, + { + "epoch": 1.02, + "learning_rate": 3.383855937283595e-05, + "loss": 3.5884, + "step": 987136 + }, + { + "epoch": 1.02, + "learning_rate": 3.383017342532544e-05, + "loss": 3.5705, + "step": 987648 + }, + { + "epoch": 1.02, + "learning_rate": 3.3821803856618647e-05, + "loss": 3.579, + "step": 988160 + }, + { + "epoch": 1.02, + "learning_rate": 3.3813417909108126e-05, + "loss": 3.581, + "step": 988672 + }, + { + "epoch": 1.02, + "learning_rate": 3.3805031961597606e-05, + "loss": 3.5799, + "step": 989184 + }, + { + "epoch": 1.02, + "learning_rate": 3.3796646014087086e-05, + "loss": 3.5757, + "step": 989696 + }, + { + "epoch": 1.02, + "learning_rate": 3.3788276445380295e-05, + "loss": 3.5802, + "step": 990208 + }, + { + "epoch": 1.02, + "learning_rate": 3.3779890497869775e-05, + "loss": 3.581, + "step": 990720 + }, + { + "epoch": 1.02, + "learning_rate": 3.3771504550359255e-05, + "loss": 3.5855, + "step": 991232 + }, + { + "epoch": 1.02, + "learning_rate": 3.3763118602848735e-05, + "loss": 3.5791, + "step": 991744 + }, + { + "epoch": 1.03, + "eval_loss": 3.8367321491241455, + "eval_runtime": 306.279, + "eval_samples_per_second": 1245.894, + "eval_steps_per_second": 38.935, + "step": 992149 + }, + { + "epoch": 0.0, + "learning_rate": 3.375473265533821e-05, + "loss": 3.5717, + "step": 992256 + }, + { + "epoch": 0.0, + "learning_rate": 3.374634670782769e-05, + "loss": 3.5649, + "step": 992768 + }, + { + "epoch": 0.0, + "learning_rate": 3.3737960760317175e-05, + "loss": 3.573, + "step": 993280 + }, + { + "epoch": 0.0, + "learning_rate": 3.3729574812806655e-05, + "loss": 3.5858, + "step": 993792 + }, + { + "epoch": 0.0, + "learning_rate": 3.3721205244099864e-05, + "loss": 3.5774, + "step": 994304 + }, + { + "epoch": 0.0, + "learning_rate": 3.3712819296589344e-05, + "loss": 3.5744, + "step": 994816 + }, + { + "epoch": 0.0, + "learning_rate": 3.3704433349078824e-05, + "loss": 3.5782, + "step": 995328 + }, + { + "epoch": 0.0, + "learning_rate": 3.3696047401568304e-05, + "loss": 3.5732, + "step": 995840 + }, + { + "epoch": 0.0, + "learning_rate": 3.3687661454057784e-05, + "loss": 3.5653, + "step": 996352 + }, + { + "epoch": 0.0, + "learning_rate": 3.367929188535099e-05, + "loss": 3.5647, + "step": 996864 + }, + { + "epoch": 0.0, + "learning_rate": 3.367090593784047e-05, + "loss": 3.5826, + "step": 997376 + }, + { + "epoch": 0.0, + "learning_rate": 3.366251999032995e-05, + "loss": 3.5819, + "step": 997888 + }, + { + "epoch": 0.0, + "learning_rate": 3.365415042162316e-05, + "loss": 3.5844, + "step": 998400 + }, + { + "epoch": 0.0, + "learning_rate": 3.364576447411264e-05, + "loss": 3.5506, + "step": 998912 + }, + { + "epoch": 0.0, + "learning_rate": 3.363737852660213e-05, + "loss": 3.5722, + "step": 999424 + }, + { + "epoch": 0.0, + "learning_rate": 3.362899257909161e-05, + "loss": 3.5601, + "step": 999936 + }, + { + "epoch": 0.0, + "learning_rate": 3.362060663158109e-05, + "loss": 3.5758, + "step": 1000448 + }, + { + "epoch": 0.0, + "learning_rate": 3.361222068407057e-05, + "loss": 3.5703, + "step": 1000960 + }, + { + "epoch": 0.0, + "learning_rate": 3.360383473656005e-05, + "loss": 3.5697, + "step": 1001472 + }, + { + "epoch": 0.0, + "learning_rate": 3.359544878904953e-05, + "loss": 3.5739, + "step": 1001984 + }, + { + "epoch": 0.0, + "learning_rate": 3.358707922034274e-05, + "loss": 3.5871, + "step": 1002496 + }, + { + "epoch": 0.0, + "learning_rate": 3.357869327283222e-05, + "loss": 3.5716, + "step": 1003008 + }, + { + "epoch": 0.0, + "learning_rate": 3.35703073253217e-05, + "loss": 3.571, + "step": 1003520 + }, + { + "epoch": 0.0, + "learning_rate": 3.356192137781118e-05, + "loss": 3.5662, + "step": 1004032 + }, + { + "epoch": 0.0, + "learning_rate": 3.355355180910439e-05, + "loss": 3.5784, + "step": 1004544 + }, + { + "epoch": 0.0, + "learning_rate": 3.354516586159387e-05, + "loss": 3.5747, + "step": 1005056 + }, + { + "epoch": 0.0, + "learning_rate": 3.353677991408335e-05, + "loss": 3.5633, + "step": 1005568 + }, + { + "epoch": 0.0, + "learning_rate": 3.3528393966572827e-05, + "loss": 3.5718, + "step": 1006080 + }, + { + "epoch": 0.0, + "learning_rate": 3.352002439786604e-05, + "loss": 3.5651, + "step": 1006592 + }, + { + "epoch": 0.0, + "learning_rate": 3.351163845035552e-05, + "loss": 3.5676, + "step": 1007104 + }, + { + "epoch": 0.01, + "learning_rate": 3.3503252502845e-05, + "loss": 3.5689, + "step": 1007616 + }, + { + "epoch": 0.01, + "learning_rate": 3.349486655533448e-05, + "loss": 3.5722, + "step": 1008128 + }, + { + "epoch": 0.01, + "learning_rate": 3.348648060782396e-05, + "loss": 3.5724, + "step": 1008640 + }, + { + "epoch": 0.01, + "learning_rate": 3.347811103911717e-05, + "loss": 3.5787, + "step": 1009152 + }, + { + "epoch": 0.01, + "learning_rate": 3.346972509160665e-05, + "loss": 3.5742, + "step": 1009664 + }, + { + "epoch": 0.01, + "learning_rate": 3.346133914409613e-05, + "loss": 3.5697, + "step": 1010176 + }, + { + "epoch": 0.01, + "learning_rate": 3.345295319658561e-05, + "loss": 3.5774, + "step": 1010688 + }, + { + "epoch": 0.01, + "learning_rate": 3.344458362787882e-05, + "loss": 3.5618, + "step": 1011200 + }, + { + "epoch": 0.01, + "learning_rate": 3.34361976803683e-05, + "loss": 3.5647, + "step": 1011712 + }, + { + "epoch": 0.01, + "learning_rate": 3.342781173285778e-05, + "loss": 3.5678, + "step": 1012224 + }, + { + "epoch": 0.01, + "learning_rate": 3.341942578534727e-05, + "loss": 3.56, + "step": 1012736 + }, + { + "epoch": 0.01, + "learning_rate": 3.3411056216640476e-05, + "loss": 3.5655, + "step": 1013248 + }, + { + "epoch": 0.01, + "learning_rate": 3.3402670269129956e-05, + "loss": 3.5687, + "step": 1013760 + }, + { + "epoch": 0.01, + "learning_rate": 3.3394284321619436e-05, + "loss": 3.5707, + "step": 1014272 + }, + { + "epoch": 0.01, + "learning_rate": 3.3385898374108916e-05, + "loss": 3.5717, + "step": 1014784 + }, + { + "epoch": 0.01, + "learning_rate": 3.3377528805402125e-05, + "loss": 3.5718, + "step": 1015296 + }, + { + "epoch": 0.01, + "learning_rate": 3.3369142857891605e-05, + "loss": 3.5726, + "step": 1015808 + }, + { + "epoch": 0.01, + "learning_rate": 3.3360756910381085e-05, + "loss": 3.5691, + "step": 1016320 + }, + { + "epoch": 0.01, + "learning_rate": 3.3352370962870565e-05, + "loss": 3.5522, + "step": 1016832 + }, + { + "epoch": 0.01, + "learning_rate": 3.3344001394163774e-05, + "loss": 3.5706, + "step": 1017344 + }, + { + "epoch": 0.01, + "learning_rate": 3.3335615446653254e-05, + "loss": 3.564, + "step": 1017856 + }, + { + "epoch": 0.01, + "learning_rate": 3.3327229499142734e-05, + "loss": 3.5703, + "step": 1018368 + }, + { + "epoch": 0.01, + "learning_rate": 3.331884355163222e-05, + "loss": 3.57, + "step": 1018880 + }, + { + "epoch": 0.01, + "learning_rate": 3.3310457604121694e-05, + "loss": 3.5635, + "step": 1019392 + }, + { + "epoch": 0.01, + "learning_rate": 3.330208803541491e-05, + "loss": 3.5539, + "step": 1019904 + }, + { + "epoch": 0.01, + "learning_rate": 3.329370208790439e-05, + "loss": 3.5573, + "step": 1020416 + }, + { + "epoch": 0.01, + "learning_rate": 3.328531614039387e-05, + "loss": 3.5699, + "step": 1020928 + }, + { + "epoch": 0.01, + "learning_rate": 3.327693019288334e-05, + "loss": 3.5531, + "step": 1021440 + }, + { + "epoch": 0.01, + "learning_rate": 3.326854424537282e-05, + "loss": 3.5778, + "step": 1021952 + }, + { + "epoch": 0.01, + "learning_rate": 3.326017467666604e-05, + "loss": 3.5686, + "step": 1022464 + }, + { + "epoch": 0.01, + "learning_rate": 3.325178872915552e-05, + "loss": 3.5451, + "step": 1022976 + }, + { + "epoch": 0.01, + "learning_rate": 3.324340278164499e-05, + "loss": 3.581, + "step": 1023488 + }, + { + "epoch": 0.01, + "learning_rate": 3.323501683413447e-05, + "loss": 3.5595, + "step": 1024000 + }, + { + "epoch": 0.01, + "learning_rate": 3.322663088662396e-05, + "loss": 3.5547, + "step": 1024512 + }, + { + "epoch": 0.01, + "learning_rate": 3.321826131791717e-05, + "loss": 3.56, + "step": 1025024 + }, + { + "epoch": 0.01, + "learning_rate": 3.320987537040665e-05, + "loss": 3.5648, + "step": 1025536 + }, + { + "epoch": 0.01, + "learning_rate": 3.320148942289613e-05, + "loss": 3.5528, + "step": 1026048 + }, + { + "epoch": 0.01, + "learning_rate": 3.319310347538561e-05, + "loss": 3.5651, + "step": 1026560 + }, + { + "epoch": 0.01, + "learning_rate": 3.3184733906678817e-05, + "loss": 3.5483, + "step": 1027072 + }, + { + "epoch": 0.01, + "learning_rate": 3.3176347959168296e-05, + "loss": 3.5551, + "step": 1027584 + }, + { + "epoch": 0.01, + "learning_rate": 3.3167962011657776e-05, + "loss": 3.5751, + "step": 1028096 + }, + { + "epoch": 0.01, + "learning_rate": 3.3159576064147256e-05, + "loss": 3.5628, + "step": 1028608 + }, + { + "epoch": 0.01, + "learning_rate": 3.3151206495440465e-05, + "loss": 3.5689, + "step": 1029120 + }, + { + "epoch": 0.01, + "learning_rate": 3.3142820547929945e-05, + "loss": 3.5635, + "step": 1029632 + }, + { + "epoch": 0.01, + "learning_rate": 3.3134434600419425e-05, + "loss": 3.5801, + "step": 1030144 + }, + { + "epoch": 0.01, + "learning_rate": 3.3126048652908905e-05, + "loss": 3.5588, + "step": 1030656 + }, + { + "epoch": 0.01, + "learning_rate": 3.311767908420212e-05, + "loss": 3.5749, + "step": 1031168 + }, + { + "epoch": 0.01, + "learning_rate": 3.31092931366916e-05, + "loss": 3.5599, + "step": 1031680 + }, + { + "epoch": 0.01, + "learning_rate": 3.310090718918108e-05, + "loss": 3.5578, + "step": 1032192 + }, + { + "epoch": 0.01, + "learning_rate": 3.309252124167056e-05, + "loss": 3.5637, + "step": 1032704 + }, + { + "epoch": 0.01, + "learning_rate": 3.308415167296377e-05, + "loss": 3.5785, + "step": 1033216 + }, + { + "epoch": 0.01, + "learning_rate": 3.307576572545325e-05, + "loss": 3.562, + "step": 1033728 + }, + { + "epoch": 0.01, + "learning_rate": 3.306737977794273e-05, + "loss": 3.5758, + "step": 1034240 + }, + { + "epoch": 0.01, + "learning_rate": 3.305899383043221e-05, + "loss": 3.547, + "step": 1034752 + }, + { + "epoch": 0.01, + "learning_rate": 3.305062426172542e-05, + "loss": 3.5488, + "step": 1035264 + }, + { + "epoch": 0.01, + "learning_rate": 3.30422383142149e-05, + "loss": 3.5611, + "step": 1035776 + }, + { + "epoch": 0.01, + "learning_rate": 3.303385236670438e-05, + "loss": 3.5633, + "step": 1036288 + }, + { + "epoch": 0.01, + "learning_rate": 3.302546641919386e-05, + "loss": 3.5596, + "step": 1036800 + }, + { + "epoch": 0.01, + "learning_rate": 3.3017096850487075e-05, + "loss": 3.5595, + "step": 1037312 + }, + { + "epoch": 0.01, + "learning_rate": 3.3008710902976555e-05, + "loss": 3.5608, + "step": 1037824 + }, + { + "epoch": 0.02, + "learning_rate": 3.3000324955466035e-05, + "loss": 3.5619, + "step": 1038336 + }, + { + "epoch": 0.02, + "learning_rate": 3.2991939007955515e-05, + "loss": 3.5589, + "step": 1038848 + }, + { + "epoch": 0.02, + "learning_rate": 3.2983569439248724e-05, + "loss": 3.5568, + "step": 1039360 + }, + { + "epoch": 0.02, + "learning_rate": 3.2975183491738204e-05, + "loss": 3.5684, + "step": 1039872 + }, + { + "epoch": 0.02, + "learning_rate": 3.2966797544227684e-05, + "loss": 3.5788, + "step": 1040384 + }, + { + "epoch": 0.02, + "learning_rate": 3.2958411596717164e-05, + "loss": 3.5736, + "step": 1040896 + }, + { + "epoch": 0.02, + "learning_rate": 3.295004202801037e-05, + "loss": 3.5521, + "step": 1041408 + }, + { + "epoch": 0.02, + "learning_rate": 3.294165608049985e-05, + "loss": 3.5592, + "step": 1041920 + }, + { + "epoch": 0.02, + "learning_rate": 3.293327013298933e-05, + "loss": 3.5629, + "step": 1042432 + }, + { + "epoch": 0.02, + "learning_rate": 3.292488418547881e-05, + "loss": 3.5699, + "step": 1042944 + }, + { + "epoch": 0.02, + "learning_rate": 3.291651461677203e-05, + "loss": 3.5643, + "step": 1043456 + }, + { + "epoch": 0.02, + "learning_rate": 3.290812866926151e-05, + "loss": 3.5595, + "step": 1043968 + }, + { + "epoch": 0.02, + "learning_rate": 3.289974272175099e-05, + "loss": 3.5604, + "step": 1044480 + }, + { + "epoch": 0.02, + "learning_rate": 3.289135677424047e-05, + "loss": 3.5673, + "step": 1044992 + }, + { + "epoch": 0.02, + "learning_rate": 3.288298720553368e-05, + "loss": 3.5648, + "step": 1045504 + }, + { + "epoch": 0.02, + "learning_rate": 3.287460125802316e-05, + "loss": 3.5611, + "step": 1046016 + }, + { + "epoch": 0.02, + "learning_rate": 3.286621531051264e-05, + "loss": 3.5574, + "step": 1046528 + }, + { + "epoch": 0.02, + "learning_rate": 3.285782936300212e-05, + "loss": 3.5517, + "step": 1047040 + }, + { + "epoch": 0.02, + "learning_rate": 3.2849459794295326e-05, + "loss": 3.5631, + "step": 1047552 + }, + { + "epoch": 0.02, + "learning_rate": 3.2841073846784806e-05, + "loss": 3.5566, + "step": 1048064 + }, + { + "epoch": 0.02, + "learning_rate": 3.2832687899274286e-05, + "loss": 3.5553, + "step": 1048576 + }, + { + "epoch": 0.02, + "learning_rate": 3.2824301951763766e-05, + "loss": 3.5568, + "step": 1049088 + }, + { + "epoch": 0.02, + "learning_rate": 3.281593238305698e-05, + "loss": 3.5633, + "step": 1049600 + }, + { + "epoch": 0.02, + "learning_rate": 3.280754643554646e-05, + "loss": 3.5555, + "step": 1050112 + }, + { + "epoch": 0.02, + "learning_rate": 3.279916048803594e-05, + "loss": 3.5659, + "step": 1050624 + }, + { + "epoch": 0.02, + "learning_rate": 3.279077454052542e-05, + "loss": 3.572, + "step": 1051136 + }, + { + "epoch": 0.02, + "learning_rate": 3.27823885930149e-05, + "loss": 3.5654, + "step": 1051648 + }, + { + "epoch": 0.02, + "learning_rate": 3.277401902430811e-05, + "loss": 3.5704, + "step": 1052160 + }, + { + "epoch": 0.02, + "learning_rate": 3.276563307679759e-05, + "loss": 3.5656, + "step": 1052672 + }, + { + "epoch": 0.02, + "learning_rate": 3.275724712928707e-05, + "loss": 3.557, + "step": 1053184 + }, + { + "epoch": 0.02, + "learning_rate": 3.274886118177655e-05, + "loss": 3.5618, + "step": 1053696 + }, + { + "epoch": 0.02, + "learning_rate": 3.274049161306976e-05, + "loss": 3.5452, + "step": 1054208 + }, + { + "epoch": 0.02, + "learning_rate": 3.273210566555924e-05, + "loss": 3.5653, + "step": 1054720 + }, + { + "epoch": 0.02, + "learning_rate": 3.272371971804872e-05, + "loss": 3.5554, + "step": 1055232 + }, + { + "epoch": 0.02, + "learning_rate": 3.271533377053821e-05, + "loss": 3.567, + "step": 1055744 + }, + { + "epoch": 0.02, + "learning_rate": 3.2706964201831416e-05, + "loss": 3.5612, + "step": 1056256 + }, + { + "epoch": 0.02, + "learning_rate": 3.2698578254320896e-05, + "loss": 3.5636, + "step": 1056768 + }, + { + "epoch": 0.02, + "learning_rate": 3.2690192306810376e-05, + "loss": 3.5554, + "step": 1057280 + }, + { + "epoch": 0.02, + "learning_rate": 3.2681806359299856e-05, + "loss": 3.5541, + "step": 1057792 + }, + { + "epoch": 0.02, + "learning_rate": 3.2673436790593065e-05, + "loss": 3.5634, + "step": 1058304 + }, + { + "epoch": 0.02, + "learning_rate": 3.2665050843082545e-05, + "loss": 3.5645, + "step": 1058816 + }, + { + "epoch": 0.02, + "learning_rate": 3.2656664895572025e-05, + "loss": 3.5708, + "step": 1059328 + }, + { + "epoch": 0.02, + "learning_rate": 3.2648278948061505e-05, + "loss": 3.558, + "step": 1059840 + }, + { + "epoch": 0.02, + "learning_rate": 3.2639909379354714e-05, + "loss": 3.5695, + "step": 1060352 + }, + { + "epoch": 0.02, + "learning_rate": 3.2631523431844194e-05, + "loss": 3.5592, + "step": 1060864 + }, + { + "epoch": 0.02, + "learning_rate": 3.2623137484333674e-05, + "loss": 3.5625, + "step": 1061376 + }, + { + "epoch": 0.02, + "learning_rate": 3.261475153682316e-05, + "loss": 3.5688, + "step": 1061888 + }, + { + "epoch": 0.02, + "learning_rate": 3.260638196811637e-05, + "loss": 3.5593, + "step": 1062400 + }, + { + "epoch": 0.02, + "learning_rate": 3.259799602060585e-05, + "loss": 3.5561, + "step": 1062912 + }, + { + "epoch": 0.02, + "learning_rate": 3.258961007309533e-05, + "loss": 3.5691, + "step": 1063424 + }, + { + "epoch": 0.02, + "learning_rate": 3.258122412558481e-05, + "loss": 3.5553, + "step": 1063936 + }, + { + "epoch": 0.02, + "learning_rate": 3.257283817807429e-05, + "loss": 3.5573, + "step": 1064448 + }, + { + "epoch": 0.02, + "learning_rate": 3.25644686093675e-05, + "loss": 3.5656, + "step": 1064960 + }, + { + "epoch": 0.02, + "learning_rate": 3.255608266185698e-05, + "loss": 3.565, + "step": 1065472 + }, + { + "epoch": 0.02, + "learning_rate": 3.254769671434646e-05, + "loss": 3.5569, + "step": 1065984 + }, + { + "epoch": 0.02, + "learning_rate": 3.253931076683594e-05, + "loss": 3.5664, + "step": 1066496 + }, + { + "epoch": 0.02, + "learning_rate": 3.253094119812915e-05, + "loss": 3.5597, + "step": 1067008 + }, + { + "epoch": 0.02, + "learning_rate": 3.252255525061863e-05, + "loss": 3.5733, + "step": 1067520 + }, + { + "epoch": 0.02, + "learning_rate": 3.2514169303108114e-05, + "loss": 3.5582, + "step": 1068032 + }, + { + "epoch": 0.03, + "eval_loss": 3.8382389545440674, + "eval_runtime": 301.8741, + "eval_samples_per_second": 1264.073, + "eval_steps_per_second": 39.503, + "step": 1068469 + }, + { + "epoch": 1.0, + "learning_rate": 3.2505783355597594e-05, + "loss": 3.5536, + "step": 1068544 + }, + { + "epoch": 1.0, + "learning_rate": 3.24974137868908e-05, + "loss": 3.5501, + "step": 1069056 + }, + { + "epoch": 1.0, + "learning_rate": 3.248902783938028e-05, + "loss": 3.5568, + "step": 1069568 + }, + { + "epoch": 1.0, + "learning_rate": 3.248064189186976e-05, + "loss": 3.5695, + "step": 1070080 + }, + { + "epoch": 1.0, + "learning_rate": 3.247225594435924e-05, + "loss": 3.5612, + "step": 1070592 + }, + { + "epoch": 1.0, + "learning_rate": 3.2463869996848716e-05, + "loss": 3.5583, + "step": 1071104 + }, + { + "epoch": 1.0, + "learning_rate": 3.245550042814193e-05, + "loss": 3.5578, + "step": 1071616 + }, + { + "epoch": 1.0, + "learning_rate": 3.244711448063141e-05, + "loss": 3.558, + "step": 1072128 + }, + { + "epoch": 1.0, + "learning_rate": 3.243872853312089e-05, + "loss": 3.5478, + "step": 1072640 + }, + { + "epoch": 1.0, + "learning_rate": 3.2430342585610365e-05, + "loss": 3.5525, + "step": 1073152 + }, + { + "epoch": 1.0, + "learning_rate": 3.242197301690358e-05, + "loss": 3.5588, + "step": 1073664 + }, + { + "epoch": 1.0, + "learning_rate": 3.241358706939306e-05, + "loss": 3.5716, + "step": 1074176 + }, + { + "epoch": 1.0, + "learning_rate": 3.240521750068628e-05, + "loss": 3.5682, + "step": 1074688 + }, + { + "epoch": 1.0, + "learning_rate": 3.239683155317576e-05, + "loss": 3.5349, + "step": 1075200 + }, + { + "epoch": 1.0, + "learning_rate": 3.238844560566524e-05, + "loss": 3.5537, + "step": 1075712 + }, + { + "epoch": 1.0, + "learning_rate": 3.238005965815472e-05, + "loss": 3.5424, + "step": 1076224 + }, + { + "epoch": 1.0, + "learning_rate": 3.237167371064419e-05, + "loss": 3.5612, + "step": 1076736 + }, + { + "epoch": 1.0, + "learning_rate": 3.236328776313367e-05, + "loss": 3.55, + "step": 1077248 + }, + { + "epoch": 1.0, + "learning_rate": 3.235490181562315e-05, + "loss": 3.5553, + "step": 1077760 + }, + { + "epoch": 1.0, + "learning_rate": 3.234651586811263e-05, + "loss": 3.5511, + "step": 1078272 + }, + { + "epoch": 1.0, + "learning_rate": 3.233814629940584e-05, + "loss": 3.572, + "step": 1078784 + }, + { + "epoch": 1.0, + "learning_rate": 3.232976035189532e-05, + "loss": 3.5539, + "step": 1079296 + }, + { + "epoch": 1.0, + "learning_rate": 3.23213744043848e-05, + "loss": 3.5559, + "step": 1079808 + }, + { + "epoch": 1.0, + "learning_rate": 3.2312988456874285e-05, + "loss": 3.5491, + "step": 1080320 + }, + { + "epoch": 1.0, + "learning_rate": 3.2304602509363765e-05, + "loss": 3.5674, + "step": 1080832 + }, + { + "epoch": 1.0, + "learning_rate": 3.2296232940656975e-05, + "loss": 3.5533, + "step": 1081344 + }, + { + "epoch": 1.0, + "learning_rate": 3.2287846993146454e-05, + "loss": 3.5491, + "step": 1081856 + }, + { + "epoch": 1.0, + "learning_rate": 3.2279461045635934e-05, + "loss": 3.5528, + "step": 1082368 + }, + { + "epoch": 1.0, + "learning_rate": 3.2271075098125414e-05, + "loss": 3.553, + "step": 1082880 + }, + { + "epoch": 1.0, + "learning_rate": 3.2262705529418623e-05, + "loss": 3.5493, + "step": 1083392 + }, + { + "epoch": 1.01, + "learning_rate": 3.2254319581908103e-05, + "loss": 3.5523, + "step": 1083904 + }, + { + "epoch": 1.01, + "learning_rate": 3.2245933634397583e-05, + "loss": 3.5532, + "step": 1084416 + }, + { + "epoch": 1.01, + "learning_rate": 3.223754768688706e-05, + "loss": 3.5584, + "step": 1084928 + }, + { + "epoch": 1.01, + "learning_rate": 3.222917811818027e-05, + "loss": 3.5588, + "step": 1085440 + }, + { + "epoch": 1.01, + "learning_rate": 3.222079217066975e-05, + "loss": 3.5614, + "step": 1085952 + }, + { + "epoch": 1.01, + "learning_rate": 3.221240622315924e-05, + "loss": 3.5556, + "step": 1086464 + }, + { + "epoch": 1.01, + "learning_rate": 3.220402027564872e-05, + "loss": 3.5622, + "step": 1086976 + }, + { + "epoch": 1.01, + "learning_rate": 3.219565070694193e-05, + "loss": 3.5417, + "step": 1087488 + }, + { + "epoch": 1.01, + "learning_rate": 3.218726475943141e-05, + "loss": 3.5485, + "step": 1088000 + }, + { + "epoch": 1.01, + "learning_rate": 3.217887881192089e-05, + "loss": 3.5507, + "step": 1088512 + }, + { + "epoch": 1.01, + "learning_rate": 3.217049286441037e-05, + "loss": 3.5402, + "step": 1089024 + }, + { + "epoch": 1.01, + "learning_rate": 3.216210691689985e-05, + "loss": 3.5526, + "step": 1089536 + }, + { + "epoch": 1.01, + "learning_rate": 3.215373734819306e-05, + "loss": 3.5547, + "step": 1090048 + }, + { + "epoch": 1.01, + "learning_rate": 3.214535140068254e-05, + "loss": 3.5483, + "step": 1090560 + }, + { + "epoch": 1.01, + "learning_rate": 3.213696545317202e-05, + "loss": 3.5571, + "step": 1091072 + }, + { + "epoch": 1.01, + "learning_rate": 3.21285795056615e-05, + "loss": 3.556, + "step": 1091584 + }, + { + "epoch": 1.01, + "learning_rate": 3.2120209936954706e-05, + "loss": 3.556, + "step": 1092096 + }, + { + "epoch": 1.01, + "learning_rate": 3.211182398944419e-05, + "loss": 3.5529, + "step": 1092608 + }, + { + "epoch": 1.01, + "learning_rate": 3.210343804193367e-05, + "loss": 3.5371, + "step": 1093120 + }, + { + "epoch": 1.01, + "learning_rate": 3.209505209442315e-05, + "loss": 3.5535, + "step": 1093632 + }, + { + "epoch": 1.01, + "learning_rate": 3.208666614691263e-05, + "loss": 3.5494, + "step": 1094144 + }, + { + "epoch": 1.01, + "learning_rate": 3.207829657820584e-05, + "loss": 3.5577, + "step": 1094656 + }, + { + "epoch": 1.01, + "learning_rate": 3.206991063069532e-05, + "loss": 3.5492, + "step": 1095168 + }, + { + "epoch": 1.01, + "learning_rate": 3.20615246831848e-05, + "loss": 3.5466, + "step": 1095680 + }, + { + "epoch": 1.01, + "learning_rate": 3.205313873567428e-05, + "loss": 3.5391, + "step": 1096192 + }, + { + "epoch": 1.01, + "learning_rate": 3.204476916696749e-05, + "loss": 3.5411, + "step": 1096704 + }, + { + "epoch": 1.01, + "learning_rate": 3.203638321945697e-05, + "loss": 3.5522, + "step": 1097216 + }, + { + "epoch": 1.01, + "learning_rate": 3.202799727194645e-05, + "loss": 3.5356, + "step": 1097728 + }, + { + "epoch": 1.01, + "learning_rate": 3.201961132443593e-05, + "loss": 3.5623, + "step": 1098240 + }, + { + "epoch": 1.01, + "learning_rate": 3.2011241755729146e-05, + "loss": 3.5541, + "step": 1098752 + }, + { + "epoch": 1.01, + "learning_rate": 3.2002855808218626e-05, + "loss": 3.5301, + "step": 1099264 + }, + { + "epoch": 1.01, + "learning_rate": 3.1994469860708106e-05, + "loss": 3.5636, + "step": 1099776 + }, + { + "epoch": 1.01, + "learning_rate": 3.1986083913197586e-05, + "loss": 3.5418, + "step": 1100288 + }, + { + "epoch": 1.01, + "learning_rate": 3.1977697965687066e-05, + "loss": 3.5442, + "step": 1100800 + }, + { + "epoch": 1.01, + "learning_rate": 3.1969328396980275e-05, + "loss": 3.5384, + "step": 1101312 + }, + { + "epoch": 1.01, + "learning_rate": 3.1960942449469755e-05, + "loss": 3.5487, + "step": 1101824 + }, + { + "epoch": 1.01, + "learning_rate": 