diff --git "a/checkpoint-2365920/trainer_state.json" "b/checkpoint-2365920/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-2365920/trainer_state.json" @@ -0,0 +1,27993 @@ +{ + "best_metric": 3.8402984142303467, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/npi-sim-ques/transformer/1/checkpoints/checkpoint-992160", + "epoch": 1.0250006060157382, + "eval_steps": 10, + "global_step": 2365920, + "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": 10.9382, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 6.826, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 6.1933, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 5.9815, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 5.8161, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 5.7147, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 5.6058, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 5.5348, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 5.4544, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 5.4065, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 5.3447, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 5.3244, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989938500867749e-05, + "loss": 5.2734, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989099906116697e-05, + "loss": 5.2075, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988261311365645e-05, + "loss": 5.1803, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.987422716614593e-05, + "loss": 5.1381, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986584121863541e-05, + "loss": 5.1198, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985745527112489e-05, + "loss": 5.0787, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984906932361437e-05, + "loss": 5.0487, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.0242, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 5.0053, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.982391148108281e-05, + "loss": 4.9826, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.981552553357229e-05, + "loss": 4.9623, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.9807155964865506e-05, + "loss": 4.9436, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 4.9222, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790384069844466e-05, + "loss": 4.9004, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9781998122333946e-05, + "loss": 4.8719, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773628553627155e-05, + "loss": 4.8583, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 4.8359, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756856658606115e-05, + "loss": 4.8294, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748470711095595e-05, + "loss": 4.8119, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.9740101142388804e-05, + "loss": 4.7943, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731715194878284e-05, + "loss": 4.7855, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.97233456261715e-05, + "loss": 4.7653, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.971495967866098e-05, + "loss": 4.762, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.970657373115046e-05, + "loss": 4.7567, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969818778363994e-05, + "loss": 4.7372, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968980183612942e-05, + "loss": 4.7022, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.96814158886189e-05, + "loss": 4.7115, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967302994110837e-05, + "loss": 4.6834, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966464399359785e-05, + "loss": 4.6802, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965627442489107e-05, + "loss": 4.6767, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964788847738054e-05, + "loss": 4.6705, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963950252987002e-05, + "loss": 4.6538, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.96311165823595e-05, + "loss": 4.6545, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962274701365272e-05, + "loss": 4.6442, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.96143610661422e-05, + "loss": 4.6358, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960597511863168e-05, + "loss": 4.6269, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.959758917112116e-05, + "loss": 4.6037, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.9589219602414374e-05, + "loss": 4.5997, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958083365490385e-05, + "loss": 4.6056, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957244770739333e-05, + "loss": 4.59, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956406175988281e-05, + "loss": 4.5756, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.9555692191176016e-05, + "loss": 4.5619, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.9547306243665496e-05, + "loss": 4.567, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.9538920296154976e-05, + "loss": 4.5488, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.9530534348644456e-05, + "loss": 4.5649, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.9522148401133936e-05, + "loss": 4.5377, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951377883242715e-05, + "loss": 4.5431, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.950539288491663e-05, + "loss": 4.5365, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949700693740611e-05, + "loss": 4.5124, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948862098989559e-05, + "loss": 4.5203, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.94802514211888e-05, + "loss": 4.5076, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947186547367828e-05, + "loss": 4.4985, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946347952616776e-05, + "loss": 4.4938, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945509357865724e-05, + "loss": 4.5108, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944672400995045e-05, + "loss": 4.4864, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.943833806243993e-05, + "loss": 4.4767, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942995211492941e-05, + "loss": 4.4631, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.942156616741889e-05, + "loss": 4.4641, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.9413196598712105e-05, + "loss": 4.4802, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.9404810651201585e-05, + "loss": 4.4789, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396424703691065e-05, + "loss": 4.452, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388038756180545e-05, + "loss": 4.4699, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379669187473754e-05, + "loss": 4.4646, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371283239963234e-05, + "loss": 4.4497, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.936291367125644e-05, + "loss": 4.4352, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.935452772374592e-05, + "loss": 4.4412, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.93461417762354e-05, + "loss": 4.4291, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.933775582872488e-05, + "loss": 4.4237, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.932936988121436e-05, + "loss": 4.4241, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.932098393370384e-05, + "loss": 4.4196, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.931259798619332e-05, + "loss": 4.4237, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.930421203868281e-05, + "loss": 4.4206, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.929584246997602e-05, + "loss": 4.4004, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.928747290126923e-05, + "loss": 4.4059, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.927908695375871e-05, + "loss": 4.406, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.927070100624819e-05, + "loss": 4.3959, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.926231505873767e-05, + "loss": 4.3922, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925392911122715e-05, + "loss": 4.3894, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.924554316371663e-05, + "loss": 4.3909, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923715721620611e-05, + "loss": 4.3782, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922877126869559e-05, + "loss": 4.3787, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.92204016999888e-05, + "loss": 4.3736, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921201575247828e-05, + "loss": 4.3766, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920362980496776e-05, + "loss": 4.3702, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919524385745724e-05, + "loss": 4.3642, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918687428875045e-05, + "loss": 4.3493, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.917848834123993e-05, + "loss": 4.3549, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.917010239372941e-05, + "loss": 4.3581, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.916171644621889e-05, + "loss": 4.363, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.91533468775121e-05, + "loss": 4.3484, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.914497730880531e-05, + "loss": 4.3387, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.913659136129479e-05, + "loss": 4.3349, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.912820541378427e-05, + "loss": 4.342, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.911981946627375e-05, + "loss": 4.313, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.9111449897566966e-05, + "loss": 4.3225, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.9103063950056446e-05, + "loss": 4.3247, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.9094678002545926e-05, + "loss": 4.3234, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.9086292055035406e-05, + "loss": 4.315, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.9077906107524886e-05, + "loss": 4.3224, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.9069520160014366e-05, + "loss": 4.304, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.9061134212503846e-05, + "loss": 4.3314, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.9052764643797055e-05, + "loss": 4.3106, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.9044378696286535e-05, + "loss": 4.3122, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.9035992748776015e-05, + "loss": 4.3161, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.9027606801265495e-05, + "loss": 4.3239, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.901925361136244e-05, + "loss": 4.3014, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.901086766385192e-05, + "loss": 4.2956, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.90024817163414e-05, + "loss": 4.3012, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.899409576883088e-05, + "loss": 4.2905, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.898570982132036e-05, + "loss": 4.296, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.897732387380984e-05, + "loss": 4.2919, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.896893792629932e-05, + "loss": 4.2813, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.89605519787888e-05, + "loss": 4.2991, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.895216603127827e-05, + "loss": 4.2806, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.894378008376775e-05, + "loss": 4.2753, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.893539413625723e-05, + "loss": 4.2735, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.892702456755045e-05, + "loss": 4.2789, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.891863862003992e-05, + "loss": 4.2657, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.891025267252941e-05, + "loss": 4.2818, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.890186672501889e-05, + "loss": 4.2754, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.889348077750837e-05, + "loss": 4.2619, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888511120880158e-05, + "loss": 4.2563, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.887672526129106e-05, + "loss": 4.2654, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886833931378054e-05, + "loss": 4.2615, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885995336627002e-05, + "loss": 4.2658, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.88515674187595e-05, + "loss": 4.2614, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884318147124898e-05, + "loss": 4.2621, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883479552373846e-05, + "loss": 4.2574, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.8826425955031666e-05, + "loss": 4.2517, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.8818040007521146e-05, + "loss": 4.2434, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.8809654060010626e-05, + "loss": 4.2421, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.8801268112500106e-05, + "loss": 4.2489, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.879289854379332e-05, + "loss": 4.2279, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.87845125962828e-05, + "loss": 4.2491, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877612664877228e-05, + "loss": 4.2438, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.876774070126176e-05, + "loss": 4.235, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875937113255497e-05, + "loss": 4.2363, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.875098518504445e-05, + "loss": 4.2375, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.197122573852539, + "eval_runtime": 304.6949, + "eval_samples_per_second": 1252.371, + "eval_steps_per_second": 39.138, + "step": 76320 + }, + { + "epoch": 1.0, + "learning_rate": 4.874259923753393e-05, + "loss": 4.2118, + "step": 76800 + }, + { + "epoch": 1.0, + "learning_rate": 4.873421329002341e-05, + "loss": 4.2212, + "step": 77312 + }, + { + "epoch": 1.0, + "learning_rate": 4.872582734251289e-05, + "loss": 4.2319, + "step": 77824 + }, + { + "epoch": 1.0, + "learning_rate": 4.871744139500237e-05, + "loss": 4.2169, + "step": 78336 + }, + { + "epoch": 1.0, + "learning_rate": 4.870907182629558e-05, + "loss": 4.2223, + "step": 78848 + }, + { + "epoch": 1.0, + "learning_rate": 4.870068587878506e-05, + "loss": 4.2114, + "step": 79360 + }, + { + "epoch": 1.0, + "learning_rate": 4.869229993127454e-05, + "loss": 4.2099, + "step": 79872 + }, + { + "epoch": 1.0, + "learning_rate": 4.8683913983764027e-05, + "loss": 4.2038, + "step": 80384 + }, + { + "epoch": 1.0, + "learning_rate": 4.8675544415057236e-05, + "loss": 4.2136, + "step": 80896 + }, + { + "epoch": 1.0, + "learning_rate": 4.8667158467546716e-05, + "loss": 4.2008, + "step": 81408 + }, + { + "epoch": 1.0, + "learning_rate": 4.8658772520036196e-05, + "loss": 4.2208, + "step": 81920 + }, + { + "epoch": 1.0, + "learning_rate": 4.8650386572525676e-05, + "loss": 4.2138, + "step": 82432 + }, + { + "epoch": 1.0, + "learning_rate": 4.8642017003818885e-05, + "loss": 4.1972, + "step": 82944 + }, + { + "epoch": 1.0, + "learning_rate": 4.8633631056308365e-05, + "loss": 4.1927, + "step": 83456 + }, + { + "epoch": 1.0, + "learning_rate": 4.8625245108797845e-05, + "loss": 4.1911, + "step": 83968 + }, + { + "epoch": 1.0, + "learning_rate": 4.8616859161287324e-05, + "loss": 4.1901, + "step": 84480 + }, + { + "epoch": 1.0, + "learning_rate": 4.8608473213776804e-05, + "loss": 4.1857, + "step": 84992 + }, + { + "epoch": 1.0, + "learning_rate": 4.860008726626628e-05, + "loss": 4.1877, + "step": 85504 + }, + { + "epoch": 1.0, + "learning_rate": 4.8591701318755764e-05, + "loss": 4.1811, + "step": 86016 + }, + { + "epoch": 1.0, + "learning_rate": 4.8583315371245244e-05, + "loss": 4.1961, + "step": 86528 + }, + { + "epoch": 1.0, + "learning_rate": 4.857494580253846e-05, + "loss": 4.187, + "step": 87040 + }, + { + "epoch": 1.0, + "learning_rate": 4.856655985502793e-05, + "loss": 4.1907, + "step": 87552 + }, + { + "epoch": 1.0, + "learning_rate": 4.855817390751741e-05, + "loss": 4.1848, + "step": 88064 + }, + { + "epoch": 1.0, + "learning_rate": 4.854978796000689e-05, + "loss": 4.193, + "step": 88576 + }, + { + "epoch": 1.0, + "learning_rate": 4.854141839130011e-05, + "loss": 4.1705, + "step": 89088 + }, + { + "epoch": 1.0, + "learning_rate": 4.853303244378958e-05, + "loss": 4.1724, + "step": 89600 + }, + { + "epoch": 1.0, + "learning_rate": 4.852464649627906e-05, + "loss": 4.1686, + "step": 90112 + }, + { + "epoch": 1.0, + "learning_rate": 4.851626054876854e-05, + "loss": 4.1664, + "step": 90624 + }, + { + "epoch": 1.0, + "learning_rate": 4.850787460125802e-05, + "loss": 4.1681, + "step": 91136 + }, + { + "epoch": 1.01, + "learning_rate": 4.849950503255123e-05, + "loss": 4.1642, + "step": 91648 + }, + { + "epoch": 1.01, + "learning_rate": 4.849111908504072e-05, + "loss": 4.1682, + "step": 92160 + }, + { + "epoch": 1.01, + "learning_rate": 4.84827331375302e-05, + "loss": 4.1683, + "step": 92672 + }, + { + "epoch": 1.01, + "learning_rate": 4.847434719001968e-05, + "loss": 4.1558, + "step": 93184 + }, + { + "epoch": 1.01, + "learning_rate": 4.846596124250916e-05, + "loss": 4.1638, + "step": 93696 + }, + { + "epoch": 1.01, + "learning_rate": 4.845759167380237e-05, + "loss": 4.1717, + "step": 94208 + }, + { + "epoch": 1.01, + "learning_rate": 4.844920572629185e-05, + "loss": 4.1582, + "step": 94720 + }, + { + "epoch": 1.01, + "learning_rate": 4.844081977878133e-05, + "loss": 4.142, + "step": 95232 + }, + { + "epoch": 1.01, + "learning_rate": 4.843243383127081e-05, + "loss": 4.1544, + "step": 95744 + }, + { + "epoch": 1.01, + "learning_rate": 4.842404788376029e-05, + "loss": 4.1361, + "step": 96256 + }, + { + "epoch": 1.01, + "learning_rate": 4.8415678315053496e-05, + "loss": 4.1461, + "step": 96768 + }, + { + "epoch": 1.01, + "learning_rate": 4.8407292367542976e-05, + "loss": 4.1464, + "step": 97280 + }, + { + "epoch": 1.01, + "learning_rate": 4.8398906420032456e-05, + "loss": 4.1525, + "step": 97792 + }, + { + "epoch": 1.01, + "learning_rate": 4.8390520472521936e-05, + "loss": 4.141, + "step": 98304 + }, + { + "epoch": 1.01, + "learning_rate": 4.838215090381515e-05, + "loss": 4.1467, + "step": 98816 + }, + { + "epoch": 1.01, + "learning_rate": 4.837376495630463e-05, + "loss": 4.1494, + "step": 99328 + }, + { + "epoch": 1.01, + "learning_rate": 4.836537900879411e-05, + "loss": 4.1421, + "step": 99840 + }, + { + "epoch": 1.01, + "learning_rate": 4.835699306128359e-05, + "loss": 4.1426, + "step": 100352 + }, + { + "epoch": 1.01, + "learning_rate": 4.83486234925768e-05, + "loss": 4.1252, + "step": 100864 + }, + { + "epoch": 1.01, + "learning_rate": 4.834023754506628e-05, + "loss": 4.1329, + "step": 101376 + }, + { + "epoch": 1.01, + "learning_rate": 4.833185159755576e-05, + "loss": 4.1394, + "step": 101888 + }, + { + "epoch": 1.01, + "learning_rate": 4.832346565004524e-05, + "loss": 4.1323, + "step": 102400 + }, + { + "epoch": 1.01, + "learning_rate": 4.831509608133845e-05, + "loss": 4.1257, + "step": 102912 + }, + { + "epoch": 1.01, + "learning_rate": 4.830671013382793e-05, + "loss": 4.1142, + "step": 103424 + }, + { + "epoch": 1.01, + "learning_rate": 4.829832418631741e-05, + "loss": 4.1276, + "step": 103936 + }, + { + "epoch": 1.01, + "learning_rate": 4.828993823880689e-05, + "loss": 4.1141, + "step": 104448 + }, + { + "epoch": 1.01, + "learning_rate": 4.8281568670100105e-05, + "loss": 4.1299, + "step": 104960 + }, + { + "epoch": 1.01, + "learning_rate": 4.8273182722589585e-05, + "loss": 4.1168, + "step": 105472 + }, + { + "epoch": 1.01, + "learning_rate": 4.8264796775079065e-05, + "loss": 4.1247, + "step": 105984 + }, + { + "epoch": 1.01, + "learning_rate": 4.8256410827568545e-05, + "loss": 4.1261, + "step": 106496 + }, + { + "epoch": 1.01, + "learning_rate": 4.8248024880058025e-05, + "loss": 4.1024, + "step": 107008 + }, + { + "epoch": 1.01, + "learning_rate": 4.8239655311351234e-05, + "loss": 4.1144, + "step": 107520 + }, + { + "epoch": 1.01, + "learning_rate": 4.8231269363840714e-05, + "loss": 4.1134, + "step": 108032 + }, + { + "epoch": 1.01, + "learning_rate": 4.8222883416330194e-05, + "loss": 4.1049, + "step": 108544 + }, + { + "epoch": 1.01, + "learning_rate": 4.8214497468819674e-05, + "loss": 4.105, + "step": 109056 + }, + { + "epoch": 1.01, + "learning_rate": 4.820612790011288e-05, + "loss": 4.1212, + "step": 109568 + }, + { + "epoch": 1.01, + "learning_rate": 4.819774195260236e-05, + "loss": 4.1081, + "step": 110080 + }, + { + "epoch": 1.01, + "learning_rate": 4.818935600509184e-05, + "loss": 4.0982, + "step": 110592 + }, + { + "epoch": 1.01, + "learning_rate": 4.818097005758132e-05, + "loss": 4.0898, + "step": 111104 + }, + { + "epoch": 1.01, + "learning_rate": 4.817260048887454e-05, + "loss": 4.0973, + "step": 111616 + }, + { + "epoch": 1.01, + "learning_rate": 4.816421454136402e-05, + "loss": 4.1121, + "step": 112128 + }, + { + "epoch": 1.01, + "learning_rate": 4.81558285938535e-05, + "loss": 4.1155, + "step": 112640 + }, + { + "epoch": 1.01, + "learning_rate": 4.814744264634298e-05, + "loss": 4.0991, + "step": 113152 + }, + { + "epoch": 1.01, + "learning_rate": 4.813907307763619e-05, + "loss": 4.1138, + "step": 113664 + }, + { + "epoch": 1.01, + "learning_rate": 4.813068713012567e-05, + "loss": 4.1089, + "step": 114176 + }, + { + "epoch": 1.01, + "learning_rate": 4.812230118261515e-05, + "loss": 4.1027, + "step": 114688 + }, + { + "epoch": 1.01, + "learning_rate": 4.811391523510463e-05, + "loss": 4.0885, + "step": 115200 + }, + { + "epoch": 1.01, + "learning_rate": 4.810554566639784e-05, + "loss": 4.1034, + "step": 115712 + }, + { + "epoch": 1.01, + "learning_rate": 4.809715971888732e-05, + "loss": 4.0917, + "step": 116224 + }, + { + "epoch": 1.01, + "learning_rate": 4.80887737713768e-05, + "loss": 4.0896, + "step": 116736 + }, + { + "epoch": 1.01, + "learning_rate": 4.808038782386628e-05, + "loss": 4.0942, + "step": 117248 + }, + { + "epoch": 1.01, + "learning_rate": 4.807201825515949e-05, + "loss": 4.0887, + "step": 117760 + }, + { + "epoch": 1.01, + "learning_rate": 4.806363230764897e-05, + "loss": 4.1018, + "step": 118272 + }, + { + "epoch": 1.01, + "learning_rate": 4.805524636013845e-05, + "loss": 4.0919, + "step": 118784 + }, + { + "epoch": 1.01, + "learning_rate": 4.804686041262793e-05, + "loss": 4.0834, + "step": 119296 + }, + { + "epoch": 1.01, + "learning_rate": 4.803849084392114e-05, + "loss": 4.0878, + "step": 119808 + }, + { + "epoch": 1.01, + "learning_rate": 4.803010489641062e-05, + "loss": 4.09, + "step": 120320 + }, + { + "epoch": 1.01, + "learning_rate": 4.80217189489001e-05, + "loss": 4.0854, + "step": 120832 + }, + { + "epoch": 1.01, + "learning_rate": 4.801333300138958e-05, + "loss": 4.0848, + "step": 121344 + }, + { + "epoch": 1.01, + "learning_rate": 4.800496343268279e-05, + "loss": 4.0746, + "step": 121856 + }, + { + "epoch": 1.02, + "learning_rate": 4.799657748517227e-05, + "loss": 4.0909, + "step": 122368 + }, + { + "epoch": 1.02, + "learning_rate": 4.798819153766175e-05, + "loss": 4.0738, + "step": 122880 + }, + { + "epoch": 1.02, + "learning_rate": 4.797980559015123e-05, + "loss": 4.0786, + "step": 123392 + }, + { + "epoch": 1.02, + "learning_rate": 4.7971436021444446e-05, + "loss": 4.0713, + "step": 123904 + }, + { + "epoch": 1.02, + "learning_rate": 4.7963050073933926e-05, + "loss": 4.0855, + "step": 124416 + }, + { + "epoch": 1.02, + "learning_rate": 4.7954664126423406e-05, + "loss": 4.0821, + "step": 124928 + }, + { + "epoch": 1.02, + "learning_rate": 4.7946278178912886e-05, + "loss": 4.0757, + "step": 125440 + }, + { + "epoch": 1.02, + "learning_rate": 4.7937908610206095e-05, + "loss": 4.0631, + "step": 125952 + }, + { + "epoch": 1.02, + "learning_rate": 4.7929522662695575e-05, + "loss": 4.071, + "step": 126464 + }, + { + "epoch": 1.02, + "learning_rate": 4.7921136715185055e-05, + "loss": 4.073, + "step": 126976 + }, + { + "epoch": 1.02, + "learning_rate": 4.7912750767674535e-05, + "loss": 4.0808, + "step": 127488 + }, + { + "epoch": 1.02, + "learning_rate": 4.7904381198967744e-05, + "loss": 4.0726, + "step": 128000 + }, + { + "epoch": 1.02, + "learning_rate": 4.7895995251457224e-05, + "loss": 4.0636, + "step": 128512 + }, + { + "epoch": 1.02, + "learning_rate": 4.7887609303946704e-05, + "loss": 4.0581, + "step": 129024 + }, + { + "epoch": 1.02, + "learning_rate": 4.787923973523992e-05, + "loss": 4.0709, + "step": 129536 + }, + { + "epoch": 1.02, + "learning_rate": 4.78708537877294e-05, + "loss": 4.0419, + "step": 130048 + }, + { + "epoch": 1.02, + "learning_rate": 4.786248421902261e-05, + "loss": 4.0572, + "step": 130560 + }, + { + "epoch": 1.02, + "learning_rate": 4.785409827151209e-05, + "loss": 4.0599, + "step": 131072 + }, + { + "epoch": 1.02, + "learning_rate": 4.784571232400157e-05, + "loss": 4.0589, + "step": 131584 + }, + { + "epoch": 1.02, + "learning_rate": 4.783732637649105e-05, + "loss": 4.0488, + "step": 132096 + }, + { + "epoch": 1.02, + "learning_rate": 4.782894042898053e-05, + "loss": 4.0587, + "step": 132608 + }, + { + "epoch": 1.02, + "learning_rate": 4.782055448147001e-05, + "loss": 4.0508, + "step": 133120 + }, + { + "epoch": 1.02, + "learning_rate": 4.781216853395948e-05, + "loss": 4.0702, + "step": 133632 + }, + { + "epoch": 1.02, + "learning_rate": 4.780378258644896e-05, + "loss": 4.0558, + "step": 134144 + }, + { + "epoch": 1.02, + "learning_rate": 4.779541301774218e-05, + "loss": 4.0523, + "step": 134656 + }, + { + "epoch": 1.02, + "learning_rate": 4.778702707023166e-05, + "loss": 4.0688, + "step": 135168 + }, + { + "epoch": 1.02, + "learning_rate": 4.777864112272114e-05, + "loss": 4.0718, + "step": 135680 + }, + { + "epoch": 1.02, + "learning_rate": 4.7770271554014354e-05, + "loss": 4.0525, + "step": 136192 + }, + { + "epoch": 1.02, + "learning_rate": 4.7761885606503834e-05, + "loss": 4.0477, + "step": 136704 + }, + { + "epoch": 1.02, + "learning_rate": 4.775349965899331e-05, + "loss": 4.0572, + "step": 137216 + }, + { + "epoch": 1.02, + "learning_rate": 4.774511371148279e-05, + "loss": 4.0463, + "step": 137728 + }, + { + "epoch": 1.02, + "learning_rate": 4.773672776397227e-05, + "loss": 4.0485, + "step": 138240 + }, + { + "epoch": 1.02, + "learning_rate": 4.7728341816461747e-05, + "loss": 4.0545, + "step": 138752 + }, + { + "epoch": 1.02, + "learning_rate": 4.7719955868951227e-05, + "loss": 4.0415, + "step": 139264 + }, + { + "epoch": 1.02, + "learning_rate": 4.7711586300244436e-05, + "loss": 4.0611, + "step": 139776 + }, + { + "epoch": 1.02, + "learning_rate": 4.7703200352733916e-05, + "loss": 4.0431, + "step": 140288 + }, + { + "epoch": 1.02, + "learning_rate": 4.7694814405223396e-05, + "loss": 4.0438, + "step": 140800 + }, + { + "epoch": 1.02, + "learning_rate": 4.7686428457712876e-05, + "loss": 4.0374, + "step": 141312 + }, + { + "epoch": 1.02, + "learning_rate": 4.767805888900609e-05, + "loss": 4.0455, + "step": 141824 + }, + { + "epoch": 1.02, + "learning_rate": 4.766967294149557e-05, + "loss": 4.0374, + "step": 142336 + }, + { + "epoch": 1.02, + "learning_rate": 4.766128699398505e-05, + "loss": 4.052, + "step": 142848 + }, + { + "epoch": 1.02, + "learning_rate": 4.765290104647453e-05, + "loss": 4.0492, + "step": 143360 + }, + { + "epoch": 1.02, + "learning_rate": 4.764453147776774e-05, + "loss": 4.0394, + "step": 143872 + }, + { + "epoch": 1.02, + "learning_rate": 4.763614553025722e-05, + "loss": 4.0246, + "step": 144384 + }, + { + "epoch": 1.02, + "learning_rate": 4.76277595827467e-05, + "loss": 4.0464, + "step": 144896 + }, + { + "epoch": 1.02, + "learning_rate": 4.761937363523618e-05, + "loss": 4.0367, + "step": 145408 + }, + { + "epoch": 1.02, + "learning_rate": 4.761100406652939e-05, + "loss": 4.0448, + "step": 145920 + }, + { + "epoch": 1.02, + "learning_rate": 4.760261811901887e-05, + "loss": 4.0398, + "step": 146432 + }, + { + "epoch": 1.02, + "learning_rate": 4.759423217150835e-05, + "loss": 4.0421, + "step": 146944 + }, + { + "epoch": 1.02, + "learning_rate": 4.758584622399783e-05, + "loss": 4.0397, + "step": 147456 + }, + { + "epoch": 1.02, + "learning_rate": 4.7577476655291045e-05, + "loss": 4.0424, + "step": 147968 + }, + { + "epoch": 1.02, + "learning_rate": 4.7569090707780525e-05, + "loss": 4.0271, + "step": 148480 + }, + { + "epoch": 1.02, + "learning_rate": 4.7560704760270005e-05, + "loss": 4.0254, + "step": 148992 + }, + { + "epoch": 1.02, + "learning_rate": 4.7552318812759485e-05, + "loss": 4.038, + "step": 149504 + }, + { + "epoch": 1.02, + "learning_rate": 4.7543949244052694e-05, + "loss": 4.0205, + "step": 150016 + }, + { + "epoch": 1.02, + "learning_rate": 4.75355796753459e-05, + "loss": 4.0363, + "step": 150528 + }, + { + "epoch": 1.02, + "learning_rate": 4.752719372783538e-05, + "loss": 4.0414, + "step": 151040 + }, + { + "epoch": 1.02, + "learning_rate": 4.751880778032486e-05, + "loss": 4.0256, + "step": 151552 + }, + { + "epoch": 1.02, + "learning_rate": 4.751042183281434e-05, + "loss": 4.025, + "step": 152064 + }, + { + "epoch": 1.02, + "learning_rate": 4.750203588530382e-05, + "loss": 4.0282, + "step": 152576 + }, + { + "epoch": 1.03, + "eval_loss": 4.028327941894531, + "eval_runtime": 305.0036, + "eval_samples_per_second": 1251.103, + "eval_steps_per_second": 39.098, + "step": 152640 + }, + { + "epoch": 0.0, + "learning_rate": 4.74936499377933e-05, + "loss": 4.0102, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.748526399028278e-05, + "loss": 4.019, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.747687804277226e-05, + "loss": 4.0284, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.746849209526175e-05, + "loss": 4.0216, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.746010614775123e-05, + "loss": 4.0264, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.745172020024071e-05, + "loss": 4.0081, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.744333425273019e-05, + "loss": 4.0217, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.743494830521967e-05, + "loss": 4.0055, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.742656235770914e-05, + "loss": 4.0191, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.741817641019862e-05, + "loss": 4.0134, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.740980684149184e-05, + "loss": 4.0227, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.740142089398132e-05, + "loss": 4.0237, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.739303494647079e-05, + "loss": 4.0051, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.738464899896027e-05, + "loss": 4.0063, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.737626305144975e-05, + "loss": 4.0067, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.736787710393923e-05, + "loss": 4.0025, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.735949115642871e-05, + "loss": 3.9991, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.73511052089182e-05, + "loss": 4.0029, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.734273564021141e-05, + "loss": 3.9979, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.733434969270089e-05, + "loss": 4.0207, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.732596374519037e-05, + "loss": 4.0019, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.731757779767985e-05, + "loss": 4.0144, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.7309208228973056e-05, + "loss": 4.0086, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.7300838660266265e-05, + "loss": 4.015, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.7292452712755745e-05, + "loss": 3.9878, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.7284066765245225e-05, + "loss": 3.999, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.7275680817734705e-05, + "loss": 3.9896, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.7267294870224185e-05, + "loss": 3.9986, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.7258908922713665e-05, + "loss": 3.9903, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.725052297520315e-05, + "loss": 3.992, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.724215340649636e-05, + "loss": 4.0023, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.723376745898584e-05, + "loss": 3.999, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.722538151147532e-05, + "loss": 3.9854, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.72169955639648e-05, + "loss": 3.9989, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.720860961645428e-05, + "loss": 3.996, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.720022366894376e-05, + "loss": 3.993, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.719183772143324e-05, + "loss": 3.9803, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.718345177392272e-05, + "loss": 3.9898, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.717508220521593e-05, + "loss": 3.9716, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.716669625770541e-05, + "loss": 3.9871, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.715831031019489e-05, + "loss": 3.9811, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.714992436268437e-05, + "loss": 3.9908, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.7141554793977585e-05, + "loss": 3.9843, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.7133168846467065e-05, + "loss": 3.9859, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.7124782898956545e-05, + "loss": 3.9899, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.7116396951446025e-05, + "loss": 3.9867, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.7108027382739234e-05, + "loss": 3.985, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.7099641435228714e-05, + "loss": 3.9679, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.7091255487718194e-05, + "loss": 3.9743, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.7082869540207674e-05, + "loss": 3.985, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.707449997150088e-05, + "loss": 3.9777, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.706611402399036e-05, + "loss": 3.9702, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.705772807647984e-05, + "loss": 3.9651, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.704934212896932e-05, + "loss": 3.9753, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.704097256026254e-05, + "loss": 3.9587, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.703260299155575e-05, + "loss": 3.9781, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.702421704404523e-05, + "loss": 3.9658, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.701583109653471e-05, + "loss": 3.9777, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.700744514902419e-05, + "loss": 3.9745, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.699905920151367e-05, + "loss": 3.9582, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.699067325400315e-05, + "loss": 3.964, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.698228730649263e-05, + "loss": 3.9668, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.69739013589821e-05, + "loss": 3.9572, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.696553179027532e-05, + "loss": 3.9647, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.69571458427648e-05, + "loss": 3.9712, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694877627405801e-05, + "loss": 3.9668, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.694039032654749e-05, + "loss": 3.9552, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.693200437903697e-05, + "loss": 3.946, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.692361843152645e-05, + "loss": 3.9527, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.6915232484015926e-05, + "loss": 3.9677, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.6906846536505406e-05, + "loss": 3.9744, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.6898460588994886e-05, + "loss": 3.9579, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.6890091020288095e-05, + "loss": 3.9718, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.6881705072777575e-05, + "loss": 3.9693, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.6873319125267055e-05, + "loss": 3.9678, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.6864933177756535e-05, + "loss": 3.9445, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.6856547230246015e-05, + "loss": 3.9684, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.684817766153923e-05, + "loss": 3.958, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.683979171402871e-05, + "loss": 3.9518, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.683140576651819e-05, + "loss": 3.9595, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.682301981900767e-05, + "loss": 3.9542, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.681463387149715e-05, + "loss": 3.9664, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.680624792398663e-05, + "loss": 3.9585, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.679786197647611e-05, + "loss": 3.947, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.678949240776932e-05, + "loss": 3.954, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.67811064602588e-05, + "loss": 3.9552, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.677272051274828e-05, + "loss": 3.9531, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.676433456523776e-05, + "loss": 3.9509, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.675594861772724e-05, + "loss": 3.9442, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.674756267021672e-05, + "loss": 3.9564, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.6739193101509935e-05, + "loss": 3.9446, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.6730807153999415e-05, + "loss": 3.9481, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.6722421206488895e-05, + "loss": 3.9417, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.6714035258978375e-05, + "loss": 3.9578, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.6705649311467855e-05, + "loss": 3.9523, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.6697263363957335e-05, + "loss": 3.9464, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.6688877416446815e-05, + "loss": 3.9388, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.6680507847740024e-05, + "loss": 3.9469, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.667213827903323e-05, + "loss": 3.9382, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.666375233152271e-05, + "loss": 3.9592, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.665536638401219e-05, + "loss": 3.9433, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.664698043650167e-05, + "loss": 3.9398, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.663859448899115e-05, + "loss": 3.934, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.663020854148063e-05, + "loss": 3.9448, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.662182259397011e-05, + "loss": 3.9211, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.661345302526333e-05, + "loss": 3.9361, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.660506707775281e-05, + "loss": 3.9378, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.659668113024229e-05, + "loss": 3.9368, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.658829518273176e-05, + "loss": 3.9243, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.657992561402498e-05, + "loss": 3.9412, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.657153966651446e-05, + "loss": 3.9262, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.656315371900393e-05, + "loss": 3.9509, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.655476777149341e-05, + "loss": 3.9355, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.654638182398289e-05, + "loss": 3.9303, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.653799587647237e-05, + "loss": 3.9481, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.652960992896185e-05, + "loss": 3.9551, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.6521240360255066e-05, + "loss": 3.9344, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.6512854412744546e-05, + "loss": 3.9279, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.6504468465234026e-05, + "loss": 3.9368, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.6496082517723506e-05, + "loss": 3.93, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.6487696570212986e-05, + "loss": 3.9291, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.6479327001506195e-05, + "loss": 3.9421, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.6470941053995675e-05, + "loss": 3.9212, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.6462555106485155e-05, + "loss": 3.944, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.6454169158974635e-05, + "loss": 3.9288, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.6445783211464115e-05, + "loss": 3.9278, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.6437413642757324e-05, + "loss": 3.9212, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.6429027695246804e-05, + "loss": 3.9326, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.642064174773629e-05, + "loss": 3.9196, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.641225580022577e-05, + "loss": 3.9409, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.640386985271525e-05, + "loss": 3.9312, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.639548390520473e-05, + "loss": 3.9284, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.638709795769421e-05, + "loss": 3.9111, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.637871201018369e-05, + "loss": 3.9347, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.63703424414769e-05, + "loss": 3.928, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.636195649396638e-05, + "loss": 3.9274, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.635357054645586e-05, + "loss": 3.924, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.634520097774907e-05, + "loss": 3.9333, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.633681503023855e-05, + "loss": 3.9289, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.632842908272803e-05, + "loss": 3.9343, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.632004313521751e-05, + "loss": 3.9163, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.6311673566510724e-05, + "loss": 3.9168, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.6303287619000204e-05, + "loss": 3.9261, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.6294901671489684e-05, + "loss": 3.9099, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.6286515723979164e-05, + "loss": 3.9263, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.6278129776468644e-05, + "loss": 3.9329, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.626976020776185e-05, + "loss": 3.9182, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.626137426025133e-05, + "loss": 3.915, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.625298831274081e-05, + "loss": 3.9236, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 3.952652931213379, + "eval_runtime": 308.9364, + "eval_samples_per_second": 1235.177, + "eval_steps_per_second": 38.6, + "step": 228960 + }, + { + "epoch": 1.0, + "learning_rate": 4.624460236523029e-05, + "loss": 3.9113, + "step": 229376 + }, + { + "epoch": 1.0, + "learning_rate": 4.62362327965235e-05, + "loss": 3.9117, + "step": 229888 + }, + { + "epoch": 1.0, + "learning_rate": 4.622784684901298e-05, + "loss": 3.9211, + "step": 230400 + }, + { + "epoch": 1.0, + "learning_rate": 4.621946090150246e-05, + "loss": 3.9106, + "step": 230912 + }, + { + "epoch": 1.0, + "learning_rate": 4.621107495399194e-05, + "loss": 3.925, + "step": 231424 + }, + { + "epoch": 1.0, + "learning_rate": 4.620268900648142e-05, + "loss": 3.9044, + "step": 231936 + }, + { + "epoch": 1.0, + "learning_rate": 4.619431943777464e-05, + "loss": 3.9183, + "step": 232448 + }, + { + "epoch": 1.0, + "learning_rate": 4.618593349026412e-05, + "loss": 3.9022, + "step": 232960 + }, + { + "epoch": 1.0, + "learning_rate": 4.617754754275359e-05, + "loss": 3.9146, + "step": 233472 + }, + { + "epoch": 1.0, + "learning_rate": 4.616916159524307e-05, + "loss": 3.9073, + "step": 233984 + }, + { + "epoch": 1.0, + "learning_rate": 4.616079202653629e-05, + "loss": 3.919, + "step": 234496 + }, + { + "epoch": 1.0, + "learning_rate": 4.615240607902577e-05, + "loss": 3.9187, + "step": 235008 + }, + { + "epoch": 1.0, + "learning_rate": 4.614402013151524e-05, + "loss": 3.9016, + "step": 235520 + }, + { + "epoch": 1.0, + "learning_rate": 4.613563418400472e-05, + "loss": 3.906, + "step": 236032 + }, + { + "epoch": 1.0, + "learning_rate": 4.61272482364942e-05, + "loss": 3.9028, + "step": 236544 + }, + { + "epoch": 1.0, + "learning_rate": 4.6118878667787416e-05, + "loss": 3.9031, + "step": 237056 + }, + { + "epoch": 1.0, + "learning_rate": 4.6110492720276896e-05, + "loss": 3.8973, + "step": 237568 + }, + { + "epoch": 1.0, + "learning_rate": 4.6102106772766376e-05, + "loss": 3.9023, + "step": 238080 + }, + { + "epoch": 1.0, + "learning_rate": 4.6093720825255856e-05, + "loss": 3.8976, + "step": 238592 + }, + { + "epoch": 1.0, + "learning_rate": 4.6085334877745336e-05, + "loss": 3.9238, + "step": 239104 + }, + { + "epoch": 1.0, + "learning_rate": 4.6076965309038545e-05, + "loss": 3.902, + "step": 239616 + }, + { + "epoch": 1.0, + "learning_rate": 4.6068579361528025e-05, + "loss": 3.9091, + "step": 240128 + }, + { + "epoch": 1.0, + "learning_rate": 4.6060193414017505e-05, + "loss": 3.9123, + "step": 240640 + }, + { + "epoch": 1.0, + "learning_rate": 4.6051807466506985e-05, + "loss": 3.9123, + "step": 241152 + }, + { + "epoch": 1.0, + "learning_rate": 4.6043437897800194e-05, + "loss": 3.8905, + "step": 241664 + }, + { + "epoch": 1.0, + "learning_rate": 4.6035051950289674e-05, + "loss": 3.9011, + "step": 242176 + }, + { + "epoch": 1.0, + "learning_rate": 4.6026666002779154e-05, + "loss": 3.8935, + "step": 242688 + }, + { + "epoch": 1.0, + "learning_rate": 4.6018280055268634e-05, + "loss": 3.8994, + "step": 243200 + }, + { + "epoch": 1.0, + "learning_rate": 4.6009894107758114e-05, + "loss": 3.8909, + "step": 243712 + }, + { + "epoch": 1.01, + "learning_rate": 4.600152453905133e-05, + "loss": 3.8934, + "step": 244224 + }, + { + "epoch": 1.01, + "learning_rate": 4.599313859154081e-05, + "loss": 3.9036, + "step": 244736 + }, + { + "epoch": 1.01, + "learning_rate": 4.598476902283402e-05, + "loss": 3.9022, + "step": 245248 + }, + { + "epoch": 1.01, + "learning_rate": 4.59763830753235e-05, + "loss": 3.8954, + "step": 245760 + }, + { + "epoch": 1.01, + "learning_rate": 4.596799712781298e-05, + "loss": 3.9009, + "step": 246272 + }, + { + "epoch": 1.01, + "learning_rate": 4.595961118030246e-05, + "loss": 3.9015, + "step": 246784 + }, + { + "epoch": 1.01, + "learning_rate": 4.595122523279194e-05, + "loss": 3.8971, + "step": 247296 + }, + { + "epoch": 1.01, + "learning_rate": 4.594283928528142e-05, + "loss": 3.8842, + "step": 247808 + }, + { + "epoch": 1.01, + "learning_rate": 4.59344533377709e-05, + "loss": 3.8968, + "step": 248320 + }, + { + "epoch": 1.01, + "learning_rate": 4.592606739026038e-05, + "loss": 3.8743, + "step": 248832 + }, + { + "epoch": 1.01, + "learning_rate": 4.591769782155359e-05, + "loss": 3.8926, + "step": 249344 + }, + { + "epoch": 1.01, + "learning_rate": 4.590931187404307e-05, + "loss": 3.8869, + "step": 249856 + }, + { + "epoch": 1.01, + "learning_rate": 4.5900925926532554e-05, + "loss": 3.8998, + "step": 250368 + }, + { + "epoch": 1.01, + "learning_rate": 4.5892539979022034e-05, + "loss": 3.8959, + "step": 250880 + }, + { + "epoch": 1.01, + "learning_rate": 4.5884154031511514e-05, + "loss": 3.8889, + "step": 251392 + }, + { + "epoch": 1.01, + "learning_rate": 4.587578446280472e-05, + "loss": 3.8975, + "step": 251904 + }, + { + "epoch": 1.01, + "learning_rate": 4.58673985152942e-05, + "loss": 3.8967, + "step": 252416 + }, + { + "epoch": 1.01, + "learning_rate": 4.585901256778368e-05, + "loss": 3.8926, + "step": 252928 + }, + { + "epoch": 1.01, + "learning_rate": 4.585062662027316e-05, + "loss": 3.878, + "step": 253440 + }, + { + "epoch": 1.01, + "learning_rate": 4.584224067276264e-05, + "loss": 3.8812, + "step": 253952 + }, + { + "epoch": 1.01, + "learning_rate": 4.583387110405585e-05, + "loss": 3.8961, + "step": 254464 + }, + { + "epoch": 1.01, + "learning_rate": 4.582548515654533e-05, + "loss": 3.8818, + "step": 254976 + }, + { + "epoch": 1.01, + "learning_rate": 4.581709920903481e-05, + "loss": 3.8781, + "step": 255488 + }, + { + "epoch": 1.01, + "learning_rate": 4.580871326152429e-05, + "loss": 3.8758, + "step": 256000 + }, + { + "epoch": 1.01, + "learning_rate": 4.580034369281751e-05, + "loss": 3.888, + "step": 256512 + }, + { + "epoch": 1.01, + "learning_rate": 4.579195774530699e-05, + "loss": 3.8707, + "step": 257024 + }, + { + "epoch": 1.01, + "learning_rate": 4.578357179779647e-05, + "loss": 3.8856, + "step": 257536 + }, + { + "epoch": 1.01, + "learning_rate": 4.577518585028595e-05, + "loss": 3.8792, + "step": 258048 + }, + { + "epoch": 1.01, + "learning_rate": 4.576679990277543e-05, + "loss": 3.8846, + "step": 258560 + }, + { + "epoch": 1.01, + "learning_rate": 4.5758430334068637e-05, + "loss": 3.8858, + "step": 259072 + }, + { + "epoch": 1.01, + "learning_rate": 4.5750044386558117e-05, + "loss": 3.8727, + "step": 259584 + }, + { + "epoch": 1.01, + "learning_rate": 4.5741658439047596e-05, + "loss": 3.8717, + "step": 260096 + }, + { + "epoch": 1.01, + "learning_rate": 4.5733272491537076e-05, + "loss": 3.884, + "step": 260608 + }, + { + "epoch": 1.01, + "learning_rate": 4.572488654402655e-05, + "loss": 3.8676, + "step": 261120 + }, + { + "epoch": 1.01, + "learning_rate": 4.5716516975319765e-05, + "loss": 3.8761, + "step": 261632 + }, + { + "epoch": 1.01, + "learning_rate": 4.5708131027809245e-05, + "loss": 3.8834, + "step": 262144 + }, + { + "epoch": 1.01, + "learning_rate": 4.5699745080298725e-05, + "loss": 3.8828, + "step": 262656 + }, + { + "epoch": 1.01, + "learning_rate": 4.5691359132788205e-05, + "loss": 3.8656, + "step": 263168 + }, + { + "epoch": 1.01, + "learning_rate": 4.5682973185277685e-05, + "loss": 3.8616, + "step": 263680 + }, + { + "epoch": 1.01, + "learning_rate": 4.5674587237767165e-05, + "loss": 3.8638, + "step": 264192 + }, + { + "epoch": 1.01, + "learning_rate": 4.5666201290256645e-05, + "loss": 3.8774, + "step": 264704 + }, + { + "epoch": 1.01, + "learning_rate": 4.5657815342746125e-05, + "loss": 3.8872, + "step": 265216 + }, + { + "epoch": 1.01, + "learning_rate": 4.5649445774039334e-05, + "loss": 3.8725, + "step": 265728 + }, + { + "epoch": 1.01, + "learning_rate": 4.5641059826528814e-05, + "loss": 3.8856, + "step": 266240 + }, + { + "epoch": 1.01, + "learning_rate": 4.5632673879018294e-05, + "loss": 3.8862, + "step": 266752 + }, + { + "epoch": 1.01, + "learning_rate": 4.5624287931507774e-05, + "loss": 3.8812, + "step": 267264 + }, + { + "epoch": 1.01, + "learning_rate": 4.5615901983997254e-05, + "loss": 3.8628, + "step": 267776 + }, + { + "epoch": 1.01, + "learning_rate": 4.560753241529046e-05, + "loss": 3.8807, + "step": 268288 + }, + { + "epoch": 1.01, + "learning_rate": 4.559914646777994e-05, + "loss": 3.8747, + "step": 268800 + }, + { + "epoch": 1.01, + "learning_rate": 4.559076052026943e-05, + "loss": 3.8673, + "step": 269312 + }, + { + "epoch": 1.01, + "learning_rate": 4.558237457275891e-05, + "loss": 3.8735, + "step": 269824 + }, + { + "epoch": 1.01, + "learning_rate": 4.557398862524839e-05, + "loss": 3.8745, + "step": 270336 + }, + { + "epoch": 1.01, + "learning_rate": 4.556560267773787e-05, + "loss": 3.8784, + "step": 270848 + }, + { + "epoch": 1.01, + "learning_rate": 4.555723310903108e-05, + "loss": 3.8748, + "step": 271360 + }, + { + "epoch": 1.01, + "learning_rate": 4.554884716152056e-05, + "loss": 3.8664, + "step": 271872 + }, + { + "epoch": 1.01, + "learning_rate": 4.554046121401004e-05, + "loss": 3.872, + "step": 272384 + }, + { + "epoch": 1.01, + "learning_rate": 4.553207526649952e-05, + "loss": 3.8691, + "step": 272896 + }, + { + "epoch": 1.01, + "learning_rate": 4.5523689318989e-05, + "loss": 3.8706, + "step": 273408 + }, + { + "epoch": 1.01, + "learning_rate": 4.551531975028221e-05, + "loss": 3.8685, + "step": 273920 + }, + { + "epoch": 1.01, + "learning_rate": 4.550693380277169e-05, + "loss": 3.8609, + "step": 274432 + }, + { + "epoch": 1.02, + "learning_rate": 4.549854785526117e-05, + "loss": 3.8737, + "step": 274944 + }, + { + "epoch": 1.02, + "learning_rate": 4.549016190775065e-05, + "loss": 3.868, + "step": 275456 + }, + { + "epoch": 1.02, + "learning_rate": 4.548177596024013e-05, + "loss": 3.8622, + "step": 275968 + }, + { + "epoch": 1.02, + "learning_rate": 4.5473406391533343e-05, + "loss": 3.8609, + "step": 276480 + }, + { + "epoch": 1.02, + "learning_rate": 4.5465020444022823e-05, + "loss": 3.8783, + "step": 276992 + }, + { + "epoch": 1.02, + "learning_rate": 4.54566344965123e-05, + "loss": 3.8709, + "step": 277504 + }, + { + "epoch": 1.02, + "learning_rate": 4.544824854900178e-05, + "loss": 3.8645, + "step": 278016 + }, + { + "epoch": 1.02, + "learning_rate": 4.543987898029499e-05, + "loss": 3.8555, + "step": 278528 + }, + { + "epoch": 1.02, + "learning_rate": 4.543149303278447e-05, + "loss": 3.8657, + "step": 279040 + }, + { + "epoch": 1.02, + "learning_rate": 4.542310708527395e-05, + "loss": 3.857, + "step": 279552 + }, + { + "epoch": 1.02, + "learning_rate": 4.541472113776343e-05, + "loss": 3.8788, + "step": 280064 + }, + { + "epoch": 1.02, + "learning_rate": 4.540635156905664e-05, + "loss": 3.8641, + "step": 280576 + }, + { + "epoch": 1.02, + "learning_rate": 4.539796562154612e-05, + "loss": 3.8605, + "step": 281088 + }, + { + "epoch": 1.02, + "learning_rate": 4.53895796740356e-05, + "loss": 3.8565, + "step": 281600 + }, + { + "epoch": 1.02, + "learning_rate": 4.538119372652508e-05, + "loss": 3.8658, + "step": 282112 + }, + { + "epoch": 1.02, + "learning_rate": 4.53728241578183e-05, + "loss": 3.8386, + "step": 282624 + }, + { + "epoch": 1.02, + "learning_rate": 4.536443821030778e-05, + "loss": 3.8575, + "step": 283136 + }, + { + "epoch": 1.02, + "learning_rate": 4.535605226279726e-05, + "loss": 3.8575, + "step": 283648 + }, + { + "epoch": 1.02, + "learning_rate": 4.534766631528674e-05, + "loss": 3.859, + "step": 284160 + }, + { + "epoch": 1.02, + "learning_rate": 4.5339296746579946e-05, + "loss": 3.8455, + "step": 284672 + }, + { + "epoch": 1.02, + "learning_rate": 4.5330910799069426e-05, + "loss": 3.863, + "step": 285184 + }, + { + "epoch": 1.02, + "learning_rate": 4.5322524851558906e-05, + "loss": 3.8478, + "step": 285696 + }, + { + "epoch": 1.02, + "learning_rate": 4.5314138904048386e-05, + "loss": 3.8689, + "step": 286208 + }, + { + "epoch": 1.02, + "learning_rate": 4.5305769335341595e-05, + "loss": 3.8598, + "step": 286720 + }, + { + "epoch": 1.02, + "learning_rate": 4.5297383387831075e-05, + "loss": 3.8503, + "step": 287232 + }, + { + "epoch": 1.02, + "learning_rate": 4.5288997440320555e-05, + "loss": 3.8697, + "step": 287744 + }, + { + "epoch": 1.02, + "learning_rate": 4.5280611492810035e-05, + "loss": 3.8767, + "step": 288256 + }, + { + "epoch": 1.02, + "learning_rate": 4.527224192410325e-05, + "loss": 3.8614, + "step": 288768 + }, + { + "epoch": 1.02, + "learning_rate": 4.526385597659273e-05, + "loss": 3.8505, + "step": 289280 + }, + { + "epoch": 1.02, + "learning_rate": 4.525547002908221e-05, + "loss": 3.8612, + "step": 289792 + }, + { + "epoch": 1.02, + "learning_rate": 4.5247084081571684e-05, + "loss": 3.8513, + "step": 290304 + }, + { + "epoch": 1.02, + "learning_rate": 4.52387145128649e-05, + "loss": 3.8516, + "step": 290816 + }, + { + "epoch": 1.02, + "learning_rate": 4.523032856535438e-05, + "loss": 3.8658, + "step": 291328 + }, + { + "epoch": 1.02, + "learning_rate": 4.522194261784386e-05, + "loss": 3.8473, + "step": 291840 + }, + { + "epoch": 1.02, + "learning_rate": 4.521355667033333e-05, + "loss": 3.8643, + "step": 292352 + }, + { + "epoch": 1.02, + "learning_rate": 4.520518710162655e-05, + "loss": 3.8539, + "step": 292864 + }, + { + "epoch": 1.02, + "learning_rate": 4.519680115411603e-05, + "loss": 3.8566, + "step": 293376 + }, + { + "epoch": 1.02, + "learning_rate": 4.518841520660551e-05, + "loss": 3.8407, + "step": 293888 + }, + { + "epoch": 1.02, + "learning_rate": 4.518002925909499e-05, + "loss": 3.8593, + "step": 294400 + }, + { + "epoch": 1.02, + "learning_rate": 4.517164331158447e-05, + "loss": 3.8458, + "step": 294912 + }, + { + "epoch": 1.02, + "learning_rate": 4.5163273742877684e-05, + "loss": 3.8625, + "step": 295424 + }, + { + "epoch": 1.02, + "learning_rate": 4.515488779536716e-05, + "loss": 3.8545, + "step": 295936 + }, + { + "epoch": 1.02, + "learning_rate": 4.514650184785664e-05, + "loss": 3.8579, + "step": 296448 + }, + { + "epoch": 1.02, + "learning_rate": 4.513811590034612e-05, + "loss": 3.8361, + "step": 296960 + }, + { + "epoch": 1.02, + "learning_rate": 4.5129746331639333e-05, + "loss": 3.8622, + "step": 297472 + }, + { + "epoch": 1.02, + "learning_rate": 4.5121360384128807e-05, + "loss": 3.8512, + "step": 297984 + }, + { + "epoch": 1.02, + "learning_rate": 4.5112974436618287e-05, + "loss": 3.855, + "step": 298496 + }, + { + "epoch": 1.02, + "learning_rate": 4.5104588489107766e-05, + "loss": 3.8504, + "step": 299008 + }, + { + "epoch": 1.02, + "learning_rate": 4.5096218920400976e-05, + "loss": 3.8599, + "step": 299520 + }, + { + "epoch": 1.02, + "learning_rate": 4.508783297289046e-05, + "loss": 3.8564, + "step": 300032 + }, + { + "epoch": 1.02, + "learning_rate": 4.507944702537994e-05, + "loss": 3.8583, + "step": 300544 + }, + { + "epoch": 1.02, + "learning_rate": 4.507106107786942e-05, + "loss": 3.844, + "step": 301056 + }, + { + "epoch": 1.02, + "learning_rate": 4.506269150916263e-05, + "loss": 3.8471, + "step": 301568 + }, + { + "epoch": 1.02, + "learning_rate": 4.505430556165211e-05, + "loss": 3.8493, + "step": 302080 + }, + { + "epoch": 1.02, + "learning_rate": 4.504591961414159e-05, + "loss": 3.8399, + "step": 302592 + }, + { + "epoch": 1.02, + "learning_rate": 4.503753366663107e-05, + "loss": 3.8533, + "step": 303104 + }, + { + "epoch": 1.02, + "learning_rate": 4.502916409792428e-05, + "loss": 3.8582, + "step": 303616 + }, + { + "epoch": 1.02, + "learning_rate": 4.502077815041376e-05, + "loss": 3.8475, + "step": 304128 + }, + { + "epoch": 1.02, + "learning_rate": 4.501239220290324e-05, + "loss": 3.8404, + "step": 304640 + }, + { + "epoch": 1.02, + "learning_rate": 4.500400625539272e-05, + "loss": 3.8528, + "step": 305152 + }, + { + "epoch": 1.03, + "eval_loss": 3.911623001098633, + "eval_runtime": 305.2751, + "eval_samples_per_second": 1249.991, + "eval_steps_per_second": 39.063, + "step": 305280 + }, + { + "epoch": 0.0, + "learning_rate": 4.49956203078822e-05, + "loss": 3.8317, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.498723436037168e-05, + "loss": 3.8407, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.497884841286116e-05, + "loss": 3.8462, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.497046246535065e-05, + "loss": 3.8452, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.496207651784013e-05, + "loss": 3.8541, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.495369057032961e-05, + "loss": 3.8328, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.4945304622819087e-05, + "loss": 3.8448, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.4936918675308567e-05, + "loss": 3.8298, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.4928549106601776e-05, + "loss": 3.8476, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.4920163159091256e-05, + "loss": 3.8387, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.4911777211580736e-05, + "loss": 3.844, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.4903391264070216e-05, + "loss": 3.8525, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.4895021695363425e-05, + "loss": 3.829, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.4886635747852905e-05, + "loss": 