diff --git "a/checkpoint-2594880/trainer_state.json" "b/checkpoint-2594880/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-2594880/trainer_state.json" @@ -0,0 +1,30705 @@ +{ + "best_metric": 3.843111753463745, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/existential-there-quantifier/transformer/4/checkpoints/checkpoint-992160", + "epoch": 1.0250006060157382, + "eval_steps": 10, + "global_step": 2594880, + "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": 11.0368, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 6.8134, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 6.1877, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 5.9788, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 5.8108, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 5.7032, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 5.5999, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 5.5361, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 5.4453, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 5.4008, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 5.3507, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 5.3098, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989936862987376e-05, + "loss": 5.2582, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989099906116697e-05, + "loss": 5.2103, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988261311365645e-05, + "loss": 5.1687, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.987422716614593e-05, + "loss": 5.1357, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986584121863541e-05, + "loss": 5.1055, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985745527112489e-05, + "loss": 5.0901, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984906932361437e-05, + "loss": 5.0477, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.0274, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 5.0154, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.9823927859886547e-05, + "loss": 4.9707, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.9815541912376026e-05, + "loss": 4.9456, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.9807155964865506e-05, + "loss": 4.9307, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 4.9209, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790400448648195e-05, + "loss": 4.8868, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9782030879941405e-05, + "loss": 4.8669, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773644932430885e-05, + "loss": 4.8606, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765258984920364e-05, + "loss": 4.8385, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756873037409844e-05, + "loss": 4.8117, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748487089899324e-05, + "loss": 4.7945, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.9740117521192533e-05, + "loss": 4.7903, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731731573682013e-05, + "loss": 4.7787, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.97233456261715e-05, + "loss": 4.7747, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.971495967866098e-05, + "loss": 4.7513, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.970657373115046e-05, + "loss": 4.736, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969820416244367e-05, + "loss": 4.7379, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968981821493315e-05, + "loss": 4.7031, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.968143226742263e-05, + "loss": 4.6961, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967304631991211e-05, + "loss": 4.6831, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966466037240159e-05, + "loss": 4.6832, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965627442489107e-05, + "loss": 4.6604, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964788847738054e-05, + "loss": 4.672, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963950252987002e-05, + "loss": 4.6425, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.963113296116324e-05, + "loss": 4.6463, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962274701365272e-05, + "loss": 4.6366, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.96143610661422e-05, + "loss": 4.6276, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960597511863168e-05, + "loss": 4.6242, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.959758917112116e-05, + "loss": 4.5995, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.9589219602414374e-05, + "loss": 4.587, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958085003370758e-05, + "loss": 4.6012, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957246408619706e-05, + "loss": 4.5854, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956407813868654e-05, + "loss": 4.5687, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.9555692191176016e-05, + "loss": 4.5577, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.954732262246923e-05, + "loss": 4.5648, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.953893667495871e-05, + "loss": 4.5469, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.953055072744819e-05, + "loss": 4.5599, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.952216477993767e-05, + "loss": 4.5342, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951377883242715e-05, + "loss": 4.5313, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.950539288491663e-05, + "loss": 4.535, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949700693740611e-05, + "loss": 4.5165, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948862098989559e-05, + "loss": 4.4989, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.94802514211888e-05, + "loss": 4.5047, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947186547367828e-05, + "loss": 4.488, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946347952616776e-05, + "loss": 4.4898, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945509357865724e-05, + "loss": 4.4974, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944670763114672e-05, + "loss": 4.4911, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.943833806243993e-05, + "loss": 4.4782, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942995211492941e-05, + "loss": 4.4663, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.942156616741889e-05, + "loss": 4.4584, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.941318021990837e-05, + "loss": 4.4699, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.9404810651201585e-05, + "loss": 4.466, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396441082494794e-05, + "loss": 4.4578, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388055134984274e-05, + "loss": 4.456, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379669187473754e-05, + "loss": 4.4582, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371283239963234e-05, + "loss": 4.4521, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.936291367125644e-05, + "loss": 4.4261, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.935452772374592e-05, + "loss": 4.4359, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.93461417762354e-05, + "loss": 4.4321, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.933775582872488e-05, + "loss": 4.4188, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.932936988121436e-05, + "loss": 4.4303, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.932098393370384e-05, + "loss": 4.4199, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.931259798619332e-05, + "loss": 4.4254, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.930422841748654e-05, + "loss": 4.4167, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.929584246997602e-05, + "loss": 4.3887, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.92874565224655e-05, + "loss": 4.3998, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.927907057495498e-05, + "loss": 4.3993, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.927068462744446e-05, + "loss": 4.3994, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.926229867993394e-05, + "loss": 4.3916, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925392911122715e-05, + "loss": 4.3838, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.924554316371663e-05, + "loss": 4.3862, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923715721620611e-05, + "loss": 4.375, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922878764749932e-05, + "loss": 4.368, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.92204016999888e-05, + "loss": 4.3685, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921201575247828e-05, + "loss": 4.3654, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920362980496776e-05, + "loss": 4.3794, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919524385745724e-05, + "loss": 4.3545, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918685790994672e-05, + "loss": 4.3487, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.91784719624362e-05, + "loss": 4.347, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.9170086014925676e-05, + "loss": 4.3576, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.9161700067415156e-05, + "loss": 4.3531, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.9153314119904636e-05, + "loss": 4.3398, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.9144928172394116e-05, + "loss": 4.3393, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.9136542224883596e-05, + "loss": 4.3214, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.9128172656176805e-05, + "loss": 4.3374, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.9119786708666285e-05, + "loss": 4.322, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.9111400761155765e-05, + "loss": 4.3206, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.910303119244898e-05, + "loss": 4.3238, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.909464524493846e-05, + "loss": 4.3228, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908625929742794e-05, + "loss": 4.3172, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907787334991742e-05, + "loss": 4.3153, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.90694874024069e-05, + "loss": 4.3074, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906110145489638e-05, + "loss": 4.3136, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.905273188618959e-05, + "loss": 4.3028, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.904434593867907e-05, + "loss": 4.3023, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903595999116855e-05, + "loss": 4.3076, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.902757404365803e-05, + "loss": 4.3048, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.901920447495124e-05, + "loss": 4.3025, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.901081852744072e-05, + "loss": 4.2937, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.90024325799302e-05, + "loss": 4.2983, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.8994046632419686e-05, + "loss": 4.2932, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.8985660684909166e-05, + "loss": 4.2793, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.8977274737398646e-05, + "loss": 4.2973, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968888789888125e-05, + "loss": 4.2813, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.8960502842377605e-05, + "loss": 4.2894, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.8952133273670815e-05, + "loss": 4.2709, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.8943747326160294e-05, + "loss": 4.2661, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.8935361378649774e-05, + "loss": 4.2649, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.8926991809942984e-05, + "loss": 4.2682, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.8918605862432463e-05, + "loss": 4.258, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.8910219914921943e-05, + "loss": 4.2754, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.8901833967411423e-05, + "loss": 4.272, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.88934480199009e-05, + "loss": 4.2555, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888506207239038e-05, + "loss": 4.2596, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.887667612487986e-05, + "loss": 4.2631, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886829017736934e-05, + "loss": 4.2597, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885992060866256e-05, + "loss": 4.2637, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.885155103995577e-05, + "loss": 4.2595, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884316509244525e-05, + "loss": 4.2466, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883477914493473e-05, + "loss": 4.2528, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882639319742421e-05, + "loss": 4.2464, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.881800724991369e-05, + "loss": 4.24, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.880962130240316e-05, + "loss": 4.2503, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.880123535489264e-05, + "loss": 4.2374, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.879286578618586e-05, + "loss": 4.2263, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.878447983867534e-05, + "loss": 4.2481, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877609389116482e-05, + "loss": 4.2278, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.87677079436543e-05, + "loss": 4.228, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875932199614378e-05, + "loss": 4.2307, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.875093604863326e-05, + "loss": 4.2235, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.195763111114502, + "eval_runtime": 304.3449, + "eval_samples_per_second": 1253.811, + "eval_steps_per_second": 39.183, + "step": 76320 + }, + { + "epoch": 1.0, + "learning_rate": 4.874255010112274e-05, + "loss": 4.2068, + "step": 76800 + }, + { + "epoch": 1.0, + "learning_rate": 4.873416415361222e-05, + "loss": 4.2199, + "step": 77312 + }, + { + "epoch": 1.0, + "learning_rate": 4.8725794584905426e-05, + "loss": 4.2339, + "step": 77824 + }, + { + "epoch": 1.0, + "learning_rate": 4.8717408637394906e-05, + "loss": 4.2115, + "step": 78336 + }, + { + "epoch": 1.0, + "learning_rate": 4.8709022689884386e-05, + "loss": 4.2262, + "step": 78848 + }, + { + "epoch": 1.0, + "learning_rate": 4.8700636742373866e-05, + "loss": 4.2001, + "step": 79360 + }, + { + "epoch": 1.0, + "learning_rate": 4.8692267173667075e-05, + "loss": 4.2133, + "step": 79872 + }, + { + "epoch": 1.0, + "learning_rate": 4.8683881226156555e-05, + "loss": 4.1979, + "step": 80384 + }, + { + "epoch": 1.0, + "learning_rate": 4.867551165744977e-05, + "loss": 4.2083, + "step": 80896 + }, + { + "epoch": 1.0, + "learning_rate": 4.866712570993925e-05, + "loss": 4.2035, + "step": 81408 + }, + { + "epoch": 1.0, + "learning_rate": 4.865873976242873e-05, + "loss": 4.209, + "step": 81920 + }, + { + "epoch": 1.0, + "learning_rate": 4.865035381491821e-05, + "loss": 4.2051, + "step": 82432 + }, + { + "epoch": 1.0, + "learning_rate": 4.864198424621142e-05, + "loss": 4.1916, + "step": 82944 + }, + { + "epoch": 1.0, + "learning_rate": 4.86335982987009e-05, + "loss": 4.1833, + "step": 83456 + }, + { + "epoch": 1.0, + "learning_rate": 4.862521235119038e-05, + "loss": 4.1845, + "step": 83968 + }, + { + "epoch": 1.0, + "learning_rate": 4.861682640367986e-05, + "loss": 4.1852, + "step": 84480 + }, + { + "epoch": 1.0, + "learning_rate": 4.860844045616934e-05, + "loss": 4.1949, + "step": 84992 + }, + { + "epoch": 1.0, + "learning_rate": 4.860005450865882e-05, + "loss": 4.1823, + "step": 85504 + }, + { + "epoch": 1.0, + "learning_rate": 4.85916685611483e-05, + "loss": 4.1885, + "step": 86016 + }, + { + "epoch": 1.0, + "learning_rate": 4.858328261363778e-05, + "loss": 4.205, + "step": 86528 + }, + { + "epoch": 1.0, + "learning_rate": 4.857489666612726e-05, + "loss": 4.179, + "step": 87040 + }, + { + "epoch": 1.0, + "learning_rate": 4.856651071861674e-05, + "loss": 4.1732, + "step": 87552 + }, + { + "epoch": 1.0, + "learning_rate": 4.8558124771106226e-05, + "loss": 4.1771, + "step": 88064 + }, + { + "epoch": 1.0, + "learning_rate": 4.8549755202399435e-05, + "loss": 4.186, + "step": 88576 + }, + { + "epoch": 1.0, + "learning_rate": 4.8541385633692644e-05, + "loss": 4.1671, + "step": 89088 + }, + { + "epoch": 1.0, + "learning_rate": 4.8532999686182124e-05, + "loss": 4.171, + "step": 89600 + }, + { + "epoch": 1.0, + "learning_rate": 4.8524613738671604e-05, + "loss": 4.1727, + "step": 90112 + }, + { + "epoch": 1.0, + "learning_rate": 4.8516227791161084e-05, + "loss": 4.1665, + "step": 90624 + }, + { + "epoch": 1.0, + "learning_rate": 4.8507841843650564e-05, + "loss": 4.1514, + "step": 91136 + }, + { + "epoch": 1.01, + "learning_rate": 4.8499455896140044e-05, + "loss": 4.1567, + "step": 91648 + }, + { + "epoch": 1.01, + "learning_rate": 4.8491069948629524e-05, + "loss": 4.1553, + "step": 92160 + }, + { + "epoch": 1.01, + "learning_rate": 4.848270037992273e-05, + "loss": 4.1666, + "step": 92672 + }, + { + "epoch": 1.01, + "learning_rate": 4.847431443241221e-05, + "loss": 4.1708, + "step": 93184 + }, + { + "epoch": 1.01, + "learning_rate": 4.846592848490169e-05, + "loss": 4.1529, + "step": 93696 + }, + { + "epoch": 1.01, + "learning_rate": 4.845754253739117e-05, + "loss": 4.1501, + "step": 94208 + }, + { + "epoch": 1.01, + "learning_rate": 4.844915658988065e-05, + "loss": 4.1648, + "step": 94720 + }, + { + "epoch": 1.01, + "learning_rate": 4.844077064237013e-05, + "loss": 4.1387, + "step": 95232 + }, + { + "epoch": 1.01, + "learning_rate": 4.843238469485961e-05, + "loss": 4.1448, + "step": 95744 + }, + { + "epoch": 1.01, + "learning_rate": 4.842401512615282e-05, + "loss": 4.1371, + "step": 96256 + }, + { + "epoch": 1.01, + "learning_rate": 4.84156291786423e-05, + "loss": 4.1433, + "step": 96768 + }, + { + "epoch": 1.01, + "learning_rate": 4.840724323113178e-05, + "loss": 4.1352, + "step": 97280 + }, + { + "epoch": 1.01, + "learning_rate": 4.839885728362126e-05, + "loss": 4.1532, + "step": 97792 + }, + { + "epoch": 1.01, + "learning_rate": 4.839048771491447e-05, + "loss": 4.1375, + "step": 98304 + }, + { + "epoch": 1.01, + "learning_rate": 4.838210176740395e-05, + "loss": 4.1386, + "step": 98816 + }, + { + "epoch": 1.01, + "learning_rate": 4.837371581989343e-05, + "loss": 4.1346, + "step": 99328 + }, + { + "epoch": 1.01, + "learning_rate": 4.836532987238292e-05, + "loss": 4.1408, + "step": 99840 + }, + { + "epoch": 1.01, + "learning_rate": 4.83569439248724e-05, + "loss": 4.133, + "step": 100352 + }, + { + "epoch": 1.01, + "learning_rate": 4.834855797736188e-05, + "loss": 4.1239, + "step": 100864 + }, + { + "epoch": 1.01, + "learning_rate": 4.834017202985136e-05, + "loss": 4.117, + "step": 101376 + }, + { + "epoch": 1.01, + "learning_rate": 4.8331802461144566e-05, + "loss": 4.1385, + "step": 101888 + }, + { + "epoch": 1.01, + "learning_rate": 4.8323416513634046e-05, + "loss": 4.1267, + "step": 102400 + }, + { + "epoch": 1.01, + "learning_rate": 4.8315030566123526e-05, + "loss": 4.1169, + "step": 102912 + }, + { + "epoch": 1.01, + "learning_rate": 4.8306644618613006e-05, + "loss": 4.1171, + "step": 103424 + }, + { + "epoch": 1.01, + "learning_rate": 4.8298275049906215e-05, + "loss": 4.1231, + "step": 103936 + }, + { + "epoch": 1.01, + "learning_rate": 4.8289889102395695e-05, + "loss": 4.112, + "step": 104448 + }, + { + "epoch": 1.01, + "learning_rate": 4.8281503154885175e-05, + "loss": 4.13, + "step": 104960 + }, + { + "epoch": 1.01, + "learning_rate": 4.8273117207374655e-05, + "loss": 4.113, + "step": 105472 + }, + { + "epoch": 1.01, + "learning_rate": 4.8264731259864135e-05, + "loss": 4.1149, + "step": 105984 + }, + { + "epoch": 1.01, + "learning_rate": 4.8256345312353615e-05, + "loss": 4.124, + "step": 106496 + }, + { + "epoch": 1.01, + "learning_rate": 4.8247959364843095e-05, + "loss": 4.1038, + "step": 107008 + }, + { + "epoch": 1.01, + "learning_rate": 4.823957341733258e-05, + "loss": 4.1002, + "step": 107520 + }, + { + "epoch": 1.01, + "learning_rate": 4.823120384862579e-05, + "loss": 4.1103, + "step": 108032 + }, + { + "epoch": 1.01, + "learning_rate": 4.822281790111527e-05, + "loss": 4.0924, + "step": 108544 + }, + { + "epoch": 1.01, + "learning_rate": 4.821443195360475e-05, + "loss": 4.0985, + "step": 109056 + }, + { + "epoch": 1.01, + "learning_rate": 4.820604600609423e-05, + "loss": 4.1096, + "step": 109568 + }, + { + "epoch": 1.01, + "learning_rate": 4.819766005858371e-05, + "loss": 4.1122, + "step": 110080 + }, + { + "epoch": 1.01, + "learning_rate": 4.8189274111073184e-05, + "loss": 4.1009, + "step": 110592 + }, + { + "epoch": 1.01, + "learning_rate": 4.8180888163562664e-05, + "loss": 4.0957, + "step": 111104 + }, + { + "epoch": 1.01, + "learning_rate": 4.817253497365961e-05, + "loss": 4.0861, + "step": 111616 + }, + { + "epoch": 1.01, + "learning_rate": 4.816414902614909e-05, + "loss": 4.1051, + "step": 112128 + }, + { + "epoch": 1.01, + "learning_rate": 4.815576307863857e-05, + "loss": 4.1013, + "step": 112640 + }, + { + "epoch": 1.01, + "learning_rate": 4.814737713112805e-05, + "loss": 4.1016, + "step": 113152 + }, + { + "epoch": 1.01, + "learning_rate": 4.8138991183617535e-05, + "loss": 4.102, + "step": 113664 + }, + { + "epoch": 1.01, + "learning_rate": 4.813060523610701e-05, + "loss": 4.1048, + "step": 114176 + }, + { + "epoch": 1.01, + "learning_rate": 4.8122235667400224e-05, + "loss": 4.1031, + "step": 114688 + }, + { + "epoch": 1.01, + "learning_rate": 4.8113849719889704e-05, + "loss": 4.0819, + "step": 115200 + }, + { + "epoch": 1.01, + "learning_rate": 4.8105480151182914e-05, + "loss": 4.0935, + "step": 115712 + }, + { + "epoch": 1.01, + "learning_rate": 4.8097094203672393e-05, + "loss": 4.095, + "step": 116224 + }, + { + "epoch": 1.01, + "learning_rate": 4.8088708256161873e-05, + "loss": 4.0788, + "step": 116736 + }, + { + "epoch": 1.01, + "learning_rate": 4.808032230865135e-05, + "loss": 4.1021, + "step": 117248 + }, + { + "epoch": 1.01, + "learning_rate": 4.8071936361140827e-05, + "loss": 4.0938, + "step": 117760 + }, + { + "epoch": 1.01, + "learning_rate": 4.8063550413630307e-05, + "loss": 4.0971, + "step": 118272 + }, + { + "epoch": 1.01, + "learning_rate": 4.8055164466119786e-05, + "loss": 4.0954, + "step": 118784 + }, + { + "epoch": 1.01, + "learning_rate": 4.804677851860927e-05, + "loss": 4.071, + "step": 119296 + }, + { + "epoch": 1.01, + "learning_rate": 4.803840894990248e-05, + "loss": 4.0829, + "step": 119808 + }, + { + "epoch": 1.01, + "learning_rate": 4.803002300239196e-05, + "loss": 4.0819, + "step": 120320 + }, + { + "epoch": 1.01, + "learning_rate": 4.802163705488144e-05, + "loss": 4.0849, + "step": 120832 + }, + { + "epoch": 1.01, + "learning_rate": 4.801325110737092e-05, + "loss": 4.0833, + "step": 121344 + }, + { + "epoch": 1.01, + "learning_rate": 4.800488153866413e-05, + "loss": 4.0746, + "step": 121856 + }, + { + "epoch": 1.02, + "learning_rate": 4.799649559115361e-05, + "loss": 4.084, + "step": 122368 + }, + { + "epoch": 1.02, + "learning_rate": 4.798810964364309e-05, + "loss": 4.0771, + "step": 122880 + }, + { + "epoch": 1.02, + "learning_rate": 4.797972369613257e-05, + "loss": 4.0647, + "step": 123392 + }, + { + "epoch": 1.02, + "learning_rate": 4.797133774862205e-05, + "loss": 4.0716, + "step": 123904 + }, + { + "epoch": 1.02, + "learning_rate": 4.796295180111153e-05, + "loss": 4.0769, + "step": 124416 + }, + { + "epoch": 1.02, + "learning_rate": 4.795458223240474e-05, + "loss": 4.0869, + "step": 124928 + }, + { + "epoch": 1.02, + "learning_rate": 4.794619628489423e-05, + "loss": 4.0682, + "step": 125440 + }, + { + "epoch": 1.02, + "learning_rate": 4.793781033738371e-05, + "loss": 4.0545, + "step": 125952 + }, + { + "epoch": 1.02, + "learning_rate": 4.792942438987319e-05, + "loss": 4.0634, + "step": 126464 + }, + { + "epoch": 1.02, + "learning_rate": 4.792103844236267e-05, + "loss": 4.074, + "step": 126976 + }, + { + "epoch": 1.02, + "learning_rate": 4.791265249485215e-05, + "loss": 4.071, + "step": 127488 + }, + { + "epoch": 1.02, + "learning_rate": 4.790426654734163e-05, + "loss": 4.0658, + "step": 128000 + }, + { + "epoch": 1.02, + "learning_rate": 4.7895880599831107e-05, + "loss": 4.0598, + "step": 128512 + }, + { + "epoch": 1.02, + "learning_rate": 4.7887494652320587e-05, + "loss": 4.0503, + "step": 129024 + }, + { + "epoch": 1.02, + "learning_rate": 4.7879125083613796e-05, + "loss": 4.0659, + "step": 129536 + }, + { + "epoch": 1.02, + "learning_rate": 4.7870739136103276e-05, + "loss": 4.0511, + "step": 130048 + }, + { + "epoch": 1.02, + "learning_rate": 4.7862353188592756e-05, + "loss": 4.0559, + "step": 130560 + }, + { + "epoch": 1.02, + "learning_rate": 4.7853983619885965e-05, + "loss": 4.0591, + "step": 131072 + }, + { + "epoch": 1.02, + "learning_rate": 4.7845597672375445e-05, + "loss": 4.0593, + "step": 131584 + }, + { + "epoch": 1.02, + "learning_rate": 4.7837211724864925e-05, + "loss": 4.0524, + "step": 132096 + }, + { + "epoch": 1.02, + "learning_rate": 4.782882577735441e-05, + "loss": 4.0583, + "step": 132608 + }, + { + "epoch": 1.02, + "learning_rate": 4.782043982984389e-05, + "loss": 4.0494, + "step": 133120 + }, + { + "epoch": 1.02, + "learning_rate": 4.781205388233337e-05, + "loss": 4.0549, + "step": 133632 + }, + { + "epoch": 1.02, + "learning_rate": 4.7803667934822844e-05, + "loss": 4.0477, + "step": 134144 + }, + { + "epoch": 1.02, + "learning_rate": 4.7795281987312324e-05, + "loss": 4.0458, + "step": 134656 + }, + { + "epoch": 1.02, + "learning_rate": 4.778691241860554e-05, + "loss": 4.0589, + "step": 135168 + }, + { + "epoch": 1.02, + "learning_rate": 4.777852647109502e-05, + "loss": 4.0574, + "step": 135680 + }, + { + "epoch": 1.02, + "learning_rate": 4.777015690238823e-05, + "loss": 4.053, + "step": 136192 + }, + { + "epoch": 1.02, + "learning_rate": 4.776177095487771e-05, + "loss": 4.0468, + "step": 136704 + }, + { + "epoch": 1.02, + "learning_rate": 4.775338500736719e-05, + "loss": 4.0515, + "step": 137216 + }, + { + "epoch": 1.02, + "learning_rate": 4.774499905985666e-05, + "loss": 4.0501, + "step": 137728 + }, + { + "epoch": 1.02, + "learning_rate": 4.773661311234615e-05, + "loss": 4.0367, + "step": 138240 + }, + { + "epoch": 1.02, + "learning_rate": 4.772822716483563e-05, + "loss": 4.057, + "step": 138752 + }, + { + "epoch": 1.02, + "learning_rate": 4.771984121732511e-05, + "loss": 4.041, + "step": 139264 + }, + { + "epoch": 1.02, + "learning_rate": 4.771145526981459e-05, + "loss": 4.0523, + "step": 139776 + }, + { + "epoch": 1.02, + "learning_rate": 4.77030857011078e-05, + "loss": 4.0341, + "step": 140288 + }, + { + "epoch": 1.02, + "learning_rate": 4.769469975359728e-05, + "loss": 4.0357, + "step": 140800 + }, + { + "epoch": 1.02, + "learning_rate": 4.768631380608676e-05, + "loss": 4.0319, + "step": 141312 + }, + { + "epoch": 1.02, + "learning_rate": 4.767792785857624e-05, + "loss": 4.0344, + "step": 141824 + }, + { + "epoch": 1.02, + "learning_rate": 4.766955828986945e-05, + "loss": 4.0316, + "step": 142336 + }, + { + "epoch": 1.02, + "learning_rate": 4.766117234235893e-05, + "loss": 4.0465, + "step": 142848 + }, + { + "epoch": 1.02, + "learning_rate": 4.765278639484841e-05, + "loss": 4.0479, + "step": 143360 + }, + { + "epoch": 1.02, + "learning_rate": 4.764440044733789e-05, + "loss": 4.0357, + "step": 143872 + }, + { + "epoch": 1.02, + "learning_rate": 4.763601449982737e-05, + "loss": 4.0289, + "step": 144384 + }, + { + "epoch": 1.02, + "learning_rate": 4.762764493112058e-05, + "loss": 4.0387, + "step": 144896 + }, + { + "epoch": 1.02, + "learning_rate": 4.761925898361006e-05, + "loss": 4.0371, + "step": 145408 + }, + { + "epoch": 1.02, + "learning_rate": 4.761087303609954e-05, + "loss": 4.0461, + "step": 145920 + }, + { + "epoch": 1.02, + "learning_rate": 4.760248708858902e-05, + "loss": 4.0374, + "step": 146432 + }, + { + "epoch": 1.02, + "learning_rate": 4.759411751988223e-05, + "loss": 4.0331, + "step": 146944 + }, + { + "epoch": 1.02, + "learning_rate": 4.758573157237171e-05, + "loss": 4.0284, + "step": 147456 + }, + { + "epoch": 1.02, + "learning_rate": 4.757734562486119e-05, + "loss": 4.0381, + "step": 147968 + }, + { + "epoch": 1.02, + "learning_rate": 4.756895967735067e-05, + "loss": 4.0264, + "step": 148480 + }, + { + "epoch": 1.02, + "learning_rate": 4.756059010864388e-05, + "loss": 4.0306, + "step": 148992 + }, + { + "epoch": 1.02, + "learning_rate": 4.755220416113336e-05, + "loss": 4.0283, + "step": 149504 + }, + { + "epoch": 1.02, + "learning_rate": 4.754381821362284e-05, + "loss": 4.0197, + "step": 150016 + }, + { + "epoch": 1.02, + "learning_rate": 4.753544864491605e-05, + "loss": 4.0409, + "step": 150528 + }, + { + "epoch": 1.02, + "learning_rate": 4.7527062697405536e-05, + "loss": 4.0207, + "step": 151040 + }, + { + "epoch": 1.02, + "learning_rate": 4.7518676749895016e-05, + "loss": 4.0199, + "step": 151552 + }, + { + "epoch": 1.02, + "learning_rate": 4.7510290802384496e-05, + "loss": 4.0233, + "step": 152064 + }, + { + "epoch": 1.02, + "learning_rate": 4.7501904854873976e-05, + "loss": 4.0188, + "step": 152576 + }, + { + "epoch": 1.03, + "eval_loss": 4.028048515319824, + "eval_runtime": 306.2895, + "eval_samples_per_second": 1245.851, + "eval_steps_per_second": 38.934, + "step": 152640 + }, + { + "epoch": 0.0, + "learning_rate": 4.7493518907363456e-05, + "loss": 4.0033, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.7485132959852936e-05, + "loss": 4.0187, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.7476747012342416e-05, + "loss": 4.0332, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.7468361064831896e-05, + "loss": 4.0153, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.7459975117321376e-05, + "loss": 4.0297, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.745158916981085e-05, + "loss": 4.0079, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.744320322230033e-05, + "loss": 4.021, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.743481727478981e-05, + "loss": 3.9999, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.742643132727929e-05, + "loss": 4.017, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.741804537976877e-05, + "loss": 4.0142, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.740965943225825e-05, + "loss": 4.0125, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.7401289863551465e-05, + "loss": 4.0213, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.739292029484468e-05, + "loss": 4.0019, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.7384534347334154e-05, + "loss": 3.9977, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.7376148399823634e-05, + "loss": 3.996, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.7367762452313114e-05, + "loss": 4.004, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.7359376504802594e-05, + "loss": 4.0087, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.7350990557292074e-05, + "loss": 4.0022, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.7342604609781554e-05, + "loss": 4.0041, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.733423504107476e-05, + "loss": 4.0239, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.732584909356424e-05, + "loss": 3.9994, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.731746314605372e-05, + "loss": 3.9946, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.73090771985432e-05, + "loss": 4.0021, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.730070762983642e-05, + "loss": 4.0077, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.72923216823259e-05, + "loss": 3.9908, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.728393573481538e-05, + "loss": 3.9969, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.727554978730486e-05, + "loss": 3.9984, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.726718021859807e-05, + "loss": 3.9948, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.725879427108755e-05, + "loss": 3.9809, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.725040832357703e-05, + "loss": 3.9865, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.724202237606651e-05, + "loss": 3.9889, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.7233652807359716e-05, + "loss": 3.9934, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.7225266859849196e-05, + "loss": 4.0065, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.7216880912338676e-05, + "loss": 3.9845, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.7208494964828156e-05, + "loss": 3.9848, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.720010901731764e-05, + "loss": 3.996, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.719172306980712e-05, + "loss": 3.9793, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.71833371222966e-05, + "loss": 3.9776, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.717496755358981e-05, + "loss": 3.9745, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.716658160607929e-05, + "loss": 3.9827, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.715819565856877e-05, + "loss": 3.9709, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.714980971105825e-05, + "loss": 3.9936, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.714144014235146e-05, + "loss": 3.9745, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.713305419484094e-05, + "loss": 3.9844, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.712466824733042e-05, + "loss": 3.9788, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.71162822998199e-05, + "loss": 3.9783, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.710791273111311e-05, + "loss": 3.9774, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.709952678360259e-05, + "loss": 3.9654, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.709114083609208e-05, + "loss": 3.9623, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.708275488858156e-05, + "loss": 3.9837, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.7074385319874766e-05, + "loss": 3.9745, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.7065999372364246e-05, + "loss": 3.9643, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.7057613424853726e-05, + "loss": 3.9668, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.7049227477343206e-05, + "loss": 3.9747, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.7040857908636415e-05, + "loss": 3.9541, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.7032471961125895e-05, + "loss": 3.9765, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.7024086013615375e-05, + "loss": 3.9645, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.7015700066104855e-05, + "loss": 3.9645, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.7007330497398064e-05, + "loss": 3.9803, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.6998944549887544e-05, + "loss": 3.9573, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.699055860237703e-05, + "loss": 3.9535, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.698217265486651e-05, + "loss": 3.9659, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.697380308615972e-05, + "loss": 3.9483, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.69654171386492e-05, + "loss": 3.9539, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.695703119113868e-05, + "loss": 3.9648, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694864524362816e-05, + "loss": 3.9693, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.694027567492137e-05, + "loss": 3.9537, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.693188972741085e-05, + "loss": 3.9554, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.692352015870406e-05, + "loss": 3.9434, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.691513421119354e-05, + "loss": 3.9656, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.690674826368302e-05, + "loss": 3.9581, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.68983623161725e-05, + "loss": 3.9644, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.6889976368661984e-05, + "loss": 3.9602, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.688159042115146e-05, + "loss": 3.9644, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.687320447364094e-05, + "loss": 3.9693, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.686481852613042e-05, + "loss": 3.9435, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.685644895742363e-05, + "loss": 3.9572, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.6848063009913106e-05, + "loss": 3.9608, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.6839677062402586e-05, + "loss": 3.944, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.6831291114892066e-05, + "loss": 3.9648, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.6822905167381546e-05, + "loss": 3.9586, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.6814519219871026e-05, + "loss": 3.9626, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.6806133272360506e-05, + "loss": 3.9618, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.6797747324849986e-05, + "loss": 3.9387, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.67893777561432e-05, + "loss": 3.9516, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.678099180863268e-05, + "loss": 3.9484, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.677260586112216e-05, + "loss": 3.9564, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.676421991361164e-05, + "loss": 3.9478, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.675585034490485e-05, + "loss": 3.9475, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.674746439739433e-05, + "loss": 3.9522, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.673907844988381e-05, + "loss": 3.9495, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.673069250237329e-05, + "loss": 3.9351, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.67223229336665e-05, + "loss": 3.9416, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.671393698615598e-05, + "loss": 3.9505, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.670556741744919e-05, + "loss": 3.9569, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.6697181469938675e-05, + "loss": 3.9474, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.6688795522428155e-05, + "loss": 3.9269, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.6680409574917635e-05, + "loss": 3.9391, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.6672023627407115e-05, + "loss": 3.9474, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.6663654058700324e-05, + "loss": 3.944, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.6655268111189804e-05, + "loss": 3.9414, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.6646882163679284e-05, + "loss": 3.9361, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.6638496216168764e-05, + "loss": 3.9264, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.6630110268658244e-05, + "loss": 3.9458, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.662174069995145e-05, + "loss": 3.9211, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.661335475244093e-05, + "loss": 3.9351, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.660496880493041e-05, + "loss": 3.9315, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.659658285741989e-05, + "loss": 3.943, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.658821328871311e-05, + "loss": 3.9272, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.657982734120259e-05, + "loss": 3.9401, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.657144139369207e-05, + "loss": 3.9298, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.656305544618155e-05, + "loss": 3.9292, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.655466949867103e-05, + "loss": 3.9344, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.654628355116051e-05, + "loss": 3.9229, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.653789760364999e-05, + "loss": 3.9399, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.652951165613947e-05, + "loss": 3.9386, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.652115846623641e-05, + "loss": 3.9365, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.651277251872589e-05, + "loss": 3.9297, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.650438657121537e-05, + "loss": 3.9341, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.649600062370485e-05, + "loss": 3.9345, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.648761467619433e-05, + "loss": 3.9155, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.647922872868381e-05, + "loss": 3.9416, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.6470842781173294e-05, + "loss": 3.9279, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.646245683366277e-05, + "loss": 3.9346, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.645408726495598e-05, + "loss": 3.9222, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.644570131744546e-05, + "loss": 3.9244, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.643731536993494e-05, + "loss": 3.9128, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.6428929422424416e-05, + "loss": 3.9204, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.642055985371763e-05, + "loss": 3.919, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.641217390620711e-05, + "loss": 3.9338, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.640378795869659e-05, + "loss": 3.9356, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.6395402011186065e-05, + "loss": 3.9235, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.638703244247928e-05, + "loss": 3.9154, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.637864649496876e-05, + "loss": 3.9256, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.637026054745824e-05, + "loss": 3.9266, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.636187459994772e-05, + "loss": 3.9315, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.6353505031240936e-05, + "loss": 3.9275, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.6345119083730416e-05, + "loss": 3.9174, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.6336749515023625e-05, + "loss": 3.9248, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.6328363567513105e-05, + "loss": 3.9292, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.6319977620002585e-05, + "loss": 3.915, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.631159167249206e-05, + "loss": 3.9225, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.630320572498154e-05, + "loss": 3.9175, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.629481977747102e-05, + "loss": 3.9107, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.6286450208764234e-05, + "loss": 3.9311, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.6278064261253714e-05, + "loss": 3.9154, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.6269678313743194e-05, + "loss": 3.912, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.6261292366232674e-05, + "loss": 3.9144, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.6252906418722154e-05, + "loss": 3.91, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 3.9538862705230713, + "eval_runtime": 