diff --git "a/checkpoint-1831680/trainer_state.json" "b/checkpoint-1831680/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-1831680/trainer_state.json" @@ -0,0 +1,21679 @@ +{ + "best_metric": 3.8432776927948, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/binding-domain/transformer/0/checkpoints/checkpoint-915840", + "epoch": 0.025000606015738065, + "eval_steps": 10, + "global_step": 1831680, + "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": 10.9402, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 6.8272, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 6.1901, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 5.9741, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 5.8089, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 5.7087, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 5.5936, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 5.5251, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 5.4409, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 5.3928, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 5.3412, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 5.3021, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989936862987376e-05, + "loss": 5.2523, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989099906116697e-05, + "loss": 5.2013, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988261311365645e-05, + "loss": 5.1676, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.987422716614593e-05, + "loss": 5.1251, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986584121863541e-05, + "loss": 5.097, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985745527112489e-05, + "loss": 5.075, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984906932361437e-05, + "loss": 5.0453, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.0127, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 5.0017, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.9823927859886547e-05, + "loss": 4.9631, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.9815541912376026e-05, + "loss": 4.9463, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.9807155964865506e-05, + "loss": 4.9236, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 4.9129, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790400448648195e-05, + "loss": 4.8836, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9782014501137675e-05, + "loss": 4.8671, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773628553627155e-05, + "loss": 4.8459, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 4.8271, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756873037409844e-05, + "loss": 4.8133, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748487089899324e-05, + "loss": 4.7946, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.9740101142388804e-05, + "loss": 4.7908, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731715194878284e-05, + "loss": 4.7707, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.9723329247367764e-05, + "loss": 4.7631, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.971495967866098e-05, + "loss": 4.7571, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.970657373115046e-05, + "loss": 4.7389, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969820416244367e-05, + "loss": 4.7307, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968981821493315e-05, + "loss": 4.7035, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.968143226742263e-05, + "loss": 4.6986, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967304631991211e-05, + "loss": 4.6811, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966466037240159e-05, + "loss": 4.6804, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965627442489107e-05, + "loss": 4.6683, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964788847738054e-05, + "loss": 4.6592, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963950252987002e-05, + "loss": 4.6375, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.96311165823595e-05, + "loss": 4.6483, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962274701365272e-05, + "loss": 4.6339, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.96143610661422e-05, + "loss": 4.6276, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960597511863168e-05, + "loss": 4.621, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.959758917112116e-05, + "loss": 4.5898, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.95892359812181e-05, + "loss": 4.5885, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958085003370758e-05, + "loss": 4.5932, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957246408619706e-05, + "loss": 4.5853, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956407813868654e-05, + "loss": 4.5673, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.9555692191176016e-05, + "loss": 4.5487, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.954732262246923e-05, + "loss": 4.5516, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.953893667495871e-05, + "loss": 4.5366, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.953055072744819e-05, + "loss": 4.564, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.952216477993767e-05, + "loss": 4.5197, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951377883242715e-05, + "loss": 4.5349, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.950539288491663e-05, + "loss": 4.5282, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949700693740611e-05, + "loss": 4.5056, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948862098989559e-05, + "loss": 4.5105, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.94802514211888e-05, + "loss": 4.4995, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947186547367828e-05, + "loss": 4.483, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946347952616776e-05, + "loss": 4.4835, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945509357865724e-05, + "loss": 4.502, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944672400995045e-05, + "loss": 4.4789, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.943833806243993e-05, + "loss": 4.4688, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942995211492941e-05, + "loss": 4.4589, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.9421582546222625e-05, + "loss": 4.4607, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.9413196598712105e-05, + "loss": 4.4728, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.9404810651201585e-05, + "loss": 4.4682, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396424703691065e-05, + "loss": 4.4569, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388038756180545e-05, + "loss": 4.4626, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379652808670025e-05, + "loss": 4.4649, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371266861159505e-05, + "loss": 4.4491, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.9362897292452714e-05, + "loss": 4.4373, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.9354511344942194e-05, + "loss": 4.4282, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.9346125397431674e-05, + "loss": 4.4274, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.9337739449921154e-05, + "loss": 4.4201, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.9329353502410634e-05, + "loss": 4.4157, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.9320967554900114e-05, + "loss": 4.418, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.9312581607389594e-05, + "loss": 4.4189, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.9304195659879074e-05, + "loss": 4.4145, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.929582609117229e-05, + "loss": 4.3895, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.928744014366177e-05, + "loss": 4.3879, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.927905419615125e-05, + "loss": 4.3972, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.927066824864073e-05, + "loss": 4.4005, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.926229867993394e-05, + "loss": 4.3816, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925392911122715e-05, + "loss": 4.3833, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.924554316371663e-05, + "loss": 4.388, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923715721620611e-05, + "loss": 4.3728, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922878764749932e-05, + "loss": 4.369, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.92204016999888e-05, + "loss": 4.3723, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921201575247828e-05, + "loss": 4.3629, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920362980496776e-05, + "loss": 4.3675, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919524385745724e-05, + "loss": 4.3589, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918685790994672e-05, + "loss": 4.3442, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.91784719624362e-05, + "loss": 4.3522, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.9170086014925676e-05, + "loss": 4.353, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.9161700067415156e-05, + "loss": 4.3479, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.9153314119904636e-05, + "loss": 4.3472, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.9144928172394116e-05, + "loss": 4.3415, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.9136542224883596e-05, + "loss": 4.3384, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.9128172656176805e-05, + "loss": 4.3383, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.9119786708666285e-05, + "loss": 4.3137, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.91114171399595e-05, + "loss": 4.3176, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.910303119244898e-05, + "loss": 4.3223, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.909464524493846e-05, + "loss": 4.3199, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908625929742794e-05, + "loss": 4.3105, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907787334991742e-05, + "loss": 4.3065, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.90694874024069e-05, + "loss": 4.3039, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906110145489638e-05, + "loss": 4.3084, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.905273188618959e-05, + "loss": 4.303, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.904434593867907e-05, + "loss": 4.3037, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903595999116855e-05, + "loss": 4.2976, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.902757404365803e-05, + "loss": 4.3028, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.901918809614751e-05, + "loss": 4.2989, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.901080214863699e-05, + "loss": 4.2949, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.900241620112647e-05, + "loss": 4.2981, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.8994046632419686e-05, + "loss": 4.2965, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.8985660684909166e-05, + "loss": 4.285, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.8977274737398646e-05, + "loss": 4.2916, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968888789888125e-05, + "loss": 4.2792, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.8960519221181335e-05, + "loss": 4.2861, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.8952133273670815e-05, + "loss": 4.264, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.8943747326160294e-05, + "loss": 4.2766, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.8935361378649774e-05, + "loss": 4.2625, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.8926991809942984e-05, + "loss": 4.2671, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.8918605862432463e-05, + "loss": 4.2521, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.8910219914921943e-05, + "loss": 4.2818, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.8901833967411423e-05, + "loss": 4.2687, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.88934480199009e-05, + "loss": 4.2551, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888506207239038e-05, + "loss": 4.2565, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.887667612487986e-05, + "loss": 4.2617, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886829017736934e-05, + "loss": 4.2646, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885992060866256e-05, + "loss": 4.2605, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.885155103995577e-05, + "loss": 4.2494, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884316509244525e-05, + "loss": 4.2561, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883477914493473e-05, + "loss": 4.2434, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882639319742421e-05, + "loss": 4.2566, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.881800724991369e-05, + "loss": 4.2391, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.880962130240316e-05, + "loss": 4.2418, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.880123535489264e-05, + "loss": 4.2418, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.879286578618586e-05, + "loss": 4.2315, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.878447983867534e-05, + "loss": 4.2366, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877609389116482e-05, + "loss": 4.2352, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.87677079436543e-05, + "loss": 4.2335, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875932199614378e-05, + "loss": 4.2347, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.8750952427436986e-05, + "loss": 4.2251, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.1916117668151855, + "eval_runtime": 306.2873, + "eval_samples_per_second": 1245.86, + "eval_steps_per_second": 38.934, + "step": 76320 + }, + { + "epoch": 1.0, + "learning_rate": 4.8742566479926466e-05, + "loss": 4.21, + "step": 76800 + }, + { + "epoch": 1.0, + "learning_rate": 4.8734180532415946e-05, + "loss": 4.2084, + "step": 77312 + }, + { + "epoch": 1.0, + "learning_rate": 4.8725794584905426e-05, + "loss": 4.2256, + "step": 77824 + }, + { + "epoch": 1.0, + "learning_rate": 4.8717408637394906e-05, + "loss": 4.2102, + "step": 78336 + }, + { + "epoch": 1.0, + "learning_rate": 4.8709039068688115e-05, + "loss": 4.2279, + "step": 78848 + }, + { + "epoch": 1.0, + "learning_rate": 4.8700653121177595e-05, + "loss": 4.2004, + "step": 79360 + }, + { + "epoch": 1.0, + "learning_rate": 4.8692267173667075e-05, + "loss": 4.2057, + "step": 79872 + }, + { + "epoch": 1.0, + "learning_rate": 4.8683881226156555e-05, + "loss": 4.1917, + "step": 80384 + }, + { + "epoch": 1.0, + "learning_rate": 4.867551165744977e-05, + "loss": 4.2061, + "step": 80896 + }, + { + "epoch": 1.0, + "learning_rate": 4.866712570993925e-05, + "loss": 4.1993, + "step": 81408 + }, + { + "epoch": 1.0, + "learning_rate": 4.865873976242873e-05, + "loss": 4.2053, + "step": 81920 + }, + { + "epoch": 1.0, + "learning_rate": 4.865035381491821e-05, + "loss": 4.201, + "step": 82432 + }, + { + "epoch": 1.0, + "learning_rate": 4.864196786740769e-05, + "loss": 4.187, + "step": 82944 + }, + { + "epoch": 1.0, + "learning_rate": 4.863358191989717e-05, + "loss": 4.1871, + "step": 83456 + }, + { + "epoch": 1.0, + "learning_rate": 4.862519597238665e-05, + "loss": 4.1836, + "step": 83968 + }, + { + "epoch": 1.0, + "learning_rate": 4.861681002487613e-05, + "loss": 4.178, + "step": 84480 + }, + { + "epoch": 1.0, + "learning_rate": 4.860844045616934e-05, + "loss": 4.1853, + "step": 84992 + }, + { + "epoch": 1.0, + "learning_rate": 4.860005450865882e-05, + "loss": 4.1823, + "step": 85504 + }, + { + "epoch": 1.0, + "learning_rate": 4.85916685611483e-05, + "loss": 4.1787, + "step": 86016 + }, + { + "epoch": 1.0, + "learning_rate": 4.858328261363778e-05, + "loss": 4.1977, + "step": 86528 + }, + { + "epoch": 1.0, + "learning_rate": 4.8574913044930995e-05, + "loss": 4.1695, + "step": 87040 + }, + { + "epoch": 1.0, + "learning_rate": 4.8566527097420475e-05, + "loss": 4.1811, + "step": 87552 + }, + { + "epoch": 1.0, + "learning_rate": 4.8558141149909955e-05, + "loss": 4.177, + "step": 88064 + }, + { + "epoch": 1.0, + "learning_rate": 4.8549755202399435e-05, + "loss": 4.1852, + "step": 88576 + }, + { + "epoch": 1.0, + "learning_rate": 4.8541385633692644e-05, + "loss": 4.1614, + "step": 89088 + }, + { + "epoch": 1.0, + "learning_rate": 4.8532999686182124e-05, + "loss": 4.1699, + "step": 89600 + }, + { + "epoch": 1.0, + "learning_rate": 4.8524613738671604e-05, + "loss": 4.1634, + "step": 90112 + }, + { + "epoch": 1.0, + "learning_rate": 4.8516227791161084e-05, + "loss": 4.1678, + "step": 90624 + }, + { + "epoch": 1.0, + "learning_rate": 4.850785822245429e-05, + "loss": 4.152, + "step": 91136 + }, + { + "epoch": 1.01, + "learning_rate": 4.849947227494377e-05, + "loss": 4.1549, + "step": 91648 + }, + { + "epoch": 1.01, + "learning_rate": 4.849108632743325e-05, + "loss": 4.1647, + "step": 92160 + }, + { + "epoch": 1.01, + "learning_rate": 4.848270037992273e-05, + "loss": 4.1587, + "step": 92672 + }, + { + "epoch": 1.01, + "learning_rate": 4.847431443241221e-05, + "loss": 4.1582, + "step": 93184 + }, + { + "epoch": 1.01, + "learning_rate": 4.846592848490169e-05, + "loss": 4.1631, + "step": 93696 + }, + { + "epoch": 1.01, + "learning_rate": 4.845755891619491e-05, + "loss": 4.1567, + "step": 94208 + }, + { + "epoch": 1.01, + "learning_rate": 4.844917296868439e-05, + "loss": 4.156, + "step": 94720 + }, + { + "epoch": 1.01, + "learning_rate": 4.844078702117387e-05, + "loss": 4.1441, + "step": 95232 + }, + { + "epoch": 1.01, + "learning_rate": 4.843240107366335e-05, + "loss": 4.1506, + "step": 95744 + }, + { + "epoch": 1.01, + "learning_rate": 4.842403150495656e-05, + "loss": 4.1361, + "step": 96256 + }, + { + "epoch": 1.01, + "learning_rate": 4.841564555744604e-05, + "loss": 4.1446, + "step": 96768 + }, + { + "epoch": 1.01, + "learning_rate": 4.840725960993552e-05, + "loss": 4.1445, + "step": 97280 + }, + { + "epoch": 1.01, + "learning_rate": 4.8398873662425e-05, + "loss": 4.1443, + "step": 97792 + }, + { + "epoch": 1.01, + "learning_rate": 4.839050409371821e-05, + "loss": 4.131, + "step": 98304 + }, + { + "epoch": 1.01, + "learning_rate": 4.8382118146207687e-05, + "loss": 4.1418, + "step": 98816 + }, + { + "epoch": 1.01, + "learning_rate": 4.8373732198697167e-05, + "loss": 4.1444, + "step": 99328 + }, + { + "epoch": 1.01, + "learning_rate": 4.8365346251186646e-05, + "loss": 4.1378, + "step": 99840 + }, + { + "epoch": 1.01, + "learning_rate": 4.835697668247986e-05, + "loss": 4.1415, + "step": 100352 + }, + { + "epoch": 1.01, + "learning_rate": 4.834859073496934e-05, + "loss": 4.1123, + "step": 100864 + }, + { + "epoch": 1.01, + "learning_rate": 4.834020478745882e-05, + "loss": 4.1183, + "step": 101376 + }, + { + "epoch": 1.01, + "learning_rate": 4.8331818839948295e-05, + "loss": 4.1369, + "step": 101888 + }, + { + "epoch": 1.01, + "learning_rate": 4.832344927124151e-05, + "loss": 4.1288, + "step": 102400 + }, + { + "epoch": 1.01, + "learning_rate": 4.831506332373099e-05, + "loss": 4.1241, + "step": 102912 + }, + { + "epoch": 1.01, + "learning_rate": 4.830667737622047e-05, + "loss": 4.1072, + "step": 103424 + }, + { + "epoch": 1.01, + "learning_rate": 4.8298291428709944e-05, + "loss": 4.1122, + "step": 103936 + }, + { + "epoch": 1.01, + "learning_rate": 4.828992186000316e-05, + "loss": 4.1054, + "step": 104448 + }, + { + "epoch": 1.01, + "learning_rate": 4.828153591249264e-05, + "loss": 4.1295, + "step": 104960 + }, + { + "epoch": 1.01, + "learning_rate": 4.827314996498212e-05, + "loss": 4.1043, + "step": 105472 + }, + { + "epoch": 1.01, + "learning_rate": 4.82647640174716e-05, + "loss": 4.1174, + "step": 105984 + }, + { + "epoch": 1.01, + "learning_rate": 4.8256394448764816e-05, + "loss": 4.1219, + "step": 106496 + }, + { + "epoch": 1.01, + "learning_rate": 4.8248008501254296e-05, + "loss": 4.1011, + "step": 107008 + }, + { + "epoch": 1.01, + "learning_rate": 4.823962255374377e-05, + "loss": 4.1084, + "step": 107520 + }, + { + "epoch": 1.01, + "learning_rate": 4.823123660623325e-05, + "loss": 4.0997, + "step": 108032 + }, + { + "epoch": 1.01, + "learning_rate": 4.8222867037526465e-05, + "loss": 4.0961, + "step": 108544 + }, + { + "epoch": 1.01, + "learning_rate": 4.8214481090015945e-05, + "loss": 4.0947, + "step": 109056 + }, + { + "epoch": 1.01, + "learning_rate": 4.820609514250542e-05, + "loss": 4.1132, + "step": 109568 + }, + { + "epoch": 1.01, + "learning_rate": 4.81977091949949e-05, + "loss": 4.1023, + "step": 110080 + }, + { + "epoch": 1.01, + "learning_rate": 4.818932324748438e-05, + "loss": 4.0926, + "step": 110592 + }, + { + "epoch": 1.01, + "learning_rate": 4.8180953678777594e-05, + "loss": 4.0899, + "step": 111104 + }, + { + "epoch": 1.01, + "learning_rate": 4.8172567731267074e-05, + "loss": 4.0915, + "step": 111616 + }, + { + "epoch": 1.01, + "learning_rate": 4.8164181783756554e-05, + "loss": 4.1056, + "step": 112128 + }, + { + "epoch": 1.01, + "learning_rate": 4.8155795836246034e-05, + "loss": 4.1072, + "step": 112640 + }, + { + "epoch": 1.01, + "learning_rate": 4.814742626753924e-05, + "loss": 4.1014, + "step": 113152 + }, + { + "epoch": 1.01, + "learning_rate": 4.813904032002872e-05, + "loss": 4.11, + "step": 113664 + }, + { + "epoch": 1.01, + "learning_rate": 4.81306543725182e-05, + "loss": 4.1085, + "step": 114176 + }, + { + "epoch": 1.01, + "learning_rate": 4.812226842500768e-05, + "loss": 4.104, + "step": 114688 + }, + { + "epoch": 1.01, + "learning_rate": 4.811389885630089e-05, + "loss": 4.0933, + "step": 115200 + }, + { + "epoch": 1.01, + "learning_rate": 4.810551290879037e-05, + "loss": 4.0905, + "step": 115712 + }, + { + "epoch": 1.01, + "learning_rate": 4.809712696127985e-05, + "loss": 4.0904, + "step": 116224 + }, + { + "epoch": 1.01, + "learning_rate": 4.808874101376933e-05, + "loss": 4.0884, + "step": 116736 + }, + { + "epoch": 1.01, + "learning_rate": 4.808037144506255e-05, + "loss": 4.0851, + "step": 117248 + }, + { + "epoch": 1.01, + "learning_rate": 4.807198549755203e-05, + "loss": 4.0917, + "step": 117760 + }, + { + "epoch": 1.01, + "learning_rate": 4.806359955004151e-05, + "loss": 4.0961, + "step": 118272 + }, + { + "epoch": 1.01, + "learning_rate": 4.805521360253099e-05, + "loss": 4.0878, + "step": 118784 + }, + { + "epoch": 1.01, + "learning_rate": 4.8046844033824197e-05, + "loss": 4.074, + "step": 119296 + }, + { + "epoch": 1.01, + "learning_rate": 4.8038458086313677e-05, + "loss": 4.0735, + "step": 119808 + }, + { + "epoch": 1.01, + "learning_rate": 4.8030072138803156e-05, + "loss": 4.0808, + "step": 120320 + }, + { + "epoch": 1.01, + "learning_rate": 4.8021702570096366e-05, + "loss": 4.0884, + "step": 120832 + }, + { + "epoch": 1.01, + "learning_rate": 4.8013316622585846e-05, + "loss": 4.0734, + "step": 121344 + }, + { + "epoch": 1.01, + "learning_rate": 4.8004930675075325e-05, + "loss": 4.0766, + "step": 121856 + }, + { + "epoch": 1.02, + "learning_rate": 4.7996544727564805e-05, + "loss": 4.0848, + "step": 122368 + }, + { + "epoch": 1.02, + "learning_rate": 4.7988175158858015e-05, + "loss": 4.0733, + "step": 122880 + }, + { + "epoch": 1.02, + "learning_rate": 4.7979789211347494e-05, + "loss": 4.072, + "step": 123392 + }, + { + "epoch": 1.02, + "learning_rate": 4.797140326383698e-05, + "loss": 4.0731, + "step": 123904 + }, + { + "epoch": 1.02, + "learning_rate": 4.796301731632646e-05, + "loss": 4.0731, + "step": 124416 + }, + { + "epoch": 1.02, + "learning_rate": 4.795464774761967e-05, + "loss": 4.0757, + "step": 124928 + }, + { + "epoch": 1.02, + "learning_rate": 4.794626180010915e-05, + "loss": 4.0743, + "step": 125440 + }, + { + "epoch": 1.02, + "learning_rate": 4.793787585259863e-05, + "loss": 4.0586, + "step": 125952 + }, + { + "epoch": 1.02, + "learning_rate": 4.792948990508811e-05, + "loss": 4.0699, + "step": 126464 + }, + { + "epoch": 1.02, + "learning_rate": 4.792110395757759e-05, + "loss": 4.0665, + "step": 126976 + }, + { + "epoch": 1.02, + "learning_rate": 4.791271801006707e-05, + "loss": 4.075, + "step": 127488 + }, + { + "epoch": 1.02, + "learning_rate": 4.790433206255655e-05, + "loss": 4.0663, + "step": 128000 + }, + { + "epoch": 1.02, + "learning_rate": 4.789594611504603e-05, + "loss": 4.0667, + "step": 128512 + }, + { + "epoch": 1.02, + "learning_rate": 4.788757654633924e-05, + "loss": 4.0638, + "step": 129024 + }, + { + "epoch": 1.02, + "learning_rate": 4.787919059882872e-05, + "loss": 4.0699, + "step": 129536 + }, + { + "epoch": 1.02, + "learning_rate": 4.7870821030121935e-05, + "loss": 4.0456, + "step": 130048 + }, + { + "epoch": 1.02, + "learning_rate": 4.7862435082611415e-05, + "loss": 4.0516, + "step": 130560 + }, + { + "epoch": 1.02, + "learning_rate": 4.7854049135100895e-05, + "loss": 4.0574, + "step": 131072 + }, + { + "epoch": 1.02, + "learning_rate": 4.7845663187590375e-05, + "loss": 4.0536, + "step": 131584 + }, + { + "epoch": 1.02, + "learning_rate": 4.7837277240079855e-05, + "loss": 4.0487, + "step": 132096 + }, + { + "epoch": 1.02, + "learning_rate": 4.7828891292569335e-05, + "loss": 4.0478, + "step": 132608 + }, + { + "epoch": 1.02, + "learning_rate": 4.7820505345058815e-05, + "loss": 4.0469, + "step": 133120 + }, + { + "epoch": 1.02, + "learning_rate": 4.7812119397548295e-05, + "loss": 4.0532, + "step": 133632 + }, + { + "epoch": 1.02, + "learning_rate": 4.7803749828841504e-05, + "loss": 4.0483, + "step": 134144 + }, + { + "epoch": 1.02, + "learning_rate": 4.7795363881330984e-05, + "loss": 4.0492, + "step": 134656 + }, + { + "epoch": 1.02, + "learning_rate": 4.7786977933820464e-05, + "loss": 4.0518, + "step": 135168 + }, + { + "epoch": 1.02, + "learning_rate": 4.7778591986309944e-05, + "loss": 4.0556, + "step": 135680 + }, + { + "epoch": 1.02, + "learning_rate": 4.7770206038799423e-05, + "loss": 4.0519, + "step": 136192 + }, + { + "epoch": 1.02, + "learning_rate": 4.776183647009263e-05, + "loss": 4.0495, + "step": 136704 + }, + { + "epoch": 1.02, + "learning_rate": 4.775345052258212e-05, + "loss": 4.0555, + "step": 137216 + }, + { + "epoch": 1.02, + "learning_rate": 4.77450645750716e-05, + "loss": 4.0551, + "step": 137728 + }, + { + "epoch": 1.02, + "learning_rate": 4.773667862756108e-05, + "loss": 4.0423, + "step": 138240 + }, + { + "epoch": 1.02, + "learning_rate": 4.772829268005055e-05, + "loss": 4.0532, + "step": 138752 + }, + { + "epoch": 1.02, + "learning_rate": 4.771990673254003e-05, + "loss": 4.0402, + "step": 139264 + }, + { + "epoch": 1.02, + "learning_rate": 4.771152078502951e-05, + "loss": 4.0528, + "step": 139776 + }, + { + "epoch": 1.02, + "learning_rate": 4.770313483751899e-05, + "loss": 4.0277, + "step": 140288 + }, + { + "epoch": 1.02, + "learning_rate": 4.76947652688122e-05, + "loss": 4.045, + "step": 140800 + }, + { + "epoch": 1.02, + "learning_rate": 4.768639570010542e-05, + "loss": 4.0278, + "step": 141312 + }, + { + "epoch": 1.02, + "learning_rate": 4.76780097525949e-05, + "loss": 4.0333, + "step": 141824 + }, + { + "epoch": 1.02, + "learning_rate": 4.766962380508437e-05, + "loss": 4.0237, + "step": 142336 + }, + { + "epoch": 1.02, + "learning_rate": 4.766123785757386e-05, + "loss": 4.0533, + "step": 142848 + }, + { + "epoch": 1.02, + "learning_rate": 4.765285191006334e-05, + "loss": 4.0424, + "step": 143360 + }, + { + "epoch": 1.02, + "learning_rate": 4.764446596255282e-05, + "loss": 4.0345, + "step": 143872 + }, + { + "epoch": 1.02, + "learning_rate": 4.76360800150423e-05, + "loss": 4.0288, + "step": 144384 + }, + { + "epoch": 1.02, + "learning_rate": 4.762769406753178e-05, + "loss": 4.0392, + "step": 144896 + }, + { + "epoch": 1.02, + "learning_rate": 4.7619324498824986e-05, + "loss": 4.0425, + "step": 145408 + }, + { + "epoch": 1.02, + "learning_rate": 4.7610938551314466e-05, + "loss": 4.0401, + "step": 145920 + }, + { + "epoch": 1.02, + "learning_rate": 4.7602552603803946e-05, + "loss": 4.0335, + "step": 146432 + }, + { + "epoch": 1.02, + "learning_rate": 4.7594166656293426e-05, + "loss": 4.0358, + "step": 146944 + }, + { + "epoch": 1.02, + "learning_rate": 4.7585797087586635e-05, + "loss": 4.0281, + "step": 147456 + }, + { + "epoch": 1.02, + "learning_rate": 4.7577411140076115e-05, + "loss": 4.0437, + "step": 147968 + }, + { + "epoch": 1.02, + "learning_rate": 4.7569025192565595e-05, + "loss": 4.0239, + "step": 148480 + }, + { + "epoch": 1.02, + "learning_rate": 4.7560639245055075e-05, + "loss": 4.0291, + "step": 148992 + }, + { + "epoch": 1.02, + "learning_rate": 4.755226967634829e-05, + "loss": 4.0274, + "step": 149504 + }, + { + "epoch": 1.02, + "learning_rate": 4.754388372883777e-05, + "loss": 4.0224, + "step": 150016 + }, + { + "epoch": 1.02, + "learning_rate": 4.753551416013098e-05, + "loss": 4.0317, + "step": 150528 + }, + { + "epoch": 1.02, + "learning_rate": 4.752712821262046e-05, + "loss": 4.0243, + "step": 151040 + }, + { + "epoch": 1.02, + "learning_rate": 4.751874226510994e-05, + "loss": 4.029, + "step": 151552 + }, + { + "epoch": 1.02, + "learning_rate": 4.751035631759942e-05, + "loss": 4.025, + "step": 152064 + }, + { + "epoch": 1.02, + "learning_rate": 4.75019703700889e-05, + "loss": 4.0212, + "step": 152576 + }, + { + "epoch": 1.03, + "eval_loss": 4.0242791175842285, + "eval_runtime": 309.0459, + "eval_samples_per_second": 1234.739, + "eval_steps_per_second": 38.587, + "step": 152640 + }, + { + "epoch": 0.0, + "learning_rate": 4.749358442257838e-05, + "loss": 4.0084, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.748519847506786e-05, + "loss": 4.0066, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.747681252755734e-05, + "loss": 4.0256, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.746842658004682e-05, + "loss": 4.0107, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.74600406325363e-05, + "loss": 4.0352, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.745165468502578e-05, + "loss": 4.0031, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.744326873751526e-05, + "loss": 4.0124, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.743488279000474e-05, + "loss": 3.9956, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.7426513221297955e-05, + "loss": 4.0151, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.7418127273787435e-05, + "loss": 4.0088, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.740974132627691e-05, + "loss": 4.0119, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.740135537876639e-05, + "loss": 4.0097, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.7392985810059604e-05, + "loss": 3.9977, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.7384599862549084e-05, + "loss": 4.0036, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.737621391503856e-05, + "loss": 3.9992, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.736782796752804e-05, + "loss": 3.9955, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.735944202001752e-05, + "loss": 3.9959, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.7351056072507e-05, + "loss": 4.0005, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.734267012499648e-05, + "loss": 3.9953, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.733428417748596e-05, + "loss": 4.0182, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.732591460877917e-05, + "loss": 3.9932, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.731752866126865e-05, + "loss": 4.0009, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.730914271375813e-05, + "loss": 3.9991, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.730075676624761e-05, + "loss": 4.0074, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.729238719754082e-05, + "loss": 3.987, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.72840012500303e-05, + "loss": 3.9994, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.727561530251978e-05, + "loss": 3.9897, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.726722935500926e-05, + "loss": 3.9941, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.725884340749874e-05, + "loss": 3.9794, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.725045745998822e-05, + "loss": 3.9842, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.72420715124777e-05, + "loss": 3.9931, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.723370194377091e-05, + "loss": 3.9923, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.72253159962604e-05, + "loss": 3.9931, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.721693004874988e-05, + "loss": 3.9956, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.720854410123936e-05, + "loss": 3.9879, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.720015815372884e-05, + "loss": 3.9903, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.7191788585022046e-05, + "loss": 3.9772, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.7183402637511526e-05, + "loss": 3.9911, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.7175016690001006e-05, + "loss": 3.9725, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.7166630742490486e-05, + "loss": 3.982, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.7158244794979966e-05, + "loss": 3.9796, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.7149858847469446e-05, + "loss": 3.9881, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.714147289995892e-05, + "loss": 3.9789, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.7133103331252135e-05, + "loss": 3.9773, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.7124717383741615e-05, + "loss": 3.9873, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.7116331436231095e-05, + "loss": 3.9818, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.7107945488720575e-05, + "loss": 3.9814, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.709957592001379e-05, + "loss": 3.9655, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.709118997250327e-05, + "loss": 3.9608, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.7082804024992744e-05, + "loss": 3.9779, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.7074418077482224e-05, + "loss": 3.9725, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.706604850877544e-05, + "loss": 3.9722, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.705766256126492e-05, + "loss": 3.9544, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.704927661375439e-05, + "loss": 3.9598, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.704089066624387e-05, + "loss": 3.9588, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.703252109753709e-05, + "loss": 3.9715, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.702413515002657e-05, + "loss": 3.9574, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.701574920251605e-05, + "loss": 3.9701, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.700736325500553e-05, + "loss": 3.969, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.6998993686298745e-05, + "loss": 3.9565, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.699060773878822e-05, + "loss": 3.9598, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.69822217912777e-05, + "loss": 3.9561, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.697383584376718e-05, + "loss": 3.9469, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.696544989625666e-05, + "loss": 3.9573, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.695708032754987e-05, + "loss": 3.9623, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694869438003935e-05, + "loss": 3.9673, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.694030843252883e-05, + "loss": 3.9444, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.6931922485018307e-05, + "loss": 3.9496, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.6923536537507787e-05, + "loss": 3.9479, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.6915166968801e-05, + "loss": 3.9707, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.690678102129048e-05, + "loss": 3.9582, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.689839507377996e-05, + "loss": 3.9606, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.689000912626944e-05, + "loss": 3.9725, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.688162317875892e-05, + "loss": 3.9699, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.68732372312484e-05, + "loss": 3.9659, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.686485128373788e-05, + "loss": 3.9543, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.685646533622736e-05, + "loss": 3.9579, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.68481121463243e-05, + "loss": 3.9537, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.683972619881378e-05, + "loss": 3.9516, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.683134025130326e-05, + "loss": 3.9535, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.682295430379274e-05, + "loss": 3.9539, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.681456835628222e-05, + "loss": 3.9615, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.680618240877171e-05, + "loss": 3.9522, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.6797812840064916e-05, + "loss": 3.9454, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.6789426892554396e-05, + "loss": 3.9385, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.6781040945043876e-05, + "loss": 3.9513, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.6772654997533356e-05, + "loss": 3.9561, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.6764285428826565e-05, + "loss": 3.9441, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.6755899481316045e-05, + "loss": 3.9433, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.6747513533805525e-05, + "loss": 3.9555, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.6739127586295005e-05, + "loss": 3.9365, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.6730758017588214e-05, + "loss": 3.945, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.6722372070077694e-05, + "loss": 3.9438, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.6713986122567174e-05, + "loss": 3.9486, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.670561655386039e-05, + "loss": 3.9493, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.669723060634987e-05, + "loss": 3.9419, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.668884465883935e-05, + "loss": 3.9331, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.668045871132883e-05, + "loss": 3.9458, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.667207276381831e-05, + "loss": 3.9374, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.666368681630779e-05, + "loss": 3.9522, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.665530086879727e-05, + "loss": 3.9428, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.664691492128675e-05, + "loss": 3.9445, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.663854535257996e-05, + "loss": 3.936, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.663015940506944e-05, + "loss": 3.9487, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.662177345755892e-05, + "loss": 3.9215, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.66133875100484e-05, + "loss": 3.9291, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.6605017941341614e-05, + "loss": 3.9343, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.6596631993831094e-05, + "loss": 3.9331, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.6588246046320574e-05, + "loss": 3.9246, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.6579860098810054e-05, + "loss": 3.9283, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.657149053010326e-05, + "loss": 3.9258, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.656310458259274e-05, + "loss": 3.935, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.655471863508222e-05, + "loss": 3.9295, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.65463326875717e-05, + "loss": 3.926, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.653796311886491e-05, + "loss": 3.937, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.652957717135439e-05, + "loss": 3.939, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.652119122384387e-05, + "loss": 3.9377, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.651280527633335e-05, + "loss": 3.9274, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.650443570762657e-05, + "loss": 3.9392, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.649604976011605e-05, + "loss": 3.9351, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.648766381260553e-05, + "loss": 3.9269, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.6479277865095e-05, + "loss": 3.9398, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.647090829638822e-05, + "loss": 3.9207, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.64625223488777e-05, + "loss": 3.9363, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.645413640136718e-05, + "loss": 3.9146, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.644575045385665e-05, + "loss": 3.9296, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.6437380885149866e-05, + "loss": 3.9133, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.6428994937639346e-05, + "loss": 3.9187, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.642060899012882e-05, + "loss": 3.9129, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.6412223042618306e-05, + "loss": 3.9371, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.640385347391152e-05, + "loss": 3.9272, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.6395467526401e-05, + "loss": 3.9257, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.6387081578890475e-05, + "loss": 3.917, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.6378695631379955e-05, + "loss": 3.9251, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.637032606267317e-05, + "loss": 3.9353, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.636194011516265e-05, + "loss": 3.926, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.6353554167652124e-05, + "loss": 3.9213, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.6345168220141604e-05, + "loss": 3.9314, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.633679865143482e-05, + "loss": 3.9211, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.632841270392429e-05, + "loss": 3.9263, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.632002675641377e-05, + "loss": 3.916, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.631164080890326e-05, + "loss": 3.9222, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.6303271240196475e-05, + "loss": 3.9173, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.629488529268595e-05, + "loss": 3.9163, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.628649934517543e-05, + "loss": 3.9179, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.627811339766491e-05, + "loss": 3.9233, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.626972745015439e-05, + "loss": 3.9161, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.62613578814476e-05, + "loss": 3.9174, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.625297193393708e-05, + "loss": 3.9155, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 3.9504966735839844, + "eval_runtime": 309.784, + "eval_samples_per_second": 1231.797, + "eval_steps_per_second": 38.495, + "step": 228960 + }, + { + "epoch": 1.0, + "learning_rate": 4.624458598642656e-05, + "loss": 3.9086, + "step": 229376 + }, + { + "epoch": 1.0, + "learning_rate": 4.623620003891604e-05, + "loss": 3.9037, + "step": 229888 + }, + { + "epoch": 1.0, + "learning_rate": 4.6227830470209246e-05, + "loss": 3.919, + "step": 230400 + }, + { + "epoch": 1.0, + "learning_rate": 4.6219444522698726e-05, + "loss": 3.9051, + "step": 230912 + }, + { + "epoch": 1.0, + "learning_rate": 4.621105857518821e-05, + "loss": 3.9327, + "step": 231424 + }, + { + "epoch": 1.0, + "learning_rate": 4.620267262767769e-05, + "loss": 3.8971, + "step": 231936 + }, + { + "epoch": 1.0, + "learning_rate": 4.61943030589709e-05, + "loss": 3.9087, + "step": 232448 + }, + { + "epoch": 1.0, + "learning_rate": 4.618591711146038e-05, + "loss": 3.8918, + "step": 232960 + }, + { + "epoch": 1.0, + "learning_rate": 4.617753116394986e-05, + "loss": 3.9105, + "step": 233472 + }, + { + "epoch": 1.0, + "learning_rate": 4.616914521643934e-05, + "loss": 3.9094, + "step": 233984 + }, + { + "epoch": 1.0, + "learning_rate": 4.616077564773255e-05, + "loss": 3.9049, + "step": 234496 + }, + { + "epoch": 1.0, + "learning_rate": 4.615238970022203e-05, + "loss": 3.9078, + "step": 235008 + }, + { + "epoch": 1.0, + "learning_rate": 4.614402013151524e-05, + "loss": 3.8962, + "step": 235520 + }, + { + "epoch": 1.0, + "learning_rate": 4.613563418400472e-05, + "loss": 3.9046, + "step": 236032 + }, + { + "epoch": 1.0, + "learning_rate": 4.61272482364942e-05, + "loss": 3.8991, + "step": 236544 + }, + { + "epoch": 1.0, + "learning_rate": 4.611886228898368e-05, + "loss": 3.8985, + "step": 237056 + }, + { + "epoch": 1.0, + "learning_rate": 4.611047634147316e-05, + "loss": 3.8961, + "step": 237568 + }, + { + "epoch": 1.0, + "learning_rate": 4.610209039396265e-05, + "loss": 3.8987, + "step": 238080 + }, + { + "epoch": 1.0, + "learning_rate": 4.609370444645213e-05, + "loss": 3.8987, + "step": 238592 + }, + { + "epoch": 1.0, + "learning_rate": 4.6085318498941607e-05, + "loss": 3.9156, + "step": 239104 + }, + { + "epoch": 1.0, + "learning_rate": 4.6076948930234816e-05, + "loss": 3.8944, + "step": 239616 + }, + { + "epoch": 1.0, + "learning_rate": 4.6068562982724296e-05, + "loss": 3.9007, + "step": 240128 + }, + { + "epoch": 1.0, + "learning_rate": 4.6060177035213776e-05, + "loss": 3.8994, + "step": 240640 + }, + { + "epoch": 1.0, + "learning_rate": 4.6051791087703256e-05, + "loss": 3.9095, + "step": 241152 + }, + { + "epoch": 1.0, + "learning_rate": 4.6043421518996465e-05, + "loss": 3.8879, + "step": 241664 + }, + { + "epoch": 1.0, + "learning_rate": 4.6035035571485945e-05, + "loss": 3.9029, + "step": 242176 + }, + { + "epoch": 1.0, + "learning_rate": 4.6026649623975425e-05, + "loss": 3.8922, + "step": 242688 + }, + { + "epoch": 