3.1952556501959235e-05, + "loss": 3.5374, + "step": 1102336 + }, + { + "epoch": 1.01, + "learning_rate": 3.1944170554448715e-05, + "loss": 3.5518, + "step": 1102848 + }, + { + "epoch": 1.01, + "learning_rate": 3.1935800985741924e-05, + "loss": 3.5274, + "step": 1103360 + }, + { + "epoch": 1.01, + "learning_rate": 3.1927415038231404e-05, + "loss": 3.5407, + "step": 1103872 + }, + { + "epoch": 1.01, + "learning_rate": 3.1919029090720884e-05, + "loss": 3.5547, + "step": 1104384 + }, + { + "epoch": 1.01, + "learning_rate": 3.1910643143210364e-05, + "loss": 3.547, + "step": 1104896 + }, + { + "epoch": 1.01, + "learning_rate": 3.190227357450358e-05, + "loss": 3.5528, + "step": 1105408 + }, + { + "epoch": 1.01, + "learning_rate": 3.189388762699306e-05, + "loss": 3.5493, + "step": 1105920 + }, + { + "epoch": 1.01, + "learning_rate": 3.188550167948254e-05, + "loss": 3.562, + "step": 1106432 + }, + { + "epoch": 1.01, + "learning_rate": 3.187711573197202e-05, + "loss": 3.5423, + "step": 1106944 + }, + { + "epoch": 1.01, + "learning_rate": 3.186874616326523e-05, + "loss": 3.5642, + "step": 1107456 + }, + { + "epoch": 1.01, + "learning_rate": 3.186036021575471e-05, + "loss": 3.5419, + "step": 1107968 + }, + { + "epoch": 1.01, + "learning_rate": 3.185197426824419e-05, + "loss": 3.5416, + "step": 1108480 + }, + { + "epoch": 1.01, + "learning_rate": 3.184358832073367e-05, + "loss": 3.5494, + "step": 1108992 + }, + { + "epoch": 1.01, + "learning_rate": 3.183521875202688e-05, + "loss": 3.5593, + "step": 1109504 + }, + { + "epoch": 1.01, + "learning_rate": 3.182683280451636e-05, + "loss": 3.549, + "step": 1110016 + }, + { + "epoch": 1.01, + "learning_rate": 3.181844685700584e-05, + "loss": 3.5573, + "step": 1110528 + }, + { + "epoch": 1.01, + "learning_rate": 3.181006090949532e-05, + "loss": 3.5351, + "step": 1111040 + }, + { + "epoch": 1.01, + "learning_rate": 3.1801691340788534e-05, + "loss": 3.5287, + "step": 1111552 + }, + { + "epoch": 1.01, + "learning_rate": 3.1793305393278014e-05, + "loss": 3.5459, + "step": 1112064 + }, + { + "epoch": 1.01, + "learning_rate": 3.1784919445767494e-05, + "loss": 3.5482, + "step": 1112576 + }, + { + "epoch": 1.01, + "learning_rate": 3.1776533498256974e-05, + "loss": 3.5417, + "step": 1113088 + }, + { + "epoch": 1.01, + "learning_rate": 3.176816392955018e-05, + "loss": 3.5419, + "step": 1113600 + }, + { + "epoch": 1.01, + "learning_rate": 3.175977798203966e-05, + "loss": 3.5477, + "step": 1114112 + }, + { + "epoch": 1.02, + "learning_rate": 3.175139203452914e-05, + "loss": 3.5457, + "step": 1114624 + }, + { + "epoch": 1.02, + "learning_rate": 3.174300608701862e-05, + "loss": 3.5426, + "step": 1115136 + }, + { + "epoch": 1.02, + "learning_rate": 3.173463651831183e-05, + "loss": 3.5369, + "step": 1115648 + }, + { + "epoch": 1.02, + "learning_rate": 3.172625057080131e-05, + "loss": 3.5542, + "step": 1116160 + }, + { + "epoch": 1.02, + "learning_rate": 3.171786462329079e-05, + "loss": 3.5637, + "step": 1116672 + }, + { + "epoch": 1.02, + "learning_rate": 3.170947867578027e-05, + "loss": 3.5549, + "step": 1117184 + }, + { + "epoch": 1.02, + "learning_rate": 3.170110910707349e-05, + "loss": 3.5384, + "step": 1117696 + }, + { + "epoch": 1.02, + "learning_rate": 3.169272315956297e-05, + "loss": 3.5439, + "step": 1118208 + }, + { + "epoch": 1.02, + "learning_rate": 3.168433721205245e-05, + "loss": 3.5444, + "step": 1118720 + }, + { + "epoch": 1.02, + "learning_rate": 3.167595126454192e-05, + "loss": 3.553, + "step": 1119232 + }, + { + "epoch": 1.02, + "learning_rate": 3.1667581695835136e-05, + "loss": 3.5513, + "step": 1119744 + }, + { + "epoch": 1.02, + "learning_rate": 3.1659195748324616e-05, + "loss": 3.5402, + "step": 1120256 + }, + { + "epoch": 1.02, + "learning_rate": 3.1650809800814096e-05, + "loss": 3.544, + "step": 1120768 + }, + { + "epoch": 1.02, + "learning_rate": 3.164242385330357e-05, + "loss": 3.5487, + "step": 1121280 + }, + { + "epoch": 1.02, + "learning_rate": 3.1634054284596785e-05, + "loss": 3.5512, + "step": 1121792 + }, + { + "epoch": 1.02, + "learning_rate": 3.1625668337086265e-05, + "loss": 3.5436, + "step": 1122304 + }, + { + "epoch": 1.02, + "learning_rate": 3.1617282389575745e-05, + "loss": 3.5459, + "step": 1122816 + }, + { + "epoch": 1.02, + "learning_rate": 3.1608896442065225e-05, + "loss": 3.5331, + "step": 1123328 + }, + { + "epoch": 1.02, + "learning_rate": 3.160052687335844e-05, + "loss": 3.5489, + "step": 1123840 + }, + { + "epoch": 1.02, + "learning_rate": 3.159214092584792e-05, + "loss": 3.5361, + "step": 1124352 + }, + { + "epoch": 1.02, + "learning_rate": 3.1583754978337394e-05, + "loss": 3.5385, + "step": 1124864 + }, + { + "epoch": 1.02, + "learning_rate": 3.1575369030826874e-05, + "loss": 3.5402, + "step": 1125376 + }, + { + "epoch": 1.02, + "learning_rate": 3.156699946212009e-05, + "loss": 3.5471, + "step": 1125888 + }, + { + "epoch": 1.02, + "learning_rate": 3.155861351460957e-05, + "loss": 3.5424, + "step": 1126400 + }, + { + "epoch": 1.02, + "learning_rate": 3.155022756709904e-05, + "loss": 3.5451, + "step": 1126912 + }, + { + "epoch": 1.02, + "learning_rate": 3.154184161958852e-05, + "loss": 3.5548, + "step": 1127424 + }, + { + "epoch": 1.02, + "learning_rate": 3.153347205088174e-05, + "loss": 3.5536, + "step": 1127936 + }, + { + "epoch": 1.02, + "learning_rate": 3.152508610337121e-05, + "loss": 3.5569, + "step": 1128448 + }, + { + "epoch": 1.02, + "learning_rate": 3.15167001558607e-05, + "loss": 3.5451, + "step": 1128960 + }, + { + "epoch": 1.02, + "learning_rate": 3.150831420835018e-05, + "loss": 3.5443, + "step": 1129472 + }, + { + "epoch": 1.02, + "learning_rate": 3.149992826083966e-05, + "loss": 3.5452, + "step": 1129984 + }, + { + "epoch": 1.02, + "learning_rate": 3.149155869213287e-05, + "loss": 3.5292, + "step": 1130496 + }, + { + "epoch": 1.02, + "learning_rate": 3.148317274462235e-05, + "loss": 3.5479, + "step": 1131008 + }, + { + "epoch": 1.02, + "learning_rate": 3.147478679711183e-05, + "loss": 3.5428, + "step": 1131520 + }, + { + "epoch": 1.02, + "learning_rate": 3.146640084960131e-05, + "loss": 3.5499, + "step": 1132032 + }, + { + "epoch": 1.02, + "learning_rate": 3.145803128089452e-05, + "loss": 3.5428, + "step": 1132544 + }, + { + "epoch": 1.02, + "learning_rate": 3.1449645333384e-05, + "loss": 3.551, + "step": 1133056 + }, + { + "epoch": 1.02, + "learning_rate": 3.144125938587348e-05, + "loss": 3.537, + "step": 1133568 + }, + { + "epoch": 1.02, + "learning_rate": 3.143287343836296e-05, + "loss": 3.541, + "step": 1134080 + }, + { + "epoch": 1.02, + "learning_rate": 3.1424503869656166e-05, + "loss": 3.5508, + "step": 1134592 + }, + { + "epoch": 1.02, + "learning_rate": 3.1416117922145646e-05, + "loss": 3.5445, + "step": 1135104 + }, + { + "epoch": 1.02, + "learning_rate": 3.140773197463513e-05, + "loss": 3.5557, + "step": 1135616 + }, + { + "epoch": 1.02, + "learning_rate": 3.139934602712461e-05, + "loss": 3.5426, + "step": 1136128 + }, + { + "epoch": 1.02, + "learning_rate": 3.139097645841782e-05, + "loss": 3.5489, + "step": 1136640 + }, + { + "epoch": 1.02, + "learning_rate": 3.13825905109073e-05, + "loss": 3.5457, + "step": 1137152 + }, + { + "epoch": 1.02, + "learning_rate": 3.137420456339678e-05, + "loss": 3.5433, + "step": 1137664 + }, + { + "epoch": 1.02, + "learning_rate": 3.136581861588626e-05, + "loss": 3.5524, + "step": 1138176 + }, + { + "epoch": 1.02, + "learning_rate": 3.135744904717947e-05, + "loss": 3.5409, + "step": 1138688 + }, + { + "epoch": 1.02, + "learning_rate": 3.134906309966895e-05, + "loss": 3.5466, + "step": 1139200 + }, + { + "epoch": 1.02, + "learning_rate": 3.134067715215843e-05, + "loss": 3.552, + "step": 1139712 + }, + { + "epoch": 1.02, + "learning_rate": 3.133229120464791e-05, + "loss": 3.5408, + "step": 1140224 + }, + { + "epoch": 1.02, + "learning_rate": 3.132392163594112e-05, + "loss": 3.541, + "step": 1140736 + }, + { + "epoch": 1.02, + "learning_rate": 3.13155356884306e-05, + "loss": 3.5512, + "step": 1141248 + }, + { + "epoch": 1.02, + "learning_rate": 3.1307149740920086e-05, + "loss": 3.5466, + "step": 1141760 + }, + { + "epoch": 1.02, + "learning_rate": 3.1298763793409566e-05, + "loss": 3.5422, + "step": 1142272 + }, + { + "epoch": 1.02, + "learning_rate": 3.1290394224702775e-05, + "loss": 3.5522, + "step": 1142784 + }, + { + "epoch": 1.02, + "learning_rate": 3.1282008277192255e-05, + "loss": 3.5405, + "step": 1143296 + }, + { + "epoch": 1.02, + "learning_rate": 3.1273622329681735e-05, + "loss": 3.5605, + "step": 1143808 + }, + { + "epoch": 1.02, + "learning_rate": 3.1265236382171215e-05, + "loss": 3.5416, + "step": 1144320 + }, + { + "epoch": 1.03, + "eval_loss": 3.83803653717041, + "eval_runtime": 301.7255, + "eval_samples_per_second": 1264.696, + "eval_steps_per_second": 39.523, + "step": 1144789 + }, + { + "epoch": 0.0, + "learning_rate": 3.1256850434660695e-05, + "loss": 3.5105, + "step": 1144832 + }, + { + "epoch": 0.0, + "learning_rate": 3.1248464487150175e-05, + "loss": 3.5411, + "step": 1145344 + }, + { + "epoch": 0.0, + "learning_rate": 3.1240078539639655e-05, + "loss": 3.5333, + "step": 1145856 + }, + { + "epoch": 0.0, + "learning_rate": 3.1231692592129135e-05, + "loss": 3.5553, + "step": 1146368 + }, + { + "epoch": 0.0, + "learning_rate": 3.1223323023422344e-05, + "loss": 3.5444, + "step": 1146880 + }, + { + "epoch": 0.0, + "learning_rate": 3.1214937075911824e-05, + "loss": 3.5462, + "step": 1147392 + }, + { + "epoch": 0.0, + "learning_rate": 3.1206551128401304e-05, + "loss": 3.5402, + "step": 1147904 + }, + { + "epoch": 0.0, + "learning_rate": 3.1198165180890784e-05, + "loss": 3.5413, + "step": 1148416 + }, + { + "epoch": 0.0, + "learning_rate": 3.118977923338027e-05, + "loss": 3.5318, + "step": 1148928 + }, + { + "epoch": 0.0, + "learning_rate": 3.118140966467348e-05, + "loss": 3.5386, + "step": 1149440 + }, + { + "epoch": 0.0, + "learning_rate": 3.117302371716296e-05, + "loss": 3.5423, + "step": 1149952 + }, + { + "epoch": 0.0, + "learning_rate": 3.116463776965244e-05, + "loss": 3.5545, + "step": 1150464 + }, + { + "epoch": 0.0, + "learning_rate": 3.115626820094565e-05, + "loss": 3.5522, + "step": 1150976 + }, + { + "epoch": 0.0, + "learning_rate": 3.114788225343513e-05, + "loss": 3.5212, + "step": 1151488 + }, + { + "epoch": 0.0, + "learning_rate": 3.113949630592461e-05, + "loss": 3.5383, + "step": 1152000 + }, + { + "epoch": 0.0, + "learning_rate": 3.113111035841409e-05, + "loss": 3.5294, + "step": 1152512 + }, + { + "epoch": 0.0, + "learning_rate": 3.112272441090357e-05, + "loss": 3.5403, + "step": 1153024 + }, + { + "epoch": 0.0, + "learning_rate": 3.111433846339305e-05, + "loss": 3.5334, + "step": 1153536 + }, + { + "epoch": 0.0, + "learning_rate": 3.110595251588252e-05, + "loss": 3.54, + "step": 1154048 + }, + { + "epoch": 0.0, + "learning_rate": 3.109756656837201e-05, + "loss": 3.5378, + "step": 1154560 + }, + { + "epoch": 0.0, + "learning_rate": 3.1089196999665224e-05, + "loss": 3.5569, + "step": 1155072 + }, + { + "epoch": 0.0, + "learning_rate": 3.1080811052154704e-05, + "loss": 3.5422, + "step": 1155584 + }, + { + "epoch": 0.0, + "learning_rate": 3.107242510464418e-05, + "loss": 3.5378, + "step": 1156096 + }, + { + "epoch": 0.0, + "learning_rate": 3.106403915713366e-05, + "loss": 3.5339, + "step": 1156608 + }, + { + "epoch": 0.0, + "learning_rate": 3.105566958842687e-05, + "loss": 3.5537, + "step": 1157120 + }, + { + "epoch": 0.0, + "learning_rate": 3.1047283640916346e-05, + "loss": 3.5354, + "step": 1157632 + }, + { + "epoch": 0.0, + "learning_rate": 3.1038897693405826e-05, + "loss": 3.5324, + "step": 1158144 + }, + { + "epoch": 0.0, + "learning_rate": 3.1030511745895306e-05, + "loss": 3.5412, + "step": 1158656 + }, + { + "epoch": 0.0, + "learning_rate": 3.1022125798384786e-05, + "loss": 3.5333, + "step": 1159168 + }, + { + "epoch": 0.0, + "learning_rate": 3.1013756229677995e-05, + "loss": 3.5326, + "step": 1159680 + }, + { + "epoch": 0.01, + "learning_rate": 3.1005370282167475e-05, + "loss": 3.5392, + "step": 1160192 + }, + { + "epoch": 0.01, + "learning_rate": 3.099698433465696e-05, + "loss": 3.5358, + "step": 1160704 + }, + { + "epoch": 0.01, + "learning_rate": 3.098859838714644e-05, + "loss": 3.5411, + "step": 1161216 + }, + { + "epoch": 0.01, + "learning_rate": 3.098022881843965e-05, + "loss": 3.5471, + "step": 1161728 + }, + { + "epoch": 0.01, + "learning_rate": 3.097184287092913e-05, + "loss": 3.5433, + "step": 1162240 + }, + { + "epoch": 0.01, + "learning_rate": 3.096345692341861e-05, + "loss": 3.5394, + "step": 1162752 + }, + { + "epoch": 0.01, + "learning_rate": 3.095507097590809e-05, + "loss": 3.5456, + "step": 1163264 + }, + { + "epoch": 0.01, + "learning_rate": 3.09467014072013e-05, + "loss": 3.5281, + "step": 1163776 + }, + { + "epoch": 0.01, + "learning_rate": 3.093831545969078e-05, + "loss": 3.5347, + "step": 1164288 + }, + { + "epoch": 0.01, + "learning_rate": 3.092992951218026e-05, + "loss": 3.5346, + "step": 1164800 + }, + { + "epoch": 0.01, + "learning_rate": 3.092154356466974e-05, + "loss": 3.5268, + "step": 1165312 + }, + { + "epoch": 0.01, + "learning_rate": 3.091317399596295e-05, + "loss": 3.536, + "step": 1165824 + }, + { + "epoch": 0.01, + "learning_rate": 3.090478804845243e-05, + "loss": 3.5395, + "step": 1166336 + }, + { + "epoch": 0.01, + "learning_rate": 3.0896402100941916e-05, + "loss": 3.5332, + "step": 1166848 + }, + { + "epoch": 0.01, + "learning_rate": 3.0888016153431396e-05, + "loss": 3.5405, + "step": 1167360 + }, + { + "epoch": 0.01, + "learning_rate": 3.0879646584724605e-05, + "loss": 3.5421, + "step": 1167872 + }, + { + "epoch": 0.01, + "learning_rate": 3.0871260637214085e-05, + "loss": 3.5406, + "step": 1168384 + }, + { + "epoch": 0.01, + "learning_rate": 3.0862874689703565e-05, + "loss": 3.5371, + "step": 1168896 + }, + { + "epoch": 0.01, + "learning_rate": 3.0854488742193045e-05, + "loss": 3.5214, + "step": 1169408 + }, + { + "epoch": 0.01, + "learning_rate": 3.0846102794682525e-05, + "loss": 3.5363, + "step": 1169920 + }, + { + "epoch": 0.01, + "learning_rate": 3.0837733225975734e-05, + "loss": 3.5392, + "step": 1170432 + }, + { + "epoch": 0.01, + "learning_rate": 3.0829347278465214e-05, + "loss": 3.5373, + "step": 1170944 + }, + { + "epoch": 0.01, + "learning_rate": 3.0820961330954694e-05, + "loss": 3.5348, + "step": 1171456 + }, + { + "epoch": 0.01, + "learning_rate": 3.0812575383444174e-05, + "loss": 3.5305, + "step": 1171968 + }, + { + "epoch": 0.01, + "learning_rate": 3.080420581473738e-05, + "loss": 3.5204, + "step": 1172480 + }, + { + "epoch": 0.01, + "learning_rate": 3.079581986722686e-05, + "loss": 3.525, + "step": 1172992 + }, + { + "epoch": 0.01, + "learning_rate": 3.078743391971635e-05, + "loss": 3.5384, + "step": 1173504 + }, + { + "epoch": 0.01, + "learning_rate": 3.077904797220583e-05, + "loss": 3.5258, + "step": 1174016 + }, + { + "epoch": 0.01, + "learning_rate": 3.077067840349904e-05, + "loss": 3.5415, + "step": 1174528 + }, + { + "epoch": 0.01, + "learning_rate": 3.076229245598852e-05, + "loss": 3.5378, + "step": 1175040 + }, + { + "epoch": 0.01, + "learning_rate": 3.0753906508478e-05, + "loss": 3.5219, + "step": 1175552 + }, + { + "epoch": 0.01, + "learning_rate": 3.074552056096748e-05, + "loss": 3.5456, + "step": 1176064 + }, + { + "epoch": 0.01, + "learning_rate": 3.073715099226069e-05, + "loss": 3.5246, + "step": 1176576 + }, + { + "epoch": 0.01, + "learning_rate": 3.072876504475017e-05, + "loss": 3.5277, + "step": 1177088 + }, + { + "epoch": 0.01, + "learning_rate": 3.072037909723965e-05, + "loss": 3.5254, + "step": 1177600 + }, + { + "epoch": 0.01, + "learning_rate": 3.071199314972913e-05, + "loss": 3.5363, + "step": 1178112 + }, + { + "epoch": 0.01, + "learning_rate": 3.0703623581022336e-05, + "loss": 3.5218, + "step": 1178624 + }, + { + "epoch": 0.01, + "learning_rate": 3.0695237633511816e-05, + "loss": 3.5331, + "step": 1179136 + }, + { + "epoch": 0.01, + "learning_rate": 3.06868516860013e-05, + "loss": 3.5128, + "step": 1179648 + }, + { + "epoch": 0.01, + "learning_rate": 3.067846573849078e-05, + "loss": 3.5254, + "step": 1180160 + }, + { + "epoch": 0.01, + "learning_rate": 3.067009616978399e-05, + "loss": 3.5406, + "step": 1180672 + }, + { + "epoch": 0.01, + "learning_rate": 3.066171022227347e-05, + "loss": 3.533, + "step": 1181184 + }, + { + "epoch": 0.01, + "learning_rate": 3.065332427476295e-05, + "loss": 3.5348, + "step": 1181696 + }, + { + "epoch": 0.01, + "learning_rate": 3.064493832725243e-05, + "loss": 3.5369, + "step": 1182208 + }, + { + "epoch": 0.01, + "learning_rate": 3.063656875854564e-05, + "loss": 3.5443, + "step": 1182720 + }, + { + "epoch": 0.01, + "learning_rate": 3.062818281103512e-05, + "loss": 3.5303, + "step": 1183232 + }, + { + "epoch": 0.01, + "learning_rate": 3.06197968635246e-05, + "loss": 3.5481, + "step": 1183744 + }, + { + "epoch": 0.01, + "learning_rate": 3.061141091601408e-05, + "loss": 3.5261, + "step": 1184256 + }, + { + "epoch": 0.01, + "learning_rate": 3.060304134730729e-05, + "loss": 3.5264, + "step": 1184768 + }, + { + "epoch": 0.01, + "learning_rate": 3.059465539979677e-05, + "loss": 3.5322, + "step": 1185280 + }, + { + "epoch": 0.01, + "learning_rate": 3.058626945228626e-05, + "loss": 3.5421, + "step": 1185792 + }, + { + "epoch": 0.01, + "learning_rate": 3.057788350477574e-05, + "loss": 3.5351, + "step": 1186304 + }, + { + "epoch": 0.01, + "learning_rate": 3.0569513936068946e-05, + "loss": 3.5425, + "step": 1186816 + }, + { + "epoch": 0.01, + "learning_rate": 3.0561127988558426e-05, + "loss": 3.5217, + "step": 1187328 + }, + { + "epoch": 0.01, + "learning_rate": 3.0552742041047906e-05, + "loss": 3.5169, + "step": 1187840 + }, + { + "epoch": 0.01, + "learning_rate": 3.0544356093537386e-05, + "loss": 3.5288, + "step": 1188352 + }, + { + "epoch": 0.01, + "learning_rate": 3.0535986524830595e-05, + "loss": 3.5308, + "step": 1188864 + }, + { + "epoch": 0.01, + "learning_rate": 3.0527600577320075e-05, + "loss": 3.5281, + "step": 1189376 + }, + { + "epoch": 0.01, + "learning_rate": 3.0519214629809555e-05, + "loss": 3.5266, + "step": 1189888 + }, + { + "epoch": 0.01, + "learning_rate": 3.0510828682299038e-05, + "loss": 3.5358, + "step": 1190400 + }, + { + "epoch": 0.02, + "learning_rate": 3.0502459113592247e-05, + "loss": 3.528, + "step": 1190912 + }, + { + "epoch": 0.02, + "learning_rate": 3.0494073166081727e-05, + "loss": 3.528, + "step": 1191424 + }, + { + "epoch": 0.02, + "learning_rate": 3.0485687218571207e-05, + "loss": 3.5252, + "step": 1191936 + }, + { + "epoch": 0.02, + "learning_rate": 3.0477301271060687e-05, + "loss": 3.5381, + "step": 1192448 + }, + { + "epoch": 0.02, + "learning_rate": 3.04689317023539e-05, + "loss": 3.5476, + "step": 1192960 + }, + { + "epoch": 0.02, + "learning_rate": 3.046054575484338e-05, + "loss": 3.5432, + "step": 1193472 + }, + { + "epoch": 0.02, + "learning_rate": 3.045215980733286e-05, + "loss": 3.5184, + "step": 1193984 + }, + { + "epoch": 0.02, + "learning_rate": 3.044377385982234e-05, + "loss": 3.5317, + "step": 1194496 + }, + { + "epoch": 0.02, + "learning_rate": 3.043540429111555e-05, + "loss": 3.5293, + "step": 1195008 + }, + { + "epoch": 0.02, + "learning_rate": 3.042701834360503e-05, + "loss": 3.5358, + "step": 1195520 + }, + { + "epoch": 0.02, + "learning_rate": 3.041863239609451e-05, + "loss": 3.5365, + "step": 1196032 + }, + { + "epoch": 0.02, + "learning_rate": 3.0410246448583988e-05, + "loss": 3.5248, + "step": 1196544 + }, + { + "epoch": 0.02, + "learning_rate": 3.04018768798772e-05, + "loss": 3.529, + "step": 1197056 + }, + { + "epoch": 0.02, + "learning_rate": 3.039349093236668e-05, + "loss": 3.5356, + "step": 1197568 + }, + { + "epoch": 0.02, + "learning_rate": 3.038510498485616e-05, + "loss": 3.5357, + "step": 1198080 + }, + { + "epoch": 0.02, + "learning_rate": 3.037671903734564e-05, + "loss": 3.5271, + "step": 1198592 + }, + { + "epoch": 0.02, + "learning_rate": 3.036834946863885e-05, + "loss": 3.5279, + "step": 1199104 + }, + { + "epoch": 0.02, + "learning_rate": 3.0359963521128333e-05, + "loss": 3.5202, + "step": 1199616 + }, + { + "epoch": 0.02, + "learning_rate": 3.0351577573617813e-05, + "loss": 3.5361, + "step": 1200128 + }, + { + "epoch": 0.02, + "learning_rate": 3.0343191626107293e-05, + "loss": 3.5199, + "step": 1200640 + }, + { + "epoch": 0.02, + "learning_rate": 3.0334822057400502e-05, + "loss": 3.5237, + "step": 1201152 + }, + { + "epoch": 0.02, + "learning_rate": 3.0326436109889982e-05, + "loss": 3.5242, + "step": 1201664 + }, + { + "epoch": 0.02, + "learning_rate": 3.0318050162379462e-05, + "loss": 3.5373, + "step": 1202176 + }, + { + "epoch": 0.02, + "learning_rate": 3.0309664214868942e-05, + "loss": 3.5268, + "step": 1202688 + }, + { + "epoch": 0.02, + "learning_rate": 3.0301278267358425e-05, + "loss": 3.5277, + "step": 1203200 + }, + { + "epoch": 0.02, + "learning_rate": 3.0292908698651634e-05, + "loss": 3.5431, + "step": 1203712 + }, + { + "epoch": 0.02, + "learning_rate": 3.0284522751141114e-05, + "loss": 3.5384, + "step": 1204224 + }, + { + "epoch": 0.02, + "learning_rate": 3.0276136803630594e-05, + "loss": 3.5392, + "step": 1204736 + }, + { + "epoch": 0.02, + "learning_rate": 3.0267750856120074e-05, + "loss": 3.5323, + "step": 1205248 + }, + { + "epoch": 0.02, + "learning_rate": 3.0259381287413287e-05, + "loss": 3.529, + "step": 1205760 + }, + { + "epoch": 0.02, + "learning_rate": 3.0250995339902767e-05, + "loss": 3.5267, + "step": 1206272 + }, + { + "epoch": 0.02, + "learning_rate": 3.0242609392392247e-05, + "loss": 3.5176, + "step": 1206784 + }, + { + "epoch": 0.02, + "learning_rate": 3.0234223444881727e-05, + "loss": 3.5316, + "step": 1207296 + }, + { + "epoch": 0.02, + "learning_rate": 3.0225853876174936e-05, + "loss": 3.5275, + "step": 1207808 + }, + { + "epoch": 0.02, + "learning_rate": 3.0217467928664416e-05, + "loss": 3.5333, + "step": 1208320 + }, + { + "epoch": 0.02, + "learning_rate": 3.0209081981153896e-05, + "loss": 3.5286, + "step": 1208832 + }, + { + "epoch": 0.02, + "learning_rate": 3.0200696033643372e-05, + "loss": 3.534, + "step": 1209344 + }, + { + "epoch": 0.02, + "learning_rate": 3.0192326464936588e-05, + "loss": 3.5257, + "step": 1209856 + }, + { + "epoch": 0.02, + "learning_rate": 3.0183940517426068e-05, + "loss": 3.5252, + "step": 1210368 + }, + { + "epoch": 0.02, + "learning_rate": 3.0175554569915548e-05, + "loss": 3.5342, + "step": 1210880 + }, + { + "epoch": 0.02, + "learning_rate": 3.0167168622405025e-05, + "loss": 3.5314, + "step": 1211392 + }, + { + "epoch": 0.02, + "learning_rate": 3.015879905369824e-05, + "loss": 3.5404, + "step": 1211904 + }, + { + "epoch": 0.02, + "learning_rate": 3.015041310618772e-05, + "loss": 3.5297, + "step": 1212416 + }, + { + "epoch": 0.02, + "learning_rate": 3.01420271586772e-05, + "loss": 3.5333, + "step": 1212928 + }, + { + "epoch": 0.02, + "learning_rate": 3.0133641211166674e-05, + "loss": 3.5337, + "step": 1213440 + }, + { + "epoch": 0.02, + "learning_rate": 3.0125255263656153e-05, + "loss": 3.5299, + "step": 1213952 + }, + { + "epoch": 0.02, + "learning_rate": 3.011688569494937e-05, + "loss": 3.5331, + "step": 1214464 + }, + { + "epoch": 0.02, + "learning_rate": 3.0108499747438846e-05, + "loss": 3.5288, + "step": 1214976 + }, + { + "epoch": 0.02, + "learning_rate": 3.0100113799928326e-05, + "loss": 3.534, + "step": 1215488 + }, + { + "epoch": 0.02, + "learning_rate": 3.0091727852417806e-05, + "loss": 3.5363, + "step": 1216000 + }, + { + "epoch": 0.02, + "learning_rate": 3.0083358283711022e-05, + "loss": 3.5281, + "step": 1216512 + }, + { + "epoch": 0.02, + "learning_rate": 3.0074972336200495e-05, + "loss": 3.5272, + "step": 1217024 + }, + { + "epoch": 0.02, + "learning_rate": 3.0066586388689978e-05, + "loss": 3.5329, + "step": 1217536 + }, + { + "epoch": 0.02, + "learning_rate": 3.0058200441179458e-05, + "loss": 