302.4885, + "eval_samples_per_second": 1261.506, + "eval_steps_per_second": 39.423, + "step": 228960 + }, + { + "epoch": 1.0, + "learning_rate": 4.624453685001536e-05, + "loss": 3.9037, + "step": 229376 + }, + { + "epoch": 1.0, + "learning_rate": 4.623615090250484e-05, + "loss": 3.9107, + "step": 229888 + }, + { + "epoch": 1.0, + "learning_rate": 4.622776495499432e-05, + "loss": 3.9273, + "step": 230400 + }, + { + "epoch": 1.0, + "learning_rate": 4.62193790074838e-05, + "loss": 3.9119, + "step": 230912 + }, + { + "epoch": 1.0, + "learning_rate": 4.621099305997328e-05, + "loss": 3.9315, + "step": 231424 + }, + { + "epoch": 1.0, + "learning_rate": 4.620260711246276e-05, + "loss": 3.8984, + "step": 231936 + }, + { + "epoch": 1.0, + "learning_rate": 4.619422116495224e-05, + "loss": 3.9195, + "step": 232448 + }, + { + "epoch": 1.0, + "learning_rate": 4.618585159624545e-05, + "loss": 3.8957, + "step": 232960 + }, + { + "epoch": 1.0, + "learning_rate": 4.617746564873494e-05, + "loss": 3.9131, + "step": 233472 + }, + { + "epoch": 1.0, + "learning_rate": 4.616907970122442e-05, + "loss": 3.9148, + "step": 233984 + }, + { + "epoch": 1.0, + "learning_rate": 4.61606937537139e-05, + "loss": 3.9083, + "step": 234496 + }, + { + "epoch": 1.0, + "learning_rate": 4.615230780620338e-05, + "loss": 3.9165, + "step": 235008 + }, + { + "epoch": 1.0, + "learning_rate": 4.614393823749659e-05, + "loss": 3.8992, + "step": 235520 + }, + { + "epoch": 1.0, + "learning_rate": 4.613555228998607e-05, + "loss": 3.8971, + "step": 236032 + }, + { + "epoch": 1.0, + "learning_rate": 4.612716634247555e-05, + "loss": 3.8962, + "step": 236544 + }, + { + "epoch": 1.0, + "learning_rate": 4.611878039496503e-05, + "loss": 3.9008, + "step": 237056 + }, + { + "epoch": 1.0, + "learning_rate": 4.6110410826258237e-05, + "loss": 3.9076, + "step": 237568 + }, + { + "epoch": 1.0, + "learning_rate": 4.6102024878747717e-05, + "loss": 3.9012, + "step": 238080 + }, + { + "epoch": 1.0, + "learning_rate": 4.6093638931237196e-05, + "loss": 3.9041, + "step": 238592 + }, + { + "epoch": 1.0, + "learning_rate": 4.6085252983726676e-05, + "loss": 3.9225, + "step": 239104 + }, + { + "epoch": 1.0, + "learning_rate": 4.607688341501989e-05, + "loss": 3.9027, + "step": 239616 + }, + { + "epoch": 1.0, + "learning_rate": 4.606849746750937e-05, + "loss": 3.8997, + "step": 240128 + }, + { + "epoch": 1.0, + "learning_rate": 4.606011151999885e-05, + "loss": 3.9046, + "step": 240640 + }, + { + "epoch": 1.0, + "learning_rate": 4.605172557248833e-05, + "loss": 3.9062, + "step": 241152 + }, + { + "epoch": 1.0, + "learning_rate": 4.604335600378154e-05, + "loss": 3.8915, + "step": 241664 + }, + { + "epoch": 1.0, + "learning_rate": 4.603497005627102e-05, + "loss": 3.9013, + "step": 242176 + }, + { + "epoch": 1.0, + "learning_rate": 4.60265841087605e-05, + "loss": 3.9022, + "step": 242688 + }, + { + "epoch": 1.0, + "learning_rate": 4.601819816124998e-05, + "loss": 3.8943, + "step": 243200 + }, + { + "epoch": 1.0, + "learning_rate": 4.600981221373946e-05, + "loss": 3.8868, + "step": 243712 + }, + { + "epoch": 1.01, + "learning_rate": 4.600142626622894e-05, + "loss": 3.8853, + "step": 244224 + }, + { + "epoch": 1.01, + "learning_rate": 4.599305669752215e-05, + "loss": 3.8975, + "step": 244736 + }, + { + "epoch": 1.01, + "learning_rate": 4.598467075001163e-05, + "loss": 3.8959, + "step": 245248 + }, + { + "epoch": 1.01, + "learning_rate": 4.597628480250111e-05, + "loss": 3.9098, + "step": 245760 + }, + { + "epoch": 1.01, + "learning_rate": 4.596789885499059e-05, + "loss": 3.8971, + "step": 246272 + }, + { + "epoch": 1.01, + "learning_rate": 4.595951290748008e-05, + "loss": 3.8862, + "step": 246784 + }, + { + "epoch": 1.01, + "learning_rate": 4.5951143338773286e-05, + "loss": 3.8985, + "step": 247296 + }, + { + "epoch": 1.01, + "learning_rate": 4.5942757391262766e-05, + "loss": 3.889, + "step": 247808 + }, + { + "epoch": 1.01, + "learning_rate": 4.5934371443752246e-05, + "loss": 3.8807, + "step": 248320 + }, + { + "epoch": 1.01, + "learning_rate": 4.5925985496241726e-05, + "loss": 3.8831, + "step": 248832 + }, + { + "epoch": 1.01, + "learning_rate": 4.59175995487312e-05, + "loss": 3.887, + "step": 249344 + }, + { + "epoch": 1.01, + "learning_rate": 4.590921360122068e-05, + "loss": 3.8802, + "step": 249856 + }, + { + "epoch": 1.01, + "learning_rate": 4.590082765371016e-05, + "loss": 3.9009, + "step": 250368 + }, + { + "epoch": 1.01, + "learning_rate": 4.589245808500337e-05, + "loss": 3.8842, + "step": 250880 + }, + { + "epoch": 1.01, + "learning_rate": 4.5884088516296584e-05, + "loss": 3.8912, + "step": 251392 + }, + { + "epoch": 1.01, + "learning_rate": 4.5875702568786064e-05, + "loss": 3.8897, + "step": 251904 + }, + { + "epoch": 1.01, + "learning_rate": 4.5867316621275544e-05, + "loss": 3.8834, + "step": 252416 + }, + { + "epoch": 1.01, + "learning_rate": 4.5858930673765024e-05, + "loss": 3.8882, + "step": 252928 + }, + { + "epoch": 1.01, + "learning_rate": 4.5850544726254504e-05, + "loss": 3.8727, + "step": 253440 + }, + { + "epoch": 1.01, + "learning_rate": 4.5842158778743984e-05, + "loss": 3.8633, + "step": 253952 + }, + { + "epoch": 1.01, + "learning_rate": 4.5833772831233464e-05, + "loss": 3.8964, + "step": 254464 + }, + { + "epoch": 1.01, + "learning_rate": 4.582540326252667e-05, + "loss": 3.8859, + "step": 254976 + }, + { + "epoch": 1.01, + "learning_rate": 4.581701731501615e-05, + "loss": 3.8793, + "step": 255488 + }, + { + "epoch": 1.01, + "learning_rate": 4.580863136750563e-05, + "loss": 3.8741, + "step": 256000 + }, + { + "epoch": 1.01, + "learning_rate": 4.580024541999511e-05, + "loss": 3.8816, + "step": 256512 + }, + { + "epoch": 1.01, + "learning_rate": 4.579187585128832e-05, + "loss": 3.8669, + "step": 257024 + }, + { + "epoch": 1.01, + "learning_rate": 4.57834899037778e-05, + "loss": 3.8855, + "step": 257536 + }, + { + "epoch": 1.01, + "learning_rate": 4.577510395626728e-05, + "loss": 3.8802, + "step": 258048 + }, + { + "epoch": 1.01, + "learning_rate": 4.576671800875677e-05, + "loss": 3.878, + "step": 258560 + }, + { + "epoch": 1.01, + "learning_rate": 4.575833206124625e-05, + "loss": 3.8896, + "step": 259072 + }, + { + "epoch": 1.01, + "learning_rate": 4.574994611373573e-05, + "loss": 3.8682, + "step": 259584 + }, + { + "epoch": 1.01, + "learning_rate": 4.574156016622521e-05, + "loss": 3.8664, + "step": 260096 + }, + { + "epoch": 1.01, + "learning_rate": 4.573319059751842e-05, + "loss": 3.8826, + "step": 260608 + }, + { + "epoch": 1.01, + "learning_rate": 4.57248046500079e-05, + "loss": 3.8575, + "step": 261120 + }, + { + "epoch": 1.01, + "learning_rate": 4.571641870249738e-05, + "loss": 3.863, + "step": 261632 + }, + { + "epoch": 1.01, + "learning_rate": 4.570803275498686e-05, + "loss": 3.8807, + "step": 262144 + }, + { + "epoch": 1.01, + "learning_rate": 4.569964680747634e-05, + "loss": 3.8832, + "step": 262656 + }, + { + "epoch": 1.01, + "learning_rate": 4.569126085996582e-05, + "loss": 3.8624, + "step": 263168 + }, + { + "epoch": 1.01, + "learning_rate": 4.56828749124553e-05, + "loss": 3.8739, + "step": 263680 + }, + { + "epoch": 1.01, + "learning_rate": 4.567448896494478e-05, + "loss": 3.8554, + "step": 264192 + }, + { + "epoch": 1.01, + "learning_rate": 4.5666119396237986e-05, + "loss": 3.8799, + "step": 264704 + }, + { + "epoch": 1.01, + "learning_rate": 4.5657733448727466e-05, + "loss": 3.8728, + "step": 265216 + }, + { + "epoch": 1.01, + "learning_rate": 4.5649347501216946e-05, + "loss": 3.8802, + "step": 265728 + }, + { + "epoch": 1.01, + "learning_rate": 4.564096155370643e-05, + "loss": 3.8711, + "step": 266240 + }, + { + "epoch": 1.01, + "learning_rate": 4.563257560619591e-05, + "loss": 3.8786, + "step": 266752 + }, + { + "epoch": 1.01, + "learning_rate": 4.562420603748912e-05, + "loss": 3.8855, + "step": 267264 + }, + { + "epoch": 1.01, + "learning_rate": 4.56158200899786e-05, + "loss": 3.8558, + "step": 267776 + }, + { + "epoch": 1.01, + "learning_rate": 4.560743414246808e-05, + "loss": 3.8762, + "step": 268288 + }, + { + "epoch": 1.01, + "learning_rate": 4.5599048194957555e-05, + "loss": 3.8783, + "step": 268800 + }, + { + "epoch": 1.01, + "learning_rate": 4.5590662247447035e-05, + "loss": 3.8542, + "step": 269312 + }, + { + "epoch": 1.01, + "learning_rate": 4.558229267874025e-05, + "loss": 3.8836, + "step": 269824 + }, + { + "epoch": 1.01, + "learning_rate": 4.557390673122973e-05, + "loss": 3.8754, + "step": 270336 + }, + { + "epoch": 1.01, + "learning_rate": 4.5565520783719204e-05, + "loss": 3.8765, + "step": 270848 + }, + { + "epoch": 1.01, + "learning_rate": 4.5557134836208684e-05, + "loss": 3.8805, + "step": 271360 + }, + { + "epoch": 1.01, + "learning_rate": 4.554874888869817e-05, + "loss": 3.8586, + "step": 271872 + }, + { + "epoch": 1.01, + "learning_rate": 4.554036294118765e-05, + "loss": 3.8616, + "step": 272384 + }, + { + "epoch": 1.01, + "learning_rate": 4.553199337248086e-05, + "loss": 3.8662, + "step": 272896 + }, + { + "epoch": 1.01, + "learning_rate": 4.552360742497034e-05, + "loss": 3.8729, + "step": 273408 + }, + { + "epoch": 1.01, + "learning_rate": 4.551522147745982e-05, + "loss": 3.8638, + "step": 273920 + }, + { + "epoch": 1.01, + "learning_rate": 4.55068355299493e-05, + "loss": 3.8668, + "step": 274432 + }, + { + "epoch": 1.02, + "learning_rate": 4.549844958243878e-05, + "loss": 3.8659, + "step": 274944 + }, + { + "epoch": 1.02, + "learning_rate": 4.549008001373199e-05, + "loss": 3.8741, + "step": 275456 + }, + { + "epoch": 1.02, + "learning_rate": 4.548169406622147e-05, + "loss": 3.8544, + "step": 275968 + }, + { + "epoch": 1.02, + "learning_rate": 4.547330811871095e-05, + "loss": 3.8592, + "step": 276480 + }, + { + "epoch": 1.02, + "learning_rate": 4.546492217120043e-05, + "loss": 3.8692, + "step": 276992 + }, + { + "epoch": 1.02, + "learning_rate": 4.545655260249364e-05, + "loss": 3.8778, + "step": 277504 + }, + { + "epoch": 1.02, + "learning_rate": 4.5448166654983124e-05, + "loss": 3.8687, + "step": 278016 + }, + { + "epoch": 1.02, + "learning_rate": 4.5439780707472604e-05, + "loss": 3.8462, + "step": 278528 + }, + { + "epoch": 1.02, + "learning_rate": 4.5431394759962084e-05, + "loss": 3.8575, + "step": 279040 + }, + { + "epoch": 1.02, + "learning_rate": 4.542302519125529e-05, + "loss": 3.8649, + "step": 279552 + }, + { + "epoch": 1.02, + "learning_rate": 4.541463924374477e-05, + "loss": 3.8661, + "step": 280064 + }, + { + "epoch": 1.02, + "learning_rate": 4.540625329623425e-05, + "loss": 3.8652, + "step": 280576 + }, + { + "epoch": 1.02, + "learning_rate": 4.539786734872373e-05, + "loss": 3.8569, + "step": 281088 + }, + { + "epoch": 1.02, + "learning_rate": 4.538949778001694e-05, + "loss": 3.8476, + "step": 281600 + }, + { + "epoch": 1.02, + "learning_rate": 4.538111183250642e-05, + "loss": 3.864, + "step": 282112 + }, + { + "epoch": 1.02, + "learning_rate": 4.53727258849959e-05, + "loss": 3.8461, + "step": 282624 + }, + { + "epoch": 1.02, + "learning_rate": 4.536433993748538e-05, + "loss": 3.8556, + "step": 283136 + }, + { + "epoch": 1.02, + "learning_rate": 4.535597036877859e-05, + "loss": 3.85, + "step": 283648 + }, + { + "epoch": 1.02, + "learning_rate": 4.534758442126808e-05, + "loss": 3.8645, + "step": 284160 + }, + { + "epoch": 1.02, + "learning_rate": 4.533919847375756e-05, + "loss": 3.8494, + "step": 284672 + }, + { + "epoch": 1.02, + "learning_rate": 4.533081252624704e-05, + "loss": 3.8662, + "step": 285184 + }, + { + "epoch": 1.02, + "learning_rate": 4.532242657873652e-05, + "loss": 3.8469, + "step": 285696 + }, + { + "epoch": 1.02, + "learning_rate": 4.531405701002973e-05, + "loss": 3.8539, + "step": 286208 + }, + { + "epoch": 1.02, + "learning_rate": 4.530567106251921e-05, + "loss": 3.8554, + "step": 286720 + }, + { + "epoch": 1.02, + "learning_rate": 4.529728511500869e-05, + "loss": 3.8511, + "step": 287232 + }, + { + "epoch": 1.02, + "learning_rate": 4.5288899167498167e-05, + "loss": 3.8584, + "step": 287744 + }, + { + "epoch": 1.02, + "learning_rate": 4.5280529598791376e-05, + "loss": 3.8647, + "step": 288256 + }, + { + "epoch": 1.02, + "learning_rate": 4.5272143651280856e-05, + "loss": 3.8579, + "step": 288768 + }, + { + "epoch": 1.02, + "learning_rate": 4.5263757703770336e-05, + "loss": 3.852, + "step": 289280 + }, + { + "epoch": 1.02, + "learning_rate": 4.5255371756259816e-05, + "loss": 3.8574, + "step": 289792 + }, + { + "epoch": 1.02, + "learning_rate": 4.5246985808749295e-05, + "loss": 3.858, + "step": 290304 + }, + { + "epoch": 1.02, + "learning_rate": 4.523861624004251e-05, + "loss": 3.8398, + "step": 290816 + }, + { + "epoch": 1.02, + "learning_rate": 4.523023029253199e-05, + "loss": 3.8636, + "step": 291328 + }, + { + "epoch": 1.02, + "learning_rate": 4.522184434502147e-05, + "loss": 3.8486, + "step": 291840 + }, + { + "epoch": 1.02, + "learning_rate": 4.521345839751095e-05, + "loss": 3.8621, + "step": 292352 + }, + { + "epoch": 1.02, + "learning_rate": 4.520507245000043e-05, + "loss": 3.85, + "step": 292864 + }, + { + "epoch": 1.02, + "learning_rate": 4.519670288129364e-05, + "loss": 3.8495, + "step": 293376 + }, + { + "epoch": 1.02, + "learning_rate": 4.518831693378312e-05, + "loss": 3.8367, + "step": 293888 + }, + { + "epoch": 1.02, + "learning_rate": 4.51799309862726e-05, + "loss": 3.8497, + "step": 294400 + }, + { + "epoch": 1.02, + "learning_rate": 4.517154503876208e-05, + "loss": 3.8454, + "step": 294912 + }, + { + "epoch": 1.02, + "learning_rate": 4.516317547005529e-05, + "loss": 3.8537, + "step": 295424 + }, + { + "epoch": 1.02, + "learning_rate": 4.515478952254477e-05, + "loss": 3.859, + "step": 295936 + }, + { + "epoch": 1.02, + "learning_rate": 4.514640357503425e-05, + "loss": 3.8537, + "step": 296448 + }, + { + "epoch": 1.02, + "learning_rate": 4.513801762752373e-05, + "loss": 3.8374, + "step": 296960 + }, + { + "epoch": 1.02, + "learning_rate": 4.512963168001321e-05, + "loss": 3.8531, + "step": 297472 + }, + { + "epoch": 1.02, + "learning_rate": 4.5121262111306425e-05, + "loss": 3.8536, + "step": 297984 + }, + { + "epoch": 1.02, + "learning_rate": 4.5112876163795905e-05, + "loss": 3.8569, + "step": 298496 + }, + { + "epoch": 1.02, + "learning_rate": 4.5104490216285385e-05, + "loss": 3.8533, + "step": 299008 + }, + { + "epoch": 1.02, + "learning_rate": 4.5096104268774865e-05, + "loss": 3.8444, + "step": 299520 + }, + { + "epoch": 1.02, + "learning_rate": 4.5087734700068074e-05, + "loss": 3.8488, + "step": 300032 + }, + { + "epoch": 1.02, + "learning_rate": 4.5079348752557554e-05, + "loss": 3.8579, + "step": 300544 + }, + { + "epoch": 1.02, + "learning_rate": 4.5070962805047034e-05, + "loss": 3.8412, + "step": 301056 + }, + { + "epoch": 1.02, + "learning_rate": 4.5062576857536514e-05, + "loss": 3.8505, + "step": 301568 + }, + { + "epoch": 1.02, + "learning_rate": 4.505420728882972e-05, + "loss": 3.8401, + "step": 302080 + }, + { + "epoch": 1.02, + "learning_rate": 4.50458213413192e-05, + "loss": 3.8439, + "step": 302592 + }, + { + "epoch": 1.02, + "learning_rate": 4.503743539380868e-05, + "loss": 3.8579, + "step": 303104 + }, + { + "epoch": 1.02, + "learning_rate": 4.502904944629816e-05, + "loss": 3.8443, + "step": 303616 + }, + { + "epoch": 1.02, + "learning_rate": 4.502066349878764e-05, + "loss": 3.8407, + "step": 304128 + }, + { + "epoch": 1.02, + "learning_rate": 4.501229393008086e-05, + "loss": 3.8382, + "step": 304640 + }, + { + "epoch": 1.02, + "learning_rate": 4.500390798257034e-05, + "loss": 3.842, + "step": 305152 + }, + { + "epoch": 1.03, + "eval_loss": 3.9126405715942383, + "eval_runtime": 301.972, + "eval_samples_per_second": 1263.664, + "eval_steps_per_second": 39.49, + "step": 305280 + }, + { + "epoch": 0.0, + "learning_rate": 4.499552203505981e-05, + "loss": 3.8269, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.498713608754929e-05, + "loss": 3.8402, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.497875014003877e-05, + "loss": 3.8511, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.497036419252825e-05, + "loss": 3.8433, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.496197824501773e-05, + "loss": 3.8576, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.495359229750721e-05, + "loss": 3.8348, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.494520634999669e-05, + "loss": 3.8434, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.493682040248617e-05, + "loss": 3.8299, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.492845083377939e-05, + "loss": 3.8385, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.492006488626887e-05, + "loss": 3.8445, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.491167893875835e-05, + "loss": 3.8406, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.490329299124783e-05, + "loss": 3.8472, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.4894923422541036e-05, + "loss": 3.8299, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.4886537475030516e-05, + "loss": 3.8302, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.4878151527519996e-05, + "loss": 3.8279, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.4869765580009476e-05, + "loss": 3.8321, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.4861396011302685e-05, + "loss": 3.84, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.4853010063792165e-05, + "loss": 3.8319, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.4844624116281645e-05, + "loss": 3.8362, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.4836238168771125e-05, + "loss": 3.8541, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.482786860006434e-05, + "loss": 3.8363, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.481948265255382e-05, + "loss": 3.8328, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.48110967050433e-05, + "loss": 3.8348, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.480271075753278e-05, + "loss": 3.8362, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.479434118882599e-05, + "loss": 3.8243, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.478595524131547e-05, + "loss": 3.8355, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.477756929380495e-05, + "loss": 3.8307, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.476918334629443e-05, + "loss": 3.8292, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.476079739878391e-05, + "loss": 3.8197, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.475242783007712e-05, + "loss": 3.8227, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.47440418825666e-05, + "loss": 3.8267, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.473565593505608e-05, + "loss": 3.8305, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.472726998754556e-05, + "loss": 3.8398, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.4718900418838775e-05, + "loss": 3.8299, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.4710514471328255e-05, + "loss": 3.8175, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.4702128523817734e-05, + "loss": 3.8322, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.4693742576307214e-05, + "loss": 3.8296, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.4685373007600424e-05, + "loss": 3.8124, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.4676987060089903e-05, + "loss": 3.8148, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.4668601112579383e-05, + "loss": 3.824, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.466021516506886e-05, + "loss": 3.8143, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.465182921755834e-05, + "loss": 3.8357, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.464345964885155e-05, + "loss": 3.8213, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.463507370134103e-05, + "loss": 3.8225, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.462668775383051e-05, + "loss": 3.8243, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.461830180631999e-05, + "loss": 3.8252, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.460993223761321e-05, + "loss": 3.8232, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.460154629010269e-05, + "loss": 3.8089, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.459316034259217e-05, + "loss": 3.7961, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.458477439508165e-05, + "loss": 3.8367, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.457640482637486e-05, + "loss": 3.817, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.456801887886434e-05, + "loss": 3.8192, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.455963293135382e-05, + "loss": 3.8147, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.455124698384329e-05, + "loss": 3.8109, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.4542877415136506e-05, + "loss": 3.8052, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.4534491467625986e-05, + "loss": 3.8196, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.4526105520115466e-05, + "loss": 3.8166, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.4517719572604946e-05, + "loss": 3.8133, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.450935000389816e-05, + "loss": 3.8315, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.450096405638764e-05, + "loss": 3.8024, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.449257810887712e-05, + "loss": 3.8005, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.4484192161366595e-05, + "loss": 3.8238, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.447582259265981e-05, + "loss": 3.7922, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.446743664514929e-05, + "loss": 3.7988, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.4459050697638764e-05, + "loss": 3.8222, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.4450664750128244e-05, + "loss": 3.8223, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.4442278802617724e-05, + "loss": 3.802, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.443390923391094e-05, + "loss": 3.8124, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.442552328640042e-05, + "loss": 3.7958, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.4417153717693636e-05, + "loss": 3.8144, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.4408767770183116e-05, + "loss": 3.8104, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.4400381822672595e-05, + "loss": 3.8161, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.439199587516207e-05, + "loss": 3.8095, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.438360992765155e-05, + "loss": 3.8183, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.437522398014103e-05, + "loss": 3.825, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.436683803263051e-05, + "loss": 3.7988, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.435845208511999e-05, + "loss": 3.8108, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.43500825164132e-05, + "loss": 3.8182, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.434169656890268e-05, + "loss": 3.7938, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.433331062139216e-05, + "loss": 3.8203, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.432492467388164e-05, + "loss": 3.8186, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.431655510517485e-05, + "loss": 3.8163, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.430816915766433e-05, + "loss": 3.82, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.429978321015381e-05, + "loss": 3.8021, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.429139726264329e-05, + "loss": 3.7982, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.42830276939365e-05, + "loss": 3.8073, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.427464174642598e-05, + "loss": 3.817, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.426625579891546e-05, + "loss": 3.8087, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.425786985140494e-05, + "loss": 3.8042, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.424950028269815e-05, + "loss": 3.8039, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.424111433518763e-05, + "loss": 3.8148, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.423272838767711e-05, + "loss": 3.7997, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.422434244016659e-05, + "loss": 3.7994, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.421595649265607e-05, + "loss": 3.808, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.4207603302753016e-05, + "loss": 3.8187, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.4199217355242496e-05, + "loss": 3.8094, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.4190831407731976e-05, + "loss": 3.7919, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.4182445460221456e-05, + "loss": 3.7978, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.4174059512710936e-05, + "loss": 3.8051, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.4165673565200416e-05, + "loss": 3.8091, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.4157287617689896e-05, + "loss": 3.805, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.4148901670179376e-05, + "loss": 3.8023, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.4140532101472585e-05, + "loss": 3.7899, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.4132146153962065e-05, + "loss": 3.8009, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.4123760206451545e-05, + "loss": 3.7899, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.4115374258941025e-05, + "loss": 3.8026, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.410700469023424e-05, + "loss": 3.7852, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.409861874272372e-05, + "loss": 3.8148, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.40902327952132e-05, + "loss": 3.7922, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.408184684770268e-05, + "loss": 3.8012, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.407346090019216e-05, + "loss": 3.7946, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.406509133148537e-05, + "loss": 3.7959, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.405670538397485e-05, + "loss": 3.798, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.404831943646433e-05, + "loss": 3.7952, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.403993348895381e-05, + "loss": 3.7998, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.403156392024702e-05, + "loss": 3.8074, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.40231779727365e-05, + "loss": 3.7992, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.401479202522598e-05, + "loss": 3.7976, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.4006406077715465e-05, + "loss": 3.7998, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.3998036509008674e-05, + "loss": 3.8053, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.3989650561498154e-05, + "loss": 3.7804, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.3981264613987634e-05, + "loss": 3.8073, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.3972878666477114e-05, + "loss": 3.791, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.396450909777032e-05, + "loss": 3.805, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.39561231502598e-05, + "loss": 3.7916, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.394773720274928e-05, + "loss": 3.7958, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.393935125523876e-05, + "loss": 3.7857, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.393098168653197e-05, + "loss": 3.7916, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.392259573902145e-05, + "loss": 3.7943, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.391420979151093e-05, + "loss": 3.7971, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.390582384400042e-05, + "loss": 3.7991, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.38974378964899e-05, + "loss": 3.8028, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.388906832778311e-05, + "loss": 3.7809, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.388068238027259e-05, + "loss": 3.7966, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.387229643276207e-05, + "loss": 3.8018, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.386391048525155e-05, + "loss": 3.7996, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.385554091654476e-05, + "loss": 3.795, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.384715496903424e-05, + "loss": 3.7967, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.383876902152372e-05, + "loss": 3.7903, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.38303830740132e-05, + "loss": 3.8036, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.3822013505306406e-05, + "loss": 3.7849, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.3813627557795886e-05, + "loss": 3.7967, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.380524161028537e-05, + "loss": 3.7866, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.3796855662774846e-05, + "loss": 3.7893, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.378848609406806e-05, + "loss": 3.803, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.378010014655754e-05, + "loss": 3.7929, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.377171419904702e-05, + "loss": 3.7885, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.3763328251536495e-05, + "loss": 3.7802, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.375495868282971e-05, + "loss": 3.7897, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 3.886935234069824, + "eval_runtime": 302.3733, + "eval_samples_per_second": 1261.986, + "eval_steps_per_second": 39.438, + "step": 381600 + }, + { + "epoch": 1.0, + "learning_rate": 4.374657273531919e-05, + "loss": 3.7834, + "step": 381952 + }, + { + "epoch": 1.0, + "learning_rate": 4.373818678780867e-05, + "loss": 3.7835, + "step": 382464 + }, + { + "epoch": 1.0, + "learning_rate": 4.3729800840298144e-05, + "loss": 3.7993, + "step": 382976 + }, + { + "epoch": 1.0, + "learning_rate": 4.372143127159136e-05, + "loss": 3.7898, + "step": 383488 + }, + { + "epoch": 1.0, + "learning_rate": 4.371304532408084e-05, + "loss": 3.8058, + "step": 384000 + }, + { + "epoch": 1.0, + "learning_rate": 4.370465937657032e-05, + "loss": 3.7817, + "step": 384512 + }, + { + "epoch": 1.0, + "learning_rate": 4.36962734290598e-05, + "loss": 3.7842, + "step": 385024 + }, + { + "epoch": 1.0, + "learning_rate": 4.368788748154928e-05, + "loss": 3.7809, + "step": 385536 + }, + { + "epoch": 1.0, + "learning_rate": 4.3679517912842495e-05, + "loss": 3.7821, + "step": 386048 + }, + { + "epoch": 1.0, + "learning_rate": 4.3671148344135704e-05, + "loss": 3.7915, + "step": 386560 + }, + { + "epoch": 1.0, + "learning_rate": 4.3662762396625184e-05, + "loss": 3.7913, + "step": 387072 + }, + { + "epoch": 1.0, + "learning_rate": 4.3654376449114664e-05, + "loss": 3.7887, + "step": 387584 + }, + { + "epoch": 1.0, + "learning_rate": 4.3645990501604144e-05, + "loss": 3.7831, + "step": 388096 + }, + { + "epoch": 1.0, + "learning_rate": 4.363760455409362e-05, + "loss": 3.7771, + "step": 388608 + }, + { + "epoch": 1.0, + "learning_rate": 4.36292186065831e-05, + "loss": 3.7753, + "step": 389120 + }, + { + "epoch": 1.0, + "learning_rate": 4.362083265907258e-05, + "loss": 3.7795, + "step": 389632 + }, + { + "epoch": 1.0, + "learning_rate": 4.361246309036579e-05, + "loss": 3.7855, + "step": 390144 + }, + { + "epoch": 1.0, + "learning_rate": 4.360407714285527e-05, + "loss": 3.7817, + "step": 390656 + }, + { + "epoch": 1.0, + "learning_rate": 4.359569119534475e-05, + "loss": 3.7854, + "step": 391168 + }, + { + "epoch": 1.0, + "learning_rate": 4.358730524783423e-05, + "loss": 3.7994, + "step": 391680 + }, + { + "epoch": 1.0, + "learning_rate": 4.357891930032371e-05, + "loss": 3.7879, + "step": 392192 + }, + { + "epoch": 1.0, + "learning_rate": 4.357054973161692e-05, + "loss": 3.7747, + "step": 392704 + }, + { + "epoch": 1.0, + "learning_rate": 4.35621637841064e-05, + "loss": 3.7834, + "step": 393216 + }, + { + "epoch": 1.0, + "learning_rate": 4.355377783659588e-05, + "loss": 3.7839, + "step": 393728 + }, + { + "epoch": 1.0, + "learning_rate": 4.354540826788909e-05, + "loss": 3.7748, + "step": 394240 + }, + { + "epoch": 1.0, + "learning_rate": 4.353702232037857e-05, + "loss": 3.7847, + "step": 394752 + }, + { + "epoch": 1.0, + "learning_rate": 4.352863637286805e-05, + "loss": 3.7804, + "step": 395264 + }, + { + "epoch": 1.0, + "learning_rate": 4.352025042535753e-05, + "loss": 3.7795, + "step": 395776 + }, + { + "epoch": 1.0, + "learning_rate": 4.351186447784701e-05, + "loss": 3.7738, + "step": 396288 + }, + { + "epoch": 1.0, + "learning_rate": 4.350349490914023e-05, + "loss": 3.7658, + "step": 396800 + }, + { + "epoch": 1.01, + "learning_rate": 4.349510896162971e-05, + "loss": 3.7762, + "step": 397312 + }, + { + "epoch": 1.01, + "learning_rate": 4.3486723014119187e-05, + "loss": 3.7794, + "step": 397824 + }, + { + "epoch": 1.01, + "learning_rate": 4.3478337066608667e-05, + "loss": 3.7873, + "step": 398336 + }, + { + "epoch": 1.01, + "learning_rate": 4.3469967497901876e-05, + "loss": 3.7821, + "step": 398848 + }, + { + "epoch": 1.01, + "learning_rate": 4.3461581550391356e-05, + "loss": 3.7656, + "step": 399360 + }, + { + "epoch": 1.01, + "learning_rate": 4.3453195602880836e-05, + "loss": 3.786, + "step": 399872 + }, + { + "epoch": 1.01, + "learning_rate": 4.3444809655370316e-05, + "loss": 3.7766, + "step": 400384 + }, + { + "epoch": 1.01, + "learning_rate": 4.3436440086663525e-05, + "loss": 3.7583, + "step": 400896 + }, + { + "epoch": 1.01, + "learning_rate": 4.3428054139153005e-05, + "loss": 3.7703, + "step": 401408 + }, + { + "epoch": 1.01, + "learning_rate": 4.3419668191642485e-05, + "loss": 3.7704, + "step": 401920 + }, + { + "epoch": 1.01, + "learning_rate": 4.34112986229357e-05, + "loss": 3.7673, + "step": 402432 + }, + { + "epoch": 1.01, + "learning_rate": 4.340291267542518e-05, + "loss": 3.7827, + "step": 402944 + }, + { + "epoch": 1.01, + "learning_rate": 4.339452672791466e-05, + "loss": 3.7719, + "step": 403456 + }, + { + "epoch": 1.01, + "learning_rate": 4.338614078040414e-05, + "loss": 3.7708, + "step": 403968 + }, + { + "epoch": 1.01, + "learning_rate": 4.337777121169735e-05, + "loss": 3.7732, + "step": 404480 + }, + { + "epoch": 1.01, + "learning_rate": 4.336938526418683e-05, + "loss": 3.7735, + "step": 404992 + }, + { + "epoch": 1.01, + "learning_rate": 4.336099931667631e-05, + "loss": 3.7778, + "step": 405504 + }, + { + "epoch": 1.01, + "learning_rate": 4.335261336916579e-05, + "loss": 3.7597, + "step": 406016 + }, + { + "epoch": 1.01, + "learning_rate": 4.3344243800459e-05, + "loss": 3.7421, + "step": 406528 + }, + { + "epoch": 1.01, + "learning_rate": 4.333585785294848e-05, + "loss": 3.789, + "step": 407040 + }, + { + "epoch": 1.01, + "learning_rate": 4.332747190543796e-05, + "loss": 3.7675, + "step": 407552 + }, + { + "epoch": 1.01, + "learning_rate": 4.331908595792744e-05, + "loss": 3.7734, + "step": 408064 + }, + { + "epoch": 1.01, + "learning_rate": 4.3310716389220654e-05, + "loss": 3.7633, + "step": 408576 + }, + { + "epoch": 1.01, + "learning_rate": 4.3302330441710134e-05, + "loss": 3.7625, + "step": 409088 + }, + { + "epoch": 1.01, + "learning_rate": 4.3293944494199614e-05, + "loss": 3.7594, + "step": 409600 + }, + { + "epoch": 1.01, + "learning_rate": 4.3285558546689094e-05, + "loss": 3.7667, + "step": 410112 + }, + { + "epoch": 1.01, + "learning_rate": 4.32771889779823e-05, + "loss": 3.7715, + "step": 410624 + }, + { + "epoch": 1.01, + "learning_rate": 4.326880303047178e-05, + "loss": 3.7601, + "step": 411136 + }, + { + "epoch": 1.01, + "learning_rate": 4.326041708296126e-05, + "loss": 3.7851, + "step": 411648 + }, + { + "epoch": 1.01, + "learning_rate": 4.325203113545074e-05, + "loss": 3.7592, + "step": 412160 + }, + { + "epoch": 1.01, + "learning_rate": 4.324366156674395e-05, + "loss": 3.7505, + "step": 412672 + }, + { + "epoch": 1.01, + "learning_rate": 4.323527561923343e-05, + "loss": 3.7731, + "step": 413184 + }, + { + "epoch": 1.01, + "learning_rate": 4.322688967172291e-05, + "loss": 3.7476, + "step": 413696 + }, + { + "epoch": 1.01, + "learning_rate": 4.321850372421239e-05, + "loss": 3.7483, + "step": 414208 + }, + { + "epoch": 1.01, + "learning_rate": 4.321013415550561e-05, + "loss": 3.7721, + "step": 414720 + }, + { + "epoch": 1.01, + "learning_rate": 4.320174820799509e-05, + "loss": 3.7703, + "step": 415232 + }, + { + "epoch": 1.01, + "learning_rate": 4.319336226048457e-05, + "loss": 3.7562, + "step": 415744 + }, + { + "epoch": 1.01, + "learning_rate": 4.318497631297405e-05, + "loss": 3.7657, + "step": 416256 + }, + { + "epoch": 1.01, + "learning_rate": 4.317660674426726e-05, + "loss": 3.7468, + "step": 416768 + }, + { + "epoch": 1.01, + "learning_rate": 4.316822079675674e-05, + "loss": 3.7676, + "step": 417280 + }, + { + "epoch": 1.01, + "learning_rate": 4.3159834849246217e-05, + "loss": 3.7601, + "step": 417792 + }, + { + "epoch": 1.01, + "learning_rate": 4.3151448901735697e-05, + "loss": 3.77, + "step": 418304 + }, + { + "epoch": 1.01, + "learning_rate": 4.3143079333028906e-05, + "loss": 3.7633, + "step": 418816 + }, + { + "epoch": 1.01, + "learning_rate": 4.3134693385518386e-05, + "loss": 3.7674, + "step": 419328 + }, + { + "epoch": 1.01, + "learning_rate": 4.3126307438007866e-05, + "loss": 3.7756, + "step": 419840 + }, + { + "epoch": 1.01, + "learning_rate": 4.3117921490497346e-05, + "loss": 3.7509, + "step": 420352 + }, + { + "epoch": 1.01, + "learning_rate": 4.310955192179056e-05, + "loss": 3.7653, + "step": 420864 + }, + { + "epoch": 1.01, + "learning_rate": 4.310116597428004e-05, + "loss": 3.7683, + "step": 421376 + }, + { + "epoch": 1.01, + "learning_rate": 4.309278002676952e-05, + "loss": 3.7503, + "step": 421888 + }, + { + "epoch": 1.01, + "learning_rate": 4.3084394079259e-05, + "loss": 3.7712, + "step": 422400 + }, + { + "epoch": 1.01, + "learning_rate": 4.307602451055221e-05, + "loss": 3.7738, + "step": 422912 + }, + { + "epoch": 1.01, + "learning_rate": 4.306763856304169e-05, + "loss": 3.7675, + "step": 423424 + }, + { + "epoch": 1.01, + "learning_rate": 4.305925261553117e-05, + "loss": 3.7774, + "step": 423936 + }, + { + "epoch": 1.01, + "learning_rate": 4.305086666802065e-05, + "loss": 3.7553, + "step": 424448 + }, + { + "epoch": 1.01, + "learning_rate": 4.304249709931386e-05, + "loss": 3.7506, + "step": 424960 + }, + { + "epoch": 1.01, + "learning_rate": 4.303411115180334e-05, + "loss": 3.7622, + "step": 425472 + }, + { + "epoch": 1.01, + "learning_rate": 4.302572520429282e-05, + "loss": 3.7653, + "step": 425984 + }, + { + "epoch": 1.01, + "learning_rate": 4.30173392567823e-05, + "loss": 3.7673, + "step": 426496 + }, + { + "epoch": 1.01, + "learning_rate": 4.3008969688075515e-05, + "loss": 3.7568, + "step": 427008 + }, + { + "epoch": 1.02, + "learning_rate": 4.3000583740564995e-05, + "loss": 3.756, + "step": 427520 + }, + { + "epoch": 1.02, + "learning_rate": 4.2992197793054475e-05, + "loss": 3.7677, + "step": 428032 + }, + { + "epoch": 1.02, + "learning_rate": 4.2983811845543955e-05, + "loss": 3.7546, + "step": 428544 + }, + { + "epoch": 1.02, + "learning_rate": 4.2975442276837164e-05, + "loss": 3.7525, + "step": 429056 + }, + { + "epoch": 1.02, + "learning_rate": 4.2967056329326644e-05, + "loss": 3.7597, + "step": 429568 + }, + { + "epoch": 1.02, + "learning_rate": 4.2958670381816124e-05, + "loss": 3.7743, + "step": 430080 + }, + { + "epoch": 1.02, + "learning_rate": 4.2950284434305604e-05, + "loss": 3.7643, + "step": 430592 + }, + { + "epoch": 1.02, + "learning_rate": 4.294191486559881e-05, + "loss": 3.7448, + "step": 431104 + }, + { + "epoch": 1.02, + "learning_rate": 4.293352891808829e-05, + "loss": 3.7527, + "step": 431616 + }, + { + "epoch": 1.02, + "learning_rate": 4.292514297057777e-05, + "loss": 3.7611, + "step": 432128 + }, + { + "epoch": 1.02, + "learning_rate": 4.291675702306725e-05, + "loss": 3.7636, + "step": 432640 + }, + { + "epoch": 1.02, + "learning_rate": 4.290838745436047e-05, + "loss": 3.7609, + "step": 433152 + }, + { + "epoch": 1.02, + "learning_rate": 4.290000150684995e-05, + "loss": 3.758, + "step": 433664 + }, + { + "epoch": 1.02, + "learning_rate": 4.289161555933943e-05, + "loss": 3.745, + "step": 434176 + }, + { + "epoch": 1.02, + "learning_rate": 4.288322961182891e-05, + "loss": 3.7525, + "step": 434688 + }, + { + "epoch": 1.02, + "learning_rate": 4.287486004312212e-05, + "loss": 3.7502, + "step": 435200 + }, + { + "epoch": 1.02, + "learning_rate": 4.28664740956116e-05, + "loss": 3.7549, + "step": 435712 + }, + { + "epoch": 1.02, + "learning_rate": 4.285808814810108e-05, + "loss": 3.7407, + "step": 436224 + }, + { + "epoch": 1.02, + "learning_rate": 4.284970220059056e-05, + "loss": 3.7701, + "step": 436736 + }, + { + "epoch": 1.02, + "learning_rate": 4.284133263188377e-05, + "loss": 3.7469, + "step": 437248 + }, + { + "epoch": 1.02, + "learning_rate": 4.2832946684373247e-05, + "loss": 3.756, + "step": 437760 + }, + { + "epoch": 1.02, + "learning_rate": 4.2824560736862727e-05, + "loss": 3.7449, + "step": 438272 + }, + { + "epoch": 1.02, + "learning_rate": 4.2816174789352207e-05, + "loss": 3.758, + "step": 438784 + }, + { + "epoch": 1.02, + "learning_rate": 4.280780522064542e-05, + "loss": 3.7519, + "step": 439296 + }, + { + "epoch": 1.02, + "learning_rate": 4.27994192731349e-05, + "loss": 3.7471, + "step": 439808 + }, + { + "epoch": 1.02, + "learning_rate": 4.279103332562438e-05, + "loss": 3.7564, + "step": 440320 + }, + { + "epoch": 1.02, + "learning_rate": 4.278264737811386e-05, + "loss": 3.7646, + "step": 440832 + }, + { + "epoch": 1.02, + "learning_rate": 4.277427780940707e-05, + "loss": 3.749, + "step": 441344 + }, + { + "epoch": 1.02, + "learning_rate": 4.276589186189655e-05, + "loss": 3.7615, + "step": 441856 + }, + { + "epoch": 1.02, + "learning_rate": 4.275750591438603e-05, + "loss": 3.7485, + "step": 442368 + }, + { + "epoch": 1.02, + "learning_rate": 4.274911996687551e-05, + "loss": 3.7603, + "step": 442880 + }, + { + "epoch": 1.02, + "learning_rate": 4.274075039816872e-05, + "loss": 3.7413, + "step": 443392 + }, + { + "epoch": 1.02, + "learning_rate": 4.27323644506582e-05, + "loss": 3.7616, + "step": 443904 + }, + { + "epoch": 1.02, + "learning_rate": 4.272397850314768e-05, + "loss": 3.7457, + "step": 444416 + }, + { + "epoch": 1.02, + "learning_rate": 4.271559255563716e-05, + "loss": 3.7603, + "step": 444928 + }, + { + "epoch": 1.02, + "learning_rate": 4.2707222986930376e-05, + "loss": 3.7503, + "step": 445440 + }, + { + "epoch": 1.02, + "learning_rate": 4.2698837039419856e-05, + "loss": 3.75, + "step": 445952 + }, + { + "epoch": 1.02, + "learning_rate": 4.2690451091909336e-05, + "loss": 3.7393, + "step": 446464 + }, + { + "epoch": 1.02, + "learning_rate": 4.2682081523202545e-05, + "loss": 3.7495, + "step": 446976 + }, + { + "epoch": 1.02, + "learning_rate": 4.2673695575692025e-05, + "loss": 3.75, + "step": 447488 + }, + { + "epoch": 1.02, + "learning_rate": 4.2665309628181505e-05, + "loss": 3.756, + "step": 448000 + }, + { + "epoch": 1.02, + "learning_rate": 4.2656923680670985e-05, + "loss": 3.7495, + "step": 448512 + }, + { + "epoch": 1.02, + "learning_rate": 4.2648554111964194e-05, + "loss": 3.7606, + "step": 449024 + }, + { + "epoch": 1.02, + "learning_rate": 4.2640168164453674e-05, + "loss": 