1.0, + "learning_rate": 4.6018263676464904e-05, + "loss": 3.8932, + "step": 243200 + }, + { + "epoch": 1.0, + "learning_rate": 4.6009894107758114e-05, + "loss": 3.8818, + "step": 243712 + }, + { + "epoch": 1.01, + "learning_rate": 4.60015081602476e-05, + "loss": 3.8937, + "step": 244224 + }, + { + "epoch": 1.01, + "learning_rate": 4.599312221273708e-05, + "loss": 3.8941, + "step": 244736 + }, + { + "epoch": 1.01, + "learning_rate": 4.598473626522656e-05, + "loss": 3.898, + "step": 245248 + }, + { + "epoch": 1.01, + "learning_rate": 4.597636669651977e-05, + "loss": 3.896, + "step": 245760 + }, + { + "epoch": 1.01, + "learning_rate": 4.596798074900925e-05, + "loss": 3.9022, + "step": 246272 + }, + { + "epoch": 1.01, + "learning_rate": 4.595959480149873e-05, + "loss": 3.8902, + "step": 246784 + }, + { + "epoch": 1.01, + "learning_rate": 4.595120885398821e-05, + "loss": 3.8973, + "step": 247296 + }, + { + "epoch": 1.01, + "learning_rate": 4.594283928528142e-05, + "loss": 3.8847, + "step": 247808 + }, + { + "epoch": 1.01, + "learning_rate": 4.59344533377709e-05, + "loss": 3.8939, + "step": 248320 + }, + { + "epoch": 1.01, + "learning_rate": 4.592606739026038e-05, + "loss": 3.8779, + "step": 248832 + }, + { + "epoch": 1.01, + "learning_rate": 4.591768144274986e-05, + "loss": 3.8889, + "step": 249344 + }, + { + "epoch": 1.01, + "learning_rate": 4.590931187404307e-05, + "loss": 3.8875, + "step": 249856 + }, + { + "epoch": 1.01, + "learning_rate": 4.5900925926532554e-05, + "loss": 3.8966, + "step": 250368 + }, + { + "epoch": 1.01, + "learning_rate": 4.5892539979022034e-05, + "loss": 3.8866, + "step": 250880 + }, + { + "epoch": 1.01, + "learning_rate": 4.5884154031511514e-05, + "loss": 3.8867, + "step": 251392 + }, + { + "epoch": 1.01, + "learning_rate": 4.587578446280472e-05, + "loss": 3.8917, + "step": 251904 + }, + { + "epoch": 1.01, + "learning_rate": 4.58673985152942e-05, + "loss": 3.8901, + "step": 252416 + }, + { + "epoch": 1.01, + "learning_rate": 4.585901256778368e-05, + "loss": 3.8905, + "step": 252928 + }, + { + "epoch": 1.01, + "learning_rate": 4.585062662027316e-05, + "loss": 3.8777, + "step": 253440 + }, + { + "epoch": 1.01, + "learning_rate": 4.584225705156637e-05, + "loss": 3.8638, + "step": 253952 + }, + { + "epoch": 1.01, + "learning_rate": 4.583387110405585e-05, + "loss": 3.8885, + "step": 254464 + }, + { + "epoch": 1.01, + "learning_rate": 4.582548515654533e-05, + "loss": 3.8809, + "step": 254976 + }, + { + "epoch": 1.01, + "learning_rate": 4.581709920903481e-05, + "loss": 3.8788, + "step": 255488 + }, + { + "epoch": 1.01, + "learning_rate": 4.580872964032802e-05, + "loss": 3.8702, + "step": 256000 + }, + { + "epoch": 1.01, + "learning_rate": 4.580034369281751e-05, + "loss": 3.8684, + "step": 256512 + }, + { + "epoch": 1.01, + "learning_rate": 4.579195774530699e-05, + "loss": 3.8649, + "step": 257024 + }, + { + "epoch": 1.01, + "learning_rate": 4.57835881766002e-05, + "loss": 3.8829, + "step": 257536 + }, + { + "epoch": 1.01, + "learning_rate": 4.577520222908968e-05, + "loss": 3.8694, + "step": 258048 + }, + { + "epoch": 1.01, + "learning_rate": 4.576681628157916e-05, + "loss": 3.8769, + "step": 258560 + }, + { + "epoch": 1.01, + "learning_rate": 4.5758430334068637e-05, + "loss": 3.8845, + "step": 259072 + }, + { + "epoch": 1.01, + "learning_rate": 4.5750044386558117e-05, + "loss": 3.8687, + "step": 259584 + }, + { + "epoch": 1.01, + "learning_rate": 4.5741658439047596e-05, + "loss": 3.8712, + "step": 260096 + }, + { + "epoch": 1.01, + "learning_rate": 4.5733272491537076e-05, + "loss": 3.8741, + "step": 260608 + }, + { + "epoch": 1.01, + "learning_rate": 4.572488654402655e-05, + "loss": 3.855, + "step": 261120 + }, + { + "epoch": 1.01, + "learning_rate": 4.5716516975319765e-05, + "loss": 3.8699, + "step": 261632 + }, + { + "epoch": 1.01, + "learning_rate": 4.5708131027809245e-05, + "loss": 3.8787, + "step": 262144 + }, + { + "epoch": 1.01, + "learning_rate": 4.5699745080298725e-05, + "loss": 3.8767, + "step": 262656 + }, + { + "epoch": 1.01, + "learning_rate": 4.5691359132788205e-05, + "loss": 3.8608, + "step": 263168 + }, + { + "epoch": 1.01, + "learning_rate": 4.568298956408142e-05, + "loss": 3.8645, + "step": 263680 + }, + { + "epoch": 1.01, + "learning_rate": 4.56746036165709e-05, + "loss": 3.8614, + "step": 264192 + }, + { + "epoch": 1.01, + "learning_rate": 4.5666217669060374e-05, + "loss": 3.8786, + "step": 264704 + }, + { + "epoch": 1.01, + "learning_rate": 4.5657831721549854e-05, + "loss": 3.8745, + "step": 265216 + }, + { + "epoch": 1.01, + "learning_rate": 4.564946215284307e-05, + "loss": 3.8772, + "step": 265728 + }, + { + "epoch": 1.01, + "learning_rate": 4.564107620533255e-05, + "loss": 3.8854, + "step": 266240 + }, + { + "epoch": 1.01, + "learning_rate": 4.563269025782202e-05, + "loss": 3.8852, + "step": 266752 + }, + { + "epoch": 1.01, + "learning_rate": 4.56243043103115e-05, + "loss": 3.8852, + "step": 267264 + }, + { + "epoch": 1.01, + "learning_rate": 4.561593474160472e-05, + "loss": 3.8654, + "step": 267776 + }, + { + "epoch": 1.01, + "learning_rate": 4.56075487940942e-05, + "loss": 3.8749, + "step": 268288 + }, + { + "epoch": 1.01, + "learning_rate": 4.559916284658368e-05, + "loss": 3.8737, + "step": 268800 + }, + { + "epoch": 1.01, + "learning_rate": 4.559077689907316e-05, + "loss": 3.8668, + "step": 269312 + }, + { + "epoch": 1.01, + "learning_rate": 4.5582407330366375e-05, + "loss": 3.8742, + "step": 269824 + }, + { + "epoch": 1.01, + "learning_rate": 4.557402138285585e-05, + "loss": 3.869, + "step": 270336 + }, + { + "epoch": 1.01, + "learning_rate": 4.556563543534533e-05, + "loss": 3.8763, + "step": 270848 + }, + { + "epoch": 1.01, + "learning_rate": 4.555724948783481e-05, + "loss": 3.8705, + "step": 271360 + }, + { + "epoch": 1.01, + "learning_rate": 4.5548879919128024e-05, + "loss": 3.8544, + "step": 271872 + }, + { + "epoch": 1.01, + "learning_rate": 4.55404939716175e-05, + "loss": 3.8583, + "step": 272384 + }, + { + "epoch": 1.01, + "learning_rate": 4.553210802410698e-05, + "loss": 3.8683, + "step": 272896 + }, + { + "epoch": 1.01, + "learning_rate": 4.552372207659646e-05, + "loss": 3.8729, + "step": 273408 + }, + { + "epoch": 1.01, + "learning_rate": 4.5515352507889666e-05, + "loss": 3.8637, + "step": 273920 + }, + { + "epoch": 1.01, + "learning_rate": 4.550696656037915e-05, + "loss": 3.8598, + "step": 274432 + }, + { + "epoch": 1.02, + "learning_rate": 4.549858061286863e-05, + "loss": 3.8716, + "step": 274944 + }, + { + "epoch": 1.02, + "learning_rate": 4.549019466535811e-05, + "loss": 3.8572, + "step": 275456 + }, + { + "epoch": 1.02, + "learning_rate": 4.548182509665132e-05, + "loss": 3.8592, + "step": 275968 + }, + { + "epoch": 1.02, + "learning_rate": 4.54734391491408e-05, + "loss": 3.8647, + "step": 276480 + }, + { + "epoch": 1.02, + "learning_rate": 4.546505320163028e-05, + "loss": 3.8701, + "step": 276992 + }, + { + "epoch": 1.02, + "learning_rate": 4.54566836329235e-05, + "loss": 3.8711, + "step": 277504 + }, + { + "epoch": 1.02, + "learning_rate": 4.544829768541297e-05, + "loss": 3.8615, + "step": 278016 + }, + { + "epoch": 1.02, + "learning_rate": 4.543991173790245e-05, + "loss": 3.8492, + "step": 278528 + }, + { + "epoch": 1.02, + "learning_rate": 4.543152579039193e-05, + "loss": 3.8687, + "step": 279040 + }, + { + "epoch": 1.02, + "learning_rate": 4.542313984288141e-05, + "loss": 3.855, + "step": 279552 + }, + { + "epoch": 1.02, + "learning_rate": 4.541475389537089e-05, + "loss": 3.8746, + "step": 280064 + }, + { + "epoch": 1.02, + "learning_rate": 4.540636794786037e-05, + "loss": 3.8662, + "step": 280576 + }, + { + "epoch": 1.02, + "learning_rate": 4.539798200034985e-05, + "loss": 3.8622, + "step": 281088 + }, + { + "epoch": 1.02, + "learning_rate": 4.5389612431643066e-05, + "loss": 3.8578, + "step": 281600 + }, + { + "epoch": 1.02, + "learning_rate": 4.5381226484132546e-05, + "loss": 3.8698, + "step": 282112 + }, + { + "epoch": 1.02, + "learning_rate": 4.5372856915425755e-05, + "loss": 3.8451, + "step": 282624 + }, + { + "epoch": 1.02, + "learning_rate": 4.5364470967915235e-05, + "loss": 3.8527, + "step": 283136 + }, + { + "epoch": 1.02, + "learning_rate": 4.5356085020404715e-05, + "loss": 3.8511, + "step": 283648 + }, + { + "epoch": 1.02, + "learning_rate": 4.5347699072894195e-05, + "loss": 3.8566, + "step": 284160 + }, + { + "epoch": 1.02, + "learning_rate": 4.5339313125383675e-05, + "loss": 3.8466, + "step": 284672 + }, + { + "epoch": 1.02, + "learning_rate": 4.5330927177873155e-05, + "loss": 3.8527, + "step": 285184 + }, + { + "epoch": 1.02, + "learning_rate": 4.5322541230362635e-05, + "loss": 3.8519, + "step": 285696 + }, + { + "epoch": 1.02, + "learning_rate": 4.5314155282852115e-05, + "loss": 3.8502, + "step": 286208 + }, + { + "epoch": 1.02, + "learning_rate": 4.5305785714145324e-05, + "loss": 3.8561, + "step": 286720 + }, + { + "epoch": 1.02, + "learning_rate": 4.5297399766634804e-05, + "loss": 3.8462, + "step": 287232 + }, + { + "epoch": 1.02, + "learning_rate": 4.5289013819124284e-05, + "loss": 3.8638, + "step": 287744 + }, + { + "epoch": 1.02, + "learning_rate": 4.528062787161377e-05, + "loss": 3.8607, + "step": 288256 + }, + { + "epoch": 1.02, + "learning_rate": 4.527225830290698e-05, + "loss": 3.8612, + "step": 288768 + }, + { + "epoch": 1.02, + "learning_rate": 4.526387235539646e-05, + "loss": 3.8518, + "step": 289280 + }, + { + "epoch": 1.02, + "learning_rate": 4.525548640788594e-05, + "loss": 3.8616, + "step": 289792 + }, + { + "epoch": 1.02, + "learning_rate": 4.524710046037542e-05, + "loss": 3.8612, + "step": 290304 + }, + { + "epoch": 1.02, + "learning_rate": 4.523873089166863e-05, + "loss": 3.8489, + "step": 290816 + }, + { + "epoch": 1.02, + "learning_rate": 4.523034494415811e-05, + "loss": 3.8627, + "step": 291328 + }, + { + "epoch": 1.02, + "learning_rate": 4.522195899664759e-05, + "loss": 3.8463, + "step": 291840 + }, + { + "epoch": 1.02, + "learning_rate": 4.521357304913707e-05, + "loss": 3.8591, + "step": 292352 + }, + { + "epoch": 1.02, + "learning_rate": 4.520520348043028e-05, + "loss": 3.8422, + "step": 292864 + }, + { + "epoch": 1.02, + "learning_rate": 4.519681753291976e-05, + "loss": 3.8539, + "step": 293376 + }, + { + "epoch": 1.02, + "learning_rate": 4.518843158540924e-05, + "loss": 3.8374, + "step": 293888 + }, + { + "epoch": 1.02, + "learning_rate": 4.5180045637898725e-05, + "loss": 3.8452, + "step": 294400 + }, + { + "epoch": 1.02, + "learning_rate": 4.5171676069191934e-05, + "loss": 3.8414, + "step": 294912 + }, + { + "epoch": 1.02, + "learning_rate": 4.5163290121681414e-05, + "loss": 3.8577, + "step": 295424 + }, + { + "epoch": 1.02, + "learning_rate": 4.5154904174170894e-05, + "loss": 3.849, + "step": 295936 + }, + { + "epoch": 1.02, + "learning_rate": 4.5146518226660373e-05, + "loss": 3.8557, + "step": 296448 + }, + { + "epoch": 1.02, + "learning_rate": 4.513814865795358e-05, + "loss": 3.8431, + "step": 296960 + }, + { + "epoch": 1.02, + "learning_rate": 4.512976271044306e-05, + "loss": 3.8517, + "step": 297472 + }, + { + "epoch": 1.02, + "learning_rate": 4.512137676293254e-05, + "loss": 3.8594, + "step": 297984 + }, + { + "epoch": 1.02, + "learning_rate": 4.511299081542202e-05, + "loss": 3.8531, + "step": 298496 + }, + { + "epoch": 1.02, + "learning_rate": 4.510462124671523e-05, + "loss": 3.8491, + "step": 299008 + }, + { + "epoch": 1.02, + "learning_rate": 4.509623529920471e-05, + "loss": 3.8558, + "step": 299520 + }, + { + "epoch": 1.02, + "learning_rate": 4.508784935169419e-05, + "loss": 3.8485, + "step": 300032 + }, + { + "epoch": 1.02, + "learning_rate": 4.507946340418368e-05, + "loss": 3.8589, + "step": 300544 + }, + { + "epoch": 1.02, + "learning_rate": 4.507109383547689e-05, + "loss": 3.839, + "step": 301056 + }, + { + "epoch": 1.02, + "learning_rate": 4.506270788796637e-05, + "loss": 3.8517, + "step": 301568 + }, + { + "epoch": 1.02, + "learning_rate": 4.505432194045585e-05, + "loss": 3.8434, + "step": 302080 + }, + { + "epoch": 1.02, + "learning_rate": 4.504593599294533e-05, + "loss": 3.8433, + "step": 302592 + }, + { + "epoch": 1.02, + "learning_rate": 4.5037566424238536e-05, + "loss": 3.85, + "step": 303104 + }, + { + "epoch": 1.02, + "learning_rate": 4.5029180476728016e-05, + "loss": 3.8475, + "step": 303616 + }, + { + "epoch": 1.02, + "learning_rate": 4.5020794529217496e-05, + "loss": 3.846, + "step": 304128 + }, + { + "epoch": 1.02, + "learning_rate": 4.5012408581706976e-05, + "loss": 3.8419, + "step": 304640 + }, + { + "epoch": 1.02, + "learning_rate": 4.5004039013000185e-05, + "loss": 3.8486, + "step": 305152 + }, + { + "epoch": 1.03, + "eval_loss": 3.909996747970581, + "eval_runtime": 309.6063, + "eval_samples_per_second": 1232.504, + "eval_steps_per_second": 38.517, + "step": 305280 + }, + { + "epoch": 0.0, + "learning_rate": 4.4995653065489665e-05, + "loss": 3.8344, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.4987267117979145e-05, + "loss": 3.8315, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.497888117046863e-05, + "loss": 3.8476, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.4970495222958105e-05, + "loss": 3.8364, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.4962109275447585e-05, + "loss": 3.8607, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.4953723327937065e-05, + "loss": 3.834, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.4945337380426545e-05, + "loss": 3.834, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.4936951432916025e-05, + "loss": 3.8216, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.4928581864209234e-05, + "loss": 3.8393, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.4920195916698714e-05, + "loss": 3.8424, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.4911809969188194e-05, + "loss": 3.8336, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.4903424021677674e-05, + "loss": 3.8359, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.489507083177462e-05, + "loss": 3.8275, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.48866848842641e-05, + "loss": 3.8348, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.487829893675358e-05, + "loss": 3.8314, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.486991298924306e-05, + "loss": 3.8272, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.486152704173254e-05, + "loss": 3.8262, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.485314109422202e-05, + "loss": 3.8337, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.48447551467115e-05, + "loss": 3.8284, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.483636919920098e-05, + "loss": 3.8432, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.4828016009297924e-05, + "loss": 3.831, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.48196300617874e-05, + "loss": 3.835, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.481124411427688e-05, + "loss": 3.8323, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.480285816676636e-05, + "loss": 3.8401, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.4794472219255837e-05, + "loss": 3.8206, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.478608627174532e-05, + "loss": 3.8341, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.47777003242348e-05, + "loss": 3.8274, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.476933075552801e-05, + "loss": 3.8242, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.476094480801749e-05, + "loss": 3.816, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.475255886050697e-05, + "loss": 3.8235, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.474417291299645e-05, + "loss": 3.8315, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.473580334428966e-05, + "loss": 3.8311, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.472741739677914e-05, + "loss": 3.8321, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.471903144926862e-05, + "loss": 3.8332, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.47106455017581e-05, + "loss": 3.8249, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.470227593305131e-05, + "loss": 3.8305, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.469388998554079e-05, + "loss": 3.8234, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.468550403803028e-05, + "loss": 3.8262, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.467711809051976e-05, + "loss": 3.8154, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.4668748521812966e-05, + "loss": 3.8246, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.4660362574302446e-05, + "loss": 3.8213, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.4651976626791926e-05, + "loss": 3.8294, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.4643590679281406e-05, + "loss": 3.8224, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.4635221110574615e-05, + "loss": 3.8217, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.4626835163064095e-05, + "loss": 3.8323, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.4618449215553575e-05, + "loss": 3.8233, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.4610063268043055e-05, + "loss": 3.8232, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.4601693699336264e-05, + "loss": 3.8145, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.4593307751825744e-05, + "loss": 3.7998, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.4584921804315224e-05, + "loss": 3.8252, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.457653585680471e-05, + "loss": 3.8183, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.456816628809792e-05, + "loss": 3.8173, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.455979671939113e-05, + "loss": 3.8017, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.455141077188061e-05, + "loss": 3.8081, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.454302482437009e-05, + "loss": 3.7999, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.453463887685957e-05, + "loss": 3.8214, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.452625292934905e-05, + "loss": 3.8077, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.451786698183853e-05, + "loss": 3.8109, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.450948103432801e-05, + "loss": 3.8225, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.450111146562122e-05, + "loss": 3.806, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.4492741896914433e-05, + "loss": 3.8098, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.4484355949403913e-05, + "loss": 3.8149, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.4475970001893393e-05, + "loss": 3.7934, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.446758405438287e-05, + "loss": 3.81, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.445919810687235e-05, + "loss": 3.8118, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.445081215936183e-05, + "loss": 3.8177, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.444242621185131e-05, + "loss": 3.7981, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.443404026434079e-05, + "loss": 3.8046, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.4425670695634e-05, + "loss": 3.7966, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.441728474812348e-05, + "loss": 3.8208, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.440889880061296e-05, + "loss": 3.8129, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.440051285310244e-05, + "loss": 3.811, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.439214328439565e-05, + "loss": 3.8261, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.438375733688513e-05, + "loss": 3.8186, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.437537138937462e-05, + "loss": 3.8328, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.43669854418641e-05, + "loss": 3.8067, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.435861587315731e-05, + "loss": 3.8113, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.435022992564679e-05, + "loss": 3.8124, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.434184397813627e-05, + "loss": 3.8034, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.4333474409429476e-05, + "loss": 3.8161, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.4325088461918956e-05, + "loss": 3.8086, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.4316702514408436e-05, + "loss": 3.8165, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.4308316566897916e-05, + "loss": 3.8082, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.4299930619387396e-05, + "loss": 3.7966, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.4291544671876876e-05, + "loss": 3.8091, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.4283158724366356e-05, + "loss": 3.7997, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.427478915565957e-05, + "loss": 3.815, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.426640320814905e-05, + "loss": 3.806, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.425801726063853e-05, + "loss": 3.7992, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.4249631313128005e-05, + "loss": 3.8116, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.4241245365617485e-05, + "loss": 3.8046, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.4232859418106965e-05, + "loss": 3.7964, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.4224473470596445e-05, + "loss": 3.8041, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.4216087523085925e-05, + "loss": 3.8144, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.4207717954379134e-05, + "loss": 3.8102, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.4199332006868614e-05, + "loss": 3.8082, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.4190946059358094e-05, + "loss": 3.7894, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.4182560111847573e-05, + "loss": 3.8077, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.4174174164337053e-05, + "loss": 3.7985, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.416578821682654e-05, + "loss": 3.8131, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.415740226931602e-05, + "loss": 3.8111, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.41490163218055e-05, + "loss": 3.8047, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.414064675309871e-05, + "loss": 3.7996, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.413227718439192e-05, + "loss": 3.8143, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.41238912368814e-05, + "loss": 3.7832, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.411550528937088e-05, + "loss": 3.7967, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.410711934186036e-05, + "loss": 3.791, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.409873339434984e-05, + "loss": 3.8063, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.409034744683932e-05, + "loss": 3.7847, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.40819614993288e-05, + "loss": 3.7934, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.407357555181828e-05, + "loss": 3.7969, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.4065205983111494e-05, + "loss": 3.7948, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.4056820035600974e-05, + "loss": 3.7973, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.4048434088090454e-05, + "loss": 3.794, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.4040048140579934e-05, + "loss": 3.8062, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.403167857187314e-05, + "loss": 3.8045, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.402329262436262e-05, + "loss": 3.8028, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.401492305565583e-05, + "loss": 3.7931, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.400653710814531e-05, + "loss": 3.8062, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.399815116063479e-05, + "loss": 3.8005, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.398976521312427e-05, + "loss": 3.7912, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.398137926561375e-05, + "loss": 3.8083, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.397299331810323e-05, + "loss": 3.7895, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.396462374939645e-05, + "loss": 3.8009, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.395623780188593e-05, + "loss": 3.7878, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.394785185437541e-05, + "loss": 3.7979, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.393946590686489e-05, + "loss": 3.785, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.393107995935437e-05, + "loss": 3.7868, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.392269401184384e-05, + "loss": 3.7902, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.3914324443137056e-05, + "loss": 3.8016, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.3905938495626536e-05, + "loss": 3.7955, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.3897552548116016e-05, + "loss": 3.7984, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.388916660060549e-05, + "loss": 3.7854, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.388078065309497e-05, + "loss": 3.7989, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.387239470558445e-05, + "loss": 3.8038, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.386400875807393e-05, + "loss": 3.7987, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.3855639189367145e-05, + "loss": 3.7943, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.3847253241856625e-05, + "loss": 3.8005, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.3838867294346105e-05, + "loss": 3.7931, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.3830481346835585e-05, + "loss": 3.802, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.3822111778128794e-05, + "loss": 3.7871, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.3813725830618274e-05, + "loss": 3.796, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.3805339883107754e-05, + "loss": 3.7909, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.3796953935597234e-05, + "loss": 3.7906, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.378858436689044e-05, + "loss": 3.7946, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.378019841937992e-05, + "loss": 3.7928, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.377182885067313e-05, + "loss": 3.7946, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.376344290316262e-05, + "loss": 3.7831, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.37550569556521e-05, + "loss": 3.798, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 3.885251045227051, + "eval_runtime": 305.6198, + "eval_samples_per_second": 1248.581, + "eval_steps_per_second": 39.019, + "step": 381600 + }, + { + "epoch": 1.0, + "learning_rate": 4.374667100814158e-05, + "loss": 3.7864, + "step": 381952 + }, + { + "epoch": 1.0, + "learning_rate": 4.373828506063106e-05, + "loss": 3.7763, + "step": 382464 + }, + { + "epoch": 1.0, + "learning_rate": 4.372989911312054e-05, + "loss": 3.7951, + "step": 382976 + }, + { + "epoch": 1.0, + "learning_rate": 4.372151316561002e-05, + "loss": 3.7843, + "step": 383488 + }, + { + "epoch": 1.0, + "learning_rate": 4.371314359690323e-05, + "loss": 3.8045, + "step": 384000 + }, + { + "epoch": 1.0, + "learning_rate": 4.370475764939271e-05, + "loss": 3.7843, + "step": 384512 + }, + { + "epoch": 1.0, + "learning_rate": 4.369638808068592e-05, + "loss": 3.7743, + "step": 385024 + }, + { + "epoch": 1.0, + "learning_rate": 4.36880021331754e-05, + "loss": 3.7755, + "step": 385536 + }, + { + "epoch": 1.0, + "learning_rate": 4.367961618566488e-05, + "loss": 3.7812, + "step": 386048 + }, + { + "epoch": 1.0, + "learning_rate": 4.367123023815436e-05, + "loss": 3.7906, + "step": 386560 + }, + { + "epoch": 1.0, + "learning_rate": 4.366284429064384e-05, + "loss": 3.781, + "step": 387072 + }, + { + "epoch": 1.0, + "learning_rate": 4.365445834313332e-05, + "loss": 3.7858, + "step": 387584 + }, + { + "epoch": 1.0, + "learning_rate": 4.364608877442653e-05, + "loss": 3.7768, + "step": 388096 + }, + { + "epoch": 1.0, + "learning_rate": 4.363770282691601e-05, + "loss": 3.7785, + "step": 388608 + }, + { + "epoch": 1.0, + "learning_rate": 4.362931687940549e-05, + "loss": 3.7832, + "step": 389120 + }, + { + "epoch": 1.0, + "learning_rate": 4.362093093189497e-05, + "loss": 3.774, + "step": 389632 + }, + { + "epoch": 1.0, + "learning_rate": 4.361254498438445e-05, + "loss": 3.7733, + "step": 390144 + }, + { + "epoch": 1.0, + "learning_rate": 4.360415903687393e-05, + "loss": 3.7815, + "step": 390656 + }, + { + "epoch": 1.0, + "learning_rate": 4.359577308936341e-05, + "loss": 3.7798, + "step": 391168 + }, + { + "epoch": 1.0, + "learning_rate": 4.358738714185289e-05, + "loss": 3.791, + "step": 391680 + }, + { + "epoch": 1.0, + "learning_rate": 4.357903395194983e-05, + "loss": 3.7823, + "step": 392192 + }, + { + "epoch": 1.0, + "learning_rate": 4.357064800443931e-05, + "loss": 3.7838, + "step": 392704 + }, + { + "epoch": 1.0, + "learning_rate": 4.356226205692879e-05, + "loss": 3.7806, + "step": 393216 + }, + { + "epoch": 1.0, + "learning_rate": 4.355387610941827e-05, + "loss": 3.7854, + "step": 393728 + }, + { + "epoch": 1.0, + "learning_rate": 4.354549016190776e-05, + "loss": 3.7689, + "step": 394240 + }, + { + "epoch": 1.0, + "learning_rate": 4.353710421439724e-05, + "loss": 3.7875, + "step": 394752 + }, + { + "epoch": 1.0, + "learning_rate": 4.352871826688672e-05, + "loss": 3.7719, + "step": 395264 + }, + { + "epoch": 1.0, + "learning_rate": 4.35203323193762e-05, + "loss": 3.7735, + "step": 395776 + }, + { + "epoch": 1.0, + "learning_rate": 4.3511962750669406e-05, + "loss": 3.7684, + "step": 396288 + }, + { + "epoch": 1.0, + "learning_rate": 4.3503576803158886e-05, + "loss": 3.7716, + "step": 396800 + }, + { + "epoch": 1.01, + "learning_rate": 4.3495190855648366e-05, + "loss": 3.7814, + "step": 397312 + }, + { + "epoch": 1.01, + "learning_rate": 4.3486821286941575e-05, + "loss": 3.7766, + "step": 397824 + }, + { + "epoch": 1.01, + "learning_rate": 4.3478435339431055e-05, + "loss": 3.7855, + "step": 398336 + }, + { + "epoch": 1.01, + "learning_rate": 4.3470049391920535e-05, + "loss": 3.7858, + "step": 398848 + }, + { + "epoch": 1.01, + "learning_rate": 4.3461663444410015e-05, + "loss": 3.7734, + "step": 399360 + }, + { + "epoch": 1.01, + "learning_rate": 4.3453277496899495e-05, + "loss": 3.7783, + "step": 399872 + }, + { + "epoch": 1.01, + "learning_rate": 4.344490792819271e-05, + "loss": 3.7748, + "step": 400384 + }, + { + "epoch": 1.01, + "learning_rate": 4.343652198068219e-05, + "loss": 3.7733, + "step": 400896 + }, + { + "epoch": 1.01, + "learning_rate": 4.342813603317167e-05, + "loss": 3.7689, + "step": 401408 + }, + { + "epoch": 1.01, + "learning_rate": 4.341975008566115e-05, + "loss": 3.7722, + "step": 401920 + }, + { + "epoch": 1.01, + "learning_rate": 4.3411364138150624e-05, + "loss": 3.7757, + "step": 402432 + }, + { + "epoch": 1.01, + "learning_rate": 4.3402978190640104e-05, + "loss": 3.7818, + "step": 402944 + }, + { + "epoch": 1.01, + "learning_rate": 4.339460862193332e-05, + "loss": 3.7692, + "step": 403456 + }, + { + "epoch": 1.01, + "learning_rate": 4.338622267442279e-05, + "loss": 3.773, + "step": 403968 + }, + { + "epoch": 1.01, + "learning_rate": 4.337783672691227e-05, + "loss": 3.7781, + "step": 404480 + }, + { + "epoch": 1.01, + "learning_rate": 4.336945077940175e-05, + "loss": 3.7756, + "step": 404992 + }, + { + "epoch": 1.01, + "learning_rate": 4.336108121069497e-05, + "loss": 3.7741, + "step": 405504 + }, + { + "epoch": 1.01, + "learning_rate": 4.335269526318445e-05, + "loss": 3.7674, + "step": 406016 + }, + { + "epoch": 1.01, + "learning_rate": 4.334430931567393e-05, + "loss": 3.7456, + "step": 406528 + }, + { + "epoch": 1.01, + "learning_rate": 4.333592336816341e-05, + "loss": 3.7805, + "step": 407040 + }, + { + "epoch": 1.01, + "learning_rate": 4.332753742065289e-05, + "loss": 3.7693, + "step": 407552 + }, + { + "epoch": 1.01, + "learning_rate": 4.331915147314237e-05, + "loss": 3.7691, + "step": 408064 + }, + { + "epoch": 1.01, + "learning_rate": 4.331078190443558e-05, + "loss": 3.7593, + "step": 408576 + }, + { + "epoch": 1.01, + "learning_rate": 4.330239595692506e-05, + "loss": 3.7538, + "step": 409088 + }, + { + "epoch": 1.01, + "learning_rate": 4.329401000941454e-05, + "loss": 3.7527, + "step": 409600 + }, + { + "epoch": 1.01, + "learning_rate": 4.328562406190402e-05, + "loss": 3.7685, + "step": 410112 + }, + { + "epoch": 1.01, + "learning_rate": 4.32772381143935e-05, + "loss": 3.7606, + "step": 410624 + }, + { + "epoch": 1.01, + "learning_rate": 4.326885216688298e-05, + "loss": 3.7652, + "step": 411136 + }, + { + "epoch": 1.01, + "learning_rate": 4.3260482598176186e-05, + "loss": 3.7703, + "step": 411648 + }, + { + "epoch": 1.01, + "learning_rate": 4.3252096650665666e-05, + "loss": 3.7593, + "step": 412160 + }, + { + "epoch": 1.01, + "learning_rate": 4.3243710703155146e-05, + "loss": 3.7619, + "step": 412672 + }, + { + "epoch": 1.01, + "learning_rate": 4.3235324755644626e-05, + "loss": 3.7681, + "step": 413184 + }, + { + "epoch": 1.01, + "learning_rate": 4.322693880813411e-05, + "loss": 3.7481, + "step": 413696 + }, + { + "epoch": 1.01, + "learning_rate": 4.321855286062359e-05, + "loss": 3.7591, + "step": 414208 + }, + { + "epoch": 1.01, + "learning_rate": 4.321016691311307e-05, + "loss": 3.7631, + "step": 414720 + }, + { + "epoch": 1.01, + "learning_rate": 4.320179734440628e-05, + "loss": 3.77, + "step": 415232 + }, + { + "epoch": 1.01, + "learning_rate": 4.319341139689576e-05, + "loss": 3.7478, + "step": 415744 + }, + { + "epoch": 1.01, + "learning_rate": 4.318502544938524e-05, + "loss": 3.7583, + "step": 416256 + }, + { + "epoch": 1.01, + "learning_rate": 4.317663950187472e-05, + "loss": 3.7494, + "step": 416768 + }, + { + "epoch": 1.01, + "learning_rate": 4.31682535543642e-05, + "loss": 3.7698, + "step": 417280 + }, + { + "epoch": 1.01, + "learning_rate": 4.315986760685368e-05, + "loss": 3.766, + "step": 417792 + }, + { + "epoch": 1.01, + "learning_rate": 4.3151481659343155e-05, + "loss": 3.7631, + "step": 418304 + }, + { + "epoch": 1.01, + "learning_rate": 4.3143095711832635e-05, + "loss": 3.7767, + "step": 418816 + }, + { + "epoch": 1.01, + "learning_rate": 4.313472614312585e-05, + "loss": 3.7714, + "step": 419328 + }, + { + "epoch": 1.01, + "learning_rate": 4.312634019561533e-05, + "loss": 3.7852, + "step": 419840 + }, + { + "epoch": 1.01, + "learning_rate": 4.311795424810481e-05, + "loss": 3.7621, + "step": 420352 + }, + { + "epoch": 1.01, + "learning_rate": 4.310956830059429e-05, + "loss": 3.7646, + "step": 420864 + }, + { + "epoch": 1.01, + "learning_rate": 4.3101198731887506e-05, + "loss": 3.7617, + "step": 421376 + }, + { + "epoch": 1.01, + "learning_rate": 4.3092829163180715e-05, + "loss": 3.7538, + "step": 421888 + }, + { + "epoch": 1.01, + "learning_rate": 4.3084443215670195e-05, + "loss": 3.7721, + "step": 422400 + }, + { + "epoch": 1.01, + "learning_rate": 4.3076057268159675e-05, + "loss": 3.7609, + "step": 422912 + }, + { + "epoch": 1.01, + "learning_rate": 4.3067671320649155e-05, + "loss": 3.7692, + "step": 423424 + }, + { + "epoch": 1.01, + "learning_rate": 4.305928537313863e-05, + "loss": 3.7633, + "step": 423936 + }, + { + "epoch": 1.01, + "learning_rate": 4.305089942562811e-05, + "loss": 3.7503, + "step": 424448 + }, + { + "epoch": 1.01, + "learning_rate": 4.3042529856921324e-05, + "loss": 3.7599, + "step": 424960 + }, + { + "epoch": 1.01, + "learning_rate": 4.3034143909410804e-05, + "loss": 3.7529, + "step": 425472 + }, + { + "epoch": 1.01, + "learning_rate": 4.3025757961900284e-05, + "loss": 3.7699, + "step": 425984 + }, + { + "epoch": 1.01, + "learning_rate": 4.3017372014389764e-05, + "loss": 3.763, + "step": 426496 + }, + { + "epoch": 1.01, + "learning_rate": 4.3008986066879244e-05, + "loss": 3.7472, + "step": 427008 + }, + { + "epoch": 1.02, + "learning_rate": 4.3000600119368724e-05, + "loss": 3.77, + "step": 427520 + }, + { + "epoch": 1.02, + "learning_rate": 4.2992214171858204e-05, + "loss": 3.7573, + "step": 428032 + }, + { + "epoch": 1.02, + "learning_rate": 4.2983828224347684e-05, + "loss": 3.7498, + "step": 428544 + }, + { + "epoch": 1.02, + "learning_rate": 4.297545865564089e-05, + "loss": 3.7583, + "step": 429056 + }, + { + "epoch": 1.02, + "learning_rate": 4.296707270813037e-05, + "loss": 3.7697, + "step": 429568 + }, + { + "epoch": 1.02, + "learning_rate": 4.295870313942358e-05, + "loss": 3.7625, + "step": 430080 + }, + { + "epoch": 1.02, + "learning_rate": 4.295031719191306e-05, + "loss": 3.766, + "step": 430592 + }, + { + "epoch": 1.02, + "learning_rate": 4.294193124440254e-05, + "loss": 3.7467, + "step": 431104 + }, + { + "epoch": 1.02, + "learning_rate": 4.293354529689202e-05, + "loss": 3.76, + "step": 431616 + }, + { + "epoch": 1.02, + "learning_rate": 4.29251593493815e-05, + "loss": 3.7517, + "step": 432128 + }, + { + "epoch": 1.02, + "learning_rate": 4.291677340187099e-05, + "loss": 3.7648, + "step": 432640 + }, + { + "epoch": 1.02, + "learning_rate": 4.290838745436047e-05, + "loss": 3.7667, + "step": 433152 + }, + { + "epoch": 1.02, + "learning_rate": 4.290000150684995e-05, + "loss": 3.755, + "step": 433664 + }, + { + "epoch": 1.02, + "learning_rate": 4.289163193814316e-05, + "loss": 3.7594, + "step": 434176 + }, + { + "epoch": 1.02, + "learning_rate": 4.288324599063264e-05, + "loss": 3.7659, + "step": 434688 + }, + { + "epoch": 1.02, + "learning_rate": 4.287487642192585e-05, + "loss": 3.74, + "step": 435200 + }, + { + "epoch": 1.02, + "learning_rate": 4.286649047441533e-05, + "loss": 3.7512, + "step": 435712 + }, + { + "epoch": 1.02, + "learning_rate": 4.285810452690481e-05, + "loss": 3.7442, + "step": 436224 + }, + { + "epoch": 1.02, + "learning_rate": 4.284971857939429e-05, + "loss": 3.7582, + "step": 436736 + }, + { + "epoch": 1.02, + "learning_rate": 4.284133263188377e-05, + "loss": 3.7436, + "step": 437248 + }, + { + "epoch": 1.02, + "learning_rate": 4.2832963063176976e-05, + "loss": 3.7524, + "step": 437760 + }, + { + "epoch": 1.02, + "learning_rate": 4.2824577115666456e-05, + "loss": 3.7499, + "step": 438272 + }, + { + "epoch": 1.02, + "learning_rate": 4.281619116815594e-05, + "loss": 3.7513, + "step": 438784 + }, + { + "epoch": 1.02, + "learning_rate": 4.280780522064542e-05, + "loss": 3.7547, + "step": 439296 + }, + { + "epoch": 1.02, + "learning_rate": 4.27994192731349e-05, + "loss": 3.7476, + "step": 439808 + }, + { + "epoch": 1.02, + "learning_rate": 4.279103332562438e-05, + "loss": 3.7601, + "step": 440320 + }, + { + "epoch": 1.02, + "learning_rate": 4.278266375691759e-05, + "loss": 3.7587, + "step": 440832 + }, + { + "epoch": 1.02, + "learning_rate": 4.277427780940707e-05, + "loss": 3.7586, + "step": 441344 + }, + { + "epoch": 1.02, + "learning_rate": 4.276589186189655e-05, + "loss": 3.7484, + "step": 441856 + }, + { + "epoch": 1.02, + "learning_rate": 4.275750591438603e-05, + "loss": 3.7595, + "step": 442368 + }, + { + "epoch": 1.02, + "learning_rate": 4.274913634567924e-05, + "loss": 3.7602, + "step": 442880 + }, + { + "epoch": 1.02, + "learning_rate": 4.274075039816872e-05, + "loss": 3.746, + "step": 443392 + }, + { + "epoch": 1.02, + "learning_rate": 4.27323644506582e-05, + "loss": 3.7673, + "step": 443904 + }, + { + "epoch": 1.02, + "learning_rate": 4.272397850314768e-05, + "loss": 3.7419, + "step": 444416 + }, + { + "epoch": 1.02, + "learning_rate": 4.271559255563716e-05, + "loss": 3.7593, + "step": 444928 + }, + { + "epoch": 1.02, + "learning_rate": 4.270720660812664e-05, + "loss": 3.7412, + "step": 445440 + }, + { + "epoch": 1.02, + "learning_rate": 4.2698837039419856e-05, + "loss": 3.7564, + "step": 445952 + }, + { + "epoch": 1.02, + "learning_rate": 4.2690451091909336e-05, + "loss": 3.741, + "step": 446464 + }, + { + "epoch": 1.02, + "learning_rate": 4.2682065144398816e-05, + "loss": 3.7447, + "step": 446976 + }, + { + "epoch": 1.02, + "learning_rate": 4.267367919688829e-05, + "loss": 3.7411, + "step": 447488 + }, + { + "epoch": 1.02, + "learning_rate": 4.2665309628181505e-05, + "loss": 3.7613, + "step": 448000 + }, + { + "epoch": 1.02, + "learning_rate": 4.2656923680670985e-05, + "loss": 3.7481, + "step": 448512 + }, + { + "epoch": 1.02, + "learning_rate": 4.2648537733160465e-05, + "loss": 3.7573, + "step": 449024 + }, + { + "epoch": 1.02, + "learning_rate": 4.264015178564994e-05, + "loss": 3.743, + "step": 449536 + }, + { + "epoch": 1.02, + "learning_rate": 4.2631782216943154e-05, + "loss": 3.757, + "step": 450048 + }, + { + "epoch": 1.02, + "learning_rate": 4.2623396269432634e-05, + "loss": 3.7568, + "step": 450560 + }, + { + "epoch": 1.02, + "learning_rate": 4.2615010321922114e-05, + "loss": 3.755, + "step": 451072 + }, + { + "epoch": 1.02, + "learning_rate": 4.2606624374411594e-05, + "loss": 3.7541, + "step": 451584 + }, + { + "epoch": 1.02, + "learning_rate": 4.2598238426901074e-05, + "loss": 3.7502, + "step": 452096 + }, + { + "epoch": 1.02, + "learning_rate": 4.258986885819429e-05, + "loss": 3.7502, + "step": 452608 + }, + { + "epoch": 1.02, + "learning_rate": 4.258148291068376e-05, + "loss": 3.761, + "step": 453120 + }, + { + "epoch": 1.02, + "learning_rate": 4.257309696317324e-05, + "loss": 3.7457, + "step": 453632 + }, + { + "epoch": 1.02, + "learning_rate": 4.256471101566272e-05, + "loss": 3.7535, + "step": 454144 + }, + { + "epoch": 1.02, + "learning_rate": 4.25563250681522e-05, + "loss": 3.748, + "step": 454656 + }, + { + "epoch": 1.02, + "learning_rate": 4.254793912064168e-05, + "loss": 3.7492, + "step": 455168 + }, + { + "epoch": 1.02, + "learning_rate": 4.253955317313116e-05, + "loss": 3.7529, + "step": 455680 + }, + { + "epoch": 1.02, + "learning_rate": 4.253116722562064e-05, + "loss": 3.7452, + "step": 456192 + }, + { + "epoch": 1.02, + "learning_rate": 4.252279765691385e-05, + "loss": 3.7604, + "step": 456704 + }, + { + "epoch": 1.02, + "learning_rate": 4.251441170940333e-05, + "loss": 3.7342, + "step": 457216 + }, + { + "epoch": 1.02, + "learning_rate": 4.250602576189281e-05, + "loss": 3.7567, + "step": 457728 + }, + { + "epoch": 1.03, + "eval_loss": 3.869717836380005, + "eval_runtime": 305.4028, + "eval_samples_per_second": 1249.468, + "eval_steps_per_second": 39.047, + "step": 457920 + }, + { + "epoch": 0.0, + "learning_rate": 4.24976398143823e-05, + "loss": 3.7455, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.248925386687178e-05, + "loss": 3.7322, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.248086791936126e-05, + "loss": 3.7486, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.247248197185074e-05, + "loss": 3.7459, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.246411240314395e-05, + "loss": 3.7594, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.245572645563343e-05, + "loss": 3.7406, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.244734050812291e-05, + "loss": 3.7345, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.243895456061239e-05, + "loss": 3.7324, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.243056861310187e-05, + "loss": 3.7417, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.242218266559135e-05, + "loss": 3.748, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.241379671808083e-05, + "loss": 3.7407, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.24054107705703e-05, + "loss": 3.7407, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.239705758066725e-05, + "loss": 3.7417, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.238867163315673e-05, + "loss": 3.7354, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.238028568564621e-05, + "loss": 3.7412, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.237189973813569e-05, + "loss": 3.7286, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.236351379062517e-05, + "loss": 3.7345, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.235512784311465e-05, + "loss": 3.7381, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.2346741895604125e-05, + "loss": 3.7387, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.2338355948093605e-05, + "loss": 3.7487, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.233000275819055e-05, + "loss": 3.7464, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.232161681068003e-05, + "loss": 3.7393, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.231323086316951e-05, + "loss": 3.7393, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.230484491565899e-05, + "loss": 3.7451, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.229645896814847e-05, + "loss": 3.7246, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.228807302063795e-05, + "loss": 3.7495, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.227968707312743e-05, + "loss": 3.7318, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.227130112561691e-05, + "loss": 3.7323, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.2262931556910125e-05, + "loss": 3.7287, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.22545456093996e-05, + "loss": 3.7337, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.224615966188908e-05, + "loss": 3.7383, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.2237790093182294e-05, + "loss": 3.74, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.2229404145671774e-05, + "loss": 3.7419, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.222101819816125e-05, + "loss": 3.7447, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.221263225065073e-05, + "loss": 3.7314, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.220424630314021e-05, + "loss": 3.7396, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.219587673443342e-05, + "loss": 3.7364, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.21874907869229e-05, + "loss": 3.7293, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.217910483941238e-05, + "loss": 3.7282, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.217071889190186e-05, + "loss": 3.7352, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.216233294439134e-05, + "loss": 3.7304, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.215394699688082e-05, + "loss": 