3.5313, + "step": 1218048 + }, + { + "epoch": 0.02, + "learning_rate": 3.0049814493668938e-05, + "loss": 3.5274, + "step": 1218560 + }, + { + "epoch": 0.02, + "learning_rate": 3.0041444924962147e-05, + "loss": 3.54, + "step": 1219072 + }, + { + "epoch": 0.02, + "learning_rate": 3.0033058977451627e-05, + "loss": 3.525, + "step": 1219584 + }, + { + "epoch": 0.02, + "learning_rate": 3.0024673029941107e-05, + "loss": 3.5425, + "step": 1220096 + }, + { + "epoch": 0.02, + "learning_rate": 3.0016287082430587e-05, + "loss": 3.5288, + "step": 1220608 + }, + { + "epoch": 0.03, + "eval_loss": 3.840222120285034, + "eval_runtime": 301.7358, + "eval_samples_per_second": 1264.653, + "eval_steps_per_second": 39.521, + "step": 1221109 + }, + { + "epoch": 1.0, + "learning_rate": 3.00079175137238e-05, + "loss": 3.5263, + "step": 1221120 + }, + { + "epoch": 1.0, + "learning_rate": 2.999953156621328e-05, + "loss": 3.5236, + "step": 1221632 + }, + { + "epoch": 1.0, + "learning_rate": 2.999114561870276e-05, + "loss": 3.519, + "step": 1222144 + }, + { + "epoch": 1.0, + "learning_rate": 2.998275967119224e-05, + "loss": 3.5386, + "step": 1222656 + }, + { + "epoch": 1.0, + "learning_rate": 2.997439010248545e-05, + "loss": 3.5352, + "step": 1223168 + }, + { + "epoch": 1.0, + "learning_rate": 2.9966004154974932e-05, + "loss": 3.5311, + "step": 1223680 + }, + { + "epoch": 1.0, + "learning_rate": 2.9957618207464412e-05, + "loss": 3.5263, + "step": 1224192 + }, + { + "epoch": 1.0, + "learning_rate": 2.9949232259953892e-05, + "loss": 3.5265, + "step": 1224704 + }, + { + "epoch": 1.0, + "learning_rate": 2.99408626912471e-05, + "loss": 3.5148, + "step": 1225216 + }, + { + "epoch": 1.0, + "learning_rate": 2.993247674373658e-05, + "loss": 3.5282, + "step": 1225728 + }, + { + "epoch": 1.0, + "learning_rate": 2.992409079622606e-05, + "loss": 3.5243, + "step": 1226240 + }, + { + "epoch": 1.0, + "learning_rate": 2.991570484871554e-05, + "loss": 3.5416, + "step": 1226752 + }, + { + "epoch": 1.0, + "learning_rate": 2.990735165881249e-05, + "loss": 3.537, + "step": 1227264 + }, + { + "epoch": 1.0, + "learning_rate": 2.989896571130197e-05, + "loss": 3.5088, + "step": 1227776 + }, + { + "epoch": 1.0, + "learning_rate": 2.9890579763791442e-05, + "loss": 3.5207, + "step": 1228288 + }, + { + "epoch": 1.0, + "learning_rate": 2.9882193816280922e-05, + "loss": 3.5192, + "step": 1228800 + }, + { + "epoch": 1.0, + "learning_rate": 2.9873807868770402e-05, + "loss": 3.5233, + "step": 1229312 + }, + { + "epoch": 1.0, + "learning_rate": 2.9865421921259886e-05, + "loss": 3.5237, + "step": 1229824 + }, + { + "epoch": 1.0, + "learning_rate": 2.9857035973749366e-05, + "loss": 3.5248, + "step": 1230336 + }, + { + "epoch": 1.0, + "learning_rate": 2.9848650026238845e-05, + "loss": 3.521, + "step": 1230848 + }, + { + "epoch": 1.0, + "learning_rate": 2.9840280457532055e-05, + "loss": 3.5422, + "step": 1231360 + }, + { + "epoch": 1.0, + "learning_rate": 2.9831894510021535e-05, + "loss": 3.5276, + "step": 1231872 + }, + { + "epoch": 1.0, + "learning_rate": 2.9823508562511014e-05, + "loss": 3.522, + "step": 1232384 + }, + { + "epoch": 1.0, + "learning_rate": 2.9815122615000494e-05, + "loss": 3.519, + "step": 1232896 + }, + { + "epoch": 1.0, + "learning_rate": 2.9806753046293707e-05, + "loss": 3.5418, + "step": 1233408 + }, + { + "epoch": 1.0, + "learning_rate": 2.9798367098783187e-05, + "loss": 3.5211, + "step": 1233920 + }, + { + "epoch": 1.0, + "learning_rate": 2.9789981151272667e-05, + "loss": 3.5181, + "step": 1234432 + }, + { + "epoch": 1.0, + "learning_rate": 2.9781595203762147e-05, + "loss": 3.5266, + "step": 1234944 + }, + { + "epoch": 1.0, + "learning_rate": 2.9773209256251627e-05, + "loss": 3.5184, + "step": 1235456 + }, + { + "epoch": 1.0, + "learning_rate": 2.976483968754484e-05, + "loss": 3.5217, + "step": 1235968 + }, + { + "epoch": 1.01, + "learning_rate": 2.975645374003432e-05, + "loss": 3.5233, + "step": 1236480 + }, + { + "epoch": 1.01, + "learning_rate": 2.97480677925238e-05, + "loss": 3.5211, + "step": 1236992 + }, + { + "epoch": 1.01, + "learning_rate": 2.973968184501328e-05, + "loss": 3.5256, + "step": 1237504 + }, + { + "epoch": 1.01, + "learning_rate": 2.9731312276306488e-05, + "loss": 3.5268, + "step": 1238016 + }, + { + "epoch": 1.01, + "learning_rate": 2.9722926328795968e-05, + "loss": 3.5323, + "step": 1238528 + }, + { + "epoch": 1.01, + "learning_rate": 2.9714540381285448e-05, + "loss": 3.5248, + "step": 1239040 + }, + { + "epoch": 1.01, + "learning_rate": 2.970615443377493e-05, + "loss": 3.5303, + "step": 1239552 + }, + { + "epoch": 1.01, + "learning_rate": 2.969778486506814e-05, + "loss": 3.5163, + "step": 1240064 + }, + { + "epoch": 1.01, + "learning_rate": 2.968939891755762e-05, + "loss": 3.5215, + "step": 1240576 + }, + { + "epoch": 1.01, + "learning_rate": 2.96810129700471e-05, + "loss": 3.5151, + "step": 1241088 + }, + { + "epoch": 1.01, + "learning_rate": 2.967262702253658e-05, + "loss": 3.5166, + "step": 1241600 + }, + { + "epoch": 1.01, + "learning_rate": 2.9664257453829793e-05, + "loss": 3.5168, + "step": 1242112 + }, + { + "epoch": 1.01, + "learning_rate": 2.9655871506319273e-05, + "loss": 3.5268, + "step": 1242624 + }, + { + "epoch": 1.01, + "learning_rate": 2.9647485558808753e-05, + "loss": 3.5183, + "step": 1243136 + }, + { + "epoch": 1.01, + "learning_rate": 2.9639099611298233e-05, + "loss": 3.5271, + "step": 1243648 + }, + { + "epoch": 1.01, + "learning_rate": 2.9630730042591442e-05, + "loss": 3.5272, + "step": 1244160 + }, + { + "epoch": 1.01, + "learning_rate": 2.9622344095080922e-05, + "loss": 3.5274, + "step": 1244672 + }, + { + "epoch": 1.01, + "learning_rate": 2.9613958147570402e-05, + "loss": 3.5224, + "step": 1245184 + }, + { + "epoch": 1.01, + "learning_rate": 2.9605572200059882e-05, + "loss": 3.5072, + "step": 1245696 + }, + { + "epoch": 1.01, + "learning_rate": 2.9597186252549365e-05, + "loss": 3.5204, + "step": 1246208 + }, + { + "epoch": 1.01, + "learning_rate": 2.9588816683842574e-05, + "loss": 3.5288, + "step": 1246720 + }, + { + "epoch": 1.01, + "learning_rate": 2.9580430736332054e-05, + "loss": 3.5223, + "step": 1247232 + }, + { + "epoch": 1.01, + "learning_rate": 2.9572044788821534e-05, + "loss": 3.516, + "step": 1247744 + }, + { + "epoch": 1.01, + "learning_rate": 2.9563658841311014e-05, + "loss": 3.5176, + "step": 1248256 + }, + { + "epoch": 1.01, + "learning_rate": 2.9555289272604227e-05, + "loss": 3.5118, + "step": 1248768 + }, + { + "epoch": 1.01, + "learning_rate": 2.9546903325093706e-05, + "loss": 3.5058, + "step": 1249280 + }, + { + "epoch": 1.01, + "learning_rate": 2.9538517377583186e-05, + "loss": 3.5291, + "step": 1249792 + }, + { + "epoch": 1.01, + "learning_rate": 2.9530131430072666e-05, + "loss": 3.5105, + "step": 1250304 + }, + { + "epoch": 1.01, + "learning_rate": 2.9521761861365875e-05, + "loss": 3.5249, + "step": 1250816 + }, + { + "epoch": 1.01, + "learning_rate": 2.9513375913855355e-05, + "loss": 3.5213, + "step": 1251328 + }, + { + "epoch": 1.01, + "learning_rate": 2.9504989966344835e-05, + "loss": 3.5068, + "step": 1251840 + }, + { + "epoch": 1.01, + "learning_rate": 2.949660401883432e-05, + "loss": 3.5315, + "step": 1252352 + }, + { + "epoch": 1.01, + "learning_rate": 2.9488234450127528e-05, + "loss": 3.5134, + "step": 1252864 + }, + { + "epoch": 1.01, + "learning_rate": 2.9479848502617008e-05, + "loss": 3.5158, + "step": 1253376 + }, + { + "epoch": 1.01, + "learning_rate": 2.9471462555106488e-05, + "loss": 3.5059, + "step": 1253888 + }, + { + "epoch": 1.01, + "learning_rate": 2.9463076607595968e-05, + "loss": 3.5246, + "step": 1254400 + }, + { + "epoch": 1.01, + "learning_rate": 2.945470703888918e-05, + "loss": 3.5097, + "step": 1254912 + }, + { + "epoch": 1.01, + "learning_rate": 2.944632109137866e-05, + "loss": 3.5147, + "step": 1255424 + }, + { + "epoch": 1.01, + "learning_rate": 2.943793514386814e-05, + "loss": 3.5026, + "step": 1255936 + }, + { + "epoch": 1.01, + "learning_rate": 2.942954919635762e-05, + "loss": 3.5091, + "step": 1256448 + }, + { + "epoch": 1.01, + "learning_rate": 2.942117962765083e-05, + "loss": 3.5231, + "step": 1256960 + }, + { + "epoch": 1.01, + "learning_rate": 2.941279368014031e-05, + "loss": 3.5266, + "step": 1257472 + }, + { + "epoch": 1.01, + "learning_rate": 2.940440773262979e-05, + "loss": 3.5144, + "step": 1257984 + }, + { + "epoch": 1.01, + "learning_rate": 2.9396021785119272e-05, + "loss": 3.5216, + "step": 1258496 + }, + { + "epoch": 1.01, + "learning_rate": 2.938765221641248e-05, + "loss": 3.5329, + "step": 1259008 + }, + { + "epoch": 1.01, + "learning_rate": 2.937926626890196e-05, + "loss": 3.5159, + "step": 1259520 + }, + { + "epoch": 1.01, + "learning_rate": 2.937088032139144e-05, + "loss": 3.5346, + "step": 1260032 + }, + { + "epoch": 1.01, + "learning_rate": 2.936249437388092e-05, + "loss": 3.5113, + "step": 1260544 + }, + { + "epoch": 1.01, + "learning_rate": 2.9354124805174134e-05, + "loss": 3.5153, + "step": 1261056 + }, + { + "epoch": 1.01, + "learning_rate": 2.9345738857663614e-05, + "loss": 3.52, + "step": 1261568 + }, + { + "epoch": 1.01, + "learning_rate": 2.9337352910153094e-05, + "loss": 3.526, + "step": 1262080 + }, + { + "epoch": 1.01, + "learning_rate": 2.9328966962642574e-05, + "loss": 3.5204, + "step": 1262592 + }, + { + "epoch": 1.01, + "learning_rate": 2.9320597393935783e-05, + "loss": 3.5303, + "step": 1263104 + }, + { + "epoch": 1.01, + "learning_rate": 2.9312211446425263e-05, + "loss": 3.5106, + "step": 1263616 + }, + { + "epoch": 1.01, + "learning_rate": 2.9303825498914743e-05, + "loss": 3.4992, + "step": 1264128 + }, + { + "epoch": 1.01, + "learning_rate": 2.929543955140422e-05, + "loss": 3.5168, + "step": 1264640 + }, + { + "epoch": 1.01, + "learning_rate": 2.9287069982697435e-05, + "loss": 3.5173, + "step": 1265152 + }, + { + "epoch": 1.01, + "learning_rate": 2.9278684035186915e-05, + "loss": 3.5133, + "step": 1265664 + }, + { + "epoch": 1.01, + "learning_rate": 2.9270298087676395e-05, + "loss": 3.5123, + "step": 1266176 + }, + { + "epoch": 1.01, + "learning_rate": 2.926191214016587e-05, + "loss": 3.5229, + "step": 1266688 + }, + { + "epoch": 1.02, + "learning_rate": 2.9253542571459088e-05, + "loss": 3.5156, + "step": 1267200 + }, + { + "epoch": 1.02, + "learning_rate": 2.9245156623948567e-05, + "loss": 3.5132, + "step": 1267712 + }, + { + "epoch": 1.02, + "learning_rate": 2.9236770676438047e-05, + "loss": 3.5129, + "step": 1268224 + }, + { + "epoch": 1.02, + "learning_rate": 2.922838472892752e-05, + "loss": 3.5248, + "step": 1268736 + }, + { + "epoch": 1.02, + "learning_rate": 2.9220015160220736e-05, + "loss": 3.532, + "step": 1269248 + }, + { + "epoch": 1.02, + "learning_rate": 2.9211629212710216e-05, + "loss": 3.5277, + "step": 1269760 + }, + { + "epoch": 1.02, + "learning_rate": 2.9203243265199693e-05, + "loss": 3.5061, + "step": 1270272 + }, + { + "epoch": 1.02, + "learning_rate": 2.9194857317689173e-05, + "loss": 3.5164, + "step": 1270784 + }, + { + "epoch": 1.02, + "learning_rate": 2.918648774898239e-05, + "loss": 3.5188, + "step": 1271296 + }, + { + "epoch": 1.02, + "learning_rate": 2.917810180147187e-05, + "loss": 3.5212, + "step": 1271808 + }, + { + "epoch": 1.02, + "learning_rate": 2.9169715853961342e-05, + "loss": 3.5234, + "step": 1272320 + }, + { + "epoch": 1.02, + "learning_rate": 2.9161329906450825e-05, + "loss": 3.5126, + "step": 1272832 + }, + { + "epoch": 1.02, + "learning_rate": 2.915296033774404e-05, + "loss": 3.5124, + "step": 1273344 + }, + { + "epoch": 1.02, + "learning_rate": 2.914457439023352e-05, + "loss": 3.522, + "step": 1273856 + }, + { + "epoch": 1.02, + "learning_rate": 2.9136188442722994e-05, + "loss": 3.5247, + "step": 1274368 + }, + { + "epoch": 1.02, + "learning_rate": 2.9127802495212474e-05, + "loss": 3.5113, + "step": 1274880 + }, + { + "epoch": 1.02, + "learning_rate": 2.9119416547701954e-05, + "loss": 3.5186, + "step": 1275392 + }, + { + "epoch": 1.02, + "learning_rate": 2.9111046978995167e-05, + "loss": 3.5092, + "step": 1275904 + }, + { + "epoch": 1.02, + "learning_rate": 2.9102661031484647e-05, + "loss": 3.5137, + "step": 1276416 + }, + { + "epoch": 1.02, + "learning_rate": 2.9094275083974127e-05, + "loss": 3.5121, + "step": 1276928 + }, + { + "epoch": 1.02, + "learning_rate": 2.9085889136463607e-05, + "loss": 3.5096, + "step": 1277440 + }, + { + "epoch": 1.02, + "learning_rate": 2.9077519567756816e-05, + "loss": 3.506, + "step": 1277952 + }, + { + "epoch": 1.02, + "learning_rate": 2.9069133620246296e-05, + "loss": 3.5212, + "step": 1278464 + }, + { + "epoch": 1.02, + "learning_rate": 2.906074767273578e-05, + "loss": 3.5152, + "step": 1278976 + }, + { + "epoch": 1.02, + "learning_rate": 2.905236172522526e-05, + "loss": 3.5137, + "step": 1279488 + }, + { + "epoch": 1.02, + "learning_rate": 2.9043992156518468e-05, + "loss": 3.5284, + "step": 1280000 + }, + { + "epoch": 1.02, + "learning_rate": 2.9035606209007948e-05, + "loss": 3.5258, + "step": 1280512 + }, + { + "epoch": 1.02, + "learning_rate": 2.9027220261497428e-05, + "loss": 3.5243, + "step": 1281024 + }, + { + "epoch": 1.02, + "learning_rate": 2.9018834313986908e-05, + "loss": 3.519, + "step": 1281536 + }, + { + "epoch": 1.02, + "learning_rate": 2.901046474528012e-05, + "loss": 3.5158, + "step": 1282048 + }, + { + "epoch": 1.02, + "learning_rate": 2.90020787977696e-05, + "loss": 3.5099, + "step": 1282560 + }, + { + "epoch": 1.02, + "learning_rate": 2.899369285025908e-05, + "loss": 3.5089, + "step": 1283072 + }, + { + "epoch": 1.02, + "learning_rate": 2.898530690274856e-05, + "loss": 3.5136, + "step": 1283584 + }, + { + "epoch": 1.02, + "learning_rate": 2.897693733404177e-05, + "loss": 3.5164, + "step": 1284096 + }, + { + "epoch": 1.02, + "learning_rate": 2.896855138653125e-05, + "loss": 3.5208, + "step": 1284608 + }, + { + "epoch": 1.02, + "learning_rate": 2.8960165439020733e-05, + "loss": 3.5141, + "step": 1285120 + }, + { + "epoch": 1.02, + "learning_rate": 2.8951779491510213e-05, + "loss": 3.52, + "step": 1285632 + }, + { + "epoch": 1.02, + "learning_rate": 2.8943409922803422e-05, + "loss": 3.5182, + "step": 1286144 + }, + { + "epoch": 1.02, + "learning_rate": 2.89350239752929e-05, + "loss": 3.5124, + "step": 1286656 + }, + { + "epoch": 1.02, + "learning_rate": 2.892663802778238e-05, + "loss": 3.5115, + "step": 1287168 + }, + { + "epoch": 1.02, + "learning_rate": 2.891825208027186e-05, + "loss": 3.5241, + "step": 1287680 + }, + { + "epoch": 1.02, + "learning_rate": 2.8909882511565074e-05, + "loss": 3.5232, + "step": 1288192 + }, + { + "epoch": 1.02, + "learning_rate": 2.8901496564054554e-05, + "loss": 3.5183, + "step": 1288704 + }, + { + "epoch": 1.02, + "learning_rate": 2.8893110616544034e-05, + "loss": 3.5169, + "step": 1289216 + }, + { + "epoch": 1.02, + "learning_rate": 2.8884724669033514e-05, + "loss": 3.5194, + "step": 1289728 + }, + { + "epoch": 1.02, + "learning_rate": 2.8876355100326723e-05, + "loss": 3.5188, + "step": 1290240 + }, + { + "epoch": 1.02, + "learning_rate": 2.8867969152816203e-05, + "loss": 3.5209, + "step": 1290752 + }, + { + "epoch": 1.02, + "learning_rate": 2.8859583205305686e-05, + "loss": 3.5135, + "step": 1291264 + }, + { + "epoch": 1.02, + "learning_rate": 2.8851197257795166e-05, + "loss": 3.5203, + "step": 1291776 + }, + { + "epoch": 1.02, + "learning_rate": 2.8842827689088375e-05, + "loss": 3.523, + "step": 1292288 + }, + { + "epoch": 1.02, + "learning_rate": 2.8834441741577855e-05, + "loss": 3.5145, + "step": 1292800 + }, + { + "epoch": 1.02, + "learning_rate": 2.8826055794067335e-05, + "loss": 3.5124, + "step": 1293312 + }, + { + "epoch": 1.02, + "learning_rate": 2.8817669846556815e-05, + "loss": 3.5186, + "step": 1293824 + }, + { + "epoch": 1.02, + "learning_rate": 2.8809300277850028e-05, + "loss": 3.5195, + "step": 1294336 + }, + { + "epoch": 1.02, + "learning_rate": 2.8800914330339508e-05, + "loss": 3.5075, + "step": 1294848 + }, + { + "epoch": 1.02, + "learning_rate": 2.8792528382828988e-05, + "loss": 3.5277, + "step": 1295360 + }, + { + "epoch": 1.02, + "learning_rate": 2.8784142435318468e-05, + "loss": 3.5132, + "step": 1295872 + }, + { + "epoch": 1.02, + "learning_rate": 2.8775772866611677e-05, + "loss": 3.5248, + "step": 1296384 + }, + { + "epoch": 1.02, + "learning_rate": 2.8767386919101157e-05, + "loss": 3.5189, + "step": 1296896 + }, + { + "epoch": 1.02, + "learning_rate": 2.875900097159064e-05, + "loss": 3.5067, + "step": 1297408 + }, + { + "epoch": 1.03, + "eval_loss": 3.8409504890441895, + "eval_runtime": 303.2407, + "eval_samples_per_second": 1258.377, + "eval_steps_per_second": 39.325, + "step": 1297429 + }, + { + "epoch": 0.0, + "learning_rate": 2.875061502408012e-05, + "loss": 3.5091, + "step": 1297920 + }, + { + "epoch": 0.0, + "learning_rate": 2.87422290765696e-05, + "loss": 3.5062, + "step": 1298432 + }, + { + "epoch": 0.0, + "learning_rate": 2.873384312905908e-05, + "loss": 3.5253, + "step": 1298944 + }, + { + "epoch": 0.0, + "learning_rate": 2.872547356035229e-05, + "loss": 3.5168, + "step": 1299456 + }, + { + "epoch": 0.0, + "learning_rate": 2.871708761284177e-05, + "loss": 3.5194, + "step": 1299968 + }, + { + "epoch": 0.0, + "learning_rate": 2.870870166533125e-05, + "loss": 3.5175, + "step": 1300480 + }, + { + "epoch": 0.0, + "learning_rate": 2.870031571782073e-05, + "loss": 3.5078, + "step": 1300992 + }, + { + "epoch": 0.0, + "learning_rate": 2.8691929770310212e-05, + "loss": 3.5043, + "step": 1301504 + }, + { + "epoch": 0.0, + "learning_rate": 2.868356020160342e-05, + "loss": 3.516, + "step": 1302016 + }, + { + "epoch": 0.0, + "learning_rate": 2.86751742540929e-05, + "loss": 3.5064, + "step": 1302528 + }, + { + "epoch": 0.0, + "learning_rate": 2.866678830658238e-05, + "loss": 3.5299, + "step": 1303040 + }, + { + "epoch": 0.0, + "learning_rate": 2.865840235907186e-05, + "loss": 3.5187, + "step": 1303552 + }, + { + "epoch": 0.0, + "learning_rate": 2.8650032790365074e-05, + "loss": 3.5031, + "step": 1304064 + }, + { + "epoch": 0.0, + "learning_rate": 2.8641646842854554e-05, + "loss": 3.502, + "step": 1304576 + }, + { + "epoch": 0.0, + "learning_rate": 2.8633260895344034e-05, + "loss": 3.5079, + "step": 1305088 + }, + { + "epoch": 0.0, + "learning_rate": 2.8624874947833513e-05, + "loss": 3.5045, + "step": 1305600 + }, + { + "epoch": 0.0, + "learning_rate": 2.8616489000322993e-05, + "loss": 3.5114, + "step": 1306112 + }, + { + "epoch": 0.0, + "learning_rate": 2.8608103052812473e-05, + "loss": 3.5139, + "step": 1306624 + }, + { + "epoch": 0.0, + "learning_rate": 2.859971710530195e-05, + "loss": 3.5038, + "step": 1307136 + }, + { + "epoch": 0.0, + "learning_rate": 2.859133115779143e-05, + "loss": 3.5325, + "step": 1307648 + }, + { + "epoch": 0.0, + "learning_rate": 2.8582961589084646e-05, + "loss": 3.5096, + "step": 1308160 + }, + { + "epoch": 0.0, + "learning_rate": 2.8574575641574126e-05, + "loss": 3.5092, + "step": 1308672 + }, + { + "epoch": 0.0, + "learning_rate": 2.85661896940636e-05, + "loss": 3.5061, + "step": 1309184 + }, + { + "epoch": 0.0, + "learning_rate": 2.8557820125356815e-05, + "loss": 3.5263, + "step": 1309696 + }, + { + "epoch": 0.0, + "learning_rate": 2.8549434177846295e-05, + "loss": 3.5052, + "step": 1310208 + }, + { + "epoch": 0.0, + "learning_rate": 2.854104823033577e-05, + "loss": 3.5095, + "step": 1310720 + }, + { + "epoch": 0.0, + "learning_rate": 2.853266228282525e-05, + "loss": 3.5072, + "step": 1311232 + }, + { + "epoch": 0.0, + "learning_rate": 2.852427633531473e-05, + "loss": 3.5082, + "step": 1311744 + }, + { + "epoch": 0.0, + "learning_rate": 2.8515906766607947e-05, + "loss": 3.5044, + "step": 1312256 + }, + { + "epoch": 0.01, + "learning_rate": 2.850752081909742e-05, + "loss": 3.5108, + "step": 1312768 + }, + { + "epoch": 0.01, + "learning_rate": 2.8499134871586904e-05, + "loss": 3.5101, + "step": 1313280 + }, + { + "epoch": 0.01, + "learning_rate": 2.8490748924076384e-05, + "loss": 3.508, + "step": 1313792 + }, + { + "epoch": 0.01, + "learning_rate": 2.84823793553696e-05, + "loss": 3.5147, + "step": 1314304 + }, + { + "epoch": 0.01, + "learning_rate": 2.8473993407859073e-05, + "loss": 3.5188, + "step": 1314816 + }, + { + "epoch": 0.01, + "learning_rate": 2.8465607460348553e-05, + "loss": 3.5106, + "step": 1315328 + }, + { + "epoch": 0.01, + "learning_rate": 2.8457221512838033e-05, + "loss": 3.5151, + "step": 1315840 + }, + { + "epoch": 0.01, + "learning_rate": 2.8448851944131245e-05, + "loss": 3.5031, + "step": 1316352 + }, + { + "epoch": 0.01, + "learning_rate": 2.8440465996620725e-05, + "loss": 3.5112, + "step": 1316864 + }, + { + "epoch": 0.01, + "learning_rate": 2.8432080049110205e-05, + "loss": 3.4995, + "step": 1317376 + }, + { + "epoch": 0.01, + "learning_rate": 2.8423694101599685e-05, + "loss": 3.5089, + "step": 1317888 + }, + { + "epoch": 0.01, + "learning_rate": 2.8415324532892894e-05, + "loss": 3.5042, + "step": 1318400 + }, + { + "epoch": 0.01, + "learning_rate": 2.8406938585382374e-05, + "loss": 3.5116, + "step": 1318912 + }, + { + "epoch": 0.01, + "learning_rate": 2.8398552637871857e-05, + "loss": 3.5036, + "step": 1319424 + }, + { + "epoch": 0.01, + "learning_rate": 2.8390166690361337e-05, + "loss": 3.5149, + "step": 1319936 + }, + { + "epoch": 0.01, + "learning_rate": 2.8381797121654546e-05, + "loss": 3.5123, + "step": 1320448 + }, + { + "epoch": 0.01, + "learning_rate": 2.8373411174144026e-05, + "loss": 3.517, + "step": 1320960 + }, + { + "epoch": 0.01, + "learning_rate": 2.8365025226633506e-05, + "loss": 3.5089, + "step": 1321472 + }, + { + "epoch": 0.01, + "learning_rate": 2.8356639279122986e-05, + "loss": 3.4961, + "step": 1321984 + }, + { + "epoch": 0.01, + "learning_rate": 2.8348253331612466e-05, + "loss": 3.5007, + "step": 1322496 + }, + { + "epoch": 0.01, + "learning_rate": 2.833988376290568e-05, + "loss": 3.5179, + "step": 1323008 + }, + { + "epoch": 0.01, + "learning_rate": 2.833149781539516e-05, + "loss": 3.5047, + "step": 1323520 + }, + { + "epoch": 0.01, + "learning_rate": 2.832311186788464e-05, + "loss": 3.5053, + "step": 1324032 + }, + { + "epoch": 0.01, + "learning_rate": 2.831472592037412e-05, + "loss": 3.4992, + "step": 1324544 + }, + { + "epoch": 0.01, + "learning_rate": 2.8306356351667328e-05, + "loss": 3.5045, + "step": 1325056 + }, + { + "epoch": 0.01, + "learning_rate": 2.829797040415681e-05, + "loss": 3.4887, + "step": 1325568 + }, + { + "epoch": 0.01, + "learning_rate": 2.828958445664629e-05, + "loss": 3.5185, + "step": 1326080 + }, + { + "epoch": 0.01, + "learning_rate": 2.828119850913577e-05, + "loss": 3.4934, + "step": 1326592 + }, + { + "epoch": 0.01, + "learning_rate": 2.827282894042898e-05, + "loss": 3.5129, + "step": 1327104 + }, + { + "epoch": 0.01, + "learning_rate": 2.826444299291846e-05, + "loss": 3.5107, + "step": 1327616 + }, + { + "epoch": 0.01, + "learning_rate": 2.825605704540794e-05, + "loss": 3.4947, + "step": 1328128 + }, + { + "epoch": 0.01, + "learning_rate": 2.824767109789742e-05, + "loss": 3.5123, + "step": 1328640 + }, + { + "epoch": 0.01, + "learning_rate": 2.8239301529190632e-05, + "loss": 3.5019, + "step": 1329152 + }, + { + "epoch": 0.01, + "learning_rate": 2.8230915581680112e-05, + "loss": 3.5049, + "step": 1329664 + }, + { + "epoch": 0.01, + "learning_rate": 2.8222529634169592e-05, + "loss": 3.4885, + "step": 1330176 + }, + { + "epoch": 0.01, + "learning_rate": 2.8214143686659072e-05, + "loss": 3.5117, + "step": 1330688 + }, + { + "epoch": 0.01, + "learning_rate": 2.820577411795228e-05, + "loss": 3.496, + "step": 1331200 + }, + { + "epoch": 0.01, + "learning_rate": 2.8197388170441765e-05, + "loss": 3.5028, + "step": 1331712 + }, + { + "epoch": 0.01, + "learning_rate": 2.8189002222931245e-05, + "loss": 3.4863, + "step": 1332224 + }, + { + "epoch": 0.01, + "learning_rate": 2.8180616275420725e-05, + "loss": 3.4985, + "step": 1332736 + }, + { + "epoch": 0.01, + "learning_rate": 2.8172246706713934e-05, + "loss": 3.5081, + "step": 1333248 + }, + { + "epoch": 0.01, + "learning_rate": 2.8163860759203414e-05, + "loss": 3.5111, + "step": 1333760 + }, + { + "epoch": 0.01, + "learning_rate": 2.8155474811692894e-05, + "loss": 3.5079, + "step": 1334272 + }, + { + "epoch": 0.01, + "learning_rate": 2.8147088864182373e-05, + "loss": 3.5071, + "step": 1334784 + }, + { + "epoch": 0.01, + "learning_rate": 2.8138719295475586e-05, + "loss": 3.5143, + "step": 1335296 + }, + { + "epoch": 0.01, + "learning_rate": 2.8130333347965066e-05, + "loss": 3.5048, + "step": 1335808 + }, + { + "epoch": 0.01, + "learning_rate": 2.8121947400454546e-05, + "loss": 3.5168, + "step": 1336320 + }, + { + "epoch": 0.01, + "learning_rate": 2.8113561452944026e-05, + "loss": 3.5029, + "step": 1336832 + }, + { + "epoch": 0.01, + "learning_rate": 2.8105191884237235e-05, + "loss": 3.5046, + "step": 1337344 + }, + { + "epoch": 0.01, + "learning_rate": 2.8096805936726718e-05, + "loss": 3.5018, + "step": 1337856 + }, + { + "epoch": 0.01, + "learning_rate": 2.8088419989216198e-05, + "loss": 3.5118, + "step": 1338368 + }, + { + "epoch": 0.01, + "learning_rate": 2.8080034041705678e-05, + "loss": 3.5091, + "step": 1338880 + }, + { + "epoch": 0.01, + "learning_rate": 2.8071664472998887e-05, + "loss": 3.5152, + "step": 1339392 + }, + { + "epoch": 0.01, + "learning_rate": 2.8063278525488367e-05, + "loss": 3.5037, + "step": 1339904 + }, + { + "epoch": 0.01, + "learning_rate": 2.8054892577977847e-05, + "loss": 3.4861, + "step": 1340416 + }, + { + "epoch": 0.01, + "learning_rate": 2.8046506630467327e-05, + "loss": 3.4985, + "step": 1340928 + }, + { + "epoch": 0.01, + "learning_rate": 2.803813706176054e-05, + "loss": 3.5042, + "step": 1341440 + }, + { + "epoch": 0.01, + "learning_rate": 2.802975111425002e-05, + "loss": 3.5016, + "step": 1341952 + }, + { + "epoch": 0.01, + "learning_rate": 2.80213651667395e-05, + "loss": 3.4964, + "step": 1342464 + }, + { + "epoch": 0.01, + "learning_rate": 2.801297921922898e-05, + "loss": 3.5109, + "step": 1342976 + }, + { + "epoch": 0.02, + "learning_rate": 2.800460965052219e-05, + "loss": 3.502, + "step": 1343488 + }, + { + "epoch": 0.02, + "learning_rate": 2.7996223703011672e-05, + "loss": 3.4978, + "step": 1344000 + }, + { + "epoch": 0.02, + "learning_rate": 2.7987837755501152e-05, + "loss": 3.5026, + "step": 1344512 + }, + { + "epoch": 0.02, + "learning_rate": 2.7979451807990632e-05, + "loss": 3.5111, + "step": 1345024 + }, + { + "epoch": 0.02, + "learning_rate": 2.797108223928384e-05, + "loss": 3.5149, + "step": 1345536 + }, + { + "epoch": 0.02, + "learning_rate": 2.796269629177332e-05, + "loss": 3.5195, + "step": 1346048 + }, + { + "epoch": 0.02, + "learning_rate": 2.79543103442628e-05, + "loss": 3.4902, + "step": 1346560 + }, + { + "epoch": 0.02, + "learning_rate": 2.794592439675228e-05, + "loss": 3.5041, + "step": 1347072 + }, + { + "epoch": 0.02, + "learning_rate": 2.7937554828045493e-05, + "loss": 3.5058, + "step": 1347584 + }, + { + "epoch": 0.02, + "learning_rate": 2.7929168880534973e-05, + "loss": 3.5057, + "step": 1348096 + }, + { + "epoch": 0.02, + "learning_rate": 2.7920782933024453e-05, + "loss": 3.5153, + "step": 1348608 + }, + { + "epoch": 0.02, + "learning_rate": 2.7912396985513933e-05, + "loss": 3.4952, + "step": 1349120 + }, + { + "epoch": 0.02, + "learning_rate": 2.7904027416807142e-05, + "loss": 3.499, + "step": 1349632 + }, + { + "epoch": 0.02, + "learning_rate": 2.7895641469296626e-05, + "loss": 3.5112, + "step": 1350144 + }, + { + "epoch": 0.02, + "learning_rate": 2.7887255521786106e-05, + "loss": 3.5129, + "step": 1350656 + }, + { + "epoch": 0.02, + "learning_rate": 2.7878869574275586e-05, + "loss": 3.4955, + "step": 1351168 + }, + { + "epoch": 0.02, + "learning_rate": 2.7870500005568795e-05, + "loss": 3.504, + "step": 1351680 + }, + { + "epoch": 0.02, + "learning_rate": 2.7862114058058275e-05, + "loss": 3.4981, + "step": 1352192 + }, + { + "epoch": 0.02, + "learning_rate": 2.7853728110547755e-05, + "loss": 3.4996, + "step": 1352704 + }, + { + "epoch": 0.02, + "learning_rate": 2.7845342163037234e-05, + "loss": 3.4958, + "step": 1353216 + }, + { + "epoch": 0.02, + "learning_rate": 2.7836956215526714e-05, + "loss": 3.4975, + "step": 1353728 + }, + { + "epoch": 0.02, + "learning_rate": 2.7828586646819927e-05, + "loss": 3.4956, + "step": 1354240 + }, + { + "epoch": 0.02, + "learning_rate": 2.7820200699309407e-05, + "loss": 3.5052, + "step": 1354752 + }, + { + "epoch": 0.02, + "learning_rate": 2.7811814751798887e-05, + "loss": 3.5002, + "step": 1355264 + }, + { + "epoch": 0.02, + "learning_rate": 2.7803428804288367e-05, + "loss": 3.5002, + "step": 1355776 + }, + { + "epoch": 0.02, + "learning_rate": 2.7795059235581576e-05, + "loss": 3.5158, + "step": 1356288 + }, + { + "epoch": 0.02, + "learning_rate": 2.778667328807106e-05, + "loss": 3.5133, + "step": 1356800 + }, + { + "epoch": 0.02, + "learning_rate": 2.777828734056054e-05, + "loss": 3.5071, + "step": 1357312 + }, + { + "epoch": 0.02, + "learning_rate": 2.776990139305002e-05, + "loss": 3.5074, + "step": 1357824 + }, + { + "epoch": 0.02, + "learning_rate": 2.7761531824343228e-05, + "loss": 3.5027, + "step": 1358336 + }, + { + "epoch": 0.02, + "learning_rate": 2.7753145876832708e-05, + "loss": 3.4986, + "step": 1358848 + }, + { + "epoch": 0.02, + "learning_rate": 2.7744759929322188e-05, + "loss": 3.4916, + "step": 1359360 + }, + { + "epoch": 0.02, + "learning_rate": 2.7736373981811668e-05, + "loss": 3.5026, + "step": 1359872 + }, + { + "epoch": 0.02, + "learning_rate": 2.772800441310488e-05, + "loss": 3.5052, + "step": 1360384 + }, + { + "epoch": 0.02, + "learning_rate": 2.771961846559436e-05, + "loss": 3.5051, + "step": 1360896 + }, + { + "epoch": 0.02, + "learning_rate": 2.771123251808384e-05, + "loss": 3.5031, + "step": 1361408 + }, + { + "epoch": 0.02, + "learning_rate": 2.770284657057332e-05, + "loss": 3.5052, + "step": 1361920 + }, + { + "epoch": 0.02, + "learning_rate": 2.769447700186653e-05, + "loss": 3.5026, + "step": 1362432 + }, + { + "epoch": 0.02, + "learning_rate": 2.7686091054356013e-05, + "loss": 3.4994, + "step": 1362944 + }, + { + "epoch": 0.02, + "learning_rate": 2.7677705106845493e-05, + "loss": 3.4983, + "step": 1363456 + }, + { + "epoch": 0.02, + "learning_rate": 2.7669319159334973e-05, + "loss": 3.5113, + "step": 1363968 + }, + { + "epoch": 0.02, + "learning_rate": 2.7660949590628182e-05, + "loss": 3.5094, + "step": 1364480 + }, + { + "epoch": 0.02, + "learning_rate": 2.7652563643117662e-05, + "loss": 3.5064, + "step": 1364992 + }, + { + "epoch": 0.02, + "learning_rate": 2.7644177695607142e-05, + "loss": 3.5006, + "step": 1365504 + }, + { + "epoch": 0.02, + "learning_rate": 2.7635791748096622e-05, + "loss": 3.5043, + "step": 1366016 + }, + { + "epoch": 0.02, + "learning_rate": 2.76274058005861e-05, + "loss": 3.5042, + "step": 1366528 + }, + { + "epoch": 0.02, + "learning_rate": 2.7619036231879314e-05, + "loss": 3.511, + "step": 1367040 + }, + { + "epoch": 0.02, + "learning_rate": 2.7610650284368794e-05, + "loss": 3.5009, + "step": 1367552 + }, + { + "epoch": 0.02, + "learning_rate": 2.7602264336858267e-05, + "loss": 3.5073, + "step": 1368064 + }, + { + "epoch": 0.02, + "learning_rate": 2.759387838934775e-05, + "loss": 3.5033, + "step": 1368576 + }, + { + "epoch": 0.02, + "learning_rate": 2.7585508820640967e-05, + "loss": 3.5037, + "step": 1369088 + }, + { + "epoch": 0.02, + "learning_rate": 2.7577122873130447e-05, + "loss": 3.5021, + "step": 1369600 + }, + { + "epoch": 0.02, + "learning_rate": 2.756873692561992e-05, + "loss": 3.5045, + "step": 1370112 + }, + { + "epoch": 0.02, + "learning_rate": 2.75603509781094e-05, + "loss": 3.5067, + "step": 1370624 + }, + { + "epoch": 0.02, + "learning_rate": 2.7551981409402616e-05, + "loss": 3.4948, + "step": 1371136 + }, + { + "epoch": 0.02, + "learning_rate": 2.7543595461892092e-05, + "loss": 3.5169, + "step": 1371648 + }, + { + "epoch": 0.02, + "learning_rate": 2.7535209514381572e-05, + "loss": 3.5038, + "step": 1372160 + }, + { + "epoch": 0.02, + "learning_rate": 2.7526823566871052e-05, + "loss": 3.5094, + "step": 1372672 + }, + { + "epoch": 0.02, + "learning_rate": 2.7518453998164268e-05, + "loss": 3.5064, + "step": 1373184 + }, + { + "epoch": 0.02, + "learning_rate": 2.751006805065374e-05, + "loss": 3.4946, + "step": 1373696 + }, + { + "epoch": 0.03, + "eval_loss": 3.8430843353271484, + "eval_runtime": 306.7261, + "eval_samples_per_second": 1244.078, + "eval_steps_per_second": 38.878, + "step": 1373749 + }, + { + "epoch": 0.0, + "learning_rate": 2.750168210314322e-05, + "loss": 3.4961, + "step": 1374208 + }, + { + "epoch": 0.0, + "learning_rate": 2.7493296155632704e-05, + "loss": 3.4919, + "step": 1374720 + }, + { + "epoch": 0.0, + "learning_rate": 2.7484910208122184e-05, + "loss": 3.5129, + "step": 1375232 + }, + { + "epoch": 0.0, + "learning_rate": 2.7476524260611664e-05, + "loss": 3.5, + "step": 1375744 + }, + { + "epoch": 0.0, + "learning_rate": 2.7468154691904873e-05, + "loss": 3.5123, + "step": 1376256 + }, + { + "epoch": 0.0, + "learning_rate": 2.7459768744394353e-05, + "loss": 3.499, + "step": 1376768 + }, + { + "epoch": 0.0, + "learning_rate": 2.7451382796883833e-05, + "loss": 3.5001, + "step": 1377280 + }, + { + "epoch": 0.0, + "learning_rate": 2.7442996849373313e-05, + "loss": 3.4882, + "step": 1377792 + }, + { + "epoch": 0.0, + "learning_rate": 2.7434627280666526e-05, + "loss": 3.4992, + "step": 1378304 + }, + { + "epoch": 0.0, + "learning_rate": 2.7426241333156006e-05, + "loss": 3.4973, + "step": 1378816 + }, + { + "epoch": 0.0, + "learning_rate": 2.7417855385645486e-05, + "loss": 3.5138, + "step": 1379328 + }, + { + "epoch": 0.0, + "learning_rate": 2.7409469438134966e-05, + "loss": 3.5047, + "step": 1379840 + }, + { + "epoch": 0.0, + "learning_rate": 2.740111624823191e-05, + "loss": 3.4898, + "step": 1380352 + }, + { + "epoch": 0.0, + "learning_rate": 2.739273030072139e-05, + "loss": 3.4906, + "step": 1380864 + }, + { + "epoch": 0.0, + "learning_rate": 2.7384344353210867e-05, + "loss": 3.5023, + "step": 1381376 + }, + { + "epoch": 0.0, + "learning_rate": 2.7375958405700347e-05, + "loss": 3.4827, + "step": 1381888 + }, + { + "epoch": 0.0, + "learning_rate": 2.7367572458189827e-05, + "loss": 3.5003, + "step": 1382400 + }, + { + "epoch": 0.0, + "learning_rate": 2.7359186510679307e-05, + "loss": 3.4994, + "step": 1382912 + }, + { + "epoch": 0.0, + "learning_rate": 2.7350800563168787e-05, + "loss": 3.492, + "step": 1383424 + }, + { + "epoch": 0.0, + "learning_rate": 2.7342414615658267e-05, + "loss": 3.5173, + "step": 1383936 + }, + { + "epoch": 0.0, + "learning_rate": 2.733404504695148e-05, + "loss": 3.4971, + "step": 1384448 + }, + { + "epoch": 0.0, + "learning_rate": 2.732565909944096e-05, + "loss": 3.4991, + "step": 1384960 + }, + { + "epoch": 0.0, + "learning_rate": 2.731727315193044e-05, + "loss": 3.493, + "step": 1385472 + }, + { + "epoch": 0.0, + "learning_rate": 2.730888720441992e-05, + "loss": 3.5142, + "step": 1385984 + }, + { + "epoch": 0.0, + "learning_rate": 2.730051763571313e-05, + "loss": 3.4853, + "step": 1386496 + }, + { + "epoch": 0.0, + "learning_rate": 2.7292131688202612e-05, + "loss": 3.5018, + "step": 1387008 + }, + { + "epoch": 0.0, + "learning_rate": 2.728374574069209e-05, + "loss": 3.4902, + "step": 1387520 + }, + { + "epoch": 0.0, + "learning_rate": 2.727535979318157e-05, + "loss": 3.495, + "step": 1388032 + }, + { + "epoch": 0.0, + "learning_rate": 2.726699022447478e-05, + "loss": 3.4973, + "step": 1388544 + }, + { + "epoch": 0.01, + "learning_rate": 2.725860427696426e-05, + "loss": 3.4931, + "step": 1389056 + }, + { + "epoch": 0.01, + "learning_rate": 2.725021832945374e-05, + "loss": 3.4982, + "step": 1389568 + }, + { + "epoch": 0.01, + "learning_rate": 2.724183238194322e-05, + "loss": 3.4968, + "step": 1390080 + }, + { + "epoch": 0.01, + "learning_rate": 2.7233462813236433e-05, + "loss": 3.4984, + "step": 1390592 + }, + { + "epoch": 0.01, + "learning_rate": 2.7225076865725913e-05, + "loss": 3.5084, + "step": 1391104 + }, + { + "epoch": 0.01, + "learning_rate": 2.7216690918215393e-05, + "loss": 3.4953, + "step": 1391616 + }, + { + "epoch": 0.01, + "learning_rate": 2.7208304970704873e-05, + "loss": 3.5009, + "step": 1392128 + }, + { + "epoch": 0.01, + "learning_rate": 2.7199935401998082e-05, + "loss": 3.4915, + "step": 1392640 + }, + { + "epoch": 0.01, + "learning_rate": 2.7191549454487565e-05, + "loss": 3.4949, + "step": 1393152 + }, + { + "epoch": 0.01, + "learning_rate": 2.7183163506977045e-05, + "loss": 3.4874, + "step": 1393664 + }, + { + "epoch": 0.01, + "learning_rate": 2.7174777559466525e-05, + "loss": 3.4933, + "step": 1394176 + }, + { + "epoch": 0.01, + "learning_rate": 2.7166391611956005e-05, + "loss": 3.4909, + "step": 1394688 + }, + { + "epoch": 0.01, + "learning_rate": 2.7158022043249214e-05, + "loss": 3.5029, + "step": 1395200 + }, + { + "epoch": 0.01, + "learning_rate": 2.7149636095738694e-05, + "loss": 3.4902, + "step": 1395712 + }, + { + "epoch": 0.01, + "learning_rate": 2.7141250148228174e-05, + "loss": 3.5011, + "step": 1396224 + }, + { + "epoch": 0.01, + "learning_rate": 2.7132864200717658e-05, + "loss": 3.5029, + "step": 1396736 + }, + { + "epoch": 0.01, + "learning_rate": 2.7124494632010867e-05, + "loss": 3.4988, + "step": 1397248 + }, + { + "epoch": 0.01, + "learning_rate": 2.7116108684500347e-05, + "loss": 3.4958, + "step": 1397760 + }, + { + "epoch": 0.01, + "learning_rate": 2.7107722736989827e-05, + "loss": 3.4838, + "step": 1398272 + }, + { + "epoch": 0.01, + "learning_rate": 2.7099336789479307e-05, + "loss": 3.4906, + "step": 1398784 + }, + { + "epoch": 0.01, + "learning_rate": 2.709096722077252e-05, + "loss": 3.503, + "step": 1399296 + }, + { + "epoch": 0.01, + "learning_rate": 2.7082581273262e-05, + "loss": 3.4924, + "step": 1399808 + }, + { + "epoch": 0.01, + "learning_rate": 2.707419532575148e-05, + "loss": 3.4956, + "step": 1400320 + }, + { + "epoch": 0.01, + "learning_rate": 2.706580937824096e-05, + "loss": 3.4822, + "step": 1400832 + }, + { + "epoch": 0.01, + "learning_rate": 2.7057439809534168e-05, + "loss": 3.4939, + "step": 1401344 + }, + { + "epoch": 0.01, + "learning_rate": 2.7049053862023648e-05, + "loss": 3.4751, + "step": 1401856 + }, + { + "epoch": 0.01, + "learning_rate": 2.7040667914513128e-05, + "loss": 3.5069, + "step": 1402368 + }, + { + "epoch": 0.01, + "learning_rate": 2.7032281967002608e-05, + "loss": 3.4792, + "step": 1402880 + }, + { + "epoch": 0.01, + "learning_rate": 2.702389601949209e-05, + "loss": 3.5019, + "step": 1403392 + }, + { + "epoch": 0.01, + "learning_rate": 2.70155264507853e-05, + "loss": 3.4936, + "step": 1403904 + }, + { + "epoch": 0.01, + "learning_rate": 2.700714050327478e-05, + "loss": 3.4814, + "step": 1404416 + }, + { + "epoch": 0.01, + "learning_rate": 2.699875455576426e-05, + "loss": 3.5014, + "step": 1404928 + }, + { + "epoch": 0.01, + "learning_rate": 2.699036860825374e-05, + "loss": 3.4913, + "step": 1405440 + }, + { + "epoch": 0.01, + "learning_rate": 2.6981999039546953e-05, + "loss": 3.4884, + "step": 1405952 + }, + { + "epoch": 0.01, + "learning_rate": 2.6973613092036433e-05, + "loss": 3.4786, + "step": 1406464 + }, + { + "epoch": 0.01, + "learning_rate": 2.6965227144525913e-05, + "loss": 3.5021, + "step": 1406976 + }, + { + "epoch": 0.01, + "learning_rate": 2.6956841197015393e-05, + "loss": 3.4828, + "step": 1407488 + }, + { + "epoch": 0.01, + "learning_rate": 2.69484716283086e-05, + "loss": 3.4885, + "step": 1408000 + }, + { + "epoch": 0.01, + "learning_rate": 2.694008568079808e-05, + "loss": 3.4753, + "step": 1408512 + }, + { + "epoch": 0.01, + "learning_rate": 2.693169973328756e-05, + "loss": 3.4856, + "step": 1409024 + }, + { + "epoch": 0.01, + "learning_rate": 2.6923313785777045e-05, + "loss": 3.4953, + "step": 1409536 + }, + { + "epoch": 0.01, + "learning_rate": 2.6914944217070254e-05, + "loss": 3.5003, + "step": 1410048 + }, + { + "epoch": 0.01, + "learning_rate": 2.6906558269559734e-05, + "loss": 3.4897, + "step": 1410560 + }, + { + "epoch": 0.01, + "learning_rate": 2.6898172322049214e-05, + "loss": 3.4985, + "step": 1411072 + }, + { + "epoch": 0.01, + "learning_rate": 2.6889786374538694e-05, + "loss": 3.4996, + "step": 1411584 + }, + { + "epoch": 0.01, + "learning_rate": 2.6881416805831906e-05, + "loss": 3.4942, + "step": 1412096 + }, + { + "epoch": 0.01, + "learning_rate": 2.6873030858321386e-05, + "loss": 3.4998, + "step": 1412608 + }, + { + "epoch": 0.01, + "learning_rate": 2.6864644910810866e-05, + "loss": 3.4941, + "step": 1413120 + }, + { + "epoch": 0.01, + "learning_rate": 2.6856258963300346e-05, + "loss": 3.4897, + "step": 1413632 + }, + { + "epoch": 0.01, + "learning_rate": 2.6847889394593555e-05, + "loss": 3.4893, + "step": 1414144 + }, + { + "epoch": 0.01, + "learning_rate": 2.6839503447083035e-05, + "loss": 3.4978, + "step": 1414656 + }, + { + "epoch": 0.01, + "learning_rate": 2.6831117499572515e-05, + "loss": 3.4994, + "step": 1415168 + }, + { + "epoch": 0.01, + "learning_rate": 2.6822731552062e-05, + "loss": 3.5028, + "step": 1415680 + }, + { + "epoch": 0.01, + "learning_rate": 2.6814361983355208e-05, + "loss": 3.4885, + "step": 1416192 + }, + { + "epoch": 0.01, + "learning_rate": 2.6805976035844688e-05, + "loss": 3.4684, + "step": 1416704 + }, + { + "epoch": 0.01, + "learning_rate": 2.6797590088334168e-05, + "loss": 3.4864, + "step": 1417216 + }, + { + "epoch": 0.01, + "learning_rate": 2.6789204140823644e-05, + "loss": 3.494, + "step": 1417728 + }, + { + "epoch": 0.01, + "learning_rate": 2.678083457211686e-05, + "loss": 3.4896, + "step": 1418240 + }, + { + "epoch": 0.01, + "learning_rate": 2.677244862460634e-05, + "loss": 3.4828, + "step": 1418752 + }, + { + "epoch": 0.01, + "learning_rate": 2.676406267709582e-05, + "loss": 3.497, + "step": 1419264 + }, + { + "epoch": 0.02, + "learning_rate": 2.6755676729585293e-05, + "loss": 3.4899, + "step": 1419776 + }, + { + "epoch": 0.02, + "learning_rate": 2.674730716087851e-05, + "loss": 3.4805, + "step": 1420288 + }, + { + "epoch": 0.02, + "learning_rate": 2.673892121336799e-05, + "loss": 3.4876, + "step": 1420800 + }, + { + "epoch": 0.02, + "learning_rate": 2.673053526585747e-05, + "loss": 3.5014, + "step": 1421312 + }, + { + "epoch": 0.02, + "learning_rate": 2.6722149318346945e-05, + "loss": 3.4991, + "step": 1421824 + }, + { + "epoch": 0.02, + "learning_rate": 2.671377974964016e-05, + "loss": 3.5031, + "step": 1422336 + }, + { + "epoch": 0.02, + "learning_rate": 2.670539380212964e-05, + "loss": 3.484, + "step": 1422848 + }, + { + "epoch": 0.02, + "learning_rate": 2.6697007854619114e-05, + "loss": 3.491, + "step": 1423360 + }, + { + "epoch": 0.02, + "learning_rate": 2.6688621907108598e-05, + "loss": 3.4912, + "step": 1423872 + }, + { + "epoch": 0.02, + "learning_rate": 2.6680252338401814e-05, + "loss": 3.4939, + "step": 1424384 + }, + { + "epoch": 0.02, + "learning_rate": 2.6671866390891294e-05, + "loss": 3.4991, + "step": 1424896 + }, + { + "epoch": 0.02, + "learning_rate": 2.6663480443380767e-05, + "loss": 3.4844, + "step": 1425408 + }, + { + "epoch": 0.02, + "learning_rate": 2.6655094495870247e-05, + "loss": 3.4878, + "step": 1425920 + }, + { + "epoch": 0.02, + "learning_rate": 2.6646724927163463e-05, + "loss": 3.4969, + "step": 1426432 + }, + { + "epoch": 0.02, + "learning_rate": 2.6638338979652943e-05, + "loss": 3.5013, + "step": 1426944 + }, + { + "epoch": 0.02, + "learning_rate": 2.662995303214242e-05, + "loss": 3.4834, + "step": 1427456 + }, + { + "epoch": 0.02, + "learning_rate": 2.66215670846319e-05, + "loss": 3.4894, + "step": 1427968 + }, + { + "epoch": 0.02, + "learning_rate": 2.6613197515925115e-05, + "loss": 3.4894, + "step": 1428480 + }, + { + "epoch": 0.02, + "learning_rate": 2.6604811568414588e-05, + "loss": 3.4876, + "step": 1428992 + }, + { + "epoch": 0.02, + "learning_rate": 2.6596425620904068e-05, + "loss": 3.479, + "step": 1429504 + }, + { + "epoch": 0.02, + "learning_rate": 2.658803967339355e-05, + "loss": 3.4829, + "step": 1430016 + }, + { + "epoch": 0.02, + "learning_rate": 2.6579670104686767e-05, + "loss": 3.4857, + "step": 1430528 + }, + { + "epoch": 0.02, + "learning_rate": 2.657128415717624e-05, + "loss": 3.492, + "step": 1431040 + }, + { + "epoch": 0.02, + "learning_rate": 2.656289820966572e-05, + "loss": 3.4847, + "step": 1431552 + }, + { + "epoch": 0.02, + "learning_rate": 2.65545122621552e-05, + "loss": 3.4881, + "step": 1432064 + }, + { + "epoch": 0.02, + "learning_rate": 2.6546142693448416e-05, + "loss": 3.503, + "step": 1432576 + }, + { + "epoch": 0.02, + "learning_rate": 2.6537756745937893e-05, + "loss": 3.5014, + "step": 1433088 + }, + { + "epoch": 0.02, + "learning_rate": 2.6529370798427373e-05, + "loss": 3.4936, + "step": 1433600 + }, + { + "epoch": 0.02, + "learning_rate": 2.6520984850916853e-05, + "loss": 3.4966, + "step": 1434112 + }, + { + "epoch": 0.02, + "learning_rate": 2.6512615282210062e-05, + "loss": 3.4887, + "step": 1434624 + }, + { + "epoch": 0.02, + "learning_rate": 2.6504229334699542e-05, + "loss": 3.4835, + "step": 1435136 + }, + { + "epoch": 0.02, + "learning_rate": 2.6495843387189022e-05, + "loss": 3.481, + "step": 1435648 + }, + { + "epoch": 0.02, + "learning_rate": 2.6487457439678505e-05, + "loss": 3.4856, + "step": 1436160 + }, + { + "epoch": 0.02, + "learning_rate": 2.6479087870971714e-05, + "loss": 3.492, + "step": 1436672 + }, + { + "epoch": 0.02, + "learning_rate": 2.6470701923461194e-05, + "loss": 3.4965, + "step": 1437184 + }, + { + "epoch": 0.02, + "learning_rate": 2.6462315975950674e-05, + "loss": 3.4878, + "step": 1437696 + }, + { + "epoch": 0.02, + "learning_rate": 2.6453930028440154e-05, + "loss": 3.4925, + "step": 1438208 + }, + { + "epoch": 0.02, + "learning_rate": 2.6445560459733367e-05, + "loss": 3.4913, + "step": 1438720 + }, + { + "epoch": 0.02, + "learning_rate": 2.6437174512222847e-05, + "loss": 3.485, + "step": 1439232 + }, + { + "epoch": 0.02, + "learning_rate": 2.6428788564712326e-05, + "loss": 3.4854, + "step": 1439744 + }, + { + "epoch": 0.02, + "learning_rate": 2.6420402617201806e-05, + "loss": 3.4989, + "step": 1440256 + }, + { + "epoch": 0.02, + "learning_rate": 2.6412033048495016e-05, + "loss": 3.4982, + "step": 1440768 + }, + { + "epoch": 0.02, + "learning_rate": 2.6403647100984495e-05, + "loss": 3.495, + "step": 1441280 + }, + { + "epoch": 0.02, + "learning_rate": 2.6395261153473975e-05, + "loss": 3.4873, + "step": 1441792 + }, + { + "epoch": 0.02, + "learning_rate": 2.638687520596346e-05, + "loss": 3.4897, + "step": 1442304 + }, + { + "epoch": 0.02, + "learning_rate": 2.6378505637256668e-05, + "loss": 3.4924, + "step": 1442816 + }, + { + "epoch": 0.02, + "learning_rate": 2.6370119689746148e-05, + "loss": 3.5052, + "step": 1443328 + }, + { + "epoch": 0.02, + "learning_rate": 2.6361733742235628e-05, + "loss": 3.4881, + "step": 1443840 + }, + { + "epoch": 0.02, + "learning_rate": 2.6353347794725108e-05, + "loss": 3.4917, + "step": 1444352 + }, + { + "epoch": 0.02, + "learning_rate": 2.634497822601832e-05, + "loss": 3.4885, + "step": 1444864 + }, + { + "epoch": 0.02, + "learning_rate": 2.63365922785078e-05, + "loss": 3.4932, + "step": 1445376 + }, + { + "epoch": 0.02, + "learning_rate": 2.632820633099728e-05, + "loss": 3.4872, + "step": 1445888 + }, + { + "epoch": 0.02, + "learning_rate": 2.631982038348676e-05, + "loss": 3.4914, + "step": 1446400 + }, + { + "epoch": 0.02, + "learning_rate": 2.631145081477997e-05, + "loss": 3.4957, + "step": 1446912 + }, + { + "epoch": 0.02, + "learning_rate": 2.630306486726945e-05, + "loss": 3.4805, + "step": 1447424 + }, + { + "epoch": 0.02, + "learning_rate": 2.629467891975893e-05, + "loss": 3.5021, + "step": 1447936 + }, + { + "epoch": 0.02, + "learning_rate": 2.6286292972248412e-05, + "loss": 