3.7412, + "step": 449536 + }, + { + "epoch": 1.02, + "learning_rate": 4.2631782216943154e-05, + "loss": 3.7522, + "step": 450048 + }, + { + "epoch": 1.02, + "learning_rate": 4.2623396269432634e-05, + "loss": 3.7557, + "step": 450560 + }, + { + "epoch": 1.02, + "learning_rate": 4.261502670072584e-05, + "loss": 3.7589, + "step": 451072 + }, + { + "epoch": 1.02, + "learning_rate": 4.260664075321533e-05, + "loss": 3.7492, + "step": 451584 + }, + { + "epoch": 1.02, + "learning_rate": 4.259825480570481e-05, + "loss": 3.7521, + "step": 452096 + }, + { + "epoch": 1.02, + "learning_rate": 4.258986885819429e-05, + "loss": 3.7456, + "step": 452608 + }, + { + "epoch": 1.02, + "learning_rate": 4.25814992894875e-05, + "loss": 3.764, + "step": 453120 + }, + { + "epoch": 1.02, + "learning_rate": 4.257311334197698e-05, + "loss": 3.7415, + "step": 453632 + }, + { + "epoch": 1.02, + "learning_rate": 4.256472739446646e-05, + "loss": 3.7547, + "step": 454144 + }, + { + "epoch": 1.02, + "learning_rate": 4.255634144695594e-05, + "loss": 3.7442, + "step": 454656 + }, + { + "epoch": 1.02, + "learning_rate": 4.254797187824915e-05, + "loss": 3.7477, + "step": 455168 + }, + { + "epoch": 1.02, + "learning_rate": 4.253958593073863e-05, + "loss": 3.7567, + "step": 455680 + }, + { + "epoch": 1.02, + "learning_rate": 4.253119998322811e-05, + "loss": 3.7467, + "step": 456192 + }, + { + "epoch": 1.02, + "learning_rate": 4.252281403571758e-05, + "loss": 3.751, + "step": 456704 + }, + { + "epoch": 1.02, + "learning_rate": 4.25144444670108e-05, + "loss": 3.7341, + "step": 457216 + }, + { + "epoch": 1.02, + "learning_rate": 4.250605851950028e-05, + "loss": 3.7491, + "step": 457728 + }, + { + "epoch": 1.03, + "eval_loss": 3.8715946674346924, + "eval_runtime": 302.2449, + "eval_samples_per_second": 1262.522, + "eval_steps_per_second": 39.455, + "step": 457920 + }, + { + "epoch": 0.0, + "learning_rate": 4.249767257198976e-05, + "loss": 3.7381, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.2489286624479237e-05, + "loss": 3.7382, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.2480900676968716e-05, + "loss": 3.7552, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.2472514729458196e-05, + "loss": 3.7495, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.2464128781947676e-05, + "loss": 3.7607, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.2455742834437156e-05, + "loss": 3.7401, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.2447356886926636e-05, + "loss": 3.7415, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.2438970939416116e-05, + "loss": 3.7415, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.2430601370709325e-05, + "loss": 3.7402, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.2422231802002534e-05, + "loss": 3.7528, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.241384585449202e-05, + "loss": 3.7424, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.24054599069815e-05, + "loss": 3.7467, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.239707395947098e-05, + "loss": 3.7417, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.238868801196046e-05, + "loss": 3.7368, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.238030206444994e-05, + "loss": 3.7361, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.237191611693942e-05, + "loss": 3.7331, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.23635301694289e-05, + "loss": 3.745, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.235516060072211e-05, + "loss": 3.7415, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.234677465321159e-05, + "loss": 3.7411, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.233838870570107e-05, + "loss": 3.754, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.233001913699428e-05, + "loss": 3.7531, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.232163318948376e-05, + "loss": 3.7366, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.231324724197324e-05, + "loss": 3.737, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.230486129446272e-05, + "loss": 3.7437, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.2296491725755935e-05, + "loss": 3.7371, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.2288105778245415e-05, + "loss": 3.7415, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.2279719830734895e-05, + "loss": 3.741, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.2271333883224375e-05, + "loss": 3.7411, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.2262947935713855e-05, + "loss": 3.731, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.2254578367007064e-05, + "loss": 3.7286, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.2246192419496544e-05, + "loss": 3.7257, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.2237806471986024e-05, + "loss": 3.7391, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.222943690327923e-05, + "loss": 3.7451, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.222105095576871e-05, + "loss": 3.7436, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.221266500825819e-05, + "loss": 3.7268, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.220427906074767e-05, + "loss": 3.7394, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.219590949204089e-05, + "loss": 3.7385, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.218752354453037e-05, + "loss": 3.721, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.217913759701985e-05, + "loss": 3.7287, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.217075164950933e-05, + "loss": 3.7295, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.216238208080254e-05, + "loss": 3.7231, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.215399613329202e-05, + "loss": 3.7413, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.21456101857815e-05, + "loss": 3.732, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.213722423827098e-05, + "loss": 3.7341, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.2128854669564186e-05, + "loss": 3.7341, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.2120468722053666e-05, + "loss": 3.7325, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.2112082774543146e-05, + "loss": 3.7376, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.2103696827032626e-05, + "loss": 3.7225, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.209532725832584e-05, + "loss": 3.6992, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.208694131081532e-05, + "loss": 3.7467, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.20785553633048e-05, + "loss": 3.7282, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.207016941579428e-05, + "loss": 3.7349, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.206179984708749e-05, + "loss": 3.7255, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.205341389957697e-05, + "loss": 3.7225, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.204502795206645e-05, + "loss": 3.7159, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.203664200455593e-05, + "loss": 3.7276, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.202827243584914e-05, + "loss": 3.735, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.201988648833862e-05, + "loss": 3.7191, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.20115005408281e-05, + "loss": 3.744, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.200311459331758e-05, + "loss": 3.7235, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.1994745024610796e-05, + "loss": 3.7123, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.1986359077100276e-05, + "loss": 3.7301, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.1977973129589756e-05, + "loss": 3.7147, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.1969587182079236e-05, + "loss": 3.7073, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.1961217613372445e-05, + "loss": 3.7355, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.1952831665861925e-05, + "loss": 3.7315, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.1944445718351405e-05, + "loss": 3.7183, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.1936059770840885e-05, + "loss": 3.7235, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.1927690202134094e-05, + "loss": 3.7108, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.1919304254623574e-05, + "loss": 3.7278, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.1910918307113054e-05, + "loss": 3.7268, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.1902532359602534e-05, + "loss": 3.7258, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.189416279089575e-05, + "loss": 3.7269, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.188577684338523e-05, + "loss": 3.7287, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.187739089587471e-05, + "loss": 3.7385, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.186900494836419e-05, + "loss": 3.7141, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.18606353796574e-05, + "loss": 3.73, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.185224943214688e-05, + "loss": 3.7263, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.184386348463636e-05, + "loss": 3.7129, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.183547753712584e-05, + "loss": 3.7315, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.182710796841905e-05, + "loss": 3.7367, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.181872202090853e-05, + "loss": 3.7275, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.181033607339801e-05, + "loss": 3.7403, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.180195012588749e-05, + "loss": 3.716, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.179356417837697e-05, + "loss": 3.7136, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.178517823086645e-05, + "loss": 3.7232, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.177679228335593e-05, + "loss": 3.7307, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.1768422714649136e-05, + "loss": 3.7217, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.1760036767138616e-05, + "loss": 3.7218, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.1751650819628096e-05, + "loss": 3.7211, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.1743264872117576e-05, + "loss": 3.7278, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.1734895303410785e-05, + "loss": 3.7171, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.1726509355900265e-05, + "loss": 3.7158, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.1718123408389745e-05, + "loss": 3.7218, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.1709737460879225e-05, + "loss": 3.7363, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.170136789217244e-05, + "loss": 3.7262, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.169298194466192e-05, + "loss": 3.7052, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.16845959971514e-05, + "loss": 3.719, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.167621004964088e-05, + "loss": 3.7198, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.166784048093409e-05, + "loss": 3.7276, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.165945453342357e-05, + "loss": 3.7204, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.165106858591305e-05, + "loss": 3.718, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.164268263840253e-05, + "loss": 3.7099, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.163431306969574e-05, + "loss": 3.7099, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.162592712218522e-05, + "loss": 3.7197, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.16175411746747e-05, + "loss": 3.7168, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.160915522716418e-05, + "loss": 3.703, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.1600785658457395e-05, + "loss": 3.7347, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.1592399710946875e-05, + "loss": 3.7102, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.1584013763436354e-05, + "loss": 3.7147, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.1575627815925834e-05, + "loss": 3.7099, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.1567258247219044e-05, + "loss": 3.7195, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.1558872299708523e-05, + "loss": 3.7188, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.1550486352198003e-05, + "loss": 3.7103, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.154210040468748e-05, + "loss": 3.7185, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.153373083598069e-05, + "loss": 3.7239, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.152534488847017e-05, + "loss": 3.7171, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.151695894095965e-05, + "loss": 3.7231, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.150857299344913e-05, + "loss": 3.711, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.150020342474235e-05, + "loss": 3.7211, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.149181747723183e-05, + "loss": 3.7084, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.148343152972131e-05, + "loss": 3.7226, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.147504558221079e-05, + "loss": 3.7115, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.1466676013504e-05, + "loss": 3.7202, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.145829006599348e-05, + "loss": 3.7174, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.144990411848296e-05, + "loss": 3.713, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.144151817097244e-05, + "loss": 3.7063, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.1433148602265646e-05, + "loss": 3.7113, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.1424762654755126e-05, + "loss": 3.7109, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.1416376707244606e-05, + "loss": 3.7243, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.1407990759734086e-05, + "loss": 3.7115, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.13996211910273e-05, + "loss": 3.7268, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.139123524351678e-05, + "loss": 3.7029, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.138284929600626e-05, + "loss": 3.7196, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.137446334849574e-05, + "loss": 3.7204, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.136609377978895e-05, + "loss": 3.7219, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.135770783227843e-05, + "loss": 3.7167, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.134932188476791e-05, + "loss": 3.7164, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.134093593725739e-05, + "loss": 3.7094, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.13325663685506e-05, + "loss": 3.7302, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.132418042104008e-05, + "loss": 3.7032, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.131579447352956e-05, + "loss": 3.7175, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.130740852601904e-05, + "loss": 3.7104, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.1299038957312256e-05, + "loss": 3.7193, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.1290669388605465e-05, + "loss": 3.7128, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.1282283441094945e-05, + "loss": 3.7123, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.1273897493584425e-05, + "loss": 3.7145, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.1265511546073905e-05, + "loss": 3.6988, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.1257125598563384e-05, + "loss": 3.7159, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 3.859863758087158, + "eval_runtime": 303.8718, + "eval_samples_per_second": 1255.763, + "eval_steps_per_second": 39.244, + "step": 534240 + }, + { + "epoch": 1.0, + "learning_rate": 4.1248739651052864e-05, + "loss": 3.7051, + "step": 534528 + }, + { + "epoch": 1.0, + "learning_rate": 4.1240353703542344e-05, + "loss": 3.7009, + "step": 535040 + }, + { + "epoch": 1.0, + "learning_rate": 4.1231967756031824e-05, + "loss": 3.7164, + "step": 535552 + }, + { + "epoch": 1.0, + "learning_rate": 4.1223598187325033e-05, + "loss": 3.7147, + "step": 536064 + }, + { + "epoch": 1.0, + "learning_rate": 4.1215212239814513e-05, + "loss": 3.7241, + "step": 536576 + }, + { + "epoch": 1.0, + "learning_rate": 4.120682629230399e-05, + "loss": 3.7087, + "step": 537088 + }, + { + "epoch": 1.0, + "learning_rate": 4.119844034479347e-05, + "loss": 3.7058, + "step": 537600 + }, + { + "epoch": 1.0, + "learning_rate": 4.119007077608669e-05, + "loss": 3.7075, + "step": 538112 + }, + { + "epoch": 1.0, + "learning_rate": 4.118168482857617e-05, + "loss": 3.7041, + "step": 538624 + }, + { + "epoch": 1.0, + "learning_rate": 4.117331525986938e-05, + "loss": 3.7155, + "step": 539136 + }, + { + "epoch": 1.0, + "learning_rate": 4.116492931235886e-05, + "loss": 3.7071, + "step": 539648 + }, + { + "epoch": 1.0, + "learning_rate": 4.115654336484834e-05, + "loss": 3.7106, + "step": 540160 + }, + { + "epoch": 1.0, + "learning_rate": 4.114815741733782e-05, + "loss": 3.71, + "step": 540672 + }, + { + "epoch": 1.0, + "learning_rate": 4.11397714698273e-05, + "loss": 3.7017, + "step": 541184 + }, + { + "epoch": 1.0, + "learning_rate": 4.113138552231678e-05, + "loss": 3.6962, + "step": 541696 + }, + { + "epoch": 1.0, + "learning_rate": 4.112299957480626e-05, + "loss": 3.6996, + "step": 542208 + }, + { + "epoch": 1.0, + "learning_rate": 4.111461362729574e-05, + "loss": 3.7122, + "step": 542720 + }, + { + "epoch": 1.0, + "learning_rate": 4.110624405858895e-05, + "loss": 3.7087, + "step": 543232 + }, + { + "epoch": 1.0, + "learning_rate": 4.109785811107843e-05, + "loss": 3.7015, + "step": 543744 + }, + { + "epoch": 1.0, + "learning_rate": 4.108947216356791e-05, + "loss": 3.7223, + "step": 544256 + }, + { + "epoch": 1.0, + "learning_rate": 4.108110259486112e-05, + "loss": 3.7159, + "step": 544768 + }, + { + "epoch": 1.0, + "learning_rate": 4.10727166473506e-05, + "loss": 3.7053, + "step": 545280 + }, + { + "epoch": 1.0, + "learning_rate": 4.106433069984008e-05, + "loss": 3.7059, + "step": 545792 + }, + { + "epoch": 1.0, + "learning_rate": 4.105594475232956e-05, + "loss": 3.702, + "step": 546304 + }, + { + "epoch": 1.0, + "learning_rate": 4.104757518362277e-05, + "loss": 3.7055, + "step": 546816 + }, + { + "epoch": 1.0, + "learning_rate": 4.103918923611225e-05, + "loss": 3.7065, + "step": 547328 + }, + { + "epoch": 1.0, + "learning_rate": 4.103080328860173e-05, + "loss": 3.7078, + "step": 547840 + }, + { + "epoch": 1.0, + "learning_rate": 4.102241734109121e-05, + "loss": 3.7095, + "step": 548352 + }, + { + "epoch": 1.0, + "learning_rate": 4.101404777238442e-05, + "loss": 3.6954, + "step": 548864 + }, + { + "epoch": 1.0, + "learning_rate": 4.10056618248739e-05, + "loss": 3.6949, + "step": 549376 + }, + { + "epoch": 1.01, + "learning_rate": 4.099727587736338e-05, + "loss": 3.6898, + "step": 549888 + }, + { + "epoch": 1.01, + "learning_rate": 4.098888992985286e-05, + "loss": 3.7085, + "step": 550400 + }, + { + "epoch": 1.01, + "learning_rate": 4.0980520361146076e-05, + "loss": 3.7092, + "step": 550912 + }, + { + "epoch": 1.01, + "learning_rate": 4.0972134413635556e-05, + "loss": 3.7098, + "step": 551424 + }, + { + "epoch": 1.01, + "learning_rate": 4.0963748466125036e-05, + "loss": 3.6983, + "step": 551936 + }, + { + "epoch": 1.01, + "learning_rate": 4.0955362518614516e-05, + "loss": 3.6971, + "step": 552448 + }, + { + "epoch": 1.01, + "learning_rate": 4.0946992949907725e-05, + "loss": 3.7078, + "step": 552960 + }, + { + "epoch": 1.01, + "learning_rate": 4.0938607002397205e-05, + "loss": 3.6937, + "step": 553472 + }, + { + "epoch": 1.01, + "learning_rate": 4.0930221054886685e-05, + "loss": 3.6906, + "step": 553984 + }, + { + "epoch": 1.01, + "learning_rate": 4.092183510737616e-05, + "loss": 3.6977, + "step": 554496 + }, + { + "epoch": 1.01, + "learning_rate": 4.0913465538669374e-05, + "loss": 3.6934, + "step": 555008 + }, + { + "epoch": 1.01, + "learning_rate": 4.0905079591158854e-05, + "loss": 3.7027, + "step": 555520 + }, + { + "epoch": 1.01, + "learning_rate": 4.0896693643648334e-05, + "loss": 3.7006, + "step": 556032 + }, + { + "epoch": 1.01, + "learning_rate": 4.0888307696137814e-05, + "loss": 3.702, + "step": 556544 + }, + { + "epoch": 1.01, + "learning_rate": 4.087993812743103e-05, + "loss": 3.6969, + "step": 557056 + }, + { + "epoch": 1.01, + "learning_rate": 4.087155217992051e-05, + "loss": 3.7021, + "step": 557568 + }, + { + "epoch": 1.01, + "learning_rate": 4.086316623240999e-05, + "loss": 3.7042, + "step": 558080 + }, + { + "epoch": 1.01, + "learning_rate": 4.085478028489946e-05, + "loss": 3.6909, + "step": 558592 + }, + { + "epoch": 1.01, + "learning_rate": 4.084641071619268e-05, + "loss": 3.6662, + "step": 559104 + }, + { + "epoch": 1.01, + "learning_rate": 4.083802476868216e-05, + "loss": 3.7105, + "step": 559616 + }, + { + "epoch": 1.01, + "learning_rate": 4.082963882117163e-05, + "loss": 3.695, + "step": 560128 + }, + { + "epoch": 1.01, + "learning_rate": 4.082125287366111e-05, + "loss": 3.704, + "step": 560640 + }, + { + "epoch": 1.01, + "learning_rate": 4.081288330495433e-05, + "loss": 3.691, + "step": 561152 + }, + { + "epoch": 1.01, + "learning_rate": 4.080449735744381e-05, + "loss": 3.6922, + "step": 561664 + }, + { + "epoch": 1.01, + "learning_rate": 4.079611140993329e-05, + "loss": 3.6783, + "step": 562176 + }, + { + "epoch": 1.01, + "learning_rate": 4.078772546242277e-05, + "loss": 3.6937, + "step": 562688 + }, + { + "epoch": 1.01, + "learning_rate": 4.0779355893715984e-05, + "loss": 3.7052, + "step": 563200 + }, + { + "epoch": 1.01, + "learning_rate": 4.0770969946205464e-05, + "loss": 3.6832, + "step": 563712 + }, + { + "epoch": 1.01, + "learning_rate": 4.076258399869494e-05, + "loss": 3.7132, + "step": 564224 + }, + { + "epoch": 1.01, + "learning_rate": 4.075419805118442e-05, + "loss": 3.6933, + "step": 564736 + }, + { + "epoch": 1.01, + "learning_rate": 4.074582848247763e-05, + "loss": 3.6789, + "step": 565248 + }, + { + "epoch": 1.01, + "learning_rate": 4.0737442534967106e-05, + "loss": 3.6931, + "step": 565760 + }, + { + "epoch": 1.01, + "learning_rate": 4.0729056587456586e-05, + "loss": 3.6833, + "step": 566272 + }, + { + "epoch": 1.01, + "learning_rate": 4.0720670639946066e-05, + "loss": 3.6767, + "step": 566784 + }, + { + "epoch": 1.01, + "learning_rate": 4.071230107123928e-05, + "loss": 3.7009, + "step": 567296 + }, + { + "epoch": 1.01, + "learning_rate": 4.070391512372876e-05, + "loss": 3.6984, + "step": 567808 + }, + { + "epoch": 1.01, + "learning_rate": 4.069552917621824e-05, + "loss": 3.6869, + "step": 568320 + }, + { + "epoch": 1.01, + "learning_rate": 4.068714322870772e-05, + "loss": 3.693, + "step": 568832 + }, + { + "epoch": 1.01, + "learning_rate": 4.067877366000094e-05, + "loss": 3.6755, + "step": 569344 + }, + { + "epoch": 1.01, + "learning_rate": 4.067038771249041e-05, + "loss": 3.6981, + "step": 569856 + }, + { + "epoch": 1.01, + "learning_rate": 4.066200176497989e-05, + "loss": 3.6893, + "step": 570368 + }, + { + "epoch": 1.01, + "learning_rate": 4.065361581746937e-05, + "loss": 3.6918, + "step": 570880 + }, + { + "epoch": 1.01, + "learning_rate": 4.064524624876258e-05, + "loss": 3.6994, + "step": 571392 + }, + { + "epoch": 1.01, + "learning_rate": 4.063686030125206e-05, + "loss": 3.6918, + "step": 571904 + }, + { + "epoch": 1.01, + "learning_rate": 4.062847435374154e-05, + "loss": 3.709, + "step": 572416 + }, + { + "epoch": 1.01, + "learning_rate": 4.062008840623102e-05, + "loss": 3.6808, + "step": 572928 + }, + { + "epoch": 1.01, + "learning_rate": 4.061171883752423e-05, + "loss": 3.6976, + "step": 573440 + }, + { + "epoch": 1.01, + "learning_rate": 4.0603332890013715e-05, + "loss": 3.6923, + "step": 573952 + }, + { + "epoch": 1.01, + "learning_rate": 4.0594946942503195e-05, + "loss": 3.683, + "step": 574464 + }, + { + "epoch": 1.01, + "learning_rate": 4.0586577373796404e-05, + "loss": 3.6983, + "step": 574976 + }, + { + "epoch": 1.01, + "learning_rate": 4.0578191426285884e-05, + "loss": 3.7042, + "step": 575488 + }, + { + "epoch": 1.01, + "learning_rate": 4.0569805478775364e-05, + "loss": 3.6966, + "step": 576000 + }, + { + "epoch": 1.01, + "learning_rate": 4.0561419531264844e-05, + "loss": 3.7079, + "step": 576512 + }, + { + "epoch": 1.01, + "learning_rate": 4.0553033583754324e-05, + "loss": 3.6856, + "step": 577024 + }, + { + "epoch": 1.01, + "learning_rate": 4.0544647636243804e-05, + "loss": 3.6793, + "step": 577536 + }, + { + "epoch": 1.01, + "learning_rate": 4.0536261688733284e-05, + "loss": 3.6911, + "step": 578048 + }, + { + "epoch": 1.01, + "learning_rate": 4.0527875741222764e-05, + "loss": 3.7005, + "step": 578560 + }, + { + "epoch": 1.01, + "learning_rate": 4.051950617251597e-05, + "loss": 3.6857, + "step": 579072 + }, + { + "epoch": 1.01, + "learning_rate": 4.051112022500545e-05, + "loss": 3.6918, + "step": 579584 + }, + { + "epoch": 1.02, + "learning_rate": 4.050273427749493e-05, + "loss": 3.6886, + "step": 580096 + }, + { + "epoch": 1.02, + "learning_rate": 4.049434832998441e-05, + "loss": 3.6949, + "step": 580608 + }, + { + "epoch": 1.02, + "learning_rate": 4.048599514008136e-05, + "loss": 3.6875, + "step": 581120 + }, + { + "epoch": 1.02, + "learning_rate": 4.047760919257084e-05, + "loss": 3.6848, + "step": 581632 + }, + { + "epoch": 1.02, + "learning_rate": 4.046922324506032e-05, + "loss": 3.6921, + "step": 582144 + }, + { + "epoch": 1.02, + "learning_rate": 4.04608372975498e-05, + "loss": 3.7037, + "step": 582656 + }, + { + "epoch": 1.02, + "learning_rate": 4.045245135003928e-05, + "loss": 3.6954, + "step": 583168 + }, + { + "epoch": 1.02, + "learning_rate": 4.044406540252876e-05, + "loss": 3.6727, + "step": 583680 + }, + { + "epoch": 1.02, + "learning_rate": 4.043567945501824e-05, + "loss": 3.6856, + "step": 584192 + }, + { + "epoch": 1.02, + "learning_rate": 4.042729350750772e-05, + "loss": 3.6863, + "step": 584704 + }, + { + "epoch": 1.02, + "learning_rate": 4.041892393880093e-05, + "loss": 3.6986, + "step": 585216 + }, + { + "epoch": 1.02, + "learning_rate": 4.041053799129041e-05, + "loss": 3.6902, + "step": 585728 + }, + { + "epoch": 1.02, + "learning_rate": 4.040215204377989e-05, + "loss": 3.6862, + "step": 586240 + }, + { + "epoch": 1.02, + "learning_rate": 4.039376609626937e-05, + "loss": 3.6814, + "step": 586752 + }, + { + "epoch": 1.02, + "learning_rate": 4.038539652756258e-05, + "loss": 3.6775, + "step": 587264 + }, + { + "epoch": 1.02, + "learning_rate": 4.037701058005206e-05, + "loss": 3.6882, + "step": 587776 + }, + { + "epoch": 1.02, + "learning_rate": 4.036862463254154e-05, + "loss": 3.6835, + "step": 588288 + }, + { + "epoch": 1.02, + "learning_rate": 4.036023868503102e-05, + "loss": 3.6729, + "step": 588800 + }, + { + "epoch": 1.02, + "learning_rate": 4.035186911632423e-05, + "loss": 3.7005, + "step": 589312 + }, + { + "epoch": 1.02, + "learning_rate": 4.034348316881371e-05, + "loss": 3.6806, + "step": 589824 + }, + { + "epoch": 1.02, + "learning_rate": 4.033509722130319e-05, + "loss": 3.6817, + "step": 590336 + }, + { + "epoch": 1.02, + "learning_rate": 4.032671127379267e-05, + "loss": 3.6814, + "step": 590848 + }, + { + "epoch": 1.02, + "learning_rate": 4.031834170508588e-05, + "loss": 3.6831, + "step": 591360 + }, + { + "epoch": 1.02, + "learning_rate": 4.030995575757536e-05, + "loss": 3.6893, + "step": 591872 + }, + { + "epoch": 1.02, + "learning_rate": 4.030156981006484e-05, + "loss": 3.6801, + "step": 592384 + }, + { + "epoch": 1.02, + "learning_rate": 4.029318386255432e-05, + "loss": 3.6899, + "step": 592896 + }, + { + "epoch": 1.02, + "learning_rate": 4.0284814293847536e-05, + "loss": 3.6948, + "step": 593408 + }, + { + "epoch": 1.02, + "learning_rate": 4.0276428346337016e-05, + "loss": 3.6839, + "step": 593920 + }, + { + "epoch": 1.02, + "learning_rate": 4.0268042398826496e-05, + "loss": 3.6909, + "step": 594432 + }, + { + "epoch": 1.02, + "learning_rate": 4.0259656451315976e-05, + "loss": 3.6802, + "step": 594944 + }, + { + "epoch": 1.02, + "learning_rate": 4.0251286882609185e-05, + "loss": 3.6911, + "step": 595456 + }, + { + "epoch": 1.02, + "learning_rate": 4.0242900935098665e-05, + "loss": 3.6806, + "step": 595968 + }, + { + "epoch": 1.02, + "learning_rate": 4.0234514987588145e-05, + "loss": 3.6855, + "step": 596480 + }, + { + "epoch": 1.02, + "learning_rate": 4.0226129040077625e-05, + "loss": 3.6814, + "step": 596992 + }, + { + "epoch": 1.02, + "learning_rate": 4.0217759471370834e-05, + "loss": 3.6909, + "step": 597504 + }, + { + "epoch": 1.02, + "learning_rate": 4.0209373523860314e-05, + "loss": 3.6906, + "step": 598016 + }, + { + "epoch": 1.02, + "learning_rate": 4.0200987576349794e-05, + "loss": 3.6808, + "step": 598528 + }, + { + "epoch": 1.02, + "learning_rate": 4.0192601628839274e-05, + "loss": 3.6704, + "step": 599040 + }, + { + "epoch": 1.02, + "learning_rate": 4.018423206013249e-05, + "loss": 3.684, + "step": 599552 + }, + { + "epoch": 1.02, + "learning_rate": 4.017584611262197e-05, + "loss": 3.6791, + "step": 600064 + }, + { + "epoch": 1.02, + "learning_rate": 4.016746016511145e-05, + "loss": 3.6888, + "step": 600576 + }, + { + "epoch": 1.02, + "learning_rate": 4.015907421760093e-05, + "loss": 3.6811, + "step": 601088 + }, + { + "epoch": 1.02, + "learning_rate": 4.015070464889414e-05, + "loss": 3.6936, + "step": 601600 + }, + { + "epoch": 1.02, + "learning_rate": 4.014231870138362e-05, + "loss": 3.6718, + "step": 602112 + }, + { + "epoch": 1.02, + "learning_rate": 4.01339327538731e-05, + "loss": 3.6925, + "step": 602624 + }, + { + "epoch": 1.02, + "learning_rate": 4.012556318516631e-05, + "loss": 3.6865, + "step": 603136 + }, + { + "epoch": 1.02, + "learning_rate": 4.011717723765579e-05, + "loss": 3.6951, + "step": 603648 + }, + { + "epoch": 1.02, + "learning_rate": 4.010879129014527e-05, + "loss": 3.6843, + "step": 604160 + }, + { + "epoch": 1.02, + "learning_rate": 4.010040534263475e-05, + "loss": 3.6814, + "step": 604672 + }, + { + "epoch": 1.02, + "learning_rate": 4.0092035773927964e-05, + "loss": 3.6809, + "step": 605184 + }, + { + "epoch": 1.02, + "learning_rate": 4.0083649826417444e-05, + "loss": 3.6989, + "step": 605696 + }, + { + "epoch": 1.02, + "learning_rate": 4.0075263878906924e-05, + "loss": 3.6723, + "step": 606208 + }, + { + "epoch": 1.02, + "learning_rate": 4.0066877931396404e-05, + "loss": 3.688, + "step": 606720 + }, + { + "epoch": 1.02, + "learning_rate": 4.005850836268961e-05, + "loss": 3.6826, + "step": 607232 + }, + { + "epoch": 1.02, + "learning_rate": 4.005012241517909e-05, + "loss": 3.6853, + "step": 607744 + }, + { + "epoch": 1.02, + "learning_rate": 4.00417528464723e-05, + "loss": 3.6825, + "step": 608256 + }, + { + "epoch": 1.02, + "learning_rate": 4.003336689896178e-05, + "loss": 3.6849, + "step": 608768 + }, + { + "epoch": 1.02, + "learning_rate": 4.002498095145126e-05, + "loss": 3.6827, + "step": 609280 + }, + { + "epoch": 1.02, + "learning_rate": 4.001659500394074e-05, + "loss": 3.6713, + "step": 609792 + }, + { + "epoch": 1.02, + "learning_rate": 4.000820905643022e-05, + "loss": 3.6834, + "step": 610304 + }, + { + "epoch": 1.03, + "eval_loss": 3.8530285358428955, + "eval_runtime": 303.7855, + "eval_samples_per_second": 1256.12, + "eval_steps_per_second": 39.255, + "step": 610560 + }, + { + "epoch": 0.0, + "learning_rate": 3.99998231089197e-05, + "loss": 3.6726, + "step": 610816 + }, + { + "epoch": 0.0, + "learning_rate": 3.999143716140918e-05, + "loss": 3.6738, + "step": 611328 + }, + { + "epoch": 0.0, + "learning_rate": 3.998305121389866e-05, + "loss": 3.6856, + "step": 611840 + }, + { + "epoch": 0.0, + "learning_rate": 3.997466526638814e-05, + "loss": 3.6834, + "step": 612352 + }, + { + "epoch": 0.0, + "learning_rate": 3.996627931887762e-05, + "loss": 3.6973, + "step": 612864 + }, + { + "epoch": 0.0, + "learning_rate": 3.99578933713671e-05, + "loss": 3.6751, + "step": 613376 + }, + { + "epoch": 0.0, + "learning_rate": 3.994950742385658e-05, + "loss": 3.6801, + "step": 613888 + }, + { + "epoch": 0.0, + "learning_rate": 3.994112147634606e-05, + "loss": 3.6789, + "step": 614400 + }, + { + "epoch": 0.0, + "learning_rate": 3.993275190763927e-05, + "loss": 3.6729, + "step": 614912 + }, + { + "epoch": 0.0, + "learning_rate": 3.992438233893248e-05, + "loss": 3.6879, + "step": 615424 + }, + { + "epoch": 0.0, + "learning_rate": 3.991599639142196e-05, + "loss": 3.6753, + "step": 615936 + }, + { + "epoch": 0.0, + "learning_rate": 3.990761044391144e-05, + "loss": 3.6782, + "step": 616448 + }, + { + "epoch": 0.0, + "learning_rate": 3.989922449640092e-05, + "loss": 3.6864, + "step": 616960 + }, + { + "epoch": 0.0, + "learning_rate": 3.98908385488904e-05, + "loss": 3.6652, + "step": 617472 + }, + { + "epoch": 0.0, + "learning_rate": 3.9882452601379886e-05, + "loss": 3.6671, + "step": 617984 + }, + { + "epoch": 0.0, + "learning_rate": 3.9874083032673095e-05, + "loss": 3.6667, + "step": 618496 + }, + { + "epoch": 0.0, + "learning_rate": 3.9865697085162575e-05, + "loss": 3.6855, + "step": 619008 + }, + { + "epoch": 0.0, + "learning_rate": 3.9857311137652055e-05, + "loss": 3.6754, + "step": 619520 + }, + { + "epoch": 0.0, + "learning_rate": 3.9848925190141535e-05, + "loss": 3.6756, + "step": 620032 + }, + { + "epoch": 0.0, + "learning_rate": 3.9840539242631015e-05, + "loss": 3.6903, + "step": 620544 + }, + { + "epoch": 0.0, + "learning_rate": 3.9832153295120495e-05, + "loss": 3.6865, + "step": 621056 + }, + { + "epoch": 0.0, + "learning_rate": 3.9823767347609975e-05, + "loss": 3.6737, + "step": 621568 + }, + { + "epoch": 0.0, + "learning_rate": 3.9815397778903184e-05, + "loss": 3.6785, + "step": 622080 + }, + { + "epoch": 0.0, + "learning_rate": 3.9807011831392664e-05, + "loss": 3.6743, + "step": 622592 + }, + { + "epoch": 0.0, + "learning_rate": 3.979864226268587e-05, + "loss": 3.677, + "step": 623104 + }, + { + "epoch": 0.0, + "learning_rate": 3.979025631517535e-05, + "loss": 3.676, + "step": 623616 + }, + { + "epoch": 0.0, + "learning_rate": 3.978187036766484e-05, + "loss": 3.6748, + "step": 624128 + }, + { + "epoch": 0.0, + "learning_rate": 3.977348442015432e-05, + "loss": 3.6835, + "step": 624640 + }, + { + "epoch": 0.0, + "learning_rate": 3.97650984726438e-05, + "loss": 3.6659, + "step": 625152 + }, + { + "epoch": 0.0, + "learning_rate": 3.975671252513328e-05, + "loss": 3.6645, + "step": 625664 + }, + { + "epoch": 0.01, + "learning_rate": 3.974832657762276e-05, + "loss": 3.6661, + "step": 626176 + }, + { + "epoch": 0.01, + "learning_rate": 3.973994063011224e-05, + "loss": 3.6729, + "step": 626688 + }, + { + "epoch": 0.01, + "learning_rate": 3.973157106140545e-05, + "loss": 3.6786, + "step": 627200 + }, + { + "epoch": 0.01, + "learning_rate": 3.972318511389493e-05, + "loss": 3.6858, + "step": 627712 + }, + { + "epoch": 0.01, + "learning_rate": 3.971479916638441e-05, + "loss": 3.6682, + "step": 628224 + }, + { + "epoch": 0.01, + "learning_rate": 3.970641321887389e-05, + "loss": 3.6706, + "step": 628736 + }, + { + "epoch": 0.01, + "learning_rate": 3.96980436501671e-05, + "loss": 3.6801, + "step": 629248 + }, + { + "epoch": 0.01, + "learning_rate": 3.968965770265658e-05, + "loss": 3.6613, + "step": 629760 + }, + { + "epoch": 0.01, + "learning_rate": 3.968127175514606e-05, + "loss": 3.6621, + "step": 630272 + }, + { + "epoch": 0.01, + "learning_rate": 3.967288580763554e-05, + "loss": 3.6716, + "step": 630784 + }, + { + "epoch": 0.01, + "learning_rate": 3.966451623892875e-05, + "loss": 3.6599, + "step": 631296 + }, + { + "epoch": 0.01, + "learning_rate": 3.965613029141823e-05, + "loss": 3.6706, + "step": 631808 + }, + { + "epoch": 0.01, + "learning_rate": 3.964774434390771e-05, + "loss": 3.6731, + "step": 632320 + }, + { + "epoch": 0.01, + "learning_rate": 3.963935839639719e-05, + "loss": 3.6755, + "step": 632832 + }, + { + "epoch": 0.01, + "learning_rate": 3.96309888276904e-05, + "loss": 3.6653, + "step": 633344 + }, + { + "epoch": 0.01, + "learning_rate": 3.962260288017988e-05, + "loss": 3.6756, + "step": 633856 + }, + { + "epoch": 0.01, + "learning_rate": 3.961421693266936e-05, + "loss": 3.6726, + "step": 634368 + }, + { + "epoch": 0.01, + "learning_rate": 3.960583098515884e-05, + "loss": 3.6649, + "step": 634880 + }, + { + "epoch": 0.01, + "learning_rate": 3.959746141645205e-05, + "loss": 3.6402, + "step": 635392 + }, + { + "epoch": 0.01, + "learning_rate": 3.958907546894153e-05, + "loss": 3.6792, + "step": 635904 + }, + { + "epoch": 0.01, + "learning_rate": 3.958068952143101e-05, + "loss": 3.6642, + "step": 636416 + }, + { + "epoch": 0.01, + "learning_rate": 3.957231995272423e-05, + "loss": 3.6731, + "step": 636928 + }, + { + "epoch": 0.01, + "learning_rate": 3.956393400521371e-05, + "loss": 3.6666, + "step": 637440 + }, + { + "epoch": 0.01, + "learning_rate": 3.955554805770319e-05, + "loss": 3.6604, + "step": 637952 + }, + { + "epoch": 0.01, + "learning_rate": 3.954716211019267e-05, + "loss": 3.6548, + "step": 638464 + }, + { + "epoch": 0.01, + "learning_rate": 3.9538792541485876e-05, + "loss": 3.6644, + "step": 638976 + }, + { + "epoch": 0.01, + "learning_rate": 3.9530406593975356e-05, + "loss": 3.6784, + "step": 639488 + }, + { + "epoch": 0.01, + "learning_rate": 3.9522037025268565e-05, + "loss": 3.652, + "step": 640000 + }, + { + "epoch": 0.01, + "learning_rate": 3.9513651077758045e-05, + "loss": 3.6853, + "step": 640512 + }, + { + "epoch": 0.01, + "learning_rate": 3.9505265130247525e-05, + "loss": 3.6647, + "step": 641024 + }, + { + "epoch": 0.01, + "learning_rate": 3.9496879182737005e-05, + "loss": 3.6495, + "step": 641536 + }, + { + "epoch": 0.01, + "learning_rate": 3.9488493235226485e-05, + "loss": 3.6652, + "step": 642048 + }, + { + "epoch": 0.01, + "learning_rate": 3.9480107287715965e-05, + "loss": 3.6553, + "step": 642560 + }, + { + "epoch": 0.01, + "learning_rate": 3.9471721340205445e-05, + "loss": 3.6517, + "step": 643072 + }, + { + "epoch": 0.01, + "learning_rate": 3.9463335392694925e-05, + "loss": 3.6687, + "step": 643584 + }, + { + "epoch": 0.01, + "learning_rate": 3.945498220279187e-05, + "loss": 3.6723, + "step": 644096 + }, + { + "epoch": 0.01, + "learning_rate": 3.944659625528135e-05, + "loss": 3.6534, + "step": 644608 + }, + { + "epoch": 0.01, + "learning_rate": 3.943821030777083e-05, + "loss": 3.6704, + "step": 645120 + }, + { + "epoch": 0.01, + "learning_rate": 3.942982436026031e-05, + "loss": 3.6477, + "step": 645632 + }, + { + "epoch": 0.01, + "learning_rate": 3.942143841274979e-05, + "loss": 3.6658, + "step": 646144 + }, + { + "epoch": 0.01, + "learning_rate": 3.941305246523926e-05, + "loss": 3.6652, + "step": 646656 + }, + { + "epoch": 0.01, + "learning_rate": 3.940466651772874e-05, + "loss": 3.6599, + "step": 647168 + }, + { + "epoch": 0.01, + "learning_rate": 3.939628057021822e-05, + "loss": 3.671, + "step": 647680 + }, + { + "epoch": 0.01, + "learning_rate": 3.938791100151144e-05, + "loss": 3.6632, + "step": 648192 + }, + { + "epoch": 0.01, + "learning_rate": 3.937952505400092e-05, + "loss": 3.6816, + "step": 648704 + }, + { + "epoch": 0.01, + "learning_rate": 3.93711391064904e-05, + "loss": 3.6551, + "step": 649216 + }, + { + "epoch": 0.01, + "learning_rate": 3.936275315897988e-05, + "loss": 3.6696, + "step": 649728 + }, + { + "epoch": 0.01, + "learning_rate": 3.935438359027309e-05, + "loss": 3.6613, + "step": 650240 + }, + { + "epoch": 0.01, + "learning_rate": 3.934599764276257e-05, + "loss": 3.6551, + "step": 650752 + }, + { + "epoch": 0.01, + "learning_rate": 3.933762807405578e-05, + "loss": 3.6694, + "step": 651264 + }, + { + "epoch": 0.01, + "learning_rate": 3.932924212654526e-05, + "loss": 3.6705, + "step": 651776 + }, + { + "epoch": 0.01, + "learning_rate": 3.9320856179034736e-05, + "loss": 3.6727, + "step": 652288 + }, + { + "epoch": 0.01, + "learning_rate": 3.9312470231524216e-05, + "loss": 3.6786, + "step": 652800 + }, + { + "epoch": 0.01, + "learning_rate": 3.9304084284013696e-05, + "loss": 3.6586, + "step": 653312 + }, + { + "epoch": 0.01, + "learning_rate": 3.9295698336503176e-05, + "loss": 3.6496, + "step": 653824 + }, + { + "epoch": 0.01, + "learning_rate": 3.9287312388992656e-05, + "loss": 3.6618, + "step": 654336 + }, + { + "epoch": 0.01, + "learning_rate": 3.927894282028587e-05, + "loss": 3.673, + "step": 654848 + }, + { + "epoch": 0.01, + "learning_rate": 3.927055687277535e-05, + "loss": 3.6577, + "step": 655360 + }, + { + "epoch": 0.01, + "learning_rate": 3.926217092526483e-05, + "loss": 3.665, + "step": 655872 + }, + { + "epoch": 0.02, + "learning_rate": 3.925378497775431e-05, + "loss": 3.6655, + "step": 656384 + }, + { + "epoch": 0.02, + "learning_rate": 3.924539903024379e-05, + "loss": 3.6636, + "step": 656896 + }, + { + "epoch": 0.02, + "learning_rate": 3.9237029461537e-05, + "loss": 3.6638, + "step": 657408 + }, + { + "epoch": 0.02, + "learning_rate": 3.922864351402648e-05, + "loss": 3.6545, + "step": 657920 + }, + { + "epoch": 0.02, + "learning_rate": 3.922025756651596e-05, + "loss": 3.6641, + "step": 658432 + }, + { + "epoch": 0.02, + "learning_rate": 3.921187161900544e-05, + "loss": 3.6762, + "step": 658944 + }, + { + "epoch": 0.02, + "learning_rate": 3.920348567149492e-05, + "loss": 3.6689, + "step": 659456 + }, + { + "epoch": 0.02, + "learning_rate": 3.91950997239844e-05, + "loss": 3.6504, + "step": 659968 + }, + { + "epoch": 0.02, + "learning_rate": 3.918671377647388e-05, + "loss": 3.6596, + "step": 660480 + }, + { + "epoch": 0.02, + "learning_rate": 3.917832782896336e-05, + "loss": 3.6589, + "step": 660992 + }, + { + "epoch": 0.02, + "learning_rate": 3.916995826025657e-05, + "loss": 3.6688, + "step": 661504 + }, + { + "epoch": 0.02, + "learning_rate": 3.9161572312746056e-05, + "loss": 3.667, + "step": 662016 + }, + { + "epoch": 0.02, + "learning_rate": 3.9153186365235536e-05, + "loss": 3.6562, + "step": 662528 + }, + { + "epoch": 0.02, + "learning_rate": 3.9144800417725016e-05, + "loss": 3.6553, + "step": 663040 + }, + { + "epoch": 0.02, + "learning_rate": 3.9136430849018225e-05, + "loss": 3.6492, + "step": 663552 + }, + { + "epoch": 0.02, + "learning_rate": 3.9128044901507705e-05, + "loss": 3.6609, + "step": 664064 + }, + { + "epoch": 0.02, + "learning_rate": 3.9119658953997185e-05, + "loss": 3.6602, + "step": 664576 + }, + { + "epoch": 0.02, + "learning_rate": 3.9111273006486665e-05, + "loss": 3.6515, + "step": 665088 + }, + { + "epoch": 0.02, + "learning_rate": 3.9102903437779874e-05, + "loss": 3.6692, + "step": 665600 + }, + { + "epoch": 0.02, + "learning_rate": 3.9094517490269354e-05, + "loss": 3.6526, + "step": 666112 + }, + { + "epoch": 0.02, + "learning_rate": 3.9086147921562563e-05, + "loss": 3.6571, + "step": 666624 + }, + { + "epoch": 0.02, + "learning_rate": 3.907776197405204e-05, + "loss": 3.6509, + "step": 667136 + }, + { + "epoch": 0.02, + "learning_rate": 3.906937602654152e-05, + "loss": 3.6558, + "step": 667648 + }, + { + "epoch": 0.02, + "learning_rate": 3.906099007903101e-05, + "loss": 3.6641, + "step": 668160 + }, + { + "epoch": 0.02, + "learning_rate": 3.905260413152049e-05, + "loss": 3.6506, + "step": 668672 + }, + { + "epoch": 0.02, + "learning_rate": 3.904421818400997e-05, + "loss": 3.6645, + "step": 669184 + }, + { + "epoch": 0.02, + "learning_rate": 