3.7411, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.21455610493703e-05, + "loss": 3.7306, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.213719148066351e-05, + "loss": 3.7326, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.212880553315299e-05, + "loss": 3.7425, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.212041958564247e-05, + "loss": 3.7319, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.211203363813195e-05, + "loss": 3.7376, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.210366406942516e-05, + "loss": 3.7289, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.209527812191464e-05, + "loss": 3.701, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.208689217440413e-05, + "loss": 3.7444, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.207850622689361e-05, + "loss": 3.7295, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.207012027938309e-05, + "loss": 3.7315, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.20617507106763e-05, + "loss": 3.7182, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.205336476316578e-05, + "loss": 3.7125, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.204497881565526e-05, + "loss": 3.719, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.203659286814474e-05, + "loss": 3.7273, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.202820692063422e-05, + "loss": 3.7243, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.20198209731237e-05, + "loss": 3.7232, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.2011451404416906e-05, + "loss": 3.7354, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.2003065456906386e-05, + "loss": 3.7195, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.1994679509395866e-05, + "loss": 3.7189, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.1986293561885346e-05, + "loss": 3.7334, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.1977907614374826e-05, + "loss": 3.7059, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.1969521666864306e-05, + "loss": 3.7195, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.1961135719353785e-05, + "loss": 3.7239, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.1952766150647e-05, + "loss": 3.733, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.194438020313648e-05, + "loss": 3.7075, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.193599425562596e-05, + "loss": 3.7226, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.1927608308115434e-05, + "loss": 3.708, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.191923873940865e-05, + "loss": 3.7333, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.191085279189813e-05, + "loss": 3.7302, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.1902466844387603e-05, + "loss": 3.7257, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.189408089687708e-05, + "loss": 3.7332, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.188569494936656e-05, + "loss": 3.7346, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.187730900185604e-05, + "loss": 3.7475, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.186892305434553e-05, + "loss": 3.7235, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.186053710683501e-05, + "loss": 3.7282, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.185216753812822e-05, + "loss": 3.7256, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.18437815906177e-05, + "loss": 3.7158, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.183539564310718e-05, + "loss": 3.7289, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.182700969559666e-05, + "loss": 3.7248, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.181862374808614e-05, + "loss": 3.729, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.181023780057562e-05, + "loss": 3.7338, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.18018518530651e-05, + "loss": 3.7136, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.179348228435831e-05, + "loss": 3.716, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.178509633684779e-05, + "loss": 3.716, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.177671038933727e-05, + "loss": 3.7334, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.176832444182675e-05, + "loss": 3.7212, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.175993849431623e-05, + "loss": 3.7144, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.1751568925609444e-05, + "loss": 3.7197, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.1743182978098924e-05, + "loss": 3.7284, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.1734797030588404e-05, + "loss": 3.7122, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.1726411083077883e-05, + "loss": 3.7207, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.1718025135567363e-05, + "loss": 3.7344, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.170965556686057e-05, + "loss": 3.7235, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.170126961935005e-05, + "loss": 3.7268, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.169288367183953e-05, + "loss": 3.7093, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.168449772432901e-05, + "loss": 3.7229, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.167611177681849e-05, + "loss": 3.7166, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.1667725829307966e-05, + "loss": 3.7276, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.165933988179745e-05, + "loss": 3.7287, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.165095393428693e-05, + "loss": 3.7234, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.164258436558015e-05, + "loss": 3.7218, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.163419841806962e-05, + "loss": 3.726, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.162582884936284e-05, + "loss": 3.7046, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.161744290185232e-05, + "loss": 3.7156, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.16090569543418e-05, + "loss": 3.7061, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.160067100683127e-05, + "loss": 3.7242, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.159228505932075e-05, + "loss": 3.7066, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.158389911181023e-05, + "loss": 3.7136, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.157552954310344e-05, + "loss": 3.7096, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.156714359559292e-05, + "loss": 3.7155, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.1558757648082406e-05, + "loss": 3.7175, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.1550371700571886e-05, + "loss": 3.7096, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.1541985753061366e-05, + "loss": 3.7207, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.1533616184354575e-05, + "loss": 3.7268, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.1525230236844055e-05, + "loss": 3.7171, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.1516844289333535e-05, + "loss": 3.7198, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.1508458341823015e-05, + "loss": 3.7191, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.1500088773116224e-05, + "loss": 3.7232, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.1491702825605704e-05, + "loss": 3.7147, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.1483316878095184e-05, + "loss": 3.724, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.1474930930584664e-05, + "loss": 3.7066, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.1466544983074144e-05, + "loss": 3.7233, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.1458159035563624e-05, + "loss": 3.7073, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.144978946685684e-05, + "loss": 3.7138, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.144140351934632e-05, + "loss": 3.7085, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.14330175718358e-05, + "loss": 3.7084, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.142463162432528e-05, + "loss": 3.7063, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.141626205561849e-05, + "loss": 3.7214, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.140787610810797e-05, + "loss": 3.7151, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.139949016059745e-05, + "loss": 3.7218, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.139110421308693e-05, + "loss": 3.7035, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.138273464438014e-05, + "loss": 3.723, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.137434869686962e-05, + "loss": 3.7187, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.13659627493591e-05, + "loss": 3.7215, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.135757680184858e-05, + "loss": 3.7184, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.134919085433806e-05, + "loss": 3.7144, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.134082128563127e-05, + "loss": 3.7157, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.133243533812075e-05, + "loss": 3.7284, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.132404939061023e-05, + "loss": 3.7065, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.131566344309971e-05, + "loss": 3.7151, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.130727749558919e-05, + "loss": 3.7158, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.129889154807867e-05, + "loss": 3.7143, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.129050560056815e-05, + "loss": 3.7099, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.1282119653057626e-05, + "loss": 3.7111, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.127375008435084e-05, + "loss": 3.7246, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.126536413684032e-05, + "loss": 3.7034, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.12569781893298e-05, + "loss": 3.721, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 3.8590776920318604, + "eval_runtime": 304.3012, + "eval_samples_per_second": 1253.991, + "eval_steps_per_second": 39.188, + "step": 534240 + }, + { + "epoch": 1.0, + "learning_rate": 4.1248592241819275e-05, + "loss": 3.7097, + "step": 534528 + }, + { + "epoch": 1.0, + "learning_rate": 4.124020629430876e-05, + "loss": 3.6955, + "step": 535040 + }, + { + "epoch": 1.0, + "learning_rate": 4.123182034679824e-05, + "loss": 3.7171, + "step": 535552 + }, + { + "epoch": 1.0, + "learning_rate": 4.122343439928772e-05, + "loss": 3.7054, + "step": 536064 + }, + { + "epoch": 1.0, + "learning_rate": 4.121506483058093e-05, + "loss": 3.7225, + "step": 536576 + }, + { + "epoch": 1.0, + "learning_rate": 4.120667888307041e-05, + "loss": 3.7093, + "step": 537088 + }, + { + "epoch": 1.0, + "learning_rate": 4.119829293555989e-05, + "loss": 3.7034, + "step": 537600 + }, + { + "epoch": 1.0, + "learning_rate": 4.118990698804937e-05, + "loss": 3.698, + "step": 538112 + }, + { + "epoch": 1.0, + "learning_rate": 4.118153741934258e-05, + "loss": 3.7088, + "step": 538624 + }, + { + "epoch": 1.0, + "learning_rate": 4.117315147183206e-05, + "loss": 3.7103, + "step": 539136 + }, + { + "epoch": 1.0, + "learning_rate": 4.116476552432154e-05, + "loss": 3.7052, + "step": 539648 + }, + { + "epoch": 1.0, + "learning_rate": 4.115637957681102e-05, + "loss": 3.7045, + "step": 540160 + }, + { + "epoch": 1.0, + "learning_rate": 4.11479936293005e-05, + "loss": 3.705, + "step": 540672 + }, + { + "epoch": 1.0, + "learning_rate": 4.113960768178998e-05, + "loss": 3.7014, + "step": 541184 + }, + { + "epoch": 1.0, + "learning_rate": 4.113122173427946e-05, + "loss": 3.7072, + "step": 541696 + }, + { + "epoch": 1.0, + "learning_rate": 4.1122835786768946e-05, + "loss": 3.6957, + "step": 542208 + }, + { + "epoch": 1.0, + "learning_rate": 4.1114466218062155e-05, + "loss": 3.6979, + "step": 542720 + }, + { + "epoch": 1.0, + "learning_rate": 4.1106080270551635e-05, + "loss": 3.7041, + "step": 543232 + }, + { + "epoch": 1.0, + "learning_rate": 4.1097694323041115e-05, + "loss": 3.7049, + "step": 543744 + }, + { + "epoch": 1.0, + "learning_rate": 4.1089308375530595e-05, + "loss": 3.7114, + "step": 544256 + }, + { + "epoch": 1.0, + "learning_rate": 4.1080922428020075e-05, + "loss": 3.7134, + "step": 544768 + }, + { + "epoch": 1.0, + "learning_rate": 4.1072552859313284e-05, + "loss": 3.7073, + "step": 545280 + }, + { + "epoch": 1.0, + "learning_rate": 4.1064166911802764e-05, + "loss": 3.7038, + "step": 545792 + }, + { + "epoch": 1.0, + "learning_rate": 4.1055780964292244e-05, + "loss": 3.7072, + "step": 546304 + }, + { + "epoch": 1.0, + "learning_rate": 4.1047395016781724e-05, + "loss": 3.6946, + "step": 546816 + }, + { + "epoch": 1.0, + "learning_rate": 4.1039009069271204e-05, + "loss": 3.7149, + "step": 547328 + }, + { + "epoch": 1.0, + "learning_rate": 4.1030623121760684e-05, + "loss": 3.6963, + "step": 547840 + }, + { + "epoch": 1.0, + "learning_rate": 4.10222535530539e-05, + "loss": 3.7015, + "step": 548352 + }, + { + "epoch": 1.0, + "learning_rate": 4.101386760554338e-05, + "loss": 3.6952, + "step": 548864 + }, + { + "epoch": 1.0, + "learning_rate": 4.100548165803286e-05, + "loss": 3.6974, + "step": 549376 + }, + { + "epoch": 1.01, + "learning_rate": 4.099709571052234e-05, + "loss": 3.702, + "step": 549888 + }, + { + "epoch": 1.01, + "learning_rate": 4.098872614181555e-05, + "loss": 3.7056, + "step": 550400 + }, + { + "epoch": 1.01, + "learning_rate": 4.098034019430503e-05, + "loss": 3.7071, + "step": 550912 + }, + { + "epoch": 1.01, + "learning_rate": 4.097195424679451e-05, + "loss": 3.7104, + "step": 551424 + }, + { + "epoch": 1.01, + "learning_rate": 4.096356829928399e-05, + "loss": 3.6964, + "step": 551936 + }, + { + "epoch": 1.01, + "learning_rate": 4.095518235177346e-05, + "loss": 3.7096, + "step": 552448 + }, + { + "epoch": 1.01, + "learning_rate": 4.094681278306668e-05, + "loss": 3.7061, + "step": 552960 + }, + { + "epoch": 1.01, + "learning_rate": 4.093842683555616e-05, + "loss": 3.6934, + "step": 553472 + }, + { + "epoch": 1.01, + "learning_rate": 4.093004088804564e-05, + "loss": 3.6986, + "step": 553984 + }, + { + "epoch": 1.01, + "learning_rate": 4.092165494053512e-05, + "loss": 3.7007, + "step": 554496 + }, + { + "epoch": 1.01, + "learning_rate": 4.09132689930246e-05, + "loss": 3.6979, + "step": 555008 + }, + { + "epoch": 1.01, + "learning_rate": 4.090488304551408e-05, + "loss": 3.7062, + "step": 555520 + }, + { + "epoch": 1.01, + "learning_rate": 4.089649709800356e-05, + "loss": 3.6975, + "step": 556032 + }, + { + "epoch": 1.01, + "learning_rate": 4.0888127529296767e-05, + "loss": 3.6996, + "step": 556544 + }, + { + "epoch": 1.01, + "learning_rate": 4.0879741581786247e-05, + "loss": 3.7076, + "step": 557056 + }, + { + "epoch": 1.01, + "learning_rate": 4.0871355634275727e-05, + "loss": 3.7, + "step": 557568 + }, + { + "epoch": 1.01, + "learning_rate": 4.0862969686765206e-05, + "loss": 3.702, + "step": 558080 + }, + { + "epoch": 1.01, + "learning_rate": 4.0854600118058416e-05, + "loss": 3.6985, + "step": 558592 + }, + { + "epoch": 1.01, + "learning_rate": 4.0846214170547896e-05, + "loss": 3.666, + "step": 559104 + }, + { + "epoch": 1.01, + "learning_rate": 4.0837828223037375e-05, + "loss": 3.7132, + "step": 559616 + }, + { + "epoch": 1.01, + "learning_rate": 4.0829442275526855e-05, + "loss": 3.6947, + "step": 560128 + }, + { + "epoch": 1.01, + "learning_rate": 4.082107270682007e-05, + "loss": 3.7024, + "step": 560640 + }, + { + "epoch": 1.01, + "learning_rate": 4.081268675930955e-05, + "loss": 3.6827, + "step": 561152 + }, + { + "epoch": 1.01, + "learning_rate": 4.080430081179903e-05, + "loss": 3.6808, + "step": 561664 + }, + { + "epoch": 1.01, + "learning_rate": 4.079591486428851e-05, + "loss": 3.6825, + "step": 562176 + }, + { + "epoch": 1.01, + "learning_rate": 4.078754529558172e-05, + "loss": 3.6913, + "step": 562688 + }, + { + "epoch": 1.01, + "learning_rate": 4.07791593480712e-05, + "loss": 3.694, + "step": 563200 + }, + { + "epoch": 1.01, + "learning_rate": 4.077077340056068e-05, + "loss": 3.6873, + "step": 563712 + }, + { + "epoch": 1.01, + "learning_rate": 4.076238745305016e-05, + "loss": 3.7056, + "step": 564224 + }, + { + "epoch": 1.01, + "learning_rate": 4.075400150553964e-05, + "loss": 3.6882, + "step": 564736 + }, + { + "epoch": 1.01, + "learning_rate": 4.074563193683285e-05, + "loss": 3.6863, + "step": 565248 + }, + { + "epoch": 1.01, + "learning_rate": 4.073724598932233e-05, + "loss": 3.7001, + "step": 565760 + }, + { + "epoch": 1.01, + "learning_rate": 4.072886004181181e-05, + "loss": 3.6733, + "step": 566272 + }, + { + "epoch": 1.01, + "learning_rate": 4.072047409430129e-05, + "loss": 3.6818, + "step": 566784 + }, + { + "epoch": 1.01, + "learning_rate": 4.071208814679077e-05, + "loss": 3.6933, + "step": 567296 + }, + { + "epoch": 1.01, + "learning_rate": 4.0703718578083985e-05, + "loss": 3.7021, + "step": 567808 + }, + { + "epoch": 1.01, + "learning_rate": 4.0695332630573465e-05, + "loss": 3.675, + "step": 568320 + }, + { + "epoch": 1.01, + "learning_rate": 4.0686946683062945e-05, + "loss": 3.6898, + "step": 568832 + }, + { + "epoch": 1.01, + "learning_rate": 4.0678560735552425e-05, + "loss": 3.6772, + "step": 569344 + }, + { + "epoch": 1.01, + "learning_rate": 4.0670191166845634e-05, + "loss": 3.7023, + "step": 569856 + }, + { + "epoch": 1.01, + "learning_rate": 4.0661805219335114e-05, + "loss": 3.6934, + "step": 570368 + }, + { + "epoch": 1.01, + "learning_rate": 4.0653419271824594e-05, + "loss": 3.6934, + "step": 570880 + }, + { + "epoch": 1.01, + "learning_rate": 4.0645033324314074e-05, + "loss": 3.6988, + "step": 571392 + }, + { + "epoch": 1.01, + "learning_rate": 4.0636647376803554e-05, + "loss": 3.7017, + "step": 571904 + }, + { + "epoch": 1.01, + "learning_rate": 4.062827780809676e-05, + "loss": 3.7143, + "step": 572416 + }, + { + "epoch": 1.01, + "learning_rate": 4.061989186058624e-05, + "loss": 3.6927, + "step": 572928 + }, + { + "epoch": 1.01, + "learning_rate": 4.061150591307572e-05, + "loss": 3.6949, + "step": 573440 + }, + { + "epoch": 1.01, + "learning_rate": 4.060311996556521e-05, + "loss": 3.6965, + "step": 573952 + }, + { + "epoch": 1.01, + "learning_rate": 4.059473401805469e-05, + "loss": 3.6822, + "step": 574464 + }, + { + "epoch": 1.01, + "learning_rate": 4.05863644493479e-05, + "loss": 3.6936, + "step": 574976 + }, + { + "epoch": 1.01, + "learning_rate": 4.057797850183738e-05, + "loss": 3.6955, + "step": 575488 + }, + { + "epoch": 1.01, + "learning_rate": 4.056959255432686e-05, + "loss": 3.6974, + "step": 576000 + }, + { + "epoch": 1.01, + "learning_rate": 4.056120660681634e-05, + "loss": 3.697, + "step": 576512 + }, + { + "epoch": 1.01, + "learning_rate": 4.055282065930582e-05, + "loss": 3.6852, + "step": 577024 + }, + { + "epoch": 1.01, + "learning_rate": 4.054445109059903e-05, + "loss": 3.681, + "step": 577536 + }, + { + "epoch": 1.01, + "learning_rate": 4.053606514308851e-05, + "loss": 3.6853, + "step": 578048 + }, + { + "epoch": 1.01, + "learning_rate": 4.052767919557799e-05, + "loss": 3.7027, + "step": 578560 + }, + { + "epoch": 1.01, + "learning_rate": 4.051929324806747e-05, + "loss": 3.6908, + "step": 579072 + }, + { + "epoch": 1.01, + "learning_rate": 4.051090730055695e-05, + "loss": 3.6832, + "step": 579584 + }, + { + "epoch": 1.02, + "learning_rate": 4.050253773185016e-05, + "loss": 3.6869, + "step": 580096 + }, + { + "epoch": 1.02, + "learning_rate": 4.049415178433964e-05, + "loss": 3.6961, + "step": 580608 + }, + { + "epoch": 1.02, + "learning_rate": 4.048576583682912e-05, + "loss": 3.6823, + "step": 581120 + }, + { + "epoch": 1.02, + "learning_rate": 4.0477379889318596e-05, + "loss": 3.6872, + "step": 581632 + }, + { + "epoch": 1.02, + "learning_rate": 4.046901032061181e-05, + "loss": 3.7008, + "step": 582144 + }, + { + "epoch": 1.02, + "learning_rate": 4.046062437310129e-05, + "loss": 3.6914, + "step": 582656 + }, + { + "epoch": 1.02, + "learning_rate": 4.045223842559077e-05, + "loss": 3.6933, + "step": 583168 + }, + { + "epoch": 1.02, + "learning_rate": 4.0443852478080245e-05, + "loss": 3.6807, + "step": 583680 + }, + { + "epoch": 1.02, + "learning_rate": 4.0435466530569725e-05, + "loss": 3.6878, + "step": 584192 + }, + { + "epoch": 1.02, + "learning_rate": 4.0427080583059205e-05, + "loss": 3.6842, + "step": 584704 + }, + { + "epoch": 1.02, + "learning_rate": 4.0418694635548685e-05, + "loss": 3.6981, + "step": 585216 + }, + { + "epoch": 1.02, + "learning_rate": 4.0410308688038165e-05, + "loss": 3.6924, + "step": 585728 + }, + { + "epoch": 1.02, + "learning_rate": 4.040193911933138e-05, + "loss": 3.6941, + "step": 586240 + }, + { + "epoch": 1.02, + "learning_rate": 4.039355317182086e-05, + "loss": 3.6894, + "step": 586752 + }, + { + "epoch": 1.02, + "learning_rate": 4.038518360311407e-05, + "loss": 3.6916, + "step": 587264 + }, + { + "epoch": 1.02, + "learning_rate": 4.037679765560355e-05, + "loss": 3.6788, + "step": 587776 + }, + { + "epoch": 1.02, + "learning_rate": 4.036841170809303e-05, + "loss": 3.6811, + "step": 588288 + }, + { + "epoch": 1.02, + "learning_rate": 4.036002576058251e-05, + "loss": 3.6774, + "step": 588800 + }, + { + "epoch": 1.02, + "learning_rate": 4.035163981307199e-05, + "loss": 3.6946, + "step": 589312 + }, + { + "epoch": 1.02, + "learning_rate": 4.03432702443652e-05, + "loss": 3.6752, + "step": 589824 + }, + { + "epoch": 1.02, + "learning_rate": 4.033488429685468e-05, + "loss": 3.6807, + "step": 590336 + }, + { + "epoch": 1.02, + "learning_rate": 4.032649834934416e-05, + "loss": 3.6772, + "step": 590848 + }, + { + "epoch": 1.02, + "learning_rate": 4.031811240183364e-05, + "loss": 3.6894, + "step": 591360 + }, + { + "epoch": 1.02, + "learning_rate": 4.030972645432312e-05, + "loss": 3.6867, + "step": 591872 + }, + { + "epoch": 1.02, + "learning_rate": 4.0301356885616334e-05, + "loss": 3.677, + "step": 592384 + }, + { + "epoch": 1.02, + "learning_rate": 4.0292970938105814e-05, + "loss": 3.6927, + "step": 592896 + }, + { + "epoch": 1.02, + "learning_rate": 4.0284584990595294e-05, + "loss": 3.6921, + "step": 593408 + }, + { + "epoch": 1.02, + "learning_rate": 4.0276199043084774e-05, + "loss": 3.6858, + "step": 593920 + }, + { + "epoch": 1.02, + "learning_rate": 4.0267829474377983e-05, + "loss": 3.6907, + "step": 594432 + }, + { + "epoch": 1.02, + "learning_rate": 4.0259443526867463e-05, + "loss": 3.6883, + "step": 594944 + }, + { + "epoch": 1.02, + "learning_rate": 4.025105757935694e-05, + "loss": 3.6877, + "step": 595456 + }, + { + "epoch": 1.02, + "learning_rate": 4.024267163184642e-05, + "loss": 3.6858, + "step": 595968 + }, + { + "epoch": 1.02, + "learning_rate": 4.023430206313963e-05, + "loss": 3.6895, + "step": 596480 + }, + { + "epoch": 1.02, + "learning_rate": 4.022591611562911e-05, + "loss": 3.6775, + "step": 596992 + }, + { + "epoch": 1.02, + "learning_rate": 4.021753016811859e-05, + "loss": 3.6907, + "step": 597504 + }, + { + "epoch": 1.02, + "learning_rate": 4.020914422060807e-05, + "loss": 3.6803, + "step": 598016 + }, + { + "epoch": 1.02, + "learning_rate": 4.020075827309755e-05, + "loss": 3.6844, + "step": 598528 + }, + { + "epoch": 1.02, + "learning_rate": 4.019238870439077e-05, + "loss": 3.6774, + "step": 599040 + }, + { + "epoch": 1.02, + "learning_rate": 4.018400275688025e-05, + "loss": 3.6783, + "step": 599552 + }, + { + "epoch": 1.02, + "learning_rate": 4.017561680936973e-05, + "loss": 3.6771, + "step": 600064 + }, + { + "epoch": 1.02, + "learning_rate": 4.016723086185921e-05, + "loss": 3.6885, + "step": 600576 + }, + { + "epoch": 1.02, + "learning_rate": 4.015886129315242e-05, + "loss": 3.6829, + "step": 601088 + }, + { + "epoch": 1.02, + "learning_rate": 4.01504753456419e-05, + "loss": 3.6924, + "step": 601600 + }, + { + "epoch": 1.02, + "learning_rate": 4.014208939813138e-05, + "loss": 3.6707, + "step": 602112 + }, + { + "epoch": 1.02, + "learning_rate": 4.013370345062086e-05, + "loss": 3.6963, + "step": 602624 + }, + { + "epoch": 1.02, + "learning_rate": 4.0125333881914066e-05, + "loss": 3.6851, + "step": 603136 + }, + { + "epoch": 1.02, + "learning_rate": 4.0116947934403546e-05, + "loss": 3.6899, + "step": 603648 + }, + { + "epoch": 1.02, + "learning_rate": 4.0108561986893026e-05, + "loss": 3.6897, + "step": 604160 + }, + { + "epoch": 1.02, + "learning_rate": 4.0100176039382506e-05, + "loss": 3.6827, + "step": 604672 + }, + { + "epoch": 1.02, + "learning_rate": 4.009180647067572e-05, + "loss": 3.684, + "step": 605184 + }, + { + "epoch": 1.02, + "learning_rate": 4.00834205231652e-05, + "loss": 3.6959, + "step": 605696 + }, + { + "epoch": 1.02, + "learning_rate": 4.007503457565468e-05, + "loss": 3.6762, + "step": 606208 + }, + { + "epoch": 1.02, + "learning_rate": 4.006664862814416e-05, + "loss": 3.6856, + "step": 606720 + }, + { + "epoch": 1.02, + "learning_rate": 4.005826268063364e-05, + "loss": 3.6889, + "step": 607232 + }, + { + "epoch": 1.02, + "learning_rate": 4.004989311192685e-05, + "loss": 3.6805, + "step": 607744 + }, + { + "epoch": 1.02, + "learning_rate": 4.004150716441633e-05, + "loss": 3.6796, + "step": 608256 + }, + { + "epoch": 1.02, + "learning_rate": 4.003312121690581e-05, + "loss": 3.683, + "step": 608768 + }, + { + "epoch": 1.02, + "learning_rate": 4.002473526939529e-05, + "loss": 3.6931, + "step": 609280 + }, + { + "epoch": 1.02, + "learning_rate": 4.00163657006885e-05, + "loss": 3.6759, + "step": 609792 + }, + { + "epoch": 1.02, + "learning_rate": 4.000797975317798e-05, + "loss": 3.6899, + "step": 610304 + }, + { + "epoch": 1.03, + "eval_loss": 3.85223126411438, + "eval_runtime": 304.0909, + "eval_samples_per_second": 1254.858, + "eval_steps_per_second": 39.215, + "step": 610560 + }, + { + "epoch": 0.0, + "learning_rate": 3.999959380566746e-05, + "loss": 3.677, + "step": 610816 + }, + { + "epoch": 0.0, + "learning_rate": 3.999120785815694e-05, + "loss": 3.6717, + "step": 611328 + }, + { + "epoch": 0.0, + "learning_rate": 3.9982821910646426e-05, + "loss": 3.679, + "step": 611840 + }, + { + "epoch": 0.0, + "learning_rate": 3.9974435963135906e-05, + "loss": 3.6802, + "step": 612352 + }, + { + "epoch": 0.0, + "learning_rate": 3.9966066394429115e-05, + "loss": 3.6929, + "step": 612864 + }, + { + "epoch": 0.0, + "learning_rate": 3.9957680446918595e-05, + "loss": 3.6787, + "step": 613376 + }, + { + "epoch": 0.0, + "learning_rate": 3.9949294499408075e-05, + "loss": 3.6736, + "step": 613888 + }, + { + "epoch": 0.0, + "learning_rate": 3.9940908551897555e-05, + "loss": 3.6706, + "step": 614400 + }, + { + "epoch": 0.0, + "learning_rate": 3.993252260438703e-05, + "loss": 3.6746, + "step": 614912 + }, + { + "epoch": 0.0, + "learning_rate": 3.9924153035680244e-05, + "loss": 3.6859, + "step": 615424 + }, + { + "epoch": 0.0, + "learning_rate": 3.9915767088169724e-05, + "loss": 3.6742, + "step": 615936 + }, + { + "epoch": 0.0, + "learning_rate": 3.99073811406592e-05, + "loss": 3.6724, + "step": 616448 + }, + { + "epoch": 0.0, + "learning_rate": 3.989899519314868e-05, + "loss": 3.6841, + "step": 616960 + }, + { + "epoch": 0.0, + "learning_rate": 3.989062562444189e-05, + "loss": 3.6626, + "step": 617472 + }, + { + "epoch": 0.0, + "learning_rate": 3.988223967693138e-05, + "loss": 3.6733, + "step": 617984 + }, + { + "epoch": 0.0, + "learning_rate": 3.987385372942085e-05, + "loss": 3.6712, + "step": 618496 + }, + { + "epoch": 0.0, + "learning_rate": 3.986546778191033e-05, + "loss": 3.6671, + "step": 619008 + }, + { + "epoch": 0.0, + "learning_rate": 3.985708183439981e-05, + "loss": 3.6767, + "step": 619520 + }, + { + "epoch": 0.0, + "learning_rate": 3.984871226569303e-05, + "loss": 3.6751, + "step": 620032 + }, + { + "epoch": 0.0, + "learning_rate": 3.98403263181825e-05, + "loss": 3.6775, + "step": 620544 + }, + { + "epoch": 0.0, + "learning_rate": 3.983194037067198e-05, + "loss": 3.6872, + "step": 621056 + }, + { + "epoch": 0.0, + "learning_rate": 3.982355442316146e-05, + "loss": 3.678, + "step": 621568 + }, + { + "epoch": 0.0, + "learning_rate": 3.981518485445467e-05, + "loss": 3.6784, + "step": 622080 + }, + { + "epoch": 0.0, + "learning_rate": 3.980679890694415e-05, + "loss": 3.674, + "step": 622592 + }, + { + "epoch": 0.0, + "learning_rate": 3.979841295943363e-05, + "loss": 3.6688, + "step": 623104 + }, + { + "epoch": 0.0, + "learning_rate": 3.979002701192312e-05, + "loss": 3.6839, + "step": 623616 + }, + { + "epoch": 0.0, + "learning_rate": 3.978165744321633e-05, + "loss": 3.6677, + "step": 624128 + }, + { + "epoch": 0.0, + "learning_rate": 3.977327149570581e-05, + "loss": 3.6747, + "step": 624640 + }, + { + "epoch": 0.0, + "learning_rate": 3.976488554819529e-05, + "loss": 3.6627, + "step": 625152 + }, + { + "epoch": 0.0, + "learning_rate": 3.975649960068477e-05, + "loss": 3.671, + "step": 625664 + }, + { + "epoch": 0.01, + "learning_rate": 3.9748130031977976e-05, + "loss": 3.669, + "step": 626176 + }, + { + "epoch": 0.01, + "learning_rate": 3.9739744084467456e-05, + "loss": 3.6756, + "step": 626688 + }, + { + "epoch": 0.01, + "learning_rate": 3.9731358136956936e-05, + "loss": 3.6802, + "step": 627200 + }, + { + "epoch": 0.01, + "learning_rate": 3.9722972189446416e-05, + "loss": 3.6823, + "step": 627712 + }, + { + "epoch": 0.01, + "learning_rate": 3.9714586241935896e-05, + "loss": 3.6702, + "step": 628224 + }, + { + "epoch": 0.01, + "learning_rate": 3.9706216673229105e-05, + "loss": 3.6732, + "step": 628736 + }, + { + "epoch": 0.01, + "learning_rate": 3.9697830725718585e-05, + "loss": 3.6788, + "step": 629248 + }, + { + "epoch": 0.01, + "learning_rate": 3.968944477820807e-05, + "loss": 3.668, + "step": 629760 + }, + { + "epoch": 0.01, + "learning_rate": 3.968105883069755e-05, + "loss": 3.6673, + "step": 630272 + }, + { + "epoch": 0.01, + "learning_rate": 3.967268926199076e-05, + "loss": 3.6696, + "step": 630784 + }, + { + "epoch": 0.01, + "learning_rate": 3.966430331448024e-05, + "loss": 3.6717, + "step": 631296 + }, + { + "epoch": 0.01, + "learning_rate": 3.965591736696972e-05, + "loss": 3.6715, + "step": 631808 + }, + { + "epoch": 0.01, + "learning_rate": 3.96475314194592e-05, + "loss": 3.6756, + "step": 632320 + }, + { + "epoch": 0.01, + "learning_rate": 3.963914547194868e-05, + "loss": 3.6716, + "step": 632832 + }, + { + "epoch": 0.01, + "learning_rate": 3.963077590324189e-05, + "loss": 3.6761, + "step": 633344 + }, + { + "epoch": 0.01, + "learning_rate": 3.962238995573137e-05, + "loss": 3.6733, + "step": 633856 + }, + { + "epoch": 0.01, + "learning_rate": 3.961400400822085e-05, + "loss": 3.6721, + "step": 634368 + }, + { + "epoch": 0.01, + "learning_rate": 3.960561806071033e-05, + "loss": 3.6703, + "step": 634880 + }, + { + "epoch": 0.01, + "learning_rate": 3.959724849200354e-05, + "loss": 3.6367, + "step": 635392 + }, + { + "epoch": 0.01, + "learning_rate": 3.9588862544493025e-05, + "loss": 3.6836, + "step": 635904 + }, + { + "epoch": 0.01, + "learning_rate": 3.9580476596982505e-05, + "loss": 3.664, + "step": 636416 + }, + { + "epoch": 0.01, + "learning_rate": 3.9572090649471985e-05, + "loss": 3.6734, + "step": 636928 + }, + { + "epoch": 0.01, + "learning_rate": 3.9563704701961465e-05, + "loss": 3.6583, + "step": 637440 + }, + { + "epoch": 0.01, + "learning_rate": 3.9555335133254674e-05, + "loss": 3.6532, + "step": 637952 + }, + { + "epoch": 0.01, + "learning_rate": 3.9546949185744154e-05, + "loss": 3.6515, + "step": 638464 + }, + { + "epoch": 0.01, + "learning_rate": 3.9538563238233634e-05, + "loss": 3.6619, + "step": 638976 + }, + { + "epoch": 0.01, + "learning_rate": 3.9530177290723114e-05, + "loss": 3.6658, + "step": 639488 + }, + { + "epoch": 0.01, + "learning_rate": 3.9521791343212594e-05, + "loss": 3.6617, + "step": 640000 + }, + { + "epoch": 0.01, + "learning_rate": 3.95134217745058e-05, + "loss": 3.6735, + "step": 640512 + }, + { + "epoch": 0.01, + "learning_rate": 3.950503582699528e-05, + "loss": 3.6612, + "step": 641024 + }, + { + "epoch": 0.01, + "learning_rate": 3.949664987948476e-05, + "loss": 3.6575, + "step": 641536 + }, + { + "epoch": 0.01, + "learning_rate": 3.948826393197424e-05, + "loss": 3.6702, + "step": 642048 + }, + { + "epoch": 0.01, + "learning_rate": 3.947987798446372e-05, + "loss": 3.648, + "step": 642560 + }, + { + "epoch": 0.01, + "learning_rate": 3.947150841575694e-05, + "loss": 3.6538, + "step": 643072 + }, + { + "epoch": 0.01, + "learning_rate": 3.946312246824642e-05, + "loss": 3.6667, + "step": 643584 + }, + { + "epoch": 0.01, + "learning_rate": 3.94547365207359e-05, + "loss": 3.6692, + "step": 644096 + }, + { + "epoch": 0.01, + "learning_rate": 3.944635057322538e-05, + "loss": 3.6517, + "step": 644608 + }, + { + "epoch": 0.01, + "learning_rate": 3.943798100451859e-05, + "loss": 3.6603, + "step": 645120 + }, + { + "epoch": 0.01, + "learning_rate": 3.942959505700807e-05, + "loss": 3.648, + "step": 645632 + }, + { + "epoch": 0.01, + "learning_rate": 3.942120910949755e-05, + "loss": 3.6713, + "step": 646144 + }, + { + "epoch": 0.01, + "learning_rate": 3.941282316198703e-05, + "loss": 3.6685, + "step": 646656 + }, + { + "epoch": 0.01, + "learning_rate": 3.9404453593280237e-05, + "loss": 3.6652, + "step": 647168 + }, + { + "epoch": 0.01, + "learning_rate": 3.9396067645769717e-05, + "loss": 3.6713, + "step": 647680 + }, + { + "epoch": 0.01, + "learning_rate": 3.9387681698259196e-05, + "loss": 3.6735, + "step": 648192 + }, + { + "epoch": 0.01, + "learning_rate": 3.9379295750748676e-05, + "loss": 3.6864, + "step": 648704 + }, + { + "epoch": 0.01, + "learning_rate": 3.937092618204189e-05, + "loss": 3.667, + "step": 649216 + }, + { + "epoch": 0.01, + "learning_rate": 3.936254023453137e-05, + "loss": 3.6675, + "step": 649728 + }, + { + "epoch": 0.01, + "learning_rate": 3.935415428702085e-05, + "loss": 3.6642, + "step": 650240 + }, + { + "epoch": 0.01, + "learning_rate": 3.934576833951033e-05, + "loss": 3.6601, + "step": 650752 + }, + { + "epoch": 0.01, + "learning_rate": 3.933739877080354e-05, + "loss": 3.6649, + "step": 651264 + }, + { + "epoch": 0.01, + "learning_rate": 3.932901282329302e-05, + "loss": 3.6684, + "step": 651776 + }, + { + "epoch": 0.01, + "learning_rate": 3.93206268757825e-05, + "loss": 3.67, + "step": 652288 + }, + { + "epoch": 0.01, + "learning_rate": 3.931224092827198e-05, + "loss": 3.6738, + "step": 652800 + }, + { + "epoch": 0.01, + "learning_rate": 3.930387135956519e-05, + "loss": 3.6532, + "step": 653312 + }, + { + "epoch": 0.01, + "learning_rate": 3.929548541205467e-05, + "loss": 3.6547, + "step": 653824 + }, + { + "epoch": 0.01, + "learning_rate": 3.928709946454415e-05, + "loss": 3.6564, + "step": 654336 + }, + { + "epoch": 0.01, + "learning_rate": 3.927871351703363e-05, + "loss": 3.677, + "step": 654848 + }, + { + "epoch": 0.01, + "learning_rate": 3.927032756952311e-05, + "loss": 3.6657, + "step": 655360 + }, + { + "epoch": 0.01, + "learning_rate": 3.9261958000816326e-05, + "loss": 3.6514, + "step": 655872 + }, + { + "epoch": 0.02, + "learning_rate": 3.9253572053305806e-05, + "loss": 3.6596, + "step": 656384 + }, + { + "epoch": 0.02, + "learning_rate": 3.924518610579528e-05, + "loss": 3.6672, + "step": 656896 + }, + { + "epoch": 0.02, + "learning_rate": 3.923680015828476e-05, + "loss": 3.6574, + "step": 657408 + }, + { + "epoch": 0.02, + "learning_rate": 3.922841421077424e-05, + "loss": 3.6554, + "step": 657920 + }, + { + "epoch": 0.02, + "learning_rate": 3.9220044642067455e-05, + "loss": 3.6751, + "step": 658432 + }, + { + "epoch": 0.02, + "learning_rate": 3.921165869455693e-05, + "loss": 3.6673, + "step": 658944 + }, + { + "epoch": 0.02, + "learning_rate": 3.920327274704641e-05, + "loss": 3.666, + "step": 659456 + }, + { + "epoch": 0.02, + "learning_rate": 3.919488679953589e-05, + "loss": 3.6559, + "step": 659968 + }, + { + "epoch": 0.02, + "learning_rate": 3.9186517230829104e-05, + "loss": 3.6593, + "step": 660480 + }, + { + "epoch": 0.02, + "learning_rate": 3.9178131283318584e-05, + "loss": 3.6588, + "step": 660992 + }, + { + "epoch": 0.02, + "learning_rate": 3.9169745335808064e-05, + "loss": 3.6687, + "step": 661504 + }, + { + "epoch": 0.02, + "learning_rate": 3.9161359388297544e-05, + "loss": 3.6671, + "step": 662016 + }, + { + "epoch": 0.02, + "learning_rate": 3.9152973440787024e-05, + "loss": 3.6658, + "step": 662528 + }, + { + "epoch": 0.02, + "learning_rate": 3.914460387208023e-05, + "loss": 3.6664, + "step": 663040 + }, + { + "epoch": 0.02, + "learning_rate": 3.913621792456971e-05, + "loss": 3.6594, + "step": 663552 + }, + { + "epoch": 0.02, + "learning_rate": 3.912783197705919e-05, + "loss": 3.6595, + "step": 664064 + }, + { + "epoch": 0.02, + "learning_rate": 3.911944602954867e-05, + "loss": 3.6517, + "step": 664576 + }, + { + "epoch": 0.02, + "learning_rate": 3.911107646084188e-05, + "loss": 3.6466, + "step": 665088 + }, + { + "epoch": 0.02, + "learning_rate": 3.910269051333136e-05, + "loss": 3.6692, + "step": 665600 + }, + { + "epoch": 0.02, + "learning_rate": 3.909430456582084e-05, + "loss": 3.6514, + "step": 666112 + }, + { + "epoch": 0.02, + "learning_rate": 3.908591861831032e-05, + "loss": 3.6484, + "step": 666624 + }, + { + "epoch": 0.02, + "learning_rate": 3.907754904960354e-05, + "loss": 3.6516, + "step": 667136 + }, + { + "epoch": 0.02, + "learning_rate": 3.906916310209302e-05, + "loss": 3.6556, + "step": 667648 + }, + { + "epoch": 0.02, + "learning_rate": 3.90607771545825e-05, + "loss": 3.6632, + "step": 668160 + }, + { + "epoch": 0.02, + "learning_rate": 3.905239120707198e-05, + "loss": 3.6518, + "step": 668672 + }, + { + "epoch": 0.02, + "learning_rate": 3.9044021638365186e-05, + "loss": 3.6629, + "step": 669184 + }, + { + "epoch": 0.02, + "learning_rate": 3.9035635690854666e-05, + "loss": 3.6644, + "step": 669696 + }, + { + "epoch": 0.02, + "learning_rate": 3.9027249743344146e-05, + "loss": 3.6616, + "step": 670208 + }, + { + "epoch": 0.02, + "learning_rate": 3.9018863795833626e-05, + "loss": 3.6634, + "step": 670720 + }, + { + "epoch": 0.02, + "learning_rate": 3.9010494227126835e-05, + "loss": 3.6615, + "step": 671232 + }, + { + "epoch": 0.02, + "learning_rate": 3.9002108279616315e-05, + "loss": 3.6607, + "step": 671744 + }, + { + "epoch": 0.02, + "learning_rate": 3.8993722332105795e-05, + "loss": 3.6616, + "step": 672256 + }, + { + "epoch": 0.02, + "learning_rate": 3.8985336384595275e-05, + "loss": 3.6627, + "step": 672768 + }, + { + "epoch": 0.02, + "learning_rate": 3.897696681588849e-05, + "loss": 3.6546, + "step": 673280 + }, + { + "epoch": 0.02, + "learning_rate": 3.896858086837797e-05, + "loss": 3.6643, + "step": 673792 + }, + { + "epoch": 0.02, + "learning_rate": 3.896019492086745e-05, + "loss": 3.6546, + "step": 674304 + }, + { + "epoch": 0.02, + "learning_rate": 3.895180897335693e-05, + "loss": 3.6547, + "step": 674816 + }, + { + "epoch": 0.02, + "learning_rate": 3.894342302584641e-05, + "loss": 3.6496, + "step": 675328 + }, + { + "epoch": 0.02, + "learning_rate": 3.893505345713962e-05, + "loss": 3.6511, + "step": 675840 + }, + { + "epoch": 0.02, + "learning_rate": 3.89266675096291e-05, + "loss": 3.6494, + "step": 676352 + }, + { + "epoch": 0.02, + "learning_rate": 3.891828156211858e-05, + "loss": 3.6621, + "step": 676864 + }, + { + "epoch": 0.02, + "learning_rate": 3.890989561460806e-05, + "loss": 3.6551, + "step": 677376 + }, + { + "epoch": 0.02, + "learning_rate": 3.890152604590127e-05, + "loss": 3.6675, + "step": 677888 + }, + { + "epoch": 0.02, + "learning_rate": 3.889314009839075e-05, + "loss": 3.6446, + "step": 678400 + }, + { + "epoch": 0.02, + "learning_rate": 3.888475415088023e-05, + "loss": 3.6658, + "step": 678912 + }, + { + "epoch": 0.02, + "learning_rate": 3.887636820336971e-05, + "loss": 3.6592, + "step": 679424 + }, + { + "epoch": 0.02, + "learning_rate": 3.8867998634662925e-05, + "loss": 3.6626, + "step": 679936 + }, + { + "epoch": 0.02, + "learning_rate": 3.8859612687152405e-05, + "loss": 3.6624, + "step": 680448 + }, + { + "epoch": 0.02, + "learning_rate": 3.8851226739641885e-05, + "loss": 3.6552, + "step": 680960 + }, + { + "epoch": 0.02, + "learning_rate": 3.8842840792131365e-05, + "loss": 3.661, + "step": 681472 + }, + { + "epoch": 0.02, + "learning_rate": 3.8834471223424574e-05, + "loss": 3.6699, + "step": 681984 + }, + { + "epoch": 0.02, + "learning_rate": 3.8826085275914054e-05, + "loss": 3.6499, + "step": 682496 + }, + { + "epoch": 0.02, + "learning_rate": 3.8817699328403534e-05, + "loss": 3.6607, + "step": 683008 + }, + { + "epoch": 0.02, + "learning_rate": 3.8809313380893014e-05, + "loss": 3.6581, + "step": 683520 + }, + { + "epoch": 0.02, + "learning_rate": 3.880094381218622e-05, + "loss": 3.6547, + "step": 684032 + }, + { + "epoch": 0.02, + "learning_rate": 3.87925578646757e-05, + "loss": 3.6572, + "step": 684544 + }, + { + "epoch": 0.02, + "learning_rate": 3.878417191716518e-05, + "loss": 3.6559, + "step": 685056 + }, + { + "epoch": 0.02, + "learning_rate": 3.877578596965466e-05, + "loss": 3.6666, + "step": 685568 + }, + { + "epoch": 0.02, + "learning_rate": 3.876740002214414e-05, + "loss": 3.6532, + "step": 686080 + }, + { + "epoch": 0.02, + "learning_rate": 3.875903045343736e-05, + "loss": 3.6612, + "step": 686592 + }, + { + "epoch": 0.03, + "eval_loss": 3.847689390182495, + "eval_runtime": 310.6019, + "eval_samples_per_second": 1228.553, + "eval_steps_per_second": 38.393, + "step": 686880 + }, + { + "epoch": 1.0, + "learning_rate": 3.875064450592684e-05, + "loss": 3.6488, + "step": 687104 + }, + { + "epoch": 1.0, + "learning_rate": 3.874225855841632e-05, + "loss": 3.6459, + "step": 687616 + }, + { + "epoch": 1.0, + "learning_rate": 3.87338726109058e-05, + "loss": 3.652, + "step": 688128 + }, + { + "epoch": 1.0, + "learning_rate": 3.872550304219901e-05, + "loss": 3.6552, + "step": 688640 + }, + { + "epoch": 1.0, + "learning_rate": 3.871711709468849e-05, + "loss": 3.669, + "step": 689152 + }, + { + "epoch": 1.0, + "learning_rate": 3.870873114717797e-05, + "loss": 3.651, + "step": 689664 + }, + { + "epoch": 1.0, + "learning_rate": 3.870034519966745e-05, + "loss": 3.6495, + "step": 690176 + }, + { + "epoch": 1.0, + "learning_rate": 3.8691975630960656e-05, + "loss": 3.6461, + "step": 690688 + }, + { + "epoch": 1.0, + "learning_rate": 3.8683589683450136e-05, + "loss": 3.6442, + "step": 691200 + }, + { + "epoch": 1.0, + "learning_rate": 3.8675203735939616e-05, + "loss": 3.66, + "step": 691712 + }, + { + "epoch": 1.0, + "learning_rate": 3.8666817788429096e-05, + "loss": 3.6473, + "step": 692224 + }, + { + "epoch": 1.0, + "learning_rate": 3.865844821972231e-05, + "loss": 3.6492, + "step": 692736 + }, + { + "epoch": 1.0, + "learning_rate": 3.865006227221179e-05, + "loss": 3.6593, + "step": 693248 + }, + { + "epoch": 1.0, + "learning_rate": 3.864167632470127e-05, + "loss": 3.6391, + "step": 693760 + }, + { + "epoch": 1.0, + "learning_rate": 3.863329037719075e-05, + "loss": 3.6479, + "step": 694272 + }, + { + "epoch": 1.0, + "learning_rate": 3.862492080848396e-05, + "loss": 3.6416, + "step": 694784 + }, + { + "epoch": 1.0, + "learning_rate": 3.861653486097344e-05, + "loss": 3.6446, + "step": 695296 + }, + { + "epoch": 1.0, + "learning_rate": 3.860814891346292e-05, + "loss": 3.6444, + "step": 695808 + }, + { + "epoch": 1.0, + "learning_rate": 3.85997629659524e-05, + "loss": 3.6528, + "step": 696320 + }, + { + "epoch": 1.0, + "learning_rate": 3.859137701844188e-05, + "loss": 3.6522, + "step": 696832 + }, + { + "epoch": 1.0, + "learning_rate": 3.858300744973509e-05, + "loss": 3.6615, + "step": 697344 + }, + { + "epoch": 1.0, + "learning_rate": 3.857462150222457e-05, + "loss": 3.6497, + "step": 697856 + }, + { + "epoch": 1.0, + "learning_rate": 3.856623555471405e-05, + "loss": 3.6513, + "step": 698368 + }, + { + "epoch": 1.0, + "learning_rate": 3.8557849607203537e-05, + "loss": 3.6462, + "step": 698880 + }, + { + "epoch": 1.0, + "learning_rate": 3.854946365969301e-05, + "loss": 3.6449, + "step": 699392 + }, + { + "epoch": 1.0, + "learning_rate": 3.8541094090986226e-05, + "loss": 3.6555, + "step": 699904 + }, + { + "epoch": 1.0, + "learning_rate": 3.8532708143475706e-05, + "loss": 3.6415, + "step": 700416 + }, + { + "epoch": 1.0, + "learning_rate": 3.8524322195965185e-05, + "loss": 3.6534, + "step": 700928 + }, + { + "epoch": 1.0, + "learning_rate": 3.851593624845466e-05, + "loss": 3.6342, + "step": 701440 + }, + { + "epoch": 1.0, + "learning_rate": 3.8507566679747875e-05, + "loss": 3.6435, + "step": 701952 + }, + { + "epoch": 1.01, + "learning_rate": 3.8499180732237354e-05, + "loss": 3.6454, + "step": 702464 + }, + { + "epoch": 1.01, + "learning_rate": 3.849079478472683e-05, + "loss": 3.6491, + "step": 702976 + }, + { + "epoch": 1.01, + "learning_rate": 3.848240883721631e-05, + "loss": 3.6575, + "step": 703488 + }, + { + "epoch": 1.01, + "learning_rate": 3.8474039268509524e-05, + "loss": 3.6557, + "step": 704000 + }, + { + "epoch": 1.01, + "learning_rate": 3.8465653320999003e-05, + "loss": 3.6472, + "step": 704512 + }, + { + "epoch": 1.01, + "learning_rate": 3.8457267373488483e-05, + "loss": 3.6421, + "step": 705024 + }, + { + "epoch": 1.01, + "learning_rate": 3.844888142597796e-05, + "loss": 3.6579, + "step": 705536 + }, + { + "epoch": 1.01, + "learning_rate": 3.844051185727118e-05, + "loss": 3.6434, + "step": 706048 + }, + { + "epoch": 1.01, + "learning_rate": 3.843212590976066e-05, + "loss": 3.641, + "step": 706560 + }, + { + "epoch": 1.01, + "learning_rate": 3.842373996225013e-05, + "loss": 3.6456, + "step": 707072 + }, + { + "epoch": 1.01, + "learning_rate": 3.841535401473961e-05, + "loss": 3.6473, + "step": 707584 + }, + { + "epoch": 1.01, + "learning_rate": 3.840696806722909e-05, + "loss": 3.6461, + "step": 708096 + }, + { + "epoch": 1.01, + "learning_rate": 3.839858211971857e-05, + "loss": 3.647, + "step": 708608 + }, + { + "epoch": 1.01, + "learning_rate": 3.839021255101178e-05, + "loss": 3.6476, + "step": 709120 + }, + { + "epoch": 1.01, + "learning_rate": 3.838182660350126e-05, + "loss": 3.6482, + "step": 709632 + }, + { + "epoch": 1.01, + "learning_rate": 3.837344065599074e-05, + "loss": 3.6492, + "step": 710144 + }, + { + "epoch": 1.01, + "learning_rate": 3.836505470848023e-05, + "loss": 3.646, + "step": 710656 + }, + { + "epoch": 1.01, + "learning_rate": 3.835668513977344e-05, + "loss": 3.6492, + "step": 711168 + }, + { + "epoch": 1.01, + "learning_rate": 