3.4953, + "step": 1448448 + }, + { + "epoch": 0.02, + "learning_rate": 2.627792340354162e-05, + "loss": 3.4923, + "step": 1448960 + }, + { + "epoch": 0.02, + "learning_rate": 2.62695374560311e-05, + "loss": 3.4928, + "step": 1449472 + }, + { + "epoch": 0.02, + "learning_rate": 2.626115150852058e-05, + "loss": 3.4805, + "step": 1449984 + }, + { + "epoch": 0.03, + "eval_loss": 3.843136787414551, + "eval_runtime": 310.7009, + "eval_samples_per_second": 1228.162, + "eval_steps_per_second": 38.381, + "step": 1450069 + }, + { + "epoch": 1.0, + "learning_rate": 2.625276556101006e-05, + "loss": 3.4908, + "step": 1450496 + }, + { + "epoch": 1.0, + "learning_rate": 2.6244395992303274e-05, + "loss": 3.4801, + "step": 1451008 + }, + { + "epoch": 1.0, + "learning_rate": 2.6236010044792754e-05, + "loss": 3.5023, + "step": 1451520 + }, + { + "epoch": 1.0, + "learning_rate": 2.6227624097282234e-05, + "loss": 3.4848, + "step": 1452032 + }, + { + "epoch": 1.0, + "learning_rate": 2.6219238149771714e-05, + "loss": 3.5006, + "step": 1452544 + }, + { + "epoch": 1.0, + "learning_rate": 2.6210868581064923e-05, + "loss": 3.4845, + "step": 1453056 + }, + { + "epoch": 1.0, + "learning_rate": 2.6202482633554403e-05, + "loss": 3.4898, + "step": 1453568 + }, + { + "epoch": 1.0, + "learning_rate": 2.6194096686043883e-05, + "loss": 3.4742, + "step": 1454080 + }, + { + "epoch": 1.0, + "learning_rate": 2.6185710738533366e-05, + "loss": 3.491, + "step": 1454592 + }, + { + "epoch": 1.0, + "learning_rate": 2.6177341169826575e-05, + "loss": 3.4825, + "step": 1455104 + }, + { + "epoch": 1.0, + "learning_rate": 2.6168955222316055e-05, + "loss": 3.5012, + "step": 1455616 + }, + { + "epoch": 1.0, + "learning_rate": 2.6160569274805535e-05, + "loss": 3.4898, + "step": 1456128 + }, + { + "epoch": 1.0, + "learning_rate": 2.6152199706098744e-05, + "loss": 3.4764, + "step": 1456640 + }, + { + "epoch": 1.0, + "learning_rate": 2.6143813758588228e-05, + "loss": 3.4787, + "step": 1457152 + }, + { + "epoch": 1.0, + "learning_rate": 2.6135427811077708e-05, + "loss": 3.4894, + "step": 1457664 + }, + { + "epoch": 1.0, + "learning_rate": 2.6127041863567187e-05, + "loss": 3.4746, + "step": 1458176 + }, + { + "epoch": 1.0, + "learning_rate": 2.6118655916056667e-05, + "loss": 3.4846, + "step": 1458688 + }, + { + "epoch": 1.0, + "learning_rate": 2.6110269968546147e-05, + "loss": 3.4856, + "step": 1459200 + }, + { + "epoch": 1.0, + "learning_rate": 2.6101884021035627e-05, + "loss": 3.4812, + "step": 1459712 + }, + { + "epoch": 1.0, + "learning_rate": 2.6093498073525107e-05, + "loss": 3.5068, + "step": 1460224 + }, + { + "epoch": 1.0, + "learning_rate": 2.6085128504818316e-05, + "loss": 3.4877, + "step": 1460736 + }, + { + "epoch": 1.0, + "learning_rate": 2.60767425573078e-05, + "loss": 3.4847, + "step": 1461248 + }, + { + "epoch": 1.0, + "learning_rate": 2.606835660979728e-05, + "loss": 3.4815, + "step": 1461760 + }, + { + "epoch": 1.0, + "learning_rate": 2.605997066228676e-05, + "loss": 3.4995, + "step": 1462272 + }, + { + "epoch": 1.0, + "learning_rate": 2.605160109357997e-05, + "loss": 3.4763, + "step": 1462784 + }, + { + "epoch": 1.0, + "learning_rate": 2.604321514606945e-05, + "loss": 3.4854, + "step": 1463296 + }, + { + "epoch": 1.0, + "learning_rate": 2.603482919855893e-05, + "loss": 3.4787, + "step": 1463808 + }, + { + "epoch": 1.0, + "learning_rate": 2.602644325104841e-05, + "loss": 3.4854, + "step": 1464320 + }, + { + "epoch": 1.0, + "learning_rate": 2.601807368234162e-05, + "loss": 3.4837, + "step": 1464832 + }, + { + "epoch": 1.01, + "learning_rate": 2.60096877348311e-05, + "loss": 3.481, + "step": 1465344 + }, + { + "epoch": 1.01, + "learning_rate": 2.600130178732058e-05, + "loss": 3.4884, + "step": 1465856 + }, + { + "epoch": 1.01, + "learning_rate": 2.599291583981006e-05, + "loss": 3.4829, + "step": 1466368 + }, + { + "epoch": 1.01, + "learning_rate": 2.598454627110327e-05, + "loss": 3.4869, + "step": 1466880 + }, + { + "epoch": 1.01, + "learning_rate": 2.5976160323592753e-05, + "loss": 3.4957, + "step": 1467392 + }, + { + "epoch": 1.01, + "learning_rate": 2.5967774376082233e-05, + "loss": 3.4822, + "step": 1467904 + }, + { + "epoch": 1.01, + "learning_rate": 2.5959388428571713e-05, + "loss": 3.4896, + "step": 1468416 + }, + { + "epoch": 1.01, + "learning_rate": 2.5951018859864922e-05, + "loss": 3.476, + "step": 1468928 + }, + { + "epoch": 1.01, + "learning_rate": 2.5942632912354402e-05, + "loss": 3.4857, + "step": 1469440 + }, + { + "epoch": 1.01, + "learning_rate": 2.5934246964843882e-05, + "loss": 3.4769, + "step": 1469952 + }, + { + "epoch": 1.01, + "learning_rate": 2.5925861017333362e-05, + "loss": 3.4819, + "step": 1470464 + }, + { + "epoch": 1.01, + "learning_rate": 2.5917491448626575e-05, + "loss": 3.4793, + "step": 1470976 + }, + { + "epoch": 1.01, + "learning_rate": 2.5909105501116055e-05, + "loss": 3.4926, + "step": 1471488 + }, + { + "epoch": 1.01, + "learning_rate": 2.5900719553605535e-05, + "loss": 3.476, + "step": 1472000 + }, + { + "epoch": 1.01, + "learning_rate": 2.5892333606095015e-05, + "loss": 3.485, + "step": 1472512 + }, + { + "epoch": 1.01, + "learning_rate": 2.5883964037388224e-05, + "loss": 3.4932, + "step": 1473024 + }, + { + "epoch": 1.01, + "learning_rate": 2.5875578089877707e-05, + "loss": 3.49, + "step": 1473536 + }, + { + "epoch": 1.01, + "learning_rate": 2.5867192142367187e-05, + "loss": 3.4866, + "step": 1474048 + }, + { + "epoch": 1.01, + "learning_rate": 2.5858806194856667e-05, + "loss": 3.4704, + "step": 1474560 + }, + { + "epoch": 1.01, + "learning_rate": 2.5850436626149876e-05, + "loss": 3.4745, + "step": 1475072 + }, + { + "epoch": 1.01, + "learning_rate": 2.5842050678639356e-05, + "loss": 3.4854, + "step": 1475584 + }, + { + "epoch": 1.01, + "learning_rate": 2.5833664731128836e-05, + "loss": 3.4834, + "step": 1476096 + }, + { + "epoch": 1.01, + "learning_rate": 2.5825278783618316e-05, + "loss": 3.4849, + "step": 1476608 + }, + { + "epoch": 1.01, + "learning_rate": 2.581690921491153e-05, + "loss": 3.4741, + "step": 1477120 + }, + { + "epoch": 1.01, + "learning_rate": 2.580852326740101e-05, + "loss": 3.4817, + "step": 1477632 + }, + { + "epoch": 1.01, + "learning_rate": 2.580013731989049e-05, + "loss": 3.4639, + "step": 1478144 + }, + { + "epoch": 1.01, + "learning_rate": 2.5791751372379968e-05, + "loss": 3.4885, + "step": 1478656 + }, + { + "epoch": 1.01, + "learning_rate": 2.5783381803673177e-05, + "loss": 3.4722, + "step": 1479168 + }, + { + "epoch": 1.01, + "learning_rate": 2.577499585616266e-05, + "loss": 3.4849, + "step": 1479680 + }, + { + "epoch": 1.01, + "learning_rate": 2.576660990865214e-05, + "loss": 3.4839, + "step": 1480192 + }, + { + "epoch": 1.01, + "learning_rate": 2.5758223961141614e-05, + "loss": 3.4693, + "step": 1480704 + }, + { + "epoch": 1.01, + "learning_rate": 2.574985439243483e-05, + "loss": 3.4867, + "step": 1481216 + }, + { + "epoch": 1.01, + "learning_rate": 2.574146844492431e-05, + "loss": 3.479, + "step": 1481728 + }, + { + "epoch": 1.01, + "learning_rate": 2.573308249741379e-05, + "loss": 3.4769, + "step": 1482240 + }, + { + "epoch": 1.01, + "learning_rate": 2.5724696549903266e-05, + "loss": 3.4639, + "step": 1482752 + }, + { + "epoch": 1.01, + "learning_rate": 2.5716326981196482e-05, + "loss": 3.4867, + "step": 1483264 + }, + { + "epoch": 1.01, + "learning_rate": 2.5707941033685962e-05, + "loss": 3.474, + "step": 1483776 + }, + { + "epoch": 1.01, + "learning_rate": 2.5699555086175442e-05, + "loss": 3.4774, + "step": 1484288 + }, + { + "epoch": 1.01, + "learning_rate": 2.5691169138664915e-05, + "loss": 3.4638, + "step": 1484800 + }, + { + "epoch": 1.01, + "learning_rate": 2.568279956995813e-05, + "loss": 3.4707, + "step": 1485312 + }, + { + "epoch": 1.01, + "learning_rate": 2.5674413622447614e-05, + "loss": 3.4806, + "step": 1485824 + }, + { + "epoch": 1.01, + "learning_rate": 2.5666027674937088e-05, + "loss": 3.491, + "step": 1486336 + }, + { + "epoch": 1.01, + "learning_rate": 2.5657641727426568e-05, + "loss": 3.4761, + "step": 1486848 + }, + { + "epoch": 1.01, + "learning_rate": 2.5649272158719783e-05, + "loss": 3.488, + "step": 1487360 + }, + { + "epoch": 1.01, + "learning_rate": 2.5640886211209263e-05, + "loss": 3.489, + "step": 1487872 + }, + { + "epoch": 1.01, + "learning_rate": 2.563250026369874e-05, + "loss": 3.479, + "step": 1488384 + }, + { + "epoch": 1.01, + "learning_rate": 2.5624130694991956e-05, + "loss": 3.4862, + "step": 1488896 + }, + { + "epoch": 1.01, + "learning_rate": 2.5615744747481436e-05, + "loss": 3.4824, + "step": 1489408 + }, + { + "epoch": 1.01, + "learning_rate": 2.560735879997091e-05, + "loss": 3.4789, + "step": 1489920 + }, + { + "epoch": 1.01, + "learning_rate": 2.559897285246039e-05, + "loss": 3.4777, + "step": 1490432 + }, + { + "epoch": 1.01, + "learning_rate": 2.5590603283753605e-05, + "loss": 3.4834, + "step": 1490944 + }, + { + "epoch": 1.01, + "learning_rate": 2.5582217336243085e-05, + "loss": 3.488, + "step": 1491456 + }, + { + "epoch": 1.01, + "learning_rate": 2.557383138873256e-05, + "loss": 3.4898, + "step": 1491968 + }, + { + "epoch": 1.01, + "learning_rate": 2.556544544122204e-05, + "loss": 3.4772, + "step": 1492480 + }, + { + "epoch": 1.01, + "learning_rate": 2.5557075872515257e-05, + "loss": 3.4604, + "step": 1492992 + }, + { + "epoch": 1.01, + "learning_rate": 2.5548689925004737e-05, + "loss": 3.4745, + "step": 1493504 + }, + { + "epoch": 1.01, + "learning_rate": 2.5540303977494214e-05, + "loss": 3.4776, + "step": 1494016 + }, + { + "epoch": 1.01, + "learning_rate": 2.5531918029983694e-05, + "loss": 3.4818, + "step": 1494528 + }, + { + "epoch": 1.01, + "learning_rate": 2.552354846127691e-05, + "loss": 3.4699, + "step": 1495040 + }, + { + "epoch": 1.01, + "learning_rate": 2.5515162513766383e-05, + "loss": 3.482, + "step": 1495552 + }, + { + "epoch": 1.02, + "learning_rate": 2.55067929450596e-05, + "loss": 3.4781, + "step": 1496064 + }, + { + "epoch": 1.02, + "learning_rate": 2.549840699754908e-05, + "loss": 3.4696, + "step": 1496576 + }, + { + "epoch": 1.02, + "learning_rate": 2.549002105003856e-05, + "loss": 3.4801, + "step": 1497088 + }, + { + "epoch": 1.02, + "learning_rate": 2.5481635102528035e-05, + "loss": 3.4869, + "step": 1497600 + }, + { + "epoch": 1.02, + "learning_rate": 2.5473249155017515e-05, + "loss": 3.4851, + "step": 1498112 + }, + { + "epoch": 1.02, + "learning_rate": 2.5464863207506995e-05, + "loss": 3.4943, + "step": 1498624 + }, + { + "epoch": 1.02, + "learning_rate": 2.5456477259996475e-05, + "loss": 3.4733, + "step": 1499136 + }, + { + "epoch": 1.02, + "learning_rate": 2.5448091312485955e-05, + "loss": 3.4778, + "step": 1499648 + }, + { + "epoch": 1.02, + "learning_rate": 2.5439721743779167e-05, + "loss": 3.4799, + "step": 1500160 + }, + { + "epoch": 1.02, + "learning_rate": 2.5431335796268647e-05, + "loss": 3.4832, + "step": 1500672 + }, + { + "epoch": 1.02, + "learning_rate": 2.5422949848758127e-05, + "loss": 3.4865, + "step": 1501184 + }, + { + "epoch": 1.02, + "learning_rate": 2.5414563901247607e-05, + "loss": 3.473, + "step": 1501696 + }, + { + "epoch": 1.02, + "learning_rate": 2.5406194332540816e-05, + "loss": 3.4771, + "step": 1502208 + }, + { + "epoch": 1.02, + "learning_rate": 2.5397808385030296e-05, + "loss": 3.4833, + "step": 1502720 + }, + { + "epoch": 1.02, + "learning_rate": 2.5389422437519776e-05, + "loss": 3.4891, + "step": 1503232 + }, + { + "epoch": 1.02, + "learning_rate": 2.538103649000926e-05, + "loss": 3.47, + "step": 1503744 + }, + { + "epoch": 1.02, + "learning_rate": 2.537266692130247e-05, + "loss": 3.481, + "step": 1504256 + }, + { + "epoch": 1.02, + "learning_rate": 2.536428097379195e-05, + "loss": 3.479, + "step": 1504768 + }, + { + "epoch": 1.02, + "learning_rate": 2.535589502628143e-05, + "loss": 3.4756, + "step": 1505280 + }, + { + "epoch": 1.02, + "learning_rate": 2.534750907877091e-05, + "loss": 3.466, + "step": 1505792 + }, + { + "epoch": 1.02, + "learning_rate": 2.533913951006412e-05, + "loss": 3.4723, + "step": 1506304 + }, + { + "epoch": 1.02, + "learning_rate": 2.53307535625536e-05, + "loss": 3.4783, + "step": 1506816 + }, + { + "epoch": 1.02, + "learning_rate": 2.532236761504308e-05, + "loss": 3.4737, + "step": 1507328 + }, + { + "epoch": 1.02, + "learning_rate": 2.531398166753256e-05, + "loss": 3.4763, + "step": 1507840 + }, + { + "epoch": 1.02, + "learning_rate": 2.530561209882577e-05, + "loss": 3.4744, + "step": 1508352 + }, + { + "epoch": 1.02, + "learning_rate": 2.529722615131525e-05, + "loss": 3.4904, + "step": 1508864 + }, + { + "epoch": 1.02, + "learning_rate": 2.528884020380473e-05, + "loss": 3.4898, + "step": 1509376 + }, + { + "epoch": 1.02, + "learning_rate": 2.528045425629421e-05, + "loss": 3.482, + "step": 1509888 + }, + { + "epoch": 1.02, + "learning_rate": 2.5272084687587422e-05, + "loss": 3.4818, + "step": 1510400 + }, + { + "epoch": 1.02, + "learning_rate": 2.5263698740076902e-05, + "loss": 3.4763, + "step": 1510912 + }, + { + "epoch": 1.02, + "learning_rate": 2.5255312792566382e-05, + "loss": 3.4743, + "step": 1511424 + }, + { + "epoch": 1.02, + "learning_rate": 2.5246926845055862e-05, + "loss": 3.4684, + "step": 1511936 + }, + { + "epoch": 1.02, + "learning_rate": 2.5238557276349075e-05, + "loss": 3.4704, + "step": 1512448 + }, + { + "epoch": 1.02, + "learning_rate": 2.5230171328838555e-05, + "loss": 3.4805, + "step": 1512960 + }, + { + "epoch": 1.02, + "learning_rate": 2.5221785381328035e-05, + "loss": 3.4828, + "step": 1513472 + }, + { + "epoch": 1.02, + "learning_rate": 2.5213399433817515e-05, + "loss": 3.4744, + "step": 1513984 + }, + { + "epoch": 1.02, + "learning_rate": 2.5205029865110724e-05, + "loss": 3.4814, + "step": 1514496 + }, + { + "epoch": 1.02, + "learning_rate": 2.5196643917600204e-05, + "loss": 3.4779, + "step": 1515008 + }, + { + "epoch": 1.02, + "learning_rate": 2.5188257970089684e-05, + "loss": 3.4717, + "step": 1515520 + }, + { + "epoch": 1.02, + "learning_rate": 2.5179872022579163e-05, + "loss": 3.4731, + "step": 1516032 + }, + { + "epoch": 1.02, + "learning_rate": 2.5171502453872376e-05, + "loss": 3.4889, + "step": 1516544 + }, + { + "epoch": 1.02, + "learning_rate": 2.5163116506361856e-05, + "loss": 3.4888, + "step": 1517056 + }, + { + "epoch": 1.02, + "learning_rate": 2.5154730558851336e-05, + "loss": 3.4806, + "step": 1517568 + }, + { + "epoch": 1.02, + "learning_rate": 2.5146344611340816e-05, + "loss": 3.476, + "step": 1518080 + }, + { + "epoch": 1.02, + "learning_rate": 2.5137975042634025e-05, + "loss": 3.4769, + "step": 1518592 + }, + { + "epoch": 1.02, + "learning_rate": 2.5129589095123508e-05, + "loss": 3.4775, + "step": 1519104 + }, + { + "epoch": 1.02, + "learning_rate": 2.5121203147612988e-05, + "loss": 3.4929, + "step": 1519616 + }, + { + "epoch": 1.02, + "learning_rate": 2.5112817200102468e-05, + "loss": 3.4769, + "step": 1520128 + }, + { + "epoch": 1.02, + "learning_rate": 2.5104447631395677e-05, + "loss": 3.4826, + "step": 1520640 + }, + { + "epoch": 1.02, + "learning_rate": 2.5096061683885157e-05, + "loss": 3.4729, + "step": 1521152 + }, + { + "epoch": 1.02, + "learning_rate": 2.5087675736374637e-05, + "loss": 3.483, + "step": 1521664 + }, + { + "epoch": 1.02, + "learning_rate": 2.5079289788864117e-05, + "loss": 3.4764, + "step": 1522176 + }, + { + "epoch": 1.02, + "learning_rate": 2.507092022015733e-05, + "loss": 3.4782, + "step": 1522688 + }, + { + "epoch": 1.02, + "learning_rate": 2.506253427264681e-05, + "loss": 3.4846, + "step": 1523200 + }, + { + "epoch": 1.02, + "learning_rate": 2.505414832513629e-05, + "loss": 3.4717, + "step": 1523712 + }, + { + "epoch": 1.02, + "learning_rate": 2.504576237762577e-05, + "loss": 3.4856, + "step": 1524224 + }, + { + "epoch": 1.02, + "learning_rate": 2.503739280891898e-05, + "loss": 3.4874, + "step": 1524736 + }, + { + "epoch": 1.02, + "learning_rate": 2.5029006861408462e-05, + "loss": 3.4813, + "step": 1525248 + }, + { + "epoch": 1.02, + "learning_rate": 2.5020620913897942e-05, + "loss": 3.4813, + "step": 1525760 + }, + { + "epoch": 1.02, + "learning_rate": 2.5012234966387422e-05, + "loss": 3.4665, + "step": 1526272 + }, + { + "epoch": 1.03, + "eval_loss": 3.846986770629883, + "eval_runtime": 304.1567, + "eval_samples_per_second": 1254.587, + "eval_steps_per_second": 39.207, + "step": 1526389 + }, + { + "epoch": 0.0, + "learning_rate": 2.500386539768063e-05, + "loss": 3.4701, + "step": 1526784 + }, + { + "epoch": 0.0, + "learning_rate": 2.499547945017011e-05, + "loss": 3.4677, + "step": 1527296 + }, + { + "epoch": 0.0, + "learning_rate": 2.498709350265959e-05, + "loss": 3.4867, + "step": 1527808 + }, + { + "epoch": 0.0, + "learning_rate": 2.497870755514907e-05, + "loss": 3.4761, + "step": 1528320 + }, + { + "epoch": 0.0, + "learning_rate": 2.4970337986442283e-05, + "loss": 3.4904, + "step": 1528832 + }, + { + "epoch": 0.0, + "learning_rate": 2.4961952038931763e-05, + "loss": 3.4725, + "step": 1529344 + }, + { + "epoch": 0.0, + "learning_rate": 2.4953566091421243e-05, + "loss": 3.4813, + "step": 1529856 + }, + { + "epoch": 0.0, + "learning_rate": 2.4945180143910723e-05, + "loss": 3.4633, + "step": 1530368 + }, + { + "epoch": 0.0, + "learning_rate": 2.4936810575203932e-05, + "loss": 3.4788, + "step": 1530880 + }, + { + "epoch": 0.0, + "learning_rate": 2.4928424627693416e-05, + "loss": 3.4679, + "step": 1531392 + }, + { + "epoch": 0.0, + "learning_rate": 2.4920038680182896e-05, + "loss": 3.4872, + "step": 1531904 + }, + { + "epoch": 0.0, + "learning_rate": 2.4911652732672372e-05, + "loss": 3.4829, + "step": 1532416 + }, + { + "epoch": 0.0, + "learning_rate": 2.4903299542769314e-05, + "loss": 3.4617, + "step": 1532928 + }, + { + "epoch": 0.0, + "learning_rate": 2.4894913595258794e-05, + "loss": 3.4684, + "step": 1533440 + }, + { + "epoch": 0.0, + "learning_rate": 2.4886527647748277e-05, + "loss": 3.475, + "step": 1533952 + }, + { + "epoch": 0.0, + "learning_rate": 2.4878141700237757e-05, + "loss": 3.4651, + "step": 1534464 + }, + { + "epoch": 0.0, + "learning_rate": 2.4869755752727237e-05, + "loss": 3.4713, + "step": 1534976 + }, + { + "epoch": 0.0, + "learning_rate": 2.4861369805216717e-05, + "loss": 3.473, + "step": 1535488 + }, + { + "epoch": 0.0, + "learning_rate": 2.4852983857706197e-05, + "loss": 3.4718, + "step": 1536000 + }, + { + "epoch": 0.0, + "learning_rate": 2.4844597910195673e-05, + "loss": 3.493, + "step": 1536512 + }, + { + "epoch": 0.0, + "learning_rate": 2.4836228341488886e-05, + "loss": 3.4738, + "step": 1537024 + }, + { + "epoch": 0.0, + "learning_rate": 2.482784239397837e-05, + "loss": 3.472, + "step": 1537536 + }, + { + "epoch": 0.0, + "learning_rate": 2.4819456446467846e-05, + "loss": 3.4728, + "step": 1538048 + }, + { + "epoch": 0.0, + "learning_rate": 2.4811070498957326e-05, + "loss": 3.4833, + "step": 1538560 + }, + { + "epoch": 0.0, + "learning_rate": 2.4802700930250538e-05, + "loss": 3.4674, + "step": 1539072 + }, + { + "epoch": 0.0, + "learning_rate": 2.4794314982740018e-05, + "loss": 3.4787, + "step": 1539584 + }, + { + "epoch": 0.0, + "learning_rate": 2.4785929035229495e-05, + "loss": 3.4656, + "step": 1540096 + }, + { + "epoch": 0.0, + "learning_rate": 2.4777543087718978e-05, + "loss": 3.4707, + "step": 1540608 + }, + { + "epoch": 0.0, + "learning_rate": 2.476917351901219e-05, + "loss": 3.4698, + "step": 1541120 + }, + { + "epoch": 0.0, + "learning_rate": 2.476078757150167e-05, + "loss": 3.4714, + "step": 1541632 + }, + { + "epoch": 0.01, + "learning_rate": 2.4752401623991147e-05, + "loss": 3.4697, + "step": 1542144 + }, + { + "epoch": 0.01, + "learning_rate": 2.4744015676480627e-05, + "loss": 3.4749, + "step": 1542656 + }, + { + "epoch": 0.01, + "learning_rate": 2.473564610777384e-05, + "loss": 3.4771, + "step": 1543168 + }, + { + "epoch": 0.01, + "learning_rate": 2.472726016026332e-05, + "loss": 3.4845, + "step": 1543680 + }, + { + "epoch": 0.01, + "learning_rate": 2.47188742127528e-05, + "loss": 3.467, + "step": 1544192 + }, + { + "epoch": 0.01, + "learning_rate": 2.471048826524228e-05, + "loss": 3.4785, + "step": 1544704 + }, + { + "epoch": 0.01, + "learning_rate": 2.4702118696535492e-05, + "loss": 3.4671, + "step": 1545216 + }, + { + "epoch": 0.01, + "learning_rate": 2.469373274902497e-05, + "loss": 3.475, + "step": 1545728 + }, + { + "epoch": 0.01, + "learning_rate": 2.468534680151445e-05, + "loss": 3.462, + "step": 1546240 + }, + { + "epoch": 0.01, + "learning_rate": 2.4676960854003932e-05, + "loss": 3.4686, + "step": 1546752 + }, + { + "epoch": 0.01, + "learning_rate": 2.4668591285297144e-05, + "loss": 3.4651, + "step": 1547264 + }, + { + "epoch": 0.01, + "learning_rate": 2.466020533778662e-05, + "loss": 3.4791, + "step": 1547776 + }, + { + "epoch": 0.01, + "learning_rate": 2.46518193902761e-05, + "loss": 3.4676, + "step": 1548288 + }, + { + "epoch": 0.01, + "learning_rate": 2.464343344276558e-05, + "loss": 3.4694, + "step": 1548800 + }, + { + "epoch": 0.01, + "learning_rate": 2.4635063874058793e-05, + "loss": 3.4837, + "step": 1549312 + }, + { + "epoch": 0.01, + "learning_rate": 2.4626677926548273e-05, + "loss": 3.4757, + "step": 1549824 + }, + { + "epoch": 0.01, + "learning_rate": 2.4618291979037753e-05, + "loss": 3.4749, + "step": 1550336 + }, + { + "epoch": 0.01, + "learning_rate": 2.4609906031527233e-05, + "loss": 3.4622, + "step": 1550848 + }, + { + "epoch": 0.01, + "learning_rate": 2.4601536462820442e-05, + "loss": 3.4588, + "step": 1551360 + }, + { + "epoch": 0.01, + "learning_rate": 2.4593150515309922e-05, + "loss": 3.4755, + "step": 1551872 + }, + { + "epoch": 0.01, + "learning_rate": 2.4584764567799402e-05, + "loss": 3.4724, + "step": 1552384 + }, + { + "epoch": 0.01, + "learning_rate": 2.4576378620288885e-05, + "loss": 3.467, + "step": 1552896 + }, + { + "epoch": 0.01, + "learning_rate": 2.4568009051582095e-05, + "loss": 3.464, + "step": 1553408 + }, + { + "epoch": 0.01, + "learning_rate": 2.4559623104071575e-05, + "loss": 3.4699, + "step": 1553920 + }, + { + "epoch": 0.01, + "learning_rate": 2.4551237156561054e-05, + "loss": 3.4515, + "step": 1554432 + }, + { + "epoch": 0.01, + "learning_rate": 2.4542851209050534e-05, + "loss": 3.4757, + "step": 1554944 + }, + { + "epoch": 0.01, + "learning_rate": 2.4534481640343747e-05, + "loss": 3.4613, + "step": 1555456 + }, + { + "epoch": 0.01, + "learning_rate": 2.4526095692833227e-05, + "loss": 3.4679, + "step": 1555968 + }, + { + "epoch": 0.01, + "learning_rate": 2.4517709745322707e-05, + "loss": 3.4754, + "step": 1556480 + }, + { + "epoch": 0.01, + "learning_rate": 2.4509323797812187e-05, + "loss": 3.457, + "step": 1556992 + }, + { + "epoch": 0.01, + "learning_rate": 2.4500954229105396e-05, + "loss": 3.471, + "step": 1557504 + }, + { + "epoch": 0.01, + "learning_rate": 2.4492568281594876e-05, + "loss": 3.4686, + "step": 1558016 + }, + { + "epoch": 0.01, + "learning_rate": 2.4484182334084356e-05, + "loss": 3.462, + "step": 1558528 + }, + { + "epoch": 0.01, + "learning_rate": 2.4475812765377568e-05, + "loss": 3.4605, + "step": 1559040 + }, + { + "epoch": 0.01, + "learning_rate": 2.4467426817867048e-05, + "loss": 3.4687, + "step": 1559552 + }, + { + "epoch": 0.01, + "learning_rate": 2.4459040870356528e-05, + "loss": 3.4638, + "step": 1560064 + }, + { + "epoch": 0.01, + "learning_rate": 2.4450654922846008e-05, + "loss": 3.4634, + "step": 1560576 + }, + { + "epoch": 0.01, + "learning_rate": 2.4442285354139217e-05, + "loss": 3.4564, + "step": 1561088 + }, + { + "epoch": 0.01, + "learning_rate": 2.44338994066287e-05, + "loss": 3.4579, + "step": 1561600 + }, + { + "epoch": 0.01, + "learning_rate": 2.442551345911818e-05, + "loss": 3.4675, + "step": 1562112 + }, + { + "epoch": 0.01, + "learning_rate": 2.441712751160766e-05, + "loss": 3.4794, + "step": 1562624 + }, + { + "epoch": 0.01, + "learning_rate": 2.440875794290087e-05, + "loss": 3.4648, + "step": 1563136 + }, + { + "epoch": 