3.903583223649945e-05, + "loss": 3.6671, + "step": 669696 + }, + { + "epoch": 0.02, + "learning_rate": 3.902746266779266e-05, + "loss": 3.6577, + "step": 670208 + }, + { + "epoch": 0.02, + "learning_rate": 3.901907672028214e-05, + "loss": 3.6639, + "step": 670720 + }, + { + "epoch": 0.02, + "learning_rate": 3.901069077277162e-05, + "loss": 3.6553, + "step": 671232 + }, + { + "epoch": 0.02, + "learning_rate": 3.90023048252611e-05, + "loss": 3.6652, + "step": 671744 + }, + { + "epoch": 0.02, + "learning_rate": 3.899393525655431e-05, + "loss": 3.6554, + "step": 672256 + }, + { + "epoch": 0.02, + "learning_rate": 3.898554930904379e-05, + "loss": 3.6603, + "step": 672768 + }, + { + "epoch": 0.02, + "learning_rate": 3.897716336153327e-05, + "loss": 3.6556, + "step": 673280 + }, + { + "epoch": 0.02, + "learning_rate": 3.896879379282648e-05, + "loss": 3.6626, + "step": 673792 + }, + { + "epoch": 0.02, + "learning_rate": 3.8960407845315964e-05, + "loss": 3.668, + "step": 674304 + }, + { + "epoch": 0.02, + "learning_rate": 3.8952021897805444e-05, + "loss": 3.6513, + "step": 674816 + }, + { + "epoch": 0.02, + "learning_rate": 3.8943635950294924e-05, + "loss": 3.6456, + "step": 675328 + }, + { + "epoch": 0.02, + "learning_rate": 3.89352500027844e-05, + "loss": 3.654, + "step": 675840 + }, + { + "epoch": 0.02, + "learning_rate": 3.892686405527388e-05, + "loss": 3.6547, + "step": 676352 + }, + { + "epoch": 0.02, + "learning_rate": 3.891847810776336e-05, + "loss": 3.6631, + "step": 676864 + }, + { + "epoch": 0.02, + "learning_rate": 3.891010853905657e-05, + "loss": 3.6559, + "step": 677376 + }, + { + "epoch": 0.02, + "learning_rate": 3.8901722591546046e-05, + "loss": 3.667, + "step": 677888 + }, + { + "epoch": 0.02, + "learning_rate": 3.8893336644035526e-05, + "loss": 3.6463, + "step": 678400 + }, + { + "epoch": 0.02, + "learning_rate": 3.8884950696525006e-05, + "loss": 3.6697, + "step": 678912 + }, + { + "epoch": 0.02, + "learning_rate": 3.8876564749014486e-05, + "loss": 3.6583, + "step": 679424 + }, + { + "epoch": 0.02, + "learning_rate": 3.8868178801503966e-05, + "loss": 3.6648, + "step": 679936 + }, + { + "epoch": 0.02, + "learning_rate": 3.8859792853993446e-05, + "loss": 3.6572, + "step": 680448 + }, + { + "epoch": 0.02, + "learning_rate": 3.885140690648293e-05, + "loss": 3.653, + "step": 680960 + }, + { + "epoch": 0.02, + "learning_rate": 3.884303733777614e-05, + "loss": 3.6549, + "step": 681472 + }, + { + "epoch": 0.02, + "learning_rate": 3.883466776906935e-05, + "loss": 3.6724, + "step": 681984 + }, + { + "epoch": 0.02, + "learning_rate": 3.882628182155883e-05, + "loss": 3.6467, + "step": 682496 + }, + { + "epoch": 0.02, + "learning_rate": 3.881789587404831e-05, + "loss": 3.6631, + "step": 683008 + }, + { + "epoch": 0.02, + "learning_rate": 3.880950992653779e-05, + "loss": 3.657, + "step": 683520 + }, + { + "epoch": 0.02, + "learning_rate": 3.880112397902727e-05, + "loss": 3.6593, + "step": 684032 + }, + { + "epoch": 0.02, + "learning_rate": 3.879275441032048e-05, + "loss": 3.656, + "step": 684544 + }, + { + "epoch": 0.02, + "learning_rate": 3.878436846280996e-05, + "loss": 3.659, + "step": 685056 + }, + { + "epoch": 0.02, + "learning_rate": 3.877598251529944e-05, + "loss": 3.6536, + "step": 685568 + }, + { + "epoch": 0.02, + "learning_rate": 3.876759656778892e-05, + "loss": 3.6516, + "step": 686080 + }, + { + "epoch": 0.02, + "learning_rate": 3.8759226999082135e-05, + "loss": 3.6553, + "step": 686592 + }, + { + "epoch": 0.03, + "eval_loss": 3.848210573196411, + "eval_runtime": 305.363, + "eval_samples_per_second": 1249.631, + "eval_steps_per_second": 39.052, + "step": 686880 + }, + { + "epoch": 1.0, + "learning_rate": 3.8750841051571615e-05, + "loss": 3.6461, + "step": 687104 + }, + { + "epoch": 1.0, + "learning_rate": 3.8742455104061095e-05, + "loss": 3.6461, + "step": 687616 + }, + { + "epoch": 1.0, + "learning_rate": 3.8734069156550575e-05, + "loss": 3.6582, + "step": 688128 + }, + { + "epoch": 1.0, + "learning_rate": 3.8725683209040055e-05, + "loss": 3.6609, + "step": 688640 + }, + { + "epoch": 1.0, + "learning_rate": 3.8717297261529535e-05, + "loss": 3.6708, + "step": 689152 + }, + { + "epoch": 1.0, + "learning_rate": 3.8708927692822744e-05, + "loss": 3.6455, + "step": 689664 + }, + { + "epoch": 1.0, + "learning_rate": 3.8700541745312224e-05, + "loss": 3.653, + "step": 690176 + }, + { + "epoch": 1.0, + "learning_rate": 3.8692155797801704e-05, + "loss": 3.6541, + "step": 690688 + }, + { + "epoch": 1.0, + "learning_rate": 3.8683769850291184e-05, + "loss": 3.6451, + "step": 691200 + }, + { + "epoch": 1.0, + "learning_rate": 3.8675383902780664e-05, + "loss": 3.662, + "step": 691712 + }, + { + "epoch": 1.0, + "learning_rate": 3.866701433407387e-05, + "loss": 3.6481, + "step": 692224 + }, + { + "epoch": 1.0, + "learning_rate": 3.865862838656335e-05, + "loss": 3.6543, + "step": 692736 + }, + { + "epoch": 1.0, + "learning_rate": 3.865024243905283e-05, + "loss": 3.6625, + "step": 693248 + }, + { + "epoch": 1.0, + "learning_rate": 3.864185649154232e-05, + "loss": 3.6407, + "step": 693760 + }, + { + "epoch": 1.0, + "learning_rate": 3.86334705440318e-05, + "loss": 3.6376, + "step": 694272 + }, + { + "epoch": 1.0, + "learning_rate": 3.862510097532501e-05, + "loss": 3.6441, + "step": 694784 + }, + { + "epoch": 1.0, + "learning_rate": 3.861671502781449e-05, + "loss": 3.6578, + "step": 695296 + }, + { + "epoch": 1.0, + "learning_rate": 3.860832908030397e-05, + "loss": 3.6561, + "step": 695808 + }, + { + "epoch": 1.0, + "learning_rate": 3.859994313279345e-05, + "loss": 3.6433, + "step": 696320 + }, + { + "epoch": 1.0, + "learning_rate": 3.859157356408666e-05, + "loss": 3.663, + "step": 696832 + }, + { + "epoch": 1.0, + "learning_rate": 3.858318761657614e-05, + "loss": 3.6641, + "step": 697344 + }, + { + "epoch": 1.0, + "learning_rate": 3.857480166906562e-05, + "loss": 3.6499, + "step": 697856 + }, + { + "epoch": 1.0, + "learning_rate": 3.85664157215551e-05, + "loss": 3.6513, + "step": 698368 + }, + { + "epoch": 1.0, + "learning_rate": 3.855802977404458e-05, + "loss": 3.6492, + "step": 698880 + }, + { + "epoch": 1.0, + "learning_rate": 3.8549660205337787e-05, + "loss": 3.6511, + "step": 699392 + }, + { + "epoch": 1.0, + "learning_rate": 3.854127425782727e-05, + "loss": 3.6502, + "step": 699904 + }, + { + "epoch": 1.0, + "learning_rate": 3.853288831031675e-05, + "loss": 3.6455, + "step": 700416 + }, + { + "epoch": 1.0, + "learning_rate": 3.852450236280623e-05, + "loss": 3.6583, + "step": 700928 + }, + { + "epoch": 1.0, + "learning_rate": 3.8516116415295706e-05, + "loss": 3.6439, + "step": 701440 + }, + { + "epoch": 1.0, + "learning_rate": 3.8507730467785186e-05, + "loss": 3.6367, + "step": 701952 + }, + { + "epoch": 1.01, + "learning_rate": 3.8499344520274666e-05, + "loss": 3.6407, + "step": 702464 + }, + { + "epoch": 1.01, + "learning_rate": 3.849097495156788e-05, + "loss": 3.6485, + "step": 702976 + }, + { + "epoch": 1.01, + "learning_rate": 3.8482589004057355e-05, + "loss": 3.6493, + "step": 703488 + }, + { + "epoch": 1.01, + "learning_rate": 3.8474203056546835e-05, + "loss": 3.66, + "step": 704000 + }, + { + "epoch": 1.01, + "learning_rate": 3.8465817109036315e-05, + "loss": 3.6431, + "step": 704512 + }, + { + "epoch": 1.01, + "learning_rate": 3.8457431161525795e-05, + "loss": 3.6443, + "step": 705024 + }, + { + "epoch": 1.01, + "learning_rate": 3.8449045214015275e-05, + "loss": 3.6583, + "step": 705536 + }, + { + "epoch": 1.01, + "learning_rate": 3.8440659266504755e-05, + "loss": 3.6315, + "step": 706048 + }, + { + "epoch": 1.01, + "learning_rate": 3.843227331899424e-05, + "loss": 3.6414, + "step": 706560 + }, + { + "epoch": 1.01, + "learning_rate": 3.842390375028745e-05, + "loss": 3.6464, + "step": 707072 + }, + { + "epoch": 1.01, + "learning_rate": 3.841551780277693e-05, + "loss": 3.6385, + "step": 707584 + }, + { + "epoch": 1.01, + "learning_rate": 3.840713185526641e-05, + "loss": 3.6407, + "step": 708096 + }, + { + "epoch": 1.01, + "learning_rate": 3.839874590775589e-05, + "loss": 3.6483, + "step": 708608 + }, + { + "epoch": 1.01, + "learning_rate": 3.83903763390491e-05, + "loss": 3.6498, + "step": 709120 + }, + { + "epoch": 1.01, + "learning_rate": 3.838199039153858e-05, + "loss": 3.6393, + "step": 709632 + }, + { + "epoch": 1.01, + "learning_rate": 3.837360444402806e-05, + "loss": 3.6484, + "step": 710144 + }, + { + "epoch": 1.01, + "learning_rate": 3.836523487532127e-05, + "loss": 3.6459, + "step": 710656 + }, + { + "epoch": 1.01, + "learning_rate": 3.835684892781075e-05, + "loss": 3.6405, + "step": 711168 + }, + { + "epoch": 1.01, + "learning_rate": 3.8348479359103965e-05, + "loss": 3.6183, + "step": 711680 + }, + { + "epoch": 1.01, + "learning_rate": 3.8340093411593445e-05, + "loss": 3.6514, + "step": 712192 + }, + { + "epoch": 1.01, + "learning_rate": 3.8331707464082925e-05, + "loss": 3.6404, + "step": 712704 + }, + { + "epoch": 1.01, + "learning_rate": 3.8323321516572405e-05, + "loss": 3.6521, + "step": 713216 + }, + { + "epoch": 1.01, + "learning_rate": 3.8314935569061885e-05, + "loss": 3.636, + "step": 713728 + }, + { + "epoch": 1.01, + "learning_rate": 3.8306566000355094e-05, + "loss": 3.6345, + "step": 714240 + }, + { + "epoch": 1.01, + "learning_rate": 3.8298180052844574e-05, + "loss": 3.6287, + "step": 714752 + }, + { + "epoch": 1.01, + "learning_rate": 3.8289794105334054e-05, + "loss": 3.6369, + "step": 715264 + }, + { + "epoch": 1.01, + "learning_rate": 3.8281408157823533e-05, + "loss": 3.655, + "step": 715776 + }, + { + "epoch": 1.01, + "learning_rate": 3.827303858911674e-05, + "loss": 3.6283, + "step": 716288 + }, + { + "epoch": 1.01, + "learning_rate": 3.826465264160622e-05, + "loss": 3.6582, + "step": 716800 + }, + { + "epoch": 1.01, + "learning_rate": 3.82562666940957e-05, + "loss": 3.6428, + "step": 717312 + }, + { + "epoch": 1.01, + "learning_rate": 3.824788074658518e-05, + "loss": 3.6247, + "step": 717824 + }, + { + "epoch": 1.01, + "learning_rate": 3.823949479907466e-05, + "loss": 3.6379, + "step": 718336 + }, + { + "epoch": 1.01, + "learning_rate": 3.823110885156415e-05, + "loss": 3.6278, + "step": 718848 + }, + { + "epoch": 1.01, + "learning_rate": 3.822272290405363e-05, + "loss": 3.6315, + "step": 719360 + }, + { + "epoch": 1.01, + "learning_rate": 3.821433695654311e-05, + "loss": 3.6418, + "step": 719872 + }, + { + "epoch": 1.01, + "learning_rate": 3.820598376664005e-05, + "loss": 3.6489, + "step": 720384 + }, + { + "epoch": 1.01, + "learning_rate": 3.819759781912953e-05, + "loss": 3.6281, + "step": 720896 + }, + { + "epoch": 1.01, + "learning_rate": 3.818921187161901e-05, + "loss": 3.6447, + "step": 721408 + }, + { + "epoch": 1.01, + "learning_rate": 3.818082592410849e-05, + "loss": 3.6225, + "step": 721920 + }, + { + "epoch": 1.01, + "learning_rate": 3.817243997659797e-05, + "loss": 3.6411, + "step": 722432 + }, + { + "epoch": 1.01, + "learning_rate": 3.816405402908745e-05, + "loss": 3.6408, + "step": 722944 + }, + { + "epoch": 1.01, + "learning_rate": 3.815566808157693e-05, + "loss": 3.6397, + "step": 723456 + }, + { + "epoch": 1.01, + "learning_rate": 3.814728213406641e-05, + "loss": 3.6413, + "step": 723968 + }, + { + "epoch": 1.01, + "learning_rate": 3.8138912565359616e-05, + "loss": 3.64, + "step": 724480 + }, + { + "epoch": 1.01, + "learning_rate": 3.8130526617849096e-05, + "loss": 3.6561, + "step": 724992 + }, + { + "epoch": 1.01, + "learning_rate": 3.812214067033858e-05, + "loss": 3.6291, + "step": 725504 + }, + { + "epoch": 1.01, + "learning_rate": 3.811375472282806e-05, + "loss": 3.647, + "step": 726016 + }, + { + "epoch": 1.01, + "learning_rate": 3.810536877531754e-05, + "loss": 3.6383, + "step": 726528 + }, + { + "epoch": 1.01, + "learning_rate": 3.8096982827807016e-05, + "loss": 3.6306, + "step": 727040 + }, + { + "epoch": 1.01, + "learning_rate": 3.808861325910023e-05, + "loss": 3.6423, + "step": 727552 + }, + { + "epoch": 1.01, + "learning_rate": 3.808022731158971e-05, + "loss": 3.6474, + "step": 728064 + }, + { + "epoch": 1.01, + "learning_rate": 3.8071841364079185e-05, + "loss": 3.6452, + "step": 728576 + }, + { + "epoch": 1.01, + "learning_rate": 3.8063455416568665e-05, + "loss": 3.6597, + "step": 729088 + }, + { + "epoch": 1.01, + "learning_rate": 3.8055069469058145e-05, + "loss": 3.6359, + "step": 729600 + }, + { + "epoch": 1.01, + "learning_rate": 3.804669990035136e-05, + "loss": 3.6241, + "step": 730112 + }, + { + "epoch": 1.01, + "learning_rate": 3.8038313952840834e-05, + "loss": 3.6362, + "step": 730624 + }, + { + "epoch": 1.01, + "learning_rate": 3.802992800533032e-05, + "loss": 3.6455, + "step": 731136 + }, + { + "epoch": 1.01, + "learning_rate": 3.80215420578198e-05, + "loss": 3.636, + "step": 731648 + }, + { + "epoch": 1.01, + "learning_rate": 3.8013172489113016e-05, + "loss": 3.6398, + "step": 732160 + }, + { + "epoch": 1.02, + "learning_rate": 3.800478654160249e-05, + "loss": 3.6385, + "step": 732672 + }, + { + "epoch": 1.02, + "learning_rate": 3.799640059409197e-05, + "loss": 3.6408, + "step": 733184 + }, + { + "epoch": 1.02, + "learning_rate": 3.798801464658145e-05, + "loss": 3.6385, + "step": 733696 + }, + { + "epoch": 1.02, + "learning_rate": 3.797964507787466e-05, + "loss": 3.6303, + "step": 734208 + }, + { + "epoch": 1.02, + "learning_rate": 3.797125913036414e-05, + "loss": 3.6388, + "step": 734720 + }, + { + "epoch": 1.02, + "learning_rate": 3.796287318285362e-05, + "loss": 3.6529, + "step": 735232 + }, + { + "epoch": 1.02, + "learning_rate": 3.79544872353431e-05, + "loss": 3.6454, + "step": 735744 + }, + { + "epoch": 1.02, + "learning_rate": 3.794610128783258e-05, + "loss": 3.6229, + "step": 736256 + }, + { + "epoch": 1.02, + "learning_rate": 3.793771534032206e-05, + "loss": 3.6348, + "step": 736768 + }, + { + "epoch": 1.02, + "learning_rate": 3.792932939281154e-05, + "loss": 3.6362, + "step": 737280 + }, + { + "epoch": 1.02, + "learning_rate": 3.792094344530102e-05, + "loss": 3.645, + "step": 737792 + }, + { + "epoch": 1.02, + "learning_rate": 3.7912573876594234e-05, + "loss": 3.641, + "step": 738304 + }, + { + "epoch": 1.02, + "learning_rate": 3.7904187929083714e-05, + "loss": 3.6325, + "step": 738816 + }, + { + "epoch": 1.02, + "learning_rate": 3.7895801981573194e-05, + "loss": 3.6316, + "step": 739328 + }, + { + "epoch": 1.02, + "learning_rate": 3.7887416034062674e-05, + "loss": 3.6249, + "step": 739840 + }, + { + "epoch": 1.02, + "learning_rate": 3.7879030086552154e-05, + "loss": 3.6383, + "step": 740352 + }, + { + "epoch": 1.02, + "learning_rate": 3.7870644139041634e-05, + "loss": 3.633, + "step": 740864 + }, + { + "epoch": 1.02, + "learning_rate": 3.7862258191531114e-05, + "loss": 3.6265, + "step": 741376 + }, + { + "epoch": 1.02, + "learning_rate": 3.7853872244020594e-05, + "loss": 3.6391, + "step": 741888 + }, + { + "epoch": 1.02, + "learning_rate": 3.78455026753138e-05, + "loss": 3.6337, + "step": 742400 + }, + { + "epoch": 1.02, + "learning_rate": 3.783713310660701e-05, + "loss": 3.6312, + "step": 742912 + }, + { + "epoch": 1.02, + "learning_rate": 3.782874715909649e-05, + "loss": 3.627, + "step": 743424 + }, + { + "epoch": 1.02, + "learning_rate": 3.782036121158597e-05, + "loss": 3.6292, + "step": 743936 + }, + { + "epoch": 1.02, + "learning_rate": 3.781197526407546e-05, + "loss": 3.6427, + "step": 744448 + }, + { + "epoch": 1.02, + "learning_rate": 3.780358931656494e-05, + "loss": 3.6229, + "step": 744960 + }, + { + "epoch": 1.02, + "learning_rate": 3.779520336905442e-05, + "loss": 3.6417, + "step": 745472 + }, + { + "epoch": 1.02, + "learning_rate": 3.778683380034763e-05, + "loss": 3.6451, + "step": 745984 + }, + { + "epoch": 1.02, + "learning_rate": 3.777844785283711e-05, + "loss": 3.6327, + "step": 746496 + }, + { + "epoch": 1.02, + "learning_rate": 3.777006190532659e-05, + "loss": 3.6396, + "step": 747008 + }, + { + "epoch": 1.02, + "learning_rate": 3.776167595781607e-05, + "loss": 3.6332, + "step": 747520 + }, + { + "epoch": 1.02, + "learning_rate": 3.775329001030555e-05, + "loss": 3.6415, + "step": 748032 + }, + { + "epoch": 1.02, + "learning_rate": 3.7744920441598757e-05, + "loss": 3.6331, + "step": 748544 + }, + { + "epoch": 1.02, + "learning_rate": 3.7736534494088237e-05, + "loss": 3.6347, + "step": 749056 + }, + { + "epoch": 1.02, + "learning_rate": 3.7728148546577716e-05, + "loss": 3.6334, + "step": 749568 + }, + { + "epoch": 1.02, + "learning_rate": 3.7719762599067196e-05, + "loss": 3.6342, + "step": 750080 + }, + { + "epoch": 1.02, + "learning_rate": 3.7711376651556676e-05, + "loss": 3.638, + "step": 750592 + }, + { + "epoch": 1.02, + "learning_rate": 3.7702990704046156e-05, + "loss": 3.6322, + "step": 751104 + }, + { + "epoch": 1.02, + "learning_rate": 3.7694604756535636e-05, + "loss": 3.6216, + "step": 751616 + }, + { + "epoch": 1.02, + "learning_rate": 3.7686218809025116e-05, + "loss": 3.6334, + "step": 752128 + }, + { + "epoch": 1.02, + "learning_rate": 3.7677849240318325e-05, + "loss": 3.6238, + "step": 752640 + }, + { + "epoch": 1.02, + "learning_rate": 3.7669463292807805e-05, + "loss": 3.6424, + "step": 753152 + }, + { + "epoch": 1.02, + "learning_rate": 3.766109372410102e-05, + "loss": 3.6307, + "step": 753664 + }, + { + "epoch": 1.02, + "learning_rate": 3.7652707776590494e-05, + "loss": 3.6407, + "step": 754176 + }, + { + "epoch": 1.02, + "learning_rate": 3.7644321829079974e-05, + "loss": 3.6223, + "step": 754688 + }, + { + "epoch": 1.02, + "learning_rate": 3.7635935881569454e-05, + "loss": 3.6448, + "step": 755200 + }, + { + "epoch": 1.02, + "learning_rate": 3.7627549934058934e-05, + "loss": 3.6317, + "step": 755712 + }, + { + "epoch": 1.02, + "learning_rate": 3.7619163986548414e-05, + "loss": 3.6464, + "step": 756224 + }, + { + "epoch": 1.02, + "learning_rate": 3.7610778039037894e-05, + "loss": 3.6352, + "step": 756736 + }, + { + "epoch": 1.02, + "learning_rate": 3.760239209152738e-05, + "loss": 3.6322, + "step": 757248 + }, + { + "epoch": 1.02, + "learning_rate": 3.759402252282059e-05, + "loss": 3.6274, + "step": 757760 + }, + { + "epoch": 1.02, + "learning_rate": 3.758563657531007e-05, + "loss": 3.6518, + "step": 758272 + }, + { + "epoch": 1.02, + "learning_rate": 3.757725062779955e-05, + "loss": 3.6203, + "step": 758784 + }, + { + "epoch": 1.02, + "learning_rate": 3.756888105909276e-05, + "loss": 3.641, + "step": 759296 + }, + { + "epoch": 1.02, + "learning_rate": 3.756049511158224e-05, + "loss": 3.6308, + "step": 759808 + }, + { + "epoch": 1.02, + "learning_rate": 3.755210916407172e-05, + "loss": 3.6344, + "step": 760320 + }, + { + "epoch": 1.02, + "learning_rate": 3.75437232165612e-05, + "loss": 3.6347, + "step": 760832 + }, + { + "epoch": 1.02, + "learning_rate": 3.753535364785441e-05, + "loss": 3.6308, + "step": 761344 + }, + { + "epoch": 1.02, + "learning_rate": 3.752696770034389e-05, + "loss": 3.6323, + "step": 761856 + }, + { + "epoch": 1.02, + "learning_rate": 3.751858175283337e-05, + "loss": 3.6311, + "step": 762368 + }, + { + "epoch": 1.02, + "learning_rate": 3.751019580532285e-05, + "loss": 3.628, + "step": 762880 + }, + { + "epoch": 1.03, + "eval_loss": 3.8452677726745605, + "eval_runtime": 302.7713, + "eval_samples_per_second": 1260.328, + "eval_steps_per_second": 39.386, + "step": 763200 + }, + { + "epoch": 0.0, + "learning_rate": 3.750180985781233e-05, + "loss": 3.6167, + "step": 763392 + }, + { + "epoch": 0.0, + "learning_rate": 3.7493423910301815e-05, + "loss": 3.6227, + "step": 763904 + }, + { + "epoch": 0.0, + "learning_rate": 3.7485037962791294e-05, + "loss": 3.6354, + "step": 764416 + }, + { + "epoch": 0.0, + "learning_rate": 3.7476652015280774e-05, + "loss": 3.6366, + "step": 764928 + }, + { + "epoch": 0.0, + "learning_rate": 3.7468266067770254e-05, + "loss": 3.648, + "step": 765440 + }, + { + "epoch": 0.0, + "learning_rate": 3.7459896499063463e-05, + "loss": 3.6256, + "step": 765952 + }, + { + "epoch": 0.0, + "learning_rate": 3.7451510551552943e-05, + "loss": 3.6288, + "step": 766464 + }, + { + "epoch": 0.0, + "learning_rate": 3.744312460404242e-05, + "loss": 3.6337, + "step": 766976 + }, + { + "epoch": 0.0, + "learning_rate": 3.74347386565319e-05, + "loss": 3.6223, + "step": 767488 + }, + { + "epoch": 0.0, + "learning_rate": 3.742635270902138e-05, + "loss": 3.6304, + "step": 768000 + }, + { + "epoch": 0.0, + "learning_rate": 3.741798314031459e-05, + "loss": 3.6324, + "step": 768512 + }, + { + "epoch": 0.0, + "learning_rate": 3.740959719280407e-05, + "loss": 3.6306, + "step": 769024 + }, + { + "epoch": 0.0, + "learning_rate": 3.740121124529355e-05, + "loss": 3.6354, + "step": 769536 + }, + { + "epoch": 0.0, + "learning_rate": 3.739282529778303e-05, + "loss": 3.6176, + "step": 770048 + }, + { + "epoch": 0.0, + "learning_rate": 3.738443935027251e-05, + "loss": 3.6166, + "step": 770560 + }, + { + "epoch": 0.0, + "learning_rate": 3.737606978156573e-05, + "loss": 3.6174, + "step": 771072 + }, + { + "epoch": 0.0, + "learning_rate": 3.736768383405521e-05, + "loss": 3.6397, + "step": 771584 + }, + { + "epoch": 0.0, + "learning_rate": 3.735929788654468e-05, + "loss": 3.63, + "step": 772096 + }, + { + "epoch": 0.0, + "learning_rate": 3.735091193903416e-05, + "loss": 3.6209, + "step": 772608 + }, + { + "epoch": 0.0, + "learning_rate": 3.734254237032738e-05, + "loss": 3.6389, + "step": 773120 + }, + { + "epoch": 0.0, + "learning_rate": 3.733415642281686e-05, + "loss": 3.6418, + "step": 773632 + }, + { + "epoch": 0.0, + "learning_rate": 3.732577047530633e-05, + "loss": 3.6276, + "step": 774144 + }, + { + "epoch": 0.0, + "learning_rate": 3.731738452779581e-05, + "loss": 3.6277, + "step": 774656 + }, + { + "epoch": 0.0, + "learning_rate": 3.730899858028529e-05, + "loss": 3.6241, + "step": 775168 + }, + { + "epoch": 0.0, + "learning_rate": 3.7300629011578506e-05, + "loss": 3.6339, + "step": 775680 + }, + { + "epoch": 0.0, + "learning_rate": 3.7292243064067986e-05, + "loss": 3.6247, + "step": 776192 + }, + { + "epoch": 0.0, + "learning_rate": 3.7283857116557466e-05, + "loss": 3.6198, + "step": 776704 + }, + { + "epoch": 0.0, + "learning_rate": 3.7275471169046946e-05, + "loss": 3.6375, + "step": 777216 + }, + { + "epoch": 0.0, + "learning_rate": 3.7267085221536426e-05, + "loss": 3.6174, + "step": 777728 + }, + { + "epoch": 0.0, + "learning_rate": 3.7258715652829635e-05, + "loss": 3.6115, + "step": 778240 + }, + { + "epoch": 0.01, + "learning_rate": 3.7250329705319115e-05, + "loss": 3.624, + "step": 778752 + }, + { + "epoch": 0.01, + "learning_rate": 3.7241943757808595e-05, + "loss": 3.6231, + "step": 779264 + }, + { + "epoch": 0.01, + "learning_rate": 3.7233557810298075e-05, + "loss": 3.6295, + "step": 779776 + }, + { + "epoch": 0.01, + "learning_rate": 3.7225171862787555e-05, + "loss": 3.6387, + "step": 780288 + }, + { + "epoch": 0.01, + "learning_rate": 3.7216785915277035e-05, + "loss": 3.6182, + "step": 780800 + }, + { + "epoch": 0.01, + "learning_rate": 3.7208399967766515e-05, + "loss": 3.6242, + "step": 781312 + }, + { + "epoch": 0.01, + "learning_rate": 3.7200014020255995e-05, + "loss": 3.6349, + "step": 781824 + }, + { + "epoch": 0.01, + "learning_rate": 3.7191644451549204e-05, + "loss": 3.6081, + "step": 782336 + }, + { + "epoch": 0.01, + "learning_rate": 3.718327488284242e-05, + "loss": 3.6189, + "step": 782848 + }, + { + "epoch": 0.01, + "learning_rate": 3.71748889353319e-05, + "loss": 3.6237, + "step": 783360 + }, + { + "epoch": 0.01, + "learning_rate": 3.716650298782138e-05, + "loss": 3.6146, + "step": 783872 + }, + { + "epoch": 0.01, + "learning_rate": 3.715811704031086e-05, + "loss": 3.6201, + "step": 784384 + }, + { + "epoch": 0.01, + "learning_rate": 3.714973109280034e-05, + "loss": 3.6257, + "step": 784896 + }, + { + "epoch": 0.01, + "learning_rate": 3.714134514528982e-05, + "loss": 3.6303, + "step": 785408 + }, + { + "epoch": 0.01, + "learning_rate": 3.713297557658303e-05, + "loss": 3.6178, + "step": 785920 + }, + { + "epoch": 0.01, + "learning_rate": 3.712458962907251e-05, + "loss": 3.6219, + "step": 786432 + }, + { + "epoch": 0.01, + "learning_rate": 3.711620368156199e-05, + "loss": 3.6245, + "step": 786944 + }, + { + "epoch": 0.01, + "learning_rate": 3.710781773405147e-05, + "loss": 3.6186, + "step": 787456 + }, + { + "epoch": 0.01, + "learning_rate": 3.709943178654095e-05, + "loss": 3.5967, + "step": 787968 + }, + { + "epoch": 0.01, + "learning_rate": 3.709104583903043e-05, + "loss": 3.6281, + "step": 788480 + }, + { + "epoch": 0.01, + "learning_rate": 3.708265989151991e-05, + "loss": 3.6217, + "step": 788992 + }, + { + "epoch": 0.01, + "learning_rate": 3.707427394400939e-05, + "loss": 3.6276, + "step": 789504 + }, + { + "epoch": 0.01, + "learning_rate": 3.7065904375302604e-05, + "loss": 3.619, + "step": 790016 + }, + { + "epoch": 0.01, + "learning_rate": 3.705753480659581e-05, + "loss": 3.6079, + "step": 790528 + }, + { + "epoch": 0.01, + "learning_rate": 3.704914885908529e-05, + "loss": 3.6106, + "step": 791040 + }, + { + "epoch": 0.01, + "learning_rate": 3.704076291157477e-05, + "loss": 3.6138, + "step": 791552 + }, + { + "epoch": 0.01, + "learning_rate": 3.703237696406425e-05, + "loss": 3.6301, + "step": 792064 + }, + { + "epoch": 0.01, + "learning_rate": 3.702400739535746e-05, + "loss": 3.6081, + "step": 792576 + }, + { + "epoch": 0.01, + "learning_rate": 3.701562144784694e-05, + "loss": 3.6326, + "step": 793088 + }, + { + "epoch": 0.01, + "learning_rate": 3.700723550033642e-05, + "loss": 3.6229, + "step": 793600 + }, + { + "epoch": 0.01, + "learning_rate": 3.69988495528259e-05, + "loss": 3.6029, + "step": 794112 + }, + { + "epoch": 0.01, + "learning_rate": 3.699046360531538e-05, + "loss": 3.6189, + "step": 794624 + }, + { + "epoch": 0.01, + "learning_rate": 3.698207765780486e-05, + "loss": 3.6039, + "step": 795136 + }, + { + "epoch": 0.01, + "learning_rate": 3.697370808909808e-05, + "loss": 3.609, + "step": 795648 + }, + { + "epoch": 0.01, + "learning_rate": 3.696532214158756e-05, + "loss": 3.6148, + "step": 796160 + }, + { + "epoch": 0.01, + "learning_rate": 3.695693619407704e-05, + "loss": 3.6284, + "step": 796672 + }, + { + "epoch": 0.01, + "learning_rate": 3.694855024656652e-05, + "loss": 3.607, + "step": 797184 + }, + { + "epoch": 0.01, + "learning_rate": 3.694016429905599e-05, + "loss": 3.6194, + "step": 797696 + }, + { + "epoch": 0.01, + "learning_rate": 3.693177835154547e-05, + "loss": 3.6023, + "step": 798208 + }, + { + "epoch": 0.01, + "learning_rate": 3.6923408782838687e-05, + "loss": 3.6174, + "step": 798720 + }, + { + "epoch": 0.01, + "learning_rate": 3.6915022835328167e-05, + "loss": 3.62, + "step": 799232 + }, + { + "epoch": 0.01, + "learning_rate": 3.690663688781764e-05, + "loss": 3.6204, + "step": 799744 + }, + { + "epoch": 0.01, + "learning_rate": 3.689825094030712e-05, + "loss": 3.6182, + "step": 800256 + }, + { + "epoch": 0.01, + "learning_rate": 3.6889881371600336e-05, + "loss": 3.6152, + "step": 800768 + }, + { + "epoch": 0.01, + "learning_rate": 3.6881495424089815e-05, + "loss": 3.6344, + "step": 801280 + }, + { + "epoch": 0.01, + "learning_rate": 3.6873109476579295e-05, + "loss": 3.6089, + "step": 801792 + }, + { + "epoch": 0.01, + "learning_rate": 3.6864723529068775e-05, + "loss": 3.6205, + "step": 802304 + }, + { + "epoch": 0.01, + "learning_rate": 3.685635396036199e-05, + "loss": 3.6154, + "step": 802816 + }, + { + "epoch": 0.01, + "learning_rate": 3.6847968012851464e-05, + "loss": 3.6124, + "step": 803328 + }, + { + "epoch": 0.01, + "learning_rate": 3.6839582065340944e-05, + "loss": 3.6207, + "step": 803840 + }, + { + "epoch": 0.01, + "learning_rate": 3.6831196117830424e-05, + "loss": 3.6206, + "step": 804352 + }, + { + "epoch": 0.01, + "learning_rate": 3.682282654912364e-05, + "loss": 3.6262, + "step": 804864 + }, + { + "epoch": 0.01, + "learning_rate": 3.6814440601613113e-05, + "loss": 3.6345, + "step": 805376 + }, + { + "epoch": 0.01, + "learning_rate": 3.680605465410259e-05, + "loss": 3.6228, + "step": 805888 + }, + { + "epoch": 0.01, + "learning_rate": 3.679766870659207e-05, + "loss": 3.6, + "step": 806400 + }, + { + "epoch": 0.01, + "learning_rate": 3.678928275908155e-05, + "loss": 3.6119, + "step": 806912 + }, + { + "epoch": 0.01, + "learning_rate": 3.678091319037477e-05, + "loss": 3.6244, + "step": 807424 + }, + { + "epoch": 0.01, + "learning_rate": 3.677252724286425e-05, + "loss": 3.6159, + "step": 807936 + }, + { + "epoch": 0.01, + "learning_rate": 3.676414129535373e-05, + "loss": 3.6164, + "step": 808448 + }, + { + "epoch": 0.01, + "learning_rate": 3.675575534784321e-05, + "loss": 3.6177, + "step": 808960 + }, + { + "epoch": 0.02, + "learning_rate": 3.674738577913642e-05, + "loss": 3.6187, + "step": 809472 + }, + { + "epoch": 0.02, + "learning_rate": 3.67389998316259e-05, + "loss": 3.6145, + "step": 809984 + }, + { + "epoch": 0.02, + "learning_rate": 3.673061388411538e-05, + "loss": 3.6081, + "step": 810496 + }, + { + "epoch": 0.02, + "learning_rate": 3.672222793660486e-05, + "loss": 3.6196, + "step": 811008 + }, + { + "epoch": 0.02, + "learning_rate": 3.671384198909434e-05, + "loss": 3.6283, + "step": 811520 + }, + { + "epoch": 0.02, + "learning_rate": 3.670545604158382e-05, + "loss": 3.6236, + "step": 812032 + }, + { + "epoch": 0.02, + "learning_rate": 3.669708647287703e-05, + "loss": 3.5986, + "step": 812544 + }, + { + "epoch": 0.02, + "learning_rate": 3.668870052536651e-05, + "loss": 3.6151, + "step": 813056 + }, + { + "epoch": 0.02, + "learning_rate": 3.668031457785599e-05, + "loss": 3.6157, + "step": 813568 + }, + { + "epoch": 0.02, + "learning_rate": 3.667192863034547e-05, + "loss": 3.6217, + "step": 814080 + }, + { + "epoch": 0.02, + "learning_rate": 3.666355906163868e-05, + "loss": 3.6185, + "step": 814592 + }, + { + "epoch": 0.02, + "learning_rate": 3.665517311412816e-05, + "loss": 3.6091, + "step": 815104 + }, + { + "epoch": 0.02, + "learning_rate": 3.664678716661764e-05, + "loss": 3.6091, + "step": 815616 + }, + { + "epoch": 0.02, + "learning_rate": 3.663840121910712e-05, + "loss": 3.6052, + "step": 816128 + }, + { + "epoch": 0.02, + "learning_rate": 3.66300152715966e-05, + "loss": 3.6142, + "step": 816640 + }, + { + "epoch": 0.02, + "learning_rate": 3.662162932408608e-05, + "loss": 3.6131, + "step": 817152 + }, + { + "epoch": 0.02, + "learning_rate": 3.661324337657556e-05, + "loss": 3.6059, + "step": 817664 + }, + { + "epoch": 0.02, + "learning_rate": 3.660485742906504e-05, + "loss": 3.62, + "step": 818176 + }, + { + "epoch": 0.02, + "learning_rate": 3.659648786035825e-05, + "loss": 3.6101, + "step": 818688 + }, + { + "epoch": 0.02, + "learning_rate": 3.658811829165146e-05, + "loss": 3.6094, + "step": 819200 + }, + { + "epoch": 0.02, + "learning_rate": 3.657973234414094e-05, + "loss": 3.6071, + "step": 819712 + }, + { + "epoch": 0.02, + "learning_rate": 3.657134639663042e-05, + "loss": 3.6058, + "step": 820224 + }, + { + "epoch": 0.02, + "learning_rate": 3.656296044911991e-05, + "loss": 3.6221, + "step": 820736 + }, + { + "epoch": 0.02, + "learning_rate": 3.655457450160939e-05, + "loss": 3.6041, + "step": 821248 + }, + { + "epoch": 0.02, + "learning_rate": 3.654618855409887e-05, + "loss": 3.6162, + "step": 821760 + }, + { + "epoch": 0.02, + "learning_rate": 3.6537818985392076e-05, + "loss": 3.621, + "step": 822272 + }, + { + "epoch": 0.02, + "learning_rate": 3.6529433037881556e-05, + "loss": 3.6133, + "step": 822784 + }, + { + "epoch": 0.02, + "learning_rate": 3.6521047090371036e-05, + "loss": 3.615, + "step": 823296 + }, + { + "epoch": 0.02, + "learning_rate": 3.6512661142860516e-05, + "loss": 3.6154, + "step": 823808 + }, + { + "epoch": 0.02, + "learning_rate": 3.6504291574153725e-05, + "loss": 3.6185, + "step": 824320 + }, + { + "epoch": 0.02, + "learning_rate": 3.6495905626643205e-05, + "loss": 3.6179, + "step": 824832 + }, + { + "epoch": 0.02, + "learning_rate": 3.6487519679132685e-05, + "loss": 3.6091, + "step": 825344 + }, + { + "epoch": 0.02, + "learning_rate": 3.6479133731622165e-05, + "loss": 3.6113, + "step": 825856 + }, + { + "epoch": 0.02, + "learning_rate": 3.6470764162915374e-05, + "loss": 3.6147, + "step": 826368 + }, + { + "epoch": 0.02, + "learning_rate": 3.646237821540486e-05, + "loss": 3.6191, + "step": 826880 + }, + { + "epoch": 0.02, + "learning_rate": 3.645399226789434e-05, + "loss": 3.6079, + "step": 827392 + }, + { + "epoch": 0.02, + "learning_rate": 3.644560632038382e-05, + "loss": 3.6006, + "step": 827904 + }, + { + "epoch": 0.02, + "learning_rate": 3.64372203728733e-05, + "loss": 3.6094, + "step": 828416 + }, + { + "epoch": 0.02, + "learning_rate": 3.6428834425362774e-05, + "loss": 3.6052, + "step": 828928 + }, + { + "epoch": 0.02, + "learning_rate": 3.6420448477852254e-05, + "loss": 3.623, + "step": 829440 + }, + { + "epoch": 0.02, + "learning_rate": 3.641207890914547e-05, + "loss": 3.61, + "step": 829952 + }, + { + "epoch": 0.02, + "learning_rate": 3.640369296163495e-05, + "loss": 3.6201, + "step": 830464 + }, + { + "epoch": 0.02, + "learning_rate": 3.639530701412442e-05, + "loss": 3.6036, + "step": 830976 + }, + { + "epoch": 0.02, + "learning_rate": 3.63869210666139e-05, + "loss": 3.6189, + "step": 831488 + }, + { + "epoch": 0.02, + "learning_rate": 3.637853511910338e-05, + "loss": 3.6133, + "step": 832000 + }, + { + "epoch": 0.02, + "learning_rate": 3.63701655503966e-05, + "loss": 3.6241, + "step": 832512 + }, + { + "epoch": 0.02, + "learning_rate": 3.636177960288608e-05, + "loss": 3.6121, + "step": 833024 + }, + { + "epoch": 0.02, + "learning_rate": 3.635339365537556e-05, + "loss": 3.6099, + "step": 833536 + }, + { + "epoch": 0.02, + "learning_rate": 3.634500770786504e-05, + "loss": 3.6088, + "step": 834048 + }, + { + "epoch": 0.02, + "learning_rate": 3.633662176035452e-05, + "loss": 3.6253, + "step": 834560 + }, + { + "epoch": 0.02, + "learning_rate": 3.6328235812844e-05, + "loss": 3.6036, + "step": 835072 + }, + { + "epoch": 0.02, + "learning_rate": 3.631986624413721e-05, + "loss": 3.6142, + "step": 835584 + }, + { + "epoch": 0.02, + "learning_rate": 3.631148029662669e-05, + "loss": 3.6128, + "step": 836096 + }, + { + "epoch": 0.02, + "learning_rate": 3.630309434911617e-05, + "loss": 3.61, + "step": 836608 + }, + { + "epoch": 0.02, + "learning_rate": 3.629470840160565e-05, + "loss": 3.6136, + "step": 837120 + }, + { + "epoch": 0.02, + "learning_rate": 3.6286338832898857e-05, + "loss": 3.612, + "step": 837632 + }, + { + "epoch": 0.02, + "learning_rate": 3.6277952885388337e-05, + "loss": 3.6102, + "step": 838144 + }, + { + "epoch": 0.02, + "learning_rate": 3.6269566937877816e-05, + "loss": 3.6098, + "step": 838656 + }, + { + "epoch": 0.02, + "learning_rate": 3.6261180990367296e-05, + "loss": 3.605, + "step": 839168 + }, + { + "epoch": 0.03, + "eval_loss": 3.844721555709839, + "eval_runtime": 304.4125, + "eval_samples_per_second": 1253.533, + "eval_steps_per_second": 39.174, + "step": 839520 + }, + { + "epoch": 1.0, + "learning_rate": 3.625281142166051e-05, + "loss": 3.602, + "step": 839680 + }, + { + "epoch": 1.0, + "learning_rate": 3.624442547414999e-05, + "loss": 3.6011, + "step": 840192 + }, + { + "epoch": 1.0, + "learning_rate": 3.623603952663947e-05, + "loss": 3.6137, + "step": 840704 + }, + { + "epoch": 1.0, + "learning_rate": 3.622765357912895e-05, + "loss": 3.6156, + "step": 841216 + }, + { + "epoch": 1.0, + "learning_rate": 3.621926763161843e-05, + "loss": 3.6268, + "step": 841728 + }, + { + "epoch": 1.0, + "learning_rate": 3.621089806291164e-05, + "loss": 3.605, + "step": 842240 + }, + { + "epoch": 1.0, + "learning_rate": 3.620251211540112e-05, + "loss": 3.6081, + "step": 842752 + }, + { + "epoch": 1.0, + "learning_rate": 3.61941261678906e-05, + "loss": 3.6133, + "step": 843264 + }, + { + "epoch": 1.0, + "learning_rate": 3.618574022038008e-05, + "loss": 3.6027, + "step": 843776 + }, + { + "epoch": 1.0, + "learning_rate": 3.617735427286956e-05, + "loss": 3.604, + "step": 844288 + }, + { + "epoch": 1.0, + "learning_rate": 3.616898470416277e-05, + "loss": 3.6169, + "step": 844800 + }, + { + "epoch": 1.0, + "learning_rate": 3.616059875665225e-05, + "loss": 3.6076, + "step": 845312 + }, + { + "epoch": 1.0, + "learning_rate": 3.615221280914173e-05, + "loss": 3.6171, + "step": 845824 + }, + { + "epoch": 1.0, + "learning_rate": 3.614382686163122e-05, + "loss": 3.5961, + "step": 846336 + }, + { + "epoch": 1.0, + "learning_rate": 3.61354409141207e-05, + "loss": 3.5931, + "step": 846848 + }, + { + "epoch": 1.0, + "learning_rate": 3.6127071345413906e-05, + "loss": 3.5985, + "step": 847360 + }, + { + "epoch": 1.0, + "learning_rate": 3.6118685397903386e-05, + "loss": 3.6159, + "step": 847872 + }, + { + "epoch": 1.0, + "learning_rate": 3.6110299450392866e-05, + "loss": 3.6134, + "step": 848384 + }, + { + "epoch": 1.0, + "learning_rate": 3.6101913502882346e-05, + "loss": 3.5991, + "step": 848896 + }, + { + "epoch": 1.0, + "learning_rate": 3.6093543934175555e-05, + "loss": 3.6139, + "step": 849408 + }, + { + "epoch": 1.0, + "learning_rate": 3.6085157986665035e-05, + "loss": 3.6221, + "step": 849920 + }, + { + "epoch": 1.0, + "learning_rate": 3.6076772039154515e-05, + "loss": 3.603, + "step": 850432 + }, + { + "epoch": 1.0, + "learning_rate": 3.6068386091643995e-05, + "loss": 3.6086, + "step": 850944 + }, + { + "epoch": 1.0, + "learning_rate": 3.6060000144133475e-05, + "loss": 3.6036, + "step": 851456 + }, + { + "epoch": 1.0, + "learning_rate": 3.6051630575426684e-05, + "loss": 3.615, + "step": 851968 + }, + { + "epoch": 1.0, + "learning_rate": 3.604324462791617e-05, + "loss": 3.6025, + "step": 852480 + }, + { + "epoch": 1.0, + "learning_rate": 3.603485868040565e-05, + "loss": 3.5997, + "step": 852992 + }, + { + "epoch": 1.0, + "learning_rate": 3.602647273289513e-05, + "loss": 3.6204, + "step": 853504 + }, + { + "epoch": 1.0, + "learning_rate": 3.601808678538461e-05, + "loss": 3.5959, + "step": 854016 + }, + { + "epoch": 1.0, + "learning_rate": 3.6009700837874083e-05, + "loss": 3.5927, + "step": 854528 + }, + { + "epoch": 1.01, + "learning_rate": 3.60013312691673e-05, + "loss": 3.5978, + "step": 855040 + }, + { + "epoch": 1.01, + "learning_rate": 3.599294532165678e-05, + "loss": 3.6011, + "step": 855552 + }, + { + "epoch": 1.01, + "learning_rate": 3.598455937414625e-05, + "loss": 3.6114, + "step": 856064 + }, + { + "epoch": 1.01, + "learning_rate": 3.597617342663573e-05, + "loss": 3.6178, + "step": 856576 + }, + { + "epoch": 1.01, + "learning_rate": 3.596778747912521e-05, + "loss": 3.5952, + "step": 857088 + }, + { + "epoch": 1.01, + "learning_rate": 3.595940153161469e-05, + "loss": 3.6063, + "step": 857600 + }, + { + "epoch": 1.01, + "learning_rate": 3.595103196290791e-05, + "loss": 3.6114, + "step": 858112 + }, + { + "epoch": 1.01, + "learning_rate": 3.594264601539739e-05, + "loss": 3.5871, + "step": 858624 + }, + { + "epoch": 1.01, + "learning_rate": 3.593426006788687e-05, + "loss": 3.5975, + "step": 859136 + }, + { + "epoch": 1.01, + "learning_rate": 3.592587412037635e-05, + "loss": 3.606, + "step": 859648 + }, + { + "epoch": 1.01, + "learning_rate": 3.591750455166956e-05, + "loss": 3.5921, + "step": 860160 + }, + { + "epoch": 1.01, + "learning_rate": 3.590911860415904e-05, + "loss": 3.6029, + "step": 860672 + }, + { + "epoch": 1.01, + "learning_rate": 3.590073265664852e-05, + "loss": 3.6076, + "step": 861184 + }, + { + "epoch": 1.01, + "learning_rate": 3.5892346709138e-05, + "loss": 3.6069, + "step": 861696 + }, + { + "epoch": 1.01, + "learning_rate": 3.5883977140431206e-05, + "loss": 3.5971, + "step": 862208 + }, + { + "epoch": 1.01, + "learning_rate": 3.5875591192920686e-05, + "loss": 3.6038, + "step": 862720 + }, + { + "epoch": 1.01, + "learning_rate": 3.5867205245410166e-05, + "loss": 3.5989, + "step": 863232 + }, + { + "epoch": 1.01, + "learning_rate": 3.5858819297899646e-05, + "loss": 3.6028, + "step": 863744 + }, + { + "epoch": 1.01, + "learning_rate": 3.5850433350389126e-05, + "loss": 3.5762, + "step": 864256 + }, + { + "epoch": 1.01, + "learning_rate": 3.584206378168234e-05, + "loss": 3.6038, + "step": 864768 + }, + { + "epoch": 1.01, + "learning_rate": 3.583367783417182e-05, + "loss": 3.6026, + "step": 865280 + }, + { + "epoch": 1.01, + "learning_rate": 3.58252918866613e-05, + "loss": 3.6061, + "step": 865792 + }, + { + "epoch": 1.01, + "learning_rate": 3.581690593915078e-05, + "loss": 3.597, + "step": 866304 + }, + { + "epoch": 1.01, + "learning_rate": 3.580851999164026e-05, + "loss": 3.5906, + "step": 866816 + }, + { + "epoch": 1.01, + "learning_rate": 3.580015042293347e-05, + "loss": 3.5911, + "step": 867328 + }, + { + "epoch": 1.01, + "learning_rate": 3.579176447542295e-05, + "loss": 3.5932, + "step": 867840 + }, + { + "epoch": 1.01, + "learning_rate": 3.578337852791243e-05, + "loss": 3.6129, + "step": 868352 + }, + { + "epoch": 1.01, + "learning_rate": 3.577499258040191e-05, + "loss": 3.5895, + "step": 868864 + }, + { + "epoch": 1.01, + "learning_rate": 3.576662301169512e-05, + "loss": 3.6038, + "step": 869376 + }, + { + "epoch": 1.01, + "learning_rate": 3.57582370641846e-05, + "loss": 3.6038, + "step": 869888 + }, + { + "epoch": 1.01, + "learning_rate": 3.574985111667408e-05, + "loss": 3.5857, + "step": 870400 + }, + { + "epoch": 1.01, + "learning_rate": 3.574146516916356e-05, + "loss": 3.5948, + "step": 870912 + }, + { + "epoch": 1.01, + "learning_rate": 3.5733095600456775e-05, + "loss": 3.5855, + "step": 871424 + }, + { + "epoch": 1.01, + "learning_rate": 3.5724709652946255e-05, + "loss": 3.5916, + "step": 871936 + }, + { + "epoch": 1.01, + "learning_rate": 3.5716323705435735e-05, + "loss": 3.5894, + "step": 872448 + }, + { + "epoch": 1.01, + "learning_rate": 3.5707937757925215e-05, + "loss": 3.6094, + "step": 872960 + }, + { + "epoch": 1.01, + "learning_rate": 3.5699568189218424e-05, + "loss": 3.5926, + "step": 873472 + }, + { + "epoch": 1.01, + "learning_rate": 3.5691182241707904e-05, + "loss": 3.5938, + "step": 873984 + }, + { + "epoch": 1.01, + "learning_rate": 3.5682796294197384e-05, + "loss": 3.5853, + "step": 874496 + }, + { + "epoch": 1.01, + "learning_rate": 3.5674410346686864e-05, + "loss": 3.595, + "step": 875008 + }, + { + "epoch": 1.01, + "learning_rate": 3.5666024399176344e-05, + "loss": 3.5999, + "step": 875520 + }, + { + "epoch": 1.01, + "learning_rate": 3.5657638451665824e-05, + "loss": 3.5968, + "step": 876032 + }, + { + "epoch": 1.01, + "learning_rate": 3.564926888295903e-05, + "loss": 3.6015, + "step": 876544 + }, + { + "epoch": 1.01, + "learning_rate": 3.564088293544851e-05, + "loss": 3.5988, + "step": 877056 + }, + { + "epoch": 1.01, + "learning_rate": 3.563249698793799e-05, + "loss": 3.6095, + "step": 877568 + }, + { + "epoch": 1.01, + "learning_rate": 3.562411104042748e-05, + "loss": 3.5889, + "step": 878080 + }, + { + "epoch": 1.01, + "learning_rate": 3.561574147172069e-05, + "loss": 3.6015, + "step": 878592 + }, + { + "epoch": 1.01, + "learning_rate": 3.560735552421017e-05, + "loss": 3.5976, + "step": 879104 + }, + { + "epoch": 1.01, + "learning_rate": 3.559896957669965e-05, + "loss": 3.5937, + "step": 879616 + }, + { + "epoch": 1.01, + "learning_rate": 3.559058362918913e-05, + "loss": 3.6009, + "step": 880128 + }, + { + "epoch": 1.01, + "learning_rate": 3.558221406048234e-05, + "loss": 3.5989, + "step": 880640 + }, + { + "epoch": 1.01, + "learning_rate": 3.557382811297182e-05, + "loss": 3.6067, + "step": 881152 + }, + { + "epoch": 1.01, + "learning_rate": 3.55654421654613e-05, + "loss": 