3.834829919226292e-05, + "loss": 3.6127, + "step": 711680 + }, + { + "epoch": 1.01, + "learning_rate": 3.83399132447524e-05, + "loss": 3.6557, + "step": 712192 + }, + { + "epoch": 1.01, + "learning_rate": 3.833152729724188e-05, + "loss": 3.6383, + "step": 712704 + }, + { + "epoch": 1.01, + "learning_rate": 3.832314134973136e-05, + "loss": 3.6527, + "step": 713216 + }, + { + "epoch": 1.01, + "learning_rate": 3.8314771781024566e-05, + "loss": 3.6342, + "step": 713728 + }, + { + "epoch": 1.01, + "learning_rate": 3.8306385833514046e-05, + "loss": 3.628, + "step": 714240 + }, + { + "epoch": 1.01, + "learning_rate": 3.8297999886003526e-05, + "loss": 3.626, + "step": 714752 + }, + { + "epoch": 1.01, + "learning_rate": 3.8289613938493006e-05, + "loss": 3.6358, + "step": 715264 + }, + { + "epoch": 1.01, + "learning_rate": 3.8281244369786215e-05, + "loss": 3.6467, + "step": 715776 + }, + { + "epoch": 1.01, + "learning_rate": 3.8272858422275695e-05, + "loss": 3.6307, + "step": 716288 + }, + { + "epoch": 1.01, + "learning_rate": 3.826447247476518e-05, + "loss": 3.6502, + "step": 716800 + }, + { + "epoch": 1.01, + "learning_rate": 3.825608652725466e-05, + "loss": 3.6413, + "step": 717312 + }, + { + "epoch": 1.01, + "learning_rate": 3.824771695854787e-05, + "loss": 3.6255, + "step": 717824 + }, + { + "epoch": 1.01, + "learning_rate": 3.823933101103735e-05, + "loss": 3.6458, + "step": 718336 + }, + { + "epoch": 1.01, + "learning_rate": 3.823094506352683e-05, + "loss": 3.6276, + "step": 718848 + }, + { + "epoch": 1.01, + "learning_rate": 3.822255911601631e-05, + "loss": 3.6273, + "step": 719360 + }, + { + "epoch": 1.01, + "learning_rate": 3.821417316850579e-05, + "loss": 3.6407, + "step": 719872 + }, + { + "epoch": 1.01, + "learning_rate": 3.8205803599799e-05, + "loss": 3.6466, + "step": 720384 + }, + { + "epoch": 1.01, + "learning_rate": 3.819741765228848e-05, + "loss": 3.629, + "step": 720896 + }, + { + "epoch": 1.01, + "learning_rate": 3.818903170477796e-05, + "loss": 3.634, + "step": 721408 + }, + { + "epoch": 1.01, + "learning_rate": 3.818064575726744e-05, + "loss": 3.624, + "step": 721920 + }, + { + "epoch": 1.01, + "learning_rate": 3.817227618856065e-05, + "loss": 3.6441, + "step": 722432 + }, + { + "epoch": 1.01, + "learning_rate": 3.8163890241050135e-05, + "loss": 3.6452, + "step": 722944 + }, + { + "epoch": 1.01, + "learning_rate": 3.8155504293539615e-05, + "loss": 3.6394, + "step": 723456 + }, + { + "epoch": 1.01, + "learning_rate": 3.8147118346029095e-05, + "loss": 3.6455, + "step": 723968 + }, + { + "epoch": 1.01, + "learning_rate": 3.8138748777322304e-05, + "loss": 3.6483, + "step": 724480 + }, + { + "epoch": 1.01, + "learning_rate": 3.8130362829811784e-05, + "loss": 3.6608, + "step": 724992 + }, + { + "epoch": 1.01, + "learning_rate": 3.8121976882301264e-05, + "loss": 3.6412, + "step": 725504 + }, + { + "epoch": 1.01, + "learning_rate": 3.8113590934790744e-05, + "loss": 3.6456, + "step": 726016 + }, + { + "epoch": 1.01, + "learning_rate": 3.810522136608395e-05, + "loss": 3.6356, + "step": 726528 + }, + { + "epoch": 1.01, + "learning_rate": 3.809683541857343e-05, + "loss": 3.6385, + "step": 727040 + }, + { + "epoch": 1.01, + "learning_rate": 3.808844947106291e-05, + "loss": 3.6348, + "step": 727552 + }, + { + "epoch": 1.01, + "learning_rate": 3.808006352355239e-05, + "loss": 3.6481, + "step": 728064 + }, + { + "epoch": 1.01, + "learning_rate": 3.80716939548456e-05, + "loss": 3.6422, + "step": 728576 + }, + { + "epoch": 1.01, + "learning_rate": 3.806330800733509e-05, + "loss": 3.6532, + "step": 729088 + }, + { + "epoch": 1.01, + "learning_rate": 3.805492205982457e-05, + "loss": 3.6272, + "step": 729600 + }, + { + "epoch": 1.01, + "learning_rate": 3.804653611231405e-05, + "loss": 3.6304, + "step": 730112 + }, + { + "epoch": 1.01, + "learning_rate": 3.803816654360726e-05, + "loss": 3.6361, + "step": 730624 + }, + { + "epoch": 1.01, + "learning_rate": 3.802978059609674e-05, + "loss": 3.6459, + "step": 731136 + }, + { + "epoch": 1.01, + "learning_rate": 3.802139464858622e-05, + "loss": 3.6419, + "step": 731648 + }, + { + "epoch": 1.01, + "learning_rate": 3.80130087010757e-05, + "loss": 3.6309, + "step": 732160 + }, + { + "epoch": 1.02, + "learning_rate": 3.800463913236891e-05, + "loss": 3.6343, + "step": 732672 + }, + { + "epoch": 1.02, + "learning_rate": 3.799625318485839e-05, + "loss": 3.6432, + "step": 733184 + }, + { + "epoch": 1.02, + "learning_rate": 3.798786723734787e-05, + "loss": 3.631, + "step": 733696 + }, + { + "epoch": 1.02, + "learning_rate": 3.797948128983735e-05, + "loss": 3.631, + "step": 734208 + }, + { + "epoch": 1.02, + "learning_rate": 3.7971111721130556e-05, + "loss": 3.6512, + "step": 734720 + }, + { + "epoch": 1.02, + "learning_rate": 3.7962725773620036e-05, + "loss": 3.6427, + "step": 735232 + }, + { + "epoch": 1.02, + "learning_rate": 3.795433982610952e-05, + "loss": 3.6433, + "step": 735744 + }, + { + "epoch": 1.02, + "learning_rate": 3.7945953878599e-05, + "loss": 3.6286, + "step": 736256 + }, + { + "epoch": 1.02, + "learning_rate": 3.793758430989221e-05, + "loss": 3.6353, + "step": 736768 + }, + { + "epoch": 1.02, + "learning_rate": 3.792919836238169e-05, + "loss": 3.6295, + "step": 737280 + }, + { + "epoch": 1.02, + "learning_rate": 3.792081241487117e-05, + "loss": 3.6451, + "step": 737792 + }, + { + "epoch": 1.02, + "learning_rate": 3.791242646736065e-05, + "loss": 3.6446, + "step": 738304 + }, + { + "epoch": 1.02, + "learning_rate": 3.790404051985013e-05, + "loss": 3.6388, + "step": 738816 + }, + { + "epoch": 1.02, + "learning_rate": 3.789567095114334e-05, + "loss": 3.6431, + "step": 739328 + }, + { + "epoch": 1.02, + "learning_rate": 3.788728500363282e-05, + "loss": 3.6351, + "step": 739840 + }, + { + "epoch": 1.02, + "learning_rate": 3.78788990561223e-05, + "loss": 3.6382, + "step": 740352 + }, + { + "epoch": 1.02, + "learning_rate": 3.787051310861178e-05, + "loss": 3.6241, + "step": 740864 + }, + { + "epoch": 1.02, + "learning_rate": 3.786214353990499e-05, + "loss": 3.6268, + "step": 741376 + }, + { + "epoch": 1.02, + "learning_rate": 3.7853757592394476e-05, + "loss": 3.6393, + "step": 741888 + }, + { + "epoch": 1.02, + "learning_rate": 3.7845371644883956e-05, + "loss": 3.6345, + "step": 742400 + }, + { + "epoch": 1.02, + "learning_rate": 3.7836985697373436e-05, + "loss": 3.6211, + "step": 742912 + }, + { + "epoch": 1.02, + "learning_rate": 3.7828616128666645e-05, + "loss": 3.629, + "step": 743424 + }, + { + "epoch": 1.02, + "learning_rate": 3.7820230181156125e-05, + "loss": 3.6295, + "step": 743936 + }, + { + "epoch": 1.02, + "learning_rate": 3.7811844233645605e-05, + "loss": 3.6385, + "step": 744448 + }, + { + "epoch": 1.02, + "learning_rate": 3.7803458286135085e-05, + "loss": 3.6291, + "step": 744960 + }, + { + "epoch": 1.02, + "learning_rate": 3.7795088717428294e-05, + "loss": 3.6402, + "step": 745472 + }, + { + "epoch": 1.02, + "learning_rate": 3.7786702769917774e-05, + "loss": 3.6427, + "step": 745984 + }, + { + "epoch": 1.02, + "learning_rate": 3.7778316822407254e-05, + "loss": 3.6378, + "step": 746496 + }, + { + "epoch": 1.02, + "learning_rate": 3.7769930874896734e-05, + "loss": 3.6341, + "step": 747008 + }, + { + "epoch": 1.02, + "learning_rate": 3.776156130618994e-05, + "loss": 3.6427, + "step": 747520 + }, + { + "epoch": 1.02, + "learning_rate": 3.775317535867943e-05, + "loss": 3.6371, + "step": 748032 + }, + { + "epoch": 1.02, + "learning_rate": 3.774478941116891e-05, + "loss": 3.6401, + "step": 748544 + }, + { + "epoch": 1.02, + "learning_rate": 3.773640346365838e-05, + "loss": 3.6375, + "step": 749056 + }, + { + "epoch": 1.02, + "learning_rate": 3.77280338949516e-05, + "loss": 3.6294, + "step": 749568 + }, + { + "epoch": 1.02, + "learning_rate": 3.771964794744108e-05, + "loss": 3.6382, + "step": 750080 + }, + { + "epoch": 1.02, + "learning_rate": 3.771126199993056e-05, + "loss": 3.6371, + "step": 750592 + }, + { + "epoch": 1.02, + "learning_rate": 3.770287605242003e-05, + "loss": 3.6291, + "step": 751104 + }, + { + "epoch": 1.02, + "learning_rate": 3.769450648371325e-05, + "loss": 3.6291, + "step": 751616 + }, + { + "epoch": 1.02, + "learning_rate": 3.768612053620273e-05, + "loss": 3.6295, + "step": 752128 + }, + { + "epoch": 1.02, + "learning_rate": 3.767773458869221e-05, + "loss": 3.6226, + "step": 752640 + }, + { + "epoch": 1.02, + "learning_rate": 3.766934864118168e-05, + "loss": 3.6408, + "step": 753152 + }, + { + "epoch": 1.02, + "learning_rate": 3.76609790724749e-05, + "loss": 3.6302, + "step": 753664 + }, + { + "epoch": 1.02, + "learning_rate": 3.7652593124964384e-05, + "loss": 3.6433, + "step": 754176 + }, + { + "epoch": 1.02, + "learning_rate": 3.764420717745386e-05, + "loss": 3.6205, + "step": 754688 + }, + { + "epoch": 1.02, + "learning_rate": 3.763582122994334e-05, + "loss": 3.641, + "step": 755200 + }, + { + "epoch": 1.02, + "learning_rate": 3.762745166123655e-05, + "loss": 3.6374, + "step": 755712 + }, + { + "epoch": 1.02, + "learning_rate": 3.761906571372603e-05, + "loss": 3.6398, + "step": 756224 + }, + { + "epoch": 1.02, + "learning_rate": 3.7610679766215506e-05, + "loss": 3.6362, + "step": 756736 + }, + { + "epoch": 1.02, + "learning_rate": 3.7602293818704986e-05, + "loss": 3.6292, + "step": 757248 + }, + { + "epoch": 1.02, + "learning_rate": 3.75939242499982e-05, + "loss": 3.6408, + "step": 757760 + }, + { + "epoch": 1.02, + "learning_rate": 3.7585538302487675e-05, + "loss": 3.6435, + "step": 758272 + }, + { + "epoch": 1.02, + "learning_rate": 3.7577152354977155e-05, + "loss": 3.6288, + "step": 758784 + }, + { + "epoch": 1.02, + "learning_rate": 3.7568766407466635e-05, + "loss": 3.6353, + "step": 759296 + }, + { + "epoch": 1.02, + "learning_rate": 3.756038045995612e-05, + "loss": 3.6371, + "step": 759808 + }, + { + "epoch": 1.02, + "learning_rate": 3.755201089124933e-05, + "loss": 3.6311, + "step": 760320 + }, + { + "epoch": 1.02, + "learning_rate": 3.754362494373881e-05, + "loss": 3.6332, + "step": 760832 + }, + { + "epoch": 1.02, + "learning_rate": 3.753523899622829e-05, + "loss": 3.6317, + "step": 761344 + }, + { + "epoch": 1.02, + "learning_rate": 3.752685304871777e-05, + "loss": 3.6404, + "step": 761856 + }, + { + "epoch": 1.02, + "learning_rate": 3.751848348001098e-05, + "loss": 3.6316, + "step": 762368 + }, + { + "epoch": 1.02, + "learning_rate": 3.751009753250046e-05, + "loss": 3.6364, + "step": 762880 + }, + { + "epoch": 1.03, + "eval_loss": 3.844886541366577, + "eval_runtime": 313.0236, + "eval_samples_per_second": 1219.049, + "eval_steps_per_second": 38.096, + "step": 763200 + }, + { + "epoch": 0.0, + "learning_rate": 3.750171158498994e-05, + "loss": 3.6235, + "step": 763392 + }, + { + "epoch": 0.0, + "learning_rate": 3.749332563747942e-05, + "loss": 3.6226, + "step": 763904 + }, + { + "epoch": 0.0, + "learning_rate": 3.74849396899689e-05, + "loss": 3.6283, + "step": 764416 + }, + { + "epoch": 0.0, + "learning_rate": 3.747655374245838e-05, + "loss": 3.6317, + "step": 764928 + }, + { + "epoch": 0.0, + "learning_rate": 3.746818417375159e-05, + "loss": 3.646, + "step": 765440 + }, + { + "epoch": 0.0, + "learning_rate": 3.7459798226241075e-05, + "loss": 3.6323, + "step": 765952 + }, + { + "epoch": 0.0, + "learning_rate": 3.7451412278730555e-05, + "loss": 3.6239, + "step": 766464 + }, + { + "epoch": 0.0, + "learning_rate": 3.7443026331220035e-05, + "loss": 3.6245, + "step": 766976 + }, + { + "epoch": 0.0, + "learning_rate": 3.7434656762513244e-05, + "loss": 3.621, + "step": 767488 + }, + { + "epoch": 0.0, + "learning_rate": 3.7426270815002724e-05, + "loss": 3.6318, + "step": 768000 + }, + { + "epoch": 0.0, + "learning_rate": 3.7417884867492204e-05, + "loss": 3.6266, + "step": 768512 + }, + { + "epoch": 0.0, + "learning_rate": 3.7409498919981684e-05, + "loss": 3.6295, + "step": 769024 + }, + { + "epoch": 0.0, + "learning_rate": 3.740112935127489e-05, + "loss": 3.6331, + "step": 769536 + }, + { + "epoch": 0.0, + "learning_rate": 3.739274340376437e-05, + "loss": 3.6145, + "step": 770048 + }, + { + "epoch": 0.0, + "learning_rate": 3.738435745625385e-05, + "loss": 3.6259, + "step": 770560 + }, + { + "epoch": 0.0, + "learning_rate": 3.737597150874333e-05, + "loss": 3.6162, + "step": 771072 + }, + { + "epoch": 0.0, + "learning_rate": 3.736760194003654e-05, + "loss": 3.6284, + "step": 771584 + }, + { + "epoch": 0.0, + "learning_rate": 3.735921599252603e-05, + "loss": 3.6214, + "step": 772096 + }, + { + "epoch": 0.0, + "learning_rate": 3.735083004501551e-05, + "loss": 3.6274, + "step": 772608 + }, + { + "epoch": 0.0, + "learning_rate": 3.734244409750499e-05, + "loss": 3.6258, + "step": 773120 + }, + { + "epoch": 0.0, + "learning_rate": 3.733405814999447e-05, + "loss": 3.6387, + "step": 773632 + }, + { + "epoch": 0.0, + "learning_rate": 3.732568858128768e-05, + "loss": 3.626, + "step": 774144 + }, + { + "epoch": 0.0, + "learning_rate": 3.731730263377716e-05, + "loss": 3.6308, + "step": 774656 + }, + { + "epoch": 0.0, + "learning_rate": 3.730891668626664e-05, + "loss": 3.6251, + "step": 775168 + }, + { + "epoch": 0.0, + "learning_rate": 3.730053073875612e-05, + "loss": 3.6231, + "step": 775680 + }, + { + "epoch": 0.0, + "learning_rate": 3.729216117004933e-05, + "loss": 3.6323, + "step": 776192 + }, + { + "epoch": 0.0, + "learning_rate": 3.728377522253881e-05, + "loss": 3.6172, + "step": 776704 + }, + { + "epoch": 0.0, + "learning_rate": 3.7275389275028287e-05, + "loss": 3.6265, + "step": 777216 + }, + { + "epoch": 0.0, + "learning_rate": 3.7267003327517767e-05, + "loss": 3.6171, + "step": 777728 + }, + { + "epoch": 0.0, + "learning_rate": 3.725863375881098e-05, + "loss": 3.6194, + "step": 778240 + }, + { + "epoch": 0.01, + "learning_rate": 3.725024781130046e-05, + "loss": 3.6253, + "step": 778752 + }, + { + "epoch": 0.01, + "learning_rate": 3.724186186378994e-05, + "loss": 3.6263, + "step": 779264 + }, + { + "epoch": 0.01, + "learning_rate": 3.723347591627942e-05, + "loss": 3.6265, + "step": 779776 + }, + { + "epoch": 0.01, + "learning_rate": 3.72250899687689e-05, + "loss": 3.6378, + "step": 780288 + }, + { + "epoch": 0.01, + "learning_rate": 3.721672040006211e-05, + "loss": 3.6189, + "step": 780800 + }, + { + "epoch": 0.01, + "learning_rate": 3.720833445255159e-05, + "loss": 3.622, + "step": 781312 + }, + { + "epoch": 0.01, + "learning_rate": 3.719994850504107e-05, + "loss": 3.6361, + "step": 781824 + }, + { + "epoch": 0.01, + "learning_rate": 3.719157893633428e-05, + "loss": 3.6205, + "step": 782336 + }, + { + "epoch": 0.01, + "learning_rate": 3.718319298882376e-05, + "loss": 3.6189, + "step": 782848 + }, + { + "epoch": 0.01, + "learning_rate": 3.717480704131324e-05, + "loss": 3.6242, + "step": 783360 + }, + { + "epoch": 0.01, + "learning_rate": 3.716642109380272e-05, + "loss": 3.62, + "step": 783872 + }, + { + "epoch": 0.01, + "learning_rate": 3.71580351462922e-05, + "loss": 3.6261, + "step": 784384 + }, + { + "epoch": 0.01, + "learning_rate": 3.7149665577585416e-05, + "loss": 3.6228, + "step": 784896 + }, + { + "epoch": 0.01, + "learning_rate": 3.7141279630074896e-05, + "loss": 3.6293, + "step": 785408 + }, + { + "epoch": 0.01, + "learning_rate": 3.7132893682564376e-05, + "loss": 3.6207, + "step": 785920 + }, + { + "epoch": 0.01, + "learning_rate": 3.7124507735053856e-05, + "loss": 3.6308, + "step": 786432 + }, + { + "epoch": 0.01, + "learning_rate": 3.7116138166347065e-05, + "loss": 3.6225, + "step": 786944 + }, + { + "epoch": 0.01, + "learning_rate": 3.7107752218836545e-05, + "loss": 3.629, + "step": 787456 + }, + { + "epoch": 0.01, + "learning_rate": 3.7099366271326025e-05, + "loss": 3.5933, + "step": 787968 + }, + { + "epoch": 0.01, + "learning_rate": 3.7090980323815505e-05, + "loss": 3.6335, + "step": 788480 + }, + { + "epoch": 0.01, + "learning_rate": 3.7082610755108714e-05, + "loss": 3.6127, + "step": 788992 + }, + { + "epoch": 0.01, + "learning_rate": 3.7074224807598194e-05, + "loss": 3.6284, + "step": 789504 + }, + { + "epoch": 0.01, + "learning_rate": 3.7065838860087674e-05, + "loss": 3.6106, + "step": 790016 + }, + { + "epoch": 0.01, + "learning_rate": 3.7057452912577154e-05, + "loss": 3.6061, + "step": 790528 + }, + { + "epoch": 0.01, + "learning_rate": 3.704908334387037e-05, + "loss": 3.6033, + "step": 791040 + }, + { + "epoch": 0.01, + "learning_rate": 3.704069739635985e-05, + "loss": 3.6144, + "step": 791552 + }, + { + "epoch": 0.01, + "learning_rate": 3.703231144884933e-05, + "loss": 3.624, + "step": 792064 + }, + { + "epoch": 0.01, + "learning_rate": 3.702392550133881e-05, + "loss": 3.6088, + "step": 792576 + }, + { + "epoch": 0.01, + "learning_rate": 3.701555593263202e-05, + "loss": 3.6281, + "step": 793088 + }, + { + "epoch": 0.01, + "learning_rate": 3.70071699851215e-05, + "loss": 3.6219, + "step": 793600 + }, + { + "epoch": 0.01, + "learning_rate": 3.699878403761098e-05, + "loss": 3.6027, + "step": 794112 + }, + { + "epoch": 0.01, + "learning_rate": 3.699039809010046e-05, + "loss": 3.6231, + "step": 794624 + }, + { + "epoch": 0.01, + "learning_rate": 3.698202852139367e-05, + "loss": 3.6042, + "step": 795136 + }, + { + "epoch": 0.01, + "learning_rate": 3.697364257388315e-05, + "loss": 3.6054, + "step": 795648 + }, + { + "epoch": 0.01, + "learning_rate": 3.696525662637263e-05, + "loss": 3.6188, + "step": 796160 + }, + { + "epoch": 0.01, + "learning_rate": 3.695687067886211e-05, + "loss": 3.6213, + "step": 796672 + }, + { + "epoch": 0.01, + "learning_rate": 3.694850111015532e-05, + "loss": 3.6037, + "step": 797184 + }, + { + "epoch": 0.01, + "learning_rate": 3.69401151626448e-05, + "loss": 3.6193, + "step": 797696 + }, + { + "epoch": 0.01, + "learning_rate": 3.693172921513428e-05, + "loss": 3.6031, + "step": 798208 + }, + { + "epoch": 0.01, + "learning_rate": 3.6923343267623756e-05, + "loss": 3.6181, + "step": 798720 + }, + { + "epoch": 0.01, + "learning_rate": 3.691497369891697e-05, + "loss": 3.6231, + "step": 799232 + }, + { + "epoch": 0.01, + "learning_rate": 3.690658775140645e-05, + "loss": 3.6161, + "step": 799744 + }, + { + "epoch": 0.01, + "learning_rate": 3.689820180389593e-05, + "loss": 3.6264, + "step": 800256 + }, + { + "epoch": 0.01, + "learning_rate": 3.6889815856385405e-05, + "loss": 3.6238, + "step": 800768 + }, + { + "epoch": 0.01, + "learning_rate": 3.688144628767862e-05, + "loss": 3.6381, + "step": 801280 + }, + { + "epoch": 0.01, + "learning_rate": 3.68730603401681e-05, + "loss": 3.6226, + "step": 801792 + }, + { + "epoch": 0.01, + "learning_rate": 3.686467439265758e-05, + "loss": 3.6265, + "step": 802304 + }, + { + "epoch": 0.01, + "learning_rate": 3.685628844514706e-05, + "loss": 3.6121, + "step": 802816 + }, + { + "epoch": 0.01, + "learning_rate": 3.684791887644028e-05, + "loss": 3.617, + "step": 803328 + }, + { + "epoch": 0.01, + "learning_rate": 3.683953292892976e-05, + "loss": 3.6147, + "step": 803840 + }, + { + "epoch": 0.01, + "learning_rate": 3.683114698141923e-05, + "loss": 3.6223, + "step": 804352 + }, + { + "epoch": 0.01, + "learning_rate": 3.682276103390871e-05, + "loss": 3.6241, + "step": 804864 + }, + { + "epoch": 0.01, + "learning_rate": 3.6814391465201926e-05, + "loss": 3.6284, + "step": 805376 + }, + { + "epoch": 0.01, + "learning_rate": 3.6806005517691406e-05, + "loss": 3.605, + "step": 805888 + }, + { + "epoch": 0.01, + "learning_rate": 3.679761957018088e-05, + "loss": 3.6092, + "step": 806400 + }, + { + "epoch": 0.01, + "learning_rate": 3.678923362267036e-05, + "loss": 3.612, + "step": 806912 + }, + { + "epoch": 0.01, + "learning_rate": 3.6780864053963575e-05, + "loss": 3.6269, + "step": 807424 + }, + { + "epoch": 0.01, + "learning_rate": 3.6772478106453055e-05, + "loss": 3.6179, + "step": 807936 + }, + { + "epoch": 0.01, + "learning_rate": 3.676409215894253e-05, + "loss": 3.6105, + "step": 808448 + }, + { + "epoch": 0.01, + "learning_rate": 3.6755706211432015e-05, + "loss": 3.6157, + "step": 808960 + }, + { + "epoch": 0.02, + "learning_rate": 3.674733664272523e-05, + "loss": 3.6189, + "step": 809472 + }, + { + "epoch": 0.02, + "learning_rate": 3.6738950695214704e-05, + "loss": 3.6105, + "step": 809984 + }, + { + "epoch": 0.02, + "learning_rate": 3.6730564747704184e-05, + "loss": 3.6109, + "step": 810496 + }, + { + "epoch": 0.02, + "learning_rate": 3.6722178800193664e-05, + "loss": 3.6283, + "step": 811008 + }, + { + "epoch": 0.02, + "learning_rate": 3.671380923148688e-05, + "loss": 3.6238, + "step": 811520 + }, + { + "epoch": 0.02, + "learning_rate": 3.670542328397635e-05, + "loss": 3.6202, + "step": 812032 + }, + { + "epoch": 0.02, + "learning_rate": 3.669703733646583e-05, + "loss": 3.6064, + "step": 812544 + }, + { + "epoch": 0.02, + "learning_rate": 3.668865138895531e-05, + "loss": 3.6132, + "step": 813056 + }, + { + "epoch": 0.02, + "learning_rate": 3.668028182024853e-05, + "loss": 3.613, + "step": 813568 + }, + { + "epoch": 0.02, + "learning_rate": 3.6671895872738e-05, + "loss": 3.6198, + "step": 814080 + }, + { + "epoch": 0.02, + "learning_rate": 3.666350992522748e-05, + "loss": 3.625, + "step": 814592 + }, + { + "epoch": 0.02, + "learning_rate": 3.665512397771697e-05, + "loss": 3.6156, + "step": 815104 + }, + { + "epoch": 0.02, + "learning_rate": 3.664673803020645e-05, + "loss": 3.6209, + "step": 815616 + }, + { + "epoch": 0.02, + "learning_rate": 3.663836846149966e-05, + "loss": 3.6167, + "step": 816128 + }, + { + "epoch": 0.02, + "learning_rate": 3.662998251398914e-05, + "loss": 3.6185, + "step": 816640 + }, + { + "epoch": 0.02, + "learning_rate": 3.662159656647862e-05, + "loss": 3.6062, + "step": 817152 + }, + { + "epoch": 0.02, + "learning_rate": 3.66132106189681e-05, + "loss": 3.6055, + "step": 817664 + }, + { + "epoch": 0.02, + "learning_rate": 3.6604841050261307e-05, + "loss": 3.6168, + "step": 818176 + }, + { + "epoch": 0.02, + "learning_rate": 3.6596455102750786e-05, + "loss": 3.6108, + "step": 818688 + }, + { + "epoch": 0.02, + "learning_rate": 3.6588069155240266e-05, + "loss": 3.6026, + "step": 819200 + }, + { + "epoch": 0.02, + "learning_rate": 3.6579683207729746e-05, + "loss": 3.6083, + "step": 819712 + }, + { + "epoch": 0.02, + "learning_rate": 3.6571313639022955e-05, + "loss": 3.6025, + "step": 820224 + }, + { + "epoch": 0.02, + "learning_rate": 3.6562927691512435e-05, + "loss": 3.6189, + "step": 820736 + }, + { + "epoch": 0.02, + "learning_rate": 3.655454174400192e-05, + "loss": 3.6104, + "step": 821248 + }, + { + "epoch": 0.02, + "learning_rate": 3.65461557964914e-05, + "loss": 3.6161, + "step": 821760 + }, + { + "epoch": 0.02, + "learning_rate": 3.653778622778461e-05, + "loss": 3.6206, + "step": 822272 + }, + { + "epoch": 0.02, + "learning_rate": 3.652940028027409e-05, + "loss": 3.6159, + "step": 822784 + }, + { + "epoch": 0.02, + "learning_rate": 3.652101433276357e-05, + "loss": 3.6128, + "step": 823296 + }, + { + "epoch": 0.02, + "learning_rate": 3.651262838525305e-05, + "loss": 3.6228, + "step": 823808 + }, + { + "epoch": 0.02, + "learning_rate": 3.650425881654626e-05, + "loss": 3.6144, + "step": 824320 + }, + { + "epoch": 0.02, + "learning_rate": 3.649587286903574e-05, + "loss": 3.6187, + "step": 824832 + }, + { + "epoch": 0.02, + "learning_rate": 3.648748692152522e-05, + "loss": 3.6141, + "step": 825344 + }, + { + "epoch": 0.02, + "learning_rate": 3.64791009740147e-05, + "loss": 3.6114, + "step": 825856 + }, + { + "epoch": 0.02, + "learning_rate": 3.647073140530791e-05, + "loss": 3.6135, + "step": 826368 + }, + { + "epoch": 0.02, + "learning_rate": 3.646234545779739e-05, + "loss": 3.6133, + "step": 826880 + }, + { + "epoch": 0.02, + "learning_rate": 3.6453959510286876e-05, + "loss": 3.6089, + "step": 827392 + }, + { + "epoch": 0.02, + "learning_rate": 3.6445573562776356e-05, + "loss": 3.6092, + "step": 827904 + }, + { + "epoch": 0.02, + "learning_rate": 3.6437203994069565e-05, + "loss": 3.6033, + "step": 828416 + }, + { + "epoch": 0.02, + "learning_rate": 3.6428818046559045e-05, + "loss": 3.6039, + "step": 828928 + }, + { + "epoch": 0.02, + "learning_rate": 3.6420432099048525e-05, + "loss": 3.6194, + "step": 829440 + }, + { + "epoch": 0.02, + "learning_rate": 3.6412046151538005e-05, + "loss": 3.611, + "step": 829952 + }, + { + "epoch": 0.02, + "learning_rate": 3.6403676582831214e-05, + "loss": 3.622, + "step": 830464 + }, + { + "epoch": 0.02, + "learning_rate": 3.6395290635320694e-05, + "loss": 3.6035, + "step": 830976 + }, + { + "epoch": 0.02, + "learning_rate": 3.6386904687810174e-05, + "loss": 3.6191, + "step": 831488 + }, + { + "epoch": 0.02, + "learning_rate": 3.6378518740299654e-05, + "loss": 3.6148, + "step": 832000 + }, + { + "epoch": 0.02, + "learning_rate": 3.637014917159286e-05, + "loss": 3.6164, + "step": 832512 + }, + { + "epoch": 0.02, + "learning_rate": 3.636176322408234e-05, + "loss": 3.615, + "step": 833024 + }, + { + "epoch": 0.02, + "learning_rate": 3.635337727657183e-05, + "loss": 3.6101, + "step": 833536 + }, + { + "epoch": 0.02, + "learning_rate": 3.634499132906131e-05, + "loss": 3.6215, + "step": 834048 + }, + { + "epoch": 0.02, + "learning_rate": 3.633662176035452e-05, + "loss": 3.6242, + "step": 834560 + }, + { + "epoch": 0.02, + "learning_rate": 3.6328235812844e-05, + "loss": 3.6057, + "step": 835072 + }, + { + "epoch": 0.02, + "learning_rate": 3.631984986533348e-05, + "loss": 3.6139, + "step": 835584 + }, + { + "epoch": 0.02, + "learning_rate": 3.631146391782296e-05, + "loss": 3.616, + "step": 836096 + }, + { + "epoch": 0.02, + "learning_rate": 3.630309434911617e-05, + "loss": 3.6103, + "step": 836608 + }, + { + "epoch": 0.02, + "learning_rate": 3.629470840160565e-05, + "loss": 3.6107, + "step": 837120 + }, + { + "epoch": 0.02, + "learning_rate": 3.628632245409513e-05, + "loss": 3.6118, + "step": 837632 + }, + { + "epoch": 0.02, + "learning_rate": 3.627793650658461e-05, + "loss": 3.6164, + "step": 838144 + }, + { + "epoch": 0.02, + "learning_rate": 3.6269566937877816e-05, + "loss": 3.6147, + "step": 838656 + }, + { + "epoch": 0.02, + "learning_rate": 3.6261180990367296e-05, + "loss": 3.6144, + "step": 839168 + }, + { + "epoch": 0.03, + "eval_loss": 3.8441224098205566, + "eval_runtime": 316.2088, + "eval_samples_per_second": 1206.769, + "eval_steps_per_second": 37.712, + "step": 839520 + }, + { + "epoch": 1.0, + "learning_rate": 3.6252795042856776e-05, + "loss": 3.6041, + "step": 839680 + }, + { + "epoch": 1.0, + "learning_rate": 3.624440909534626e-05, + "loss": 3.6009, + "step": 840192 + }, + { + "epoch": 1.0, + "learning_rate": 3.623603952663947e-05, + "loss": 3.6068, + "step": 840704 + }, + { + "epoch": 1.0, + "learning_rate": 3.622765357912895e-05, + "loss": 3.6106, + "step": 841216 + }, + { + "epoch": 1.0, + "learning_rate": 3.621926763161843e-05, + "loss": 3.622, + "step": 841728 + }, + { + "epoch": 1.0, + "learning_rate": 3.621088168410791e-05, + "loss": 3.6122, + "step": 842240 + }, + { + "epoch": 1.0, + "learning_rate": 3.620251211540112e-05, + "loss": 3.6081, + "step": 842752 + }, + { + "epoch": 1.0, + "learning_rate": 3.61941261678906e-05, + "loss": 3.605, + "step": 843264 + }, + { + "epoch": 1.0, + "learning_rate": 3.618574022038008e-05, + "loss": 3.5985, + "step": 843776 + }, + { + "epoch": 1.0, + "learning_rate": 3.617735427286956e-05, + "loss": 3.6077, + "step": 844288 + }, + { + "epoch": 1.0, + "learning_rate": 3.616898470416277e-05, + "loss": 3.6118, + "step": 844800 + }, + { + "epoch": 1.0, + "learning_rate": 3.616059875665225e-05, + "loss": 3.6065, + "step": 845312 + }, + { + "epoch": 1.0, + "learning_rate": 3.615221280914173e-05, + "loss": 3.6109, + "step": 845824 + }, + { + "epoch": 1.0, + "learning_rate": 3.614382686163122e-05, + "loss": 3.5941, + "step": 846336 + }, + { + "epoch": 1.0, + "learning_rate": 3.6135457292924426e-05, + "loss": 3.6057, + "step": 846848 + }, + { + "epoch": 1.0, + "learning_rate": 3.6127071345413906e-05, + "loss": 3.5922, + "step": 847360 + }, + { + "epoch": 1.0, + "learning_rate": 3.6118685397903386e-05, + "loss": 3.6078, + "step": 847872 + }, + { + "epoch": 1.0, + "learning_rate": 3.6110299450392866e-05, + "loss": 3.601, + "step": 848384 + }, + { + "epoch": 1.0, + "learning_rate": 3.6101913502882346e-05, + "loss": 3.6049, + "step": 848896 + }, + { + "epoch": 1.0, + "learning_rate": 3.6093543934175555e-05, + "loss": 3.6055, + "step": 849408 + }, + { + "epoch": 1.0, + "learning_rate": 3.6085157986665035e-05, + "loss": 3.6223, + "step": 849920 + }, + { + "epoch": 1.0, + "learning_rate": 3.6076772039154515e-05, + "loss": 3.6054, + "step": 850432 + }, + { + "epoch": 1.0, + "learning_rate": 3.6068386091643995e-05, + "loss": 3.6112, + "step": 850944 + }, + { + "epoch": 1.0, + "learning_rate": 3.6060016522937204e-05, + "loss": 3.6039, + "step": 851456 + }, + { + "epoch": 1.0, + "learning_rate": 3.6051630575426684e-05, + "loss": 3.6052, + "step": 851968 + }, + { + "epoch": 1.0, + "learning_rate": 3.604324462791617e-05, + "loss": 3.6138, + "step": 852480 + }, + { + "epoch": 1.0, + "learning_rate": 3.603485868040565e-05, + "loss": 3.5942, + "step": 852992 + }, + { + "epoch": 1.0, + "learning_rate": 3.602648911169886e-05, + "loss": 3.606, + "step": 853504 + }, + { + "epoch": 1.0, + "learning_rate": 3.601810316418834e-05, + "loss": 3.5968, + "step": 854016 + }, + { + "epoch": 1.0, + "learning_rate": 3.600971721667782e-05, + "loss": 3.5978, + "step": 854528 + }, + { + "epoch": 1.01, + "learning_rate": 3.60013312691673e-05, + "loss": 3.606, + "step": 855040 + }, + { + "epoch": 1.01, + "learning_rate": 3.599296170046051e-05, + "loss": 3.6079, + "step": 855552 + }, + { + "epoch": 1.01, + "learning_rate": 3.598457575294999e-05, + "loss": 3.6016, + "step": 856064 + }, + { + "epoch": 1.01, + "learning_rate": 3.597618980543947e-05, + "loss": 3.6237, + "step": 856576 + }, + { + "epoch": 1.01, + "learning_rate": 3.596780385792895e-05, + "loss": 3.6037, + "step": 857088 + }, + { + "epoch": 1.01, + "learning_rate": 3.595943428922216e-05, + "loss": 3.6001, + "step": 857600 + }, + { + "epoch": 1.01, + "learning_rate": 3.595104834171164e-05, + "loss": 3.6137, + "step": 858112 + }, + { + "epoch": 1.01, + "learning_rate": 3.5942662394201124e-05, + "loss": 3.5986, + "step": 858624 + }, + { + "epoch": 1.01, + "learning_rate": 3.5934276446690604e-05, + "loss": 3.6003, + "step": 859136 + }, + { + "epoch": 1.01, + "learning_rate": 3.592590687798381e-05, + "loss": 3.6071, + "step": 859648 + }, + { + "epoch": 1.01, + "learning_rate": 3.591752093047329e-05, + "loss": 3.5977, + "step": 860160 + }, + { + "epoch": 1.01, + "learning_rate": 3.590913498296277e-05, + "loss": 3.6037, + "step": 860672 + }, + { + "epoch": 1.01, + "learning_rate": 3.590074903545225e-05, + "loss": 3.6073, + "step": 861184 + }, + { + "epoch": 1.01, + "learning_rate": 3.589237946674546e-05, + "loss": 3.6034, + "step": 861696 + }, + { + "epoch": 1.01, + "learning_rate": 3.588399351923494e-05, + "loss": 3.6054, + "step": 862208 + }, + { + "epoch": 1.01, + "learning_rate": 3.587560757172442e-05, + "loss": 3.6058, + "step": 862720 + }, + { + "epoch": 1.01, + "learning_rate": 3.58672216242139e-05, + "loss": 3.603, + "step": 863232 + }, + { + "epoch": 1.01, + "learning_rate": 3.5858835676703375e-05, + "loss": 3.605, + "step": 863744 + }, + { + "epoch": 1.01, + "learning_rate": 3.585046610799659e-05, + "loss": 3.5751, + "step": 864256 + }, + { + "epoch": 1.01, + "learning_rate": 3.584208016048608e-05, + "loss": 3.6093, + "step": 864768 + }, + { + "epoch": 1.01, + "learning_rate": 3.583369421297556e-05, + "loss": 3.5952, + "step": 865280 + }, + { + "epoch": 1.01, + "learning_rate": 3.582530826546503e-05, + "loss": 3.6091, + "step": 865792 + }, + { + "epoch": 1.01, + "learning_rate": 3.581693869675825e-05, + "loss": 3.5919, + "step": 866304 + }, + { + "epoch": 1.01, + "learning_rate": 3.580855274924773e-05, + "loss": 3.5837, + "step": 866816 + }, + { + "epoch": 1.01, + "learning_rate": 3.58001668017372e-05, + "loss": 3.5872, + "step": 867328 + }, + { + "epoch": 1.01, + "learning_rate": 3.579178085422668e-05, + "loss": 3.5936, + "step": 867840 + }, + { + "epoch": 1.01, + "learning_rate": 3.5783411285519896e-05, + "loss": 3.6035, + "step": 868352 + }, + { + "epoch": 1.01, + "learning_rate": 3.5775025338009376e-05, + "loss": 3.5858, + "step": 868864 + }, + { + "epoch": 1.01, + "learning_rate": 3.576663939049885e-05, + "loss": 3.6105, + "step": 869376 + }, + { + "epoch": 1.01, + "learning_rate": 3.575825344298833e-05, + "loss": 3.6029, + "step": 869888 + }, + { + "epoch": 1.01, + "learning_rate": 3.5749883874281545e-05, + "loss": 3.5785, + "step": 870400 + }, + { + "epoch": 1.01, + "learning_rate": 3.574149792677103e-05, + "loss": 3.6036, + "step": 870912 + }, + { + "epoch": 1.01, + "learning_rate": 3.5733111979260505e-05, + "loss": 3.5872, + "step": 871424 + }, + { + "epoch": 1.01, + "learning_rate": 3.5724726031749985e-05, + "loss": 3.5858, + "step": 871936 + }, + { + "epoch": 1.01, + "learning_rate": 3.57163564630432e-05, + "loss": 3.5938, + "step": 872448 + }, + { + "epoch": 1.01, + "learning_rate": 3.5707970515532674e-05, + "loss": 3.6068, + "step": 872960 + }, + { + "epoch": 1.01, + "learning_rate": 3.5699584568022154e-05, + "loss": 3.5829, + "step": 873472 + }, + { + "epoch": 1.01, + "learning_rate": 3.5691198620511634e-05, + "loss": 3.5994, + "step": 873984 + }, + { + "epoch": 1.01, + "learning_rate": 3.568282905180485e-05, + "loss": 3.5792, + "step": 874496 + }, + { + "epoch": 1.01, + "learning_rate": 3.567444310429432e-05, + "loss": 3.5982, + "step": 875008 + }, + { + "epoch": 1.01, + "learning_rate": 3.56660571567838e-05, + "loss": 3.601, + "step": 875520 + }, + { + "epoch": 1.01, + "learning_rate": 3.565767120927328e-05, + "loss": 3.6021, + "step": 876032 + }, + { + "epoch": 1.01, + "learning_rate": 3.56493016405665e-05, + "loss": 3.6039, + "step": 876544 + }, + { + "epoch": 1.01, + "learning_rate": 3.564091569305598e-05, + "loss": 3.6038, + "step": 877056 + }, + { + "epoch": 1.01, + "learning_rate": 3.563252974554546e-05, + "loss": 3.6181, + "step": 877568 + }, + { + "epoch": 1.01, + "learning_rate": 3.562414379803494e-05, + "loss": 3.6028, + "step": 878080 + }, + { + "epoch": 1.01, + "learning_rate": 3.561577422932815e-05, + "loss": 3.6092, + "step": 878592 + }, + { + "epoch": 1.01, + "learning_rate": 3.560738828181763e-05, + "loss": 3.59, + "step": 879104 + }, + { + "epoch": 1.01, + "learning_rate": 3.559900233430711e-05, + "loss": 3.5968, + "step": 879616 + }, + { + "epoch": 1.01, + "learning_rate": 3.559061638679659e-05, + "loss": 3.5957, + "step": 880128 + }, + { + "epoch": 1.01, + "learning_rate": 3.5582246818089796e-05, + "loss": 3.5997, + "step": 880640 + }, + { + "epoch": 1.01, + "learning_rate": 3.5573860870579276e-05, + "loss": 3.6056, + "step": 881152 + }, + { + "epoch": 1.01, + "learning_rate": 3.5565474923068756e-05, + "loss": 3.6086, + "step": 881664 + }, + { + "epoch": 1.01, + "learning_rate": 3.5557088975558236e-05, + "loss": 3.5895, + "step": 882176 + }, + { + "epoch": 1.01, + "learning_rate": 3.554871940685145e-05, + "loss": 3.5898, + "step": 882688 + }, + { + "epoch": 1.01, + "learning_rate": 3.554033345934093e-05, + "loss": 3.587, + "step": 883200 + }, + { + "epoch": 1.01, + "learning_rate": 3.553194751183041e-05, + "loss": 3.6101, + "step": 883712 + }, + { + "epoch": 1.01, + "learning_rate": 3.552356156431989e-05, + "loss": 3.5966, + "step": 884224 + }, + { + "epoch": 1.01, + "learning_rate": 3.55151919956131e-05, + "loss": 3.5891, + "step": 884736 + }, + { + "epoch": 1.01, + "learning_rate": 3.550680604810258e-05, + "loss": 3.5985, + "step": 885248 + }, + { + "epoch": 1.02, + "learning_rate": 3.549842010059206e-05, + "loss": 3.5967, + "step": 885760 + }, + { + "epoch": 1.02, + "learning_rate": 3.549003415308154e-05, + "loss": 3.5902, + "step": 886272 + }, + { + "epoch": 1.02, + "learning_rate": 3.548166458437475e-05, + "loss": 3.592, + "step": 886784 + }, + { + "epoch": 1.02, + "learning_rate": 3.547327863686423e-05, + "loss": 3.6071, + "step": 887296 + }, + { + "epoch": 1.02, + "learning_rate": 3.546489268935371e-05, + "loss": 3.6024, + "step": 887808 + }, + { + "epoch": 1.02, + "learning_rate": 3.545650674184319e-05, + "loss": 3.602, + "step": 888320 + }, + { + "epoch": 1.02, + "learning_rate": 3.5448137173136406e-05, + "loss": 3.5862, + "step": 888832 + }, + { + "epoch": 1.02, + "learning_rate": 3.5439751225625886e-05, + "loss": 3.5926, + "step": 889344 + }, + { + "epoch": 1.02, + "learning_rate": 3.5431365278115366e-05, + "loss": 3.5942, + "step": 889856 + }, + { + "epoch": 1.02, + "learning_rate": 3.5422979330604846e-05, + "loss": 3.6015, + "step": 890368 + }, + { + "epoch": 1.02, + "learning_rate": 3.5414609761898055e-05, + "loss": 3.6023, + "step": 890880 + }, + { + "epoch": 1.02, + "learning_rate": 3.5406223814387535e-05, + "loss": 3.6012, + "step": 891392 + }, + { + "epoch": 1.02, + "learning_rate": 3.5397837866877015e-05, + "loss": 3.5995, + "step": 891904 + }, + { + "epoch": 1.02, + "learning_rate": 3.5389451919366495e-05, + "loss": 3.5973, + "step": 892416 + }, + { + "epoch": 1.02, + "learning_rate": 3.5381082350659704e-05, + "loss": 3.5961, + "step": 892928 + }, + { + "epoch": 1.02, + "learning_rate": 3.5372696403149184e-05, + "loss": 3.5841, + "step": 893440 + }, + { + "epoch": 1.02, + "learning_rate": 3.5364310455638664e-05, + "loss": 3.5888, + "step": 893952 + }, + { + "epoch": 1.02, + "learning_rate": 3.5355924508128144e-05, + "loss": 3.5937, + "step": 894464 + }, + { + "epoch": 1.02, + "learning_rate": 3.534755493942136e-05, + "loss": 3.5929, + "step": 894976 + }, + { + "epoch": 1.02, + "learning_rate": 3.533916899191084e-05, + "loss": 3.5833, + "step": 895488 + }, + { + "epoch": 1.02, + "learning_rate": 3.533078304440032e-05, + "loss": 3.5876, + "step": 896000 + }, + { + "epoch": 1.02, + "learning_rate": 3.53223970968898e-05, + "loss": 3.5862, + "step": 896512 + }, + { + "epoch": 1.02, + "learning_rate": 3.531402752818301e-05, + "loss": 3.5955, + "step": 897024 + }, + { + "epoch": 1.02, + "learning_rate": 3.530564158067249e-05, + "loss": 3.5958, + "step": 897536 + }, + { + "epoch": 1.02, + "learning_rate": 3.529725563316197e-05, + "loss": 3.5942, + "step": 898048 + }, + { + "epoch": 1.02, + "learning_rate": 3.528886968565145e-05, + "loss": 3.6005, + "step": 898560 + }, + { + "epoch": 1.02, + "learning_rate": 3.528050011694466e-05, + "loss": 3.5996, + "step": 899072 + }, + { + "epoch": 1.02, + "learning_rate": 3.527211416943414e-05, + "loss": 3.5936, + "step": 899584 + }, + { + "epoch": 1.02, + "learning_rate": 3.526372822192362e-05, + "loss": 3.6032, + "step": 900096 + }, + { + "epoch": 1.02, + "learning_rate": 3.52553422744131e-05, + "loss": 3.594, + "step": 900608 + }, + { + "epoch": 1.02, + "learning_rate": 3.524697270570631e-05, + "loss": 3.5998, + "step": 901120 + }, + { + "epoch": 1.02, + "learning_rate": 3.523858675819579e-05, + "loss": 3.594, + "step": 901632 + }, + { + "epoch": 1.02, + "learning_rate": 3.523020081068527e-05, + "loss": 3.5937, + "step": 902144 + }, + { + "epoch": 1.02, + "learning_rate": 3.522181486317475e-05, + "loss": 3.5925, + "step": 902656 + }, + { + "epoch": 1.02, + "learning_rate": 3.521344529446796e-05, + "loss": 3.5957, + "step": 903168 + }, + { + "epoch": 1.02, + "learning_rate": 3.520505934695744e-05, + "loss": 3.5889, + "step": 903680 + }, + { + "epoch": 1.02, + "learning_rate": 3.519667339944692e-05, + "loss": 3.5895, + "step": 904192 + }, + { + "epoch": 1.02, + "learning_rate": 3.51882874519364e-05, + "loss": 3.5808, + "step": 904704 + }, + { + "epoch": 1.02, + "learning_rate": 3.517991788322961e-05, + "loss": 3.5879, + "step": 905216 + }, + { + "epoch": 1.02, + "learning_rate": 3.517153193571909e-05, + "loss": 3.5989, + "step": 905728 + }, + { + "epoch": 1.02, + "learning_rate": 3.516314598820857e-05, + "loss": 3.5915, + "step": 906240 + }, + { + "epoch": 1.02, + "learning_rate": 3.515476004069805e-05, + "loss": 3.6028, + "step": 906752 + }, + { + "epoch": 1.02, + "learning_rate": 3.514639047199127e-05, + "loss": 3.5779, + "step": 907264 + }, + { + "epoch": 1.02, + "learning_rate": 3.513800452448075e-05, + "loss": 3.6048, + "step": 907776 + }, + { + "epoch": 1.02, + "learning_rate": 3.512961857697023e-05, + "loss": 3.5973, + "step": 908288 + }, + { + "epoch": 1.02, + "learning_rate": 3.5121232629459707e-05, + "loss": 3.5989, + "step": 908800 + }, + { + "epoch": 1.02, + "learning_rate": 3.5112863060752916e-05, + "loss": 3.5879, + "step": 909312 + }, + { + "epoch": 1.02, + "learning_rate": 3.5104477113242396e-05, + "loss": 3.5924, + "step": 909824 + }, + { + "epoch": 1.02, + "learning_rate": 3.5096091165731876e-05, + "loss": 3.6046, + "step": 910336 + }, + { + "epoch": 1.02, + "learning_rate": 3.5087705218221356e-05, + "loss": 3.6036, + "step": 910848 + }, + { + "epoch": 1.02, + "learning_rate": 3.5079335649514565e-05, + "loss": 3.5913, + "step": 911360 + }, + { + "epoch": 1.02, + "learning_rate": 3.5070949702004045e-05, + "loss": 3.5895, + "step": 911872 + }, + { + "epoch": 1.02, + "learning_rate": 3.5062563754493525e-05, + "loss": 3.5965, + "step": 912384 + }, + { + "epoch": 1.02, + "learning_rate": 3.5054177806983005e-05, + "loss": 3.5963, + "step": 912896 + }, + { + "epoch": 1.02, + "learning_rate": 3.504580823827622e-05, + "loss": 3.5894, + "step": 913408 + }, + { + "epoch": 1.02, + "learning_rate": 3.50374222907657e-05, + "loss": 3.5989, + "step": 913920 + }, + { + "epoch": 1.02, + "learning_rate": 3.502903634325518e-05, + "loss": 3.5906, + "step": 914432 + }, + { + "epoch": 1.02, + "learning_rate": 3.502065039574466e-05, + "loss": 3.5945, + "step": 914944 + }, + { + "epoch": 1.02, + "learning_rate": 3.501228082703787e-05, + "loss": 3.5971, + "step": 915456 + }, + { + "epoch": 1.03, + "eval_loss": 3.8432776927948, + "eval_runtime": 318.401, + "eval_samples_per_second": 1198.461, + "eval_steps_per_second": 37.453, + "step": 915840 + }, + { + "epoch": 0.0, + "learning_rate": 3.500389487952735e-05, + "loss": 3.5926, + "step": 915968 + }, + { + "epoch": 0.0, + "learning_rate": 3.499550893201683e-05, + "loss": 3.5783, + "step": 916480 + }, + { + "epoch": 0.0, + "learning_rate": 3.498712298450631e-05, + "loss": 3.5908, + "step": 916992 + }, + { + "epoch": 0.0, + "learning_rate": 3.497873703699579e-05, + "loss": 3.5945, + "step": 917504 + }, + { + "epoch": 0.0, + "learning_rate": 3.4970367468289e-05, + "loss": 3.596, + "step": 918016 + }, + { + "epoch": 0.0, + "learning_rate": 3.496198152077848e-05, + "loss": 3.5974, + "step": 918528 + }, + { + "epoch": 0.0, + "learning_rate": 3.495359557326796e-05, + "loss": 3.5893, + "step": 919040 + }, + { + "epoch": 0.0, + "learning_rate": 3.494520962575744e-05, + "loss": 3.5843, + "step": 919552 + }, + { + "epoch": 0.0, + "learning_rate": 3.4936823678246925e-05, + "loss": 3.5751, + "step": 920064 + }, + { + "epoch": 0.0, + "learning_rate": 3.4928454109540134e-05, + "loss": 3.5906, + "step": 920576 + }, + { + "epoch": 0.0, + "learning_rate": 3.4920068162029614e-05, + "loss": 3.5925, + "step": 921088 + }, + { + "epoch": 0.0, + "learning_rate": 3.4911682214519094e-05, + "loss": 3.5891, + "step": 921600 + }, + { + "epoch": 0.0, + "learning_rate": 3.4903296267008574e-05, + "loss": 3.5955, + "step": 922112 + }, + { + "epoch": 0.0, + "learning_rate": 3.489492669830178e-05, + "loss": 3.5726, + "step": 922624 + }, + { + "epoch": 0.0, + "learning_rate": 3.488654075079126e-05, + "loss": 3.5844, + "step": 923136 + }, + { + "epoch": 0.0, + "learning_rate": 3.487815480328074e-05, + "loss": 3.577, + "step": 923648 + }, + { + "epoch": 0.0, + "learning_rate": 3.486976885577022e-05, + "loss": 3.5894, + "step": 924160 + }, + { + "epoch": 0.0, + "learning_rate": 3.486139928706343e-05, + "loss": 3.581, + "step": 924672 + }, + { + "epoch": 0.0, + "learning_rate": 3.485301333955291e-05, + "loss": 3.5851, + "step": 925184 + }, + { + "epoch": 0.0, + "learning_rate": 3.484462739204239e-05, + "loss": 3.5848, + "step": 925696 + }, + { + "epoch": 0.0, + "learning_rate": 3.483624144453188e-05, + "loss": 3.6043, + "step": 926208 + }, + { + "epoch": 0.0, + "learning_rate": 3.482787187582509e-05, + "loss": 3.585, + "step": 926720 + }, + { + "epoch": 0.0, + "learning_rate": 3.481948592831457e-05, + "loss": 3.5921, + "step": 927232 + }, + { + "epoch": 0.0, + "learning_rate": 3.481109998080405e-05, + "loss": 3.5855, + "step": 927744 + }, + { + "epoch": 0.0, + "learning_rate": 3.480271403329352e-05, + "loss": 3.5902, + "step": 928256 + }, + { + "epoch": 0.0, + "learning_rate": 3.4794344464586737e-05, + "loss": 3.5931, + "step": 928768 + }, + { + "epoch": 0.0, + "learning_rate": 3.4785958517076217e-05, + "loss": 3.5763, + "step": 929280 + }, + { + "epoch": 0.0, + "learning_rate": 3.4777572569565697e-05, + "loss": 3.586, + "step": 929792 + }, + { + "epoch": 0.0, + "learning_rate": 3.476918662205517e-05, + "loss": 3.5766, + "step": 930304 + }, + { + "epoch": 0.0, + "learning_rate": 3.4760817053348386e-05, + "loss": 3.58, + "step": 930816 + }, + { + "epoch": 0.01, + "learning_rate": 3.4752431105837866e-05, + "loss": 3.5902, + "step": 931328 + }, + { + "epoch": 0.01, + "learning_rate": 3.4744045158327345e-05, + "loss": 3.5879, + "step": 931840 + }, + { + "epoch": 0.01, + "learning_rate": 3.4735659210816825e-05, + "loss": 3.5843, + "step": 932352 + }, + { + "epoch": 0.01, + "learning_rate": 3.472728964211004e-05, + "loss": 3.5996, + "step": 932864 + }, + { + "epoch": 0.01, + "learning_rate": 3.471890369459952e-05, + "loss": 3.585, + "step": 933376 + }, + { + "epoch": 0.01, + "learning_rate": 3.4710517747088994e-05, + "loss": 3.585, + "step": 933888 + }, + { + "epoch": 0.01, + "learning_rate": 3.4702131799578474e-05, + "loss": 3.5949, + "step": 934400 + }, + { + "epoch": 0.01, + "learning_rate": 3.469376223087169e-05, + "loss": 3.5769, + "step": 934912 + }, + { + "epoch": 0.01, + "learning_rate": 3.468537628336117e-05, + "loss": 3.5828, + "step": 935424 + }, + { + "epoch": 0.01, + "learning_rate": 3.4676990335850643e-05, + "loss": 3.5854, + "step": 935936 + }, + { + "epoch": 0.01, + "learning_rate": 3.466860438834012e-05, + "loss": 3.5803, + "step": 936448 + }, + { + "epoch": 0.01, + "learning_rate": 3.466023481963334e-05, + "loss": 3.5862, + "step": 936960 + }, + { + "epoch": 0.01, + "learning_rate": 3.465184887212282e-05, + "loss": 3.592, + "step": 937472 + }, + { + "epoch": 0.01, + "learning_rate": 