3.8415, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.4878249800342385e-05, + "loss": 3.8336, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.4869863852831864e-05, + "loss": 3.8351, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.486149428412508e-05, + "loss": 3.8267, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.485310833661456e-05, + "loss": 3.8344, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.484472238910404e-05, + "loss": 3.8307, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.483633644159352e-05, + "loss": 3.8524, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.482796687288673e-05, + "loss": 3.8319, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.481958092537621e-05, + "loss": 3.8412, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.481119497786569e-05, + "loss": 3.8439, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.480280903035516e-05, + "loss": 3.8448, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.479443946164838e-05, + "loss": 3.823, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.478605351413786e-05, + "loss": 3.8372, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.477766756662734e-05, + "loss": 3.8239, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.476928161911682e-05, + "loss": 3.8333, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.47608956716063e-05, + "loss": 3.8213, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.4752526102899514e-05, + "loss": 3.8268, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.4744140155388994e-05, + "loss": 3.8364, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.47357705866822e-05, + "loss": 3.8366, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.472738463917168e-05, + "loss": 3.8265, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.471899869166116e-05, + "loss": 3.8371, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.4710612744150636e-05, + "loss": 3.8287, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.4702226796640116e-05, + "loss": 3.8371, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.4693840849129596e-05, + "loss": 3.8176, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.4685454901619076e-05, + "loss": 3.8305, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.4677068954108556e-05, + "loss": 3.8132, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.466869938540177e-05, + "loss": 3.8239, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.466031343789125e-05, + "loss": 3.8203, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.465192749038073e-05, + "loss": 3.8348, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.464354154287021e-05, + "loss": 3.8302, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.463517197416342e-05, + "loss": 3.8277, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.46267860266529e-05, + "loss": 3.8316, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.461840007914238e-05, + "loss": 3.8309, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.461001413163186e-05, + "loss": 3.827, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.460164456292507e-05, + "loss": 3.8203, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.459325861541455e-05, + "loss": 3.81, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.458487266790403e-05, + "loss": 3.8315, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.457648672039351e-05, + "loss": 3.8207, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.4568117151686725e-05, + "loss": 3.8141, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.4559731204176205e-05, + "loss": 3.8162, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.4551345256665685e-05, + "loss": 3.8233, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.4542959309155165e-05, + "loss": 3.8078, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.4534589740448374e-05, + "loss": 3.8159, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.4526203792937854e-05, + "loss": 3.8163, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.4517817845427334e-05, + "loss": 3.8176, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.4509431897916814e-05, + "loss": 3.8277, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.4501062329210023e-05, + "loss": 3.8085, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.44926763816995e-05, + "loss": 3.8103, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.448429043418898e-05, + "loss": 3.822, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.447590448667846e-05, + "loss": 3.8081, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.446753491797168e-05, + "loss": 3.8126, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.445914897046116e-05, + "loss": 3.821, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.445076302295064e-05, + "loss": 3.8206, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.444237707544012e-05, + "loss": 3.8046, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.44339911279296e-05, + "loss": 3.7986, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.442562155922281e-05, + "loss": 3.7997, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.441723561171229e-05, + "loss": 3.8135, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.440884966420177e-05, + "loss": 3.8269, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.440046371669125e-05, + "loss": 3.8094, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.439209414798446e-05, + "loss": 3.8224, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.438370820047394e-05, + "loss": 3.8215, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.437532225296342e-05, + "loss": 3.8239, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.43669363054529e-05, + "loss": 3.8032, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.435856673674611e-05, + "loss": 3.8192, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.435018078923559e-05, + "loss": 3.8113, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.434179484172507e-05, + "loss": 3.8045, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.433340889421455e-05, + "loss": 3.8181, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.432503932550776e-05, + "loss": 3.8122, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.431665337799724e-05, + "loss": 3.8126, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.430826743048672e-05, + "loss": 3.8141, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.42998814829762e-05, + "loss": 3.8104, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.429151191426941e-05, + "loss": 3.8128, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.428312596675889e-05, + "loss": 3.8077, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.427474001924837e-05, + "loss": 3.8113, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.426635407173785e-05, + "loss": 3.8049, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.4257984503031066e-05, + "loss": 3.8049, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.4249598555520546e-05, + "loss": 3.8115, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.4241212608010026e-05, + "loss": 3.8113, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.4232826660499506e-05, + "loss": 3.8014, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.4224457091792715e-05, + "loss": 3.8011, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.4216071144282195e-05, + "loss": 3.8178, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.4207685196771675e-05, + "loss": 3.8123, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.4199299249261155e-05, + "loss": 3.8073, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.4190929680554364e-05, + "loss": 3.7966, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.4182543733043844e-05, + "loss": 3.8039, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.4174157785533324e-05, + "loss": 3.8003, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.4165771838022804e-05, + "loss": 3.8144, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.415740226931602e-05, + "loss": 3.8121, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.41490163218055e-05, + "loss": 3.802, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.414063037429498e-05, + "loss": 3.7956, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.413224442678446e-05, + "loss": 3.809, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.412387485807767e-05, + "loss": 3.7775, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.411548891056715e-05, + "loss": 3.8039, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.410710296305663e-05, + "loss": 3.7948, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.409871701554611e-05, + "loss": 3.8017, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.409034744683932e-05, + "loss": 3.7878, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.40819614993288e-05, + "loss": 3.805, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.407357555181828e-05, + "loss": 3.7971, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.406518960430776e-05, + "loss": 3.8031, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.4056820035600974e-05, + "loss": 3.8069, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.4048434088090454e-05, + "loss": 3.7923, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.4040048140579934e-05, + "loss": 3.8129, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.4031662193069414e-05, + "loss": 3.8202, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.402329262436262e-05, + "loss": 3.803, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.40149066768521e-05, + "loss": 3.7918, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.400652072934158e-05, + "loss": 3.8061, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.399813478183106e-05, + "loss": 3.7983, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.398976521312427e-05, + "loss": 3.7912, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.398137926561375e-05, + "loss": 3.8105, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.397299331810323e-05, + "loss": 3.7907, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.396460737059271e-05, + "loss": 3.8046, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.395623780188593e-05, + "loss": 3.799, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.394785185437541e-05, + "loss": 3.8013, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.393946590686489e-05, + "loss": 3.7919, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.393107995935437e-05, + "loss": 3.7963, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.3922710390647576e-05, + "loss": 3.795, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.3914324443137056e-05, + "loss": 3.808, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.3905938495626536e-05, + "loss": 3.7974, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.3897552548116016e-05, + "loss": 3.8012, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.3889182979409225e-05, + "loss": 3.7805, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.3880797031898705e-05, + "loss": 3.8071, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.3872411084388185e-05, + "loss": 3.7944, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.3864025136877665e-05, + "loss": 3.803, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.385565556817088e-05, + "loss": 3.7935, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.384726962066036e-05, + "loss": 3.8048, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.383888367314984e-05, + "loss": 3.7995, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.3830497725639314e-05, + "loss": 3.808, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.382212815693253e-05, + "loss": 3.7859, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.381374220942201e-05, + "loss": 3.7956, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.380535626191148e-05, + "loss": 3.7932, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.379697031440096e-05, + "loss": 3.7872, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.378860074569418e-05, + "loss": 3.8014, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.378021479818366e-05, + "loss": 3.8009, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.377182885067313e-05, + "loss": 3.799, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.376344290316262e-05, + "loss": 3.7796, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.3755073334455835e-05, + "loss": 3.7989, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 3.886021614074707, + "eval_runtime": 314.3717, + "eval_samples_per_second": 1213.821, + "eval_steps_per_second": 37.933, + "step": 381600 + }, + { + "epoch": 0.0, + "learning_rate": 4.3746687386945315e-05, + "loss": 3.7813, + "step": 381952 + }, + { + "epoch": 0.0, + "learning_rate": 4.373830143943479e-05, + "loss": 3.7831, + "step": 382464 + }, + { + "epoch": 0.0, + "learning_rate": 4.372991549192427e-05, + "loss": 3.7951, + "step": 382976 + }, + { + "epoch": 0.0, + "learning_rate": 4.372152954441375e-05, + "loss": 3.7933, + "step": 383488 + }, + { + "epoch": 0.0, + "learning_rate": 4.371314359690323e-05, + "loss": 3.795, + "step": 384000 + }, + { + "epoch": 0.0, + "learning_rate": 4.370475764939271e-05, + "loss": 3.7829, + "step": 384512 + }, + { + "epoch": 0.0, + "learning_rate": 4.369637170188219e-05, + "loss": 3.7882, + "step": 385024 + }, + { + "epoch": 0.0, + "learning_rate": 4.368798575437167e-05, + "loss": 3.7789, + "step": 385536 + }, + { + "epoch": 0.0, + "learning_rate": 4.367961618566488e-05, + "loss": 3.7913, + "step": 386048 + }, + { + "epoch": 0.0, + "learning_rate": 4.367123023815436e-05, + "loss": 3.7865, + "step": 386560 + }, + { + "epoch": 0.0, + "learning_rate": 4.366284429064384e-05, + "loss": 3.7889, + "step": 387072 + }, + { + "epoch": 0.0, + "learning_rate": 4.365445834313332e-05, + "loss": 3.798, + "step": 387584 + }, + { + "epoch": 0.0, + "learning_rate": 4.364608877442653e-05, + "loss": 3.7787, + "step": 388096 + }, + { + "epoch": 0.0, + "learning_rate": 4.363770282691601e-05, + "loss": 3.7897, + "step": 388608 + }, + { + "epoch": 0.0, + "learning_rate": 4.362931687940549e-05, + "loss": 3.7834, + "step": 389120 + }, + { + "epoch": 0.0, + "learning_rate": 4.362093093189497e-05, + "loss": 3.7817, + "step": 389632 + }, + { + "epoch": 0.0, + "learning_rate": 4.361256136318818e-05, + "loss": 3.7742, + "step": 390144 + }, + { + "epoch": 0.0, + "learning_rate": 4.360417541567766e-05, + "loss": 3.7843, + "step": 390656 + }, + { + "epoch": 0.0, + "learning_rate": 4.359578946816714e-05, + "loss": 3.7758, + "step": 391168 + }, + { + "epoch": 0.0, + "learning_rate": 4.358740352065662e-05, + "loss": 3.7977, + "step": 391680 + }, + { + "epoch": 0.0, + "learning_rate": 4.357903395194983e-05, + "loss": 3.785, + "step": 392192 + }, + { + "epoch": 0.0, + "learning_rate": 4.357064800443931e-05, + "loss": 3.7875, + "step": 392704 + }, + { + "epoch": 0.0, + "learning_rate": 4.356226205692879e-05, + "loss": 3.7931, + "step": 393216 + }, + { + "epoch": 0.0, + "learning_rate": 4.355387610941827e-05, + "loss": 3.7924, + "step": 393728 + }, + { + "epoch": 0.0, + "learning_rate": 4.3545506540711486e-05, + "loss": 3.7697, + "step": 394240 + }, + { + "epoch": 0.0, + "learning_rate": 4.3537120593200966e-05, + "loss": 3.784, + "step": 394752 + }, + { + "epoch": 0.0, + "learning_rate": 4.3528734645690446e-05, + "loss": 3.7774, + "step": 395264 + }, + { + "epoch": 0.0, + "learning_rate": 4.3520348698179926e-05, + "loss": 3.7802, + "step": 395776 + }, + { + "epoch": 0.0, + "learning_rate": 4.3511979129473135e-05, + "loss": 3.7707, + "step": 396288 + }, + { + "epoch": 0.0, + "learning_rate": 4.3503593181962615e-05, + "loss": 3.7743, + "step": 396800 + }, + { + "epoch": 0.01, + "learning_rate": 4.3495207234452095e-05, + "loss": 3.7862, + "step": 397312 + }, + { + "epoch": 0.01, + "learning_rate": 4.3486837665745304e-05, + "loss": 3.7829, + "step": 397824 + }, + { + "epoch": 0.01, + "learning_rate": 4.3478451718234784e-05, + "loss": 3.7792, + "step": 398336 + }, + { + "epoch": 0.01, + "learning_rate": 4.3470065770724264e-05, + "loss": 3.7829, + "step": 398848 + }, + { + "epoch": 0.01, + "learning_rate": 4.3461679823213744e-05, + "loss": 3.7809, + "step": 399360 + }, + { + "epoch": 0.01, + "learning_rate": 4.3453293875703224e-05, + "loss": 3.7829, + "step": 399872 + }, + { + "epoch": 0.01, + "learning_rate": 4.344490792819271e-05, + "loss": 3.7713, + "step": 400384 + }, + { + "epoch": 0.01, + "learning_rate": 4.343652198068219e-05, + "loss": 3.7717, + "step": 400896 + }, + { + "epoch": 0.01, + "learning_rate": 4.342813603317167e-05, + "loss": 3.7684, + "step": 401408 + }, + { + "epoch": 0.01, + "learning_rate": 4.341976646446488e-05, + "loss": 3.7718, + "step": 401920 + }, + { + "epoch": 0.01, + "learning_rate": 4.341138051695436e-05, + "loss": 3.7702, + "step": 402432 + }, + { + "epoch": 0.01, + "learning_rate": 4.340299456944384e-05, + "loss": 3.7826, + "step": 402944 + }, + { + "epoch": 0.01, + "learning_rate": 4.339460862193332e-05, + "loss": 3.7809, + "step": 403456 + }, + { + "epoch": 0.01, + "learning_rate": 4.338623905322653e-05, + "loss": 3.7771, + "step": 403968 + }, + { + "epoch": 0.01, + "learning_rate": 4.337785310571601e-05, + "loss": 3.7856, + "step": 404480 + }, + { + "epoch": 0.01, + "learning_rate": 4.336946715820549e-05, + "loss": 3.7772, + "step": 404992 + }, + { + "epoch": 0.01, + "learning_rate": 4.336108121069497e-05, + "loss": 3.7794, + "step": 405504 + }, + { + "epoch": 0.01, + "learning_rate": 4.335271164198818e-05, + "loss": 3.7689, + "step": 406016 + }, + { + "epoch": 0.01, + "learning_rate": 4.3344325694477664e-05, + "loss": 3.7575, + "step": 406528 + }, + { + "epoch": 0.01, + "learning_rate": 4.3335939746967144e-05, + "loss": 3.7828, + "step": 407040 + }, + { + "epoch": 0.01, + "learning_rate": 4.3327553799456624e-05, + "loss": 3.7716, + "step": 407552 + }, + { + "epoch": 0.01, + "learning_rate": 4.331918423074983e-05, + "loss": 3.7688, + "step": 408064 + }, + { + "epoch": 0.01, + "learning_rate": 4.331079828323931e-05, + "loss": 3.7669, + "step": 408576 + }, + { + "epoch": 0.01, + "learning_rate": 4.330241233572879e-05, + "loss": 3.7711, + "step": 409088 + }, + { + "epoch": 0.01, + "learning_rate": 4.3294026388218266e-05, + "loss": 3.7587, + "step": 409600 + }, + { + "epoch": 0.01, + "learning_rate": 4.328565681951148e-05, + "loss": 3.7676, + "step": 410112 + }, + { + "epoch": 0.01, + "learning_rate": 4.327727087200096e-05, + "loss": 3.7693, + "step": 410624 + }, + { + "epoch": 0.01, + "learning_rate": 4.326888492449044e-05, + "loss": 3.7662, + "step": 411136 + }, + { + "epoch": 0.01, + "learning_rate": 4.3260498976979915e-05, + "loss": 3.7763, + "step": 411648 + }, + { + "epoch": 0.01, + "learning_rate": 4.325212940827313e-05, + "loss": 3.7585, + "step": 412160 + }, + { + "epoch": 0.01, + "learning_rate": 4.324374346076261e-05, + "loss": 3.7631, + "step": 412672 + }, + { + "epoch": 0.01, + "learning_rate": 4.32353575132521e-05, + "loss": 3.7738, + "step": 413184 + }, + { + "epoch": 0.01, + "learning_rate": 4.322697156574157e-05, + "loss": 3.7606, + "step": 413696 + }, + { + "epoch": 0.01, + "learning_rate": 4.321860199703479e-05, + "loss": 3.763, + "step": 414208 + }, + { + "epoch": 0.01, + "learning_rate": 4.321021604952427e-05, + "loss": 3.7686, + "step": 414720 + }, + { + "epoch": 0.01, + "learning_rate": 4.320183010201374e-05, + "loss": 3.7728, + "step": 415232 + }, + { + "epoch": 0.01, + "learning_rate": 4.3193460533306956e-05, + "loss": 3.7564, + "step": 415744 + }, + { + "epoch": 0.01, + "learning_rate": 4.3185074585796436e-05, + "loss": 3.757, + "step": 416256 + }, + { + "epoch": 0.01, + "learning_rate": 4.3176688638285916e-05, + "loss": 3.7483, + "step": 416768 + }, + { + "epoch": 0.01, + "learning_rate": 4.316830269077539e-05, + "loss": 3.7668, + "step": 417280 + }, + { + "epoch": 0.01, + "learning_rate": 4.3159933122068605e-05, + "loss": 3.7793, + "step": 417792 + }, + { + "epoch": 0.01, + "learning_rate": 4.3151547174558085e-05, + "loss": 3.7633, + "step": 418304 + }, + { + "epoch": 0.01, + "learning_rate": 4.3143161227047565e-05, + "loss": 3.7704, + "step": 418816 + }, + { + "epoch": 0.01, + "learning_rate": 4.3134775279537045e-05, + "loss": 3.7734, + "step": 419328 + }, + { + "epoch": 0.01, + "learning_rate": 4.312640571083026e-05, + "loss": 3.78, + "step": 419840 + }, + { + "epoch": 0.01, + "learning_rate": 4.311801976331974e-05, + "loss": 3.7556, + "step": 420352 + }, + { + "epoch": 0.01, + "learning_rate": 4.3109633815809214e-05, + "loss": 3.7708, + "step": 420864 + }, + { + "epoch": 0.01, + "learning_rate": 4.3101247868298694e-05, + "loss": 3.7666, + "step": 421376 + }, + { + "epoch": 0.01, + "learning_rate": 4.309287829959191e-05, + "loss": 3.7545, + "step": 421888 + }, + { + "epoch": 0.01, + "learning_rate": 4.308449235208139e-05, + "loss": 3.7715, + "step": 422400 + }, + { + "epoch": 0.01, + "learning_rate": 4.307610640457086e-05, + "loss": 3.7673, + "step": 422912 + }, + { + "epoch": 0.01, + "learning_rate": 4.306772045706034e-05, + "loss": 3.7646, + "step": 423424 + }, + { + "epoch": 0.01, + "learning_rate": 4.305935088835356e-05, + "loss": 3.7688, + "step": 423936 + }, + { + "epoch": 0.01, + "learning_rate": 4.305096494084304e-05, + "loss": 3.7636, + "step": 424448 + }, + { + "epoch": 0.01, + "learning_rate": 4.304257899333252e-05, + "loss": 3.758, + "step": 424960 + }, + { + "epoch": 0.01, + "learning_rate": 4.3034193045822e-05, + "loss": 3.7632, + "step": 425472 + }, + { + "epoch": 0.01, + "learning_rate": 4.3025823477115214e-05, + "loss": 3.7653, + "step": 425984 + }, + { + "epoch": 0.01, + "learning_rate": 4.301743752960469e-05, + "loss": 3.7539, + "step": 426496 + }, + { + "epoch": 0.01, + "learning_rate": 4.300905158209417e-05, + "loss": 3.7586, + "step": 427008 + }, + { + "epoch": 0.02, + "learning_rate": 4.300066563458365e-05, + "loss": 3.7671, + "step": 427520 + }, + { + "epoch": 0.02, + "learning_rate": 4.299229606587686e-05, + "loss": 3.7654, + "step": 428032 + }, + { + "epoch": 0.02, + "learning_rate": 4.2983910118366337e-05, + "loss": 3.7538, + "step": 428544 + }, + { + "epoch": 0.02, + "learning_rate": 4.2975524170855817e-05, + "loss": 3.7564, + "step": 429056 + }, + { + "epoch": 0.02, + "learning_rate": 4.2967138223345296e-05, + "loss": 3.7737, + "step": 429568 + }, + { + "epoch": 0.02, + "learning_rate": 4.295876865463851e-05, + "loss": 3.766, + "step": 430080 + }, + { + "epoch": 0.02, + "learning_rate": 4.295038270712799e-05, + "loss": 3.7634, + "step": 430592 + }, + { + "epoch": 0.02, + "learning_rate": 4.294199675961747e-05, + "loss": 3.7475, + "step": 431104 + }, + { + "epoch": 0.02, + "learning_rate": 4.293361081210695e-05, + "loss": 3.7606, + "step": 431616 + }, + { + "epoch": 0.02, + "learning_rate": 4.292524124340016e-05, + "loss": 3.7568, + "step": 432128 + }, + { + "epoch": 0.02, + "learning_rate": 4.291685529588964e-05, + "loss": 3.7663, + "step": 432640 + }, + { + "epoch": 0.02, + "learning_rate": 4.290846934837912e-05, + "loss": 3.7678, + "step": 433152 + }, + { + "epoch": 0.02, + "learning_rate": 4.29000834008686e-05, + "loss": 3.757, + "step": 433664 + }, + { + "epoch": 0.02, + "learning_rate": 4.289171383216181e-05, + "loss": 3.749, + "step": 434176 + }, + { + "epoch": 0.02, + "learning_rate": 4.288332788465129e-05, + "loss": 3.7622, + "step": 434688 + }, + { + "epoch": 0.02, + "learning_rate": 4.287494193714077e-05, + "loss": 3.7349, + "step": 435200 + }, + { + "epoch": 0.02, + "learning_rate": 4.286655598963025e-05, + "loss": 3.7571, + "step": 435712 + }, + { + "epoch": 0.02, + "learning_rate": 4.2858186420923466e-05, + "loss": 3.7464, + "step": 436224 + }, + { + "epoch": 0.02, + "learning_rate": 4.2849800473412946e-05, + "loss": 3.7608, + "step": 436736 + }, + { + "epoch": 0.02, + "learning_rate": 4.2841414525902426e-05, + "loss": 3.7432, + "step": 437248 + }, + { + "epoch": 0.02, + "learning_rate": 4.2833028578391906e-05, + "loss": 3.7602, + "step": 437760 + }, + { + "epoch": 0.02, + "learning_rate": 4.2824659009685115e-05, + "loss": 3.7508, + "step": 438272 + }, + { + "epoch": 0.02, + "learning_rate": 4.2816273062174595e-05, + "loss": 3.759, + "step": 438784 + }, + { + "epoch": 0.02, + "learning_rate": 4.2807887114664075e-05, + "loss": 3.7622, + "step": 439296 + }, + { + "epoch": 0.02, + "learning_rate": 4.2799501167153555e-05, + "loss": 3.7517, + "step": 439808 + }, + { + "epoch": 0.02, + "learning_rate": 4.2791131598446764e-05, + "loss": 3.7638, + "step": 440320 + }, + { + "epoch": 0.02, + "learning_rate": 4.2782745650936244e-05, + "loss": 3.7726, + "step": 440832 + }, + { + "epoch": 0.02, + "learning_rate": 4.2774359703425724e-05, + "loss": 3.7581, + "step": 441344 + }, + { + "epoch": 0.02, + "learning_rate": 4.2765973755915204e-05, + "loss": 3.7521, + "step": 441856 + }, + { + "epoch": 0.02, + "learning_rate": 4.275760418720842e-05, + "loss": 3.7565, + "step": 442368 + }, + { + "epoch": 0.02, + "learning_rate": 4.27492182396979e-05, + "loss": 3.7573, + "step": 442880 + }, + { + "epoch": 0.02, + "learning_rate": 4.274083229218738e-05, + "loss": 3.7433, + "step": 443392 + }, + { + "epoch": 0.02, + "learning_rate": 4.273244634467686e-05, + "loss": 3.7707, + "step": 443904 + }, + { + "epoch": 0.02, + "learning_rate": 4.272407677597007e-05, + "loss": 3.7435, + "step": 444416 + }, + { + "epoch": 0.02, + "learning_rate": 4.271569082845955e-05, + "loss": 3.7635, + "step": 444928 + }, + { + "epoch": 0.02, + "learning_rate": 4.270730488094903e-05, + "loss": 3.7547, + "step": 445440 + }, + { + "epoch": 0.02, + "learning_rate": 4.269891893343851e-05, + "loss": 3.7566, + "step": 445952 + }, + { + "epoch": 0.02, + "learning_rate": 4.269054936473172e-05, + "loss": 3.7496, + "step": 446464 + }, + { + "epoch": 0.02, + "learning_rate": 4.26821634172212e-05, + "loss": 3.7553, + "step": 446976 + }, + { + "epoch": 0.02, + "learning_rate": 4.267377746971068e-05, + "loss": 3.7495, + "step": 447488 + }, + { + "epoch": 0.02, + "learning_rate": 4.266539152220016e-05, + "loss": 3.7648, + "step": 448000 + }, + { + "epoch": 0.02, + "learning_rate": 4.265702195349337e-05, + "loss": 3.7522, + "step": 448512 + }, + { + "epoch": 0.02, + "learning_rate": 4.264863600598285e-05, + "loss": 3.7593, + "step": 449024 + }, + { + "epoch": 0.02, + "learning_rate": 4.264025005847233e-05, + "loss": 3.7392, + "step": 449536 + }, + { + "epoch": 0.02, + "learning_rate": 4.263186411096181e-05, + "loss": 3.7636, + "step": 450048 + }, + { + "epoch": 0.02, + "learning_rate": 4.262349454225502e-05, + "loss": 3.7498, + "step": 450560 + }, + { + "epoch": 0.02, + "learning_rate": 4.26151085947445e-05, + "loss": 3.7586, + "step": 451072 + }, + { + "epoch": 0.02, + "learning_rate": 4.260672264723398e-05, + "loss": 3.7527, + "step": 451584 + }, + { + "epoch": 0.02, + "learning_rate": 4.259833669972346e-05, + "loss": 3.7572, + "step": 452096 + }, + { + "epoch": 0.02, + "learning_rate": 4.258996713101667e-05, + "loss": 3.7542, + "step": 452608 + }, + { + "epoch": 0.02, + "learning_rate": 4.258158118350615e-05, + "loss": 3.7686, + "step": 453120 + }, + { + "epoch": 0.02, + "learning_rate": 4.257319523599563e-05, + "loss": 3.7407, + "step": 453632 + }, + { + "epoch": 0.02, + "learning_rate": 4.256480928848511e-05, + "loss": 3.7534, + "step": 454144 + }, + { + "epoch": 0.02, + "learning_rate": 4.255643971977833e-05, + "loss": 3.7483, + "step": 454656 + }, + { + "epoch": 0.02, + "learning_rate": 4.254805377226781e-05, + "loss": 3.7482, + "step": 455168 + }, + { + "epoch": 0.02, + "learning_rate": 4.253966782475729e-05, + "loss": 3.7515, + "step": 455680 + }, + { + "epoch": 0.02, + "learning_rate": 4.253128187724677e-05, + "loss": 3.7593, + "step": 456192 + }, + { + "epoch": 0.02, + "learning_rate": 4.2522912308539976e-05, + "loss": 3.7585, + "step": 456704 + }, + { + "epoch": 0.02, + "learning_rate": 4.2514526361029456e-05, + "loss": 3.7374, + "step": 457216 + }, + { + "epoch": 0.02, + "learning_rate": 4.2506140413518936e-05, + "loss": 3.7596, + "step": 457728 + }, + { + "epoch": 0.03, + "eval_loss": 3.8695147037506104, + "eval_runtime": 304.879, + "eval_samples_per_second": 1251.615, + "eval_steps_per_second": 39.114, + "step": 457920 + }, + { + "epoch": 1.0, + "learning_rate": 4.2497770844812145e-05, + "loss": 3.7464, + "step": 458240 + }, + { + "epoch": 1.0, + "learning_rate": 4.2489384897301625e-05, + "loss": 3.7382, + "step": 458752 + }, + { + "epoch": 1.0, + "learning_rate": 4.2480998949791105e-05, + "loss": 3.7548, + "step": 459264 + }, + { + "epoch": 1.0, + "learning_rate": 4.2472613002280585e-05, + "loss": 3.7496, + "step": 459776 + }, + { + "epoch": 1.0, + "learning_rate": 4.2464243433573794e-05, + "loss": 3.7527, + "step": 460288 + }, + { + "epoch": 1.0, + "learning_rate": 4.245585748606328e-05, + "loss": 3.7392, + "step": 460800 + }, + { + "epoch": 1.0, + "learning_rate": 4.244747153855276e-05, + "loss": 3.7428, + "step": 461312 + }, + { + "epoch": 1.0, + "learning_rate": 4.243908559104224e-05, + "loss": 3.7387, + "step": 461824 + }, + { + "epoch": 1.0, + "learning_rate": 4.243071602233545e-05, + "loss": 3.7482, + "step": 462336 + }, + { + "epoch": 1.0, + "learning_rate": 4.242233007482493e-05, + "loss": 3.7459, + "step": 462848 + }, + { + "epoch": 1.0, + "learning_rate": 4.241394412731441e-05, + "loss": 3.7489, + "step": 463360 + }, + { + "epoch": 1.0, + "learning_rate": 4.240555817980389e-05, + "loss": 3.7545, + "step": 463872 + }, + { + "epoch": 1.0, + "learning_rate": 4.23971886110971e-05, + "loss": 3.7394, + "step": 464384 + }, + { + "epoch": 1.0, + "learning_rate": 4.238880266358658e-05, + "loss": 3.7429, + "step": 464896 + }, + { + "epoch": 1.0, + "learning_rate": 4.238041671607606e-05, + "loss": 3.7452, + "step": 465408 + }, + { + "epoch": 1.0, + "learning_rate": 4.237203076856554e-05, + "loss": 3.7363, + "step": 465920 + }, + { + "epoch": 1.0, + "learning_rate": 4.236364482105502e-05, + "loss": 3.7324, + "step": 466432 + }, + { + "epoch": 1.0, + "learning_rate": 4.23552588735445e-05, + "loss": 3.7397, + "step": 466944 + }, + { + "epoch": 1.0, + "learning_rate": 4.234687292603398e-05, + "loss": 3.7364, + "step": 467456 + }, + { + "epoch": 1.0, + "learning_rate": 4.233848697852346e-05, + "loss": 3.752, + "step": 467968 + }, + { + "epoch": 1.0, + "learning_rate": 4.2330117409816674e-05, + "loss": 3.744, + "step": 468480 + }, + { + "epoch": 1.0, + "learning_rate": 4.2321731462306154e-05, + "loss": 3.7485, + "step": 468992 + }, + { + "epoch": 1.0, + "learning_rate": 4.2313345514795634e-05, + "loss": 3.7492, + "step": 469504 + }, + { + "epoch": 1.0, + "learning_rate": 4.2304959567285114e-05, + "loss": 3.7497, + "step": 470016 + }, + { + "epoch": 1.0, + "learning_rate": 4.229658999857832e-05, + "loss": 3.7319, + "step": 470528 + }, + { + "epoch": 1.0, + "learning_rate": 4.22882040510678e-05, + "loss": 3.7436, + "step": 471040 + }, + { + "epoch": 1.0, + "learning_rate": 4.227981810355728e-05, + "loss": 3.7318, + "step": 471552 + }, + { + "epoch": 1.0, + "learning_rate": 4.227143215604676e-05, + "loss": 3.7391, + "step": 472064 + }, + { + "epoch": 1.0, + "learning_rate": 4.226306258733997e-05, + "loss": 3.733, + "step": 472576 + }, + { + "epoch": 1.0, + "learning_rate": 4.225467663982945e-05, + "loss": 3.7316, + "step": 473088 + }, + { + "epoch": 1.01, + "learning_rate": 4.224629069231893e-05, + "loss": 3.7469, + "step": 473600 + }, + { + "epoch": 1.01, + "learning_rate": 4.223792112361215e-05, + "loss": 3.7424, + "step": 474112 + }, + { + "epoch": 1.01, + "learning_rate": 4.222953517610163e-05, + "loss": 3.7391, + "step": 474624 + }, + { + "epoch": 1.01, + "learning_rate": 4.222114922859111e-05, + "loss": 3.7417, + "step": 475136 + }, + { + "epoch": 1.01, + "learning_rate": 4.221276328108059e-05, + "loss": 3.7383, + "step": 475648 + }, + { + "epoch": 1.01, + "learning_rate": 4.220437733357006e-05, + "loss": 3.7457, + "step": 476160 + }, + { + "epoch": 1.01, + "learning_rate": 4.219599138605954e-05, + "loss": 3.7329, + "step": 476672 + }, + { + "epoch": 1.01, + "learning_rate": 4.218760543854902e-05, + "loss": 3.7324, + "step": 477184 + }, + { + "epoch": 1.01, + "learning_rate": 4.21792194910385e-05, + "loss": 3.7266, + "step": 477696 + }, + { + "epoch": 1.01, + "learning_rate": 4.217084992233171e-05, + "loss": 3.7322, + "step": 478208 + }, + { + "epoch": 1.01, + "learning_rate": 4.216246397482119e-05, + "loss": 3.7329, + "step": 478720 + }, + { + "epoch": 1.01, + "learning_rate": 4.215407802731067e-05, + "loss": 3.7412, + "step": 479232 + }, + { + "epoch": 1.01, + "learning_rate": 4.2145708458603886e-05, + "loss": 3.7397, + "step": 479744 + }, + { + "epoch": 1.01, + "learning_rate": 4.2137322511093366e-05, + "loss": 3.7369, + "step": 480256 + }, + { + "epoch": 1.01, + "learning_rate": 4.2128936563582846e-05, + "loss": 3.745, + "step": 480768 + }, + { + "epoch": 1.01, + "learning_rate": 4.2120550616072326e-05, + "loss": 3.7386, + "step": 481280 + }, + { + "epoch": 1.01, + "learning_rate": 4.2112181047365535e-05, + "loss": 3.7407, + "step": 481792 + }, + { + "epoch": 1.01, + "learning_rate": 4.2103795099855015e-05, + "loss": 3.7276, + "step": 482304 + }, + { + "epoch": 1.01, + "learning_rate": 4.2095409152344495e-05, + "loss": 3.717, + "step": 482816 + }, + { + "epoch": 1.01, + "learning_rate": 4.2087023204833975e-05, + "loss": 3.745, + "step": 483328 + }, + { + "epoch": 1.01, + "learning_rate": 4.2078653636127184e-05, + "loss": 3.7321, + "step": 483840 + }, + { + "epoch": 1.01, + "learning_rate": 4.2070267688616664e-05, + "loss": 3.7262, + "step": 484352 + }, + { + "epoch": 1.01, + "learning_rate": 4.2061881741106144e-05, + "loss": 3.7311, + "step": 484864 + }, + { + "epoch": 1.01, + "learning_rate": 4.2053495793595623e-05, + "loss": 3.7274, + "step": 485376 + }, + { + "epoch": 1.01, + "learning_rate": 4.204512622488884e-05, + "loss": 3.7235, + "step": 485888 + }, + { + "epoch": 1.01, + "learning_rate": 4.203674027737832e-05, + "loss": 3.7248, + "step": 486400 + }, + { + "epoch": 1.01, + "learning_rate": 4.20283543298678e-05, + "loss": 3.7279, + "step": 486912 + }, + { + "epoch": 1.01, + "learning_rate": 4.201996838235728e-05, + "loss": 3.7279, + "step": 487424 + }, + { + "epoch": 1.01, + "learning_rate": 4.201159881365049e-05, + "loss": 3.7392, + "step": 487936 + }, + { + "epoch": 1.01, + "learning_rate": 4.200321286613997e-05, + "loss": 3.7201, + "step": 488448 + }, + { + "epoch": 1.01, + "learning_rate": 4.199482691862945e-05, + "loss": 3.7222, + "step": 488960 + }, + { + "epoch": 1.01, + "learning_rate": 4.198644097111893e-05, + "loss": 3.7427, + "step": 489472 + }, + { + "epoch": 1.01, + "learning_rate": 4.197807140241214e-05, + "loss": 3.7152, + "step": 489984 + }, + { + "epoch": 1.01, + "learning_rate": 4.196968545490162e-05, + "loss": 3.7223, + "step": 490496 + }, + { + "epoch": 1.01, + "learning_rate": 4.19612995073911e-05, + "loss": 3.7319, + "step": 491008 + }, + { + "epoch": 1.01, + "learning_rate": 4.195291355988058e-05, + "loss": 3.7381, + "step": 491520 + }, + { + "epoch": 1.01, + "learning_rate": 4.194454399117379e-05, + "loss": 3.7176, + "step": 492032 + }, + { + "epoch": 1.01, + "learning_rate": 4.193615804366327e-05, + "loss": 3.7181, + "step": 492544 + }, + { + "epoch": 1.01, + "learning_rate": 4.192777209615275e-05, + "loss": 3.7083, + "step": 493056 + }, + { + "epoch": 1.01, + "learning_rate": 4.191938614864223e-05, + "loss": 3.7251, + "step": 493568 + }, + { + "epoch": 1.01, + "learning_rate": 4.191101657993544e-05, + "loss": 3.7409, + "step": 494080 + }, + { + "epoch": 1.01, + "learning_rate": 4.190263063242492e-05, + "loss": 3.7255, + "step": 494592 + }, + { + "epoch": 1.01, + "learning_rate": 4.18942446849144e-05, + "loss": 3.7291, + "step": 495104 + }, + { + "epoch": 1.01, + "learning_rate": 4.188585873740388e-05, + "loss": 3.7351, + "step": 495616 + }, + { + "epoch": 1.01, + "learning_rate": 4.187748916869709e-05, + "loss": 3.7415, + "step": 496128 + }, + { + "epoch": 1.01, + "learning_rate": 4.186910322118657e-05, + "loss": 3.7192, + "step": 496640 + }, + { + "epoch": 1.01, + "learning_rate": 4.186071727367605e-05, + "loss": 3.732, + "step": 497152 + }, + { + "epoch": 1.01, + "learning_rate": 4.185233132616553e-05, + "loss": 3.7285, + "step": 497664 + }, + { + "epoch": 1.01, + "learning_rate": 4.184396175745875e-05, + "loss": 3.7161, + "step": 498176 + }, + { + "epoch": 1.01, + "learning_rate": 4.183557580994823e-05, + "loss": 3.7314, + "step": 498688 + }, + { + "epoch": 1.01, + "learning_rate": 4.182718986243771e-05, + "loss": 3.7307, + "step": 499200 + }, + { + "epoch": 1.01, + "learning_rate": 4.1818803914927187e-05, + "loss": 3.7303, + "step": 499712 + }, + { + "epoch": 1.01, + "learning_rate": 4.1810434346220396e-05, + "loss": 3.7269, + "step": 500224 + }, + { + "epoch": 1.01, + "learning_rate": 4.1802048398709876e-05, + "loss": 3.7275, + "step": 500736 + }, + { + "epoch": 1.01, + "learning_rate": 4.1793662451199356e-05, + "loss": 3.7169, + "step": 501248 + }, + { + "epoch": 1.01, + "learning_rate": 4.1785276503688836e-05, + "loss": 3.7271, + "step": 501760 + }, + { + "epoch": 1.01, + "learning_rate": 4.1776906934982045e-05, + "loss": 3.7264, + "step": 502272 + }, + { + "epoch": 1.01, + "learning_rate": 4.1768520987471525e-05, + "loss": 3.7199, + "step": 502784 + }, + { + "epoch": 1.01, + "learning_rate": 4.1760135039961005e-05, + "loss": 3.7221, + "step": 503296 + }, + { + "epoch": 1.02, + "learning_rate": 4.1751749092450484e-05, + "loss": 3.7216, + "step": 503808 + }, + { + "epoch": 1.02, + "learning_rate": 4.17433795237437e-05, + "loss": 3.731, + "step": 504320 + }, + { + "epoch": 1.02, + "learning_rate": 4.173499357623318e-05, + "loss": 3.7193, + "step": 504832 + }, + { + "epoch": 1.02, + "learning_rate": 4.172660762872266e-05, + "loss": 3.7151, + "step": 505344 + }, + { + "epoch": 1.02, + "learning_rate": 4.171822168121214e-05, + "loss": 3.736, + "step": 505856 + }, + { + "epoch": 1.02, + "learning_rate": 4.170985211250535e-05, + "loss": 3.7259, + "step": 506368 + }, + { + "epoch": 1.02, + "learning_rate": 4.170146616499483e-05, + "loss": 3.7278, + "step": 506880 + }, + { + "epoch": 1.02, + "learning_rate": 4.169308021748431e-05, + "loss": 3.7094, + "step": 507392 + }, + { + "epoch": 1.02, + "learning_rate": 4.168471064877752e-05, + "loss": 3.7245, + "step": 507904 + }, + { + "epoch": 1.02, + "learning_rate": 4.1676324701267e-05, + "loss": 3.7163, + "step": 508416 + }, + { + "epoch": 1.02, + "learning_rate": 4.166793875375648e-05, + "loss": 3.7261, + "step": 508928 + }, + { + "epoch": 1.02, + "learning_rate": 4.165955280624596e-05, + "loss": 3.7337, + "step": 509440 + }, + { + "epoch": 1.02, + "learning_rate": 4.1651183237539174e-05, + "loss": 3.7172, + "step": 509952 + }, + { + "epoch": 1.02, + "learning_rate": 4.1642797290028654e-05, + "loss": 3.7162, + "step": 510464 + }, + { + "epoch": 1.02, + "learning_rate": 4.1634411342518134e-05, + "loss": 3.7213, + "step": 510976 + }, + { + "epoch": 1.02, + "learning_rate": 4.1626025395007614e-05, + "loss": 3.6995, + "step": 511488 + }, + { + "epoch": 1.02, + "learning_rate": 4.161765582630082e-05, + "loss": 3.7243, + "step": 512000 + }, + { + "epoch": 1.02, + "learning_rate": 4.16092698787903e-05, + "loss": 3.7059, + "step": 512512 + }, + { + "epoch": 1.02, + "learning_rate": 4.160088393127978e-05, + "loss": 3.7238, + "step": 513024 + }, + { + "epoch": 1.02, + "learning_rate": 4.159249798376926e-05, + "loss": 3.7075, + "step": 513536 + }, + { + "epoch": 1.02, + "learning_rate": 4.158412841506247e-05, + "loss": 3.7208, + "step": 514048 + }, + { + "epoch": 1.02, + "learning_rate": 4.157574246755195e-05, + "loss": 3.7157, + "step": 514560 + }, + { + "epoch": 1.02, + "learning_rate": 4.156735652004143e-05, + "loss": 3.7171, + "step": 515072 + }, + { + "epoch": 1.02, + "learning_rate": 4.155897057253091e-05, + "loss": 3.7296, + "step": 515584 + }, + { + "epoch": 1.02, + "learning_rate": 4.155060100382413e-05, + "loss": 3.7127, + "step": 516096 + }, + { + "epoch": 1.02, + "learning_rate": 4.154221505631361e-05, + "loss": 3.728, + "step": 516608 + }, + { + "epoch": 1.02, + "learning_rate": 4.153382910880309e-05, + "loss": 3.7352, + "step": 517120 + }, + { + "epoch": 1.02, + "learning_rate": 4.152544316129257e-05, + "loss": 3.7218, + "step": 517632 + }, + { + "epoch": 1.02, + "learning_rate": 4.151707359258578e-05, + "loss": 3.7191, + "step": 518144 + }, + { + "epoch": 1.02, + "learning_rate": 4.150868764507526e-05, + "loss": 3.715, + "step": 518656 + }, + { + "epoch": 1.02, + "learning_rate": 4.150030169756474e-05, + "loss": 3.7198, + "step": 519168 + }, + { + "epoch": 1.02, + "learning_rate": 4.1491915750054217e-05, + "loss": 3.7136, + "step": 519680 + }, + { + "epoch": 1.02, + "learning_rate": 4.1483546181347426e-05, + "loss": 3.7311, + "step": 520192 + }, + { + "epoch": 1.02, + "learning_rate": 4.1475160233836906e-05, + "loss": 3.7039, + "step": 520704 + }, + { + "epoch": 1.02, + "learning_rate": 4.1466774286326386e-05, + "loss": 3.7249, + "step": 521216 + }, + { + "epoch": 1.02, + "learning_rate": 4.1458388338815866e-05, + "loss": 3.72, + "step": 521728 + }, + { + "epoch": 1.02, + "learning_rate": 4.145001877010908e-05, + "loss": 3.7185, + "step": 522240 + }, + { + "epoch": 1.02, + "learning_rate": 4.144163282259856e-05, + "loss": 3.7092, + "step": 522752 + }, + { + "epoch": 1.02, + "learning_rate": 4.143324687508804e-05, + "loss": 3.7209, + "step": 523264 + }, + { + "epoch": 1.02, + "learning_rate": 4.142486092757752e-05, + "loss": 3.709, + "step": 523776 + }, + { + "epoch": 1.02, + "learning_rate": 4.141649135887073e-05, + "loss": 3.7323, + "step": 524288 + }, + { + "epoch": 1.02, + "learning_rate": 4.140810541136021e-05, + "loss": 3.7129, + "step": 524800 + }, + { + "epoch": 1.02, + "learning_rate": 4.139971946384969e-05, + "loss": 3.7235, + "step": 525312 + }, + { + "epoch": 1.02, + "learning_rate": 4.139133351633917e-05, + "loss": 3.7014, + "step": 525824 + }, + { + "epoch": 1.02, + "learning_rate": 4.138296394763238e-05, + "loss": 3.729, + "step": 526336 + }, + { + "epoch": 1.02, + "learning_rate": 4.137457800012186e-05, + "loss": 3.7163, + "step": 526848 + }, + { + "epoch": 1.02, + "learning_rate": 4.136619205261134e-05, + "loss": 3.7225, + "step": 527360 + }, + { + "epoch": 1.02, + "learning_rate": 4.135780610510082e-05, + "loss": 3.7161, + "step": 527872 + }, + { + "epoch": 1.02, + "learning_rate": 4.1349436536394035e-05, + "loss": 3.7164, + "step": 528384 + }, + { + "epoch": 1.02, + "learning_rate": 4.1341050588883515e-05, + "loss": 3.7219, + "step": 528896 + }, + { + "epoch": 1.02, + "learning_rate": 4.1332664641372995e-05, + "loss": 3.7346, + "step": 529408 + }, + { + "epoch": 1.02, + "learning_rate": 4.1324278693862475e-05, + "loss": 3.7024, + "step": 529920 + }, + { + "epoch": 1.02, + "learning_rate": 4.1315909125155684e-05, + "loss": 3.7163, + "step": 530432 + }, + { + "epoch": 1.02, + "learning_rate": 4.1307523177645164e-05, + "loss": 3.713, + "step": 530944 + }, + { + "epoch": 1.02, + "learning_rate": 4.1299137230134644e-05, + "loss": 3.7178, + "step": 531456 + }, + { + "epoch": 1.02, + "learning_rate": 4.1290751282624124e-05, + "loss": 3.7115, + "step": 531968 + }, + { + "epoch": 1.02, + "learning_rate": 4.128238171391733e-05, + "loss": 3.7208, + "step": 532480 + }, + { + "epoch": 1.02, + "learning_rate": 4.127399576640681e-05, + "loss": 3.7216, + "step": 532992 + }, + { + "epoch": 1.02, + "learning_rate": 4.126560981889629e-05, + "loss": 3.7054, + "step": 533504 + }, + { + "epoch": 1.02, + "learning_rate": 4.12572402501895e-05, + "loss": 3.725, + "step": 534016 + }, + { + "epoch": 1.03, + "eval_loss": 3.858961343765259, + "eval_runtime": 304.9762, + "eval_samples_per_second": 1251.216, + "eval_steps_per_second": 39.101, + "step": 534240 + }, + { + "epoch": 0.0, + "learning_rate": 4.124885430267898e-05, + "loss": 3.7083, + "step": 534528 + }, + { + "epoch": 0.0, + "learning_rate": 4.124046835516847e-05, + "loss": 3.7038, + "step": 535040 + }, + { + "epoch": 0.0, + "learning_rate": 4.123208240765795e-05, + "loss": 3.7189, + "step": 535552 + }, + { + "epoch": 0.0, + "learning_rate": 4.122369646014743e-05, + "loss": 3.7107, + "step": 536064 + }, + { + "epoch": 0.0, + "learning_rate": 4.121531051263691e-05, + "loss": 3.7169, + "step": 536576 + }, + { + "epoch": 0.0, + "learning_rate": 4.120692456512638e-05, + "loss": 3.7038, + "step": 537088 + }, + { + "epoch": 0.0, + "learning_rate": 4.119853861761586e-05, + "loss": 3.7104, + "step": 537600 + }, + { + "epoch": 0.0, + "learning_rate": 4.119015267010534e-05, + "loss": 3.7032, + "step": 538112 + }, + { + "epoch": 0.0, + "learning_rate": 4.118178310139856e-05, + "loss": 3.7164, + "step": 538624 + }, + { + "epoch": 0.0, + "learning_rate": 4.117339715388803e-05, + "loss": 3.7051, + "step": 539136 + }, + { + "epoch": 0.0, + "learning_rate": 4.116501120637751e-05, + "loss": 3.7131, + "step": 539648 + }, + { + "epoch": 0.0, + "learning_rate": 4.115662525886699e-05, + "loss": 3.7184, + "step": 540160 + }, + { + "epoch": 0.0, + "learning_rate": 4.1148272068963936e-05, + "loss": 3.7092, + "step": 540672 + }, + { + "epoch": 0.0, + "learning_rate": 4.113988612145342e-05, + "loss": 3.708, + "step": 541184 + }, + { + "epoch": 0.0, + "learning_rate": 4.11315001739429e-05, + "loss": 3.7072, + "step": 541696 + }, + { + "epoch": 0.0, + "learning_rate": 4.112311422643238e-05, + "loss": 3.6987, + "step": 542208 + }, + { + "epoch": 0.0, + "learning_rate": 4.1114728278921855e-05, + "loss": 3.6992, + "step": 542720 + }, + { + "epoch": 0.0, + "learning_rate": 4.1106342331411335e-05, + "loss": 3.7055, + "step": 543232 + }, + { + "epoch": 0.0, + "learning_rate": 4.1097956383900815e-05, + "loss": 3.7041, + "step": 543744 + }, + { + "epoch": 0.0, + "learning_rate": 4.1089570436390295e-05, + "loss": 3.7115, + "step": 544256 + }, + { + "epoch": 0.0, + "learning_rate": 4.1081200867683504e-05, + "loss": 3.7152, + "step": 544768 + }, + { + "epoch": 0.0, + "learning_rate": 4.1072814920172984e-05, + "loss": 3.7103, + "step": 545280 + }, + { + "epoch": 0.0, + "learning_rate": 4.1064428972662464e-05, + "loss": 3.7132, + "step": 545792 + }, + { + "epoch": 0.0, + "learning_rate": 4.1056043025151944e-05, + "loss": 3.7157, + "step": 546304 + }, + { + "epoch": 0.0, + "learning_rate": 4.104767345644516e-05, + "loss": 3.695, + "step": 546816 + }, + { + "epoch": 0.0, + "learning_rate": 4.103928750893464e-05, + "loss": 3.7141, + "step": 547328 + }, + { + "epoch": 0.0, + "learning_rate": 4.103090156142412e-05, + "loss": 3.6988, + "step": 547840 + }, + { + "epoch": 0.0, + "learning_rate": 4.10225156139136e-05, + "loss": 3.7015, + "step": 548352 + }, + { + "epoch": 0.0, + "learning_rate": 4.101414604520681e-05, + "loss": 3.6978, + "step": 548864 + }, + { + "epoch": 0.0, + "learning_rate": 4.100576009769629e-05, + "loss": 3.7019, + "step": 549376 + }, + { + "epoch": 0.01, + "learning_rate": 4.099737415018577e-05, + "loss": 3.707, + "step": 549888 + }, + { + "epoch": 0.01, + "learning_rate": 4.098900458147898e-05, + "loss": 3.713, + "step": 550400 + }, + { + "epoch": 0.01, + "learning_rate": 4.098061863396846e-05, + "loss": 3.7051, + "step": 550912 + }, + { + "epoch": 0.01, + "learning_rate": 4.097223268645794e-05, + "loss": 3.7104, + "step": 551424 + }, + { + "epoch": 0.01, + "learning_rate": 4.096384673894742e-05, + "loss": 3.6982, + "step": 551936 + }, + { + "epoch": 0.01, + "learning_rate": 4.09554607914369e-05, + "loss": 3.7115, + "step": 552448 + }, + { + "epoch": 0.01, + "learning_rate": 4.094707484392638e-05, + "loss": 3.7058, + "step": 552960 + }, + { + "epoch": 0.01, + "learning_rate": 4.093868889641586e-05, + "loss": 3.6916, + "step": 553472 + }, + { + "epoch": 0.01, + "learning_rate": 4.0930302948905345e-05, + "loss": 3.6936, + "step": 553984 + }, + { + "epoch": 0.01, + "learning_rate": 4.0921933380198554e-05, + "loss": 3.6973, + "step": 554496 + }, + { + "epoch": 0.01, + "learning_rate": 4.0913547432688034e-05, + "loss": 3.7018, + "step": 555008 + }, + { + "epoch": 0.01, + "learning_rate": 4.0905161485177514e-05, + "loss": 3.7033, + "step": 555520 + }, + { + "epoch": 0.01, + "learning_rate": 4.0896775537666994e-05, + "loss": 3.7059, + "step": 556032 + }, + { + "epoch": 0.01, + "learning_rate": 4.08884059689602e-05, + "loss": 3.7014, + "step": 556544 + }, + { + "epoch": 0.01, + "learning_rate": 4.088002002144968e-05, + "loss": 3.7132, + "step": 557056 + }, + { + "epoch": 0.01, + "learning_rate": 4.087163407393916e-05, + "loss": 3.7013, + "step": 557568 + }, + { + "epoch": 0.01, + "learning_rate": 4.086326450523237e-05, + "loss": 3.7094, + "step": 558080 + }, + { + "epoch": 0.01, + "learning_rate": 4.085487855772185e-05, + "loss": 3.6967, + "step": 558592 + }, + { + "epoch": 0.01, + "learning_rate": 4.084649261021133e-05, + "loss": 3.6788, + "step": 559104 + }, + { + "epoch": 0.01, + "learning_rate": 4.083810666270081e-05, + "loss": 3.7134, + "step": 559616 + }, + { + "epoch": 0.01, + "learning_rate": 4.082973709399403e-05, + "loss": 3.6992, + "step": 560128 + }, + { + "epoch": 0.01, + "learning_rate": 4.082135114648351e-05, + "loss": 3.6983, + "step": 560640 + }, + { + "epoch": 0.01, + "learning_rate": 4.081296519897299e-05, + "loss": 3.6957, + "step": 561152 + }, + { + "epoch": 0.01, + "learning_rate": 4.080457925146247e-05, + "loss": 3.6949, + "step": 561664 + }, + { + "epoch": 0.01, + "learning_rate": 4.0796209682755676e-05, + "loss": 3.6918, + "step": 562176 + }, + { + "epoch": 0.01, + "learning_rate": 4.0787823735245156e-05, + "loss": 3.6897, + "step": 562688 + }, + { + "epoch": 0.01, + "learning_rate": 4.0779437787734636e-05, + "loss": 3.6963, + "step": 563200 + }, + { + "epoch": 0.01, + "learning_rate": 4.0771051840224116e-05, + "loss": 3.6913, + "step": 563712 + }, + { + "epoch": 0.01, + "learning_rate": 4.0762682271517325e-05, + "loss": 3.7093, + "step": 564224 + }, + { + "epoch": 0.01, + "learning_rate": 4.0754296324006805e-05, + "loss": 3.6895, + "step": 564736 + }, + { + "epoch": 0.01, + "learning_rate": 4.0745910376496285e-05, + "loss": 3.6884, + "step": 565248 + }, + { + "epoch": 0.01, + "learning_rate": 4.0737524428985765e-05, + "loss": 3.7074, + "step": 565760 + }, + { + "epoch": 0.01, + "learning_rate": 4.072915486027898e-05, + "loss": 3.6824, + "step": 566272 + }, + { + "epoch": 0.01, + "learning_rate": 4.072076891276846e-05, + "loss": 3.6875, + "step": 566784 + }, + { + "epoch": 0.01, + "learning_rate": 4.071238296525794e-05, + "loss": 3.7001, + "step": 567296 + }, + { + "epoch": 0.01, + "learning_rate": 4.070399701774742e-05, + "loss": 3.7052, + "step": 567808 + }, + { + "epoch": 0.01, + "learning_rate": 4.069562744904063e-05, + "loss": 3.685, + "step": 568320 + }, + { + "epoch": 0.01, + "learning_rate": 4.068724150153011e-05, + "loss": 3.685, + "step": 568832 + }, + { + "epoch": 0.01, + "learning_rate": 4.067885555401959e-05, + "loss": 3.6783, + "step": 569344 + }, + { + "epoch": 0.01, + "learning_rate": 4.067046960650907e-05, + "loss": 3.6917, + "step": 569856 + }, + { + "epoch": 0.01, + "learning_rate": 4.066210003780228e-05, + "loss": 3.7072, + "step": 570368 + }, + { + "epoch": 0.01, + "learning_rate": 4.065371409029176e-05, + "loss": 3.6931, + "step": 570880 + }, + { + "epoch": 0.01, + "learning_rate": 4.064532814278124e-05, + "loss": 3.6949, + "step": 571392 + }, + { + "epoch": 0.01, + "learning_rate": 4.063694219527072e-05, + "loss": 3.7032, + "step": 571904 + }, + { + "epoch": 0.01, + "learning_rate": 4.0628572626563935e-05, + "loss": 3.7081, + "step": 572416 + }, + { + "epoch": 0.01, + "learning_rate": 4.0620186679053415e-05, + "loss": 3.6845, + "step": 572928 + }, + { + "epoch": 0.01, + "learning_rate": 4.0611817110346624e-05, + "loss": 3.702, + "step": 573440 + }, + { + "epoch": 0.01, + "learning_rate": 4.0603431162836104e-05, + "loss": 3.69, + "step": 573952 + }, + { + "epoch": 0.01, + "learning_rate": 4.0595045215325584e-05, + "loss": 3.6903, + "step": 574464 + }, + { + "epoch": 0.01, + "learning_rate": 4.0586659267815064e-05, + "loss": 3.6938, + "step": 574976 + }, + { + "epoch": 0.01, + "learning_rate": 4.0578273320304544e-05, + "loss": 3.7022, + "step": 575488 + }, + { + "epoch": 0.01, + "learning_rate": 4.0569887372794024e-05, + "loss": 3.6953, + "step": 576000 + }, + { + "epoch": 0.01, + "learning_rate": 4.0561501425283504e-05, + "loss": 3.7003, + "step": 576512 + }, + { + "epoch": 0.01, + "learning_rate": 4.0553115477772983e-05, + "loss": 3.6923, + "step": 577024 + }, + { + "epoch": 0.01, + "learning_rate": 4.054474590906619e-05, + "loss": 3.685, + "step": 577536 + }, + { + "epoch": 0.01, + "learning_rate": 4.053635996155567e-05, + "loss": 3.6959, + "step": 578048 + }, + { + "epoch": 0.01, + "learning_rate": 4.052797401404515e-05, + "loss": 3.6938, + "step": 578560 + }, + { + "epoch": 0.01, + "learning_rate": 4.051958806653464e-05, + "loss": 3.6882, + "step": 579072 + }, + { + "epoch": 0.01, + "learning_rate": 4.051121849782785e-05, + "loss": 3.6899, + "step": 579584 + }, + { + "epoch": 0.02, + "learning_rate": 4.050283255031733e-05, + "loss": 3.6913, + "step": 580096 + }, + { + "epoch": 0.02, + "learning_rate": 4.049444660280681e-05, + "loss": 3.6976, + "step": 580608 + }, + { + "epoch": 0.02, + "learning_rate": 4.048606065529629e-05, + "loss": 3.6867, + "step": 581120 + }, + { + "epoch": 0.02, + "learning_rate": 4.04776910865895e-05, + "loss": 3.682, + "step": 581632 + }, + { + "epoch": 0.02, + "learning_rate": 4.046930513907898e-05, + "loss": 3.7015, + "step": 582144 + }, + { + "epoch": 0.02, + "learning_rate": 4.046091919156846e-05, + "loss": 3.698, + "step": 582656 + }, + { + "epoch": 0.02, + "learning_rate": 4.0452549622861666e-05, + "loss": 3.6949, + "step": 583168 + }, + { + "epoch": 0.02, + "learning_rate": 4.0444163675351146e-05, + "loss": 3.6813, + "step": 583680 + }, + { + "epoch": 0.02, + "learning_rate": 4.0435777727840626e-05, + "loss": 3.6895, + "step": 584192 + }, + { + "epoch": 0.02, + "learning_rate": 4.0427391780330106e-05, + "loss": 3.6845, + "step": 584704 + }, + { + "epoch": 0.02, + "learning_rate": 4.041902221162332e-05, + "loss": 3.695, + "step": 585216 + }, + { + "epoch": 0.02, + "learning_rate": 4.04106362641128e-05, + "loss": 3.6998, + "step": 585728 + }, + { + "epoch": 0.02, + "learning_rate": 4.040225031660228e-05, + "loss": 3.691, + "step": 586240 + }, + { + "epoch": 0.02, + "learning_rate": 4.039386436909176e-05, + "loss": 3.6857, + "step": 586752 + }, + { + "epoch": 0.02, + "learning_rate": 4.038549480038497e-05, + "loss": 3.6827, + "step": 587264 + }, + { + "epoch": 0.02, + "learning_rate": 4.037710885287445e-05, + "loss": 3.6737, + "step": 587776 + }, + { + "epoch": 0.02, + "learning_rate": 4.036873928416766e-05, + "loss": 3.6887, + "step": 588288 + }, + { + "epoch": 0.02, + "learning_rate": 4.036035333665714e-05, + "loss": 3.6772, + "step": 588800 + }, + { + "epoch": 0.02, + "learning_rate": 4.035196738914662e-05, + "loss": 3.694, + "step": 589312 + }, + { + "epoch": 0.02, + "learning_rate": 4.03435814416361e-05, + "loss": 3.6764, + "step": 589824 + }, + { + "epoch": 0.02, + "learning_rate": 4.033519549412558e-05, + "loss": 3.6883, + "step": 590336 + }, + { + "epoch": 0.02, + "learning_rate": 4.032680954661506e-05, + "loss": 3.6825, + "step": 590848 + }, + { + "epoch": 0.02, + "learning_rate": 4.031842359910454e-05, + "loss": 3.6903, + "step": 591360 + }, + { + "epoch": 0.02, + "learning_rate": 4.031003765159402e-05, + "loss": 3.6942, + "step": 591872 + }, + { + "epoch": 0.02, + "learning_rate": 4.0301668082887236e-05, + "loss": 3.6839, + "step": 592384 + }, + { + "epoch": 0.02, + "learning_rate": 4.029328213537671e-05, + "loss": 3.6979, + "step": 592896 + }, + { + "epoch": 0.02, + "learning_rate": 4.028489618786619e-05, + "loss": 3.7016, + "step": 593408 + }, + { + "epoch": 0.02, + "learning_rate": 4.027651024035567e-05, + "loss": 3.6913, + "step": 593920 + }, + { + "epoch": 0.02, + "learning_rate": 4.026814067164888e-05, + "loss": 3.6923, + "step": 594432 + }, + { + "epoch": 0.02, + "learning_rate": 4.025975472413836e-05, + "loss": 3.6827, + "step": 594944 + }, + { + "epoch": 0.02, + "learning_rate": 4.025136877662784e-05, + "loss": 3.6876, + "step": 595456 + }, + { + "epoch": 0.02, + "learning_rate": 4.024298282911732e-05, + "loss": 3.6863, + "step": 595968 + }, + { + "epoch": 0.02, + "learning_rate": 4.0234613260410534e-05, + "loss": 3.6933, + "step": 596480 + }, + { + "epoch": 0.02, + "learning_rate": 4.0226227312900013e-05, + "loss": 3.6761, + "step": 596992 + }, + { + "epoch": 0.02, + "learning_rate": 4.0217841365389493e-05, + "loss": 3.6945, + "step": 597504 + }, + { + "epoch": 0.02, + "learning_rate": 4.0209455417878973e-05, + "loss": 3.6908, + "step": 598016 + }, + { + "epoch": 0.02, + "learning_rate": 4.020108584917218e-05, + "loss": 3.687, + "step": 598528 + }, + { + "epoch": 0.02, + "learning_rate": 4.019269990166166e-05, + "loss": 3.6777, + "step": 599040 + }, + { + "epoch": 0.02, + "learning_rate": 4.018431395415114e-05, + "loss": 3.6907, + "step": 599552 + }, + { + "epoch": 0.02, + "learning_rate": 4.017592800664062e-05, + "loss": 3.6804, + "step": 600064 + }, + { + "epoch": 0.02, + "learning_rate": 4.016755843793383e-05, + "loss": 3.6979, + "step": 600576 + }, + { + "epoch": 0.02, + "learning_rate": 4.015917249042331e-05, + "loss": 3.6871, + "step": 601088 + }, + { + "epoch": 0.02, + "learning_rate": 4.015078654291279e-05, + "loss": 3.6917, + "step": 601600 + }, + { + "epoch": 0.02, + "learning_rate": 4.014241697420601e-05, + "loss": 3.6702, + "step": 602112 + }, + { + "epoch": 0.02, + "learning_rate": 4.013403102669549e-05, + "loss": 3.7, + "step": 602624 + }, + { + "epoch": 0.02, + "learning_rate": 4.012564507918497e-05, + "loss": 3.6826, + "step": 603136 + }, + { + "epoch": 0.02, + "learning_rate": 4.011725913167445e-05, + "loss": 3.6895, + "step": 603648 + }, + { + "epoch": 0.02, + "learning_rate": 4.0108889562967656e-05, + "loss": 3.6857, + "step": 604160 + }, + { + "epoch": 0.02, + "learning_rate": 4.0100503615457136e-05, + "loss": 3.6844, + "step": 604672 + }, + { + "epoch": 0.02, + "learning_rate": 4.0092117667946616e-05, + "loss": 3.6915, + "step": 605184 + }, + { + "epoch": 0.02, + "learning_rate": 4.0083731720436096e-05, + "loss": 3.7015, + "step": 605696 + }, + { + "epoch": 0.02, + "learning_rate": 4.0075362151729305e-05, + "loss": 3.6745, + "step": 606208 + }, + { + "epoch": 0.02, + "learning_rate": 4.0066976204218785e-05, + "loss": 3.6882, + "step": 606720 + }, + { + "epoch": 0.02, + "learning_rate": 4.0058590256708265e-05, + "loss": 3.6834, + "step": 607232 + }, + { + "epoch": 0.02, + "learning_rate": 4.0050204309197745e-05, + "loss": 3.6839, + "step": 607744 + }, + { + "epoch": 0.02, + "learning_rate": 4.004183474049096e-05, + "loss": 3.6804, + "step": 608256 + }, + { + "epoch": 0.02, + "learning_rate": 4.003346517178418e-05, + "loss": 3.692, + "step": 608768 + }, + { + "epoch": 0.02, + "learning_rate": 4.002507922427366e-05, + "loss": 3.6914, + "step": 609280 + }, + { + "epoch": 0.02, + "learning_rate": 4.001669327676313e-05, + "loss": 3.6733, + "step": 609792 + }, + { + "epoch": 0.02, + "learning_rate": 4.000830732925261e-05, + "loss": 3.6914, + "step": 610304 + }, + { + "epoch": 0.03, + "eval_loss": 3.8515453338623047, + "eval_runtime": 305.233, + "eval_samples_per_second": 1250.163, + "eval_steps_per_second": 39.069, + "step": 610560 + }, + { + "epoch": 1.0, + "learning_rate": 3.999992138174209e-05, + "loss": 3.6797, + "step": 610816 + }, + { + "epoch": 1.0, + "learning_rate": 3.999153543423157e-05, + "loss": 3.6767, + "step": 611328 + }, + { + "epoch": 1.0, + "learning_rate": 3.998314948672105e-05, + "loss": 3.6833, + "step": 611840 + }, + { + "epoch": 1.0, + "learning_rate": 3.997477991801426e-05, + "loss": 3.6786, + "step": 612352 + }, + { + "epoch": 1.0, + "learning_rate": 3.996639397050374e-05, + "loss": 3.6875, + "step": 612864 + }, + { + "epoch": 1.0, + "learning_rate": 3.995800802299322e-05, + "loss": 3.6701, + "step": 613376 + }, + { + "epoch": 1.0, + "learning_rate": 3.994963845428643e-05, + "loss": 3.686, + "step": 613888 + }, + { + "epoch": 1.0, + "learning_rate": 