3.6118, + "step": 881664 + }, + { + "epoch": 1.01, + "learning_rate": 3.555705621795078e-05, + "loss": 3.6067, + "step": 882176 + }, + { + "epoch": 1.01, + "learning_rate": 3.554867027044026e-05, + "loss": 3.5801, + "step": 882688 + }, + { + "epoch": 1.01, + "learning_rate": 3.554028432292974e-05, + "loss": 3.5946, + "step": 883200 + }, + { + "epoch": 1.01, + "learning_rate": 3.553191475422295e-05, + "loss": 3.6008, + "step": 883712 + }, + { + "epoch": 1.01, + "learning_rate": 3.5523528806712434e-05, + "loss": 3.5997, + "step": 884224 + }, + { + "epoch": 1.01, + "learning_rate": 3.5515142859201914e-05, + "loss": 3.5947, + "step": 884736 + }, + { + "epoch": 1.01, + "learning_rate": 3.550675691169139e-05, + "loss": 3.5987, + "step": 885248 + }, + { + "epoch": 1.02, + "learning_rate": 3.54983873429846e-05, + "loss": 3.6, + "step": 885760 + }, + { + "epoch": 1.02, + "learning_rate": 3.549000139547408e-05, + "loss": 3.5922, + "step": 886272 + }, + { + "epoch": 1.02, + "learning_rate": 3.548161544796356e-05, + "loss": 3.5924, + "step": 886784 + }, + { + "epoch": 1.02, + "learning_rate": 3.5473229500453036e-05, + "loss": 3.5996, + "step": 887296 + }, + { + "epoch": 1.02, + "learning_rate": 3.5464843552942516e-05, + "loss": 3.6037, + "step": 887808 + }, + { + "epoch": 1.02, + "learning_rate": 3.5456457605431996e-05, + "loss": 3.6076, + "step": 888320 + }, + { + "epoch": 1.02, + "learning_rate": 3.544808803672521e-05, + "loss": 3.5788, + "step": 888832 + }, + { + "epoch": 1.02, + "learning_rate": 3.5439702089214685e-05, + "loss": 3.5955, + "step": 889344 + }, + { + "epoch": 1.02, + "learning_rate": 3.543131614170417e-05, + "loss": 3.5949, + "step": 889856 + }, + { + "epoch": 1.02, + "learning_rate": 3.542293019419365e-05, + "loss": 3.6041, + "step": 890368 + }, + { + "epoch": 1.02, + "learning_rate": 3.541456062548686e-05, + "loss": 3.6011, + "step": 890880 + }, + { + "epoch": 1.02, + "learning_rate": 3.540617467797634e-05, + "loss": 3.5891, + "step": 891392 + }, + { + "epoch": 1.02, + "learning_rate": 3.539778873046582e-05, + "loss": 3.5912, + "step": 891904 + }, + { + "epoch": 1.02, + "learning_rate": 3.53894027829553e-05, + "loss": 3.5825, + "step": 892416 + }, + { + "epoch": 1.02, + "learning_rate": 3.538101683544478e-05, + "loss": 3.5985, + "step": 892928 + }, + { + "epoch": 1.02, + "learning_rate": 3.537263088793426e-05, + "loss": 3.5887, + "step": 893440 + }, + { + "epoch": 1.02, + "learning_rate": 3.536424494042374e-05, + "loss": 3.5866, + "step": 893952 + }, + { + "epoch": 1.02, + "learning_rate": 3.535587537171695e-05, + "loss": 3.6, + "step": 894464 + }, + { + "epoch": 1.02, + "learning_rate": 3.534750580301016e-05, + "loss": 3.5925, + "step": 894976 + }, + { + "epoch": 1.02, + "learning_rate": 3.533911985549964e-05, + "loss": 3.5884, + "step": 895488 + }, + { + "epoch": 1.02, + "learning_rate": 3.5330733907989125e-05, + "loss": 3.5918, + "step": 896000 + }, + { + "epoch": 1.02, + "learning_rate": 3.5322347960478605e-05, + "loss": 3.5836, + "step": 896512 + }, + { + "epoch": 1.02, + "learning_rate": 3.5313978391771814e-05, + "loss": 3.6034, + "step": 897024 + }, + { + "epoch": 1.02, + "learning_rate": 3.5305592444261294e-05, + "loss": 3.5822, + "step": 897536 + }, + { + "epoch": 1.02, + "learning_rate": 3.5297206496750774e-05, + "loss": 3.5982, + "step": 898048 + }, + { + "epoch": 1.02, + "learning_rate": 3.5288820549240254e-05, + "loss": 3.5965, + "step": 898560 + }, + { + "epoch": 1.02, + "learning_rate": 3.5280434601729734e-05, + "loss": 3.5975, + "step": 899072 + }, + { + "epoch": 1.02, + "learning_rate": 3.527206503302294e-05, + "loss": 3.5941, + "step": 899584 + }, + { + "epoch": 1.02, + "learning_rate": 3.526367908551242e-05, + "loss": 3.5942, + "step": 900096 + }, + { + "epoch": 1.02, + "learning_rate": 3.52552931380019e-05, + "loss": 3.601, + "step": 900608 + }, + { + "epoch": 1.02, + "learning_rate": 3.524690719049138e-05, + "loss": 3.5989, + "step": 901120 + }, + { + "epoch": 1.02, + "learning_rate": 3.523853762178459e-05, + "loss": 3.5899, + "step": 901632 + }, + { + "epoch": 1.02, + "learning_rate": 3.523015167427408e-05, + "loss": 3.5924, + "step": 902144 + }, + { + "epoch": 1.02, + "learning_rate": 3.522176572676356e-05, + "loss": 3.5937, + "step": 902656 + }, + { + "epoch": 1.02, + "learning_rate": 3.521337977925304e-05, + "loss": 3.5986, + "step": 903168 + }, + { + "epoch": 1.02, + "learning_rate": 3.520499383174252e-05, + "loss": 3.5882, + "step": 903680 + }, + { + "epoch": 1.02, + "learning_rate": 3.5196607884232e-05, + "loss": 3.5851, + "step": 904192 + }, + { + "epoch": 1.02, + "learning_rate": 3.518823831552521e-05, + "loss": 3.5855, + "step": 904704 + }, + { + "epoch": 1.02, + "learning_rate": 3.517985236801469e-05, + "loss": 3.5876, + "step": 905216 + }, + { + "epoch": 1.02, + "learning_rate": 3.517146642050417e-05, + "loss": 3.5986, + "step": 905728 + }, + { + "epoch": 1.02, + "learning_rate": 3.516308047299365e-05, + "loss": 3.5917, + "step": 906240 + }, + { + "epoch": 1.02, + "learning_rate": 3.515471090428686e-05, + "loss": 3.6058, + "step": 906752 + }, + { + "epoch": 1.02, + "learning_rate": 3.5146324956776337e-05, + "loss": 3.5806, + "step": 907264 + }, + { + "epoch": 1.02, + "learning_rate": 3.5137939009265817e-05, + "loss": 3.6014, + "step": 907776 + }, + { + "epoch": 1.02, + "learning_rate": 3.5129553061755297e-05, + "loss": 3.5954, + "step": 908288 + }, + { + "epoch": 1.02, + "learning_rate": 3.512118349304851e-05, + "loss": 3.5996, + "step": 908800 + }, + { + "epoch": 1.02, + "learning_rate": 3.511279754553799e-05, + "loss": 3.596, + "step": 909312 + }, + { + "epoch": 1.02, + "learning_rate": 3.510441159802747e-05, + "loss": 3.5902, + "step": 909824 + }, + { + "epoch": 1.02, + "learning_rate": 3.509602565051695e-05, + "loss": 3.5917, + "step": 910336 + }, + { + "epoch": 1.02, + "learning_rate": 3.508763970300643e-05, + "loss": 3.6048, + "step": 910848 + }, + { + "epoch": 1.02, + "learning_rate": 3.507927013429964e-05, + "loss": 3.5877, + "step": 911360 + }, + { + "epoch": 1.02, + "learning_rate": 3.507088418678912e-05, + "loss": 3.5922, + "step": 911872 + }, + { + "epoch": 1.02, + "learning_rate": 3.50624982392786e-05, + "loss": 3.5968, + "step": 912384 + }, + { + "epoch": 1.02, + "learning_rate": 3.505411229176808e-05, + "loss": 3.5915, + "step": 912896 + }, + { + "epoch": 1.02, + "learning_rate": 3.504574272306129e-05, + "loss": 3.5903, + "step": 913408 + }, + { + "epoch": 1.02, + "learning_rate": 3.503735677555077e-05, + "loss": 3.5982, + "step": 913920 + }, + { + "epoch": 1.02, + "learning_rate": 3.502897082804025e-05, + "loss": 3.5871, + "step": 914432 + }, + { + "epoch": 1.02, + "learning_rate": 3.502058488052973e-05, + "loss": 3.5911, + "step": 914944 + }, + { + "epoch": 1.02, + "learning_rate": 3.5012215311822946e-05, + "loss": 3.5866, + "step": 915456 + }, + { + "epoch": 1.03, + "eval_loss": 3.8441641330718994, + "eval_runtime": 304.0696, + "eval_samples_per_second": 1254.946, + "eval_steps_per_second": 39.218, + "step": 915840 + }, + { + "epoch": 0.0, + "learning_rate": 3.5003829364312426e-05, + "loss": 3.5951, + "step": 915968 + }, + { + "epoch": 0.0, + "learning_rate": 3.4995443416801906e-05, + "loss": 3.578, + "step": 916480 + }, + { + "epoch": 0.0, + "learning_rate": 3.4987057469291386e-05, + "loss": 3.5951, + "step": 916992 + }, + { + "epoch": 0.0, + "learning_rate": 3.4978671521780866e-05, + "loss": 3.5978, + "step": 917504 + }, + { + "epoch": 0.0, + "learning_rate": 3.4970285574270346e-05, + "loss": 3.6014, + "step": 918016 + }, + { + "epoch": 0.0, + "learning_rate": 3.4961916005563555e-05, + "loss": 3.5915, + "step": 918528 + }, + { + "epoch": 0.0, + "learning_rate": 3.4953530058053035e-05, + "loss": 3.5884, + "step": 919040 + }, + { + "epoch": 0.0, + "learning_rate": 3.4945144110542515e-05, + "loss": 3.5925, + "step": 919552 + }, + { + "epoch": 0.0, + "learning_rate": 3.493675816303199e-05, + "loss": 3.5837, + "step": 920064 + }, + { + "epoch": 0.0, + "learning_rate": 3.4928388594325204e-05, + "loss": 3.5869, + "step": 920576 + }, + { + "epoch": 0.0, + "learning_rate": 3.4920002646814684e-05, + "loss": 3.5935, + "step": 921088 + }, + { + "epoch": 0.0, + "learning_rate": 3.4911616699304164e-05, + "loss": 3.5898, + "step": 921600 + }, + { + "epoch": 0.0, + "learning_rate": 3.4903230751793644e-05, + "loss": 3.6006, + "step": 922112 + }, + { + "epoch": 0.0, + "learning_rate": 3.4894844804283124e-05, + "loss": 3.5783, + "step": 922624 + }, + { + "epoch": 0.0, + "learning_rate": 3.488647523557634e-05, + "loss": 3.5745, + "step": 923136 + }, + { + "epoch": 0.0, + "learning_rate": 3.487808928806582e-05, + "loss": 3.5773, + "step": 923648 + }, + { + "epoch": 0.0, + "learning_rate": 3.486970334055529e-05, + "loss": 3.6012, + "step": 924160 + }, + { + "epoch": 0.0, + "learning_rate": 3.486131739304477e-05, + "loss": 3.5886, + "step": 924672 + }, + { + "epoch": 0.0, + "learning_rate": 3.485293144553425e-05, + "loss": 3.5835, + "step": 925184 + }, + { + "epoch": 0.0, + "learning_rate": 3.484456187682746e-05, + "loss": 3.5958, + "step": 925696 + }, + { + "epoch": 0.0, + "learning_rate": 3.483617592931694e-05, + "loss": 3.602, + "step": 926208 + }, + { + "epoch": 0.0, + "learning_rate": 3.482778998180642e-05, + "loss": 3.5868, + "step": 926720 + }, + { + "epoch": 0.0, + "learning_rate": 3.48194040342959e-05, + "loss": 3.5885, + "step": 927232 + }, + { + "epoch": 0.0, + "learning_rate": 3.481103446558912e-05, + "loss": 3.5855, + "step": 927744 + }, + { + "epoch": 0.0, + "learning_rate": 3.48026485180786e-05, + "loss": 3.5995, + "step": 928256 + }, + { + "epoch": 0.0, + "learning_rate": 3.479426257056808e-05, + "loss": 3.582, + "step": 928768 + }, + { + "epoch": 0.0, + "learning_rate": 3.478587662305756e-05, + "loss": 3.5798, + "step": 929280 + }, + { + "epoch": 0.0, + "learning_rate": 3.477749067554704e-05, + "loss": 3.6027, + "step": 929792 + }, + { + "epoch": 0.0, + "learning_rate": 3.4769121106840246e-05, + "loss": 3.5713, + "step": 930304 + }, + { + "epoch": 0.0, + "learning_rate": 3.4760735159329726e-05, + "loss": 3.5749, + "step": 930816 + }, + { + "epoch": 0.01, + "learning_rate": 3.4752349211819206e-05, + "loss": 3.5805, + "step": 931328 + }, + { + "epoch": 0.01, + "learning_rate": 3.4743963264308686e-05, + "loss": 3.583, + "step": 931840 + }, + { + "epoch": 0.01, + "learning_rate": 3.4735593695601895e-05, + "loss": 3.5924, + "step": 932352 + }, + { + "epoch": 0.01, + "learning_rate": 3.4727207748091375e-05, + "loss": 3.596, + "step": 932864 + }, + { + "epoch": 0.01, + "learning_rate": 3.4718821800580855e-05, + "loss": 3.5803, + "step": 933376 + }, + { + "epoch": 0.01, + "learning_rate": 3.471043585307034e-05, + "loss": 3.5831, + "step": 933888 + }, + { + "epoch": 0.01, + "learning_rate": 3.470204990555982e-05, + "loss": 3.5947, + "step": 934400 + }, + { + "epoch": 0.01, + "learning_rate": 3.46936639580493e-05, + "loss": 3.5699, + "step": 934912 + }, + { + "epoch": 0.01, + "learning_rate": 3.468527801053878e-05, + "loss": 3.5825, + "step": 935424 + }, + { + "epoch": 0.01, + "learning_rate": 3.467690844183199e-05, + "loss": 3.5843, + "step": 935936 + }, + { + "epoch": 0.01, + "learning_rate": 3.466852249432147e-05, + "loss": 3.5732, + "step": 936448 + }, + { + "epoch": 0.01, + "learning_rate": 3.466013654681095e-05, + "loss": 3.5822, + "step": 936960 + }, + { + "epoch": 0.01, + "learning_rate": 3.465175059930043e-05, + "loss": 3.5938, + "step": 937472 + }, + { + "epoch": 0.01, + "learning_rate": 3.464338103059364e-05, + "loss": 3.5848, + "step": 937984 + }, + { + "epoch": 0.01, + "learning_rate": 3.463499508308312e-05, + "loss": 3.5781, + "step": 938496 + }, + { + "epoch": 0.01, + "learning_rate": 3.46266091355726e-05, + "loss": 3.5913, + "step": 939008 + }, + { + "epoch": 0.01, + "learning_rate": 3.461822318806208e-05, + "loss": 3.5808, + "step": 939520 + }, + { + "epoch": 0.01, + "learning_rate": 3.460983724055156e-05, + "loss": 3.5844, + "step": 940032 + }, + { + "epoch": 0.01, + "learning_rate": 3.4601467671844776e-05, + "loss": 3.5554, + "step": 940544 + }, + { + "epoch": 0.01, + "learning_rate": 3.4593081724334256e-05, + "loss": 3.583, + "step": 941056 + }, + { + "epoch": 0.01, + "learning_rate": 3.4584695776823735e-05, + "loss": 3.5901, + "step": 941568 + }, + { + "epoch": 0.01, + "learning_rate": 3.4576309829313215e-05, + "loss": 3.5841, + "step": 942080 + }, + { + "epoch": 0.01, + "learning_rate": 3.4567940260606425e-05, + "loss": 3.5773, + "step": 942592 + }, + { + "epoch": 0.01, + "learning_rate": 3.4559554313095904e-05, + "loss": 3.5767, + "step": 943104 + }, + { + "epoch": 0.01, + "learning_rate": 3.4551168365585384e-05, + "loss": 3.5705, + "step": 943616 + }, + { + "epoch": 0.01, + "learning_rate": 3.4542782418074864e-05, + "loss": 3.5715, + "step": 944128 + }, + { + "epoch": 0.01, + "learning_rate": 3.4534396470564344e-05, + "loss": 3.5993, + "step": 944640 + }, + { + "epoch": 0.01, + "learning_rate": 3.4526026901857553e-05, + "loss": 3.5736, + "step": 945152 + }, + { + "epoch": 0.01, + "learning_rate": 3.4517640954347033e-05, + "loss": 3.5839, + "step": 945664 + }, + { + "epoch": 0.01, + "learning_rate": 3.450925500683651e-05, + "loss": 3.5859, + "step": 946176 + }, + { + "epoch": 0.01, + "learning_rate": 3.450086905932599e-05, + "loss": 3.5677, + "step": 946688 + }, + { + "epoch": 0.01, + "learning_rate": 3.449249949061921e-05, + "loss": 3.5761, + "step": 947200 + }, + { + "epoch": 0.01, + "learning_rate": 3.448411354310869e-05, + "loss": 3.5689, + "step": 947712 + }, + { + "epoch": 0.01, + "learning_rate": 3.447572759559817e-05, + "loss": 3.5702, + "step": 948224 + }, + { + "epoch": 0.01, + "learning_rate": 3.446734164808765e-05, + "loss": 3.5734, + "step": 948736 + }, + { + "epoch": 0.01, + "learning_rate": 3.445895570057712e-05, + "loss": 3.5906, + "step": 949248 + }, + { + "epoch": 0.01, + "learning_rate": 3.445058613187034e-05, + "loss": 3.5804, + "step": 949760 + }, + { + "epoch": 0.01, + "learning_rate": 3.444220018435982e-05, + "loss": 3.5729, + "step": 950272 + }, + { + "epoch": 0.01, + "learning_rate": 3.44338142368493e-05, + "loss": 3.564, + "step": 950784 + }, + { + "epoch": 0.01, + "learning_rate": 3.442542828933877e-05, + "loss": 3.5781, + "step": 951296 + }, + { + "epoch": 0.01, + "learning_rate": 3.441704234182825e-05, + "loss": 3.5812, + "step": 951808 + }, + { + "epoch": 0.01, + "learning_rate": 3.440865639431773e-05, + "loss": 3.5803, + "step": 952320 + }, + { + "epoch": 0.01, + "learning_rate": 3.440028682561095e-05, + "loss": 3.5805, + "step": 952832 + }, + { + "epoch": 0.01, + "learning_rate": 3.439190087810043e-05, + "loss": 3.5803, + "step": 953344 + }, + { + "epoch": 0.01, + "learning_rate": 3.438351493058991e-05, + "loss": 3.5918, + "step": 953856 + }, + { + "epoch": 0.01, + "learning_rate": 3.437512898307939e-05, + "loss": 3.5724, + "step": 954368 + }, + { + "epoch": 0.01, + "learning_rate": 3.436674303556887e-05, + "loss": 3.5779, + "step": 954880 + }, + { + "epoch": 0.01, + "learning_rate": 3.4358373466862076e-05, + "loss": 3.5851, + "step": 955392 + }, + { + "epoch": 0.01, + "learning_rate": 3.4349987519351556e-05, + "loss": 3.5767, + "step": 955904 + }, + { + "epoch": 0.01, + "learning_rate": 3.4341601571841036e-05, + "loss": 3.5799, + "step": 956416 + }, + { + "epoch": 0.01, + "learning_rate": 3.4333215624330516e-05, + "loss": 3.5823, + "step": 956928 + }, + { + "epoch": 0.01, + "learning_rate": 3.4324829676819996e-05, + "loss": 3.5854, + "step": 957440 + }, + { + "epoch": 0.01, + "learning_rate": 3.4316460108113205e-05, + "loss": 3.5972, + "step": 957952 + }, + { + "epoch": 0.01, + "learning_rate": 3.4308074160602685e-05, + "loss": 3.5858, + "step": 958464 + }, + { + "epoch": 0.01, + "learning_rate": 3.429968821309217e-05, + "loss": 3.5617, + "step": 958976 + }, + { + "epoch": 0.01, + "learning_rate": 3.429130226558165e-05, + "loss": 3.5719, + "step": 959488 + }, + { + "epoch": 0.01, + "learning_rate": 3.428293269687486e-05, + "loss": 3.5849, + "step": 960000 + }, + { + "epoch": 0.01, + "learning_rate": 3.427454674936434e-05, + "loss": 3.5831, + "step": 960512 + }, + { + "epoch": 0.01, + "learning_rate": 3.426616080185382e-05, + "loss": 3.5744, + "step": 961024 + }, + { + "epoch": 0.01, + "learning_rate": 3.42577748543433e-05, + "loss": 3.5836, + "step": 961536 + }, + { + "epoch": 0.02, + "learning_rate": 3.424940528563651e-05, + "loss": 3.5823, + "step": 962048 + }, + { + "epoch": 0.02, + "learning_rate": 3.424101933812599e-05, + "loss": 3.5722, + "step": 962560 + }, + { + "epoch": 0.02, + "learning_rate": 3.423263339061547e-05, + "loss": 3.5726, + "step": 963072 + }, + { + "epoch": 0.02, + "learning_rate": 3.422424744310495e-05, + "loss": 3.5813, + "step": 963584 + }, + { + "epoch": 0.02, + "learning_rate": 3.421586149559443e-05, + "loss": 3.5808, + "step": 964096 + }, + { + "epoch": 0.02, + "learning_rate": 3.420747554808391e-05, + "loss": 3.5894, + "step": 964608 + }, + { + "epoch": 0.02, + "learning_rate": 3.4199105979377125e-05, + "loss": 3.5681, + "step": 965120 + }, + { + "epoch": 0.02, + "learning_rate": 3.4190720031866605e-05, + "loss": 3.5731, + "step": 965632 + }, + { + "epoch": 0.02, + "learning_rate": 3.4182334084356085e-05, + "loss": 3.5808, + "step": 966144 + }, + { + "epoch": 0.02, + "learning_rate": 3.4173948136845565e-05, + "loss": 3.5826, + "step": 966656 + }, + { + "epoch": 0.02, + "learning_rate": 3.4165578568138774e-05, + "loss": 3.5828, + "step": 967168 + }, + { + "epoch": 0.02, + "learning_rate": 3.4157192620628254e-05, + "loss": 3.5727, + "step": 967680 + }, + { + "epoch": 0.02, + "learning_rate": 3.4148806673117734e-05, + "loss": 3.5722, + "step": 968192 + }, + { + "epoch": 0.02, + "learning_rate": 3.4140420725607214e-05, + "loss": 3.565, + "step": 968704 + }, + { + "epoch": 0.02, + "learning_rate": 3.413205115690042e-05, + "loss": 3.5797, + "step": 969216 + }, + { + "epoch": 0.02, + "learning_rate": 3.41236652093899e-05, + "loss": 3.5704, + "step": 969728 + }, + { + "epoch": 0.02, + "learning_rate": 3.411527926187938e-05, + "loss": 3.5695, + "step": 970240 + }, + { + "epoch": 0.02, + "learning_rate": 3.410689331436886e-05, + "loss": 3.5801, + "step": 970752 + }, + { + "epoch": 0.02, + "learning_rate": 3.409850736685834e-05, + "loss": 3.5743, + "step": 971264 + }, + { + "epoch": 0.02, + "learning_rate": 3.409013779815156e-05, + "loss": 3.5733, + "step": 971776 + }, + { + "epoch": 0.02, + "learning_rate": 3.408175185064104e-05, + "loss": 3.5758, + "step": 972288 + }, + { + "epoch": 0.02, + "learning_rate": 3.407336590313052e-05, + "loss": 3.5623, + "step": 972800 + }, + { + "epoch": 0.02, + "learning_rate": 3.406497995562e-05, + "loss": 3.5817, + "step": 973312 + }, + { + "epoch": 0.02, + "learning_rate": 3.405659400810948e-05, + "loss": 3.5673, + "step": 973824 + }, + { + "epoch": 0.02, + "learning_rate": 3.404822443940269e-05, + "loss": 3.5751, + "step": 974336 + }, + { + "epoch": 0.02, + "learning_rate": 3.403983849189217e-05, + "loss": 3.5814, + "step": 974848 + }, + { + "epoch": 0.02, + "learning_rate": 3.403145254438165e-05, + "loss": 3.5817, + "step": 975360 + }, + { + "epoch": 0.02, + "learning_rate": 3.402306659687113e-05, + "loss": 3.5755, + "step": 975872 + }, + { + "epoch": 0.02, + "learning_rate": 3.401469702816434e-05, + "loss": 3.5777, + "step": 976384 + }, + { + "epoch": 0.02, + "learning_rate": 3.400631108065382e-05, + "loss": 3.5823, + "step": 976896 + }, + { + "epoch": 0.02, + "learning_rate": 3.3997925133143297e-05, + "loss": 3.5774, + "step": 977408 + }, + { + "epoch": 0.02, + "learning_rate": 3.3989539185632777e-05, + "loss": 3.5724, + "step": 977920 + }, + { + "epoch": 0.02, + "learning_rate": 3.3981153238122257e-05, + "loss": 3.5747, + "step": 978432 + }, + { + "epoch": 0.02, + "learning_rate": 3.397278366941547e-05, + "loss": 3.574, + "step": 978944 + }, + { + "epoch": 0.02, + "learning_rate": 3.396439772190495e-05, + "loss": 3.5812, + "step": 979456 + }, + { + "epoch": 0.02, + "learning_rate": 3.395601177439443e-05, + "loss": 3.5654, + "step": 979968 + }, + { + "epoch": 0.02, + "learning_rate": 3.3947625826883905e-05, + "loss": 3.5711, + "step": 980480 + }, + { + "epoch": 0.02, + "learning_rate": 3.393925625817712e-05, + "loss": 3.5683, + "step": 980992 + }, + { + "epoch": 0.02, + "learning_rate": 3.39308703106666e-05, + "loss": 3.573, + "step": 981504 + }, + { + "epoch": 0.02, + "learning_rate": 3.392248436315608e-05, + "loss": 3.5822, + "step": 982016 + }, + { + "epoch": 0.02, + "learning_rate": 3.3914098415645554e-05, + "loss": 3.5716, + "step": 982528 + }, + { + "epoch": 0.02, + "learning_rate": 3.390572884693877e-05, + "loss": 3.5853, + "step": 983040 + }, + { + "epoch": 0.02, + "learning_rate": 3.389734289942825e-05, + "loss": 3.5683, + "step": 983552 + }, + { + "epoch": 0.02, + "learning_rate": 3.388895695191773e-05, + "loss": 3.5817, + "step": 984064 + }, + { + "epoch": 0.02, + "learning_rate": 3.388057100440721e-05, + "loss": 3.5768, + "step": 984576 + }, + { + "epoch": 0.02, + "learning_rate": 3.3872201435700426e-05, + "loss": 3.5825, + "step": 985088 + }, + { + "epoch": 0.02, + "learning_rate": 3.3863815488189906e-05, + "loss": 3.5758, + "step": 985600 + }, + { + "epoch": 0.02, + "learning_rate": 3.385542954067938e-05, + "loss": 3.5749, + "step": 986112 + }, + { + "epoch": 0.02, + "learning_rate": 3.384704359316886e-05, + "loss": 3.5756, + "step": 986624 + }, + { + "epoch": 0.02, + "learning_rate": 3.383865764565834e-05, + "loss": 3.5866, + "step": 987136 + }, + { + "epoch": 0.02, + "learning_rate": 3.383027169814782e-05, + "loss": 3.5713, + "step": 987648 + }, + { + "epoch": 0.02, + "learning_rate": 3.382190212944103e-05, + "loss": 3.5742, + "step": 988160 + }, + { + "epoch": 0.02, + "learning_rate": 3.381351618193051e-05, + "loss": 3.5801, + "step": 988672 + }, + { + "epoch": 0.02, + "learning_rate": 3.380513023441999e-05, + "loss": 3.5725, + "step": 989184 + }, + { + "epoch": 0.02, + "learning_rate": 3.379674428690947e-05, + "loss": 3.5696, + "step": 989696 + }, + { + "epoch": 0.02, + "learning_rate": 3.3788374718202684e-05, + "loss": 3.5835, + "step": 990208 + }, + { + "epoch": 0.02, + "learning_rate": 3.3779988770692164e-05, + "loss": 3.568, + "step": 990720 + }, + { + "epoch": 0.02, + "learning_rate": 3.3771602823181644e-05, + "loss": 3.5751, + "step": 991232 + }, + { + "epoch": 0.02, + "learning_rate": 3.3763216875671124e-05, + "loss": 3.57, + "step": 991744 + }, + { + "epoch": 0.03, + "eval_loss": 3.843111753463745, + "eval_runtime": 304.8917, + "eval_samples_per_second": 1251.563, + "eval_steps_per_second": 39.112, + "step": 992160 + }, + { + "epoch": 1.0, + "learning_rate": 3.375484730696433e-05, + "loss": 3.57, + "step": 992256 + }, + { + "epoch": 1.0, + "learning_rate": 3.374646135945381e-05, + "loss": 3.5621, + "step": 992768 + }, + { + "epoch": 1.0, + "learning_rate": 3.373807541194329e-05, + "loss": 3.576, + "step": 993280 + }, + { + "epoch": 1.0, + "learning_rate": 3.372968946443277e-05, + "loss": 3.5863, + "step": 993792 + }, + { + "epoch": 1.0, + "learning_rate": 3.372130351692225e-05, + "loss": 3.58, + "step": 994304 + }, + { + "epoch": 1.0, + "learning_rate": 3.371293394821546e-05, + "loss": 3.5767, + "step": 994816 + }, + { + "epoch": 1.0, + "learning_rate": 3.370454800070494e-05, + "loss": 3.565, + "step": 995328 + }, + { + "epoch": 1.0, + "learning_rate": 3.369616205319442e-05, + "loss": 3.5762, + "step": 995840 + }, + { + "epoch": 1.0, + "learning_rate": 3.36877761056839e-05, + "loss": 3.5649, + "step": 996352 + }, + { + "epoch": 1.0, + "learning_rate": 3.367940653697712e-05, + "loss": 3.5749, + "step": 996864 + }, + { + "epoch": 1.0, + "learning_rate": 3.36710205894666e-05, + "loss": 3.5748, + "step": 997376 + }, + { + "epoch": 1.0, + "learning_rate": 3.366263464195608e-05, + "loss": 3.5729, + "step": 997888 + }, + { + "epoch": 1.0, + "learning_rate": 3.365424869444556e-05, + "loss": 3.5835, + "step": 998400 + }, + { + "epoch": 1.0, + "learning_rate": 3.3645879125738766e-05, + "loss": 3.5586, + "step": 998912 + }, + { + "epoch": 1.0, + "learning_rate": 3.3637493178228246e-05, + "loss": 3.558, + "step": 999424 + }, + { + "epoch": 1.0, + "learning_rate": 3.3629107230717726e-05, + "loss": 3.5608, + "step": 999936 + }, + { + "epoch": 1.0, + "learning_rate": 3.3620721283207206e-05, + "loss": 3.5818, + "step": 1000448 + }, + { + "epoch": 1.0, + "learning_rate": 3.3612351714500415e-05, + "loss": 3.5696, + "step": 1000960 + }, + { + "epoch": 1.0, + "learning_rate": 3.3603965766989895e-05, + "loss": 3.569, + "step": 1001472 + }, + { + "epoch": 1.0, + "learning_rate": 3.3595579819479375e-05, + "loss": 3.5764, + "step": 1001984 + }, + { + "epoch": 1.0, + "learning_rate": 3.3587193871968855e-05, + "loss": 3.5848, + "step": 1002496 + }, + { + "epoch": 1.0, + "learning_rate": 3.357882430326207e-05, + "loss": 3.57, + "step": 1003008 + }, + { + "epoch": 1.0, + "learning_rate": 3.357043835575155e-05, + "loss": 3.5686, + "step": 1003520 + }, + { + "epoch": 1.0, + "learning_rate": 3.356205240824103e-05, + "loss": 3.5699, + "step": 1004032 + }, + { + "epoch": 1.0, + "learning_rate": 3.355366646073051e-05, + "loss": 3.5813, + "step": 1004544 + }, + { + "epoch": 1.0, + "learning_rate": 3.354529689202372e-05, + "loss": 3.5672, + "step": 1005056 + }, + { + "epoch": 1.0, + "learning_rate": 3.35369109445132e-05, + "loss": 3.5631, + "step": 1005568 + }, + { + "epoch": 1.0, + "learning_rate": 3.352852499700268e-05, + "loss": 3.5865, + "step": 1006080 + }, + { + "epoch": 1.0, + "learning_rate": 3.352013904949216e-05, + "loss": 3.5547, + "step": 1006592 + }, + { + "epoch": 1.0, + "learning_rate": 3.351175310198164e-05, + "loss": 3.5599, + "step": 1007104 + }, + { + "epoch": 1.01, + "learning_rate": 3.350338353327485e-05, + "loss": 3.5624, + "step": 1007616 + }, + { + "epoch": 1.01, + "learning_rate": 3.349499758576433e-05, + "loss": 3.5665, + "step": 1008128 + }, + { + "epoch": 1.01, + "learning_rate": 3.348661163825381e-05, + "loss": 3.5747, + "step": 1008640 + }, + { + "epoch": 1.01, + "learning_rate": 3.347822569074329e-05, + "loss": 3.5798, + "step": 1009152 + }, + { + "epoch": 1.01, + "learning_rate": 3.3469856122036505e-05, + "loss": 3.5636, + "step": 1009664 + }, + { + "epoch": 1.01, + "learning_rate": 3.3461470174525985e-05, + "loss": 3.5655, + "step": 1010176 + }, + { + "epoch": 1.01, + "learning_rate": 3.3453084227015465e-05, + "loss": 3.576, + "step": 1010688 + }, + { + "epoch": 1.01, + "learning_rate": 3.3444698279504945e-05, + "loss": 3.5561, + "step": 1011200 + }, + { + "epoch": 1.01, + "learning_rate": 3.3436328710798154e-05, + "loss": 3.5632, + "step": 1011712 + }, + { + "epoch": 1.01, + "learning_rate": 3.3427942763287634e-05, + "loss": 3.5642, + "step": 1012224 + }, + { + "epoch": 1.01, + "learning_rate": 3.3419556815777114e-05, + "loss": 3.5618, + "step": 1012736 + }, + { + "epoch": 1.01, + "learning_rate": 3.3411170868266594e-05, + "loss": 3.5579, + "step": 1013248 + }, + { + "epoch": 1.01, + "learning_rate": 3.3402784920756074e-05, + "loss": 3.5798, + "step": 1013760 + }, + { + "epoch": 1.01, + "learning_rate": 3.3394398973245554e-05, + "loss": 3.5645, + "step": 1014272 + }, + { + "epoch": 1.01, + "learning_rate": 3.3386013025735033e-05, + "loss": 3.5664, + "step": 1014784 + }, + { + "epoch": 1.01, + "learning_rate": 3.337764345702824e-05, + "loss": 3.5699, + "step": 1015296 + }, + { + "epoch": 1.01, + "learning_rate": 3.336925750951773e-05, + "loss": 3.5648, + "step": 1015808 + }, + { + "epoch": 1.01, + "learning_rate": 3.336087156200721e-05, + "loss": 3.5636, + "step": 1016320 + }, + { + "epoch": 1.01, + "learning_rate": 3.335248561449669e-05, + "loss": 3.5427, + "step": 1016832 + }, + { + "epoch": 1.01, + "learning_rate": 3.33441160457899e-05, + "loss": 3.5617, + "step": 1017344 + }, + { + "epoch": 1.01, + "learning_rate": 3.333573009827938e-05, + "loss": 3.5742, + "step": 1017856 + }, + { + "epoch": 1.01, + "learning_rate": 3.332734415076886e-05, + "loss": 3.569, + "step": 1018368 + }, + { + "epoch": 1.01, + "learning_rate": 3.331895820325834e-05, + "loss": 3.5555, + "step": 1018880 + }, + { + "epoch": 1.01, + "learning_rate": 3.331058863455155e-05, + "loss": 3.5551, + "step": 1019392 + }, + { + "epoch": 1.01, + "learning_rate": 3.330220268704103e-05, + "loss": 3.5596, + "step": 1019904 + }, + { + "epoch": 1.01, + "learning_rate": 3.329381673953051e-05, + "loss": 3.5512, + "step": 1020416 + }, + { + "epoch": 1.01, + "learning_rate": 3.328543079201998e-05, + "loss": 3.583, + "step": 1020928 + }, + { + "epoch": 1.01, + "learning_rate": 3.3277061223313196e-05, + "loss": 3.5533, + "step": 1021440 + }, + { + "epoch": 1.01, + "learning_rate": 3.326867527580268e-05, + "loss": 3.5699, + "step": 1021952 + }, + { + "epoch": 1.01, + "learning_rate": 3.326028932829216e-05, + "loss": 3.5695, + "step": 1022464 + }, + { + "epoch": 1.01, + "learning_rate": 3.3251903380781636e-05, + "loss": 3.5472, + "step": 1022976 + }, + { + "epoch": 1.01, + "learning_rate": 3.324353381207485e-05, + "loss": 3.5609, + "step": 1023488 + }, + { + "epoch": 1.01, + "learning_rate": 3.323514786456433e-05, + "loss": 3.5504, + "step": 1024000 + }, + { + "epoch": 1.01, + "learning_rate": 3.3226761917053805e-05, + "loss": 3.553, + "step": 1024512 + }, + { + "epoch": 1.01, + "learning_rate": 3.3218375969543285e-05, + "loss": 3.5537, + "step": 1025024 + }, + { + "epoch": 1.01, + "learning_rate": 3.3209990022032765e-05, + "loss": 3.5718, + "step": 1025536 + }, + { + "epoch": 1.01, + "learning_rate": 3.320162045332598e-05, + "loss": 3.5642, + "step": 1026048 + }, + { + "epoch": 1.01, + "learning_rate": 3.3193234505815454e-05, + "loss": 3.5579, + "step": 1026560 + }, + { + "epoch": 1.01, + "learning_rate": 3.3184848558304934e-05, + "loss": 3.5472, + "step": 1027072 + }, + { + "epoch": 1.01, + "learning_rate": 3.317646261079442e-05, + "loss": 3.5607, + "step": 1027584 + }, + { + "epoch": 1.01, + "learning_rate": 3.31680766632839e-05, + "loss": 3.5651, + "step": 1028096 + }, + { + "epoch": 1.01, + "learning_rate": 3.315969071577338e-05, + "loss": 3.5656, + "step": 1028608 + }, + { + "epoch": 1.01, + "learning_rate": 3.315132114706659e-05, + "loss": 3.5595, + "step": 1029120 + }, + { + "epoch": 1.01, + "learning_rate": 3.314293519955607e-05, + "loss": 3.5644, + "step": 1029632 + }, + { + "epoch": 1.01, + "learning_rate": 3.313454925204555e-05, + "loss": 3.5759, + "step": 1030144 + }, + { + "epoch": 1.01, + "learning_rate": 3.312616330453503e-05, + "loss": 3.5576, + "step": 1030656 + }, + { + "epoch": 1.01, + "learning_rate": 3.311779373582824e-05, + "loss": 3.5592, + "step": 1031168 + }, + { + "epoch": 1.01, + "learning_rate": 3.310940778831772e-05, + "loss": 3.5639, + "step": 1031680 + }, + { + "epoch": 1.01, + "learning_rate": 3.31010218408072e-05, + "loss": 3.562, + "step": 1032192 + }, + { + "epoch": 1.01, + "learning_rate": 3.309263589329668e-05, + "loss": 3.5644, + "step": 1032704 + }, + { + "epoch": 1.01, + "learning_rate": 3.308426632458989e-05, + "loss": 3.5667, + "step": 1033216 + }, + { + "epoch": 1.01, + "learning_rate": 3.3075880377079374e-05, + "loss": 3.5693, + "step": 1033728 + }, + { + "epoch": 1.01, + "learning_rate": 3.3067494429568854e-05, + "loss": 3.5756, + "step": 1034240 + }, + { + "epoch": 1.01, + "learning_rate": 3.3059108482058334e-05, + "loss": 3.5702, + "step": 1034752 + }, + { + "epoch": 1.01, + "learning_rate": 3.3050722534547814e-05, + "loss": 3.5485, + "step": 1035264 + }, + { + "epoch": 1.01, + "learning_rate": 3.3042336587037294e-05, + "loss": 3.5553, + "step": 1035776 + }, + { + "epoch": 1.01, + "learning_rate": 3.30339670183305e-05, + "loss": 3.5691, + "step": 1036288 + }, + { + "epoch": 1.01, + "learning_rate": 3.302558107081998e-05, + "loss": 3.5675, + "step": 1036800 + }, + { + "epoch": 1.01, + "learning_rate": 3.301719512330946e-05, + "loss": 3.5616, + "step": 1037312 + }, + { + "epoch": 1.01, + "learning_rate": 3.300880917579894e-05, + "loss": 3.5617, + "step": 1037824 + }, + { + "epoch": 1.02, + "learning_rate": 3.300043960709215e-05, + "loss": 3.5703, + "step": 1038336 + }, + { + "epoch": 1.02, + "learning_rate": 3.299205365958163e-05, + "loss": 3.5528, + "step": 1038848 + }, + { + "epoch": 1.02, + "learning_rate": 3.298366771207111e-05, + "loss": 3.5554, + "step": 1039360 + }, + { + "epoch": 1.02, + "learning_rate": 3.297528176456059e-05, + "loss": 3.5657, + "step": 1039872 + }, + { + "epoch": 1.02, + "learning_rate": 3.296691219585381e-05, + "loss": 3.5614, + "step": 1040384 + }, + { + "epoch": 1.02, + "learning_rate": 3.295852624834329e-05, + "loss": 3.5771, + "step": 1040896 + }, + { + "epoch": 1.02, + "learning_rate": 3.295014030083277e-05, + "loss": 3.5516, + "step": 1041408 + }, + { + "epoch": 1.02, + "learning_rate": 3.294175435332225e-05, + "loss": 3.5528, + "step": 1041920 + }, + { + "epoch": 1.02, + "learning_rate": 3.293336840581173e-05, + "loss": 3.5647, + "step": 1042432 + }, + { + "epoch": 1.02, + "learning_rate": 3.292499883710494e-05, + "loss": 3.5679, + "step": 1042944 + }, + { + "epoch": 1.02, + "learning_rate": 3.291661288959442e-05, + "loss": 3.5665, + "step": 1043456 + }, + { + "epoch": 1.02, + "learning_rate": 3.29082269420839e-05, + "loss": 3.556, + "step": 1043968 + }, + { + "epoch": 1.02, + "learning_rate": 3.289984099457338e-05, + "loss": 3.5546, + "step": 1044480 + }, + { + "epoch": 1.02, + "learning_rate": 3.2891471425866586e-05, + "loss": 3.5478, + "step": 1044992 + }, + { + "epoch": 1.02, + "learning_rate": 3.2883085478356066e-05, + "loss": 3.5654, + "step": 1045504 + }, + { + "epoch": 1.02, + "learning_rate": 3.2874699530845546e-05, + "loss": 3.5517, + "step": 1046016 + }, + { + "epoch": 1.02, + "learning_rate": 3.2866313583335026e-05, + "loss": 3.5524, + "step": 1046528 + }, + { + "epoch": 1.02, + "learning_rate": 3.285792763582451e-05, + "loss": 3.5652, + "step": 1047040 + }, + { + "epoch": 1.02, + "learning_rate": 3.284955806711772e-05, + "loss": 3.5574, + "step": 1047552 + }, + { + "epoch": 1.02, + "learning_rate": 3.28411721196072e-05, + "loss": 3.5516, + "step": 1048064 + }, + { + "epoch": 1.02, + "learning_rate": 3.283278617209668e-05, + "loss": 3.5628, + "step": 1048576 + }, + { + "epoch": 1.02, + "learning_rate": 3.282440022458616e-05, + "loss": 3.5477, + "step": 1049088 + }, + { + "epoch": 1.02, + "learning_rate": 3.281603065587937e-05, + "loss": 3.5642, + "step": 1049600 + }, + { + "epoch": 1.02, + "learning_rate": 3.280764470836885e-05, + "loss": 3.5525, + "step": 1050112 + }, + { + "epoch": 1.02, + "learning_rate": 3.279925876085833e-05, + "loss": 3.5592, + "step": 1050624 + }, + { + "epoch": 1.02, + "learning_rate": 3.279087281334781e-05, + "loss": 3.5658, + "step": 1051136 + }, + { + "epoch": 1.02, + "learning_rate": 3.278250324464102e-05, + "loss": 3.5627, + "step": 1051648 + }, + { + "epoch": 1.02, + "learning_rate": 3.27741172971305e-05, + "loss": 3.5556, + "step": 1052160 + }, + { + "epoch": 1.02, + "learning_rate": 3.276573134961998e-05, + "loss": 3.562, + "step": 1052672 + }, + { + "epoch": 1.02, + "learning_rate": 3.275734540210946e-05, + "loss": 3.5699, + "step": 1053184 + }, + { + "epoch": 1.02, + "learning_rate": 3.2748959454598946e-05, + "loss": 3.5576, + "step": 1053696 + }, + { + "epoch": 1.02, + "learning_rate": 3.2740589885892155e-05, + "loss": 3.5564, + "step": 1054208 + }, + { + "epoch": 1.02, + "learning_rate": 3.2732203938381635e-05, + "loss": 3.5578, + "step": 1054720 + }, + { + "epoch": 1.02, + "learning_rate": 3.2723817990871115e-05, + "loss": 3.5628, + "step": 1055232 + }, + { + "epoch": 1.02, + "learning_rate": 3.271543204336059e-05, + "loss": 3.5642, + "step": 1055744 + }, + { + "epoch": 1.02, + "learning_rate": 3.2707062474653804e-05, + "loss": 3.5508, + "step": 1056256 + }, + { + "epoch": 1.02, + "learning_rate": 3.2698676527143284e-05, + "loss": 3.5546, + "step": 1056768 + }, + { + "epoch": 1.02, + "learning_rate": 3.2690290579632764e-05, + "loss": 3.5542, + "step": 1057280 + }, + { + "epoch": 1.02, + "learning_rate": 3.268190463212224e-05, + "loss": 3.5527, + "step": 1057792 + }, + { + "epoch": 1.02, + "learning_rate": 3.267351868461172e-05, + "loss": 3.5626, + "step": 1058304 + }, + { + "epoch": 1.02, + "learning_rate": 3.266514911590493e-05, + "loss": 3.5624, + "step": 1058816 + }, + { + "epoch": 1.02, + "learning_rate": 3.265676316839441e-05, + "loss": 3.5661, + "step": 1059328 + }, + { + "epoch": 1.02, + "learning_rate": 3.264837722088389e-05, + "loss": 3.5526, + "step": 1059840 + }, + { + "epoch": 1.02, + "learning_rate": 3.263999127337337e-05, + "loss": 3.5642, + "step": 1060352 + }, + { + "epoch": 1.02, + "learning_rate": 3.263160532586285e-05, + "loss": 3.5603, + "step": 1060864 + }, + { + "epoch": 1.02, + "learning_rate": 3.262323575715606e-05, + "loss": 3.5693, + "step": 1061376 + }, + { + "epoch": 1.02, + "learning_rate": 3.261484980964554e-05, + "loss": 3.5568, + "step": 1061888 + }, + { + "epoch": 1.02, + "learning_rate": 3.260646386213502e-05, + "loss": 3.5599, + "step": 1062400 + }, + { + "epoch": 1.02, + "learning_rate": 3.25980779146245e-05, + "loss": 3.5601, + "step": 1062912 + }, + { + "epoch": 1.02, + "learning_rate": 3.258970834591771e-05, + "loss": 3.5697, + "step": 1063424 + }, + { + "epoch": 1.02, + "learning_rate": 3.258132239840719e-05, + "loss": 3.5557, + "step": 1063936 + }, + { + "epoch": 1.02, + "learning_rate": 3.257293645089667e-05, + "loss": 3.5543, + "step": 1064448 + }, + { + "epoch": 1.02, + "learning_rate": 3.256455050338615e-05, + "loss": 3.5643, + "step": 1064960 + }, + { + "epoch": 1.02, + "learning_rate": 3.255616455587564e-05, + "loss": 3.5547, + "step": 1065472 + }, + { + "epoch": 1.02, + "learning_rate": 3.254779498716885e-05, + "loss": 3.5549, + "step": 1065984 + }, + { + "epoch": 1.02, + "learning_rate": 3.253940903965833e-05, + "loss": 3.5682, + "step": 1066496 + }, + { + "epoch": 1.02, + "learning_rate": 3.253102309214781e-05, + "loss": 3.5465, + "step": 1067008 + }, + { + "epoch": 1.02, + "learning_rate": 3.2522637144637287e-05, + "loss": 3.5616, + "step": 1067520 + }, + { + "epoch": 1.02, + "learning_rate": 3.2514267575930496e-05, + "loss": 3.5489, + "step": 1068032 + }, + { + "epoch": 1.03, + "eval_loss": 3.844719171524048, + "eval_runtime": 305.1795, + "eval_samples_per_second": 1250.382, + "eval_steps_per_second": 39.075, + "step": 1068480 + }, + { + "epoch": 0.0, + "learning_rate": 3.2505881628419976e-05, + "loss": 3.5527, + "step": 1068544 + }, + { + "epoch": 0.0, + "learning_rate": 3.2497495680909456e-05, + "loss": 3.5462, + "step": 1069056 + }, + { + "epoch": 0.0, + "learning_rate": 3.2489109733398936e-05, + "loss": 3.5587, + "step": 1069568 + }, + { + "epoch": 0.0, + "learning_rate": 3.2480723785888416e-05, + "loss": 3.5696, + "step": 1070080 + }, + { + "epoch": 0.0, + "learning_rate": 3.2472337838377895e-05, + "loss": 3.5658, + "step": 1070592 + }, + { + "epoch": 0.0, + "learning_rate": 3.2463968269671105e-05, + "loss": 3.5613, + "step": 1071104 + }, + { + "epoch": 0.0, + "learning_rate": 3.245558232216059e-05, + "loss": 3.5447, + "step": 1071616 + }, + { + "epoch": 0.0, + "learning_rate": 3.244719637465007e-05, + "loss": 3.5612, + "step": 1072128 + }, + { + "epoch": 0.0, + "learning_rate": 3.243881042713955e-05, + "loss": 3.5539, + "step": 1072640 + }, + { + "epoch": 0.0, + "learning_rate": 3.243044085843276e-05, + "loss": 3.5574, + "step": 1073152 + }, + { + "epoch": 0.0, + "learning_rate": 3.242205491092224e-05, + "loss": 3.5568, + "step": 1073664 + }, + { + "epoch": 0.0, + "learning_rate": 3.241366896341172e-05, + "loss": 3.5578, + "step": 1074176 + }, + { + "epoch": 0.0, + "learning_rate": 3.24052830159012e-05, + "loss": 3.5653, + "step": 1074688 + }, + { + "epoch": 0.0, + "learning_rate": 3.239691344719441e-05, + "loss": 3.5457, + "step": 1075200 + }, + { + "epoch": 0.0, + "learning_rate": 3.238852749968389e-05, + "loss": 3.5372, + "step": 1075712 + }, + { + "epoch": 0.0, + "learning_rate": 3.238014155217337e-05, + "loss": 3.5471, + "step": 1076224 + }, + { + "epoch": 0.0, + "learning_rate": 3.237175560466285e-05, + "loss": 3.5639, + "step": 1076736 + }, + { + "epoch": 0.0, + "learning_rate": 3.236338603595606e-05, + "loss": 3.5563, + "step": 1077248 + }, + { + "epoch": 0.0, + "learning_rate": 3.2355000088445545e-05, + "loss": 3.5532, + "step": 1077760 + }, + { + "epoch": 0.0, + "learning_rate": 3.2346614140935025e-05, + "loss": 3.558, + "step": 1078272 + }, + { + "epoch": 0.0, + "learning_rate": 3.2338228193424505e-05, + "loss": 3.5699, + "step": 1078784 + }, + { + "epoch": 0.0, + "learning_rate": 3.2329858624717714e-05, + "loss": 3.5503, + "step": 1079296 + }, + { + "epoch": 0.0, + "learning_rate": 3.2321472677207194e-05, + "loss": 3.5518, + "step": 1079808 + }, + { + "epoch": 0.0, + "learning_rate": 3.2313086729696674e-05, + "loss": 3.5571, + "step": 1080320 + }, + { + "epoch": 0.0, + "learning_rate": 3.2304700782186154e-05, + "loss": 3.5654, + "step": 1080832 + }, + { + "epoch": 0.0, + "learning_rate": 3.229633121347936e-05, + "loss": 3.5476, + "step": 1081344 + }, + { + "epoch": 0.0, + "learning_rate": 3.228794526596884e-05, + "loss": 3.5501, + "step": 1081856 + }, + { + "epoch": 0.0, + "learning_rate": 3.227955931845832e-05, + "loss": 3.5674, + "step": 1082368 + }, + { + "epoch": 0.0, + "learning_rate": 3.22711733709478e-05, + "loss": 3.5442, + "step": 1082880 + }, + { + "epoch": 0.0, + "learning_rate": 3.226278742343728e-05, + "loss": 3.5422, + "step": 1083392 + }, + { + "epoch": 0.01, + "learning_rate": 3.22544178547305e-05, + "loss": 3.5411, + "step": 1083904 + }, + { + "epoch": 0.01, + "learning_rate": 3.224603190721998e-05, + "loss": 3.5516, + "step": 1084416 + }, + { + "epoch": 0.01, + "learning_rate": 3.223764595970946e-05, + "loss": 3.5566, + "step": 1084928 + }, + { + "epoch": 0.01, + "learning_rate": 3.222926001219894e-05, + "loss": 3.5613, + "step": 1085440 + }, + { + "epoch": 0.01, + "learning_rate": 3.222089044349215e-05, + "loss": 3.5522, + "step": 1085952 + }, + { + "epoch": 0.01, + "learning_rate": 3.221250449598163e-05, + "loss": 3.5498, + "step": 1086464 + }, + { + "epoch": 0.01, + "learning_rate": 3.220411854847111e-05, + "loss": 3.5602, + "step": 1086976 + }, + { + "epoch": 0.01, + "learning_rate": 3.219573260096059e-05, + "loss": 3.5364, + "step": 1087488 + }, + { + "epoch": 0.01, + "learning_rate": 3.2187363032253797e-05, + "loss": 3.5477, + "step": 1088000 + }, + { + "epoch": 0.01, + "learning_rate": 3.2178977084743277e-05, + "loss": 3.5459, + "step": 1088512 + }, + { + "epoch": 0.01, + "learning_rate": 3.2170591137232756e-05, + "loss": 3.5487, + "step": 1089024 + }, + { + "epoch": 0.01, + "learning_rate": 3.2162205189722236e-05, + "loss": 3.5405, + "step": 1089536 + }, + { + "epoch": 0.01, + "learning_rate": 3.2153819242211716e-05, + "loss": 3.5626, + "step": 1090048 + }, + { + "epoch": 0.01, + "learning_rate": 3.214544967350493e-05, + "loss": 3.5456, + "step": 1090560 + }, + { + "epoch": 0.01, + "learning_rate": 3.213706372599441e-05, + "loss": 3.5521, + "step": 1091072 + }, + { + "epoch": 0.01, + "learning_rate": 3.212867777848389e-05, + "loss": 3.5538, + "step": 1091584 + }, + { + "epoch": 0.01, + "learning_rate": 3.212029183097337e-05, + "loss": 3.5476, + "step": 1092096 + }, + { + "epoch": 0.01, + "learning_rate": 3.211192226226658e-05, + "loss": 3.5501, + "step": 1092608 + }, + { + "epoch": 