3.46434629246123e-05, + "loss": 3.5837, + "step": 937984 + }, + { + "epoch": 0.01, + "learning_rate": 3.463507697710178e-05, + "loss": 3.5872, + "step": 938496 + }, + { + "epoch": 0.01, + "learning_rate": 3.4626707408394995e-05, + "loss": 3.5878, + "step": 939008 + }, + { + "epoch": 0.01, + "learning_rate": 3.461832146088447e-05, + "loss": 3.5827, + "step": 939520 + }, + { + "epoch": 0.01, + "learning_rate": 3.460993551337395e-05, + "loss": 3.5889, + "step": 940032 + }, + { + "epoch": 0.01, + "learning_rate": 3.460154956586343e-05, + "loss": 3.5591, + "step": 940544 + }, + { + "epoch": 0.01, + "learning_rate": 3.4593179997156644e-05, + "loss": 3.5872, + "step": 941056 + }, + { + "epoch": 0.01, + "learning_rate": 3.458479404964612e-05, + "loss": 3.5821, + "step": 941568 + }, + { + "epoch": 0.01, + "learning_rate": 3.45764081021356e-05, + "loss": 3.5867, + "step": 942080 + }, + { + "epoch": 0.01, + "learning_rate": 3.456802215462508e-05, + "loss": 3.5756, + "step": 942592 + }, + { + "epoch": 0.01, + "learning_rate": 3.455965258591829e-05, + "loss": 3.5627, + "step": 943104 + }, + { + "epoch": 0.01, + "learning_rate": 3.455126663840777e-05, + "loss": 3.5677, + "step": 943616 + }, + { + "epoch": 0.01, + "learning_rate": 3.454288069089725e-05, + "loss": 3.5724, + "step": 944128 + }, + { + "epoch": 0.01, + "learning_rate": 3.453449474338673e-05, + "loss": 3.5899, + "step": 944640 + }, + { + "epoch": 0.01, + "learning_rate": 3.452612517467994e-05, + "loss": 3.5658, + "step": 945152 + }, + { + "epoch": 0.01, + "learning_rate": 3.451773922716942e-05, + "loss": 3.5914, + "step": 945664 + }, + { + "epoch": 0.01, + "learning_rate": 3.45093532796589e-05, + "loss": 3.5828, + "step": 946176 + }, + { + "epoch": 0.01, + "learning_rate": 3.450096733214838e-05, + "loss": 3.5652, + "step": 946688 + }, + { + "epoch": 0.01, + "learning_rate": 3.449259776344159e-05, + "loss": 3.5824, + "step": 947200 + }, + { + "epoch": 0.01, + "learning_rate": 3.448421181593107e-05, + "loss": 3.5668, + "step": 947712 + }, + { + "epoch": 0.01, + "learning_rate": 3.447582586842055e-05, + "loss": 3.5682, + "step": 948224 + }, + { + "epoch": 0.01, + "learning_rate": 3.446743992091003e-05, + "loss": 3.5728, + "step": 948736 + }, + { + "epoch": 0.01, + "learning_rate": 3.4459070352203247e-05, + "loss": 3.5859, + "step": 949248 + }, + { + "epoch": 0.01, + "learning_rate": 3.4450684404692727e-05, + "loss": 3.5694, + "step": 949760 + }, + { + "epoch": 0.01, + "learning_rate": 3.4442298457182206e-05, + "loss": 3.5818, + "step": 950272 + }, + { + "epoch": 0.01, + "learning_rate": 3.4433912509671686e-05, + "loss": 3.5589, + "step": 950784 + }, + { + "epoch": 0.01, + "learning_rate": 3.4425542940964896e-05, + "loss": 3.5804, + "step": 951296 + }, + { + "epoch": 0.01, + "learning_rate": 3.4417156993454375e-05, + "loss": 3.5826, + "step": 951808 + }, + { + "epoch": 0.01, + "learning_rate": 3.4408771045943855e-05, + "loss": 3.5842, + "step": 952320 + }, + { + "epoch": 0.01, + "learning_rate": 3.4400385098433335e-05, + "loss": 3.5848, + "step": 952832 + }, + { + "epoch": 0.01, + "learning_rate": 3.4392015529726544e-05, + "loss": 3.5884, + "step": 953344 + }, + { + "epoch": 0.01, + "learning_rate": 3.4383629582216024e-05, + "loss": 3.5986, + "step": 953856 + }, + { + "epoch": 0.01, + "learning_rate": 3.4375243634705504e-05, + "loss": 3.5858, + "step": 954368 + }, + { + "epoch": 0.01, + "learning_rate": 3.4366857687194984e-05, + "loss": 3.5906, + "step": 954880 + }, + { + "epoch": 0.01, + "learning_rate": 3.4358488118488193e-05, + "loss": 3.5722, + "step": 955392 + }, + { + "epoch": 0.01, + "learning_rate": 3.435010217097768e-05, + "loss": 3.5779, + "step": 955904 + }, + { + "epoch": 0.01, + "learning_rate": 3.434171622346716e-05, + "loss": 3.577, + "step": 956416 + }, + { + "epoch": 0.01, + "learning_rate": 3.433333027595664e-05, + "loss": 3.5807, + "step": 956928 + }, + { + "epoch": 0.01, + "learning_rate": 3.432494432844612e-05, + "loss": 3.5883, + "step": 957440 + }, + { + "epoch": 0.01, + "learning_rate": 3.431657475973933e-05, + "loss": 3.588, + "step": 957952 + }, + { + "epoch": 0.01, + "learning_rate": 3.430818881222881e-05, + "loss": 3.5761, + "step": 958464 + }, + { + "epoch": 0.01, + "learning_rate": 3.429980286471829e-05, + "loss": 3.5692, + "step": 958976 + }, + { + "epoch": 0.01, + "learning_rate": 3.42914332960115e-05, + "loss": 3.57, + "step": 959488 + }, + { + "epoch": 0.01, + "learning_rate": 3.428304734850098e-05, + "loss": 3.5907, + "step": 960000 + }, + { + "epoch": 0.01, + "learning_rate": 3.427466140099046e-05, + "loss": 3.5787, + "step": 960512 + }, + { + "epoch": 0.01, + "learning_rate": 3.426627545347994e-05, + "loss": 3.5715, + "step": 961024 + }, + { + "epoch": 0.01, + "learning_rate": 3.425788950596942e-05, + "loss": 3.581, + "step": 961536 + }, + { + "epoch": 0.02, + "learning_rate": 3.4249519937262634e-05, + "loss": 3.5795, + "step": 962048 + }, + { + "epoch": 0.02, + "learning_rate": 3.4241133989752114e-05, + "loss": 3.5705, + "step": 962560 + }, + { + "epoch": 0.02, + "learning_rate": 3.4232748042241594e-05, + "loss": 3.5747, + "step": 963072 + }, + { + "epoch": 0.02, + "learning_rate": 3.42243784735348e-05, + "loss": 3.5881, + "step": 963584 + }, + { + "epoch": 0.02, + "learning_rate": 3.421599252602428e-05, + "loss": 3.5888, + "step": 964096 + }, + { + "epoch": 0.02, + "learning_rate": 3.420760657851376e-05, + "loss": 3.5852, + "step": 964608 + }, + { + "epoch": 0.02, + "learning_rate": 3.419922063100324e-05, + "loss": 3.5693, + "step": 965120 + }, + { + "epoch": 0.02, + "learning_rate": 3.419083468349272e-05, + "loss": 3.5759, + "step": 965632 + }, + { + "epoch": 0.02, + "learning_rate": 3.418246511478593e-05, + "loss": 3.5774, + "step": 966144 + }, + { + "epoch": 0.02, + "learning_rate": 3.417407916727541e-05, + "loss": 3.5794, + "step": 966656 + }, + { + "epoch": 0.02, + "learning_rate": 3.416569321976489e-05, + "loss": 3.5858, + "step": 967168 + }, + { + "epoch": 0.02, + "learning_rate": 3.415730727225437e-05, + "loss": 3.5819, + "step": 967680 + }, + { + "epoch": 0.02, + "learning_rate": 3.414893770354759e-05, + "loss": 3.5794, + "step": 968192 + }, + { + "epoch": 0.02, + "learning_rate": 3.414055175603707e-05, + "loss": 3.5787, + "step": 968704 + }, + { + "epoch": 0.02, + "learning_rate": 3.413216580852655e-05, + "loss": 3.5794, + "step": 969216 + }, + { + "epoch": 0.02, + "learning_rate": 3.412377986101603e-05, + "loss": 3.5688, + "step": 969728 + }, + { + "epoch": 0.02, + "learning_rate": 3.4115410292309236e-05, + "loss": 3.5716, + "step": 970240 + }, + { + "epoch": 0.02, + "learning_rate": 3.4107024344798716e-05, + "loss": 3.5767, + "step": 970752 + }, + { + "epoch": 0.02, + "learning_rate": 3.4098638397288196e-05, + "loss": 3.5753, + "step": 971264 + }, + { + "epoch": 0.02, + "learning_rate": 3.4090252449777676e-05, + "loss": 3.5609, + "step": 971776 + }, + { + "epoch": 0.02, + "learning_rate": 3.4081882881070885e-05, + "loss": 3.5732, + "step": 972288 + }, + { + "epoch": 0.02, + "learning_rate": 3.4073496933560365e-05, + "loss": 3.5645, + "step": 972800 + }, + { + "epoch": 0.02, + "learning_rate": 3.4065110986049845e-05, + "loss": 3.5821, + "step": 973312 + }, + { + "epoch": 0.02, + "learning_rate": 3.4056725038539325e-05, + "loss": 3.5759, + "step": 973824 + }, + { + "epoch": 0.02, + "learning_rate": 3.404835546983254e-05, + "loss": 3.5756, + "step": 974336 + }, + { + "epoch": 0.02, + "learning_rate": 3.403996952232202e-05, + "loss": 3.5785, + "step": 974848 + }, + { + "epoch": 0.02, + "learning_rate": 3.40315835748115e-05, + "loss": 3.5819, + "step": 975360 + }, + { + "epoch": 0.02, + "learning_rate": 3.402319762730098e-05, + "loss": 3.578, + "step": 975872 + }, + { + "epoch": 0.02, + "learning_rate": 3.401482805859419e-05, + "loss": 3.5797, + "step": 976384 + }, + { + "epoch": 0.02, + "learning_rate": 3.400644211108367e-05, + "loss": 3.582, + "step": 976896 + }, + { + "epoch": 0.02, + "learning_rate": 3.399805616357315e-05, + "loss": 3.5807, + "step": 977408 + }, + { + "epoch": 0.02, + "learning_rate": 3.398968659486636e-05, + "loss": 3.5771, + "step": 977920 + }, + { + "epoch": 0.02, + "learning_rate": 3.398130064735584e-05, + "loss": 3.5777, + "step": 978432 + }, + { + "epoch": 0.02, + "learning_rate": 3.397291469984532e-05, + "loss": 3.5751, + "step": 978944 + }, + { + "epoch": 0.02, + "learning_rate": 3.39645287523348e-05, + "loss": 3.5744, + "step": 979456 + }, + { + "epoch": 0.02, + "learning_rate": 3.395614280482428e-05, + "loss": 3.5725, + "step": 979968 + }, + { + "epoch": 0.02, + "learning_rate": 3.3947773236117495e-05, + "loss": 3.5739, + "step": 980480 + }, + { + "epoch": 0.02, + "learning_rate": 3.3939387288606975e-05, + "loss": 3.562, + "step": 980992 + }, + { + "epoch": 0.02, + "learning_rate": 3.3931001341096455e-05, + "loss": 3.571, + "step": 981504 + }, + { + "epoch": 0.02, + "learning_rate": 3.3922615393585935e-05, + "loss": 3.5788, + "step": 982016 + }, + { + "epoch": 0.02, + "learning_rate": 3.3914245824879144e-05, + "loss": 3.5768, + "step": 982528 + }, + { + "epoch": 0.02, + "learning_rate": 3.3905859877368624e-05, + "loss": 3.5796, + "step": 983040 + }, + { + "epoch": 0.02, + "learning_rate": 3.3897473929858104e-05, + "loss": 3.5684, + "step": 983552 + }, + { + "epoch": 0.02, + "learning_rate": 3.3889087982347584e-05, + "loss": 3.5826, + "step": 984064 + }, + { + "epoch": 0.02, + "learning_rate": 3.388071841364079e-05, + "loss": 3.5818, + "step": 984576 + }, + { + "epoch": 0.02, + "learning_rate": 3.387233246613027e-05, + "loss": 3.5763, + "step": 985088 + }, + { + "epoch": 0.02, + "learning_rate": 3.386394651861975e-05, + "loss": 3.5752, + "step": 985600 + }, + { + "epoch": 0.02, + "learning_rate": 3.385556057110923e-05, + "loss": 3.5747, + "step": 986112 + }, + { + "epoch": 0.02, + "learning_rate": 3.384719100240245e-05, + "loss": 3.5873, + "step": 986624 + }, + { + "epoch": 0.02, + "learning_rate": 3.383880505489193e-05, + "loss": 3.582, + "step": 987136 + }, + { + "epoch": 0.02, + "learning_rate": 3.383041910738141e-05, + "loss": 3.5745, + "step": 987648 + }, + { + "epoch": 0.02, + "learning_rate": 3.382203315987089e-05, + "loss": 3.5728, + "step": 988160 + }, + { + "epoch": 0.02, + "learning_rate": 3.38136635911641e-05, + "loss": 3.5787, + "step": 988672 + }, + { + "epoch": 0.02, + "learning_rate": 3.380527764365358e-05, + "loss": 3.5768, + "step": 989184 + }, + { + "epoch": 0.02, + "learning_rate": 3.379689169614306e-05, + "loss": 3.5745, + "step": 989696 + }, + { + "epoch": 0.02, + "learning_rate": 3.378850574863254e-05, + "loss": 3.5785, + "step": 990208 + }, + { + "epoch": 0.02, + "learning_rate": 3.3780136179925746e-05, + "loss": 3.5751, + "step": 990720 + }, + { + "epoch": 0.02, + "learning_rate": 3.3771750232415226e-05, + "loss": 3.5801, + "step": 991232 + }, + { + "epoch": 0.02, + "learning_rate": 3.3763364284904706e-05, + "loss": 3.5764, + "step": 991744 + }, + { + "epoch": 0.03, + "eval_loss": 3.8434360027313232, + "eval_runtime": 307.1148, + "eval_samples_per_second": 1242.503, + "eval_steps_per_second": 38.829, + "step": 992160 + }, + { + "epoch": 1.0, + "learning_rate": 3.3754978337394186e-05, + "loss": 3.5747, + "step": 992256 + }, + { + "epoch": 1.0, + "learning_rate": 3.37466087686874e-05, + "loss": 3.5609, + "step": 992768 + }, + { + "epoch": 1.0, + "learning_rate": 3.373822282117688e-05, + "loss": 3.5711, + "step": 993280 + }, + { + "epoch": 1.0, + "learning_rate": 3.372983687366636e-05, + "loss": 3.5801, + "step": 993792 + }, + { + "epoch": 1.0, + "learning_rate": 3.372146730495957e-05, + "loss": 3.5777, + "step": 994304 + }, + { + "epoch": 1.0, + "learning_rate": 3.371308135744905e-05, + "loss": 3.5802, + "step": 994816 + }, + { + "epoch": 1.0, + "learning_rate": 3.370469540993853e-05, + "loss": 3.568, + "step": 995328 + }, + { + "epoch": 1.0, + "learning_rate": 3.369630946242801e-05, + "loss": 3.5683, + "step": 995840 + }, + { + "epoch": 1.0, + "learning_rate": 3.368793989372122e-05, + "loss": 3.5577, + "step": 996352 + }, + { + "epoch": 1.0, + "learning_rate": 3.36795539462107e-05, + "loss": 3.5776, + "step": 996864 + }, + { + "epoch": 1.0, + "learning_rate": 3.367116799870018e-05, + "loss": 3.57, + "step": 997376 + }, + { + "epoch": 1.0, + "learning_rate": 3.366278205118966e-05, + "loss": 3.573, + "step": 997888 + }, + { + "epoch": 1.0, + "learning_rate": 3.3654428861286605e-05, + "loss": 3.5801, + "step": 998400 + }, + { + "epoch": 1.0, + "learning_rate": 3.3646042913776085e-05, + "loss": 3.5545, + "step": 998912 + }, + { + "epoch": 1.0, + "learning_rate": 3.3637656966265565e-05, + "loss": 3.5691, + "step": 999424 + }, + { + "epoch": 1.0, + "learning_rate": 3.3629271018755045e-05, + "loss": 3.5553, + "step": 999936 + }, + { + "epoch": 1.0, + "learning_rate": 3.3620885071244525e-05, + "loss": 3.5744, + "step": 1000448 + }, + { + "epoch": 1.0, + "learning_rate": 3.3612499123734005e-05, + "loss": 3.5619, + "step": 1000960 + }, + { + "epoch": 1.0, + "learning_rate": 3.3604113176223485e-05, + "loss": 3.5709, + "step": 1001472 + }, + { + "epoch": 1.0, + "learning_rate": 3.3595727228712965e-05, + "loss": 3.5648, + "step": 1001984 + }, + { + "epoch": 1.0, + "learning_rate": 3.3587357660006174e-05, + "loss": 3.5842, + "step": 1002496 + }, + { + "epoch": 1.0, + "learning_rate": 3.3578971712495654e-05, + "loss": 3.5708, + "step": 1003008 + }, + { + "epoch": 1.0, + "learning_rate": 3.3570585764985134e-05, + "loss": 3.5729, + "step": 1003520 + }, + { + "epoch": 1.0, + "learning_rate": 3.3562199817474614e-05, + "loss": 3.5693, + "step": 1004032 + }, + { + "epoch": 1.0, + "learning_rate": 3.355383024876782e-05, + "loss": 3.5746, + "step": 1004544 + }, + { + "epoch": 1.0, + "learning_rate": 3.35454443012573e-05, + "loss": 3.5702, + "step": 1005056 + }, + { + "epoch": 1.0, + "learning_rate": 3.353705835374679e-05, + "loss": 3.5608, + "step": 1005568 + }, + { + "epoch": 1.0, + "learning_rate": 3.352867240623626e-05, + "loss": 3.5722, + "step": 1006080 + }, + { + "epoch": 1.0, + "learning_rate": 3.352028645872574e-05, + "loss": 3.5572, + "step": 1006592 + }, + { + "epoch": 1.0, + "learning_rate": 3.351191689001896e-05, + "loss": 3.5624, + "step": 1007104 + }, + { + "epoch": 1.01, + "learning_rate": 3.350353094250844e-05, + "loss": 3.5696, + "step": 1007616 + }, + { + "epoch": 1.01, + "learning_rate": 3.349514499499791e-05, + "loss": 3.5666, + "step": 1008128 + }, + { + "epoch": 1.01, + "learning_rate": 3.348675904748739e-05, + "loss": 3.5704, + "step": 1008640 + }, + { + "epoch": 1.01, + "learning_rate": 3.347838947878061e-05, + "loss": 3.5818, + "step": 1009152 + }, + { + "epoch": 1.01, + "learning_rate": 3.347000353127009e-05, + "loss": 3.5683, + "step": 1009664 + }, + { + "epoch": 1.01, + "learning_rate": 3.346161758375956e-05, + "loss": 3.572, + "step": 1010176 + }, + { + "epoch": 1.01, + "learning_rate": 3.345323163624904e-05, + "loss": 3.5729, + "step": 1010688 + }, + { + "epoch": 1.01, + "learning_rate": 3.3444862067542256e-05, + "loss": 3.5626, + "step": 1011200 + }, + { + "epoch": 1.01, + "learning_rate": 3.3436476120031736e-05, + "loss": 3.5687, + "step": 1011712 + }, + { + "epoch": 1.01, + "learning_rate": 3.3428090172521216e-05, + "loss": 3.5652, + "step": 1012224 + }, + { + "epoch": 1.01, + "learning_rate": 3.3419704225010696e-05, + "loss": 3.5607, + "step": 1012736 + }, + { + "epoch": 1.01, + "learning_rate": 3.341133465630391e-05, + "loss": 3.572, + "step": 1013248 + }, + { + "epoch": 1.01, + "learning_rate": 3.3402948708793385e-05, + "loss": 3.5761, + "step": 1013760 + }, + { + "epoch": 1.01, + "learning_rate": 3.3394562761282865e-05, + "loss": 3.5644, + "step": 1014272 + }, + { + "epoch": 1.01, + "learning_rate": 3.3386176813772345e-05, + "loss": 3.5719, + "step": 1014784 + }, + { + "epoch": 1.01, + "learning_rate": 3.337780724506556e-05, + "loss": 3.5714, + "step": 1015296 + }, + { + "epoch": 1.01, + "learning_rate": 3.3369421297555034e-05, + "loss": 3.5662, + "step": 1015808 + }, + { + "epoch": 1.01, + "learning_rate": 3.3361035350044514e-05, + "loss": 3.5732, + "step": 1016320 + }, + { + "epoch": 1.01, + "learning_rate": 3.3352649402533994e-05, + "loss": 3.5398, + "step": 1016832 + }, + { + "epoch": 1.01, + "learning_rate": 3.334427983382721e-05, + "loss": 3.5704, + "step": 1017344 + }, + { + "epoch": 1.01, + "learning_rate": 3.333589388631669e-05, + "loss": 3.5655, + "step": 1017856 + }, + { + "epoch": 1.01, + "learning_rate": 3.332750793880617e-05, + "loss": 3.5732, + "step": 1018368 + }, + { + "epoch": 1.01, + "learning_rate": 3.331912199129565e-05, + "loss": 3.5588, + "step": 1018880 + }, + { + "epoch": 1.01, + "learning_rate": 3.331075242258886e-05, + "loss": 3.5494, + "step": 1019392 + }, + { + "epoch": 1.01, + "learning_rate": 3.330236647507834e-05, + "loss": 3.5486, + "step": 1019904 + }, + { + "epoch": 1.01, + "learning_rate": 3.329398052756782e-05, + "loss": 3.5529, + "step": 1020416 + }, + { + "epoch": 1.01, + "learning_rate": 3.32855945800573e-05, + "loss": 3.5746, + "step": 1020928 + }, + { + "epoch": 1.01, + "learning_rate": 3.327722501135051e-05, + "loss": 3.5507, + "step": 1021440 + }, + { + "epoch": 1.01, + "learning_rate": 3.326883906383999e-05, + "loss": 3.5722, + "step": 1021952 + }, + { + "epoch": 1.01, + "learning_rate": 3.326045311632947e-05, + "loss": 3.562, + "step": 1022464 + }, + { + "epoch": 1.01, + "learning_rate": 3.325206716881895e-05, + "loss": 3.5545, + "step": 1022976 + }, + { + "epoch": 1.01, + "learning_rate": 3.3243697600112164e-05, + "loss": 3.5644, + "step": 1023488 + }, + { + "epoch": 1.01, + "learning_rate": 3.3235311652601644e-05, + "loss": 3.5472, + "step": 1024000 + }, + { + "epoch": 1.01, + "learning_rate": 3.3226925705091124e-05, + "loss": 3.5533, + "step": 1024512 + }, + { + "epoch": 1.01, + "learning_rate": 3.321855613638433e-05, + "loss": 3.5539, + "step": 1025024 + }, + { + "epoch": 1.01, + "learning_rate": 3.321017018887381e-05, + "loss": 3.5724, + "step": 1025536 + }, + { + "epoch": 1.01, + "learning_rate": 3.320178424136329e-05, + "loss": 3.5546, + "step": 1026048 + }, + { + "epoch": 1.01, + "learning_rate": 3.319339829385277e-05, + "loss": 3.5582, + "step": 1026560 + }, + { + "epoch": 1.01, + "learning_rate": 3.318501234634225e-05, + "loss": 3.5464, + "step": 1027072 + }, + { + "epoch": 1.01, + "learning_rate": 3.317664277763546e-05, + "loss": 3.5609, + "step": 1027584 + }, + { + "epoch": 1.01, + "learning_rate": 3.316825683012494e-05, + "loss": 3.5663, + "step": 1028096 + }, + { + "epoch": 1.01, + "learning_rate": 3.315987088261442e-05, + "loss": 3.5668, + "step": 1028608 + }, + { + "epoch": 1.01, + "learning_rate": 3.315150131390764e-05, + "loss": 3.5687, + "step": 1029120 + }, + { + "epoch": 1.01, + "learning_rate": 3.314311536639712e-05, + "loss": 3.5691, + "step": 1029632 + }, + { + "epoch": 1.01, + "learning_rate": 3.31347294188866e-05, + "loss": 3.5807, + "step": 1030144 + }, + { + "epoch": 1.01, + "learning_rate": 3.312634347137608e-05, + "loss": 3.5691, + "step": 1030656 + }, + { + "epoch": 1.01, + "learning_rate": 3.3117973902669286e-05, + "loss": 3.5744, + "step": 1031168 + }, + { + "epoch": 1.01, + "learning_rate": 3.3109587955158766e-05, + "loss": 3.5597, + "step": 1031680 + }, + { + "epoch": 1.01, + "learning_rate": 3.3101202007648246e-05, + "loss": 3.5612, + "step": 1032192 + }, + { + "epoch": 1.01, + "learning_rate": 3.3092816060137726e-05, + "loss": 3.5599, + "step": 1032704 + }, + { + "epoch": 1.01, + "learning_rate": 3.3084430112627206e-05, + "loss": 3.5608, + "step": 1033216 + }, + { + "epoch": 1.01, + "learning_rate": 3.3076060543920415e-05, + "loss": 3.57, + "step": 1033728 + }, + { + "epoch": 1.01, + "learning_rate": 3.3067674596409895e-05, + "loss": 3.5712, + "step": 1034240 + }, + { + "epoch": 1.01, + "learning_rate": 3.3059288648899375e-05, + "loss": 3.567, + "step": 1034752 + }, + { + "epoch": 1.01, + "learning_rate": 3.3050902701388855e-05, + "loss": 3.5478, + "step": 1035264 + }, + { + "epoch": 1.01, + "learning_rate": 3.304253313268207e-05, + "loss": 3.5543, + "step": 1035776 + }, + { + "epoch": 1.01, + "learning_rate": 3.303414718517155e-05, + "loss": 3.5722, + "step": 1036288 + }, + { + "epoch": 1.01, + "learning_rate": 3.302576123766103e-05, + "loss": 3.5648, + "step": 1036800 + }, + { + "epoch": 1.01, + "learning_rate": 3.301737529015051e-05, + "loss": 3.5569, + "step": 1037312 + }, + { + "epoch": 1.01, + "learning_rate": 3.300900572144372e-05, + "loss": 3.5613, + "step": 1037824 + }, + { + "epoch": 1.02, + "learning_rate": 3.30006197739332e-05, + "loss": 3.563, + "step": 1038336 + }, + { + "epoch": 1.02, + "learning_rate": 3.299225020522641e-05, + "loss": 3.5552, + "step": 1038848 + }, + { + "epoch": 1.02, + "learning_rate": 3.298386425771589e-05, + "loss": 3.5584, + "step": 1039360 + }, + { + "epoch": 1.02, + "learning_rate": 3.297547831020537e-05, + "loss": 3.5713, + "step": 1039872 + }, + { + "epoch": 1.02, + "learning_rate": 3.296709236269485e-05, + "loss": 3.5695, + "step": 1040384 + }, + { + "epoch": 1.02, + "learning_rate": 3.295870641518433e-05, + "loss": 3.5671, + "step": 1040896 + }, + { + "epoch": 1.02, + "learning_rate": 3.295032046767381e-05, + "loss": 3.5494, + "step": 1041408 + }, + { + "epoch": 1.02, + "learning_rate": 3.2941934520163296e-05, + "loss": 3.5578, + "step": 1041920 + }, + { + "epoch": 1.02, + "learning_rate": 3.2933548572652776e-05, + "loss": 3.5633, + "step": 1042432 + }, + { + "epoch": 1.02, + "learning_rate": 3.2925179003945985e-05, + "loss": 3.5656, + "step": 1042944 + }, + { + "epoch": 1.02, + "learning_rate": 3.2916793056435465e-05, + "loss": 3.5666, + "step": 1043456 + }, + { + "epoch": 1.02, + "learning_rate": 3.2908407108924945e-05, + "loss": 3.568, + "step": 1043968 + }, + { + "epoch": 1.02, + "learning_rate": 3.2900021161414425e-05, + "loss": 3.5618, + "step": 1044480 + }, + { + "epoch": 1.02, + "learning_rate": 3.2891651592707634e-05, + "loss": 3.5601, + "step": 1044992 + }, + { + "epoch": 1.02, + "learning_rate": 3.2883265645197114e-05, + "loss": 3.5636, + "step": 1045504 + }, + { + "epoch": 1.02, + "learning_rate": 3.2874879697686594e-05, + "loss": 3.5515, + "step": 1046016 + }, + { + "epoch": 1.02, + "learning_rate": 3.2866493750176073e-05, + "loss": 3.5518, + "step": 1046528 + }, + { + "epoch": 1.02, + "learning_rate": 3.285812418146928e-05, + "loss": 3.5617, + "step": 1047040 + }, + { + "epoch": 1.02, + "learning_rate": 3.284973823395876e-05, + "loss": 3.5588, + "step": 1047552 + }, + { + "epoch": 1.02, + "learning_rate": 3.284135228644825e-05, + "loss": 3.5464, + "step": 1048064 + }, + { + "epoch": 1.02, + "learning_rate": 3.283296633893773e-05, + "loss": 3.5546, + "step": 1048576 + }, + { + "epoch": 1.02, + "learning_rate": 3.282459677023094e-05, + "loss": 3.5502, + "step": 1049088 + }, + { + "epoch": 1.02, + "learning_rate": 3.281621082272042e-05, + "loss": 3.562, + "step": 1049600 + }, + { + "epoch": 1.02, + "learning_rate": 3.28078248752099e-05, + "loss": 3.5604, + "step": 1050112 + }, + { + "epoch": 1.02, + "learning_rate": 3.279943892769938e-05, + "loss": 3.5575, + "step": 1050624 + }, + { + "epoch": 1.02, + "learning_rate": 3.279106935899259e-05, + "loss": 3.5642, + "step": 1051136 + }, + { + "epoch": 1.02, + "learning_rate": 3.2782699790285796e-05, + "loss": 3.5652, + "step": 1051648 + }, + { + "epoch": 1.02, + "learning_rate": 3.2774313842775276e-05, + "loss": 3.5591, + "step": 1052160 + }, + { + "epoch": 1.02, + "learning_rate": 3.2765927895264756e-05, + "loss": 3.5657, + "step": 1052672 + }, + { + "epoch": 1.02, + "learning_rate": 3.2757541947754236e-05, + "loss": 3.568, + "step": 1053184 + }, + { + "epoch": 1.02, + "learning_rate": 3.2749156000243716e-05, + "loss": 3.5625, + "step": 1053696 + }, + { + "epoch": 1.02, + "learning_rate": 3.2740770052733196e-05, + "loss": 3.5577, + "step": 1054208 + }, + { + "epoch": 1.02, + "learning_rate": 3.273238410522268e-05, + "loss": 3.5658, + "step": 1054720 + }, + { + "epoch": 1.02, + "learning_rate": 3.272399815771216e-05, + "loss": 3.5594, + "step": 1055232 + }, + { + "epoch": 1.02, + "learning_rate": 3.271562858900537e-05, + "loss": 3.5573, + "step": 1055744 + }, + { + "epoch": 1.02, + "learning_rate": 3.270724264149485e-05, + "loss": 3.5502, + "step": 1056256 + }, + { + "epoch": 1.02, + "learning_rate": 3.269885669398433e-05, + "loss": 3.5615, + "step": 1056768 + }, + { + "epoch": 1.02, + "learning_rate": 3.269047074647381e-05, + "loss": 3.5515, + "step": 1057280 + }, + { + "epoch": 1.02, + "learning_rate": 3.268210117776702e-05, + "loss": 3.5534, + "step": 1057792 + }, + { + "epoch": 1.02, + "learning_rate": 3.26737152302565e-05, + "loss": 3.5539, + "step": 1058304 + }, + { + "epoch": 1.02, + "learning_rate": 3.266532928274598e-05, + "loss": 3.5648, + "step": 1058816 + }, + { + "epoch": 1.02, + "learning_rate": 3.265694333523546e-05, + "loss": 3.5644, + "step": 1059328 + }, + { + "epoch": 1.02, + "learning_rate": 3.264857376652867e-05, + "loss": 3.5515, + "step": 1059840 + }, + { + "epoch": 1.02, + "learning_rate": 3.264018781901815e-05, + "loss": 3.5652, + "step": 1060352 + }, + { + "epoch": 1.02, + "learning_rate": 3.2631801871507637e-05, + "loss": 3.5639, + "step": 1060864 + }, + { + "epoch": 1.02, + "learning_rate": 3.2623415923997117e-05, + "loss": 3.5643, + "step": 1061376 + }, + { + "epoch": 1.02, + "learning_rate": 3.2615046355290326e-05, + "loss": 3.5591, + "step": 1061888 + }, + { + "epoch": 1.02, + "learning_rate": 3.2606660407779806e-05, + "loss": 3.5551, + "step": 1062400 + }, + { + "epoch": 1.02, + "learning_rate": 3.2598274460269286e-05, + "loss": 3.574, + "step": 1062912 + }, + { + "epoch": 1.02, + "learning_rate": 3.258988851275876e-05, + "loss": 3.5596, + "step": 1063424 + }, + { + "epoch": 1.02, + "learning_rate": 3.2581518944051975e-05, + "loss": 3.5635, + "step": 1063936 + }, + { + "epoch": 1.02, + "learning_rate": 3.2573132996541455e-05, + "loss": 3.5556, + "step": 1064448 + }, + { + "epoch": 1.02, + "learning_rate": 3.2564747049030934e-05, + "loss": 3.5611, + "step": 1064960 + }, + { + "epoch": 1.02, + "learning_rate": 3.255636110152041e-05, + "loss": 3.5574, + "step": 1065472 + }, + { + "epoch": 1.02, + "learning_rate": 3.2547991532813624e-05, + "loss": 3.557, + "step": 1065984 + }, + { + "epoch": 1.02, + "learning_rate": 3.2539605585303103e-05, + "loss": 3.5648, + "step": 1066496 + }, + { + "epoch": 1.02, + "learning_rate": 3.253121963779259e-05, + "loss": 3.558, + "step": 1067008 + }, + { + "epoch": 1.02, + "learning_rate": 3.2522833690282063e-05, + "loss": 3.5649, + "step": 1067520 + }, + { + "epoch": 1.02, + "learning_rate": 3.251446412157528e-05, + "loss": 3.5571, + "step": 1068032 + }, + { + "epoch": 1.03, + "eval_loss": 3.8441572189331055, + "eval_runtime": 314.3616, + "eval_samples_per_second": 1213.86, + "eval_steps_per_second": 37.934, + "step": 1068480 + }, + { + "epoch": 0.0, + "learning_rate": 3.250607817406476e-05, + "loss": 3.5471, + "step": 1068544 + }, + { + "epoch": 0.0, + "learning_rate": 3.249769222655423e-05, + "loss": 3.5484, + "step": 1069056 + }, + { + "epoch": 0.0, + "learning_rate": 3.248930627904371e-05, + "loss": 3.5494, + "step": 1069568 + }, + { + "epoch": 0.0, + "learning_rate": 3.248092033153319e-05, + "loss": 3.5644, + "step": 1070080 + }, + { + "epoch": 0.0, + "learning_rate": 3.247255076282641e-05, + "loss": 3.5617, + "step": 1070592 + }, + { + "epoch": 0.0, + "learning_rate": 3.246416481531588e-05, + "loss": 3.5656, + "step": 1071104 + }, + { + "epoch": 0.0, + "learning_rate": 3.245577886780536e-05, + "loss": 3.5496, + "step": 1071616 + }, + { + "epoch": 0.0, + "learning_rate": 3.244739292029484e-05, + "loss": 3.5518, + "step": 1072128 + }, + { + "epoch": 0.0, + "learning_rate": 3.243902335158806e-05, + "loss": 3.5435, + "step": 1072640 + }, + { + "epoch": 0.0, + "learning_rate": 3.243063740407754e-05, + "loss": 3.5596, + "step": 1073152 + }, + { + "epoch": 0.0, + "learning_rate": 3.242225145656702e-05, + "loss": 3.5561, + "step": 1073664 + }, + { + "epoch": 0.0, + "learning_rate": 3.24138655090565e-05, + "loss": 3.5554, + "step": 1074176 + }, + { + "epoch": 0.0, + "learning_rate": 3.2405495940349706e-05, + "loss": 3.5608, + "step": 1074688 + }, + { + "epoch": 0.0, + "learning_rate": 3.239712637164292e-05, + "loss": 3.5423, + "step": 1075200 + }, + { + "epoch": 0.0, + "learning_rate": 3.23887404241324e-05, + "loss": 3.5482, + "step": 1075712 + }, + { + "epoch": 0.0, + "learning_rate": 3.238035447662188e-05, + "loss": 3.5417, + "step": 1076224 + }, + { + "epoch": 0.0, + "learning_rate": 3.2371968529111355e-05, + "loss": 3.5557, + "step": 1076736 + }, + { + "epoch": 0.0, + "learning_rate": 3.2363582581600835e-05, + "loss": 3.5447, + "step": 1077248 + }, + { + "epoch": 0.0, + "learning_rate": 3.2355196634090315e-05, + "loss": 3.5578, + "step": 1077760 + }, + { + "epoch": 0.0, + "learning_rate": 3.2346810686579795e-05, + "loss": 3.5488, + "step": 1078272 + }, + { + "epoch": 0.0, + "learning_rate": 3.233842473906928e-05, + "loss": 3.5685, + "step": 1078784 + }, + { + "epoch": 0.0, + "learning_rate": 3.233005517036249e-05, + "loss": 3.5544, + "step": 1079296 + }, + { + "epoch": 0.0, + "learning_rate": 3.232166922285197e-05, + "loss": 3.5514, + "step": 1079808 + }, + { + "epoch": 0.0, + "learning_rate": 3.231328327534145e-05, + "loss": 3.5523, + "step": 1080320 + }, + { + "epoch": 0.0, + "learning_rate": 3.230489732783093e-05, + "loss": 3.5648, + "step": 1080832 + }, + { + "epoch": 0.0, + "learning_rate": 3.229652775912414e-05, + "loss": 3.555, + "step": 1081344 + }, + { + "epoch": 0.0, + "learning_rate": 3.228814181161362e-05, + "loss": 3.5462, + "step": 1081856 + }, + { + "epoch": 0.0, + "learning_rate": 3.22797558641031e-05, + "loss": 3.5553, + "step": 1082368 + }, + { + "epoch": 0.0, + "learning_rate": 3.227136991659258e-05, + "loss": 3.5404, + "step": 1082880 + }, + { + "epoch": 0.0, + "learning_rate": 3.226300034788579e-05, + "loss": 3.546, + "step": 1083392 + }, + { + "epoch": 0.01, + "learning_rate": 3.225461440037527e-05, + "loss": 3.5518, + "step": 1083904 + }, + { + "epoch": 0.01, + "learning_rate": 3.224622845286475e-05, + "loss": 3.5504, + "step": 1084416 + }, + { + "epoch": 0.01, + "learning_rate": 3.2237842505354235e-05, + "loss": 3.5544, + "step": 1084928 + }, + { + "epoch": 0.01, + "learning_rate": 3.2229472936647444e-05, + "loss": 3.5627, + "step": 1085440 + }, + { + "epoch": 0.01, + "learning_rate": 3.2221086989136924e-05, + "loss": 3.5541, + "step": 1085952 + }, + { + "epoch": 0.01, + "learning_rate": 3.2212701041626404e-05, + "loss": 3.5571, + "step": 1086464 + }, + { + "epoch": 0.01, + "learning_rate": 3.2204315094115884e-05, + "loss": 3.5562, + "step": 1086976 + }, + { + "epoch": 0.01, + "learning_rate": 3.2195945525409093e-05, + "loss": 3.5451, + "step": 1087488 + }, + { + "epoch": 0.01, + "learning_rate": 3.218755957789857e-05, + "loss": 3.5569, + "step": 1088000 + }, + { + "epoch": 0.01, + "learning_rate": 3.217917363038805e-05, + "loss": 3.5502, + "step": 1088512 + }, + { + "epoch": 0.01, + "learning_rate": 3.217078768287753e-05, + "loss": 3.5477, + "step": 1089024 + }, + { + "epoch": 0.01, + "learning_rate": 3.216241811417074e-05, + "loss": 3.55, + "step": 1089536 + }, + { + "epoch": 0.01, + "learning_rate": 3.215403216666022e-05, + "loss": 3.5607, + "step": 1090048 + }, + { + "epoch": 0.01, + "learning_rate": 3.21456462191497e-05, + "loss": 3.5456, + "step": 1090560 + }, + { + "epoch": 0.01, + "learning_rate": 3.213726027163919e-05, + "loss": 3.5607, + "step": 1091072 + }, + { + "epoch": 0.01, + "learning_rate": 3.21288907029324e-05, + "loss": 3.5526, + "step": 1091584 + }, + { + "epoch": 0.01, + "learning_rate": 3.212050475542188e-05, + "loss": 3.5521, + "step": 1092096 + }, + { + "epoch": 0.01, + "learning_rate": 3.211211880791136e-05, + "loss": 3.5534, + "step": 1092608 + }, + { + "epoch": 0.01, + "learning_rate": 3.210373286040084e-05, + "loss": 3.5255, + "step": 1093120 + }, + { + "epoch": 0.01, + "learning_rate": 3.209536329169405e-05, + "loss": 3.5511, + "step": 1093632 + }, + { + "epoch": 0.01, + "learning_rate": 3.208697734418353e-05, + "loss": 3.5569, + "step": 1094144 + }, + { + "epoch": 0.01, + "learning_rate": 3.207859139667301e-05, + "loss": 3.553, + "step": 1094656 + }, + { + "epoch": 0.01, + "learning_rate": 3.207020544916249e-05, + "loss": 3.5404, + "step": 1095168 + }, + { + "epoch": 0.01, + "learning_rate": 3.2061835880455696e-05, + "loss": 3.5363, + "step": 1095680 + }, + { + "epoch": 0.01, + "learning_rate": 3.2053449932945176e-05, + "loss": 3.5318, + "step": 1096192 + }, + { + "epoch": 0.01, + "learning_rate": 3.2045063985434656e-05, + "loss": 3.5362, + "step": 1096704 + }, + { + "epoch": 0.01, + "learning_rate": 3.203667803792414e-05, + "loss": 3.561, + "step": 1097216 + }, + { + "epoch": 0.01, + "learning_rate": 3.202830846921735e-05, + "loss": 3.5335, + "step": 1097728 + }, + { + "epoch": 0.01, + "learning_rate": 3.201992252170683e-05, + "loss": 3.5562, + "step": 1098240 + }, + { + "epoch": 0.01, + "learning_rate": 3.201153657419631e-05, + "loss": 3.5473, + "step": 1098752 + }, + { + "epoch": 0.01, + "learning_rate": 3.200315062668579e-05, + "loss": 3.5361, + "step": 1099264 + }, + { + "epoch": 0.01, + "learning_rate": 3.1994781057979e-05, + "loss": 3.551, + "step": 1099776 + }, + { + "epoch": 0.01, + "learning_rate": 3.198639511046848e-05, + "loss": 3.5367, + "step": 1100288 + }, + { + "epoch": 0.01, + "learning_rate": 3.197800916295796e-05, + "loss": 3.5399, + "step": 1100800 + }, + { + "epoch": 0.01, + "learning_rate": 3.196962321544744e-05, + "loss": 3.5345, + "step": 1101312 + }, + { + "epoch": 0.01, + "learning_rate": 3.196125364674065e-05, + "loss": 3.5532, + "step": 1101824 + }, + { + "epoch": 0.01, + "learning_rate": 3.195286769923013e-05, + "loss": 3.5417, + "step": 1102336 + }, + { + "epoch": 0.01, + "learning_rate": 3.194448175171961e-05, + "loss": 3.5407, + "step": 1102848 + }, + { + "epoch": 0.01, + "learning_rate": 3.1936095804209096e-05, + "loss": 3.5323, + "step": 1103360 + }, + { + "epoch": 0.01, + "learning_rate": 3.1927726235502305e-05, + "loss": 3.5448, + "step": 1103872 + }, + { + "epoch": 0.01, + "learning_rate": 3.1919340287991785e-05, + "loss": 3.5502, + "step": 1104384 + }, + { + "epoch": 0.01, + "learning_rate": 3.1910954340481265e-05, + "loss": 3.5511, + "step": 1104896 + }, + { + "epoch": 0.01, + "learning_rate": 3.1902568392970745e-05, + "loss": 3.5512, + "step": 1105408 + }, + { + "epoch": 0.01, + "learning_rate": 3.1894198824263954e-05, + "loss": 3.5548, + "step": 1105920 + }, + { + "epoch": 0.01, + "learning_rate": 3.1885812876753434e-05, + "loss": 3.5653, + "step": 1106432 + }, + { + "epoch": 0.01, + "learning_rate": 3.1877426929242914e-05, + "loss": 3.5525, + "step": 1106944 + }, + { + "epoch": 0.01, + "learning_rate": 3.1869040981732394e-05, + "loss": 3.5566, + "step": 1107456 + }, + { + "epoch": 0.01, + "learning_rate": 3.18606714130256e-05, + "loss": 3.546, + "step": 1107968 + }, + { + "epoch": 0.01, + "learning_rate": 3.185228546551508e-05, + "loss": 3.5469, + "step": 1108480 + }, + { + "epoch": 0.01, + "learning_rate": 3.184389951800456e-05, + "loss": 3.5458, + "step": 1108992 + }, + { + "epoch": 0.01, + "learning_rate": 3.183551357049404e-05, + "loss": 3.5421, + "step": 1109504 + }, + { + "epoch": 0.01, + "learning_rate": 3.182714400178726e-05, + "loss": 3.5573, + "step": 1110016 + }, + { + "epoch": 0.01, + "learning_rate": 3.181875805427674e-05, + "loss": 3.5581, + "step": 1110528 + }, + { + "epoch": 0.01, + "learning_rate": 3.181037210676622e-05, + "loss": 3.5521, + "step": 1111040 + }, + { + "epoch": 0.01, + "learning_rate": 3.18019861592557e-05, + "loss": 3.529, + "step": 1111552 + }, + { + "epoch": 0.01, + "learning_rate": 3.179361659054891e-05, + "loss": 3.543, + "step": 1112064 + }, + { + "epoch": 0.01, + "learning_rate": 3.178523064303839e-05, + "loss": 3.5527, + "step": 1112576 + }, + { + "epoch": 0.01, + "learning_rate": 3.177684469552787e-05, + "loss": 3.5516, + "step": 1113088 + }, + { + "epoch": 0.01, + "learning_rate": 3.176845874801735e-05, + "loss": 3.5395, + "step": 1113600 + }, + { + "epoch": 0.01, + "learning_rate": 3.176008917931056e-05, + "loss": 3.5496, + "step": 1114112 + }, + { + "epoch": 0.02, + "learning_rate": 3.175170323180004e-05, + "loss": 3.5463, + "step": 1114624 + }, + { + "epoch": 0.02, + "learning_rate": 3.174333366309325e-05, + "loss": 3.5384, + "step": 1115136 + }, + { + "epoch": 0.02, + "learning_rate": 3.173494771558273e-05, + "loss": 3.5425, + "step": 1115648 + }, + { + "epoch": 0.02, + "learning_rate": 3.172656176807221e-05, + "loss": 3.5557, + "step": 1116160 + }, + { + "epoch": 0.02, + "learning_rate": 3.171817582056169e-05, + "loss": 3.5498, + "step": 1116672 + }, + { + "epoch": 0.02, + "learning_rate": 3.170978987305117e-05, + "loss": 3.5549, + "step": 1117184 + }, + { + "epoch": 0.02, + "learning_rate": 3.170140392554065e-05, + "loss": 3.5358, + "step": 1117696 + }, + { + "epoch": 0.02, + "learning_rate": 3.169301797803013e-05, + "loss": 3.5415, + "step": 1118208 + }, + { + "epoch": 0.02, + "learning_rate": 3.1684632030519606e-05, + "loss": 3.549, + "step": 1118720 + }, + { + "epoch": 0.02, + "learning_rate": 3.167626246181282e-05, + "loss": 3.5486, + "step": 1119232 + }, + { + "epoch": 0.02, + "learning_rate": 3.16678765143023e-05, + "loss": 3.5508, + "step": 1119744 + }, + { + "epoch": 0.02, + "learning_rate": 3.165949056679178e-05, + "loss": 3.5524, + "step": 1120256 + }, + { + "epoch": 0.02, + "learning_rate": 3.1651104619281255e-05, + "loss": 3.5464, + "step": 1120768 + }, + { + "epoch": 0.02, + "learning_rate": 3.164273505057447e-05, + "loss": 3.5473, + "step": 1121280 + }, + { + "epoch": 0.02, + "learning_rate": 3.163434910306395e-05, + "loss": 3.5521, + "step": 1121792 + }, + { + "epoch": 0.02, + "learning_rate": 3.162596315555344e-05, + "loss": 3.5328, + "step": 1122304 + }, + { + "epoch": 0.02, + "learning_rate": 3.161757720804291e-05, + "loss": 3.5392, + "step": 1122816 + }, + { + "epoch": 0.02, + "learning_rate": 3.1609207639336126e-05, + "loss": 3.5446, + "step": 1123328 + }, + { + "epoch": 0.02, + "learning_rate": 3.1600821691825606e-05, + "loss": 3.5449, + "step": 1123840 + }, + { + "epoch": 0.02, + "learning_rate": 3.159243574431508e-05, + "loss": 3.5352, + "step": 1124352 + }, + { + "epoch": 0.02, + "learning_rate": 3.158404979680456e-05, + "loss": 3.5371, + "step": 1124864 + }, + { + "epoch": 0.02, + "learning_rate": 3.1575680228097775e-05, + "loss": 3.5341, + "step": 1125376 + }, + { + "epoch": 0.02, + "learning_rate": 3.1567294280587255e-05, + "loss": 3.5507, + "step": 1125888 + }, + { + "epoch": 0.02, + "learning_rate": 3.155890833307673e-05, + "loss": 3.5443, + "step": 1126400 + }, + { + "epoch": 0.02, + "learning_rate": 3.155052238556621e-05, + "loss": 3.5419, + "step": 1126912 + }, + { + "epoch": 0.02, + "learning_rate": 3.1542152816859424e-05, + "loss": 3.5488, + "step": 1127424 + }, + { + "epoch": 0.02, + "learning_rate": 3.1533766869348904e-05, + "loss": 3.5508, + "step": 1127936 + }, + { + "epoch": 0.02, + "learning_rate": 3.1525380921838384e-05, + "loss": 3.5475, + "step": 1128448 + }, + { + "epoch": 0.02, + "learning_rate": 3.1516994974327864e-05, + "loss": 3.5443, + "step": 1128960 + }, + { + "epoch": 0.02, + "learning_rate": 3.150862540562108e-05, + "loss": 3.5562, + "step": 1129472 + }, + { + "epoch": 0.02, + "learning_rate": 3.150023945811055e-05, + "loss": 3.5476, + "step": 1129984 + }, + { + "epoch": 0.02, + "learning_rate": 3.149185351060003e-05, + "loss": 3.5388, + "step": 1130496 + }, + { + "epoch": 0.02, + "learning_rate": 3.148346756308951e-05, + "loss": 3.5484, + "step": 1131008 + }, + { + "epoch": 0.02, + "learning_rate": 3.147509799438273e-05, + "loss": 3.5436, + "step": 1131520 + }, + { + "epoch": 0.02, + "learning_rate": 3.14667120468722e-05, + "loss": 3.5457, + "step": 1132032 + }, + { + "epoch": 0.02, + "learning_rate": 3.145832609936168e-05, + "loss": 3.5332, + "step": 1132544 + }, + { + "epoch": 0.02, + "learning_rate": 3.144994015185116e-05, + "loss": 3.5491, + "step": 1133056 + }, + { + "epoch": 0.02, + "learning_rate": 3.144157058314438e-05, + "loss": 3.5362, + "step": 1133568 + }, + { + "epoch": 0.02, + "learning_rate": 3.143318463563386e-05, + "loss": 3.5402, + "step": 1134080 + }, + { + "epoch": 0.02, + "learning_rate": 3.142479868812334e-05, + "loss": 3.5316, + "step": 1134592 + }, + { + "epoch": 0.02, + "learning_rate": 3.141641274061282e-05, + "loss": 3.5519, + "step": 1135104 + }, + { + "epoch": 0.02, + "learning_rate": 3.140804317190603e-05, + "loss": 3.5504, + "step": 1135616 + }, + { + "epoch": 0.02, + "learning_rate": 3.139965722439551e-05, + "loss": 3.5319, + "step": 1136128 + }, + { + "epoch": 0.02, + "learning_rate": 3.139127127688499e-05, + "loss": 3.5522, + "step": 1136640 + }, + { + "epoch": 0.02, + "learning_rate": 3.138288532937447e-05, + "loss": 3.5481, + "step": 1137152 + }, + { + "epoch": 0.02, + "learning_rate": 3.1374515760667676e-05, + "loss": 3.5496, + "step": 1137664 + }, + { + "epoch": 0.02, + "learning_rate": 3.1366129813157156e-05, + "loss": 3.5439, + "step": 1138176 + }, + { + "epoch": 0.02, + "learning_rate": 3.1357743865646636e-05, + "loss": 3.5438, + "step": 1138688 + }, + { + "epoch": 0.02, + "learning_rate": 3.1349357918136116e-05, + "loss": 3.5591, + "step": 1139200 + }, + { + "epoch": 0.02, + "learning_rate": 3.134098834942933e-05, + "loss": 3.541, + "step": 1139712 + }, + { + "epoch": 0.02, + "learning_rate": 3.133260240191881e-05, + "loss": 3.551, + "step": 1140224 + }, + { + "epoch": 0.02, + "learning_rate": 3.132421645440829e-05, + "loss": 3.539, + "step": 1140736 + }, + { + "epoch": 0.02, + "learning_rate": 3.131583050689777e-05, + "loss": 3.5464, + "step": 1141248 + }, + { + "epoch": 0.02, + "learning_rate": 3.130746093819098e-05, + "loss": 3.5398, + "step": 1141760 + }, + { + "epoch": 0.02, + "learning_rate": 3.129907499068046e-05, + "loss": 3.5401, + "step": 1142272 + }, + { + "epoch": 0.02, + "learning_rate": 3.129068904316994e-05, + "loss": 3.5488, + "step": 1142784 + }, + { + "epoch": 0.02, + "learning_rate": 3.128231947446315e-05, + "loss": 3.5436, + "step": 1143296 + }, + { + "epoch": 0.02, + "learning_rate": 3.127393352695263e-05, + "loss": 3.5504, + "step": 1143808 + }, + { + "epoch": 0.02, + "learning_rate": 3.126554757944211e-05, + "loss": 3.5422, + "step": 1144320 + }, + { + "epoch": 0.03, + "eval_loss": 3.843904972076416, + "eval_runtime": 310.7982, + "eval_samples_per_second": 1227.777, + "eval_steps_per_second": 38.369, + "step": 1144800 + }, + { + "epoch": 1.0, + "learning_rate": 3.125716163193159e-05, + "loss": 3.54, + "step": 1144832 + }, + { + "epoch": 1.0, + "learning_rate": 3.1248792063224805e-05, + "loss": 3.5379, + "step": 1145344 + }, + { + "epoch": 1.0, + "learning_rate": 3.1240406115714285e-05, + "loss": 3.5356, + "step": 1145856 + }, + { + "epoch": 1.0, + "learning_rate": 3.1232020168203765e-05, + "loss": 3.5471, + "step": 1146368 + }, + { + "epoch": 1.0, + "learning_rate": 3.1223634220693245e-05, + "loss": 3.5462, + "step": 1146880 + }, + { + "epoch": 1.0, + "learning_rate": 3.1215264651986454e-05, + "loss": 3.5541, + "step": 1147392 + }, + { + "epoch": 1.0, + "learning_rate": 3.1206878704475934e-05, + "loss": 3.5332, + "step": 1147904 + }, + { + "epoch": 1.0, + "learning_rate": 3.1198492756965414e-05, + "loss": 3.5373, + "step": 1148416 + }, + { + "epoch": 1.0, + "learning_rate": 3.1190106809454894e-05, + "loss": 3.527, + "step": 1148928 + }, + { + "epoch": 1.0, + "learning_rate": 3.11817372407481e-05, + "loss": 3.5474, + "step": 1149440 + }, + { + "epoch": 1.0, + "learning_rate": 3.117335129323758e-05, + "loss": 3.5349, + "step": 1149952 + }, + { + "epoch": 1.0, + "learning_rate": 3.116496534572706e-05, + "loss": 3.5449, + "step": 1150464 + }, + { + "epoch": 1.0, + "learning_rate": 3.115657939821654e-05, + "loss": 3.547, + "step": 1150976 + }, + { + "epoch": 1.0, + "learning_rate": 3.114820982950976e-05, + "loss": 3.529, + "step": 1151488 + }, + { + "epoch": 1.0, + "learning_rate": 3.113982388199924e-05, + "loss": 3.5311, + "step": 1152000 + }, + { + "epoch": 1.0, + "learning_rate": 3.113143793448872e-05, + "loss": 3.5305, + "step": 1152512 + }, + { + "epoch": 1.0, + "learning_rate": 3.11230519869782e-05, + "loss": 3.537, + "step": 1153024 + }, + { + "epoch": 1.0, + "learning_rate": 3.111466603946768e-05, + "loss": 3.5333, + "step": 1153536 + }, + { + "epoch": 1.0, + "learning_rate": 3.110628009195716e-05, + "loss": 3.5401, + "step": 1154048 + }, + { + "epoch": 1.0, + "learning_rate": 3.109789414444664e-05, + "loss": 3.5313, + "step": 1154560 + }, + { + "epoch": 1.0, + "learning_rate": 3.108952457573985e-05, + "loss": 3.5518, + "step": 1155072 + }, + { + "epoch": 1.0, + "learning_rate": 3.108113862822933e-05, + "loss": 3.5383, + "step": 1155584 + }, + { + "epoch": 1.0, + "learning_rate": 3.107275268071881e-05, + "loss": 3.5399, + "step": 1156096 + }, + { + "epoch": 1.0, + "learning_rate": 3.106436673320829e-05, + "loss": 3.5393, + "step": 1156608 + }, + { + "epoch": 1.0, + "learning_rate": 3.105598078569777e-05, + "loss": 3.5466, + "step": 1157120 + }, + { + "epoch": 1.0, + "learning_rate": 3.104761121699098e-05, + "loss": 3.538, + "step": 1157632 + }, + { + "epoch": 1.0, + "learning_rate": 3.103922526948046e-05, + "loss": 3.5326, + "step": 1158144 + }, + { + "epoch": 1.0, + "learning_rate": 3.103083932196994e-05, + "loss": 3.5378, + "step": 1158656 + }, + { + "epoch": 1.0, + "learning_rate": 3.102246975326315e-05, + "loss": 3.5242, + "step": 1159168 + }, + { + "epoch": 1.0, + "learning_rate": 3.101408380575263e-05, + "loss": 3.5347, + "step": 1159680 + }, + { + "epoch": 1.01, + "learning_rate": 3.100569785824211e-05, + "loss": 3.5337, + "step": 1160192 + }, + { + "epoch": 1.01, + "learning_rate": 3.099731191073159e-05, + "loss": 3.5407, + "step": 1160704 + }, + { + "epoch": 1.01, + "learning_rate": 3.09889423420248e-05, + "loss": 3.5362, + "step": 1161216 + }, + { + "epoch": 1.01, + "learning_rate": 3.098055639451428e-05, + "loss": 3.5459, + "step": 1161728 + }, + { + "epoch": 1.01, + "learning_rate": 3.097217044700376e-05, + "loss": 3.5431, + "step": 1162240 + }, + { + "epoch": 