3.9941252506775915e-05, + "loss": 3.6731, + "step": 614400 + }, + { + "epoch": 1.0, + "learning_rate": 3.9932866559265395e-05, + "loss": 3.6834, + "step": 614912 + }, + { + "epoch": 1.0, + "learning_rate": 3.9924480611754874e-05, + "loss": 3.6778, + "step": 615424 + }, + { + "epoch": 1.0, + "learning_rate": 3.9916094664244354e-05, + "loss": 3.6792, + "step": 615936 + }, + { + "epoch": 1.0, + "learning_rate": 3.9907708716733834e-05, + "loss": 3.6893, + "step": 616448 + }, + { + "epoch": 1.0, + "learning_rate": 3.9899339148027044e-05, + "loss": 3.6779, + "step": 616960 + }, + { + "epoch": 1.0, + "learning_rate": 3.9890953200516523e-05, + "loss": 3.6801, + "step": 617472 + }, + { + "epoch": 1.0, + "learning_rate": 3.9882567253006003e-05, + "loss": 3.6793, + "step": 617984 + }, + { + "epoch": 1.0, + "learning_rate": 3.987418130549548e-05, + "loss": 3.6678, + "step": 618496 + }, + { + "epoch": 1.0, + "learning_rate": 3.986579535798496e-05, + "loss": 3.6679, + "step": 619008 + }, + { + "epoch": 1.0, + "learning_rate": 3.985740941047444e-05, + "loss": 3.6778, + "step": 619520 + }, + { + "epoch": 1.0, + "learning_rate": 3.984902346296392e-05, + "loss": 3.6741, + "step": 620032 + }, + { + "epoch": 1.0, + "learning_rate": 3.98406375154534e-05, + "loss": 3.677, + "step": 620544 + }, + { + "epoch": 1.0, + "learning_rate": 3.983226794674661e-05, + "loss": 3.6865, + "step": 621056 + }, + { + "epoch": 1.0, + "learning_rate": 3.98238819992361e-05, + "loss": 3.6822, + "step": 621568 + }, + { + "epoch": 1.0, + "learning_rate": 3.981549605172558e-05, + "loss": 3.6845, + "step": 622080 + }, + { + "epoch": 1.0, + "learning_rate": 3.980711010421506e-05, + "loss": 3.6839, + "step": 622592 + }, + { + "epoch": 1.0, + "learning_rate": 3.979874053550827e-05, + "loss": 3.6697, + "step": 623104 + }, + { + "epoch": 1.0, + "learning_rate": 3.979035458799775e-05, + "loss": 3.681, + "step": 623616 + }, + { + "epoch": 1.0, + "learning_rate": 3.978196864048723e-05, + "loss": 3.6695, + "step": 624128 + }, + { + "epoch": 1.0, + "learning_rate": 3.977358269297671e-05, + "loss": 3.6753, + "step": 624640 + }, + { + "epoch": 1.0, + "learning_rate": 3.976521312426992e-05, + "loss": 3.6716, + "step": 625152 + }, + { + "epoch": 1.0, + "learning_rate": 3.97568271767594e-05, + "loss": 3.6696, + "step": 625664 + }, + { + "epoch": 1.01, + "learning_rate": 3.974844122924888e-05, + "loss": 3.6763, + "step": 626176 + }, + { + "epoch": 1.01, + "learning_rate": 3.974005528173836e-05, + "loss": 3.6813, + "step": 626688 + }, + { + "epoch": 1.01, + "learning_rate": 3.9731685713031566e-05, + "loss": 3.6758, + "step": 627200 + }, + { + "epoch": 1.01, + "learning_rate": 3.9723299765521046e-05, + "loss": 3.6785, + "step": 627712 + }, + { + "epoch": 1.01, + "learning_rate": 3.971491381801053e-05, + "loss": 3.6692, + "step": 628224 + }, + { + "epoch": 1.01, + "learning_rate": 3.970654424930374e-05, + "loss": 3.6839, + "step": 628736 + }, + { + "epoch": 1.01, + "learning_rate": 3.969815830179322e-05, + "loss": 3.6758, + "step": 629248 + }, + { + "epoch": 1.01, + "learning_rate": 3.96897723542827e-05, + "loss": 3.6633, + "step": 629760 + }, + { + "epoch": 1.01, + "learning_rate": 3.968138640677218e-05, + "loss": 3.6658, + "step": 630272 + }, + { + "epoch": 1.01, + "learning_rate": 3.967301683806539e-05, + "loss": 3.6647, + "step": 630784 + }, + { + "epoch": 1.01, + "learning_rate": 3.966463089055487e-05, + "loss": 3.6735, + "step": 631296 + }, + { + "epoch": 1.01, + "learning_rate": 3.965624494304435e-05, + "loss": 3.6752, + "step": 631808 + }, + { + "epoch": 1.01, + "learning_rate": 3.964785899553383e-05, + "loss": 3.6754, + "step": 632320 + }, + { + "epoch": 1.01, + "learning_rate": 3.963948942682704e-05, + "loss": 3.6746, + "step": 632832 + }, + { + "epoch": 1.01, + "learning_rate": 3.963110347931652e-05, + "loss": 3.6811, + "step": 633344 + }, + { + "epoch": 1.01, + "learning_rate": 3.9622717531806e-05, + "loss": 3.6746, + "step": 633856 + }, + { + "epoch": 1.01, + "learning_rate": 3.9614331584295486e-05, + "loss": 3.6787, + "step": 634368 + }, + { + "epoch": 1.01, + "learning_rate": 3.9605978394392425e-05, + "loss": 3.6704, + "step": 634880 + }, + { + "epoch": 1.01, + "learning_rate": 3.9597592446881905e-05, + "loss": 3.6444, + "step": 635392 + }, + { + "epoch": 1.01, + "learning_rate": 3.9589206499371384e-05, + "loss": 3.6898, + "step": 635904 + }, + { + "epoch": 1.01, + "learning_rate": 3.9580820551860864e-05, + "loss": 3.6677, + "step": 636416 + }, + { + "epoch": 1.01, + "learning_rate": 3.9572434604350344e-05, + "loss": 3.6703, + "step": 636928 + }, + { + "epoch": 1.01, + "learning_rate": 3.9564048656839824e-05, + "loss": 3.6677, + "step": 637440 + }, + { + "epoch": 1.01, + "learning_rate": 3.9555662709329304e-05, + "loss": 3.6638, + "step": 637952 + }, + { + "epoch": 1.01, + "learning_rate": 3.954729314062251e-05, + "loss": 3.659, + "step": 638464 + }, + { + "epoch": 1.01, + "learning_rate": 3.953890719311199e-05, + "loss": 3.6604, + "step": 638976 + }, + { + "epoch": 1.01, + "learning_rate": 3.953052124560147e-05, + "loss": 3.6699, + "step": 639488 + }, + { + "epoch": 1.01, + "learning_rate": 3.952213529809095e-05, + "loss": 3.6618, + "step": 640000 + }, + { + "epoch": 1.01, + "learning_rate": 3.951374935058043e-05, + "loss": 3.6812, + "step": 640512 + }, + { + "epoch": 1.01, + "learning_rate": 3.950536340306991e-05, + "loss": 3.6634, + "step": 641024 + }, + { + "epoch": 1.01, + "learning_rate": 3.949697745555939e-05, + "loss": 3.6578, + "step": 641536 + }, + { + "epoch": 1.01, + "learning_rate": 3.948859150804887e-05, + "loss": 3.6778, + "step": 642048 + }, + { + "epoch": 1.01, + "learning_rate": 3.948022193934208e-05, + "loss": 3.6565, + "step": 642560 + }, + { + "epoch": 1.01, + "learning_rate": 3.947183599183156e-05, + "loss": 3.659, + "step": 643072 + }, + { + "epoch": 1.01, + "learning_rate": 3.946345004432104e-05, + "loss": 3.6723, + "step": 643584 + }, + { + "epoch": 1.01, + "learning_rate": 3.945506409681052e-05, + "loss": 3.6736, + "step": 644096 + }, + { + "epoch": 1.01, + "learning_rate": 3.944669452810373e-05, + "loss": 3.6584, + "step": 644608 + }, + { + "epoch": 1.01, + "learning_rate": 3.943830858059321e-05, + "loss": 3.6575, + "step": 645120 + }, + { + "epoch": 1.01, + "learning_rate": 3.942992263308269e-05, + "loss": 3.6501, + "step": 645632 + }, + { + "epoch": 1.01, + "learning_rate": 3.942155306437591e-05, + "loss": 3.6632, + "step": 646144 + }, + { + "epoch": 1.01, + "learning_rate": 3.941316711686539e-05, + "loss": 3.6788, + "step": 646656 + }, + { + "epoch": 1.01, + "learning_rate": 3.940478116935487e-05, + "loss": 3.6644, + "step": 647168 + }, + { + "epoch": 1.01, + "learning_rate": 3.939639522184435e-05, + "loss": 3.6696, + "step": 647680 + }, + { + "epoch": 1.01, + "learning_rate": 3.9388025653137556e-05, + "loss": 3.6726, + "step": 648192 + }, + { + "epoch": 1.01, + "learning_rate": 3.9379639705627036e-05, + "loss": 3.6787, + "step": 648704 + }, + { + "epoch": 1.01, + "learning_rate": 3.9371253758116516e-05, + "loss": 3.6592, + "step": 649216 + }, + { + "epoch": 1.01, + "learning_rate": 3.936288418940973e-05, + "loss": 3.6742, + "step": 649728 + }, + { + "epoch": 1.01, + "learning_rate": 3.9354498241899205e-05, + "loss": 3.6612, + "step": 650240 + }, + { + "epoch": 1.01, + "learning_rate": 3.9346112294388685e-05, + "loss": 3.6637, + "step": 650752 + }, + { + "epoch": 1.01, + "learning_rate": 3.9337726346878165e-05, + "loss": 3.6641, + "step": 651264 + }, + { + "epoch": 1.01, + "learning_rate": 3.9329340399367645e-05, + "loss": 3.6732, + "step": 651776 + }, + { + "epoch": 1.01, + "learning_rate": 3.932095445185713e-05, + "loss": 3.667, + "step": 652288 + }, + { + "epoch": 1.01, + "learning_rate": 3.931256850434661e-05, + "loss": 3.6745, + "step": 652800 + }, + { + "epoch": 1.01, + "learning_rate": 3.930418255683609e-05, + "loss": 3.66, + "step": 653312 + }, + { + "epoch": 1.01, + "learning_rate": 3.92958129881293e-05, + "loss": 3.6597, + "step": 653824 + }, + { + "epoch": 1.01, + "learning_rate": 3.928742704061878e-05, + "loss": 3.6686, + "step": 654336 + }, + { + "epoch": 1.01, + "learning_rate": 3.927904109310826e-05, + "loss": 3.6643, + "step": 654848 + }, + { + "epoch": 1.01, + "learning_rate": 3.927067152440147e-05, + "loss": 3.6556, + "step": 655360 + }, + { + "epoch": 1.01, + "learning_rate": 3.926228557689095e-05, + "loss": 3.6649, + "step": 655872 + }, + { + "epoch": 1.02, + "learning_rate": 3.925389962938043e-05, + "loss": 3.6633, + "step": 656384 + }, + { + "epoch": 1.02, + "learning_rate": 3.924551368186991e-05, + "loss": 3.6722, + "step": 656896 + }, + { + "epoch": 1.02, + "learning_rate": 3.923714411316312e-05, + "loss": 3.6584, + "step": 657408 + }, + { + "epoch": 1.02, + "learning_rate": 3.92287581656526e-05, + "loss": 3.6545, + "step": 657920 + }, + { + "epoch": 1.02, + "learning_rate": 3.9220372218142085e-05, + "loss": 3.6757, + "step": 658432 + }, + { + "epoch": 1.02, + "learning_rate": 3.9211986270631565e-05, + "loss": 3.6667, + "step": 658944 + }, + { + "epoch": 1.02, + "learning_rate": 3.9203616701924774e-05, + "loss": 3.6662, + "step": 659456 + }, + { + "epoch": 1.02, + "learning_rate": 3.9195230754414254e-05, + "loss": 3.6557, + "step": 659968 + }, + { + "epoch": 1.02, + "learning_rate": 3.9186844806903734e-05, + "loss": 3.6593, + "step": 660480 + }, + { + "epoch": 1.02, + "learning_rate": 3.9178458859393214e-05, + "loss": 3.6578, + "step": 660992 + }, + { + "epoch": 1.02, + "learning_rate": 3.917008929068642e-05, + "loss": 3.6674, + "step": 661504 + }, + { + "epoch": 1.02, + "learning_rate": 3.91617033431759e-05, + "loss": 3.6715, + "step": 662016 + }, + { + "epoch": 1.02, + "learning_rate": 3.915331739566538e-05, + "loss": 3.6639, + "step": 662528 + }, + { + "epoch": 1.02, + "learning_rate": 3.914493144815486e-05, + "loss": 3.6576, + "step": 663040 + }, + { + "epoch": 1.02, + "learning_rate": 3.913656187944807e-05, + "loss": 3.6503, + "step": 663552 + }, + { + "epoch": 1.02, + "learning_rate": 3.912817593193755e-05, + "loss": 3.6537, + "step": 664064 + }, + { + "epoch": 1.02, + "learning_rate": 3.911980636323077e-05, + "loss": 3.6575, + "step": 664576 + }, + { + "epoch": 1.02, + "learning_rate": 3.911142041572025e-05, + "loss": 3.65, + "step": 665088 + }, + { + "epoch": 1.02, + "learning_rate": 3.910303446820973e-05, + "loss": 3.6674, + "step": 665600 + }, + { + "epoch": 1.02, + "learning_rate": 3.909464852069921e-05, + "loss": 3.6516, + "step": 666112 + }, + { + "epoch": 1.02, + "learning_rate": 3.908626257318869e-05, + "loss": 3.6572, + "step": 666624 + }, + { + "epoch": 1.02, + "learning_rate": 3.90778930044819e-05, + "loss": 3.6526, + "step": 667136 + }, + { + "epoch": 1.02, + "learning_rate": 3.906950705697138e-05, + "loss": 3.6641, + "step": 667648 + }, + { + "epoch": 1.02, + "learning_rate": 3.906112110946086e-05, + "loss": 3.6655, + "step": 668160 + }, + { + "epoch": 1.02, + "learning_rate": 3.905273516195034e-05, + "loss": 3.6546, + "step": 668672 + }, + { + "epoch": 1.02, + "learning_rate": 3.904434921443982e-05, + "loss": 3.6709, + "step": 669184 + }, + { + "epoch": 1.02, + "learning_rate": 3.9035963266929297e-05, + "loss": 3.676, + "step": 669696 + }, + { + "epoch": 1.02, + "learning_rate": 3.9027577319418777e-05, + "loss": 3.6634, + "step": 670208 + }, + { + "epoch": 1.02, + "learning_rate": 3.901920775071199e-05, + "loss": 3.6634, + "step": 670720 + }, + { + "epoch": 1.02, + "learning_rate": 3.901082180320147e-05, + "loss": 3.6565, + "step": 671232 + }, + { + "epoch": 1.02, + "learning_rate": 3.900243585569095e-05, + "loss": 3.6555, + "step": 671744 + }, + { + "epoch": 1.02, + "learning_rate": 3.899406628698416e-05, + "loss": 3.6645, + "step": 672256 + }, + { + "epoch": 1.02, + "learning_rate": 3.898568033947364e-05, + "loss": 3.663, + "step": 672768 + }, + { + "epoch": 1.02, + "learning_rate": 3.897729439196312e-05, + "loss": 3.6493, + "step": 673280 + }, + { + "epoch": 1.02, + "learning_rate": 3.89689084444526e-05, + "loss": 3.6687, + "step": 673792 + }, + { + "epoch": 1.02, + "learning_rate": 3.896052249694208e-05, + "loss": 3.6663, + "step": 674304 + }, + { + "epoch": 1.02, + "learning_rate": 3.895213654943156e-05, + "loss": 3.6601, + "step": 674816 + }, + { + "epoch": 1.02, + "learning_rate": 3.8943750601921034e-05, + "loss": 3.6529, + "step": 675328 + }, + { + "epoch": 1.02, + "learning_rate": 3.8935364654410514e-05, + "loss": 3.659, + "step": 675840 + }, + { + "epoch": 1.02, + "learning_rate": 3.892699508570373e-05, + "loss": 3.6518, + "step": 676352 + }, + { + "epoch": 1.02, + "learning_rate": 3.891860913819321e-05, + "loss": 3.6692, + "step": 676864 + }, + { + "epoch": 1.02, + "learning_rate": 3.891022319068269e-05, + "loss": 3.6585, + "step": 677376 + }, + { + "epoch": 1.02, + "learning_rate": 3.890183724317217e-05, + "loss": 3.6679, + "step": 677888 + }, + { + "epoch": 1.02, + "learning_rate": 3.8893467674465386e-05, + "loss": 3.6435, + "step": 678400 + }, + { + "epoch": 1.02, + "learning_rate": 3.8885081726954866e-05, + "loss": 3.6717, + "step": 678912 + }, + { + "epoch": 1.02, + "learning_rate": 3.887669577944434e-05, + "loss": 3.6536, + "step": 679424 + }, + { + "epoch": 1.02, + "learning_rate": 3.8868326210737555e-05, + "loss": 3.6662, + "step": 679936 + }, + { + "epoch": 1.02, + "learning_rate": 3.8859940263227035e-05, + "loss": 3.6614, + "step": 680448 + }, + { + "epoch": 1.02, + "learning_rate": 3.885155431571651e-05, + "loss": 3.6531, + "step": 680960 + }, + { + "epoch": 1.02, + "learning_rate": 3.884316836820599e-05, + "loss": 3.6637, + "step": 681472 + }, + { + "epoch": 1.02, + "learning_rate": 3.8834798799499204e-05, + "loss": 3.6758, + "step": 681984 + }, + { + "epoch": 1.02, + "learning_rate": 3.8826412851988684e-05, + "loss": 3.6464, + "step": 682496 + }, + { + "epoch": 1.02, + "learning_rate": 3.8818026904478164e-05, + "loss": 3.6625, + "step": 683008 + }, + { + "epoch": 1.02, + "learning_rate": 3.8809640956967644e-05, + "loss": 3.6557, + "step": 683520 + }, + { + "epoch": 1.02, + "learning_rate": 3.880127138826086e-05, + "loss": 3.6563, + "step": 684032 + }, + { + "epoch": 1.02, + "learning_rate": 3.879288544075034e-05, + "loss": 3.657, + "step": 684544 + }, + { + "epoch": 1.02, + "learning_rate": 3.878451587204355e-05, + "loss": 3.6627, + "step": 685056 + }, + { + "epoch": 1.02, + "learning_rate": 3.877612992453303e-05, + "loss": 3.6658, + "step": 685568 + }, + { + "epoch": 1.02, + "learning_rate": 3.876774397702251e-05, + "loss": 3.6536, + "step": 686080 + }, + { + "epoch": 1.02, + "learning_rate": 3.875935802951198e-05, + "loss": 3.663, + "step": 686592 + }, + { + "epoch": 1.03, + "eval_loss": 3.8471899032592773, + "eval_runtime": 305.6564, + "eval_samples_per_second": 1248.431, + "eval_steps_per_second": 39.014, + "step": 686880 + }, + { + "epoch": 0.0, + "learning_rate": 3.875097208200146e-05, + "loss": 3.6452, + "step": 687104 + }, + { + "epoch": 0.0, + "learning_rate": 3.874258613449094e-05, + "loss": 3.651, + "step": 687616 + }, + { + "epoch": 0.0, + "learning_rate": 3.873420018698042e-05, + "loss": 3.6584, + "step": 688128 + }, + { + "epoch": 0.0, + "learning_rate": 3.87258142394699e-05, + "loss": 3.6543, + "step": 688640 + }, + { + "epoch": 0.0, + "learning_rate": 3.871742829195938e-05, + "loss": 3.6603, + "step": 689152 + }, + { + "epoch": 0.0, + "learning_rate": 3.87090587232526e-05, + "loss": 3.6456, + "step": 689664 + }, + { + "epoch": 0.0, + "learning_rate": 3.870067277574208e-05, + "loss": 3.6595, + "step": 690176 + }, + { + "epoch": 0.0, + "learning_rate": 3.869228682823156e-05, + "loss": 3.647, + "step": 690688 + }, + { + "epoch": 0.0, + "learning_rate": 3.868390088072104e-05, + "loss": 3.6516, + "step": 691200 + }, + { + "epoch": 0.0, + "learning_rate": 3.867551493321052e-05, + "loss": 3.6542, + "step": 691712 + }, + { + "epoch": 0.0, + "learning_rate": 3.8667145364503726e-05, + "loss": 3.6511, + "step": 692224 + }, + { + "epoch": 0.0, + "learning_rate": 3.8658759416993206e-05, + "loss": 3.6591, + "step": 692736 + }, + { + "epoch": 0.0, + "learning_rate": 3.8650373469482686e-05, + "loss": 3.6636, + "step": 693248 + }, + { + "epoch": 0.0, + "learning_rate": 3.8641987521972166e-05, + "loss": 3.6477, + "step": 693760 + }, + { + "epoch": 0.0, + "learning_rate": 3.8633601574461646e-05, + "loss": 3.6532, + "step": 694272 + }, + { + "epoch": 0.0, + "learning_rate": 3.8625215626951126e-05, + "loss": 3.6432, + "step": 694784 + }, + { + "epoch": 0.0, + "learning_rate": 3.8616846058244335e-05, + "loss": 3.6406, + "step": 695296 + }, + { + "epoch": 0.0, + "learning_rate": 3.8608460110733815e-05, + "loss": 3.654, + "step": 695808 + }, + { + "epoch": 0.0, + "learning_rate": 3.86000741632233e-05, + "loss": 3.645, + "step": 696320 + }, + { + "epoch": 0.0, + "learning_rate": 3.859168821571278e-05, + "loss": 3.6511, + "step": 696832 + }, + { + "epoch": 0.0, + "learning_rate": 3.858330226820226e-05, + "loss": 3.6621, + "step": 697344 + }, + { + "epoch": 0.0, + "learning_rate": 3.857491632069174e-05, + "loss": 3.6589, + "step": 697856 + }, + { + "epoch": 0.0, + "learning_rate": 3.856654675198495e-05, + "loss": 3.6593, + "step": 698368 + }, + { + "epoch": 0.0, + "learning_rate": 3.855816080447443e-05, + "loss": 3.6569, + "step": 698880 + }, + { + "epoch": 0.0, + "learning_rate": 3.854977485696391e-05, + "loss": 3.644, + "step": 699392 + }, + { + "epoch": 0.0, + "learning_rate": 3.854138890945339e-05, + "loss": 3.6533, + "step": 699904 + }, + { + "epoch": 0.0, + "learning_rate": 3.853300296194287e-05, + "loss": 3.6455, + "step": 700416 + }, + { + "epoch": 0.0, + "learning_rate": 3.8524617014432344e-05, + "loss": 3.6516, + "step": 700928 + }, + { + "epoch": 0.0, + "learning_rate": 3.8516231066921824e-05, + "loss": 3.6412, + "step": 701440 + }, + { + "epoch": 0.0, + "learning_rate": 3.8507845119411304e-05, + "loss": 3.646, + "step": 701952 + }, + { + "epoch": 0.01, + "learning_rate": 3.849947555070452e-05, + "loss": 3.6487, + "step": 702464 + }, + { + "epoch": 0.01, + "learning_rate": 3.8491105981997736e-05, + "loss": 3.6546, + "step": 702976 + }, + { + "epoch": 0.01, + "learning_rate": 3.8482720034487216e-05, + "loss": 3.6528, + "step": 703488 + }, + { + "epoch": 0.01, + "learning_rate": 3.8474334086976695e-05, + "loss": 3.651, + "step": 704000 + }, + { + "epoch": 0.01, + "learning_rate": 3.846594813946617e-05, + "loss": 3.645, + "step": 704512 + }, + { + "epoch": 0.01, + "learning_rate": 3.845756219195565e-05, + "loss": 3.6545, + "step": 705024 + }, + { + "epoch": 0.01, + "learning_rate": 3.844917624444513e-05, + "loss": 3.6537, + "step": 705536 + }, + { + "epoch": 0.01, + "learning_rate": 3.8440806675738344e-05, + "loss": 3.6405, + "step": 706048 + }, + { + "epoch": 0.01, + "learning_rate": 3.843242072822782e-05, + "loss": 3.6421, + "step": 706560 + }, + { + "epoch": 0.01, + "learning_rate": 3.84240347807173e-05, + "loss": 3.6389, + "step": 707072 + }, + { + "epoch": 0.01, + "learning_rate": 3.841564883320678e-05, + "loss": 3.6422, + "step": 707584 + }, + { + "epoch": 0.01, + "learning_rate": 3.840726288569626e-05, + "loss": 3.6483, + "step": 708096 + }, + { + "epoch": 0.01, + "learning_rate": 3.839887693818574e-05, + "loss": 3.6527, + "step": 708608 + }, + { + "epoch": 0.01, + "learning_rate": 3.8390490990675224e-05, + "loss": 3.6494, + "step": 709120 + }, + { + "epoch": 0.01, + "learning_rate": 3.8382105043164704e-05, + "loss": 3.6526, + "step": 709632 + }, + { + "epoch": 0.01, + "learning_rate": 3.837373547445791e-05, + "loss": 3.6528, + "step": 710144 + }, + { + "epoch": 0.01, + "learning_rate": 3.836534952694739e-05, + "loss": 3.6525, + "step": 710656 + }, + { + "epoch": 0.01, + "learning_rate": 3.835696357943687e-05, + "loss": 3.6433, + "step": 711168 + }, + { + "epoch": 0.01, + "learning_rate": 3.834859401073008e-05, + "loss": 3.6224, + "step": 711680 + }, + { + "epoch": 0.01, + "learning_rate": 3.834020806321956e-05, + "loss": 3.6617, + "step": 712192 + }, + { + "epoch": 0.01, + "learning_rate": 3.833182211570904e-05, + "loss": 3.6418, + "step": 712704 + }, + { + "epoch": 0.01, + "learning_rate": 3.832343616819852e-05, + "loss": 3.6456, + "step": 713216 + }, + { + "epoch": 0.01, + "learning_rate": 3.8315050220688e-05, + "loss": 3.6454, + "step": 713728 + }, + { + "epoch": 0.01, + "learning_rate": 3.830666427317748e-05, + "loss": 3.6386, + "step": 714240 + }, + { + "epoch": 0.01, + "learning_rate": 3.829827832566696e-05, + "loss": 3.6341, + "step": 714752 + }, + { + "epoch": 0.01, + "learning_rate": 3.828990875696017e-05, + "loss": 3.6355, + "step": 715264 + }, + { + "epoch": 0.01, + "learning_rate": 3.828152280944966e-05, + "loss": 3.6449, + "step": 715776 + }, + { + "epoch": 0.01, + "learning_rate": 3.827313686193914e-05, + "loss": 3.6365, + "step": 716288 + }, + { + "epoch": 0.01, + "learning_rate": 3.826475091442862e-05, + "loss": 3.6555, + "step": 716800 + }, + { + "epoch": 0.01, + "learning_rate": 3.825638134572183e-05, + "loss": 3.638, + "step": 717312 + }, + { + "epoch": 0.01, + "learning_rate": 3.824799539821131e-05, + "loss": 3.628, + "step": 717824 + }, + { + "epoch": 0.01, + "learning_rate": 3.823960945070079e-05, + "loss": 3.6545, + "step": 718336 + }, + { + "epoch": 0.01, + "learning_rate": 3.823122350319027e-05, + "loss": 3.6363, + "step": 718848 + }, + { + "epoch": 0.01, + "learning_rate": 3.8222853934483476e-05, + "loss": 3.6325, + "step": 719360 + }, + { + "epoch": 0.01, + "learning_rate": 3.8214467986972956e-05, + "loss": 3.6471, + "step": 719872 + }, + { + "epoch": 0.01, + "learning_rate": 3.8206082039462436e-05, + "loss": 3.6507, + "step": 720384 + }, + { + "epoch": 0.01, + "learning_rate": 3.8197696091951916e-05, + "loss": 3.6319, + "step": 720896 + }, + { + "epoch": 0.01, + "learning_rate": 3.8189326523245125e-05, + "loss": 3.6304, + "step": 721408 + }, + { + "epoch": 0.01, + "learning_rate": 3.818094057573461e-05, + "loss": 3.6263, + "step": 721920 + }, + { + "epoch": 0.01, + "learning_rate": 3.817255462822409e-05, + "loss": 3.6402, + "step": 722432 + }, + { + "epoch": 0.01, + "learning_rate": 3.816416868071357e-05, + "loss": 3.6508, + "step": 722944 + }, + { + "epoch": 0.01, + "learning_rate": 3.815579911200678e-05, + "loss": 3.6408, + "step": 723456 + }, + { + "epoch": 0.01, + "learning_rate": 3.814741316449626e-05, + "loss": 3.6452, + "step": 723968 + }, + { + "epoch": 0.01, + "learning_rate": 3.813904359578947e-05, + "loss": 3.6435, + "step": 724480 + }, + { + "epoch": 0.01, + "learning_rate": 3.813065764827895e-05, + "loss": 3.6516, + "step": 724992 + }, + { + "epoch": 0.01, + "learning_rate": 3.812227170076843e-05, + "loss": 3.6378, + "step": 725504 + }, + { + "epoch": 0.01, + "learning_rate": 3.811388575325791e-05, + "loss": 3.6511, + "step": 726016 + }, + { + "epoch": 0.01, + "learning_rate": 3.810549980574739e-05, + "loss": 3.6315, + "step": 726528 + }, + { + "epoch": 0.01, + "learning_rate": 3.809711385823687e-05, + "loss": 3.6395, + "step": 727040 + }, + { + "epoch": 0.01, + "learning_rate": 3.808872791072635e-05, + "loss": 3.6392, + "step": 727552 + }, + { + "epoch": 0.01, + "learning_rate": 3.808034196321583e-05, + "loss": 3.6449, + "step": 728064 + }, + { + "epoch": 0.01, + "learning_rate": 3.8071988773312774e-05, + "loss": 3.6453, + "step": 728576 + }, + { + "epoch": 0.01, + "learning_rate": 3.8063602825802254e-05, + "loss": 3.6486, + "step": 729088 + }, + { + "epoch": 0.01, + "learning_rate": 3.8055216878291734e-05, + "loss": 3.6363, + "step": 729600 + }, + { + "epoch": 0.01, + "learning_rate": 3.8046830930781214e-05, + "loss": 3.6351, + "step": 730112 + }, + { + "epoch": 0.01, + "learning_rate": 3.8038444983270694e-05, + "loss": 3.6416, + "step": 730624 + }, + { + "epoch": 0.01, + "learning_rate": 3.8030059035760174e-05, + "loss": 3.647, + "step": 731136 + }, + { + "epoch": 0.01, + "learning_rate": 3.8021673088249654e-05, + "loss": 3.6309, + "step": 731648 + }, + { + "epoch": 0.01, + "learning_rate": 3.801328714073913e-05, + "loss": 3.6373, + "step": 732160 + }, + { + "epoch": 0.02, + "learning_rate": 3.800491757203234e-05, + "loss": 3.641, + "step": 732672 + }, + { + "epoch": 0.02, + "learning_rate": 3.799653162452182e-05, + "loss": 3.6436, + "step": 733184 + }, + { + "epoch": 0.02, + "learning_rate": 3.79881456770113e-05, + "loss": 3.638, + "step": 733696 + }, + { + "epoch": 0.02, + "learning_rate": 3.797975972950078e-05, + "loss": 3.6301, + "step": 734208 + }, + { + "epoch": 0.02, + "learning_rate": 3.7971390160794e-05, + "loss": 3.6468, + "step": 734720 + }, + { + "epoch": 0.02, + "learning_rate": 3.796300421328348e-05, + "loss": 3.6447, + "step": 735232 + }, + { + "epoch": 0.02, + "learning_rate": 3.795461826577295e-05, + "loss": 3.6435, + "step": 735744 + }, + { + "epoch": 0.02, + "learning_rate": 3.794623231826243e-05, + "loss": 3.6309, + "step": 736256 + }, + { + "epoch": 0.02, + "learning_rate": 3.793784637075191e-05, + "loss": 3.6364, + "step": 736768 + }, + { + "epoch": 0.02, + "learning_rate": 3.792946042324139e-05, + "loss": 3.6324, + "step": 737280 + }, + { + "epoch": 0.02, + "learning_rate": 3.792107447573087e-05, + "loss": 3.6455, + "step": 737792 + }, + { + "epoch": 0.02, + "learning_rate": 3.791270490702408e-05, + "loss": 3.6452, + "step": 738304 + }, + { + "epoch": 0.02, + "learning_rate": 3.790431895951356e-05, + "loss": 3.6357, + "step": 738816 + }, + { + "epoch": 0.02, + "learning_rate": 3.789593301200304e-05, + "loss": 3.6381, + "step": 739328 + }, + { + "epoch": 0.02, + "learning_rate": 3.788754706449252e-05, + "loss": 3.625, + "step": 739840 + }, + { + "epoch": 0.02, + "learning_rate": 3.7879177495785737e-05, + "loss": 3.6326, + "step": 740352 + }, + { + "epoch": 0.02, + "learning_rate": 3.787080792707895e-05, + "loss": 3.6295, + "step": 740864 + }, + { + "epoch": 0.02, + "learning_rate": 3.7862421979568426e-05, + "loss": 3.6282, + "step": 741376 + }, + { + "epoch": 0.02, + "learning_rate": 3.7854036032057906e-05, + "loss": 3.6388, + "step": 741888 + }, + { + "epoch": 0.02, + "learning_rate": 3.7845650084547386e-05, + "loss": 3.6291, + "step": 742400 + }, + { + "epoch": 0.02, + "learning_rate": 3.7837264137036865e-05, + "loss": 3.6307, + "step": 742912 + }, + { + "epoch": 0.02, + "learning_rate": 3.7828878189526345e-05, + "loss": 3.6323, + "step": 743424 + }, + { + "epoch": 0.02, + "learning_rate": 3.7820492242015825e-05, + "loss": 3.6323, + "step": 743936 + }, + { + "epoch": 0.02, + "learning_rate": 3.7812106294505305e-05, + "loss": 3.6433, + "step": 744448 + }, + { + "epoch": 0.02, + "learning_rate": 3.7803736725798514e-05, + "loss": 3.6323, + "step": 744960 + }, + { + "epoch": 0.02, + "learning_rate": 3.7795350778287994e-05, + "loss": 3.6479, + "step": 745472 + }, + { + "epoch": 0.02, + "learning_rate": 3.778698120958121e-05, + "loss": 3.6506, + "step": 745984 + }, + { + "epoch": 0.02, + "learning_rate": 3.777859526207069e-05, + "loss": 3.6414, + "step": 746496 + }, + { + "epoch": 0.02, + "learning_rate": 3.777020931456017e-05, + "loss": 3.6345, + "step": 747008 + }, + { + "epoch": 0.02, + "learning_rate": 3.776182336704965e-05, + "loss": 3.6354, + "step": 747520 + }, + { + "epoch": 0.02, + "learning_rate": 3.775343741953913e-05, + "loss": 3.6342, + "step": 748032 + }, + { + "epoch": 0.02, + "learning_rate": 3.774505147202861e-05, + "loss": 3.6398, + "step": 748544 + }, + { + "epoch": 0.02, + "learning_rate": 3.773666552451809e-05, + "loss": 3.6366, + "step": 749056 + }, + { + "epoch": 0.02, + "learning_rate": 3.772827957700757e-05, + "loss": 3.6266, + "step": 749568 + }, + { + "epoch": 0.02, + "learning_rate": 3.771991000830078e-05, + "loss": 3.6458, + "step": 750080 + }, + { + "epoch": 0.02, + "learning_rate": 3.771152406079026e-05, + "loss": 3.6446, + "step": 750592 + }, + { + "epoch": 0.02, + "learning_rate": 3.770313811327974e-05, + "loss": 3.6303, + "step": 751104 + }, + { + "epoch": 0.02, + "learning_rate": 3.769475216576922e-05, + "loss": 3.6295, + "step": 751616 + }, + { + "epoch": 0.02, + "learning_rate": 3.768638259706243e-05, + "loss": 3.639, + "step": 752128 + }, + { + "epoch": 0.02, + "learning_rate": 3.7678013028355644e-05, + "loss": 3.6265, + "step": 752640 + }, + { + "epoch": 0.02, + "learning_rate": 3.7669627080845124e-05, + "loss": 3.6489, + "step": 753152 + }, + { + "epoch": 0.02, + "learning_rate": 3.7661241133334604e-05, + "loss": 3.6328, + "step": 753664 + }, + { + "epoch": 0.02, + "learning_rate": 3.7652855185824084e-05, + "loss": 3.6455, + "step": 754176 + }, + { + "epoch": 0.02, + "learning_rate": 3.7644469238313564e-05, + "loss": 3.6201, + "step": 754688 + }, + { + "epoch": 0.02, + "learning_rate": 3.7636083290803044e-05, + "loss": 3.6431, + "step": 755200 + }, + { + "epoch": 0.02, + "learning_rate": 3.7627697343292524e-05, + "loss": 3.6361, + "step": 755712 + }, + { + "epoch": 0.02, + "learning_rate": 3.761932777458573e-05, + "loss": 3.6358, + "step": 756224 + }, + { + "epoch": 0.02, + "learning_rate": 3.761094182707521e-05, + "loss": 3.6395, + "step": 756736 + }, + { + "epoch": 0.02, + "learning_rate": 3.760255587956469e-05, + "loss": 3.6268, + "step": 757248 + }, + { + "epoch": 0.02, + "learning_rate": 3.759416993205417e-05, + "loss": 3.6382, + "step": 757760 + }, + { + "epoch": 0.02, + "learning_rate": 3.758578398454365e-05, + "loss": 3.6564, + "step": 758272 + }, + { + "epoch": 0.02, + "learning_rate": 3.757739803703313e-05, + "loss": 3.6218, + "step": 758784 + }, + { + "epoch": 0.02, + "learning_rate": 3.756902846832634e-05, + "loss": 3.6383, + "step": 759296 + }, + { + "epoch": 0.02, + "learning_rate": 3.756064252081583e-05, + "loss": 3.6325, + "step": 759808 + }, + { + "epoch": 0.02, + "learning_rate": 3.755225657330531e-05, + "loss": 3.6279, + "step": 760320 + }, + { + "epoch": 0.02, + "learning_rate": 3.754387062579479e-05, + "loss": 3.6335, + "step": 760832 + }, + { + "epoch": 0.02, + "learning_rate": 3.753548467828426e-05, + "loss": 3.6392, + "step": 761344 + }, + { + "epoch": 0.02, + "learning_rate": 3.752709873077374e-05, + "loss": 3.6404, + "step": 761856 + }, + { + "epoch": 0.02, + "learning_rate": 3.751871278326322e-05, + "loss": 3.6322, + "step": 762368 + }, + { + "epoch": 0.02, + "learning_rate": 3.751034321455644e-05, + "loss": 3.6364, + "step": 762880 + }, + { + "epoch": 0.03, + "eval_loss": 3.8442981243133545, + "eval_runtime": 304.1689, + "eval_samples_per_second": 1254.537, + "eval_steps_per_second": 39.205, + "step": 763200 + }, + { + "epoch": 1.0, + "learning_rate": 3.750195726704591e-05, + "loss": 3.6256, + "step": 763392 + }, + { + "epoch": 1.0, + "learning_rate": 3.749357131953539e-05, + "loss": 3.6278, + "step": 763904 + }, + { + "epoch": 1.0, + "learning_rate": 3.748518537202487e-05, + "loss": 3.6351, + "step": 764416 + }, + { + "epoch": 1.0, + "learning_rate": 3.747679942451435e-05, + "loss": 3.6317, + "step": 764928 + }, + { + "epoch": 1.0, + "learning_rate": 3.746841347700383e-05, + "loss": 3.6399, + "step": 765440 + }, + { + "epoch": 1.0, + "learning_rate": 3.7460043908297046e-05, + "loss": 3.6233, + "step": 765952 + }, + { + "epoch": 1.0, + "learning_rate": 3.7451657960786526e-05, + "loss": 3.6354, + "step": 766464 + }, + { + "epoch": 1.0, + "learning_rate": 3.7443272013276006e-05, + "loss": 3.6221, + "step": 766976 + }, + { + "epoch": 1.0, + "learning_rate": 3.7434886065765486e-05, + "loss": 3.633, + "step": 767488 + }, + { + "epoch": 1.0, + "learning_rate": 3.7426500118254966e-05, + "loss": 3.6307, + "step": 768000 + }, + { + "epoch": 1.0, + "learning_rate": 3.7418130549548175e-05, + "loss": 3.626, + "step": 768512 + }, + { + "epoch": 1.0, + "learning_rate": 3.7409744602037655e-05, + "loss": 3.6386, + "step": 769024 + }, + { + "epoch": 1.0, + "learning_rate": 3.7401375033330864e-05, + "loss": 3.6406, + "step": 769536 + }, + { + "epoch": 1.0, + "learning_rate": 3.7392989085820344e-05, + "loss": 3.6223, + "step": 770048 + }, + { + "epoch": 1.0, + "learning_rate": 3.7384603138309824e-05, + "loss": 3.6322, + "step": 770560 + }, + { + "epoch": 1.0, + "learning_rate": 3.7376217190799304e-05, + "loss": 3.6161, + "step": 771072 + }, + { + "epoch": 1.0, + "learning_rate": 3.7367831243288784e-05, + "loss": 3.6178, + "step": 771584 + }, + { + "epoch": 1.0, + "learning_rate": 3.7359445295778264e-05, + "loss": 3.6291, + "step": 772096 + }, + { + "epoch": 1.0, + "learning_rate": 3.735105934826775e-05, + "loss": 3.6208, + "step": 772608 + }, + { + "epoch": 1.0, + "learning_rate": 3.734267340075723e-05, + "loss": 3.6295, + "step": 773120 + }, + { + "epoch": 1.0, + "learning_rate": 3.733428745324671e-05, + "loss": 3.6389, + "step": 773632 + }, + { + "epoch": 1.0, + "learning_rate": 3.732590150573619e-05, + "loss": 3.6323, + "step": 774144 + }, + { + "epoch": 1.0, + "learning_rate": 3.731751555822567e-05, + "loss": 3.635, + "step": 774656 + }, + { + "epoch": 1.0, + "learning_rate": 3.730912961071515e-05, + "loss": 3.6323, + "step": 775168 + }, + { + "epoch": 1.0, + "learning_rate": 3.730076004200836e-05, + "loss": 3.6228, + "step": 775680 + }, + { + "epoch": 1.0, + "learning_rate": 3.729237409449784e-05, + "loss": 3.6286, + "step": 776192 + }, + { + "epoch": 1.0, + "learning_rate": 3.728398814698732e-05, + "loss": 3.6239, + "step": 776704 + }, + { + "epoch": 1.0, + "learning_rate": 3.727560219947679e-05, + "loss": 3.6312, + "step": 777216 + }, + { + "epoch": 1.0, + "learning_rate": 3.726723263077001e-05, + "loss": 3.6164, + "step": 777728 + }, + { + "epoch": 1.0, + "learning_rate": 3.725884668325949e-05, + "loss": 3.6247, + "step": 778240 + }, + { + "epoch": 1.01, + "learning_rate": 3.725046073574897e-05, + "loss": 3.6245, + "step": 778752 + }, + { + "epoch": 1.01, + "learning_rate": 3.7242091167042184e-05, + "loss": 3.6315, + "step": 779264 + }, + { + "epoch": 1.01, + "learning_rate": 3.7233705219531664e-05, + "loss": 3.6337, + "step": 779776 + }, + { + "epoch": 1.01, + "learning_rate": 3.7225319272021144e-05, + "loss": 3.6245, + "step": 780288 + }, + { + "epoch": 1.01, + "learning_rate": 3.7216933324510624e-05, + "loss": 3.625, + "step": 780800 + }, + { + "epoch": 1.01, + "learning_rate": 3.72085473770001e-05, + "loss": 3.6278, + "step": 781312 + }, + { + "epoch": 1.01, + "learning_rate": 3.720017780829331e-05, + "loss": 3.6342, + "step": 781824 + }, + { + "epoch": 1.01, + "learning_rate": 3.719179186078279e-05, + "loss": 3.6165, + "step": 782336 + }, + { + "epoch": 1.01, + "learning_rate": 3.7183405913272266e-05, + "loss": 3.6188, + "step": 782848 + }, + { + "epoch": 1.01, + "learning_rate": 3.7175019965761746e-05, + "loss": 3.6184, + "step": 783360 + }, + { + "epoch": 1.01, + "learning_rate": 3.7166634018251226e-05, + "loss": 3.6205, + "step": 783872 + }, + { + "epoch": 1.01, + "learning_rate": 3.7158248070740706e-05, + "loss": 3.6232, + "step": 784384 + }, + { + "epoch": 1.01, + "learning_rate": 3.7149862123230186e-05, + "loss": 3.6314, + "step": 784896 + }, + { + "epoch": 1.01, + "learning_rate": 3.714147617571967e-05, + "loss": 3.628, + "step": 785408 + }, + { + "epoch": 1.01, + "learning_rate": 3.713310660701288e-05, + "loss": 3.6286, + "step": 785920 + }, + { + "epoch": 1.01, + "learning_rate": 3.712472065950236e-05, + "loss": 3.6289, + "step": 786432 + }, + { + "epoch": 1.01, + "learning_rate": 3.711635109079557e-05, + "loss": 3.6294, + "step": 786944 + }, + { + "epoch": 1.01, + "learning_rate": 3.710796514328505e-05, + "loss": 3.6225, + "step": 787456 + }, + { + "epoch": 1.01, + "learning_rate": 3.709957919577453e-05, + "loss": 3.599, + "step": 787968 + }, + { + "epoch": 1.01, + "learning_rate": 3.709119324826401e-05, + "loss": 3.6377, + "step": 788480 + }, + { + "epoch": 1.01, + "learning_rate": 3.708282367955722e-05, + "loss": 3.6181, + "step": 788992 + }, + { + "epoch": 1.01, + "learning_rate": 3.70744377320467e-05, + "loss": 3.6229, + "step": 789504 + }, + { + "epoch": 1.01, + "learning_rate": 3.706605178453618e-05, + "loss": 3.6223, + "step": 790016 + }, + { + "epoch": 1.01, + "learning_rate": 3.705766583702566e-05, + "loss": 3.6138, + "step": 790528 + }, + { + "epoch": 1.01, + "learning_rate": 3.704927988951514e-05, + "loss": 3.6154, + "step": 791040 + }, + { + "epoch": 1.01, + "learning_rate": 3.704089394200462e-05, + "loss": 3.6115, + "step": 791552 + }, + { + "epoch": 1.01, + "learning_rate": 3.7032524373297836e-05, + "loss": 3.6263, + "step": 792064 + }, + { + "epoch": 1.01, + "learning_rate": 3.7024138425787316e-05, + "loss": 3.6111, + "step": 792576 + }, + { + "epoch": 1.01, + "learning_rate": 3.7015752478276795e-05, + "loss": 3.6315, + "step": 793088 + }, + { + "epoch": 1.01, + "learning_rate": 3.7007366530766275e-05, + "loss": 3.6191, + "step": 793600 + }, + { + "epoch": 1.01, + "learning_rate": 3.6998996962059485e-05, + "loss": 3.6032, + "step": 794112 + }, + { + "epoch": 1.01, + "learning_rate": 3.6990611014548964e-05, + "loss": 3.6337, + "step": 794624 + }, + { + "epoch": 1.01, + "learning_rate": 3.6982225067038444e-05, + "loss": 3.6118, + "step": 795136 + }, + { + "epoch": 1.01, + "learning_rate": 3.6973839119527924e-05, + "loss": 3.6076, + "step": 795648 + }, + { + "epoch": 1.01, + "learning_rate": 3.6965453172017404e-05, + "loss": 3.6238, + "step": 796160 + }, + { + "epoch": 1.01, + "learning_rate": 3.6957067224506884e-05, + "loss": 3.629, + "step": 796672 + }, + { + "epoch": 1.01, + "learning_rate": 3.6948697655800093e-05, + "loss": 3.6072, + "step": 797184 + }, + { + "epoch": 1.01, + "learning_rate": 3.694031170828957e-05, + "loss": 3.6093, + "step": 797696 + }, + { + "epoch": 1.01, + "learning_rate": 3.693192576077906e-05, + "loss": 3.6047, + "step": 798208 + }, + { + "epoch": 1.01, + "learning_rate": 3.692353981326854e-05, + "loss": 3.6146, + "step": 798720 + }, + { + "epoch": 1.01, + "learning_rate": 3.691515386575802e-05, + "loss": 3.6263, + "step": 799232 + }, + { + "epoch": 1.01, + "learning_rate": 3.69067679182475e-05, + "loss": 3.6216, + "step": 799744 + }, + { + "epoch": 1.01, + "learning_rate": 3.689838197073698e-05, + "loss": 3.6222, + "step": 800256 + }, + { + "epoch": 1.01, + "learning_rate": 3.689001240203019e-05, + "loss": 3.6203, + "step": 800768 + }, + { + "epoch": 1.01, + "learning_rate": 3.688162645451967e-05, + "loss": 3.63, + "step": 801280 + }, + { + "epoch": 1.01, + "learning_rate": 3.687324050700915e-05, + "loss": 3.6189, + "step": 801792 + }, + { + "epoch": 1.01, + "learning_rate": 3.686485455949863e-05, + "loss": 3.6293, + "step": 802304 + }, + { + "epoch": 1.01, + "learning_rate": 3.68564686119881e-05, + "loss": 3.6087, + "step": 802816 + }, + { + "epoch": 1.01, + "learning_rate": 3.684808266447758e-05, + "loss": 3.6159, + "step": 803328 + }, + { + "epoch": 1.01, + "learning_rate": 3.683969671696706e-05, + "loss": 3.6165, + "step": 803840 + }, + { + "epoch": 1.01, + "learning_rate": 3.683132714826028e-05, + "loss": 3.6202, + "step": 804352 + }, + { + "epoch": 1.01, + "learning_rate": 3.682294120074976e-05, + "loss": 3.6251, + "step": 804864 + }, + { + "epoch": 1.01, + "learning_rate": 3.681455525323924e-05, + "loss": 3.6262, + "step": 805376 + }, + { + "epoch": 1.01, + "learning_rate": 3.680616930572872e-05, + "loss": 3.6168, + "step": 805888 + }, + { + "epoch": 1.01, + "learning_rate": 3.67977833582182e-05, + "loss": 3.6121, + "step": 806400 + }, + { + "epoch": 1.01, + "learning_rate": 3.678941378951141e-05, + "loss": 3.6179, + "step": 806912 + }, + { + "epoch": 1.01, + "learning_rate": 3.678102784200089e-05, + "loss": 3.6245, + "step": 807424 + }, + { + "epoch": 1.01, + "learning_rate": 3.677264189449037e-05, + "loss": 3.6084, + "step": 807936 + }, + { + "epoch": 1.01, + "learning_rate": 3.676425594697985e-05, + "loss": 3.6143, + "step": 808448 + }, + { + "epoch": 1.01, + "learning_rate": 3.6755869999469327e-05, + "loss": 3.6234, + "step": 808960 + }, + { + "epoch": 1.02, + "learning_rate": 3.6747484051958807e-05, + "loss": 3.6176, + "step": 809472 + }, + { + "epoch": 1.02, + "learning_rate": 3.6739098104448286e-05, + "loss": 3.6148, + "step": 809984 + }, + { + "epoch": 1.02, + "learning_rate": 3.6730728535741496e-05, + "loss": 3.6097, + "step": 810496 + }, + { + "epoch": 1.02, + "learning_rate": 3.672234258823098e-05, + "loss": 3.6219, + "step": 811008 + }, + { + "epoch": 1.02, + "learning_rate": 3.671395664072046e-05, + "loss": 3.6254, + "step": 811520 + }, + { + "epoch": 1.02, + "learning_rate": 3.670557069320994e-05, + "loss": 3.6193, + "step": 812032 + }, + { + "epoch": 1.02, + "learning_rate": 3.669718474569942e-05, + "loss": 3.6106, + "step": 812544 + }, + { + "epoch": 1.02, + "learning_rate": 3.66887987981889e-05, + "loss": 3.6129, + "step": 813056 + }, + { + "epoch": 1.02, + "learning_rate": 3.668041285067838e-05, + "loss": 3.6122, + "step": 813568 + }, + { + "epoch": 1.02, + "learning_rate": 3.667202690316786e-05, + "loss": 3.6226, + "step": 814080 + }, + { + "epoch": 1.02, + "learning_rate": 3.666365733446107e-05, + "loss": 3.6247, + "step": 814592 + }, + { + "epoch": 1.02, + "learning_rate": 3.665528776575428e-05, + "loss": 3.6128, + "step": 815104 + }, + { + "epoch": 1.02, + "learning_rate": 3.664690181824376e-05, + "loss": 3.6138, + "step": 815616 + }, + { + "epoch": 1.02, + "learning_rate": 3.663851587073324e-05, + "loss": 3.6084, + "step": 816128 + }, + { + "epoch": 1.02, + "learning_rate": 3.663012992322272e-05, + "loss": 3.6085, + "step": 816640 + }, + { + "epoch": 1.02, + "learning_rate": 3.6621760354515936e-05, + "loss": 3.6112, + "step": 817152 + }, + { + "epoch": 1.02, + "learning_rate": 3.6613374407005416e-05, + "loss": 3.6102, + "step": 817664 + }, + { + "epoch": 1.02, + "learning_rate": 3.6604988459494896e-05, + "loss": 3.6114, + "step": 818176 + }, + { + "epoch": 1.02, + "learning_rate": 3.6596602511984376e-05, + "loss": 3.6107, + "step": 818688 + }, + { + "epoch": 1.02, + "learning_rate": 3.6588216564473856e-05, + "loss": 3.6065, + "step": 819200 + }, + { + "epoch": 1.02, + "learning_rate": 3.6579846995767065e-05, + "loss": 3.6152, + "step": 819712 + }, + { + "epoch": 1.02, + "learning_rate": 3.6571461048256545e-05, + "loss": 3.6086, + "step": 820224 + }, + { + "epoch": 1.02, + "learning_rate": 3.6563075100746025e-05, + "loss": 3.6229, + "step": 820736 + }, + { + "epoch": 1.02, + "learning_rate": 3.6554689153235505e-05, + "loss": 3.608, + "step": 821248 + }, + { + "epoch": 1.02, + "learning_rate": 3.6546303205724985e-05, + "loss": 3.6277, + "step": 821760 + }, + { + "epoch": 1.02, + "learning_rate": 3.6537933637018194e-05, + "loss": 3.6286, + "step": 822272 + }, + { + "epoch": 1.02, + "learning_rate": 3.6529547689507674e-05, + "loss": 3.6222, + "step": 822784 + }, + { + "epoch": 1.02, + "learning_rate": 3.6521161741997154e-05, + "loss": 3.6126, + "step": 823296 + }, + { + "epoch": 1.02, + "learning_rate": 3.6512775794486634e-05, + "loss": 3.6148, + "step": 823808 + }, + { + "epoch": 1.02, + "learning_rate": 3.6504389846976114e-05, + "loss": 3.6128, + "step": 824320 + }, + { + "epoch": 1.02, + "learning_rate": 3.6496003899465594e-05, + "loss": 3.619, + "step": 824832 + }, + { + "epoch": 1.02, + "learning_rate": 3.6487617951955074e-05, + "loss": 3.614, + "step": 825344 + }, + { + "epoch": 1.02, + "learning_rate": 3.647924838324829e-05, + "loss": 3.6056, + "step": 825856 + }, + { + "epoch": 1.02, + "learning_rate": 3.647086243573776e-05, + "loss": 3.6211, + "step": 826368 + }, + { + "epoch": 1.02, + "learning_rate": 3.646247648822724e-05, + "loss": 3.6242, + "step": 826880 + }, + { + "epoch": 1.02, + "learning_rate": 3.645409054071672e-05, + "loss": 3.608, + "step": 827392 + }, + { + "epoch": 1.02, + "learning_rate": 3.64457045932062e-05, + "loss": 3.6102, + "step": 827904 + }, + { + "epoch": 1.02, + "learning_rate": 3.643733502449941e-05, + "loss": 3.616, + "step": 828416 + }, + { + "epoch": 1.02, + "learning_rate": 3.642894907698889e-05, + "loss": 3.604, + "step": 828928 + }, + { + "epoch": 1.02, + "learning_rate": 3.642056312947837e-05, + "loss": 3.6307, + "step": 829440 + }, + { + "epoch": 1.02, + "learning_rate": 3.641217718196785e-05, + "loss": 3.6092, + "step": 829952 + }, + { + "epoch": 1.02, + "learning_rate": 3.640379123445734e-05, + "loss": 3.6253, + "step": 830464 + }, + { + "epoch": 1.02, + "learning_rate": 3.639540528694682e-05, + "loss": 3.5981, + "step": 830976 + }, + { + "epoch": 1.02, + "learning_rate": 3.63870193394363e-05, + "loss": 3.622, + "step": 831488 + }, + { + "epoch": 1.02, + "learning_rate": 3.637864977072951e-05, + "loss": 3.616, + "step": 832000 + }, + { + "epoch": 1.02, + "learning_rate": 3.637026382321899e-05, + "loss": 3.6158, + "step": 832512 + }, + { + "epoch": 1.02, + "learning_rate": 3.636187787570847e-05, + "loss": 3.6159, + "step": 833024 + }, + { + "epoch": 1.02, + "learning_rate": 3.6353508307001676e-05, + "loss": 3.6081, + "step": 833536 + }, + { + "epoch": 1.02, + "learning_rate": 3.6345122359491156e-05, + "loss": 3.6182, + "step": 834048 + }, + { + "epoch": 1.02, + "learning_rate": 3.6336736411980636e-05, + "loss": 3.6345, + "step": 834560 + }, + { + "epoch": 1.02, + "learning_rate": 3.6328350464470116e-05, + "loss": 3.6036, + "step": 835072 + }, + { + "epoch": 1.02, + "learning_rate": 3.6319964516959596e-05, + "loss": 3.6137, + "step": 835584 + }, + { + "epoch": 1.02, + "learning_rate": 3.6311594948252805e-05, + "loss": 3.6142, + "step": 836096 + }, + { + "epoch": 1.02, + "learning_rate": 3.630320900074229e-05, + "loss": 3.6097, + "step": 836608 + }, + { + "epoch": 1.02, + "learning_rate": 3.629482305323177e-05, + "loss": 3.613, + "step": 837120 + }, + { + "epoch": 1.02, + "learning_rate": 3.628643710572125e-05, + "loss": 3.6166, + "step": 837632 + }, + { + "epoch": 1.02, + "learning_rate": 3.627806753701446e-05, + "loss": 3.6162, + "step": 838144 + }, + { + "epoch": 1.02, + "learning_rate": 3.626968158950394e-05, + "loss": 3.6137, + "step": 838656 + }, + { + "epoch": 1.02, + "learning_rate": 3.626129564199342e-05, + "loss": 3.6133, + "step": 839168 + }, + { + "epoch": 1.03, + "eval_loss": 3.8424363136291504, + "eval_runtime": 304.9822, + "eval_samples_per_second": 1251.191, + "eval_steps_per_second": 39.101, + "step": 839520 + }, + { + "epoch": 0.0, + "learning_rate": 3.62529096944829e-05, + "loss": 3.5942, + "step": 839680 + }, + { + "epoch": 0.0, + "learning_rate": 3.624452374697238e-05, + "loss": 3.6039, + "step": 840192 + }, + { + "epoch": 0.0, + "learning_rate": 3.623613779946186e-05, + "loss": 3.6164, + "step": 840704 + }, + { + "epoch": 0.0, + "learning_rate": 3.622775185195134e-05, + "loss": 3.6112, + "step": 841216 + }, + { + "epoch": 0.0, + "learning_rate": 3.621936590444082e-05, + "loss": 3.619, + "step": 841728 + }, + { + "epoch": 0.0, + "learning_rate": 3.621099633573403e-05, + "loss": 3.6043, + "step": 842240 + }, + { + "epoch": 0.0, + "learning_rate": 3.620261038822351e-05, + "loss": 3.6115, + "step": 842752 + }, + { + "epoch": 0.0, + "learning_rate": 3.619422444071299e-05, + "loss": 3.6052, + "step": 843264 + }, + { + "epoch": 0.0, + "learning_rate": 3.6185838493202476e-05, + "loss": 3.6109, + "step": 843776 + }, + { + "epoch": 0.0, + "learning_rate": 3.6177468924495685e-05, + "loss": 3.6033, + "step": 844288 + }, + { + "epoch": 0.0, + "learning_rate": 3.6169082976985165e-05, + "loss": 3.6054, + "step": 844800 + }, + { + "epoch": 0.0, + "learning_rate": 3.6160697029474645e-05, + "loss": 3.6214, + "step": 845312 + }, + { + "epoch": 0.0, + "learning_rate": 3.6152327460767854e-05, + "loss": 3.6142, + "step": 845824 + }, + { + "epoch": 0.0, + "learning_rate": 3.6143941513257334e-05, + "loss": 3.6026, + "step": 846336 + }, + { + "epoch": 0.0, + "learning_rate": 3.6135555565746814e-05, + "loss": 3.6096, + "step": 846848 + }, + { + "epoch": 0.0, + "learning_rate": 3.6127169618236294e-05, + "loss": 3.5942, + "step": 847360 + }, + { + "epoch": 0.0, + "learning_rate": 3.6118783670725774e-05, + "loss": 3.599, + "step": 847872 + }, + { + "epoch": 0.0, + "learning_rate": 3.611039772321525e-05, + "loss": 3.6091, + "step": 848384 + }, + { + "epoch": 0.0, + "learning_rate": 3.610201177570473e-05, + "loss": 3.5972, + "step": 848896 + }, + { + "epoch": 0.0, + "learning_rate": 3.6093625828194214e-05, + "loss": 3.607, + "step": 849408 + }, + { + "epoch": 0.0, + "learning_rate": 3.608525625948742e-05, + "loss": 3.615, + "step": 849920 + }, + { + "epoch": 0.0, + "learning_rate": 3.60768703119769e-05, + "loss": 3.6129, + "step": 850432 + }, + { + "epoch": 0.0, + "learning_rate": 3.606848436446638e-05, + "loss": 3.6179, + "step": 850944 + }, + { + "epoch": 0.0, + "learning_rate": 3.606009841695586e-05, + "loss": 3.6122, + "step": 851456 + }, + { + "epoch": 0.0, + "learning_rate": 3.605171246944534e-05, + "loss": 3.6028, + "step": 851968 + }, + { + "epoch": 0.0, + "learning_rate": 3.604332652193482e-05, + "loss": 3.6057, + "step": 852480 + }, + { + "epoch": 0.0, + "learning_rate": 3.603495695322803e-05, + "loss": 3.6013, + "step": 852992 + }, + { + "epoch": 0.0, + "learning_rate": 3.602657100571751e-05, + "loss": 3.6105, + "step": 853504 + }, + { + "epoch": 0.0, + "learning_rate": 3.601818505820699e-05, + "loss": 3.5961, + "step": 854016 + }, + { + "epoch": 0.0, + "learning_rate": 3.600979911069647e-05, + "loss": 3.6051, + "step": 854528 + }, + { + "epoch": 0.01, + "learning_rate": 3.600142954198968e-05, + "loss": 3.6064, + "step": 855040 + }, + { + "epoch": 0.01, + "learning_rate": 3.599304359447917e-05, + "loss": 3.6064, + "step": 855552 + }, + { + "epoch": 0.01, + "learning_rate": 3.598465764696865e-05, + "loss": 3.6084, + "step": 856064 + }, + { + "epoch": 0.01, + "learning_rate": 3.597627169945813e-05, + "loss": 3.6084, + "step": 856576 + }, + { + "epoch": 0.01, + "learning_rate": 3.596788575194761e-05, + "loss": 3.6011, + "step": 857088 + }, + { + "epoch": 0.01, + "learning_rate": 3.595951618324082e-05, + "loss": 3.6094, + "step": 857600 + }, + { + "epoch": 0.01, + "learning_rate": 3.59511302357303e-05, + "loss": 3.6163, + "step": 858112 + }, + { + "epoch": 0.01, + "learning_rate": 3.5942744288219777e-05, + "loss": 3.5956, + "step": 858624 + }, + { + "epoch": 0.01, + "learning_rate": 3.5934358340709257e-05, + "loss": 3.5972, + "step": 859136 + }, + { + "epoch": 0.01, + "learning_rate": 3.5925988772002466e-05, + "loss": 3.5986, + "step": 859648 + }, + { + "epoch": 0.01, + "learning_rate": 3.5917602824491946e-05, + "loss": 3.5967, + "step": 860160 + }, + { + "epoch": 0.01, + "learning_rate": 3.5909216876981426e-05, + "loss": 3.6018, + "step": 860672 + }, + { + "epoch": 0.01, + "learning_rate": 3.5900830929470906e-05, + "loss": 3.6078, + "step": 861184 + }, + { + "epoch": 0.01, + "learning_rate": 3.5892444981960385e-05, + "loss": 3.6107, + "step": 861696 + }, + { + "epoch": 0.01, + "learning_rate": 3.58840754132536e-05, + "loss": 3.6053, + "step": 862208 + }, + { + "epoch": 0.01, + "learning_rate": 3.587568946574308e-05, + "loss": 3.6099, + "step": 862720 + }, + { + "epoch": 0.01, + "learning_rate": 3.586730351823256e-05, + "loss": 3.6104, + "step": 863232 + }, + { + "epoch": 0.01, + "learning_rate": 3.585891757072204e-05, + "loss": 3.6048, + "step": 863744 + }, + { + "epoch": 0.01, + "learning_rate": 3.585054800201525e-05, + "loss": 3.5797, + "step": 864256 + }, + { + "epoch": 0.01, + "learning_rate": 3.584216205450473e-05, + "loss": 3.6147, + "step": 864768 + }, + { + "epoch": 0.01, + "learning_rate": 3.583377610699421e-05, + "loss": 3.5967, + "step": 865280 + }, + { + "epoch": 0.01, + "learning_rate": 3.582539015948369e-05, + "loss": 3.6038, + "step": 865792 + }, + { + "epoch": 0.01, + "learning_rate": 3.58170205907769e-05, + "loss": 3.5969, + "step": 866304 + }, + { + "epoch": 0.01, + "learning_rate": 3.580863464326638e-05, + "loss": 3.5926, + "step": 866816 + }, + { + "epoch": 0.01, + "learning_rate": 3.580024869575586e-05, + "loss": 3.5967, + "step": 867328 + }, + { + "epoch": 0.01, + "learning_rate": 3.579186274824534e-05, + "loss": 3.5939, + "step": 867840 + }, + { + "epoch": 0.01, + "learning_rate": 3.578347680073482e-05, + "loss": 3.6047, + "step": 868352 + }, + { + "epoch": 0.01, + "learning_rate": 3.5775107232028035e-05, + "loss": 3.5879, + "step": 868864 + }, + { + "epoch": 0.01, + "learning_rate": 3.5766721284517515e-05, + "loss": 3.612, + "step": 869376 + }, + { + "epoch": 0.01, + "learning_rate": 3.5758335337006995e-05, + "loss": 3.6011, + "step": 869888 + }, + { + "epoch": 0.01, + "learning_rate": 3.5749949389496475e-05, + "loss": 3.5794, + "step": 870400 + }, + { + "epoch": 0.01, + "learning_rate": 3.5741563441985955e-05, + "loss": 3.6132, + "step": 870912 + }, + { + "epoch": 0.01, + "learning_rate": 3.5733193873279164e-05, + "loss": 3.5917, + "step": 871424 + }, + { + "epoch": 0.01, + "learning_rate": 3.5724807925768644e-05, + "loss": 3.5916, + "step": 871936 + }, + { + "epoch": 0.01, + "learning_rate": 3.5716421978258124e-05, + "loss": 3.6002, + "step": 872448 + }, + { + "epoch": 0.01, + "learning_rate": 3.5708036030747604e-05, + "loss": 3.6088, + "step": 872960 + }, + { + "epoch": 0.01, + "learning_rate": 3.569966646204081e-05, + "loss": 3.588, + "step": 873472 + }, + { + "epoch": 0.01, + "learning_rate": 3.569128051453029e-05, + "loss": 3.5956, + "step": 873984 + }, + { + "epoch": 0.01, + "learning_rate": 3.568289456701977e-05, + "loss": 3.5816, + "step": 874496 + }, + { + "epoch": 0.01, + "learning_rate": 3.567450861950925e-05, + "loss": 3.593, + "step": 875008 + }, + { + "epoch": 0.01, + "learning_rate": 3.566612267199873e-05, + "loss": 3.6087, + "step": 875520 + }, + { + "epoch": 0.01, + "learning_rate": 3.565773672448821e-05, + "loss": 3.5977, + "step": 876032 + }, + { + "epoch": 0.01, + "learning_rate": 3.564936715578143e-05, + "loss": 3.6016, + "step": 876544 + }, + { + "epoch": 0.01, + "learning_rate": 3.564098120827091e-05, + "loss": 3.6002, + "step": 877056 + }, + { + "epoch": 0.01, + "learning_rate": 3.563259526076038e-05, + "loss": 3.6102, + "step": 877568 + }, + { + "epoch": 0.01, + "learning_rate": 3.562420931324986e-05, + "loss": 3.6001, + "step": 878080 + }, + { + "epoch": 0.01, + "learning_rate": 3.561583974454308e-05, + "loss": 3.6064, + "step": 878592 + }, + { + "epoch": 0.01, + "learning_rate": 3.560745379703255e-05, + "loss": 3.5912, + "step": 879104 + }, + { + "epoch": 0.01, + "learning_rate": 3.559906784952203e-05, + "loss": 3.596, + "step": 879616 + }, + { + "epoch": 0.01, + "learning_rate": 3.559068190201151e-05, + "loss": 3.5953, + "step": 880128 + }, + { + "epoch": 0.01, + "learning_rate": 3.5582312333304726e-05, + "loss": 3.6002, + "step": 880640 + }, + { + "epoch": 0.01, + "learning_rate": 3.5573926385794206e-05, + "loss": 3.6035, + "step": 881152 + }, + { + "epoch": 0.01, + "learning_rate": 3.5565540438283686e-05, + "loss": 3.6064, + "step": 881664 + }, + { + "epoch": 0.01, + "learning_rate": 3.5557154490773166e-05, + "loss": 3.6031, + "step": 882176 + }, + { + "epoch": 0.01, + "learning_rate": 3.5548768543262646e-05, + "loss": 3.5874, + "step": 882688 + }, + { + "epoch": 0.01, + "learning_rate": 3.5540398974555855e-05, + "loss": 3.5991, + "step": 883200 + }, + { + "epoch": 0.01, + "learning_rate": 3.5532013027045335e-05, + "loss": 3.6033, + "step": 883712 + }, + { + "epoch": 0.01, + "learning_rate": 3.5523627079534815e-05, + "loss": 3.5885, + "step": 884224 + }, + { + "epoch": 0.01, + "learning_rate": 3.5515241132024295e-05, + "loss": 3.5954, + "step": 884736 + }, + { + "epoch": 0.01, + "learning_rate": 3.5506855184513775e-05, + "loss": 3.6041, + "step": 885248 + }, + { + "epoch": 0.02, + "learning_rate": 3.5498485615806984e-05, + "loss": 3.595, + "step": 885760 + }, + { + "epoch": 0.02, + "learning_rate": 3.5490099668296464e-05, + "loss": 3.5993, + "step": 886272 + }, + { + "epoch": 0.02, + "learning_rate": 3.5481713720785944e-05, + "loss": 3.5872, + "step": 886784 + }, + { + "epoch": 0.02, + "learning_rate": 3.547332777327543e-05, + "loss": 3.6041, + "step": 887296 + }, + { + "epoch": 0.02, + "learning_rate": 3.546494182576491e-05, + "loss": 3.6025, + "step": 887808 + }, + { + "epoch": 0.02, + "learning_rate": 3.545655587825439e-05, + "loss": 3.6049, + "step": 888320 + }, + { + "epoch": 0.02, + "learning_rate": 3.544816993074387e-05, + "loss": 3.5834, + "step": 888832 + }, + { + "epoch": 0.02, + "learning_rate": 3.543978398323335e-05, + "loss": 3.5969, + "step": 889344 + }, + { + "epoch": 0.02, + "learning_rate": 3.543141441452656e-05, + "loss": 3.5903, + "step": 889856 + }, + { + "epoch": 0.02, + "learning_rate": 3.542304484581977e-05, + "loss": 3.602, + "step": 890368 + }, + { + "epoch": 0.02, + "learning_rate": 3.541465889830925e-05, + "loss": 3.6061, + "step": 890880 + }, + { + "epoch": 0.02, + "learning_rate": 3.540627295079873e-05, + "loss": 3.5931, + "step": 891392 + }, + { + "epoch": 0.02, + "learning_rate": 3.539788700328821e-05, + "loss": 3.5941, + "step": 891904 + }, + { + "epoch": 0.02, + "learning_rate": 3.538950105577769e-05, + "loss": 3.5866, + "step": 892416 + }, + { + "epoch": 0.02, + "learning_rate": 3.53811314870709e-05, + "loss": 3.5877, + "step": 892928 + }, + { + "epoch": 0.02, + "learning_rate": 3.5372745539560385e-05, + "loss": 3.5927, + "step": 893440 + }, + { + "epoch": 0.02, + "learning_rate": 3.5364359592049865e-05, + "loss": 3.5899, + "step": 893952 + }, + { + "epoch": 0.02, + "learning_rate": 3.5355973644539344e-05, + "loss": 3.593, + "step": 894464 + }, + { + "epoch": 0.02, + "learning_rate": 3.5347587697028824e-05, + "loss": 3.5906, + "step": 894976 + }, + { + "epoch": 0.02, + "learning_rate": 3.5339201749518304e-05, + "loss": 3.5873, + "step": 895488 + }, + { + "epoch": 0.02, + "learning_rate": 3.5330832180811513e-05, + "loss": 3.5897, + "step": 896000 + }, + { + "epoch": 0.02, + "learning_rate": 3.5322446233300993e-05, + "loss": 3.5883, + "step": 896512 + }, + { + "epoch": 0.02, + "learning_rate": 3.5314060285790473e-05, + "loss": 3.6064, + "step": 897024 + }, + { + "epoch": 0.02, + "learning_rate": 3.530567433827995e-05, + "loss": 3.5902, + "step": 897536 + }, + { + "epoch": 0.02, + "learning_rate": 3.529728839076943e-05, + "loss": 3.6036, + "step": 898048 + }, + { + "epoch": 0.02, + "learning_rate": 3.528891882206264e-05, + "loss": 3.6053, + "step": 898560 + }, + { + "epoch": 0.02, + "learning_rate": 3.528053287455212e-05, + "loss": 3.6084, + "step": 899072 + }, + { + "epoch": 0.02, + "learning_rate": 3.52721469270416e-05, + "loss": 3.5897, + "step": 899584 + }, + { + "epoch": 0.02, + "learning_rate": 3.526376097953108e-05, + "loss": 3.5954, + "step": 900096 + }, + { + "epoch": 0.02, + "learning_rate": 3.52553914108243e-05, + "loss": 3.5942, + "step": 900608 + }, + { + "epoch": 0.02, + "learning_rate": 3.524700546331378e-05, + "loss": 3.5976, + "step": 901120 + }, + { + "epoch": 0.02, + "learning_rate": 3.523861951580326e-05, + "loss": 3.598, + "step": 901632 + }, + { + "epoch": 0.02, + "learning_rate": 3.523023356829274e-05, + "loss": 3.5882, + "step": 902144 + }, + { + "epoch": 0.02, + "learning_rate": 3.522184762078222e-05, + "loss": 3.5957, + "step": 902656 + }, + { + "epoch": 0.02, + "learning_rate": 3.521346167327169e-05, + "loss": 3.6056, + "step": 903168 + }, + { + "epoch": 0.02, + "learning_rate": 3.520507572576117e-05, + "loss": 3.5955, + "step": 903680 + }, + { + "epoch": 0.02, + "learning_rate": 3.519670615705439e-05, + "loss": 3.5873, + "step": 904192 + }, + { + "epoch": 0.02, + "learning_rate": 3.518832020954386e-05, + "loss": 3.5961, + "step": 904704 + }, + { + "epoch": 0.02, + "learning_rate": 3.517993426203334e-05, + "loss": 3.5869, + "step": 905216 + }, + { + "epoch": 0.02, + "learning_rate": 3.517154831452282e-05, + "loss": 3.608, + "step": 905728 + }, + { + "epoch": 0.02, + "learning_rate": 3.51631623670123e-05, + "loss": 3.5908, + "step": 906240 + }, + { + "epoch": 0.02, + "learning_rate": 3.5154792798305516e-05, + "loss": 3.6047, + "step": 906752 + }, + { + "epoch": 0.02, + "learning_rate": 3.5146406850794996e-05, + "loss": 3.5794, + "step": 907264 + }, + { + "epoch": 0.02, + "learning_rate": 3.5138020903284476e-05, + "loss": 3.6004, + "step": 907776 + }, + { + "epoch": 0.02, + "learning_rate": 3.512965133457769e-05, + "loss": 3.5951, + "step": 908288 + }, + { + "epoch": 0.02, + "learning_rate": 3.5121265387067165e-05, + "loss": 3.5936, + "step": 908800 + }, + { + "epoch": 0.02, + "learning_rate": 3.5112879439556645e-05, + "loss": 3.5989, + "step": 909312 + }, + { + "epoch": 0.02, + "learning_rate": 3.5104493492046125e-05, + "loss": 3.5863, + "step": 