0.01, + "learning_rate": 3.210353631475606e-05, + "loss": 3.5293, + "step": 1093120 + }, + { + "epoch": 0.01, + "learning_rate": 3.209515036724554e-05, + "loss": 3.5458, + "step": 1093632 + }, + { + "epoch": 0.01, + "learning_rate": 3.208676441973502e-05, + "loss": 3.5579, + "step": 1094144 + }, + { + "epoch": 0.01, + "learning_rate": 3.207839485102823e-05, + "loss": 3.5496, + "step": 1094656 + }, + { + "epoch": 0.01, + "learning_rate": 3.207000890351771e-05, + "loss": 3.5429, + "step": 1095168 + }, + { + "epoch": 0.01, + "learning_rate": 3.206162295600719e-05, + "loss": 3.538, + "step": 1095680 + }, + { + "epoch": 0.01, + "learning_rate": 3.205323700849667e-05, + "loss": 3.5459, + "step": 1096192 + }, + { + "epoch": 0.01, + "learning_rate": 3.2044867439789886e-05, + "loss": 3.5323, + "step": 1096704 + }, + { + "epoch": 0.01, + "learning_rate": 3.2036481492279366e-05, + "loss": 3.5666, + "step": 1097216 + }, + { + "epoch": 0.01, + "learning_rate": 3.2028095544768846e-05, + "loss": 3.5421, + "step": 1097728 + }, + { + "epoch": 0.01, + "learning_rate": 3.201970959725832e-05, + "loss": 3.5503, + "step": 1098240 + }, + { + "epoch": 0.01, + "learning_rate": 3.2011340028551535e-05, + "loss": 3.5551, + "step": 1098752 + }, + { + "epoch": 0.01, + "learning_rate": 3.2002954081041015e-05, + "loss": 3.5347, + "step": 1099264 + }, + { + "epoch": 0.01, + "learning_rate": 3.1994568133530495e-05, + "loss": 3.5425, + "step": 1099776 + }, + { + "epoch": 0.01, + "learning_rate": 3.198618218601997e-05, + "loss": 3.5395, + "step": 1100288 + }, + { + "epoch": 0.01, + "learning_rate": 3.197779623850945e-05, + "loss": 3.5356, + "step": 1100800 + }, + { + "epoch": 0.01, + "learning_rate": 3.1969426669802664e-05, + "loss": 3.534, + "step": 1101312 + }, + { + "epoch": 0.01, + "learning_rate": 3.1961040722292144e-05, + "loss": 3.5584, + "step": 1101824 + }, + { + "epoch": 0.01, + "learning_rate": 3.1952654774781624e-05, + "loss": 3.5485, + "step": 1102336 + }, + { + "epoch": 0.01, + "learning_rate": 3.1944268827271104e-05, + "loss": 3.5419, + "step": 1102848 + }, + { + "epoch": 0.01, + "learning_rate": 3.193589925856432e-05, + "loss": 3.5344, + "step": 1103360 + }, + { + "epoch": 0.01, + "learning_rate": 3.192751331105379e-05, + "loss": 3.5437, + "step": 1103872 + }, + { + "epoch": 0.01, + "learning_rate": 3.191912736354327e-05, + "loss": 3.5484, + "step": 1104384 + }, + { + "epoch": 0.01, + "learning_rate": 3.191074141603275e-05, + "loss": 3.5496, + "step": 1104896 + }, + { + "epoch": 0.01, + "learning_rate": 3.190237184732596e-05, + "loss": 3.5444, + "step": 1105408 + }, + { + "epoch": 0.01, + "learning_rate": 3.189398589981544e-05, + "loss": 3.5497, + "step": 1105920 + }, + { + "epoch": 0.01, + "learning_rate": 3.188559995230492e-05, + "loss": 3.557, + "step": 1106432 + }, + { + "epoch": 0.01, + "learning_rate": 3.18772140047944e-05, + "loss": 3.5461, + "step": 1106944 + }, + { + "epoch": 0.01, + "learning_rate": 3.186884443608761e-05, + "loss": 3.5405, + "step": 1107456 + }, + { + "epoch": 0.01, + "learning_rate": 3.186045848857709e-05, + "loss": 3.5506, + "step": 1107968 + }, + { + "epoch": 0.01, + "learning_rate": 3.185207254106658e-05, + "loss": 3.5478, + "step": 1108480 + }, + { + "epoch": 0.01, + "learning_rate": 3.184368659355606e-05, + "loss": 3.547, + "step": 1108992 + }, + { + "epoch": 0.01, + "learning_rate": 3.1835317024849266e-05, + "loss": 3.5519, + "step": 1109504 + }, + { + "epoch": 0.01, + "learning_rate": 3.1826931077338746e-05, + "loss": 3.5526, + "step": 1110016 + }, + { + "epoch": 0.01, + "learning_rate": 3.1818545129828226e-05, + "loss": 3.5616, + "step": 1110528 + }, + { + "epoch": 0.01, + "learning_rate": 3.1810159182317706e-05, + "loss": 3.5513, + "step": 1111040 + }, + { + "epoch": 0.01, + "learning_rate": 3.1801773234807186e-05, + "loss": 3.534, + "step": 1111552 + }, + { + "epoch": 0.01, + "learning_rate": 3.1793387287296666e-05, + "loss": 3.5396, + "step": 1112064 + }, + { + "epoch": 0.01, + "learning_rate": 3.1785017718589875e-05, + "loss": 3.5555, + "step": 1112576 + }, + { + "epoch": 0.01, + "learning_rate": 3.1776631771079355e-05, + "loss": 3.5493, + "step": 1113088 + }, + { + "epoch": 0.01, + "learning_rate": 3.1768245823568835e-05, + "loss": 3.5438, + "step": 1113600 + }, + { + "epoch": 0.01, + "learning_rate": 3.1759859876058315e-05, + "loss": 3.547, + "step": 1114112 + }, + { + "epoch": 0.02, + "learning_rate": 3.175149030735153e-05, + "loss": 3.5521, + "step": 1114624 + }, + { + "epoch": 0.02, + "learning_rate": 3.174310435984101e-05, + "loss": 3.5386, + "step": 1115136 + }, + { + "epoch": 0.02, + "learning_rate": 3.173471841233049e-05, + "loss": 3.5461, + "step": 1115648 + }, + { + "epoch": 0.02, + "learning_rate": 3.172633246481997e-05, + "loss": 3.5424, + "step": 1116160 + }, + { + "epoch": 0.02, + "learning_rate": 3.171796289611318e-05, + "loss": 3.5477, + "step": 1116672 + }, + { + "epoch": 0.02, + "learning_rate": 3.170957694860266e-05, + "loss": 3.5552, + "step": 1117184 + }, + { + "epoch": 0.02, + "learning_rate": 3.170119100109214e-05, + "loss": 3.5465, + "step": 1117696 + }, + { + "epoch": 0.02, + "learning_rate": 3.169280505358162e-05, + "loss": 3.5314, + "step": 1118208 + }, + { + "epoch": 0.02, + "learning_rate": 3.16844191060711e-05, + "loss": 3.5479, + "step": 1118720 + }, + { + "epoch": 0.02, + "learning_rate": 3.167604953736431e-05, + "loss": 3.5492, + "step": 1119232 + }, + { + "epoch": 0.02, + "learning_rate": 3.166766358985379e-05, + "loss": 3.5512, + "step": 1119744 + }, + { + "epoch": 0.02, + "learning_rate": 3.165927764234327e-05, + "loss": 3.5438, + "step": 1120256 + }, + { + "epoch": 0.02, + "learning_rate": 3.165089169483275e-05, + "loss": 3.537, + "step": 1120768 + }, + { + "epoch": 0.02, + "learning_rate": 3.1642522126125965e-05, + "loss": 3.5326, + "step": 1121280 + }, + { + "epoch": 0.02, + "learning_rate": 3.1634136178615445e-05, + "loss": 3.547, + "step": 1121792 + }, + { + "epoch": 0.02, + "learning_rate": 3.1625750231104925e-05, + "loss": 3.5388, + "step": 1122304 + }, + { + "epoch": 0.02, + "learning_rate": 3.1617364283594405e-05, + "loss": 3.5366, + "step": 1122816 + }, + { + "epoch": 0.02, + "learning_rate": 3.1608978336083884e-05, + "loss": 3.5499, + "step": 1123328 + }, + { + "epoch": 0.02, + "learning_rate": 3.1600608767377094e-05, + "loss": 3.5453, + "step": 1123840 + }, + { + "epoch": 0.02, + "learning_rate": 3.1592222819866574e-05, + "loss": 3.5366, + "step": 1124352 + }, + { + "epoch": 0.02, + "learning_rate": 3.1583836872356054e-05, + "loss": 3.5452, + "step": 1124864 + }, + { + "epoch": 0.02, + "learning_rate": 3.1575450924845533e-05, + "loss": 3.5339, + "step": 1125376 + }, + { + "epoch": 0.02, + "learning_rate": 3.156708135613874e-05, + "loss": 3.5479, + "step": 1125888 + }, + { + "epoch": 0.02, + "learning_rate": 3.155869540862822e-05, + "loss": 3.5384, + "step": 1126400 + }, + { + "epoch": 0.02, + "learning_rate": 3.15503094611177e-05, + "loss": 3.5435, + "step": 1126912 + }, + { + "epoch": 0.02, + "learning_rate": 3.154192351360718e-05, + "loss": 3.5489, + "step": 1127424 + }, + { + "epoch": 0.02, + "learning_rate": 3.15335539449004e-05, + "loss": 3.5502, + "step": 1127936 + }, + { + "epoch": 0.02, + "learning_rate": 3.152516799738988e-05, + "loss": 3.5414, + "step": 1128448 + }, + { + "epoch": 0.02, + "learning_rate": 3.151678204987936e-05, + "loss": 3.5465, + "step": 1128960 + }, + { + "epoch": 0.02, + "learning_rate": 3.150839610236884e-05, + "loss": 3.5514, + "step": 1129472 + }, + { + "epoch": 0.02, + "learning_rate": 3.150002653366205e-05, + "loss": 3.5431, + "step": 1129984 + }, + { + "epoch": 0.02, + "learning_rate": 3.149164058615153e-05, + "loss": 3.5383, + "step": 1130496 + }, + { + "epoch": 0.02, + "learning_rate": 3.148325463864101e-05, + "loss": 3.5457, + "step": 1131008 + }, + { + "epoch": 0.02, + "learning_rate": 3.147486869113049e-05, + "loss": 3.5432, + "step": 1131520 + }, + { + "epoch": 0.02, + "learning_rate": 3.1466499122423696e-05, + "loss": 3.5504, + "step": 1132032 + }, + { + "epoch": 0.02, + "learning_rate": 3.1458113174913176e-05, + "loss": 3.5349, + "step": 1132544 + }, + { + "epoch": 0.02, + "learning_rate": 3.1449727227402656e-05, + "loss": 3.538, + "step": 1133056 + }, + { + "epoch": 0.02, + "learning_rate": 3.1441341279892136e-05, + "loss": 3.5395, + "step": 1133568 + }, + { + "epoch": 0.02, + "learning_rate": 3.143295533238162e-05, + "loss": 3.5427, + "step": 1134080 + }, + { + "epoch": 0.02, + "learning_rate": 3.14245693848711e-05, + "loss": 3.5398, + "step": 1134592 + }, + { + "epoch": 0.02, + "learning_rate": 3.141619981616431e-05, + "loss": 3.5498, + "step": 1135104 + }, + { + "epoch": 0.02, + "learning_rate": 3.140781386865379e-05, + "loss": 3.5508, + "step": 1135616 + }, + { + "epoch": 0.02, + "learning_rate": 3.139942792114327e-05, + "loss": 3.538, + "step": 1136128 + }, + { + "epoch": 0.02, + "learning_rate": 3.1391041973632745e-05, + "loss": 3.5462, + "step": 1136640 + }, + { + "epoch": 0.02, + "learning_rate": 3.138267240492596e-05, + "loss": 3.5471, + "step": 1137152 + }, + { + "epoch": 0.02, + "learning_rate": 3.137428645741544e-05, + "loss": 3.5535, + "step": 1137664 + }, + { + "epoch": 0.02, + "learning_rate": 3.136590050990492e-05, + "loss": 3.5399, + "step": 1138176 + }, + { + "epoch": 0.02, + "learning_rate": 3.1357514562394394e-05, + "loss": 3.544, + "step": 1138688 + }, + { + "epoch": 0.02, + "learning_rate": 3.1349128614883874e-05, + "loss": 3.5469, + "step": 1139200 + }, + { + "epoch": 0.02, + "learning_rate": 3.134075904617709e-05, + "loss": 3.5499, + "step": 1139712 + }, + { + "epoch": 0.02, + "learning_rate": 3.133237309866657e-05, + "loss": 3.5394, + "step": 1140224 + }, + { + "epoch": 0.02, + "learning_rate": 3.132398715115605e-05, + "loss": 3.5411, + "step": 1140736 + }, + { + "epoch": 0.02, + "learning_rate": 3.131560120364553e-05, + "loss": 3.5486, + "step": 1141248 + }, + { + "epoch": 0.02, + "learning_rate": 3.1307231634938745e-05, + "loss": 3.5389, + "step": 1141760 + }, + { + "epoch": 0.02, + "learning_rate": 3.129884568742822e-05, + "loss": 3.5375, + "step": 1142272 + }, + { + "epoch": 0.02, + "learning_rate": 3.1290476118721435e-05, + "loss": 3.5548, + "step": 1142784 + }, + { + "epoch": 0.02, + "learning_rate": 3.1282090171210915e-05, + "loss": 3.5349, + "step": 1143296 + }, + { + "epoch": 0.02, + "learning_rate": 3.1273704223700394e-05, + "loss": 3.5451, + "step": 1143808 + }, + { + "epoch": 0.02, + "learning_rate": 3.126531827618987e-05, + "loss": 3.5349, + "step": 1144320 + }, + { + "epoch": 0.03, + "eval_loss": 3.846574068069458, + "eval_runtime": 304.0843, + "eval_samples_per_second": 1254.885, + "eval_steps_per_second": 39.216, + "step": 1144800 + }, + { + "epoch": 1.0, + "learning_rate": 3.125693232867935e-05, + "loss": 3.5379, + "step": 1144832 + }, + { + "epoch": 1.0, + "learning_rate": 3.124854638116883e-05, + "loss": 3.5343, + "step": 1145344 + }, + { + "epoch": 1.0, + "learning_rate": 3.1240160433658314e-05, + "loss": 3.5417, + "step": 1145856 + }, + { + "epoch": 1.0, + "learning_rate": 3.1231774486147794e-05, + "loss": 3.5521, + "step": 1146368 + }, + { + "epoch": 1.0, + "learning_rate": 3.1223388538637274e-05, + "loss": 3.5467, + "step": 1146880 + }, + { + "epoch": 1.0, + "learning_rate": 3.121501896993048e-05, + "loss": 3.5494, + "step": 1147392 + }, + { + "epoch": 1.0, + "learning_rate": 3.120663302241996e-05, + "loss": 3.5346, + "step": 1147904 + }, + { + "epoch": 1.0, + "learning_rate": 3.119824707490944e-05, + "loss": 3.5423, + "step": 1148416 + }, + { + "epoch": 1.0, + "learning_rate": 3.118986112739892e-05, + "loss": 3.5359, + "step": 1148928 + }, + { + "epoch": 1.0, + "learning_rate": 3.118149155869213e-05, + "loss": 3.543, + "step": 1149440 + }, + { + "epoch": 1.0, + "learning_rate": 3.117310561118161e-05, + "loss": 3.541, + "step": 1149952 + }, + { + "epoch": 1.0, + "learning_rate": 3.116471966367109e-05, + "loss": 3.5452, + "step": 1150464 + }, + { + "epoch": 1.0, + "learning_rate": 3.115633371616057e-05, + "loss": 3.5545, + "step": 1150976 + }, + { + "epoch": 1.0, + "learning_rate": 3.114796414745378e-05, + "loss": 3.5315, + "step": 1151488 + }, + { + "epoch": 1.0, + "learning_rate": 3.113957819994326e-05, + "loss": 3.5233, + "step": 1152000 + }, + { + "epoch": 1.0, + "learning_rate": 3.113119225243275e-05, + "loss": 3.5281, + "step": 1152512 + }, + { + "epoch": 1.0, + "learning_rate": 3.112280630492223e-05, + "loss": 3.5435, + "step": 1153024 + }, + { + "epoch": 1.0, + "learning_rate": 3.111443673621544e-05, + "loss": 3.543, + "step": 1153536 + }, + { + "epoch": 1.0, + "learning_rate": 3.110605078870492e-05, + "loss": 3.5405, + "step": 1154048 + }, + { + "epoch": 1.0, + "learning_rate": 3.10976648411944e-05, + "loss": 3.5402, + "step": 1154560 + }, + { + "epoch": 1.0, + "learning_rate": 3.108927889368388e-05, + "loss": 3.5618, + "step": 1155072 + }, + { + "epoch": 1.0, + "learning_rate": 3.1080909324977086e-05, + "loss": 3.5345, + "step": 1155584 + }, + { + "epoch": 1.0, + "learning_rate": 3.1072523377466566e-05, + "loss": 3.5342, + "step": 1156096 + }, + { + "epoch": 1.0, + "learning_rate": 3.1064137429956046e-05, + "loss": 3.5415, + "step": 1156608 + }, + { + "epoch": 1.0, + "learning_rate": 3.1055751482445526e-05, + "loss": 3.5509, + "step": 1157120 + }, + { + "epoch": 1.0, + "learning_rate": 3.1047381913738735e-05, + "loss": 3.5288, + "step": 1157632 + }, + { + "epoch": 1.0, + "learning_rate": 3.1038995966228215e-05, + "loss": 3.5373, + "step": 1158144 + }, + { + "epoch": 1.0, + "learning_rate": 3.10306100187177e-05, + "loss": 3.5477, + "step": 1158656 + }, + { + "epoch": 1.0, + "learning_rate": 3.102222407120718e-05, + "loss": 3.5356, + "step": 1159168 + }, + { + "epoch": 1.0, + "learning_rate": 3.101383812369666e-05, + "loss": 3.5277, + "step": 1159680 + }, + { + "epoch": 1.01, + "learning_rate": 3.100546855498987e-05, + "loss": 3.5261, + "step": 1160192 + }, + { + "epoch": 1.01, + "learning_rate": 3.099708260747935e-05, + "loss": 3.5376, + "step": 1160704 + }, + { + "epoch": 1.01, + "learning_rate": 3.098869665996883e-05, + "loss": 3.546, + "step": 1161216 + }, + { + "epoch": 1.01, + "learning_rate": 3.098031071245831e-05, + "loss": 3.5424, + "step": 1161728 + }, + { + "epoch": 1.01, + "learning_rate": 3.097194114375152e-05, + "loss": 3.5383, + "step": 1162240 + }, + { + "epoch": 1.01, + "learning_rate": 3.0963555196241e-05, + "loss": 3.5327, + "step": 1162752 + }, + { + "epoch": 1.01, + "learning_rate": 3.095516924873048e-05, + "loss": 3.5447, + "step": 1163264 + }, + { + "epoch": 1.01, + "learning_rate": 3.094678330121996e-05, + "loss": 3.5252, + "step": 1163776 + }, + { + "epoch": 1.01, + "learning_rate": 3.093841373251317e-05, + "loss": 3.5337, + "step": 1164288 + }, + { + "epoch": 1.01, + "learning_rate": 3.0930027785002655e-05, + "loss": 3.5309, + "step": 1164800 + }, + { + "epoch": 1.01, + "learning_rate": 3.0921641837492135e-05, + "loss": 3.5335, + "step": 1165312 + }, + { + "epoch": 1.01, + "learning_rate": 3.0913255889981615e-05, + "loss": 3.5259, + "step": 1165824 + }, + { + "epoch": 1.01, + "learning_rate": 3.0904869942471095e-05, + "loss": 3.5481, + "step": 1166336 + }, + { + "epoch": 1.01, + "learning_rate": 3.0896500373764304e-05, + "loss": 3.5327, + "step": 1166848 + }, + { + "epoch": 1.01, + "learning_rate": 3.0888114426253784e-05, + "loss": 3.536, + "step": 1167360 + }, + { + "epoch": 1.01, + "learning_rate": 3.0879728478743264e-05, + "loss": 3.5413, + "step": 1167872 + }, + { + "epoch": 1.01, + "learning_rate": 3.0871342531232744e-05, + "loss": 3.5321, + "step": 1168384 + }, + { + "epoch": 1.01, + "learning_rate": 3.086297296252595e-05, + "loss": 3.5336, + "step": 1168896 + }, + { + "epoch": 1.01, + "learning_rate": 3.085458701501543e-05, + "loss": 3.5151, + "step": 1169408 + }, + { + "epoch": 1.01, + "learning_rate": 3.084620106750491e-05, + "loss": 3.5281, + "step": 1169920 + }, + { + "epoch": 1.01, + "learning_rate": 3.083781511999439e-05, + "loss": 3.5435, + "step": 1170432 + }, + { + "epoch": 1.01, + "learning_rate": 3.082944555128761e-05, + "loss": 3.5354, + "step": 1170944 + }, + { + "epoch": 1.01, + "learning_rate": 3.082105960377709e-05, + "loss": 3.5262, + "step": 1171456 + }, + { + "epoch": 1.01, + "learning_rate": 3.081267365626657e-05, + "loss": 3.5216, + "step": 1171968 + }, + { + "epoch": 1.01, + "learning_rate": 3.080428770875605e-05, + "loss": 3.5313, + "step": 1172480 + }, + { + "epoch": 1.01, + "learning_rate": 3.079591814004926e-05, + "loss": 3.5226, + "step": 1172992 + }, + { + "epoch": 1.01, + "learning_rate": 3.078753219253874e-05, + "loss": 3.5462, + "step": 1173504 + }, + { + "epoch": 1.01, + "learning_rate": 3.077914624502822e-05, + "loss": 3.5275, + "step": 1174016 + }, + { + "epoch": 1.01, + "learning_rate": 3.07707602975177e-05, + "loss": 3.5339, + "step": 1174528 + }, + { + "epoch": 1.01, + "learning_rate": 3.076237435000718e-05, + "loss": 3.5439, + "step": 1175040 + }, + { + "epoch": 1.01, + "learning_rate": 3.075400478130039e-05, + "loss": 3.5172, + "step": 1175552 + }, + { + "epoch": 1.01, + "learning_rate": 3.074561883378987e-05, + "loss": 3.5272, + "step": 1176064 + }, + { + "epoch": 1.01, + "learning_rate": 3.073723288627935e-05, + "loss": 3.5275, + "step": 1176576 + }, + { + "epoch": 1.01, + "learning_rate": 3.072884693876883e-05, + "loss": 3.5209, + "step": 1177088 + }, + { + "epoch": 1.01, + "learning_rate": 3.072047737006204e-05, + "loss": 3.5236, + "step": 1177600 + }, + { + "epoch": 1.01, + "learning_rate": 3.071209142255152e-05, + "loss": 3.5376, + "step": 1178112 + }, + { + "epoch": 1.01, + "learning_rate": 3.0703705475041e-05, + "loss": 3.5378, + "step": 1178624 + }, + { + "epoch": 1.01, + "learning_rate": 3.0695319527530476e-05, + "loss": 3.5256, + "step": 1179136 + }, + { + "epoch": 1.01, + "learning_rate": 3.068694995882369e-05, + "loss": 3.5169, + "step": 1179648 + }, + { + "epoch": 1.01, + "learning_rate": 3.067856401131317e-05, + "loss": 3.5295, + "step": 1180160 + }, + { + "epoch": 1.01, + "learning_rate": 3.0670178063802645e-05, + "loss": 3.5317, + "step": 1180672 + }, + { + "epoch": 1.01, + "learning_rate": 3.0661792116292125e-05, + "loss": 3.533, + "step": 1181184 + }, + { + "epoch": 1.01, + "learning_rate": 3.065342254758534e-05, + "loss": 3.533, + "step": 1181696 + }, + { + "epoch": 1.01, + "learning_rate": 3.064503660007482e-05, + "loss": 3.5332, + "step": 1182208 + }, + { + "epoch": 1.01, + "learning_rate": 3.06366506525643e-05, + "loss": 3.5419, + "step": 1182720 + }, + { + "epoch": 1.01, + "learning_rate": 3.062826470505378e-05, + "loss": 3.5341, + "step": 1183232 + }, + { + "epoch": 1.01, + "learning_rate": 3.061987875754326e-05, + "loss": 3.5204, + "step": 1183744 + }, + { + "epoch": 1.01, + "learning_rate": 3.0611509188836476e-05, + "loss": 3.5391, + "step": 1184256 + }, + { + "epoch": 1.01, + "learning_rate": 3.060312324132595e-05, + "loss": 3.5321, + "step": 1184768 + }, + { + "epoch": 1.01, + "learning_rate": 3.059473729381543e-05, + "loss": 3.5289, + "step": 1185280 + }, + { + "epoch": 1.01, + "learning_rate": 3.058635134630491e-05, + "loss": 3.5394, + "step": 1185792 + }, + { + "epoch": 1.01, + "learning_rate": 3.057798177759812e-05, + "loss": 3.5378, + "step": 1186304 + }, + { + "epoch": 1.01, + "learning_rate": 3.05695958300876e-05, + "loss": 3.5481, + "step": 1186816 + }, + { + "epoch": 1.01, + "learning_rate": 3.056120988257708e-05, + "loss": 3.5364, + "step": 1187328 + }, + { + "epoch": 1.01, + "learning_rate": 3.055282393506656e-05, + "loss": 3.5217, + "step": 1187840 + }, + { + "epoch": 1.01, + "learning_rate": 3.054443798755604e-05, + "loss": 3.5257, + "step": 1188352 + }, + { + "epoch": 1.01, + "learning_rate": 3.0536068418849254e-05, + "loss": 3.5335, + "step": 1188864 + }, + { + "epoch": 1.01, + "learning_rate": 3.0527682471338734e-05, + "loss": 3.5395, + "step": 1189376 + }, + { + "epoch": 1.01, + "learning_rate": 3.0519296523828214e-05, + "loss": 3.5309, + "step": 1189888 + }, + { + "epoch": 1.01, + "learning_rate": 3.051091057631769e-05, + "loss": 3.5309, + "step": 1190400 + }, + { + "epoch": 1.02, + "learning_rate": 3.0502541007610903e-05, + "loss": 3.5385, + "step": 1190912 + }, + { + "epoch": 1.02, + "learning_rate": 3.0494155060100383e-05, + "loss": 3.5253, + "step": 1191424 + }, + { + "epoch": 1.02, + "learning_rate": 3.0485769112589863e-05, + "loss": 3.5303, + "step": 1191936 + }, + { + "epoch": 1.02, + "learning_rate": 3.0477383165079343e-05, + "loss": 3.5263, + "step": 1192448 + }, + { + "epoch": 1.02, + "learning_rate": 3.0469013596372552e-05, + "loss": 3.5352, + "step": 1192960 + }, + { + "epoch": 1.02, + "learning_rate": 3.0460627648862032e-05, + "loss": 3.5426, + "step": 1193472 + }, + { + "epoch": 1.02, + "learning_rate": 3.0452241701351515e-05, + "loss": 3.5319, + "step": 1193984 + }, + { + "epoch": 1.02, + "learning_rate": 3.0443855753840995e-05, + "loss": 3.519, + "step": 1194496 + }, + { + "epoch": 1.02, + "learning_rate": 3.0435486185134204e-05, + "loss": 3.5312, + "step": 1195008 + }, + { + "epoch": 1.02, + "learning_rate": 3.0427100237623684e-05, + "loss": 3.5359, + "step": 1195520 + }, + { + "epoch": 1.02, + "learning_rate": 3.0418714290113164e-05, + "loss": 3.5378, + "step": 1196032 + }, + { + "epoch": 1.02, + "learning_rate": 3.0410328342602644e-05, + "loss": 3.5243, + "step": 1196544 + }, + { + "epoch": 1.02, + "learning_rate": 3.0401958773895857e-05, + "loss": 3.5248, + "step": 1197056 + }, + { + "epoch": 1.02, + "learning_rate": 3.0393572826385337e-05, + "loss": 3.5162, + "step": 1197568 + }, + { + "epoch": 1.02, + "learning_rate": 3.0385186878874817e-05, + "loss": 3.5358, + "step": 1198080 + }, + { + "epoch": 1.02, + "learning_rate": 3.0376800931364297e-05, + "loss": 3.5203, + "step": 1198592 + }, + { + "epoch": 1.02, + "learning_rate": 3.0368414983853776e-05, + "loss": 3.5258, + "step": 1199104 + }, + { + "epoch": 1.02, + "learning_rate": 3.0360045415146986e-05, + "loss": 3.5338, + "step": 1199616 + }, + { + "epoch": 1.02, + "learning_rate": 3.035165946763647e-05, + "loss": 3.5276, + "step": 1200128 + }, + { + "epoch": 1.02, + "learning_rate": 3.034327352012595e-05, + "loss": 3.5225, + "step": 1200640 + }, + { + "epoch": 1.02, + "learning_rate": 3.033488757261543e-05, + "loss": 3.529, + "step": 1201152 + }, + { + "epoch": 1.02, + "learning_rate": 3.0326518003908638e-05, + "loss": 3.5223, + "step": 1201664 + }, + { + "epoch": 1.02, + "learning_rate": 3.0318132056398118e-05, + "loss": 3.5335, + "step": 1202176 + }, + { + "epoch": 1.02, + "learning_rate": 3.0309746108887598e-05, + "loss": 3.5247, + "step": 1202688 + }, + { + "epoch": 1.02, + "learning_rate": 3.0301360161377078e-05, + "loss": 3.5316, + "step": 1203200 + }, + { + "epoch": 1.02, + "learning_rate": 3.029299059267029e-05, + "loss": 3.5301, + "step": 1203712 + }, + { + "epoch": 1.02, + "learning_rate": 3.028460464515977e-05, + "loss": 3.5384, + "step": 1204224 + }, + { + "epoch": 1.02, + "learning_rate": 3.027621869764925e-05, + "loss": 3.5284, + "step": 1204736 + }, + { + "epoch": 1.02, + "learning_rate": 3.026783275013873e-05, + "loss": 3.533, + "step": 1205248 + }, + { + "epoch": 1.02, + "learning_rate": 3.025946318143194e-05, + "loss": 3.5351, + "step": 1205760 + }, + { + "epoch": 1.02, + "learning_rate": 3.0251077233921423e-05, + "loss": 3.5318, + "step": 1206272 + }, + { + "epoch": 1.02, + "learning_rate": 3.0242691286410903e-05, + "loss": 3.5153, + "step": 1206784 + }, + { + "epoch": 1.02, + "learning_rate": 3.0234305338900383e-05, + "loss": 3.5353, + "step": 1207296 + }, + { + "epoch": 1.02, + "learning_rate": 3.022593577019359e-05, + "loss": 3.5296, + "step": 1207808 + }, + { + "epoch": 1.02, + "learning_rate": 3.021754982268307e-05, + "loss": 3.5362, + "step": 1208320 + }, + { + "epoch": 1.02, + "learning_rate": 3.020916387517255e-05, + "loss": 3.5202, + "step": 1208832 + }, + { + "epoch": 1.02, + "learning_rate": 3.020077792766203e-05, + "loss": 3.5236, + "step": 1209344 + }, + { + "epoch": 1.02, + "learning_rate": 3.0192391980151515e-05, + "loss": 3.5244, + "step": 1209856 + }, + { + "epoch": 1.02, + "learning_rate": 3.0184022411444724e-05, + "loss": 3.5255, + "step": 1210368 + }, + { + "epoch": 1.02, + "learning_rate": 3.0175636463934204e-05, + "loss": 3.5251, + "step": 1210880 + }, + { + "epoch": 1.02, + "learning_rate": 3.0167250516423684e-05, + "loss": 3.5366, + "step": 1211392 + }, + { + "epoch": 1.02, + "learning_rate": 3.0158864568913164e-05, + "loss": 3.5399, + "step": 1211904 + }, + { + "epoch": 1.02, + "learning_rate": 3.0150495000206376e-05, + "loss": 3.5258, + "step": 1212416 + }, + { + "epoch": 1.02, + "learning_rate": 3.0142109052695856e-05, + "loss": 3.5308, + "step": 1212928 + }, + { + "epoch": 1.02, + "learning_rate": 3.0133723105185336e-05, + "loss": 3.5326, + "step": 1213440 + }, + { + "epoch": 1.02, + "learning_rate": 3.0125337157674816e-05, + "loss": 3.5355, + "step": 1213952 + }, + { + "epoch": 1.02, + "learning_rate": 3.0116967588968025e-05, + "loss": 3.5326, + "step": 1214464 + }, + { + "epoch": 1.02, + "learning_rate": 3.0108581641457505e-05, + "loss": 3.5305, + "step": 1214976 + }, + { + "epoch": 1.02, + "learning_rate": 3.0100195693946985e-05, + "loss": 3.5337, + "step": 1215488 + }, + { + "epoch": 1.02, + "learning_rate": 3.0091809746436465e-05, + "loss": 3.5322, + "step": 1216000 + }, + { + "epoch": 1.02, + "learning_rate": 3.0083440177729678e-05, + "loss": 3.5299, + "step": 1216512 + }, + { + "epoch": 1.02, + "learning_rate": 3.0075054230219158e-05, + "loss": 3.5252, + "step": 1217024 + }, + { + "epoch": 1.02, + "learning_rate": 3.0066668282708637e-05, + "loss": 3.535, + "step": 1217536 + }, + { + "epoch": 1.02, + "learning_rate": 3.0058282335198117e-05, + "loss": 3.524, + "step": 1218048 + }, + { + "epoch": 1.02, + "learning_rate": 3.004991276649133e-05, + "loss": 3.5187, + "step": 1218560 + }, + { + "epoch": 1.02, + "learning_rate": 3.004154319778454e-05, + "loss": 3.5429, + "step": 1219072 + }, + { + "epoch": 1.02, + "learning_rate": 3.003315725027402e-05, + "loss": 3.5251, + "step": 1219584 + }, + { + "epoch": 1.02, + "learning_rate": 3.00247713027635e-05, + "loss": 3.5274, + "step": 1220096 + }, + { + "epoch": 1.02, + "learning_rate": 3.001638535525298e-05, + "loss": 3.5211, + "step": 1220608 + }, + { + "epoch": 1.03, + "learning_rate": 3.000799940774246e-05, + "loss": 3.5248, + "step": 1221120 + }, + { + "epoch": 1.03, + "eval_loss": 3.8464195728302, + "eval_runtime": 304.8533, + "eval_samples_per_second": 1251.72, + "eval_steps_per_second": 39.117, + "step": 1221120 + }, + { + "epoch": 0.0, + "learning_rate": 2.999961346023194e-05, + "loss": 3.5167, + "step": 1221632 + }, + { + "epoch": 0.0, + "learning_rate": 2.999122751272142e-05, + "loss": 3.529, + "step": 1222144 + }, + { + "epoch": 0.0, + "learning_rate": 2.9982841565210902e-05, + "loss": 3.5373, + "step": 1222656 + }, + { + "epoch": 0.0, + "learning_rate": 2.9974455617700375e-05, + "loss": 3.5344, + "step": 1223168 + }, + { + "epoch": 0.0, + "learning_rate": 2.996608604899359e-05, + "loss": 3.5376, + "step": 1223680 + }, + { + "epoch": 0.0, + "learning_rate": 2.995770010148307e-05, + "loss": 3.5211, + "step": 1224192 + }, + { + "epoch": 0.0, + "learning_rate": 2.994931415397255e-05, + "loss": 3.5273, + "step": 1224704 + }, + { + "epoch": 0.0, + "learning_rate": 2.9940928206462028e-05, + "loss": 3.5201, + "step": 1225216 + }, + { + "epoch": 0.0, + "learning_rate": 2.9932558637755244e-05, + "loss": 3.5308, + "step": 1225728 + }, + { + "epoch": 0.0, + "learning_rate": 2.9924172690244723e-05, + "loss": 3.527, + "step": 1226240 + }, + { + "epoch": 0.0, + "learning_rate": 2.9915786742734197e-05, + "loss": 3.531, + "step": 1226752 + }, + { + "epoch": 0.0, + "learning_rate": 2.9907400795223677e-05, + "loss": 3.5322, + "step": 1227264 + }, + { + "epoch": 0.0, + "learning_rate": 2.9899031226516892e-05, + "loss": 3.523, + "step": 1227776 + }, + { + "epoch": 0.0, + "learning_rate": 2.9890645279006372e-05, + "loss": 3.509, + "step": 1228288 + }, + { + "epoch": 0.0, + "learning_rate": 2.988225933149585e-05, + "loss": 3.5186, + "step": 1228800 + }, + { + "epoch": 0.0, + "learning_rate": 2.987387338398533e-05, + "loss": 3.5217, + "step": 1229312 + }, + { + "epoch": 0.0, + "learning_rate": 2.9865503815278545e-05, + "loss": 3.5279, + "step": 1229824 + }, + { + "epoch": 0.0, + "learning_rate": 2.9857117867768025e-05, + "loss": 3.5237, + "step": 1230336 + }, + { + "epoch": 0.0, + "learning_rate": 2.98487319202575e-05, + "loss": 3.5254, + "step": 1230848 + }, + { + "epoch": 0.0, + "learning_rate": 2.984034597274698e-05, + "loss": 3.5511, + "step": 1231360 + }, + { + "epoch": 0.0, + "learning_rate": 2.9831976404040197e-05, + "loss": 3.5195, + "step": 1231872 + }, + { + "epoch": 0.0, + "learning_rate": 2.982359045652967e-05, + "loss": 3.5236, + "step": 1232384 + }, + { + "epoch": 0.0, + "learning_rate": 2.981520450901915e-05, + "loss": 3.5269, + "step": 1232896 + }, + { + "epoch": 0.0, + "learning_rate": 2.980681856150863e-05, + "loss": 3.5356, + "step": 1233408 + }, + { + "epoch": 0.0, + "learning_rate": 2.9798448992801846e-05, + "loss": 3.5158, + "step": 1233920 + }, + { + "epoch": 0.0, + "learning_rate": 2.9790063045291323e-05, + "loss": 3.5205, + "step": 1234432 + }, + { + "epoch": 0.0, + "learning_rate": 2.9781677097780803e-05, + "loss": 3.5354, + "step": 1234944 + }, + { + "epoch": 0.0, + "learning_rate": 2.9773291150270283e-05, + "loss": 3.5193, + "step": 1235456 + }, + { + "epoch": 0.0, + "learning_rate": 2.9764905202759763e-05, + "loss": 3.5083, + "step": 1235968 + }, + { + "epoch": 0.01, + "learning_rate": 2.975653563405297e-05, + "loss": 3.51, + "step": 1236480 + }, + { + "epoch": 0.01, + "learning_rate": 2.9748149686542455e-05, + "loss": 3.5251, + "step": 1236992 + }, + { + "epoch": 0.01, + "learning_rate": 2.9739763739031935e-05, + "loss": 3.5298, + "step": 1237504 + }, + { + "epoch": 0.01, + "learning_rate": 2.9731377791521415e-05, + "loss": 3.5358, + "step": 1238016 + }, + { + "epoch": 0.01, + "learning_rate": 2.9723008222814624e-05, + "loss": 3.5214, + "step": 1238528 + }, + { + "epoch": 0.01, + "learning_rate": 2.9714622275304104e-05, + "loss": 3.5171, + "step": 1239040 + }, + { + "epoch": 0.01, + "learning_rate": 2.9706236327793584e-05, + "loss": 3.5302, + "step": 1239552 + }, + { + "epoch": 0.01, + "learning_rate": 2.9697850380283064e-05, + "loss": 3.5103, + "step": 1240064 + }, + { + "epoch": 0.01, + "learning_rate": 2.9689480811576276e-05, + "loss": 3.521, + "step": 1240576 + }, + { + "epoch": 0.01, + "learning_rate": 2.9681094864065756e-05, + "loss": 3.5152, + "step": 1241088 + }, + { + "epoch": 0.01, + "learning_rate": 2.9672708916555236e-05, + "loss": 3.522, + "step": 1241600 + }, + { + "epoch": 0.01, + "learning_rate": 2.9664322969044716e-05, + "loss": 3.5104, + "step": 1242112 + }, + { + "epoch": 0.01, + "learning_rate": 2.9655953400337925e-05, + "loss": 3.5341, + "step": 1242624 + }, + { + "epoch": 0.01, + "learning_rate": 2.964756745282741e-05, + "loss": 3.518, + "step": 1243136 + }, + { + "epoch": 0.01, + "learning_rate": 2.963918150531689e-05, + "loss": 3.5204, + "step": 1243648 + }, + { + "epoch": 0.01, + "learning_rate": 2.963079555780637e-05, + "loss": 3.5272, + "step": 1244160 + }, + { + "epoch": 0.01, + "learning_rate": 2.9622425989099578e-05, + "loss": 3.5228, + "step": 1244672 + }, + { + "epoch": 0.01, + "learning_rate": 2.9614040041589058e-05, + "loss": 3.5197, + "step": 1245184 + }, + { + "epoch": 0.01, + "learning_rate": 2.9605654094078538e-05, + "loss": 3.5054, + "step": 1245696 + }, + { + "epoch": 0.01, + "learning_rate": 2.9597268146568018e-05, + "loss": 3.5099, + "step": 1246208 + }, + { + "epoch": 0.01, + "learning_rate": 2.958889857786123e-05, + "loss": 3.5311, + "step": 1246720 + }, + { + "epoch": 0.01, + "learning_rate": 2.958051263035071e-05, + "loss": 3.5202, + "step": 1247232 + }, + { + "epoch": 0.01, + "learning_rate": 2.957212668284019e-05, + "loss": 3.5131, + "step": 1247744 + }, + { + "epoch": 0.01, + "learning_rate": 2.956374073532967e-05, + "loss": 3.5105, + "step": 1248256 + }, + { + "epoch": 0.01, + "learning_rate": 2.955537116662288e-05, + "loss": 3.5185, + "step": 1248768 + }, + { + "epoch": 0.01, + "learning_rate": 2.9546985219112362e-05, + "loss": 3.509, + "step": 1249280 + }, + { + "epoch": 0.01, + "learning_rate": 2.9538599271601842e-05, + "loss": 3.5291, + "step": 1249792 + }, + { + "epoch": 0.01, + "learning_rate": 2.9530213324091322e-05, + "loss": 3.5147, + "step": 1250304 + }, + { + "epoch": 0.01, + "learning_rate": 2.9521827376580802e-05, + "loss": 3.519, + "step": 1250816 + }, + { + "epoch": 0.01, + "learning_rate": 2.951345780787401e-05, + "loss": 3.5274, + "step": 1251328 + }, + { + "epoch": 0.01, + "learning_rate": 2.950507186036349e-05, + "loss": 3.5138, + "step": 1251840 + }, + { + "epoch": 0.01, + "learning_rate": 2.949668591285297e-05, + "loss": 3.5076, + "step": 1252352 + }, + { + "epoch": 0.01, + "learning_rate": 2.9488299965342455e-05, + "loss": 3.5125, + "step": 1252864 + }, + { + "epoch": 0.01, + "learning_rate": 2.9479930396635664e-05, + "loss": 3.5078, + "step": 1253376 + }, + { + "epoch": 0.01, + "learning_rate": 2.9471544449125144e-05, + "loss": 3.5077, + "step": 1253888 + }, + { + "epoch": 0.01, + "learning_rate": 2.9463158501614624e-05, + "loss": 3.5221, + "step": 1254400 + }, + { + "epoch": 0.01, + "learning_rate": 2.9454772554104104e-05, + "loss": 3.5268, + "step": 1254912 + }, + { + "epoch": 0.01, + "learning_rate": 2.9446402985397316e-05, + "loss": 3.5114, + "step": 1255424 + }, + { + "epoch": 0.01, + "learning_rate": 2.9438017037886796e-05, + "loss": 3.5076, + "step": 1255936 + }, + { + "epoch": 0.01, + "learning_rate": 2.9429631090376276e-05, + "loss": 3.5111, + "step": 1256448 + }, + { + "epoch": 0.01, + "learning_rate": 2.9421245142865756e-05, + "loss": 3.5162, + "step": 1256960 + }, + { + "epoch": 0.01, + "learning_rate": 2.9412859195355236e-05, + "loss": 3.5181, + "step": 1257472 + }, + { + "epoch": 0.01, + "learning_rate": 2.9404489626648445e-05, + "loss": 3.5203, + "step": 1257984 + }, + { + "epoch": 0.01, + "learning_rate": 2.9396103679137925e-05, + "loss": 3.5201, + "step": 1258496 + }, + { + "epoch": 0.01, + "learning_rate": 2.9387717731627408e-05, + "loss": 3.5249, + "step": 1259008 + }, + { + "epoch": 0.01, + "learning_rate": 2.9379331784116888e-05, + "loss": 3.5256, + "step": 1259520 + }, + { + "epoch": 0.01, + "learning_rate": 2.9370962215410097e-05, + "loss": 3.5044, + "step": 1260032 + }, + { + "epoch": 0.01, + "learning_rate": 2.9362576267899577e-05, + "loss": 3.5233, + "step": 1260544 + }, + { + "epoch": 0.01, + "learning_rate": 2.9354190320389057e-05, + "loss": 3.5209, + "step": 1261056 + }, + { + "epoch": 0.01, + "learning_rate": 2.9345804372878537e-05, + "loss": 3.5109, + "step": 1261568 + }, + { + "epoch": 0.01, + "learning_rate": 2.9337418425368017e-05, + "loss": 3.5268, + "step": 1262080 + }, + { + "epoch": 0.01, + "learning_rate": 2.932904885666123e-05, + "loss": 3.5229, + "step": 1262592 + }, + { + "epoch": 0.01, + "learning_rate": 2.932066290915071e-05, + "loss": 3.533, + "step": 1263104 + }, + { + "epoch": 0.01, + "learning_rate": 2.931227696164019e-05, + "loss": 3.5269, + "step": 1263616 + }, + { + "epoch": 0.01, + "learning_rate": 2.930389101412967e-05, + "loss": 3.5044, + "step": 1264128 + }, + { + "epoch": 0.01, + "learning_rate": 2.929552144542288e-05, + "loss": 3.5122, + "step": 1264640 + }, + { + "epoch": 0.01, + "learning_rate": 2.9287135497912362e-05, + "loss": 3.5204, + "step": 1265152 + }, + { + "epoch": 0.01, + "learning_rate": 2.9278749550401842e-05, + "loss": 3.5234, + "step": 1265664 + }, + { + "epoch": 0.01, + "learning_rate": 2.9270363602891322e-05, + "loss": 3.5196, + "step": 1266176 + }, + { + "epoch": 0.01, + "learning_rate": 2.926199403418453e-05, + "loss": 3.5171, + "step": 1266688 + }, + { + "epoch": 0.02, + "learning_rate": 2.925360808667401e-05, + "loss": 3.5224, + "step": 1267200 + }, + { + "epoch": 0.02, + "learning_rate": 2.924522213916349e-05, + "loss": 3.5131, + "step": 1267712 + }, + { + "epoch": 0.02, + "learning_rate": 2.923683619165297e-05, + "loss": 3.5104, + "step": 1268224 + }, + { + "epoch": 0.02, + "learning_rate": 2.9228466622946183e-05, + "loss": 3.516, + "step": 1268736 + }, + { + "epoch": 0.02, + "learning_rate": 2.9220080675435663e-05, + "loss": 3.5217, + "step": 1269248 + }, + { + "epoch": 0.02, + "learning_rate": 2.9211694727925143e-05, + "loss": 3.5334, + "step": 1269760 + }, + { + "epoch": 0.02, + "learning_rate": 2.9203308780414623e-05, + "loss": 3.5142, + "step": 1270272 + }, + { + "epoch": 0.02, + "learning_rate": 2.9194939211707832e-05, + "loss": 3.5063, + "step": 1270784 + }, + { + "epoch": 0.02, + "learning_rate": 2.9186553264197312e-05, + "loss": 3.5151, + "step": 1271296 + }, + { + "epoch": 0.02, + "learning_rate": 2.9178167316686796e-05, + "loss": 3.5229, + "step": 1271808 + }, + { + "epoch": 0.02, + "learning_rate": 2.9169781369176275e-05, + "loss": 3.5249, + "step": 1272320 + }, + { + "epoch": 0.02, + "learning_rate": 2.9161411800469485e-05, + "loss": 3.5126, + "step": 1272832 + }, + { + "epoch": 0.02, + "learning_rate": 2.9153025852958965e-05, + "loss": 3.5174, + "step": 1273344 + }, + { + "epoch": 0.02, + "learning_rate": 2.9144639905448444e-05, + "loss": 3.4982, + "step": 1273856 + }, + { + "epoch": 0.02, + "learning_rate": 2.9136253957937924e-05, + "loss": 3.5193, + "step": 1274368 + }, + { + "epoch": 0.02, + "learning_rate": 2.9127884389231137e-05, + "loss": 3.5117, + "step": 1274880 + }, + { + "epoch": 0.02, + "learning_rate": 2.9119498441720617e-05, + "loss": 3.509, + "step": 1275392 + }, + { + "epoch": 0.02, + "learning_rate": 2.9111112494210097e-05, + "loss": 3.5166, + "step": 1275904 + }, + { + "epoch": 0.02, + "learning_rate": 2.9102726546699577e-05, + "loss": 3.5171, + "step": 1276416 + }, + { + "epoch": 0.02, + "learning_rate": 2.9094356977992786e-05, + "loss": 3.509, + "step": 1276928 + }, + { + "epoch": 0.02, + "learning_rate": 2.9085971030482266e-05, + "loss": 3.5167, + "step": 1277440 + }, + { + "epoch": 0.02, + "learning_rate": 2.907758508297175e-05, + "loss": 3.5094, + "step": 1277952 + }, + { + "epoch": 0.02, + "learning_rate": 2.9069199135461222e-05, + "loss": 3.52, + "step": 1278464 + }, + { + "epoch": 0.02, + "learning_rate": 2.9060829566754438e-05, + "loss": 3.5084, + "step": 1278976 + }, + { + "epoch": 0.02, + "learning_rate": 2.9052443619243918e-05, + "loss": 3.5166, + "step": 1279488 + }, + { + "epoch": 0.02, + "learning_rate": 2.9044057671733398e-05, + "loss": 3.5207, + "step": 1280000 + }, + { + "epoch": 0.02, + "learning_rate": 2.9035671724222875e-05, + "loss": 3.5207, + "step": 1280512 + }, + { + "epoch": 0.02, + "learning_rate": 2.9027285776712355e-05, + "loss": 3.5164, + "step": 1281024 + }, + { + "epoch": 0.02, + "learning_rate": 2.901891620800557e-05, + "loss": 3.5169, + "step": 1281536 + }, + { + "epoch": 0.02, + "learning_rate": 2.901053026049505e-05, + "loss": 3.5231, + "step": 1282048 + }, + { + "epoch": 0.02, + "learning_rate": 2.9002144312984524e-05, + "loss": 3.5152, + "step": 1282560 + }, + { + "epoch": 0.02, + "learning_rate": 2.8993758365474004e-05, + "loss": 3.5059, + "step": 1283072 + }, + { + "epoch": 0.02, + "learning_rate": 2.8985372417963487e-05, + "loss": 3.5225, + "step": 1283584 + }, + { + "epoch": 0.02, + "learning_rate": 2.8977002849256696e-05, + "loss": 3.5151, + "step": 1284096 + }, + { + "epoch": 0.02, + "learning_rate": 2.8968616901746176e-05, + "loss": 3.5212, + "step": 1284608 + }, + { + "epoch": 0.02, + "learning_rate": 2.8960230954235656e-05, + "loss": 3.5087, + "step": 1285120 + }, + { + "epoch": 0.02, + "learning_rate": 2.8951845006725136e-05, + "loss": 3.5105, + "step": 1285632 + }, + { + "epoch": 0.02, + "learning_rate": 2.894347543801835e-05, + "loss": 3.508, + "step": 1286144 + }, + { + "epoch": 0.02, + "learning_rate": 2.893508949050783e-05, + "loss": 3.5128, + "step": 1286656 + }, + { + "epoch": 0.02, + "learning_rate": 2.892670354299731e-05, + "loss": 3.5113, + "step": 1287168 + }, + { + "epoch": 0.02, + "learning_rate": 2.8918317595486788e-05, + "loss": 3.5245, + "step": 1287680 + }, + { + "epoch": 0.02, + "learning_rate": 2.8909948026779997e-05, + "loss": 3.5277, + "step": 1288192 + }, + { + "epoch": 0.02, + "learning_rate": 2.8901562079269477e-05, + "loss": 3.5098, + "step": 1288704 + }, + { + "epoch": 0.02, + "learning_rate": 2.8893176131758957e-05, + "loss": 3.5115, + "step": 1289216 + }, + { + "epoch": 0.02, + "learning_rate": 2.888479018424844e-05, + "loss": 3.5189, + "step": 1289728 + }, + { + "epoch": 0.02, + "learning_rate": 2.887642061554165e-05, + "loss": 3.5219, + "step": 1290240 + }, + { + "epoch": 0.02, + "learning_rate": 2.886803466803113e-05, + "loss": 3.5231, + "step": 1290752 + }, + { + "epoch": 0.02, + "learning_rate": 2.885964872052061e-05, + "loss": 3.5204, + "step": 1291264 + }, + { + "epoch": 0.02, + "learning_rate": 2.885126277301009e-05, + "loss": 3.5143, + "step": 1291776 + }, + { + "epoch": 0.02, + "learning_rate": 2.8842893204303302e-05, + "loss": 3.5172, + "step": 1292288 + }, + { + "epoch": 0.02, + "learning_rate": 2.8834507256792782e-05, + "loss": 3.5165, + "step": 1292800 + }, + { + "epoch": 0.02, + "learning_rate": 2.8826121309282262e-05, + "loss": 3.5116, + "step": 1293312 + }, + { + "epoch": 0.02, + "learning_rate": 2.8817735361771742e-05, + "loss": 3.5241, + "step": 1293824 + }, + { + "epoch": 0.02, + "learning_rate": 2.880936579306495e-05, + "loss": 3.5127, + "step": 1294336 + }, + { + "epoch": 0.02, + "learning_rate": 2.880097984555443e-05, + "loss": 3.5009, + "step": 1294848 + }, + { + "epoch": 0.02, + "learning_rate": 2.8792610276847643e-05, + "loss": 3.5324, + "step": 1295360 + }, + { + "epoch": 0.02, + "learning_rate": 2.8784224329337123e-05, + "loss": 3.5116, + "step": 1295872 + }, + { + "epoch": 0.02, + "learning_rate": 2.8775838381826603e-05, + "loss": 3.5156, + "step": 1296384 + }, + { + "epoch": 0.02, + "learning_rate": 2.8767452434316083e-05, + "loss": 3.5074, + "step": 1296896 + }, + { + "epoch": 0.02, + "learning_rate": 2.8759066486805563e-05, + "loss": 3.5096, + "step": 1297408 + }, + { + "epoch": 0.03, + "eval_loss": 3.847977876663208, + "eval_runtime": 304.9741, + "eval_samples_per_second": 1251.224, + "eval_steps_per_second": 39.102, + "step": 1297440 + }, + { + "epoch": 1.0, + "learning_rate": 2.8750680539295043e-05, + "loss": 3.5033, + "step": 1297920 + }, + { + "epoch": 1.0, + "learning_rate": 2.8742294591784523e-05, + "loss": 3.5174, + "step": 1298432 + }, + { + "epoch": 1.0, + "learning_rate": 2.8733908644274003e-05, + "loss": 3.5272, + "step": 1298944 + }, + { + "epoch": 1.0, + "learning_rate": 2.8725539075567216e-05, + "loss": 3.5126, + "step": 1299456 + }, + { + "epoch": 1.0, + "learning_rate": 2.8717153128056696e-05, + "loss": 3.5304, + "step": 1299968 + }, + { + "epoch": 1.0, + "learning_rate": 2.8708767180546176e-05, + "loss": 3.5031, + "step": 1300480 + }, + { + "epoch": 1.0, + "learning_rate": 2.8700381233035656e-05, + "loss": 3.5166, + "step": 1300992 + }, + { + "epoch": 1.0, + "learning_rate": 2.8692011664328865e-05, + "loss": 3.504, + "step": 1301504 + }, + { + "epoch": 1.0, + "learning_rate": 2.8683625716818348e-05, + "loss": 3.5165, + "step": 1302016 + }, + { + "epoch": 1.0, + "learning_rate": 