1.01, + "learning_rate": 3.096378449949324e-05, + "loss": 3.539, + "step": 1162752 + }, + { + "epoch": 1.01, + "learning_rate": 3.095541493078645e-05, + "loss": 3.5424, + "step": 1163264 + }, + { + "epoch": 1.01, + "learning_rate": 3.094702898327593e-05, + "loss": 3.5293, + "step": 1163776 + }, + { + "epoch": 1.01, + "learning_rate": 3.093864303576541e-05, + "loss": 3.5414, + "step": 1164288 + }, + { + "epoch": 1.01, + "learning_rate": 3.093025708825489e-05, + "loss": 3.531, + "step": 1164800 + }, + { + "epoch": 1.01, + "learning_rate": 3.0921887519548106e-05, + "loss": 3.5346, + "step": 1165312 + }, + { + "epoch": 1.01, + "learning_rate": 3.0913501572037586e-05, + "loss": 3.5388, + "step": 1165824 + }, + { + "epoch": 1.01, + "learning_rate": 3.0905115624527066e-05, + "loss": 3.5449, + "step": 1166336 + }, + { + "epoch": 1.01, + "learning_rate": 3.0896729677016546e-05, + "loss": 3.5338, + "step": 1166848 + }, + { + "epoch": 1.01, + "learning_rate": 3.0888360108309755e-05, + "loss": 3.5424, + "step": 1167360 + }, + { + "epoch": 1.01, + "learning_rate": 3.0879974160799235e-05, + "loss": 3.5399, + "step": 1167872 + }, + { + "epoch": 1.01, + "learning_rate": 3.0871588213288715e-05, + "loss": 3.5368, + "step": 1168384 + }, + { + "epoch": 1.01, + "learning_rate": 3.0863202265778195e-05, + "loss": 3.5421, + "step": 1168896 + }, + { + "epoch": 1.01, + "learning_rate": 3.0854832697071404e-05, + "loss": 3.513, + "step": 1169408 + }, + { + "epoch": 1.01, + "learning_rate": 3.0846446749560884e-05, + "loss": 3.532, + "step": 1169920 + }, + { + "epoch": 1.01, + "learning_rate": 3.0838060802050364e-05, + "loss": 3.5423, + "step": 1170432 + }, + { + "epoch": 1.01, + "learning_rate": 3.0829674854539844e-05, + "loss": 3.5399, + "step": 1170944 + }, + { + "epoch": 1.01, + "learning_rate": 3.082130528583306e-05, + "loss": 3.5267, + "step": 1171456 + }, + { + "epoch": 1.01, + "learning_rate": 3.081291933832254e-05, + "loss": 3.5159, + "step": 1171968 + }, + { + "epoch": 1.01, + "learning_rate": 3.080453339081202e-05, + "loss": 3.5218, + "step": 1172480 + }, + { + "epoch": 1.01, + "learning_rate": 3.07961474433015e-05, + "loss": 3.517, + "step": 1172992 + }, + { + "epoch": 1.01, + "learning_rate": 3.078777787459471e-05, + "loss": 3.55, + "step": 1173504 + }, + { + "epoch": 1.01, + "learning_rate": 3.077939192708419e-05, + "loss": 3.5172, + "step": 1174016 + }, + { + "epoch": 1.01, + "learning_rate": 3.077100597957367e-05, + "loss": 3.5401, + "step": 1174528 + }, + { + "epoch": 1.01, + "learning_rate": 3.076262003206315e-05, + "loss": 3.5315, + "step": 1175040 + }, + { + "epoch": 1.01, + "learning_rate": 3.075425046335636e-05, + "loss": 3.5233, + "step": 1175552 + }, + { + "epoch": 1.01, + "learning_rate": 3.074586451584584e-05, + "loss": 3.5316, + "step": 1176064 + }, + { + "epoch": 1.01, + "learning_rate": 3.073747856833532e-05, + "loss": 3.526, + "step": 1176576 + }, + { + "epoch": 1.01, + "learning_rate": 3.07290926208248e-05, + "loss": 3.5219, + "step": 1177088 + }, + { + "epoch": 1.01, + "learning_rate": 3.0720723052118014e-05, + "loss": 3.5184, + "step": 1177600 + }, + { + "epoch": 1.01, + "learning_rate": 3.0712337104607493e-05, + "loss": 3.5424, + "step": 1178112 + }, + { + "epoch": 1.01, + "learning_rate": 3.0703951157096973e-05, + "loss": 3.5276, + "step": 1178624 + }, + { + "epoch": 1.01, + "learning_rate": 3.0695565209586453e-05, + "loss": 3.5233, + "step": 1179136 + }, + { + "epoch": 1.01, + "learning_rate": 3.068719564087966e-05, + "loss": 3.518, + "step": 1179648 + }, + { + "epoch": 1.01, + "learning_rate": 3.067880969336914e-05, + "loss": 3.529, + "step": 1180160 + }, + { + "epoch": 1.01, + "learning_rate": 3.067042374585862e-05, + "loss": 3.5369, + "step": 1180672 + }, + { + "epoch": 1.01, + "learning_rate": 3.06620377983481e-05, + "loss": 3.5349, + "step": 1181184 + }, + { + "epoch": 1.01, + "learning_rate": 3.065366822964131e-05, + "loss": 3.5385, + "step": 1181696 + }, + { + "epoch": 1.01, + "learning_rate": 3.064528228213079e-05, + "loss": 3.5394, + "step": 1182208 + }, + { + "epoch": 1.01, + "learning_rate": 3.063689633462027e-05, + "loss": 3.5487, + "step": 1182720 + }, + { + "epoch": 1.01, + "learning_rate": 3.062851038710975e-05, + "loss": 3.5407, + "step": 1183232 + }, + { + "epoch": 1.01, + "learning_rate": 3.062014081840297e-05, + "loss": 3.54, + "step": 1183744 + }, + { + "epoch": 1.01, + "learning_rate": 3.061175487089245e-05, + "loss": 3.5283, + "step": 1184256 + }, + { + "epoch": 1.01, + "learning_rate": 3.060336892338193e-05, + "loss": 3.5325, + "step": 1184768 + }, + { + "epoch": 1.01, + "learning_rate": 3.059498297587141e-05, + "loss": 3.5274, + "step": 1185280 + }, + { + "epoch": 1.01, + "learning_rate": 3.0586613407164616e-05, + "loss": 3.5336, + "step": 1185792 + }, + { + "epoch": 1.01, + "learning_rate": 3.0578227459654096e-05, + "loss": 3.5394, + "step": 1186304 + }, + { + "epoch": 1.01, + "learning_rate": 3.0569841512143576e-05, + "loss": 3.5429, + "step": 1186816 + }, + { + "epoch": 1.01, + "learning_rate": 3.056145556463305e-05, + "loss": 3.5338, + "step": 1187328 + }, + { + "epoch": 1.01, + "learning_rate": 3.0553085995926265e-05, + "loss": 3.5183, + "step": 1187840 + }, + { + "epoch": 1.01, + "learning_rate": 3.0544700048415745e-05, + "loss": 3.5257, + "step": 1188352 + }, + { + "epoch": 1.01, + "learning_rate": 3.0536314100905225e-05, + "loss": 3.5327, + "step": 1188864 + }, + { + "epoch": 1.01, + "learning_rate": 3.0527928153394705e-05, + "loss": 3.5416, + "step": 1189376 + }, + { + "epoch": 1.01, + "learning_rate": 3.051955858468792e-05, + "loss": 3.5223, + "step": 1189888 + }, + { + "epoch": 1.01, + "learning_rate": 3.0511172637177397e-05, + "loss": 3.5334, + "step": 1190400 + }, + { + "epoch": 1.02, + "learning_rate": 3.0502786689666877e-05, + "loss": 3.5352, + "step": 1190912 + }, + { + "epoch": 1.02, + "learning_rate": 3.049441712096009e-05, + "loss": 3.5239, + "step": 1191424 + }, + { + "epoch": 1.02, + "learning_rate": 3.048603117344957e-05, + "loss": 3.5262, + "step": 1191936 + }, + { + "epoch": 1.02, + "learning_rate": 3.047764522593905e-05, + "loss": 3.54, + "step": 1192448 + }, + { + "epoch": 1.02, + "learning_rate": 3.0469259278428526e-05, + "loss": 3.5342, + "step": 1192960 + }, + { + "epoch": 1.02, + "learning_rate": 3.0460873330918006e-05, + "loss": 3.5383, + "step": 1193472 + }, + { + "epoch": 1.02, + "learning_rate": 3.0452487383407486e-05, + "loss": 3.5235, + "step": 1193984 + }, + { + "epoch": 1.02, + "learning_rate": 3.0444101435896966e-05, + "loss": 3.5277, + "step": 1194496 + }, + { + "epoch": 1.02, + "learning_rate": 3.0435715488386446e-05, + "loss": 3.5331, + "step": 1195008 + }, + { + "epoch": 1.02, + "learning_rate": 3.0427345919679655e-05, + "loss": 3.5381, + "step": 1195520 + }, + { + "epoch": 1.02, + "learning_rate": 3.0418959972169135e-05, + "loss": 3.5344, + "step": 1196032 + }, + { + "epoch": 1.02, + "learning_rate": 3.0410574024658615e-05, + "loss": 3.5374, + "step": 1196544 + }, + { + "epoch": 1.02, + "learning_rate": 3.04021880771481e-05, + "loss": 3.5346, + "step": 1197056 + }, + { + "epoch": 1.02, + "learning_rate": 3.0393818508441308e-05, + "loss": 3.5325, + "step": 1197568 + }, + { + "epoch": 1.02, + "learning_rate": 3.0385448939734524e-05, + "loss": 3.5341, + "step": 1198080 + }, + { + "epoch": 1.02, + "learning_rate": 3.0377062992223997e-05, + "loss": 3.5163, + "step": 1198592 + }, + { + "epoch": 1.02, + "learning_rate": 3.0368677044713477e-05, + "loss": 3.5233, + "step": 1199104 + }, + { + "epoch": 1.02, + "learning_rate": 3.036029109720296e-05, + "loss": 3.5323, + "step": 1199616 + }, + { + "epoch": 1.02, + "learning_rate": 3.035190514969244e-05, + "loss": 3.5275, + "step": 1200128 + }, + { + "epoch": 1.02, + "learning_rate": 3.034351920218192e-05, + "loss": 3.5204, + "step": 1200640 + }, + { + "epoch": 1.02, + "learning_rate": 3.03351332546714e-05, + "loss": 3.524, + "step": 1201152 + }, + { + "epoch": 1.02, + "learning_rate": 3.032674730716088e-05, + "loss": 3.5192, + "step": 1201664 + }, + { + "epoch": 1.02, + "learning_rate": 3.031837773845409e-05, + "loss": 3.5331, + "step": 1202176 + }, + { + "epoch": 1.02, + "learning_rate": 3.030999179094357e-05, + "loss": 3.5259, + "step": 1202688 + }, + { + "epoch": 1.02, + "learning_rate": 3.0301605843433052e-05, + "loss": 3.5313, + "step": 1203200 + }, + { + "epoch": 1.02, + "learning_rate": 3.0293219895922532e-05, + "loss": 3.5302, + "step": 1203712 + }, + { + "epoch": 1.02, + "learning_rate": 3.028485032721574e-05, + "loss": 3.5372, + "step": 1204224 + }, + { + "epoch": 1.02, + "learning_rate": 3.027646437970522e-05, + "loss": 3.5319, + "step": 1204736 + }, + { + "epoch": 1.02, + "learning_rate": 3.02680784321947e-05, + "loss": 3.5319, + "step": 1205248 + }, + { + "epoch": 1.02, + "learning_rate": 3.025969248468418e-05, + "loss": 3.5378, + "step": 1205760 + }, + { + "epoch": 1.02, + "learning_rate": 3.0251322915977394e-05, + "loss": 3.5321, + "step": 1206272 + }, + { + "epoch": 1.02, + "learning_rate": 3.0242936968466874e-05, + "loss": 3.5258, + "step": 1206784 + }, + { + "epoch": 1.02, + "learning_rate": 3.0234551020956354e-05, + "loss": 3.5337, + "step": 1207296 + }, + { + "epoch": 1.02, + "learning_rate": 3.0226165073445833e-05, + "loss": 3.5289, + "step": 1207808 + }, + { + "epoch": 1.02, + "learning_rate": 3.0217795504739043e-05, + "loss": 3.5311, + "step": 1208320 + }, + { + "epoch": 1.02, + "learning_rate": 3.0209409557228523e-05, + "loss": 3.5227, + "step": 1208832 + }, + { + "epoch": 1.02, + "learning_rate": 3.0201023609718006e-05, + "loss": 3.5273, + "step": 1209344 + }, + { + "epoch": 1.02, + "learning_rate": 3.0192637662207486e-05, + "loss": 3.5217, + "step": 1209856 + }, + { + "epoch": 1.02, + "learning_rate": 3.0184268093500695e-05, + "loss": 3.522, + "step": 1210368 + }, + { + "epoch": 1.02, + "learning_rate": 3.0175882145990175e-05, + "loss": 3.5198, + "step": 1210880 + }, + { + "epoch": 1.02, + "learning_rate": 3.0167496198479655e-05, + "loss": 3.5423, + "step": 1211392 + }, + { + "epoch": 1.02, + "learning_rate": 3.0159126629772867e-05, + "loss": 3.535, + "step": 1211904 + }, + { + "epoch": 1.02, + "learning_rate": 3.0150740682262347e-05, + "loss": 3.5253, + "step": 1212416 + }, + { + "epoch": 1.02, + "learning_rate": 3.0142354734751827e-05, + "loss": 3.5291, + "step": 1212928 + }, + { + "epoch": 1.02, + "learning_rate": 3.0133968787241307e-05, + "loss": 3.5304, + "step": 1213440 + }, + { + "epoch": 1.02, + "learning_rate": 3.0125599218534516e-05, + "loss": 3.5397, + "step": 1213952 + }, + { + "epoch": 1.02, + "learning_rate": 3.0117213271023996e-05, + "loss": 3.5323, + "step": 1214464 + }, + { + "epoch": 1.02, + "learning_rate": 3.0108827323513476e-05, + "loss": 3.5279, + "step": 1214976 + }, + { + "epoch": 1.02, + "learning_rate": 3.010044137600296e-05, + "loss": 3.5411, + "step": 1215488 + }, + { + "epoch": 1.02, + "learning_rate": 3.009207180729617e-05, + "loss": 3.5234, + "step": 1216000 + }, + { + "epoch": 1.02, + "learning_rate": 3.008368585978565e-05, + "loss": 3.5367, + "step": 1216512 + }, + { + "epoch": 1.02, + "learning_rate": 3.007529991227513e-05, + "loss": 3.5274, + "step": 1217024 + }, + { + "epoch": 1.02, + "learning_rate": 3.006691396476461e-05, + "loss": 3.5356, + "step": 1217536 + }, + { + "epoch": 1.02, + "learning_rate": 3.005854439605782e-05, + "loss": 3.5302, + "step": 1218048 + }, + { + "epoch": 1.02, + "learning_rate": 3.00501584485473e-05, + "loss": 3.5175, + "step": 1218560 + }, + { + "epoch": 1.02, + "learning_rate": 3.004177250103678e-05, + "loss": 3.5371, + "step": 1219072 + }, + { + "epoch": 1.02, + "learning_rate": 3.003338655352626e-05, + "loss": 3.5329, + "step": 1219584 + }, + { + "epoch": 1.02, + "learning_rate": 3.002501698481947e-05, + "loss": 3.5329, + "step": 1220096 + }, + { + "epoch": 1.02, + "learning_rate": 3.001663103730895e-05, + "loss": 3.5256, + "step": 1220608 + }, + { + "epoch": 1.03, + "learning_rate": 3.000824508979843e-05, + "loss": 3.5308, + "step": 1221120 + }, + { + "epoch": 1.03, + "eval_loss": 3.845118761062622, + "eval_runtime": 315.658, + "eval_samples_per_second": 1208.875, + "eval_steps_per_second": 37.778, + "step": 1221120 + }, + { + "epoch": 0.0, + "learning_rate": 2.9999859142287913e-05, + "loss": 3.5208, + "step": 1221632 + }, + { + "epoch": 0.0, + "learning_rate": 2.9991473194777393e-05, + "loss": 3.5171, + "step": 1222144 + }, + { + "epoch": 0.0, + "learning_rate": 2.9983087247266873e-05, + "loss": 3.5354, + "step": 1222656 + }, + { + "epoch": 0.0, + "learning_rate": 2.9974717678560082e-05, + "loss": 3.5319, + "step": 1223168 + }, + { + "epoch": 0.0, + "learning_rate": 2.9966331731049562e-05, + "loss": 3.539, + "step": 1223680 + }, + { + "epoch": 0.0, + "learning_rate": 2.9957945783539042e-05, + "loss": 3.5187, + "step": 1224192 + }, + { + "epoch": 0.0, + "learning_rate": 2.9949559836028522e-05, + "loss": 3.5236, + "step": 1224704 + }, + { + "epoch": 0.0, + "learning_rate": 2.9941173888518005e-05, + "loss": 3.5131, + "step": 1225216 + }, + { + "epoch": 0.0, + "learning_rate": 2.9932804319811215e-05, + "loss": 3.5344, + "step": 1225728 + }, + { + "epoch": 0.0, + "learning_rate": 2.9924418372300694e-05, + "loss": 3.5208, + "step": 1226240 + }, + { + "epoch": 0.0, + "learning_rate": 2.9916032424790174e-05, + "loss": 3.5326, + "step": 1226752 + }, + { + "epoch": 0.0, + "learning_rate": 2.9907646477279654e-05, + "loss": 3.5283, + "step": 1227264 + }, + { + "epoch": 0.0, + "learning_rate": 2.9899293287376596e-05, + "loss": 3.5184, + "step": 1227776 + }, + { + "epoch": 0.0, + "learning_rate": 2.9890907339866076e-05, + "loss": 3.5192, + "step": 1228288 + }, + { + "epoch": 0.0, + "learning_rate": 2.9882521392355556e-05, + "loss": 3.5182, + "step": 1228800 + }, + { + "epoch": 0.0, + "learning_rate": 2.9874135444845036e-05, + "loss": 3.5152, + "step": 1229312 + }, + { + "epoch": 0.0, + "learning_rate": 2.9865749497334516e-05, + "loss": 3.5235, + "step": 1229824 + }, + { + "epoch": 0.0, + "learning_rate": 2.9857363549823996e-05, + "loss": 3.5258, + "step": 1230336 + }, + { + "epoch": 0.0, + "learning_rate": 2.9848977602313476e-05, + "loss": 3.5164, + "step": 1230848 + }, + { + "epoch": 0.0, + "learning_rate": 2.9840591654802952e-05, + "loss": 3.5442, + "step": 1231360 + }, + { + "epoch": 0.0, + "learning_rate": 2.9832222086096168e-05, + "loss": 3.5227, + "step": 1231872 + }, + { + "epoch": 0.0, + "learning_rate": 2.9823836138585648e-05, + "loss": 3.5294, + "step": 1232384 + }, + { + "epoch": 0.0, + "learning_rate": 2.9815450191075128e-05, + "loss": 3.5232, + "step": 1232896 + }, + { + "epoch": 0.0, + "learning_rate": 2.9807064243564605e-05, + "loss": 3.5328, + "step": 1233408 + }, + { + "epoch": 0.0, + "learning_rate": 2.979869467485782e-05, + "loss": 3.5207, + "step": 1233920 + }, + { + "epoch": 0.0, + "learning_rate": 2.97903087273473e-05, + "loss": 3.5229, + "step": 1234432 + }, + { + "epoch": 0.0, + "learning_rate": 2.978192277983678e-05, + "loss": 3.5194, + "step": 1234944 + }, + { + "epoch": 0.0, + "learning_rate": 2.9773536832326254e-05, + "loss": 3.5164, + "step": 1235456 + }, + { + "epoch": 0.0, + "learning_rate": 2.976516726361947e-05, + "loss": 3.5168, + "step": 1235968 + }, + { + "epoch": 0.01, + "learning_rate": 2.975678131610895e-05, + "loss": 3.5174, + "step": 1236480 + }, + { + "epoch": 0.01, + "learning_rate": 2.9748395368598426e-05, + "loss": 3.5287, + "step": 1236992 + }, + { + "epoch": 0.01, + "learning_rate": 2.9740025799891642e-05, + "loss": 3.5234, + "step": 1237504 + }, + { + "epoch": 0.01, + "learning_rate": 2.9731639852381122e-05, + "loss": 3.5282, + "step": 1238016 + }, + { + "epoch": 0.01, + "learning_rate": 2.9723253904870602e-05, + "loss": 3.5294, + "step": 1238528 + }, + { + "epoch": 0.01, + "learning_rate": 2.9714867957360075e-05, + "loss": 3.5272, + "step": 1239040 + }, + { + "epoch": 0.01, + "learning_rate": 2.970649838865329e-05, + "loss": 3.5283, + "step": 1239552 + }, + { + "epoch": 0.01, + "learning_rate": 2.969811244114277e-05, + "loss": 3.5185, + "step": 1240064 + }, + { + "epoch": 0.01, + "learning_rate": 2.9689726493632254e-05, + "loss": 3.5221, + "step": 1240576 + }, + { + "epoch": 0.01, + "learning_rate": 2.9681340546121727e-05, + "loss": 3.5172, + "step": 1241088 + }, + { + "epoch": 0.01, + "learning_rate": 2.9672970977414943e-05, + "loss": 3.5227, + "step": 1241600 + }, + { + "epoch": 0.01, + "learning_rate": 2.9664585029904423e-05, + "loss": 3.5201, + "step": 1242112 + }, + { + "epoch": 0.01, + "learning_rate": 2.96561990823939e-05, + "loss": 3.5302, + "step": 1242624 + }, + { + "epoch": 0.01, + "learning_rate": 2.964781313488338e-05, + "loss": 3.5165, + "step": 1243136 + }, + { + "epoch": 0.01, + "learning_rate": 2.9639443566176596e-05, + "loss": 3.5286, + "step": 1243648 + }, + { + "epoch": 0.01, + "learning_rate": 2.9631057618666076e-05, + "loss": 3.5261, + "step": 1244160 + }, + { + "epoch": 0.01, + "learning_rate": 2.962267167115555e-05, + "loss": 3.5254, + "step": 1244672 + }, + { + "epoch": 0.01, + "learning_rate": 2.961428572364503e-05, + "loss": 3.5229, + "step": 1245184 + }, + { + "epoch": 0.01, + "learning_rate": 2.9605916154938245e-05, + "loss": 3.4988, + "step": 1245696 + }, + { + "epoch": 0.01, + "learning_rate": 2.9597530207427724e-05, + "loss": 3.5188, + "step": 1246208 + }, + { + "epoch": 0.01, + "learning_rate": 2.95891442599172e-05, + "loss": 3.5251, + "step": 1246720 + }, + { + "epoch": 0.01, + "learning_rate": 2.958075831240668e-05, + "loss": 3.5264, + "step": 1247232 + }, + { + "epoch": 0.01, + "learning_rate": 2.9572388743699897e-05, + "loss": 3.5126, + "step": 1247744 + }, + { + "epoch": 0.01, + "learning_rate": 2.956400279618937e-05, + "loss": 3.5008, + "step": 1248256 + }, + { + "epoch": 0.01, + "learning_rate": 2.9555616848678853e-05, + "loss": 3.5093, + "step": 1248768 + }, + { + "epoch": 0.01, + "learning_rate": 2.9547230901168333e-05, + "loss": 3.5034, + "step": 1249280 + }, + { + "epoch": 0.01, + "learning_rate": 2.953886133246155e-05, + "loss": 3.533, + "step": 1249792 + }, + { + "epoch": 0.01, + "learning_rate": 2.9530475384951022e-05, + "loss": 3.5073, + "step": 1250304 + }, + { + "epoch": 0.01, + "learning_rate": 2.9522089437440502e-05, + "loss": 3.5253, + "step": 1250816 + }, + { + "epoch": 0.01, + "learning_rate": 2.9513703489929982e-05, + "loss": 3.5191, + "step": 1251328 + }, + { + "epoch": 0.01, + "learning_rate": 2.9505333921223198e-05, + "loss": 3.506, + "step": 1251840 + }, + { + "epoch": 0.01, + "learning_rate": 2.9496947973712675e-05, + "loss": 3.5204, + "step": 1252352 + }, + { + "epoch": 0.01, + "learning_rate": 2.9488562026202155e-05, + "loss": 3.512, + "step": 1252864 + }, + { + "epoch": 0.01, + "learning_rate": 2.9480176078691635e-05, + "loss": 3.5043, + "step": 1253376 + }, + { + "epoch": 0.01, + "learning_rate": 2.9471806509984844e-05, + "loss": 3.5035, + "step": 1253888 + }, + { + "epoch": 0.01, + "learning_rate": 2.9463420562474324e-05, + "loss": 3.5297, + "step": 1254400 + }, + { + "epoch": 0.01, + "learning_rate": 2.9455034614963807e-05, + "loss": 3.516, + "step": 1254912 + }, + { + "epoch": 0.01, + "learning_rate": 2.9446648667453287e-05, + "loss": 3.5079, + "step": 1255424 + }, + { + "epoch": 0.01, + "learning_rate": 2.9438279098746496e-05, + "loss": 3.5047, + "step": 1255936 + }, + { + "epoch": 0.01, + "learning_rate": 2.9429893151235976e-05, + "loss": 3.5139, + "step": 1256448 + }, + { + "epoch": 0.01, + "learning_rate": 2.9421507203725456e-05, + "loss": 3.5217, + "step": 1256960 + }, + { + "epoch": 0.01, + "learning_rate": 2.9413121256214936e-05, + "loss": 3.5229, + "step": 1257472 + }, + { + "epoch": 0.01, + "learning_rate": 2.940475168750815e-05, + "loss": 3.5222, + "step": 1257984 + }, + { + "epoch": 0.01, + "learning_rate": 2.939636573999763e-05, + "loss": 3.5273, + "step": 1258496 + }, + { + "epoch": 0.01, + "learning_rate": 2.938797979248711e-05, + "loss": 3.531, + "step": 1259008 + }, + { + "epoch": 0.01, + "learning_rate": 2.937959384497659e-05, + "loss": 3.5267, + "step": 1259520 + }, + { + "epoch": 0.01, + "learning_rate": 2.9371224276269797e-05, + "loss": 3.5244, + "step": 1260032 + }, + { + "epoch": 0.01, + "learning_rate": 2.9362838328759277e-05, + "loss": 3.5154, + "step": 1260544 + }, + { + "epoch": 0.01, + "learning_rate": 2.935445238124876e-05, + "loss": 3.5228, + "step": 1261056 + }, + { + "epoch": 0.01, + "learning_rate": 2.934606643373824e-05, + "loss": 3.5178, + "step": 1261568 + }, + { + "epoch": 0.01, + "learning_rate": 2.933769686503145e-05, + "loss": 3.5186, + "step": 1262080 + }, + { + "epoch": 0.01, + "learning_rate": 2.932931091752093e-05, + "loss": 3.5225, + "step": 1262592 + }, + { + "epoch": 0.01, + "learning_rate": 2.932092497001041e-05, + "loss": 3.5256, + "step": 1263104 + }, + { + "epoch": 0.01, + "learning_rate": 2.931253902249989e-05, + "loss": 3.525, + "step": 1263616 + }, + { + "epoch": 0.01, + "learning_rate": 2.9304169453793102e-05, + "loss": 3.5046, + "step": 1264128 + }, + { + "epoch": 0.01, + "learning_rate": 2.9295783506282582e-05, + "loss": 3.5104, + "step": 1264640 + }, + { + "epoch": 0.01, + "learning_rate": 2.9287397558772062e-05, + "loss": 3.5216, + "step": 1265152 + }, + { + "epoch": 0.01, + "learning_rate": 2.9279011611261542e-05, + "loss": 3.5293, + "step": 1265664 + }, + { + "epoch": 0.01, + "learning_rate": 2.927064204255475e-05, + "loss": 3.5093, + "step": 1266176 + }, + { + "epoch": 0.01, + "learning_rate": 2.926225609504423e-05, + "loss": 3.5193, + "step": 1266688 + }, + { + "epoch": 0.02, + "learning_rate": 2.9253870147533714e-05, + "loss": 3.5226, + "step": 1267200 + }, + { + "epoch": 0.02, + "learning_rate": 2.9245500578826923e-05, + "loss": 3.5097, + "step": 1267712 + }, + { + "epoch": 0.02, + "learning_rate": 2.9237114631316403e-05, + "loss": 3.5129, + "step": 1268224 + }, + { + "epoch": 0.02, + "learning_rate": 2.9228728683805883e-05, + "loss": 3.5217, + "step": 1268736 + }, + { + "epoch": 0.02, + "learning_rate": 2.9220342736295363e-05, + "loss": 3.5216, + "step": 1269248 + }, + { + "epoch": 0.02, + "learning_rate": 2.9211956788784843e-05, + "loss": 3.5194, + "step": 1269760 + }, + { + "epoch": 0.02, + "learning_rate": 2.9203570841274323e-05, + "loss": 3.5176, + "step": 1270272 + }, + { + "epoch": 0.02, + "learning_rate": 2.9195184893763807e-05, + "loss": 3.5063, + "step": 1270784 + }, + { + "epoch": 0.02, + "learning_rate": 2.9186798946253287e-05, + "loss": 3.5221, + "step": 1271296 + }, + { + "epoch": 0.02, + "learning_rate": 2.9178429377546496e-05, + "loss": 3.5214, + "step": 1271808 + }, + { + "epoch": 0.02, + "learning_rate": 2.9170043430035976e-05, + "loss": 3.5169, + "step": 1272320 + }, + { + "epoch": 0.02, + "learning_rate": 2.9161657482525456e-05, + "loss": 3.5244, + "step": 1272832 + }, + { + "epoch": 0.02, + "learning_rate": 2.9153271535014936e-05, + "loss": 3.5161, + "step": 1273344 + }, + { + "epoch": 0.02, + "learning_rate": 2.9144901966308148e-05, + "loss": 3.5195, + "step": 1273856 + }, + { + "epoch": 0.02, + "learning_rate": 2.9136532397601357e-05, + "loss": 3.5241, + "step": 1274368 + }, + { + "epoch": 0.02, + "learning_rate": 2.9128146450090837e-05, + "loss": 3.5021, + "step": 1274880 + }, + { + "epoch": 0.02, + "learning_rate": 2.9119760502580317e-05, + "loss": 3.5058, + "step": 1275392 + }, + { + "epoch": 0.02, + "learning_rate": 2.9111374555069797e-05, + "loss": 3.5192, + "step": 1275904 + }, + { + "epoch": 0.02, + "learning_rate": 2.9102988607559277e-05, + "loss": 3.5185, + "step": 1276416 + }, + { + "epoch": 0.02, + "learning_rate": 2.909460266004876e-05, + "loss": 3.5013, + "step": 1276928 + }, + { + "epoch": 0.02, + "learning_rate": 2.908621671253824e-05, + "loss": 3.5112, + "step": 1277440 + }, + { + "epoch": 0.02, + "learning_rate": 2.907783076502772e-05, + "loss": 3.5105, + "step": 1277952 + }, + { + "epoch": 0.02, + "learning_rate": 2.906946119632093e-05, + "loss": 3.5175, + "step": 1278464 + }, + { + "epoch": 0.02, + "learning_rate": 2.906107524881041e-05, + "loss": 3.5122, + "step": 1278976 + }, + { + "epoch": 0.02, + "learning_rate": 2.905268930129989e-05, + "loss": 3.5148, + "step": 1279488 + }, + { + "epoch": 0.02, + "learning_rate": 2.904430335378937e-05, + "loss": 3.5168, + "step": 1280000 + }, + { + "epoch": 0.02, + "learning_rate": 2.903595016388631e-05, + "loss": 3.5233, + "step": 1280512 + }, + { + "epoch": 0.02, + "learning_rate": 2.902756421637579e-05, + "loss": 3.5198, + "step": 1281024 + }, + { + "epoch": 0.02, + "learning_rate": 2.901917826886527e-05, + "loss": 3.5219, + "step": 1281536 + }, + { + "epoch": 0.02, + "learning_rate": 2.901079232135475e-05, + "loss": 3.5236, + "step": 1282048 + }, + { + "epoch": 0.02, + "learning_rate": 2.900240637384423e-05, + "loss": 3.5203, + "step": 1282560 + }, + { + "epoch": 0.02, + "learning_rate": 2.8994020426333714e-05, + "loss": 3.5066, + "step": 1283072 + }, + { + "epoch": 0.02, + "learning_rate": 2.8985634478823194e-05, + "loss": 3.5208, + "step": 1283584 + }, + { + "epoch": 0.02, + "learning_rate": 2.8977248531312674e-05, + "loss": 3.5125, + "step": 1284096 + }, + { + "epoch": 0.02, + "learning_rate": 2.8968878962605883e-05, + "loss": 3.5249, + "step": 1284608 + }, + { + "epoch": 0.02, + "learning_rate": 2.8960493015095363e-05, + "loss": 3.5035, + "step": 1285120 + }, + { + "epoch": 0.02, + "learning_rate": 2.8952107067584843e-05, + "loss": 3.5195, + "step": 1285632 + }, + { + "epoch": 0.02, + "learning_rate": 2.8943721120074323e-05, + "loss": 3.5049, + "step": 1286144 + }, + { + "epoch": 0.02, + "learning_rate": 2.8935351551367535e-05, + "loss": 3.5071, + "step": 1286656 + }, + { + "epoch": 0.02, + "learning_rate": 2.8926965603857015e-05, + "loss": 3.5061, + "step": 1287168 + }, + { + "epoch": 0.02, + "learning_rate": 2.8918579656346495e-05, + "loss": 3.5294, + "step": 1287680 + }, + { + "epoch": 0.02, + "learning_rate": 2.8910193708835975e-05, + "loss": 3.5272, + "step": 1288192 + }, + { + "epoch": 0.02, + "learning_rate": 2.8901824140129184e-05, + "loss": 3.5095, + "step": 1288704 + }, + { + "epoch": 0.02, + "learning_rate": 2.8893438192618664e-05, + "loss": 3.5138, + "step": 1289216 + }, + { + "epoch": 0.02, + "learning_rate": 2.8885052245108148e-05, + "loss": 3.5178, + "step": 1289728 + }, + { + "epoch": 0.02, + "learning_rate": 2.8876666297597628e-05, + "loss": 3.5229, + "step": 1290240 + }, + { + "epoch": 0.02, + "learning_rate": 2.8868296728890837e-05, + "loss": 3.5214, + "step": 1290752 + }, + { + "epoch": 0.02, + "learning_rate": 2.8859910781380317e-05, + "loss": 3.5111, + "step": 1291264 + }, + { + "epoch": 0.02, + "learning_rate": 2.8851524833869797e-05, + "loss": 3.5274, + "step": 1291776 + }, + { + "epoch": 0.02, + "learning_rate": 2.8843138886359276e-05, + "loss": 3.5088, + "step": 1292288 + }, + { + "epoch": 0.02, + "learning_rate": 2.883476931765249e-05, + "loss": 3.5248, + "step": 1292800 + }, + { + "epoch": 0.02, + "learning_rate": 2.882638337014197e-05, + "loss": 3.5123, + "step": 1293312 + }, + { + "epoch": 0.02, + "learning_rate": 2.881799742263145e-05, + "loss": 3.5182, + "step": 1293824 + }, + { + "epoch": 0.02, + "learning_rate": 2.8809611475120922e-05, + "loss": 3.5179, + "step": 1294336 + }, + { + "epoch": 0.02, + "learning_rate": 2.8801241906414138e-05, + "loss": 3.5076, + "step": 1294848 + }, + { + "epoch": 0.02, + "learning_rate": 2.8792855958903618e-05, + "loss": 3.523, + "step": 1295360 + }, + { + "epoch": 0.02, + "learning_rate": 2.87844700113931e-05, + "loss": 3.5195, + "step": 1295872 + }, + { + "epoch": 0.02, + "learning_rate": 2.8776084063882574e-05, + "loss": 3.5191, + "step": 1296384 + }, + { + "epoch": 0.02, + "learning_rate": 2.876771449517579e-05, + "loss": 3.5131, + "step": 1296896 + }, + { + "epoch": 0.02, + "learning_rate": 2.875932854766527e-05, + "loss": 3.5117, + "step": 1297408 + }, + { + "epoch": 0.03, + "eval_loss": 3.8469269275665283, + "eval_runtime": 309.3811, + "eval_samples_per_second": 1233.401, + "eval_steps_per_second": 38.545, + "step": 1297440 + }, + { + "epoch": 1.0, + "learning_rate": 2.875094260015475e-05, + "loss": 3.5062, + "step": 1297920 + }, + { + "epoch": 1.0, + "learning_rate": 2.8742556652644227e-05, + "loss": 3.5074, + "step": 1298432 + }, + { + "epoch": 1.0, + "learning_rate": 2.8734187083937443e-05, + "loss": 3.5221, + "step": 1298944 + }, + { + "epoch": 1.0, + "learning_rate": 2.8725801136426923e-05, + "loss": 3.512, + "step": 1299456 + }, + { + "epoch": 1.0, + "learning_rate": 2.8717415188916396e-05, + "loss": 3.5302, + "step": 1299968 + }, + { + "epoch": 1.0, + "learning_rate": 2.8709029241405876e-05, + "loss": 3.5043, + "step": 1300480 + }, + { + "epoch": 1.0, + "learning_rate": 2.870065967269909e-05, + "loss": 3.5111, + "step": 1300992 + }, + { + "epoch": 1.0, + "learning_rate": 2.869227372518857e-05, + "loss": 3.4994, + "step": 1301504 + }, + { + "epoch": 1.0, + "learning_rate": 2.8683887777678048e-05, + "loss": 3.5174, + "step": 1302016 + }, + { + "epoch": 1.0, + "learning_rate": 2.8675501830167528e-05, + "loss": 3.5092, + "step": 1302528 + }, + { + "epoch": 1.0, + "learning_rate": 2.8667132261460744e-05, + "loss": 3.5166, + "step": 1303040 + }, + { + "epoch": 1.0, + "learning_rate": 2.8658746313950224e-05, + "loss": 3.5141, + "step": 1303552 + }, + { + "epoch": 1.0, + "learning_rate": 2.8650376745243433e-05, + "loss": 3.5048, + "step": 1304064 + }, + { + "epoch": 1.0, + "learning_rate": 2.8641990797732916e-05, + "loss": 3.5068, + "step": 1304576 + }, + { + "epoch": 1.0, + "learning_rate": 2.8633604850222396e-05, + "loss": 3.5061, + "step": 1305088 + }, + { + "epoch": 1.0, + "learning_rate": 2.862521890271187e-05, + "loss": 3.5007, + "step": 1305600 + }, + { + "epoch": 1.0, + "learning_rate": 2.861683295520135e-05, + "loss": 3.5088, + "step": 1306112 + }, + { + "epoch": 1.0, + "learning_rate": 2.860844700769083e-05, + "loss": 3.5098, + "step": 1306624 + }, + { + "epoch": 1.0, + "learning_rate": 2.860006106018031e-05, + "loss": 3.5062, + "step": 1307136 + }, + { + "epoch": 1.0, + "learning_rate": 2.8591675112669793e-05, + "loss": 3.5288, + "step": 1307648 + }, + { + "epoch": 1.0, + "learning_rate": 2.8583305543963002e-05, + "loss": 3.506, + "step": 1308160 + }, + { + "epoch": 1.0, + "learning_rate": 2.8574919596452482e-05, + "loss": 3.5145, + "step": 1308672 + }, + { + "epoch": 1.0, + "learning_rate": 2.8566533648941962e-05, + "loss": 3.5126, + "step": 1309184 + }, + { + "epoch": 1.0, + "learning_rate": 2.855814770143144e-05, + "loss": 3.5217, + "step": 1309696 + }, + { + "epoch": 1.0, + "learning_rate": 2.8549778132724654e-05, + "loss": 3.5017, + "step": 1310208 + }, + { + "epoch": 1.0, + "learning_rate": 2.8541392185214134e-05, + "loss": 3.5121, + "step": 1310720 + }, + { + "epoch": 1.0, + "learning_rate": 2.8533006237703614e-05, + "loss": 3.5033, + "step": 1311232 + }, + { + "epoch": 1.0, + "learning_rate": 2.8524620290193094e-05, + "loss": 3.5115, + "step": 1311744 + }, + { + "epoch": 1.0, + "learning_rate": 2.8516250721486303e-05, + "loss": 3.4987, + "step": 1312256 + }, + { + "epoch": 1.01, + "learning_rate": 2.8507864773975783e-05, + "loss": 3.5037, + "step": 1312768 + }, + { + "epoch": 1.01, + "learning_rate": 2.8499478826465263e-05, + "loss": 3.5161, + "step": 1313280 + }, + { + "epoch": 1.01, + "learning_rate": 2.8491092878954746e-05, + "loss": 3.5092, + "step": 1313792 + }, + { + "epoch": 1.01, + "learning_rate": 2.8482723310247955e-05, + "loss": 3.5137, + "step": 1314304 + }, + { + "epoch": 1.01, + "learning_rate": 2.8474337362737435e-05, + "loss": 3.5177, + "step": 1314816 + }, + { + "epoch": 1.01, + "learning_rate": 2.8465951415226915e-05, + "loss": 3.5112, + "step": 1315328 + }, + { + "epoch": 1.01, + "learning_rate": 2.8457565467716395e-05, + "loss": 3.5119, + "step": 1315840 + }, + { + "epoch": 1.01, + "learning_rate": 2.8449195899009608e-05, + "loss": 3.506, + "step": 1316352 + }, + { + "epoch": 1.01, + "learning_rate": 2.8440809951499088e-05, + "loss": 3.5128, + "step": 1316864 + }, + { + "epoch": 1.01, + "learning_rate": 2.8432424003988568e-05, + "loss": 3.5012, + "step": 1317376 + }, + { + "epoch": 1.01, + "learning_rate": 2.8424038056478048e-05, + "loss": 3.5085, + "step": 1317888 + }, + { + "epoch": 1.01, + "learning_rate": 2.8415668487771257e-05, + "loss": 3.5092, + "step": 1318400 + }, + { + "epoch": 1.01, + "learning_rate": 2.8407282540260737e-05, + "loss": 3.515, + "step": 1318912 + }, + { + "epoch": 1.01, + "learning_rate": 2.8398896592750217e-05, + "loss": 3.5034, + "step": 1319424 + }, + { + "epoch": 1.01, + "learning_rate": 2.83905106452397e-05, + "loss": 3.5126, + "step": 1319936 + }, + { + "epoch": 1.01, + "learning_rate": 2.838214107653291e-05, + "loss": 3.5184, + "step": 1320448 + }, + { + "epoch": 1.01, + "learning_rate": 2.837375512902239e-05, + "loss": 3.5109, + "step": 1320960 + }, + { + "epoch": 1.01, + "learning_rate": 2.836536918151187e-05, + "loss": 3.5126, + "step": 1321472 + }, + { + "epoch": 1.01, + "learning_rate": 2.835698323400135e-05, + "loss": 3.4862, + "step": 1321984 + }, + { + "epoch": 1.01, + "learning_rate": 2.834861366529456e-05, + "loss": 3.5016, + "step": 1322496 + }, + { + "epoch": 1.01, + "learning_rate": 2.834022771778404e-05, + "loss": 3.5153, + "step": 1323008 + }, + { + "epoch": 1.01, + "learning_rate": 2.833184177027352e-05, + "loss": 3.5113, + "step": 1323520 + }, + { + "epoch": 1.01, + "learning_rate": 2.832347220156673e-05, + "loss": 3.5064, + "step": 1324032 + }, + { + "epoch": 1.01, + "learning_rate": 2.831508625405621e-05, + "loss": 3.4867, + "step": 1324544 + }, + { + "epoch": 1.01, + "learning_rate": 2.830670030654569e-05, + "loss": 3.4957, + "step": 1325056 + }, + { + "epoch": 1.01, + "learning_rate": 2.829831435903517e-05, + "loss": 3.4903, + "step": 1325568 + }, + { + "epoch": 1.01, + "learning_rate": 2.8289944790328383e-05, + "loss": 3.5156, + "step": 1326080 + }, + { + "epoch": 1.01, + "learning_rate": 2.8281558842817863e-05, + "loss": 3.4943, + "step": 1326592 + }, + { + "epoch": 1.01, + "learning_rate": 2.8273172895307343e-05, + "loss": 3.5098, + "step": 1327104 + }, + { + "epoch": 1.01, + "learning_rate": 2.8264786947796823e-05, + "loss": 3.5096, + "step": 1327616 + }, + { + "epoch": 1.01, + "learning_rate": 2.8256417379090032e-05, + "loss": 3.4946, + "step": 1328128 + }, + { + "epoch": 1.01, + "learning_rate": 2.8248031431579515e-05, + "loss": 3.5039, + "step": 1328640 + }, + { + "epoch": 1.01, + "learning_rate": 2.8239645484068995e-05, + "loss": 3.4949, + "step": 1329152 + }, + { + "epoch": 1.01, + "learning_rate": 2.8231259536558475e-05, + "loss": 3.4932, + "step": 1329664 + }, + { + "epoch": 1.01, + "learning_rate": 2.8222889967851684e-05, + "loss": 3.4918, + "step": 1330176 + }, + { + "epoch": 1.01, + "learning_rate": 2.8214504020341164e-05, + "loss": 3.5118, + "step": 1330688 + }, + { + "epoch": 1.01, + "learning_rate": 2.8206118072830644e-05, + "loss": 3.5053, + "step": 1331200 + }, + { + "epoch": 1.01, + "learning_rate": 2.8197732125320124e-05, + "loss": 3.4913, + "step": 1331712 + }, + { + "epoch": 1.01, + "learning_rate": 2.8189362556613337e-05, + "loss": 3.4918, + "step": 1332224 + }, + { + "epoch": 1.01, + "learning_rate": 2.8180976609102816e-05, + "loss": 3.4971, + "step": 1332736 + }, + { + "epoch": 1.01, + "learning_rate": 2.8172590661592296e-05, + "loss": 3.5084, + "step": 1333248 + }, + { + "epoch": 1.01, + "learning_rate": 2.8164204714081776e-05, + "loss": 3.5089, + "step": 1333760 + }, + { + "epoch": 1.01, + "learning_rate": 2.8155835145374985e-05, + "loss": 3.5077, + "step": 1334272 + }, + { + "epoch": 1.01, + "learning_rate": 2.814744919786447e-05, + "loss": 3.5175, + "step": 1334784 + }, + { + "epoch": 1.01, + "learning_rate": 2.813906325035395e-05, + "loss": 3.5137, + "step": 1335296 + }, + { + "epoch": 1.01, + "learning_rate": 2.813067730284343e-05, + "loss": 3.5159, + "step": 1335808 + }, + { + "epoch": 1.01, + "learning_rate": 2.8122307734136638e-05, + "loss": 3.507, + "step": 1336320 + }, + { + "epoch": 1.01, + "learning_rate": 2.8113921786626118e-05, + "loss": 3.504, + "step": 1336832 + }, + { + "epoch": 1.01, + "learning_rate": 2.8105535839115598e-05, + "loss": 3.5072, + "step": 1337344 + }, + { + "epoch": 1.01, + "learning_rate": 2.8097149891605078e-05, + "loss": 3.5024, + "step": 1337856 + }, + { + "epoch": 1.01, + "learning_rate": 2.808878032289829e-05, + "loss": 3.5044, + "step": 1338368 + }, + { + "epoch": 1.01, + "learning_rate": 2.808039437538777e-05, + "loss": 3.5092, + "step": 1338880 + }, + { + "epoch": 1.01, + "learning_rate": 2.807200842787725e-05, + "loss": 3.5132, + "step": 1339392 + }, + { + "epoch": 1.01, + "learning_rate": 2.806362248036673e-05, + "loss": 3.5068, + "step": 1339904 + }, + { + "epoch": 1.01, + "learning_rate": 2.805525291165994e-05, + "loss": 3.4953, + "step": 1340416 + }, + { + "epoch": 1.01, + "learning_rate": 2.8046866964149422e-05, + "loss": 3.496, + "step": 1340928 + }, + { + "epoch": 1.01, + "learning_rate": 2.8038481016638902e-05, + "loss": 3.5057, + "step": 1341440 + }, + { + "epoch": 1.01, + "learning_rate": 2.8030095069128382e-05, + "loss": 3.5137, + "step": 1341952 + }, + { + "epoch": 1.01, + "learning_rate": 2.802172550042159e-05, + "loss": 3.4987, + "step": 1342464 + }, + { + "epoch": 1.01, + "learning_rate": 2.801333955291107e-05, + "loss": 3.5034, + "step": 1342976 + }, + { + "epoch": 1.02, + "learning_rate": 2.800495360540055e-05, + "loss": 3.5113, + "step": 1343488 + }, + { + "epoch": 1.02, + "learning_rate": 2.7996584036693764e-05, + "loss": 3.4977, + "step": 1344000 + }, + { + "epoch": 1.02, + "learning_rate": 2.7988198089183244e-05, + "loss": 3.5009, + "step": 1344512 + }, + { + "epoch": 1.02, + "learning_rate": 2.7979812141672724e-05, + "loss": 3.5028, + "step": 1345024 + }, + { + "epoch": 1.02, + "learning_rate": 2.7971426194162204e-05, + "loss": 3.5095, + "step": 1345536 + }, + { + "epoch": 1.02, + "learning_rate": 2.7963040246651684e-05, + "loss": 3.5072, + "step": 1346048 + }, + { + "epoch": 1.02, + "learning_rate": 2.7954654299141164e-05, + "loss": 3.509, + "step": 1346560 + }, + { + "epoch": 1.02, + "learning_rate": 2.7946268351630644e-05, + "loss": 3.4932, + "step": 1347072 + }, + { + "epoch": 1.02, + "learning_rate": 2.7937882404120124e-05, + "loss": 3.5108, + "step": 1347584 + }, + { + "epoch": 1.02, + "learning_rate": 2.7929512835413336e-05, + "loss": 3.5034, + "step": 1348096 + }, + { + "epoch": 1.02, + "learning_rate": 2.7921126887902816e-05, + "loss": 3.5107, + "step": 1348608 + }, + { + "epoch": 1.02, + "learning_rate": 2.7912740940392296e-05, + "loss": 3.5072, + "step": 1349120 + }, + { + "epoch": 1.02, + "learning_rate": 2.790435499288177e-05, + "loss": 3.5083, + "step": 1349632 + }, + { + "epoch": 1.02, + "learning_rate": 2.7895985424174985e-05, + "loss": 3.506, + "step": 1350144 + }, + { + "epoch": 1.02, + "learning_rate": 2.7887599476664465e-05, + "loss": 3.5118, + "step": 1350656 + }, + { + "epoch": 1.02, + "learning_rate": 2.787921352915395e-05, + "loss": 3.4889, + "step": 1351168 + }, + { + "epoch": 1.02, + "learning_rate": 2.787082758164342e-05, + "loss": 3.496, + "step": 1351680 + }, + { + "epoch": 1.02, + "learning_rate": 2.7862458012936637e-05, + "loss": 3.5031, + "step": 1352192 + }, + { + "epoch": 1.02, + "learning_rate": 2.7854072065426117e-05, + "loss": 3.5016, + "step": 1352704 + }, + { + "epoch": 1.02, + "learning_rate": 2.7845686117915597e-05, + "loss": 3.4885, + "step": 1353216 + }, + { + "epoch": 1.02, + "learning_rate": 2.7837300170405074e-05, + "loss": 3.4983, + "step": 1353728 + }, + { + "epoch": 1.02, + "learning_rate": 2.782893060169829e-05, + "loss": 3.4955, + "step": 1354240 + }, + { + "epoch": 1.02, + "learning_rate": 2.782054465418777e-05, + "loss": 3.5043, + "step": 1354752 + }, + { + "epoch": 1.02, + "learning_rate": 2.781217508548098e-05, + "loss": 3.5008, + "step": 1355264 + }, + { + "epoch": 1.02, + "learning_rate": 2.780378913797046e-05, + "loss": 3.5004, + "step": 1355776 + }, + { + "epoch": 1.02, + "learning_rate": 2.779540319045994e-05, + "loss": 3.5049, + "step": 1356288 + }, + { + "epoch": 1.02, + "learning_rate": 2.778701724294942e-05, + "loss": 3.5099, + "step": 1356800 + }, + { + "epoch": 1.02, + "learning_rate": 2.7778631295438895e-05, + "loss": 3.5047, + "step": 1357312 + }, + { + "epoch": 1.02, + "learning_rate": 2.7770245347928375e-05, + "loss": 3.505, + "step": 1357824 + }, + { + "epoch": 1.02, + "learning_rate": 2.7761859400417855e-05, + "loss": 3.5119, + "step": 1358336 + }, + { + "epoch": 1.02, + "learning_rate": 2.775348983171107e-05, + "loss": 3.5089, + "step": 1358848 + }, + { + "epoch": 1.02, + "learning_rate": 2.7745103884200548e-05, + "loss": 3.4946, + "step": 1359360 + }, + { + "epoch": 1.02, + "learning_rate": 2.7736717936690028e-05, + "loss": 3.5088, + "step": 1359872 + }, + { + "epoch": 1.02, + "learning_rate": 2.7728348367983243e-05, + "loss": 3.4991, + "step": 1360384 + }, + { + "epoch": 1.02, + "learning_rate": 2.7719962420472717e-05, + "loss": 3.5102, + "step": 1360896 + }, + { + "epoch": 1.02, + "learning_rate": 2.7711576472962197e-05, + "loss": 3.4879, + "step": 1361408 + }, + { + "epoch": 1.02, + "learning_rate": 2.7703190525451676e-05, + "loss": 3.5077, + "step": 1361920 + }, + { + "epoch": 1.02, + "learning_rate": 2.7694804577941156e-05, + "loss": 3.4915, + "step": 1362432 + }, + { + "epoch": 1.02, + "learning_rate": 2.768641863043064e-05, + "loss": 3.4917, + "step": 1362944 + }, + { + "epoch": 1.02, + "learning_rate": 2.767803268292012e-05, + "loss": 3.491, + "step": 1363456 + }, + { + "epoch": 1.02, + "learning_rate": 2.766966311421333e-05, + "loss": 3.5159, + "step": 1363968 + }, + { + "epoch": 1.02, + "learning_rate": 2.766127716670281e-05, + "loss": 3.5104, + "step": 1364480 + }, + { + "epoch": 1.02, + "learning_rate": 2.765289121919229e-05, + "loss": 3.4998, + "step": 1364992 + }, + { + "epoch": 1.02, + "learning_rate": 2.764450527168177e-05, + "loss": 3.4988, + "step": 1365504 + }, + { + "epoch": 1.02, + "learning_rate": 2.763613570297498e-05, + "loss": 3.5061, + "step": 1366016 + }, + { + "epoch": 1.02, + "learning_rate": 2.762774975546446e-05, + "loss": 3.5091, + "step": 1366528 + }, + { + "epoch": 1.02, + "learning_rate": 2.761936380795394e-05, + "loss": 3.5045, + "step": 1367040 + }, + { + "epoch": 1.02, + "learning_rate": 2.761097786044342e-05, + "loss": 3.5021, + "step": 1367552 + }, + { + "epoch": 1.02, + "learning_rate": 2.760260829173663e-05, + "loss": 3.5084, + "step": 1368064 + }, + { + "epoch": 1.02, + "learning_rate": 2.759422234422611e-05, + "loss": 3.5008, + "step": 1368576 + }, + { + "epoch": 1.02, + "learning_rate": 2.7585836396715593e-05, + "loss": 3.513, + "step": 1369088 + }, + { + "epoch": 1.02, + "learning_rate": 2.7577450449205073e-05, + "loss": 3.4996, + "step": 1369600 + }, + { + "epoch": 1.02, + "learning_rate": 2.7569080880498283e-05, + "loss": 3.5048, + "step": 1370112 + }, + { + "epoch": 1.02, + "learning_rate": 2.7560694932987762e-05, + "loss": 3.5018, + "step": 1370624 + }, + { + "epoch": 1.02, + "learning_rate": 2.7552308985477242e-05, + "loss": 3.4942, + "step": 1371136 + }, + { + "epoch": 1.02, + "learning_rate": 2.7543923037966722e-05, + "loss": 3.5096, + "step": 1371648 + }, + { + "epoch": 1.02, + "learning_rate": 2.7535553469259935e-05, + "loss": 3.5037, + "step": 1372160 + }, + { + "epoch": 1.02, + "learning_rate": 2.7527167521749415e-05, + "loss": 3.5061, + "step": 1372672 + }, + { + "epoch": 1.02, + "learning_rate": 2.7518781574238895e-05, + "loss": 3.4989, + "step": 1373184 + }, + { + "epoch": 1.02, + "learning_rate": 2.7510395626728375e-05, + "loss": 3.4987, + "step": 1373696 + }, + { + "epoch": 1.03, + "eval_loss": 3.848916530609131, + "eval_runtime": 308.5251, + "eval_samples_per_second": 1236.823, + "eval_steps_per_second": 38.652, + "step": 1373760 + }, + { + "epoch": 0.0, + "learning_rate": 2.7502009679217855e-05, + "loss": 3.4932, + "step": 1374208 + }, + { + "epoch": 0.0, + "learning_rate": 2.7493623731707335e-05, + "loss": 3.4936, + "step": 1374720 + }, + { + "epoch": 0.0, + "learning_rate": 2.7485237784196815e-05, + "loss": 3.5074, + "step": 1375232 + }, + { + "epoch": 0.0, + "learning_rate": 2.7476851836686295e-05, + "loss": 3.4973, + "step": 1375744 + }, + { + "epoch": 0.0, + "learning_rate": 2.7468482267979507e-05, + "loss": 3.5195, + "step": 1376256 + }, + { + "epoch": 0.0, + "learning_rate": 2.7460096320468987e-05, + "loss": 3.4893, + "step": 1376768 + }, + { + "epoch": 0.0, + "learning_rate": 2.7451710372958467e-05, + "loss": 3.4994, + "step": 1377280 + }, + { + "epoch": 0.0, + "learning_rate": 2.7443340804251676e-05, + "loss": 3.4842, + "step": 1377792 + }, + { + "epoch": 0.0, + "learning_rate": 2.7434954856741156e-05, + "loss": 3.5036, + "step": 1378304 + }, + { + "epoch": 0.0, + "learning_rate": 2.742656890923064e-05, + "loss": 3.4961, + "step": 1378816 + }, + { + "epoch": 0.0, + "learning_rate": 2.741818296172012e-05, + "loss": 3.502, + "step": 1379328 + }, + { + "epoch": 0.0, + "learning_rate": 2.74097970142096e-05, + "loss": 3.4985, + "step": 1379840 + }, + { + "epoch": 0.0, + "learning_rate": 2.7401443824306537e-05, + "loss": 3.49, + "step": 1380352 + }, + { + "epoch": 0.0, + "learning_rate": 2.7393057876796017e-05, + "loss": 3.4972, + "step": 1380864 + }, + { + "epoch": 0.0, + "learning_rate": 2.73846719292855e-05, + "loss": 3.4945, + "step": 1381376 + }, + { + "epoch": 0.0, + "learning_rate": 2.737628598177498e-05, + "loss": 3.4902, + "step": 1381888 + }, + { + "epoch": 0.0, + "learning_rate": 2.736790003426446e-05, + "loss": 3.493, + "step": 1382400 + }, + { + "epoch": 0.0, + "learning_rate": 2.735951408675394e-05, + "loss": 3.4948, + "step": 1382912 + }, + { + "epoch": 0.0, + "learning_rate": 2.735112813924342e-05, + "loss": 3.4922, + "step": 1383424 + }, + { + "epoch": 0.0, + "learning_rate": 2.73427421917329e-05, + "loss": 3.5158, + "step": 1383936 + }, + { + "epoch": 0.0, + "learning_rate": 2.733437262302611e-05, + "loss": 3.4949, + "step": 1384448 + }, + { + "epoch": 0.0, + "learning_rate": 2.7325986675515593e-05, + "loss": 3.4985, + "step": 1384960 + }, + { + "epoch": 0.0, + "learning_rate": 2.7317600728005073e-05, + "loss": 3.4993, + "step": 1385472 + }, + { + "epoch": 0.0, + "learning_rate": 