0.01, + "learning_rate": 2.440037199539035e-05, + "loss": 3.4753, + "step": 1563648 + }, + { + "epoch": 0.01, + "learning_rate": 2.439198604787983e-05, + "loss": 3.4725, + "step": 1564160 + }, + { + "epoch": 0.01, + "learning_rate": 2.438360010036931e-05, + "loss": 3.4678, + "step": 1564672 + }, + { + "epoch": 0.01, + "learning_rate": 2.4375230531662522e-05, + "loss": 3.4714, + "step": 1565184 + }, + { + "epoch": 0.01, + "learning_rate": 2.4366844584152002e-05, + "loss": 3.4767, + "step": 1565696 + }, + { + "epoch": 0.01, + "learning_rate": 2.4358458636641482e-05, + "loss": 3.4656, + "step": 1566208 + }, + { + "epoch": 0.01, + "learning_rate": 2.4350072689130962e-05, + "loss": 3.4654, + "step": 1566720 + }, + { + "epoch": 0.01, + "learning_rate": 2.434170312042417e-05, + "loss": 3.4749, + "step": 1567232 + }, + { + "epoch": 0.01, + "learning_rate": 2.4333317172913654e-05, + "loss": 3.473, + "step": 1567744 + }, + { + "epoch": 0.01, + "learning_rate": 2.4324931225403134e-05, + "loss": 3.4736, + "step": 1568256 + }, + { + "epoch": 0.01, + "learning_rate": 2.4316545277892614e-05, + "loss": 3.469, + "step": 1568768 + }, + { + "epoch": 0.01, + "learning_rate": 2.4308175709185823e-05, + "loss": 3.451, + "step": 1569280 + }, + { + "epoch": 0.01, + "learning_rate": 2.4299789761675303e-05, + "loss": 3.4569, + "step": 1569792 + }, + { + "epoch": 0.01, + "learning_rate": 2.4291403814164783e-05, + "loss": 3.469, + "step": 1570304 + }, + { + "epoch": 0.01, + "learning_rate": 2.4283017866654263e-05, + "loss": 3.4684, + "step": 1570816 + }, + { + "epoch": 0.01, + "learning_rate": 2.4274648297947476e-05, + "loss": 3.4619, + "step": 1571328 + }, + { + "epoch": 0.01, + "learning_rate": 2.4266262350436956e-05, + "loss": 3.4696, + "step": 1571840 + }, + { + "epoch": 0.02, + "learning_rate": 2.4257892781730165e-05, + "loss": 3.4697, + "step": 1572352 + }, + { + "epoch": 0.02, + "learning_rate": 2.4249506834219645e-05, + "loss": 3.4586, + "step": 1572864 + }, + { + "epoch": 0.02, + "learning_rate": 2.4241120886709125e-05, + "loss": 3.4633, + "step": 1573376 + }, + { + "epoch": 0.02, + "learning_rate": 2.4232734939198608e-05, + "loss": 3.4693, + "step": 1573888 + }, + { + "epoch": 0.02, + "learning_rate": 2.4224348991688088e-05, + "loss": 3.4788, + "step": 1574400 + }, + { + "epoch": 0.02, + "learning_rate": 2.4215963044177568e-05, + "loss": 3.4755, + "step": 1574912 + }, + { + "epoch": 0.02, + "learning_rate": 2.4207577096667044e-05, + "loss": 3.4719, + "step": 1575424 + }, + { + "epoch": 0.02, + "learning_rate": 2.4199191149156524e-05, + "loss": 3.4574, + "step": 1575936 + }, + { + "epoch": 0.02, + "learning_rate": 2.4190821580449737e-05, + "loss": 3.4743, + "step": 1576448 + }, + { + "epoch": 0.02, + "learning_rate": 2.4182435632939217e-05, + "loss": 3.4688, + "step": 1576960 + }, + { + "epoch": 0.02, + "learning_rate": 2.4174049685428697e-05, + "loss": 3.4743, + "step": 1577472 + }, + { + "epoch": 0.02, + "learning_rate": 2.4165663737918177e-05, + "loss": 3.4645, + "step": 1577984 + }, + { + "epoch": 0.02, + "learning_rate": 2.415729416921139e-05, + "loss": 3.4596, + "step": 1578496 + }, + { + "epoch": 0.02, + "learning_rate": 2.4148908221700866e-05, + "loss": 3.4723, + "step": 1579008 + }, + { + "epoch": 0.02, + "learning_rate": 2.4140522274190346e-05, + "loss": 3.4785, + "step": 1579520 + }, + { + "epoch": 0.02, + "learning_rate": 2.4132136326679826e-05, + "loss": 3.4627, + "step": 1580032 + }, + { + "epoch": 0.02, + "learning_rate": 2.412376675797304e-05, + "loss": 3.4671, + "step": 1580544 + }, + { + "epoch": 0.02, + "learning_rate": 2.4115380810462518e-05, + "loss": 3.4674, + "step": 1581056 + }, + { + "epoch": 0.02, + "learning_rate": 2.4106994862951998e-05, + "loss": 3.4576, + "step": 1581568 + }, + { + "epoch": 0.02, + "learning_rate": 2.4098608915441478e-05, + "loss": 3.4563, + "step": 1582080 + }, + { + "epoch": 0.02, + "learning_rate": 2.4090239346734687e-05, + "loss": 3.466, + "step": 1582592 + }, + { + "epoch": 0.02, + "learning_rate": 2.408185339922417e-05, + "loss": 3.4639, + "step": 1583104 + }, + { + "epoch": 0.02, + "learning_rate": 2.407346745171365e-05, + "loss": 3.4609, + "step": 1583616 + }, + { + "epoch": 0.02, + "learning_rate": 2.406508150420313e-05, + "loss": 3.4634, + "step": 1584128 + }, + { + "epoch": 0.02, + "learning_rate": 2.405671193549634e-05, + "loss": 3.4614, + "step": 1584640 + }, + { + "epoch": 0.02, + "learning_rate": 2.404832598798582e-05, + "loss": 3.4804, + "step": 1585152 + }, + { + "epoch": 0.02, + "learning_rate": 2.40399400404753e-05, + "loss": 3.4808, + "step": 1585664 + }, + { + "epoch": 0.02, + "learning_rate": 2.403155409296478e-05, + "loss": 3.4705, + "step": 1586176 + }, + { + "epoch": 0.02, + "learning_rate": 2.4023184524257992e-05, + "loss": 3.4729, + "step": 1586688 + }, + { + "epoch": 0.02, + "learning_rate": 2.4014798576747472e-05, + "loss": 3.464, + "step": 1587200 + }, + { + "epoch": 0.02, + "learning_rate": 2.4006412629236952e-05, + "loss": 3.4606, + "step": 1587712 + }, + { + "epoch": 0.02, + "learning_rate": 2.3998026681726432e-05, + "loss": 3.4587, + "step": 1588224 + }, + { + "epoch": 0.02, + "learning_rate": 2.398965711301964e-05, + "loss": 3.4626, + "step": 1588736 + }, + { + "epoch": 0.02, + "learning_rate": 2.3981271165509124e-05, + "loss": 3.4695, + "step": 1589248 + }, + { + "epoch": 0.02, + "learning_rate": 2.3972885217998604e-05, + "loss": 3.4685, + "step": 1589760 + }, + { + "epoch": 0.02, + "learning_rate": 2.3964499270488084e-05, + "loss": 3.4638, + "step": 1590272 + }, + { + "epoch": 0.02, + "learning_rate": 2.3956129701781293e-05, + "loss": 3.4696, + "step": 1590784 + }, + { + "epoch": 0.02, + "learning_rate": 2.3947743754270773e-05, + "loss": 3.4647, + "step": 1591296 + }, + { + "epoch": 0.02, + "learning_rate": 2.3939357806760253e-05, + "loss": 3.461, + "step": 1591808 + }, + { + "epoch": 0.02, + "learning_rate": 2.3930971859249733e-05, + "loss": 3.4627, + "step": 1592320 + }, + { + "epoch": 0.02, + "learning_rate": 2.3922602290542946e-05, + "loss": 3.4761, + "step": 1592832 + }, + { + "epoch": 0.02, + "learning_rate": 2.3914216343032425e-05, + "loss": 3.476, + "step": 1593344 + }, + { + "epoch": 0.02, + "learning_rate": 2.3905830395521905e-05, + "loss": 3.4738, + "step": 1593856 + }, + { + "epoch": 0.02, + "learning_rate": 2.3897460826815115e-05, + "loss": 3.4605, + "step": 1594368 + }, + { + "epoch": 0.02, + "learning_rate": 2.3889074879304594e-05, + "loss": 3.4691, + "step": 1594880 + }, + { + "epoch": 0.02, + "learning_rate": 2.3880688931794078e-05, + "loss": 3.4665, + "step": 1595392 + }, + { + "epoch": 0.02, + "learning_rate": 2.3872302984283558e-05, + "loss": 3.4771, + "step": 1595904 + }, + { + "epoch": 0.02, + "learning_rate": 2.3863933415576767e-05, + "loss": 3.464, + "step": 1596416 + }, + { + "epoch": 0.02, + "learning_rate": 2.3855547468066247e-05, + "loss": 3.4692, + "step": 1596928 + }, + { + "epoch": 0.02, + "learning_rate": 2.3847161520555727e-05, + "loss": 3.4665, + "step": 1597440 + }, + { + "epoch": 0.02, + "learning_rate": 2.3838775573045207e-05, + "loss": 3.4735, + "step": 1597952 + }, + { + "epoch": 0.02, + "learning_rate": 2.383040600433842e-05, + "loss": 3.4607, + "step": 1598464 + }, + { + "epoch": 0.02, + "learning_rate": 2.38220200568279e-05, + "loss": 3.4658, + "step": 1598976 + }, + { + "epoch": 0.02, + "learning_rate": 2.381363410931738e-05, + "loss": 3.4708, + "step": 1599488 + }, + { + "epoch": 0.02, + "learning_rate": 2.380524816180686e-05, + "loss": 3.4616, + "step": 1600000 + }, + { + "epoch": 0.02, + "learning_rate": 2.3796878593100068e-05, + "loss": 3.4716, + "step": 1600512 + }, + { + "epoch": 0.02, + "learning_rate": 2.3788492645589548e-05, + "loss": 3.4783, + "step": 1601024 + }, + { + "epoch": 0.02, + "learning_rate": 2.378010669807903e-05, + "loss": 3.4699, + "step": 1601536 + }, + { + "epoch": 0.02, + "learning_rate": 2.377172075056851e-05, + "loss": 3.4648, + "step": 1602048 + }, + { + "epoch": 0.02, + "learning_rate": 2.376335118186172e-05, + "loss": 3.4615, + "step": 1602560 + }, + { + "epoch": 0.03, + "eval_loss": 3.8477835655212402, + "eval_runtime": 312.3651, + "eval_samples_per_second": 1221.619, + "eval_steps_per_second": 38.176, + "step": 1602709 + }, + { + "epoch": 1.0, + "learning_rate": 2.37549652343512e-05, + "loss": 3.4655, + "step": 1603072 + }, + { + "epoch": 1.0, + "learning_rate": 2.374657928684068e-05, + "loss": 3.4555, + "step": 1603584 + }, + { + "epoch": 1.0, + "learning_rate": 2.373819333933016e-05, + "loss": 3.4737, + "step": 1604096 + }, + { + "epoch": 1.0, + "learning_rate": 2.3729823770623373e-05, + "loss": 3.4672, + "step": 1604608 + }, + { + "epoch": 1.0, + "learning_rate": 2.3721437823112853e-05, + "loss": 3.4764, + "step": 1605120 + }, + { + "epoch": 1.0, + "learning_rate": 2.3713051875602333e-05, + "loss": 3.4649, + "step": 1605632 + }, + { + "epoch": 1.0, + "learning_rate": 2.3704665928091813e-05, + "loss": 3.4677, + "step": 1606144 + }, + { + "epoch": 1.0, + "learning_rate": 2.3696296359385022e-05, + "loss": 3.4516, + "step": 1606656 + }, + { + "epoch": 1.0, + "learning_rate": 2.3687910411874502e-05, + "loss": 3.465, + "step": 1607168 + }, + { + "epoch": 1.0, + "learning_rate": 2.3679524464363985e-05, + "loss": 3.4576, + "step": 1607680 + }, + { + "epoch": 1.0, + "learning_rate": 2.3671138516853465e-05, + "loss": 3.4689, + "step": 1608192 + }, + { + "epoch": 1.0, + "learning_rate": 2.3662768948146674e-05, + "loss": 3.4708, + "step": 1608704 + }, + { + "epoch": 1.0, + "learning_rate": 2.3654399379439883e-05, + "loss": 3.4522, + "step": 1609216 + }, + { + "epoch": 1.0, + "learning_rate": 2.3646013431929363e-05, + "loss": 3.4582, + "step": 1609728 + }, + { + "epoch": 1.0, + "learning_rate": 2.3637627484418847e-05, + "loss": 3.4657, + "step": 1610240 + }, + { + "epoch": 1.0, + "learning_rate": 2.3629241536908327e-05, + "loss": 3.4537, + "step": 1610752 + }, + { + "epoch": 1.0, + "learning_rate": 2.3620855589397807e-05, + "loss": 3.4598, + "step": 1611264 + }, + { + "epoch": 1.0, + "learning_rate": 2.3612469641887286e-05, + "loss": 3.4604, + "step": 1611776 + }, + { + "epoch": 1.0, + "learning_rate": 2.3604083694376763e-05, + "loss": 3.4616, + "step": 1612288 + }, + { + "epoch": 1.0, + "learning_rate": 2.3595697746866243e-05, + "loss": 3.4772, + "step": 1612800 + }, + { + "epoch": 1.0, + "learning_rate": 2.3587328178159455e-05, + "loss": 3.4607, + "step": 1613312 + }, + { + "epoch": 1.0, + "learning_rate": 2.357894223064894e-05, + "loss": 3.4613, + "step": 1613824 + }, + { + "epoch": 1.0, + "learning_rate": 2.3570556283138415e-05, + "loss": 3.4647, + "step": 1614336 + }, + { + "epoch": 1.0, + "learning_rate": 2.3562170335627895e-05, + "loss": 3.4675, + "step": 1614848 + }, + { + "epoch": 1.0, + "learning_rate": 2.3553800766921108e-05, + "loss": 3.4583, + "step": 1615360 + }, + { + "epoch": 1.0, + "learning_rate": 2.3545414819410584e-05, + "loss": 3.4683, + "step": 1615872 + }, + { + "epoch": 1.0, + "learning_rate": 2.3537028871900064e-05, + "loss": 3.4563, + "step": 1616384 + }, + { + "epoch": 1.0, + "learning_rate": 2.3528642924389548e-05, + "loss": 3.4588, + "step": 1616896 + }, + { + "epoch": 1.0, + "learning_rate": 2.352027335568276e-05, + "loss": 3.4572, + "step": 1617408 + }, + { + "epoch": 1.0, + "learning_rate": 2.3511887408172237e-05, + "loss": 3.4632, + "step": 1617920 + }, + { + "epoch": 1.01, + "learning_rate": 2.3503501460661717e-05, + "loss": 3.4589, + "step": 1618432 + }, + { + "epoch": 1.01, + "learning_rate": 2.349513189195493e-05, + "loss": 3.4627, + "step": 1618944 + }, + { + "epoch": 1.01, + "learning_rate": 2.348674594444441e-05, + "loss": 3.4676, + "step": 1619456 + }, + { + "epoch": 1.01, + "learning_rate": 2.347835999693389e-05, + "loss": 3.4694, + "step": 1619968 + }, + { + "epoch": 1.01, + "learning_rate": 2.346997404942337e-05, + "loss": 3.4601, + "step": 1620480 + }, + { + "epoch": 1.01, + "learning_rate": 2.346160448071658e-05, + "loss": 3.4666, + "step": 1620992 + }, + { + "epoch": 1.01, + "learning_rate": 2.3453218533206058e-05, + "loss": 3.4573, + "step": 1621504 + }, + { + "epoch": 1.01, + "learning_rate": 2.3444832585695538e-05, + "loss": 3.461, + "step": 1622016 + }, + { + "epoch": 1.01, + "learning_rate": 2.3436446638185018e-05, + "loss": 3.4509, + "step": 1622528 + }, + { + "epoch": 1.01, + "learning_rate": 2.3428077069478234e-05, + "loss": 3.4553, + "step": 1623040 + }, + { + "epoch": 1.01, + "learning_rate": 2.341969112196771e-05, + "loss": 3.4581, + "step": 1623552 + }, + { + "epoch": 1.01, + "learning_rate": 2.341130517445719e-05, + "loss": 3.4663, + "step": 1624064 + }, + { + "epoch": 1.01, + "learning_rate": 2.340291922694667e-05, + "loss": 3.4549, + "step": 1624576 + }, + { + "epoch": 1.01, + "learning_rate": 2.3394549658239883e-05, + "loss": 3.4598, + "step": 1625088 + }, + { + "epoch": 1.01, + "learning_rate": 2.3386163710729363e-05, + "loss": 3.4745, + "step": 1625600 + }, + { + "epoch": 1.01, + "learning_rate": 2.3377777763218843e-05, + "loss": 3.4658, + "step": 1626112 + }, + { + "epoch": 1.01, + "learning_rate": 2.3369391815708323e-05, + "loss": 3.463, + "step": 1626624 + }, + { + "epoch": 1.01, + "learning_rate": 2.3361022247001532e-05, + "loss": 3.453, + "step": 1627136 + }, + { + "epoch": 1.01, + "learning_rate": 2.3352636299491012e-05, + "loss": 3.4406, + "step": 1627648 + }, + { + "epoch": 1.01, + "learning_rate": 2.3344250351980492e-05, + "loss": 3.4675, + "step": 1628160 + }, + { + "epoch": 1.01, + "learning_rate": 2.333586440446997e-05, + "loss": 3.4571, + "step": 1628672 + }, + { + "epoch": 1.01, + "learning_rate": 2.3327494835763184e-05, + "loss": 3.456, + "step": 1629184 + }, + { + "epoch": 1.01, + "learning_rate": 2.3319108888252664e-05, + "loss": 3.4565, + "step": 1629696 + }, + { + "epoch": 1.01, + "learning_rate": 2.3310722940742144e-05, + "loss": 3.4612, + "step": 1630208 + }, + { + "epoch": 1.01, + "learning_rate": 2.3302336993231624e-05, + "loss": 3.4368, + "step": 1630720 + }, + { + "epoch": 1.01, + "learning_rate": 2.3293967424524833e-05, + "loss": 3.4655, + "step": 1631232 + }, + { + "epoch": 1.01, + "learning_rate": 2.3285581477014316e-05, + "loss": 3.4491, + "step": 1631744 + }, + { + "epoch": 1.01, + "learning_rate": 2.3277195529503796e-05, + "loss": 3.4575, + "step": 1632256 + }, + { + "epoch": 1.01, + "learning_rate": 2.3268809581993276e-05, + "loss": 3.4616, + "step": 1632768 + }, + { + "epoch": 1.01, + "learning_rate": 2.3260440013286485e-05, + "loss": 3.4552, + "step": 1633280 + }, + { + "epoch": 1.01, + "learning_rate": 2.3252054065775965e-05, + "loss": 3.4544, + "step": 1633792 + }, + { + "epoch": 1.01, + "learning_rate": 2.3243668118265445e-05, + "loss": 3.4625, + "step": 1634304 + }, + { + "epoch": 1.01, + "learning_rate": 2.3235282170754925e-05, + "loss": 3.4473, + "step": 1634816 + }, + { + "epoch": 1.01, + "learning_rate": 2.3226912602048138e-05, + "loss": 3.4513, + "step": 1635328 + }, + { + "epoch": 1.01, + "learning_rate": 2.3218526654537618e-05, + "loss": 3.4564, + "step": 1635840 + }, + { + "epoch": 1.01, + "learning_rate": 2.3210140707027098e-05, + "loss": 3.456, + "step": 1636352 + }, + { + "epoch": 1.01, + "learning_rate": 2.3201754759516578e-05, + "loss": 3.4512, + "step": 1636864 + }, + { + "epoch": 1.01, + "learning_rate": 2.3193385190809787e-05, + "loss": 3.445, + "step": 1637376 + }, + { + "epoch": 1.01, + "learning_rate": 2.318499924329927e-05, + "loss": 3.4463, + "step": 1637888 + }, + { + "epoch": 1.01, + "learning_rate": 2.317661329578875e-05, + "loss": 3.4538, + "step": 1638400 + }, + { + "epoch": 1.01, + "learning_rate": 2.316822734827823e-05, + "loss": 3.4656, + "step": 1638912 + }, + { + "epoch": 1.01, + "learning_rate": 2.315985777957144e-05, + "loss": 3.4513, + "step": 1639424 + }, + { + "epoch": 1.01, + "learning_rate": 2.315147183206092e-05, + "loss": 3.4687, + "step": 1639936 + }, + { + "epoch": 1.01, + "learning_rate": 2.31430858845504e-05, + "loss": 3.4643, + "step": 1640448 + }, + { + "epoch": 1.01, + "learning_rate": 2.313469993703988e-05, + "loss": 3.4591, + "step": 1640960 + }, + { + "epoch": 1.01, + "learning_rate": 2.312633036833309e-05, + "loss": 3.4565, + "step": 1641472 + }, + { + "epoch": 1.01, + "learning_rate": 2.311794442082257e-05, + "loss": 3.4633, + "step": 1641984 + }, + { + "epoch": 1.01, + "learning_rate": 2.310955847331205e-05, + "loss": 3.4583, + "step": 1642496 + }, + { + "epoch": 1.01, + "learning_rate": 2.310117252580153e-05, + "loss": 3.4521, + "step": 1643008 + }, + { + "epoch": 1.01, + "learning_rate": 2.309280295709474e-05, + "loss": 3.4659, + "step": 1643520 + }, + { + "epoch": 1.01, + "learning_rate": 2.3084417009584224e-05, + "loss": 3.4604, + "step": 1644032 + }, + { + "epoch": 1.01, + "learning_rate": 2.3076047440877433e-05, + "loss": 3.464, + "step": 1644544 + }, + { + "epoch": 1.01, + "learning_rate": 2.3067661493366913e-05, + "loss": 3.4579, + "step": 1645056 + }, + { + "epoch": 1.01, + "learning_rate": 2.3059275545856393e-05, + "loss": 3.4384, + "step": 1645568 + }, + { + "epoch": 1.01, + "learning_rate": 2.3050889598345873e-05, + "loss": 3.4454, + "step": 1646080 + }, + { + "epoch": 1.01, + "learning_rate": 2.3042503650835353e-05, + "loss": 3.4534, + "step": 1646592 + }, + { + "epoch": 1.01, + "learning_rate": 2.3034117703324833e-05, + "loss": 3.4577, + "step": 1647104 + }, + { + "epoch": 1.01, + "learning_rate": 2.3025731755814313e-05, + "loss": 3.4534, + "step": 1647616 + }, + { + "epoch": 1.01, + "learning_rate": 2.3017362187107525e-05, + "loss": 3.4573, + "step": 1648128 + }, + { + "epoch": 1.02, + "learning_rate": 2.3008992618400734e-05, + "loss": 3.4546, + "step": 1648640 + }, + { + "epoch": 1.02, + "learning_rate": 2.3000606670890214e-05, + "loss": 3.4483, + "step": 1649152 + }, + { + "epoch": 1.02, + "learning_rate": 2.2992220723379694e-05, + "loss": 3.4559, + "step": 1649664 + }, + { + "epoch": 1.02, + "learning_rate": 2.2983834775869174e-05, + "loss": 3.4519, + "step": 1650176 + }, + { + "epoch": 1.02, + "learning_rate": 2.2975448828358657e-05, + "loss": 3.4665, + "step": 1650688 + }, + { + "epoch": 1.02, + "learning_rate": 2.2967062880848134e-05, + "loss": 3.4652, + "step": 1651200 + }, + { + "epoch": 1.02, + "learning_rate": 2.2958676933337614e-05, + "loss": 3.4612, + "step": 1651712 + }, + { + "epoch": 1.02, + "learning_rate": 2.2950290985827094e-05, + "loss": 3.4474, + "step": 1652224 + }, + { + "epoch": 1.02, + "learning_rate": 2.2941921417120306e-05, + "loss": 3.4606, + "step": 1652736 + }, + { + "epoch": 1.02, + "learning_rate": 2.2933535469609786e-05, + "loss": 3.4583, + "step": 1653248 + }, + { + "epoch": 1.02, + "learning_rate": 2.2925149522099266e-05, + "loss": 3.463, + "step": 1653760 + }, + { + "epoch": 1.02, + "learning_rate": 2.2916763574588746e-05, + "loss": 3.4545, + "step": 1654272 + }, + { + "epoch": 1.02, + "learning_rate": 2.2908394005881955e-05, + "loss": 3.4476, + "step": 1654784 + }, + { + "epoch": 1.02, + "learning_rate": 2.2900008058371435e-05, + "loss": 3.4639, + "step": 1655296 + }, + { + "epoch": 1.02, + "learning_rate": 2.2891622110860915e-05, + "loss": 3.4604, + "step": 1655808 + }, + { + "epoch": 1.02, + "learning_rate": 2.2883236163350395e-05, + "loss": 3.4542, + "step": 1656320 + }, + { + "epoch": 1.02, + "learning_rate": 2.2874866594643608e-05, + "loss": 3.4579, + "step": 1656832 + }, + { + "epoch": 1.02, + "learning_rate": 2.2866480647133088e-05, + "loss": 3.4543, + "step": 1657344 + }, + { + "epoch": 1.02, + "learning_rate": 2.2858094699622568e-05, + "loss": 3.4472, + "step": 1657856 + }, + { + "epoch": 1.02, + "learning_rate": 2.2849708752112048e-05, + "loss": 3.442, + "step": 1658368 + }, + { + "epoch": 1.02, + "learning_rate": 2.2841339183405257e-05, + "loss": 3.4541, + "step": 1658880 + }, + { + "epoch": 1.02, + "learning_rate": 2.283295323589474e-05, + "loss": 3.4555, + "step": 1659392 + }, + { + "epoch": 1.02, + "learning_rate": 2.282456728838422e-05, + "loss": 3.4495, + "step": 1659904 + }, + { + "epoch": 1.02, + "learning_rate": 2.28161813408737e-05, + "loss": 3.4498, + "step": 1660416 + }, + { + "epoch": 1.02, + "learning_rate": 2.280781177216691e-05, + "loss": 3.4473, + "step": 1660928 + }, + { + "epoch": 1.02, + "learning_rate": 2.279942582465639e-05, + "loss": 3.4677, + "step": 1661440 + }, + { + "epoch": 1.02, + "learning_rate": 2.279103987714587e-05, + "loss": 3.4689, + "step": 1661952 + }, + { + "epoch": 1.02, + "learning_rate": 2.278265392963535e-05, + "loss": 3.4616, + "step": 1662464 + }, + { + "epoch": 1.02, + "learning_rate": 2.277428436092856e-05, + "loss": 3.461, + "step": 1662976 + }, + { + "epoch": 1.02, + "learning_rate": 2.276589841341804e-05, + "loss": 3.4494, + "step": 1663488 + }, + { + "epoch": 1.02, + "learning_rate": 2.275751246590752e-05, + "loss": 3.4506, + "step": 1664000 + }, + { + "epoch": 1.02, + "learning_rate": 2.2749126518397e-05, + "loss": 3.4461, + "step": 1664512 + }, + { + "epoch": 1.02, + "learning_rate": 2.274075694969021e-05, + "loss": 3.4499, + "step": 1665024 + }, + { + "epoch": 1.02, + "learning_rate": 2.2732371002179694e-05, + "loss": 3.4548, + "step": 1665536 + }, + { + "epoch": 1.02, + "learning_rate": 2.2723985054669174e-05, + "loss": 3.4581, + "step": 1666048 + }, + { + "epoch": 1.02, + "learning_rate": 2.2715599107158654e-05, + "loss": 3.4537, + "step": 1666560 + }, + { + "epoch": 1.02, + "learning_rate": 2.2707229538451863e-05, + "loss": 3.4544, + "step": 1667072 + }, + { + "epoch": 1.02, + "learning_rate": 2.2698843590941343e-05, + "loss": 3.454, + "step": 1667584 + }, + { + "epoch": 1.02, + "learning_rate": 2.2690457643430823e-05, + "loss": 3.4518, + "step": 1668096 + }, + { + "epoch": 1.02, + "learning_rate": 2.2682071695920303e-05, + "loss": 3.4546, + "step": 1668608 + }, + { + "epoch": 1.02, + "learning_rate": 2.2673702127213515e-05, + "loss": 3.4601, + "step": 1669120 + }, + { + "epoch": 1.02, + "learning_rate": 2.2665316179702995e-05, + "loss": 3.4641, + "step": 1669632 + }, + { + "epoch": 1.02, + "learning_rate": 2.2656930232192475e-05, + "loss": 3.4653, + "step": 1670144 + }, + { + "epoch": 1.02, + "learning_rate": 2.2648544284681955e-05, + "loss": 3.4498, + "step": 1670656 + }, + { + "epoch": 1.02, + "learning_rate": 2.2640174715975164e-05, + "loss": 3.4592, + "step": 1671168 + }, + { + "epoch": 1.02, + "learning_rate": 2.2631788768464647e-05, + "loss": 3.4519, + "step": 1671680 + }, + { + "epoch": 1.02, + "learning_rate": 2.2623402820954127e-05, + "loss": 3.4642, + "step": 1672192 + }, + { + "epoch": 1.02, + "learning_rate": 2.2615016873443607e-05, + "loss": 3.4551, + "step": 1672704 + }, + { + "epoch": 1.02, + "learning_rate": 2.2606647304736816e-05, + "loss": 3.4559, + "step": 1673216 + }, + { + "epoch": 1.02, + "learning_rate": 2.2598261357226296e-05, + "loss": 3.4518, + "step": 1673728 + }, + { + "epoch": 1.02, + "learning_rate": 2.2589875409715776e-05, + "loss": 3.4635, + "step": 1674240 + }, + { + "epoch": 1.02, + "learning_rate": 2.2581489462205256e-05, + "loss": 3.4531, + "step": 1674752 + }, + { + "epoch": 1.02, + "learning_rate": 2.257311989349847e-05, + "loss": 3.4559, + "step": 1675264 + }, + { + "epoch": 1.02, + "learning_rate": 2.256473394598795e-05, + "loss": 3.4526, + "step": 1675776 + }, + { + "epoch": 1.02, + "learning_rate": 2.255634799847743e-05, + "loss": 3.4567, + "step": 1676288 + }, + { + "epoch": 1.02, + "learning_rate": 2.2547978429770638e-05, + "loss": 3.4612, + "step": 1676800 + }, + { + "epoch": 1.02, + "learning_rate": 2.2539592482260118e-05, + "loss": 3.4593, + "step": 1677312 + }, + { + "epoch": 1.02, + "learning_rate": 2.2531206534749598e-05, + "loss": 3.4649, + "step": 1677824 + }, + { + "epoch": 1.02, + "learning_rate": 2.252282058723908e-05, + "loss": 3.4489, + "step": 1678336 + }, + { + "epoch": 1.02, + "learning_rate": 2.251445101853229e-05, + "loss": 