2.8675239769307828e-05, + "loss": 3.516, + "step": 1302528 + }, + { + "epoch": 1.0, + "learning_rate": 2.8666853821797308e-05, + "loss": 3.5158, + "step": 1303040 + }, + { + "epoch": 1.0, + "learning_rate": 2.8658484253090517e-05, + "loss": 3.5194, + "step": 1303552 + }, + { + "epoch": 1.0, + "learning_rate": 2.8650098305579997e-05, + "loss": 3.5066, + "step": 1304064 + }, + { + "epoch": 1.0, + "learning_rate": 2.8641712358069477e-05, + "loss": 3.5, + "step": 1304576 + }, + { + "epoch": 1.0, + "learning_rate": 2.8633326410558957e-05, + "loss": 3.504, + "step": 1305088 + }, + { + "epoch": 1.0, + "learning_rate": 2.862495684185217e-05, + "loss": 3.5082, + "step": 1305600 + }, + { + "epoch": 1.0, + "learning_rate": 2.861657089434165e-05, + "loss": 3.5153, + "step": 1306112 + }, + { + "epoch": 1.0, + "learning_rate": 2.860818494683113e-05, + "loss": 3.5089, + "step": 1306624 + }, + { + "epoch": 1.0, + "learning_rate": 2.859979899932061e-05, + "loss": 3.5152, + "step": 1307136 + }, + { + "epoch": 1.0, + "learning_rate": 2.8591429430613818e-05, + "loss": 3.5372, + "step": 1307648 + }, + { + "epoch": 1.0, + "learning_rate": 2.85830434831033e-05, + "loss": 3.5088, + "step": 1308160 + }, + { + "epoch": 1.0, + "learning_rate": 2.857465753559278e-05, + "loss": 3.5097, + "step": 1308672 + }, + { + "epoch": 1.0, + "learning_rate": 2.856627158808226e-05, + "loss": 3.5127, + "step": 1309184 + }, + { + "epoch": 1.0, + "learning_rate": 2.855790201937547e-05, + "loss": 3.5179, + "step": 1309696 + }, + { + "epoch": 1.0, + "learning_rate": 2.854951607186495e-05, + "loss": 3.504, + "step": 1310208 + }, + { + "epoch": 1.0, + "learning_rate": 2.854113012435443e-05, + "loss": 3.5137, + "step": 1310720 + }, + { + "epoch": 1.0, + "learning_rate": 2.853274417684391e-05, + "loss": 3.5184, + "step": 1311232 + }, + { + "epoch": 1.0, + "learning_rate": 2.8524374608137123e-05, + "loss": 3.5109, + "step": 1311744 + }, + { + "epoch": 1.0, + "learning_rate": 2.8515988660626603e-05, + "loss": 3.4925, + "step": 1312256 + }, + { + "epoch": 1.01, + "learning_rate": 2.8507602713116083e-05, + "loss": 3.5036, + "step": 1312768 + }, + { + "epoch": 1.01, + "learning_rate": 2.8499216765605563e-05, + "loss": 3.509, + "step": 1313280 + }, + { + "epoch": 1.01, + "learning_rate": 2.8490847196898772e-05, + "loss": 3.5144, + "step": 1313792 + }, + { + "epoch": 1.01, + "learning_rate": 2.8482461249388255e-05, + "loss": 3.5236, + "step": 1314304 + }, + { + "epoch": 1.01, + "learning_rate": 2.8474075301877735e-05, + "loss": 3.5078, + "step": 1314816 + }, + { + "epoch": 1.01, + "learning_rate": 2.8465689354367215e-05, + "loss": 3.5027, + "step": 1315328 + }, + { + "epoch": 1.01, + "learning_rate": 2.8457319785660424e-05, + "loss": 3.5171, + "step": 1315840 + }, + { + "epoch": 1.01, + "learning_rate": 2.8448933838149904e-05, + "loss": 3.4985, + "step": 1316352 + }, + { + "epoch": 1.01, + "learning_rate": 2.8440547890639384e-05, + "loss": 3.5077, + "step": 1316864 + }, + { + "epoch": 1.01, + "learning_rate": 2.8432161943128864e-05, + "loss": 3.4985, + "step": 1317376 + }, + { + "epoch": 1.01, + "learning_rate": 2.8423792374422077e-05, + "loss": 3.5067, + "step": 1317888 + }, + { + "epoch": 1.01, + "learning_rate": 2.8415406426911557e-05, + "loss": 3.5004, + "step": 1318400 + }, + { + "epoch": 1.01, + "learning_rate": 2.8407020479401037e-05, + "loss": 3.5205, + "step": 1318912 + }, + { + "epoch": 1.01, + "learning_rate": 2.8398634531890517e-05, + "loss": 3.5078, + "step": 1319424 + }, + { + "epoch": 1.01, + "learning_rate": 2.8390248584379996e-05, + "loss": 3.5057, + "step": 1319936 + }, + { + "epoch": 1.01, + "learning_rate": 2.8381879015673206e-05, + "loss": 3.512, + "step": 1320448 + }, + { + "epoch": 1.01, + "learning_rate": 2.837349306816269e-05, + "loss": 3.5108, + "step": 1320960 + }, + { + "epoch": 1.01, + "learning_rate": 2.836510712065217e-05, + "loss": 3.5039, + "step": 1321472 + }, + { + "epoch": 1.01, + "learning_rate": 2.8356737551945378e-05, + "loss": 3.4956, + "step": 1321984 + }, + { + "epoch": 1.01, + "learning_rate": 2.8348351604434858e-05, + "loss": 3.4941, + "step": 1322496 + }, + { + "epoch": 1.01, + "learning_rate": 2.8339965656924338e-05, + "loss": 3.5158, + "step": 1323008 + }, + { + "epoch": 1.01, + "learning_rate": 2.8331579709413818e-05, + "loss": 3.5062, + "step": 1323520 + }, + { + "epoch": 1.01, + "learning_rate": 2.8323193761903298e-05, + "loss": 3.4993, + "step": 1324032 + }, + { + "epoch": 1.01, + "learning_rate": 2.831482419319651e-05, + "loss": 3.4985, + "step": 1324544 + }, + { + "epoch": 1.01, + "learning_rate": 2.830643824568599e-05, + "loss": 3.506, + "step": 1325056 + }, + { + "epoch": 1.01, + "learning_rate": 2.829805229817547e-05, + "loss": 3.4938, + "step": 1325568 + }, + { + "epoch": 1.01, + "learning_rate": 2.828966635066495e-05, + "loss": 3.5131, + "step": 1326080 + }, + { + "epoch": 1.01, + "learning_rate": 2.828129678195816e-05, + "loss": 3.5026, + "step": 1326592 + }, + { + "epoch": 1.01, + "learning_rate": 2.8272910834447643e-05, + "loss": 3.5036, + "step": 1327104 + }, + { + "epoch": 1.01, + "learning_rate": 2.8264524886937123e-05, + "loss": 3.5169, + "step": 1327616 + }, + { + "epoch": 1.01, + "learning_rate": 2.8256138939426603e-05, + "loss": 3.4947, + "step": 1328128 + }, + { + "epoch": 1.01, + "learning_rate": 2.824776937071981e-05, + "loss": 3.4967, + "step": 1328640 + }, + { + "epoch": 1.01, + "learning_rate": 2.823938342320929e-05, + "loss": 3.5044, + "step": 1329152 + }, + { + "epoch": 1.01, + "learning_rate": 2.823099747569877e-05, + "loss": 3.4916, + "step": 1329664 + }, + { + "epoch": 1.01, + "learning_rate": 2.8222611528188248e-05, + "loss": 3.4956, + "step": 1330176 + }, + { + "epoch": 1.01, + "learning_rate": 2.8214241959481464e-05, + "loss": 3.5094, + "step": 1330688 + }, + { + "epoch": 1.01, + "learning_rate": 2.8205856011970944e-05, + "loss": 3.5135, + "step": 1331200 + }, + { + "epoch": 1.01, + "learning_rate": 2.8197470064460424e-05, + "loss": 3.4991, + "step": 1331712 + }, + { + "epoch": 1.01, + "learning_rate": 2.8189084116949897e-05, + "loss": 3.4963, + "step": 1332224 + }, + { + "epoch": 1.01, + "learning_rate": 2.8180714548243113e-05, + "loss": 3.4927, + "step": 1332736 + }, + { + "epoch": 1.01, + "learning_rate": 2.8172328600732596e-05, + "loss": 3.5052, + "step": 1333248 + }, + { + "epoch": 1.01, + "learning_rate": 2.8163942653222076e-05, + "loss": 3.5046, + "step": 1333760 + }, + { + "epoch": 1.01, + "learning_rate": 2.815555670571155e-05, + "loss": 3.5047, + "step": 1334272 + }, + { + "epoch": 1.01, + "learning_rate": 2.8147187137004765e-05, + "loss": 3.5086, + "step": 1334784 + }, + { + "epoch": 1.01, + "learning_rate": 2.8138801189494245e-05, + "loss": 3.5115, + "step": 1335296 + }, + { + "epoch": 1.01, + "learning_rate": 2.8130415241983722e-05, + "loss": 3.5134, + "step": 1335808 + }, + { + "epoch": 1.01, + "learning_rate": 2.8122029294473202e-05, + "loss": 3.4942, + "step": 1336320 + }, + { + "epoch": 1.01, + "learning_rate": 2.8113659725766418e-05, + "loss": 3.5087, + "step": 1336832 + }, + { + "epoch": 1.01, + "learning_rate": 2.8105273778255898e-05, + "loss": 3.5104, + "step": 1337344 + }, + { + "epoch": 1.01, + "learning_rate": 2.809688783074537e-05, + "loss": 3.4952, + "step": 1337856 + }, + { + "epoch": 1.01, + "learning_rate": 2.808850188323485e-05, + "loss": 3.5176, + "step": 1338368 + }, + { + "epoch": 1.01, + "learning_rate": 2.8080115935724334e-05, + "loss": 3.51, + "step": 1338880 + }, + { + "epoch": 1.01, + "learning_rate": 2.8071746367017543e-05, + "loss": 3.5155, + "step": 1339392 + }, + { + "epoch": 1.01, + "learning_rate": 2.8063360419507023e-05, + "loss": 3.516, + "step": 1339904 + }, + { + "epoch": 1.01, + "learning_rate": 2.8054974471996503e-05, + "loss": 3.4909, + "step": 1340416 + }, + { + "epoch": 1.01, + "learning_rate": 2.8046588524485983e-05, + "loss": 3.5052, + "step": 1340928 + }, + { + "epoch": 1.01, + "learning_rate": 2.8038218955779196e-05, + "loss": 3.5037, + "step": 1341440 + }, + { + "epoch": 1.01, + "learning_rate": 2.8029833008268675e-05, + "loss": 3.508, + "step": 1341952 + }, + { + "epoch": 1.01, + "learning_rate": 2.8021447060758155e-05, + "loss": 3.5077, + "step": 1342464 + }, + { + "epoch": 1.01, + "learning_rate": 2.8013061113247635e-05, + "loss": 3.5025, + "step": 1342976 + }, + { + "epoch": 1.02, + "learning_rate": 2.8004691544540844e-05, + "loss": 3.5097, + "step": 1343488 + }, + { + "epoch": 1.02, + "learning_rate": 2.7996305597030324e-05, + "loss": 3.506, + "step": 1344000 + }, + { + "epoch": 1.02, + "learning_rate": 2.7987919649519804e-05, + "loss": 3.4929, + "step": 1344512 + }, + { + "epoch": 1.02, + "learning_rate": 2.7979533702009288e-05, + "loss": 3.5019, + "step": 1345024 + }, + { + "epoch": 1.02, + "learning_rate": 2.7971164133302497e-05, + "loss": 3.5116, + "step": 1345536 + }, + { + "epoch": 1.02, + "learning_rate": 2.7962778185791977e-05, + "loss": 3.5185, + "step": 1346048 + }, + { + "epoch": 1.02, + "learning_rate": 2.7954392238281457e-05, + "loss": 3.5037, + "step": 1346560 + }, + { + "epoch": 1.02, + "learning_rate": 2.7946006290770937e-05, + "loss": 3.4876, + "step": 1347072 + }, + { + "epoch": 1.02, + "learning_rate": 2.793763672206415e-05, + "loss": 3.5044, + "step": 1347584 + }, + { + "epoch": 1.02, + "learning_rate": 2.792925077455363e-05, + "loss": 3.5101, + "step": 1348096 + }, + { + "epoch": 1.02, + "learning_rate": 2.792086482704311e-05, + "loss": 3.5099, + "step": 1348608 + }, + { + "epoch": 1.02, + "learning_rate": 2.791247887953259e-05, + "loss": 3.5032, + "step": 1349120 + }, + { + "epoch": 1.02, + "learning_rate": 2.7904109310825798e-05, + "loss": 3.5005, + "step": 1349632 + }, + { + "epoch": 1.02, + "learning_rate": 2.7895723363315278e-05, + "loss": 3.49, + "step": 1350144 + }, + { + "epoch": 1.02, + "learning_rate": 2.7887337415804758e-05, + "loss": 3.5051, + "step": 1350656 + }, + { + "epoch": 1.02, + "learning_rate": 2.787895146829424e-05, + "loss": 3.4954, + "step": 1351168 + }, + { + "epoch": 1.02, + "learning_rate": 2.787058189958745e-05, + "loss": 3.4985, + "step": 1351680 + }, + { + "epoch": 1.02, + "learning_rate": 2.786219595207693e-05, + "loss": 3.5008, + "step": 1352192 + }, + { + "epoch": 1.02, + "learning_rate": 2.785381000456641e-05, + "loss": 3.5058, + "step": 1352704 + }, + { + "epoch": 1.02, + "learning_rate": 2.784542405705589e-05, + "loss": 3.4965, + "step": 1353216 + }, + { + "epoch": 1.02, + "learning_rate": 2.7837054488349103e-05, + "loss": 3.5062, + "step": 1353728 + }, + { + "epoch": 1.02, + "learning_rate": 2.7828668540838583e-05, + "loss": 3.498, + "step": 1354240 + }, + { + "epoch": 1.02, + "learning_rate": 2.7820282593328063e-05, + "loss": 3.5027, + "step": 1354752 + }, + { + "epoch": 1.02, + "learning_rate": 2.7811896645817543e-05, + "loss": 3.4958, + "step": 1355264 + }, + { + "epoch": 1.02, + "learning_rate": 2.7803527077110752e-05, + "loss": 3.4988, + "step": 1355776 + }, + { + "epoch": 1.02, + "learning_rate": 2.7795141129600232e-05, + "loss": 3.5091, + "step": 1356288 + }, + { + "epoch": 1.02, + "learning_rate": 2.7786755182089712e-05, + "loss": 3.5099, + "step": 1356800 + }, + { + "epoch": 1.02, + "learning_rate": 2.7778369234579195e-05, + "loss": 3.5023, + "step": 1357312 + }, + { + "epoch": 1.02, + "learning_rate": 2.7769999665872404e-05, + "loss": 3.5016, + "step": 1357824 + }, + { + "epoch": 1.02, + "learning_rate": 2.7761613718361884e-05, + "loss": 3.5094, + "step": 1358336 + }, + { + "epoch": 1.02, + "learning_rate": 2.7753227770851364e-05, + "loss": 3.5044, + "step": 1358848 + }, + { + "epoch": 1.02, + "learning_rate": 2.7744841823340844e-05, + "loss": 3.4928, + "step": 1359360 + }, + { + "epoch": 1.02, + "learning_rate": 2.7736472254634057e-05, + "loss": 3.5113, + "step": 1359872 + }, + { + "epoch": 1.02, + "learning_rate": 2.7728086307123536e-05, + "loss": 3.5, + "step": 1360384 + }, + { + "epoch": 1.02, + "learning_rate": 2.7719700359613016e-05, + "loss": 3.508, + "step": 1360896 + }, + { + "epoch": 1.02, + "learning_rate": 2.7711314412102496e-05, + "loss": 3.4964, + "step": 1361408 + }, + { + "epoch": 1.02, + "learning_rate": 2.7702944843395705e-05, + "loss": 3.4987, + "step": 1361920 + }, + { + "epoch": 1.02, + "learning_rate": 2.7694558895885185e-05, + "loss": 3.4958, + "step": 1362432 + }, + { + "epoch": 1.02, + "learning_rate": 2.7686172948374665e-05, + "loss": 3.4963, + "step": 1362944 + }, + { + "epoch": 1.02, + "learning_rate": 2.767778700086415e-05, + "loss": 3.4986, + "step": 1363456 + }, + { + "epoch": 1.02, + "learning_rate": 2.7669417432157358e-05, + "loss": 3.5091, + "step": 1363968 + }, + { + "epoch": 1.02, + "learning_rate": 2.7661031484646838e-05, + "loss": 3.517, + "step": 1364480 + }, + { + "epoch": 1.02, + "learning_rate": 2.7652645537136318e-05, + "loss": 3.5026, + "step": 1364992 + }, + { + "epoch": 1.02, + "learning_rate": 2.7644259589625798e-05, + "loss": 3.4928, + "step": 1365504 + }, + { + "epoch": 1.02, + "learning_rate": 2.763589002091901e-05, + "loss": 3.507, + "step": 1366016 + }, + { + "epoch": 1.02, + "learning_rate": 2.762750407340849e-05, + "loss": 3.5073, + "step": 1366528 + }, + { + "epoch": 1.02, + "learning_rate": 2.761911812589797e-05, + "loss": 3.512, + "step": 1367040 + }, + { + "epoch": 1.02, + "learning_rate": 2.761073217838745e-05, + "loss": 3.507, + "step": 1367552 + }, + { + "epoch": 1.02, + "learning_rate": 2.760234623087693e-05, + "loss": 3.5032, + "step": 1368064 + }, + { + "epoch": 1.02, + "learning_rate": 2.759397666217014e-05, + "loss": 3.4979, + "step": 1368576 + }, + { + "epoch": 1.02, + "learning_rate": 2.758559071465962e-05, + "loss": 3.5098, + "step": 1369088 + }, + { + "epoch": 1.02, + "learning_rate": 2.7577204767149102e-05, + "loss": 3.4994, + "step": 1369600 + }, + { + "epoch": 1.02, + "learning_rate": 2.7568818819638582e-05, + "loss": 3.5044, + "step": 1370112 + }, + { + "epoch": 1.02, + "learning_rate": 2.756044925093179e-05, + "loss": 3.5039, + "step": 1370624 + }, + { + "epoch": 1.02, + "learning_rate": 2.755206330342127e-05, + "loss": 3.4924, + "step": 1371136 + }, + { + "epoch": 1.02, + "learning_rate": 2.754369373471448e-05, + "loss": 3.5187, + "step": 1371648 + }, + { + "epoch": 1.02, + "learning_rate": 2.7535307787203964e-05, + "loss": 3.5016, + "step": 1372160 + }, + { + "epoch": 1.02, + "learning_rate": 2.7526921839693444e-05, + "loss": 3.4998, + "step": 1372672 + }, + { + "epoch": 1.02, + "learning_rate": 2.7518535892182924e-05, + "loss": 3.4949, + "step": 1373184 + }, + { + "epoch": 1.02, + "learning_rate": 2.7510149944672404e-05, + "loss": 3.4935, + "step": 1373696 + }, + { + "epoch": 1.03, + "eval_loss": 3.8504014015197754, + "eval_runtime": 304.6079, + "eval_samples_per_second": 1252.728, + "eval_steps_per_second": 39.149, + "step": 1373760 + }, + { + "epoch": 0.0, + "learning_rate": 2.7501763997161884e-05, + "loss": 3.4889, + "step": 1374208 + }, + { + "epoch": 0.0, + "learning_rate": 2.7493378049651364e-05, + "loss": 3.5049, + "step": 1374720 + }, + { + "epoch": 0.0, + "learning_rate": 2.7484992102140844e-05, + "loss": 3.5127, + "step": 1375232 + }, + { + "epoch": 0.0, + "learning_rate": 2.7476606154630324e-05, + "loss": 3.4987, + "step": 1375744 + }, + { + "epoch": 0.0, + "learning_rate": 2.7468236585923536e-05, + "loss": 3.5163, + "step": 1376256 + }, + { + "epoch": 0.0, + "learning_rate": 2.7459850638413016e-05, + "loss": 3.4931, + "step": 1376768 + }, + { + "epoch": 0.0, + "learning_rate": 2.7451464690902496e-05, + "loss": 3.5048, + "step": 1377280 + }, + { + "epoch": 0.0, + "learning_rate": 2.7443078743391976e-05, + "loss": 3.4884, + "step": 1377792 + }, + { + "epoch": 0.0, + "learning_rate": 2.7434709174685185e-05, + "loss": 3.5046, + "step": 1378304 + }, + { + "epoch": 0.0, + "learning_rate": 2.7426323227174665e-05, + "loss": 3.5009, + "step": 1378816 + }, + { + "epoch": 0.0, + "learning_rate": 2.7417937279664145e-05, + "loss": 3.4988, + "step": 1379328 + }, + { + "epoch": 0.0, + "learning_rate": 2.740955133215362e-05, + "loss": 3.5101, + "step": 1379840 + }, + { + "epoch": 0.0, + "learning_rate": 2.7401181763446837e-05, + "loss": 3.4919, + "step": 1380352 + }, + { + "epoch": 0.0, + "learning_rate": 2.7392795815936317e-05, + "loss": 3.4881, + "step": 1380864 + }, + { + "epoch": 0.0, + "learning_rate": 2.7384409868425797e-05, + "loss": 3.4906, + "step": 1381376 + }, + { + "epoch": 0.0, + "learning_rate": 2.7376023920915274e-05, + "loss": 3.4972, + "step": 1381888 + }, + { + "epoch": 0.0, + "learning_rate": 2.736765435220849e-05, + "loss": 3.5044, + "step": 1382400 + }, + { + "epoch": 0.0, + "learning_rate": 2.735926840469797e-05, + "loss": 3.496, + "step": 1382912 + }, + { + "epoch": 0.0, + "learning_rate": 2.735088245718745e-05, + "loss": 3.5012, + "step": 1383424 + }, + { + "epoch": 0.0, + "learning_rate": 2.7342496509676923e-05, + "loss": 3.5223, + "step": 1383936 + }, + { + "epoch": 0.0, + "learning_rate": 2.733412694097014e-05, + "loss": 3.4954, + "step": 1384448 + }, + { + "epoch": 0.0, + "learning_rate": 2.732574099345962e-05, + "loss": 3.4946, + "step": 1384960 + }, + { + "epoch": 0.0, + "learning_rate": 2.7317355045949095e-05, + "loss": 3.5033, + "step": 1385472 + }, + { + "epoch": 0.0, + "learning_rate": 2.7308969098438575e-05, + "loss": 3.5042, + "step": 1385984 + }, + { + "epoch": 0.0, + "learning_rate": 2.730059952973179e-05, + "loss": 3.4913, + "step": 1386496 + }, + { + "epoch": 0.0, + "learning_rate": 2.729221358222127e-05, + "loss": 3.5019, + "step": 1387008 + }, + { + "epoch": 0.0, + "learning_rate": 2.7283827634710744e-05, + "loss": 3.5016, + "step": 1387520 + }, + { + "epoch": 0.0, + "learning_rate": 2.7275441687200227e-05, + "loss": 3.4985, + "step": 1388032 + }, + { + "epoch": 0.0, + "learning_rate": 2.7267072118493443e-05, + "loss": 3.4816, + "step": 1388544 + }, + { + "epoch": 0.01, + "learning_rate": 2.7258686170982923e-05, + "loss": 3.4907, + "step": 1389056 + }, + { + "epoch": 0.01, + "learning_rate": 2.7250300223472396e-05, + "loss": 3.4983, + "step": 1389568 + }, + { + "epoch": 0.01, + "learning_rate": 2.7241914275961876e-05, + "loss": 3.4975, + "step": 1390080 + }, + { + "epoch": 0.01, + "learning_rate": 2.7233544707255092e-05, + "loss": 3.5141, + "step": 1390592 + }, + { + "epoch": 0.01, + "learning_rate": 2.722515875974457e-05, + "loss": 3.4942, + "step": 1391104 + }, + { + "epoch": 0.01, + "learning_rate": 2.721677281223405e-05, + "loss": 3.491, + "step": 1391616 + }, + { + "epoch": 0.01, + "learning_rate": 2.720838686472353e-05, + "loss": 3.5039, + "step": 1392128 + }, + { + "epoch": 0.01, + "learning_rate": 2.7200017296016745e-05, + "loss": 3.4882, + "step": 1392640 + }, + { + "epoch": 0.01, + "learning_rate": 2.7191631348506218e-05, + "loss": 3.4899, + "step": 1393152 + }, + { + "epoch": 0.01, + "learning_rate": 2.7183245400995698e-05, + "loss": 3.4864, + "step": 1393664 + }, + { + "epoch": 0.01, + "learning_rate": 2.717485945348518e-05, + "loss": 3.4948, + "step": 1394176 + }, + { + "epoch": 0.01, + "learning_rate": 2.7166489884778397e-05, + "loss": 3.4866, + "step": 1394688 + }, + { + "epoch": 0.01, + "learning_rate": 2.715810393726787e-05, + "loss": 3.5095, + "step": 1395200 + }, + { + "epoch": 0.01, + "learning_rate": 2.714971798975735e-05, + "loss": 3.4907, + "step": 1395712 + }, + { + "epoch": 0.01, + "learning_rate": 2.714133204224683e-05, + "loss": 3.4983, + "step": 1396224 + }, + { + "epoch": 0.01, + "learning_rate": 2.713294609473631e-05, + "loss": 3.5, + "step": 1396736 + }, + { + "epoch": 0.01, + "learning_rate": 2.7124576526029523e-05, + "loss": 3.494, + "step": 1397248 + }, + { + "epoch": 0.01, + "learning_rate": 2.7116190578519003e-05, + "loss": 3.4923, + "step": 1397760 + }, + { + "epoch": 0.01, + "learning_rate": 2.7107804631008482e-05, + "loss": 3.483, + "step": 1398272 + }, + { + "epoch": 0.01, + "learning_rate": 2.7099418683497962e-05, + "loss": 3.4814, + "step": 1398784 + }, + { + "epoch": 0.01, + "learning_rate": 2.709104911479117e-05, + "loss": 3.5055, + "step": 1399296 + }, + { + "epoch": 0.01, + "learning_rate": 2.708266316728065e-05, + "loss": 3.4934, + "step": 1399808 + }, + { + "epoch": 0.01, + "learning_rate": 2.7074277219770135e-05, + "loss": 3.4867, + "step": 1400320 + }, + { + "epoch": 0.01, + "learning_rate": 2.7065891272259615e-05, + "loss": 3.487, + "step": 1400832 + }, + { + "epoch": 0.01, + "learning_rate": 2.7057521703552824e-05, + "loss": 3.4962, + "step": 1401344 + }, + { + "epoch": 0.01, + "learning_rate": 2.7049135756042304e-05, + "loss": 3.4771, + "step": 1401856 + }, + { + "epoch": 0.01, + "learning_rate": 2.7040749808531784e-05, + "loss": 3.5, + "step": 1402368 + }, + { + "epoch": 0.01, + "learning_rate": 2.7032363861021264e-05, + "loss": 3.4918, + "step": 1402880 + }, + { + "epoch": 0.01, + "learning_rate": 2.7023994292314476e-05, + "loss": 3.4897, + "step": 1403392 + }, + { + "epoch": 0.01, + "learning_rate": 2.7015608344803956e-05, + "loss": 3.5055, + "step": 1403904 + }, + { + "epoch": 0.01, + "learning_rate": 2.7007222397293436e-05, + "loss": 3.485, + "step": 1404416 + }, + { + "epoch": 0.01, + "learning_rate": 2.6998836449782916e-05, + "loss": 3.4852, + "step": 1404928 + }, + { + "epoch": 0.01, + "learning_rate": 2.6990466881076125e-05, + "loss": 3.4914, + "step": 1405440 + }, + { + "epoch": 0.01, + "learning_rate": 2.6982080933565605e-05, + "loss": 3.4798, + "step": 1405952 + }, + { + "epoch": 0.01, + "learning_rate": 2.697369498605509e-05, + "loss": 3.4831, + "step": 1406464 + }, + { + "epoch": 0.01, + "learning_rate": 2.696530903854457e-05, + "loss": 3.4963, + "step": 1406976 + }, + { + "epoch": 0.01, + "learning_rate": 2.6956939469837778e-05, + "loss": 3.4997, + "step": 1407488 + }, + { + "epoch": 0.01, + "learning_rate": 2.6948553522327257e-05, + "loss": 3.4853, + "step": 1408000 + }, + { + "epoch": 0.01, + "learning_rate": 2.6940167574816737e-05, + "loss": 3.4885, + "step": 1408512 + }, + { + "epoch": 0.01, + "learning_rate": 2.6931781627306217e-05, + "loss": 3.4795, + "step": 1409024 + }, + { + "epoch": 0.01, + "learning_rate": 2.692341205859943e-05, + "loss": 3.494, + "step": 1409536 + }, + { + "epoch": 0.01, + "learning_rate": 2.691502611108891e-05, + "loss": 3.4905, + "step": 1410048 + }, + { + "epoch": 0.01, + "learning_rate": 2.690664016357839e-05, + "loss": 3.4949, + "step": 1410560 + }, + { + "epoch": 0.01, + "learning_rate": 2.689825421606787e-05, + "loss": 3.4938, + "step": 1411072 + }, + { + "epoch": 0.01, + "learning_rate": 2.688988464736108e-05, + "loss": 3.4969, + "step": 1411584 + }, + { + "epoch": 0.01, + "learning_rate": 2.688149869985056e-05, + "loss": 3.5041, + "step": 1412096 + }, + { + "epoch": 0.01, + "learning_rate": 2.6873112752340042e-05, + "loss": 3.4797, + "step": 1412608 + }, + { + "epoch": 0.01, + "learning_rate": 2.6864726804829522e-05, + "loss": 3.4946, + "step": 1413120 + }, + { + "epoch": 0.01, + "learning_rate": 2.685635723612273e-05, + "loss": 3.4985, + "step": 1413632 + }, + { + "epoch": 0.01, + "learning_rate": 2.684797128861221e-05, + "loss": 3.4845, + "step": 1414144 + }, + { + "epoch": 0.01, + "learning_rate": 2.683958534110169e-05, + "loss": 3.5035, + "step": 1414656 + }, + { + "epoch": 0.01, + "learning_rate": 2.683119939359117e-05, + "loss": 3.498, + "step": 1415168 + }, + { + "epoch": 0.01, + "learning_rate": 2.6822829824884384e-05, + "loss": 3.5042, + "step": 1415680 + }, + { + "epoch": 0.01, + "learning_rate": 2.6814443877373864e-05, + "loss": 3.5027, + "step": 1416192 + }, + { + "epoch": 0.01, + "learning_rate": 2.6806057929863343e-05, + "loss": 3.48, + "step": 1416704 + }, + { + "epoch": 0.01, + "learning_rate": 2.6797671982352823e-05, + "loss": 3.4932, + "step": 1417216 + }, + { + "epoch": 0.01, + "learning_rate": 2.6789286034842303e-05, + "loss": 3.4879, + "step": 1417728 + }, + { + "epoch": 0.01, + "learning_rate": 2.6780916466135512e-05, + "loss": 3.4987, + "step": 1418240 + }, + { + "epoch": 0.01, + "learning_rate": 2.6772530518624996e-05, + "loss": 3.4938, + "step": 1418752 + }, + { + "epoch": 0.01, + "learning_rate": 2.6764144571114476e-05, + "loss": 3.4917, + "step": 1419264 + }, + { + "epoch": 0.02, + "learning_rate": 2.6755775002407685e-05, + "loss": 3.495, + "step": 1419776 + }, + { + "epoch": 0.02, + "learning_rate": 2.6747389054897165e-05, + "loss": 3.4941, + "step": 1420288 + }, + { + "epoch": 0.02, + "learning_rate": 2.6739003107386645e-05, + "loss": 3.4797, + "step": 1420800 + }, + { + "epoch": 0.02, + "learning_rate": 2.6730617159876125e-05, + "loss": 3.4891, + "step": 1421312 + }, + { + "epoch": 0.02, + "learning_rate": 2.6722247591169337e-05, + "loss": 3.4978, + "step": 1421824 + }, + { + "epoch": 0.02, + "learning_rate": 2.6713861643658817e-05, + "loss": 3.5046, + "step": 1422336 + }, + { + "epoch": 0.02, + "learning_rate": 2.6705475696148297e-05, + "loss": 3.4948, + "step": 1422848 + }, + { + "epoch": 0.02, + "learning_rate": 2.6697089748637777e-05, + "loss": 3.476, + "step": 1423360 + }, + { + "epoch": 0.02, + "learning_rate": 2.6688720179930986e-05, + "loss": 3.4913, + "step": 1423872 + }, + { + "epoch": 0.02, + "learning_rate": 2.6680334232420466e-05, + "loss": 3.4962, + "step": 1424384 + }, + { + "epoch": 0.02, + "learning_rate": 2.667194828490995e-05, + "loss": 3.4948, + "step": 1424896 + }, + { + "epoch": 0.02, + "learning_rate": 2.666356233739943e-05, + "loss": 3.4902, + "step": 1425408 + }, + { + "epoch": 0.02, + "learning_rate": 2.665519276869264e-05, + "loss": 3.489, + "step": 1425920 + }, + { + "epoch": 0.02, + "learning_rate": 2.664680682118212e-05, + "loss": 3.4769, + "step": 1426432 + }, + { + "epoch": 0.02, + "learning_rate": 2.66384208736716e-05, + "loss": 3.496, + "step": 1426944 + }, + { + "epoch": 0.02, + "learning_rate": 2.663003492616108e-05, + "loss": 3.4773, + "step": 1427456 + }, + { + "epoch": 0.02, + "learning_rate": 2.662164897865056e-05, + "loss": 3.4883, + "step": 1427968 + }, + { + "epoch": 0.02, + "learning_rate": 2.661327940994377e-05, + "loss": 3.4818, + "step": 1428480 + }, + { + "epoch": 0.02, + "learning_rate": 2.660489346243325e-05, + "loss": 3.4984, + "step": 1428992 + }, + { + "epoch": 0.02, + "learning_rate": 2.659650751492273e-05, + "loss": 3.4775, + "step": 1429504 + }, + { + "epoch": 0.02, + "learning_rate": 2.658812156741221e-05, + "loss": 3.496, + "step": 1430016 + }, + { + "epoch": 0.02, + "learning_rate": 2.657975199870542e-05, + "loss": 3.4856, + "step": 1430528 + }, + { + "epoch": 0.02, + "learning_rate": 2.65713660511949e-05, + "loss": 3.4844, + "step": 1431040 + }, + { + "epoch": 0.02, + "learning_rate": 2.6562980103684383e-05, + "loss": 3.4888, + "step": 1431552 + }, + { + "epoch": 0.02, + "learning_rate": 2.6554594156173863e-05, + "loss": 3.484, + "step": 1432064 + }, + { + "epoch": 0.02, + "learning_rate": 2.6546224587467072e-05, + "loss": 3.4963, + "step": 1432576 + }, + { + "epoch": 0.02, + "learning_rate": 2.6537838639956552e-05, + "loss": 3.4972, + "step": 1433088 + }, + { + "epoch": 0.02, + "learning_rate": 2.6529452692446032e-05, + "loss": 3.4913, + "step": 1433600 + }, + { + "epoch": 0.02, + "learning_rate": 2.6521066744935512e-05, + "loss": 3.4868, + "step": 1434112 + }, + { + "epoch": 0.02, + "learning_rate": 2.6512697176228725e-05, + "loss": 3.4926, + "step": 1434624 + }, + { + "epoch": 0.02, + "learning_rate": 2.6504311228718204e-05, + "loss": 3.4942, + "step": 1435136 + }, + { + "epoch": 0.02, + "learning_rate": 2.6495925281207684e-05, + "loss": 3.4768, + "step": 1435648 + }, + { + "epoch": 0.02, + "learning_rate": 2.6487539333697164e-05, + "loss": 3.4978, + "step": 1436160 + }, + { + "epoch": 0.02, + "learning_rate": 2.6479169764990373e-05, + "loss": 3.4921, + "step": 1436672 + }, + { + "epoch": 0.02, + "learning_rate": 2.6470783817479853e-05, + "loss": 3.4939, + "step": 1437184 + }, + { + "epoch": 0.02, + "learning_rate": 2.6462397869969337e-05, + "loss": 3.4857, + "step": 1437696 + }, + { + "epoch": 0.02, + "learning_rate": 2.6454011922458817e-05, + "loss": 3.4883, + "step": 1438208 + }, + { + "epoch": 0.02, + "learning_rate": 2.6445642353752026e-05, + "loss": 3.4796, + "step": 1438720 + }, + { + "epoch": 0.02, + "learning_rate": 2.6437256406241506e-05, + "loss": 3.4858, + "step": 1439232 + }, + { + "epoch": 0.02, + "learning_rate": 2.6428870458730986e-05, + "loss": 3.486, + "step": 1439744 + }, + { + "epoch": 0.02, + "learning_rate": 2.6420484511220466e-05, + "loss": 3.4962, + "step": 1440256 + }, + { + "epoch": 0.02, + "learning_rate": 2.6412114942513678e-05, + "loss": 3.5046, + "step": 1440768 + }, + { + "epoch": 0.02, + "learning_rate": 2.6403728995003158e-05, + "loss": 3.4897, + "step": 1441280 + }, + { + "epoch": 0.02, + "learning_rate": 2.6395343047492638e-05, + "loss": 3.4811, + "step": 1441792 + }, + { + "epoch": 0.02, + "learning_rate": 2.6386957099982118e-05, + "loss": 3.4922, + "step": 1442304 + }, + { + "epoch": 0.02, + "learning_rate": 2.6378587531275327e-05, + "loss": 3.4958, + "step": 1442816 + }, + { + "epoch": 0.02, + "learning_rate": 2.6370201583764807e-05, + "loss": 3.4959, + "step": 1443328 + }, + { + "epoch": 0.02, + "learning_rate": 2.636181563625429e-05, + "loss": 3.4964, + "step": 1443840 + }, + { + "epoch": 0.02, + "learning_rate": 2.635342968874377e-05, + "loss": 3.4855, + "step": 1444352 + }, + { + "epoch": 0.02, + "learning_rate": 2.634506012003698e-05, + "loss": 3.4908, + "step": 1444864 + }, + { + "epoch": 0.02, + "learning_rate": 2.633667417252646e-05, + "loss": 3.4965, + "step": 1445376 + }, + { + "epoch": 0.02, + "learning_rate": 2.632828822501594e-05, + "loss": 3.4853, + "step": 1445888 + }, + { + "epoch": 0.02, + "learning_rate": 2.631990227750542e-05, + "loss": 3.4925, + "step": 1446400 + }, + { + "epoch": 0.02, + "learning_rate": 2.6311532708798632e-05, + "loss": 3.4906, + "step": 1446912 + }, + { + "epoch": 0.02, + "learning_rate": 2.6303146761288112e-05, + "loss": 3.4802, + "step": 1447424 + }, + { + "epoch": 0.02, + "learning_rate": 2.629477719258132e-05, + "loss": 3.5018, + "step": 1447936 + }, + { + "epoch": 0.02, + "learning_rate": 2.62863912450708e-05, + "loss": 3.4919, + "step": 1448448 + }, + { + "epoch": 0.02, + "learning_rate": 2.627800529756028e-05, + "loss": 3.4842, + "step": 1448960 + }, + { + "epoch": 0.02, + "learning_rate": 2.626961935004976e-05, + "loss": 3.4827, + "step": 1449472 + }, + { + "epoch": 0.02, + "learning_rate": 2.6261233402539244e-05, + "loss": 3.4796, + "step": 1449984 + }, + { + "epoch": 0.03, + "eval_loss": 3.8504655361175537, + "eval_runtime": 365.4179, + "eval_samples_per_second": 1044.259, + "eval_steps_per_second": 32.634, + "step": 1450080 + }, + { + "epoch": 1.0, + "learning_rate": 2.6252847455028717e-05, + "loss": 3.4812, + "step": 1450496 + }, + { + "epoch": 1.0, + "learning_rate": 2.6244461507518197e-05, + "loss": 3.4912, + "step": 1451008 + }, + { + "epoch": 1.0, + "learning_rate": 2.6236075560007677e-05, + "loss": 3.4986, + "step": 1451520 + }, + { + "epoch": 1.0, + "learning_rate": 2.6227705991300893e-05, + "loss": 3.4866, + "step": 1452032 + }, + { + "epoch": 1.0, + "learning_rate": 2.621932004379037e-05, + "loss": 3.5085, + "step": 1452544 + }, + { + "epoch": 1.0, + "learning_rate": 2.621093409627985e-05, + "loss": 3.4778, + "step": 1453056 + }, + { + "epoch": 1.0, + "learning_rate": 2.620254814876933e-05, + "loss": 3.4939, + "step": 1453568 + }, + { + "epoch": 1.0, + "learning_rate": 2.619417858006254e-05, + "loss": 3.4759, + "step": 1454080 + }, + { + "epoch": 1.0, + "learning_rate": 2.618579263255202e-05, + "loss": 3.4914, + "step": 1454592 + }, + { + "epoch": 1.0, + "learning_rate": 2.61774066850415e-05, + "loss": 3.4903, + "step": 1455104 + }, + { + "epoch": 1.0, + "learning_rate": 2.6169020737530982e-05, + "loss": 3.4842, + "step": 1455616 + }, + { + "epoch": 1.0, + "learning_rate": 2.616065116882419e-05, + "loss": 3.4978, + "step": 1456128 + }, + { + "epoch": 1.0, + "learning_rate": 2.615226522131367e-05, + "loss": 3.4784, + "step": 1456640 + }, + { + "epoch": 1.0, + "learning_rate": 2.614387927380315e-05, + "loss": 3.4782, + "step": 1457152 + }, + { + "epoch": 1.0, + "learning_rate": 2.613549332629263e-05, + "loss": 3.4784, + "step": 1457664 + }, + { + "epoch": 1.0, + "learning_rate": 2.6127123757585843e-05, + "loss": 3.483, + "step": 1458176 + }, + { + "epoch": 1.0, + "learning_rate": 2.6118737810075323e-05, + "loss": 3.49, + "step": 1458688 + }, + { + "epoch": 1.0, + "learning_rate": 2.6110351862564803e-05, + "loss": 3.4841, + "step": 1459200 + }, + { + "epoch": 1.0, + "learning_rate": 2.6101965915054283e-05, + "loss": 3.4875, + "step": 1459712 + }, + { + "epoch": 1.0, + "learning_rate": 2.6093596346347492e-05, + "loss": 3.5073, + "step": 1460224 + }, + { + "epoch": 1.0, + "learning_rate": 2.6085210398836972e-05, + "loss": 3.4844, + "step": 1460736 + }, + { + "epoch": 1.0, + "learning_rate": 2.6076824451326452e-05, + "loss": 3.4861, + "step": 1461248 + }, + { + "epoch": 1.0, + "learning_rate": 2.6068438503815936e-05, + "loss": 3.4884, + "step": 1461760 + }, + { + "epoch": 1.0, + "learning_rate": 2.6060068935109145e-05, + "loss": 3.4905, + "step": 1462272 + }, + { + "epoch": 1.0, + "learning_rate": 2.6051682987598625e-05, + "loss": 3.4781, + "step": 1462784 + }, + { + "epoch": 1.0, + "learning_rate": 2.6043297040088105e-05, + "loss": 3.49, + "step": 1463296 + }, + { + "epoch": 1.0, + "learning_rate": 2.6034911092577585e-05, + "loss": 3.4908, + "step": 1463808 + }, + { + "epoch": 1.0, + "learning_rate": 2.6026541523870797e-05, + "loss": 3.4828, + "step": 1464320 + }, + { + "epoch": 1.0, + "learning_rate": 2.6018155576360277e-05, + "loss": 3.4723, + "step": 1464832 + }, + { + "epoch": 1.01, + "learning_rate": 2.6009769628849757e-05, + "loss": 3.4741, + "step": 1465344 + }, + { + "epoch": 1.01, + "learning_rate": 2.6001383681339237e-05, + "loss": 3.4888, + "step": 1465856 + }, + { + "epoch": 1.01, + "learning_rate": 2.5993014112632446e-05, + "loss": 3.4839, + "step": 1466368 + }, + { + "epoch": 1.01, + "learning_rate": 2.5984628165121926e-05, + "loss": 3.4986, + "step": 1466880 + }, + { + "epoch": 1.01, + "learning_rate": 2.5976242217611406e-05, + "loss": 3.4858, + "step": 1467392 + }, + { + "epoch": 1.01, + "learning_rate": 2.596785627010089e-05, + "loss": 3.4744, + "step": 1467904 + }, + { + "epoch": 1.01, + "learning_rate": 2.59594867013941e-05, + "loss": 3.4899, + "step": 1468416 + }, + { + "epoch": 1.01, + "learning_rate": 2.5951100753883578e-05, + "loss": 3.4813, + "step": 1468928 + }, + { + "epoch": 1.01, + "learning_rate": 2.5942714806373058e-05, + "loss": 3.4756, + "step": 1469440 + }, + { + "epoch": 1.01, + "learning_rate": 2.5934328858862538e-05, + "loss": 3.4763, + "step": 1469952 + }, + { + "epoch": 1.01, + "learning_rate": 2.592595929015575e-05, + "loss": 3.4802, + "step": 1470464 + }, + { + "epoch": 1.01, + "learning_rate": 2.591757334264523e-05, + "loss": 3.4746, + "step": 1470976 + }, + { + "epoch": 1.01, + "learning_rate": 2.590918739513471e-05, + "loss": 3.495, + "step": 1471488 + }, + { + "epoch": 1.01, + "learning_rate": 2.590080144762419e-05, + "loss": 3.4795, + "step": 1472000 + }, + { + "epoch": 1.01, + "learning_rate": 2.58924318789174e-05, + "loss": 3.4855, + "step": 1472512 + }, + { + "epoch": 1.01, + "learning_rate": 2.588404593140688e-05, + "loss": 3.4913, + "step": 1473024 + }, + { + "epoch": 1.01, + "learning_rate": 2.587565998389636e-05, + "loss": 3.4805, + "step": 1473536 + }, + { + "epoch": 1.01, + "learning_rate": 2.5867274036385843e-05, + "loss": 3.483, + "step": 1474048 + }, + { + "epoch": 1.01, + "learning_rate": 2.5858904467679052e-05, + "loss": 3.4681, + "step": 1474560 + }, + { + "epoch": 1.01, + "learning_rate": 2.5850518520168532e-05, + "loss": 3.4619, + "step": 1475072 + }, + { + "epoch": 1.01, + "learning_rate": 2.5842132572658012e-05, + "loss": 3.496, + "step": 1475584 + }, + { + "epoch": 1.01, + "learning_rate": 2.5833746625147492e-05, + "loss": 3.4812, + "step": 1476096 + }, + { + "epoch": 1.01, + "learning_rate": 2.5825377056440704e-05, + "loss": 3.4777, + "step": 1476608 + }, + { + "epoch": 1.01, + "learning_rate": 2.5816991108930184e-05, + "loss": 3.4732, + "step": 1477120 + }, + { + "epoch": 1.01, + "learning_rate": 2.5808605161419664e-05, + "loss": 3.4823, + "step": 1477632 + }, + { + "epoch": 1.01, + "learning_rate": 2.5800219213909144e-05, + "loss": 3.4655, + "step": 1478144 + }, + { + "epoch": 1.01, + "learning_rate": 2.5791849645202353e-05, + "loss": 3.4879, + "step": 1478656 + }, + { + "epoch": 1.01, + "learning_rate": 2.5783463697691833e-05, + "loss": 3.4826, + "step": 1479168 + }, + { + "epoch": 1.01, + "learning_rate": 2.5775077750181313e-05, + "loss": 3.4764, + "step": 1479680 + }, + { + "epoch": 1.01, + "learning_rate": 2.5766691802670793e-05, + "loss": 3.4917, + "step": 1480192 + }, + { + "epoch": 1.01, + "learning_rate": 2.5758322233964006e-05, + "loss": 3.4724, + "step": 1480704 + }, + { + "epoch": 1.01, + "learning_rate": 2.5749936286453486e-05, + "loss": 3.4714, + "step": 1481216 + }, + { + "epoch": 1.01, + "learning_rate": 2.5741550338942966e-05, + "loss": 3.489, + "step": 1481728 + }, + { + "epoch": 1.01, + "learning_rate": 2.5733164391432446e-05, + "loss": 3.464, + "step": 1482240 + }, + { + "epoch": 1.01, + "learning_rate": 2.5724794822725658e-05, + "loss": 3.4661, + "step": 1482752 + }, + { + "epoch": 1.01, + "learning_rate": 2.5716408875215138e-05, + "loss": 3.4871, + "step": 1483264 + }, + { + "epoch": 1.01, + "learning_rate": 2.5708022927704618e-05, + "loss": 3.4883, + "step": 1483776 + }, + { + "epoch": 1.01, + "learning_rate": 2.5699636980194098e-05, + "loss": 3.4681, + "step": 1484288 + }, + { + "epoch": 1.01, + "learning_rate": 2.5691251032683578e-05, + "loss": 3.4811, + "step": 1484800 + }, + { + "epoch": 1.01, + "learning_rate": 2.5682881463976787e-05, + "loss": 3.4636, + "step": 1485312 + }, + { + "epoch": 1.01, + "learning_rate": 2.5674495516466267e-05, + "loss": 3.483, + "step": 1485824 + }, + { + "epoch": 1.01, + "learning_rate": 2.5666109568955747e-05, + "loss": 3.477, + "step": 1486336 + }, + { + "epoch": 1.01, + "learning_rate": 2.565772362144523e-05, + "loss": 3.483, + "step": 1486848 + }, + { + "epoch": 1.01, + "learning_rate": 2.564935405273844e-05, + "loss": 3.4805, + "step": 1487360 + }, + { + "epoch": 1.01, + "learning_rate": 2.564096810522792e-05, + "loss": 3.4872, + "step": 1487872 + }, + { + "epoch": 1.01, + "learning_rate": 2.56325821577174e-05, + "loss": 3.4919, + "step": 1488384 + }, + { + "epoch": 1.01, + "learning_rate": 2.562419621020688e-05, + "loss": 3.4666, + "step": 1488896 + }, + { + "epoch": 1.01, + "learning_rate": 2.561582664150009e-05, + "loss": 3.4849, + "step": 1489408 + }, + { + "epoch": 1.01, + "learning_rate": 2.560744069398957e-05, + "loss": 3.4868, + "step": 1489920 + }, + { + "epoch": 1.01, + "learning_rate": 2.559905474647905e-05, + "loss": 3.4658, + "step": 1490432 + }, + { + "epoch": 1.01, + "learning_rate": 2.559066879896853e-05, + "loss": 3.4925, + "step": 1490944 + }, + { + "epoch": 1.01, + "learning_rate": 2.558229923026174e-05, + "loss": 3.4855, + "step": 1491456 + }, + { + "epoch": 1.01, + "learning_rate": 2.557391328275122e-05, + "loss": 3.4879, + "step": 1491968 + }, + { + "epoch": 1.01, + "learning_rate": 2.55655273352407e-05, + "loss": 3.4935, + "step": 1492480 + }, + { + "epoch": 1.01, + "learning_rate": 2.5557141387730184e-05, + "loss": 3.4703, + "step": 1492992 + }, + { + "epoch": 1.01, + "learning_rate": 2.5548771819023393e-05, + "loss": 3.4744, + "step": 1493504 + }, + { + "epoch": 1.01, + "learning_rate": 2.5540385871512873e-05, + "loss": 3.4789, + "step": 1494016 + }, + { + "epoch": 1.01, + "learning_rate": 2.5531999924002353e-05, + "loss": 3.4867, + "step": 1494528 + }, + { + "epoch": 1.01, + "learning_rate": 2.5523613976491833e-05, + "loss": 3.4814, + "step": 1495040 + }, + { + "epoch": 1.01, + "learning_rate": 2.5515244407785045e-05, + "loss": 3.482, + "step": 1495552 + }, + { + "epoch": 1.02, + "learning_rate": 2.5506858460274525e-05, + "loss": 3.4791, + "step": 1496064 + }, + { + "epoch": 1.02, + "learning_rate": 2.5498472512764005e-05, + "loss": 3.4863, + "step": 1496576 + }, + { + "epoch": 1.02, + "learning_rate": 2.5490086565253485e-05, + "loss": 3.4677, + "step": 1497088 + }, + { + "epoch": 1.02, + "learning_rate": 2.5481716996546694e-05, + "loss": 3.4754, + "step": 1497600 + }, + { + "epoch": 1.02, + "learning_rate": 2.5473331049036174e-05, + "loss": 3.4869, + "step": 1498112 + }, + { + "epoch": 1.02, + "learning_rate": 2.5464945101525654e-05, + "loss": 3.4918, + "step": 1498624 + }, + { + "epoch": 1.02, + "learning_rate": 2.5456559154015138e-05, + "loss": 3.4834, + "step": 1499136 + }, + { + "epoch": 1.02, + "learning_rate": 2.5448189585308347e-05, + "loss": 3.4631, + "step": 1499648 + }, + { + "epoch": 1.02, + "learning_rate": 2.5439803637797827e-05, + "loss": 3.4788, + "step": 1500160 + }, + { + "epoch": 1.02, + "learning_rate": 2.5431417690287307e-05, + "loss": 3.4823, + "step": 1500672 + }, + { + "epoch": 1.02, + "learning_rate": 2.5423031742776786e-05, + "loss": 3.4843, + "step": 1501184 + }, + { + "epoch": 1.02, + "learning_rate": 2.541466217407e-05, + "loss": 3.4808, + "step": 1501696 + }, + { + "epoch": 1.02, + "learning_rate": 2.540627622655948e-05, + "loss": 3.4778, + "step": 1502208 + }, + { + "epoch": 1.02, + "learning_rate": 2.539789027904896e-05, + "loss": 3.4653, + "step": 1502720 + }, + { + "epoch": 1.02, + "learning_rate": 2.538950433153844e-05, + "loss": 3.48, + "step": 1503232 + }, + { + "epoch": 1.02, + "learning_rate": 2.5381134762831648e-05, + "loss": 3.4693, + "step": 1503744 + }, + { + "epoch": 1.02, + "learning_rate": 2.5372748815321128e-05, + "loss": 3.4753, + "step": 1504256 + }, + { + "epoch": 1.02, + "learning_rate": 2.5364362867810608e-05, + "loss": 3.4657, + "step": 1504768 + }, + { + "epoch": 1.02, + "learning_rate": 2.535597692030009e-05, + "loss": 3.4864, + "step": 1505280 + }, + { + "epoch": 1.02, + "learning_rate": 2.53476073515933e-05, + "loss": 3.4657, + "step": 1505792 + }, + { + "epoch": 1.02, + "learning_rate": 2.533922140408278e-05, + "loss": 3.4865, + "step": 1506304 + }, + { + "epoch": 1.02, + "learning_rate": 2.533083545657226e-05, + "loss": 3.4695, + "step": 1506816 + }, + { + "epoch": 1.02, + "learning_rate": 2.532244950906174e-05, + "loss": 3.4763, + "step": 1507328 + }, + { + "epoch": 1.02, + "learning_rate": 2.5314079940354953e-05, + "loss": 3.477, + "step": 1507840 + }, + { + "epoch": 1.02, + "learning_rate": 2.5305693992844433e-05, + "loss": 3.4746, + "step": 1508352 + }, + { + "epoch": 1.02, + "learning_rate": 2.5297308045333913e-05, + "loss": 3.4817, + "step": 1508864 + }, + { + "epoch": 1.02, + "learning_rate": 2.5288922097823386e-05, + "loss": 3.488, + "step": 1509376 + }, + { + "epoch": 1.02, + "learning_rate": 2.52805525291166e-05, + "loss": 3.4795, + "step": 1509888 + }, + { + "epoch": 1.02, + "learning_rate": 2.527216658160608e-05, + "loss": 3.4742, + "step": 1510400 + }, + { + "epoch": 1.02, + "learning_rate": 2.526378063409556e-05, + "loss": 3.4834, + "step": 1510912 + }, + { + "epoch": 1.02, + "learning_rate": 2.5255394686585038e-05, + "loss": 3.4809, + "step": 1511424 + }, + { + "epoch": 1.02, + "learning_rate": 2.5247025117878254e-05, + "loss": 3.4667, + "step": 1511936 + }, + { + "epoch": 1.02, + "learning_rate": 2.5238639170367734e-05, + "loss": 3.4852, + "step": 1512448 + }, + { + "epoch": 