2.7309231159298282e-05, + "loss": 3.5065, + "step": 1385984 + }, + { + "epoch": 0.0, + "learning_rate": 2.7300845211787762e-05, + "loss": 3.4893, + "step": 1386496 + }, + { + "epoch": 0.0, + "learning_rate": 2.7292459264277242e-05, + "loss": 3.5016, + "step": 1387008 + }, + { + "epoch": 0.0, + "learning_rate": 2.7284073316766722e-05, + "loss": 3.4911, + "step": 1387520 + }, + { + "epoch": 0.0, + "learning_rate": 2.7275703748059934e-05, + "loss": 3.4967, + "step": 1388032 + }, + { + "epoch": 0.0, + "learning_rate": 2.7267317800549414e-05, + "loss": 3.4832, + "step": 1388544 + }, + { + "epoch": 0.01, + "learning_rate": 2.7258931853038894e-05, + "loss": 3.49, + "step": 1389056 + }, + { + "epoch": 0.01, + "learning_rate": 2.7250545905528374e-05, + "loss": 3.501, + "step": 1389568 + }, + { + "epoch": 0.01, + "learning_rate": 2.7242176336821583e-05, + "loss": 3.5004, + "step": 1390080 + }, + { + "epoch": 0.01, + "learning_rate": 2.7233790389311063e-05, + "loss": 3.5006, + "step": 1390592 + }, + { + "epoch": 0.01, + "learning_rate": 2.7225404441800543e-05, + "loss": 3.5042, + "step": 1391104 + }, + { + "epoch": 0.01, + "learning_rate": 2.7217018494290027e-05, + "loss": 3.497, + "step": 1391616 + }, + { + "epoch": 0.01, + "learning_rate": 2.7208648925583236e-05, + "loss": 3.5012, + "step": 1392128 + }, + { + "epoch": 0.01, + "learning_rate": 2.7200262978072716e-05, + "loss": 3.4912, + "step": 1392640 + }, + { + "epoch": 0.01, + "learning_rate": 2.7191877030562196e-05, + "loss": 3.5035, + "step": 1393152 + }, + { + "epoch": 0.01, + "learning_rate": 2.7183491083051676e-05, + "loss": 3.4885, + "step": 1393664 + }, + { + "epoch": 0.01, + "learning_rate": 2.7175121514344888e-05, + "loss": 3.4954, + "step": 1394176 + }, + { + "epoch": 0.01, + "learning_rate": 2.7166735566834368e-05, + "loss": 3.4921, + "step": 1394688 + }, + { + "epoch": 0.01, + "learning_rate": 2.7158349619323848e-05, + "loss": 3.5043, + "step": 1395200 + }, + { + "epoch": 0.01, + "learning_rate": 2.714996367181332e-05, + "loss": 3.4938, + "step": 1395712 + }, + { + "epoch": 0.01, + "learning_rate": 2.7141594103106537e-05, + "loss": 3.4953, + "step": 1396224 + }, + { + "epoch": 0.01, + "learning_rate": 2.7133208155596017e-05, + "loss": 3.5054, + "step": 1396736 + }, + { + "epoch": 0.01, + "learning_rate": 2.7124822208085497e-05, + "loss": 3.4996, + "step": 1397248 + }, + { + "epoch": 0.01, + "learning_rate": 2.7116436260574974e-05, + "loss": 3.4977, + "step": 1397760 + }, + { + "epoch": 0.01, + "learning_rate": 2.7108050313064453e-05, + "loss": 3.4817, + "step": 1398272 + }, + { + "epoch": 0.01, + "learning_rate": 2.709968074435767e-05, + "loss": 3.4839, + "step": 1398784 + }, + { + "epoch": 0.01, + "learning_rate": 2.709129479684715e-05, + "loss": 3.4971, + "step": 1399296 + }, + { + "epoch": 0.01, + "learning_rate": 2.7082908849336626e-05, + "loss": 3.4977, + "step": 1399808 + }, + { + "epoch": 0.01, + "learning_rate": 2.7074522901826106e-05, + "loss": 3.4933, + "step": 1400320 + }, + { + "epoch": 0.01, + "learning_rate": 2.7066153333119322e-05, + "loss": 3.4747, + "step": 1400832 + }, + { + "epoch": 0.01, + "learning_rate": 2.7057767385608795e-05, + "loss": 3.4806, + "step": 1401344 + }, + { + "epoch": 0.01, + "learning_rate": 2.7049381438098275e-05, + "loss": 3.4841, + "step": 1401856 + }, + { + "epoch": 0.01, + "learning_rate": 2.704101186939149e-05, + "loss": 3.4951, + "step": 1402368 + }, + { + "epoch": 0.01, + "learning_rate": 2.703262592188097e-05, + "loss": 3.4834, + "step": 1402880 + }, + { + "epoch": 0.01, + "learning_rate": 2.7024239974370447e-05, + "loss": 3.4968, + "step": 1403392 + }, + { + "epoch": 0.01, + "learning_rate": 2.7015854026859927e-05, + "loss": 3.4941, + "step": 1403904 + }, + { + "epoch": 0.01, + "learning_rate": 2.7007484458153143e-05, + "loss": 3.4859, + "step": 1404416 + }, + { + "epoch": 0.01, + "learning_rate": 2.6999098510642623e-05, + "loss": 3.4893, + "step": 1404928 + }, + { + "epoch": 0.01, + "learning_rate": 2.6990712563132096e-05, + "loss": 3.4858, + "step": 1405440 + }, + { + "epoch": 0.01, + "learning_rate": 2.698232661562158e-05, + "loss": 3.4774, + "step": 1405952 + }, + { + "epoch": 0.01, + "learning_rate": 2.6973957046914795e-05, + "loss": 3.4869, + "step": 1406464 + }, + { + "epoch": 0.01, + "learning_rate": 2.696557109940427e-05, + "loss": 3.4929, + "step": 1406976 + }, + { + "epoch": 0.01, + "learning_rate": 2.695718515189375e-05, + "loss": 3.4991, + "step": 1407488 + }, + { + "epoch": 0.01, + "learning_rate": 2.694879920438323e-05, + "loss": 3.4755, + "step": 1408000 + }, + { + "epoch": 0.01, + "learning_rate": 2.6940429635676444e-05, + "loss": 3.4821, + "step": 1408512 + }, + { + "epoch": 0.01, + "learning_rate": 2.693204368816592e-05, + "loss": 3.4823, + "step": 1409024 + }, + { + "epoch": 0.01, + "learning_rate": 2.69236577406554e-05, + "loss": 3.501, + "step": 1409536 + }, + { + "epoch": 0.01, + "learning_rate": 2.691527179314488e-05, + "loss": 3.4888, + "step": 1410048 + }, + { + "epoch": 0.01, + "learning_rate": 2.6906902224438097e-05, + "loss": 3.4938, + "step": 1410560 + }, + { + "epoch": 0.01, + "learning_rate": 2.689851627692757e-05, + "loss": 3.5081, + "step": 1411072 + }, + { + "epoch": 0.01, + "learning_rate": 2.689013032941705e-05, + "loss": 3.5006, + "step": 1411584 + }, + { + "epoch": 0.01, + "learning_rate": 2.6881744381906533e-05, + "loss": 3.5044, + "step": 1412096 + }, + { + "epoch": 0.01, + "learning_rate": 2.6873374813199742e-05, + "loss": 3.4925, + "step": 1412608 + }, + { + "epoch": 0.01, + "learning_rate": 2.6864988865689222e-05, + "loss": 3.4939, + "step": 1413120 + }, + { + "epoch": 0.01, + "learning_rate": 2.6856602918178702e-05, + "loss": 3.4929, + "step": 1413632 + }, + { + "epoch": 0.01, + "learning_rate": 2.6848216970668182e-05, + "loss": 3.4899, + "step": 1414144 + }, + { + "epoch": 0.01, + "learning_rate": 2.6839847401961395e-05, + "loss": 3.4937, + "step": 1414656 + }, + { + "epoch": 0.01, + "learning_rate": 2.6831461454450875e-05, + "loss": 3.4945, + "step": 1415168 + }, + { + "epoch": 0.01, + "learning_rate": 2.6823075506940355e-05, + "loss": 3.5007, + "step": 1415680 + }, + { + "epoch": 0.01, + "learning_rate": 2.6814689559429835e-05, + "loss": 3.491, + "step": 1416192 + }, + { + "epoch": 0.01, + "learning_rate": 2.6806319990723044e-05, + "loss": 3.4866, + "step": 1416704 + }, + { + "epoch": 0.01, + "learning_rate": 2.6797934043212524e-05, + "loss": 3.4802, + "step": 1417216 + }, + { + "epoch": 0.01, + "learning_rate": 2.6789548095702004e-05, + "loss": 3.4948, + "step": 1417728 + }, + { + "epoch": 0.01, + "learning_rate": 2.6781162148191487e-05, + "loss": 3.5005, + "step": 1418240 + }, + { + "epoch": 0.01, + "learning_rate": 2.6772792579484696e-05, + "loss": 3.487, + "step": 1418752 + }, + { + "epoch": 0.01, + "learning_rate": 2.6764406631974176e-05, + "loss": 3.4899, + "step": 1419264 + }, + { + "epoch": 0.02, + "learning_rate": 2.6756020684463656e-05, + "loss": 3.499, + "step": 1419776 + }, + { + "epoch": 0.02, + "learning_rate": 2.6747651115756865e-05, + "loss": 3.4788, + "step": 1420288 + }, + { + "epoch": 0.02, + "learning_rate": 2.673926516824635e-05, + "loss": 3.4892, + "step": 1420800 + }, + { + "epoch": 0.02, + "learning_rate": 2.6730879220735828e-05, + "loss": 3.4889, + "step": 1421312 + }, + { + "epoch": 0.02, + "learning_rate": 2.6722493273225308e-05, + "loss": 3.4987, + "step": 1421824 + }, + { + "epoch": 0.02, + "learning_rate": 2.6714107325714788e-05, + "loss": 3.4952, + "step": 1422336 + }, + { + "epoch": 0.02, + "learning_rate": 2.6705721378204268e-05, + "loss": 3.4939, + "step": 1422848 + }, + { + "epoch": 0.02, + "learning_rate": 2.6697335430693748e-05, + "loss": 3.4819, + "step": 1423360 + }, + { + "epoch": 0.02, + "learning_rate": 2.6688949483183228e-05, + "loss": 3.4992, + "step": 1423872 + }, + { + "epoch": 0.02, + "learning_rate": 2.668057991447644e-05, + "loss": 3.4871, + "step": 1424384 + }, + { + "epoch": 0.02, + "learning_rate": 2.667219396696592e-05, + "loss": 3.5023, + "step": 1424896 + }, + { + "epoch": 0.02, + "learning_rate": 2.66638080194554e-05, + "loss": 3.4946, + "step": 1425408 + }, + { + "epoch": 0.02, + "learning_rate": 2.665542207194488e-05, + "loss": 3.4964, + "step": 1425920 + }, + { + "epoch": 0.02, + "learning_rate": 2.664705250323809e-05, + "loss": 3.4881, + "step": 1426432 + }, + { + "epoch": 0.02, + "learning_rate": 2.6638682934531302e-05, + "loss": 3.5017, + "step": 1426944 + }, + { + "epoch": 0.02, + "learning_rate": 2.6630296987020782e-05, + "loss": 3.4742, + "step": 1427456 + }, + { + "epoch": 0.02, + "learning_rate": 2.6621911039510262e-05, + "loss": 3.483, + "step": 1427968 + }, + { + "epoch": 0.02, + "learning_rate": 2.6613525091999742e-05, + "loss": 3.4905, + "step": 1428480 + }, + { + "epoch": 0.02, + "learning_rate": 2.6605139144489222e-05, + "loss": 3.4914, + "step": 1428992 + }, + { + "epoch": 0.02, + "learning_rate": 2.6596753196978702e-05, + "loss": 3.4756, + "step": 1429504 + }, + { + "epoch": 0.02, + "learning_rate": 2.6588367249468182e-05, + "loss": 3.4864, + "step": 1430016 + }, + { + "epoch": 0.02, + "learning_rate": 2.657998130195766e-05, + "loss": 3.4819, + "step": 1430528 + }, + { + "epoch": 0.02, + "learning_rate": 2.6571611733250874e-05, + "loss": 3.4928, + "step": 1431040 + }, + { + "epoch": 0.02, + "learning_rate": 2.6563242164544083e-05, + "loss": 3.4871, + "step": 1431552 + }, + { + "epoch": 0.02, + "learning_rate": 2.6554856217033563e-05, + "loss": 3.482, + "step": 1432064 + }, + { + "epoch": 0.02, + "learning_rate": 2.6546470269523043e-05, + "loss": 3.4963, + "step": 1432576 + }, + { + "epoch": 0.02, + "learning_rate": 2.6538084322012523e-05, + "loss": 3.4971, + "step": 1433088 + }, + { + "epoch": 0.02, + "learning_rate": 2.6529698374502003e-05, + "loss": 3.4941, + "step": 1433600 + }, + { + "epoch": 0.02, + "learning_rate": 2.6521312426991486e-05, + "loss": 3.4879, + "step": 1434112 + }, + { + "epoch": 0.02, + "learning_rate": 2.6512926479480966e-05, + "loss": 3.5006, + "step": 1434624 + }, + { + "epoch": 0.02, + "learning_rate": 2.6504556910774175e-05, + "loss": 3.4908, + "step": 1435136 + }, + { + "epoch": 0.02, + "learning_rate": 2.6496170963263655e-05, + "loss": 3.4844, + "step": 1435648 + }, + { + "epoch": 0.02, + "learning_rate": 2.6487785015753135e-05, + "loss": 3.5015, + "step": 1436160 + }, + { + "epoch": 0.02, + "learning_rate": 2.6479415447046348e-05, + "loss": 3.4832, + "step": 1436672 + }, + { + "epoch": 0.02, + "learning_rate": 2.6471029499535828e-05, + "loss": 3.4997, + "step": 1437184 + }, + { + "epoch": 0.02, + "learning_rate": 2.6462643552025308e-05, + "loss": 3.4771, + "step": 1437696 + }, + { + "epoch": 0.02, + "learning_rate": 2.6454257604514788e-05, + "loss": 3.4938, + "step": 1438208 + }, + { + "epoch": 0.02, + "learning_rate": 2.6445871657004268e-05, + "loss": 3.4781, + "step": 1438720 + }, + { + "epoch": 0.02, + "learning_rate": 2.6437485709493748e-05, + "loss": 3.4808, + "step": 1439232 + }, + { + "epoch": 0.02, + "learning_rate": 2.6429099761983228e-05, + "loss": 3.4799, + "step": 1439744 + }, + { + "epoch": 0.02, + "learning_rate": 2.6420730193276437e-05, + "loss": 3.4994, + "step": 1440256 + }, + { + "epoch": 0.02, + "learning_rate": 2.641234424576592e-05, + "loss": 3.4955, + "step": 1440768 + }, + { + "epoch": 0.02, + "learning_rate": 2.64039582982554e-05, + "loss": 3.4903, + "step": 1441280 + }, + { + "epoch": 0.02, + "learning_rate": 2.6395572350744873e-05, + "loss": 3.4875, + "step": 1441792 + }, + { + "epoch": 0.02, + "learning_rate": 2.638720278203809e-05, + "loss": 3.4899, + "step": 1442304 + }, + { + "epoch": 0.02, + "learning_rate": 2.637881683452757e-05, + "loss": 3.4999, + "step": 1442816 + }, + { + "epoch": 0.02, + "learning_rate": 2.637043088701705e-05, + "loss": 3.4908, + "step": 1443328 + }, + { + "epoch": 0.02, + "learning_rate": 2.6362044939506526e-05, + "loss": 3.4881, + "step": 1443840 + }, + { + "epoch": 0.02, + "learning_rate": 2.635367537079974e-05, + "loss": 3.4997, + "step": 1444352 + }, + { + "epoch": 0.02, + "learning_rate": 2.634528942328922e-05, + "loss": 3.49, + "step": 1444864 + }, + { + "epoch": 0.02, + "learning_rate": 2.63369034757787e-05, + "loss": 3.498, + "step": 1445376 + }, + { + "epoch": 0.02, + "learning_rate": 2.6328517528268178e-05, + "loss": 3.4873, + "step": 1445888 + }, + { + "epoch": 0.02, + "learning_rate": 2.632014795956139e-05, + "loss": 3.4922, + "step": 1446400 + }, + { + "epoch": 0.02, + "learning_rate": 2.6311762012050874e-05, + "loss": 3.4888, + "step": 1446912 + }, + { + "epoch": 0.02, + "learning_rate": 2.6303376064540347e-05, + "loss": 3.4871, + "step": 1447424 + }, + { + "epoch": 0.02, + "learning_rate": 2.6294990117029827e-05, + "loss": 3.4907, + "step": 1447936 + }, + { + "epoch": 0.02, + "learning_rate": 2.6286620548323043e-05, + "loss": 3.498, + "step": 1448448 + }, + { + "epoch": 0.02, + "learning_rate": 2.6278234600812523e-05, + "loss": 3.487, + "step": 1448960 + }, + { + "epoch": 0.02, + "learning_rate": 2.6269848653302e-05, + "loss": 3.4867, + "step": 1449472 + }, + { + "epoch": 0.02, + "learning_rate": 2.626146270579148e-05, + "loss": 3.4862, + "step": 1449984 + }, + { + "epoch": 0.03, + "eval_loss": 3.8484787940979004, + "eval_runtime": 561.7633, + "eval_samples_per_second": 679.274, + "eval_steps_per_second": 21.228, + "step": 1450080 + }, + { + "epoch": 1.0, + "learning_rate": 2.6253093137084695e-05, + "loss": 3.4864, + "step": 1450496 + }, + { + "epoch": 1.0, + "learning_rate": 2.6244707189574175e-05, + "loss": 3.4821, + "step": 1451008 + }, + { + "epoch": 1.0, + "learning_rate": 2.6236321242063648e-05, + "loss": 3.4942, + "step": 1451520 + }, + { + "epoch": 1.0, + "learning_rate": 2.6227935294553128e-05, + "loss": 3.482, + "step": 1452032 + }, + { + "epoch": 1.0, + "learning_rate": 2.6219565725846344e-05, + "loss": 3.5095, + "step": 1452544 + }, + { + "epoch": 1.0, + "learning_rate": 2.621117977833582e-05, + "loss": 3.4765, + "step": 1453056 + }, + { + "epoch": 1.0, + "learning_rate": 2.62027938308253e-05, + "loss": 3.4836, + "step": 1453568 + }, + { + "epoch": 1.0, + "learning_rate": 2.619440788331478e-05, + "loss": 3.4708, + "step": 1454080 + }, + { + "epoch": 1.0, + "learning_rate": 2.6186038314607996e-05, + "loss": 3.492, + "step": 1454592 + }, + { + "epoch": 1.0, + "learning_rate": 2.6177652367097473e-05, + "loss": 3.4875, + "step": 1455104 + }, + { + "epoch": 1.0, + "learning_rate": 2.6169266419586953e-05, + "loss": 3.4838, + "step": 1455616 + }, + { + "epoch": 1.0, + "learning_rate": 2.6160880472076433e-05, + "loss": 3.4888, + "step": 1456128 + }, + { + "epoch": 1.0, + "learning_rate": 2.615251090336965e-05, + "loss": 3.4771, + "step": 1456640 + }, + { + "epoch": 1.0, + "learning_rate": 2.6144124955859122e-05, + "loss": 3.4852, + "step": 1457152 + }, + { + "epoch": 1.0, + "learning_rate": 2.6135739008348602e-05, + "loss": 3.4795, + "step": 1457664 + }, + { + "epoch": 1.0, + "learning_rate": 2.6127353060838082e-05, + "loss": 3.4794, + "step": 1458176 + }, + { + "epoch": 1.0, + "learning_rate": 2.6118967113327565e-05, + "loss": 3.4796, + "step": 1458688 + }, + { + "epoch": 1.0, + "learning_rate": 2.6110581165817045e-05, + "loss": 3.4828, + "step": 1459200 + }, + { + "epoch": 1.0, + "learning_rate": 2.6102195218306525e-05, + "loss": 3.4821, + "step": 1459712 + }, + { + "epoch": 1.0, + "learning_rate": 2.6093809270796005e-05, + "loss": 3.5003, + "step": 1460224 + }, + { + "epoch": 1.0, + "learning_rate": 2.6085439702089214e-05, + "loss": 3.4821, + "step": 1460736 + }, + { + "epoch": 1.0, + "learning_rate": 2.6077053754578694e-05, + "loss": 3.4867, + "step": 1461248 + }, + { + "epoch": 1.0, + "learning_rate": 2.6068667807068174e-05, + "loss": 3.4869, + "step": 1461760 + }, + { + "epoch": 1.0, + "learning_rate": 2.6060281859557657e-05, + "loss": 3.4958, + "step": 1462272 + }, + { + "epoch": 1.0, + "learning_rate": 2.6051912290850866e-05, + "loss": 3.4759, + "step": 1462784 + }, + { + "epoch": 1.0, + "learning_rate": 2.6043526343340346e-05, + "loss": 3.4918, + "step": 1463296 + }, + { + "epoch": 1.0, + "learning_rate": 2.6035140395829826e-05, + "loss": 3.4787, + "step": 1463808 + }, + { + "epoch": 1.0, + "learning_rate": 2.6026754448319306e-05, + "loss": 3.4815, + "step": 1464320 + }, + { + "epoch": 1.0, + "learning_rate": 2.601838487961252e-05, + "loss": 3.4705, + "step": 1464832 + }, + { + "epoch": 1.01, + "learning_rate": 2.6009998932102e-05, + "loss": 3.4829, + "step": 1465344 + }, + { + "epoch": 1.01, + "learning_rate": 2.600161298459148e-05, + "loss": 3.4858, + "step": 1465856 + }, + { + "epoch": 1.01, + "learning_rate": 2.599322703708096e-05, + "loss": 3.4873, + "step": 1466368 + }, + { + "epoch": 1.01, + "learning_rate": 2.5984857468374168e-05, + "loss": 3.4874, + "step": 1466880 + }, + { + "epoch": 1.01, + "learning_rate": 2.5976471520863648e-05, + "loss": 3.4922, + "step": 1467392 + }, + { + "epoch": 1.01, + "learning_rate": 2.5968085573353128e-05, + "loss": 3.4826, + "step": 1467904 + }, + { + "epoch": 1.01, + "learning_rate": 2.595971600464634e-05, + "loss": 3.4885, + "step": 1468416 + }, + { + "epoch": 1.01, + "learning_rate": 2.595133005713582e-05, + "loss": 3.4805, + "step": 1468928 + }, + { + "epoch": 1.01, + "learning_rate": 2.59429441096253e-05, + "loss": 3.4895, + "step": 1469440 + }, + { + "epoch": 1.01, + "learning_rate": 2.593455816211478e-05, + "loss": 3.4753, + "step": 1469952 + }, + { + "epoch": 1.01, + "learning_rate": 2.592618859340799e-05, + "loss": 3.4847, + "step": 1470464 + }, + { + "epoch": 1.01, + "learning_rate": 2.5917802645897473e-05, + "loss": 3.4809, + "step": 1470976 + }, + { + "epoch": 1.01, + "learning_rate": 2.5909416698386952e-05, + "loss": 3.4924, + "step": 1471488 + }, + { + "epoch": 1.01, + "learning_rate": 2.5901030750876432e-05, + "loss": 3.4837, + "step": 1472000 + }, + { + "epoch": 1.01, + "learning_rate": 2.589266118216964e-05, + "loss": 3.4836, + "step": 1472512 + }, + { + "epoch": 1.01, + "learning_rate": 2.588427523465912e-05, + "loss": 3.4892, + "step": 1473024 + }, + { + "epoch": 1.01, + "learning_rate": 2.58758892871486e-05, + "loss": 3.4874, + "step": 1473536 + }, + { + "epoch": 1.01, + "learning_rate": 2.586750333963808e-05, + "loss": 3.4852, + "step": 1474048 + }, + { + "epoch": 1.01, + "learning_rate": 2.5859117392127565e-05, + "loss": 3.4761, + "step": 1474560 + }, + { + "epoch": 1.01, + "learning_rate": 2.5850747823420774e-05, + "loss": 3.4647, + "step": 1475072 + }, + { + "epoch": 1.01, + "learning_rate": 2.5842361875910254e-05, + "loss": 3.4869, + "step": 1475584 + }, + { + "epoch": 1.01, + "learning_rate": 2.5833975928399734e-05, + "loss": 3.4826, + "step": 1476096 + }, + { + "epoch": 1.01, + "learning_rate": 2.5825606359692943e-05, + "loss": 3.4787, + "step": 1476608 + }, + { + "epoch": 1.01, + "learning_rate": 2.5817220412182426e-05, + "loss": 3.47, + "step": 1477120 + }, + { + "epoch": 1.01, + "learning_rate": 2.5808834464671906e-05, + "loss": 3.4683, + "step": 1477632 + }, + { + "epoch": 1.01, + "learning_rate": 2.5800448517161386e-05, + "loss": 3.4678, + "step": 1478144 + }, + { + "epoch": 1.01, + "learning_rate": 2.5792078948454595e-05, + "loss": 3.4838, + "step": 1478656 + }, + { + "epoch": 1.01, + "learning_rate": 2.5783693000944075e-05, + "loss": 3.4725, + "step": 1479168 + }, + { + "epoch": 1.01, + "learning_rate": 2.5775307053433555e-05, + "loss": 3.4803, + "step": 1479680 + }, + { + "epoch": 1.01, + "learning_rate": 2.5766921105923035e-05, + "loss": 3.4835, + "step": 1480192 + }, + { + "epoch": 1.01, + "learning_rate": 2.5758551537216248e-05, + "loss": 3.4731, + "step": 1480704 + }, + { + "epoch": 1.01, + "learning_rate": 2.5750165589705727e-05, + "loss": 3.4756, + "step": 1481216 + }, + { + "epoch": 1.01, + "learning_rate": 2.5741779642195207e-05, + "loss": 3.4786, + "step": 1481728 + }, + { + "epoch": 1.01, + "learning_rate": 2.5733393694684687e-05, + "loss": 3.4596, + "step": 1482240 + }, + { + "epoch": 1.01, + "learning_rate": 2.5725024125977896e-05, + "loss": 3.4747, + "step": 1482752 + }, + { + "epoch": 1.01, + "learning_rate": 2.571663817846738e-05, + "loss": 3.4838, + "step": 1483264 + }, + { + "epoch": 1.01, + "learning_rate": 2.570825223095686e-05, + "loss": 3.4833, + "step": 1483776 + }, + { + "epoch": 1.01, + "learning_rate": 2.569986628344634e-05, + "loss": 3.4648, + "step": 1484288 + }, + { + "epoch": 1.01, + "learning_rate": 2.569149671473955e-05, + "loss": 3.4733, + "step": 1484800 + }, + { + "epoch": 1.01, + "learning_rate": 2.568311076722903e-05, + "loss": 3.469, + "step": 1485312 + }, + { + "epoch": 1.01, + "learning_rate": 2.567472481971851e-05, + "loss": 3.4845, + "step": 1485824 + }, + { + "epoch": 1.01, + "learning_rate": 2.566633887220799e-05, + "loss": 3.4787, + "step": 1486336 + }, + { + "epoch": 1.01, + "learning_rate": 2.56579693035012e-05, + "loss": 3.4824, + "step": 1486848 + }, + { + "epoch": 1.01, + "learning_rate": 2.564959973479441e-05, + "loss": 3.4933, + "step": 1487360 + }, + { + "epoch": 1.01, + "learning_rate": 2.564121378728389e-05, + "loss": 3.4901, + "step": 1487872 + }, + { + "epoch": 1.01, + "learning_rate": 2.563282783977337e-05, + "loss": 3.4965, + "step": 1488384 + }, + { + "epoch": 1.01, + "learning_rate": 2.562444189226285e-05, + "loss": 3.475, + "step": 1488896 + }, + { + "epoch": 1.01, + "learning_rate": 2.5616055944752334e-05, + "loss": 3.4846, + "step": 1489408 + }, + { + "epoch": 1.01, + "learning_rate": 2.5607669997241813e-05, + "loss": 3.483, + "step": 1489920 + }, + { + "epoch": 1.01, + "learning_rate": 2.5599284049731293e-05, + "loss": 3.4776, + "step": 1490432 + }, + { + "epoch": 1.01, + "learning_rate": 2.5590898102220773e-05, + "loss": 3.4871, + "step": 1490944 + }, + { + "epoch": 1.01, + "learning_rate": 2.5582528533513982e-05, + "loss": 3.4798, + "step": 1491456 + }, + { + "epoch": 1.01, + "learning_rate": 2.5574142586003462e-05, + "loss": 3.4882, + "step": 1491968 + }, + { + "epoch": 1.01, + "learning_rate": 2.5565756638492942e-05, + "loss": 3.4828, + "step": 1492480 + }, + { + "epoch": 1.01, + "learning_rate": 2.5557370690982422e-05, + "loss": 3.4683, + "step": 1492992 + }, + { + "epoch": 1.01, + "learning_rate": 2.5549001122275635e-05, + "loss": 3.4709, + "step": 1493504 + }, + { + "epoch": 1.01, + "learning_rate": 2.5540615174765115e-05, + "loss": 3.4837, + "step": 1494016 + }, + { + "epoch": 1.01, + "learning_rate": 2.5532229227254595e-05, + "loss": 3.488, + "step": 1494528 + }, + { + "epoch": 1.01, + "learning_rate": 2.5523843279744075e-05, + "loss": 3.4766, + "step": 1495040 + }, + { + "epoch": 1.01, + "learning_rate": 2.5515473711037284e-05, + "loss": 3.4753, + "step": 1495552 + }, + { + "epoch": 1.02, + "learning_rate": 2.5507087763526767e-05, + "loss": 3.4855, + "step": 1496064 + }, + { + "epoch": 1.02, + "learning_rate": 2.5498718194819976e-05, + "loss": 3.4714, + "step": 1496576 + }, + { + "epoch": 1.02, + "learning_rate": 2.5490332247309456e-05, + "loss": 3.4735, + "step": 1497088 + }, + { + "epoch": 1.02, + "learning_rate": 2.5481946299798936e-05, + "loss": 3.4801, + "step": 1497600 + }, + { + "epoch": 1.02, + "learning_rate": 2.5473560352288416e-05, + "loss": 3.4865, + "step": 1498112 + }, + { + "epoch": 1.02, + "learning_rate": 2.5465174404777896e-05, + "loss": 3.4853, + "step": 1498624 + }, + { + "epoch": 1.02, + "learning_rate": 2.5456788457267373e-05, + "loss": 3.4801, + "step": 1499136 + }, + { + "epoch": 1.02, + "learning_rate": 2.5448402509756853e-05, + "loss": 3.4669, + "step": 1499648 + }, + { + "epoch": 1.02, + "learning_rate": 2.5440016562246333e-05, + "loss": 3.4899, + "step": 1500160 + }, + { + "epoch": 1.02, + "learning_rate": 2.543164699353955e-05, + "loss": 3.4719, + "step": 1500672 + }, + { + "epoch": 1.02, + "learning_rate": 2.542326104602902e-05, + "loss": 3.4914, + "step": 1501184 + }, + { + "epoch": 1.02, + "learning_rate": 2.5414875098518505e-05, + "loss": 3.4843, + "step": 1501696 + }, + { + "epoch": 1.02, + "learning_rate": 2.5406489151007985e-05, + "loss": 3.4822, + "step": 1502208 + }, + { + "epoch": 1.02, + "learning_rate": 2.53981195823012e-05, + "loss": 3.4748, + "step": 1502720 + }, + { + "epoch": 1.02, + "learning_rate": 2.538975001359441e-05, + "loss": 3.4896, + "step": 1503232 + }, + { + "epoch": 1.02, + "learning_rate": 2.538136406608389e-05, + "loss": 3.4646, + "step": 1503744 + }, + { + "epoch": 1.02, + "learning_rate": 2.537297811857337e-05, + "loss": 3.4739, + "step": 1504256 + }, + { + "epoch": 1.02, + "learning_rate": 2.5364592171062846e-05, + "loss": 3.4719, + "step": 1504768 + }, + { + "epoch": 1.02, + "learning_rate": 2.5356206223552326e-05, + "loss": 3.4795, + "step": 1505280 + }, + { + "epoch": 1.02, + "learning_rate": 2.5347820276041806e-05, + "loss": 3.4654, + "step": 1505792 + }, + { + "epoch": 1.02, + "learning_rate": 2.5339434328531286e-05, + "loss": 3.4757, + "step": 1506304 + }, + { + "epoch": 1.02, + "learning_rate": 2.5331048381020766e-05, + "loss": 3.4738, + "step": 1506816 + }, + { + "epoch": 1.02, + "learning_rate": 2.5322678812313975e-05, + "loss": 3.4738, + "step": 1507328 + }, + { + "epoch": 1.02, + "learning_rate": 2.531430924360719e-05, + "loss": 3.4786, + "step": 1507840 + }, + { + "epoch": 1.02, + "learning_rate": 2.5305923296096668e-05, + "loss": 3.4694, + "step": 1508352 + }, + { + "epoch": 1.02, + "learning_rate": 2.5297537348586148e-05, + "loss": 3.4865, + "step": 1508864 + }, + { + "epoch": 1.02, + "learning_rate": 2.5289151401075628e-05, + "loss": 3.4841, + "step": 1509376 + }, + { + "epoch": 1.02, + "learning_rate": 2.5280765453565108e-05, + "loss": 3.4823, + "step": 1509888 + }, + { + "epoch": 1.02, + "learning_rate": 2.5272379506054588e-05, + "loss": 3.4767, + "step": 1510400 + }, + { + "epoch": 1.02, + "learning_rate": 2.52640099373478e-05, + "loss": 3.4865, + "step": 1510912 + }, + { + "epoch": 1.02, + "learning_rate": 2.525562398983728e-05, + "loss": 3.484, + "step": 1511424 + }, + { + "epoch": 1.02, + "learning_rate": 2.524723804232676e-05, + "loss": 3.4705, + "step": 1511936 + }, + { + "epoch": 1.02, + "learning_rate": 2.523885209481624e-05, + "loss": 3.4858, + "step": 1512448 + }, + { + "epoch": 1.02, + "learning_rate": 2.523046614730572e-05, + "loss": 3.4731, + "step": 1512960 + }, + { + "epoch": 1.02, + "learning_rate": 2.52220801997952e-05, + "loss": 3.4851, + "step": 1513472 + }, + { + "epoch": 1.02, + "learning_rate": 2.521369425228468e-05, + "loss": 3.4688, + "step": 1513984 + }, + { + "epoch": 1.02, + "learning_rate": 2.520530830477416e-05, + "loss": 3.479, + "step": 1514496 + }, + { + "epoch": 1.02, + "learning_rate": 2.5196938736067372e-05, + "loss": 3.4668, + "step": 1515008 + }, + { + "epoch": 1.02, + "learning_rate": 2.5188552788556852e-05, + "loss": 3.4703, + "step": 1515520 + }, + { + "epoch": 1.02, + "learning_rate": 2.5180166841046332e-05, + "loss": 3.4693, + "step": 1516032 + }, + { + "epoch": 1.02, + "learning_rate": 2.5171780893535812e-05, + "loss": 3.4828, + "step": 1516544 + }, + { + "epoch": 1.02, + "learning_rate": 2.516341132482902e-05, + "loss": 3.4784, + "step": 1517056 + }, + { + "epoch": 1.02, + "learning_rate": 2.5155025377318504e-05, + "loss": 3.4827, + "step": 1517568 + }, + { + "epoch": 1.02, + "learning_rate": 2.5146639429807984e-05, + "loss": 3.4741, + "step": 1518080 + }, + { + "epoch": 1.02, + "learning_rate": 2.5138253482297464e-05, + "loss": 3.4792, + "step": 1518592 + }, + { + "epoch": 1.02, + "learning_rate": 2.5129883913590673e-05, + "loss": 3.486, + "step": 1519104 + }, + { + "epoch": 1.02, + "learning_rate": 2.5121497966080153e-05, + "loss": 3.4803, + "step": 1519616 + }, + { + "epoch": 1.02, + "learning_rate": 2.5113112018569633e-05, + "loss": 3.475, + "step": 1520128 + }, + { + "epoch": 1.02, + "learning_rate": 2.5104726071059113e-05, + "loss": 3.4863, + "step": 1520640 + }, + { + "epoch": 1.02, + "learning_rate": 2.5096356502352326e-05, + "loss": 3.4779, + "step": 1521152 + }, + { + "epoch": 1.02, + "learning_rate": 2.5087970554841806e-05, + "loss": 3.4869, + "step": 1521664 + }, + { + "epoch": 1.02, + "learning_rate": 2.5079584607331286e-05, + "loss": 3.4721, + "step": 1522176 + }, + { + "epoch": 1.02, + "learning_rate": 2.5071198659820766e-05, + "loss": 3.483, + "step": 1522688 + }, + { + "epoch": 1.02, + "learning_rate": 2.5062829091113975e-05, + "loss": 3.476, + "step": 1523200 + }, + { + "epoch": 1.02, + "learning_rate": 2.5054443143603458e-05, + "loss": 3.4734, + "step": 1523712 + }, + { + "epoch": 1.02, + "learning_rate": 2.5046057196092938e-05, + "loss": 3.4827, + "step": 1524224 + }, + { + "epoch": 1.02, + "learning_rate": 2.5037671248582418e-05, + "loss": 3.4802, + "step": 1524736 + }, + { + "epoch": 1.02, + "learning_rate": 2.5029301679875627e-05, + "loss": 3.4777, + "step": 1525248 + }, + { + "epoch": 1.02, + "learning_rate": 2.5020915732365107e-05, + "loss": 3.4697, + "step": 1525760 + }, + { + "epoch": 1.02, + "learning_rate": 2.5012529784854587e-05, + "loss": 3.4788, + "step": 1526272 + }, + { + "epoch": 1.03, + "eval_loss": 3.850346565246582, + "eval_runtime": 554.4189, + "eval_samples_per_second": 688.272, + "eval_steps_per_second": 21.509, + "step": 1526400 + }, + { + "epoch": 0.0, + "learning_rate": 2.5004143837344067e-05, + "loss": 3.4702, + "step": 1526784 + }, + { + "epoch": 0.0, + "learning_rate": 2.4995757889833547e-05, + "loss": 3.4677, + "step": 1527296 + }, + { + "epoch": 0.0, + "learning_rate": 2.4987371942323027e-05, + "loss": 3.4809, + "step": 1527808 + }, + { + "epoch": 0.0, + "learning_rate": 2.4978985994812507e-05, + "loss": 3.4717, + "step": 1528320 + }, + { + "epoch": 0.0, + "learning_rate": 2.4970616426105716e-05, + "loss": 3.4941, + "step": 1528832 + }, + { + "epoch": 0.0, + "learning_rate": 2.4962230478595196e-05, + "loss": 3.4737, + "step": 1529344 + }, + { + "epoch": 0.0, + "learning_rate": 2.4953844531084676e-05, + "loss": 3.4698, + "step": 1529856 + }, + { + "epoch": 0.0, + "learning_rate": 2.494545858357416e-05, + "loss": 3.4577, + "step": 1530368 + }, + { + "epoch": 0.0, + "learning_rate": 2.493708901486737e-05, + "loss": 3.4786, + "step": 1530880 + }, + { + "epoch": 0.0, + "learning_rate": 2.4928703067356848e-05, + "loss": 3.4784, + "step": 1531392 + }, + { + "epoch": 0.0, + "learning_rate": 2.4920317119846328e-05, + "loss": 3.4701, + "step": 1531904 + }, + { + "epoch": 0.0, + "learning_rate": 2.4911931172335808e-05, + "loss": 3.4727, + "step": 1532416 + }, + { + "epoch": 0.0, + "learning_rate": 2.4903577982432753e-05, + "loss": 3.4671, + "step": 1532928 + }, + { + "epoch": 0.0, + "learning_rate": 2.4895192034922233e-05, + "loss": 3.4718, + "step": 1533440 + }, + { + "epoch": 0.0, + "learning_rate": 2.4886806087411713e-05, + "loss": 3.4705, + "step": 1533952 + }, + { + "epoch": 0.0, + "learning_rate": 2.487842013990119e-05, + "loss": 3.4668, + "step": 1534464 + }, + { + "epoch": 0.0, + "learning_rate": 2.487003419239067e-05, + "loss": 3.4671, + "step": 1534976 + }, + { + "epoch": 0.0, + "learning_rate": 2.486164824488015e-05, + "loss": 3.4742, + "step": 1535488 + }, + { + "epoch": 0.0, + "learning_rate": 2.485326229736963e-05, + "loss": 3.4672, + "step": 1536000 + }, + { + "epoch": 0.0, + "learning_rate": 2.4844876349859113e-05, + "loss": 3.485, + "step": 1536512 + }, + { + "epoch": 0.0, + "learning_rate": 2.4836506781152322e-05, + "loss": 3.4746, + "step": 1537024 + }, + { + "epoch": 0.0, + "learning_rate": 2.4828120833641802e-05, + "loss": 3.4745, + "step": 1537536 + }, + { + "epoch": 0.0, + "learning_rate": 2.4819734886131282e-05, + "loss": 3.4736, + "step": 1538048 + }, + { + "epoch": 0.0, + "learning_rate": 2.4811348938620762e-05, + "loss": 3.4819, + "step": 1538560 + }, + { + "epoch": 0.0, + "learning_rate": 2.4802979369913974e-05, + "loss": 3.4651, + "step": 1539072 + }, + { + "epoch": 0.0, + "learning_rate": 2.4794593422403454e-05, + "loss": 3.4757, + "step": 1539584 + }, + { + "epoch": 0.0, + "learning_rate": 2.4786207474892934e-05, + "loss": 3.4692, + "step": 1540096 + }, + { + "epoch": 0.0, + "learning_rate": 2.4777821527382414e-05, + "loss": 3.4664, + "step": 1540608 + }, + { + "epoch": 0.0, + "learning_rate": 2.4769451958675623e-05, + "loss": 3.4611, + "step": 1541120 + }, + { + "epoch": 0.0, + "learning_rate": 2.4761066011165103e-05, + "loss": 3.4686, + "step": 1541632 + }, + { + "epoch": 0.01, + "learning_rate": 2.4752680063654583e-05, + "loss": 3.4778, + "step": 1542144 + }, + { + "epoch": 0.01, + "learning_rate": 2.4744310494947796e-05, + "loss": 3.4746, + "step": 1542656 + }, + { + "epoch": 0.01, + "learning_rate": 2.4735924547437276e-05, + "loss": 3.4784, + "step": 1543168 + }, + { + "epoch": 0.01, + "learning_rate": 2.4727538599926756e-05, + "loss": 3.4772, + "step": 1543680 + }, + { + "epoch": 0.01, + "learning_rate": 2.4719152652416236e-05, + "loss": 3.4707, + "step": 1544192 + }, + { + "epoch": 0.01, + "learning_rate": 2.4710783083709445e-05, + "loss": 3.4752, + "step": 1544704 + }, + { + "epoch": 0.01, + "learning_rate": 2.4702397136198928e-05, + "loss": 3.4711, + "step": 1545216 + }, + { + "epoch": 0.01, + "learning_rate": 2.4694011188688408e-05, + "loss": 3.4744, + "step": 1545728 + }, + { + "epoch": 0.01, + "learning_rate": 2.4685625241177888e-05, + "loss": 3.4642, + "step": 1546240 + }, + { + "epoch": 0.01, + "learning_rate": 2.4677255672471097e-05, + "loss": 3.4714, + "step": 1546752 + }, + { + "epoch": 0.01, + "learning_rate": 2.4668869724960577e-05, + "loss": 3.4696, + "step": 1547264 + }, + { + "epoch": 0.01, + "learning_rate": 2.4660483777450057e-05, + "loss": 3.4789, + "step": 1547776 + }, + { + "epoch": 0.01, + "learning_rate": 2.4652097829939537e-05, + "loss": 3.4714, + "step": 1548288 + }, + { + "epoch": 0.01, + "learning_rate": 2.464372826123275e-05, + "loss": 3.4733, + "step": 1548800 + }, + { + "epoch": 0.01, + "learning_rate": 2.463535869252596e-05, + "loss": 3.4812, + "step": 1549312 + }, + { + "epoch": 0.01, + "learning_rate": 2.462697274501544e-05, + "loss": 3.4715, + "step": 1549824 + }, + { + "epoch": 0.01, + "learning_rate": 2.461858679750492e-05, + "loss": 3.4724, + "step": 1550336 + }, + { + "epoch": 0.01, + "learning_rate": 2.46102008499944e-05, + "loss": 3.4628, + "step": 1550848 + }, + { + "epoch": 0.01, + "learning_rate": 2.460181490248388e-05, + "loss": 3.4518, + "step": 1551360 + }, + { + "epoch": 0.01, + "learning_rate": 2.459342895497336e-05, + "loss": 3.4749, + "step": 1551872 + }, + { + "epoch": 0.01, + "learning_rate": 2.4585043007462838e-05, + "loss": 3.4736, + "step": 1552384 + }, + { + "epoch": 0.01, + "learning_rate": 2.457667343875605e-05, + "loss": 3.4685, + "step": 1552896 + }, + { + "epoch": 0.01, + "learning_rate": 2.456828749124553e-05, + "loss": 3.4521, + "step": 1553408 + }, + { + "epoch": 0.01, + "learning_rate": 2.455990154373501e-05, + "loss": 3.4584, + "step": 1553920 + }, + { + "epoch": 0.01, + "learning_rate": 2.455151559622449e-05, + "loss": 3.4536, + "step": 1554432 + }, + { + "epoch": 0.01, + "learning_rate": 2.4543146027517703e-05, + "loss": 3.4733, + "step": 1554944 + }, + { + "epoch": 0.01, + "learning_rate": 2.4534760080007183e-05, + "loss": 3.4611, + "step": 1555456 + }, + { + "epoch": 0.01, + "learning_rate": 2.4526374132496663e-05, + "loss": 3.4647, + "step": 1555968 + }, + { + "epoch": 0.01, + "learning_rate": 2.451798818498614e-05, + "loss": 3.4735, + "step": 1556480 + }, + { + "epoch": 0.01, + "learning_rate": 2.4509618616279352e-05, + "loss": 3.4608, + "step": 1556992 + }, + { + "epoch": 0.01, + "learning_rate": 2.4501232668768835e-05, + "loss": 3.4635, + "step": 1557504 + }, + { + "epoch": 0.01, + "learning_rate": 2.4492846721258312e-05, + "loss": 3.4693, + "step": 1558016 + }, + { + "epoch": 0.01, + "learning_rate": 2.4484460773747792e-05, + "loss": 3.4483, + "step": 1558528 + }, + { + "epoch": 0.01, + "learning_rate": 2.4476091205041004e-05, + "loss": 3.4628, + "step": 1559040 + }, + { + "epoch": 0.01, + "learning_rate": 2.4467705257530484e-05, + "loss": 3.4684, + "step": 1559552 + }, + { + "epoch": 0.01, + "learning_rate": 2.445931931001996e-05, + "loss": 3.4724, + "step": 1560064 + }, + { + "epoch": 0.01, + "learning_rate": 2.4450933362509444e-05, + "loss": 3.4538, + "step": 1560576 + }, + { + "epoch": 0.01, + "learning_rate": 2.4442563793802657e-05, + "loss": 3.4599, + "step": 1561088 + }, + { + "epoch": 0.01, + "learning_rate": 2.4434177846292137e-05, + "loss": 3.4535, + "step": 1561600 + }, + { + "epoch": 0.01, + "learning_rate": 2.4425791898781613e-05, + "loss": 3.475, + "step": 1562112 + }, + { + "epoch": 0.01, + "learning_rate": 2.4417405951271093e-05, + "loss": 3.4673, + "step": 1562624 + }, + { + "epoch": 0.01, + "learning_rate": 2.4409036382564306e-05, + "loss": 3.4677, + "step": 1563136 + }, + { + "epoch": 0.01, + "learning_rate": 2.4400666813857518e-05, + "loss": 3.4836, + "step": 1563648 + }, + { + "epoch": 0.01, + "learning_rate": 2.4392280866346998e-05, + "loss": 3.4742, + "step": 1564160 + }, + { + "epoch": 0.01, + "learning_rate": 2.4383894918836478e-05, + "loss": 3.4899, + "step": 1564672 + }, + { + "epoch": 0.01, + "learning_rate": 2.4375508971325958e-05, + "loss": 3.4649, + "step": 1565184 + }, + { + "epoch": 0.01, + "learning_rate": 2.4367123023815435e-05, + "loss": 3.4725, + "step": 1565696 + }, + { + "epoch": 0.01, + "learning_rate": 2.4358737076304915e-05, + "loss": 3.4722, + "step": 1566208 + }, + { + "epoch": 0.01, + "learning_rate": 2.4350351128794398e-05, + "loss": 3.4624, + "step": 1566720 + }, + { + "epoch": 0.01, + "learning_rate": 2.4341965181283878e-05, + "loss": 3.4763, + "step": 1567232 + }, + { + "epoch": 0.01, + "learning_rate": 2.4333595612577087e-05, + "loss": 3.4676, + "step": 1567744 + }, + { + "epoch": 0.01, + "learning_rate": 2.4325209665066567e-05, + "loss": 3.4742, + "step": 1568256 + }, + { + "epoch": 0.01, + "learning_rate": 2.4316823717556047e-05, + "loss": 3.4701, + "step": 1568768 + }, + { + "epoch": 0.01, + "learning_rate": 2.4308437770045527e-05, + "loss": 3.4571, + "step": 1569280 + }, + { + "epoch": 0.01, + "learning_rate": 2.430006820133874e-05, + "loss": 3.4656, + "step": 1569792 + }, + { + "epoch": 0.01, + "learning_rate": 2.429168225382822e-05, + "loss": 3.4623, + "step": 1570304 + }, + { + "epoch": 0.01, + "learning_rate": 2.4283312685121432e-05, + "loss": 3.4767, + "step": 1570816 + }, + { + "epoch": 0.01, + "learning_rate": 2.427492673761091e-05, + "loss": 3.4671, + "step": 1571328 + }, + { + "epoch": 0.01, + "learning_rate": 2.4266540790100388e-05, + "loss": 3.4612, + "step": 1571840 + }, + { + "epoch": 0.02, + "learning_rate": 2.4258154842589868e-05, + "loss": 3.4708, + "step": 1572352 + }, + { + "epoch": 0.02, + "learning_rate": 2.4249785273883084e-05, + "loss": 3.465, + "step": 1572864 + }, + { + "epoch": 0.02, + "learning_rate": 2.424139932637256e-05, + "loss": 3.4591, + "step": 1573376 + }, + { + "epoch": 0.02, + "learning_rate": 2.423301337886204e-05, + "loss": 3.4658, + "step": 1573888 + }, + { + "epoch": 0.02, + "learning_rate": 2.422462743135152e-05, + "loss": 3.4779, + "step": 1574400 + }, + { + "epoch": 0.02, + "learning_rate": 2.4216241483841e-05, + "loss": 3.4723, + "step": 1574912 + }, + { + "epoch": 0.02, + "learning_rate": 2.420785553633048e-05, + "loss": 3.4691, + "step": 1575424 + }, + { + "epoch": 0.02, + "learning_rate": 2.419946958881996e-05, + "loss": 3.4531, + "step": 1575936 + }, + { + "epoch": 0.02, + "learning_rate": 2.419108364130944e-05, + "loss": 3.4734, + "step": 1576448 + }, + { + "epoch": 0.02, + "learning_rate": 2.4182714072602653e-05, + "loss": 3.4633, + "step": 1576960 + }, + { + "epoch": 0.02, + "learning_rate": 2.4174328125092133e-05, + "loss": 3.4769, + "step": 1577472 + }, + { + "epoch": 0.02, + "learning_rate": 2.4165942177581613e-05, + "loss": 3.4736, + "step": 1577984 + }, + { + "epoch": 0.02, + "learning_rate": 2.415755623007109e-05, + "loss": 3.4702, + "step": 1578496 + }, + { + "epoch": 0.02, + "learning_rate": 2.4149186661364305e-05, + "loss": 3.4645, + "step": 1579008 + }, + { + "epoch": 0.02, + "learning_rate": 2.4140817092657514e-05, + "loss": 3.4804, + "step": 1579520 + }, + { + "epoch": 0.02, + "learning_rate": 2.4132431145146994e-05, + "loss": 3.4505, + "step": 1580032 + }, + { + "epoch": 0.02, + "learning_rate": 2.4124045197636474e-05, + "loss": 3.4615, + "step": 1580544 + }, + { + "epoch": 0.02, + "learning_rate": 2.4115659250125954e-05, + "loss": 3.4577, + "step": 1581056 + }, + { + "epoch": 0.02, + "learning_rate": 2.4107273302615434e-05, + "loss": 3.4748, + "step": 1581568 + }, + { + "epoch": 0.02, + "learning_rate": 2.4098887355104914e-05, + "loss": 3.4499, + "step": 1582080 + }, + { + "epoch": 0.02, + "learning_rate": 2.4090501407594394e-05, + "loss": 3.4625, + "step": 1582592 + }, + { + "epoch": 0.02, + "learning_rate": 2.4082115460083874e-05, + "loss": 3.4632, + "step": 1583104 + }, + { + "epoch": 0.02, + "learning_rate": 2.4073745891377086e-05, + "loss": 3.4636, + "step": 1583616 + }, + { + "epoch": 0.02, + "learning_rate": 2.4065376322670296e-05, + "loss": 3.465, + "step": 1584128 + }, + { + "epoch": 0.02, + "learning_rate": 2.4056990375159776e-05, + "loss": 3.4607, + "step": 1584640 + }, + { + "epoch": 0.02, + "learning_rate": 2.404860442764926e-05, + "loss": 3.4722, + "step": 1585152 + }, + { + "epoch": 0.02, + "learning_rate": 2.4040218480138735e-05, + "loss": 3.473, + "step": 1585664 + }, + { + "epoch": 0.02, + "learning_rate": 2.4031832532628215e-05, + "loss": 3.4695, + "step": 1586176 + }, + { + "epoch": 0.02, + "learning_rate": 2.4023446585117695e-05, + "loss": 3.464, + "step": 1586688 + }, + { + "epoch": 0.02, + "learning_rate": 2.4015077016410908e-05, + "loss": 3.4775, + "step": 1587200 + }, + { + "epoch": 0.02, + "learning_rate": 2.4006691068900384e-05, + "loss": 3.4683, + "step": 1587712 + }, + { + "epoch": 0.02, + "learning_rate": 2.3998305121389868e-05, + "loss": 3.4593, + "step": 1588224 + }, + { + "epoch": 0.02, + "learning_rate": 2.3989919173879348e-05, + "loss": 3.4747, + "step": 1588736 + }, + { + "epoch": 0.02, + "learning_rate": 2.3981533226368828e-05, + "loss": 3.4602, + "step": 1589248 + }, + { + "epoch": 0.02, + "learning_rate": 2.3973147278858308e-05, + "loss": 3.4715, + "step": 1589760 + }, + { + "epoch": 0.02, + "learning_rate": 2.3964761331347788e-05, + "loss": 3.4574, + "step": 1590272 + }, + { + "epoch": 0.02, + "learning_rate": 2.3956375383837268e-05, + "loss": 3.4687, + "step": 1590784 + }, + { + "epoch": 0.02, + "learning_rate": 2.3948005815130477e-05, + "loss": 3.4584, + "step": 1591296 + }, + { + "epoch": 0.02, + "learning_rate": 2.393961986761996e-05, + "loss": 3.4568, + "step": 1591808 + }, + { + "epoch": 0.02, + "learning_rate": 2.393123392010944e-05, + "loss": 3.4627, + "step": 1592320 + }, + { + "epoch": 0.02, + "learning_rate": 2.3922847972598917e-05, + "loss": 3.4704, + "step": 1592832 + }, + { + "epoch": 0.02, + "learning_rate": 2.391447840389213e-05, + "loss": 3.4645, + "step": 1593344 + }, + { + "epoch": 0.02, + "learning_rate": 2.390609245638161e-05, + "loss": 3.4709, + "step": 1593856 + }, + { + "epoch": 0.02, + "learning_rate": 2.389770650887109e-05, + "loss": 3.4588, + "step": 1594368 + }, + { + "epoch": 0.02, + "learning_rate": 2.388932056136057e-05, + "loss": 3.4697, + "step": 1594880 + }, + { + "epoch": 0.02, + "learning_rate": 2.388093461385005e-05, + "loss": 3.473, + "step": 1595392 + }, + { + "epoch": 0.02, + "learning_rate": 2.387254866633953e-05, + "loss": 3.4701, + "step": 1595904 + }, + { + "epoch": 0.02, + "learning_rate": 2.386416271882901e-05, + "loss": 3.4644, + "step": 1596416 + }, + { + "epoch": 0.02, + "learning_rate": 2.3855793150122218e-05, + "loss": 3.4723, + "step": 1596928 + }, + { + "epoch": 0.02, + "learning_rate": 2.3847407202611698e-05, + "loss": 3.4661, + "step": 1597440 + }, + { + "epoch": 0.02, + "learning_rate": 2.3839021255101178e-05, + "loss": 3.4742, + "step": 1597952 + }, + { + "epoch": 0.02, + "learning_rate": 2.383063530759066e-05, + "loss": 3.4603, + "step": 1598464 + }, + { + "epoch": 0.02, + "learning_rate": 2.382226573888387e-05, + "loss": 3.4692, + "step": 1598976 + }, + { + "epoch": 0.02, + "learning_rate": 2.381387979137335e-05, + "loss": 3.4646, + "step": 1599488 + }, + { + "epoch": 0.02, + "learning_rate": 2.380549384386283e-05, + "loss": 3.4636, + "step": 1600000 + }, + { + "epoch": 0.02, + "learning_rate": 2.379710789635231e-05, + "loss": 3.4691, + "step": 1600512 + }, + { + "epoch": 0.02, + "learning_rate": 2.3788738327645523e-05, + "loss": 3.4688, + "step": 1601024 + }, + { + "epoch": 0.02, + "learning_rate": 2.3780352380135002e-05, + "loss": 3.4695, + "step": 1601536 + }, + { + "epoch": 0.02, + "learning_rate": 2.3771966432624482e-05, + "loss": 3.4544, + "step": 1602048 + }, + { + "epoch": 0.02, + "learning_rate": 2.3763580485113962e-05, + "loss": 3.4699, + "step": 1602560 + }, + { + "epoch": 0.03, + "eval_loss": 3.8529348373413086, + "eval_runtime": 305.0371, + "eval_samples_per_second": 1250.966, + "eval_steps_per_second": 39.094, + "step": 1602720 + }, + { + "epoch": 0.0, + "learning_rate": 2.3755194537603442e-05, + "loss": 3.459, + "step": 1603072 + }, + { + "epoch": 0.0, + "learning_rate": 2.3746808590092922e-05, + "loss": 3.4561, + "step": 1603584 + }, + { + "epoch": 0.0, + "learning_rate": 2.37384226425824e-05, + "loss": 3.4723, + "step": 1604096 + }, + { + "epoch": 0.0, + "learning_rate": 2.3730036695071882e-05, + "loss": 3.4617, + "step": 1604608 + }, + { + "epoch": 0.0, + "learning_rate": 2.3721667126365095e-05, + "loss": 3.4794, + "step": 1605120 + }, + { + "epoch": 0.0, + "learning_rate": 2.371328117885457e-05, + "loss": 3.465, + "step": 1605632 + }, + { + "epoch": 0.0, + "learning_rate": 2.370489523134405e-05, + "loss": 3.4527, + "step": 1606144 + }, + { + "epoch": 0.0, + "learning_rate": 2.369650928383353e-05, + "loss": 3.4533, + "step": 1606656 + }, + { + "epoch": 0.0, + "learning_rate": 2.3688139715126744e-05, + "loss": 3.4608, + "step": 1607168 + }, + { + "epoch": 0.0, + "learning_rate": 2.3679753767616224e-05, + "loss": 3.4659, + "step": 1607680 + }, + { + "epoch": 0.0, + "learning_rate": 2.3671367820105704e-05, + "loss": 3.4594, + "step": 1608192 + }, + { + "epoch": 0.0, + "learning_rate": 2.3662981872595184e-05, + "loss": 3.4646, + "step": 1608704 + }, + { + "epoch": 