909824 + }, + { + "epoch": 0.02, + "learning_rate": 3.5096107544535605e-05, + "loss": 3.6014, + "step": 910336 + }, + { + "epoch": 0.02, + "learning_rate": 3.5087737975828814e-05, + "loss": 3.6118, + "step": 910848 + }, + { + "epoch": 0.02, + "learning_rate": 3.5079352028318294e-05, + "loss": 3.5842, + "step": 911360 + }, + { + "epoch": 0.02, + "learning_rate": 3.5070966080807774e-05, + "loss": 3.5913, + "step": 911872 + }, + { + "epoch": 0.02, + "learning_rate": 3.5062580133297254e-05, + "loss": 3.5954, + "step": 912384 + }, + { + "epoch": 0.02, + "learning_rate": 3.505421056459047e-05, + "loss": 3.592, + "step": 912896 + }, + { + "epoch": 0.02, + "learning_rate": 3.504582461707995e-05, + "loss": 3.5905, + "step": 913408 + }, + { + "epoch": 0.02, + "learning_rate": 3.503743866956943e-05, + "loss": 3.6004, + "step": 913920 + }, + { + "epoch": 0.02, + "learning_rate": 3.502905272205891e-05, + "loss": 3.5933, + "step": 914432 + }, + { + "epoch": 0.02, + "learning_rate": 3.502066677454839e-05, + "loss": 3.5943, + "step": 914944 + }, + { + "epoch": 0.02, + "learning_rate": 3.50122972058416e-05, + "loss": 3.5958, + "step": 915456 + }, + { + "epoch": 0.03, + "eval_loss": 3.841254711151123, + "eval_runtime": 304.0455, + "eval_samples_per_second": 1255.046, + "eval_steps_per_second": 39.221, + "step": 915840 + }, + { + "epoch": 1.0, + "learning_rate": 3.500391125833108e-05, + "loss": 3.5895, + "step": 915968 + }, + { + "epoch": 1.0, + "learning_rate": 3.499552531082056e-05, + "loss": 3.5794, + "step": 916480 + }, + { + "epoch": 1.0, + "learning_rate": 3.498713936331004e-05, + "loss": 3.5983, + "step": 916992 + }, + { + "epoch": 1.0, + "learning_rate": 3.497876979460325e-05, + "loss": 3.5928, + "step": 917504 + }, + { + "epoch": 1.0, + "learning_rate": 3.497038384709273e-05, + "loss": 3.5947, + "step": 918016 + }, + { + "epoch": 1.0, + "learning_rate": 3.496199789958221e-05, + "loss": 3.5843, + "step": 918528 + }, + { + "epoch": 1.0, + "learning_rate": 3.4953611952071694e-05, + "loss": 3.5961, + "step": 919040 + }, + { + "epoch": 1.0, + "learning_rate": 3.4945226004561174e-05, + "loss": 3.5843, + "step": 919552 + }, + { + "epoch": 1.0, + "learning_rate": 3.4936840057050654e-05, + "loss": 3.5909, + "step": 920064 + }, + { + "epoch": 1.0, + "learning_rate": 3.492847048834386e-05, + "loss": 3.5859, + "step": 920576 + }, + { + "epoch": 1.0, + "learning_rate": 3.492008454083334e-05, + "loss": 3.5908, + "step": 921088 + }, + { + "epoch": 1.0, + "learning_rate": 3.491169859332282e-05, + "loss": 3.5982, + "step": 921600 + }, + { + "epoch": 1.0, + "learning_rate": 3.490332902461603e-05, + "loss": 3.5993, + "step": 922112 + }, + { + "epoch": 1.0, + "learning_rate": 3.489494307710551e-05, + "loss": 3.5822, + "step": 922624 + }, + { + "epoch": 1.0, + "learning_rate": 3.488655712959499e-05, + "loss": 3.5905, + "step": 923136 + }, + { + "epoch": 1.0, + "learning_rate": 3.487817118208447e-05, + "loss": 3.5737, + "step": 923648 + }, + { + "epoch": 1.0, + "learning_rate": 3.486978523457395e-05, + "loss": 3.584, + "step": 924160 + }, + { + "epoch": 1.0, + "learning_rate": 3.486139928706343e-05, + "loss": 3.5873, + "step": 924672 + }, + { + "epoch": 1.0, + "learning_rate": 3.485301333955291e-05, + "loss": 3.5801, + "step": 925184 + }, + { + "epoch": 1.0, + "learning_rate": 3.484462739204239e-05, + "loss": 3.5875, + "step": 925696 + }, + { + "epoch": 1.0, + "learning_rate": 3.483625782333561e-05, + "loss": 3.5954, + "step": 926208 + }, + { + "epoch": 1.0, + "learning_rate": 3.482787187582509e-05, + "loss": 3.5893, + "step": 926720 + }, + { + "epoch": 1.0, + "learning_rate": 3.481948592831457e-05, + "loss": 3.6011, + "step": 927232 + }, + { + "epoch": 1.0, + "learning_rate": 3.481109998080405e-05, + "loss": 3.5942, + "step": 927744 + }, + { + "epoch": 1.0, + "learning_rate": 3.480271403329352e-05, + "loss": 3.5802, + "step": 928256 + }, + { + "epoch": 1.0, + "learning_rate": 3.4794328085783e-05, + "loss": 3.5911, + "step": 928768 + }, + { + "epoch": 1.0, + "learning_rate": 3.4785958517076217e-05, + "loss": 3.5823, + "step": 929280 + }, + { + "epoch": 1.0, + "learning_rate": 3.4777572569565697e-05, + "loss": 3.5888, + "step": 929792 + }, + { + "epoch": 1.0, + "learning_rate": 3.476918662205517e-05, + "loss": 3.58, + "step": 930304 + }, + { + "epoch": 1.0, + "learning_rate": 3.476080067454465e-05, + "loss": 3.5821, + "step": 930816 + }, + { + "epoch": 1.01, + "learning_rate": 3.4752431105837866e-05, + "loss": 3.5885, + "step": 931328 + }, + { + "epoch": 1.01, + "learning_rate": 3.4744045158327345e-05, + "loss": 3.5866, + "step": 931840 + }, + { + "epoch": 1.01, + "learning_rate": 3.4735659210816825e-05, + "loss": 3.587, + "step": 932352 + }, + { + "epoch": 1.01, + "learning_rate": 3.4727273263306305e-05, + "loss": 3.5923, + "step": 932864 + }, + { + "epoch": 1.01, + "learning_rate": 3.4718887315795785e-05, + "loss": 3.5845, + "step": 933376 + }, + { + "epoch": 1.01, + "learning_rate": 3.4710517747088994e-05, + "loss": 3.5871, + "step": 933888 + }, + { + "epoch": 1.01, + "learning_rate": 3.4702131799578474e-05, + "loss": 3.5969, + "step": 934400 + }, + { + "epoch": 1.01, + "learning_rate": 3.4693745852067954e-05, + "loss": 3.5722, + "step": 934912 + }, + { + "epoch": 1.01, + "learning_rate": 3.4685359904557434e-05, + "loss": 3.5845, + "step": 935424 + }, + { + "epoch": 1.01, + "learning_rate": 3.4676990335850643e-05, + "loss": 3.581, + "step": 935936 + }, + { + "epoch": 1.01, + "learning_rate": 3.466860438834012e-05, + "loss": 3.577, + "step": 936448 + }, + { + "epoch": 1.01, + "learning_rate": 3.46602184408296e-05, + "loss": 3.5825, + "step": 936960 + }, + { + "epoch": 1.01, + "learning_rate": 3.465183249331908e-05, + "loss": 3.5872, + "step": 937472 + }, + { + "epoch": 1.01, + "learning_rate": 3.46434629246123e-05, + "loss": 3.5922, + "step": 937984 + }, + { + "epoch": 1.01, + "learning_rate": 3.463507697710178e-05, + "loss": 3.5882, + "step": 938496 + }, + { + "epoch": 1.01, + "learning_rate": 3.462669102959126e-05, + "loss": 3.5908, + "step": 939008 + }, + { + "epoch": 1.01, + "learning_rate": 3.461830508208074e-05, + "loss": 3.5927, + "step": 939520 + }, + { + "epoch": 1.01, + "learning_rate": 3.460991913457022e-05, + "loss": 3.5825, + "step": 940032 + }, + { + "epoch": 1.01, + "learning_rate": 3.460154956586343e-05, + "loss": 3.5649, + "step": 940544 + }, + { + "epoch": 1.01, + "learning_rate": 3.459316361835291e-05, + "loss": 3.5919, + "step": 941056 + }, + { + "epoch": 1.01, + "learning_rate": 3.458477767084239e-05, + "loss": 3.5779, + "step": 941568 + }, + { + "epoch": 1.01, + "learning_rate": 3.457639172333187e-05, + "loss": 3.5824, + "step": 942080 + }, + { + "epoch": 1.01, + "learning_rate": 3.456802215462508e-05, + "loss": 3.5806, + "step": 942592 + }, + { + "epoch": 1.01, + "learning_rate": 3.455963620711456e-05, + "loss": 3.5767, + "step": 943104 + }, + { + "epoch": 1.01, + "learning_rate": 3.455125025960404e-05, + "loss": 3.5765, + "step": 943616 + }, + { + "epoch": 1.01, + "learning_rate": 3.454286431209352e-05, + "loss": 3.5741, + "step": 944128 + }, + { + "epoch": 1.01, + "learning_rate": 3.4534478364583004e-05, + "loss": 3.5867, + "step": 944640 + }, + { + "epoch": 1.01, + "learning_rate": 3.452610879587621e-05, + "loss": 3.5679, + "step": 945152 + }, + { + "epoch": 1.01, + "learning_rate": 3.451772284836569e-05, + "loss": 3.596, + "step": 945664 + }, + { + "epoch": 1.01, + "learning_rate": 3.450933690085517e-05, + "loss": 3.5826, + "step": 946176 + }, + { + "epoch": 1.01, + "learning_rate": 3.450095095334465e-05, + "loss": 3.5645, + "step": 946688 + }, + { + "epoch": 1.01, + "learning_rate": 3.449258138463786e-05, + "loss": 3.5912, + "step": 947200 + }, + { + "epoch": 1.01, + "learning_rate": 3.448419543712734e-05, + "loss": 3.5702, + "step": 947712 + }, + { + "epoch": 1.01, + "learning_rate": 3.447580948961682e-05, + "loss": 3.5766, + "step": 948224 + }, + { + "epoch": 1.01, + "learning_rate": 3.44674235421063e-05, + "loss": 3.5786, + "step": 948736 + }, + { + "epoch": 1.01, + "learning_rate": 3.445903759459578e-05, + "loss": 3.5914, + "step": 949248 + }, + { + "epoch": 1.01, + "learning_rate": 3.445066802588899e-05, + "loss": 3.5711, + "step": 949760 + }, + { + "epoch": 1.01, + "learning_rate": 3.444228207837847e-05, + "loss": 3.5746, + "step": 950272 + }, + { + "epoch": 1.01, + "learning_rate": 3.443389613086796e-05, + "loss": 3.5599, + "step": 950784 + }, + { + "epoch": 1.01, + "learning_rate": 3.442551018335744e-05, + "loss": 3.5787, + "step": 951296 + }, + { + "epoch": 1.01, + "learning_rate": 3.4417140614650646e-05, + "loss": 3.5845, + "step": 951808 + }, + { + "epoch": 1.01, + "learning_rate": 3.4408754667140126e-05, + "loss": 3.584, + "step": 952320 + }, + { + "epoch": 1.01, + "learning_rate": 3.4400368719629606e-05, + "loss": 3.5831, + "step": 952832 + }, + { + "epoch": 1.01, + "learning_rate": 3.4391982772119086e-05, + "loss": 3.5834, + "step": 953344 + }, + { + "epoch": 1.01, + "learning_rate": 3.4383613203412295e-05, + "loss": 3.5948, + "step": 953856 + }, + { + "epoch": 1.01, + "learning_rate": 3.4375227255901775e-05, + "loss": 3.579, + "step": 954368 + }, + { + "epoch": 1.01, + "learning_rate": 3.4366841308391255e-05, + "loss": 3.5866, + "step": 954880 + }, + { + "epoch": 1.01, + "learning_rate": 3.4358455360880735e-05, + "loss": 3.5745, + "step": 955392 + }, + { + "epoch": 1.01, + "learning_rate": 3.4350069413370215e-05, + "loss": 3.5793, + "step": 955904 + }, + { + "epoch": 1.01, + "learning_rate": 3.4341699844663424e-05, + "loss": 3.5755, + "step": 956416 + }, + { + "epoch": 1.01, + "learning_rate": 3.433331389715291e-05, + "loss": 3.578, + "step": 956928 + }, + { + "epoch": 1.01, + "learning_rate": 3.432492794964239e-05, + "loss": 3.5877, + "step": 957440 + }, + { + "epoch": 1.01, + "learning_rate": 3.431654200213187e-05, + "loss": 3.5841, + "step": 957952 + }, + { + "epoch": 1.01, + "learning_rate": 3.430817243342508e-05, + "loss": 3.5888, + "step": 958464 + }, + { + "epoch": 1.01, + "learning_rate": 3.429978648591456e-05, + "loss": 3.5677, + "step": 958976 + }, + { + "epoch": 1.01, + "learning_rate": 3.429140053840404e-05, + "loss": 3.5804, + "step": 959488 + }, + { + "epoch": 1.01, + "learning_rate": 3.428301459089352e-05, + "loss": 3.5858, + "step": 960000 + }, + { + "epoch": 1.01, + "learning_rate": 3.4274628643383e-05, + "loss": 3.5722, + "step": 960512 + }, + { + "epoch": 1.01, + "learning_rate": 3.426625907467621e-05, + "loss": 3.5731, + "step": 961024 + }, + { + "epoch": 1.01, + "learning_rate": 3.425787312716569e-05, + "loss": 3.5846, + "step": 961536 + }, + { + "epoch": 1.02, + "learning_rate": 3.424948717965517e-05, + "loss": 3.5811, + "step": 962048 + }, + { + "epoch": 1.02, + "learning_rate": 3.424110123214465e-05, + "loss": 3.5774, + "step": 962560 + }, + { + "epoch": 1.02, + "learning_rate": 3.4232731663437865e-05, + "loss": 3.5716, + "step": 963072 + }, + { + "epoch": 1.02, + "learning_rate": 3.4224345715927345e-05, + "loss": 3.5809, + "step": 963584 + }, + { + "epoch": 1.02, + "learning_rate": 3.4215959768416825e-05, + "loss": 3.5894, + "step": 964096 + }, + { + "epoch": 1.02, + "learning_rate": 3.4207573820906304e-05, + "loss": 3.5833, + "step": 964608 + }, + { + "epoch": 1.02, + "learning_rate": 3.4199204252199514e-05, + "loss": 3.5665, + "step": 965120 + }, + { + "epoch": 1.02, + "learning_rate": 3.4190818304688994e-05, + "loss": 3.5794, + "step": 965632 + }, + { + "epoch": 1.02, + "learning_rate": 3.4182432357178473e-05, + "loss": 3.5717, + "step": 966144 + }, + { + "epoch": 1.02, + "learning_rate": 3.4174046409667953e-05, + "loss": 3.5833, + "step": 966656 + }, + { + "epoch": 1.02, + "learning_rate": 3.416567684096116e-05, + "loss": 3.5896, + "step": 967168 + }, + { + "epoch": 1.02, + "learning_rate": 3.415729089345064e-05, + "loss": 3.5747, + "step": 967680 + }, + { + "epoch": 1.02, + "learning_rate": 3.414890494594012e-05, + "loss": 3.5732, + "step": 968192 + }, + { + "epoch": 1.02, + "learning_rate": 3.41405189984296e-05, + "loss": 3.5718, + "step": 968704 + }, + { + "epoch": 1.02, + "learning_rate": 3.413214942972282e-05, + "loss": 3.5705, + "step": 969216 + }, + { + "epoch": 1.02, + "learning_rate": 3.41237634822123e-05, + "loss": 3.5674, + "step": 969728 + }, + { + "epoch": 1.02, + "learning_rate": 3.411537753470178e-05, + "loss": 3.5765, + "step": 970240 + }, + { + "epoch": 1.02, + "learning_rate": 3.410699158719125e-05, + "loss": 3.5738, + "step": 970752 + }, + { + "epoch": 1.02, + "learning_rate": 3.409862201848447e-05, + "loss": 3.5741, + "step": 971264 + }, + { + "epoch": 1.02, + "learning_rate": 3.409023607097395e-05, + "loss": 3.5671, + "step": 971776 + }, + { + "epoch": 1.02, + "learning_rate": 3.408185012346343e-05, + "loss": 3.575, + "step": 972288 + }, + { + "epoch": 1.02, + "learning_rate": 3.40734641759529e-05, + "loss": 3.5682, + "step": 972800 + }, + { + "epoch": 1.02, + "learning_rate": 3.4065094607246116e-05, + "loss": 3.5867, + "step": 973312 + }, + { + "epoch": 1.02, + "learning_rate": 3.4056708659735596e-05, + "loss": 3.5708, + "step": 973824 + }, + { + "epoch": 1.02, + "learning_rate": 3.404832271222507e-05, + "loss": 3.5855, + "step": 974336 + }, + { + "epoch": 1.02, + "learning_rate": 3.4039936764714556e-05, + "loss": 3.5838, + "step": 974848 + }, + { + "epoch": 1.02, + "learning_rate": 3.403156719600777e-05, + "loss": 3.5952, + "step": 975360 + }, + { + "epoch": 1.02, + "learning_rate": 3.402318124849725e-05, + "loss": 3.5754, + "step": 975872 + }, + { + "epoch": 1.02, + "learning_rate": 3.4014795300986725e-05, + "loss": 3.575, + "step": 976384 + }, + { + "epoch": 1.02, + "learning_rate": 3.4006409353476205e-05, + "loss": 3.5771, + "step": 976896 + }, + { + "epoch": 1.02, + "learning_rate": 3.3998023405965685e-05, + "loss": 3.5769, + "step": 977408 + }, + { + "epoch": 1.02, + "learning_rate": 3.39896538372589e-05, + "loss": 3.5745, + "step": 977920 + }, + { + "epoch": 1.02, + "learning_rate": 3.3981267889748374e-05, + "loss": 3.5774, + "step": 978432 + }, + { + "epoch": 1.02, + "learning_rate": 3.3972881942237854e-05, + "loss": 3.5747, + "step": 978944 + }, + { + "epoch": 1.02, + "learning_rate": 3.396451237353107e-05, + "loss": 3.5871, + "step": 979456 + }, + { + "epoch": 1.02, + "learning_rate": 3.395612642602054e-05, + "loss": 3.5756, + "step": 979968 + }, + { + "epoch": 1.02, + "learning_rate": 3.394774047851002e-05, + "loss": 3.5725, + "step": 980480 + }, + { + "epoch": 1.02, + "learning_rate": 3.393935453099951e-05, + "loss": 3.5788, + "step": 980992 + }, + { + "epoch": 1.02, + "learning_rate": 3.393096858348899e-05, + "loss": 3.572, + "step": 981504 + }, + { + "epoch": 1.02, + "learning_rate": 3.39225990147822e-05, + "loss": 3.5882, + "step": 982016 + }, + { + "epoch": 1.02, + "learning_rate": 3.391421306727168e-05, + "loss": 3.5717, + "step": 982528 + }, + { + "epoch": 1.02, + "learning_rate": 3.390582711976116e-05, + "loss": 3.5874, + "step": 983040 + }, + { + "epoch": 1.02, + "learning_rate": 3.389744117225064e-05, + "loss": 3.5674, + "step": 983552 + }, + { + "epoch": 1.02, + "learning_rate": 3.388907160354385e-05, + "loss": 3.5806, + "step": 984064 + }, + { + "epoch": 1.02, + "learning_rate": 3.388068565603333e-05, + "loss": 3.5769, + "step": 984576 + }, + { + "epoch": 1.02, + "learning_rate": 3.387229970852281e-05, + "loss": 3.5775, + "step": 985088 + }, + { + "epoch": 1.02, + "learning_rate": 3.386391376101229e-05, + "loss": 3.5736, + "step": 985600 + }, + { + "epoch": 1.02, + "learning_rate": 3.385552781350177e-05, + "loss": 3.5761, + "step": 986112 + }, + { + "epoch": 1.02, + "learning_rate": 3.384715824479498e-05, + "loss": 3.5839, + "step": 986624 + }, + { + "epoch": 1.02, + "learning_rate": 3.3838772297284463e-05, + "loss": 3.5902, + "step": 987136 + }, + { + "epoch": 1.02, + "learning_rate": 3.383038634977394e-05, + "loss": 3.57, + "step": 987648 + }, + { + "epoch": 1.02, + "learning_rate": 3.382200040226342e-05, + "loss": 3.5729, + "step": 988160 + }, + { + "epoch": 1.02, + "learning_rate": 3.381363083355663e-05, + "loss": 3.5783, + "step": 988672 + }, + { + "epoch": 1.02, + "learning_rate": 3.380524488604611e-05, + "loss": 3.5759, + "step": 989184 + }, + { + "epoch": 1.02, + "learning_rate": 3.379685893853559e-05, + "loss": 3.57, + "step": 989696 + }, + { + "epoch": 1.02, + "learning_rate": 3.378847299102507e-05, + "loss": 3.5855, + "step": 990208 + }, + { + "epoch": 1.02, + "learning_rate": 3.378010342231828e-05, + "loss": 3.5738, + "step": 990720 + }, + { + "epoch": 1.02, + "learning_rate": 3.377171747480776e-05, + "loss": 3.5829, + "step": 991232 + }, + { + "epoch": 1.02, + "learning_rate": 3.376333152729724e-05, + "loss": 3.5717, + "step": 991744 + }, + { + "epoch": 1.03, + "eval_loss": 3.8402984142303467, + "eval_runtime": 304.6228, + "eval_samples_per_second": 1252.667, + "eval_steps_per_second": 39.147, + "step": 992160 + }, + { + "epoch": 0.0, + "learning_rate": 3.375494557978672e-05, + "loss": 3.5755, + "step": 992256 + }, + { + "epoch": 0.0, + "learning_rate": 3.37465596322762e-05, + "loss": 3.5602, + "step": 992768 + }, + { + "epoch": 0.0, + "learning_rate": 3.373817368476568e-05, + "loss": 3.5799, + "step": 993280 + }, + { + "epoch": 0.0, + "learning_rate": 3.372978773725516e-05, + "loss": 3.5767, + "step": 993792 + }, + { + "epoch": 0.0, + "learning_rate": 3.372141816854838e-05, + "loss": 3.5757, + "step": 994304 + }, + { + "epoch": 0.0, + "learning_rate": 3.371303222103786e-05, + "loss": 3.5715, + "step": 994816 + }, + { + "epoch": 0.0, + "learning_rate": 3.370464627352734e-05, + "loss": 3.5728, + "step": 995328 + }, + { + "epoch": 0.0, + "learning_rate": 3.369626032601682e-05, + "loss": 3.5703, + "step": 995840 + }, + { + "epoch": 0.0, + "learning_rate": 3.3687890757310026e-05, + "loss": 3.568, + "step": 996352 + }, + { + "epoch": 0.0, + "learning_rate": 3.3679504809799506e-05, + "loss": 3.5727, + "step": 996864 + }, + { + "epoch": 0.0, + "learning_rate": 3.3671118862288986e-05, + "loss": 3.5692, + "step": 997376 + }, + { + "epoch": 0.0, + "learning_rate": 3.3662732914778466e-05, + "loss": 3.5798, + "step": 997888 + }, + { + "epoch": 0.0, + "learning_rate": 3.3654363346071675e-05, + "loss": 3.5878, + "step": 998400 + }, + { + "epoch": 0.0, + "learning_rate": 3.3645977398561155e-05, + "loss": 3.5628, + "step": 998912 + }, + { + "epoch": 0.0, + "learning_rate": 3.3637591451050635e-05, + "loss": 3.5667, + "step": 999424 + }, + { + "epoch": 0.0, + "learning_rate": 3.3629205503540115e-05, + "loss": 3.5611, + "step": 999936 + }, + { + "epoch": 0.0, + "learning_rate": 3.3620819556029595e-05, + "loss": 3.5659, + "step": 1000448 + }, + { + "epoch": 0.0, + "learning_rate": 3.361243360851908e-05, + "loss": 3.5709, + "step": 1000960 + }, + { + "epoch": 0.0, + "learning_rate": 3.360404766100856e-05, + "loss": 3.5625, + "step": 1001472 + }, + { + "epoch": 0.0, + "learning_rate": 3.3595661713498035e-05, + "loss": 3.5647, + "step": 1001984 + }, + { + "epoch": 0.0, + "learning_rate": 3.358729214479125e-05, + "loss": 3.5832, + "step": 1002496 + }, + { + "epoch": 0.0, + "learning_rate": 3.357890619728073e-05, + "loss": 3.5711, + "step": 1003008 + }, + { + "epoch": 0.0, + "learning_rate": 3.3570520249770204e-05, + "loss": 3.581, + "step": 1003520 + }, + { + "epoch": 0.0, + "learning_rate": 3.3562134302259684e-05, + "loss": 3.5784, + "step": 1004032 + }, + { + "epoch": 0.0, + "learning_rate": 3.35537647335529e-05, + "loss": 3.5654, + "step": 1004544 + }, + { + "epoch": 0.0, + "learning_rate": 3.354537878604238e-05, + "loss": 3.5728, + "step": 1005056 + }, + { + "epoch": 0.0, + "learning_rate": 3.353699283853185e-05, + "loss": 3.5641, + "step": 1005568 + }, + { + "epoch": 0.0, + "learning_rate": 3.352860689102133e-05, + "loss": 3.5708, + "step": 1006080 + }, + { + "epoch": 0.0, + "learning_rate": 3.352023732231455e-05, + "loss": 3.5628, + "step": 1006592 + }, + { + "epoch": 0.0, + "learning_rate": 3.3511851374804035e-05, + "loss": 3.5634, + "step": 1007104 + }, + { + "epoch": 0.01, + "learning_rate": 3.350346542729351e-05, + "loss": 3.574, + "step": 1007616 + }, + { + "epoch": 0.01, + "learning_rate": 3.349507947978299e-05, + "loss": 3.567, + "step": 1008128 + }, + { + "epoch": 0.01, + "learning_rate": 3.348669353227247e-05, + "loss": 3.5738, + "step": 1008640 + }, + { + "epoch": 0.01, + "learning_rate": 3.347832396356568e-05, + "loss": 3.5687, + "step": 1009152 + }, + { + "epoch": 0.01, + "learning_rate": 3.346993801605516e-05, + "loss": 3.5669, + "step": 1009664 + }, + { + "epoch": 0.01, + "learning_rate": 3.346155206854464e-05, + "loss": 3.5714, + "step": 1010176 + }, + { + "epoch": 0.01, + "learning_rate": 3.345316612103412e-05, + "loss": 3.5814, + "step": 1010688 + }, + { + "epoch": 0.01, + "learning_rate": 3.3444796552327326e-05, + "loss": 3.5508, + "step": 1011200 + }, + { + "epoch": 0.01, + "learning_rate": 3.3436410604816806e-05, + "loss": 3.5692, + "step": 1011712 + }, + { + "epoch": 0.01, + "learning_rate": 3.3428024657306286e-05, + "loss": 3.5654, + "step": 1012224 + }, + { + "epoch": 0.01, + "learning_rate": 3.341963870979577e-05, + "loss": 3.5576, + "step": 1012736 + }, + { + "epoch": 0.01, + "learning_rate": 3.341126914108898e-05, + "loss": 3.5624, + "step": 1013248 + }, + { + "epoch": 0.01, + "learning_rate": 3.340288319357846e-05, + "loss": 3.5766, + "step": 1013760 + }, + { + "epoch": 0.01, + "learning_rate": 3.339449724606794e-05, + "loss": 3.5719, + "step": 1014272 + }, + { + "epoch": 0.01, + "learning_rate": 3.338611129855742e-05, + "loss": 3.5725, + "step": 1014784 + }, + { + "epoch": 0.01, + "learning_rate": 3.337774172985063e-05, + "loss": 3.5718, + "step": 1015296 + }, + { + "epoch": 0.01, + "learning_rate": 3.336935578234011e-05, + "loss": 3.5735, + "step": 1015808 + }, + { + "epoch": 0.01, + "learning_rate": 3.336096983482959e-05, + "loss": 3.5643, + "step": 1016320 + }, + { + "epoch": 0.01, + "learning_rate": 3.335258388731907e-05, + "loss": 3.5498, + "step": 1016832 + }, + { + "epoch": 0.01, + "learning_rate": 3.334421431861228e-05, + "loss": 3.5764, + "step": 1017344 + }, + { + "epoch": 0.01, + "learning_rate": 3.333582837110176e-05, + "loss": 3.5636, + "step": 1017856 + }, + { + "epoch": 0.01, + "learning_rate": 3.332744242359124e-05, + "loss": 3.5681, + "step": 1018368 + }, + { + "epoch": 0.01, + "learning_rate": 3.3319056476080727e-05, + "loss": 3.5617, + "step": 1018880 + }, + { + "epoch": 0.01, + "learning_rate": 3.3310686907373936e-05, + "loss": 3.5582, + "step": 1019392 + }, + { + "epoch": 0.01, + "learning_rate": 3.3302300959863416e-05, + "loss": 3.5575, + "step": 1019904 + }, + { + "epoch": 0.01, + "learning_rate": 3.3293915012352896e-05, + "loss": 3.5548, + "step": 1020416 + }, + { + "epoch": 0.01, + "learning_rate": 3.3285529064842376e-05, + "loss": 3.5713, + "step": 1020928 + }, + { + "epoch": 0.01, + "learning_rate": 3.3277159496135585e-05, + "loss": 3.5555, + "step": 1021440 + }, + { + "epoch": 0.01, + "learning_rate": 3.3268773548625065e-05, + "loss": 3.5731, + "step": 1021952 + }, + { + "epoch": 0.01, + "learning_rate": 3.3260387601114545e-05, + "loss": 3.567, + "step": 1022464 + }, + { + "epoch": 0.01, + "learning_rate": 3.3252001653604025e-05, + "loss": 3.5509, + "step": 1022976 + }, + { + "epoch": 0.01, + "learning_rate": 3.3243632084897234e-05, + "loss": 3.5717, + "step": 1023488 + }, + { + "epoch": 0.01, + "learning_rate": 3.3235246137386714e-05, + "loss": 3.5547, + "step": 1024000 + }, + { + "epoch": 0.01, + "learning_rate": 3.3226860189876194e-05, + "loss": 3.5599, + "step": 1024512 + }, + { + "epoch": 0.01, + "learning_rate": 3.321847424236568e-05, + "loss": 3.5569, + "step": 1025024 + }, + { + "epoch": 0.01, + "learning_rate": 3.321010467365889e-05, + "loss": 3.5751, + "step": 1025536 + }, + { + "epoch": 0.01, + "learning_rate": 3.320171872614837e-05, + "loss": 3.5573, + "step": 1026048 + }, + { + "epoch": 0.01, + "learning_rate": 3.319333277863785e-05, + "loss": 3.5553, + "step": 1026560 + }, + { + "epoch": 0.01, + "learning_rate": 3.318494683112733e-05, + "loss": 3.5433, + "step": 1027072 + }, + { + "epoch": 0.01, + "learning_rate": 3.317657726242054e-05, + "loss": 3.5598, + "step": 1027584 + }, + { + "epoch": 0.01, + "learning_rate": 3.316819131491002e-05, + "loss": 3.5696, + "step": 1028096 + }, + { + "epoch": 0.01, + "learning_rate": 3.31598053673995e-05, + "loss": 3.5706, + "step": 1028608 + }, + { + "epoch": 0.01, + "learning_rate": 3.315141941988898e-05, + "loss": 3.5622, + "step": 1029120 + }, + { + "epoch": 0.01, + "learning_rate": 3.314304985118219e-05, + "loss": 3.5669, + "step": 1029632 + }, + { + "epoch": 0.01, + "learning_rate": 3.313466390367167e-05, + "loss": 3.5757, + "step": 1030144 + }, + { + "epoch": 0.01, + "learning_rate": 3.312627795616115e-05, + "loss": 3.5593, + "step": 1030656 + }, + { + "epoch": 0.01, + "learning_rate": 3.3117892008650634e-05, + "loss": 3.5669, + "step": 1031168 + }, + { + "epoch": 0.01, + "learning_rate": 3.3109506061140114e-05, + "loss": 3.5635, + "step": 1031680 + }, + { + "epoch": 0.01, + "learning_rate": 3.310113649243332e-05, + "loss": 3.5599, + "step": 1032192 + }, + { + "epoch": 0.01, + "learning_rate": 3.30927505449228e-05, + "loss": 3.5578, + "step": 1032704 + }, + { + "epoch": 0.01, + "learning_rate": 3.308436459741228e-05, + "loss": 3.5623, + "step": 1033216 + }, + { + "epoch": 0.01, + "learning_rate": 3.307597864990176e-05, + "loss": 3.5709, + "step": 1033728 + }, + { + "epoch": 0.01, + "learning_rate": 3.306760908119497e-05, + "loss": 3.5699, + "step": 1034240 + }, + { + "epoch": 0.01, + "learning_rate": 3.305922313368445e-05, + "loss": 3.5712, + "step": 1034752 + }, + { + "epoch": 0.01, + "learning_rate": 3.305083718617393e-05, + "loss": 3.5514, + "step": 1035264 + }, + { + "epoch": 0.01, + "learning_rate": 3.304245123866341e-05, + "loss": 3.5645, + "step": 1035776 + }, + { + "epoch": 0.01, + "learning_rate": 3.303408166995662e-05, + "loss": 3.5661, + "step": 1036288 + }, + { + "epoch": 0.01, + "learning_rate": 3.30256957224461e-05, + "loss": 3.5553, + "step": 1036800 + }, + { + "epoch": 0.01, + "learning_rate": 3.301730977493558e-05, + "loss": 3.5573, + "step": 1037312 + }, + { + "epoch": 0.01, + "learning_rate": 3.300892382742507e-05, + "loss": 3.566, + "step": 1037824 + }, + { + "epoch": 0.02, + "learning_rate": 3.300055425871828e-05, + "loss": 3.5609, + "step": 1038336 + }, + { + "epoch": 0.02, + "learning_rate": 3.2992168311207757e-05, + "loss": 3.5629, + "step": 1038848 + }, + { + "epoch": 0.02, + "learning_rate": 3.2983782363697237e-05, + "loss": 3.5569, + "step": 1039360 + }, + { + "epoch": 0.02, + "learning_rate": 3.2975396416186717e-05, + "loss": 3.5675, + "step": 1039872 + }, + { + "epoch": 0.02, + "learning_rate": 3.2967026847479926e-05, + "loss": 3.5715, + "step": 1040384 + }, + { + "epoch": 0.02, + "learning_rate": 3.2958640899969406e-05, + "loss": 3.567, + "step": 1040896 + }, + { + "epoch": 0.02, + "learning_rate": 3.2950254952458886e-05, + "loss": 3.5495, + "step": 1041408 + }, + { + "epoch": 0.02, + "learning_rate": 3.2941869004948365e-05, + "loss": 3.5617, + "step": 1041920 + }, + { + "epoch": 0.02, + "learning_rate": 3.2933499436241575e-05, + "loss": 3.5583, + "step": 1042432 + }, + { + "epoch": 0.02, + "learning_rate": 3.2925113488731055e-05, + "loss": 3.5627, + "step": 1042944 + }, + { + "epoch": 0.02, + "learning_rate": 3.2916727541220534e-05, + "loss": 3.5746, + "step": 1043456 + }, + { + "epoch": 0.02, + "learning_rate": 3.290834159371002e-05, + "loss": 3.5562, + "step": 1043968 + }, + { + "epoch": 0.02, + "learning_rate": 3.289997202500323e-05, + "loss": 3.5558, + "step": 1044480 + }, + { + "epoch": 0.02, + "learning_rate": 3.289158607749271e-05, + "loss": 3.5528, + "step": 1044992 + }, + { + "epoch": 0.02, + "learning_rate": 3.288320012998219e-05, + "loss": 3.5609, + "step": 1045504 + }, + { + "epoch": 0.02, + "learning_rate": 3.287481418247167e-05, + "loss": 3.5525, + "step": 1046016 + }, + { + "epoch": 0.02, + "learning_rate": 3.286644461376488e-05, + "loss": 3.5562, + "step": 1046528 + }, + { + "epoch": 0.02, + "learning_rate": 3.285805866625436e-05, + "loss": 3.5579, + "step": 1047040 + }, + { + "epoch": 0.02, + "learning_rate": 3.284967271874384e-05, + "loss": 3.5574, + "step": 1047552 + }, + { + "epoch": 0.02, + "learning_rate": 3.284128677123332e-05, + "loss": 3.5513, + "step": 1048064 + }, + { + "epoch": 0.02, + "learning_rate": 3.283291720252653e-05, + "loss": 3.5562, + "step": 1048576 + }, + { + "epoch": 0.02, + "learning_rate": 3.282453125501601e-05, + "loss": 3.5492, + "step": 1049088 + }, + { + "epoch": 0.02, + "learning_rate": 3.281614530750549e-05, + "loss": 3.5707, + "step": 1049600 + }, + { + "epoch": 0.02, + "learning_rate": 3.2807759359994975e-05, + "loss": 3.5563, + "step": 1050112 + }, + { + "epoch": 0.02, + "learning_rate": 3.2799373412484455e-05, + "loss": 3.5672, + "step": 1050624 + }, + { + "epoch": 0.02, + "learning_rate": 3.2791003843777664e-05, + "loss": 3.5671, + "step": 1051136 + }, + { + "epoch": 0.02, + "learning_rate": 3.2782617896267144e-05, + "loss": 3.5808, + "step": 1051648 + }, + { + "epoch": 0.02, + "learning_rate": 3.2774231948756624e-05, + "loss": 3.5571, + "step": 1052160 + }, + { + "epoch": 0.02, + "learning_rate": 3.276586238004983e-05, + "loss": 3.5614, + "step": 1052672 + }, + { + "epoch": 0.02, + "learning_rate": 3.275747643253931e-05, + "loss": 3.5618, + "step": 1053184 + }, + { + "epoch": 0.02, + "learning_rate": 3.274909048502879e-05, + "loss": 3.5576, + "step": 1053696 + }, + { + "epoch": 0.02, + "learning_rate": 3.274070453751827e-05, + "loss": 3.5576, + "step": 1054208 + }, + { + "epoch": 0.02, + "learning_rate": 3.273231859000775e-05, + "loss": 3.56, + "step": 1054720 + }, + { + "epoch": 0.02, + "learning_rate": 3.272394902130096e-05, + "loss": 3.5585, + "step": 1055232 + }, + { + "epoch": 0.02, + "learning_rate": 3.271556307379044e-05, + "loss": 3.5665, + "step": 1055744 + }, + { + "epoch": 0.02, + "learning_rate": 3.270717712627993e-05, + "loss": 3.5582, + "step": 1056256 + }, + { + "epoch": 0.02, + "learning_rate": 3.269879117876941e-05, + "loss": 3.5541, + "step": 1056768 + }, + { + "epoch": 0.02, + "learning_rate": 3.269042161006262e-05, + "loss": 3.5605, + "step": 1057280 + }, + { + "epoch": 0.02, + "learning_rate": 3.26820356625521e-05, + "loss": 3.5572, + "step": 1057792 + }, + { + "epoch": 0.02, + "learning_rate": 3.267364971504158e-05, + "loss": 3.5646, + "step": 1058304 + }, + { + "epoch": 0.02, + "learning_rate": 3.266526376753106e-05, + "loss": 3.5614, + "step": 1058816 + }, + { + "epoch": 0.02, + "learning_rate": 3.2656894198824267e-05, + "loss": 3.5644, + "step": 1059328 + }, + { + "epoch": 0.02, + "learning_rate": 3.2648508251313747e-05, + "loss": 3.5532, + "step": 1059840 + }, + { + "epoch": 0.02, + "learning_rate": 3.2640122303803226e-05, + "loss": 3.5594, + "step": 1060352 + }, + { + "epoch": 0.02, + "learning_rate": 3.26317363562927e-05, + "loss": 3.5643, + "step": 1060864 + }, + { + "epoch": 0.02, + "learning_rate": 3.2623366787585916e-05, + "loss": 3.5584, + "step": 1061376 + }, + { + "epoch": 0.02, + "learning_rate": 3.2614980840075395e-05, + "loss": 3.5587, + "step": 1061888 + }, + { + "epoch": 0.02, + "learning_rate": 3.260659489256488e-05, + "loss": 3.5588, + "step": 1062400 + }, + { + "epoch": 0.02, + "learning_rate": 3.2598208945054355e-05, + "loss": 3.5667, + "step": 1062912 + }, + { + "epoch": 0.02, + "learning_rate": 3.258983937634757e-05, + "loss": 3.5753, + "step": 1063424 + }, + { + "epoch": 0.02, + "learning_rate": 3.258145342883705e-05, + "loss": 3.5556, + "step": 1063936 + }, + { + "epoch": 0.02, + "learning_rate": 3.257306748132653e-05, + "loss": 3.5541, + "step": 1064448 + }, + { + "epoch": 0.02, + "learning_rate": 3.2564681533816004e-05, + "loss": 3.5576, + "step": 1064960 + }, + { + "epoch": 0.02, + "learning_rate": 3.255631196510922e-05, + "loss": 3.5612, + "step": 1065472 + }, + { + "epoch": 0.02, + "learning_rate": 3.25479260175987e-05, + "loss": 3.5508, + "step": 1065984 + }, + { + "epoch": 0.02, + "learning_rate": 3.253954007008817e-05, + "loss": 3.5705, + "step": 1066496 + }, + { + "epoch": 0.02, + "learning_rate": 3.253115412257765e-05, + "loss": 3.5595, + "step": 1067008 + }, + { + "epoch": 0.02, + "learning_rate": 3.252278455387087e-05, + "loss": 3.5667, + "step": 1067520 + }, + { + "epoch": 0.02, + "learning_rate": 3.251439860636035e-05, + "loss": 3.5508, + "step": 1068032 + }, + { + "epoch": 0.03, + "eval_loss": 3.841140031814575, + "eval_runtime": 305.9348, + "eval_samples_per_second": 1247.295, + "eval_steps_per_second": 38.979, + "step": 1068480 + }, + { + "epoch": 1.0, + "learning_rate": 3.250601265884983e-05, + "loss": 3.557, + "step": 1068544 + }, + { + "epoch": 1.0, + "learning_rate": 3.249762671133931e-05, + "loss": 3.5497, + "step": 1069056 + }, + { + "epoch": 1.0, + "learning_rate": 3.2489257142632525e-05, + "loss": 3.5609, + "step": 1069568 + }, + { + "epoch": 1.0, + "learning_rate": 3.2480871195122e-05, + "loss": 3.5604, + "step": 1070080 + }, + { + "epoch": 1.0, + "learning_rate": 3.247248524761148e-05, + "loss": 3.5612, + "step": 1070592 + }, + { + "epoch": 1.0, + "learning_rate": 3.246409930010096e-05, + "loss": 3.5552, + "step": 1071104 + }, + { + "epoch": 1.0, + "learning_rate": 3.2455729731394174e-05, + "loss": 3.5538, + "step": 1071616 + }, + { + "epoch": 1.0, + "learning_rate": 3.244734378388365e-05, + "loss": 3.554, + "step": 1072128 + }, + { + "epoch": 1.0, + "learning_rate": 3.243895783637313e-05, + "loss": 3.5516, + "step": 1072640 + }, + { + "epoch": 1.0, + "learning_rate": 3.243057188886261e-05, + "loss": 3.5564, + "step": 1073152 + }, + { + "epoch": 1.0, + "learning_rate": 3.242220232015582e-05, + "loss": 3.5527, + "step": 1073664 + }, + { + "epoch": 1.0, + "learning_rate": 3.24138163726453e-05, + "loss": 3.566, + "step": 1074176 + }, + { + "epoch": 1.0, + "learning_rate": 3.240543042513478e-05, + "loss": 3.5689, + "step": 1074688 + }, + { + "epoch": 1.0, + "learning_rate": 3.239704447762426e-05, + "loss": 3.5476, + "step": 1075200 + }, + { + "epoch": 1.0, + "learning_rate": 3.238867490891747e-05, + "loss": 3.5546, + "step": 1075712 + }, + { + "epoch": 1.0, + "learning_rate": 3.238028896140695e-05, + "loss": 3.542, + "step": 1076224 + }, + { + "epoch": 1.0, + "learning_rate": 3.237190301389643e-05, + "loss": 3.5517, + "step": 1076736 + }, + { + "epoch": 1.0, + "learning_rate": 3.236351706638591e-05, + "loss": 3.5492, + "step": 1077248 + }, + { + "epoch": 1.0, + "learning_rate": 3.235514749767912e-05, + "loss": 3.551, + "step": 1077760 + }, + { + "epoch": 1.0, + "learning_rate": 3.23467615501686e-05, + "loss": 3.5446, + "step": 1078272 + }, + { + "epoch": 1.0, + "learning_rate": 3.233837560265808e-05, + "loss": 3.5679, + "step": 1078784 + }, + { + "epoch": 1.0, + "learning_rate": 3.232998965514756e-05, + "loss": 3.5548, + "step": 1079296 + }, + { + "epoch": 1.0, + "learning_rate": 3.2321620086440777e-05, + "loss": 3.5628, + "step": 1079808 + }, + { + "epoch": 1.0, + "learning_rate": 3.2313234138930256e-05, + "loss": 3.5595, + "step": 1080320 + }, + { + "epoch": 1.0, + "learning_rate": 3.2304848191419736e-05, + "loss": 3.5555, + "step": 1080832 + }, + { + "epoch": 1.0, + "learning_rate": 3.2296462243909216e-05, + "loss": 3.5522, + "step": 1081344 + }, + { + "epoch": 1.0, + "learning_rate": 3.2288092675202425e-05, + "loss": 3.549, + "step": 1081856 + }, + { + "epoch": 1.0, + "learning_rate": 3.2279706727691905e-05, + "loss": 3.5546, + "step": 1082368 + }, + { + "epoch": 1.0, + "learning_rate": 3.2271320780181385e-05, + "loss": 3.547, + "step": 1082880 + }, + { + "epoch": 1.0, + "learning_rate": 3.2262934832670865e-05, + "loss": 3.548, + "step": 1083392 + }, + { + "epoch": 1.01, + "learning_rate": 3.2254565263964074e-05, + "loss": 3.5556, + "step": 1083904 + }, + { + "epoch": 1.01, + "learning_rate": 3.2246179316453554e-05, + "loss": 3.5493, + "step": 1084416 + }, + { + "epoch": 1.01, + "learning_rate": 3.2237793368943034e-05, + "loss": 3.5613, + "step": 1084928 + }, + { + "epoch": 1.01, + "learning_rate": 3.2229407421432514e-05, + "loss": 3.5517, + "step": 1085440 + }, + { + "epoch": 1.01, + "learning_rate": 3.222103785272573e-05, + "loss": 3.5525, + "step": 1085952 + }, + { + "epoch": 1.01, + "learning_rate": 3.221265190521521e-05, + "loss": 3.5612, + "step": 1086464 + }, + { + "epoch": 1.01, + "learning_rate": 3.220426595770469e-05, + "loss": 3.561, + "step": 1086976 + }, + { + "epoch": 1.01, + "learning_rate": 3.219588001019417e-05, + "loss": 3.5358, + "step": 1087488 + }, + { + "epoch": 1.01, + "learning_rate": 3.218751044148738e-05, + "loss": 3.5516, + "step": 1088000 + }, + { + "epoch": 1.01, + "learning_rate": 3.217912449397686e-05, + "loss": 3.5501, + "step": 1088512 + }, + { + "epoch": 1.01, + "learning_rate": 3.217073854646634e-05, + "loss": 3.54, + "step": 1089024 + }, + { + "epoch": 1.01, + "learning_rate": 3.216235259895582e-05, + "loss": 3.5524, + "step": 1089536 + }, + { + "epoch": 1.01, + "learning_rate": 3.215398303024903e-05, + "loss": 3.5625, + "step": 1090048 + }, + { + "epoch": 1.01, + "learning_rate": 3.214559708273851e-05, + "loss": 3.5528, + "step": 1090560 + }, + { + "epoch": 1.01, + "learning_rate": 3.213721113522799e-05, + "loss": 3.5564, + "step": 1091072 + }, + { + "epoch": 1.01, + "learning_rate": 3.212882518771747e-05, + "loss": 3.5584, + "step": 1091584 + }, + { + "epoch": 1.01, + "learning_rate": 3.2120455619010684e-05, + "loss": 3.5558, + "step": 1092096 + }, + { + "epoch": 1.01, + "learning_rate": 3.2112069671500164e-05, + "loss": 3.5499, + "step": 1092608 + }, + { + "epoch": 1.01, + "learning_rate": 3.2103683723989644e-05, + "loss": 3.5359, + "step": 1093120 + }, + { + "epoch": 1.01, + "learning_rate": 3.2095297776479124e-05, + "loss": 3.5567, + "step": 1093632 + }, + { + "epoch": 1.01, + "learning_rate": 3.208692820777233e-05, + "loss": 3.5493, + "step": 1094144 + }, + { + "epoch": 1.01, + "learning_rate": 3.207854226026181e-05, + "loss": 3.5505, + "step": 1094656 + }, + { + "epoch": 1.01, + "learning_rate": 3.207015631275129e-05, + "loss": 3.5465, + "step": 1095168 + }, + { + "epoch": 1.01, + "learning_rate": 3.206177036524077e-05, + "loss": 3.5428, + "step": 1095680 + }, + { + "epoch": 1.01, + "learning_rate": 3.205340079653398e-05, + "loss": 3.5383, + "step": 1096192 + }, + { + "epoch": 1.01, + "learning_rate": 3.204501484902346e-05, + "loss": 3.5401, + "step": 1096704 + }, + { + "epoch": 1.01, + "learning_rate": 3.203662890151294e-05, + "loss": 3.5584, + "step": 1097216 + }, + { + "epoch": 1.01, + "learning_rate": 3.202824295400242e-05, + "loss": 3.536, + "step": 1097728 + }, + { + "epoch": 1.01, + "learning_rate": 3.201987338529564e-05, + "loss": 3.5548, + "step": 1098240 + }, + { + "epoch": 1.01, + "learning_rate": 3.201148743778512e-05, + "loss": 3.5505, + "step": 1098752 + }, + { + "epoch": 1.01, + "learning_rate": 3.20031014902746e-05, + "loss": 3.5386, + "step": 1099264 + }, + { + "epoch": 1.01, + "learning_rate": 3.199471554276408e-05, + "loss": 3.551, + "step": 1099776 + }, + { + "epoch": 1.01, + "learning_rate": 3.1986345974057287e-05, + "loss": 3.5411, + "step": 1100288 + }, + { + "epoch": 1.01, + "learning_rate": 3.1977960026546766e-05, + "loss": 3.5456, + "step": 1100800 + }, + { + "epoch": 1.01, + "learning_rate": 3.1969574079036246e-05, + "loss": 3.5365, + "step": 1101312 + }, + { + "epoch": 1.01, + "learning_rate": 3.1961188131525726e-05, + "loss": 3.56, + "step": 1101824 + }, + { + "epoch": 1.01, + "learning_rate": 3.1952802184015206e-05, + "loss": 3.546, + "step": 1102336 + }, + { + "epoch": 1.01, + "learning_rate": 3.1944432615308415e-05, + "loss": 3.5353, + "step": 1102848 + }, + { + "epoch": 1.01, + "learning_rate": 3.1936046667797895e-05, + "loss": 3.5301, + "step": 1103360 + }, + { + "epoch": 1.01, + "learning_rate": 3.1927660720287375e-05, + "loss": 3.5428, + "step": 1103872 + }, + { + "epoch": 1.01, + "learning_rate": 3.1919274772776855e-05, + "loss": 3.5488, + "step": 1104384 + }, + { + "epoch": 1.01, + "learning_rate": 3.191090520407007e-05, + "loss": 3.5597, + "step": 1104896 + }, + { + "epoch": 1.01, + "learning_rate": 3.190251925655955e-05, + "loss": 3.5436, + "step": 1105408 + }, + { + "epoch": 1.01, + "learning_rate": 3.189413330904903e-05, + "loss": 3.5572, + "step": 1105920 + }, + { + "epoch": 1.01, + "learning_rate": 3.188574736153851e-05, + "loss": 3.5571, + "step": 1106432 + }, + { + "epoch": 1.01, + "learning_rate": 3.187737779283172e-05, + "loss": 3.5475, + "step": 1106944 + }, + { + "epoch": 1.01, + "learning_rate": 3.18689918453212e-05, + "loss": 3.5465, + "step": 1107456 + }, + { + "epoch": 1.01, + "learning_rate": 3.186060589781068e-05, + "loss": 3.5488, + "step": 1107968 + }, + { + "epoch": 1.01, + "learning_rate": 3.185221995030016e-05, + "loss": 3.5476, + "step": 1108480 + }, + { + "epoch": 1.01, + "learning_rate": 3.184385038159337e-05, + "loss": 3.5405, + "step": 1108992 + }, + { + "epoch": 1.01, + "learning_rate": 3.183546443408285e-05, + "loss": 3.5462, + "step": 1109504 + }, + { + "epoch": 1.01, + "learning_rate": 3.182707848657233e-05, + "loss": 3.5547, + "step": 1110016 + }, + { + "epoch": 1.01, + "learning_rate": 3.181869253906181e-05, + "loss": 3.5573, + "step": 1110528 + }, + { + "epoch": 1.01, + "learning_rate": 3.1810322970355025e-05, + "loss": 3.5524, + "step": 1111040 + }, + { + "epoch": 1.01, + "learning_rate": 3.1801937022844505e-05, + "loss": 3.536, + "step": 1111552 + }, + { + "epoch": 1.01, + "learning_rate": 3.1793551075333985e-05, + "loss": 3.547, + "step": 1112064 + }, + { + "epoch": 1.01, + "learning_rate": 3.1785165127823465e-05, + "loss": 3.5506, + "step": 1112576 + }, + { + "epoch": 1.01, + "learning_rate": 3.1776795559116674e-05, + "loss": 3.5443, + "step": 1113088 + }, + { + "epoch": 1.01, + "learning_rate": 3.1768409611606154e-05, + "loss": 3.5425, + "step": 1113600 + }, + { + "epoch": 1.01, + "learning_rate": 3.1760023664095634e-05, + "loss": 3.5465, + "step": 1114112 + }, + { + "epoch": 1.02, + "learning_rate": 3.1751637716585114e-05, + "loss": 3.5486, + "step": 1114624 + }, + { + "epoch": 1.02, + "learning_rate": 3.174326814787832e-05, + "loss": 3.5406, + "step": 1115136 + }, + { + "epoch": 1.02, + "learning_rate": 3.17348822003678e-05, + "loss": 3.5457, + "step": 1115648 + }, + { + "epoch": 1.02, + "learning_rate": 3.172649625285728e-05, + "loss": 3.5479, + "step": 1116160 + }, + { + "epoch": 1.02, + "learning_rate": 3.171811030534676e-05, + "loss": 3.551, + "step": 1116672 + }, + { + "epoch": 1.02, + "learning_rate": 3.170974073663998e-05, + "loss": 3.5552, + "step": 1117184 + }, + { + "epoch": 1.02, + "learning_rate": 3.170135478912946e-05, + "loss": 3.5326, + "step": 1117696 + }, + { + "epoch": 1.02, + "learning_rate": 3.169296884161894e-05, + "loss": 3.547, + "step": 1118208 + }, + { + "epoch": 1.02, + "learning_rate": 3.168458289410842e-05, + "loss": 3.5472, + "step": 1118720 + }, + { + "epoch": 1.02, + "learning_rate": 3.167621332540163e-05, + "loss": 3.5429, + "step": 1119232 + }, + { + "epoch": 1.02, + "learning_rate": 3.166782737789111e-05, + "loss": 3.5611, + "step": 1119744 + }, + { + "epoch": 1.02, + "learning_rate": 3.165944143038059e-05, + "loss": 3.5437, + "step": 1120256 + }, + { + "epoch": 1.02, + "learning_rate": 3.165105548287007e-05, + "loss": 3.5345, + "step": 1120768 + }, + { + "epoch": 1.02, + "learning_rate": 3.1642685914163276e-05, + "loss": 3.5422, + "step": 1121280 + }, + { + "epoch": 1.02, + "learning_rate": 3.1634299966652756e-05, + "loss": 3.5422, + "step": 1121792 + }, + { + "epoch": 1.02, + "learning_rate": 3.1625914019142236e-05, + "loss": 3.532, + "step": 1122304 + }, + { + "epoch": 1.02, + "learning_rate": 3.1617528071631716e-05, + "loss": 3.5433, + "step": 1122816 + }, + { + "epoch": 1.02, + "learning_rate": 3.160915850292493e-05, + "loss": 3.5417, + "step": 1123328 + }, + { + "epoch": 1.02, + "learning_rate": 3.160077255541441e-05, + "loss": 3.539, + "step": 1123840 + }, + { + "epoch": 1.02, + "learning_rate": 3.159238660790389e-05, + "loss": 3.5333, + "step": 1124352 + }, + { + "epoch": 1.02, + "learning_rate": 3.158400066039337e-05, + "loss": 3.546, + "step": 1124864 + }, + { + "epoch": 1.02, + "learning_rate": 3.157563109168658e-05, + "loss": 3.532, + "step": 1125376 + }, + { + "epoch": 1.02, + "learning_rate": 3.156724514417606e-05, + "loss": 3.5554, + "step": 1125888 + }, + { + "epoch": 1.02, + "learning_rate": 3.155885919666554e-05, + "loss": 3.5408, + "step": 1126400 + }, + { + "epoch": 1.02, + "learning_rate": 3.155047324915502e-05, + "loss": 3.549, + "step": 1126912 + }, + { + "epoch": 1.02, + "learning_rate": 3.154210368044823e-05, + "loss": 3.5512, + "step": 1127424 + }, + { + "epoch": 1.02, + "learning_rate": 3.153371773293771e-05, + "loss": 3.567, + "step": 1127936 + }, + { + "epoch": 1.02, + "learning_rate": 3.152533178542719e-05, + "loss": 3.5419, + "step": 1128448 + }, + { + "epoch": 1.02, + "learning_rate": 3.151694583791667e-05, + "loss": 3.5422, + "step": 1128960 + }, + { + "epoch": 1.02, + "learning_rate": 3.1508576269209886e-05, + "loss": 3.5487, + "step": 1129472 + }, + { + "epoch": 1.02, + "learning_rate": 3.1500190321699366e-05, + "loss": 3.5379, + "step": 1129984 + }, + { + "epoch": 1.02, + "learning_rate": 3.1491804374188846e-05, + "loss": 3.5442, + "step": 1130496 + }, + { + "epoch": 1.02, + "learning_rate": 3.1483418426678326e-05, + "loss": 3.5457, + "step": 1131008 + }, + { + "epoch": 1.02, + "learning_rate": 3.1475048857971535e-05, + "loss": 3.5436, + "step": 1131520 + }, + { + "epoch": 1.02, + "learning_rate": 3.1466662910461015e-05, + "loss": 3.5531, + "step": 1132032 + }, + { + "epoch": 1.02, + "learning_rate": 3.1458276962950495e-05, + "loss": 3.542, + "step": 1132544 + }, + { + "epoch": 1.02, + "learning_rate": 3.144989101543997e-05, + "loss": 3.5386, + "step": 1133056 + }, + { + "epoch": 1.02, + "learning_rate": 3.1441521446733184e-05, + "loss": 3.5441, + "step": 1133568 + }, + { + "epoch": 1.02, + "learning_rate": 3.1433135499222664e-05, + "loss": 3.5497, + "step": 1134080 + }, + { + "epoch": 1.02, + "learning_rate": 3.1424749551712144e-05, + "loss": 3.5428, + "step": 1134592 + }, + { + "epoch": 1.02, + "learning_rate": 3.1416363604201624e-05, + "loss": 3.5477, + "step": 1135104 + }, + { + "epoch": 1.02, + "learning_rate": 3.140799403549484e-05, + "loss": 3.5491, + "step": 1135616 + }, + { + "epoch": 1.02, + "learning_rate": 3.139960808798432e-05, + "loss": 3.5367, + "step": 1136128 + }, + { + "epoch": 1.02, + "learning_rate": 3.13912221404738e-05, + "loss": 3.5423, + "step": 1136640 + }, + { + "epoch": 1.02, + "learning_rate": 3.138283619296327e-05, + "loss": 3.5484, + "step": 1137152 + }, + { + "epoch": 1.02, + "learning_rate": 3.137446662425649e-05, + "loss": 3.5465, + "step": 1137664 + }, + { + "epoch": 1.02, + "learning_rate": 3.136608067674597e-05, + "loss": 3.5403, + "step": 1138176 + }, + { + "epoch": 1.02, + "learning_rate": 3.135769472923544e-05, + "loss": 3.5459, + "step": 1138688 + }, + { + "epoch": 1.02, + "learning_rate": 3.134930878172492e-05, + "loss": 3.5496, + "step": 1139200 + }, + { + "epoch": 1.02, + "learning_rate": 3.134093921301814e-05, + "loss": 3.5525, + "step": 1139712 + }, + { + "epoch": 1.02, + "learning_rate": 3.133255326550762e-05, + "loss": 3.5444, + "step": 1140224 + }, + { + "epoch": 1.02, + "learning_rate": 3.13241673179971e-05, + "loss": 3.5415, + "step": 1140736 + }, + { + "epoch": 1.02, + "learning_rate": 3.131578137048658e-05, + "loss": 3.5393, + "step": 1141248 + }, + { + "epoch": 1.02, + "learning_rate": 3.130741180177979e-05, + "loss": 3.5454, + "step": 1141760 + }, + { + "epoch": 1.02, + "learning_rate": 3.129902585426927e-05, + "loss": 3.5347, + "step": 1142272 + }, + { + "epoch": 1.02, + "learning_rate": 3.1290639906758746e-05, + "loss": 3.5566, + "step": 1142784 + }, + { + "epoch": 1.02, + "learning_rate": 3.1282253959248226e-05, + "loss": 3.5433, + "step": 1143296 + }, + { + "epoch": 1.02, + "learning_rate": 3.127388439054144e-05, + "loss": 3.5494, + "step": 1143808 + }, + { + "epoch": 1.02, + "learning_rate": 3.1265498443030915e-05, + "loss": 3.5374, + "step": 1144320 + }, + { + "epoch": 1.03, + "eval_loss": 3.840376377105713, + "eval_runtime": 305.3163, + "eval_samples_per_second": 1249.822, + "eval_steps_per_second": 39.058, + "step": 1144800 + }, + { + "epoch": 0.0, + "learning_rate": 3.1257112495520395e-05, + "loss": 3.4943, + "step": 1144832 + }, + { + "epoch": 0.0, + "learning_rate": 3.1248726548009875e-05, + "loss": 3.5357, + "step": 1145344 + }, + { + "epoch": 0.0, + "learning_rate": 3.1240340600499355e-05, + "loss": 3.5459, + "step": 1145856 + }, + { + "epoch": 0.0, + "learning_rate": 3.1231954652988835e-05, + "loss": 3.5447, + "step": 1146368 + }, + { + "epoch": 0.0, + "learning_rate": 3.122358508428205e-05, + "loss": 3.543, + "step": 1146880 + }, + { + "epoch": 0.0, + "learning_rate": 3.121519913677153e-05, + "loss": 3.5426, + "step": 1147392 + }, + { + "epoch": 0.0, + "learning_rate": 3.120681318926101e-05, + "loss": 3.5364, + "step": 1147904 + }, + { + "epoch": 0.0, + "learning_rate": 3.119842724175049e-05, + "loss": 3.5373, + "step": 1148416 + }, + { + "epoch": 0.0, + "learning_rate": 3.11900576730437e-05, + "loss": 3.5393, + "step": 1148928 + }, + { + "epoch": 0.0, + "learning_rate": 3.118167172553318e-05, + "loss": 3.5401, + "step": 1149440 + }, + { + "epoch": 0.0, + "learning_rate": 3.117328577802266e-05, + "loss": 3.5382, + "step": 1149952 + }, + { + "epoch": 0.0, + "learning_rate": 3.116489983051214e-05, + "loss": 3.5501, + "step": 1150464 + }, + { + "epoch": 0.0, + "learning_rate": 3.115653026180535e-05, + "loss": 3.5519, + "step": 1150976 + }, + { + "epoch": 0.0, + "learning_rate": 3.114814431429483e-05, + "loss": 3.5335, + "step": 1151488 + }, + { + "epoch": 0.0, + "learning_rate": 3.113975836678431e-05, + "loss": 3.5389, + "step": 1152000 + }, + { + "epoch": 0.0, + "learning_rate": 3.113137241927379e-05, + "loss": 3.5267, + "step": 1152512 + }, + { + "epoch": 0.0, + "learning_rate": 3.1123002850567e-05, + "loss": 3.5413, + "step": 1153024 + }, + { + "epoch": 0.0, + "learning_rate": 3.1114616903056485e-05, + "loss": 3.5295, + "step": 1153536 + }, + { + "epoch": 0.0, + "learning_rate": 3.1106230955545965e-05, + "loss": 3.5368, + "step": 1154048 + }, + { + "epoch": 0.0, + "learning_rate": 3.1097845008035445e-05, + "loss": 3.5335, + "step": 1154560 + }, + { + "epoch": 0.0, + "learning_rate": 3.1089475439328654e-05, + "loss": 3.5496, + "step": 1155072 + }, + { + "epoch": 0.0, + "learning_rate": 3.1081089491818134e-05, + "loss": 3.5421, + "step": 1155584 + }, + { + "epoch": 0.0, + "learning_rate": 3.1072703544307614e-05, + "loss": 3.5435, + "step": 1156096 + }, + { + "epoch": 0.0, + "learning_rate": 3.1064317596797093e-05, + "loss": 3.5468, + "step": 1156608 + }, + { + "epoch": 0.0, + "learning_rate": 3.10559480280903e-05, + "loss": 3.5431, + "step": 1157120 + }, + { + "epoch": 0.0, + "learning_rate": 3.104756208057978e-05, + "loss": 3.5338, + "step": 1157632 + }, + { + "epoch": 0.0, + "learning_rate": 3.103917613306926e-05, + "loss": 3.5314, + "step": 1158144 + }, + { + "epoch": 0.0, + "learning_rate": 3.103079018555874e-05, + "loss": 3.5388, + "step": 1158656 + }, + { + "epoch": 0.0, + "learning_rate": 3.102242061685195e-05, + "loss": 3.5293, + "step": 1159168 + }, + { + "epoch": 0.0, + "learning_rate": 3.101403466934144e-05, + "loss": 3.5326, + "step": 1159680 + }, + { + "epoch": 0.01, + "learning_rate": 3.100564872183092e-05, + "loss": 3.5384, + "step": 1160192 + }, + { + "epoch": 0.01, + "learning_rate": 3.09972627743204e-05, + "loss": 3.5365, + "step": 1160704 + }, + { + "epoch": 0.01, + "learning_rate": 3.098889320561361e-05, + "loss": 3.5443, + "step": 1161216 + }, + { + "epoch": 0.01, + "learning_rate": 3.098050725810309e-05, + "loss": 3.5366, + "step": 1161728 + }, + { + "epoch": 0.01, + "learning_rate": 3.097212131059257e-05, + "loss": 3.5379, + "step": 1162240 + }, + { + "epoch": 0.01, + "learning_rate": 3.096373536308205e-05, + "loss": 3.5484, + "step": 1162752 + }, + { + "epoch": 0.01, + "learning_rate": 3.0955365794375256e-05, + "loss": 3.5437, + "step": 1163264 + }, + { + "epoch": 0.01, + "learning_rate": 3.0946979846864736e-05, + "loss": 3.5177, + "step": 1163776 + }, + { + "epoch": 0.01, + "learning_rate": 3.0938593899354216e-05, + "loss": 3.5447, + "step": 1164288 + }, + { + "epoch": 0.01, + "learning_rate": 3.0930207951843696e-05, + "loss": 3.5302, + "step": 1164800 + }, + { + "epoch": 0.01, + "learning_rate": 3.0921838383136905e-05, + "loss": 3.5217, + "step": 1165312 + }, + { + "epoch": 0.01, + "learning_rate": 3.091345243562639e-05, + "loss": 3.539, + "step": 1165824 + }, + { + "epoch": 0.01, + "learning_rate": 3.090506648811587e-05, + "loss": 3.5488, + "step": 1166336 + }, + { + "epoch": 0.01, + "learning_rate": 3.089668054060535e-05, + "loss": 3.5359, + "step": 1166848 + }, + { + "epoch": 0.01, + "learning_rate": 3.088831097189856e-05, + "loss": 3.539, + "step": 1167360 + }, + { + "epoch": 0.01, + "learning_rate": 3.087992502438804e-05, + "loss": 3.5461, + "step": 1167872 + }, + { + "epoch": 0.01, + "learning_rate": 3.087153907687752e-05, + "loss": 3.5409, + "step": 1168384 + }, + { + "epoch": 0.01, + "learning_rate": 3.0863153129367e-05, + "loss": 3.5336, + "step": 1168896 + }, + { + "epoch": 0.01, + "learning_rate": 3.085478356066021e-05, + "loss": 3.5205, + "step": 1169408 + }, + { + "epoch": 0.01, + "learning_rate": 3.084639761314969e-05, + "loss": 3.5403, + "step": 1169920 + }, + { + "epoch": 0.01, + "learning_rate": 3.083801166563917e-05, + "loss": 3.5377, + "step": 1170432 + }, + { + "epoch": 0.01, + "learning_rate": 3.082962571812865e-05, + "loss": 3.5332, + "step": 1170944 + }, + { + "epoch": 0.01, + "learning_rate": 3.082125614942186e-05, + "loss": 3.5292, + "step": 1171456 + }, + { + "epoch": 0.01, + "learning_rate": 3.0812870201911346e-05, + "loss": 3.5264, + "step": 1171968 + }, + { + "epoch": 0.01, + "learning_rate": 3.0804484254400826e-05, + "loss": 3.53, + "step": 1172480 + }, + { + "epoch": 0.01, + "learning_rate": 3.0796098306890306e-05, + "loss": 3.5219, + "step": 1172992 + }, + { + "epoch": 0.01, + "learning_rate": 3.0787728738183515e-05, + "loss": 3.5432, + "step": 1173504 + }, + { + "epoch": 0.01, + "learning_rate": 3.0779342790672995e-05, + "loss": 3.5222, + "step": 1174016 + }, + { + "epoch": 0.01, + "learning_rate": 3.0770956843162475e-05, + "loss": 3.5386, + "step": 1174528 + }, + { + "epoch": 0.01, + "learning_rate": 3.0762570895651954e-05, + "loss": 3.5354, + "step": 1175040 + }, + { + "epoch": 0.01, + "learning_rate": 3.0754201326945164e-05, + "loss": 3.5249, + "step": 1175552 + }, + { + "epoch": 0.01, + "learning_rate": 3.0745815379434644e-05, + "loss": 3.5352, + "step": 1176064 + }, + { + "epoch": 0.01, + "learning_rate": 3.0737429431924124e-05, + "loss": 3.529, + "step": 1176576 + }, + { + "epoch": 0.01, + "learning_rate": 3.0729043484413603e-05, + "loss": 3.5274, + "step": 1177088 + }, + { + "epoch": 0.01, + "learning_rate": 3.072067391570681e-05, + "loss": 3.5188, + "step": 1177600 + }, + { + "epoch": 0.01, + "learning_rate": 3.07122879681963e-05, + "loss": 3.5497, + "step": 1178112 + }, + { + "epoch": 0.01, + "learning_rate": 3.070390202068578e-05, + "loss": 3.5289, + "step": 1178624 + }, + { + "epoch": 0.01, + "learning_rate": 3.069551607317526e-05, + "loss": 3.5217, + "step": 1179136 + }, + { + "epoch": 0.01, + "learning_rate": 3.068714650446847e-05, + "loss": 3.5143, + "step": 1179648 + }, + { + "epoch": 0.01, + "learning_rate": 3.067876055695795e-05, + "loss": 3.5283, + "step": 1180160 + }, + { + "epoch": 0.01, + "learning_rate": 3.067037460944743e-05, + "loss": 3.535, + "step": 1180672 + }, + { + "epoch": 0.01, + "learning_rate": 3.066198866193691e-05, + "loss": 3.5435, + "step": 1181184 + }, + { + "epoch": 0.01, + "learning_rate": 3.065361909323012e-05, + "loss": 3.5291, + "step": 1181696 + }, + { + "epoch": 0.01, + "learning_rate": 3.06452331457196e-05, + "loss": 3.5405, + "step": 1182208 + }, + { + "epoch": 0.01, + "learning_rate": 3.063684719820908e-05, + "loss": 3.5422, + "step": 1182720 + }, + { + "epoch": 0.01, + "learning_rate": 3.062846125069856e-05, + "loss": 3.5325, + "step": 1183232 + }, + { + "epoch": 0.01, + "learning_rate": 3.0620091681991766e-05, + "loss": 3.531, + "step": 1183744 + }, + { + "epoch": 0.01, + "learning_rate": 3.061170573448125e-05, + "loss": 3.5345, + "step": 1184256 + }, + { + "epoch": 0.01, + "learning_rate": 3.060331978697073e-05, + "loss": 3.5324, + "step": 1184768 + }, + { + "epoch": 0.01, + "learning_rate": 3.059493383946021e-05, + "loss": 3.528, + "step": 1185280 + }, + { + "epoch": 0.01, + "learning_rate": 3.058656427075342e-05, + "loss": 3.5295, + "step": 1185792 + }, + { + "epoch": 0.01, + "learning_rate": 3.05781783232429e-05, + "loss": 3.5392, + "step": 1186304 + }, + { + "epoch": 0.01, + "learning_rate": 3.056979237573238e-05, + "loss": 3.5382, + "step": 1186816 + }, + { + "epoch": 0.01, + "learning_rate": 3.056140642822186e-05, + "loss": 3.538, + "step": 1187328 + }, + { + "epoch": 0.01, + "learning_rate": 3.055303685951507e-05, + "loss": 3.5211, + "step": 1187840 + }, + { + "epoch": 0.01, + "learning_rate": 3.054465091200455e-05, + "loss": 3.5317, + "step": 1188352 + }, + { + "epoch": 0.01, + "learning_rate": 3.053626496449403e-05, + "loss": 3.5395, + "step": 1188864 + }, + { + "epoch": 0.01, + "learning_rate": 3.052787901698351e-05, + "loss": 3.5323, + "step": 1189376 + }, + { + "epoch": 0.01, + "learning_rate": 3.051950944827672e-05, + "loss": 3.5273, + "step": 1189888 + }, + { + "epoch": 0.01, + "learning_rate": 3.0511123500766203e-05, + "loss": 3.5305, + "step": 1190400 + }, + { + "epoch": 0.02, + "learning_rate": 3.0502737553255683e-05, + "loss": 3.5369, + "step": 1190912 + }, + { + "epoch": 0.02, + "learning_rate": 3.0494351605745163e-05, + "loss": 3.5246, + "step": 1191424 + }, + { + "epoch": 0.02, + "learning_rate": 3.0485982037038376e-05, + "loss": 3.5306, + "step": 1191936 + }, + { + "epoch": 0.02, + "learning_rate": 3.0477596089527856e-05, + "loss": 3.5312, + "step": 1192448 + }, + { + "epoch": 0.02, + "learning_rate": 3.0469210142017336e-05, + "loss": 3.5358, + "step": 1192960 + }, + { + "epoch": 0.02, + "learning_rate": 3.0460824194506815e-05, + "loss": 3.5395, + "step": 1193472 + }, + { + "epoch": 0.02, + "learning_rate": 3.0452454625800025e-05, + "loss": 3.5268, + "step": 1193984 + }, + { + "epoch": 0.02, + "learning_rate": 3.0444068678289505e-05, + "loss": 3.5259, + "step": 1194496 + }, + { + "epoch": 0.02, + "learning_rate": 3.0435682730778985e-05, + "loss": 3.533, + "step": 1195008 + }, + { + "epoch": 0.02, + "learning_rate": 3.0427296783268468e-05, + "loss": 3.5329, + "step": 1195520 + }, + { + "epoch": 0.02, + "learning_rate": 3.0418927214561677e-05, + "loss": 3.5417, + "step": 1196032 + }, + { + "epoch": 0.02, + "learning_rate": 3.0410541267051157e-05, + "loss": 3.5337, + "step": 1196544 + }, + { + "epoch": 0.02, + "learning_rate": 3.0402155319540637e-05, + "loss": 3.5203, + "step": 1197056 + }, + { + "epoch": 0.02, + "learning_rate": 3.0393769372030117e-05, + "loss": 3.525, + "step": 1197568 + }, + { + "epoch": 0.02, + "learning_rate": 3.038539980332333e-05, + "loss": 3.5352, + "step": 1198080 + }, + { + "epoch": 0.02, + "learning_rate": 3.037701385581281e-05, + "loss": 3.5103, + "step": 1198592 + }, + { + "epoch": 0.02, + "learning_rate": 3.036862790830229e-05, + "loss": 3.5298, + "step": 1199104 + }, + { + "epoch": 0.02, + "learning_rate": 3.0360241960791762e-05, + "loss": 3.5317, + "step": 1199616 + }, + { + "epoch": 0.02, + "learning_rate": 3.0351872392084978e-05, + "loss": 3.5243, + "step": 1200128 + }, + { + "epoch": 0.02, + "learning_rate": 3.0343486444574458e-05, + "loss": 3.5191, + "step": 1200640 + }, + { + "epoch": 0.02, + "learning_rate": 3.0335100497063938e-05, + "loss": 3.533, + "step": 1201152 + }, + { + "epoch": 0.02, + "learning_rate": 3.0326714549553415e-05, + "loss": 3.5155, + "step": 1201664 + }, + { + "epoch": 0.02, + "learning_rate": 3.031834498084663e-05, + "loss": 3.539, + "step": 1202176 + }, + { + "epoch": 0.02, + "learning_rate": 3.030995903333611e-05, + "loss": 3.5252, + "step": 