3.4538, + "step": 1678848 + }, + { + "epoch": 1.03, + "eval_loss": 3.8470618724823, + "eval_runtime": 314.6749, + "eval_samples_per_second": 1212.652, + "eval_steps_per_second": 37.896, + "step": 1679029 + }, + { + "epoch": 0.0, + "learning_rate": 2.250606507102177e-05, + "loss": 3.4495, + "step": 1679360 + }, + { + "epoch": 0.0, + "learning_rate": 2.249767912351125e-05, + "loss": 3.4428, + "step": 1679872 + }, + { + "epoch": 0.0, + "learning_rate": 2.248929317600073e-05, + "loss": 3.4582, + "step": 1680384 + }, + { + "epoch": 0.0, + "learning_rate": 2.248090722849021e-05, + "loss": 3.456, + "step": 1680896 + }, + { + "epoch": 0.0, + "learning_rate": 2.2472537659783422e-05, + "loss": 3.4649, + "step": 1681408 + }, + { + "epoch": 0.0, + "learning_rate": 2.2464151712272902e-05, + "loss": 3.4518, + "step": 1681920 + }, + { + "epoch": 0.0, + "learning_rate": 2.2455765764762382e-05, + "loss": 3.4505, + "step": 1682432 + }, + { + "epoch": 0.0, + "learning_rate": 2.244737981725186e-05, + "loss": 3.4474, + "step": 1682944 + }, + { + "epoch": 0.0, + "learning_rate": 2.243901024854507e-05, + "loss": 3.4511, + "step": 1683456 + }, + { + "epoch": 0.0, + "learning_rate": 2.243062430103455e-05, + "loss": 3.4481, + "step": 1683968 + }, + { + "epoch": 0.0, + "learning_rate": 2.242223835352403e-05, + "loss": 3.4573, + "step": 1684480 + }, + { + "epoch": 0.0, + "learning_rate": 2.241385240601351e-05, + "loss": 3.4623, + "step": 1684992 + }, + { + "epoch": 0.0, + "learning_rate": 2.2405499216110453e-05, + "loss": 3.4392, + "step": 1685504 + }, + { + "epoch": 0.0, + "learning_rate": 2.2397113268599933e-05, + "loss": 3.4468, + "step": 1686016 + }, + { + "epoch": 0.0, + "learning_rate": 2.2388727321089413e-05, + "loss": 3.4554, + "step": 1686528 + }, + { + "epoch": 0.0, + "learning_rate": 2.2380341373578896e-05, + "loss": 3.4384, + "step": 1687040 + }, + { + "epoch": 0.0, + "learning_rate": 2.2371955426068376e-05, + "loss": 3.4484, + "step": 1687552 + }, + { + "epoch": 0.0, + "learning_rate": 2.2363569478557856e-05, + "loss": 3.4494, + "step": 1688064 + }, + { + "epoch": 0.0, + "learning_rate": 2.2355183531047333e-05, + "loss": 3.4472, + "step": 1688576 + }, + { + "epoch": 0.0, + "learning_rate": 2.2346797583536813e-05, + "loss": 3.4666, + "step": 1689088 + }, + { + "epoch": 0.0, + "learning_rate": 2.2338428014830025e-05, + "loss": 3.4535, + "step": 1689600 + }, + { + "epoch": 0.0, + "learning_rate": 2.2330042067319505e-05, + "loss": 3.4538, + "step": 1690112 + }, + { + "epoch": 0.0, + "learning_rate": 2.2321656119808985e-05, + "loss": 3.4501, + "step": 1690624 + }, + { + "epoch": 0.0, + "learning_rate": 2.2313270172298465e-05, + "loss": 3.4565, + "step": 1691136 + }, + { + "epoch": 0.0, + "learning_rate": 2.2304900603591677e-05, + "loss": 3.4487, + "step": 1691648 + }, + { + "epoch": 0.0, + "learning_rate": 2.2296514656081154e-05, + "loss": 3.456, + "step": 1692160 + }, + { + "epoch": 0.0, + "learning_rate": 2.2288128708570634e-05, + "loss": 3.4471, + "step": 1692672 + }, + { + "epoch": 0.0, + "learning_rate": 2.227975913986385e-05, + "loss": 3.4433, + "step": 1693184 + }, + { + "epoch": 0.0, + "learning_rate": 2.2271373192353326e-05, + "loss": 3.4481, + "step": 1693696 + }, + { + "epoch": 0.0, + "learning_rate": 2.2262987244842806e-05, + "loss": 3.4502, + "step": 1694208 + }, + { + "epoch": 0.01, + "learning_rate": 2.2254601297332286e-05, + "loss": 3.4524, + "step": 1694720 + }, + { + "epoch": 0.01, + "learning_rate": 2.2246215349821766e-05, + "loss": 3.4477, + "step": 1695232 + }, + { + "epoch": 0.01, + "learning_rate": 2.2237829402311246e-05, + "loss": 3.4564, + "step": 1695744 + }, + { + "epoch": 0.01, + "learning_rate": 2.2229443454800726e-05, + "loss": 3.4616, + "step": 1696256 + }, + { + "epoch": 0.01, + "learning_rate": 2.2221057507290206e-05, + "loss": 3.4473, + "step": 1696768 + }, + { + "epoch": 0.01, + "learning_rate": 2.221268793858342e-05, + "loss": 3.4501, + "step": 1697280 + }, + { + "epoch": 0.01, + "learning_rate": 2.22043019910729e-05, + "loss": 3.4509, + "step": 1697792 + }, + { + "epoch": 0.01, + "learning_rate": 2.219591604356238e-05, + "loss": 3.4473, + "step": 1698304 + }, + { + "epoch": 0.01, + "learning_rate": 2.218753009605186e-05, + "loss": 3.44, + "step": 1698816 + }, + { + "epoch": 0.01, + "learning_rate": 2.217916052734507e-05, + "loss": 3.4431, + "step": 1699328 + }, + { + "epoch": 0.01, + "learning_rate": 2.217077457983455e-05, + "loss": 3.4457, + "step": 1699840 + }, + { + "epoch": 0.01, + "learning_rate": 2.216238863232403e-05, + "loss": 3.4525, + "step": 1700352 + }, + { + "epoch": 0.01, + "learning_rate": 2.2154002684813507e-05, + "loss": 3.4455, + "step": 1700864 + }, + { + "epoch": 0.01, + "learning_rate": 2.214563311610672e-05, + "loss": 3.4468, + "step": 1701376 + }, + { + "epoch": 0.01, + "learning_rate": 2.21372471685962e-05, + "loss": 3.4675, + "step": 1701888 + }, + { + "epoch": 0.01, + "learning_rate": 2.212886122108568e-05, + "loss": 3.4515, + "step": 1702400 + }, + { + "epoch": 0.01, + "learning_rate": 2.212047527357516e-05, + "loss": 3.451, + "step": 1702912 + }, + { + "epoch": 0.01, + "learning_rate": 2.2112105704868372e-05, + "loss": 3.4426, + "step": 1703424 + }, + { + "epoch": 0.01, + "learning_rate": 2.2103719757357852e-05, + "loss": 3.4309, + "step": 1703936 + }, + { + "epoch": 0.01, + "learning_rate": 2.2095333809847332e-05, + "loss": 3.4567, + "step": 1704448 + }, + { + "epoch": 0.01, + "learning_rate": 2.208694786233681e-05, + "loss": 3.4461, + "step": 1704960 + }, + { + "epoch": 0.01, + "learning_rate": 2.207857829363002e-05, + "loss": 3.4455, + "step": 1705472 + }, + { + "epoch": 0.01, + "learning_rate": 2.2070192346119505e-05, + "loss": 3.4458, + "step": 1705984 + }, + { + "epoch": 0.01, + "learning_rate": 2.206180639860898e-05, + "loss": 3.4523, + "step": 1706496 + }, + { + "epoch": 0.01, + "learning_rate": 2.205342045109846e-05, + "loss": 3.4259, + "step": 1707008 + }, + { + "epoch": 0.01, + "learning_rate": 2.2045050882391674e-05, + "loss": 3.4466, + "step": 1707520 + }, + { + "epoch": 0.01, + "learning_rate": 2.2036664934881153e-05, + "loss": 3.4439, + "step": 1708032 + }, + { + "epoch": 0.01, + "learning_rate": 2.2028278987370633e-05, + "loss": 3.44, + "step": 1708544 + }, + { + "epoch": 0.01, + "learning_rate": 2.2019893039860113e-05, + "loss": 3.4575, + "step": 1709056 + }, + { + "epoch": 0.01, + "learning_rate": 2.2011523471153326e-05, + "loss": 3.4423, + "step": 1709568 + }, + { + "epoch": 0.01, + "learning_rate": 2.2003137523642806e-05, + "loss": 3.4416, + "step": 1710080 + }, + { + "epoch": 0.01, + "learning_rate": 2.1994751576132282e-05, + "loss": 3.454, + "step": 1710592 + }, + { + "epoch": 0.01, + "learning_rate": 2.1986365628621762e-05, + "loss": 3.44, + "step": 1711104 + }, + { + "epoch": 0.01, + "learning_rate": 2.1977996059914975e-05, + "loss": 3.436, + "step": 1711616 + }, + { + "epoch": 0.01, + "learning_rate": 2.1969610112404455e-05, + "loss": 3.4435, + "step": 1712128 + }, + { + "epoch": 0.01, + "learning_rate": 2.1961224164893935e-05, + "loss": 3.4458, + "step": 1712640 + }, + { + "epoch": 0.01, + "learning_rate": 2.1952838217383415e-05, + "loss": 3.4427, + "step": 1713152 + }, + { + "epoch": 0.01, + "learning_rate": 2.1944468648676627e-05, + "loss": 3.4354, + "step": 1713664 + }, + { + "epoch": 0.01, + "learning_rate": 2.1936082701166104e-05, + "loss": 3.4282, + "step": 1714176 + }, + { + "epoch": 0.01, + "learning_rate": 2.1927696753655587e-05, + "loss": 3.4408, + "step": 1714688 + }, + { + "epoch": 0.01, + "learning_rate": 2.1919310806145067e-05, + "loss": 3.4551, + "step": 1715200 + }, + { + "epoch": 0.01, + "learning_rate": 2.191094123743828e-05, + "loss": 3.4406, + "step": 1715712 + }, + { + "epoch": 0.01, + "learning_rate": 2.1902555289927756e-05, + "loss": 3.459, + "step": 1716224 + }, + { + "epoch": 0.01, + "learning_rate": 2.1894169342417236e-05, + "loss": 3.4521, + "step": 1716736 + }, + { + "epoch": 0.01, + "learning_rate": 2.1885783394906716e-05, + "loss": 3.45, + "step": 1717248 + }, + { + "epoch": 0.01, + "learning_rate": 2.187741382619993e-05, + "loss": 3.4415, + "step": 1717760 + }, + { + "epoch": 0.01, + "learning_rate": 2.186902787868941e-05, + "loss": 3.4579, + "step": 1718272 + }, + { + "epoch": 0.01, + "learning_rate": 2.186064193117889e-05, + "loss": 3.4434, + "step": 1718784 + }, + { + "epoch": 0.01, + "learning_rate": 2.18522723624721e-05, + "loss": 3.4413, + "step": 1719296 + }, + { + "epoch": 0.01, + "learning_rate": 2.1843886414961577e-05, + "loss": 3.456, + "step": 1719808 + }, + { + "epoch": 0.01, + "learning_rate": 2.1835500467451057e-05, + "loss": 3.4477, + "step": 1720320 + }, + { + "epoch": 0.01, + "learning_rate": 2.1827130898744273e-05, + "loss": 3.4546, + "step": 1720832 + }, + { + "epoch": 0.01, + "learning_rate": 2.1818744951233753e-05, + "loss": 3.4473, + "step": 1721344 + }, + { + "epoch": 0.01, + "learning_rate": 2.181035900372323e-05, + "loss": 3.4273, + "step": 1721856 + }, + { + "epoch": 0.01, + "learning_rate": 2.180197305621271e-05, + "loss": 3.4345, + "step": 1722368 + }, + { + "epoch": 0.01, + "learning_rate": 2.179358710870219e-05, + "loss": 3.444, + "step": 1722880 + }, + { + "epoch": 0.01, + "learning_rate": 2.178520116119167e-05, + "loss": 3.4469, + "step": 1723392 + }, + { + "epoch": 0.01, + "learning_rate": 2.177681521368115e-05, + "loss": 3.443, + "step": 1723904 + }, + { + "epoch": 0.01, + "learning_rate": 2.176842926617063e-05, + "loss": 3.4403, + "step": 1724416 + }, + { + "epoch": 0.02, + "learning_rate": 2.1760076076267575e-05, + "loss": 3.4498, + "step": 1724928 + }, + { + "epoch": 0.02, + "learning_rate": 2.175169012875705e-05, + "loss": 3.4342, + "step": 1725440 + }, + { + "epoch": 0.02, + "learning_rate": 2.174330418124653e-05, + "loss": 3.4416, + "step": 1725952 + }, + { + "epoch": 0.02, + "learning_rate": 2.173491823373601e-05, + "loss": 3.4401, + "step": 1726464 + }, + { + "epoch": 0.02, + "learning_rate": 2.1726532286225494e-05, + "loss": 3.4601, + "step": 1726976 + }, + { + "epoch": 0.02, + "learning_rate": 2.1718146338714974e-05, + "loss": 3.455, + "step": 1727488 + }, + { + "epoch": 0.02, + "learning_rate": 2.1709760391204454e-05, + "loss": 3.4512, + "step": 1728000 + }, + { + "epoch": 0.02, + "learning_rate": 2.1701374443693934e-05, + "loss": 3.4382, + "step": 1728512 + }, + { + "epoch": 0.02, + "learning_rate": 2.1693004874987143e-05, + "loss": 3.4487, + "step": 1729024 + }, + { + "epoch": 0.02, + "learning_rate": 2.1684618927476623e-05, + "loss": 3.4425, + "step": 1729536 + }, + { + "epoch": 0.02, + "learning_rate": 2.1676232979966103e-05, + "loss": 3.4518, + "step": 1730048 + }, + { + "epoch": 0.02, + "learning_rate": 2.1667847032455583e-05, + "loss": 3.4424, + "step": 1730560 + }, + { + "epoch": 0.02, + "learning_rate": 2.1659477463748796e-05, + "loss": 3.44, + "step": 1731072 + }, + { + "epoch": 0.02, + "learning_rate": 2.1651091516238276e-05, + "loss": 3.4492, + "step": 1731584 + }, + { + "epoch": 0.02, + "learning_rate": 2.1642705568727756e-05, + "loss": 3.4536, + "step": 1732096 + }, + { + "epoch": 0.02, + "learning_rate": 2.1634319621217232e-05, + "loss": 3.4404, + "step": 1732608 + }, + { + "epoch": 0.02, + "learning_rate": 2.1625950052510445e-05, + "loss": 3.4466, + "step": 1733120 + }, + { + "epoch": 0.02, + "learning_rate": 2.1617564104999928e-05, + "loss": 3.44, + "step": 1733632 + }, + { + "epoch": 0.02, + "learning_rate": 2.1609178157489405e-05, + "loss": 3.4394, + "step": 1734144 + }, + { + "epoch": 0.02, + "learning_rate": 2.1600792209978885e-05, + "loss": 3.428, + "step": 1734656 + }, + { + "epoch": 0.02, + "learning_rate": 2.1592422641272097e-05, + "loss": 3.4483, + "step": 1735168 + }, + { + "epoch": 0.02, + "learning_rate": 2.1584036693761577e-05, + "loss": 3.4429, + "step": 1735680 + }, + { + "epoch": 0.02, + "learning_rate": 2.1575650746251057e-05, + "loss": 3.4419, + "step": 1736192 + }, + { + "epoch": 0.02, + "learning_rate": 2.1567264798740537e-05, + "loss": 3.4421, + "step": 1736704 + }, + { + "epoch": 0.02, + "learning_rate": 2.155889523003375e-05, + "loss": 3.4387, + "step": 1737216 + }, + { + "epoch": 0.02, + "learning_rate": 2.155050928252323e-05, + "loss": 3.4532, + "step": 1737728 + }, + { + "epoch": 0.02, + "learning_rate": 2.1542123335012706e-05, + "loss": 3.4594, + "step": 1738240 + }, + { + "epoch": 0.02, + "learning_rate": 2.1533737387502186e-05, + "loss": 3.4526, + "step": 1738752 + }, + { + "epoch": 0.02, + "learning_rate": 2.15253678187954e-05, + "loss": 3.4487, + "step": 1739264 + }, + { + "epoch": 0.02, + "learning_rate": 2.151698187128488e-05, + "loss": 3.4404, + "step": 1739776 + }, + { + "epoch": 0.02, + "learning_rate": 2.1508595923774358e-05, + "loss": 3.4402, + "step": 1740288 + }, + { + "epoch": 0.02, + "learning_rate": 2.1500209976263838e-05, + "loss": 3.4322, + "step": 1740800 + }, + { + "epoch": 0.02, + "learning_rate": 2.149184040755705e-05, + "loss": 3.4423, + "step": 1741312 + }, + { + "epoch": 0.02, + "learning_rate": 2.1483454460046527e-05, + "loss": 3.4466, + "step": 1741824 + }, + { + "epoch": 0.02, + "learning_rate": 2.147506851253601e-05, + "loss": 3.4442, + "step": 1742336 + }, + { + "epoch": 0.02, + "learning_rate": 2.146668256502549e-05, + "loss": 3.4457, + "step": 1742848 + }, + { + "epoch": 0.02, + "learning_rate": 2.1458312996318703e-05, + "loss": 3.441, + "step": 1743360 + }, + { + "epoch": 0.02, + "learning_rate": 2.144992704880818e-05, + "loss": 3.4492, + "step": 1743872 + }, + { + "epoch": 0.02, + "learning_rate": 2.1441557480101392e-05, + "loss": 3.4365, + "step": 1744384 + }, + { + "epoch": 0.02, + "learning_rate": 2.1433171532590872e-05, + "loss": 3.4459, + "step": 1744896 + }, + { + "epoch": 0.02, + "learning_rate": 2.1424785585080352e-05, + "loss": 3.4461, + "step": 1745408 + }, + { + "epoch": 0.02, + "learning_rate": 2.1416399637569832e-05, + "loss": 3.4509, + "step": 1745920 + }, + { + "epoch": 0.02, + "learning_rate": 2.1408013690059312e-05, + "loss": 3.4527, + "step": 1746432 + }, + { + "epoch": 0.02, + "learning_rate": 2.1399627742548792e-05, + "loss": 3.441, + "step": 1746944 + }, + { + "epoch": 0.02, + "learning_rate": 2.1391241795038272e-05, + "loss": 3.4495, + "step": 1747456 + }, + { + "epoch": 0.02, + "learning_rate": 2.1382855847527752e-05, + "loss": 3.4443, + "step": 1747968 + }, + { + "epoch": 0.02, + "learning_rate": 2.1374486278820964e-05, + "loss": 3.4523, + "step": 1748480 + }, + { + "epoch": 0.02, + "learning_rate": 2.1366100331310444e-05, + "loss": 3.4442, + "step": 1748992 + }, + { + "epoch": 0.02, + "learning_rate": 2.1357714383799924e-05, + "loss": 3.4512, + "step": 1749504 + }, + { + "epoch": 0.02, + "learning_rate": 2.1349328436289404e-05, + "loss": 3.4405, + "step": 1750016 + }, + { + "epoch": 0.02, + "learning_rate": 2.1340958867582613e-05, + "loss": 3.4503, + "step": 1750528 + }, + { + "epoch": 0.02, + "learning_rate": 2.1332572920072093e-05, + "loss": 3.4384, + "step": 1751040 + }, + { + "epoch": 0.02, + "learning_rate": 2.1324186972561573e-05, + "loss": 3.4439, + "step": 1751552 + }, + { + "epoch": 0.02, + "learning_rate": 2.1315801025051053e-05, + "loss": 3.4446, + "step": 1752064 + }, + { + "epoch": 0.02, + "learning_rate": 2.1307431456344266e-05, + "loss": 3.4462, + "step": 1752576 + }, + { + "epoch": 0.02, + "learning_rate": 2.1299045508833746e-05, + "loss": 3.4485, + "step": 1753088 + }, + { + "epoch": 0.02, + "learning_rate": 2.1290659561323226e-05, + "loss": 3.4465, + "step": 1753600 + }, + { + "epoch": 0.02, + "learning_rate": 2.1282273613812705e-05, + "loss": 3.4551, + "step": 1754112 + }, + { + "epoch": 0.02, + "learning_rate": 2.1273904045105918e-05, + "loss": 3.4382, + "step": 1754624 + }, + { + "epoch": 0.02, + "learning_rate": 2.1265518097595398e-05, + "loss": 3.448, + "step": 1755136 + }, + { + "epoch": 0.03, + "eval_loss": 3.8479199409484863, + "eval_runtime": 303.0682, + "eval_samples_per_second": 1259.093, + "eval_steps_per_second": 39.348, + "step": 1755349 + }, + { + "epoch": 1.0, + "learning_rate": 2.1257132150084878e-05, + "loss": 3.4434, + "step": 1755648 + }, + { + "epoch": 1.0, + "learning_rate": 2.1248746202574358e-05, + "loss": 3.4336, + "step": 1756160 + }, + { + "epoch": 1.0, + "learning_rate": 2.1240376633867567e-05, + "loss": 3.4459, + "step": 1756672 + }, + { + "epoch": 1.0, + "learning_rate": 2.1231990686357047e-05, + "loss": 3.4483, + "step": 1757184 + }, + { + "epoch": 1.0, + "learning_rate": 2.1223604738846527e-05, + "loss": 3.451, + "step": 1757696 + }, + { + "epoch": 1.0, + "learning_rate": 2.1215218791336007e-05, + "loss": 3.443, + "step": 1758208 + }, + { + "epoch": 1.0, + "learning_rate": 2.120684922262922e-05, + "loss": 3.4411, + "step": 1758720 + }, + { + "epoch": 1.0, + "learning_rate": 2.11984632751187e-05, + "loss": 3.4375, + "step": 1759232 + }, + { + "epoch": 1.0, + "learning_rate": 2.119007732760818e-05, + "loss": 3.4425, + "step": 1759744 + }, + { + "epoch": 1.0, + "learning_rate": 2.1181691380097656e-05, + "loss": 3.4337, + "step": 1760256 + }, + { + "epoch": 1.0, + "learning_rate": 2.1173321811390868e-05, + "loss": 3.4499, + "step": 1760768 + }, + { + "epoch": 1.0, + "learning_rate": 2.116493586388035e-05, + "loss": 3.4489, + "step": 1761280 + }, + { + "epoch": 1.0, + "learning_rate": 2.115656629517356e-05, + "loss": 3.4365, + "step": 1761792 + }, + { + "epoch": 1.0, + "learning_rate": 2.114818034766304e-05, + "loss": 3.4297, + "step": 1762304 + }, + { + "epoch": 1.0, + "learning_rate": 2.113979440015252e-05, + "loss": 3.4431, + "step": 1762816 + }, + { + "epoch": 1.0, + "learning_rate": 2.1131408452642e-05, + "loss": 3.4319, + "step": 1763328 + }, + { + "epoch": 1.0, + "learning_rate": 2.112302250513148e-05, + "loss": 3.4375, + "step": 1763840 + }, + { + "epoch": 1.0, + "learning_rate": 2.111463655762096e-05, + "loss": 3.4361, + "step": 1764352 + }, + { + "epoch": 1.0, + "learning_rate": 2.110625061011044e-05, + "loss": 3.4398, + "step": 1764864 + }, + { + "epoch": 1.0, + "learning_rate": 2.109786466259992e-05, + "loss": 3.4519, + "step": 1765376 + }, + { + "epoch": 1.0, + "learning_rate": 2.108949509389313e-05, + "loss": 3.4438, + "step": 1765888 + }, + { + "epoch": 1.0, + "learning_rate": 2.108110914638261e-05, + "loss": 3.4366, + "step": 1766400 + }, + { + "epoch": 1.0, + "learning_rate": 2.107272319887209e-05, + "loss": 3.4413, + "step": 1766912 + }, + { + "epoch": 1.0, + "learning_rate": 2.1064337251361573e-05, + "loss": 3.443, + "step": 1767424 + }, + { + "epoch": 1.0, + "learning_rate": 2.1055967682654782e-05, + "loss": 3.4335, + "step": 1767936 + }, + { + "epoch": 1.0, + "learning_rate": 2.1047581735144262e-05, + "loss": 3.4471, + "step": 1768448 + }, + { + "epoch": 1.0, + "learning_rate": 2.1039195787633742e-05, + "loss": 3.4361, + "step": 1768960 + }, + { + "epoch": 1.0, + "learning_rate": 2.103082621892695e-05, + "loss": 3.4319, + "step": 1769472 + }, + { + "epoch": 1.0, + "learning_rate": 2.1022440271416434e-05, + "loss": 3.437, + "step": 1769984 + }, + { + "epoch": 1.0, + "learning_rate": 2.1014054323905914e-05, + "loss": 3.444, + "step": 1770496 + }, + { + "epoch": 1.01, + "learning_rate": 2.1005668376395394e-05, + "loss": 3.4383, + "step": 1771008 + }, + { + "epoch": 1.01, + "learning_rate": 2.0997282428884874e-05, + "loss": 3.4409, + "step": 1771520 + }, + { + "epoch": 1.01, + "learning_rate": 2.0988896481374354e-05, + "loss": 3.4467, + "step": 1772032 + }, + { + "epoch": 1.01, + "learning_rate": 2.0980510533863834e-05, + "loss": 3.4489, + "step": 1772544 + }, + { + "epoch": 1.01, + "learning_rate": 2.0972140965157043e-05, + "loss": 3.4335, + "step": 1773056 + }, + { + "epoch": 1.01, + "learning_rate": 2.0963755017646526e-05, + "loss": 3.4414, + "step": 1773568 + }, + { + "epoch": 1.01, + "learning_rate": 2.0955369070136006e-05, + "loss": 3.4448, + "step": 1774080 + }, + { + "epoch": 1.01, + "learning_rate": 2.0946983122625483e-05, + "loss": 3.4352, + "step": 1774592 + }, + { + "epoch": 1.01, + "learning_rate": 2.0938597175114963e-05, + "loss": 3.4291, + "step": 1775104 + }, + { + "epoch": 1.01, + "learning_rate": 2.0930211227604443e-05, + "loss": 3.4317, + "step": 1775616 + }, + { + "epoch": 1.01, + "learning_rate": 2.0921825280093923e-05, + "loss": 3.4368, + "step": 1776128 + }, + { + "epoch": 1.01, + "learning_rate": 2.0913439332583403e-05, + "loss": 3.4422, + "step": 1776640 + }, + { + "epoch": 1.01, + "learning_rate": 2.0905069763876615e-05, + "loss": 3.4344, + "step": 1777152 + }, + { + "epoch": 1.01, + "learning_rate": 2.0896683816366095e-05, + "loss": 3.4336, + "step": 1777664 + }, + { + "epoch": 1.01, + "learning_rate": 2.0888297868855575e-05, + "loss": 3.4524, + "step": 1778176 + }, + { + "epoch": 1.01, + "learning_rate": 2.0879911921345055e-05, + "loss": 3.4421, + "step": 1778688 + }, + { + "epoch": 1.01, + "learning_rate": 2.0871542352638264e-05, + "loss": 3.4441, + "step": 1779200 + }, + { + "epoch": 1.01, + "learning_rate": 2.0863156405127744e-05, + "loss": 3.4299, + "step": 1779712 + }, + { + "epoch": 1.01, + "learning_rate": 2.0854770457617227e-05, + "loss": 3.4185, + "step": 1780224 + }, + { + "epoch": 1.01, + "learning_rate": 2.0846384510106707e-05, + "loss": 3.4472, + "step": 1780736 + }, + { + "epoch": 1.01, + "learning_rate": 2.0838014941399917e-05, + "loss": 3.4333, + "step": 1781248 + }, + { + "epoch": 1.01, + "learning_rate": 2.0829628993889396e-05, + "loss": 3.4349, + "step": 1781760 + }, + { + "epoch": 1.01, + "learning_rate": 2.0821243046378876e-05, + "loss": 3.4402, + "step": 1782272 + }, + { + "epoch": 1.01, + "learning_rate": 2.0812857098868356e-05, + "loss": 3.434, + "step": 1782784 + }, + { + "epoch": 1.01, + "learning_rate": 2.080448753016157e-05, + "loss": 3.4198, + "step": 1783296 + }, + { + "epoch": 1.01, + "learning_rate": 2.079610158265105e-05, + "loss": 3.4332, + "step": 1783808 + }, + { + "epoch": 1.01, + "learning_rate": 2.078771563514053e-05, + "loss": 3.4347, + "step": 1784320 + }, + { + "epoch": 1.01, + "learning_rate": 2.077932968763001e-05, + "loss": 3.4322, + "step": 1784832 + }, + { + "epoch": 1.01, + "learning_rate": 2.0770960118923218e-05, + "loss": 3.4431, + "step": 1785344 + }, + { + "epoch": 1.01, + "learning_rate": 2.0762574171412698e-05, + "loss": 3.4324, + "step": 1785856 + }, + { + "epoch": 1.01, + "learning_rate": 2.075418822390218e-05, + "loss": 3.4303, + "step": 1786368 + }, + { + "epoch": 1.01, + "learning_rate": 2.074580227639166e-05, + "loss": 3.4445, + "step": 1786880 + }, + { + "epoch": 1.01, + "learning_rate": 2.073743270768487e-05, + "loss": 3.4258, + "step": 1787392 + }, + { + "epoch": 1.01, + "learning_rate": 2.072904676017435e-05, + "loss": 3.429, + "step": 1787904 + }, + { + "epoch": 1.01, + "learning_rate": 2.072066081266383e-05, + "loss": 3.4321, + "step": 1788416 + }, + { + "epoch": 1.01, + "learning_rate": 2.071227486515331e-05, + "loss": 3.4308, + "step": 1788928 + }, + { + "epoch": 1.01, + "learning_rate": 2.0703905296446523e-05, + "loss": 3.429, + "step": 1789440 + }, + { + "epoch": 1.01, + "learning_rate": 2.0695519348936003e-05, + "loss": 3.4304, + "step": 1789952 + }, + { + "epoch": 1.01, + "learning_rate": 2.0687133401425482e-05, + "loss": 3.4177, + "step": 1790464 + }, + { + "epoch": 1.01, + "learning_rate": 2.067876383271869e-05, + "loss": 3.4284, + "step": 1790976 + }, + { + "epoch": 1.01, + "learning_rate": 2.067037788520817e-05, + "loss": 3.447, + "step": 1791488 + }, + { + "epoch": 1.01, + "learning_rate": 2.066199193769765e-05, + "loss": 3.4271, + "step": 1792000 + }, + { + "epoch": 1.01, + "learning_rate": 2.0653605990187135e-05, + "loss": 3.4508, + "step": 1792512 + }, + { + "epoch": 1.01, + "learning_rate": 2.0645236421480344e-05, + "loss": 3.4388, + "step": 1793024 + }, + { + "epoch": 1.01, + "learning_rate": 2.0636850473969824e-05, + "loss": 3.4438, + "step": 1793536 + }, + { + "epoch": 