0.0, + "learning_rate": 2.3654628682692125e-05, + "loss": 3.4562, + "step": 1609216 + }, + { + "epoch": 0.0, + "learning_rate": 2.3646242735181605e-05, + "loss": 3.458, + "step": 1609728 + }, + { + "epoch": 0.0, + "learning_rate": 2.3637856787671085e-05, + "loss": 3.4629, + "step": 1610240 + }, + { + "epoch": 0.0, + "learning_rate": 2.362947084016057e-05, + "loss": 3.4537, + "step": 1610752 + }, + { + "epoch": 0.0, + "learning_rate": 2.3621084892650045e-05, + "loss": 3.4512, + "step": 1611264 + }, + { + "epoch": 0.0, + "learning_rate": 2.3612698945139525e-05, + "loss": 3.4614, + "step": 1611776 + }, + { + "epoch": 0.0, + "learning_rate": 2.3604312997629005e-05, + "loss": 3.4598, + "step": 1612288 + }, + { + "epoch": 0.0, + "learning_rate": 2.3595927050118485e-05, + "loss": 3.4716, + "step": 1612800 + }, + { + "epoch": 0.0, + "learning_rate": 2.3587557481411694e-05, + "loss": 3.4635, + "step": 1613312 + }, + { + "epoch": 0.0, + "learning_rate": 2.3579171533901177e-05, + "loss": 3.4624, + "step": 1613824 + }, + { + "epoch": 0.0, + "learning_rate": 2.3570785586390657e-05, + "loss": 3.4627, + "step": 1614336 + }, + { + "epoch": 0.0, + "learning_rate": 2.3562399638880137e-05, + "loss": 3.4671, + "step": 1614848 + }, + { + "epoch": 0.0, + "learning_rate": 2.3554030070173346e-05, + "loss": 3.4522, + "step": 1615360 + }, + { + "epoch": 0.0, + "learning_rate": 2.3545644122662826e-05, + "loss": 3.47, + "step": 1615872 + }, + { + "epoch": 0.0, + "learning_rate": 2.3537258175152306e-05, + "loss": 3.4546, + "step": 1616384 + }, + { + "epoch": 0.0, + "learning_rate": 2.3528872227641786e-05, + "loss": 3.4563, + "step": 1616896 + }, + { + "epoch": 0.0, + "learning_rate": 2.3520502658935e-05, + "loss": 3.4529, + "step": 1617408 + }, + { + "epoch": 0.0, + "learning_rate": 2.351211671142448e-05, + "loss": 3.4565, + "step": 1617920 + }, + { + "epoch": 0.01, + "learning_rate": 2.350373076391396e-05, + "loss": 3.4662, + "step": 1618432 + }, + { + "epoch": 0.01, + "learning_rate": 2.349534481640344e-05, + "loss": 3.4593, + "step": 1618944 + }, + { + "epoch": 0.01, + "learning_rate": 2.3486975247696648e-05, + "loss": 3.469, + "step": 1619456 + }, + { + "epoch": 0.01, + "learning_rate": 2.347858930018613e-05, + "loss": 3.468, + "step": 1619968 + }, + { + "epoch": 0.01, + "learning_rate": 2.347020335267561e-05, + "loss": 3.4576, + "step": 1620480 + }, + { + "epoch": 0.01, + "learning_rate": 2.346183378396882e-05, + "loss": 3.4642, + "step": 1620992 + }, + { + "epoch": 0.01, + "learning_rate": 2.34534478364583e-05, + "loss": 3.4591, + "step": 1621504 + }, + { + "epoch": 0.01, + "learning_rate": 2.344506188894778e-05, + "loss": 3.4598, + "step": 1622016 + }, + { + "epoch": 0.01, + "learning_rate": 2.343667594143726e-05, + "loss": 3.4542, + "step": 1622528 + }, + { + "epoch": 0.01, + "learning_rate": 2.3428306372730472e-05, + "loss": 3.4573, + "step": 1623040 + }, + { + "epoch": 0.01, + "learning_rate": 2.3419920425219952e-05, + "loss": 3.4613, + "step": 1623552 + }, + { + "epoch": 0.01, + "learning_rate": 2.3411534477709432e-05, + "loss": 3.4691, + "step": 1624064 + }, + { + "epoch": 0.01, + "learning_rate": 2.3403148530198912e-05, + "loss": 3.4589, + "step": 1624576 + }, + { + "epoch": 0.01, + "learning_rate": 2.339477896149212e-05, + "loss": 3.4602, + "step": 1625088 + }, + { + "epoch": 0.01, + "learning_rate": 2.33863930139816e-05, + "loss": 3.4688, + "step": 1625600 + }, + { + "epoch": 0.01, + "learning_rate": 2.3378007066471085e-05, + "loss": 3.4629, + "step": 1626112 + }, + { + "epoch": 0.01, + "learning_rate": 2.3369621118960565e-05, + "loss": 3.4628, + "step": 1626624 + }, + { + "epoch": 0.01, + "learning_rate": 2.3361251550253774e-05, + "loss": 3.4537, + "step": 1627136 + }, + { + "epoch": 0.01, + "learning_rate": 2.3352865602743254e-05, + "loss": 3.4363, + "step": 1627648 + }, + { + "epoch": 0.01, + "learning_rate": 2.3344479655232734e-05, + "loss": 3.4671, + "step": 1628160 + }, + { + "epoch": 0.01, + "learning_rate": 2.3336093707722214e-05, + "loss": 3.462, + "step": 1628672 + }, + { + "epoch": 0.01, + "learning_rate": 2.3327724139015426e-05, + "loss": 3.457, + "step": 1629184 + }, + { + "epoch": 0.01, + "learning_rate": 2.3319338191504906e-05, + "loss": 3.4467, + "step": 1629696 + }, + { + "epoch": 0.01, + "learning_rate": 2.3310952243994386e-05, + "loss": 3.4423, + "step": 1630208 + }, + { + "epoch": 0.01, + "learning_rate": 2.3302566296483866e-05, + "loss": 3.4425, + "step": 1630720 + }, + { + "epoch": 0.01, + "learning_rate": 2.3294196727777075e-05, + "loss": 3.458, + "step": 1631232 + }, + { + "epoch": 0.01, + "learning_rate": 2.3285810780266555e-05, + "loss": 3.4525, + "step": 1631744 + }, + { + "epoch": 0.01, + "learning_rate": 2.3277424832756038e-05, + "loss": 3.4563, + "step": 1632256 + }, + { + "epoch": 0.01, + "learning_rate": 2.3269038885245518e-05, + "loss": 3.4611, + "step": 1632768 + }, + { + "epoch": 0.01, + "learning_rate": 2.3260669316538727e-05, + "loss": 3.4486, + "step": 1633280 + }, + { + "epoch": 0.01, + "learning_rate": 2.3252283369028207e-05, + "loss": 3.4535, + "step": 1633792 + }, + { + "epoch": 0.01, + "learning_rate": 2.3243897421517687e-05, + "loss": 3.4585, + "step": 1634304 + }, + { + "epoch": 0.01, + "learning_rate": 2.3235511474007167e-05, + "loss": 3.4382, + "step": 1634816 + }, + { + "epoch": 0.01, + "learning_rate": 2.322714190530038e-05, + "loss": 3.4472, + "step": 1635328 + }, + { + "epoch": 0.01, + "learning_rate": 2.321875595778986e-05, + "loss": 3.4557, + "step": 1635840 + }, + { + "epoch": 0.01, + "learning_rate": 2.321037001027934e-05, + "loss": 3.4626, + "step": 1636352 + }, + { + "epoch": 0.01, + "learning_rate": 2.320198406276882e-05, + "loss": 3.4397, + "step": 1636864 + }, + { + "epoch": 0.01, + "learning_rate": 2.319361449406203e-05, + "loss": 3.4529, + "step": 1637376 + }, + { + "epoch": 0.01, + "learning_rate": 2.318522854655151e-05, + "loss": 3.4439, + "step": 1637888 + }, + { + "epoch": 0.01, + "learning_rate": 2.3176842599040992e-05, + "loss": 3.4615, + "step": 1638400 + }, + { + "epoch": 0.01, + "learning_rate": 2.316845665153047e-05, + "loss": 3.4596, + "step": 1638912 + }, + { + "epoch": 0.01, + "learning_rate": 2.316008708282368e-05, + "loss": 3.4566, + "step": 1639424 + }, + { + "epoch": 0.01, + "learning_rate": 2.315171751411689e-05, + "loss": 3.4697, + "step": 1639936 + }, + { + "epoch": 0.01, + "learning_rate": 2.314333156660637e-05, + "loss": 3.4638, + "step": 1640448 + }, + { + "epoch": 0.01, + "learning_rate": 2.3134945619095853e-05, + "loss": 3.4809, + "step": 1640960 + }, + { + "epoch": 0.01, + "learning_rate": 2.3126559671585333e-05, + "loss": 3.455, + "step": 1641472 + }, + { + "epoch": 0.01, + "learning_rate": 2.3118173724074813e-05, + "loss": 3.4593, + "step": 1641984 + }, + { + "epoch": 0.01, + "learning_rate": 2.3109787776564293e-05, + "loss": 3.4579, + "step": 1642496 + }, + { + "epoch": 0.01, + "learning_rate": 2.310140182905377e-05, + "loss": 3.4516, + "step": 1643008 + }, + { + "epoch": 0.01, + "learning_rate": 2.309301588154325e-05, + "loss": 3.4667, + "step": 1643520 + }, + { + "epoch": 0.01, + "learning_rate": 2.3084646312836462e-05, + "loss": 3.4567, + "step": 1644032 + }, + { + "epoch": 0.01, + "learning_rate": 2.3076260365325942e-05, + "loss": 3.4627, + "step": 1644544 + }, + { + "epoch": 0.01, + "learning_rate": 2.3067874417815422e-05, + "loss": 3.4589, + "step": 1645056 + }, + { + "epoch": 0.01, + "learning_rate": 2.3059488470304902e-05, + "loss": 3.4463, + "step": 1645568 + }, + { + "epoch": 0.01, + "learning_rate": 2.3051118901598115e-05, + "loss": 3.4551, + "step": 1646080 + }, + { + "epoch": 0.01, + "learning_rate": 2.304273295408759e-05, + "loss": 3.4495, + "step": 1646592 + }, + { + "epoch": 0.01, + "learning_rate": 2.303434700657707e-05, + "loss": 3.4691, + "step": 1647104 + }, + { + "epoch": 0.01, + "learning_rate": 2.3025961059066554e-05, + "loss": 3.4587, + "step": 1647616 + }, + { + "epoch": 0.01, + "learning_rate": 2.3017591490359767e-05, + "loss": 3.4458, + "step": 1648128 + }, + { + "epoch": 0.02, + "learning_rate": 2.3009221921652976e-05, + "loss": 3.4638, + "step": 1648640 + }, + { + "epoch": 0.02, + "learning_rate": 2.3000835974142456e-05, + "loss": 3.4539, + "step": 1649152 + }, + { + "epoch": 0.02, + "learning_rate": 2.2992450026631936e-05, + "loss": 3.4475, + "step": 1649664 + }, + { + "epoch": 0.02, + "learning_rate": 2.2984064079121416e-05, + "loss": 3.4524, + "step": 1650176 + }, + { + "epoch": 0.02, + "learning_rate": 2.2975678131610896e-05, + "loss": 3.4663, + "step": 1650688 + }, + { + "epoch": 0.02, + "learning_rate": 2.2967292184100376e-05, + "loss": 3.4579, + "step": 1651200 + }, + { + "epoch": 0.02, + "learning_rate": 2.2958906236589856e-05, + "loss": 3.463, + "step": 1651712 + }, + { + "epoch": 0.02, + "learning_rate": 2.2950520289079336e-05, + "loss": 3.4448, + "step": 1652224 + }, + { + "epoch": 0.02, + "learning_rate": 2.2942150720372545e-05, + "loss": 3.4624, + "step": 1652736 + }, + { + "epoch": 0.02, + "learning_rate": 2.2933764772862025e-05, + "loss": 3.4524, + "step": 1653248 + }, + { + "epoch": 0.02, + "learning_rate": 2.2925378825351508e-05, + "loss": 3.4639, + "step": 1653760 + }, + { + "epoch": 0.02, + "learning_rate": 2.2916992877840988e-05, + "loss": 3.4636, + "step": 1654272 + }, + { + "epoch": 0.02, + "learning_rate": 2.2908623309134197e-05, + "loss": 3.4562, + "step": 1654784 + }, + { + "epoch": 0.02, + "learning_rate": 2.2900237361623677e-05, + "loss": 3.4562, + "step": 1655296 + }, + { + "epoch": 0.02, + "learning_rate": 2.2891867792916886e-05, + "loss": 3.4654, + "step": 1655808 + }, + { + "epoch": 0.02, + "learning_rate": 2.288348184540637e-05, + "loss": 3.4402, + "step": 1656320 + }, + { + "epoch": 0.02, + "learning_rate": 2.287509589789585e-05, + "loss": 3.4501, + "step": 1656832 + }, + { + "epoch": 0.02, + "learning_rate": 2.286670995038533e-05, + "loss": 3.4449, + "step": 1657344 + }, + { + "epoch": 0.02, + "learning_rate": 2.285832400287481e-05, + "loss": 3.4591, + "step": 1657856 + }, + { + "epoch": 0.02, + "learning_rate": 2.284993805536429e-05, + "loss": 3.4426, + "step": 1658368 + }, + { + "epoch": 0.02, + "learning_rate": 2.284155210785377e-05, + "loss": 3.4535, + "step": 1658880 + }, + { + "epoch": 0.02, + "learning_rate": 2.2833166160343246e-05, + "loss": 3.4501, + "step": 1659392 + }, + { + "epoch": 0.02, + "learning_rate": 2.2824796591636462e-05, + "loss": 3.453, + "step": 1659904 + }, + { + "epoch": 0.02, + "learning_rate": 2.281642702292967e-05, + "loss": 3.4553, + "step": 1660416 + }, + { + "epoch": 0.02, + "learning_rate": 2.280804107541915e-05, + "loss": 3.4482, + "step": 1660928 + }, + { + "epoch": 0.02, + "learning_rate": 2.279965512790863e-05, + "loss": 3.4617, + "step": 1661440 + }, + { + "epoch": 0.02, + "learning_rate": 2.279126918039811e-05, + "loss": 3.4593, + "step": 1661952 + }, + { + "epoch": 0.02, + "learning_rate": 2.278288323288759e-05, + "loss": 3.4588, + "step": 1662464 + }, + { + "epoch": 0.02, + "learning_rate": 2.277449728537707e-05, + "loss": 3.4511, + "step": 1662976 + }, + { + "epoch": 0.02, + "learning_rate": 2.2766127716670283e-05, + "loss": 3.4635, + "step": 1663488 + }, + { + "epoch": 0.02, + "learning_rate": 2.2757741769159763e-05, + "loss": 3.4641, + "step": 1664000 + }, + { + "epoch": 0.02, + "learning_rate": 2.2749355821649243e-05, + "loss": 3.4442, + "step": 1664512 + }, + { + "epoch": 0.02, + "learning_rate": 2.274096987413872e-05, + "loss": 3.467, + "step": 1665024 + }, + { + "epoch": 0.02, + "learning_rate": 2.27325839266282e-05, + "loss": 3.4445, + "step": 1665536 + }, + { + "epoch": 0.02, + "learning_rate": 2.272419797911768e-05, + "loss": 3.4612, + "step": 1666048 + }, + { + "epoch": 0.02, + "learning_rate": 2.2715812031607163e-05, + "loss": 3.442, + "step": 1666560 + }, + { + "epoch": 0.02, + "learning_rate": 2.2707426084096643e-05, + "loss": 3.4588, + "step": 1667072 + }, + { + "epoch": 0.02, + "learning_rate": 2.2699056515389852e-05, + "loss": 3.4469, + "step": 1667584 + }, + { + "epoch": 0.02, + "learning_rate": 2.2690670567879332e-05, + "loss": 3.4488, + "step": 1668096 + }, + { + "epoch": 0.02, + "learning_rate": 2.2682284620368812e-05, + "loss": 3.4469, + "step": 1668608 + }, + { + "epoch": 0.02, + "learning_rate": 2.2673898672858292e-05, + "loss": 3.4626, + "step": 1669120 + }, + { + "epoch": 0.02, + "learning_rate": 2.2665529104151504e-05, + "loss": 3.4519, + "step": 1669632 + }, + { + "epoch": 0.02, + "learning_rate": 2.2657143156640984e-05, + "loss": 3.4607, + "step": 1670144 + }, + { + "epoch": 0.02, + "learning_rate": 2.2648757209130464e-05, + "loss": 3.4495, + "step": 1670656 + }, + { + "epoch": 0.02, + "learning_rate": 2.2640371261619944e-05, + "loss": 3.4609, + "step": 1671168 + }, + { + "epoch": 0.02, + "learning_rate": 2.2632001692913153e-05, + "loss": 3.4602, + "step": 1671680 + }, + { + "epoch": 0.02, + "learning_rate": 2.2623615745402633e-05, + "loss": 3.4593, + "step": 1672192 + }, + { + "epoch": 0.02, + "learning_rate": 2.2615229797892117e-05, + "loss": 3.4551, + "step": 1672704 + }, + { + "epoch": 0.02, + "learning_rate": 2.2606843850381597e-05, + "loss": 3.4573, + "step": 1673216 + }, + { + "epoch": 0.02, + "learning_rate": 2.2598474281674806e-05, + "loss": 3.4553, + "step": 1673728 + }, + { + "epoch": 0.02, + "learning_rate": 2.2590088334164286e-05, + "loss": 3.4622, + "step": 1674240 + }, + { + "epoch": 0.02, + "learning_rate": 2.2581702386653766e-05, + "loss": 3.4509, + "step": 1674752 + }, + { + "epoch": 0.02, + "learning_rate": 2.2573316439143246e-05, + "loss": 3.4587, + "step": 1675264 + }, + { + "epoch": 0.02, + "learning_rate": 2.2564946870436458e-05, + "loss": 3.454, + "step": 1675776 + }, + { + "epoch": 0.02, + "learning_rate": 2.2556560922925938e-05, + "loss": 3.4542, + "step": 1676288 + }, + { + "epoch": 0.02, + "learning_rate": 2.2548174975415418e-05, + "loss": 3.4573, + "step": 1676800 + }, + { + "epoch": 0.02, + "learning_rate": 2.2539789027904898e-05, + "loss": 3.452, + "step": 1677312 + }, + { + "epoch": 0.02, + "learning_rate": 2.2531419459198107e-05, + "loss": 3.4651, + "step": 1677824 + }, + { + "epoch": 0.02, + "learning_rate": 2.2523033511687587e-05, + "loss": 3.4398, + "step": 1678336 + }, + { + "epoch": 0.02, + "learning_rate": 2.251464756417707e-05, + "loss": 3.4611, + "step": 1678848 + }, + { + "epoch": 0.03, + "eval_loss": 3.8530433177948, + "eval_runtime": 303.2729, + "eval_samples_per_second": 1258.243, + "eval_steps_per_second": 39.321, + "step": 1679040 + }, + { + "epoch": 1.0, + "learning_rate": 2.2506261616666547e-05, + "loss": 3.4515, + "step": 1679360 + }, + { + "epoch": 1.0, + "learning_rate": 2.249789204795976e-05, + "loss": 3.4423, + "step": 1679872 + }, + { + "epoch": 1.0, + "learning_rate": 2.248950610044924e-05, + "loss": 3.4578, + "step": 1680384 + }, + { + "epoch": 1.0, + "learning_rate": 2.248112015293872e-05, + "loss": 3.4523, + "step": 1680896 + }, + { + "epoch": 1.0, + "learning_rate": 2.24727342054282e-05, + "loss": 3.4667, + "step": 1681408 + }, + { + "epoch": 1.0, + "learning_rate": 2.246436463672141e-05, + "loss": 3.452, + "step": 1681920 + }, + { + "epoch": 1.0, + "learning_rate": 2.245597868921089e-05, + "loss": 3.4439, + "step": 1682432 + }, + { + "epoch": 1.0, + "learning_rate": 2.244759274170037e-05, + "loss": 3.4377, + "step": 1682944 + }, + { + "epoch": 1.0, + "learning_rate": 2.243922317299358e-05, + "loss": 3.4527, + "step": 1683456 + }, + { + "epoch": 1.0, + "learning_rate": 2.243083722548306e-05, + "loss": 3.4556, + "step": 1683968 + }, + { + "epoch": 1.0, + "learning_rate": 2.242245127797254e-05, + "loss": 3.4466, + "step": 1684480 + }, + { + "epoch": 1.0, + "learning_rate": 2.241406533046202e-05, + "loss": 3.4491, + "step": 1684992 + }, + { + "epoch": 1.0, + "learning_rate": 2.24056793829515e-05, + "loss": 3.4519, + "step": 1685504 + }, + { + "epoch": 1.0, + "learning_rate": 2.2397309814244713e-05, + "loss": 3.4436, + "step": 1686016 + }, + { + "epoch": 1.0, + "learning_rate": 2.2388923866734193e-05, + "loss": 3.4518, + "step": 1686528 + }, + { + "epoch": 1.0, + "learning_rate": 2.238053791922367e-05, + "loss": 3.4375, + "step": 1687040 + }, + { + "epoch": 1.0, + "learning_rate": 2.237215197171315e-05, + "loss": 3.4439, + "step": 1687552 + }, + { + "epoch": 1.0, + "learning_rate": 2.2363766024202633e-05, + "loss": 3.449, + "step": 1688064 + }, + { + "epoch": 1.0, + "learning_rate": 2.2355380076692113e-05, + "loss": 3.4488, + "step": 1688576 + }, + { + "epoch": 1.0, + "learning_rate": 2.2346994129181593e-05, + "loss": 3.4595, + "step": 1689088 + }, + { + "epoch": 1.0, + "learning_rate": 2.2338608181671073e-05, + "loss": 3.4569, + "step": 1689600 + }, + { + "epoch": 1.0, + "learning_rate": 2.2330238612964282e-05, + "loss": 3.4498, + "step": 1690112 + }, + { + "epoch": 1.0, + "learning_rate": 2.2321852665453762e-05, + "loss": 3.4498, + "step": 1690624 + }, + { + "epoch": 1.0, + "learning_rate": 2.231346671794324e-05, + "loss": 3.4583, + "step": 1691136 + }, + { + "epoch": 1.0, + "learning_rate": 2.2305080770432725e-05, + "loss": 3.4383, + "step": 1691648 + }, + { + "epoch": 1.0, + "learning_rate": 2.2296711201725934e-05, + "loss": 3.4626, + "step": 1692160 + }, + { + "epoch": 1.0, + "learning_rate": 2.2288325254215414e-05, + "loss": 3.4439, + "step": 1692672 + }, + { + "epoch": 1.0, + "learning_rate": 2.2279939306704894e-05, + "loss": 3.4418, + "step": 1693184 + }, + { + "epoch": 1.0, + "learning_rate": 2.2271553359194374e-05, + "loss": 3.4417, + "step": 1693696 + }, + { + "epoch": 1.0, + "learning_rate": 2.2263183790487586e-05, + "loss": 3.4479, + "step": 1694208 + }, + { + "epoch": 1.01, + "learning_rate": 2.2254797842977066e-05, + "loss": 3.4526, + "step": 1694720 + }, + { + "epoch": 1.01, + "learning_rate": 2.2246411895466546e-05, + "loss": 3.4504, + "step": 1695232 + }, + { + "epoch": 1.01, + "learning_rate": 2.2238025947956026e-05, + "loss": 3.4547, + "step": 1695744 + }, + { + "epoch": 1.01, + "learning_rate": 2.2229656379249235e-05, + "loss": 3.4578, + "step": 1696256 + }, + { + "epoch": 1.01, + "learning_rate": 2.2221270431738715e-05, + "loss": 3.4466, + "step": 1696768 + }, + { + "epoch": 1.01, + "learning_rate": 2.2212884484228195e-05, + "loss": 3.4524, + "step": 1697280 + }, + { + "epoch": 1.01, + "learning_rate": 2.2204498536717675e-05, + "loss": 3.4508, + "step": 1697792 + }, + { + "epoch": 1.01, + "learning_rate": 2.2196128968010888e-05, + "loss": 3.4463, + "step": 1698304 + }, + { + "epoch": 1.01, + "learning_rate": 2.2187743020500368e-05, + "loss": 3.4437, + "step": 1698816 + }, + { + "epoch": 1.01, + "learning_rate": 2.2179357072989848e-05, + "loss": 3.4486, + "step": 1699328 + }, + { + "epoch": 1.01, + "learning_rate": 2.2170971125479324e-05, + "loss": 3.4458, + "step": 1699840 + }, + { + "epoch": 1.01, + "learning_rate": 2.216260155677254e-05, + "loss": 3.458, + "step": 1700352 + }, + { + "epoch": 1.01, + "learning_rate": 2.215421560926202e-05, + "loss": 3.4473, + "step": 1700864 + }, + { + "epoch": 1.01, + "learning_rate": 2.2145829661751497e-05, + "loss": 3.4497, + "step": 1701376 + }, + { + "epoch": 1.01, + "learning_rate": 2.213746009304471e-05, + "loss": 3.4585, + "step": 1701888 + }, + { + "epoch": 1.01, + "learning_rate": 2.212907414553419e-05, + "loss": 3.4493, + "step": 1702400 + }, + { + "epoch": 1.01, + "learning_rate": 2.212068819802367e-05, + "loss": 3.4523, + "step": 1702912 + }, + { + "epoch": 1.01, + "learning_rate": 2.211230225051315e-05, + "loss": 3.446, + "step": 1703424 + }, + { + "epoch": 1.01, + "learning_rate": 2.210391630300263e-05, + "loss": 3.4183, + "step": 1703936 + }, + { + "epoch": 1.01, + "learning_rate": 2.209553035549211e-05, + "loss": 3.4624, + "step": 1704448 + }, + { + "epoch": 1.01, + "learning_rate": 2.208714440798159e-05, + "loss": 3.4485, + "step": 1704960 + }, + { + "epoch": 1.01, + "learning_rate": 2.207875846047107e-05, + "loss": 3.4475, + "step": 1705472 + }, + { + "epoch": 1.01, + "learning_rate": 2.2070388891764278e-05, + "loss": 3.4345, + "step": 1705984 + }, + { + "epoch": 1.01, + "learning_rate": 2.2062002944253758e-05, + "loss": 3.4269, + "step": 1706496 + }, + { + "epoch": 1.01, + "learning_rate": 2.205361699674324e-05, + "loss": 3.4353, + "step": 1707008 + }, + { + "epoch": 1.01, + "learning_rate": 2.204524742803645e-05, + "loss": 3.4463, + "step": 1707520 + }, + { + "epoch": 1.01, + "learning_rate": 2.203686148052593e-05, + "loss": 3.4414, + "step": 1708032 + }, + { + "epoch": 1.01, + "learning_rate": 2.202847553301541e-05, + "loss": 3.4429, + "step": 1708544 + }, + { + "epoch": 1.01, + "learning_rate": 2.202008958550489e-05, + "loss": 3.4505, + "step": 1709056 + }, + { + "epoch": 1.01, + "learning_rate": 2.2011720016798103e-05, + "loss": 3.4368, + "step": 1709568 + }, + { + "epoch": 1.01, + "learning_rate": 2.2003334069287583e-05, + "loss": 3.4397, + "step": 1710080 + }, + { + "epoch": 1.01, + "learning_rate": 2.1994948121777063e-05, + "loss": 3.4509, + "step": 1710592 + }, + { + "epoch": 1.01, + "learning_rate": 2.1986562174266543e-05, + "loss": 3.4252, + "step": 1711104 + }, + { + "epoch": 1.01, + "learning_rate": 2.197819260555975e-05, + "loss": 3.4366, + "step": 1711616 + }, + { + "epoch": 1.01, + "learning_rate": 2.196980665804923e-05, + "loss": 3.4459, + "step": 1712128 + }, + { + "epoch": 1.01, + "learning_rate": 2.196142071053871e-05, + "loss": 3.4521, + "step": 1712640 + }, + { + "epoch": 1.01, + "learning_rate": 2.1953034763028195e-05, + "loss": 3.4273, + "step": 1713152 + }, + { + "epoch": 1.01, + "learning_rate": 2.1944665194321404e-05, + "loss": 3.4438, + "step": 1713664 + }, + { + "epoch": 1.01, + "learning_rate": 2.1936279246810884e-05, + "loss": 3.4291, + "step": 1714176 + }, + { + "epoch": 1.01, + "learning_rate": 2.1927893299300364e-05, + "loss": 3.4506, + "step": 1714688 + }, + { + "epoch": 1.01, + "learning_rate": 2.1919507351789844e-05, + "loss": 3.4486, + "step": 1715200 + }, + { + "epoch": 1.01, + "learning_rate": 2.1911137783083056e-05, + "loss": 3.445, + "step": 1715712 + }, + { + "epoch": 1.01, + "learning_rate": 2.1902751835572536e-05, + "loss": 3.4539, + "step": 1716224 + }, + { + "epoch": 1.01, + "learning_rate": 2.1894382266865745e-05, + "loss": 3.4546, + "step": 1716736 + }, + { + "epoch": 1.01, + "learning_rate": 2.1885996319355225e-05, + "loss": 3.4689, + "step": 1717248 + }, + { + "epoch": 1.01, + "learning_rate": 2.1877610371844705e-05, + "loss": 3.445, + "step": 1717760 + }, + { + "epoch": 1.01, + "learning_rate": 2.1869224424334185e-05, + "loss": 3.4494, + "step": 1718272 + }, + { + "epoch": 1.01, + "learning_rate": 2.1860838476823665e-05, + "loss": 3.4479, + "step": 1718784 + }, + { + "epoch": 1.01, + "learning_rate": 2.185245252931315e-05, + "loss": 3.4382, + "step": 1719296 + }, + { + "epoch": 1.01, + "learning_rate": 2.1844066581802625e-05, + "loss": 3.4498, + "step": 1719808 + }, + { + "epoch": 1.01, + "learning_rate": 2.1835697013095838e-05, + "loss": 3.4495, + "step": 1720320 + }, + { + "epoch": 1.01, + "learning_rate": 2.1827311065585318e-05, + "loss": 3.4518, + "step": 1720832 + }, + { + "epoch": 1.01, + "learning_rate": 2.1818925118074798e-05, + "loss": 3.455, + "step": 1721344 + }, + { + "epoch": 1.01, + "learning_rate": 2.1810539170564277e-05, + "loss": 3.4364, + "step": 1721856 + }, + { + "epoch": 1.01, + "learning_rate": 2.180216960185749e-05, + "loss": 3.4387, + "step": 1722368 + }, + { + "epoch": 1.01, + "learning_rate": 2.179378365434697e-05, + "loss": 3.4413, + "step": 1722880 + }, + { + "epoch": 1.01, + "learning_rate": 2.178539770683645e-05, + "loss": 3.4596, + "step": 1723392 + }, + { + "epoch": 1.01, + "learning_rate": 2.1777011759325926e-05, + "loss": 3.4451, + "step": 1723904 + }, + { + "epoch": 1.01, + "learning_rate": 2.176864219061914e-05, + "loss": 3.4388, + "step": 1724416 + }, + { + "epoch": 1.02, + "learning_rate": 2.176027262191235e-05, + "loss": 3.4403, + "step": 1724928 + }, + { + "epoch": 1.02, + "learning_rate": 2.175188667440183e-05, + "loss": 3.4498, + "step": 1725440 + }, + { + "epoch": 1.02, + "learning_rate": 2.174350072689131e-05, + "loss": 3.4374, + "step": 1725952 + }, + { + "epoch": 1.02, + "learning_rate": 2.173511477938079e-05, + "loss": 3.4423, + "step": 1726464 + }, + { + "epoch": 1.02, + "learning_rate": 2.172672883187027e-05, + "loss": 3.4582, + "step": 1726976 + }, + { + "epoch": 1.02, + "learning_rate": 2.1718342884359748e-05, + "loss": 3.4481, + "step": 1727488 + }, + { + "epoch": 1.02, + "learning_rate": 2.170995693684923e-05, + "loss": 3.4491, + "step": 1728000 + }, + { + "epoch": 1.02, + "learning_rate": 2.170157098933871e-05, + "loss": 3.4339, + "step": 1728512 + }, + { + "epoch": 1.02, + "learning_rate": 2.1693201420631924e-05, + "loss": 3.4499, + "step": 1729024 + }, + { + "epoch": 1.02, + "learning_rate": 2.16848154731214e-05, + "loss": 3.4407, + "step": 1729536 + }, + { + "epoch": 1.02, + "learning_rate": 2.167642952561088e-05, + "loss": 3.4514, + "step": 1730048 + }, + { + "epoch": 1.02, + "learning_rate": 2.166804357810036e-05, + "loss": 3.4513, + "step": 1730560 + }, + { + "epoch": 1.02, + "learning_rate": 2.1659674009393573e-05, + "loss": 3.4504, + "step": 1731072 + }, + { + "epoch": 1.02, + "learning_rate": 2.1651288061883053e-05, + "loss": 3.4464, + "step": 1731584 + }, + { + "epoch": 1.02, + "learning_rate": 2.1642918493176265e-05, + "loss": 3.4527, + "step": 1732096 + }, + { + "epoch": 1.02, + "learning_rate": 2.1634532545665745e-05, + "loss": 3.4317, + "step": 1732608 + }, + { + "epoch": 1.02, + "learning_rate": 2.162614659815522e-05, + "loss": 3.4396, + "step": 1733120 + }, + { + "epoch": 1.02, + "learning_rate": 2.16177606506447e-05, + "loss": 3.4338, + "step": 1733632 + }, + { + "epoch": 1.02, + "learning_rate": 2.160937470313418e-05, + "loss": 3.4521, + "step": 1734144 + }, + { + "epoch": 1.02, + "learning_rate": 2.1600988755623665e-05, + "loss": 3.4314, + "step": 1734656 + }, + { + "epoch": 1.02, + "learning_rate": 2.1592602808113145e-05, + "loss": 3.4395, + "step": 1735168 + }, + { + "epoch": 1.02, + "learning_rate": 2.1584216860602625e-05, + "loss": 3.4345, + "step": 1735680 + }, + { + "epoch": 1.02, + "learning_rate": 2.1575847291895834e-05, + "loss": 3.4426, + "step": 1736192 + }, + { + "epoch": 1.02, + "learning_rate": 2.1567477723189046e-05, + "loss": 3.4437, + "step": 1736704 + }, + { + "epoch": 1.02, + "learning_rate": 2.1559091775678526e-05, + "loss": 3.4357, + "step": 1737216 + }, + { + "epoch": 1.02, + "learning_rate": 2.1550705828168006e-05, + "loss": 3.446, + "step": 1737728 + }, + { + "epoch": 1.02, + "learning_rate": 2.1542319880657486e-05, + "loss": 3.4545, + "step": 1738240 + }, + { + "epoch": 1.02, + "learning_rate": 2.1533933933146966e-05, + "loss": 3.445, + "step": 1738752 + }, + { + "epoch": 1.02, + "learning_rate": 2.1525547985636446e-05, + "loss": 3.4479, + "step": 1739264 + }, + { + "epoch": 1.02, + "learning_rate": 2.1517178416929655e-05, + "loss": 3.4475, + "step": 1739776 + }, + { + "epoch": 1.02, + "learning_rate": 2.1508792469419135e-05, + "loss": 3.4506, + "step": 1740288 + }, + { + "epoch": 1.02, + "learning_rate": 2.150040652190862e-05, + "loss": 3.4382, + "step": 1740800 + }, + { + "epoch": 1.02, + "learning_rate": 2.14920205743981e-05, + "loss": 3.4506, + "step": 1741312 + }, + { + "epoch": 1.02, + "learning_rate": 2.1483634626887575e-05, + "loss": 3.4357, + "step": 1741824 + }, + { + "epoch": 1.02, + "learning_rate": 2.1475248679377055e-05, + "loss": 3.4496, + "step": 1742336 + }, + { + "epoch": 1.02, + "learning_rate": 2.1466862731866535e-05, + "loss": 3.4326, + "step": 1742848 + }, + { + "epoch": 1.02, + "learning_rate": 2.1458476784356015e-05, + "loss": 3.4422, + "step": 1743360 + }, + { + "epoch": 1.02, + "learning_rate": 2.1450107215649227e-05, + "loss": 3.4393, + "step": 1743872 + }, + { + "epoch": 1.02, + "learning_rate": 2.1441721268138707e-05, + "loss": 3.437, + "step": 1744384 + }, + { + "epoch": 1.02, + "learning_rate": 2.143335169943192e-05, + "loss": 3.4358, + "step": 1744896 + }, + { + "epoch": 1.02, + "learning_rate": 2.14249657519214e-05, + "loss": 3.4465, + "step": 1745408 + }, + { + "epoch": 1.02, + "learning_rate": 2.1416579804410876e-05, + "loss": 3.4449, + "step": 1745920 + }, + { + "epoch": 1.02, + "learning_rate": 2.1408193856900356e-05, + "loss": 3.4498, + "step": 1746432 + }, + { + "epoch": 1.02, + "learning_rate": 2.139980790938984e-05, + "loss": 3.4364, + "step": 1746944 + }, + { + "epoch": 1.02, + "learning_rate": 2.139142196187932e-05, + "loss": 3.4523, + "step": 1747456 + }, + { + "epoch": 1.02, + "learning_rate": 2.13830360143688e-05, + "loss": 3.4455, + "step": 1747968 + }, + { + "epoch": 1.02, + "learning_rate": 2.137465006685828e-05, + "loss": 3.4507, + "step": 1748480 + }, + { + "epoch": 1.02, + "learning_rate": 2.136628049815149e-05, + "loss": 3.4435, + "step": 1748992 + }, + { + "epoch": 1.02, + "learning_rate": 2.135789455064097e-05, + "loss": 3.4437, + "step": 1749504 + }, + { + "epoch": 1.02, + "learning_rate": 2.134950860313045e-05, + "loss": 3.4457, + "step": 1750016 + }, + { + "epoch": 1.02, + "learning_rate": 2.134112265561993e-05, + "loss": 3.4548, + "step": 1750528 + }, + { + "epoch": 1.02, + "learning_rate": 2.133275308691314e-05, + "loss": 3.4362, + "step": 1751040 + }, + { + "epoch": 1.02, + "learning_rate": 2.132436713940262e-05, + "loss": 3.4437, + "step": 1751552 + }, + { + "epoch": 1.02, + "learning_rate": 2.13159811918921e-05, + "loss": 3.4466, + "step": 1752064 + }, + { + "epoch": 1.02, + "learning_rate": 2.130761162318531e-05, + "loss": 3.4458, + "step": 1752576 + }, + { + "epoch": 1.02, + "learning_rate": 2.129922567567479e-05, + "loss": 3.4385, + "step": 1753088 + }, + { + "epoch": 1.02, + "learning_rate": 2.1290839728164273e-05, + "loss": 3.4409, + "step": 1753600 + }, + { + "epoch": 1.02, + "learning_rate": 2.1282453780653753e-05, + "loss": 3.4538, + "step": 1754112 + }, + { + "epoch": 1.02, + "learning_rate": 2.1274084211946962e-05, + "loss": 3.4303, + "step": 1754624 + }, + { + "epoch": 1.02, + "learning_rate": 2.126571464324017e-05, + "loss": 3.4492, + "step": 1755136 + }, + { + "epoch": 1.03, + "eval_loss": 3.855316162109375, + "eval_runtime": 303.6898, + "eval_samples_per_second": 1256.516, + "eval_steps_per_second": 39.267, + "step": 1755360 + }, + { + "epoch": 0.0, + "learning_rate": 2.1257328695729655e-05, + "loss": 3.4427, + "step": 1755648 + }, + { + "epoch": 0.0, + "learning_rate": 2.1248942748219135e-05, + "loss": 3.4318, + "step": 1756160 + }, + { + "epoch": 0.0, + "learning_rate": 2.1240556800708615e-05, + "loss": 3.4475, + "step": 1756672 + }, + { + "epoch": 0.0, + "learning_rate": 2.1232170853198095e-05, + "loss": 3.4377, + "step": 1757184 + }, + { + "epoch": 0.0, + "learning_rate": 2.1223801284491304e-05, + "loss": 3.4535, + "step": 1757696 + }, + { + "epoch": 0.0, + "learning_rate": 2.1215415336980784e-05, + "loss": 3.4431, + "step": 1758208 + }, + { + "epoch": 0.0, + "learning_rate": 2.1207029389470264e-05, + "loss": 3.4351, + "step": 1758720 + }, + { + "epoch": 0.0, + "learning_rate": 2.1198643441959744e-05, + "loss": 3.4304, + "step": 1759232 + }, + { + "epoch": 0.0, + "learning_rate": 2.119029025205669e-05, + "loss": 3.44, + "step": 1759744 + }, + { + "epoch": 0.0, + "learning_rate": 2.118190430454617e-05, + "loss": 3.4438, + "step": 1760256 + }, + { + "epoch": 0.0, + "learning_rate": 2.1173518357035645e-05, + "loss": 3.4381, + "step": 1760768 + }, + { + "epoch": 0.0, + "learning_rate": 2.1165132409525125e-05, + "loss": 3.4376, + "step": 1761280 + }, + { + "epoch": 0.0, + "learning_rate": 2.1156746462014605e-05, + "loss": 3.4381, + "step": 1761792 + }, + { + "epoch": 0.0, + "learning_rate": 2.114837689330782e-05, + "loss": 3.4336, + "step": 1762304 + }, + { + "epoch": 0.0, + "learning_rate": 2.1139990945797297e-05, + "loss": 3.4398, + "step": 1762816 + }, + { + "epoch": 0.0, + "learning_rate": 2.1131604998286777e-05, + "loss": 3.4291, + "step": 1763328 + }, + { + "epoch": 0.0, + "learning_rate": 2.1123219050776257e-05, + "loss": 3.4311, + "step": 1763840 + }, + { + "epoch": 0.0, + "learning_rate": 2.1114833103265737e-05, + "loss": 3.4384, + "step": 1764352 + }, + { + "epoch": 0.0, + "learning_rate": 2.1106447155755217e-05, + "loss": 3.4382, + "step": 1764864 + }, + { + "epoch": 0.0, + "learning_rate": 2.1098061208244697e-05, + "loss": 3.4443, + "step": 1765376 + }, + { + "epoch": 0.0, + "learning_rate": 2.1089675260734177e-05, + "loss": 3.4491, + "step": 1765888 + }, + { + "epoch": 0.0, + "learning_rate": 2.108130569202739e-05, + "loss": 3.4416, + "step": 1766400 + }, + { + "epoch": 0.0, + "learning_rate": 2.107291974451687e-05, + "loss": 3.4368, + "step": 1766912 + }, + { + "epoch": 0.0, + "learning_rate": 2.106453379700635e-05, + "loss": 3.4421, + "step": 1767424 + }, + { + "epoch": 0.0, + "learning_rate": 2.1056147849495826e-05, + "loss": 3.4301, + "step": 1767936 + }, + { + "epoch": 0.0, + "learning_rate": 2.1047778280789042e-05, + "loss": 3.4513, + "step": 1768448 + }, + { + "epoch": 0.0, + "learning_rate": 2.1039392333278522e-05, + "loss": 3.4304, + "step": 1768960 + }, + { + "epoch": 0.0, + "learning_rate": 2.1031006385768002e-05, + "loss": 3.4362, + "step": 1769472 + }, + { + "epoch": 0.0, + "learning_rate": 2.102262043825748e-05, + "loss": 3.4329, + "step": 1769984 + }, + { + "epoch": 0.0, + "learning_rate": 2.101425086955069e-05, + "loss": 3.4346, + "step": 1770496 + }, + { + "epoch": 0.01, + "learning_rate": 2.100586492204017e-05, + "loss": 3.4365, + "step": 1771008 + }, + { + "epoch": 0.01, + "learning_rate": 2.099747897452965e-05, + "loss": 3.4429, + "step": 1771520 + }, + { + "epoch": 0.01, + "learning_rate": 2.098909302701913e-05, + "loss": 3.4433, + "step": 1772032 + }, + { + "epoch": 0.01, + "learning_rate": 2.0980723458312343e-05, + "loss": 3.4454, + "step": 1772544 + }, + { + "epoch": 0.01, + "learning_rate": 2.0972337510801823e-05, + "loss": 3.4329, + "step": 1773056 + }, + { + "epoch": 0.01, + "learning_rate": 2.09639515632913e-05, + "loss": 3.4445, + "step": 1773568 + }, + { + "epoch": 0.01, + "learning_rate": 2.095556561578078e-05, + "loss": 3.4419, + "step": 1774080 + }, + { + "epoch": 0.01, + "learning_rate": 2.0947196047073996e-05, + "loss": 3.4334, + "step": 1774592 + }, + { + "epoch": 0.01, + "learning_rate": 2.0938810099563476e-05, + "loss": 3.4351, + "step": 1775104 + }, + { + "epoch": 0.01, + "learning_rate": 2.0930424152052952e-05, + "loss": 3.4379, + "step": 1775616 + }, + { + "epoch": 0.01, + "learning_rate": 2.0922038204542432e-05, + "loss": 3.436, + "step": 1776128 + }, + { + "epoch": 0.01, + "learning_rate": 2.0913668635835645e-05, + "loss": 3.4443, + "step": 1776640 + }, + { + "epoch": 0.01, + "learning_rate": 2.0905282688325125e-05, + "loss": 3.4379, + "step": 1777152 + }, + { + "epoch": 0.01, + "learning_rate": 2.0896896740814605e-05, + "loss": 3.4386, + "step": 1777664 + }, + { + "epoch": 0.01, + "learning_rate": 2.0888510793304084e-05, + "loss": 3.4459, + "step": 1778176 + }, + { + "epoch": 0.01, + "learning_rate": 2.0880141224597297e-05, + "loss": 3.4381, + "step": 1778688 + }, + { + "epoch": 0.01, + "learning_rate": 2.0871755277086774e-05, + "loss": 3.4402, + "step": 1779200 + }, + { + "epoch": 0.01, + "learning_rate": 2.0863369329576253e-05, + "loss": 3.4357, + "step": 1779712 + }, + { + "epoch": 0.01, + "learning_rate": 2.0854983382065733e-05, + "loss": 3.4072, + "step": 1780224 + }, + { + "epoch": 0.01, + "learning_rate": 2.0846613813358946e-05, + "loss": 3.4506, + "step": 1780736 + }, + { + "epoch": 0.01, + "learning_rate": 2.0838227865848426e-05, + "loss": 3.4371, + "step": 1781248 + }, + { + "epoch": 0.01, + "learning_rate": 2.0829841918337906e-05, + "loss": 3.439, + "step": 1781760 + }, + { + "epoch": 0.01, + "learning_rate": 2.082147234963112e-05, + "loss": 3.4219, + "step": 1782272 + }, + { + "epoch": 0.01, + "learning_rate": 2.0813086402120595e-05, + "loss": 3.4205, + "step": 1782784 + }, + { + "epoch": 0.01, + "learning_rate": 2.0804700454610078e-05, + "loss": 3.4222, + "step": 1783296 + }, + { + "epoch": 0.01, + "learning_rate": 2.0796314507099558e-05, + "loss": 3.4334, + "step": 1783808 + }, + { + "epoch": 0.01, + "learning_rate": 2.0787928559589038e-05, + "loss": 3.4331, + "step": 1784320 + }, + { + "epoch": 0.01, + "learning_rate": 2.0779542612078518e-05, + "loss": 3.429, + "step": 1784832 + }, + { + "epoch": 0.01, + "learning_rate": 2.0771156664567998e-05, + "loss": 3.4444, + "step": 1785344 + }, + { + "epoch": 0.01, + "learning_rate": 2.0762770717057478e-05, + "loss": 3.4278, + "step": 1785856 + }, + { + "epoch": 0.01, + "learning_rate": 2.0754401148350687e-05, + "loss": 3.4284, + "step": 1786368 + }, + { + "epoch": 0.01, + "learning_rate": 2.0746015200840167e-05, + "loss": 3.4399, + "step": 1786880 + }, + { + "epoch": 0.01, + "learning_rate": 2.073762925332965e-05, + "loss": 3.4136, + "step": 1787392 + }, + { + "epoch": 0.01, + "learning_rate": 2.072925968462286e-05, + "loss": 3.4221, + "step": 1787904 + }, + { + "epoch": 0.01, + "learning_rate": 2.072087373711234e-05, + "loss": 3.4378, + "step": 1788416 + }, + { + "epoch": 0.01, + "learning_rate": 2.071248778960182e-05, + "loss": 3.4428, + "step": 1788928 + }, + { + "epoch": 0.01, + "learning_rate": 2.07041018420913e-05, + "loss": 3.4175, + "step": 1789440 + }, + { + "epoch": 0.01, + "learning_rate": 2.0695732273384512e-05, + "loss": 3.4315, + "step": 1789952 + }, + { + "epoch": 0.01, + "learning_rate": 2.0687346325873992e-05, + "loss": 3.419, + "step": 1790464 + }, + { + "epoch": 0.01, + "learning_rate": 2.0678960378363472e-05, + "loss": 3.4403, + "step": 1790976 + }, + { + "epoch": 0.01, + "learning_rate": 2.0670574430852952e-05, + "loss": 3.4349, + "step": 1791488 + }, + { + "epoch": 0.01, + "learning_rate": 2.066220486214616e-05, + "loss": 3.4347, + "step": 1792000 + }, + { + "epoch": 0.01, + "learning_rate": 2.065381891463564e-05, + "loss": 3.4411, + "step": 1792512 + }, + { + "epoch": 0.01, + "learning_rate": 2.0645449345928853e-05, + "loss": 3.4439, + "step": 1793024 + }, + { + "epoch": 0.01, + "learning_rate": 2.0637063398418333e-05, + "loss": 3.4578, + "step": 1793536 + }, + { + "epoch": 0.01, + "learning_rate": 2.0628677450907813e-05, + "loss": 3.4363, + "step": 1794048 + }, + { + "epoch": 0.01, + "learning_rate": 2.0620291503397293e-05, + "loss": 3.4383, + "step": 1794560 + }, + { + "epoch": 0.01, + "learning_rate": 2.0611905555886773e-05, + "loss": 3.4389, + "step": 1795072 + }, + { + "epoch": 0.01, + "learning_rate": 2.060351960837625e-05, + "loss": 3.4254, + "step": 1795584 + }, + { + "epoch": 0.01, + "learning_rate": 2.0595133660865733e-05, + "loss": 3.4377, + "step": 1796096 + }, + { + "epoch": 0.01, + "learning_rate": 2.0586764092158945e-05, + "loss": 3.4387, + "step": 1796608 + }, + { + "epoch": 0.01, + "learning_rate": 2.0578378144648425e-05, + "loss": 3.4409, + "step": 1797120 + }, + { + "epoch": 0.01, + "learning_rate": 2.0569992197137902e-05, + "loss": 3.4405, + "step": 1797632 + }, + { + "epoch": 0.01, + "learning_rate": 2.0561606249627382e-05, + "loss": 3.4283, + "step": 1798144 + }, + { + "epoch": 0.01, + "learning_rate": 2.0553236680920594e-05, + "loss": 3.4247, + "step": 1798656 + }, + { + "epoch": 0.01, + "learning_rate": 2.0544867112213807e-05, + "loss": 3.4297, + "step": 1799168 + }, + { + "epoch": 0.01, + "learning_rate": 2.0536481164703287e-05, + "loss": 3.4484, + "step": 1799680 + }, + { + "epoch": 0.01, + "learning_rate": 2.0528095217192767e-05, + "loss": 3.4353, + "step": 1800192 + }, + { + "epoch": 0.01, + "learning_rate": 2.0519709269682247e-05, + "loss": 3.4293, + "step": 1800704 + }, + { + "epoch": 0.02, + "learning_rate": 2.0511339700975456e-05, + "loss": 3.4296, + "step": 1801216 + }, + { + "epoch": 0.02, + "learning_rate": 2.0502953753464936e-05, + "loss": 3.4411, + "step": 1801728 + }, + { + "epoch": 0.02, + "learning_rate": 2.049456780595442e-05, + "loss": 3.4279, + "step": 1802240 + }, + { + "epoch": 0.02, + "learning_rate": 2.04861818584439e-05, + "loss": 3.4306, + "step": 1802752 + }, + { + "epoch": 0.02, + "learning_rate": 2.0477795910933376e-05, + "loss": 3.4472, + "step": 1803264 + }, + { + "epoch": 0.02, + "learning_rate": 2.0469409963422856e-05, + "loss": 3.4354, + "step": 1803776 + }, + { + "epoch": 0.02, + "learning_rate": 2.0461024015912336e-05, + "loss": 3.4373, + "step": 1804288 + }, + { + "epoch": 0.02, + "learning_rate": 2.0452638068401816e-05, + "loss": 3.4262, + "step": 1804800 + }, + { + "epoch": 0.02, + "learning_rate": 2.0444268499695028e-05, + "loss": 3.4347, + "step": 1805312 + }, + { + "epoch": 0.02, + "learning_rate": 2.0435882552184508e-05, + "loss": 3.4291, + "step": 1805824 + }, + { + "epoch": 0.02, + "learning_rate": 2.0427496604673988e-05, + "loss": 3.4429, + "step": 1806336 + }, + { + "epoch": 0.02, + "learning_rate": 2.0419110657163468e-05, + "loss": 3.4357, + "step": 1806848 + }, + { + "epoch": 0.02, + "learning_rate": 2.0410741088456677e-05, + "loss": 3.4442, + "step": 1807360 + }, + { + "epoch": 0.02, + "learning_rate": 2.0402355140946157e-05, + "loss": 3.4365, + "step": 1807872 + }, + { + "epoch": 0.02, + "learning_rate": 2.0393985572239373e-05, + "loss": 3.439, + "step": 1808384 + }, + { + "epoch": 0.02, + "learning_rate": 2.038559962472885e-05, + "loss": 3.4259, + "step": 1808896 + }, + { + "epoch": 0.02, + "learning_rate": 2.037721367721833e-05, + "loss": 3.4265, + "step": 1809408 + }, + { + "epoch": 0.02, + "learning_rate": 2.036882772970781e-05, + "loss": 3.4247, + "step": 1809920 + }, + { + "epoch": 0.02, + "learning_rate": 2.036044178219729e-05, + "loss": 3.4413, + "step": 1810432 + }, + { + "epoch": 0.02, + "learning_rate": 2.035205583468677e-05, + "loss": 3.421, + "step": 1810944 + }, + { + "epoch": 0.02, + "learning_rate": 2.034366988717625e-05, + "loss": 3.427, + "step": 1811456 + }, + { + "epoch": 0.02, + "learning_rate": 2.033528393966573e-05, + "loss": 3.4244, + "step": 1811968 + }, + { + "epoch": 0.02, + "learning_rate": 2.032691437095894e-05, + "loss": 3.434, + "step": 1812480 + }, + { + "epoch": 0.02, + "learning_rate": 2.031854480225215e-05, + "loss": 3.4351, + "step": 1812992 + }, + { + "epoch": 0.02, + "learning_rate": 2.031015885474163e-05, + "loss": 3.4248, + "step": 1813504 + }, + { + "epoch": 0.02, + "learning_rate": 2.030177290723111e-05, + "loss": 3.4395, + "step": 1814016 + }, + { + "epoch": 0.02, + "learning_rate": 2.029338695972059e-05, + "loss": 3.4385, + "step": 1814528 + }, + { + "epoch": 0.02, + "learning_rate": 2.0285001012210074e-05, + "loss": 3.4329, + "step": 1815040 + }, + { + "epoch": 0.02, + "learning_rate": 2.0276615064699554e-05, + "loss": 3.4391, + "step": 1815552 + }, + { + "epoch": 0.02, + "learning_rate": 2.026822911718903e-05, + "loss": 3.4381, + "step": 1816064 + }, + { + "epoch": 0.02, + "learning_rate": 2.025984316967851e-05, + "loss": 3.4349, + "step": 1816576 + }, + { + "epoch": 0.02, + "learning_rate": 2.0251473600971723e-05, + "loss": 3.4324, + "step": 1817088 + }, + { + "epoch": 0.02, + "learning_rate": 2.0243087653461203e-05, + "loss": 3.4376, + "step": 1817600 + }, + { + "epoch": 0.02, + "learning_rate": 2.0234718084754415e-05, + "loss": 3.4251, + "step": 1818112 + }, + { + "epoch": 0.02, + "learning_rate": 2.0226332137243895e-05, + "loss": 3.4382, + "step": 1818624 + }, + { + "epoch": 0.02, + "learning_rate": 2.0217946189733375e-05, + "loss": 3.4268, + "step": 1819136 + }, + { + "epoch": 0.02, + "learning_rate": 2.0209560242222852e-05, + "loss": 3.4319, + "step": 1819648 + }, + { + "epoch": 0.02, + "learning_rate": 2.0201174294712332e-05, + "loss": 3.426, + "step": 1820160 + }, + { + "epoch": 0.02, + "learning_rate": 2.0192804726005544e-05, + "loss": 3.4262, + "step": 1820672 + }, + { + "epoch": 0.02, + "learning_rate": 2.0184418778495024e-05, + "loss": 3.4254, + "step": 1821184 + }, + { + "epoch": 0.02, + "learning_rate": 2.0176032830984504e-05, + "loss": 3.4352, + "step": 1821696 + }, + { + "epoch": 0.02, + "learning_rate": 2.0167646883473984e-05, + "loss": 3.4305, + "step": 1822208 + }, + { + "epoch": 0.02, + "learning_rate": 2.0159260935963464e-05, + "loss": 3.44, + "step": 1822720 + }, + { + "epoch": 0.02, + "learning_rate": 2.0150874988452944e-05, + "loss": 3.4224, + "step": 1823232 + }, + { + "epoch": 0.02, + "learning_rate": 2.0142489040942424e-05, + "loss": 3.4461, + "step": 1823744 + }, + { + "epoch": 0.02, + "learning_rate": 2.0134103093431904e-05, + "loss": 3.4335, + "step": 1824256 + }, + { + "epoch": 0.02, + "learning_rate": 2.0125733524725116e-05, + "loss": 3.4386, + "step": 1824768 + }, + { + "epoch": 0.02, + "learning_rate": 2.0117347577214596e-05, + "loss": 3.4359, + "step": 1825280 + }, + { + "epoch": 0.02, + "learning_rate": 2.0108961629704076e-05, + "loss": 3.4329, + "step": 1825792 + }, + { + "epoch": 0.02, + "learning_rate": 2.0100575682193556e-05, + "loss": 3.4339, + "step": 1826304 + }, + { + "epoch": 0.02, + "learning_rate": 2.0092206113486765e-05, + "loss": 3.4429, + "step": 1826816 + }, + { + "epoch": 0.02, + "learning_rate": 2.0083820165976245e-05, + "loss": 3.428, + "step": 1827328 + }, + { + "epoch": 0.02, + "learning_rate": 2.007543421846573e-05, + "loss": 3.4348, + "step": 1827840 + }, + { + "epoch": 0.02, + "learning_rate": 2.0067048270955205e-05, + "loss": 3.4357, + "step": 1828352 + }, + { + "epoch": 0.02, + "learning_rate": 2.0058678702248418e-05, + "loss": 3.4308, + "step": 1828864 + }, + { + "epoch": 0.02, + "learning_rate": 2.0050292754737898e-05, + "loss": 3.4287, + "step": 1829376 + }, + { + "epoch": 0.02, + "learning_rate": 2.0041906807227378e-05, + "loss": 3.4304, + "step": 1829888 + }, + { + "epoch": 0.02, + "learning_rate": 2.0033520859716858e-05, + "loss": 3.4402, + "step": 1830400 + }, + { + "epoch": 0.02, + "learning_rate": 2.002515129101007e-05, + "loss": 3.4236, + "step": 1830912 + }, + { + "epoch": 0.02, + "learning_rate": 2.001676534349955e-05, + "loss": 3.4392, + "step": 1831424 + }, + { + "epoch": 0.03, + "eval_loss": 3.8567299842834473, + "eval_runtime": 303.3937, + "eval_samples_per_second": 1257.742, + "eval_steps_per_second": 39.305, + "step": 1831680 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 1.273860426623017e+18, + "trial_name": null, + "trial_params": null +}