1202688 + }, + { + "epoch": 0.02, + "learning_rate": 3.030157308582559e-05, + "loss": 3.5314, + "step": 1203200 + }, + { + "epoch": 0.02, + "learning_rate": 3.0293187138315067e-05, + "loss": 3.5381, + "step": 1203712 + }, + { + "epoch": 0.02, + "learning_rate": 3.0284817569608283e-05, + "loss": 3.5523, + "step": 1204224 + }, + { + "epoch": 0.02, + "learning_rate": 3.0276431622097763e-05, + "loss": 3.5294, + "step": 1204736 + }, + { + "epoch": 0.02, + "learning_rate": 3.0268045674587236e-05, + "loss": 3.5269, + "step": 1205248 + }, + { + "epoch": 0.02, + "learning_rate": 3.0259659727076716e-05, + "loss": 3.5346, + "step": 1205760 + }, + { + "epoch": 0.02, + "learning_rate": 3.0251290158369932e-05, + "loss": 3.5237, + "step": 1206272 + }, + { + "epoch": 0.02, + "learning_rate": 3.0242904210859412e-05, + "loss": 3.5272, + "step": 1206784 + }, + { + "epoch": 0.02, + "learning_rate": 3.023451826334889e-05, + "loss": 3.5297, + "step": 1207296 + }, + { + "epoch": 0.02, + "learning_rate": 3.022613231583837e-05, + "loss": 3.5304, + "step": 1207808 + }, + { + "epoch": 0.02, + "learning_rate": 3.0217762747131584e-05, + "loss": 3.5387, + "step": 1208320 + }, + { + "epoch": 0.02, + "learning_rate": 3.0209376799621064e-05, + "loss": 3.5308, + "step": 1208832 + }, + { + "epoch": 0.02, + "learning_rate": 3.0200990852110537e-05, + "loss": 3.5241, + "step": 1209344 + }, + { + "epoch": 0.02, + "learning_rate": 3.019260490460002e-05, + "loss": 3.5301, + "step": 1209856 + }, + { + "epoch": 0.02, + "learning_rate": 3.0184235335893237e-05, + "loss": 3.5324, + "step": 1210368 + }, + { + "epoch": 0.02, + "learning_rate": 3.017584938838271e-05, + "loss": 3.5244, + "step": 1210880 + }, + { + "epoch": 0.02, + "learning_rate": 3.016746344087219e-05, + "loss": 3.5331, + "step": 1211392 + }, + { + "epoch": 0.02, + "learning_rate": 3.015907749336167e-05, + "loss": 3.5372, + "step": 1211904 + }, + { + "epoch": 0.02, + "learning_rate": 3.0150707924654886e-05, + "loss": 3.5275, + "step": 1212416 + }, + { + "epoch": 0.02, + "learning_rate": 3.0142321977144362e-05, + "loss": 3.5218, + "step": 1212928 + }, + { + "epoch": 0.02, + "learning_rate": 3.0133936029633842e-05, + "loss": 3.5341, + "step": 1213440 + }, + { + "epoch": 0.02, + "learning_rate": 3.0125550082123322e-05, + "loss": 3.5318, + "step": 1213952 + }, + { + "epoch": 0.02, + "learning_rate": 3.0117180513416538e-05, + "loss": 3.5298, + "step": 1214464 + }, + { + "epoch": 0.02, + "learning_rate": 3.010879456590601e-05, + "loss": 3.5304, + "step": 1214976 + }, + { + "epoch": 0.02, + "learning_rate": 3.010040861839549e-05, + "loss": 3.539, + "step": 1215488 + }, + { + "epoch": 0.02, + "learning_rate": 3.0092022670884974e-05, + "loss": 3.536, + "step": 1216000 + }, + { + "epoch": 0.02, + "learning_rate": 3.0083653102178184e-05, + "loss": 3.531, + "step": 1216512 + }, + { + "epoch": 0.02, + "learning_rate": 3.0075267154667663e-05, + "loss": 3.5257, + "step": 1217024 + }, + { + "epoch": 0.02, + "learning_rate": 3.0066881207157143e-05, + "loss": 3.5273, + "step": 1217536 + }, + { + "epoch": 0.02, + "learning_rate": 3.0058495259646623e-05, + "loss": 3.5321, + "step": 1218048 + }, + { + "epoch": 0.02, + "learning_rate": 3.0050125690939836e-05, + "loss": 3.5173, + "step": 1218560 + }, + { + "epoch": 0.02, + "learning_rate": 3.0041739743429316e-05, + "loss": 3.5411, + "step": 1219072 + }, + { + "epoch": 0.02, + "learning_rate": 3.0033353795918796e-05, + "loss": 3.5333, + "step": 1219584 + }, + { + "epoch": 0.02, + "learning_rate": 3.0024967848408276e-05, + "loss": 3.5319, + "step": 1220096 + }, + { + "epoch": 0.02, + "learning_rate": 3.0016598279701485e-05, + "loss": 3.5215, + "step": 1220608 + }, + { + "epoch": 0.03, + "learning_rate": 3.0008212332190965e-05, + "loss": 3.5307, + "step": 1221120 + }, + { + "epoch": 0.03, + "eval_loss": 3.8424341678619385, + "eval_runtime": 304.9999, + "eval_samples_per_second": 1251.119, + "eval_steps_per_second": 39.098, + "step": 1221120 + }, + { + "epoch": 1.0, + "learning_rate": 2.9999826384680445e-05, + "loss": 3.5177, + "step": 1221632 + }, + { + "epoch": 1.0, + "learning_rate": 2.9991440437169928e-05, + "loss": 3.5275, + "step": 1222144 + }, + { + "epoch": 1.0, + "learning_rate": 2.9983070868463137e-05, + "loss": 3.531, + "step": 1222656 + }, + { + "epoch": 1.0, + "learning_rate": 2.9974684920952617e-05, + "loss": 3.5318, + "step": 1223168 + }, + { + "epoch": 1.0, + "learning_rate": 2.9966298973442097e-05, + "loss": 3.5314, + "step": 1223680 + }, + { + "epoch": 1.0, + "learning_rate": 2.9957929404735306e-05, + "loss": 3.5183, + "step": 1224192 + }, + { + "epoch": 1.0, + "learning_rate": 2.994954345722479e-05, + "loss": 3.5234, + "step": 1224704 + }, + { + "epoch": 1.0, + "learning_rate": 2.994115750971427e-05, + "loss": 3.5197, + "step": 1225216 + }, + { + "epoch": 1.0, + "learning_rate": 2.993277156220375e-05, + "loss": 3.532, + "step": 1225728 + }, + { + "epoch": 1.0, + "learning_rate": 2.992438561469323e-05, + "loss": 3.5185, + "step": 1226240 + }, + { + "epoch": 1.0, + "learning_rate": 2.991601604598644e-05, + "loss": 3.5383, + "step": 1226752 + }, + { + "epoch": 1.0, + "learning_rate": 2.990763009847592e-05, + "loss": 3.5396, + "step": 1227264 + }, + { + "epoch": 1.0, + "learning_rate": 2.98992441509654e-05, + "loss": 3.517, + "step": 1227776 + }, + { + "epoch": 1.0, + "learning_rate": 2.9890858203454882e-05, + "loss": 3.522, + "step": 1228288 + }, + { + "epoch": 1.0, + "learning_rate": 2.988248863474809e-05, + "loss": 3.5129, + "step": 1228800 + }, + { + "epoch": 1.0, + "learning_rate": 2.987410268723757e-05, + "loss": 3.5253, + "step": 1229312 + }, + { + "epoch": 1.0, + "learning_rate": 2.986571673972705e-05, + "loss": 3.5184, + "step": 1229824 + }, + { + "epoch": 1.0, + "learning_rate": 2.985733079221653e-05, + "loss": 3.5238, + "step": 1230336 + }, + { + "epoch": 1.0, + "learning_rate": 2.9848961223509743e-05, + "loss": 3.5194, + "step": 1230848 + }, + { + "epoch": 1.0, + "learning_rate": 2.9840575275999223e-05, + "loss": 3.5316, + "step": 1231360 + }, + { + "epoch": 1.0, + "learning_rate": 2.9832189328488703e-05, + "loss": 3.5256, + "step": 1231872 + }, + { + "epoch": 1.0, + "learning_rate": 2.9823803380978183e-05, + "loss": 3.5298, + "step": 1232384 + }, + { + "epoch": 1.0, + "learning_rate": 2.9815433812271392e-05, + "loss": 3.5301, + "step": 1232896 + }, + { + "epoch": 1.0, + "learning_rate": 2.9807047864760872e-05, + "loss": 3.5339, + "step": 1233408 + }, + { + "epoch": 1.0, + "learning_rate": 2.9798661917250352e-05, + "loss": 3.5206, + "step": 1233920 + }, + { + "epoch": 1.0, + "learning_rate": 2.9790275969739832e-05, + "loss": 3.5199, + "step": 1234432 + }, + { + "epoch": 1.0, + "learning_rate": 2.9781906401033045e-05, + "loss": 3.5261, + "step": 1234944 + }, + { + "epoch": 1.0, + "learning_rate": 2.9773520453522524e-05, + "loss": 3.5177, + "step": 1235456 + }, + { + "epoch": 1.0, + "learning_rate": 2.9765134506012004e-05, + "loss": 3.518, + "step": 1235968 + }, + { + "epoch": 1.01, + "learning_rate": 2.9756748558501484e-05, + "loss": 3.5202, + "step": 1236480 + }, + { + "epoch": 1.01, + "learning_rate": 2.9748378989794693e-05, + "loss": 3.5273, + "step": 1236992 + }, + { + "epoch": 1.01, + "learning_rate": 2.9739993042284177e-05, + "loss": 3.5295, + "step": 1237504 + }, + { + "epoch": 1.01, + "learning_rate": 2.9731607094773657e-05, + "loss": 3.5186, + "step": 1238016 + }, + { + "epoch": 1.01, + "learning_rate": 2.9723221147263137e-05, + "loss": 3.5243, + "step": 1238528 + }, + { + "epoch": 1.01, + "learning_rate": 2.9714851578556346e-05, + "loss": 3.533, + "step": 1239040 + }, + { + "epoch": 1.01, + "learning_rate": 2.9706465631045826e-05, + "loss": 3.5279, + "step": 1239552 + }, + { + "epoch": 1.01, + "learning_rate": 2.9698079683535306e-05, + "loss": 3.5081, + "step": 1240064 + }, + { + "epoch": 1.01, + "learning_rate": 2.9689710114828518e-05, + "loss": 3.5285, + "step": 1240576 + }, + { + "epoch": 1.01, + "learning_rate": 2.9681324167317998e-05, + "loss": 3.5133, + "step": 1241088 + }, + { + "epoch": 1.01, + "learning_rate": 2.9672938219807478e-05, + "loss": 3.5146, + "step": 1241600 + }, + { + "epoch": 1.01, + "learning_rate": 2.9664552272296958e-05, + "loss": 3.5204, + "step": 1242112 + }, + { + "epoch": 1.01, + "learning_rate": 2.9656182703590167e-05, + "loss": 3.53, + "step": 1242624 + }, + { + "epoch": 1.01, + "learning_rate": 2.9647796756079647e-05, + "loss": 3.5237, + "step": 1243136 + }, + { + "epoch": 1.01, + "learning_rate": 2.963941080856913e-05, + "loss": 3.5252, + "step": 1243648 + }, + { + "epoch": 1.01, + "learning_rate": 2.963102486105861e-05, + "loss": 3.5314, + "step": 1244160 + }, + { + "epoch": 1.01, + "learning_rate": 2.962265529235182e-05, + "loss": 3.5287, + "step": 1244672 + }, + { + "epoch": 1.01, + "learning_rate": 2.96142693448413e-05, + "loss": 3.5227, + "step": 1245184 + }, + { + "epoch": 1.01, + "learning_rate": 2.960588339733078e-05, + "loss": 3.5048, + "step": 1245696 + }, + { + "epoch": 1.01, + "learning_rate": 2.959749744982026e-05, + "loss": 3.5227, + "step": 1246208 + }, + { + "epoch": 1.01, + "learning_rate": 2.9589127881113472e-05, + "loss": 3.5247, + "step": 1246720 + }, + { + "epoch": 1.01, + "learning_rate": 2.9580741933602952e-05, + "loss": 3.5207, + "step": 1247232 + }, + { + "epoch": 1.01, + "learning_rate": 2.9572355986092432e-05, + "loss": 3.5139, + "step": 1247744 + }, + { + "epoch": 1.01, + "learning_rate": 2.9563970038581912e-05, + "loss": 3.5109, + "step": 1248256 + }, + { + "epoch": 1.01, + "learning_rate": 2.955560046987512e-05, + "loss": 3.5183, + "step": 1248768 + }, + { + "epoch": 1.01, + "learning_rate": 2.95472145223646e-05, + "loss": 3.5065, + "step": 1249280 + }, + { + "epoch": 1.01, + "learning_rate": 2.9538844953657813e-05, + "loss": 3.5266, + "step": 1249792 + }, + { + "epoch": 1.01, + "learning_rate": 2.9530459006147293e-05, + "loss": 3.5098, + "step": 1250304 + }, + { + "epoch": 1.01, + "learning_rate": 2.9522073058636773e-05, + "loss": 3.5255, + "step": 1250816 + }, + { + "epoch": 1.01, + "learning_rate": 2.9513687111126253e-05, + "loss": 3.5207, + "step": 1251328 + }, + { + "epoch": 1.01, + "learning_rate": 2.9505301163615733e-05, + "loss": 3.5058, + "step": 1251840 + }, + { + "epoch": 1.01, + "learning_rate": 2.9496915216105213e-05, + "loss": 3.5241, + "step": 1252352 + }, + { + "epoch": 1.01, + "learning_rate": 2.9488529268594693e-05, + "loss": 3.5164, + "step": 1252864 + }, + { + "epoch": 1.01, + "learning_rate": 2.9480159699887906e-05, + "loss": 3.5135, + "step": 1253376 + }, + { + "epoch": 1.01, + "learning_rate": 2.9471773752377385e-05, + "loss": 3.5076, + "step": 1253888 + }, + { + "epoch": 1.01, + "learning_rate": 2.9463387804866865e-05, + "loss": 3.5305, + "step": 1254400 + }, + { + "epoch": 1.01, + "learning_rate": 2.9455001857356345e-05, + "loss": 3.5182, + "step": 1254912 + }, + { + "epoch": 1.01, + "learning_rate": 2.9446632288649554e-05, + "loss": 3.5057, + "step": 1255424 + }, + { + "epoch": 1.01, + "learning_rate": 2.9438246341139038e-05, + "loss": 3.5036, + "step": 1255936 + }, + { + "epoch": 1.01, + "learning_rate": 2.9429860393628518e-05, + "loss": 3.5118, + "step": 1256448 + }, + { + "epoch": 1.01, + "learning_rate": 2.9421474446117998e-05, + "loss": 3.5211, + "step": 1256960 + }, + { + "epoch": 1.01, + "learning_rate": 2.9413104877411207e-05, + "loss": 3.53, + "step": 1257472 + }, + { + "epoch": 1.01, + "learning_rate": 2.9404718929900687e-05, + "loss": 3.5136, + "step": 1257984 + }, + { + "epoch": 1.01, + "learning_rate": 2.9396332982390167e-05, + "loss": 3.5282, + "step": 1258496 + }, + { + "epoch": 1.01, + "learning_rate": 2.9387947034879647e-05, + "loss": 3.5275, + "step": 1259008 + }, + { + "epoch": 1.01, + "learning_rate": 2.937957746617286e-05, + "loss": 3.519, + "step": 1259520 + }, + { + "epoch": 1.01, + "learning_rate": 2.937119151866234e-05, + "loss": 3.5141, + "step": 1260032 + }, + { + "epoch": 1.01, + "learning_rate": 2.936280557115182e-05, + "loss": 3.5231, + "step": 1260544 + }, + { + "epoch": 1.01, + "learning_rate": 2.93544196236413e-05, + "loss": 3.518, + "step": 1261056 + }, + { + "epoch": 1.01, + "learning_rate": 2.9346050054934508e-05, + "loss": 3.5153, + "step": 1261568 + }, + { + "epoch": 1.01, + "learning_rate": 2.933766410742399e-05, + "loss": 3.5171, + "step": 1262080 + }, + { + "epoch": 1.01, + "learning_rate": 2.932927815991347e-05, + "loss": 3.5197, + "step": 1262592 + }, + { + "epoch": 1.01, + "learning_rate": 2.932089221240295e-05, + "loss": 3.5263, + "step": 1263104 + }, + { + "epoch": 1.01, + "learning_rate": 2.931252264369616e-05, + "loss": 3.5228, + "step": 1263616 + }, + { + "epoch": 1.01, + "learning_rate": 2.930413669618564e-05, + "loss": 3.5123, + "step": 1264128 + }, + { + "epoch": 1.01, + "learning_rate": 2.929575074867512e-05, + "loss": 3.5132, + "step": 1264640 + }, + { + "epoch": 1.01, + "learning_rate": 2.92873648011646e-05, + "loss": 3.525, + "step": 1265152 + }, + { + "epoch": 1.01, + "learning_rate": 2.9278995232457813e-05, + "loss": 3.5163, + "step": 1265664 + }, + { + "epoch": 1.01, + "learning_rate": 2.9270609284947293e-05, + "loss": 3.5169, + "step": 1266176 + }, + { + "epoch": 1.01, + "learning_rate": 2.9262223337436773e-05, + "loss": 3.5134, + "step": 1266688 + }, + { + "epoch": 1.02, + "learning_rate": 2.9253837389926253e-05, + "loss": 3.5229, + "step": 1267200 + }, + { + "epoch": 1.02, + "learning_rate": 2.9245467821219462e-05, + "loss": 3.5116, + "step": 1267712 + }, + { + "epoch": 1.02, + "learning_rate": 2.9237081873708945e-05, + "loss": 3.5166, + "step": 1268224 + }, + { + "epoch": 1.02, + "learning_rate": 2.9228695926198425e-05, + "loss": 3.5159, + "step": 1268736 + }, + { + "epoch": 1.02, + "learning_rate": 2.9220309978687905e-05, + "loss": 3.5261, + "step": 1269248 + }, + { + "epoch": 1.02, + "learning_rate": 2.9211940409981114e-05, + "loss": 3.521, + "step": 1269760 + }, + { + "epoch": 1.02, + "learning_rate": 2.9203554462470594e-05, + "loss": 3.5198, + "step": 1270272 + }, + { + "epoch": 1.02, + "learning_rate": 2.9195168514960074e-05, + "loss": 3.5081, + "step": 1270784 + }, + { + "epoch": 1.02, + "learning_rate": 2.9186782567449554e-05, + "loss": 3.5159, + "step": 1271296 + }, + { + "epoch": 1.02, + "learning_rate": 2.9178412998742767e-05, + "loss": 3.5202, + "step": 1271808 + }, + { + "epoch": 1.02, + "learning_rate": 2.9170027051232246e-05, + "loss": 3.5268, + "step": 1272320 + }, + { + "epoch": 1.02, + "learning_rate": 2.9161641103721726e-05, + "loss": 3.5187, + "step": 1272832 + }, + { + "epoch": 1.02, + "learning_rate": 2.9153255156211206e-05, + "loss": 3.5087, + "step": 1273344 + }, + { + "epoch": 1.02, + "learning_rate": 2.9144885587504415e-05, + "loss": 3.5076, + "step": 1273856 + }, + { + "epoch": 1.02, + "learning_rate": 2.91364996399939e-05, + "loss": 3.5229, + "step": 1274368 + }, + { + "epoch": 1.02, + "learning_rate": 2.912811369248338e-05, + "loss": 3.4996, + "step": 1274880 + }, + { + "epoch": 1.02, + "learning_rate": 2.911972774497286e-05, + "loss": 3.5121, + "step": 1275392 + }, + { + "epoch": 1.02, + "learning_rate": 2.9111358176266068e-05, + "loss": 3.5163, + "step": 1275904 + }, + { + "epoch": 1.02, + "learning_rate": 2.9102972228755548e-05, + "loss": 3.5145, + "step": 1276416 + }, + { + "epoch": 1.02, + "learning_rate": 2.9094586281245028e-05, + "loss": 3.5053, + "step": 1276928 + }, + { + "epoch": 1.02, + "learning_rate": 2.9086200333734504e-05, + "loss": 3.5206, + "step": 1277440 + }, + { + "epoch": 1.02, + "learning_rate": 2.907783076502772e-05, + "loss": 3.5028, + "step": 1277952 + }, + { + "epoch": 1.02, + "learning_rate": 2.90694448175172e-05, + "loss": 3.5268, + "step": 1278464 + }, + { + "epoch": 1.02, + "learning_rate": 2.906105887000668e-05, + "loss": 3.5092, + "step": 1278976 + }, + { + "epoch": 1.02, + "learning_rate": 2.9052672922496153e-05, + "loss": 3.5194, + "step": 1279488 + }, + { + "epoch": 1.02, + "learning_rate": 2.904430335378937e-05, + "loss": 3.524, + "step": 1280000 + }, + { + "epoch": 1.02, + "learning_rate": 2.9035917406278853e-05, + "loss": 3.5386, + "step": 1280512 + }, + { + "epoch": 1.02, + "learning_rate": 2.9027531458768332e-05, + "loss": 3.5127, + "step": 1281024 + }, + { + "epoch": 1.02, + "learning_rate": 2.9019145511257806e-05, + "loss": 3.5185, + "step": 1281536 + }, + { + "epoch": 1.02, + "learning_rate": 2.901077594255102e-05, + "loss": 3.5192, + "step": 1282048 + }, + { + "epoch": 1.02, + "learning_rate": 2.90023899950405e-05, + "loss": 3.5063, + "step": 1282560 + }, + { + "epoch": 1.02, + "learning_rate": 2.8994004047529978e-05, + "loss": 3.5177, + "step": 1283072 + }, + { + "epoch": 1.02, + "learning_rate": 2.8985618100019458e-05, + "loss": 3.5157, + "step": 1283584 + }, + { + "epoch": 1.02, + "learning_rate": 2.8977248531312674e-05, + "loss": 3.5115, + "step": 1284096 + }, + { + "epoch": 1.02, + "learning_rate": 2.8968862583802154e-05, + "loss": 3.5296, + "step": 1284608 + }, + { + "epoch": 1.02, + "learning_rate": 2.8960476636291627e-05, + "loss": 3.5165, + "step": 1285120 + }, + { + "epoch": 1.02, + "learning_rate": 2.8952090688781107e-05, + "loss": 3.5106, + "step": 1285632 + }, + { + "epoch": 1.02, + "learning_rate": 2.8943721120074323e-05, + "loss": 3.5149, + "step": 1286144 + }, + { + "epoch": 1.02, + "learning_rate": 2.8935335172563803e-05, + "loss": 3.5186, + "step": 1286656 + }, + { + "epoch": 1.02, + "learning_rate": 2.892694922505328e-05, + "loss": 3.5104, + "step": 1287168 + }, + { + "epoch": 1.02, + "learning_rate": 2.891856327754276e-05, + "loss": 3.5238, + "step": 1287680 + }, + { + "epoch": 1.02, + "learning_rate": 2.8910193708835975e-05, + "loss": 3.5237, + "step": 1288192 + }, + { + "epoch": 1.02, + "learning_rate": 2.8901807761325452e-05, + "loss": 3.5135, + "step": 1288704 + }, + { + "epoch": 1.02, + "learning_rate": 2.8893421813814932e-05, + "loss": 3.5048, + "step": 1289216 + }, + { + "epoch": 1.02, + "learning_rate": 2.888503586630441e-05, + "loss": 3.5196, + "step": 1289728 + }, + { + "epoch": 1.02, + "learning_rate": 2.8876666297597628e-05, + "loss": 3.5156, + "step": 1290240 + }, + { + "epoch": 1.02, + "learning_rate": 2.88682803500871e-05, + "loss": 3.521, + "step": 1290752 + }, + { + "epoch": 1.02, + "learning_rate": 2.885989440257658e-05, + "loss": 3.5157, + "step": 1291264 + }, + { + "epoch": 1.02, + "learning_rate": 2.885150845506606e-05, + "loss": 3.5254, + "step": 1291776 + }, + { + "epoch": 1.02, + "learning_rate": 2.8843138886359276e-05, + "loss": 3.5181, + "step": 1292288 + }, + { + "epoch": 1.02, + "learning_rate": 2.8834752938848753e-05, + "loss": 3.5163, + "step": 1292800 + }, + { + "epoch": 1.02, + "learning_rate": 2.8826366991338233e-05, + "loss": 3.515, + "step": 1293312 + }, + { + "epoch": 1.02, + "learning_rate": 2.8817981043827713e-05, + "loss": 3.5112, + "step": 1293824 + }, + { + "epoch": 1.02, + "learning_rate": 2.8809611475120922e-05, + "loss": 3.521, + "step": 1294336 + }, + { + "epoch": 1.02, + "learning_rate": 2.8801241906414138e-05, + "loss": 3.5003, + "step": 1294848 + }, + { + "epoch": 1.02, + "learning_rate": 2.8792855958903618e-05, + "loss": 3.5266, + "step": 1295360 + }, + { + "epoch": 1.02, + "learning_rate": 2.87844700113931e-05, + "loss": 3.5229, + "step": 1295872 + }, + { + "epoch": 1.02, + "learning_rate": 2.8776084063882574e-05, + "loss": 3.5191, + "step": 1296384 + }, + { + "epoch": 1.02, + "learning_rate": 2.8767698116372054e-05, + "loss": 3.5072, + "step": 1296896 + }, + { + "epoch": 1.02, + "learning_rate": 2.8759312168861534e-05, + "loss": 3.5136, + "step": 1297408 + }, + { + "epoch": 1.03, + "eval_loss": 3.8437016010284424, + "eval_runtime": 304.6027, + "eval_samples_per_second": 1252.75, + "eval_steps_per_second": 39.149, + "step": 1297440 + }, + { + "epoch": 0.0, + "learning_rate": 2.8750926221351014e-05, + "loss": 3.5022, + "step": 1297920 + }, + { + "epoch": 0.0, + "learning_rate": 2.8742540273840494e-05, + "loss": 3.5147, + "step": 1298432 + }, + { + "epoch": 0.0, + "learning_rate": 2.8734154326329978e-05, + "loss": 3.521, + "step": 1298944 + }, + { + "epoch": 0.0, + "learning_rate": 2.8725784757623187e-05, + "loss": 3.5114, + "step": 1299456 + }, + { + "epoch": 0.0, + "learning_rate": 2.8717398810112667e-05, + "loss": 3.5177, + "step": 1299968 + }, + { + "epoch": 0.0, + "learning_rate": 2.8709012862602147e-05, + "loss": 3.5073, + "step": 1300480 + }, + { + "epoch": 0.0, + "learning_rate": 2.8700626915091627e-05, + "loss": 3.5097, + "step": 1300992 + }, + { + "epoch": 0.0, + "learning_rate": 2.869225734638484e-05, + "loss": 3.5082, + "step": 1301504 + }, + { + "epoch": 0.0, + "learning_rate": 2.868387139887432e-05, + "loss": 3.5158, + "step": 1302016 + }, + { + "epoch": 0.0, + "learning_rate": 2.86754854513638e-05, + "loss": 3.5075, + "step": 1302528 + }, + { + "epoch": 0.0, + "learning_rate": 2.866709950385328e-05, + "loss": 3.5247, + "step": 1303040 + }, + { + "epoch": 0.0, + "learning_rate": 2.8658729935146488e-05, + "loss": 3.5222, + "step": 1303552 + }, + { + "epoch": 0.0, + "learning_rate": 2.8650343987635968e-05, + "loss": 3.5096, + "step": 1304064 + }, + { + "epoch": 0.0, + "learning_rate": 2.8641958040125448e-05, + "loss": 3.506, + "step": 1304576 + }, + { + "epoch": 0.0, + "learning_rate": 2.863357209261493e-05, + "loss": 3.505, + "step": 1305088 + }, + { + "epoch": 0.0, + "learning_rate": 2.862520252390814e-05, + "loss": 3.5074, + "step": 1305600 + }, + { + "epoch": 0.0, + "learning_rate": 2.861681657639762e-05, + "loss": 3.5045, + "step": 1306112 + }, + { + "epoch": 0.0, + "learning_rate": 2.86084306288871e-05, + "loss": 3.5117, + "step": 1306624 + }, + { + "epoch": 0.0, + "learning_rate": 2.860004468137658e-05, + "loss": 3.5029, + "step": 1307136 + }, + { + "epoch": 0.0, + "learning_rate": 2.8591675112669793e-05, + "loss": 3.5229, + "step": 1307648 + }, + { + "epoch": 0.0, + "learning_rate": 2.8583289165159273e-05, + "loss": 3.5118, + "step": 1308160 + }, + { + "epoch": 0.0, + "learning_rate": 2.8574903217648753e-05, + "loss": 3.5182, + "step": 1308672 + }, + { + "epoch": 0.0, + "learning_rate": 2.8566517270138233e-05, + "loss": 3.5156, + "step": 1309184 + }, + { + "epoch": 0.0, + "learning_rate": 2.855814770143144e-05, + "loss": 3.5224, + "step": 1309696 + }, + { + "epoch": 0.0, + "learning_rate": 2.854976175392092e-05, + "loss": 3.4999, + "step": 1310208 + }, + { + "epoch": 0.0, + "learning_rate": 2.85413758064104e-05, + "loss": 3.5083, + "step": 1310720 + }, + { + "epoch": 0.0, + "learning_rate": 2.8532989858899885e-05, + "loss": 3.5064, + "step": 1311232 + }, + { + "epoch": 0.0, + "learning_rate": 2.8524620290193094e-05, + "loss": 3.5071, + "step": 1311744 + }, + { + "epoch": 0.0, + "learning_rate": 2.8516234342682574e-05, + "loss": 3.5043, + "step": 1312256 + }, + { + "epoch": 0.01, + "learning_rate": 2.8507848395172054e-05, + "loss": 3.5067, + "step": 1312768 + }, + { + "epoch": 0.01, + "learning_rate": 2.8499462447661534e-05, + "loss": 3.5167, + "step": 1313280 + }, + { + "epoch": 0.01, + "learning_rate": 2.8491092878954746e-05, + "loss": 3.5134, + "step": 1313792 + }, + { + "epoch": 0.01, + "learning_rate": 2.8482706931444226e-05, + "loss": 3.5023, + "step": 1314304 + }, + { + "epoch": 0.01, + "learning_rate": 2.8474320983933706e-05, + "loss": 3.5142, + "step": 1314816 + }, + { + "epoch": 0.01, + "learning_rate": 2.8465935036423186e-05, + "loss": 3.5217, + "step": 1315328 + }, + { + "epoch": 0.01, + "learning_rate": 2.8457565467716395e-05, + "loss": 3.5126, + "step": 1315840 + }, + { + "epoch": 0.01, + "learning_rate": 2.8449179520205875e-05, + "loss": 3.4954, + "step": 1316352 + }, + { + "epoch": 0.01, + "learning_rate": 2.8440793572695355e-05, + "loss": 3.5145, + "step": 1316864 + }, + { + "epoch": 0.01, + "learning_rate": 2.843240762518484e-05, + "loss": 3.497, + "step": 1317376 + }, + { + "epoch": 0.01, + "learning_rate": 2.8424038056478048e-05, + "loss": 3.5056, + "step": 1317888 + }, + { + "epoch": 0.01, + "learning_rate": 2.8415652108967528e-05, + "loss": 3.5065, + "step": 1318400 + }, + { + "epoch": 0.01, + "learning_rate": 2.8407266161457008e-05, + "loss": 3.5179, + "step": 1318912 + }, + { + "epoch": 0.01, + "learning_rate": 2.8398880213946488e-05, + "loss": 3.5086, + "step": 1319424 + }, + { + "epoch": 0.01, + "learning_rate": 2.83905106452397e-05, + "loss": 3.511, + "step": 1319936 + }, + { + "epoch": 0.01, + "learning_rate": 2.838212469772918e-05, + "loss": 3.5184, + "step": 1320448 + }, + { + "epoch": 0.01, + "learning_rate": 2.837373875021866e-05, + "loss": 3.5134, + "step": 1320960 + }, + { + "epoch": 0.01, + "learning_rate": 2.836535280270814e-05, + "loss": 3.5096, + "step": 1321472 + }, + { + "epoch": 0.01, + "learning_rate": 2.835698323400135e-05, + "loss": 3.4936, + "step": 1321984 + }, + { + "epoch": 0.01, + "learning_rate": 2.834859728649083e-05, + "loss": 3.5097, + "step": 1322496 + }, + { + "epoch": 0.01, + "learning_rate": 2.834021133898031e-05, + "loss": 3.5115, + "step": 1323008 + }, + { + "epoch": 0.01, + "learning_rate": 2.8331825391469792e-05, + "loss": 3.5071, + "step": 1323520 + }, + { + "epoch": 0.01, + "learning_rate": 2.8323455822763e-05, + "loss": 3.5036, + "step": 1324032 + }, + { + "epoch": 0.01, + "learning_rate": 2.831506987525248e-05, + "loss": 3.4908, + "step": 1324544 + }, + { + "epoch": 0.01, + "learning_rate": 2.830668392774196e-05, + "loss": 3.5079, + "step": 1325056 + }, + { + "epoch": 0.01, + "learning_rate": 2.829829798023144e-05, + "loss": 3.4912, + "step": 1325568 + }, + { + "epoch": 0.01, + "learning_rate": 2.8289928411524654e-05, + "loss": 3.5123, + "step": 1326080 + }, + { + "epoch": 0.01, + "learning_rate": 2.8281542464014134e-05, + "loss": 3.4992, + "step": 1326592 + }, + { + "epoch": 0.01, + "learning_rate": 2.8273156516503614e-05, + "loss": 3.5101, + "step": 1327104 + }, + { + "epoch": 0.01, + "learning_rate": 2.8264770568993094e-05, + "loss": 3.5089, + "step": 1327616 + }, + { + "epoch": 0.01, + "learning_rate": 2.8256401000286303e-05, + "loss": 3.4923, + "step": 1328128 + }, + { + "epoch": 0.01, + "learning_rate": 2.8248015052775783e-05, + "loss": 3.5056, + "step": 1328640 + }, + { + "epoch": 0.01, + "learning_rate": 2.8239629105265263e-05, + "loss": 3.5052, + "step": 1329152 + }, + { + "epoch": 0.01, + "learning_rate": 2.8231243157754746e-05, + "loss": 3.4991, + "step": 1329664 + }, + { + "epoch": 0.01, + "learning_rate": 2.8222873589047955e-05, + "loss": 3.4955, + "step": 1330176 + }, + { + "epoch": 0.01, + "learning_rate": 2.8214487641537435e-05, + "loss": 3.5164, + "step": 1330688 + }, + { + "epoch": 0.01, + "learning_rate": 2.8206101694026915e-05, + "loss": 3.5064, + "step": 1331200 + }, + { + "epoch": 0.01, + "learning_rate": 2.8197715746516395e-05, + "loss": 3.492, + "step": 1331712 + }, + { + "epoch": 0.01, + "learning_rate": 2.8189346177809607e-05, + "loss": 3.488, + "step": 1332224 + }, + { + "epoch": 0.01, + "learning_rate": 2.8180960230299087e-05, + "loss": 3.5008, + "step": 1332736 + }, + { + "epoch": 0.01, + "learning_rate": 2.8172574282788567e-05, + "loss": 3.5064, + "step": 1333248 + }, + { + "epoch": 0.01, + "learning_rate": 2.8164188335278047e-05, + "loss": 3.5154, + "step": 1333760 + }, + { + "epoch": 0.01, + "learning_rate": 2.8155818766571256e-05, + "loss": 3.5032, + "step": 1334272 + }, + { + "epoch": 0.01, + "learning_rate": 2.8147432819060736e-05, + "loss": 3.5161, + "step": 1334784 + }, + { + "epoch": 0.01, + "learning_rate": 2.8139046871550216e-05, + "loss": 3.5127, + "step": 1335296 + }, + { + "epoch": 0.01, + "learning_rate": 2.8130660924039696e-05, + "loss": 3.5104, + "step": 1335808 + }, + { + "epoch": 0.01, + "learning_rate": 2.812229135533291e-05, + "loss": 3.4974, + "step": 1336320 + }, + { + "epoch": 0.01, + "learning_rate": 2.811390540782239e-05, + "loss": 3.5121, + "step": 1336832 + }, + { + "epoch": 0.01, + "learning_rate": 2.810551946031187e-05, + "loss": 3.505, + "step": 1337344 + }, + { + "epoch": 0.01, + "learning_rate": 2.809713351280135e-05, + "loss": 3.5011, + "step": 1337856 + }, + { + "epoch": 0.01, + "learning_rate": 2.808876394409456e-05, + "loss": 3.5046, + "step": 1338368 + }, + { + "epoch": 0.01, + "learning_rate": 2.808037799658404e-05, + "loss": 3.5039, + "step": 1338880 + }, + { + "epoch": 0.01, + "learning_rate": 2.807200842787725e-05, + "loss": 3.518, + "step": 1339392 + }, + { + "epoch": 0.01, + "learning_rate": 2.806362248036673e-05, + "loss": 3.5059, + "step": 1339904 + }, + { + "epoch": 0.01, + "learning_rate": 2.805523653285621e-05, + "loss": 3.5012, + "step": 1340416 + }, + { + "epoch": 0.01, + "learning_rate": 2.804685058534569e-05, + "loss": 3.5015, + "step": 1340928 + }, + { + "epoch": 0.01, + "learning_rate": 2.803846463783517e-05, + "loss": 3.5111, + "step": 1341440 + }, + { + "epoch": 0.01, + "learning_rate": 2.803007869032465e-05, + "loss": 3.5037, + "step": 1341952 + }, + { + "epoch": 0.01, + "learning_rate": 2.8021692742814126e-05, + "loss": 3.5056, + "step": 1342464 + }, + { + "epoch": 0.01, + "learning_rate": 2.8013306795303606e-05, + "loss": 3.4983, + "step": 1342976 + }, + { + "epoch": 0.02, + "learning_rate": 2.8004937226596822e-05, + "loss": 3.5119, + "step": 1343488 + }, + { + "epoch": 0.02, + "learning_rate": 2.7996551279086302e-05, + "loss": 3.4998, + "step": 1344000 + }, + { + "epoch": 0.02, + "learning_rate": 2.798816533157578e-05, + "loss": 3.5015, + "step": 1344512 + }, + { + "epoch": 0.02, + "learning_rate": 2.797977938406526e-05, + "loss": 3.4991, + "step": 1345024 + }, + { + "epoch": 0.02, + "learning_rate": 2.7971409815358475e-05, + "loss": 3.5144, + "step": 1345536 + }, + { + "epoch": 0.02, + "learning_rate": 2.7963023867847948e-05, + "loss": 3.5103, + "step": 1346048 + }, + { + "epoch": 0.02, + "learning_rate": 2.7954637920337428e-05, + "loss": 3.5078, + "step": 1346560 + }, + { + "epoch": 0.02, + "learning_rate": 2.7946251972826908e-05, + "loss": 3.4954, + "step": 1347072 + }, + { + "epoch": 0.02, + "learning_rate": 2.7937882404120124e-05, + "loss": 3.5061, + "step": 1347584 + }, + { + "epoch": 0.02, + "learning_rate": 2.79294964566096e-05, + "loss": 3.5056, + "step": 1348096 + }, + { + "epoch": 0.02, + "learning_rate": 2.792111050909908e-05, + "loss": 3.5124, + "step": 1348608 + }, + { + "epoch": 0.02, + "learning_rate": 2.791272456158856e-05, + "loss": 3.5075, + "step": 1349120 + }, + { + "epoch": 0.02, + "learning_rate": 2.790435499288177e-05, + "loss": 3.4974, + "step": 1349632 + }, + { + "epoch": 0.02, + "learning_rate": 2.789596904537125e-05, + "loss": 3.494, + "step": 1350144 + }, + { + "epoch": 0.02, + "learning_rate": 2.7887583097860732e-05, + "loss": 3.5091, + "step": 1350656 + }, + { + "epoch": 0.02, + "learning_rate": 2.7879197150350212e-05, + "loss": 3.4819, + "step": 1351168 + }, + { + "epoch": 0.02, + "learning_rate": 2.787082758164342e-05, + "loss": 3.5007, + "step": 1351680 + }, + { + "epoch": 0.02, + "learning_rate": 2.78624416341329e-05, + "loss": 3.5026, + "step": 1352192 + }, + { + "epoch": 0.02, + "learning_rate": 2.785405568662238e-05, + "loss": 3.5027, + "step": 1352704 + }, + { + "epoch": 0.02, + "learning_rate": 2.784566973911186e-05, + "loss": 3.4899, + "step": 1353216 + }, + { + "epoch": 0.02, + "learning_rate": 2.7837300170405074e-05, + "loss": 3.5058, + "step": 1353728 + }, + { + "epoch": 0.02, + "learning_rate": 2.7828914222894554e-05, + "loss": 3.4967, + "step": 1354240 + }, + { + "epoch": 0.02, + "learning_rate": 2.7820528275384034e-05, + "loss": 3.5095, + "step": 1354752 + }, + { + "epoch": 0.02, + "learning_rate": 2.7812158706677243e-05, + "loss": 3.4983, + "step": 1355264 + }, + { + "epoch": 0.02, + "learning_rate": 2.7803772759166723e-05, + "loss": 3.5001, + "step": 1355776 + }, + { + "epoch": 0.02, + "learning_rate": 2.7795386811656203e-05, + "loss": 3.5158, + "step": 1356288 + }, + { + "epoch": 0.02, + "learning_rate": 2.7787000864145686e-05, + "loss": 3.523, + "step": 1356800 + }, + { + "epoch": 0.02, + "learning_rate": 2.7778631295438895e-05, + "loss": 3.4991, + "step": 1357312 + }, + { + "epoch": 0.02, + "learning_rate": 2.7770245347928375e-05, + "loss": 3.5015, + "step": 1357824 + }, + { + "epoch": 0.02, + "learning_rate": 2.776187577922159e-05, + "loss": 3.5088, + "step": 1358336 + }, + { + "epoch": 0.02, + "learning_rate": 2.775348983171107e-05, + "loss": 3.4943, + "step": 1358848 + }, + { + "epoch": 0.02, + "learning_rate": 2.7745103884200548e-05, + "loss": 3.5025, + "step": 1359360 + }, + { + "epoch": 0.02, + "learning_rate": 2.7736717936690028e-05, + "loss": 3.504, + "step": 1359872 + }, + { + "epoch": 0.02, + "learning_rate": 2.7728331989179507e-05, + "loss": 3.4999, + "step": 1360384 + }, + { + "epoch": 0.02, + "learning_rate": 2.7719946041668987e-05, + "loss": 3.5152, + "step": 1360896 + }, + { + "epoch": 0.02, + "learning_rate": 2.7711560094158467e-05, + "loss": 3.5011, + "step": 1361408 + }, + { + "epoch": 0.02, + "learning_rate": 2.7703174146647947e-05, + "loss": 3.5018, + "step": 1361920 + }, + { + "epoch": 0.02, + "learning_rate": 2.7694804577941156e-05, + "loss": 3.4977, + "step": 1362432 + }, + { + "epoch": 0.02, + "learning_rate": 2.768641863043064e-05, + "loss": 3.5055, + "step": 1362944 + }, + { + "epoch": 0.02, + "learning_rate": 2.767803268292012e-05, + "loss": 3.4978, + "step": 1363456 + }, + { + "epoch": 0.02, + "learning_rate": 2.76696467354096e-05, + "loss": 3.511, + "step": 1363968 + }, + { + "epoch": 0.02, + "learning_rate": 2.766127716670281e-05, + "loss": 3.5131, + "step": 1364480 + }, + { + "epoch": 0.02, + "learning_rate": 2.765289121919229e-05, + "loss": 3.5025, + "step": 1364992 + }, + { + "epoch": 0.02, + "learning_rate": 2.764450527168177e-05, + "loss": 3.4881, + "step": 1365504 + }, + { + "epoch": 0.02, + "learning_rate": 2.763611932417125e-05, + "loss": 3.5104, + "step": 1366016 + }, + { + "epoch": 0.02, + "learning_rate": 2.762774975546446e-05, + "loss": 3.5018, + "step": 1366528 + }, + { + "epoch": 0.02, + "learning_rate": 2.761936380795394e-05, + "loss": 3.5061, + "step": 1367040 + }, + { + "epoch": 0.02, + "learning_rate": 2.761097786044342e-05, + "loss": 3.5026, + "step": 1367552 + }, + { + "epoch": 0.02, + "learning_rate": 2.76025919129329e-05, + "loss": 3.5094, + "step": 1368064 + }, + { + "epoch": 0.02, + "learning_rate": 2.759422234422611e-05, + "loss": 3.5054, + "step": 1368576 + }, + { + "epoch": 0.02, + "learning_rate": 2.7585836396715593e-05, + "loss": 3.511, + "step": 1369088 + }, + { + "epoch": 0.02, + "learning_rate": 2.7577450449205073e-05, + "loss": 3.4978, + "step": 1369600 + }, + { + "epoch": 0.02, + "learning_rate": 2.7569064501694553e-05, + "loss": 3.4975, + "step": 1370112 + }, + { + "epoch": 0.02, + "learning_rate": 2.7560694932987762e-05, + "loss": 3.5084, + "step": 1370624 + }, + { + "epoch": 0.02, + "learning_rate": 2.755232536428097e-05, + "loss": 3.4911, + "step": 1371136 + }, + { + "epoch": 0.02, + "learning_rate": 2.7543939416770455e-05, + "loss": 3.5094, + "step": 1371648 + }, + { + "epoch": 0.02, + "learning_rate": 2.7535553469259935e-05, + "loss": 3.5163, + "step": 1372160 + }, + { + "epoch": 0.02, + "learning_rate": 2.7527167521749415e-05, + "loss": 3.5041, + "step": 1372672 + }, + { + "epoch": 0.02, + "learning_rate": 2.7518781574238895e-05, + "loss": 3.4947, + "step": 1373184 + }, + { + "epoch": 0.02, + "learning_rate": 2.7510395626728375e-05, + "loss": 3.5008, + "step": 1373696 + }, + { + "epoch": 0.03, + "eval_loss": 3.845893621444702, + "eval_runtime": 308.4098, + "eval_samples_per_second": 1237.286, + "eval_steps_per_second": 38.666, + "step": 1373760 + }, + { + "epoch": 1.0, + "learning_rate": 2.7502009679217855e-05, + "loss": 3.496, + "step": 1374208 + }, + { + "epoch": 1.0, + "learning_rate": 2.7493623731707335e-05, + "loss": 3.5001, + "step": 1374720 + }, + { + "epoch": 1.0, + "learning_rate": 2.7485254163000547e-05, + "loss": 3.506, + "step": 1375232 + }, + { + "epoch": 1.0, + "learning_rate": 2.7476868215490027e-05, + "loss": 3.501, + "step": 1375744 + }, + { + "epoch": 1.0, + "learning_rate": 2.7468482267979507e-05, + "loss": 3.5075, + "step": 1376256 + }, + { + "epoch": 1.0, + "learning_rate": 2.7460096320468987e-05, + "loss": 3.4911, + "step": 1376768 + }, + { + "epoch": 1.0, + "learning_rate": 2.7451726751762196e-05, + "loss": 3.5019, + "step": 1377280 + }, + { + "epoch": 1.0, + "learning_rate": 2.7443340804251676e-05, + "loss": 3.493, + "step": 1377792 + }, + { + "epoch": 1.0, + "learning_rate": 2.7434954856741156e-05, + "loss": 3.5014, + "step": 1378304 + }, + { + "epoch": 1.0, + "learning_rate": 2.742656890923064e-05, + "loss": 3.4991, + "step": 1378816 + }, + { + "epoch": 1.0, + "learning_rate": 2.741819934052385e-05, + "loss": 3.5045, + "step": 1379328 + }, + { + "epoch": 1.0, + "learning_rate": 2.740981339301333e-05, + "loss": 3.5121, + "step": 1379840 + }, + { + "epoch": 1.0, + "learning_rate": 2.740142744550281e-05, + "loss": 3.4941, + "step": 1380352 + }, + { + "epoch": 1.0, + "learning_rate": 2.7393057876796017e-05, + "loss": 3.4944, + "step": 1380864 + }, + { + "epoch": 1.0, + "learning_rate": 2.73846719292855e-05, + "loss": 3.4942, + "step": 1381376 + }, + { + "epoch": 1.0, + "learning_rate": 2.737628598177498e-05, + "loss": 3.4934, + "step": 1381888 + }, + { + "epoch": 1.0, + "learning_rate": 2.736790003426446e-05, + "loss": 3.4894, + "step": 1382400 + }, + { + "epoch": 1.0, + "learning_rate": 2.735953046555767e-05, + "loss": 3.4992, + "step": 1382912 + }, + { + "epoch": 1.0, + "learning_rate": 2.735114451804715e-05, + "loss": 3.4876, + "step": 1383424 + }, + { + "epoch": 1.0, + "learning_rate": 2.734275857053663e-05, + "loss": 3.5131, + "step": 1383936 + }, + { + "epoch": 1.0, + "learning_rate": 2.733437262302611e-05, + "loss": 3.4952, + "step": 1384448 + }, + { + "epoch": 1.0, + "learning_rate": 2.7326003054319322e-05, + "loss": 3.5075, + "step": 1384960 + }, + { + "epoch": 1.0, + "learning_rate": 2.7317617106808802e-05, + "loss": 3.5049, + "step": 1385472 + }, + { + "epoch": 1.0, + "learning_rate": 2.7309231159298282e-05, + "loss": 3.5086, + "step": 1385984 + }, + { + "epoch": 1.0, + "learning_rate": 2.7300845211787762e-05, + "loss": 3.4855, + "step": 1386496 + }, + { + "epoch": 1.0, + "learning_rate": 2.729247564308097e-05, + "loss": 3.4979, + "step": 1387008 + }, + { + "epoch": 1.0, + "learning_rate": 2.7284089695570454e-05, + "loss": 3.4913, + "step": 1387520 + }, + { + "epoch": 1.0, + "learning_rate": 2.7275703748059934e-05, + "loss": 3.4959, + "step": 1388032 + }, + { + "epoch": 1.0, + "learning_rate": 2.7267317800549414e-05, + "loss": 3.4903, + "step": 1388544 + }, + { + "epoch": 1.01, + "learning_rate": 2.7258948231842623e-05, + "loss": 3.4923, + "step": 1389056 + }, + { + "epoch": 1.01, + "learning_rate": 2.7250562284332103e-05, + "loss": 3.5059, + "step": 1389568 + }, + { + "epoch": 1.01, + "learning_rate": 2.7242176336821583e-05, + "loss": 3.5013, + "step": 1390080 + }, + { + "epoch": 1.01, + "learning_rate": 2.7233790389311063e-05, + "loss": 3.4886, + "step": 1390592 + }, + { + "epoch": 1.01, + "learning_rate": 2.7225420820604276e-05, + "loss": 3.5047, + "step": 1391104 + }, + { + "epoch": 1.01, + "learning_rate": 2.7217034873093756e-05, + "loss": 3.5013, + "step": 1391616 + }, + { + "epoch": 1.01, + "learning_rate": 2.7208648925583236e-05, + "loss": 3.5004, + "step": 1392128 + }, + { + "epoch": 1.01, + "learning_rate": 2.7200262978072716e-05, + "loss": 3.4841, + "step": 1392640 + }, + { + "epoch": 1.01, + "learning_rate": 2.7191893409365925e-05, + "loss": 3.5006, + "step": 1393152 + }, + { + "epoch": 1.01, + "learning_rate": 2.7183507461855405e-05, + "loss": 3.4845, + "step": 1393664 + }, + { + "epoch": 1.01, + "learning_rate": 2.7175121514344888e-05, + "loss": 3.4957, + "step": 1394176 + }, + { + "epoch": 1.01, + "learning_rate": 2.7166735566834368e-05, + "loss": 3.4922, + "step": 1394688 + }, + { + "epoch": 1.01, + "learning_rate": 2.7158365998127577e-05, + "loss": 3.5013, + "step": 1395200 + }, + { + "epoch": 1.01, + "learning_rate": 2.7149980050617057e-05, + "loss": 3.4977, + "step": 1395712 + }, + { + "epoch": 1.01, + "learning_rate": 2.7141594103106537e-05, + "loss": 3.4977, + "step": 1396224 + }, + { + "epoch": 1.01, + "learning_rate": 2.7133208155596017e-05, + "loss": 3.5045, + "step": 1396736 + }, + { + "epoch": 1.01, + "learning_rate": 2.712483858688923e-05, + "loss": 3.5018, + "step": 1397248 + }, + { + "epoch": 1.01, + "learning_rate": 2.711645263937871e-05, + "loss": 3.4982, + "step": 1397760 + }, + { + "epoch": 1.01, + "learning_rate": 2.710806669186819e-05, + "loss": 3.4831, + "step": 1398272 + }, + { + "epoch": 1.01, + "learning_rate": 2.709968074435767e-05, + "loss": 3.4928, + "step": 1398784 + }, + { + "epoch": 1.01, + "learning_rate": 2.709131117565088e-05, + "loss": 3.5013, + "step": 1399296 + }, + { + "epoch": 1.01, + "learning_rate": 2.708292522814036e-05, + "loss": 3.4951, + "step": 1399808 + }, + { + "epoch": 1.01, + "learning_rate": 2.7074539280629842e-05, + "loss": 3.4889, + "step": 1400320 + }, + { + "epoch": 1.01, + "learning_rate": 2.7066153333119322e-05, + "loss": 3.4818, + "step": 1400832 + }, + { + "epoch": 1.01, + "learning_rate": 2.705778376441253e-05, + "loss": 3.4943, + "step": 1401344 + }, + { + "epoch": 1.01, + "learning_rate": 2.704939781690201e-05, + "loss": 3.4775, + "step": 1401856 + }, + { + "epoch": 1.01, + "learning_rate": 2.704102824819522e-05, + "loss": 3.4983, + "step": 1402368 + }, + { + "epoch": 1.01, + "learning_rate": 2.7032642300684703e-05, + "loss": 3.4867, + "step": 1402880 + }, + { + "epoch": 1.01, + "learning_rate": 2.7024256353174183e-05, + "loss": 3.5, + "step": 1403392 + }, + { + "epoch": 1.01, + "learning_rate": 2.7015870405663663e-05, + "loss": 3.4946, + "step": 1403904 + }, + { + "epoch": 1.01, + "learning_rate": 2.7007484458153143e-05, + "loss": 3.4808, + "step": 1404416 + }, + { + "epoch": 1.01, + "learning_rate": 2.6999098510642623e-05, + "loss": 3.4942, + "step": 1404928 + }, + { + "epoch": 1.01, + "learning_rate": 2.6990712563132096e-05, + "loss": 3.4902, + "step": 1405440 + }, + { + "epoch": 1.01, + "learning_rate": 2.6982342994425312e-05, + "loss": 3.4844, + "step": 1405952 + }, + { + "epoch": 1.01, + "learning_rate": 2.6973957046914795e-05, + "loss": 3.4907, + "step": 1406464 + }, + { + "epoch": 1.01, + "learning_rate": 2.696557109940427e-05, + "loss": 3.4951, + "step": 1406976 + }, + { + "epoch": 1.01, + "learning_rate": 2.695718515189375e-05, + "loss": 3.4955, + "step": 1407488 + }, + { + "epoch": 1.01, + "learning_rate": 2.6948815583186964e-05, + "loss": 3.4825, + "step": 1408000 + }, + { + "epoch": 1.01, + "learning_rate": 2.6940429635676444e-05, + "loss": 3.477, + "step": 1408512 + }, + { + "epoch": 1.01, + "learning_rate": 2.693204368816592e-05, + "loss": 3.4844, + "step": 1409024 + }, + { + "epoch": 1.01, + "learning_rate": 2.69236577406554e-05, + "loss": 3.4929, + "step": 1409536 + }, + { + "epoch": 1.01, + "learning_rate": 2.6915288171948617e-05, + "loss": 3.5032, + "step": 1410048 + }, + { + "epoch": 1.01, + "learning_rate": 2.6906902224438097e-05, + "loss": 3.4894, + "step": 1410560 + }, + { + "epoch": 1.01, + "learning_rate": 2.689851627692757e-05, + "loss": 3.5018, + "step": 1411072 + }, + { + "epoch": 1.01, + "learning_rate": 2.689013032941705e-05, + "loss": 3.4997, + "step": 1411584 + }, + { + "epoch": 1.01, + "learning_rate": 2.6881760760710266e-05, + "loss": 3.5003, + "step": 1412096 + }, + { + "epoch": 1.01, + "learning_rate": 2.6873374813199742e-05, + "loss": 3.4794, + "step": 1412608 + }, + { + "epoch": 1.01, + "learning_rate": 2.6864988865689222e-05, + "loss": 3.4996, + "step": 1413120 + }, + { + "epoch": 1.01, + "learning_rate": 2.6856602918178702e-05, + "loss": 3.4943, + "step": 1413632 + }, + { + "epoch": 1.01, + "learning_rate": 2.6848233349471918e-05, + "loss": 3.4886, + "step": 1414144 + }, + { + "epoch": 1.01, + "learning_rate": 2.6839847401961395e-05, + "loss": 3.4962, + "step": 1414656 + }, + { + "epoch": 1.01, + "learning_rate": 2.6831461454450875e-05, + "loss": 3.4896, + "step": 1415168 + }, + { + "epoch": 1.01, + "learning_rate": 2.682309188574409e-05, + "loss": 3.5037, + "step": 1415680 + }, + { + "epoch": 1.01, + "learning_rate": 2.681470593823357e-05, + "loss": 3.4958, + "step": 1416192 + }, + { + "epoch": 1.01, + "learning_rate": 2.6806319990723044e-05, + "loss": 3.4841, + "step": 1416704 + }, + { + "epoch": 1.01, + "learning_rate": 2.6797934043212524e-05, + "loss": 3.4902, + "step": 1417216 + }, + { + "epoch": 1.01, + "learning_rate": 2.6789548095702004e-05, + "loss": 3.4972, + "step": 1417728 + }, + { + "epoch": 1.01, + "learning_rate": 2.6781162148191487e-05, + "loss": 3.4934, + "step": 1418240 + }, + { + "epoch": 1.01, + "learning_rate": 2.6772776200680967e-05, + "loss": 3.4901, + "step": 1418752 + }, + { + "epoch": 1.01, + "learning_rate": 2.6764390253170447e-05, + "loss": 3.4888, + "step": 1419264 + }, + { + "epoch": 1.02, + "learning_rate": 2.6756020684463656e-05, + "loss": 3.4948, + "step": 1419776 + }, + { + "epoch": 1.02, + "learning_rate": 2.6747634736953136e-05, + "loss": 3.4863, + "step": 1420288 + }, + { + "epoch": 1.02, + "learning_rate": 2.6739248789442616e-05, + "loss": 3.4912, + "step": 1420800 + }, + { + "epoch": 1.02, + "learning_rate": 2.6730862841932096e-05, + "loss": 3.4847, + "step": 1421312 + }, + { + "epoch": 1.02, + "learning_rate": 2.6722493273225308e-05, + "loss": 3.5024, + "step": 1421824 + }, + { + "epoch": 1.02, + "learning_rate": 2.6714107325714788e-05, + "loss": 3.4968, + "step": 1422336 + }, + { + "epoch": 1.02, + "learning_rate": 2.6705721378204268e-05, + "loss": 3.4948, + "step": 1422848 + }, + { + "epoch": 1.02, + "learning_rate": 2.6697335430693748e-05, + "loss": 3.4845, + "step": 1423360 + }, + { + "epoch": 1.02, + "learning_rate": 2.6688965861986957e-05, + "loss": 3.4952, + "step": 1423872 + }, + { + "epoch": 1.02, + "learning_rate": 2.668057991447644e-05, + "loss": 3.4855, + "step": 1424384 + }, + { + "epoch": 1.02, + "learning_rate": 2.667219396696592e-05, + "loss": 3.5036, + "step": 1424896 + }, + { + "epoch": 1.02, + "learning_rate": 2.66638080194554e-05, + "loss": 3.4905, + "step": 1425408 + }, + { + "epoch": 1.02, + "learning_rate": 2.665543845074861e-05, + "loss": 3.4867, + "step": 1425920 + }, + { + "epoch": 1.02, + "learning_rate": 2.664705250323809e-05, + "loss": 3.4806, + "step": 1426432 + }, + { + "epoch": 1.02, + "learning_rate": 2.663866655572757e-05, + "loss": 3.4937, + "step": 1426944 + }, + { + "epoch": 1.02, + "learning_rate": 2.663028060821705e-05, + "loss": 3.4757, + "step": 1427456 + }, + { + "epoch": 1.02, + "learning_rate": 2.6621911039510262e-05, + "loss": 3.4887, + "step": 1427968 + }, + { + "epoch": 1.02, + "learning_rate": 2.6613525091999742e-05, + "loss": 3.4884, + "step": 1428480 + }, + { + "epoch": 1.02, + "learning_rate": 2.6605139144489222e-05, + "loss": 3.4884, + "step": 1428992 + }, + { + "epoch": 1.02, + "learning_rate": 2.6596753196978702e-05, + "loss": 3.4774, + "step": 1429504 + }, + { + "epoch": 1.02, + "learning_rate": 2.658838362827191e-05, + "loss": 3.4956, + "step": 1430016 + }, + { + "epoch": 1.02, + "learning_rate": 2.6579997680761394e-05, + "loss": 3.4786, + "step": 1430528 + }, + { + "epoch": 1.02, + "learning_rate": 2.6571611733250874e-05, + "loss": 3.5016, + "step": 1431040 + }, + { + "epoch": 1.02, + "learning_rate": 2.6563225785740354e-05, + "loss": 3.487, + "step": 1431552 + }, + { + "epoch": 1.02, + "learning_rate": 2.6554856217033563e-05, + "loss": 3.4865, + "step": 1432064 + }, + { + "epoch": 1.02, + "learning_rate": 2.6546470269523043e-05, + "loss": 3.5037, + "step": 1432576 + }, + { + "epoch": 1.02, + "learning_rate": 2.6538084322012523e-05, + "loss": 3.5114, + "step": 1433088 + }, + { + "epoch": 1.02, + "learning_rate": 2.6529714753305736e-05, + "loss": 3.4877, + "step": 1433600 + }, + { + "epoch": 1.02, + "learning_rate": 2.6521345184598945e-05, + "loss": 3.4862, + "step": 1434112 + }, + { + "epoch": 1.02, + "learning_rate": 2.6512959237088425e-05, + "loss": 3.4953, + "step": 1434624 + }, + { + "epoch": 1.02, + "learning_rate": 2.6504573289577905e-05, + "loss": 3.4831, + "step": 1435136 + }, + { + "epoch": 1.02, + "learning_rate": 2.6496187342067385e-05, + "loss": 3.487, + "step": 1435648 + }, + { + "epoch": 1.02, + "learning_rate": 2.6487801394556865e-05, + "loss": 3.498, + "step": 1436160 + }, + { + "epoch": 1.02, + "learning_rate": 2.6479415447046348e-05, + "loss": 3.4846, + "step": 1436672 + }, + { + "epoch": 1.02, + "learning_rate": 2.6471029499535828e-05, + "loss": 3.5014, + "step": 1437184 + }, + { + "epoch": 1.02, + "learning_rate": 2.6462643552025308e-05, + "loss": 3.4897, + "step": 1437696 + }, + { + "epoch": 1.02, + "learning_rate": 2.6454273983318517e-05, + "loss": 3.491, + "step": 1438208 + }, + { + "epoch": 1.02, + "learning_rate": 2.6445888035807997e-05, + "loss": 3.4852, + "step": 1438720 + }, + { + "epoch": 1.02, + "learning_rate": 2.6437502088297477e-05, + "loss": 3.4921, + "step": 1439232 + }, + { + "epoch": 1.02, + "learning_rate": 2.6429116140786957e-05, + "loss": 3.4827, + "step": 1439744 + }, + { + "epoch": 1.02, + "learning_rate": 2.642074657208017e-05, + "loss": 3.5007, + "step": 1440256 + }, + { + "epoch": 1.02, + "learning_rate": 2.641236062456965e-05, + "loss": 3.4944, + "step": 1440768 + }, + { + "epoch": 1.02, + "learning_rate": 2.640397467705913e-05, + "loss": 3.4933, + "step": 1441280 + }, + { + "epoch": 1.02, + "learning_rate": 2.639558872954861e-05, + "loss": 3.4755, + "step": 1441792 + }, + { + "epoch": 1.02, + "learning_rate": 2.6387219160841818e-05, + "loss": 3.497, + "step": 1442304 + }, + { + "epoch": 1.02, + "learning_rate": 2.63788332133313e-05, + "loss": 3.4897, + "step": 1442816 + }, + { + "epoch": 1.02, + "learning_rate": 2.637044726582078e-05, + "loss": 3.4921, + "step": 1443328 + }, + { + "epoch": 1.02, + "learning_rate": 2.636207769711399e-05, + "loss": 3.4891, + "step": 1443840 + }, + { + "epoch": 1.02, + "learning_rate": 2.635369174960347e-05, + "loss": 3.4985, + "step": 1444352 + }, + { + "epoch": 1.02, + "learning_rate": 2.634530580209295e-05, + "loss": 3.4944, + "step": 1444864 + }, + { + "epoch": 1.02, + "learning_rate": 2.633691985458243e-05, + "loss": 3.4983, + "step": 1445376 + }, + { + "epoch": 1.02, + "learning_rate": 2.6328550285875643e-05, + "loss": 3.4848, + "step": 1445888 + }, + { + "epoch": 1.02, + "learning_rate": 2.6320164338365123e-05, + "loss": 3.4869, + "step": 1446400 + }, + { + "epoch": 1.02, + "learning_rate": 2.6311778390854603e-05, + "loss": 3.4942, + "step": 1446912 + }, + { + "epoch": 1.02, + "learning_rate": 2.6303408822147812e-05, + "loss": 3.4786, + "step": 1447424 + }, + { + "epoch": 1.02, + "learning_rate": 2.6295022874637292e-05, + "loss": 3.4937, + "step": 1447936 + }, + { + "epoch": 1.02, + "learning_rate": 2.6286636927126772e-05, + "loss": 3.5039, + "step": 1448448 + }, + { + "epoch": 1.02, + "learning_rate": 2.6278250979616252e-05, + "loss": 3.4929, + "step": 1448960 + }, + { + "epoch": 1.02, + "learning_rate": 2.6269865032105735e-05, + "loss": 3.4811, + "step": 1449472 + }, + { + "epoch": 1.02, + "learning_rate": 2.6261479084595215e-05, + "loss": 3.4902, + "step": 1449984 + }, + { + "epoch": 1.03, + "eval_loss": 3.846748113632202, + "eval_runtime": 308.2736, + "eval_samples_per_second": 1237.832, + "eval_steps_per_second": 38.683, + "step": 1450080 + }, + { + "epoch": 0.0, + "learning_rate": 2.6253093137084695e-05, + "loss": 3.4805, + "step": 1450496 + }, + { + "epoch": 0.0, + "learning_rate": 2.6244707189574175e-05, + "loss": 3.488, + "step": 1451008 + }, + { + "epoch": 0.0, + "learning_rate": 2.6236321242063648e-05, + "loss": 3.4932, + "step": 1451520 + }, + { + "epoch": 0.0, + "learning_rate": 2.6227935294553128e-05, + "loss": 3.4863, + "step": 1452032 + }, + { + "epoch": 0.0, + "learning_rate": 2.6219565725846344e-05, + "loss": 3.4976, + "step": 1452544 + }, + { + "epoch": 0.0, + "learning_rate": 2.621117977833582e-05, + "loss": 3.4781, + "step": 1453056 + }, + { + "epoch": 0.0, + "learning_rate": 2.62027938308253e-05, + "loss": 3.4904, + "step": 1453568 + }, + { + "epoch": 0.0, + "learning_rate": 2.619440788331478e-05, + "loss": 3.4748, + "step": 1454080 + }, + { + "epoch": 0.0, + "learning_rate": 2.6186038314607996e-05, + "loss": 3.4891, + "step": 1454592 + }, + { + "epoch": 0.0, + "learning_rate": 2.6177652367097473e-05, + "loss": 3.4847, + "step": 1455104 + }, + { + "epoch": 0.0, + "learning_rate": 2.6169266419586953e-05, + "loss": 3.4924, + "step": 1455616 + }, + { + "epoch": 0.0, + "learning_rate": 2.616089685088017e-05, + "loss": 3.4971, + "step": 1456128 + }, + { + "epoch": 0.0, + "learning_rate": 2.615251090336965e-05, + "loss": 3.4836, + "step": 1456640 + }, + { + "epoch": 0.0, + "learning_rate": 2.6144124955859122e-05, + "loss": 3.4846, + "step": 1457152 + }, + { + "epoch": 0.0, + "learning_rate": 2.6135739008348602e-05, + "loss": 3.4825, + "step": 1457664 + }, + { + "epoch": 0.0, + "learning_rate": 2.6127369439641818e-05, + "loss": 3.4838, + "step": 1458176 + }, + { + "epoch": 0.0, + "learning_rate": 2.6118983492131294e-05, + "loss": 3.4758, + "step": 1458688 + }, + { + "epoch": 0.0, + "learning_rate": 2.6110597544620774e-05, + "loss": 3.4841, + "step": 1459200 + }, + { + "epoch": 0.0, + "learning_rate": 2.6102211597110254e-05, + "loss": 3.4748, + "step": 1459712 + }, + { + "epoch": 0.0, + "learning_rate": 2.609384202840347e-05, + "loss": 3.504, + "step": 1460224 + }, + { + "epoch": 0.0, + "learning_rate": 2.6085456080892943e-05, + "loss": 3.4826, + "step": 1460736 + }, + { + "epoch": 0.0, + "learning_rate": 2.6077070133382427e-05, + "loss": 3.4878, + "step": 1461248 + }, + { + "epoch": 0.0, + "learning_rate": 2.6068684185871907e-05, + "loss": 3.4956, + "step": 1461760 + }, + { + "epoch": 0.0, + "learning_rate": 2.6060314617165122e-05, + "loss": 3.4951, + "step": 1462272 + }, + { + "epoch": 0.0, + "learning_rate": 2.6051928669654596e-05, + "loss": 3.4739, + "step": 1462784 + }, + { + "epoch": 0.0, + "learning_rate": 2.6043542722144076e-05, + "loss": 3.4853, + "step": 1463296 + }, + { + "epoch": 0.0, + "learning_rate": 2.6035156774633556e-05, + "loss": 3.4789, + "step": 1463808 + }, + { + "epoch": 0.0, + "learning_rate": 2.6026787205926768e-05, + "loss": 3.4845, + "step": 1464320 + }, + { + "epoch": 0.0, + "learning_rate": 2.6018401258416248e-05, + "loss": 3.4755, + "step": 1464832 + }, + { + "epoch": 0.01, + "learning_rate": 2.6010015310905728e-05, + "loss": 3.4783, + "step": 1465344 + }, + { + "epoch": 0.01, + "learning_rate": 2.6001629363395208e-05, + "loss": 3.4924, + "step": 1465856 + }, + { + "epoch": 0.01, + "learning_rate": 2.5993259794688417e-05, + "loss": 3.49, + "step": 1466368 + }, + { + "epoch": 0.01, + "learning_rate": 2.5984873847177897e-05, + "loss": 3.4812, + "step": 1466880 + }, + { + "epoch": 0.01, + "learning_rate": 2.597648789966738e-05, + "loss": 3.4912, + "step": 1467392 + }, + { + "epoch": 0.01, + "learning_rate": 2.596810195215686e-05, + "loss": 3.4889, + "step": 1467904 + }, + { + "epoch": 0.01, + "learning_rate": 2.595973238345007e-05, + "loss": 3.4852, + "step": 1468416 + }, + { + "epoch": 0.01, + "learning_rate": 2.595134643593955e-05, + "loss": 3.4732, + "step": 1468928 + }, + { + "epoch": 0.01, + "learning_rate": 2.594296048842903e-05, + "loss": 3.492, + "step": 1469440 + }, + { + "epoch": 0.01, + "learning_rate": 2.5934590919722242e-05, + "loss": 3.4674, + "step": 1469952 + }, + { + "epoch": 0.01, + "learning_rate": 2.5926204972211722e-05, + "loss": 3.4847, + "step": 1470464 + }, + { + "epoch": 0.01, + "learning_rate": 2.59178190247012e-05, + "loss": 3.4793, + "step": 1470976 + }, + { + "epoch": 0.01, + "learning_rate": 2.590943307719068e-05, + "loss": 3.4909, + "step": 1471488 + }, + { + "epoch": 0.01, + "learning_rate": 2.590104712968016e-05, + "loss": 3.4891, + "step": 1472000 + }, + { + "epoch": 0.01, + "learning_rate": 2.589266118216964e-05, + "loss": 3.4829, + "step": 1472512 + }, + { + "epoch": 0.01, + "learning_rate": 2.588427523465912e-05, + "loss": 3.4927, + "step": 1473024 + }, + { + "epoch": 0.01, + "learning_rate": 2.58758892871486e-05, + "loss": 3.4916, + "step": 1473536 + }, + { + "epoch": 0.01, + "learning_rate": 2.5867519718441814e-05, + "loss": 3.4842, + "step": 1474048 + }, + { + "epoch": 0.01, + "learning_rate": 2.5859133770931294e-05, + "loss": 3.4717, + "step": 1474560 + }, + { + "epoch": 0.01, + "learning_rate": 2.5850747823420774e-05, + "loss": 3.4778, + "step": 1475072 + }, + { + "epoch": 0.01, + "learning_rate": 2.5842361875910254e-05, + "loss": 3.4914, + "step": 1475584 + }, + { + "epoch": 0.01, + "learning_rate": 2.5833992307203463e-05, + "loss": 3.4803, + "step": 1476096 + }, + { + "epoch": 0.01, + "learning_rate": 2.5825606359692943e-05, + "loss": 3.4736, + "step": 1476608 + }, + { + "epoch": 0.01, + "learning_rate": 2.5817220412182426e-05, + "loss": 3.4734, + "step": 1477120 + }, + { + "epoch": 0.01, + "learning_rate": 2.5808834464671906e-05, + "loss": 3.4828, + "step": 1477632 + }, + { + "epoch": 0.01, + "learning_rate": 2.5800464895965115e-05, + "loss": 3.4697, + "step": 1478144 + }, + { + "epoch": 0.01, + "learning_rate": 2.5792095327258324e-05, + "loss": 3.4802, + "step": 1478656 + }, + { + "epoch": 0.01, + "learning_rate": 2.5783709379747804e-05, + "loss": 3.4791, + "step": 1479168 + }, + { + "epoch": 0.01, + "learning_rate": 2.5775323432237288e-05, + "loss": 3.4848, + "step": 1479680 + }, + { + "epoch": 0.01, + "learning_rate": 2.5766937484726768e-05, + "loss": 3.4831, + "step": 1480192 + }, + { + "epoch": 0.01, + "learning_rate": 2.5758551537216248e-05, + "loss": 3.4708, + "step": 1480704 + }, + { + "epoch": 0.01, + "learning_rate": 2.5750165589705727e-05, + "loss": 3.4788, + "step": 1481216 + }, + { + "epoch": 0.01, + "learning_rate": 2.5741779642195207e-05, + "loss": 3.487, + "step": 1481728 + }, + { + "epoch": 0.01, + "learning_rate": 2.5733393694684687e-05, + "loss": 3.4704, + "step": 1482240 + }, + { + "epoch": 0.01, + "learning_rate": 2.5725024125977896e-05, + "loss": 3.4779, + "step": 1482752 + }, + { + "epoch": 0.01, + "learning_rate": 2.571663817846738e-05, + "loss": 3.4831, + "step": 1483264 + }, + { + "epoch": 0.01, + "learning_rate": 2.570825223095686e-05, + "loss": 3.4881, + "step": 1483776 + }, + { + "epoch": 0.01, + "learning_rate": 2.569988266225007e-05, + "loss": 3.4674, + "step": 1484288 + }, + { + "epoch": 0.01, + "learning_rate": 2.569149671473955e-05, + "loss": 3.4661, + "step": 1484800 + }, + { + "epoch": 0.01, + "learning_rate": 2.568311076722903e-05, + "loss": 3.4694, + "step": 1485312 + }, + { + "epoch": 0.01, + "learning_rate": 2.567472481971851e-05, + "loss": 3.479, + "step": 1485824 + }, + { + "epoch": 0.01, + "learning_rate": 2.566633887220799e-05, + "loss": 3.4887, + "step": 1486336 + }, + { + "epoch": 0.01, + "learning_rate": 2.565795292469747e-05, + "loss": 3.4801, + "step": 1486848 + }, + { + "epoch": 0.01, + "learning_rate": 2.5649566977186952e-05, + "loss": 3.4886, + "step": 1487360 + }, + { + "epoch": 0.01, + "learning_rate": 2.5641181029676425e-05, + "loss": 3.4884, + "step": 1487872 + }, + { + "epoch": 0.01, + "learning_rate": 2.563281146096964e-05, + "loss": 3.4887, + "step": 1488384 + }, + { + "epoch": 0.01, + "learning_rate": 2.562442551345912e-05, + "loss": 3.4686, + "step": 1488896 + }, + { + "epoch": 0.01, + "learning_rate": 2.56160395659486e-05, + "loss": 3.4881, + "step": 1489408 + }, + { + "epoch": 0.01, + "learning_rate": 2.5607653618438078e-05, + "loss": 3.4816, + "step": 1489920 + }, + { + "epoch": 0.01, + "learning_rate": 2.5599284049731293e-05, + "loss": 3.4751, + "step": 1490432 + }, + { + "epoch": 0.01, + "learning_rate": 2.5590898102220773e-05, + "loss": 3.4815, + "step": 1490944 + }, + { + "epoch": 0.01, + "learning_rate": 2.5582512154710253e-05, + "loss": 3.48, + "step": 1491456 + }, + { + "epoch": 0.01, + "learning_rate": 2.5574142586003462e-05, + "loss": 3.4873, + "step": 1491968 + }, + { + "epoch": 0.01, + "learning_rate": 2.5565756638492942e-05, + "loss": 3.4823, + "step": 1492480 + }, + { + "epoch": 0.01, + "learning_rate": 2.5557370690982422e-05, + "loss": 3.4753, + "step": 1492992 + }, + { + "epoch": 0.01, + "learning_rate": 2.55489847434719e-05, + "loss": 3.4808, + "step": 1493504 + }, + { + "epoch": 