1.01, + "learning_rate": 2.0628464526459304e-05, + "loss": 3.4279, + "step": 1794048 + }, + { + "epoch": 1.01, + "learning_rate": 2.0620078578948784e-05, + "loss": 3.4458, + "step": 1794560 + }, + { + "epoch": 1.01, + "learning_rate": 2.0611709010241996e-05, + "loss": 3.4373, + "step": 1795072 + }, + { + "epoch": 1.01, + "learning_rate": 2.0603323062731476e-05, + "loss": 3.4294, + "step": 1795584 + }, + { + "epoch": 1.01, + "learning_rate": 2.0594937115220956e-05, + "loss": 3.4466, + "step": 1796096 + }, + { + "epoch": 1.01, + "learning_rate": 2.0586551167710436e-05, + "loss": 3.4341, + "step": 1796608 + }, + { + "epoch": 1.01, + "learning_rate": 2.0578181599003645e-05, + "loss": 3.4417, + "step": 1797120 + }, + { + "epoch": 1.01, + "learning_rate": 2.0569795651493125e-05, + "loss": 3.4383, + "step": 1797632 + }, + { + "epoch": 1.01, + "learning_rate": 2.0561409703982605e-05, + "loss": 3.4166, + "step": 1798144 + }, + { + "epoch": 1.01, + "learning_rate": 2.0553023756472085e-05, + "loss": 3.4232, + "step": 1798656 + }, + { + "epoch": 1.01, + "learning_rate": 2.0544637808961565e-05, + "loss": 3.4301, + "step": 1799168 + }, + { + "epoch": 1.01, + "learning_rate": 2.0536251861451045e-05, + "loss": 3.438, + "step": 1799680 + }, + { + "epoch": 1.01, + "learning_rate": 2.0527865913940525e-05, + "loss": 3.4336, + "step": 1800192 + }, + { + "epoch": 1.01, + "learning_rate": 2.0519479966430005e-05, + "loss": 3.4307, + "step": 1800704 + }, + { + "epoch": 1.02, + "learning_rate": 2.051112677652695e-05, + "loss": 3.4353, + "step": 1801216 + }, + { + "epoch": 1.02, + "learning_rate": 2.050274082901643e-05, + "loss": 3.4271, + "step": 1801728 + }, + { + "epoch": 1.02, + "learning_rate": 2.049435488150591e-05, + "loss": 3.4302, + "step": 1802240 + }, + { + "epoch": 1.02, + "learning_rate": 2.0485968933995386e-05, + "loss": 3.4278, + "step": 1802752 + }, + { + "epoch": 1.02, + "learning_rate": 2.0477582986484866e-05, + "loss": 3.4472, + "step": 1803264 + }, + { + "epoch": 1.02, + "learning_rate": 2.0469197038974346e-05, + "loss": 3.4511, + "step": 1803776 + }, + { + "epoch": 1.02, + "learning_rate": 2.0460811091463826e-05, + "loss": 3.434, + "step": 1804288 + }, + { + "epoch": 1.02, + "learning_rate": 2.0452425143953306e-05, + "loss": 3.4284, + "step": 1804800 + }, + { + "epoch": 1.02, + "learning_rate": 2.044405557524652e-05, + "loss": 3.4373, + "step": 1805312 + }, + { + "epoch": 1.02, + "learning_rate": 2.0435669627736e-05, + "loss": 3.4334, + "step": 1805824 + }, + { + "epoch": 1.02, + "learning_rate": 2.042728368022548e-05, + "loss": 3.4421, + "step": 1806336 + }, + { + "epoch": 1.02, + "learning_rate": 2.041889773271496e-05, + "loss": 3.431, + "step": 1806848 + }, + { + "epoch": 1.02, + "learning_rate": 2.0410528164008168e-05, + "loss": 3.4315, + "step": 1807360 + }, + { + "epoch": 1.02, + "learning_rate": 2.040214221649765e-05, + "loss": 3.4374, + "step": 1807872 + }, + { + "epoch": 1.02, + "learning_rate": 2.039375626898713e-05, + "loss": 3.4417, + "step": 1808384 + }, + { + "epoch": 1.02, + "learning_rate": 2.038537032147661e-05, + "loss": 3.4271, + "step": 1808896 + }, + { + "epoch": 1.02, + "learning_rate": 2.037700075276982e-05, + "loss": 3.4358, + "step": 1809408 + }, + { + "epoch": 1.02, + "learning_rate": 2.03686148052593e-05, + "loss": 3.4305, + "step": 1809920 + }, + { + "epoch": 1.02, + "learning_rate": 2.036022885774878e-05, + "loss": 3.4269, + "step": 1810432 + }, + { + "epoch": 1.02, + "learning_rate": 2.035184291023826e-05, + "loss": 3.4219, + "step": 1810944 + }, + { + "epoch": 1.02, + "learning_rate": 2.0343473341531472e-05, + "loss": 3.4303, + "step": 1811456 + }, + { + "epoch": 1.02, + "learning_rate": 2.0335087394020952e-05, + "loss": 3.4342, + "step": 1811968 + }, + { + "epoch": 1.02, + "learning_rate": 2.0326701446510432e-05, + "loss": 3.4265, + "step": 1812480 + }, + { + "epoch": 1.02, + "learning_rate": 2.0318315498999912e-05, + "loss": 3.4337, + "step": 1812992 + }, + { + "epoch": 1.02, + "learning_rate": 2.030994593029312e-05, + "loss": 3.4292, + "step": 1813504 + }, + { + "epoch": 1.02, + "learning_rate": 2.0301559982782605e-05, + "loss": 3.4405, + "step": 1814016 + }, + { + "epoch": 1.02, + "learning_rate": 2.0293174035272085e-05, + "loss": 3.4474, + "step": 1814528 + }, + { + "epoch": 1.02, + "learning_rate": 2.028478808776156e-05, + "loss": 3.4405, + "step": 1815040 + }, + { + "epoch": 1.02, + "learning_rate": 2.0276418519054774e-05, + "loss": 3.4379, + "step": 1815552 + }, + { + "epoch": 1.02, + "learning_rate": 2.0268032571544254e-05, + "loss": 3.4259, + "step": 1816064 + }, + { + "epoch": 1.02, + "learning_rate": 2.0259646624033734e-05, + "loss": 3.4312, + "step": 1816576 + }, + { + "epoch": 1.02, + "learning_rate": 2.0251260676523214e-05, + "loss": 3.4215, + "step": 1817088 + }, + { + "epoch": 1.02, + "learning_rate": 2.0242891107816426e-05, + "loss": 3.4288, + "step": 1817600 + }, + { + "epoch": 1.02, + "learning_rate": 2.0234505160305906e-05, + "loss": 3.4378, + "step": 1818112 + }, + { + "epoch": 1.02, + "learning_rate": 2.0226119212795386e-05, + "loss": 3.4316, + "step": 1818624 + }, + { + "epoch": 1.02, + "learning_rate": 2.0217733265284863e-05, + "loss": 3.4325, + "step": 1819136 + }, + { + "epoch": 1.02, + "learning_rate": 2.0209363696578075e-05, + "loss": 3.4337, + "step": 1819648 + }, + { + "epoch": 1.02, + "learning_rate": 2.020097774906756e-05, + "loss": 3.4401, + "step": 1820160 + }, + { + "epoch": 1.02, + "learning_rate": 2.0192591801557035e-05, + "loss": 3.4279, + "step": 1820672 + }, + { + "epoch": 1.02, + "learning_rate": 2.0184205854046515e-05, + "loss": 3.432, + "step": 1821184 + }, + { + "epoch": 1.02, + "learning_rate": 2.0175836285339727e-05, + "loss": 3.4345, + "step": 1821696 + }, + { + "epoch": 1.02, + "learning_rate": 2.0167450337829207e-05, + "loss": 3.4352, + "step": 1822208 + }, + { + "epoch": 1.02, + "learning_rate": 2.0159064390318684e-05, + "loss": 3.4457, + "step": 1822720 + }, + { + "epoch": 1.02, + "learning_rate": 2.0150678442808167e-05, + "loss": 3.4309, + "step": 1823232 + }, + { + "epoch": 1.02, + "learning_rate": 2.014230887410138e-05, + "loss": 3.4393, + "step": 1823744 + }, + { + "epoch": 1.02, + "learning_rate": 2.013392292659086e-05, + "loss": 3.4325, + "step": 1824256 + }, + { + "epoch": 1.02, + "learning_rate": 2.0125536979080336e-05, + "loss": 3.4413, + "step": 1824768 + }, + { + "epoch": 1.02, + "learning_rate": 2.0117151031569816e-05, + "loss": 3.4286, + "step": 1825280 + }, + { + "epoch": 1.02, + "learning_rate": 2.010878146286303e-05, + "loss": 3.4386, + "step": 1825792 + }, + { + "epoch": 1.02, + "learning_rate": 2.010039551535251e-05, + "loss": 3.4303, + "step": 1826304 + }, + { + "epoch": 1.02, + "learning_rate": 2.009200956784199e-05, + "loss": 3.4402, + "step": 1826816 + }, + { + "epoch": 1.02, + "learning_rate": 2.00836399991352e-05, + "loss": 3.4255, + "step": 1827328 + }, + { + "epoch": 1.02, + "learning_rate": 2.007525405162468e-05, + "loss": 3.4351, + "step": 1827840 + }, + { + "epoch": 1.02, + "learning_rate": 2.0066868104114158e-05, + "loss": 3.4338, + "step": 1828352 + }, + { + "epoch": 1.02, + "learning_rate": 2.0058482156603638e-05, + "loss": 3.4369, + "step": 1828864 + }, + { + "epoch": 1.02, + "learning_rate": 2.0050112587896853e-05, + "loss": 3.4331, + "step": 1829376 + }, + { + "epoch": 1.02, + "learning_rate": 2.0041726640386333e-05, + "loss": 3.4375, + "step": 1829888 + }, + { + "epoch": 1.02, + "learning_rate": 2.003334069287581e-05, + "loss": 3.444, + "step": 1830400 + }, + { + "epoch": 1.02, + "learning_rate": 2.002495474536529e-05, + "loss": 3.4274, + "step": 1830912 + }, + { + "epoch": 1.02, + "learning_rate": 2.0016585176658502e-05, + "loss": 3.4378, + "step": 1831424 + }, + { + "epoch": 1.03, + "eval_loss": 3.8502888679504395, + "eval_runtime": 302.7533, + "eval_samples_per_second": 1260.403, + "eval_steps_per_second": 39.389, + "step": 1831669 + }, + { + "epoch": 0.0, + "learning_rate": 2.0008199229147982e-05, + "loss": 3.4272, + "step": 1831936 + }, + { + "epoch": 0.0, + "learning_rate": 1.9999813281637462e-05, + "loss": 3.4262, + "step": 1832448 + }, + { + "epoch": 0.0, + "learning_rate": 1.9991427334126942e-05, + "loss": 3.4298, + "step": 1832960 + }, + { + "epoch": 0.0, + "learning_rate": 1.9983041386616422e-05, + "loss": 3.4372, + "step": 1833472 + }, + { + "epoch": 0.0, + "learning_rate": 1.997467181790963e-05, + "loss": 3.4404, + "step": 1833984 + }, + { + "epoch": 0.0, + "learning_rate": 1.996628587039911e-05, + "loss": 3.4323, + "step": 1834496 + }, + { + "epoch": 0.0, + "learning_rate": 1.995789992288859e-05, + "loss": 3.4356, + "step": 1835008 + }, + { + "epoch": 0.0, + "learning_rate": 1.9949513975378075e-05, + "loss": 3.4292, + "step": 1835520 + }, + { + "epoch": 0.0, + "learning_rate": 1.9941144406671284e-05, + "loss": 3.4266, + "step": 1836032 + }, + { + "epoch": 0.0, + "learning_rate": 1.9932758459160764e-05, + "loss": 3.426, + "step": 1836544 + }, + { + "epoch": 0.0, + "learning_rate": 1.9924372511650244e-05, + "loss": 3.4369, + "step": 1837056 + }, + { + "epoch": 0.0, + "learning_rate": 1.9916002942943453e-05, + "loss": 3.437, + "step": 1837568 + }, + { + "epoch": 0.0, + "learning_rate": 1.9907616995432936e-05, + "loss": 3.4261, + "step": 1838080 + }, + { + "epoch": 0.0, + "learning_rate": 1.9899231047922416e-05, + "loss": 3.4168, + "step": 1838592 + }, + { + "epoch": 0.0, + "learning_rate": 1.9890845100411896e-05, + "loss": 3.4339, + "step": 1839104 + }, + { + "epoch": 0.0, + "learning_rate": 1.9882459152901376e-05, + "loss": 3.4169, + "step": 1839616 + }, + { + "epoch": 0.0, + "learning_rate": 1.9874073205390856e-05, + "loss": 3.4285, + "step": 1840128 + }, + { + "epoch": 0.0, + "learning_rate": 1.9865687257880336e-05, + "loss": 3.425, + "step": 1840640 + }, + { + "epoch": 0.0, + "learning_rate": 1.9857317689173545e-05, + "loss": 3.4321, + "step": 1841152 + }, + { + "epoch": 0.0, + "learning_rate": 1.9848931741663028e-05, + "loss": 3.4362, + "step": 1841664 + }, + { + "epoch": 0.0, + "learning_rate": 1.9840545794152508e-05, + "loss": 3.4348, + "step": 1842176 + }, + { + "epoch": 0.0, + "learning_rate": 1.9832159846641988e-05, + "loss": 3.4284, + "step": 1842688 + }, + { + "epoch": 0.0, + "learning_rate": 1.9823790277935197e-05, + "loss": 3.4286, + "step": 1843200 + }, + { + "epoch": 0.0, + "learning_rate": 1.9815404330424677e-05, + "loss": 3.429, + "step": 1843712 + }, + { + "epoch": 0.0, + "learning_rate": 1.9807018382914157e-05, + "loss": 3.4285, + "step": 1844224 + }, + { + "epoch": 0.0, + "learning_rate": 1.9798632435403637e-05, + "loss": 3.4379, + "step": 1844736 + }, + { + "epoch": 0.0, + "learning_rate": 1.979026286669685e-05, + "loss": 3.4214, + "step": 1845248 + }, + { + "epoch": 0.0, + "learning_rate": 1.978189329799006e-05, + "loss": 3.4245, + "step": 1845760 + }, + { + "epoch": 0.0, + "learning_rate": 1.977350735047954e-05, + "loss": 3.4296, + "step": 1846272 + }, + { + "epoch": 0.0, + "learning_rate": 1.976512140296902e-05, + "loss": 3.4271, + "step": 1846784 + }, + { + "epoch": 0.01, + "learning_rate": 1.97567354554585e-05, + "loss": 3.4271, + "step": 1847296 + }, + { + "epoch": 0.01, + "learning_rate": 1.9748349507947982e-05, + "loss": 3.4332, + "step": 1847808 + }, + { + "epoch": 0.01, + "learning_rate": 1.973996356043746e-05, + "loss": 3.4368, + "step": 1848320 + }, + { + "epoch": 0.01, + "learning_rate": 1.973157761292694e-05, + "loss": 3.433, + "step": 1848832 + }, + { + "epoch": 0.01, + "learning_rate": 1.972319166541642e-05, + "loss": 3.4238, + "step": 1849344 + }, + { + "epoch": 0.01, + "learning_rate": 1.971482209670963e-05, + "loss": 3.4341, + "step": 1849856 + }, + { + "epoch": 0.01, + "learning_rate": 1.9706436149199107e-05, + "loss": 3.4331, + "step": 1850368 + }, + { + "epoch": 0.01, + "learning_rate": 1.969805020168859e-05, + "loss": 3.4264, + "step": 1850880 + }, + { + "epoch": 0.01, + "learning_rate": 1.968966425417807e-05, + "loss": 3.4183, + "step": 1851392 + }, + { + "epoch": 0.01, + "learning_rate": 1.968127830666755e-05, + "loss": 3.4208, + "step": 1851904 + }, + { + "epoch": 0.01, + "learning_rate": 1.967289235915703e-05, + "loss": 3.4258, + "step": 1852416 + }, + { + "epoch": 0.01, + "learning_rate": 1.966450641164651e-05, + "loss": 3.4341, + "step": 1852928 + }, + { + "epoch": 0.01, + "learning_rate": 1.965612046413599e-05, + "loss": 3.4236, + "step": 1853440 + }, + { + "epoch": 0.01, + "learning_rate": 1.96477508954292e-05, + "loss": 3.4218, + "step": 1853952 + }, + { + "epoch": 0.01, + "learning_rate": 1.9639364947918683e-05, + "loss": 3.4414, + "step": 1854464 + }, + { + "epoch": 0.01, + "learning_rate": 1.9630979000408163e-05, + "loss": 3.4304, + "step": 1854976 + }, + { + "epoch": 0.01, + "learning_rate": 1.962259305289764e-05, + "loss": 3.435, + "step": 1855488 + }, + { + "epoch": 0.01, + "learning_rate": 1.9614223484190852e-05, + "loss": 3.4224, + "step": 1856000 + }, + { + "epoch": 0.01, + "learning_rate": 1.9605837536680332e-05, + "loss": 3.4027, + "step": 1856512 + }, + { + "epoch": 0.01, + "learning_rate": 1.9597451589169812e-05, + "loss": 3.4377, + "step": 1857024 + }, + { + "epoch": 0.01, + "learning_rate": 1.9589065641659292e-05, + "loss": 3.4253, + "step": 1857536 + }, + { + "epoch": 0.01, + "learning_rate": 1.9580696072952504e-05, + "loss": 3.4242, + "step": 1858048 + }, + { + "epoch": 0.01, + "learning_rate": 1.9572310125441984e-05, + "loss": 3.428, + "step": 1858560 + }, + { + "epoch": 0.01, + "learning_rate": 1.9563924177931464e-05, + "loss": 3.4237, + "step": 1859072 + }, + { + "epoch": 0.01, + "learning_rate": 1.955553823042094e-05, + "loss": 3.4118, + "step": 1859584 + }, + { + "epoch": 0.01, + "learning_rate": 1.9547168661714153e-05, + "loss": 3.4205, + "step": 1860096 + }, + { + "epoch": 0.01, + "learning_rate": 1.9538782714203637e-05, + "loss": 3.4238, + "step": 1860608 + }, + { + "epoch": 0.01, + "learning_rate": 1.9530396766693113e-05, + "loss": 3.4194, + "step": 1861120 + }, + { + "epoch": 0.01, + "learning_rate": 1.9522010819182593e-05, + "loss": 3.4345, + "step": 1861632 + }, + { + "epoch": 0.01, + "learning_rate": 1.9513641250475806e-05, + "loss": 3.4218, + "step": 1862144 + }, + { + "epoch": 0.01, + "learning_rate": 1.9505255302965286e-05, + "loss": 3.4202, + "step": 1862656 + }, + { + "epoch": 0.01, + "learning_rate": 1.9496869355454762e-05, + "loss": 3.4372, + "step": 1863168 + }, + { + "epoch": 0.01, + "learning_rate": 1.9488499786747978e-05, + "loss": 3.4128, + "step": 1863680 + }, + { + "epoch": 0.01, + "learning_rate": 1.9480113839237458e-05, + "loss": 3.4183, + "step": 1864192 + }, + { + "epoch": 0.01, + "learning_rate": 1.9471727891726938e-05, + "loss": 3.4187, + "step": 1864704 + }, + { + "epoch": 0.01, + "learning_rate": 1.9463341944216415e-05, + "loss": 3.4257, + "step": 1865216 + }, + { + "epoch": 0.01, + "learning_rate": 1.9454972375509627e-05, + "loss": 3.4186, + "step": 1865728 + }, + { + "epoch": 0.01, + "learning_rate": 1.9446586427999107e-05, + "loss": 3.4228, + "step": 1866240 + }, + { + "epoch": 0.01, + "learning_rate": 1.9438200480488587e-05, + "loss": 3.4029, + "step": 1866752 + }, + { + "epoch": 0.01, + "learning_rate": 1.9429814532978067e-05, + "loss": 3.4223, + "step": 1867264 + }, + { + "epoch": 0.01, + "learning_rate": 1.942144496427128e-05, + "loss": 3.4331, + "step": 1867776 + }, + { + "epoch": 0.01, + "learning_rate": 1.941305901676076e-05, + "loss": 3.4168, + "step": 1868288 + }, + { + "epoch": 0.01, + "learning_rate": 1.9404673069250236e-05, + "loss": 3.439, + "step": 1868800 + }, + { + "epoch": 0.01, + "learning_rate": 1.9396287121739716e-05, + "loss": 3.4266, + "step": 1869312 + }, + { + "epoch": 0.01, + "learning_rate": 1.9387917553032932e-05, + "loss": 3.439, + "step": 1869824 + }, + { + "epoch": 0.01, + "learning_rate": 1.9379531605522412e-05, + "loss": 3.4173, + "step": 1870336 + }, + { + "epoch": 0.01, + "learning_rate": 1.9371145658011888e-05, + "loss": 3.4341, + "step": 1870848 + }, + { + "epoch": 0.01, + "learning_rate": 1.9362759710501368e-05, + "loss": 3.4264, + "step": 1871360 + }, + { + "epoch": 0.01, + "learning_rate": 1.935439014179458e-05, + "loss": 3.4179, + "step": 1871872 + }, + { + "epoch": 0.01, + "learning_rate": 1.9346020573087793e-05, + "loss": 3.4352, + "step": 1872384 + }, + { + "epoch": 0.01, + "learning_rate": 1.9337634625577273e-05, + "loss": 3.4216, + "step": 1872896 + }, + { + "epoch": 0.01, + "learning_rate": 1.9329248678066753e-05, + "loss": 3.4325, + "step": 1873408 + }, + { + "epoch": 0.01, + "learning_rate": 1.9320862730556233e-05, + "loss": 3.4264, + "step": 1873920 + }, + { + "epoch": 0.01, + "learning_rate": 1.931247678304571e-05, + "loss": 3.4076, + "step": 1874432 + }, + { + "epoch": 0.01, + "learning_rate": 1.930409083553519e-05, + "loss": 3.4134, + "step": 1874944 + }, + { + "epoch": 0.01, + "learning_rate": 1.929570488802467e-05, + "loss": 3.422, + "step": 1875456 + }, + { + "epoch": 0.01, + "learning_rate": 1.9287318940514153e-05, + "loss": 3.4263, + "step": 1875968 + }, + { + "epoch": 0.01, + "learning_rate": 1.9278949371807362e-05, + "loss": 3.4231, + "step": 1876480 + }, + { + "epoch": 0.01, + "learning_rate": 1.9270563424296842e-05, + "loss": 3.4165, + "step": 1876992 + }, + { + "epoch": 0.02, + "learning_rate": 1.9262193855590054e-05, + "loss": 3.4246, + "step": 1877504 + }, + { + "epoch": 0.02, + "learning_rate": 1.925380790807953e-05, + "loss": 3.4206, + "step": 1878016 + }, + { + "epoch": 0.02, + "learning_rate": 1.9245421960569014e-05, + "loss": 3.4185, + "step": 1878528 + }, + { + "epoch": 0.02, + "learning_rate": 1.9237036013058494e-05, + "loss": 3.417, + "step": 1879040 + }, + { + "epoch": 0.02, + "learning_rate": 1.9228650065547974e-05, + "loss": 3.4408, + "step": 1879552 + }, + { + "epoch": 0.02, + "learning_rate": 1.9220264118037454e-05, + "loss": 3.4381, + "step": 1880064 + }, + { + "epoch": 0.02, + "learning_rate": 1.9211878170526934e-05, + "loss": 3.4269, + "step": 1880576 + }, + { + "epoch": 0.02, + "learning_rate": 1.9203492223016414e-05, + "loss": 3.4145, + "step": 1881088 + }, + { + "epoch": 0.02, + "learning_rate": 1.9195122654309623e-05, + "loss": 3.4275, + "step": 1881600 + }, + { + "epoch": 0.02, + "learning_rate": 1.9186736706799107e-05, + "loss": 3.4216, + "step": 1882112 + }, + { + "epoch": 0.02, + "learning_rate": 1.9178350759288587e-05, + "loss": 3.4329, + "step": 1882624 + }, + { + "epoch": 0.02, + "learning_rate": 1.9169964811778066e-05, + "loss": 3.42, + "step": 1883136 + }, + { + "epoch": 0.02, + "learning_rate": 1.9161595243071276e-05, + "loss": 3.422, + "step": 1883648 + }, + { + "epoch": 0.02, + "learning_rate": 1.9153209295560756e-05, + "loss": 3.4269, + "step": 1884160 + }, + { + "epoch": 0.02, + "learning_rate": 1.9144823348050235e-05, + "loss": 3.4311, + "step": 1884672 + }, + { + "epoch": 0.02, + "learning_rate": 1.9136437400539715e-05, + "loss": 3.4178, + "step": 1885184 + }, + { + "epoch": 0.02, + "learning_rate": 1.9128067831832928e-05, + "loss": 3.4252, + "step": 1885696 + }, + { + "epoch": 0.02, + "learning_rate": 1.9119681884322408e-05, + "loss": 3.4196, + "step": 1886208 + }, + { + "epoch": 0.02, + "learning_rate": 1.9111295936811888e-05, + "loss": 3.4172, + "step": 1886720 + }, + { + "epoch": 0.02, + "learning_rate": 1.9102909989301364e-05, + "loss": 3.4115, + "step": 1887232 + }, + { + "epoch": 0.02, + "learning_rate": 1.9094540420594577e-05, + "loss": 3.4175, + "step": 1887744 + }, + { + "epoch": 0.02, + "learning_rate": 1.908615447308406e-05, + "loss": 3.4212, + "step": 1888256 + }, + { + "epoch": 0.02, + "learning_rate": 1.9077768525573537e-05, + "loss": 3.4213, + "step": 1888768 + }, + { + "epoch": 0.02, + "learning_rate": 1.9069382578063017e-05, + "loss": 3.4256, + "step": 1889280 + }, + { + "epoch": 0.02, + "learning_rate": 1.906101300935623e-05, + "loss": 3.4158, + "step": 1889792 + }, + { + "epoch": 0.02, + "learning_rate": 1.905262706184571e-05, + "loss": 3.4281, + "step": 1890304 + }, + { + "epoch": 0.02, + "learning_rate": 1.9044241114335186e-05, + "loss": 3.4397, + "step": 1890816 + }, + { + "epoch": 0.02, + "learning_rate": 1.903585516682467e-05, + "loss": 3.428, + "step": 1891328 + }, + { + "epoch": 0.02, + "learning_rate": 1.902748559811788e-05, + "loss": 3.4312, + "step": 1891840 + }, + { + "epoch": 0.02, + "learning_rate": 1.901909965060736e-05, + "loss": 3.4131, + "step": 1892352 + }, + { + "epoch": 0.02, + "learning_rate": 1.9010713703096838e-05, + "loss": 3.4235, + "step": 1892864 + }, + { + "epoch": 0.02, + "learning_rate": 1.9002327755586318e-05, + "loss": 3.4169, + "step": 1893376 + }, + { + "epoch": 0.02, + "learning_rate": 1.899395818687953e-05, + "loss": 3.4191, + "step": 1893888 + }, + { + "epoch": 0.02, + "learning_rate": 1.898557223936901e-05, + "loss": 3.4201, + "step": 1894400 + }, + { + "epoch": 0.02, + "learning_rate": 1.897718629185849e-05, + "loss": 3.4221, + "step": 1894912 + }, + { + "epoch": 0.02, + "learning_rate": 1.896880034434797e-05, + "loss": 3.4227, + "step": 1895424 + }, + { + "epoch": 0.02, + "learning_rate": 1.8960430775641183e-05, + "loss": 3.4222, + "step": 1895936 + }, + { + "epoch": 0.02, + "learning_rate": 1.895204482813066e-05, + "loss": 3.4277, + "step": 1896448 + }, + { + "epoch": 0.02, + "learning_rate": 1.8943675259423875e-05, + "loss": 3.4203, + "step": 1896960 + }, + { + "epoch": 0.02, + "learning_rate": 1.8935289311913355e-05, + "loss": 3.419, + "step": 1897472 + }, + { + "epoch": 0.02, + "learning_rate": 1.8926903364402835e-05, + "loss": 3.4273, + "step": 1897984 + }, + { + "epoch": 0.02, + "learning_rate": 1.8918517416892312e-05, + "loss": 3.4223, + "step": 1898496 + }, + { + "epoch": 0.02, + "learning_rate": 1.8910131469381792e-05, + "loss": 3.4381, + "step": 1899008 + }, + { + "epoch": 0.02, + "learning_rate": 1.8901745521871272e-05, + "loss": 3.4186, + "step": 1899520 + }, + { + "epoch": 0.02, + "learning_rate": 1.889335957436075e-05, + "loss": 3.43, + "step": 1900032 + }, + { + "epoch": 0.02, + "learning_rate": 1.888497362685023e-05, + "loss": 3.4198, + "step": 1900544 + }, + { + "epoch": 0.02, + "learning_rate": 1.8876604058143444e-05, + "loss": 3.4283, + "step": 1901056 + }, + { + "epoch": 0.02, + "learning_rate": 1.8868218110632924e-05, + "loss": 3.424, + "step": 1901568 + }, + { + "epoch": 0.02, + "learning_rate": 1.8859832163122404e-05, + "loss": 3.4247, + "step": 1902080 + }, + { + "epoch": 0.02, + "learning_rate": 1.8851446215611884e-05, + "loss": 3.4176, + "step": 1902592 + }, + { + "epoch": 0.02, + "learning_rate": 1.8843076646905093e-05, + "loss": 3.4343, + "step": 1903104 + }, + { + "epoch": 0.02, + "learning_rate": 1.8834690699394576e-05, + "loss": 3.4146, + "step": 1903616 + }, + { + "epoch": 0.02, + "learning_rate": 1.8826304751884056e-05, + "loss": 3.4228, + "step": 1904128 + }, + { + "epoch": 0.02, + "learning_rate": 1.8817918804373536e-05, + "loss": 3.4255, + "step": 1904640 + }, + { + "epoch": 0.02, + "learning_rate": 1.8809549235666745e-05, + "loss": 3.4311, + "step": 1905152 + }, + { + "epoch": 0.02, + "learning_rate": 1.8801163288156225e-05, + "loss": 3.4186, + "step": 1905664 + }, + { + "epoch": 0.02, + "learning_rate": 1.8792777340645705e-05, + "loss": 3.4268, + "step": 1906176 + }, + { + "epoch": 0.02, + "learning_rate": 1.8784391393135185e-05, + "loss": 3.431, + "step": 1906688 + }, + { + "epoch": 0.02, + "learning_rate": 1.8776021824428398e-05, + "loss": 3.4222, + "step": 1907200 + }, + { + "epoch": 0.02, + "learning_rate": 1.8767635876917878e-05, + "loss": 3.4252, + "step": 1907712 + }, + { + "epoch": 0.03, + "eval_loss": 3.851841926574707, + "eval_runtime": 307.7566, + "eval_samples_per_second": 1239.912, + "eval_steps_per_second": 38.748, + "step": 1907989 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 1.3272995561936947e+18, + "trial_name": null, + "trial_params": null +}