0.01, + "learning_rate": 2.554059879596138e-05, + "loss": 3.4809, + "step": 1494016 + }, + { + "epoch": 0.01, + "learning_rate": 2.553221284845086e-05, + "loss": 3.4808, + "step": 1494528 + }, + { + "epoch": 0.01, + "learning_rate": 2.552382690094034e-05, + "loss": 3.4781, + "step": 1495040 + }, + { + "epoch": 0.01, + "learning_rate": 2.551544095342982e-05, + "loss": 3.4739, + "step": 1495552 + }, + { + "epoch": 0.02, + "learning_rate": 2.550707138472303e-05, + "loss": 3.4834, + "step": 1496064 + }, + { + "epoch": 0.02, + "learning_rate": 2.549868543721251e-05, + "loss": 3.4779, + "step": 1496576 + }, + { + "epoch": 0.02, + "learning_rate": 2.549029948970199e-05, + "loss": 3.4736, + "step": 1497088 + }, + { + "epoch": 0.02, + "learning_rate": 2.548191354219147e-05, + "loss": 3.4732, + "step": 1497600 + }, + { + "epoch": 0.02, + "learning_rate": 2.547354397348468e-05, + "loss": 3.4927, + "step": 1498112 + }, + { + "epoch": 0.02, + "learning_rate": 2.546515802597416e-05, + "loss": 3.4863, + "step": 1498624 + }, + { + "epoch": 0.02, + "learning_rate": 2.5456772078463643e-05, + "loss": 3.4789, + "step": 1499136 + }, + { + "epoch": 0.02, + "learning_rate": 2.5448386130953123e-05, + "loss": 3.47, + "step": 1499648 + }, + { + "epoch": 0.02, + "learning_rate": 2.5440016562246333e-05, + "loss": 3.4813, + "step": 1500160 + }, + { + "epoch": 0.02, + "learning_rate": 2.5431630614735812e-05, + "loss": 3.4725, + "step": 1500672 + }, + { + "epoch": 0.02, + "learning_rate": 2.5423244667225292e-05, + "loss": 3.4944, + "step": 1501184 + }, + { + "epoch": 0.02, + "learning_rate": 2.5414858719714772e-05, + "loss": 3.4807, + "step": 1501696 + }, + { + "epoch": 0.02, + "learning_rate": 2.5406489151007985e-05, + "loss": 3.4776, + "step": 1502208 + }, + { + "epoch": 0.02, + "learning_rate": 2.5398103203497465e-05, + "loss": 3.4713, + "step": 1502720 + }, + { + "epoch": 0.02, + "learning_rate": 2.5389717255986945e-05, + "loss": 3.4811, + "step": 1503232 + }, + { + "epoch": 0.02, + "learning_rate": 2.5381331308476425e-05, + "loss": 3.4583, + "step": 1503744 + }, + { + "epoch": 0.02, + "learning_rate": 2.5372961739769634e-05, + "loss": 3.4791, + "step": 1504256 + }, + { + "epoch": 0.02, + "learning_rate": 2.5364575792259114e-05, + "loss": 3.475, + "step": 1504768 + }, + { + "epoch": 0.02, + "learning_rate": 2.5356189844748597e-05, + "loss": 3.4783, + "step": 1505280 + }, + { + "epoch": 0.02, + "learning_rate": 2.5347803897238077e-05, + "loss": 3.4658, + "step": 1505792 + }, + { + "epoch": 0.02, + "learning_rate": 2.5339434328531286e-05, + "loss": 3.4843, + "step": 1506304 + }, + { + "epoch": 0.02, + "learning_rate": 2.5331048381020766e-05, + "loss": 3.4675, + "step": 1506816 + }, + { + "epoch": 0.02, + "learning_rate": 2.5322662433510246e-05, + "loss": 3.4843, + "step": 1507328 + }, + { + "epoch": 0.02, + "learning_rate": 2.5314276485999726e-05, + "loss": 3.4755, + "step": 1507840 + }, + { + "epoch": 0.02, + "learning_rate": 2.530590691729294e-05, + "loss": 3.4738, + "step": 1508352 + }, + { + "epoch": 0.02, + "learning_rate": 2.529752096978242e-05, + "loss": 3.4879, + "step": 1508864 + }, + { + "epoch": 0.02, + "learning_rate": 2.52891350222719e-05, + "loss": 3.4975, + "step": 1509376 + }, + { + "epoch": 0.02, + "learning_rate": 2.5280765453565108e-05, + "loss": 3.4813, + "step": 1509888 + }, + { + "epoch": 0.02, + "learning_rate": 2.527239588485832e-05, + "loss": 3.475, + "step": 1510400 + }, + { + "epoch": 0.02, + "learning_rate": 2.52640099373478e-05, + "loss": 3.4835, + "step": 1510912 + }, + { + "epoch": 0.02, + "learning_rate": 2.525562398983728e-05, + "loss": 3.4681, + "step": 1511424 + }, + { + "epoch": 0.02, + "learning_rate": 2.524723804232676e-05, + "loss": 3.4738, + "step": 1511936 + }, + { + "epoch": 0.02, + "learning_rate": 2.523885209481624e-05, + "loss": 3.4857, + "step": 1512448 + }, + { + "epoch": 0.02, + "learning_rate": 2.523046614730572e-05, + "loss": 3.472, + "step": 1512960 + }, + { + "epoch": 0.02, + "learning_rate": 2.52220801997952e-05, + "loss": 3.4877, + "step": 1513472 + }, + { + "epoch": 0.02, + "learning_rate": 2.521369425228468e-05, + "loss": 3.4785, + "step": 1513984 + }, + { + "epoch": 0.02, + "learning_rate": 2.5205324683577892e-05, + "loss": 3.4817, + "step": 1514496 + }, + { + "epoch": 0.02, + "learning_rate": 2.5196938736067372e-05, + "loss": 3.4668, + "step": 1515008 + }, + { + "epoch": 0.02, + "learning_rate": 2.5188552788556852e-05, + "loss": 3.4831, + "step": 1515520 + }, + { + "epoch": 0.02, + "learning_rate": 2.5180166841046332e-05, + "loss": 3.4715, + "step": 1516032 + }, + { + "epoch": 0.02, + "learning_rate": 2.517179727233954e-05, + "loss": 3.4843, + "step": 1516544 + }, + { + "epoch": 0.02, + "learning_rate": 2.516341132482902e-05, + "loss": 3.4784, + "step": 1517056 + }, + { + "epoch": 0.02, + "learning_rate": 2.5155025377318504e-05, + "loss": 3.4863, + "step": 1517568 + }, + { + "epoch": 0.02, + "learning_rate": 2.5146639429807984e-05, + "loss": 3.4644, + "step": 1518080 + }, + { + "epoch": 0.02, + "learning_rate": 2.5138269861101194e-05, + "loss": 3.4885, + "step": 1518592 + }, + { + "epoch": 0.02, + "learning_rate": 2.5129883913590673e-05, + "loss": 3.4759, + "step": 1519104 + }, + { + "epoch": 0.02, + "learning_rate": 2.5121497966080153e-05, + "loss": 3.479, + "step": 1519616 + }, + { + "epoch": 0.02, + "learning_rate": 2.5113112018569633e-05, + "loss": 3.4769, + "step": 1520128 + }, + { + "epoch": 0.02, + "learning_rate": 2.5104742449862846e-05, + "loss": 3.4869, + "step": 1520640 + }, + { + "epoch": 0.02, + "learning_rate": 2.5096356502352326e-05, + "loss": 3.4818, + "step": 1521152 + }, + { + "epoch": 0.02, + "learning_rate": 2.5087970554841806e-05, + "loss": 3.4844, + "step": 1521664 + }, + { + "epoch": 0.02, + "learning_rate": 2.5079600986135015e-05, + "loss": 3.4731, + "step": 1522176 + }, + { + "epoch": 0.02, + "learning_rate": 2.5071215038624495e-05, + "loss": 3.4778, + "step": 1522688 + }, + { + "epoch": 0.02, + "learning_rate": 2.5062829091113975e-05, + "loss": 3.4792, + "step": 1523200 + }, + { + "epoch": 0.02, + "learning_rate": 2.5054443143603458e-05, + "loss": 3.4703, + "step": 1523712 + }, + { + "epoch": 0.02, + "learning_rate": 2.5046073574896667e-05, + "loss": 3.4787, + "step": 1524224 + }, + { + "epoch": 0.02, + "learning_rate": 2.5037687627386147e-05, + "loss": 3.4911, + "step": 1524736 + }, + { + "epoch": 0.02, + "learning_rate": 2.5029301679875627e-05, + "loss": 3.4799, + "step": 1525248 + }, + { + "epoch": 0.02, + "learning_rate": 2.5020915732365107e-05, + "loss": 3.4662, + "step": 1525760 + }, + { + "epoch": 0.02, + "learning_rate": 2.501254616365832e-05, + "loss": 3.4789, + "step": 1526272 + }, + { + "epoch": 0.03, + "eval_loss": 3.848705291748047, + "eval_runtime": 303.2294, + "eval_samples_per_second": 1258.424, + "eval_steps_per_second": 39.327, + "step": 1526400 + }, + { + "epoch": 1.0, + "learning_rate": 2.50041602161478e-05, + "loss": 3.472, + "step": 1526784 + }, + { + "epoch": 1.0, + "learning_rate": 2.499577426863728e-05, + "loss": 3.4748, + "step": 1527296 + }, + { + "epoch": 1.0, + "learning_rate": 2.498738832112676e-05, + "loss": 3.4794, + "step": 1527808 + }, + { + "epoch": 1.0, + "learning_rate": 2.497901875241997e-05, + "loss": 3.4772, + "step": 1528320 + }, + { + "epoch": 1.0, + "learning_rate": 2.497063280490945e-05, + "loss": 3.4858, + "step": 1528832 + }, + { + "epoch": 1.0, + "learning_rate": 2.496224685739893e-05, + "loss": 3.4679, + "step": 1529344 + }, + { + "epoch": 1.0, + "learning_rate": 2.4953860909888412e-05, + "loss": 3.4758, + "step": 1529856 + }, + { + "epoch": 1.0, + "learning_rate": 2.494549134118162e-05, + "loss": 3.4643, + "step": 1530368 + }, + { + "epoch": 1.0, + "learning_rate": 2.49371053936711e-05, + "loss": 3.4789, + "step": 1530880 + }, + { + "epoch": 1.0, + "learning_rate": 2.492871944616058e-05, + "loss": 3.4719, + "step": 1531392 + }, + { + "epoch": 1.0, + "learning_rate": 2.492033349865006e-05, + "loss": 3.4748, + "step": 1531904 + }, + { + "epoch": 1.0, + "learning_rate": 2.4911963929943273e-05, + "loss": 3.4892, + "step": 1532416 + }, + { + "epoch": 1.0, + "learning_rate": 2.4903577982432753e-05, + "loss": 3.4668, + "step": 1532928 + }, + { + "epoch": 1.0, + "learning_rate": 2.4895192034922233e-05, + "loss": 3.4758, + "step": 1533440 + }, + { + "epoch": 1.0, + "learning_rate": 2.4886806087411713e-05, + "loss": 3.4707, + "step": 1533952 + }, + { + "epoch": 1.0, + "learning_rate": 2.4878436518704922e-05, + "loss": 3.4718, + "step": 1534464 + }, + { + "epoch": 1.0, + "learning_rate": 2.4870050571194402e-05, + "loss": 3.4638, + "step": 1534976 + }, + { + "epoch": 1.0, + "learning_rate": 2.4861664623683882e-05, + "loss": 3.4724, + "step": 1535488 + }, + { + "epoch": 1.0, + "learning_rate": 2.4853278676173362e-05, + "loss": 3.4687, + "step": 1536000 + }, + { + "epoch": 1.0, + "learning_rate": 2.4844909107466575e-05, + "loss": 3.4884, + "step": 1536512 + }, + { + "epoch": 1.0, + "learning_rate": 2.4836523159956055e-05, + "loss": 3.4707, + "step": 1537024 + }, + { + "epoch": 1.0, + "learning_rate": 2.4828137212445534e-05, + "loss": 3.477, + "step": 1537536 + }, + { + "epoch": 1.0, + "learning_rate": 2.481975126493501e-05, + "loss": 3.4832, + "step": 1538048 + }, + { + "epoch": 1.0, + "learning_rate": 2.4811381696228227e-05, + "loss": 3.4842, + "step": 1538560 + }, + { + "epoch": 1.0, + "learning_rate": 2.4802995748717707e-05, + "loss": 3.463, + "step": 1539072 + }, + { + "epoch": 1.0, + "learning_rate": 2.4794609801207187e-05, + "loss": 3.478, + "step": 1539584 + }, + { + "epoch": 1.0, + "learning_rate": 2.4786223853696663e-05, + "loss": 3.4668, + "step": 1540096 + }, + { + "epoch": 1.0, + "learning_rate": 2.4777854284989876e-05, + "loss": 3.4738, + "step": 1540608 + }, + { + "epoch": 1.0, + "learning_rate": 2.4769468337479356e-05, + "loss": 3.4606, + "step": 1541120 + }, + { + "epoch": 1.0, + "learning_rate": 2.4761082389968836e-05, + "loss": 3.4674, + "step": 1541632 + }, + { + "epoch": 1.01, + "learning_rate": 2.4752696442458316e-05, + "loss": 3.4799, + "step": 1542144 + }, + { + "epoch": 1.01, + "learning_rate": 2.4744326873751528e-05, + "loss": 3.4777, + "step": 1542656 + }, + { + "epoch": 1.01, + "learning_rate": 2.4735940926241008e-05, + "loss": 3.4694, + "step": 1543168 + }, + { + "epoch": 1.01, + "learning_rate": 2.4727554978730485e-05, + "loss": 3.4819, + "step": 1543680 + }, + { + "epoch": 1.01, + "learning_rate": 2.4719169031219965e-05, + "loss": 3.4719, + "step": 1544192 + }, + { + "epoch": 1.01, + "learning_rate": 2.4710799462513177e-05, + "loss": 3.4797, + "step": 1544704 + }, + { + "epoch": 1.01, + "learning_rate": 2.470241351500266e-05, + "loss": 3.4593, + "step": 1545216 + }, + { + "epoch": 1.01, + "learning_rate": 2.4694027567492137e-05, + "loss": 3.4784, + "step": 1545728 + }, + { + "epoch": 1.01, + "learning_rate": 2.468565799878535e-05, + "loss": 3.4597, + "step": 1546240 + }, + { + "epoch": 1.01, + "learning_rate": 2.467727205127483e-05, + "loss": 3.4701, + "step": 1546752 + }, + { + "epoch": 1.01, + "learning_rate": 2.4668886103764306e-05, + "loss": 3.4654, + "step": 1547264 + }, + { + "epoch": 1.01, + "learning_rate": 2.466050015625379e-05, + "loss": 3.4794, + "step": 1547776 + }, + { + "epoch": 1.01, + "learning_rate": 2.465211420874327e-05, + "loss": 3.4769, + "step": 1548288 + }, + { + "epoch": 1.01, + "learning_rate": 2.464372826123275e-05, + "loss": 3.4732, + "step": 1548800 + }, + { + "epoch": 1.01, + "learning_rate": 2.463534231372223e-05, + "loss": 3.4764, + "step": 1549312 + }, + { + "epoch": 1.01, + "learning_rate": 2.462695636621171e-05, + "loss": 3.4782, + "step": 1549824 + }, + { + "epoch": 1.01, + "learning_rate": 2.461858679750492e-05, + "loss": 3.4726, + "step": 1550336 + }, + { + "epoch": 1.01, + "learning_rate": 2.46102008499944e-05, + "loss": 3.4658, + "step": 1550848 + }, + { + "epoch": 1.01, + "learning_rate": 2.460181490248388e-05, + "loss": 3.4589, + "step": 1551360 + }, + { + "epoch": 1.01, + "learning_rate": 2.459342895497336e-05, + "loss": 3.4794, + "step": 1551872 + }, + { + "epoch": 1.01, + "learning_rate": 2.458505938626657e-05, + "loss": 3.4711, + "step": 1552384 + }, + { + "epoch": 1.01, + "learning_rate": 2.457667343875605e-05, + "loss": 3.4621, + "step": 1552896 + }, + { + "epoch": 1.01, + "learning_rate": 2.456828749124553e-05, + "loss": 3.4648, + "step": 1553408 + }, + { + "epoch": 1.01, + "learning_rate": 2.455990154373501e-05, + "loss": 3.4702, + "step": 1553920 + }, + { + "epoch": 1.01, + "learning_rate": 2.4551531975028223e-05, + "loss": 3.4577, + "step": 1554432 + }, + { + "epoch": 1.01, + "learning_rate": 2.4543162406321432e-05, + "loss": 3.4659, + "step": 1554944 + }, + { + "epoch": 1.01, + "learning_rate": 2.4534776458810912e-05, + "loss": 3.4657, + "step": 1555456 + }, + { + "epoch": 1.01, + "learning_rate": 2.4526390511300392e-05, + "loss": 3.4692, + "step": 1555968 + }, + { + "epoch": 1.01, + "learning_rate": 2.4518004563789872e-05, + "loss": 3.4758, + "step": 1556480 + }, + { + "epoch": 1.01, + "learning_rate": 2.4509618616279352e-05, + "loss": 3.4599, + "step": 1556992 + }, + { + "epoch": 1.01, + "learning_rate": 2.4501232668768835e-05, + "loss": 3.4641, + "step": 1557504 + }, + { + "epoch": 1.01, + "learning_rate": 2.4492846721258312e-05, + "loss": 3.4742, + "step": 1558016 + }, + { + "epoch": 1.01, + "learning_rate": 2.4484460773747792e-05, + "loss": 3.4598, + "step": 1558528 + }, + { + "epoch": 1.01, + "learning_rate": 2.4476091205041004e-05, + "loss": 3.4649, + "step": 1559040 + }, + { + "epoch": 1.01, + "learning_rate": 2.4467705257530484e-05, + "loss": 3.4712, + "step": 1559552 + }, + { + "epoch": 1.01, + "learning_rate": 2.445931931001996e-05, + "loss": 3.4756, + "step": 1560064 + }, + { + "epoch": 1.01, + "learning_rate": 2.4450949741313177e-05, + "loss": 3.4597, + "step": 1560576 + }, + { + "epoch": 1.01, + "learning_rate": 2.4442563793802657e-05, + "loss": 3.4541, + "step": 1561088 + }, + { + "epoch": 1.01, + "learning_rate": 2.4434177846292137e-05, + "loss": 3.4552, + "step": 1561600 + }, + { + "epoch": 1.01, + "learning_rate": 2.4425791898781613e-05, + "loss": 3.4663, + "step": 1562112 + }, + { + "epoch": 1.01, + "learning_rate": 2.4417405951271093e-05, + "loss": 3.4788, + "step": 1562624 + }, + { + "epoch": 1.01, + "learning_rate": 2.4409020003760573e-05, + "loss": 3.4666, + "step": 1563136 + }, + { + "epoch": 1.01, + "learning_rate": 2.4400634056250053e-05, + "loss": 3.4762, + "step": 1563648 + }, + { + "epoch": 1.01, + "learning_rate": 2.4392248108739536e-05, + "loss": 3.474, + "step": 1564160 + }, + { + "epoch": 1.01, + "learning_rate": 2.4383878540032746e-05, + "loss": 3.4806, + "step": 1564672 + }, + { + "epoch": 1.01, + "learning_rate": 2.4375492592522225e-05, + "loss": 3.4585, + "step": 1565184 + }, + { + "epoch": 1.01, + "learning_rate": 2.4367106645011705e-05, + "loss": 3.4741, + "step": 1565696 + }, + { + "epoch": 1.01, + "learning_rate": 2.4358720697501185e-05, + "loss": 3.4687, + "step": 1566208 + }, + { + "epoch": 1.01, + "learning_rate": 2.4350351128794398e-05, + "loss": 3.462, + "step": 1566720 + }, + { + "epoch": 1.01, + "learning_rate": 2.4341965181283878e-05, + "loss": 3.4745, + "step": 1567232 + }, + { + "epoch": 1.01, + "learning_rate": 2.4333579233773358e-05, + "loss": 3.4687, + "step": 1567744 + }, + { + "epoch": 1.01, + "learning_rate": 2.4325209665066567e-05, + "loss": 3.4713, + "step": 1568256 + }, + { + "epoch": 1.01, + "learning_rate": 2.4316823717556047e-05, + "loss": 3.4725, + "step": 1568768 + }, + { + "epoch": 1.01, + "learning_rate": 2.4308437770045527e-05, + "loss": 3.4664, + "step": 1569280 + }, + { + "epoch": 1.01, + "learning_rate": 2.4300051822535007e-05, + "loss": 3.4688, + "step": 1569792 + }, + { + "epoch": 1.01, + "learning_rate": 2.429166587502449e-05, + "loss": 3.4674, + "step": 1570304 + }, + { + "epoch": 1.01, + "learning_rate": 2.4283279927513967e-05, + "loss": 3.4701, + "step": 1570816 + }, + { + "epoch": 1.01, + "learning_rate": 2.4274893980003447e-05, + "loss": 3.4635, + "step": 1571328 + }, + { + "epoch": 1.01, + "learning_rate": 2.4266508032492927e-05, + "loss": 3.4652, + "step": 1571840 + }, + { + "epoch": 1.02, + "learning_rate": 2.425813846378614e-05, + "loss": 3.4705, + "step": 1572352 + }, + { + "epoch": 1.02, + "learning_rate": 2.4249752516275616e-05, + "loss": 3.47, + "step": 1572864 + }, + { + "epoch": 1.02, + "learning_rate": 2.42413665687651e-05, + "loss": 3.4603, + "step": 1573376 + }, + { + "epoch": 1.02, + "learning_rate": 2.423298062125458e-05, + "loss": 3.4611, + "step": 1573888 + }, + { + "epoch": 1.02, + "learning_rate": 2.422461105254779e-05, + "loss": 3.4807, + "step": 1574400 + }, + { + "epoch": 1.02, + "learning_rate": 2.4216225105037268e-05, + "loss": 3.4731, + "step": 1574912 + }, + { + "epoch": 1.02, + "learning_rate": 2.4207839157526748e-05, + "loss": 3.4699, + "step": 1575424 + }, + { + "epoch": 1.02, + "learning_rate": 2.4199453210016228e-05, + "loss": 3.4583, + "step": 1575936 + }, + { + "epoch": 1.02, + "learning_rate": 2.419108364130944e-05, + "loss": 3.4693, + "step": 1576448 + }, + { + "epoch": 1.02, + "learning_rate": 2.418269769379892e-05, + "loss": 3.4613, + "step": 1576960 + }, + { + "epoch": 1.02, + "learning_rate": 2.41743117462884e-05, + "loss": 3.4781, + "step": 1577472 + }, + { + "epoch": 1.02, + "learning_rate": 2.416592579877788e-05, + "loss": 3.4733, + "step": 1577984 + }, + { + "epoch": 1.02, + "learning_rate": 2.415755623007109e-05, + "loss": 3.4633, + "step": 1578496 + }, + { + "epoch": 1.02, + "learning_rate": 2.414917028256057e-05, + "loss": 3.4611, + "step": 1579008 + }, + { + "epoch": 1.02, + "learning_rate": 2.4140784335050053e-05, + "loss": 3.4704, + "step": 1579520 + }, + { + "epoch": 1.02, + "learning_rate": 2.4132398387539533e-05, + "loss": 3.4426, + "step": 1580032 + }, + { + "epoch": 1.02, + "learning_rate": 2.4124028818832742e-05, + "loss": 3.4714, + "step": 1580544 + }, + { + "epoch": 1.02, + "learning_rate": 2.411564287132222e-05, + "loss": 3.4596, + "step": 1581056 + }, + { + "epoch": 1.02, + "learning_rate": 2.41072569238117e-05, + "loss": 3.4673, + "step": 1581568 + }, + { + "epoch": 1.02, + "learning_rate": 2.409887097630118e-05, + "loss": 3.4541, + "step": 1582080 + }, + { + "epoch": 1.02, + "learning_rate": 2.4090501407594394e-05, + "loss": 3.471, + "step": 1582592 + }, + { + "epoch": 1.02, + "learning_rate": 2.4082115460083874e-05, + "loss": 3.4617, + "step": 1583104 + }, + { + "epoch": 1.02, + "learning_rate": 2.4073729512573354e-05, + "loss": 3.4667, + "step": 1583616 + }, + { + "epoch": 1.02, + "learning_rate": 2.4065343565062834e-05, + "loss": 3.4679, + "step": 1584128 + }, + { + "epoch": 1.02, + "learning_rate": 2.4056973996356043e-05, + "loss": 3.4597, + "step": 1584640 + }, + { + "epoch": 1.02, + "learning_rate": 2.4048588048845523e-05, + "loss": 3.4767, + "step": 1585152 + }, + { + "epoch": 1.02, + "learning_rate": 2.4040202101335006e-05, + "loss": 3.4873, + "step": 1585664 + }, + { + "epoch": 1.02, + "learning_rate": 2.4031816153824486e-05, + "loss": 3.468, + "step": 1586176 + }, + { + "epoch": 1.02, + "learning_rate": 2.4023462963921428e-05, + "loss": 3.4612, + "step": 1586688 + }, + { + "epoch": 1.02, + "learning_rate": 2.4015077016410908e-05, + "loss": 3.4744, + "step": 1587200 + }, + { + "epoch": 1.02, + "learning_rate": 2.4006691068900384e-05, + "loss": 3.4628, + "step": 1587712 + }, + { + "epoch": 1.02, + "learning_rate": 2.3998305121389868e-05, + "loss": 3.4595, + "step": 1588224 + }, + { + "epoch": 1.02, + "learning_rate": 2.3989919173879348e-05, + "loss": 3.4751, + "step": 1588736 + }, + { + "epoch": 1.02, + "learning_rate": 2.3981533226368828e-05, + "loss": 3.4595, + "step": 1589248 + }, + { + "epoch": 1.02, + "learning_rate": 2.3973147278858308e-05, + "loss": 3.4734, + "step": 1589760 + }, + { + "epoch": 1.02, + "learning_rate": 2.3964761331347788e-05, + "loss": 3.4663, + "step": 1590272 + }, + { + "epoch": 1.02, + "learning_rate": 2.3956391762640997e-05, + "loss": 3.4702, + "step": 1590784 + }, + { + "epoch": 1.02, + "learning_rate": 2.3948005815130477e-05, + "loss": 3.4628, + "step": 1591296 + }, + { + "epoch": 1.02, + "learning_rate": 2.393961986761996e-05, + "loss": 3.466, + "step": 1591808 + }, + { + "epoch": 1.02, + "learning_rate": 2.393123392010944e-05, + "loss": 3.4637, + "step": 1592320 + }, + { + "epoch": 1.02, + "learning_rate": 2.392286435140265e-05, + "loss": 3.4711, + "step": 1592832 + }, + { + "epoch": 1.02, + "learning_rate": 2.391447840389213e-05, + "loss": 3.4658, + "step": 1593344 + }, + { + "epoch": 1.02, + "learning_rate": 2.390609245638161e-05, + "loss": 3.4729, + "step": 1593856 + }, + { + "epoch": 1.02, + "learning_rate": 2.389770650887109e-05, + "loss": 3.4539, + "step": 1594368 + }, + { + "epoch": 1.02, + "learning_rate": 2.38893369401643e-05, + "loss": 3.477, + "step": 1594880 + }, + { + "epoch": 1.02, + "learning_rate": 2.388095099265378e-05, + "loss": 3.4655, + "step": 1595392 + }, + { + "epoch": 1.02, + "learning_rate": 2.387256504514326e-05, + "loss": 3.4691, + "step": 1595904 + }, + { + "epoch": 1.02, + "learning_rate": 2.386417909763274e-05, + "loss": 3.4654, + "step": 1596416 + }, + { + "epoch": 1.02, + "learning_rate": 2.385580952892595e-05, + "loss": 3.4754, + "step": 1596928 + }, + { + "epoch": 1.02, + "learning_rate": 2.384742358141543e-05, + "loss": 3.4686, + "step": 1597440 + }, + { + "epoch": 1.02, + "learning_rate": 2.3839037633904914e-05, + "loss": 3.4769, + "step": 1597952 + }, + { + "epoch": 1.02, + "learning_rate": 2.383065168639439e-05, + "loss": 3.4565, + "step": 1598464 + }, + { + "epoch": 1.02, + "learning_rate": 2.3822298496491332e-05, + "loss": 3.4686, + "step": 1598976 + }, + { + "epoch": 1.02, + "learning_rate": 2.3813912548980812e-05, + "loss": 3.4654, + "step": 1599488 + }, + { + "epoch": 1.02, + "learning_rate": 2.3805526601470292e-05, + "loss": 3.4602, + "step": 1600000 + }, + { + "epoch": 1.02, + "learning_rate": 2.3797140653959775e-05, + "loss": 3.4712, + "step": 1600512 + }, + { + "epoch": 1.02, + "learning_rate": 2.3788754706449255e-05, + "loss": 3.4739, + "step": 1601024 + }, + { + "epoch": 1.02, + "learning_rate": 2.3780368758938735e-05, + "loss": 3.4742, + "step": 1601536 + }, + { + "epoch": 1.02, + "learning_rate": 2.3771982811428215e-05, + "loss": 3.4507, + "step": 1602048 + }, + { + "epoch": 1.02, + "learning_rate": 2.376359686391769e-05, + "loss": 3.469, + "step": 1602560 + }, + { + "epoch": 1.03, + "eval_loss": 3.849381923675537, + "eval_runtime": 303.442, + "eval_samples_per_second": 1257.542, + "eval_steps_per_second": 39.299, + "step": 1602720 + }, + { + "epoch": 0.0, + "learning_rate": 2.3755227295210904e-05, + "loss": 3.4598, + "step": 1603072 + }, + { + "epoch": 0.0, + "learning_rate": 2.3746841347700384e-05, + "loss": 3.4596, + "step": 1603584 + }, + { + "epoch": 0.0, + "learning_rate": 2.3738455400189864e-05, + "loss": 3.4708, + "step": 1604096 + }, + { + "epoch": 0.0, + "learning_rate": 2.3730069452679344e-05, + "loss": 3.4677, + "step": 1604608 + }, + { + "epoch": 0.0, + "learning_rate": 2.3721699883972556e-05, + "loss": 3.4683, + "step": 1605120 + }, + { + "epoch": 0.0, + "learning_rate": 2.3713313936462036e-05, + "loss": 3.4599, + "step": 1605632 + }, + { + "epoch": 0.0, + "learning_rate": 2.3704927988951513e-05, + "loss": 3.4628, + "step": 1606144 + }, + { + "epoch": 0.0, + "learning_rate": 2.3696542041440993e-05, + "loss": 3.4529, + "step": 1606656 + }, + { + "epoch": 0.0, + "learning_rate": 2.368817247273421e-05, + "loss": 3.4669, + "step": 1607168 + }, + { + "epoch": 0.0, + "learning_rate": 2.367978652522369e-05, + "loss": 3.4628, + "step": 1607680 + }, + { + "epoch": 0.0, + "learning_rate": 2.3671400577713165e-05, + "loss": 3.4623, + "step": 1608192 + }, + { + "epoch": 0.0, + "learning_rate": 2.3663014630202645e-05, + "loss": 3.4751, + "step": 1608704 + }, + { + "epoch": 0.0, + "learning_rate": 2.365466144029959e-05, + "loss": 3.458, + "step": 1609216 + }, + { + "epoch": 0.0, + "learning_rate": 2.364627549278907e-05, + "loss": 3.465, + "step": 1609728 + }, + { + "epoch": 0.0, + "learning_rate": 2.363788954527855e-05, + "loss": 3.4614, + "step": 1610240 + }, + { + "epoch": 0.0, + "learning_rate": 2.362950359776803e-05, + "loss": 3.4593, + "step": 1610752 + }, + { + "epoch": 0.0, + "learning_rate": 2.362111765025751e-05, + "loss": 3.4512, + "step": 1611264 + }, + { + "epoch": 0.0, + "learning_rate": 2.3612731702746987e-05, + "loss": 3.4624, + "step": 1611776 + }, + { + "epoch": 0.0, + "learning_rate": 2.3604345755236467e-05, + "loss": 3.4544, + "step": 1612288 + }, + { + "epoch": 0.0, + "learning_rate": 2.3595959807725947e-05, + "loss": 3.4743, + "step": 1612800 + }, + { + "epoch": 0.0, + "learning_rate": 2.3587590239019162e-05, + "loss": 3.4641, + "step": 1613312 + }, + { + "epoch": 0.0, + "learning_rate": 2.357920429150864e-05, + "loss": 3.4626, + "step": 1613824 + }, + { + "epoch": 0.0, + "learning_rate": 2.357081834399812e-05, + "loss": 3.4735, + "step": 1614336 + }, + { + "epoch": 0.0, + "learning_rate": 2.35624323964876e-05, + "loss": 3.4727, + "step": 1614848 + }, + { + "epoch": 0.0, + "learning_rate": 2.3554062827780808e-05, + "loss": 3.4484, + "step": 1615360 + }, + { + "epoch": 0.0, + "learning_rate": 2.354567688027029e-05, + "loss": 3.4639, + "step": 1615872 + }, + { + "epoch": 0.0, + "learning_rate": 2.353729093275977e-05, + "loss": 3.4598, + "step": 1616384 + }, + { + "epoch": 0.0, + "learning_rate": 2.3528921364052984e-05, + "loss": 3.4616, + "step": 1616896 + }, + { + "epoch": 0.0, + "learning_rate": 2.352053541654246e-05, + "loss": 3.4504, + "step": 1617408 + }, + { + "epoch": 0.0, + "learning_rate": 2.351214946903194e-05, + "loss": 3.4557, + "step": 1617920 + }, + { + "epoch": 0.01, + "learning_rate": 2.350376352152142e-05, + "loss": 3.4695, + "step": 1618432 + }, + { + "epoch": 0.01, + "learning_rate": 2.3495393952814633e-05, + "loss": 3.4635, + "step": 1618944 + }, + { + "epoch": 0.01, + "learning_rate": 2.3487008005304113e-05, + "loss": 3.4602, + "step": 1619456 + }, + { + "epoch": 0.01, + "learning_rate": 2.3478622057793593e-05, + "loss": 3.467, + "step": 1619968 + }, + { + "epoch": 0.01, + "learning_rate": 2.3470236110283073e-05, + "loss": 3.4636, + "step": 1620480 + }, + { + "epoch": 0.01, + "learning_rate": 2.346186654157628e-05, + "loss": 3.4671, + "step": 1620992 + }, + { + "epoch": 0.01, + "learning_rate": 2.345348059406576e-05, + "loss": 3.4519, + "step": 1621504 + }, + { + "epoch": 0.01, + "learning_rate": 2.3445094646555245e-05, + "loss": 3.4566, + "step": 1622016 + }, + { + "epoch": 0.01, + "learning_rate": 2.3436708699044725e-05, + "loss": 3.4542, + "step": 1622528 + }, + { + "epoch": 0.01, + "learning_rate": 2.3428339130337934e-05, + "loss": 3.457, + "step": 1623040 + }, + { + "epoch": 0.01, + "learning_rate": 2.3419953182827414e-05, + "loss": 3.4545, + "step": 1623552 + }, + { + "epoch": 0.01, + "learning_rate": 2.3411567235316894e-05, + "loss": 3.4668, + "step": 1624064 + }, + { + "epoch": 0.01, + "learning_rate": 2.3403181287806374e-05, + "loss": 3.4649, + "step": 1624576 + }, + { + "epoch": 0.01, + "learning_rate": 2.3394795340295854e-05, + "loss": 3.46, + "step": 1625088 + }, + { + "epoch": 0.01, + "learning_rate": 2.3386409392785337e-05, + "loss": 3.4712, + "step": 1625600 + }, + { + "epoch": 0.01, + "learning_rate": 2.3378023445274814e-05, + "loss": 3.4615, + "step": 1626112 + }, + { + "epoch": 0.01, + "learning_rate": 2.3369653876568026e-05, + "loss": 3.4634, + "step": 1626624 + }, + { + "epoch": 0.01, + "learning_rate": 2.3361267929057506e-05, + "loss": 3.4547, + "step": 1627136 + }, + { + "epoch": 0.01, + "learning_rate": 2.3352881981546986e-05, + "loss": 3.4435, + "step": 1627648 + }, + { + "epoch": 0.01, + "learning_rate": 2.3344496034036463e-05, + "loss": 3.4702, + "step": 1628160 + }, + { + "epoch": 0.01, + "learning_rate": 2.333612646532968e-05, + "loss": 3.4594, + "step": 1628672 + }, + { + "epoch": 0.01, + "learning_rate": 2.332774051781916e-05, + "loss": 3.4558, + "step": 1629184 + }, + { + "epoch": 0.01, + "learning_rate": 2.331935457030864e-05, + "loss": 3.4524, + "step": 1629696 + }, + { + "epoch": 0.01, + "learning_rate": 2.3310985001601848e-05, + "loss": 3.4574, + "step": 1630208 + }, + { + "epoch": 0.01, + "learning_rate": 2.3302599054091328e-05, + "loss": 3.4457, + "step": 1630720 + }, + { + "epoch": 0.01, + "learning_rate": 2.3294213106580808e-05, + "loss": 3.4571, + "step": 1631232 + }, + { + "epoch": 0.01, + "learning_rate": 2.3285827159070287e-05, + "loss": 3.456, + "step": 1631744 + }, + { + "epoch": 0.01, + "learning_rate": 2.3277441211559767e-05, + "loss": 3.456, + "step": 1632256 + }, + { + "epoch": 0.01, + "learning_rate": 2.3269055264049247e-05, + "loss": 3.4636, + "step": 1632768 + }, + { + "epoch": 0.01, + "learning_rate": 2.3260669316538727e-05, + "loss": 3.4475, + "step": 1633280 + }, + { + "epoch": 0.01, + "learning_rate": 2.3252299747831936e-05, + "loss": 3.4551, + "step": 1633792 + }, + { + "epoch": 0.01, + "learning_rate": 2.3243913800321416e-05, + "loss": 3.4647, + "step": 1634304 + }, + { + "epoch": 0.01, + "learning_rate": 2.32355278528109e-05, + "loss": 3.4488, + "step": 1634816 + }, + { + "epoch": 0.01, + "learning_rate": 2.322714190530038e-05, + "loss": 3.4498, + "step": 1635328 + }, + { + "epoch": 0.01, + "learning_rate": 2.321877233659359e-05, + "loss": 3.4583, + "step": 1635840 + }, + { + "epoch": 0.01, + "learning_rate": 2.321038638908307e-05, + "loss": 3.4634, + "step": 1636352 + }, + { + "epoch": 0.01, + "learning_rate": 2.320201682037628e-05, + "loss": 3.4476, + "step": 1636864 + }, + { + "epoch": 0.01, + "learning_rate": 2.319363087286576e-05, + "loss": 3.449, + "step": 1637376 + }, + { + "epoch": 0.01, + "learning_rate": 2.318524492535524e-05, + "loss": 3.4402, + "step": 1637888 + }, + { + "epoch": 0.01, + "learning_rate": 2.317685897784472e-05, + "loss": 3.4564, + "step": 1638400 + }, + { + "epoch": 0.01, + "learning_rate": 2.31684730303342e-05, + "loss": 3.4647, + "step": 1638912 + }, + { + "epoch": 0.01, + "learning_rate": 2.316010346162741e-05, + "loss": 3.4563, + "step": 1639424 + }, + { + "epoch": 0.01, + "learning_rate": 2.315171751411689e-05, + "loss": 3.4612, + "step": 1639936 + }, + { + "epoch": 0.01, + "learning_rate": 2.314333156660637e-05, + "loss": 3.463, + "step": 1640448 + }, + { + "epoch": 0.01, + "learning_rate": 2.3134945619095853e-05, + "loss": 3.473, + "step": 1640960 + }, + { + "epoch": 0.01, + "learning_rate": 2.3126559671585333e-05, + "loss": 3.4471, + "step": 1641472 + }, + { + "epoch": 0.01, + "learning_rate": 2.3118173724074813e-05, + "loss": 3.4615, + "step": 1641984 + }, + { + "epoch": 0.01, + "learning_rate": 2.3109787776564293e-05, + "loss": 3.4581, + "step": 1642496 + }, + { + "epoch": 0.01, + "learning_rate": 2.310140182905377e-05, + "loss": 3.4498, + "step": 1643008 + }, + { + "epoch": 0.01, + "learning_rate": 2.3093032260346982e-05, + "loss": 3.4624, + "step": 1643520 + }, + { + "epoch": 0.01, + "learning_rate": 2.3084646312836462e-05, + "loss": 3.4616, + "step": 1644032 + }, + { + "epoch": 0.01, + "learning_rate": 2.3076276744129675e-05, + "loss": 3.4598, + "step": 1644544 + }, + { + "epoch": 0.01, + "learning_rate": 2.3067890796619155e-05, + "loss": 3.4604, + "step": 1645056 + }, + { + "epoch": 0.01, + "learning_rate": 2.3059504849108635e-05, + "loss": 3.4573, + "step": 1645568 + }, + { + "epoch": 0.01, + "learning_rate": 2.3051118901598115e-05, + "loss": 3.4502, + "step": 1646080 + }, + { + "epoch": 0.01, + "learning_rate": 2.304273295408759e-05, + "loss": 3.4559, + "step": 1646592 + }, + { + "epoch": 0.01, + "learning_rate": 2.303434700657707e-05, + "loss": 3.4607, + "step": 1647104 + }, + { + "epoch": 0.01, + "learning_rate": 2.3025961059066554e-05, + "loss": 3.4504, + "step": 1647616 + }, + { + "epoch": 0.01, + "learning_rate": 2.3017575111556034e-05, + "loss": 3.4535, + "step": 1648128 + }, + { + "epoch": 0.02, + "learning_rate": 2.3009205542849244e-05, + "loss": 3.4602, + "step": 1648640 + }, + { + "epoch": 0.02, + "learning_rate": 2.3000819595338724e-05, + "loss": 3.4584, + "step": 1649152 + }, + { + "epoch": 0.02, + "learning_rate": 2.2992433647828203e-05, + "loss": 3.4501, + "step": 1649664 + }, + { + "epoch": 0.02, + "learning_rate": 2.2984047700317683e-05, + "loss": 3.4534, + "step": 1650176 + }, + { + "epoch": 0.02, + "learning_rate": 2.2975678131610896e-05, + "loss": 3.4681, + "step": 1650688 + }, + { + "epoch": 0.02, + "learning_rate": 2.2967292184100376e-05, + "loss": 3.4623, + "step": 1651200 + }, + { + "epoch": 0.02, + "learning_rate": 2.2958906236589856e-05, + "loss": 3.4616, + "step": 1651712 + }, + { + "epoch": 0.02, + "learning_rate": 2.2950520289079336e-05, + "loss": 3.4432, + "step": 1652224 + }, + { + "epoch": 0.02, + "learning_rate": 2.2942150720372545e-05, + "loss": 3.4598, + "step": 1652736 + }, + { + "epoch": 0.02, + "learning_rate": 2.2933764772862025e-05, + "loss": 3.4519, + "step": 1653248 + }, + { + "epoch": 0.02, + "learning_rate": 2.2925378825351508e-05, + "loss": 3.4626, + "step": 1653760 + }, + { + "epoch": 0.02, + "learning_rate": 2.2916992877840988e-05, + "loss": 3.4626, + "step": 1654272 + }, + { + "epoch": 0.02, + "learning_rate": 2.2908623309134197e-05, + "loss": 3.4516, + "step": 1654784 + }, + { + "epoch": 0.02, + "learning_rate": 2.2900237361623677e-05, + "loss": 3.4479, + "step": 1655296 + }, + { + "epoch": 0.02, + "learning_rate": 2.2891851414113157e-05, + "loss": 3.4562, + "step": 1655808 + }, + { + "epoch": 0.02, + "learning_rate": 2.2883465466602637e-05, + "loss": 3.4337, + "step": 1656320 + }, + { + "epoch": 0.02, + "learning_rate": 2.287509589789585e-05, + "loss": 3.4575, + "step": 1656832 + }, + { + "epoch": 0.02, + "learning_rate": 2.286670995038533e-05, + "loss": 3.4455, + "step": 1657344 + }, + { + "epoch": 0.02, + "learning_rate": 2.285832400287481e-05, + "loss": 3.4587, + "step": 1657856 + }, + { + "epoch": 0.02, + "learning_rate": 2.284993805536429e-05, + "loss": 3.4428, + "step": 1658368 + }, + { + "epoch": 0.02, + "learning_rate": 2.28415684866575e-05, + "loss": 3.4599, + "step": 1658880 + }, + { + "epoch": 0.02, + "learning_rate": 2.283318253914698e-05, + "loss": 3.4484, + "step": 1659392 + }, + { + "epoch": 0.02, + "learning_rate": 2.2824796591636462e-05, + "loss": 3.4547, + "step": 1659904 + }, + { + "epoch": 0.02, + "learning_rate": 2.2816410644125942e-05, + "loss": 3.4588, + "step": 1660416 + }, + { + "epoch": 0.02, + "learning_rate": 2.280804107541915e-05, + "loss": 3.4531, + "step": 1660928 + }, + { + "epoch": 0.02, + "learning_rate": 2.279965512790863e-05, + "loss": 3.4662, + "step": 1661440 + }, + { + "epoch": 0.02, + "learning_rate": 2.279126918039811e-05, + "loss": 3.4734, + "step": 1661952 + }, + { + "epoch": 0.02, + "learning_rate": 2.278288323288759e-05, + "loss": 3.456, + "step": 1662464 + }, + { + "epoch": 0.02, + "learning_rate": 2.2774530042984536e-05, + "loss": 3.4532, + "step": 1662976 + }, + { + "epoch": 0.02, + "learning_rate": 2.2766144095474012e-05, + "loss": 3.457, + "step": 1663488 + }, + { + "epoch": 0.02, + "learning_rate": 2.2757758147963492e-05, + "loss": 3.4544, + "step": 1664000 + }, + { + "epoch": 0.02, + "learning_rate": 2.2749372200452972e-05, + "loss": 3.4436, + "step": 1664512 + }, + { + "epoch": 0.02, + "learning_rate": 2.2741002631746185e-05, + "loss": 3.4666, + "step": 1665024 + }, + { + "epoch": 0.02, + "learning_rate": 2.2732616684235665e-05, + "loss": 3.4445, + "step": 1665536 + }, + { + "epoch": 0.02, + "learning_rate": 2.2724230736725145e-05, + "loss": 3.4645, + "step": 1666048 + }, + { + "epoch": 0.02, + "learning_rate": 2.2715844789214625e-05, + "loss": 3.4549, + "step": 1666560 + }, + { + "epoch": 0.02, + "learning_rate": 2.2707458841704105e-05, + "loss": 3.4578, + "step": 1667072 + }, + { + "epoch": 0.02, + "learning_rate": 2.2699072894193585e-05, + "loss": 3.4483, + "step": 1667584 + }, + { + "epoch": 0.02, + "learning_rate": 2.2690686946683064e-05, + "loss": 3.4564, + "step": 1668096 + }, + { + "epoch": 0.02, + "learning_rate": 2.268230099917254e-05, + "loss": 3.4516, + "step": 1668608 + }, + { + "epoch": 0.02, + "learning_rate": 2.2673931430465757e-05, + "loss": 3.461, + "step": 1669120 + }, + { + "epoch": 0.02, + "learning_rate": 2.2665545482955237e-05, + "loss": 3.4536, + "step": 1669632 + }, + { + "epoch": 0.02, + "learning_rate": 2.2657159535444717e-05, + "loss": 3.4634, + "step": 1670144 + }, + { + "epoch": 0.02, + "learning_rate": 2.2648773587934193e-05, + "loss": 3.441, + "step": 1670656 + }, + { + "epoch": 0.02, + "learning_rate": 2.2640404019227406e-05, + "loss": 3.4671, + "step": 1671168 + }, + { + "epoch": 0.02, + "learning_rate": 2.2632018071716886e-05, + "loss": 3.4514, + "step": 1671680 + }, + { + "epoch": 0.02, + "learning_rate": 2.2623632124206366e-05, + "loss": 3.4588, + "step": 1672192 + }, + { + "epoch": 0.02, + "learning_rate": 2.2615246176695846e-05, + "loss": 3.454, + "step": 1672704 + }, + { + "epoch": 0.02, + "learning_rate": 2.2606876607989058e-05, + "loss": 3.4608, + "step": 1673216 + }, + { + "epoch": 0.02, + "learning_rate": 2.2598490660478538e-05, + "loss": 3.4554, + "step": 1673728 + }, + { + "epoch": 0.02, + "learning_rate": 2.2590104712968015e-05, + "loss": 3.471, + "step": 1674240 + }, + { + "epoch": 0.02, + "learning_rate": 2.2581718765457495e-05, + "loss": 3.4445, + "step": 1674752 + }, + { + "epoch": 0.02, + "learning_rate": 2.257336557555444e-05, + "loss": 3.4568, + "step": 1675264 + }, + { + "epoch": 0.02, + "learning_rate": 2.256497962804392e-05, + "loss": 3.4553, + "step": 1675776 + }, + { + "epoch": 0.02, + "learning_rate": 2.25565936805334e-05, + "loss": 3.4544, + "step": 1676288 + }, + { + "epoch": 0.02, + "learning_rate": 2.254820773302288e-05, + "loss": 3.4513, + "step": 1676800 + }, + { + "epoch": 0.02, + "learning_rate": 2.253982178551236e-05, + "loss": 3.4636, + "step": 1677312 + }, + { + "epoch": 0.02, + "learning_rate": 2.253143583800184e-05, + "loss": 3.4638, + "step": 1677824 + }, + { + "epoch": 0.02, + "learning_rate": 2.252304989049132e-05, + "loss": 3.4408, + "step": 1678336 + }, + { + "epoch": 0.02, + "learning_rate": 2.25146639429808e-05, + "loss": 3.46, + "step": 1678848 + }, + { + "epoch": 0.03, + "eval_loss": 3.850989818572998, + "eval_runtime": 308.4348, + "eval_samples_per_second": 1237.185, + "eval_steps_per_second": 38.663, + "step": 1679040 + }, + { + "epoch": 1.0, + "learning_rate": 2.2506294374274012e-05, + "loss": 3.4523, + "step": 1679360 + }, + { + "epoch": 1.0, + "learning_rate": 2.249790842676349e-05, + "loss": 3.4437, + "step": 1679872 + }, + { + "epoch": 1.0, + "learning_rate": 2.248952247925297e-05, + "loss": 3.4606, + "step": 1680384 + }, + { + "epoch": 1.0, + "learning_rate": 2.248113653174245e-05, + "loss": 3.4547, + "step": 1680896 + }, + { + "epoch": 1.0, + "learning_rate": 2.2472766963035664e-05, + "loss": 3.4583, + "step": 1681408 + }, + { + "epoch": 1.0, + "learning_rate": 2.246438101552514e-05, + "loss": 3.4466, + "step": 1681920 + }, + { + "epoch": 1.0, + "learning_rate": 2.245599506801462e-05, + "loss": 3.4473, + "step": 1682432 + }, + { + "epoch": 1.0, + "learning_rate": 2.24476091205041e-05, + "loss": 3.4457, + "step": 1682944 + }, + { + "epoch": 1.0, + "learning_rate": 2.243923955179731e-05, + "loss": 3.454, + "step": 1683456 + }, + { + "epoch": 1.0, + "learning_rate": 2.2430853604286793e-05, + "loss": 3.4505, + "step": 1683968 + }, + { + "epoch": 1.0, + "learning_rate": 2.2422467656776273e-05, + "loss": 3.4523, + "step": 1684480 + }, + { + "epoch": 1.0, + "learning_rate": 2.2414081709265753e-05, + "loss": 3.4609, + "step": 1684992 + }, + { + "epoch": 1.0, + "learning_rate": 2.2405728519362695e-05, + "loss": 3.4479, + "step": 1685504 + }, + { + "epoch": 1.0, + "learning_rate": 2.2397342571852175e-05, + "loss": 3.4513, + "step": 1686016 + }, + { + "epoch": 1.0, + "learning_rate": 2.2388956624341655e-05, + "loss": 3.4544, + "step": 1686528 + }, + { + "epoch": 1.0, + "learning_rate": 2.2380570676831138e-05, + "loss": 3.4462, + "step": 1687040 + }, + { + "epoch": 1.0, + "learning_rate": 2.2372184729320615e-05, + "loss": 3.439, + "step": 1687552 + }, + { + "epoch": 1.0, + "learning_rate": 2.2363798781810094e-05, + "loss": 3.4485, + "step": 1688064 + }, + { + "epoch": 1.0, + "learning_rate": 2.2355412834299574e-05, + "loss": 3.4453, + "step": 1688576 + }, + { + "epoch": 1.0, + "learning_rate": 2.2347026886789054e-05, + "loss": 3.4619, + "step": 1689088 + }, + { + "epoch": 1.0, + "learning_rate": 2.2338657318082263e-05, + "loss": 3.4527, + "step": 1689600 + }, + { + "epoch": 1.0, + "learning_rate": 2.2330271370571747e-05, + "loss": 3.4551, + "step": 1690112 + }, + { + "epoch": 1.0, + "learning_rate": 2.2321885423061227e-05, + "loss": 3.4594, + "step": 1690624 + }, + { + "epoch": 1.0, + "learning_rate": 2.2313499475550707e-05, + "loss": 3.4597, + "step": 1691136 + }, + { + "epoch": 1.0, + "learning_rate": 2.2305129906843916e-05, + "loss": 3.44, + "step": 1691648 + }, + { + "epoch": 1.0, + "learning_rate": 2.2296743959333396e-05, + "loss": 3.4549, + "step": 1692160 + }, + { + "epoch": 1.0, + "learning_rate": 2.2288374390626608e-05, + "loss": 3.4417, + "step": 1692672 + }, + { + "epoch": 1.0, + "learning_rate": 2.2279988443116088e-05, + "loss": 3.449, + "step": 1693184 + }, + { + "epoch": 1.0, + "learning_rate": 2.2271602495605568e-05, + "loss": 3.4445, + "step": 1693696 + }, + { + "epoch": 1.0, + "learning_rate": 2.2263216548095048e-05, + "loss": 3.4436, + "step": 1694208 + }, + { + "epoch": 1.01, + "learning_rate": 2.2254830600584528e-05, + "loss": 3.4589, + "step": 1694720 + }, + { + "epoch": 1.01, + "learning_rate": 2.2246444653074008e-05, + "loss": 3.4511, + "step": 1695232 + }, + { + "epoch": 1.01, + "learning_rate": 2.2238075084367217e-05, + "loss": 3.4485, + "step": 1695744 + }, + { + "epoch": 1.01, + "learning_rate": 2.22296891368567e-05, + "loss": 3.4552, + "step": 1696256 + }, + { + "epoch": 1.01, + "learning_rate": 2.222130318934618e-05, + "loss": 3.4499, + "step": 1696768 + }, + { + "epoch": 1.01, + "learning_rate": 2.221291724183566e-05, + "loss": 3.4569, + "step": 1697280 + }, + { + "epoch": 1.01, + "learning_rate": 2.220453129432514e-05, + "loss": 3.4422, + "step": 1697792 + }, + { + "epoch": 1.01, + "learning_rate": 2.2196145346814617e-05, + "loss": 3.4454, + "step": 1698304 + }, + { + "epoch": 1.01, + "learning_rate": 2.2187759399304097e-05, + "loss": 3.4407, + "step": 1698816 + }, + { + "epoch": 1.01, + "learning_rate": 2.217938983059731e-05, + "loss": 3.4452, + "step": 1699328 + }, + { + "epoch": 1.01, + "learning_rate": 2.2171003883086793e-05, + "loss": 3.445, + "step": 1699840 + }, + { + "epoch": 1.01, + "learning_rate": 2.216261793557627e-05, + "loss": 3.4544, + "step": 1700352 + }, + { + "epoch": 1.01, + "learning_rate": 2.215423198806575e-05, + "loss": 3.4536, + "step": 1700864 + }, + { + "epoch": 1.01, + "learning_rate": 2.214584604055523e-05, + "loss": 3.4513, + "step": 1701376 + }, + { + "epoch": 1.01, + "learning_rate": 2.213746009304471e-05, + "loss": 3.4596, + "step": 1701888 + }, + { + "epoch": 1.01, + "learning_rate": 2.212907414553419e-05, + "loss": 3.4532, + "step": 1702400 + }, + { + "epoch": 1.01, + "learning_rate": 2.21207045768274e-05, + "loss": 3.4533, + "step": 1702912 + }, + { + "epoch": 1.01, + "learning_rate": 2.211231862931688e-05, + "loss": 3.4406, + "step": 1703424 + }, + { + "epoch": 1.01, + "learning_rate": 2.210393268180636e-05, + "loss": 3.4304, + "step": 1703936 + }, + { + "epoch": 1.01, + "learning_rate": 2.209554673429584e-05, + "loss": 3.462, + "step": 1704448 + }, + { + "epoch": 1.01, + "learning_rate": 2.208717716558905e-05, + "loss": 3.4471, + "step": 1704960 + }, + { + "epoch": 1.01, + "learning_rate": 2.207879121807853e-05, + "loss": 3.4402, + "step": 1705472 + }, + { + "epoch": 1.01, + "learning_rate": 2.207040527056801e-05, + "loss": 3.4452, + "step": 1705984 + }, + { + "epoch": 1.01, + "learning_rate": 2.2062019323057494e-05, + "loss": 3.4389, + "step": 1706496 + }, + { + "epoch": 1.01, + "learning_rate": 2.205363337554697e-05, + "loss": 3.4382, + "step": 1707008 + }, + { + "epoch": 1.01, + "learning_rate": 2.2045263806840183e-05, + "loss": 3.4402, + "step": 1707520 + }, + { + "epoch": 1.01, + "learning_rate": 2.2036877859329663e-05, + "loss": 3.4444, + "step": 1708032 + }, + { + "epoch": 1.01, + "learning_rate": 2.2028491911819143e-05, + "loss": 3.4462, + "step": 1708544 + }, + { + "epoch": 1.01, + "learning_rate": 2.2020105964308623e-05, + "loss": 3.4553, + "step": 1709056 + }, + { + "epoch": 1.01, + "learning_rate": 2.2011720016798103e-05, + "loss": 3.4373, + "step": 1709568 + }, + { + "epoch": 1.01, + "learning_rate": 2.2003334069287583e-05, + "loss": 3.4393, + "step": 1710080 + }, + { + "epoch": 1.01, + "learning_rate": 2.1994948121777063e-05, + "loss": 3.4596, + "step": 1710592 + }, + { + "epoch": 1.01, + "learning_rate": 2.1986562174266543e-05, + "loss": 3.4311, + "step": 1711104 + }, + { + "epoch": 1.01, + "learning_rate": 2.197819260555975e-05, + "loss": 3.4393, + "step": 1711616 + }, + { + "epoch": 1.01, + "learning_rate": 2.196980665804923e-05, + "loss": 3.4468, + "step": 1712128 + }, + { + "epoch": 1.01, + "learning_rate": 2.196142071053871e-05, + "loss": 3.4568, + "step": 1712640 + }, + { + "epoch": 1.01, + "learning_rate": 2.1953051141831924e-05, + "loss": 3.4353, + "step": 1713152 + }, + { + "epoch": 1.01, + "learning_rate": 2.1944665194321404e-05, + "loss": 3.4356, + "step": 1713664 + }, + { + "epoch": 1.01, + "learning_rate": 2.1936279246810884e-05, + "loss": 3.4279, + "step": 1714176 + }, + { + "epoch": 1.01, + "learning_rate": 2.1927893299300364e-05, + "loss": 3.4412, + "step": 1714688 + }, + { + "epoch": 1.01, + "learning_rate": 2.1919507351789844e-05, + "loss": 3.4562, + "step": 1715200 + }, + { + "epoch": 1.01, + "learning_rate": 2.1911121404279324e-05, + "loss": 3.446, + "step": 1715712 + }, + { + "epoch": 1.01, + "learning_rate": 2.1902735456768804e-05, + "loss": 3.4489, + "step": 1716224 + }, + { + "epoch": 1.01, + "learning_rate": 2.1894349509258284e-05, + "loss": 3.4528, + "step": 1716736 + }, + { + "epoch": 1.01, + "learning_rate": 2.1885979940551496e-05, + "loss": 3.461, + "step": 1717248 + }, + { + "epoch": 1.01, + "learning_rate": 2.1877593993040976e-05, + "loss": 3.4397, + "step": 1717760 + }, + { + "epoch": 1.01, + "learning_rate": 2.1869208045530453e-05, + "loss": 3.4503, + "step": 1718272 + }, + { + "epoch": 1.01, + "learning_rate": 2.1860822098019933e-05, + "loss": 3.4475, + "step": 1718784 + }, + { + "epoch": 1.01, + "learning_rate": 2.185245252931315e-05, + "loss": 3.4365, + "step": 1719296 + }, + { + "epoch": 1.01, + "learning_rate": 2.1844066581802625e-05, + "loss": 3.4487, + "step": 1719808 + }, + { + "epoch": 1.01, + "learning_rate": 2.1835680634292105e-05, + "loss": 3.4499, + "step": 1720320 + }, + { + "epoch": 1.01, + "learning_rate": 2.1827311065585318e-05, + "loss": 3.4525, + "step": 1720832 + }, + { + "epoch": 1.01, + "learning_rate": 2.1818925118074798e-05, + "loss": 3.4481, + "step": 1721344 + }, + { + "epoch": 1.01, + "learning_rate": 2.1810539170564277e-05, + "loss": 3.4486, + "step": 1721856 + }, + { + "epoch": 1.01, + "learning_rate": 2.1802153223053757e-05, + "loss": 3.4391, + "step": 1722368 + }, + { + "epoch": 1.01, + "learning_rate": 2.1793767275543237e-05, + "loss": 3.4472, + "step": 1722880 + }, + { + "epoch": 1.01, + "learning_rate": 2.1785381328032717e-05, + "loss": 3.4469, + "step": 1723392 + }, + { + "epoch": 1.01, + "learning_rate": 2.1776995380522197e-05, + "loss": 3.4428, + "step": 1723904 + }, + { + "epoch": 1.01, + "learning_rate": 2.1768609433011677e-05, + "loss": 3.4427, + "step": 1724416 + }, + { + "epoch": 1.02, + "learning_rate": 2.1760239864304886e-05, + "loss": 3.442, + "step": 1724928 + }, + { + "epoch": 1.02, + "learning_rate": 2.175185391679437e-05, + "loss": 3.451, + "step": 1725440 + }, + { + "epoch": 1.02, + "learning_rate": 2.174346796928385e-05, + "loss": 3.4391, + "step": 1725952 + }, + { + "epoch": 1.02, + "learning_rate": 2.173508202177333e-05, + "loss": 3.4384, + "step": 1726464 + }, + { + "epoch": 1.02, + "learning_rate": 2.172671245306654e-05, + "loss": 3.4596, + "step": 1726976 + }, + { + "epoch": 1.02, + "learning_rate": 2.171832650555602e-05, + "loss": 3.4489, + "step": 1727488 + }, + { + "epoch": 1.02, + "learning_rate": 2.17099405580455e-05, + "loss": 3.4499, + "step": 1728000 + }, + { + "epoch": 1.02, + "learning_rate": 2.170155461053498e-05, + "loss": 3.4327, + "step": 1728512 + }, + { + "epoch": 1.02, + "learning_rate": 2.169318504182819e-05, + "loss": 3.4508, + "step": 1729024 + }, + { + "epoch": 1.02, + "learning_rate": 2.168479909431767e-05, + "loss": 3.4383, + "step": 1729536 + }, + { + "epoch": 1.02, + "learning_rate": 2.167641314680715e-05, + "loss": 3.4486, + "step": 1730048 + }, + { + "epoch": 1.02, + "learning_rate": 2.166802719929663e-05, + "loss": 3.4552, + "step": 1730560 + }, + { + "epoch": 1.02, + "learning_rate": 2.165965763058984e-05, + "loss": 3.4409, + "step": 1731072 + }, + { + "epoch": 1.02, + "learning_rate": 2.165127168307932e-05, + "loss": 3.4399, + "step": 1731584 + }, + { + "epoch": 1.02, + "learning_rate": 2.1642885735568803e-05, + "loss": 3.4417, + "step": 1732096 + }, + { + "epoch": 1.02, + "learning_rate": 2.163449978805828e-05, + "loss": 3.4235, + "step": 1732608 + }, + { + "epoch": 1.02, + "learning_rate": 2.1626130219351492e-05, + "loss": 3.4494, + "step": 1733120 + }, + { + "epoch": 1.02, + "learning_rate": 2.1617744271840972e-05, + "loss": 3.4315, + "step": 1733632 + }, + { + "epoch": 1.02, + "learning_rate": 2.1609358324330452e-05, + "loss": 3.4465, + "step": 1734144 + }, + { + "epoch": 1.02, + "learning_rate": 2.1600972376819932e-05, + "loss": 3.4342, + "step": 1734656 + }, + { + "epoch": 1.02, + "learning_rate": 2.1592602808113145e-05, + "loss": 3.4478, + "step": 1735168 + }, + { + "epoch": 1.02, + "learning_rate": 2.1584216860602625e-05, + "loss": 3.4402, + "step": 1735680 + }, + { + "epoch": 1.02, + "learning_rate": 2.1575830913092105e-05, + "loss": 3.4415, + "step": 1736192 + }, + { + "epoch": 1.02, + "learning_rate": 2.156744496558158e-05, + "loss": 3.4507, + "step": 1736704 + }, + { + "epoch": 1.02, + "learning_rate": 2.1559075396874794e-05, + "loss": 3.4384, + "step": 1737216 + }, + { + "epoch": 1.02, + "learning_rate": 2.1550689449364274e-05, + "loss": 3.4538, + "step": 1737728 + }, + { + "epoch": 1.02, + "learning_rate": 2.1542303501853754e-05, + "loss": 3.4594, + "step": 1738240 + }, + { + "epoch": 1.02, + "learning_rate": 2.1533917554343234e-05, + "loss": 3.4443, + "step": 1738752 + }, + { + "epoch": 1.02, + "learning_rate": 2.1525564364440175e-05, + "loss": 3.4468, + "step": 1739264 + }, + { + "epoch": 1.02, + "learning_rate": 2.1517178416929655e-05, + "loss": 3.4413, + "step": 1739776 + }, + { + "epoch": 1.02, + "learning_rate": 2.1508792469419135e-05, + "loss": 3.4433, + "step": 1740288 + }, + { + "epoch": 1.02, + "learning_rate": 2.150040652190862e-05, + "loss": 3.4373, + "step": 1740800 + }, + { + "epoch": 1.02, + "learning_rate": 2.14920205743981e-05, + "loss": 3.4546, + "step": 1741312 + }, + { + "epoch": 1.02, + "learning_rate": 2.1483634626887575e-05, + "loss": 3.4324, + "step": 1741824 + }, + { + "epoch": 1.02, + "learning_rate": 2.1475248679377055e-05, + "loss": 3.4518, + "step": 1742336 + }, + { + "epoch": 1.02, + "learning_rate": 2.1466862731866535e-05, + "loss": 3.4462, + "step": 1742848 + }, + { + "epoch": 1.02, + "learning_rate": 2.1458493163159747e-05, + "loss": 3.4481, + "step": 1743360 + }, + { + "epoch": 1.02, + "learning_rate": 2.1450107215649227e-05, + "loss": 3.4354, + "step": 1743872 + }, + { + "epoch": 1.02, + "learning_rate": 2.144173764694244e-05, + "loss": 3.4461, + "step": 1744384 + }, + { + "epoch": 1.02, + "learning_rate": 2.143335169943192e-05, + "loss": 3.4373, + "step": 1744896 + }, + { + "epoch": 1.02, + "learning_rate": 2.14249657519214e-05, + "loss": 3.4533, + "step": 1745408 + }, + { + "epoch": 1.02, + "learning_rate": 2.1416579804410876e-05, + "loss": 3.4387, + "step": 1745920 + }, + { + "epoch": 1.02, + "learning_rate": 2.1408193856900356e-05, + "loss": 3.4527, + "step": 1746432 + }, + { + "epoch": 1.02, + "learning_rate": 2.139980790938984e-05, + "loss": 3.4293, + "step": 1746944 + }, + { + "epoch": 1.02, + "learning_rate": 2.139142196187932e-05, + "loss": 3.4581, + "step": 1747456 + }, + { + "epoch": 1.02, + "learning_rate": 2.13830360143688e-05, + "loss": 3.4427, + "step": 1747968 + }, + { + "epoch": 1.02, + "learning_rate": 2.137466644566201e-05, + "loss": 3.4465, + "step": 1748480 + }, + { + "epoch": 1.02, + "learning_rate": 2.136628049815149e-05, + "loss": 3.4429, + "step": 1748992 + }, + { + "epoch": 1.02, + "learning_rate": 2.13579109294447e-05, + "loss": 3.444, + "step": 1749504 + }, + { + "epoch": 1.02, + "learning_rate": 2.134952498193418e-05, + "loss": 3.4482, + "step": 1750016 + }, + { + "epoch": 1.02, + "learning_rate": 2.134113903442366e-05, + "loss": 3.4625, + "step": 1750528 + }, + { + "epoch": 1.02, + "learning_rate": 2.133275308691314e-05, + "loss": 3.4291, + "step": 1751040 + }, + { + "epoch": 1.02, + "learning_rate": 2.132436713940262e-05, + "loss": 3.4446, + "step": 1751552 + }, + { + "epoch": 1.02, + "learning_rate": 2.13159811918921e-05, + "loss": 3.4419, + "step": 1752064 + }, + { + "epoch": 1.02, + "learning_rate": 2.130761162318531e-05, + "loss": 3.4463, + "step": 1752576 + }, + { + "epoch": 1.02, + "learning_rate": 2.129922567567479e-05, + "loss": 3.4384, + "step": 1753088 + }, + { + "epoch": 1.02, + "learning_rate": 2.1290839728164273e-05, + "loss": 3.4503, + "step": 1753600 + }, + { + "epoch": 1.02, + "learning_rate": 2.1282453780653753e-05, + "loss": 3.4514, + "step": 1754112 + }, + { + "epoch": 1.02, + "learning_rate": 2.127406783314323e-05, + "loss": 3.4318, + "step": 1754624 + }, + { + "epoch": 1.02, + "learning_rate": 2.126568188563271e-05, + "loss": 3.4508, + "step": 1755136 + }, + { + "epoch": 1.03, + "eval_loss": 3.8525586128234863, + "eval_runtime": 309.809, + "eval_samples_per_second": 1231.698, + "eval_steps_per_second": 38.491, + "step": 1755360 + }, + { + "epoch": 0.0, + "learning_rate": 2.125729593812219e-05, + "loss": 3.4409, + "step": 1755648 + }, + { + "epoch": 0.0, + "learning_rate": 2.124890999061167e-05, + "loss": 3.4353, + "step": 1756160 + }, + { + "epoch": 0.0, + "learning_rate": 2.124052404310115e-05, + "loss": 3.449, + "step": 1756672 + }, + { + "epoch": 0.0, + "learning_rate": 2.1232138095590633e-05, + "loss": 3.4401, + "step": 1757184 + }, + { + "epoch": 0.0, + "learning_rate": 2.1223768526883842e-05, + "loss": 3.4471, + "step": 1757696 + }, + { + "epoch": 0.0, + "learning_rate": 2.1215382579373322e-05, + "loss": 3.4353, + "step": 1758208 + }, + { + "epoch": 0.0, + "learning_rate": 2.1206996631862802e-05, + "loss": 3.4403, + "step": 1758720 + }, + { + "epoch": 0.0, + "learning_rate": 2.1198610684352282e-05, + "loss": 3.4333, + "step": 1759232 + }, + { + "epoch": 0.0, + "learning_rate": 2.1190241115645494e-05, + "loss": 3.4455, + "step": 1759744 + }, + { + "epoch": 0.0, + "learning_rate": 2.1181855168134974e-05, + "loss": 3.4354, + "step": 1760256 + }, + { + "epoch": 0.0, + "learning_rate": 2.1173469220624454e-05, + "loss": 3.4443, + "step": 1760768 + }, + { + "epoch": 0.0, + "learning_rate": 2.1165083273113934e-05, + "loss": 3.4502, + "step": 1761280 + }, + { + "epoch": 0.0, + "learning_rate": 2.1156713704407143e-05, + "loss": 3.444, + "step": 1761792 + }, + { + "epoch": 0.0, + "learning_rate": 2.1148327756896623e-05, + "loss": 3.4381, + "step": 1762304 + }, + { + "epoch": 0.0, + "learning_rate": 2.1139941809386103e-05, + "loss": 3.4398, + "step": 1762816 + }, + { + "epoch": 0.0, + "learning_rate": 2.1131555861875587e-05, + "loss": 3.4306, + "step": 1763328 + }, + { + "epoch": 0.0, + "learning_rate": 2.1123186293168796e-05, + "loss": 3.4295, + "step": 1763840 + }, + { + "epoch": 0.0, + "learning_rate": 2.1114800345658276e-05, + "loss": 3.4384, + "step": 1764352 + }, + { + "epoch": 0.0, + "learning_rate": 2.1106414398147756e-05, + "loss": 3.4378, + "step": 1764864 + }, + { + "epoch": 0.0, + "learning_rate": 2.1098028450637236e-05, + "loss": 3.4454, + "step": 1765376 + }, + { + "epoch": 0.0, + "learning_rate": 2.1089658881930448e-05, + "loss": 3.4474, + "step": 1765888 + }, + { + "epoch": 0.0, + "learning_rate": 2.1081272934419928e-05, + "loss": 3.4409, + "step": 1766400 + }, + { + "epoch": 0.0, + "learning_rate": 2.1072886986909408e-05, + "loss": 3.4492, + "step": 1766912 + }, + { + "epoch": 0.0, + "learning_rate": 2.1064517418202617e-05, + "loss": 3.4478, + "step": 1767424 + }, + { + "epoch": 0.0, + "learning_rate": 2.1056131470692097e-05, + "loss": 3.4301, + "step": 1767936 + }, + { + "epoch": 0.0, + "learning_rate": 2.1047745523181577e-05, + "loss": 3.4457, + "step": 1768448 + }, + { + "epoch": 0.0, + "learning_rate": 2.103937595447479e-05, + "loss": 3.4351, + "step": 1768960 + }, + { + "epoch": 0.0, + "learning_rate": 2.103099000696427e-05, + "loss": 3.4347, + "step": 1769472 + }, + { + "epoch": 0.0, + "learning_rate": 2.102260405945375e-05, + "loss": 3.4305, + "step": 1769984 + }, + { + "epoch": 0.0, + "learning_rate": 2.101421811194323e-05, + "loss": 3.4363, + "step": 1770496 + }, + { + "epoch": 0.01, + "learning_rate": 2.100583216443271e-05, + "loss": 3.4431, + "step": 1771008 + }, + { + "epoch": 0.01, + "learning_rate": 2.0997446216922186e-05, + "loss": 3.445, + "step": 1771520 + }, + { + "epoch": 0.01, + "learning_rate": 2.0989060269411666e-05, + "loss": 3.44, + "step": 1772032 + }, + { + "epoch": 0.01, + "learning_rate": 2.098067432190115e-05, + "loss": 3.4452, + "step": 1772544 + }, + { + "epoch": 0.01, + "learning_rate": 2.0972304753194358e-05, + "loss": 3.433, + "step": 1773056 + }, + { + "epoch": 0.01, + "learning_rate": 2.0963918805683838e-05, + "loss": 3.4451, + "step": 1773568 + }, + { + "epoch": 0.01, + "learning_rate": 2.0955532858173318e-05, + "loss": 3.4386, + "step": 1774080 + }, + { + "epoch": 0.01, + "learning_rate": 2.094716328946653e-05, + "loss": 3.4313, + "step": 1774592 + }, + { + "epoch": 0.01, + "learning_rate": 2.093877734195601e-05, + "loss": 3.4293, + "step": 1775104 + }, + { + "epoch": 0.01, + "learning_rate": 2.0930407773249223e-05, + "loss": 3.435, + "step": 1775616 + }, + { + "epoch": 0.01, + "learning_rate": 2.0922021825738703e-05, + "loss": 3.4389, + "step": 1776128 + }, + { + "epoch": 0.01, + "learning_rate": 2.0913635878228183e-05, + "loss": 3.4395, + "step": 1776640 + }, + { + "epoch": 0.01, + "learning_rate": 2.090524993071766e-05, + "loss": 3.4437, + "step": 1777152 + }, + { + "epoch": 0.01, + "learning_rate": 2.089686398320714e-05, + "loss": 3.4386, + "step": 1777664 + }, + { + "epoch": 0.01, + "learning_rate": 2.088847803569662e-05, + "loss": 3.4504, + "step": 1778176 + }, + { + "epoch": 0.01, + "learning_rate": 2.0880092088186103e-05, + "loss": 3.4395, + "step": 1778688 + }, + { + "epoch": 0.01, + "learning_rate": 2.0871722519479312e-05, + "loss": 3.4451, + "step": 1779200 + }, + { + "epoch": 0.01, + "learning_rate": 2.0863336571968792e-05, + "loss": 3.4327, + "step": 1779712 + }, + { + "epoch": 0.01, + "learning_rate": 2.0854950624458272e-05, + "loss": 3.4156, + "step": 1780224 + }, + { + "epoch": 0.01, + "learning_rate": 2.0846564676947752e-05, + "loss": 3.4511, + "step": 1780736 + }, + { + "epoch": 0.01, + "learning_rate": 2.0838195108240964e-05, + "loss": 3.4373, + "step": 1781248 + }, + { + "epoch": 0.01, + "learning_rate": 2.0829809160730444e-05, + "loss": 3.4342, + "step": 1781760 + }, + { + "epoch": 0.01, + "learning_rate": 2.0821423213219924e-05, + "loss": 3.4322, + "step": 1782272 + }, + { + "epoch": 0.01, + "learning_rate": 2.0813037265709404e-05, + "loss": 3.4297, + "step": 1782784 + }, + { + "epoch": 0.01, + "learning_rate": 2.0804651318198884e-05, + "loss": 3.4286, + "step": 1783296 + }, + { + "epoch": 0.01, + "learning_rate": 2.0796281749492093e-05, + "loss": 3.4271, + "step": 1783808 + }, + { + "epoch": 0.01, + "learning_rate": 2.0787895801981573e-05, + "loss": 3.4363, + "step": 1784320 + }, + { + "epoch": 0.01, + "learning_rate": 2.0779509854471056e-05, + "loss": 3.4302, + "step": 1784832 + }, + { + "epoch": 0.01, + "learning_rate": 2.0771123906960536e-05, + "loss": 3.4472, + "step": 1785344 + }, + { + "epoch": 0.01, + "learning_rate": 2.0762737959450013e-05, + "loss": 3.4289, + "step": 1785856 + }, + { + "epoch": 0.01, + "learning_rate": 2.0754352011939493e-05, + "loss": 3.4283, + "step": 1786368 + }, + { + "epoch": 0.01, + "learning_rate": 2.0745966064428973e-05, + "loss": 3.4495, + "step": 1786880 + }, + { + "epoch": 0.01, + "learning_rate": 2.0737580116918453e-05, + "loss": 3.4214, + "step": 1787392 + }, + { + "epoch": 0.01, + "learning_rate": 2.0729210548211665e-05, + "loss": 3.4278, + "step": 1787904 + }, + { + "epoch": 0.01, + "learning_rate": 2.0720824600701145e-05, + "loss": 3.4385, + "step": 1788416 + }, + { + "epoch": 0.01, + "learning_rate": 2.0712438653190625e-05, + "loss": 3.4432, + "step": 1788928 + }, + { + "epoch": 0.01, + "learning_rate": 2.0704069084483834e-05, + "loss": 3.4257, + "step": 1789440 + }, + { + "epoch": 0.01, + "learning_rate": 2.0695683136973314e-05, + "loss": 3.427, + "step": 1789952 + }, + { + "epoch": 0.01, + "learning_rate": 2.0687297189462794e-05, + "loss": 3.4195, + "step": 1790464 + }, + { + "epoch": 0.01, + "learning_rate": 2.0678911241952274e-05, + "loss": 3.4283, + "step": 1790976 + }, + { + "epoch": 0.01, + "learning_rate": 2.0670525294441758e-05, + "loss": 3.4467, + "step": 1791488 + }, + { + "epoch": 0.01, + "learning_rate": 2.0662139346931237e-05, + "loss": 3.4342, + "step": 1792000 + }, + { + "epoch": 0.01, + "learning_rate": 2.0653753399420717e-05, + "loss": 3.4363, + "step": 1792512 + }, + { + "epoch": 0.01, + "learning_rate": 2.0645367451910194e-05, + "loss": 3.4416, + "step": 1793024 + }, + { + "epoch": 0.01, + "learning_rate": 2.0636997883203406e-05, + "loss": 3.4498, + "step": 1793536 + }, + { + "epoch": 0.01, + "learning_rate": 2.0628611935692886e-05, + "loss": 3.4267, + "step": 1794048 + }, + { + "epoch": 0.01, + "learning_rate": 2.0620225988182366e-05, + "loss": 3.4425, + "step": 1794560 + }, + { + "epoch": 0.01, + "learning_rate": 2.0611840040671846e-05, + "loss": 3.4295, + "step": 1795072 + }, + { + "epoch": 0.01, + "learning_rate": 2.060347047196506e-05, + "loss": 3.4304, + "step": 1795584 + }, + { + "epoch": 0.01, + "learning_rate": 2.059508452445454e-05, + "loss": 3.433, + "step": 1796096 + }, + { + "epoch": 0.01, + "learning_rate": 2.0586698576944015e-05, + "loss": 3.4452, + "step": 1796608 + }, + { + "epoch": 0.01, + "learning_rate": 2.0578329008237228e-05, + "loss": 3.4373, + "step": 1797120 + }, + { + "epoch": 0.01, + "learning_rate": 2.056994306072671e-05, + "loss": 3.4421, + "step": 1797632 + }, + { + "epoch": 0.01, + "learning_rate": 2.056155711321619e-05, + "loss": 3.4338, + "step": 1798144 + }, + { + "epoch": 0.01, + "learning_rate": 2.0553171165705668e-05, + "loss": 3.4255, + "step": 1798656 + }, + { + "epoch": 0.01, + "learning_rate": 2.0544785218195148e-05, + "loss": 3.4387, + "step": 1799168 + }, + { + "epoch": 0.01, + "learning_rate": 2.0536399270684628e-05, + "loss": 3.4354, + "step": 1799680 + }, + { + "epoch": 0.01, + "learning_rate": 2.0528013323174108e-05, + "loss": 3.4302, + "step": 1800192 + }, + { + "epoch": 0.01, + "learning_rate": 2.0519627375663588e-05, + "loss": 3.4316, + "step": 1800704 + }, + { + "epoch": 0.02, + "learning_rate": 2.05112578069568e-05, + "loss": 3.4332, + "step": 1801216 + }, + { + "epoch": 0.02, + "learning_rate": 2.050287185944628e-05, + "loss": 3.4405, + "step": 1801728 + }, + { + "epoch": 0.02, + "learning_rate": 2.049448591193576e-05, + "loss": 3.4303, + "step": 1802240 + }, + { + "epoch": 0.02, + "learning_rate": 2.048609996442524e-05, + "loss": 3.4259, + "step": 1802752 + }, + { + "epoch": 0.02, + "learning_rate": 2.047773039571845e-05, + "loss": 3.4445, + "step": 1803264 + }, + { + "epoch": 0.02, + "learning_rate": 2.046934444820793e-05, + "loss": 3.4396, + "step": 1803776 + }, + { + "epoch": 0.02, + "learning_rate": 2.0460958500697412e-05, + "loss": 3.4391, + "step": 1804288 + }, + { + "epoch": 0.02, + "learning_rate": 2.0452572553186892e-05, + "loss": 3.4249, + "step": 1804800 + }, + { + "epoch": 0.02, + "learning_rate": 2.04442029844801e-05, + "loss": 3.4349, + "step": 1805312 + }, + { + "epoch": 0.02, + "learning_rate": 2.043581703696958e-05, + "loss": 3.4267, + "step": 1805824 + }, + { + "epoch": 0.02, + "learning_rate": 2.042743108945906e-05, + "loss": 3.4385, + "step": 1806336 + }, + { + "epoch": 0.02, + "learning_rate": 2.041904514194854e-05, + "loss": 3.4411, + "step": 1806848 + }, + { + "epoch": 0.02, + "learning_rate": 2.0410675573241754e-05, + "loss": 3.4338, + "step": 1807360 + }, + { + "epoch": 0.02, + "learning_rate": 2.0402289625731234e-05, + "loss": 3.4299, + "step": 1807872 + }, + { + "epoch": 0.02, + "learning_rate": 2.0393903678220714e-05, + "loss": 3.4262, + "step": 1808384 + }, + { + "epoch": 0.02, + "learning_rate": 2.0385517730710194e-05, + "loss": 3.4182, + "step": 1808896 + }, + { + "epoch": 0.02, + "learning_rate": 2.0377148162003403e-05, + "loss": 3.4335, + "step": 1809408 + }, + { + "epoch": 0.02, + "learning_rate": 2.0368762214492883e-05, + "loss": 3.4249, + "step": 1809920 + }, + { + "epoch": 0.02, + "learning_rate": 2.0360376266982366e-05, + "loss": 3.4385, + "step": 1810432 + }, + { + "epoch": 0.02, + "learning_rate": 2.0351990319471846e-05, + "loss": 3.4214, + "step": 1810944 + }, + { + "epoch": 0.02, + "learning_rate": 2.0343620750765055e-05, + "loss": 3.4342, + "step": 1811456 + }, + { + "epoch": 0.02, + "learning_rate": 2.0335234803254535e-05, + "loss": 3.4284, + "step": 1811968 + }, + { + "epoch": 0.02, + "learning_rate": 2.0326848855744015e-05, + "loss": 3.4342, + "step": 1812480 + }, + { + "epoch": 0.02, + "learning_rate": 2.0318462908233495e-05, + "loss": 3.4365, + "step": 1812992 + }, + { + "epoch": 0.02, + "learning_rate": 2.0310093339526707e-05, + "loss": 3.4288, + "step": 1813504 + }, + { + "epoch": 0.02, + "learning_rate": 2.0301707392016187e-05, + "loss": 3.4426, + "step": 1814016 + }, + { + "epoch": 0.02, + "learning_rate": 2.0293321444505667e-05, + "loss": 3.4469, + "step": 1814528 + }, + { + "epoch": 0.02, + "learning_rate": 2.0284935496995144e-05, + "loss": 3.4356, + "step": 1815040 + }, + { + "epoch": 0.02, + "learning_rate": 2.027658230709209e-05, + "loss": 3.4393, + "step": 1815552 + }, + { + "epoch": 0.02, + "learning_rate": 2.026819635958157e-05, + "loss": 3.4296, + "step": 1816064 + }, + { + "epoch": 0.02, + "learning_rate": 2.025981041207105e-05, + "loss": 3.432, + "step": 1816576 + }, + { + "epoch": 0.02, + "learning_rate": 2.025142446456053e-05, + "loss": 3.4298, + "step": 1817088 + }, + { + "epoch": 0.02, + "learning_rate": 2.024303851705001e-05, + "loss": 3.4399, + "step": 1817600 + }, + { + "epoch": 0.02, + "learning_rate": 2.023465256953949e-05, + "loss": 3.4231, + "step": 1818112 + }, + { + "epoch": 0.02, + "learning_rate": 2.0226266622028965e-05, + "loss": 3.441, + "step": 1818624 + }, + { + "epoch": 0.02, + "learning_rate": 2.0217880674518445e-05, + "loss": 3.4368, + "step": 1819136 + }, + { + "epoch": 0.02, + "learning_rate": 2.020951110581166e-05, + "loss": 3.4353, + "step": 1819648 + }, + { + "epoch": 0.02, + "learning_rate": 2.020112515830114e-05, + "loss": 3.4229, + "step": 1820160 + }, + { + "epoch": 0.02, + "learning_rate": 2.0192739210790618e-05, + "loss": 3.4372, + "step": 1820672 + }, + { + "epoch": 0.02, + "learning_rate": 2.0184353263280097e-05, + "loss": 3.4296, + "step": 1821184 + }, + { + "epoch": 0.02, + "learning_rate": 2.017598369457331e-05, + "loss": 3.4406, + "step": 1821696 + }, + { + "epoch": 0.02, + "learning_rate": 2.016759774706279e-05, + "loss": 3.4321, + "step": 1822208 + }, + { + "epoch": 0.02, + "learning_rate": 2.015921179955227e-05, + "loss": 3.4408, + "step": 1822720 + }, + { + "epoch": 0.02, + "learning_rate": 2.015082585204175e-05, + "loss": 3.4187, + "step": 1823232 + }, + { + "epoch": 0.02, + "learning_rate": 2.0142456283334962e-05, + "loss": 3.4503, + "step": 1823744 + }, + { + "epoch": 0.02, + "learning_rate": 2.013407033582444e-05, + "loss": 3.4286, + "step": 1824256 + }, + { + "epoch": 0.02, + "learning_rate": 2.012568438831392e-05, + "loss": 3.4339, + "step": 1824768 + }, + { + "epoch": 0.02, + "learning_rate": 2.01172984408034e-05, + "loss": 3.4332, + "step": 1825280 + }, + { + "epoch": 0.02, + "learning_rate": 2.0108928872096615e-05, + "loss": 3.431, + "step": 1825792 + }, + { + "epoch": 0.02, + "learning_rate": 2.010054292458609e-05, + "loss": 3.4371, + "step": 1826304 + }, + { + "epoch": 0.02, + "learning_rate": 2.009215697707557e-05, + "loss": 3.4484, + "step": 1826816 + }, + { + "epoch": 0.02, + "learning_rate": 2.008377102956505e-05, + "loss": 3.4218, + "step": 1827328 + }, + { + "epoch": 0.02, + "learning_rate": 2.0075401460858264e-05, + "loss": 3.4356, + "step": 1827840 + }, + { + "epoch": 0.02, + "learning_rate": 2.0067031892151476e-05, + "loss": 3.4332, + "step": 1828352 + }, + { + "epoch": 0.02, + "learning_rate": 2.0058645944640956e-05, + "loss": 3.4346, + "step": 1828864 + }, + { + "epoch": 0.02, + "learning_rate": 2.0050259997130436e-05, + "loss": 3.4288, + "step": 1829376 + }, + { + "epoch": 0.02, + "learning_rate": 2.0041874049619913e-05, + "loss": 3.4394, + "step": 1829888 + }, + { + "epoch": 0.02, + "learning_rate": 2.0033488102109393e-05, + "loss": 3.4418, + "step": 1830400 + }, + { + "epoch": 0.02, + "learning_rate": 2.0025102154598873e-05, + "loss": 3.4226, + "step": 1830912 + }, + { + "epoch": 0.02, + "learning_rate": 2.0016716207088352e-05, + "loss": 3.437, + "step": 1831424 + }, + { + "epoch": 0.03, + "eval_loss": 3.8533687591552734, + "eval_runtime": 303.3451, + "eval_samples_per_second": 1257.943, + "eval_steps_per_second": 39.312, + "step": 1831680 + }, + { + "epoch": 1.0, + "learning_rate": 2.0008330259577836e-05, + "loss": 3.4304, + "step": 1831936 + }, + { + "epoch": 1.0, + "learning_rate": 1.9999960690871045e-05, + "loss": 3.4296, + "step": 1832448 + }, + { + "epoch": 1.0, + "learning_rate": 1.9991574743360525e-05, + "loss": 3.4333, + "step": 1832960 + }, + { + "epoch": 1.0, + "learning_rate": 1.9983188795850005e-05, + "loss": 3.4282, + "step": 1833472 + }, + { + "epoch": 1.0, + "learning_rate": 1.9974819227143214e-05, + "loss": 3.439, + "step": 1833984 + }, + { + "epoch": 1.0, + "learning_rate": 1.9966433279632697e-05, + "loss": 3.423, + "step": 1834496 + }, + { + "epoch": 1.0, + "learning_rate": 1.9958047332122177e-05, + "loss": 3.4346, + "step": 1835008 + }, + { + "epoch": 1.0, + "learning_rate": 1.9949661384611657e-05, + "loss": 3.4237, + "step": 1835520 + }, + { + "epoch": 1.0, + "learning_rate": 1.9941291815904866e-05, + "loss": 3.4329, + "step": 1836032 + }, + { + "epoch": 1.0, + "learning_rate": 1.9932905868394346e-05, + "loss": 3.4281, + "step": 1836544 + }, + { + "epoch": 1.0, + "learning_rate": 1.9924519920883826e-05, + "loss": 3.4297, + "step": 1837056 + }, + { + "epoch": 1.0, + "learning_rate": 1.9916133973373306e-05, + "loss": 3.4383, + "step": 1837568 + }, + { + "epoch": 1.0, + "learning_rate": 1.990776440466652e-05, + "loss": 3.4308, + "step": 1838080 + }, + { + "epoch": 1.0, + "learning_rate": 1.9899378457156e-05, + "loss": 3.4282, + "step": 1838592 + }, + { + "epoch": 1.0, + "learning_rate": 1.989099250964548e-05, + "loss": 3.4323, + "step": 1839104 + }, + { + "epoch": 1.0, + "learning_rate": 1.988260656213496e-05, + "loss": 3.4182, + "step": 1839616 + }, + { + "epoch": 1.0, + "learning_rate": 1.9874236993428168e-05, + "loss": 3.4209, + "step": 1840128 + }, + { + "epoch": 1.0, + "learning_rate": 1.986585104591765e-05, + "loss": 3.4287, + "step": 1840640 + }, + { + "epoch": 1.0, + "learning_rate": 1.985746509840713e-05, + "loss": 3.4261, + "step": 1841152 + }, + { + "epoch": 1.0, + "learning_rate": 1.984907915089661e-05, + "loss": 3.431, + "step": 1841664 + }, + { + "epoch": 1.0, + "learning_rate": 1.984070958218982e-05, + "loss": 3.4362, + "step": 1842176 + }, + { + "epoch": 1.0, + "learning_rate": 1.98323236346793e-05, + "loss": 3.4323, + "step": 1842688 + }, + { + "epoch": 1.0, + "learning_rate": 1.9823954065972512e-05, + "loss": 3.4384, + "step": 1843200 + }, + { + "epoch": 1.0, + "learning_rate": 1.9815568118461992e-05, + "loss": 3.4356, + "step": 1843712 + }, + { + "epoch": 1.0, + "learning_rate": 1.9807182170951472e-05, + "loss": 3.4212, + "step": 1844224 + }, + { + "epoch": 1.0, + "learning_rate": 1.9798796223440952e-05, + "loss": 3.4368, + "step": 1844736 + }, + { + "epoch": 1.0, + "learning_rate": 1.979042665473416e-05, + "loss": 3.4218, + "step": 1845248 + }, + { + "epoch": 1.0, + "learning_rate": 1.978204070722364e-05, + "loss": 3.4267, + "step": 1845760 + }, + { + "epoch": 1.0, + "learning_rate": 1.977365475971312e-05, + "loss": 3.4238, + "step": 1846272 + }, + { + "epoch": 1.0, + "learning_rate": 1.9765268812202605e-05, + "loss": 3.4243, + "step": 1846784 + }, + { + "epoch": 1.01, + "learning_rate": 1.9756882864692085e-05, + "loss": 3.4302, + "step": 1847296 + }, + { + "epoch": 1.01, + "learning_rate": 1.9748496917181565e-05, + "loss": 3.434, + "step": 1847808 + }, + { + "epoch": 1.01, + "learning_rate": 1.9740127348474774e-05, + "loss": 3.4277, + "step": 1848320 + }, + { + "epoch": 1.01, + "learning_rate": 1.9731741400964254e-05, + "loss": 3.4341, + "step": 1848832 + }, + { + "epoch": 1.01, + "learning_rate": 1.9723355453453734e-05, + "loss": 3.4217, + "step": 1849344 + }, + { + "epoch": 1.01, + "learning_rate": 1.9714969505943213e-05, + "loss": 3.4368, + "step": 1849856 + }, + { + "epoch": 1.01, + "learning_rate": 1.9706583558432693e-05, + "loss": 3.428, + "step": 1850368 + }, + { + "epoch": 1.01, + "learning_rate": 1.9698197610922173e-05, + "loss": 3.4196, + "step": 1850880 + }, + { + "epoch": 1.01, + "learning_rate": 1.9689811663411653e-05, + "loss": 3.4204, + "step": 1851392 + }, + { + "epoch": 1.01, + "learning_rate": 1.9681442094704866e-05, + "loss": 3.4213, + "step": 1851904 + }, + { + "epoch": 1.01, + "learning_rate": 1.9673056147194342e-05, + "loss": 3.4285, + "step": 1852416 + }, + { + "epoch": 1.01, + "learning_rate": 1.9664670199683822e-05, + "loss": 3.4291, + "step": 1852928 + }, + { + "epoch": 1.01, + "learning_rate": 1.9656284252173306e-05, + "loss": 3.4316, + "step": 1853440 + }, + { + "epoch": 1.01, + "learning_rate": 1.9647898304662786e-05, + "loss": 3.4292, + "step": 1853952 + }, + { + "epoch": 1.01, + "learning_rate": 1.9639512357152266e-05, + "loss": 3.4369, + "step": 1854464 + }, + { + "epoch": 1.01, + "learning_rate": 1.9631126409641746e-05, + "loss": 3.4309, + "step": 1854976 + }, + { + "epoch": 1.01, + "learning_rate": 1.9622740462131222e-05, + "loss": 3.4331, + "step": 1855488 + }, + { + "epoch": 1.01, + "learning_rate": 1.9614370893424435e-05, + "loss": 3.4243, + "step": 1856000 + }, + { + "epoch": 1.01, + "learning_rate": 1.9605984945913915e-05, + "loss": 3.3991, + "step": 1856512 + }, + { + "epoch": 1.01, + "learning_rate": 1.9597615377207127e-05, + "loss": 3.4464, + "step": 1857024 + }, + { + "epoch": 1.01, + "learning_rate": 1.9589229429696607e-05, + "loss": 3.4205, + "step": 1857536 + }, + { + "epoch": 1.01, + "learning_rate": 1.9580843482186087e-05, + "loss": 3.4245, + "step": 1858048 + }, + { + "epoch": 1.01, + "learning_rate": 1.9572457534675567e-05, + "loss": 3.4222, + "step": 1858560 + }, + { + "epoch": 1.01, + "learning_rate": 1.9564071587165043e-05, + "loss": 3.4189, + "step": 1859072 + }, + { + "epoch": 1.01, + "learning_rate": 1.9555685639654527e-05, + "loss": 3.4142, + "step": 1859584 + }, + { + "epoch": 1.01, + "learning_rate": 1.954731607094774e-05, + "loss": 3.4155, + "step": 1860096 + }, + { + "epoch": 1.01, + "learning_rate": 1.953893012343722e-05, + "loss": 3.4253, + "step": 1860608 + }, + { + "epoch": 1.01, + "learning_rate": 1.9530544175926696e-05, + "loss": 3.4185, + "step": 1861120 + }, + { + "epoch": 1.01, + "learning_rate": 1.9522158228416176e-05, + "loss": 3.4357, + "step": 1861632 + }, + { + "epoch": 1.01, + "learning_rate": 1.9513772280905656e-05, + "loss": 3.4195, + "step": 1862144 + }, + { + "epoch": 1.01, + "learning_rate": 1.9505386333395136e-05, + "loss": 3.4139, + "step": 1862656 + }, + { + "epoch": 1.01, + "learning_rate": 1.9497000385884616e-05, + "loss": 3.4359, + "step": 1863168 + }, + { + "epoch": 1.01, + "learning_rate": 1.94886144383741e-05, + "loss": 3.4132, + "step": 1863680 + }, + { + "epoch": 1.01, + "learning_rate": 1.9480244869667308e-05, + "loss": 3.4165, + "step": 1864192 + }, + { + "epoch": 1.01, + "learning_rate": 1.9471858922156788e-05, + "loss": 3.4286, + "step": 1864704 + }, + { + "epoch": 1.01, + "learning_rate": 1.9463472974646268e-05, + "loss": 3.4324, + "step": 1865216 + }, + { + "epoch": 1.01, + "learning_rate": 1.9455103405939477e-05, + "loss": 3.4164, + "step": 1865728 + }, + { + "epoch": 1.01, + "learning_rate": 1.944671745842896e-05, + "loss": 3.4158, + "step": 1866240 + }, + { + "epoch": 1.01, + "learning_rate": 1.943833151091844e-05, + "loss": 3.4072, + "step": 1866752 + }, + { + "epoch": 1.01, + "learning_rate": 1.942994556340792e-05, + "loss": 3.4197, + "step": 1867264 + }, + { + "epoch": 1.01, + "learning_rate": 1.94215596158974e-05, + "loss": 3.4352, + "step": 1867776 + }, + { + "epoch": 1.01, + "learning_rate": 1.9413173668386877e-05, + "loss": 3.4232, + "step": 1868288 + }, + { + "epoch": 1.01, + "learning_rate": 1.940480409968009e-05, + "loss": 3.4276, + "step": 1868800 + }, + { + "epoch": 1.01, + "learning_rate": 1.939641815216957e-05, + "loss": 3.4303, + "step": 1869312 + }, + { + "epoch": 1.01, + "learning_rate": 1.9388032204659053e-05, + "loss": 3.4368, + "step": 1869824 + }, + { + "epoch": 1.01, + "learning_rate": 1.937964625714853e-05, + "loss": 3.4197, + "step": 1870336 + }, + { + "epoch": 1.01, + "learning_rate": 1.937126030963801e-05, + "loss": 3.4314, + "step": 1870848 + }, + { + "epoch": 1.01, + "learning_rate": 1.936287436212749e-05, + "loss": 3.4181, + "step": 1871360 + }, + { + "epoch": 1.01, + "learning_rate": 1.935448841461697e-05, + "loss": 3.4216, + "step": 1871872 + }, + { + "epoch": 1.01, + "learning_rate": 1.934610246710645e-05, + "loss": 3.4227, + "step": 1872384 + }, + { + "epoch": 1.01, + "learning_rate": 1.933773289839966e-05, + "loss": 3.4322, + "step": 1872896 + }, + { + "epoch": 1.01, + "learning_rate": 1.9329363329692874e-05, + "loss": 3.4268, + "step": 1873408 + }, + { + "epoch": 1.01, + "learning_rate": 1.932097738218235e-05, + "loss": 3.4342, + "step": 1873920 + }, + { + "epoch": 1.01, + "learning_rate": 1.931259143467183e-05, + "loss": 3.4195, + "step": 1874432 + }, + { + "epoch": 1.01, + "learning_rate": 1.930420548716131e-05, + "loss": 3.4188, + "step": 1874944 + }, + { + "epoch": 1.01, + "learning_rate": 1.929581953965079e-05, + "loss": 3.4291, + "step": 1875456 + }, + { + "epoch": 1.01, + "learning_rate": 1.9287433592140274e-05, + "loss": 3.4266, + "step": 1875968 + }, + { + "epoch": 1.01, + "learning_rate": 1.9279047644629754e-05, + "loss": 3.4145, + "step": 1876480 + }, + { + "epoch": 1.01, + "learning_rate": 1.9270661697119234e-05, + "loss": 3.425, + "step": 1876992 + }, + { + "epoch": 1.02, + "learning_rate": 1.9262292128412443e-05, + "loss": 3.4232, + "step": 1877504 + }, + { + "epoch": 1.02, + "learning_rate": 1.9253906180901923e-05, + "loss": 3.4301, + "step": 1878016 + }, + { + "epoch": 1.02, + "learning_rate": 1.9245520233391403e-05, + "loss": 3.4172, + "step": 1878528 + }, + { + "epoch": 1.02, + "learning_rate": 1.9237134285880883e-05, + "loss": 3.4151, + "step": 1879040 + }, + { + "epoch": 1.02, + "learning_rate": 1.9228764717174095e-05, + "loss": 3.4358, + "step": 1879552 + }, + { + "epoch": 1.02, + "learning_rate": 1.9220378769663575e-05, + "loss": 3.4285, + "step": 1880064 + }, + { + "epoch": 1.02, + "learning_rate": 1.9211992822153055e-05, + "loss": 3.4275, + "step": 1880576 + }, + { + "epoch": 1.02, + "learning_rate": 1.920360687464253e-05, + "loss": 3.4164, + "step": 1881088 + }, + { + "epoch": 1.02, + "learning_rate": 1.9195237305935744e-05, + "loss": 3.4236, + "step": 1881600 + }, + { + "epoch": 1.02, + "learning_rate": 1.9186851358425224e-05, + "loss": 3.4182, + "step": 1882112 + }, + { + "epoch": 1.02, + "learning_rate": 1.9178465410914707e-05, + "loss": 3.428, + "step": 1882624 + }, + { + "epoch": 1.02, + "learning_rate": 1.9170079463404184e-05, + "loss": 3.4294, + "step": 1883136 + }, + { + "epoch": 1.02, + "learning_rate": 1.9161709894697396e-05, + "loss": 3.4245, + "step": 1883648 + }, + { + "epoch": 1.02, + "learning_rate": 1.9153323947186876e-05, + "loss": 3.4193, + "step": 1884160 + }, + { + "epoch": 1.02, + "learning_rate": 1.9144937999676353e-05, + "loss": 3.4115, + "step": 1884672 + }, + { + "epoch": 1.02, + "learning_rate": 1.9136552052165836e-05, + "loss": 3.4161, + "step": 1885184 + }, + { + "epoch": 1.02, + "learning_rate": 1.912818248345905e-05, + "loss": 3.4197, + "step": 1885696 + }, + { + "epoch": 1.02, + "learning_rate": 1.911979653594853e-05, + "loss": 3.4137, + "step": 1886208 + }, + { + "epoch": 1.02, + "learning_rate": 1.9111410588438005e-05, + "loss": 3.428, + "step": 1886720 + }, + { + "epoch": 1.02, + "learning_rate": 1.9103024640927485e-05, + "loss": 3.4131, + "step": 1887232 + }, + { + "epoch": 1.02, + "learning_rate": 1.9094655072220698e-05, + "loss": 3.4213, + "step": 1887744 + }, + { + "epoch": 1.02, + "learning_rate": 1.9086269124710178e-05, + "loss": 3.4149, + "step": 1888256 + }, + { + "epoch": 1.02, + "learning_rate": 1.9077883177199658e-05, + "loss": 3.4249, + "step": 1888768 + }, + { + "epoch": 1.02, + "learning_rate": 1.9069497229689138e-05, + "loss": 3.4268, + "step": 1889280 + }, + { + "epoch": 1.02, + "learning_rate": 1.906112766098235e-05, + "loss": 3.4161, + "step": 1889792 + }, + { + "epoch": 1.02, + "learning_rate": 1.9052741713471827e-05, + "loss": 3.4346, + "step": 1890304 + }, + { + "epoch": 1.02, + "learning_rate": 1.9044355765961307e-05, + "loss": 3.4374, + "step": 1890816 + }, + { + "epoch": 1.02, + "learning_rate": 1.903596981845079e-05, + "loss": 3.4255, + "step": 1891328 + }, + { + "epoch": 1.02, + "learning_rate": 1.902761662854773e-05, + "loss": 3.426, + "step": 1891840 + }, + { + "epoch": 1.02, + "learning_rate": 1.901923068103721e-05, + "loss": 3.4187, + "step": 1892352 + }, + { + "epoch": 1.02, + "learning_rate": 1.901084473352669e-05, + "loss": 3.4171, + "step": 1892864 + }, + { + "epoch": 1.02, + "learning_rate": 1.900245878601617e-05, + "loss": 3.4261, + "step": 1893376 + }, + { + "epoch": 1.02, + "learning_rate": 1.8994089217309384e-05, + "loss": 3.4228, + "step": 1893888 + }, + { + "epoch": 1.02, + "learning_rate": 1.8985703269798864e-05, + "loss": 3.412, + "step": 1894400 + }, + { + "epoch": 1.02, + "learning_rate": 1.8977317322288344e-05, + "loss": 3.4323, + "step": 1894912 + }, + { + "epoch": 1.02, + "learning_rate": 1.8968931374777824e-05, + "loss": 3.4297, + "step": 1895424 + }, + { + "epoch": 1.02, + "learning_rate": 1.89605454272673e-05, + "loss": 3.4255, + "step": 1895936 + }, + { + "epoch": 1.02, + "learning_rate": 1.895215947975678e-05, + "loss": 3.4178, + "step": 1896448 + }, + { + "epoch": 1.02, + "learning_rate": 1.8943789911049993e-05, + "loss": 3.4212, + "step": 1896960 + }, + { + "epoch": 1.02, + "learning_rate": 1.8935403963539476e-05, + "loss": 3.4184, + "step": 1897472 + }, + { + "epoch": 1.02, + "learning_rate": 1.8927018016028953e-05, + "loss": 3.4326, + "step": 1897984 + }, + { + "epoch": 1.02, + "learning_rate": 1.8918632068518433e-05, + "loss": 3.4206, + "step": 1898496 + }, + { + "epoch": 1.02, + "learning_rate": 1.8910246121007913e-05, + "loss": 3.4315, + "step": 1899008 + }, + { + "epoch": 1.02, + "learning_rate": 1.8901860173497393e-05, + "loss": 3.409, + "step": 1899520 + }, + { + "epoch": 1.02, + "learning_rate": 1.8893474225986873e-05, + "loss": 3.4388, + "step": 1900032 + }, + { + "epoch": 1.02, + "learning_rate": 1.8885088278476353e-05, + "loss": 3.4171, + "step": 1900544 + }, + { + "epoch": 1.02, + "learning_rate": 1.8876718709769565e-05, + "loss": 3.4267, + "step": 1901056 + }, + { + "epoch": 1.02, + "learning_rate": 1.8868332762259045e-05, + "loss": 3.4266, + "step": 1901568 + }, + { + "epoch": 1.02, + "learning_rate": 1.8859946814748525e-05, + "loss": 3.4158, + "step": 1902080 + }, + { + "epoch": 1.02, + "learning_rate": 1.8851560867238005e-05, + "loss": 3.4269, + "step": 1902592 + }, + { + "epoch": 1.02, + "learning_rate": 1.8843191298531214e-05, + "loss": 3.4401, + "step": 1903104 + }, + { + "epoch": 1.02, + "learning_rate": 1.8834805351020694e-05, + "loss": 3.4097, + "step": 1903616 + }, + { + "epoch": 1.02, + "learning_rate": 1.8826419403510177e-05, + "loss": 3.4283, + "step": 1904128 + }, + { + "epoch": 1.02, + "learning_rate": 1.8818049834803386e-05, + "loss": 3.4232, + "step": 1904640 + }, + { + "epoch": 1.02, + "learning_rate": 1.8809663887292866e-05, + "loss": 3.4205, + "step": 1905152 + }, + { + "epoch": 1.02, + "learning_rate": 1.8801277939782346e-05, + "loss": 3.42, + "step": 1905664 + }, + { + "epoch": 1.02, + "learning_rate": 1.8792891992271826e-05, + "loss": 3.4276, + "step": 1906176 + }, + { + "epoch": 1.02, + "learning_rate": 1.8784506044761306e-05, + "loss": 3.4293, + "step": 1906688 + }, + { + "epoch": 1.02, + "learning_rate": 1.8776120097250786e-05, + "loss": 3.4193, + "step": 1907200 + }, + { + "epoch": 1.02, + "learning_rate": 1.8767734149740266e-05, + "loss": 3.4233, + "step": 1907712 + }, + { + "epoch": 1.03, + "eval_loss": 3.8545544147491455, + "eval_runtime": 310.5286, + "eval_samples_per_second": 1228.843, + "eval_steps_per_second": 38.402, + "step": 1908000 + }, + { + "epoch": 0.0, + "learning_rate": 1.8759348202229746e-05, + "loss": 3.4159, + "step": 1908224 + }, + { + "epoch": 0.0, + "learning_rate": 1.8750962254719226e-05, + "loss": 3.4186, + "step": 1908736 + }, + { + "epoch": 0.0, + "learning_rate": 1.8742576307208706e-05, + "loss": 3.4237, + "step": 1909248 + }, + { + "epoch": 0.0, + "learning_rate": 1.8734190359698186e-05, + "loss": 3.4193, + "step": 1909760 + }, + { + "epoch": 0.0, + "learning_rate": 1.87258207909914e-05, + "loss": 3.427, + "step": 1910272 + }, + { + "epoch": 0.0, + "learning_rate": 1.871743484348088e-05, + "loss": 3.4132, + "step": 1910784 + }, + { + "epoch": 0.0, + "learning_rate": 1.870904889597036e-05, + "loss": 3.4249, + "step": 1911296 + }, + { + "epoch": 0.0, + "learning_rate": 1.870066294845984e-05, + "loss": 3.4142, + "step": 1911808 + }, + { + "epoch": 0.0, + "learning_rate": 1.8692293379753047e-05, + "loss": 3.4178, + "step": 1912320 + }, + { + "epoch": 0.0, + "learning_rate": 1.8683907432242527e-05, + "loss": 3.4221, + "step": 1912832 + }, + { + "epoch": 0.0, + "learning_rate": 1.8675521484732007e-05, + "loss": 3.4149, + "step": 1913344 + }, + { + "epoch": 0.0, + "learning_rate": 1.8667135537221487e-05, + "loss": 3.4257, + "step": 1913856 + }, + { + "epoch": 0.0, + "learning_rate": 1.86587659685147e-05, + "loss": 3.4316, + "step": 1914368 + }, + { + "epoch": 0.0, + "learning_rate": 1.865038002100418e-05, + "loss": 3.4142, + "step": 1914880 + }, + { + "epoch": 0.0, + "learning_rate": 1.864199407349366e-05, + "loss": 3.4189, + "step": 1915392 + }, + { + "epoch": 0.0, + "learning_rate": 1.8633608125983136e-05, + "loss": 3.4112, + "step": 1915904 + }, + { + "epoch": 0.0, + "learning_rate": 1.8625238557276352e-05, + "loss": 3.4075, + "step": 1916416 + }, + { + "epoch": 0.0, + "learning_rate": 1.8616852609765832e-05, + "loss": 3.4222, + "step": 1916928 + }, + { + "epoch": 0.0, + "learning_rate": 1.8608466662255312e-05, + "loss": 3.4132, + "step": 1917440 + }, + { + "epoch": 0.0, + "learning_rate": 1.860008071474479e-05, + "loss": 3.4199, + "step": 1917952 + }, + { + "epoch": 0.0, + "learning_rate": 1.8591711146038e-05, + "loss": 3.4275, + "step": 1918464 + }, + { + "epoch": 0.0, + "learning_rate": 1.858332519852748e-05, + "loss": 3.4255, + "step": 1918976 + }, + { + "epoch": 0.0, + "learning_rate": 1.857493925101696e-05, + "loss": 3.427, + "step": 1919488 + }, + { + "epoch": 0.0, + "learning_rate": 1.856655330350644e-05, + "loss": 3.4227, + "step": 1920000 + }, + { + "epoch": 0.0, + "learning_rate": 1.8558183734799653e-05, + "loss": 3.4111, + "step": 1920512 + }, + { + "epoch": 0.0, + "learning_rate": 1.8549797787289133e-05, + "loss": 3.4238, + "step": 1921024 + }, + { + "epoch": 0.0, + "learning_rate": 1.8541428218582342e-05, + "loss": 3.4146, + "step": 1921536 + }, + { + "epoch": 0.0, + "learning_rate": 1.8533042271071822e-05, + "loss": 3.4197, + "step": 1922048 + }, + { + "epoch": 0.0, + "learning_rate": 1.8524656323561306e-05, + "loss": 3.409, + "step": 1922560 + }, + { + "epoch": 0.0, + "learning_rate": 1.8516270376050786e-05, + "loss": 3.4137, + "step": 1923072 + }, + { + "epoch": 0.01, + "learning_rate": 1.8507884428540262e-05, + "loss": 3.4189, + "step": 1923584 + }, + { + "epoch": 0.01, + "learning_rate": 1.8499498481029742e-05, + "loss": 3.4229, + "step": 1924096 + }, + { + "epoch": 0.01, + "learning_rate": 1.8491112533519222e-05, + "loss": 3.4197, + "step": 1924608 + }, + { + "epoch": 0.01, + "learning_rate": 1.8482726586008702e-05, + "loss": 3.4212, + "step": 1925120 + }, + { + "epoch": 0.01, + "learning_rate": 1.8474357017301915e-05, + "loss": 3.4145, + "step": 1925632 + }, + { + "epoch": 0.01, + "learning_rate": 1.8465971069791395e-05, + "loss": 3.4216, + "step": 1926144 + }, + { + "epoch": 0.01, + "learning_rate": 1.8457585122280875e-05, + "loss": 3.4216, + "step": 1926656 + }, + { + "epoch": 0.01, + "learning_rate": 1.8449199174770355e-05, + "loss": 3.4109, + "step": 1927168 + }, + { + "epoch": 0.01, + "learning_rate": 1.8440829606063564e-05, + "loss": 3.4124, + "step": 1927680 + }, + { + "epoch": 0.01, + "learning_rate": 1.8432460037356776e-05, + "loss": 3.4117, + "step": 1928192 + }, + { + "epoch": 0.01, + "learning_rate": 1.8424074089846256e-05, + "loss": 3.4137, + "step": 1928704 + }, + { + "epoch": 0.01, + "learning_rate": 1.8415688142335736e-05, + "loss": 3.4171, + "step": 1929216 + }, + { + "epoch": 0.01, + "learning_rate": 1.8407302194825216e-05, + "loss": 3.4247, + "step": 1929728 + }, + { + "epoch": 0.01, + "learning_rate": 1.8398916247314696e-05, + "loss": 3.4202, + "step": 1930240 + }, + { + "epoch": 0.01, + "learning_rate": 1.8390530299804176e-05, + "loss": 3.4232, + "step": 1930752 + }, + { + "epoch": 0.01, + "learning_rate": 1.8382144352293656e-05, + "loss": 3.4246, + "step": 1931264 + }, + { + "epoch": 0.01, + "learning_rate": 1.8373758404783136e-05, + "loss": 3.4199, + "step": 1931776 + }, + { + "epoch": 0.01, + "learning_rate": 1.8365388836076348e-05, + "loss": 3.4137, + "step": 1932288 + }, + { + "epoch": 0.01, + "learning_rate": 1.8357002888565828e-05, + "loss": 3.3927, + "step": 1932800 + }, + { + "epoch": 0.01, + "learning_rate": 1.8348616941055308e-05, + "loss": 3.4328, + "step": 1933312 + }, + { + "epoch": 0.01, + "learning_rate": 1.8340247372348517e-05, + "loss": 3.4104, + "step": 1933824 + }, + { + "epoch": 0.01, + "learning_rate": 1.8331861424837997e-05, + "loss": 3.4168, + "step": 1934336 + }, + { + "epoch": 0.01, + "learning_rate": 1.8323475477327477e-05, + "loss": 3.4181, + "step": 1934848 + }, + { + "epoch": 0.01, + "learning_rate": 1.831508952981696e-05, + "loss": 3.4047, + "step": 1935360 + }, + { + "epoch": 0.01, + "learning_rate": 1.8306703582306437e-05, + "loss": 3.4041, + "step": 1935872 + }, + { + "epoch": 0.01, + "learning_rate": 1.829833401359965e-05, + "loss": 3.405, + "step": 1936384 + }, + { + "epoch": 0.01, + "learning_rate": 1.828994806608913e-05, + "loss": 3.4149, + "step": 1936896 + }, + { + "epoch": 0.01, + "learning_rate": 1.828156211857861e-05, + "loss": 3.4075, + "step": 1937408 + }, + { + "epoch": 0.01, + "learning_rate": 1.8273176171068086e-05, + "loss": 3.4264, + "step": 1937920 + }, + { + "epoch": 0.01, + "learning_rate": 1.826479022355757e-05, + "loss": 3.4108, + "step": 1938432 + }, + { + "epoch": 0.01, + "learning_rate": 1.825640427604705e-05, + "loss": 3.3986, + "step": 1938944 + }, + { + "epoch": 0.01, + "learning_rate": 1.824801832853653e-05, + "loss": 3.4263, + "step": 1939456 + }, + { + "epoch": 0.01, + "learning_rate": 1.823963238102601e-05, + "loss": 3.4067, + "step": 1939968 + }, + { + "epoch": 0.01, + "learning_rate": 1.823126281231922e-05, + "loss": 3.4038, + "step": 1940480 + }, + { + "epoch": 0.01, + "learning_rate": 1.82228768648087e-05, + "loss": 3.418, + "step": 1940992 + }, + { + "epoch": 0.01, + "learning_rate": 1.8214490917298178e-05, + "loss": 3.4231, + "step": 1941504 + }, + { + "epoch": 0.01, + "learning_rate": 1.820612134859139e-05, + "loss": 3.4045, + "step": 1942016 + }, + { + "epoch": 0.01, + "learning_rate": 1.819773540108087e-05, + "loss": 3.4043, + "step": 1942528 + }, + { + "epoch": 0.01, + "learning_rate": 1.818934945357035e-05, + "loss": 3.4004, + "step": 1943040 + }, + { + "epoch": 0.01, + "learning_rate": 1.818096350605983e-05, + "loss": 3.4108, + "step": 1943552 + }, + { + "epoch": 0.01, + "learning_rate": 1.817257755854931e-05, + "loss": 3.4211, + "step": 1944064 + }, + { + "epoch": 0.01, + "learning_rate": 1.816419161103879e-05, + "loss": 3.4166, + "step": 1944576 + }, + { + "epoch": 0.01, + "learning_rate": 1.815580566352827e-05, + "loss": 3.4179, + "step": 1945088 + }, + { + "epoch": 0.01, + "learning_rate": 1.814741971601775e-05, + "loss": 3.4164, + "step": 1945600 + }, + { + "epoch": 0.01, + "learning_rate": 1.8139050147310963e-05, + "loss": 3.4253, + "step": 1946112 + }, + { + "epoch": 0.01, + "learning_rate": 1.8130664199800443e-05, + "loss": 3.4117, + "step": 1946624 + }, + { + "epoch": 0.01, + "learning_rate": 1.812227825228992e-05, + "loss": 3.4246, + "step": 1947136 + }, + { + "epoch": 0.01, + "learning_rate": 1.81138923047794e-05, + "loss": 3.4044, + "step": 1947648 + }, + { + "epoch": 0.01, + "learning_rate": 1.8105522736072615e-05, + "loss": 3.4127, + "step": 1948160 + }, + { + "epoch": 0.01, + "learning_rate": 1.8097136788562092e-05, + "loss": 3.4135, + "step": 1948672 + }, + { + "epoch": 0.01, + "learning_rate": 1.8088750841051572e-05, + "loss": 3.4188, + "step": 1949184 + }, + { + "epoch": 0.01, + "learning_rate": 1.8080381272344784e-05, + "loss": 3.4197, + "step": 1949696 + }, + { + "epoch": 0.01, + "learning_rate": 1.8071995324834264e-05, + "loss": 3.4209, + "step": 1950208 + }, + { + "epoch": 0.01, + "learning_rate": 1.806360937732374e-05, + "loss": 3.4089, + "step": 1950720 + }, + { + "epoch": 0.01, + "learning_rate": 1.8055223429813224e-05, + "loss": 3.4076, + "step": 1951232 + }, + { + "epoch": 0.01, + "learning_rate": 1.8046837482302704e-05, + "loss": 3.4163, + "step": 1951744 + }, + { + "epoch": 0.01, + "learning_rate": 1.8038451534792184e-05, + "loss": 3.4207, + "step": 1952256 + }, + { + "epoch": 0.01, + "learning_rate": 1.8030065587281664e-05, + "loss": 3.4052, + "step": 1952768 + }, + { + "epoch": 0.01, + "learning_rate": 1.8021679639771144e-05, + "loss": 3.4115, + "step": 1953280 + }, + { + "epoch": 0.02, + "learning_rate": 1.8013310071064353e-05, + "loss": 3.4154, + "step": 1953792 + }, + { + "epoch": 0.02, + "learning_rate": 1.8004940502357566e-05, + "loss": 3.4163, + "step": 1954304 + }, + { + "epoch": 0.02, + "learning_rate": 1.7996554554847046e-05, + "loss": 3.4133, + "step": 1954816 + }, + { + "epoch": 0.02, + "learning_rate": 1.7988168607336525e-05, + "loss": 3.4042, + "step": 1955328 + }, + { + "epoch": 0.02, + "learning_rate": 1.7979782659826005e-05, + "loss": 3.4227, + "step": 1955840 + }, + { + "epoch": 0.02, + "learning_rate": 1.7971396712315485e-05, + "loss": 3.42, + "step": 1956352 + }, + { + "epoch": 0.02, + "learning_rate": 1.7963010764804965e-05, + "loss": 3.4175, + "step": 1956864 + }, + { + "epoch": 0.02, + "learning_rate": 1.7954641196098178e-05, + "loss": 3.404, + "step": 1957376 + }, + { + "epoch": 0.02, + "learning_rate": 1.7946255248587658e-05, + "loss": 3.4134, + "step": 1957888 + }, + { + "epoch": 0.02, + "learning_rate": 1.7937869301077138e-05, + "loss": 3.406, + "step": 1958400 + }, + { + "epoch": 0.02, + "learning_rate": 1.7929483353566618e-05, + "loss": 3.4191, + "step": 1958912 + }, + { + "epoch": 0.02, + "learning_rate": 1.7921097406056098e-05, + "loss": 3.4189, + "step": 1959424 + }, + { + "epoch": 0.02, + "learning_rate": 1.7912711458545574e-05, + "loss": 3.4144, + "step": 1959936 + }, + { + "epoch": 0.02, + "learning_rate": 1.7904325511035054e-05, + "loss": 3.4125, + "step": 1960448 + }, + { + "epoch": 0.02, + "learning_rate": 1.7895939563524534e-05, + "loss": 3.3995, + "step": 1960960 + }, + { + "epoch": 0.02, + "learning_rate": 1.7887569994817747e-05, + "loss": 3.4085, + "step": 1961472 + }, + { + "epoch": 0.02, + "learning_rate": 1.7879184047307227e-05, + "loss": 3.4064, + "step": 1961984 + }, + { + "epoch": 0.02, + "learning_rate": 1.7870798099796707e-05, + "loss": 3.4075, + "step": 1962496 + }, + { + "epoch": 0.02, + "learning_rate": 1.7862412152286186e-05, + "loss": 3.4132, + "step": 1963008 + }, + { + "epoch": 0.02, + "learning_rate": 1.78540425835794e-05, + "loss": 3.4049, + "step": 1963520 + }, + { + "epoch": 0.02, + "learning_rate": 1.784565663606888e-05, + "loss": 3.4113, + "step": 1964032 + }, + { + "epoch": 0.02, + "learning_rate": 1.783727068855836e-05, + "loss": 3.4071, + "step": 1964544 + }, + { + "epoch": 0.02, + "learning_rate": 1.782888474104784e-05, + "loss": 3.4082, + "step": 1965056 + }, + { + "epoch": 0.02, + "learning_rate": 1.7820515172341048e-05, + "loss": 3.4189, + "step": 1965568 + }, + { + "epoch": 0.02, + "learning_rate": 1.7812129224830528e-05, + "loss": 3.4087, + "step": 1966080 + }, + { + "epoch": 0.02, + "learning_rate": 1.7803743277320008e-05, + "loss": 3.4227, + "step": 1966592 + }, + { + "epoch": 0.02, + "learning_rate": 1.7795357329809488e-05, + "loss": 3.4266, + "step": 1967104 + }, + { + "epoch": 0.02, + "learning_rate": 1.77869877611027e-05, + "loss": 3.4177, + "step": 1967616 + }, + { + "epoch": 0.02, + "learning_rate": 1.7778618192395913e-05, + "loss": 3.4106, + "step": 1968128 + }, + { + "epoch": 0.02, + "learning_rate": 1.7770232244885393e-05, + "loss": 3.4139, + "step": 1968640 + }, + { + "epoch": 0.02, + "learning_rate": 1.776184629737487e-05, + "loss": 3.4089, + "step": 1969152 + }, + { + "epoch": 0.02, + "learning_rate": 1.775346034986435e-05, + "loss": 3.4135, + "step": 1969664 + }, + { + "epoch": 0.02, + "learning_rate": 1.7745074402353833e-05, + "loss": 3.4128, + "step": 1970176 + }, + { + "epoch": 0.02, + "learning_rate": 1.7736688454843313e-05, + "loss": 3.4028, + "step": 1970688 + }, + { + "epoch": 0.02, + "learning_rate": 1.7728302507332793e-05, + "loss": 3.4228, + "step": 1971200 + }, + { + "epoch": 0.02, + "learning_rate": 1.7719916559822272e-05, + "loss": 3.4199, + "step": 1971712 + }, + { + "epoch": 0.02, + "learning_rate": 1.771154699111548e-05, + "loss": 3.4097, + "step": 1972224 + }, + { + "epoch": 0.02, + "learning_rate": 1.770316104360496e-05, + "loss": 3.4076, + "step": 1972736 + }, + { + "epoch": 0.02, + "learning_rate": 1.769477509609444e-05, + "loss": 3.4153, + "step": 1973248 + }, + { + "epoch": 0.02, + "learning_rate": 1.7686389148583925e-05, + "loss": 3.4057, + "step": 1973760 + }, + { + "epoch": 0.02, + "learning_rate": 1.7678019579877134e-05, + "loss": 3.4244, + "step": 1974272 + }, + { + "epoch": 0.02, + "learning_rate": 1.7669633632366614e-05, + "loss": 3.4089, + "step": 1974784 + }, + { + "epoch": 0.02, + "learning_rate": 1.7661247684856094e-05, + "loss": 3.4221, + "step": 1975296 + }, + { + "epoch": 0.02, + "learning_rate": 1.7652861737345574e-05, + "loss": 3.3971, + "step": 1975808 + }, + { + "epoch": 0.02, + "learning_rate": 1.7644492168638786e-05, + "loss": 3.4226, + "step": 1976320 + }, + { + "epoch": 0.02, + "learning_rate": 1.7636106221128266e-05, + "loss": 3.4143, + "step": 1976832 + }, + { + "epoch": 0.02, + "learning_rate": 1.7627720273617746e-05, + "loss": 3.4099, + "step": 1977344 + }, + { + "epoch": 0.02, + "learning_rate": 1.7619334326107223e-05, + "loss": 3.415, + "step": 1977856 + }, + { + "epoch": 0.02, + "learning_rate": 1.7610964757400435e-05, + "loss": 3.4066, + "step": 1978368 + }, + { + "epoch": 0.02, + "learning_rate": 1.7602578809889915e-05, + "loss": 3.4156, + "step": 1978880 + }, + { + "epoch": 0.02, + "learning_rate": 1.7594192862379395e-05, + "loss": 3.4332, + "step": 1979392 + }, + { + "epoch": 0.02, + "learning_rate": 1.7585806914868875e-05, + "loss": 3.3974, + "step": 1979904 + }, + { + "epoch": 0.02, + "learning_rate": 1.7577453724965817e-05, + "loss": 3.4157, + "step": 1980416 + }, + { + "epoch": 0.02, + "learning_rate": 1.7569067777455297e-05, + "loss": 3.4147, + "step": 1980928 + }, + { + "epoch": 0.02, + "learning_rate": 1.7560681829944777e-05, + "loss": 3.4079, + "step": 1981440 + }, + { + "epoch": 0.02, + "learning_rate": 1.7552295882434257e-05, + "loss": 3.4137, + "step": 1981952 + }, + { + "epoch": 0.02, + "learning_rate": 1.754390993492374e-05, + "loss": 3.4155, + "step": 1982464 + }, + { + "epoch": 0.02, + "learning_rate": 1.753552398741322e-05, + "loss": 3.4183, + "step": 1982976 + }, + { + "epoch": 0.02, + "learning_rate": 1.7527138039902696e-05, + "loss": 3.4098, + "step": 1983488 + }, + { + "epoch": 0.02, + "learning_rate": 1.7518752092392176e-05, + "loss": 3.4119, + "step": 1984000 + }, + { + "epoch": 0.03, + "eval_loss": 3.856178045272827, + "eval_runtime": 306.6015, + "eval_samples_per_second": 1244.583, + "eval_steps_per_second": 38.894, + "step": 1984320 + }, + { + "epoch": 1.0, + "learning_rate": 1.751038252368539e-05, + "loss": 3.4057, + "step": 1984512 + }, + { + "epoch": 1.0, + "learning_rate": 1.750199657617487e-05, + "loss": 3.4076, + "step": 1985024 + }, + { + "epoch": 1.0, + "learning_rate": 1.749361062866435e-05, + "loss": 3.4122, + "step": 1985536 + }, + { + "epoch": 1.0, + "learning_rate": 1.748522468115383e-05, + "loss": 3.4111, + "step": 1986048 + }, + { + "epoch": 1.0, + "learning_rate": 1.747685511244704e-05, + "loss": 3.4203, + "step": 1986560 + }, + { + "epoch": 1.0, + "learning_rate": 1.746846916493652e-05, + "loss": 3.4029, + "step": 1987072 + }, + { + "epoch": 1.0, + "learning_rate": 1.7460083217425998e-05, + "loss": 3.4128, + "step": 1987584 + }, + { + "epoch": 1.0, + "learning_rate": 1.7451697269915478e-05, + "loss": 3.4019, + "step": 1988096 + }, + { + "epoch": 1.0, + "learning_rate": 1.7443327701208694e-05, + "loss": 3.4098, + "step": 1988608 + }, + { + "epoch": 1.0, + "learning_rate": 1.743494175369817e-05, + "loss": 3.4094, + "step": 1989120 + }, + { + "epoch": 1.0, + "learning_rate": 1.742655580618765e-05, + "loss": 3.4034, + "step": 1989632 + }, + { + "epoch": 1.0, + "learning_rate": 1.741816985867713e-05, + "loss": 3.4162, + "step": 1990144 + }, + { + "epoch": 1.0, + "learning_rate": 1.7409816668774072e-05, + "loss": 3.4217, + "step": 1990656 + }, + { + "epoch": 1.0, + "learning_rate": 1.7401430721263555e-05, + "loss": 3.4027, + "step": 1991168 + }, + { + "epoch": 1.0, + "learning_rate": 1.7393044773753035e-05, + "loss": 3.4116, + "step": 1991680 + }, + { + "epoch": 1.0, + "learning_rate": 1.7384658826242515e-05, + "loss": 3.3966, + "step": 1992192 + }, + { + "epoch": 1.0, + "learning_rate": 1.7376272878731995e-05, + "loss": 3.3986, + "step": 1992704 + }, + { + "epoch": 1.0, + "learning_rate": 1.736788693122147e-05, + "loss": 3.4092, + "step": 1993216 + }, + { + "epoch": 1.0, + "learning_rate": 1.735950098371095e-05, + "loss": 3.4036, + "step": 1993728 + }, + { + "epoch": 1.0, + "learning_rate": 1.735111503620043e-05, + "loss": 3.4099, + "step": 1994240 + }, + { + "epoch": 1.0, + "learning_rate": 1.7342745467493644e-05, + "loss": 3.4179, + "step": 1994752 + }, + { + "epoch": 1.0, + "learning_rate": 1.7334359519983124e-05, + "loss": 3.4136, + "step": 1995264 + }, + { + "epoch": 1.0, + "learning_rate": 1.7325989951276336e-05, + "loss": 3.4159, + "step": 1995776 + }, + { + "epoch": 1.0, + "learning_rate": 1.7317604003765816e-05, + "loss": 3.4108, + "step": 1996288 + }, + { + "epoch": 1.0, + "learning_rate": 1.7309218056255293e-05, + "loss": 3.404, + "step": 1996800 + }, + { + "epoch": 1.0, + "learning_rate": 1.7300832108744773e-05, + "loss": 3.4113, + "step": 1997312 + }, + { + "epoch": 1.0, + "learning_rate": 1.729246254003799e-05, + "loss": 3.4053, + "step": 1997824 + }, + { + "epoch": 1.0, + "learning_rate": 1.728407659252747e-05, + "loss": 3.4095, + "step": 1998336 + }, + { + "epoch": 1.0, + "learning_rate": 1.7275690645016945e-05, + "loss": 3.3972, + "step": 1998848 + }, + { + "epoch": 1.0, + "learning_rate": 1.7267304697506425e-05, + "loss": 3.404, + "step": 1999360 + }, + { + "epoch": 1.01, + "learning_rate": 1.7258918749995905e-05, + "loss": 3.4071, + "step": 1999872 + }, + { + "epoch": 1.01, + "learning_rate": 1.7250532802485385e-05, + "loss": 3.4124, + "step": 2000384 + }, + { + "epoch": 1.01, + "learning_rate": 1.7242146854974865e-05, + "loss": 3.4111, + "step": 2000896 + }, + { + "epoch": 1.01, + "learning_rate": 1.723376090746435e-05, + "loss": 3.4075, + "step": 2001408 + }, + { + "epoch": 1.01, + "learning_rate": 1.7225391338757557e-05, + "loss": 3.406, + "step": 2001920 + }, + { + "epoch": 1.01, + "learning_rate": 1.7217005391247037e-05, + "loss": 3.407, + "step": 2002432 + }, + { + "epoch": 1.01, + "learning_rate": 1.7208619443736517e-05, + "loss": 3.4148, + "step": 2002944 + }, + { + "epoch": 1.01, + "learning_rate": 1.7200233496225997e-05, + "loss": 3.398, + "step": 2003456 + }, + { + "epoch": 1.01, + "learning_rate": 1.719186392751921e-05, + "loss": 3.4015, + "step": 2003968 + }, + { + "epoch": 1.01, + "learning_rate": 1.718349435881242e-05, + "loss": 3.4017, + "step": 2004480 + }, + { + "epoch": 1.01, + "learning_rate": 1.71751084113019e-05, + "loss": 3.4032, + "step": 2004992 + }, + { + "epoch": 1.01, + "learning_rate": 1.716672246379138e-05, + "loss": 3.4053, + "step": 2005504 + }, + { + "epoch": 1.01, + "learning_rate": 1.715833651628086e-05, + "loss": 3.4145, + "step": 2006016 + }, + { + "epoch": 1.01, + "learning_rate": 1.714995056877034e-05, + "loss": 3.4098, + "step": 2006528 + }, + { + "epoch": 1.01, + "learning_rate": 1.714156462125982e-05, + "loss": 3.4137, + "step": 2007040 + }, + { + "epoch": 1.01, + "learning_rate": 1.71331786737493e-05, + "loss": 3.4129, + "step": 2007552 + }, + { + "epoch": 1.01, + "learning_rate": 1.712480910504251e-05, + "loss": 3.413, + "step": 2008064 + }, + { + "epoch": 1.01, + "learning_rate": 1.711642315753199e-05, + "loss": 3.4036, + "step": 2008576 + }, + { + "epoch": 1.01, + "learning_rate": 1.710803721002147e-05, + "loss": 3.3804, + "step": 2009088 + }, + { + "epoch": 1.01, + "learning_rate": 1.7099651262510948e-05, + "loss": 3.4212, + "step": 2009600 + }, + { + "epoch": 1.01, + "learning_rate": 1.7091281693804163e-05, + "loss": 3.4009, + "step": 2010112 + }, + { + "epoch": 1.01, + "learning_rate": 1.7082895746293643e-05, + "loss": 3.4078, + "step": 2010624 + }, + { + "epoch": 1.01, + "learning_rate": 1.707450979878312e-05, + "loss": 3.4066, + "step": 2011136 + }, + { + "epoch": 1.01, + "learning_rate": 1.70661238512726e-05, + "loss": 3.3937, + "step": 2011648 + }, + { + "epoch": 1.01, + "learning_rate": 1.705773790376208e-05, + "loss": 3.398, + "step": 2012160 + }, + { + "epoch": 1.01, + "learning_rate": 1.7049368335055292e-05, + "loss": 3.3941, + "step": 2012672 + }, + { + "epoch": 1.01, + "learning_rate": 1.7040982387544772e-05, + "loss": 3.4086, + "step": 2013184 + }, + { + "epoch": 1.01, + "learning_rate": 1.7032596440034252e-05, + "loss": 3.396, + "step": 2013696 + }, + { + "epoch": 1.01, + "learning_rate": 1.7024210492523732e-05, + "loss": 3.4135, + "step": 2014208 + }, + { + "epoch": 1.01, + "learning_rate": 1.7015824545013212e-05, + "loss": 3.403, + "step": 2014720 + }, + { + "epoch": 1.01, + "learning_rate": 1.7007438597502692e-05, + "loss": 3.3865, + "step": 2015232 + }, + { + "epoch": 1.01, + "learning_rate": 1.6999052649992172e-05, + "loss": 3.4192, + "step": 2015744 + }, + { + "epoch": 1.01, + "learning_rate": 1.6990666702481652e-05, + "loss": 3.396, + "step": 2016256 + }, + { + "epoch": 1.01, + "learning_rate": 1.6982297133774865e-05, + "loss": 3.3915, + "step": 2016768 + }, + { + "epoch": 1.01, + "learning_rate": 1.6973911186264345e-05, + "loss": 3.4085, + "step": 2017280 + }, + { + "epoch": 1.01, + "learning_rate": 1.6965525238753824e-05, + "loss": 3.4132, + "step": 2017792 + }, + { + "epoch": 1.01, + "learning_rate": 1.6957155670047034e-05, + "loss": 3.393, + "step": 2018304 + }, + { + "epoch": 1.01, + "learning_rate": 1.6948769722536514e-05, + "loss": 3.3945, + "step": 2018816 + }, + { + "epoch": 1.01, + "learning_rate": 1.6940383775025993e-05, + "loss": 3.3901, + "step": 2019328 + }, + { + "epoch": 1.01, + "learning_rate": 1.6931997827515473e-05, + "loss": 3.3965, + "step": 2019840 + }, + { + "epoch": 1.01, + "learning_rate": 1.6923611880004953e-05, + "loss": 3.4097, + "step": 2020352 + }, + { + "epoch": 1.01, + "learning_rate": 1.6915225932494433e-05, + "loss": 3.4069, + "step": 2020864 + }, + { + "epoch": 1.01, + "learning_rate": 1.6906839984983913e-05, + "loss": 3.4085, + "step": 2021376 + }, + { + "epoch": 1.01, + "learning_rate": 1.6898454037473393e-05, + "loss": 3.4048, + "step": 2021888 + }, + { + "epoch": 1.01, + "learning_rate": 1.6890084468766602e-05, + "loss": 3.4162, + "step": 2022400 + }, + { + "epoch": 1.01, + "learning_rate": 1.6881698521256086e-05, + "loss": 3.4041, + "step": 2022912 + }, + { + "epoch": 1.01, + "learning_rate": 1.6873312573745566e-05, + "loss": 3.4117, + "step": 2023424 + }, + { + "epoch": 1.01, + "learning_rate": 1.6864926626235046e-05, + "loss": 3.3935, + "step": 2023936 + }, + { + "epoch": 1.01, + "learning_rate": 1.6856557057528255e-05, + "loss": 3.4019, + "step": 2024448 + }, + { + "epoch": 1.01, + "learning_rate": 1.6848171110017735e-05, + "loss": 3.402, + "step": 2024960 + }, + { + "epoch": 1.01, + "learning_rate": 1.6839801541310947e-05, + "loss": 3.4061, + "step": 2025472 + }, + { + "epoch": 1.01, + "learning_rate": 1.6831415593800427e-05, + "loss": 3.4112, + "step": 2025984 + }, + { + "epoch": 1.01, + "learning_rate": 1.6823029646289907e-05, + "loss": 3.4118, + "step": 2026496 + }, + { + "epoch": 1.01, + "learning_rate": 1.6814643698779387e-05, + "loss": 3.4012, + "step": 2027008 + }, + { + "epoch": 1.01, + "learning_rate": 1.6806257751268867e-05, + "loss": 3.3977, + "step": 2027520 + }, + { + "epoch": 1.01, + "learning_rate": 1.6797888182562076e-05, + "loss": 3.4044, + "step": 2028032 + }, + { + "epoch": 1.01, + "learning_rate": 1.6789502235051556e-05, + "loss": 3.4108, + "step": 2028544 + }, + { + "epoch": 1.01, + "learning_rate": 1.678111628754104e-05, + "loss": 3.3958, + "step": 2029056 + }, + { + "epoch": 1.01, + "learning_rate": 1.677273034003052e-05, + "loss": 3.3997, + "step": 2029568 + }, + { + "epoch": 1.01, + "learning_rate": 1.676434439252e-05, + "loss": 3.4118, + "step": 2030080 + }, + { + "epoch": 1.02, + "learning_rate": 1.675597482381321e-05, + "loss": 3.4004, + "step": 2030592 + }, + { + "epoch": 1.02, + "learning_rate": 1.674758887630269e-05, + "loss": 3.3995, + "step": 2031104 + }, + { + "epoch": 1.02, + "learning_rate": 1.6739202928792168e-05, + "loss": 3.3965, + "step": 2031616 + }, + { + "epoch": 1.02, + "learning_rate": 1.6730816981281648e-05, + "loss": 3.4093, + "step": 2032128 + }, + { + "epoch": 1.02, + "learning_rate": 1.6722431033771128e-05, + "loss": 3.4141, + "step": 2032640 + }, + { + "epoch": 1.02, + "learning_rate": 1.6714045086260608e-05, + "loss": 3.4062, + "step": 2033152 + }, + { + "epoch": 1.02, + "learning_rate": 1.6705659138750088e-05, + "loss": 3.3968, + "step": 2033664 + }, + { + "epoch": 1.02, + "learning_rate": 1.6697273191239568e-05, + "loss": 3.4024, + "step": 2034176 + }, + { + "epoch": 1.02, + "learning_rate": 1.668890362253278e-05, + "loss": 3.3981, + "step": 2034688 + }, + { + "epoch": 1.02, + "learning_rate": 1.6680517675022257e-05, + "loss": 3.4077, + "step": 2035200 + }, + { + "epoch": 1.02, + "learning_rate": 1.667213172751174e-05, + "loss": 3.4071, + "step": 2035712 + }, + { + "epoch": 1.02, + "learning_rate": 1.666374578000122e-05, + "loss": 3.4026, + "step": 2036224 + }, + { + "epoch": 1.02, + "learning_rate": 1.665537621129443e-05, + "loss": 3.4, + "step": 2036736 + }, + { + "epoch": 1.02, + "learning_rate": 1.664699026378391e-05, + "loss": 3.3936, + "step": 2037248 + }, + { + "epoch": 1.02, + "learning_rate": 1.663860431627339e-05, + "loss": 3.3936, + "step": 2037760 + }, + { + "epoch": 1.02, + "learning_rate": 1.663021836876287e-05, + "loss": 3.3975, + "step": 2038272 + }, + { + "epoch": 1.02, + "learning_rate": 1.6621848800056082e-05, + "loss": 3.3976, + "step": 2038784 + }, + { + "epoch": 1.02, + "learning_rate": 1.6613462852545562e-05, + "loss": 3.3972, + "step": 2039296 + }, + { + "epoch": 1.02, + "learning_rate": 1.6605076905035042e-05, + "loss": 3.3996, + "step": 2039808 + }, + { + "epoch": 1.02, + "learning_rate": 1.6596690957524522e-05, + "loss": 3.3957, + "step": 2040320 + }, + { + "epoch": 1.02, + "learning_rate": 1.658832138881773e-05, + "loss": 3.4017, + "step": 2040832 + }, + { + "epoch": 1.02, + "learning_rate": 1.657993544130721e-05, + "loss": 3.3949, + "step": 2041344 + }, + { + "epoch": 1.02, + "learning_rate": 1.6571549493796694e-05, + "loss": 3.4105, + "step": 2041856 + }, + { + "epoch": 1.02, + "learning_rate": 1.6563163546286174e-05, + "loss": 3.3949, + "step": 2042368 + }, + { + "epoch": 1.02, + "learning_rate": 1.6554793977579383e-05, + "loss": 3.4141, + "step": 2042880 + }, + { + "epoch": 1.02, + "learning_rate": 1.6546408030068863e-05, + "loss": 3.4149, + "step": 2043392 + }, + { + "epoch": 1.02, + "learning_rate": 1.6538022082558343e-05, + "loss": 3.4092, + "step": 2043904 + }, + { + "epoch": 1.02, + "learning_rate": 1.6529652513851556e-05, + "loss": 3.4007, + "step": 2044416 + }, + { + "epoch": 1.02, + "learning_rate": 1.6521266566341036e-05, + "loss": 3.4019, + "step": 2044928 + }, + { + "epoch": 1.02, + "learning_rate": 1.6512880618830515e-05, + "loss": 3.3986, + "step": 2045440 + }, + { + "epoch": 1.02, + "learning_rate": 1.6504494671319995e-05, + "loss": 3.4046, + "step": 2045952 + }, + { + "epoch": 1.02, + "learning_rate": 1.6496108723809475e-05, + "loss": 3.4026, + "step": 2046464 + }, + { + "epoch": 1.02, + "learning_rate": 1.6487722776298955e-05, + "loss": 3.3958, + "step": 2046976 + }, + { + "epoch": 1.02, + "learning_rate": 1.6479336828788432e-05, + "loss": 3.4095, + "step": 2047488 + }, + { + "epoch": 1.02, + "learning_rate": 1.6470950881277912e-05, + "loss": 3.4125, + "step": 2048000 + }, + { + "epoch": 1.02, + "learning_rate": 1.6462581312571128e-05, + "loss": 3.3981, + "step": 2048512 + }, + { + "epoch": 1.02, + "learning_rate": 1.6454195365060608e-05, + "loss": 3.3983, + "step": 2049024 + }, + { + "epoch": 1.02, + "learning_rate": 1.6445825796353817e-05, + "loss": 3.4033, + "step": 2049536 + }, + { + "epoch": 1.02, + "learning_rate": 1.6437439848843297e-05, + "loss": 3.3932, + "step": 2050048 + }, + { + "epoch": 1.02, + "learning_rate": 1.6429053901332777e-05, + "loss": 3.418, + "step": 2050560 + }, + { + "epoch": 1.02, + "learning_rate": 1.6420667953822257e-05, + "loss": 3.3953, + "step": 2051072 + }, + { + "epoch": 1.02, + "learning_rate": 1.6412282006311737e-05, + "loss": 3.4153, + "step": 2051584 + }, + { + "epoch": 1.02, + "learning_rate": 1.6403896058801217e-05, + "loss": 3.3867, + "step": 2052096 + }, + { + "epoch": 1.02, + "learning_rate": 1.6395510111290697e-05, + "loss": 3.4117, + "step": 2052608 + }, + { + "epoch": 1.02, + "learning_rate": 1.6387124163780176e-05, + "loss": 3.4021, + "step": 2053120 + }, + { + "epoch": 1.02, + "learning_rate": 1.6378754595073386e-05, + "loss": 3.4011, + "step": 2053632 + }, + { + "epoch": 1.02, + "learning_rate": 1.6370368647562866e-05, + "loss": 3.403, + "step": 2054144 + }, + { + "epoch": 1.02, + "learning_rate": 1.636198270005235e-05, + "loss": 3.3984, + "step": 2054656 + }, + { + "epoch": 1.02, + "learning_rate": 1.635359675254183e-05, + "loss": 3.4089, + "step": 2055168 + }, + { + "epoch": 1.02, + "learning_rate": 1.6345227183835038e-05, + "loss": 3.4195, + "step": 2055680 + }, + { + "epoch": 1.02, + "learning_rate": 1.6336841236324518e-05, + "loss": 3.3913, + "step": 2056192 + }, + { + "epoch": 1.02, + "learning_rate": 1.632847166761773e-05, + "loss": 3.4051, + "step": 2056704 + }, + { + "epoch": 1.02, + "learning_rate": 1.632008572010721e-05, + "loss": 3.4078, + "step": 2057216 + }, + { + "epoch": 1.02, + "learning_rate": 1.631169977259669e-05, + "loss": 3.3977, + "step": 2057728 + }, + { + "epoch": 1.02, + "learning_rate": 1.630331382508617e-05, + "loss": 3.4015, + "step": 2058240 + }, + { + "epoch": 1.02, + "learning_rate": 1.629492787757565e-05, + "loss": 3.4037, + "step": 2058752 + }, + { + "epoch": 1.02, + "learning_rate": 1.628654193006513e-05, + "loss": 3.4053, + "step": 2059264 + }, + { + "epoch": 1.02, + "learning_rate": 1.627815598255461e-05, + "loss": 3.4026, + "step": 2059776 + }, + { + "epoch": 1.02, + "learning_rate": 1.6269770035044087e-05, + "loss": 3.3993, + "step": 2060288 + }, + { + "epoch": 1.03, + "eval_loss": 3.8577840328216553, + "eval_runtime": 306.4631, + "eval_samples_per_second": 1245.145, + "eval_steps_per_second": 38.912, + "step": 2060640 + }, + { + "epoch": 0.0, + "learning_rate": 1.6261400466337303e-05, + "loss": 3.387, + "step": 2060800 + }, + { + "epoch": 0.0, + "learning_rate": 1.6253014518826783e-05, + "loss": 3.395, + "step": 2061312 + }, + { + "epoch": 0.0, + "learning_rate": 1.6244628571316262e-05, + "loss": 3.4051, + "step": 2061824 + }, + { + "epoch": 0.0, + "learning_rate": 1.623624262380574e-05, + "loss": 3.3985, + "step": 2062336 + }, + { + "epoch": 0.0, + "learning_rate": 1.622787305509895e-05, + "loss": 3.4109, + "step": 2062848 + }, + { + "epoch": 0.0, + "learning_rate": 1.621948710758843e-05, + "loss": 3.3934, + "step": 2063360 + }, + { + "epoch": 0.0, + "learning_rate": 1.621110116007791e-05, + "loss": 3.4015, + "step": 2063872 + }, + { + "epoch": 0.0, + "learning_rate": 1.620271521256739e-05, + "loss": 3.3978, + "step": 2064384 + }, + { + "epoch": 0.0, + "learning_rate": 1.6194345643860604e-05, + "loss": 3.4023, + "step": 2064896 + }, + { + "epoch": 0.0, + "learning_rate": 1.6185959696350084e-05, + "loss": 3.3956, + "step": 2065408 + }, + { + "epoch": 0.0, + "learning_rate": 1.617757374883956e-05, + "loss": 3.3944, + "step": 2065920 + }, + { + "epoch": 0.0, + "learning_rate": 1.616918780132904e-05, + "loss": 3.411, + "step": 2066432 + }, + { + "epoch": 0.0, + "learning_rate": 1.6160818232622256e-05, + "loss": 3.4075, + "step": 2066944 + }, + { + "epoch": 0.0, + "learning_rate": 1.6152432285111736e-05, + "loss": 3.393, + "step": 2067456 + }, + { + "epoch": 0.0, + "learning_rate": 1.6144046337601213e-05, + "loss": 3.4008, + "step": 2067968 + }, + { + "epoch": 0.0, + "learning_rate": 1.6135660390090693e-05, + "loss": 3.3831, + "step": 2068480 + }, + { + "epoch": 0.0, + "learning_rate": 1.6127290821383905e-05, + "loss": 3.3912, + "step": 2068992 + }, + { + "epoch": 0.0, + "learning_rate": 1.6118904873873385e-05, + "loss": 3.4021, + "step": 2069504 + }, + { + "epoch": 0.0, + "learning_rate": 1.6110518926362865e-05, + "loss": 3.3897, + "step": 2070016 + }, + { + "epoch": 0.0, + "learning_rate": 1.6102132978852345e-05, + "loss": 3.3987, + "step": 2070528 + }, + { + "epoch": 0.0, + "learning_rate": 1.6093763410145558e-05, + "loss": 3.4048, + "step": 2071040 + }, + { + "epoch": 0.0, + "learning_rate": 1.6085377462635034e-05, + "loss": 3.4046, + "step": 2071552 + }, + { + "epoch": 0.0, + "learning_rate": 1.6076991515124514e-05, + "loss": 3.4086, + "step": 2072064 + }, + { + "epoch": 0.0, + "learning_rate": 1.6068605567613994e-05, + "loss": 3.4036, + "step": 2072576 + }, + { + "epoch": 0.0, + "learning_rate": 1.606023599890721e-05, + "loss": 3.3928, + "step": 2073088 + }, + { + "epoch": 0.0, + "learning_rate": 1.6051850051396686e-05, + "loss": 3.4005, + "step": 2073600 + }, + { + "epoch": 0.0, + "learning_rate": 1.60434804826899e-05, + "loss": 3.3932, + "step": 2074112 + }, + { + "epoch": 0.0, + "learning_rate": 1.603509453517938e-05, + "loss": 3.4, + "step": 2074624 + }, + { + "epoch": 0.0, + "learning_rate": 1.602670858766886e-05, + "loss": 3.3871, + "step": 2075136 + }, + { + "epoch": 0.0, + "learning_rate": 1.6018322640158335e-05, + "loss": 3.3943, + "step": 2075648 + }, + { + "epoch": 0.01, + "learning_rate": 1.600993669264782e-05, + "loss": 3.4001, + "step": 2076160 + }, + { + "epoch": 0.01, + "learning_rate": 1.60015507451373e-05, + "loss": 3.3977, + "step": 2076672 + }, + { + "epoch": 0.01, + "learning_rate": 1.599316479762678e-05, + "loss": 3.3991, + "step": 2077184 + }, + { + "epoch": 0.01, + "learning_rate": 1.598477885011626e-05, + "loss": 3.4008, + "step": 2077696 + }, + { + "epoch": 0.01, + "learning_rate": 1.59764256602132e-05, + "loss": 3.3937, + "step": 2078208 + }, + { + "epoch": 0.01, + "learning_rate": 1.596803971270268e-05, + "loss": 3.3996, + "step": 2078720 + }, + { + "epoch": 0.01, + "learning_rate": 1.595965376519216e-05, + "loss": 3.4064, + "step": 2079232 + }, + { + "epoch": 0.01, + "learning_rate": 1.595126781768164e-05, + "loss": 3.3889, + "step": 2079744 + }, + { + "epoch": 0.01, + "learning_rate": 1.594288187017112e-05, + "loss": 3.3908, + "step": 2080256 + }, + { + "epoch": 0.01, + "learning_rate": 1.5934512301464333e-05, + "loss": 3.3921, + "step": 2080768 + }, + { + "epoch": 0.01, + "learning_rate": 1.592612635395381e-05, + "loss": 3.3908, + "step": 2081280 + }, + { + "epoch": 0.01, + "learning_rate": 1.591774040644329e-05, + "loss": 3.3957, + "step": 2081792 + }, + { + "epoch": 0.01, + "learning_rate": 1.5909354458932772e-05, + "loss": 3.4003, + "step": 2082304 + }, + { + "epoch": 0.01, + "learning_rate": 1.5900968511422252e-05, + "loss": 3.4052, + "step": 2082816 + }, + { + "epoch": 0.01, + "learning_rate": 1.5892582563911732e-05, + "loss": 3.4003, + "step": 2083328 + }, + { + "epoch": 0.01, + "learning_rate": 1.5884196616401212e-05, + "loss": 3.4014, + "step": 2083840 + }, + { + "epoch": 0.01, + "learning_rate": 1.587581066889069e-05, + "loss": 3.4023, + "step": 2084352 + }, + { + "epoch": 0.01, + "learning_rate": 1.58674411001839e-05, + "loss": 3.3969, + "step": 2084864 + }, + { + "epoch": 0.01, + "learning_rate": 1.585905515267338e-05, + "loss": 3.3733, + "step": 2085376 + }, + { + "epoch": 0.01, + "learning_rate": 1.5850669205162865e-05, + "loss": 3.4087, + "step": 2085888 + }, + { + "epoch": 0.01, + "learning_rate": 1.5842299636456074e-05, + "loss": 3.3893, + "step": 2086400 + }, + { + "epoch": 0.01, + "learning_rate": 1.5833913688945554e-05, + "loss": 3.3975, + "step": 2086912 + }, + { + "epoch": 0.01, + "learning_rate": 1.5825527741435034e-05, + "loss": 3.3915, + "step": 2087424 + }, + { + "epoch": 0.01, + "learning_rate": 1.581714179392451e-05, + "loss": 3.3853, + "step": 2087936 + }, + { + "epoch": 0.01, + "learning_rate": 1.580875584641399e-05, + "loss": 3.3873, + "step": 2088448 + }, + { + "epoch": 0.01, + "learning_rate": 1.5800386277707206e-05, + "loss": 3.3881, + "step": 2088960 + }, + { + "epoch": 0.01, + "learning_rate": 1.5792000330196686e-05, + "loss": 3.3968, + "step": 2089472 + }, + { + "epoch": 0.01, + "learning_rate": 1.5783614382686163e-05, + "loss": 3.3821, + "step": 2089984 + }, + { + "epoch": 0.01, + "learning_rate": 1.5775228435175643e-05, + "loss": 3.4075, + "step": 2090496 + }, + { + "epoch": 0.01, + "learning_rate": 1.5766842487665122e-05, + "loss": 3.394, + "step": 2091008 + }, + { + "epoch": 0.01, + "learning_rate": 1.5758456540154602e-05, + "loss": 3.374, + "step": 2091520 + }, + { + "epoch": 0.01, + "learning_rate": 1.5750070592644082e-05, + "loss": 3.4066, + "step": 2092032 + }, + { + "epoch": 0.01, + "learning_rate": 1.5741684645133566e-05, + "loss": 3.3845, + "step": 2092544 + }, + { + "epoch": 0.01, + "learning_rate": 1.5733315076426775e-05, + "loss": 3.3874, + "step": 2093056 + }, + { + "epoch": 0.01, + "learning_rate": 1.5724929128916255e-05, + "loss": 3.3942, + "step": 2093568 + }, + { + "epoch": 0.01, + "learning_rate": 1.5716543181405735e-05, + "loss": 3.404, + "step": 2094080 + }, + { + "epoch": 0.01, + "learning_rate": 1.5708173612698944e-05, + "loss": 3.3835, + "step": 2094592 + }, + { + "epoch": 0.01, + "learning_rate": 1.5699787665188427e-05, + "loss": 3.3893, + "step": 2095104 + }, + { + "epoch": 0.01, + "learning_rate": 1.5691401717677907e-05, + "loss": 3.3787, + "step": 2095616 + }, + { + "epoch": 0.01, + "learning_rate": 1.5683015770167387e-05, + "loss": 3.3865, + "step": 2096128 + }, + { + "epoch": 0.01, + "learning_rate": 1.5674629822656867e-05, + "loss": 3.3997, + "step": 2096640 + }, + { + "epoch": 0.01, + "learning_rate": 1.5666243875146344e-05, + "loss": 3.3961, + "step": 2097152 + }, + { + "epoch": 0.01, + "learning_rate": 1.5657857927635824e-05, + "loss": 3.3974, + "step": 2097664 + }, + { + "epoch": 0.01, + "learning_rate": 1.5649471980125304e-05, + "loss": 3.3944, + "step": 2098176 + }, + { + "epoch": 0.01, + "learning_rate": 1.564110241141852e-05, + "loss": 3.4055, + "step": 2098688 + }, + { + "epoch": 0.01, + "learning_rate": 1.5632716463907996e-05, + "loss": 3.3964, + "step": 2099200 + }, + { + "epoch": 0.01, + "learning_rate": 1.5624330516397476e-05, + "loss": 3.4006, + "step": 2099712 + }, + { + "epoch": 0.01, + "learning_rate": 1.5615944568886956e-05, + "loss": 3.3857, + "step": 2100224 + }, + { + "epoch": 0.01, + "learning_rate": 1.5607575000180165e-05, + "loss": 3.3904, + "step": 2100736 + }, + { + "epoch": 0.01, + "learning_rate": 1.5599189052669645e-05, + "loss": 3.3926, + "step": 2101248 + }, + { + "epoch": 0.01, + "learning_rate": 1.5590803105159128e-05, + "loss": 3.3956, + "step": 2101760 + }, + { + "epoch": 0.01, + "learning_rate": 1.5582417157648608e-05, + "loss": 3.3999, + "step": 2102272 + }, + { + "epoch": 0.01, + "learning_rate": 1.5574047588941817e-05, + "loss": 3.4021, + "step": 2102784 + }, + { + "epoch": 0.01, + "learning_rate": 1.5565661641431297e-05, + "loss": 3.3965, + "step": 2103296 + }, + { + "epoch": 0.01, + "learning_rate": 1.5557275693920777e-05, + "loss": 3.3835, + "step": 2103808 + }, + { + "epoch": 0.01, + "learning_rate": 1.5548889746410257e-05, + "loss": 3.3953, + "step": 2104320 + }, + { + "epoch": 0.01, + "learning_rate": 1.5540503798899737e-05, + "loss": 3.3978, + "step": 2104832 + }, + { + "epoch": 0.01, + "learning_rate": 1.553211785138922e-05, + "loss": 3.3847, + "step": 2105344 + }, + { + "epoch": 0.01, + "learning_rate": 1.55237319038787e-05, + "loss": 3.391, + "step": 2105856 + }, + { + "epoch": 0.01, + "learning_rate": 1.551536233517191e-05, + "loss": 3.4007, + "step": 2106368 + }, + { + "epoch": 0.02, + "learning_rate": 1.550699276646512e-05, + "loss": 3.3903, + "step": 2106880 + }, + { + "epoch": 0.02, + "learning_rate": 1.54986068189546e-05, + "loss": 3.3941, + "step": 2107392 + }, + { + "epoch": 0.02, + "learning_rate": 1.5490220871444082e-05, + "loss": 3.3842, + "step": 2107904 + }, + { + "epoch": 0.02, + "learning_rate": 1.5481834923933562e-05, + "loss": 3.4015, + "step": 2108416 + }, + { + "epoch": 0.02, + "learning_rate": 1.5473448976423042e-05, + "loss": 3.4, + "step": 2108928 + }, + { + "epoch": 0.02, + "learning_rate": 1.5465063028912522e-05, + "loss": 3.4026, + "step": 2109440 + }, + { + "epoch": 0.02, + "learning_rate": 1.5456677081402e-05, + "loss": 3.3822, + "step": 2109952 + }, + { + "epoch": 0.02, + "learning_rate": 1.544829113389148e-05, + "loss": 3.3966, + "step": 2110464 + }, + { + "epoch": 0.02, + "learning_rate": 1.543992156518469e-05, + "loss": 3.3849, + "step": 2110976 + }, + { + "epoch": 0.02, + "learning_rate": 1.5431535617674174e-05, + "loss": 3.3977, + "step": 2111488 + }, + { + "epoch": 0.02, + "learning_rate": 1.542314967016365e-05, + "loss": 3.4017, + "step": 2112000 + }, + { + "epoch": 0.02, + "learning_rate": 1.541476372265313e-05, + "loss": 3.3899, + "step": 2112512 + }, + { + "epoch": 0.02, + "learning_rate": 1.5406394153946343e-05, + "loss": 3.3917, + "step": 2113024 + }, + { + "epoch": 0.02, + "learning_rate": 1.539800820643582e-05, + "loss": 3.3831, + "step": 2113536 + }, + { + "epoch": 0.02, + "learning_rate": 1.5389622258925303e-05, + "loss": 3.3847, + "step": 2114048 + }, + { + "epoch": 0.02, + "learning_rate": 1.5381236311414783e-05, + "loss": 3.39, + "step": 2114560 + }, + { + "epoch": 0.02, + "learning_rate": 1.5372866742707996e-05, + "loss": 3.3894, + "step": 2115072 + }, + { + "epoch": 0.02, + "learning_rate": 1.5364480795197472e-05, + "loss": 3.3907, + "step": 2115584 + }, + { + "epoch": 0.02, + "learning_rate": 1.5356094847686952e-05, + "loss": 3.3891, + "step": 2116096 + }, + { + "epoch": 0.02, + "learning_rate": 1.5347708900176432e-05, + "loss": 3.3853, + "step": 2116608 + }, + { + "epoch": 0.02, + "learning_rate": 1.5339339331469644e-05, + "loss": 3.386, + "step": 2117120 + }, + { + "epoch": 0.02, + "learning_rate": 1.5330953383959124e-05, + "loss": 3.3843, + "step": 2117632 + }, + { + "epoch": 0.02, + "learning_rate": 1.5322567436448604e-05, + "loss": 3.4022, + "step": 2118144 + }, + { + "epoch": 0.02, + "learning_rate": 1.5314197867741817e-05, + "loss": 3.3862, + "step": 2118656 + }, + { + "epoch": 0.02, + "learning_rate": 1.5305811920231293e-05, + "loss": 3.4006, + "step": 2119168 + }, + { + "epoch": 0.02, + "learning_rate": 1.5297425972720773e-05, + "loss": 3.4009, + "step": 2119680 + }, + { + "epoch": 0.02, + "learning_rate": 1.5289040025210253e-05, + "loss": 3.4063, + "step": 2120192 + }, + { + "epoch": 0.02, + "learning_rate": 1.52806868353072e-05, + "loss": 3.3878, + "step": 2120704 + }, + { + "epoch": 0.02, + "learning_rate": 1.527230088779668e-05, + "loss": 3.3921, + "step": 2121216 + }, + { + "epoch": 0.02, + "learning_rate": 1.5263914940286158e-05, + "loss": 3.3912, + "step": 2121728 + }, + { + "epoch": 0.02, + "learning_rate": 1.5255528992775638e-05, + "loss": 3.3932, + "step": 2122240 + }, + { + "epoch": 0.02, + "learning_rate": 1.5247143045265117e-05, + "loss": 3.3933, + "step": 2122752 + }, + { + "epoch": 0.02, + "learning_rate": 1.5238757097754596e-05, + "loss": 3.3875, + "step": 2123264 + }, + { + "epoch": 0.02, + "learning_rate": 1.523038752904781e-05, + "loss": 3.3938, + "step": 2123776 + }, + { + "epoch": 0.02, + "learning_rate": 1.522200158153729e-05, + "loss": 3.3994, + "step": 2124288 + }, + { + "epoch": 0.02, + "learning_rate": 1.5213615634026767e-05, + "loss": 3.3952, + "step": 2124800 + }, + { + "epoch": 0.02, + "learning_rate": 1.5205229686516249e-05, + "loss": 3.3853, + "step": 2125312 + }, + { + "epoch": 0.02, + "learning_rate": 1.5196843739005729e-05, + "loss": 3.3934, + "step": 2125824 + }, + { + "epoch": 0.02, + "learning_rate": 1.5188457791495209e-05, + "loss": 3.3838, + "step": 2126336 + }, + { + "epoch": 0.02, + "learning_rate": 1.5180071843984689e-05, + "loss": 3.4033, + "step": 2126848 + }, + { + "epoch": 0.02, + "learning_rate": 1.5171685896474169e-05, + "loss": 3.3867, + "step": 2127360 + }, + { + "epoch": 0.02, + "learning_rate": 1.516331632776738e-05, + "loss": 3.4031, + "step": 2127872 + }, + { + "epoch": 0.02, + "learning_rate": 1.515493038025686e-05, + "loss": 3.3779, + "step": 2128384 + }, + { + "epoch": 0.02, + "learning_rate": 1.514654443274634e-05, + "loss": 3.3989, + "step": 2128896 + }, + { + "epoch": 0.02, + "learning_rate": 1.5138158485235821e-05, + "loss": 3.3928, + "step": 2129408 + }, + { + "epoch": 0.02, + "learning_rate": 1.512978891652903e-05, + "loss": 3.3896, + "step": 2129920 + }, + { + "epoch": 0.02, + "learning_rate": 1.5121402969018512e-05, + "loss": 3.3953, + "step": 2130432 + }, + { + "epoch": 0.02, + "learning_rate": 1.5113017021507992e-05, + "loss": 3.3858, + "step": 2130944 + }, + { + "epoch": 0.02, + "learning_rate": 1.5104631073997472e-05, + "loss": 3.3986, + "step": 2131456 + }, + { + "epoch": 0.02, + "learning_rate": 1.5096261505290682e-05, + "loss": 3.4095, + "step": 2131968 + }, + { + "epoch": 0.02, + "learning_rate": 1.5087875557780162e-05, + "loss": 3.3816, + "step": 2132480 + }, + { + "epoch": 0.02, + "learning_rate": 1.5079505989073373e-05, + "loss": 3.392, + "step": 2132992 + }, + { + "epoch": 0.02, + "learning_rate": 1.5071120041562853e-05, + "loss": 3.396, + "step": 2133504 + }, + { + "epoch": 0.02, + "learning_rate": 1.5062734094052333e-05, + "loss": 3.3905, + "step": 2134016 + }, + { + "epoch": 0.02, + "learning_rate": 1.5054348146541813e-05, + "loss": 3.3896, + "step": 2134528 + }, + { + "epoch": 0.02, + "learning_rate": 1.5045962199031293e-05, + "loss": 3.4001, + "step": 2135040 + }, + { + "epoch": 0.02, + "learning_rate": 1.5037576251520771e-05, + "loss": 3.3925, + "step": 2135552 + }, + { + "epoch": 0.02, + "learning_rate": 1.5029190304010251e-05, + "loss": 3.3932, + "step": 2136064 + }, + { + "epoch": 0.02, + "learning_rate": 1.5020820735303465e-05, + "loss": 3.3929, + "step": 2136576 + }, + { + "epoch": 0.03, + "eval_loss": 3.858140468597412, + "eval_runtime": 302.4459, + "eval_samples_per_second": 1261.683, + "eval_steps_per_second": 39.429, + "step": 2136960 + }, + { + "epoch": 1.0, + "learning_rate": 1.5012434787792945e-05, + "loss": 3.3863, + "step": 2137088 + }, + { + "epoch": 1.0, + "learning_rate": 1.5004048840282422e-05, + "loss": 3.3821, + "step": 2137600 + }, + { + "epoch": 1.0, + "learning_rate": 1.4995662892771904e-05, + "loss": 3.396, + "step": 2138112 + }, + { + "epoch": 1.0, + "learning_rate": 1.4987276945261384e-05, + "loss": 3.3904, + "step": 2138624 + }, + { + "epoch": 1.0, + "learning_rate": 1.4978890997750863e-05, + "loss": 3.3942, + "step": 2139136 + }, + { + "epoch": 1.0, + "learning_rate": 1.4970505050240343e-05, + "loss": 3.3839, + "step": 2139648 + }, + { + "epoch": 1.0, + "learning_rate": 1.4962119102729823e-05, + "loss": 3.397, + "step": 2140160 + }, + { + "epoch": 1.0, + "learning_rate": 1.4953749534023034e-05, + "loss": 3.3846, + "step": 2140672 + }, + { + "epoch": 1.0, + "learning_rate": 1.4945363586512514e-05, + "loss": 3.388, + "step": 2141184 + }, + { + "epoch": 1.0, + "learning_rate": 1.4936977639001996e-05, + "loss": 3.3851, + "step": 2141696 + }, + { + "epoch": 1.0, + "learning_rate": 1.4928591691491476e-05, + "loss": 3.3876, + "step": 2142208 + }, + { + "epoch": 1.0, + "learning_rate": 1.4920222122784685e-05, + "loss": 3.3979, + "step": 2142720 + }, + { + "epoch": 1.0, + "learning_rate": 1.4911836175274167e-05, + "loss": 3.3993, + "step": 2143232 + }, + { + "epoch": 1.0, + "learning_rate": 1.4903450227763646e-05, + "loss": 3.3832, + "step": 2143744 + }, + { + "epoch": 1.0, + "learning_rate": 1.4895064280253126e-05, + "loss": 3.3915, + "step": 2144256 + }, + { + "epoch": 1.0, + "learning_rate": 1.4886694711546337e-05, + "loss": 3.374, + "step": 2144768 + }, + { + "epoch": 1.0, + "learning_rate": 1.4878308764035817e-05, + "loss": 3.3847, + "step": 2145280 + }, + { + "epoch": 1.0, + "learning_rate": 1.4869922816525297e-05, + "loss": 3.3887, + "step": 2145792 + }, + { + "epoch": 1.0, + "learning_rate": 1.4861536869014777e-05, + "loss": 3.3823, + "step": 2146304 + }, + { + "epoch": 1.0, + "learning_rate": 1.4853167300307988e-05, + "loss": 3.3873, + "step": 2146816 + }, + { + "epoch": 1.0, + "learning_rate": 1.4844781352797468e-05, + "loss": 3.3942, + "step": 2147328 + }, + { + "epoch": 1.0, + "learning_rate": 1.4836395405286948e-05, + "loss": 3.3903, + "step": 2147840 + }, + { + "epoch": 1.0, + "learning_rate": 1.4828009457776426e-05, + "loss": 3.4006, + "step": 2148352 + }, + { + "epoch": 1.0, + "learning_rate": 1.4819639889069639e-05, + "loss": 3.3942, + "step": 2148864 + }, + { + "epoch": 1.0, + "learning_rate": 1.481125394155912e-05, + "loss": 3.3824, + "step": 2149376 + }, + { + "epoch": 1.0, + "learning_rate": 1.48028679940486e-05, + "loss": 3.3925, + "step": 2149888 + }, + { + "epoch": 1.0, + "learning_rate": 1.4794498425341811e-05, + "loss": 3.3845, + "step": 2150400 + }, + { + "epoch": 1.0, + "learning_rate": 1.4786112477831291e-05, + "loss": 3.3876, + "step": 2150912 + }, + { + "epoch": 1.0, + "learning_rate": 1.477772653032077e-05, + "loss": 3.3806, + "step": 2151424 + }, + { + "epoch": 1.0, + "learning_rate": 1.476934058281025e-05, + "loss": 3.383, + "step": 2151936 + }, + { + "epoch": 1.01, + "learning_rate": 1.4760954635299729e-05, + "loss": 3.3919, + "step": 2152448 + }, + { + "epoch": 1.01, + "learning_rate": 1.4752568687789209e-05, + "loss": 3.3883, + "step": 2152960 + }, + { + "epoch": 1.01, + "learning_rate": 1.4744182740278689e-05, + "loss": 3.3871, + "step": 2153472 + }, + { + "epoch": 1.01, + "learning_rate": 1.4735796792768169e-05, + "loss": 3.3941, + "step": 2153984 + }, + { + "epoch": 1.01, + "learning_rate": 1.472742722406138e-05, + "loss": 3.3878, + "step": 2154496 + }, + { + "epoch": 1.01, + "learning_rate": 1.471904127655086e-05, + "loss": 3.3872, + "step": 2155008 + }, + { + "epoch": 1.01, + "learning_rate": 1.471065532904034e-05, + "loss": 3.3971, + "step": 2155520 + }, + { + "epoch": 1.01, + "learning_rate": 1.4702269381529821e-05, + "loss": 3.3745, + "step": 2156032 + }, + { + "epoch": 1.01, + "learning_rate": 1.469389981282303e-05, + "loss": 3.3866, + "step": 2156544 + }, + { + "epoch": 1.01, + "learning_rate": 1.4685530244116245e-05, + "loss": 3.3835, + "step": 2157056 + }, + { + "epoch": 1.01, + "learning_rate": 1.4677144296605724e-05, + "loss": 3.3801, + "step": 2157568 + }, + { + "epoch": 1.01, + "learning_rate": 1.4668758349095201e-05, + "loss": 3.3845, + "step": 2158080 + }, + { + "epoch": 1.01, + "learning_rate": 1.4660372401584683e-05, + "loss": 3.3897, + "step": 2158592 + }, + { + "epoch": 1.01, + "learning_rate": 1.4651986454074163e-05, + "loss": 3.3944, + "step": 2159104 + }, + { + "epoch": 1.01, + "learning_rate": 1.4643600506563643e-05, + "loss": 3.3901, + "step": 2159616 + }, + { + "epoch": 1.01, + "learning_rate": 1.4635214559053123e-05, + "loss": 3.3928, + "step": 2160128 + }, + { + "epoch": 1.01, + "learning_rate": 1.4626844990346333e-05, + "loss": 3.3934, + "step": 2160640 + }, + { + "epoch": 1.01, + "learning_rate": 1.4618459042835813e-05, + "loss": 3.3874, + "step": 2161152 + }, + { + "epoch": 1.01, + "learning_rate": 1.4610073095325293e-05, + "loss": 3.3671, + "step": 2161664 + }, + { + "epoch": 1.01, + "learning_rate": 1.4601687147814775e-05, + "loss": 3.3958, + "step": 2162176 + }, + { + "epoch": 1.01, + "learning_rate": 1.4593317579107984e-05, + "loss": 3.3811, + "step": 2162688 + }, + { + "epoch": 1.01, + "learning_rate": 1.4584931631597466e-05, + "loss": 3.3863, + "step": 2163200 + }, + { + "epoch": 1.01, + "learning_rate": 1.4576545684086946e-05, + "loss": 3.3828, + "step": 2163712 + }, + { + "epoch": 1.01, + "learning_rate": 1.4568159736576426e-05, + "loss": 3.3733, + "step": 2164224 + }, + { + "epoch": 1.01, + "learning_rate": 1.4559773789065904e-05, + "loss": 3.3787, + "step": 2164736 + }, + { + "epoch": 1.01, + "learning_rate": 1.4551404220359116e-05, + "loss": 3.3767, + "step": 2165248 + }, + { + "epoch": 1.01, + "learning_rate": 1.4543018272848596e-05, + "loss": 3.3895, + "step": 2165760 + }, + { + "epoch": 1.01, + "learning_rate": 1.4534632325338076e-05, + "loss": 3.369, + "step": 2166272 + }, + { + "epoch": 1.01, + "learning_rate": 1.4526246377827555e-05, + "loss": 3.3975, + "step": 2166784 + }, + { + "epoch": 1.01, + "learning_rate": 1.4517860430317034e-05, + "loss": 3.385, + "step": 2167296 + }, + { + "epoch": 1.01, + "learning_rate": 1.4509474482806514e-05, + "loss": 3.3674, + "step": 2167808 + }, + { + "epoch": 1.01, + "learning_rate": 1.4501088535295994e-05, + "loss": 3.3953, + "step": 2168320 + }, + { + "epoch": 1.01, + "learning_rate": 1.4492702587785476e-05, + "loss": 3.3731, + "step": 2168832 + }, + { + "epoch": 1.01, + "learning_rate": 1.4484333019078685e-05, + "loss": 3.3797, + "step": 2169344 + }, + { + "epoch": 1.01, + "learning_rate": 1.4475947071568167e-05, + "loss": 3.3811, + "step": 2169856 + }, + { + "epoch": 1.01, + "learning_rate": 1.4467561124057647e-05, + "loss": 3.394, + "step": 2170368 + }, + { + "epoch": 1.01, + "learning_rate": 1.4459175176547127e-05, + "loss": 3.3762, + "step": 2170880 + }, + { + "epoch": 1.01, + "learning_rate": 1.4450805607840337e-05, + "loss": 3.3808, + "step": 2171392 + }, + { + "epoch": 1.01, + "learning_rate": 1.4442419660329817e-05, + "loss": 3.3654, + "step": 2171904 + }, + { + "epoch": 1.01, + "learning_rate": 1.4434033712819297e-05, + "loss": 3.3811, + "step": 2172416 + }, + { + "epoch": 1.01, + "learning_rate": 1.4425647765308777e-05, + "loss": 3.3876, + "step": 2172928 + }, + { + "epoch": 1.01, + "learning_rate": 1.4417261817798259e-05, + "loss": 3.3896, + "step": 2173440 + }, + { + "epoch": 1.01, + "learning_rate": 1.4408875870287736e-05, + "loss": 3.3868, + "step": 2173952 + }, + { + "epoch": 1.01, + "learning_rate": 1.4400489922777216e-05, + "loss": 3.3856, + "step": 2174464 + }, + { + "epoch": 1.01, + "learning_rate": 1.439212035407043e-05, + "loss": 3.3976, + "step": 2174976 + }, + { + "epoch": 1.01, + "learning_rate": 1.438373440655991e-05, + "loss": 3.3829, + "step": 2175488 + }, + { + "epoch": 1.01, + "learning_rate": 1.4375348459049386e-05, + "loss": 3.3905, + "step": 2176000 + }, + { + "epoch": 1.01, + "learning_rate": 1.4366962511538868e-05, + "loss": 3.3796, + "step": 2176512 + }, + { + "epoch": 1.01, + "learning_rate": 1.435859294283208e-05, + "loss": 3.3836, + "step": 2177024 + }, + { + "epoch": 1.01, + "learning_rate": 1.4350206995321559e-05, + "loss": 3.382, + "step": 2177536 + }, + { + "epoch": 1.01, + "learning_rate": 1.4341837426614771e-05, + "loss": 3.3812, + "step": 2178048 + }, + { + "epoch": 1.01, + "learning_rate": 1.4333451479104251e-05, + "loss": 3.3912, + "step": 2178560 + }, + { + "epoch": 1.01, + "learning_rate": 1.4325065531593731e-05, + "loss": 3.3871, + "step": 2179072 + }, + { + "epoch": 1.01, + "learning_rate": 1.431667958408321e-05, + "loss": 3.3948, + "step": 2179584 + }, + { + "epoch": 1.01, + "learning_rate": 1.430829363657269e-05, + "loss": 3.374, + "step": 2180096 + }, + { + "epoch": 1.01, + "learning_rate": 1.4299924067865902e-05, + "loss": 3.3835, + "step": 2180608 + }, + { + "epoch": 1.01, + "learning_rate": 1.4291538120355383e-05, + "loss": 3.3895, + "step": 2181120 + }, + { + "epoch": 1.01, + "learning_rate": 1.428315217284486e-05, + "loss": 3.3758, + "step": 2181632 + }, + { + "epoch": 1.01, + "learning_rate": 1.427476622533434e-05, + "loss": 3.3791, + "step": 2182144 + }, + { + "epoch": 1.01, + "learning_rate": 1.4266380277823822e-05, + "loss": 3.3861, + "step": 2182656 + }, + { + "epoch": 1.02, + "learning_rate": 1.425801070911703e-05, + "loss": 3.3831, + "step": 2183168 + }, + { + "epoch": 1.02, + "learning_rate": 1.4249624761606512e-05, + "loss": 3.3805, + "step": 2183680 + }, + { + "epoch": 1.02, + "learning_rate": 1.4241238814095992e-05, + "loss": 3.3776, + "step": 2184192 + }, + { + "epoch": 1.02, + "learning_rate": 1.4232852866585472e-05, + "loss": 3.3883, + "step": 2184704 + }, + { + "epoch": 1.02, + "learning_rate": 1.4224466919074952e-05, + "loss": 3.3943, + "step": 2185216 + }, + { + "epoch": 1.02, + "learning_rate": 1.4216080971564432e-05, + "loss": 3.3891, + "step": 2185728 + }, + { + "epoch": 1.02, + "learning_rate": 1.4207695024053914e-05, + "loss": 3.3707, + "step": 2186240 + }, + { + "epoch": 1.02, + "learning_rate": 1.419930907654339e-05, + "loss": 3.3861, + "step": 2186752 + }, + { + "epoch": 1.02, + "learning_rate": 1.4190939507836603e-05, + "loss": 3.376, + "step": 2187264 + }, + { + "epoch": 1.02, + "learning_rate": 1.4182553560326084e-05, + "loss": 3.388, + "step": 2187776 + }, + { + "epoch": 1.02, + "learning_rate": 1.4174167612815564e-05, + "loss": 3.3911, + "step": 2188288 + }, + { + "epoch": 1.02, + "learning_rate": 1.4165781665305041e-05, + "loss": 3.3803, + "step": 2188800 + }, + { + "epoch": 1.02, + "learning_rate": 1.4157412096598255e-05, + "loss": 3.3788, + "step": 2189312 + }, + { + "epoch": 1.02, + "learning_rate": 1.4149026149087735e-05, + "loss": 3.3776, + "step": 2189824 + }, + { + "epoch": 1.02, + "learning_rate": 1.4140640201577213e-05, + "loss": 3.3751, + "step": 2190336 + }, + { + "epoch": 1.02, + "learning_rate": 1.4132254254066693e-05, + "loss": 3.3737, + "step": 2190848 + }, + { + "epoch": 1.02, + "learning_rate": 1.4123884685359906e-05, + "loss": 3.3846, + "step": 2191360 + }, + { + "epoch": 1.02, + "learning_rate": 1.4115498737849386e-05, + "loss": 3.3785, + "step": 2191872 + }, + { + "epoch": 1.02, + "learning_rate": 1.4107112790338864e-05, + "loss": 3.3815, + "step": 2192384 + }, + { + "epoch": 1.02, + "learning_rate": 1.4098726842828344e-05, + "loss": 3.373, + "step": 2192896 + }, + { + "epoch": 1.02, + "learning_rate": 1.4090357274121556e-05, + "loss": 3.3769, + "step": 2193408 + }, + { + "epoch": 1.02, + "learning_rate": 1.4081971326611038e-05, + "loss": 3.3735, + "step": 2193920 + }, + { + "epoch": 1.02, + "learning_rate": 1.4073585379100515e-05, + "loss": 3.3926, + "step": 2194432 + }, + { + "epoch": 1.02, + "learning_rate": 1.4065199431589995e-05, + "loss": 3.3757, + "step": 2194944 + }, + { + "epoch": 1.02, + "learning_rate": 1.4056829862883209e-05, + "loss": 3.3912, + "step": 2195456 + }, + { + "epoch": 1.02, + "learning_rate": 1.4048443915372685e-05, + "loss": 3.3872, + "step": 2195968 + }, + { + "epoch": 1.02, + "learning_rate": 1.4040057967862167e-05, + "loss": 3.4005, + "step": 2196480 + }, + { + "epoch": 1.02, + "learning_rate": 1.4031704777959109e-05, + "loss": 3.3834, + "step": 2196992 + }, + { + "epoch": 1.02, + "learning_rate": 1.402331883044859e-05, + "loss": 3.3812, + "step": 2197504 + }, + { + "epoch": 1.02, + "learning_rate": 1.401493288293807e-05, + "loss": 3.3819, + "step": 2198016 + }, + { + "epoch": 1.02, + "learning_rate": 1.400654693542755e-05, + "loss": 3.3823, + "step": 2198528 + }, + { + "epoch": 1.02, + "learning_rate": 1.399816098791703e-05, + "loss": 3.3818, + "step": 2199040 + }, + { + "epoch": 1.02, + "learning_rate": 1.3989775040406508e-05, + "loss": 3.3814, + "step": 2199552 + }, + { + "epoch": 1.02, + "learning_rate": 1.3981389092895988e-05, + "loss": 3.3807, + "step": 2200064 + }, + { + "epoch": 1.02, + "learning_rate": 1.3973003145385468e-05, + "loss": 3.3915, + "step": 2200576 + }, + { + "epoch": 1.02, + "learning_rate": 1.3964633576678683e-05, + "loss": 3.3804, + "step": 2201088 + }, + { + "epoch": 1.02, + "learning_rate": 1.3956247629168159e-05, + "loss": 3.3772, + "step": 2201600 + }, + { + "epoch": 1.02, + "learning_rate": 1.3947861681657639e-05, + "loss": 3.3815, + "step": 2202112 + }, + { + "epoch": 1.02, + "learning_rate": 1.393947573414712e-05, + "loss": 3.3786, + "step": 2202624 + }, + { + "epoch": 1.02, + "learning_rate": 1.3931106165440333e-05, + "loss": 3.3924, + "step": 2203136 + }, + { + "epoch": 1.02, + "learning_rate": 1.392272021792981e-05, + "loss": 3.3767, + "step": 2203648 + }, + { + "epoch": 1.02, + "learning_rate": 1.3914334270419291e-05, + "loss": 3.3925, + "step": 2204160 + }, + { + "epoch": 1.02, + "learning_rate": 1.3905948322908771e-05, + "loss": 3.374, + "step": 2204672 + }, + { + "epoch": 1.02, + "learning_rate": 1.3897578754201982e-05, + "loss": 3.3878, + "step": 2205184 + }, + { + "epoch": 1.02, + "learning_rate": 1.3889192806691462e-05, + "loss": 3.384, + "step": 2205696 + }, + { + "epoch": 1.02, + "learning_rate": 1.3880806859180942e-05, + "loss": 3.3815, + "step": 2206208 + }, + { + "epoch": 1.02, + "learning_rate": 1.3872420911670422e-05, + "loss": 3.3793, + "step": 2206720 + }, + { + "epoch": 1.02, + "learning_rate": 1.3864051342963633e-05, + "loss": 3.3837, + "step": 2207232 + }, + { + "epoch": 1.02, + "learning_rate": 1.3855665395453113e-05, + "loss": 3.3906, + "step": 2207744 + }, + { + "epoch": 1.02, + "learning_rate": 1.3847279447942593e-05, + "loss": 3.3976, + "step": 2208256 + }, + { + "epoch": 1.02, + "learning_rate": 1.3838893500432074e-05, + "loss": 3.3753, + "step": 2208768 + }, + { + "epoch": 1.02, + "learning_rate": 1.3830523931725283e-05, + "loss": 3.3808, + "step": 2209280 + }, + { + "epoch": 1.02, + "learning_rate": 1.3822137984214763e-05, + "loss": 3.3867, + "step": 2209792 + }, + { + "epoch": 1.02, + "learning_rate": 1.3813768415507978e-05, + "loss": 3.3803, + "step": 2210304 + }, + { + "epoch": 1.02, + "learning_rate": 1.3805382467997454e-05, + "loss": 3.375, + "step": 2210816 + }, + { + "epoch": 1.02, + "learning_rate": 1.3796996520486936e-05, + "loss": 3.3904, + "step": 2211328 + }, + { + "epoch": 1.02, + "learning_rate": 1.3788610572976416e-05, + "loss": 3.3806, + "step": 2211840 + }, + { + "epoch": 1.02, + "learning_rate": 1.3780224625465896e-05, + "loss": 3.3876, + "step": 2212352 + }, + { + "epoch": 1.02, + "learning_rate": 1.3771838677955376e-05, + "loss": 3.3765, + "step": 2212864 + }, + { + "epoch": 1.03, + "eval_loss": 3.8605878353118896, + "eval_runtime": 302.7251, + "eval_samples_per_second": 1260.52, + "eval_steps_per_second": 39.392, + "step": 2213280 + }, + { + "epoch": 0.0, + "learning_rate": 1.3763452730444856e-05, + "loss": 3.38, + "step": 2213376 + }, + { + "epoch": 0.0, + "learning_rate": 1.3755066782934337e-05, + "loss": 3.3691, + "step": 2213888 + }, + { + "epoch": 0.0, + "learning_rate": 1.3746680835423814e-05, + "loss": 3.3857, + "step": 2214400 + }, + { + "epoch": 0.0, + "learning_rate": 1.3738294887913294e-05, + "loss": 3.383, + "step": 2214912 + }, + { + "epoch": 0.0, + "learning_rate": 1.3729925319206508e-05, + "loss": 3.3829, + "step": 2215424 + }, + { + "epoch": 0.0, + "learning_rate": 1.3721555750499717e-05, + "loss": 3.3772, + "step": 2215936 + }, + { + "epoch": 0.0, + "learning_rate": 1.3713169802989199e-05, + "loss": 3.382, + "step": 2216448 + }, + { + "epoch": 0.0, + "learning_rate": 1.3704783855478679e-05, + "loss": 3.3779, + "step": 2216960 + }, + { + "epoch": 0.0, + "learning_rate": 1.3696397907968159e-05, + "loss": 3.3764, + "step": 2217472 + }, + { + "epoch": 0.0, + "learning_rate": 1.3688011960457637e-05, + "loss": 3.3822, + "step": 2217984 + }, + { + "epoch": 0.0, + "learning_rate": 1.367964239175085e-05, + "loss": 3.3758, + "step": 2218496 + }, + { + "epoch": 0.0, + "learning_rate": 1.367125644424033e-05, + "loss": 3.3869, + "step": 2219008 + }, + { + "epoch": 0.0, + "learning_rate": 1.366287049672981e-05, + "loss": 3.3921, + "step": 2219520 + }, + { + "epoch": 0.0, + "learning_rate": 1.3654484549219288e-05, + "loss": 3.3725, + "step": 2220032 + }, + { + "epoch": 0.0, + "learning_rate": 1.3646098601708768e-05, + "loss": 3.3755, + "step": 2220544 + }, + { + "epoch": 0.0, + "learning_rate": 1.3637712654198247e-05, + "loss": 3.3674, + "step": 2221056 + }, + { + "epoch": 0.0, + "learning_rate": 1.3629326706687729e-05, + "loss": 3.3739, + "step": 2221568 + }, + { + "epoch": 0.0, + "learning_rate": 1.3620940759177209e-05, + "loss": 3.379, + "step": 2222080 + }, + { + "epoch": 0.0, + "learning_rate": 1.3612571190470418e-05, + "loss": 3.3722, + "step": 2222592 + }, + { + "epoch": 0.0, + "learning_rate": 1.36041852429599e-05, + "loss": 3.3742, + "step": 2223104 + }, + { + "epoch": 0.0, + "learning_rate": 1.359579929544938e-05, + "loss": 3.3897, + "step": 2223616 + }, + { + "epoch": 0.0, + "learning_rate": 1.358741334793886e-05, + "loss": 3.3791, + "step": 2224128 + }, + { + "epoch": 0.0, + "learning_rate": 1.357904377923207e-05, + "loss": 3.387, + "step": 2224640 + }, + { + "epoch": 0.0, + "learning_rate": 1.357065783172155e-05, + "loss": 3.3862, + "step": 2225152 + }, + { + "epoch": 0.0, + "learning_rate": 1.356227188421103e-05, + "loss": 3.3763, + "step": 2225664 + }, + { + "epoch": 0.0, + "learning_rate": 1.355388593670051e-05, + "loss": 3.3838, + "step": 2226176 + }, + { + "epoch": 0.0, + "learning_rate": 1.3545532746797454e-05, + "loss": 3.3714, + "step": 2226688 + }, + { + "epoch": 0.0, + "learning_rate": 1.3537146799286934e-05, + "loss": 3.3781, + "step": 2227200 + }, + { + "epoch": 0.0, + "learning_rate": 1.3528760851776412e-05, + "loss": 3.3695, + "step": 2227712 + }, + { + "epoch": 0.0, + "learning_rate": 1.3520374904265892e-05, + "loss": 3.3693, + "step": 2228224 + }, + { + "epoch": 0.01, + "learning_rate": 1.3511988956755372e-05, + "loss": 3.383, + "step": 2228736 + }, + { + "epoch": 0.01, + "learning_rate": 1.3503603009244853e-05, + "loss": 3.3775, + "step": 2229248 + }, + { + "epoch": 0.01, + "learning_rate": 1.3495217061734333e-05, + "loss": 3.3822, + "step": 2229760 + }, + { + "epoch": 0.01, + "learning_rate": 1.3486831114223813e-05, + "loss": 3.378, + "step": 2230272 + }, + { + "epoch": 0.01, + "learning_rate": 1.3478461545517024e-05, + "loss": 3.3761, + "step": 2230784 + }, + { + "epoch": 0.01, + "learning_rate": 1.3470075598006504e-05, + "loss": 3.3821, + "step": 2231296 + }, + { + "epoch": 0.01, + "learning_rate": 1.3461689650495984e-05, + "loss": 3.3896, + "step": 2231808 + }, + { + "epoch": 0.01, + "learning_rate": 1.3453303702985464e-05, + "loss": 3.3621, + "step": 2232320 + }, + { + "epoch": 0.01, + "learning_rate": 1.3444934134278675e-05, + "loss": 3.3774, + "step": 2232832 + }, + { + "epoch": 0.01, + "learning_rate": 1.3436564565571886e-05, + "loss": 3.3754, + "step": 2233344 + }, + { + "epoch": 0.01, + "learning_rate": 1.3428178618061366e-05, + "loss": 3.3671, + "step": 2233856 + }, + { + "epoch": 0.01, + "learning_rate": 1.3419792670550846e-05, + "loss": 3.3717, + "step": 2234368 + }, + { + "epoch": 0.01, + "learning_rate": 1.3411406723040326e-05, + "loss": 3.3874, + "step": 2234880 + }, + { + "epoch": 0.01, + "learning_rate": 1.3403020775529807e-05, + "loss": 3.3811, + "step": 2235392 + }, + { + "epoch": 0.01, + "learning_rate": 1.3394634828019287e-05, + "loss": 3.3806, + "step": 2235904 + }, + { + "epoch": 0.01, + "learning_rate": 1.3386248880508764e-05, + "loss": 3.3809, + "step": 2236416 + }, + { + "epoch": 0.01, + "learning_rate": 1.3377879311801978e-05, + "loss": 3.3824, + "step": 2236928 + }, + { + "epoch": 0.01, + "learning_rate": 1.3369493364291458e-05, + "loss": 3.3739, + "step": 2237440 + }, + { + "epoch": 0.01, + "learning_rate": 1.3361107416780938e-05, + "loss": 3.3582, + "step": 2237952 + }, + { + "epoch": 0.01, + "learning_rate": 1.3352721469270416e-05, + "loss": 3.3843, + "step": 2238464 + }, + { + "epoch": 0.01, + "learning_rate": 1.3344351900563629e-05, + "loss": 3.3724, + "step": 2238976 + }, + { + "epoch": 0.01, + "learning_rate": 1.3335965953053108e-05, + "loss": 3.3783, + "step": 2239488 + }, + { + "epoch": 0.01, + "learning_rate": 1.3327580005542587e-05, + "loss": 3.3716, + "step": 2240000 + }, + { + "epoch": 0.01, + "learning_rate": 1.3319194058032067e-05, + "loss": 3.3655, + "step": 2240512 + }, + { + "epoch": 0.01, + "learning_rate": 1.3310808110521547e-05, + "loss": 3.3683, + "step": 2241024 + }, + { + "epoch": 0.01, + "learning_rate": 1.330243854181476e-05, + "loss": 3.365, + "step": 2241536 + }, + { + "epoch": 0.01, + "learning_rate": 1.3294052594304237e-05, + "loss": 3.3801, + "step": 2242048 + }, + { + "epoch": 0.01, + "learning_rate": 1.3285666646793717e-05, + "loss": 3.3646, + "step": 2242560 + }, + { + "epoch": 0.01, + "learning_rate": 1.3277280699283199e-05, + "loss": 3.3833, + "step": 2243072 + }, + { + "epoch": 0.01, + "learning_rate": 1.3268894751772679e-05, + "loss": 3.377, + "step": 2243584 + }, + { + "epoch": 0.01, + "learning_rate": 1.3260508804262159e-05, + "loss": 3.3608, + "step": 2244096 + }, + { + "epoch": 0.01, + "learning_rate": 1.3252122856751639e-05, + "loss": 3.3842, + "step": 2244608 + }, + { + "epoch": 0.01, + "learning_rate": 1.3243736909241119e-05, + "loss": 3.3652, + "step": 2245120 + }, + { + "epoch": 0.01, + "learning_rate": 1.323536734053433e-05, + "loss": 3.3724, + "step": 2245632 + }, + { + "epoch": 0.01, + "learning_rate": 1.322698139302381e-05, + "loss": 3.3676, + "step": 2246144 + }, + { + "epoch": 0.01, + "learning_rate": 1.3218595445513291e-05, + "loss": 3.3848, + "step": 2246656 + }, + { + "epoch": 0.01, + "learning_rate": 1.3210209498002768e-05, + "loss": 3.3686, + "step": 2247168 + }, + { + "epoch": 0.01, + "learning_rate": 1.320183992929598e-05, + "loss": 3.3671, + "step": 2247680 + }, + { + "epoch": 0.01, + "learning_rate": 1.3193453981785462e-05, + "loss": 3.3559, + "step": 2248192 + }, + { + "epoch": 0.01, + "learning_rate": 1.3185068034274942e-05, + "loss": 3.3687, + "step": 2248704 + }, + { + "epoch": 0.01, + "learning_rate": 1.3176682086764418e-05, + "loss": 3.3788, + "step": 2249216 + }, + { + "epoch": 0.01, + "learning_rate": 1.31682961392539e-05, + "loss": 3.3829, + "step": 2249728 + }, + { + "epoch": 0.01, + "learning_rate": 1.315991019174338e-05, + "loss": 3.3742, + "step": 2250240 + }, + { + "epoch": 0.01, + "learning_rate": 1.315152424423286e-05, + "loss": 3.3801, + "step": 2250752 + }, + { + "epoch": 0.01, + "learning_rate": 1.314315467552607e-05, + "loss": 3.3875, + "step": 2251264 + }, + { + "epoch": 0.01, + "learning_rate": 1.313476872801555e-05, + "loss": 3.3723, + "step": 2251776 + }, + { + "epoch": 0.01, + "learning_rate": 1.312638278050503e-05, + "loss": 3.3768, + "step": 2252288 + }, + { + "epoch": 0.01, + "learning_rate": 1.311799683299451e-05, + "loss": 3.3762, + "step": 2252800 + }, + { + "epoch": 0.01, + "learning_rate": 1.3109627264287721e-05, + "loss": 3.3699, + "step": 2253312 + }, + { + "epoch": 0.01, + "learning_rate": 1.3101241316777201e-05, + "loss": 3.3702, + "step": 2253824 + }, + { + "epoch": 0.01, + "learning_rate": 1.3092855369266683e-05, + "loss": 3.3735, + "step": 2254336 + }, + { + "epoch": 0.01, + "learning_rate": 1.3084469421756163e-05, + "loss": 3.382, + "step": 2254848 + }, + { + "epoch": 0.01, + "learning_rate": 1.3076099853049372e-05, + "loss": 3.3806, + "step": 2255360 + }, + { + "epoch": 0.01, + "learning_rate": 1.3067713905538854e-05, + "loss": 3.3819, + "step": 2255872 + }, + { + "epoch": 0.01, + "learning_rate": 1.3059327958028334e-05, + "loss": 3.3633, + "step": 2256384 + }, + { + "epoch": 0.01, + "learning_rate": 1.3050942010517814e-05, + "loss": 3.3772, + "step": 2256896 + }, + { + "epoch": 0.01, + "learning_rate": 1.3042556063007294e-05, + "loss": 3.3791, + "step": 2257408 + }, + { + "epoch": 0.01, + "learning_rate": 1.3034170115496774e-05, + "loss": 3.3667, + "step": 2257920 + }, + { + "epoch": 0.01, + "learning_rate": 1.3025784167986252e-05, + "loss": 3.3706, + "step": 2258432 + }, + { + "epoch": 0.01, + "learning_rate": 1.3017398220475732e-05, + "loss": 3.3781, + "step": 2258944 + }, + { + "epoch": 0.02, + "learning_rate": 1.3009028651768946e-05, + "loss": 3.371, + "step": 2259456 + }, + { + "epoch": 0.02, + "learning_rate": 1.3000642704258423e-05, + "loss": 3.3725, + "step": 2259968 + }, + { + "epoch": 0.02, + "learning_rate": 1.2992256756747903e-05, + "loss": 3.3689, + "step": 2260480 + }, + { + "epoch": 0.02, + "learning_rate": 1.2983887188041117e-05, + "loss": 3.3802, + "step": 2260992 + }, + { + "epoch": 0.02, + "learning_rate": 1.2975501240530597e-05, + "loss": 3.3823, + "step": 2261504 + }, + { + "epoch": 0.02, + "learning_rate": 1.2967115293020073e-05, + "loss": 3.3794, + "step": 2262016 + }, + { + "epoch": 0.02, + "learning_rate": 1.2958729345509555e-05, + "loss": 3.3584, + "step": 2262528 + }, + { + "epoch": 0.02, + "learning_rate": 1.2950343397999035e-05, + "loss": 3.3753, + "step": 2263040 + }, + { + "epoch": 0.02, + "learning_rate": 1.2941957450488515e-05, + "loss": 3.3726, + "step": 2263552 + }, + { + "epoch": 0.02, + "learning_rate": 1.2933571502977995e-05, + "loss": 3.3746, + "step": 2264064 + }, + { + "epoch": 0.02, + "learning_rate": 1.2925185555467476e-05, + "loss": 3.3846, + "step": 2264576 + }, + { + "epoch": 0.02, + "learning_rate": 1.2916815986760685e-05, + "loss": 3.3689, + "step": 2265088 + }, + { + "epoch": 0.02, + "learning_rate": 1.2908430039250165e-05, + "loss": 3.369, + "step": 2265600 + }, + { + "epoch": 0.02, + "learning_rate": 1.2900044091739647e-05, + "loss": 3.3664, + "step": 2266112 + }, + { + "epoch": 0.02, + "learning_rate": 1.2891658144229127e-05, + "loss": 3.3701, + "step": 2266624 + }, + { + "epoch": 0.02, + "learning_rate": 1.2883288575522338e-05, + "loss": 3.3629, + "step": 2267136 + }, + { + "epoch": 0.02, + "learning_rate": 1.2874902628011818e-05, + "loss": 3.3718, + "step": 2267648 + }, + { + "epoch": 0.02, + "learning_rate": 1.2866516680501298e-05, + "loss": 3.369, + "step": 2268160 + }, + { + "epoch": 0.02, + "learning_rate": 1.2858130732990778e-05, + "loss": 3.369, + "step": 2268672 + }, + { + "epoch": 0.02, + "learning_rate": 1.2849761164283988e-05, + "loss": 3.3641, + "step": 2269184 + }, + { + "epoch": 0.02, + "learning_rate": 1.2841375216773468e-05, + "loss": 3.368, + "step": 2269696 + }, + { + "epoch": 0.02, + "learning_rate": 1.2832989269262948e-05, + "loss": 3.3614, + "step": 2270208 + }, + { + "epoch": 0.02, + "learning_rate": 1.2824603321752427e-05, + "loss": 3.3823, + "step": 2270720 + }, + { + "epoch": 0.02, + "learning_rate": 1.2816233753045639e-05, + "loss": 3.3679, + "step": 2271232 + }, + { + "epoch": 0.02, + "learning_rate": 1.2807847805535119e-05, + "loss": 3.3789, + "step": 2271744 + }, + { + "epoch": 0.02, + "learning_rate": 1.27994618580246e-05, + "loss": 3.3784, + "step": 2272256 + }, + { + "epoch": 0.02, + "learning_rate": 1.2791075910514077e-05, + "loss": 3.3915, + "step": 2272768 + }, + { + "epoch": 0.02, + "learning_rate": 1.2782706341807291e-05, + "loss": 3.3714, + "step": 2273280 + }, + { + "epoch": 0.02, + "learning_rate": 1.27743367731005e-05, + "loss": 3.374, + "step": 2273792 + }, + { + "epoch": 0.02, + "learning_rate": 1.276595082558998e-05, + "loss": 3.3729, + "step": 2274304 + }, + { + "epoch": 0.02, + "learning_rate": 1.2757564878079462e-05, + "loss": 3.3705, + "step": 2274816 + }, + { + "epoch": 0.02, + "learning_rate": 1.2749178930568942e-05, + "loss": 3.3695, + "step": 2275328 + }, + { + "epoch": 0.02, + "learning_rate": 1.2740792983058422e-05, + "loss": 3.3703, + "step": 2275840 + }, + { + "epoch": 0.02, + "learning_rate": 1.27324070355479e-05, + "loss": 3.3718, + "step": 2276352 + }, + { + "epoch": 0.02, + "learning_rate": 1.272402108803738e-05, + "loss": 3.3786, + "step": 2276864 + }, + { + "epoch": 0.02, + "learning_rate": 1.2715651519330593e-05, + "loss": 3.3733, + "step": 2277376 + }, + { + "epoch": 0.02, + "learning_rate": 1.2707265571820073e-05, + "loss": 3.366, + "step": 2277888 + }, + { + "epoch": 0.02, + "learning_rate": 1.2698896003113284e-05, + "loss": 3.3725, + "step": 2278400 + }, + { + "epoch": 0.02, + "learning_rate": 1.2690510055602764e-05, + "loss": 3.3719, + "step": 2278912 + }, + { + "epoch": 0.02, + "learning_rate": 1.2682124108092243e-05, + "loss": 3.3752, + "step": 2279424 + }, + { + "epoch": 0.02, + "learning_rate": 1.2673738160581725e-05, + "loss": 3.3716, + "step": 2279936 + }, + { + "epoch": 0.02, + "learning_rate": 1.2665352213071202e-05, + "loss": 3.3793, + "step": 2280448 + }, + { + "epoch": 0.02, + "learning_rate": 1.2656966265560682e-05, + "loss": 3.367, + "step": 2280960 + }, + { + "epoch": 0.02, + "learning_rate": 1.2648580318050163e-05, + "loss": 3.3749, + "step": 2281472 + }, + { + "epoch": 0.02, + "learning_rate": 1.2640194370539643e-05, + "loss": 3.3764, + "step": 2281984 + }, + { + "epoch": 0.02, + "learning_rate": 1.2631824801832854e-05, + "loss": 3.3677, + "step": 2282496 + }, + { + "epoch": 0.02, + "learning_rate": 1.2623438854322334e-05, + "loss": 3.3724, + "step": 2283008 + }, + { + "epoch": 0.02, + "learning_rate": 1.2615052906811814e-05, + "loss": 3.372, + "step": 2283520 + }, + { + "epoch": 0.02, + "learning_rate": 1.2606666959301294e-05, + "loss": 3.3794, + "step": 2284032 + }, + { + "epoch": 0.02, + "learning_rate": 1.2598297390594505e-05, + "loss": 3.3875, + "step": 2284544 + }, + { + "epoch": 0.02, + "learning_rate": 1.2589911443083985e-05, + "loss": 3.3681, + "step": 2285056 + }, + { + "epoch": 0.02, + "learning_rate": 1.2581525495573465e-05, + "loss": 3.3694, + "step": 2285568 + }, + { + "epoch": 0.02, + "learning_rate": 1.2573155926866675e-05, + "loss": 3.3735, + "step": 2286080 + }, + { + "epoch": 0.02, + "learning_rate": 1.2564769979356155e-05, + "loss": 3.3749, + "step": 2286592 + }, + { + "epoch": 0.02, + "learning_rate": 1.2556384031845635e-05, + "loss": 3.3644, + "step": 2287104 + }, + { + "epoch": 0.02, + "learning_rate": 1.2547998084335117e-05, + "loss": 3.3812, + "step": 2287616 + }, + { + "epoch": 0.02, + "learning_rate": 1.2539612136824597e-05, + "loss": 3.373, + "step": 2288128 + }, + { + "epoch": 0.02, + "learning_rate": 1.2531226189314077e-05, + "loss": 3.3808, + "step": 2288640 + }, + { + "epoch": 0.02, + "learning_rate": 1.2522840241803555e-05, + "loss": 3.3611, + "step": 2289152 + }, + { + "epoch": 0.03, + "eval_loss": 3.8611857891082764, + "eval_runtime": 332.3199, + "eval_samples_per_second": 1148.264, + "eval_steps_per_second": 35.884, + "step": 2289600 + }, + { + "epoch": 1.0, + "learning_rate": 1.2514454294293035e-05, + "loss": 3.3735, + "step": 2289664 + }, + { + "epoch": 1.0, + "learning_rate": 1.2506084725586248e-05, + "loss": 3.3656, + "step": 2290176 + }, + { + "epoch": 1.0, + "learning_rate": 1.2497698778075728e-05, + "loss": 3.3741, + "step": 2290688 + }, + { + "epoch": 1.0, + "learning_rate": 1.2489312830565207e-05, + "loss": 3.3726, + "step": 2291200 + }, + { + "epoch": 1.0, + "learning_rate": 1.2480926883054687e-05, + "loss": 3.3767, + "step": 2291712 + }, + { + "epoch": 1.0, + "learning_rate": 1.2472557314347898e-05, + "loss": 3.369, + "step": 2292224 + }, + { + "epoch": 1.0, + "learning_rate": 1.2464171366837378e-05, + "loss": 3.3684, + "step": 2292736 + }, + { + "epoch": 1.0, + "learning_rate": 1.2455785419326858e-05, + "loss": 3.367, + "step": 2293248 + }, + { + "epoch": 1.0, + "learning_rate": 1.2447399471816338e-05, + "loss": 3.3659, + "step": 2293760 + }, + { + "epoch": 1.0, + "learning_rate": 1.2439029903109549e-05, + "loss": 3.3711, + "step": 2294272 + }, + { + "epoch": 1.0, + "learning_rate": 1.2430643955599029e-05, + "loss": 3.3669, + "step": 2294784 + }, + { + "epoch": 1.0, + "learning_rate": 1.2422258008088509e-05, + "loss": 3.379, + "step": 2295296 + }, + { + "epoch": 1.0, + "learning_rate": 1.2413872060577989e-05, + "loss": 3.383, + "step": 2295808 + }, + { + "epoch": 1.0, + "learning_rate": 1.24055024918712e-05, + "loss": 3.3645, + "step": 2296320 + }, + { + "epoch": 1.0, + "learning_rate": 1.2397116544360681e-05, + "loss": 3.3701, + "step": 2296832 + }, + { + "epoch": 1.0, + "learning_rate": 1.2388730596850161e-05, + "loss": 3.3566, + "step": 2297344 + }, + { + "epoch": 1.0, + "learning_rate": 1.238034464933964e-05, + "loss": 3.3687, + "step": 2297856 + }, + { + "epoch": 1.0, + "learning_rate": 1.2371975080632852e-05, + "loss": 3.3644, + "step": 2298368 + }, + { + "epoch": 1.0, + "learning_rate": 1.2363589133122332e-05, + "loss": 3.3657, + "step": 2298880 + }, + { + "epoch": 1.0, + "learning_rate": 1.235520318561181e-05, + "loss": 3.3603, + "step": 2299392 + }, + { + "epoch": 1.0, + "learning_rate": 1.234681723810129e-05, + "loss": 3.3813, + "step": 2299904 + }, + { + "epoch": 1.0, + "learning_rate": 1.2338447669394503e-05, + "loss": 3.3706, + "step": 2300416 + }, + { + "epoch": 1.0, + "learning_rate": 1.2330061721883982e-05, + "loss": 3.3768, + "step": 2300928 + }, + { + "epoch": 1.0, + "learning_rate": 1.2321675774373462e-05, + "loss": 3.3732, + "step": 2301440 + }, + { + "epoch": 1.0, + "learning_rate": 1.2313289826862942e-05, + "loss": 3.373, + "step": 2301952 + }, + { + "epoch": 1.0, + "learning_rate": 1.2304920258156153e-05, + "loss": 3.3674, + "step": 2302464 + }, + { + "epoch": 1.0, + "learning_rate": 1.2296550689449366e-05, + "loss": 3.3641, + "step": 2302976 + }, + { + "epoch": 1.0, + "learning_rate": 1.2288164741938844e-05, + "loss": 3.3701, + "step": 2303488 + }, + { + "epoch": 1.0, + "learning_rate": 1.2279778794428324e-05, + "loss": 3.363, + "step": 2304000 + }, + { + "epoch": 1.0, + "learning_rate": 1.2271392846917806e-05, + "loss": 3.3616, + "step": 2304512 + }, + { + "epoch": 1.01, + "learning_rate": 1.2263006899407284e-05, + "loss": 3.3709, + "step": 2305024 + }, + { + "epoch": 1.01, + "learning_rate": 1.2254620951896764e-05, + "loss": 3.3652, + "step": 2305536 + }, + { + "epoch": 1.01, + "learning_rate": 1.2246235004386244e-05, + "loss": 3.3738, + "step": 2306048 + }, + { + "epoch": 1.01, + "learning_rate": 1.2237849056875725e-05, + "loss": 3.3647, + "step": 2306560 + }, + { + "epoch": 1.01, + "learning_rate": 1.2229479488168934e-05, + "loss": 3.3666, + "step": 2307072 + }, + { + "epoch": 1.01, + "learning_rate": 1.2221093540658416e-05, + "loss": 3.3761, + "step": 2307584 + }, + { + "epoch": 1.01, + "learning_rate": 1.2212707593147896e-05, + "loss": 3.3758, + "step": 2308096 + }, + { + "epoch": 1.01, + "learning_rate": 1.2204321645637374e-05, + "loss": 3.3514, + "step": 2308608 + }, + { + "epoch": 1.01, + "learning_rate": 1.2195952076930587e-05, + "loss": 3.3687, + "step": 2309120 + }, + { + "epoch": 1.01, + "learning_rate": 1.2187582508223798e-05, + "loss": 3.3631, + "step": 2309632 + }, + { + "epoch": 1.01, + "learning_rate": 1.2179196560713278e-05, + "loss": 3.3552, + "step": 2310144 + }, + { + "epoch": 1.01, + "learning_rate": 1.2170810613202758e-05, + "loss": 3.3665, + "step": 2310656 + }, + { + "epoch": 1.01, + "learning_rate": 1.2162424665692237e-05, + "loss": 3.3786, + "step": 2311168 + }, + { + "epoch": 1.01, + "learning_rate": 1.2154038718181717e-05, + "loss": 3.3684, + "step": 2311680 + }, + { + "epoch": 1.01, + "learning_rate": 1.2145652770671197e-05, + "loss": 3.3717, + "step": 2312192 + }, + { + "epoch": 1.01, + "learning_rate": 1.2137266823160677e-05, + "loss": 3.3734, + "step": 2312704 + }, + { + "epoch": 1.01, + "learning_rate": 1.2128897254453888e-05, + "loss": 3.3702, + "step": 2313216 + }, + { + "epoch": 1.01, + "learning_rate": 1.212051130694337e-05, + "loss": 3.365, + "step": 2313728 + }, + { + "epoch": 1.01, + "learning_rate": 1.2112125359432848e-05, + "loss": 3.3516, + "step": 2314240 + }, + { + "epoch": 1.01, + "learning_rate": 1.2103739411922328e-05, + "loss": 3.3741, + "step": 2314752 + }, + { + "epoch": 1.01, + "learning_rate": 1.209536984321554e-05, + "loss": 3.3646, + "step": 2315264 + }, + { + "epoch": 1.01, + "learning_rate": 1.208698389570502e-05, + "loss": 3.3674, + "step": 2315776 + }, + { + "epoch": 1.01, + "learning_rate": 1.2078597948194499e-05, + "loss": 3.3595, + "step": 2316288 + }, + { + "epoch": 1.01, + "learning_rate": 1.2070212000683979e-05, + "loss": 3.3562, + "step": 2316800 + }, + { + "epoch": 1.01, + "learning_rate": 1.2061842431977191e-05, + "loss": 3.3551, + "step": 2317312 + }, + { + "epoch": 1.01, + "learning_rate": 1.205345648446667e-05, + "loss": 3.3583, + "step": 2317824 + }, + { + "epoch": 1.01, + "learning_rate": 1.2045070536956151e-05, + "loss": 3.3723, + "step": 2318336 + }, + { + "epoch": 1.01, + "learning_rate": 1.2036684589445631e-05, + "loss": 3.3528, + "step": 2318848 + }, + { + "epoch": 1.01, + "learning_rate": 1.2028298641935111e-05, + "loss": 3.3721, + "step": 2319360 + }, + { + "epoch": 1.01, + "learning_rate": 1.201991269442459e-05, + "loss": 3.3648, + "step": 2319872 + }, + { + "epoch": 1.01, + "learning_rate": 1.2011526746914071e-05, + "loss": 3.3539, + "step": 2320384 + }, + { + "epoch": 1.01, + "learning_rate": 1.200314079940355e-05, + "loss": 3.3664, + "step": 2320896 + }, + { + "epoch": 1.01, + "learning_rate": 1.1994771230696762e-05, + "loss": 3.3601, + "step": 2321408 + }, + { + "epoch": 1.01, + "learning_rate": 1.1986385283186242e-05, + "loss": 3.3656, + "step": 2321920 + }, + { + "epoch": 1.01, + "learning_rate": 1.1977999335675722e-05, + "loss": 3.3547, + "step": 2322432 + }, + { + "epoch": 1.01, + "learning_rate": 1.1969613388165201e-05, + "loss": 3.3757, + "step": 2322944 + }, + { + "epoch": 1.01, + "learning_rate": 1.1961243819458412e-05, + "loss": 3.3623, + "step": 2323456 + }, + { + "epoch": 1.01, + "learning_rate": 1.1952874250751623e-05, + "loss": 3.3544, + "step": 2323968 + }, + { + "epoch": 1.01, + "learning_rate": 1.1944488303241105e-05, + "loss": 3.3481, + "step": 2324480 + }, + { + "epoch": 1.01, + "learning_rate": 1.1936102355730585e-05, + "loss": 3.36, + "step": 2324992 + }, + { + "epoch": 1.01, + "learning_rate": 1.1927716408220063e-05, + "loss": 3.3653, + "step": 2325504 + }, + { + "epoch": 1.01, + "learning_rate": 1.1919330460709543e-05, + "loss": 3.3768, + "step": 2326016 + }, + { + "epoch": 1.01, + "learning_rate": 1.1910944513199025e-05, + "loss": 3.3604, + "step": 2326528 + }, + { + "epoch": 1.01, + "learning_rate": 1.1902558565688503e-05, + "loss": 3.3722, + "step": 2327040 + }, + { + "epoch": 1.01, + "learning_rate": 1.1894188996981714e-05, + "loss": 3.3729, + "step": 2327552 + }, + { + "epoch": 1.01, + "learning_rate": 1.1885803049471195e-05, + "loss": 3.3644, + "step": 2328064 + }, + { + "epoch": 1.01, + "learning_rate": 1.1877417101960675e-05, + "loss": 3.3642, + "step": 2328576 + }, + { + "epoch": 1.01, + "learning_rate": 1.1869031154450153e-05, + "loss": 3.3631, + "step": 2329088 + }, + { + "epoch": 1.01, + "learning_rate": 1.1860661585743366e-05, + "loss": 3.3638, + "step": 2329600 + }, + { + "epoch": 1.01, + "learning_rate": 1.1852275638232846e-05, + "loss": 3.361, + "step": 2330112 + }, + { + "epoch": 1.01, + "learning_rate": 1.1843889690722324e-05, + "loss": 3.3624, + "step": 2330624 + }, + { + "epoch": 1.01, + "learning_rate": 1.1835503743211806e-05, + "loss": 3.3719, + "step": 2331136 + }, + { + "epoch": 1.01, + "learning_rate": 1.1827134174505017e-05, + "loss": 3.3741, + "step": 2331648 + }, + { + "epoch": 1.01, + "learning_rate": 1.1818748226994497e-05, + "loss": 3.3681, + "step": 2332160 + }, + { + "epoch": 1.01, + "learning_rate": 1.1810362279483977e-05, + "loss": 3.3555, + "step": 2332672 + }, + { + "epoch": 1.01, + "learning_rate": 1.1801976331973456e-05, + "loss": 3.3648, + "step": 2333184 + }, + { + "epoch": 1.01, + "learning_rate": 1.1793590384462936e-05, + "loss": 3.3693, + "step": 2333696 + }, + { + "epoch": 1.01, + "learning_rate": 1.1785204436952416e-05, + "loss": 3.3606, + "step": 2334208 + }, + { + "epoch": 1.01, + "learning_rate": 1.1776818489441896e-05, + "loss": 3.3599, + "step": 2334720 + }, + { + "epoch": 1.01, + "learning_rate": 1.1768432541931376e-05, + "loss": 3.3663, + "step": 2335232 + }, + { + "epoch": 1.02, + "learning_rate": 1.1760062973224587e-05, + "loss": 3.3658, + "step": 2335744 + }, + { + "epoch": 1.02, + "learning_rate": 1.1751677025714067e-05, + "loss": 3.3576, + "step": 2336256 + }, + { + "epoch": 1.02, + "learning_rate": 1.1743291078203547e-05, + "loss": 3.3612, + "step": 2336768 + }, + { + "epoch": 1.02, + "learning_rate": 1.1734905130693027e-05, + "loss": 3.3681, + "step": 2337280 + }, + { + "epoch": 1.02, + "learning_rate": 1.172655194078997e-05, + "loss": 3.3699, + "step": 2337792 + }, + { + "epoch": 1.02, + "learning_rate": 1.1718165993279449e-05, + "loss": 3.373, + "step": 2338304 + }, + { + "epoch": 1.02, + "learning_rate": 1.170978004576893e-05, + "loss": 3.3517, + "step": 2338816 + }, + { + "epoch": 1.02, + "learning_rate": 1.170139409825841e-05, + "loss": 3.3644, + "step": 2339328 + }, + { + "epoch": 1.02, + "learning_rate": 1.1693008150747888e-05, + "loss": 3.365, + "step": 2339840 + }, + { + "epoch": 1.02, + "learning_rate": 1.168462220323737e-05, + "loss": 3.3596, + "step": 2340352 + }, + { + "epoch": 1.02, + "learning_rate": 1.167623625572685e-05, + "loss": 3.3766, + "step": 2340864 + }, + { + "epoch": 1.02, + "learning_rate": 1.166785030821633e-05, + "loss": 3.3629, + "step": 2341376 + }, + { + "epoch": 1.02, + "learning_rate": 1.165948073950954e-05, + "loss": 3.3559, + "step": 2341888 + }, + { + "epoch": 1.02, + "learning_rate": 1.165109479199902e-05, + "loss": 3.3617, + "step": 2342400 + }, + { + "epoch": 1.02, + "learning_rate": 1.16427088444885e-05, + "loss": 3.3602, + "step": 2342912 + }, + { + "epoch": 1.02, + "learning_rate": 1.1634322896977979e-05, + "loss": 3.3502, + "step": 2343424 + }, + { + "epoch": 1.02, + "learning_rate": 1.1625953328271191e-05, + "loss": 3.361, + "step": 2343936 + }, + { + "epoch": 1.02, + "learning_rate": 1.1617583759564402e-05, + "loss": 3.3602, + "step": 2344448 + }, + { + "epoch": 1.02, + "learning_rate": 1.1609197812053884e-05, + "loss": 3.359, + "step": 2344960 + }, + { + "epoch": 1.02, + "learning_rate": 1.1600811864543362e-05, + "loss": 3.3536, + "step": 2345472 + }, + { + "epoch": 1.02, + "learning_rate": 1.1592425917032842e-05, + "loss": 3.3639, + "step": 2345984 + }, + { + "epoch": 1.02, + "learning_rate": 1.1584039969522322e-05, + "loss": 3.3472, + "step": 2346496 + }, + { + "epoch": 1.02, + "learning_rate": 1.1575654022011804e-05, + "loss": 3.3732, + "step": 2347008 + }, + { + "epoch": 1.02, + "learning_rate": 1.1567268074501282e-05, + "loss": 3.3571, + "step": 2347520 + }, + { + "epoch": 1.02, + "learning_rate": 1.1558882126990762e-05, + "loss": 3.3665, + "step": 2348032 + }, + { + "epoch": 1.02, + "learning_rate": 1.1550512558283974e-05, + "loss": 3.3694, + "step": 2348544 + }, + { + "epoch": 1.02, + "learning_rate": 1.1542126610773453e-05, + "loss": 3.3857, + "step": 2349056 + }, + { + "epoch": 1.02, + "learning_rate": 1.1533740663262933e-05, + "loss": 3.3608, + "step": 2349568 + }, + { + "epoch": 1.02, + "learning_rate": 1.1525371094556145e-05, + "loss": 3.3619, + "step": 2350080 + }, + { + "epoch": 1.02, + "learning_rate": 1.1516985147045625e-05, + "loss": 3.3679, + "step": 2350592 + }, + { + "epoch": 1.02, + "learning_rate": 1.1508599199535105e-05, + "loss": 3.3549, + "step": 2351104 + }, + { + "epoch": 1.02, + "learning_rate": 1.1500213252024585e-05, + "loss": 3.362, + "step": 2351616 + }, + { + "epoch": 1.02, + "learning_rate": 1.1491843683317796e-05, + "loss": 3.3617, + "step": 2352128 + }, + { + "epoch": 1.02, + "learning_rate": 1.1483457735807276e-05, + "loss": 3.3616, + "step": 2352640 + }, + { + "epoch": 1.02, + "learning_rate": 1.1475071788296756e-05, + "loss": 3.3708, + "step": 2353152 + }, + { + "epoch": 1.02, + "learning_rate": 1.1466685840786236e-05, + "loss": 3.3635, + "step": 2353664 + }, + { + "epoch": 1.02, + "learning_rate": 1.1458299893275716e-05, + "loss": 3.3568, + "step": 2354176 + }, + { + "epoch": 1.02, + "learning_rate": 1.1449913945765196e-05, + "loss": 3.3617, + "step": 2354688 + }, + { + "epoch": 1.02, + "learning_rate": 1.1441527998254675e-05, + "loss": 3.3685, + "step": 2355200 + }, + { + "epoch": 1.02, + "learning_rate": 1.1433142050744155e-05, + "loss": 3.361, + "step": 2355712 + }, + { + "epoch": 1.02, + "learning_rate": 1.1424772482037366e-05, + "loss": 3.3647, + "step": 2356224 + }, + { + "epoch": 1.02, + "learning_rate": 1.1416386534526846e-05, + "loss": 3.3703, + "step": 2356736 + }, + { + "epoch": 1.02, + "learning_rate": 1.1408000587016326e-05, + "loss": 3.3561, + "step": 2357248 + }, + { + "epoch": 1.02, + "learning_rate": 1.1399614639505806e-05, + "loss": 3.3648, + "step": 2357760 + }, + { + "epoch": 1.02, + "learning_rate": 1.1391245070799017e-05, + "loss": 3.364, + "step": 2358272 + }, + { + "epoch": 1.02, + "learning_rate": 1.1382859123288497e-05, + "loss": 3.3667, + "step": 2358784 + }, + { + "epoch": 1.02, + "learning_rate": 1.1374473175777978e-05, + "loss": 3.3596, + "step": 2359296 + }, + { + "epoch": 1.02, + "learning_rate": 1.136610360707119e-05, + "loss": 3.3662, + "step": 2359808 + }, + { + "epoch": 1.02, + "learning_rate": 1.13577340383644e-05, + "loss": 3.3715, + "step": 2360320 + }, + { + "epoch": 1.02, + "learning_rate": 1.134934809085388e-05, + "loss": 3.372, + "step": 2360832 + }, + { + "epoch": 1.02, + "learning_rate": 1.134096214334336e-05, + "loss": 3.3607, + "step": 2361344 + }, + { + "epoch": 1.02, + "learning_rate": 1.133257619583284e-05, + "loss": 3.3616, + "step": 2361856 + }, + { + "epoch": 1.02, + "learning_rate": 1.132420662712605e-05, + "loss": 3.3604, + "step": 2362368 + }, + { + "epoch": 1.02, + "learning_rate": 1.131582067961553e-05, + "loss": 3.3653, + "step": 2362880 + }, + { + "epoch": 1.02, + "learning_rate": 1.130743473210501e-05, + "loss": 3.3548, + "step": 2363392 + }, + { + "epoch": 1.02, + "learning_rate": 1.129904878459449e-05, + "loss": 3.3733, + "step": 2363904 + }, + { + "epoch": 1.02, + "learning_rate": 1.129066283708397e-05, + "loss": 3.3626, + "step": 2364416 + }, + { + "epoch": 1.02, + "learning_rate": 1.128227688957345e-05, + "loss": 3.3686, + "step": 2364928 + }, + { + "epoch": 1.02, + "learning_rate": 1.127389094206293e-05, + "loss": 3.3543, + "step": 2365440 + }, + { + "epoch": 1.03, + "eval_loss": 3.862396001815796, + "eval_runtime": 338.6895, + "eval_samples_per_second": 1126.669, + "eval_steps_per_second": 35.209, + "step": 2365920 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 1.6581087008830956e+18, + "trial_name": null, + "trial_params": null +}