1.02, + "learning_rate": 2.5230253222857214e-05, + "loss": 3.4756, + "step": 1512960 + }, + { + "epoch": 1.02, + "learning_rate": 2.5221883654150423e-05, + "loss": 3.4828, + "step": 1513472 + }, + { + "epoch": 1.02, + "learning_rate": 2.5213497706639906e-05, + "loss": 3.4749, + "step": 1513984 + }, + { + "epoch": 1.02, + "learning_rate": 2.5205111759129386e-05, + "loss": 3.4789, + "step": 1514496 + }, + { + "epoch": 1.02, + "learning_rate": 2.519672581161886e-05, + "loss": 3.4651, + "step": 1515008 + }, + { + "epoch": 1.02, + "learning_rate": 2.5188356242912075e-05, + "loss": 3.4776, + "step": 1515520 + }, + { + "epoch": 1.02, + "learning_rate": 2.5179970295401555e-05, + "loss": 3.4731, + "step": 1516032 + }, + { + "epoch": 1.02, + "learning_rate": 2.5171584347891035e-05, + "loss": 3.4797, + "step": 1516544 + }, + { + "epoch": 1.02, + "learning_rate": 2.5163198400380512e-05, + "loss": 3.4878, + "step": 1517056 + }, + { + "epoch": 1.02, + "learning_rate": 2.5154828831673728e-05, + "loss": 3.4822, + "step": 1517568 + }, + { + "epoch": 1.02, + "learning_rate": 2.5146442884163208e-05, + "loss": 3.4685, + "step": 1518080 + }, + { + "epoch": 1.02, + "learning_rate": 2.5138056936652688e-05, + "loss": 3.4802, + "step": 1518592 + }, + { + "epoch": 1.02, + "learning_rate": 2.512967098914216e-05, + "loss": 3.486, + "step": 1519104 + }, + { + "epoch": 1.02, + "learning_rate": 2.5121301420435377e-05, + "loss": 3.4832, + "step": 1519616 + }, + { + "epoch": 1.02, + "learning_rate": 2.511291547292486e-05, + "loss": 3.4854, + "step": 1520128 + }, + { + "epoch": 1.02, + "learning_rate": 2.5104529525414333e-05, + "loss": 3.4739, + "step": 1520640 + }, + { + "epoch": 1.02, + "learning_rate": 2.5096143577903813e-05, + "loss": 3.4763, + "step": 1521152 + }, + { + "epoch": 1.02, + "learning_rate": 2.5087757630393293e-05, + "loss": 3.4879, + "step": 1521664 + }, + { + "epoch": 1.02, + "learning_rate": 2.507938806168651e-05, + "loss": 3.4719, + "step": 1522176 + }, + { + "epoch": 1.02, + "learning_rate": 2.5071002114175986e-05, + "loss": 3.4825, + "step": 1522688 + }, + { + "epoch": 1.02, + "learning_rate": 2.5062616166665465e-05, + "loss": 3.4729, + "step": 1523200 + }, + { + "epoch": 1.02, + "learning_rate": 2.5054230219154945e-05, + "loss": 3.4749, + "step": 1523712 + }, + { + "epoch": 1.02, + "learning_rate": 2.504587702925189e-05, + "loss": 3.4886, + "step": 1524224 + }, + { + "epoch": 1.02, + "learning_rate": 2.503749108174137e-05, + "loss": 3.4809, + "step": 1524736 + }, + { + "epoch": 1.02, + "learning_rate": 2.502910513423085e-05, + "loss": 3.4732, + "step": 1525248 + }, + { + "epoch": 1.02, + "learning_rate": 2.502071918672033e-05, + "loss": 3.4678, + "step": 1525760 + }, + { + "epoch": 1.02, + "learning_rate": 2.5012333239209807e-05, + "loss": 3.4725, + "step": 1526272 + }, + { + "epoch": 1.03, + "eval_loss": 3.852881669998169, + "eval_runtime": 356.0148, + "eval_samples_per_second": 1071.84, + "eval_steps_per_second": 33.496, + "step": 1526400 + }, + { + "epoch": 0.0, + "learning_rate": 2.5003947291699287e-05, + "loss": 3.4614, + "step": 1526784 + }, + { + "epoch": 0.0, + "learning_rate": 2.499556134418877e-05, + "loss": 3.4801, + "step": 1527296 + }, + { + "epoch": 0.0, + "learning_rate": 2.498717539667825e-05, + "loss": 3.4832, + "step": 1527808 + }, + { + "epoch": 0.0, + "learning_rate": 2.4978789449167727e-05, + "loss": 3.4769, + "step": 1528320 + }, + { + "epoch": 0.0, + "learning_rate": 2.497041988046094e-05, + "loss": 3.4945, + "step": 1528832 + }, + { + "epoch": 0.0, + "learning_rate": 2.4962033932950423e-05, + "loss": 3.4742, + "step": 1529344 + }, + { + "epoch": 0.0, + "learning_rate": 2.49536479854399e-05, + "loss": 3.4763, + "step": 1529856 + }, + { + "epoch": 0.0, + "learning_rate": 2.494526203792938e-05, + "loss": 3.468, + "step": 1530368 + }, + { + "epoch": 0.0, + "learning_rate": 2.493689246922259e-05, + "loss": 3.4754, + "step": 1530880 + }, + { + "epoch": 0.0, + "learning_rate": 2.492850652171207e-05, + "loss": 3.4794, + "step": 1531392 + }, + { + "epoch": 0.0, + "learning_rate": 2.492012057420155e-05, + "loss": 3.4753, + "step": 1531904 + }, + { + "epoch": 0.0, + "learning_rate": 2.491173462669103e-05, + "loss": 3.4844, + "step": 1532416 + }, + { + "epoch": 0.0, + "learning_rate": 2.4903365057984244e-05, + "loss": 3.4661, + "step": 1532928 + }, + { + "epoch": 0.0, + "learning_rate": 2.4894979110473724e-05, + "loss": 3.466, + "step": 1533440 + }, + { + "epoch": 0.0, + "learning_rate": 2.48865931629632e-05, + "loss": 3.4678, + "step": 1533952 + }, + { + "epoch": 0.0, + "learning_rate": 2.487820721545268e-05, + "loss": 3.4689, + "step": 1534464 + }, + { + "epoch": 0.0, + "learning_rate": 2.4869837646745893e-05, + "loss": 3.4788, + "step": 1534976 + }, + { + "epoch": 0.0, + "learning_rate": 2.4861451699235373e-05, + "loss": 3.4702, + "step": 1535488 + }, + { + "epoch": 0.0, + "learning_rate": 2.4853065751724853e-05, + "loss": 3.4773, + "step": 1536000 + }, + { + "epoch": 0.0, + "learning_rate": 2.4844679804214333e-05, + "loss": 3.497, + "step": 1536512 + }, + { + "epoch": 0.0, + "learning_rate": 2.4836310235507545e-05, + "loss": 3.475, + "step": 1537024 + }, + { + "epoch": 0.0, + "learning_rate": 2.4827924287997022e-05, + "loss": 3.4746, + "step": 1537536 + }, + { + "epoch": 0.0, + "learning_rate": 2.4819538340486502e-05, + "loss": 3.4751, + "step": 1538048 + }, + { + "epoch": 0.0, + "learning_rate": 2.4811152392975985e-05, + "loss": 3.4768, + "step": 1538560 + }, + { + "epoch": 0.0, + "learning_rate": 2.4802782824269194e-05, + "loss": 3.4671, + "step": 1539072 + }, + { + "epoch": 0.0, + "learning_rate": 2.4794396876758674e-05, + "loss": 3.4795, + "step": 1539584 + }, + { + "epoch": 0.0, + "learning_rate": 2.4786010929248154e-05, + "loss": 3.4742, + "step": 1540096 + }, + { + "epoch": 0.0, + "learning_rate": 2.4777624981737634e-05, + "loss": 3.4739, + "step": 1540608 + }, + { + "epoch": 0.0, + "learning_rate": 2.4769255413030847e-05, + "loss": 3.4619, + "step": 1541120 + }, + { + "epoch": 0.0, + "learning_rate": 2.4760869465520326e-05, + "loss": 3.4662, + "step": 1541632 + }, + { + "epoch": 0.01, + "learning_rate": 2.4752483518009806e-05, + "loss": 3.4748, + "step": 1542144 + }, + { + "epoch": 0.01, + "learning_rate": 2.4744097570499286e-05, + "loss": 3.4742, + "step": 1542656 + }, + { + "epoch": 0.01, + "learning_rate": 2.4735728001792495e-05, + "loss": 3.4857, + "step": 1543168 + }, + { + "epoch": 0.01, + "learning_rate": 2.4727342054281975e-05, + "loss": 3.4744, + "step": 1543680 + }, + { + "epoch": 0.01, + "learning_rate": 2.4718956106771455e-05, + "loss": 3.4612, + "step": 1544192 + }, + { + "epoch": 0.01, + "learning_rate": 2.471057015926094e-05, + "loss": 3.4767, + "step": 1544704 + }, + { + "epoch": 0.01, + "learning_rate": 2.4702200590554148e-05, + "loss": 3.4728, + "step": 1545216 + }, + { + "epoch": 0.01, + "learning_rate": 2.4693814643043628e-05, + "loss": 3.4594, + "step": 1545728 + }, + { + "epoch": 0.01, + "learning_rate": 2.4685428695533108e-05, + "loss": 3.4606, + "step": 1546240 + }, + { + "epoch": 0.01, + "learning_rate": 2.4677042748022588e-05, + "loss": 3.4704, + "step": 1546752 + }, + { + "epoch": 0.01, + "learning_rate": 2.46686731793158e-05, + "loss": 3.4604, + "step": 1547264 + }, + { + "epoch": 0.01, + "learning_rate": 2.466028723180528e-05, + "loss": 3.4855, + "step": 1547776 + }, + { + "epoch": 0.01, + "learning_rate": 2.465190128429476e-05, + "loss": 3.4709, + "step": 1548288 + }, + { + "epoch": 0.01, + "learning_rate": 2.464351533678424e-05, + "loss": 3.471, + "step": 1548800 + }, + { + "epoch": 0.01, + "learning_rate": 2.463514576807745e-05, + "loss": 3.4766, + "step": 1549312 + }, + { + "epoch": 0.01, + "learning_rate": 2.462675982056693e-05, + "loss": 3.4734, + "step": 1549824 + }, + { + "epoch": 0.01, + "learning_rate": 2.461837387305641e-05, + "loss": 3.4704, + "step": 1550336 + }, + { + "epoch": 0.01, + "learning_rate": 2.4609987925545892e-05, + "loss": 3.4576, + "step": 1550848 + }, + { + "epoch": 0.01, + "learning_rate": 2.46016183568391e-05, + "loss": 3.4462, + "step": 1551360 + }, + { + "epoch": 0.01, + "learning_rate": 2.459323240932858e-05, + "loss": 3.4881, + "step": 1551872 + }, + { + "epoch": 0.01, + "learning_rate": 2.458484646181806e-05, + "loss": 3.4663, + "step": 1552384 + }, + { + "epoch": 0.01, + "learning_rate": 2.457646051430754e-05, + "loss": 3.4688, + "step": 1552896 + }, + { + "epoch": 0.01, + "learning_rate": 2.4568090945600754e-05, + "loss": 3.4655, + "step": 1553408 + }, + { + "epoch": 0.01, + "learning_rate": 2.4559704998090234e-05, + "loss": 3.4629, + "step": 1553920 + }, + { + "epoch": 0.01, + "learning_rate": 2.4551319050579714e-05, + "loss": 3.4576, + "step": 1554432 + }, + { + "epoch": 0.01, + "learning_rate": 2.4542933103069194e-05, + "loss": 3.472, + "step": 1554944 + }, + { + "epoch": 0.01, + "learning_rate": 2.4534563534362403e-05, + "loss": 3.4701, + "step": 1555456 + }, + { + "epoch": 0.01, + "learning_rate": 2.4526177586851883e-05, + "loss": 3.4654, + "step": 1555968 + }, + { + "epoch": 0.01, + "learning_rate": 2.4517791639341363e-05, + "loss": 3.4848, + "step": 1556480 + }, + { + "epoch": 0.01, + "learning_rate": 2.4509405691830846e-05, + "loss": 3.4555, + "step": 1556992 + }, + { + "epoch": 0.01, + "learning_rate": 2.4501036123124055e-05, + "loss": 3.4568, + "step": 1557504 + }, + { + "epoch": 0.01, + "learning_rate": 2.4492650175613535e-05, + "loss": 3.4804, + "step": 1558016 + }, + { + "epoch": 0.01, + "learning_rate": 2.4484264228103015e-05, + "loss": 3.4514, + "step": 1558528 + }, + { + "epoch": 0.01, + "learning_rate": 2.4475878280592495e-05, + "loss": 3.4548, + "step": 1559040 + }, + { + "epoch": 0.01, + "learning_rate": 2.4467508711885708e-05, + "loss": 3.4764, + "step": 1559552 + }, + { + "epoch": 0.01, + "learning_rate": 2.4459122764375187e-05, + "loss": 3.4766, + "step": 1560064 + }, + { + "epoch": 0.01, + "learning_rate": 2.4450736816864667e-05, + "loss": 3.4576, + "step": 1560576 + }, + { + "epoch": 0.01, + "learning_rate": 2.4442350869354147e-05, + "loss": 3.4675, + "step": 1561088 + }, + { + "epoch": 0.01, + "learning_rate": 2.4433981300647356e-05, + "loss": 3.4547, + "step": 1561600 + }, + { + "epoch": 0.01, + "learning_rate": 2.4425595353136836e-05, + "loss": 3.4702, + "step": 1562112 + }, + { + "epoch": 0.01, + "learning_rate": 2.4417209405626316e-05, + "loss": 3.4651, + "step": 1562624 + }, + { + "epoch": 0.01, + "learning_rate": 2.4408823458115796e-05, + "loss": 3.4705, + "step": 1563136 + }, + { + "epoch": 0.01, + "learning_rate": 2.440045388940901e-05, + "loss": 3.4645, + "step": 1563648 + }, + { + "epoch": 0.01, + "learning_rate": 2.439206794189849e-05, + "loss": 3.4764, + "step": 1564160 + }, + { + "epoch": 0.01, + "learning_rate": 2.438368199438797e-05, + "loss": 3.4807, + "step": 1564672 + }, + { + "epoch": 0.01, + "learning_rate": 2.4375296046877445e-05, + "loss": 3.458, + "step": 1565184 + }, + { + "epoch": 0.01, + "learning_rate": 2.436692647817066e-05, + "loss": 3.4686, + "step": 1565696 + }, + { + "epoch": 0.01, + "learning_rate": 2.435854053066014e-05, + "loss": 3.4755, + "step": 1566208 + }, + { + "epoch": 0.01, + "learning_rate": 2.435015458314962e-05, + "loss": 3.4542, + "step": 1566720 + }, + { + "epoch": 0.01, + "learning_rate": 2.4341768635639098e-05, + "loss": 3.4786, + "step": 1567232 + }, + { + "epoch": 0.01, + "learning_rate": 2.433339906693231e-05, + "loss": 3.4768, + "step": 1567744 + }, + { + "epoch": 0.01, + "learning_rate": 2.432501311942179e-05, + "loss": 3.4754, + "step": 1568256 + }, + { + "epoch": 0.01, + "learning_rate": 2.431662717191127e-05, + "loss": 3.4781, + "step": 1568768 + }, + { + "epoch": 0.01, + "learning_rate": 2.430824122440075e-05, + "loss": 3.4628, + "step": 1569280 + }, + { + "epoch": 0.01, + "learning_rate": 2.4299871655693962e-05, + "loss": 3.4594, + "step": 1569792 + }, + { + "epoch": 0.01, + "learning_rate": 2.4291485708183442e-05, + "loss": 3.4666, + "step": 1570304 + }, + { + "epoch": 0.01, + "learning_rate": 2.428309976067292e-05, + "loss": 3.4751, + "step": 1570816 + }, + { + "epoch": 0.01, + "learning_rate": 2.42747138131624e-05, + "loss": 3.4702, + "step": 1571328 + }, + { + "epoch": 0.01, + "learning_rate": 2.4266344244455615e-05, + "loss": 3.4677, + "step": 1571840 + }, + { + "epoch": 0.02, + "learning_rate": 2.4257958296945095e-05, + "loss": 3.4653, + "step": 1572352 + }, + { + "epoch": 0.02, + "learning_rate": 2.424957234943457e-05, + "loss": 3.4746, + "step": 1572864 + }, + { + "epoch": 0.02, + "learning_rate": 2.424118640192405e-05, + "loss": 3.4603, + "step": 1573376 + }, + { + "epoch": 0.02, + "learning_rate": 2.4232816833217264e-05, + "loss": 3.4641, + "step": 1573888 + }, + { + "epoch": 0.02, + "learning_rate": 2.422443088570674e-05, + "loss": 3.4696, + "step": 1574400 + }, + { + "epoch": 0.02, + "learning_rate": 2.4216044938196224e-05, + "loss": 3.4812, + "step": 1574912 + }, + { + "epoch": 0.02, + "learning_rate": 2.4207658990685704e-05, + "loss": 3.4727, + "step": 1575424 + }, + { + "epoch": 0.02, + "learning_rate": 2.4199289421978916e-05, + "loss": 3.4542, + "step": 1575936 + }, + { + "epoch": 0.02, + "learning_rate": 2.4190903474468393e-05, + "loss": 3.4635, + "step": 1576448 + }, + { + "epoch": 0.02, + "learning_rate": 2.4182517526957873e-05, + "loss": 3.4693, + "step": 1576960 + }, + { + "epoch": 0.02, + "learning_rate": 2.4174131579447353e-05, + "loss": 3.4743, + "step": 1577472 + }, + { + "epoch": 0.02, + "learning_rate": 2.4165762010740565e-05, + "loss": 3.4658, + "step": 1577984 + }, + { + "epoch": 0.02, + "learning_rate": 2.4157376063230045e-05, + "loss": 3.4682, + "step": 1578496 + }, + { + "epoch": 0.02, + "learning_rate": 2.4148990115719525e-05, + "loss": 3.4551, + "step": 1579008 + }, + { + "epoch": 0.02, + "learning_rate": 2.4140604168209005e-05, + "loss": 3.4642, + "step": 1579520 + }, + { + "epoch": 0.02, + "learning_rate": 2.4132234599502214e-05, + "loss": 3.4588, + "step": 1580032 + }, + { + "epoch": 0.02, + "learning_rate": 2.4123848651991694e-05, + "loss": 3.468, + "step": 1580544 + }, + { + "epoch": 0.02, + "learning_rate": 2.4115462704481177e-05, + "loss": 3.4495, + "step": 1581056 + }, + { + "epoch": 0.02, + "learning_rate": 2.4107076756970657e-05, + "loss": 3.4822, + "step": 1581568 + }, + { + "epoch": 0.02, + "learning_rate": 2.4098707188263866e-05, + "loss": 3.4555, + "step": 1582080 + }, + { + "epoch": 0.02, + "learning_rate": 2.4090321240753346e-05, + "loss": 3.4699, + "step": 1582592 + }, + { + "epoch": 0.02, + "learning_rate": 2.4081935293242826e-05, + "loss": 3.4601, + "step": 1583104 + }, + { + "epoch": 0.02, + "learning_rate": 2.4073549345732306e-05, + "loss": 3.4644, + "step": 1583616 + }, + { + "epoch": 0.02, + "learning_rate": 2.406517977702552e-05, + "loss": 3.4623, + "step": 1584128 + }, + { + "epoch": 0.02, + "learning_rate": 2.4056793829515e-05, + "loss": 3.4667, + "step": 1584640 + }, + { + "epoch": 0.02, + "learning_rate": 2.404840788200448e-05, + "loss": 3.4668, + "step": 1585152 + }, + { + "epoch": 0.02, + "learning_rate": 2.404002193449396e-05, + "loss": 3.4757, + "step": 1585664 + }, + { + "epoch": 0.02, + "learning_rate": 2.4031652365787168e-05, + "loss": 3.4649, + "step": 1586176 + }, + { + "epoch": 0.02, + "learning_rate": 2.4023266418276648e-05, + "loss": 3.4631, + "step": 1586688 + }, + { + "epoch": 0.02, + "learning_rate": 2.401488047076613e-05, + "loss": 3.4705, + "step": 1587200 + }, + { + "epoch": 0.02, + "learning_rate": 2.400649452325561e-05, + "loss": 3.4727, + "step": 1587712 + }, + { + "epoch": 0.02, + "learning_rate": 2.399812495454882e-05, + "loss": 3.4521, + "step": 1588224 + }, + { + "epoch": 0.02, + "learning_rate": 2.39897390070383e-05, + "loss": 3.4744, + "step": 1588736 + }, + { + "epoch": 0.02, + "learning_rate": 2.398135305952778e-05, + "loss": 3.4617, + "step": 1589248 + }, + { + "epoch": 0.02, + "learning_rate": 2.397296711201726e-05, + "loss": 3.4722, + "step": 1589760 + }, + { + "epoch": 0.02, + "learning_rate": 2.3964597543310472e-05, + "loss": 3.4622, + "step": 1590272 + }, + { + "epoch": 0.02, + "learning_rate": 2.3956211595799952e-05, + "loss": 3.4685, + "step": 1590784 + }, + { + "epoch": 0.02, + "learning_rate": 2.3947825648289432e-05, + "loss": 3.4574, + "step": 1591296 + }, + { + "epoch": 0.02, + "learning_rate": 2.3939439700778912e-05, + "loss": 3.4621, + "step": 1591808 + }, + { + "epoch": 0.02, + "learning_rate": 2.393107013207212e-05, + "loss": 3.4652, + "step": 1592320 + }, + { + "epoch": 0.02, + "learning_rate": 2.39226841845616e-05, + "loss": 3.4667, + "step": 1592832 + }, + { + "epoch": 0.02, + "learning_rate": 2.3914298237051085e-05, + "loss": 3.472, + "step": 1593344 + }, + { + "epoch": 0.02, + "learning_rate": 2.3905912289540565e-05, + "loss": 3.4738, + "step": 1593856 + }, + { + "epoch": 0.02, + "learning_rate": 2.3897542720833774e-05, + "loss": 3.4561, + "step": 1594368 + }, + { + "epoch": 0.02, + "learning_rate": 2.3889156773323254e-05, + "loss": 3.4685, + "step": 1594880 + }, + { + "epoch": 0.02, + "learning_rate": 2.3880770825812734e-05, + "loss": 3.4731, + "step": 1595392 + }, + { + "epoch": 0.02, + "learning_rate": 2.3872384878302214e-05, + "loss": 3.4695, + "step": 1595904 + }, + { + "epoch": 0.02, + "learning_rate": 2.3864015309595426e-05, + "loss": 3.4693, + "step": 1596416 + }, + { + "epoch": 0.02, + "learning_rate": 2.3855629362084906e-05, + "loss": 3.4676, + "step": 1596928 + }, + { + "epoch": 0.02, + "learning_rate": 2.3847243414574386e-05, + "loss": 3.4614, + "step": 1597440 + }, + { + "epoch": 0.02, + "learning_rate": 2.3838857467063866e-05, + "loss": 3.4794, + "step": 1597952 + }, + { + "epoch": 0.02, + "learning_rate": 2.3830487898357075e-05, + "loss": 3.4592, + "step": 1598464 + }, + { + "epoch": 0.02, + "learning_rate": 2.3822101950846555e-05, + "loss": 3.471, + "step": 1598976 + }, + { + "epoch": 0.02, + "learning_rate": 2.381371600333604e-05, + "loss": 3.4626, + "step": 1599488 + }, + { + "epoch": 0.02, + "learning_rate": 2.380533005582552e-05, + "loss": 3.4612, + "step": 1600000 + }, + { + "epoch": 0.02, + "learning_rate": 2.3796960487118727e-05, + "loss": 3.4761, + "step": 1600512 + }, + { + "epoch": 0.02, + "learning_rate": 2.3788574539608207e-05, + "loss": 3.4703, + "step": 1601024 + }, + { + "epoch": 0.02, + "learning_rate": 2.3780188592097687e-05, + "loss": 3.4617, + "step": 1601536 + }, + { + "epoch": 0.02, + "learning_rate": 2.3771802644587164e-05, + "loss": 3.4518, + "step": 1602048 + }, + { + "epoch": 0.02, + "learning_rate": 2.3763416697076647e-05, + "loss": 3.4618, + "step": 1602560 + }, + { + "epoch": 0.03, + "eval_loss": 3.8540990352630615, + "eval_runtime": 306.4357, + "eval_samples_per_second": 1245.256, + "eval_steps_per_second": 38.915, + "step": 1602720 + }, + { + "epoch": 1.0, + "learning_rate": 2.3755030749566127e-05, + "loss": 3.4574, + "step": 1603072 + }, + { + "epoch": 1.0, + "learning_rate": 2.3746644802055607e-05, + "loss": 3.4643, + "step": 1603584 + }, + { + "epoch": 1.0, + "learning_rate": 2.3738258854545087e-05, + "loss": 3.4756, + "step": 1604096 + }, + { + "epoch": 1.0, + "learning_rate": 2.3729889285838296e-05, + "loss": 3.4664, + "step": 1604608 + }, + { + "epoch": 1.0, + "learning_rate": 2.3721503338327776e-05, + "loss": 3.4816, + "step": 1605120 + }, + { + "epoch": 1.0, + "learning_rate": 2.3713117390817256e-05, + "loss": 3.4613, + "step": 1605632 + }, + { + "epoch": 1.0, + "learning_rate": 2.370473144330674e-05, + "loss": 3.4597, + "step": 1606144 + }, + { + "epoch": 1.0, + "learning_rate": 2.369636187459995e-05, + "loss": 3.4595, + "step": 1606656 + }, + { + "epoch": 1.0, + "learning_rate": 2.368797592708943e-05, + "loss": 3.4607, + "step": 1607168 + }, + { + "epoch": 1.0, + "learning_rate": 2.367958997957891e-05, + "loss": 3.467, + "step": 1607680 + }, + { + "epoch": 1.0, + "learning_rate": 2.367120403206839e-05, + "loss": 3.467, + "step": 1608192 + }, + { + "epoch": 1.0, + "learning_rate": 2.36628344633616e-05, + "loss": 3.4669, + "step": 1608704 + }, + { + "epoch": 1.0, + "learning_rate": 2.365444851585108e-05, + "loss": 3.4599, + "step": 1609216 + }, + { + "epoch": 1.0, + "learning_rate": 2.364606256834056e-05, + "loss": 3.4547, + "step": 1609728 + }, + { + "epoch": 1.0, + "learning_rate": 2.363767662083004e-05, + "loss": 3.4564, + "step": 1610240 + }, + { + "epoch": 1.0, + "learning_rate": 2.362930705212325e-05, + "loss": 3.4569, + "step": 1610752 + }, + { + "epoch": 1.0, + "learning_rate": 2.362092110461273e-05, + "loss": 3.464, + "step": 1611264 + }, + { + "epoch": 1.0, + "learning_rate": 2.361253515710221e-05, + "loss": 3.4607, + "step": 1611776 + }, + { + "epoch": 1.0, + "learning_rate": 2.3604149209591693e-05, + "loss": 3.466, + "step": 1612288 + }, + { + "epoch": 1.0, + "learning_rate": 2.3595779640884902e-05, + "loss": 3.4808, + "step": 1612800 + }, + { + "epoch": 1.0, + "learning_rate": 2.3587393693374382e-05, + "loss": 3.4675, + "step": 1613312 + }, + { + "epoch": 1.0, + "learning_rate": 2.3579007745863862e-05, + "loss": 3.4584, + "step": 1613824 + }, + { + "epoch": 1.0, + "learning_rate": 2.3570621798353342e-05, + "loss": 3.4656, + "step": 1614336 + }, + { + "epoch": 1.0, + "learning_rate": 2.3562252229646555e-05, + "loss": 3.462, + "step": 1614848 + }, + { + "epoch": 1.0, + "learning_rate": 2.3553866282136035e-05, + "loss": 3.4568, + "step": 1615360 + }, + { + "epoch": 1.0, + "learning_rate": 2.3545480334625515e-05, + "loss": 3.469, + "step": 1615872 + }, + { + "epoch": 1.0, + "learning_rate": 2.3537094387114994e-05, + "loss": 3.463, + "step": 1616384 + }, + { + "epoch": 1.0, + "learning_rate": 2.3528724818408204e-05, + "loss": 3.4648, + "step": 1616896 + }, + { + "epoch": 1.0, + "learning_rate": 2.3520338870897684e-05, + "loss": 3.4554, + "step": 1617408 + }, + { + "epoch": 1.0, + "learning_rate": 2.3511952923387163e-05, + "loss": 3.4494, + "step": 1617920 + }, + { + "epoch": 1.01, + "learning_rate": 2.3503566975876643e-05, + "loss": 3.4619, + "step": 1618432 + }, + { + "epoch": 1.01, + "learning_rate": 2.3495197407169856e-05, + "loss": 3.4634, + "step": 1618944 + }, + { + "epoch": 1.01, + "learning_rate": 2.3486811459659336e-05, + "loss": 3.4708, + "step": 1619456 + }, + { + "epoch": 1.01, + "learning_rate": 2.3478425512148816e-05, + "loss": 3.4632, + "step": 1619968 + }, + { + "epoch": 1.01, + "learning_rate": 2.3470039564638292e-05, + "loss": 3.4516, + "step": 1620480 + }, + { + "epoch": 1.01, + "learning_rate": 2.3461669995931508e-05, + "loss": 3.466, + "step": 1620992 + }, + { + "epoch": 1.01, + "learning_rate": 2.3453284048420988e-05, + "loss": 3.461, + "step": 1621504 + }, + { + "epoch": 1.01, + "learning_rate": 2.3444898100910468e-05, + "loss": 3.4455, + "step": 1622016 + }, + { + "epoch": 1.01, + "learning_rate": 2.3436512153399945e-05, + "loss": 3.4561, + "step": 1622528 + }, + { + "epoch": 1.01, + "learning_rate": 2.3428142584693157e-05, + "loss": 3.4571, + "step": 1623040 + }, + { + "epoch": 1.01, + "learning_rate": 2.3419756637182637e-05, + "loss": 3.4537, + "step": 1623552 + }, + { + "epoch": 1.01, + "learning_rate": 2.3411370689672117e-05, + "loss": 3.4719, + "step": 1624064 + }, + { + "epoch": 1.01, + "learning_rate": 2.3402984742161597e-05, + "loss": 3.4612, + "step": 1624576 + }, + { + "epoch": 1.01, + "learning_rate": 2.339461517345481e-05, + "loss": 3.4575, + "step": 1625088 + }, + { + "epoch": 1.01, + "learning_rate": 2.338622922594429e-05, + "loss": 3.4617, + "step": 1625600 + }, + { + "epoch": 1.01, + "learning_rate": 2.3377843278433766e-05, + "loss": 3.4606, + "step": 1626112 + }, + { + "epoch": 1.01, + "learning_rate": 2.3369457330923246e-05, + "loss": 3.4617, + "step": 1626624 + }, + { + "epoch": 1.01, + "learning_rate": 2.3361087762216462e-05, + "loss": 3.4449, + "step": 1627136 + }, + { + "epoch": 1.01, + "learning_rate": 2.3352701814705942e-05, + "loss": 3.4321, + "step": 1627648 + }, + { + "epoch": 1.01, + "learning_rate": 2.334431586719542e-05, + "loss": 3.4771, + "step": 1628160 + }, + { + "epoch": 1.01, + "learning_rate": 2.33359299196849e-05, + "loss": 3.4535, + "step": 1628672 + }, + { + "epoch": 1.01, + "learning_rate": 2.332756035097811e-05, + "loss": 3.4641, + "step": 1629184 + }, + { + "epoch": 1.01, + "learning_rate": 2.3319174403467587e-05, + "loss": 3.4515, + "step": 1629696 + }, + { + "epoch": 1.01, + "learning_rate": 2.331078845595707e-05, + "loss": 3.4512, + "step": 1630208 + }, + { + "epoch": 1.01, + "learning_rate": 2.330240250844655e-05, + "loss": 3.4477, + "step": 1630720 + }, + { + "epoch": 1.01, + "learning_rate": 2.3294032939739763e-05, + "loss": 3.4545, + "step": 1631232 + }, + { + "epoch": 1.01, + "learning_rate": 2.328564699222924e-05, + "loss": 3.4602, + "step": 1631744 + }, + { + "epoch": 1.01, + "learning_rate": 2.327726104471872e-05, + "loss": 3.4498, + "step": 1632256 + }, + { + "epoch": 1.01, + "learning_rate": 2.32688750972082e-05, + "loss": 3.4745, + "step": 1632768 + }, + { + "epoch": 1.01, + "learning_rate": 2.3260505528501416e-05, + "loss": 3.4482, + "step": 1633280 + }, + { + "epoch": 1.01, + "learning_rate": 2.3252119580990892e-05, + "loss": 3.4425, + "step": 1633792 + }, + { + "epoch": 1.01, + "learning_rate": 2.3243733633480372e-05, + "loss": 3.466, + "step": 1634304 + }, + { + "epoch": 1.01, + "learning_rate": 2.3235347685969852e-05, + "loss": 3.4424, + "step": 1634816 + }, + { + "epoch": 1.01, + "learning_rate": 2.322697811726306e-05, + "loss": 3.4395, + "step": 1635328 + }, + { + "epoch": 1.01, + "learning_rate": 2.321859216975254e-05, + "loss": 3.4627, + "step": 1635840 + }, + { + "epoch": 1.01, + "learning_rate": 2.3210206222242024e-05, + "loss": 3.4619, + "step": 1636352 + }, + { + "epoch": 1.01, + "learning_rate": 2.3201820274731504e-05, + "loss": 3.4491, + "step": 1636864 + }, + { + "epoch": 1.01, + "learning_rate": 2.3193450706024714e-05, + "loss": 3.4576, + "step": 1637376 + }, + { + "epoch": 1.01, + "learning_rate": 2.3185064758514193e-05, + "loss": 3.4428, + "step": 1637888 + }, + { + "epoch": 1.01, + "learning_rate": 2.3176678811003673e-05, + "loss": 3.4595, + "step": 1638400 + }, + { + "epoch": 1.01, + "learning_rate": 2.3168292863493153e-05, + "loss": 3.4537, + "step": 1638912 + }, + { + "epoch": 1.01, + "learning_rate": 2.3159923294786366e-05, + "loss": 3.4621, + "step": 1639424 + }, + { + "epoch": 1.01, + "learning_rate": 2.3151537347275846e-05, + "loss": 3.456, + "step": 1639936 + }, + { + "epoch": 1.01, + "learning_rate": 2.3143151399765326e-05, + "loss": 3.4608, + "step": 1640448 + }, + { + "epoch": 1.01, + "learning_rate": 2.3134765452254806e-05, + "loss": 3.4688, + "step": 1640960 + }, + { + "epoch": 1.01, + "learning_rate": 2.3126395883548015e-05, + "loss": 3.4449, + "step": 1641472 + }, + { + "epoch": 1.01, + "learning_rate": 2.3118009936037495e-05, + "loss": 3.4606, + "step": 1641984 + }, + { + "epoch": 1.01, + "learning_rate": 2.3109623988526978e-05, + "loss": 3.4625, + "step": 1642496 + }, + { + "epoch": 1.01, + "learning_rate": 2.3101238041016458e-05, + "loss": 3.4459, + "step": 1643008 + }, + { + "epoch": 1.01, + "learning_rate": 2.3092868472309667e-05, + "loss": 3.4674, + "step": 1643520 + }, + { + "epoch": 1.01, + "learning_rate": 2.3084482524799147e-05, + "loss": 3.4672, + "step": 1644032 + }, + { + "epoch": 1.01, + "learning_rate": 2.3076096577288627e-05, + "loss": 3.4635, + "step": 1644544 + }, + { + "epoch": 1.01, + "learning_rate": 2.3067710629778107e-05, + "loss": 3.473, + "step": 1645056 + }, + { + "epoch": 1.01, + "learning_rate": 2.305934106107132e-05, + "loss": 3.4486, + "step": 1645568 + }, + { + "epoch": 1.01, + "learning_rate": 2.30509551135608e-05, + "loss": 3.4476, + "step": 1646080 + }, + { + "epoch": 1.01, + "learning_rate": 2.304256916605028e-05, + "loss": 3.4558, + "step": 1646592 + }, + { + "epoch": 1.01, + "learning_rate": 2.303418321853976e-05, + "loss": 3.4608, + "step": 1647104 + }, + { + "epoch": 1.01, + "learning_rate": 2.302581364983297e-05, + "loss": 3.4621, + "step": 1647616 + }, + { + "epoch": 1.01, + "learning_rate": 2.301742770232245e-05, + "loss": 3.4557, + "step": 1648128 + }, + { + "epoch": 1.02, + "learning_rate": 2.3009041754811932e-05, + "loss": 3.4531, + "step": 1648640 + }, + { + "epoch": 1.02, + "learning_rate": 2.3000655807301412e-05, + "loss": 3.4636, + "step": 1649152 + }, + { + "epoch": 1.02, + "learning_rate": 2.299228623859462e-05, + "loss": 3.4503, + "step": 1649664 + }, + { + "epoch": 1.02, + "learning_rate": 2.29839002910841e-05, + "loss": 3.4506, + "step": 1650176 + }, + { + "epoch": 1.02, + "learning_rate": 2.297551434357358e-05, + "loss": 3.4591, + "step": 1650688 + }, + { + "epoch": 1.02, + "learning_rate": 2.296712839606306e-05, + "loss": 3.4718, + "step": 1651200 + }, + { + "epoch": 1.02, + "learning_rate": 2.2958758827356273e-05, + "loss": 3.4641, + "step": 1651712 + }, + { + "epoch": 1.02, + "learning_rate": 2.2950372879845753e-05, + "loss": 3.4414, + "step": 1652224 + }, + { + "epoch": 1.02, + "learning_rate": 2.2941986932335233e-05, + "loss": 3.4532, + "step": 1652736 + }, + { + "epoch": 1.02, + "learning_rate": 2.2933600984824713e-05, + "loss": 3.4586, + "step": 1653248 + }, + { + "epoch": 1.02, + "learning_rate": 2.2925231416117922e-05, + "loss": 3.4615, + "step": 1653760 + }, + { + "epoch": 1.02, + "learning_rate": 2.2916845468607402e-05, + "loss": 3.4576, + "step": 1654272 + }, + { + "epoch": 1.02, + "learning_rate": 2.2908459521096885e-05, + "loss": 3.4566, + "step": 1654784 + }, + { + "epoch": 1.02, + "learning_rate": 2.2900073573586365e-05, + "loss": 3.4414, + "step": 1655296 + }, + { + "epoch": 1.02, + "learning_rate": 2.2891704004879575e-05, + "loss": 3.451, + "step": 1655808 + }, + { + "epoch": 1.02, + "learning_rate": 2.2883318057369054e-05, + "loss": 3.4533, + "step": 1656320 + }, + { + "epoch": 1.02, + "learning_rate": 2.2874932109858534e-05, + "loss": 3.4563, + "step": 1656832 + }, + { + "epoch": 1.02, + "learning_rate": 2.286654616234801e-05, + "loss": 3.4377, + "step": 1657344 + }, + { + "epoch": 1.02, + "learning_rate": 2.2858176593641227e-05, + "loss": 3.4684, + "step": 1657856 + }, + { + "epoch": 1.02, + "learning_rate": 2.2849790646130707e-05, + "loss": 3.4447, + "step": 1658368 + }, + { + "epoch": 1.02, + "learning_rate": 2.2841404698620187e-05, + "loss": 3.4565, + "step": 1658880 + }, + { + "epoch": 1.02, + "learning_rate": 2.2833018751109663e-05, + "loss": 3.4452, + "step": 1659392 + }, + { + "epoch": 1.02, + "learning_rate": 2.2824649182402876e-05, + "loss": 3.458, + "step": 1659904 + }, + { + "epoch": 1.02, + "learning_rate": 2.2816263234892356e-05, + "loss": 3.4511, + "step": 1660416 + }, + { + "epoch": 1.02, + "learning_rate": 2.280787728738184e-05, + "loss": 3.4504, + "step": 1660928 + }, + { + "epoch": 1.02, + "learning_rate": 2.2799491339871316e-05, + "loss": 3.4575, + "step": 1661440 + }, + { + "epoch": 1.02, + "learning_rate": 2.2791121771164528e-05, + "loss": 3.4679, + "step": 1661952 + }, + { + "epoch": 1.02, + "learning_rate": 2.2782735823654008e-05, + "loss": 3.4507, + "step": 1662464 + }, + { + "epoch": 1.02, + "learning_rate": 2.2774349876143485e-05, + "loss": 3.4587, + "step": 1662976 + }, + { + "epoch": 1.02, + "learning_rate": 2.2765963928632965e-05, + "loss": 3.4527, + "step": 1663488 + }, + { + "epoch": 1.02, + "learning_rate": 2.275759435992618e-05, + "loss": 3.4606, + "step": 1664000 + }, + { + "epoch": 1.02, + "learning_rate": 2.274920841241566e-05, + "loss": 3.4472, + "step": 1664512 + }, + { + "epoch": 1.02, + "learning_rate": 2.2740822464905137e-05, + "loss": 3.4622, + "step": 1665024 + }, + { + "epoch": 1.02, + "learning_rate": 2.2732436517394617e-05, + "loss": 3.4504, + "step": 1665536 + }, + { + "epoch": 1.02, + "learning_rate": 2.272406694868783e-05, + "loss": 3.4602, + "step": 1666048 + }, + { + "epoch": 1.02, + "learning_rate": 2.271568100117731e-05, + "loss": 3.4539, + "step": 1666560 + }, + { + "epoch": 1.02, + "learning_rate": 2.270729505366679e-05, + "loss": 3.457, + "step": 1667072 + }, + { + "epoch": 1.02, + "learning_rate": 2.269890910615627e-05, + "loss": 3.4428, + "step": 1667584 + }, + { + "epoch": 1.02, + "learning_rate": 2.2690539537449482e-05, + "loss": 3.4524, + "step": 1668096 + }, + { + "epoch": 1.02, + "learning_rate": 2.268215358993896e-05, + "loss": 3.4532, + "step": 1668608 + }, + { + "epoch": 1.02, + "learning_rate": 2.267376764242844e-05, + "loss": 3.4583, + "step": 1669120 + }, + { + "epoch": 1.02, + "learning_rate": 2.266538169491792e-05, + "loss": 3.4547, + "step": 1669632 + }, + { + "epoch": 1.02, + "learning_rate": 2.2657012126211134e-05, + "loss": 3.4632, + "step": 1670144 + }, + { + "epoch": 1.02, + "learning_rate": 2.264862617870061e-05, + "loss": 3.4458, + "step": 1670656 + }, + { + "epoch": 1.02, + "learning_rate": 2.264024023119009e-05, + "loss": 3.4564, + "step": 1671168 + }, + { + "epoch": 1.02, + "learning_rate": 2.263185428367957e-05, + "loss": 3.4596, + "step": 1671680 + }, + { + "epoch": 1.02, + "learning_rate": 2.2623484714972783e-05, + "loss": 3.4636, + "step": 1672192 + }, + { + "epoch": 1.02, + "learning_rate": 2.2615098767462263e-05, + "loss": 3.4549, + "step": 1672704 + }, + { + "epoch": 1.02, + "learning_rate": 2.2606712819951743e-05, + "loss": 3.4561, + "step": 1673216 + }, + { + "epoch": 1.02, + "learning_rate": 2.2598326872441223e-05, + "loss": 3.4476, + "step": 1673728 + }, + { + "epoch": 1.02, + "learning_rate": 2.2589957303734432e-05, + "loss": 3.471, + "step": 1674240 + }, + { + "epoch": 1.02, + "learning_rate": 2.2581571356223912e-05, + "loss": 3.4467, + "step": 1674752 + }, + { + "epoch": 1.02, + "learning_rate": 2.2573185408713392e-05, + "loss": 3.4587, + "step": 1675264 + }, + { + "epoch": 1.02, + "learning_rate": 2.2564815840006605e-05, + "loss": 3.4506, + "step": 1675776 + }, + { + "epoch": 1.02, + "learning_rate": 2.2556429892496084e-05, + "loss": 3.4516, + "step": 1676288 + }, + { + "epoch": 1.02, + "learning_rate": 2.2548060323789297e-05, + "loss": 3.4626, + "step": 1676800 + }, + { + "epoch": 1.02, + "learning_rate": 2.2539674376278777e-05, + "loss": 3.4566, + "step": 1677312 + }, + { + "epoch": 1.02, + "learning_rate": 2.2531288428768257e-05, + "loss": 3.4574, + "step": 1677824 + }, + { + "epoch": 1.02, + "learning_rate": 2.2522902481257733e-05, + "loss": 3.4363, + "step": 1678336 + }, + { + "epoch": 1.02, + "learning_rate": 2.2514516533747217e-05, + "loss": 3.4538, + "step": 1678848 + }, + { + "epoch": 1.03, + "eval_loss": 3.8553287982940674, + "eval_runtime": 305.9054, + "eval_samples_per_second": 1247.415, + "eval_steps_per_second": 38.983, + "step": 1679040 + }, + { + "epoch": 0.0, + "learning_rate": 2.2506130586236697e-05, + "loss": 3.4452, + "step": 1679360 + }, + { + "epoch": 0.0, + "learning_rate": 2.2497744638726177e-05, + "loss": 3.4508, + "step": 1679872 + }, + { + "epoch": 0.0, + "learning_rate": 2.2489358691215657e-05, + "loss": 3.4609, + "step": 1680384 + }, + { + "epoch": 0.0, + "learning_rate": 2.2480972743705137e-05, + "loss": 3.4572, + "step": 1680896 + }, + { + "epoch": 0.0, + "learning_rate": 2.2472603174998346e-05, + "loss": 3.4681, + "step": 1681408 + }, + { + "epoch": 0.0, + "learning_rate": 2.2464217227487826e-05, + "loss": 3.4503, + "step": 1681920 + }, + { + "epoch": 0.0, + "learning_rate": 2.245583127997731e-05, + "loss": 3.4469, + "step": 1682432 + }, + { + "epoch": 0.0, + "learning_rate": 2.244744533246679e-05, + "loss": 3.4502, + "step": 1682944 + }, + { + "epoch": 0.0, + "learning_rate": 2.2439075763759998e-05, + "loss": 3.448, + "step": 1683456 + }, + { + "epoch": 0.0, + "learning_rate": 2.2430689816249478e-05, + "loss": 3.4586, + "step": 1683968 + }, + { + "epoch": 0.0, + "learning_rate": 2.2422303868738958e-05, + "loss": 3.4504, + "step": 1684480 + }, + { + "epoch": 0.0, + "learning_rate": 2.2413917921228438e-05, + "loss": 3.4567, + "step": 1684992 + }, + { + "epoch": 0.0, + "learning_rate": 2.240554835252165e-05, + "loss": 3.4487, + "step": 1685504 + }, + { + "epoch": 0.0, + "learning_rate": 2.239716240501113e-05, + "loss": 3.444, + "step": 1686016 + }, + { + "epoch": 0.0, + "learning_rate": 2.238877645750061e-05, + "loss": 3.4448, + "step": 1686528 + }, + { + "epoch": 0.0, + "learning_rate": 2.2380390509990087e-05, + "loss": 3.443, + "step": 1687040 + }, + { + "epoch": 0.0, + "learning_rate": 2.23720209412833e-05, + "loss": 3.4546, + "step": 1687552 + }, + { + "epoch": 0.0, + "learning_rate": 2.236363499377278e-05, + "loss": 3.4505, + "step": 1688064 + }, + { + "epoch": 0.0, + "learning_rate": 2.2355249046262263e-05, + "loss": 3.451, + "step": 1688576 + }, + { + "epoch": 0.0, + "learning_rate": 2.234686309875174e-05, + "loss": 3.4668, + "step": 1689088 + }, + { + "epoch": 0.0, + "learning_rate": 2.2338493530044952e-05, + "loss": 3.4611, + "step": 1689600 + }, + { + "epoch": 0.0, + "learning_rate": 2.233010758253443e-05, + "loss": 3.4489, + "step": 1690112 + }, + { + "epoch": 0.0, + "learning_rate": 2.232172163502391e-05, + "loss": 3.4497, + "step": 1690624 + }, + { + "epoch": 0.0, + "learning_rate": 2.2313335687513388e-05, + "loss": 3.4505, + "step": 1691136 + }, + { + "epoch": 0.0, + "learning_rate": 2.2304966118806604e-05, + "loss": 3.4479, + "step": 1691648 + }, + { + "epoch": 0.0, + "learning_rate": 2.2296580171296084e-05, + "loss": 3.4554, + "step": 1692160 + }, + { + "epoch": 0.0, + "learning_rate": 2.228819422378556e-05, + "loss": 3.4517, + "step": 1692672 + }, + { + "epoch": 0.0, + "learning_rate": 2.227980827627504e-05, + "loss": 3.454, + "step": 1693184 + }, + { + "epoch": 0.0, + "learning_rate": 2.2271438707568253e-05, + "loss": 3.4446, + "step": 1693696 + }, + { + "epoch": 0.0, + "learning_rate": 2.2263052760057733e-05, + "loss": 3.4424, + "step": 1694208 + }, + { + "epoch": 0.01, + "learning_rate": 2.2254666812547213e-05, + "loss": 3.4438, + "step": 1694720 + }, + { + "epoch": 0.01, + "learning_rate": 2.2246297243840425e-05, + "loss": 3.453, + "step": 1695232 + }, + { + "epoch": 0.01, + "learning_rate": 2.2237911296329905e-05, + "loss": 3.459, + "step": 1695744 + }, + { + "epoch": 0.01, + "learning_rate": 2.2229525348819382e-05, + "loss": 3.4559, + "step": 1696256 + }, + { + "epoch": 0.01, + "learning_rate": 2.2221139401308862e-05, + "loss": 3.4418, + "step": 1696768 + }, + { + "epoch": 0.01, + "learning_rate": 2.2212769832602078e-05, + "loss": 3.4533, + "step": 1697280 + }, + { + "epoch": 0.01, + "learning_rate": 2.2204383885091558e-05, + "loss": 3.4506, + "step": 1697792 + }, + { + "epoch": 0.01, + "learning_rate": 2.2195997937581034e-05, + "loss": 3.4376, + "step": 1698304 + }, + { + "epoch": 0.01, + "learning_rate": 2.2187611990070514e-05, + "loss": 3.4431, + "step": 1698816 + }, + { + "epoch": 0.01, + "learning_rate": 2.2179242421363727e-05, + "loss": 3.445, + "step": 1699328 + }, + { + "epoch": 0.01, + "learning_rate": 2.2170856473853207e-05, + "loss": 3.4396, + "step": 1699840 + }, + { + "epoch": 0.01, + "learning_rate": 2.2162470526342687e-05, + "loss": 3.4575, + "step": 1700352 + }, + { + "epoch": 0.01, + "learning_rate": 2.2154084578832167e-05, + "loss": 3.4493, + "step": 1700864 + }, + { + "epoch": 0.01, + "learning_rate": 2.214571501012538e-05, + "loss": 3.4502, + "step": 1701376 + }, + { + "epoch": 0.01, + "learning_rate": 2.2137329062614856e-05, + "loss": 3.4518, + "step": 1701888 + }, + { + "epoch": 0.01, + "learning_rate": 2.2128943115104336e-05, + "loss": 3.4485, + "step": 1702400 + }, + { + "epoch": 0.01, + "learning_rate": 2.2120557167593816e-05, + "loss": 3.4533, + "step": 1702912 + }, + { + "epoch": 0.01, + "learning_rate": 2.2112187598887028e-05, + "loss": 3.4368, + "step": 1703424 + }, + { + "epoch": 0.01, + "learning_rate": 2.2103801651376508e-05, + "loss": 3.417, + "step": 1703936 + }, + { + "epoch": 0.01, + "learning_rate": 2.2095415703865988e-05, + "loss": 3.4643, + "step": 1704448 + }, + { + "epoch": 0.01, + "learning_rate": 2.2087029756355468e-05, + "loss": 3.4453, + "step": 1704960 + }, + { + "epoch": 0.01, + "learning_rate": 2.207866018764868e-05, + "loss": 3.4525, + "step": 1705472 + }, + { + "epoch": 0.01, + "learning_rate": 2.2070274240138157e-05, + "loss": 3.4413, + "step": 1705984 + }, + { + "epoch": 0.01, + "learning_rate": 2.206188829262764e-05, + "loss": 3.4393, + "step": 1706496 + }, + { + "epoch": 0.01, + "learning_rate": 2.205350234511712e-05, + "loss": 3.4334, + "step": 1707008 + }, + { + "epoch": 0.01, + "learning_rate": 2.204513277641033e-05, + "loss": 3.4462, + "step": 1707520 + }, + { + "epoch": 0.01, + "learning_rate": 2.203674682889981e-05, + "loss": 3.4531, + "step": 1708032 + }, + { + "epoch": 0.01, + "learning_rate": 2.202836088138929e-05, + "loss": 3.437, + "step": 1708544 + }, + { + "epoch": 0.01, + "learning_rate": 2.201997493387877e-05, + "loss": 3.4615, + "step": 1709056 + }, + { + "epoch": 0.01, + "learning_rate": 2.2011605365171982e-05, + "loss": 3.4408, + "step": 1709568 + }, + { + "epoch": 0.01, + "learning_rate": 2.2003219417661462e-05, + "loss": 3.4323, + "step": 1710080 + }, + { + "epoch": 0.01, + "learning_rate": 2.199483347015094e-05, + "loss": 3.4493, + "step": 1710592 + }, + { + "epoch": 0.01, + "learning_rate": 2.198644752264042e-05, + "loss": 3.4346, + "step": 1711104 + }, + { + "epoch": 0.01, + "learning_rate": 2.197807795393363e-05, + "loss": 3.4274, + "step": 1711616 + }, + { + "epoch": 0.01, + "learning_rate": 2.196969200642311e-05, + "loss": 3.4554, + "step": 1712128 + }, + { + "epoch": 0.01, + "learning_rate": 2.1961306058912594e-05, + "loss": 3.452, + "step": 1712640 + }, + { + "epoch": 0.01, + "learning_rate": 2.1952920111402074e-05, + "loss": 3.4382, + "step": 1713152 + }, + { + "epoch": 0.01, + "learning_rate": 2.1944550542695283e-05, + "loss": 3.4412, + "step": 1713664 + }, + { + "epoch": 0.01, + "learning_rate": 2.1936164595184763e-05, + "loss": 3.4337, + "step": 1714176 + }, + { + "epoch": 0.01, + "learning_rate": 2.1927778647674243e-05, + "loss": 3.4471, + "step": 1714688 + }, + { + "epoch": 0.01, + "learning_rate": 2.1919392700163723e-05, + "loss": 3.4452, + "step": 1715200 + }, + { + "epoch": 0.01, + "learning_rate": 2.1911023131456935e-05, + "loss": 3.4473, + "step": 1715712 + }, + { + "epoch": 0.01, + "learning_rate": 2.1902637183946415e-05, + "loss": 3.4463, + "step": 1716224 + }, + { + "epoch": 0.01, + "learning_rate": 2.1894251236435895e-05, + "loss": 3.4494, + "step": 1716736 + }, + { + "epoch": 0.01, + "learning_rate": 2.1885865288925375e-05, + "loss": 3.4586, + "step": 1717248 + }, + { + "epoch": 0.01, + "learning_rate": 2.1877495720218584e-05, + "loss": 3.4354, + "step": 1717760 + }, + { + "epoch": 0.01, + "learning_rate": 2.1869109772708064e-05, + "loss": 3.4529, + "step": 1718272 + }, + { + "epoch": 0.01, + "learning_rate": 2.1860723825197548e-05, + "loss": 3.4459, + "step": 1718784 + }, + { + "epoch": 0.01, + "learning_rate": 2.1852337877687028e-05, + "loss": 3.4368, + "step": 1719296 + }, + { + "epoch": 0.01, + "learning_rate": 2.1843968308980237e-05, + "loss": 3.4545, + "step": 1719808 + }, + { + "epoch": 0.01, + "learning_rate": 2.1835582361469717e-05, + "loss": 3.4596, + "step": 1720320 + }, + { + "epoch": 0.01, + "learning_rate": 2.1827196413959197e-05, + "loss": 3.4487, + "step": 1720832 + }, + { + "epoch": 0.01, + "learning_rate": 2.1818810466448677e-05, + "loss": 3.4641, + "step": 1721344 + }, + { + "epoch": 0.01, + "learning_rate": 2.181044089774189e-05, + "loss": 3.4369, + "step": 1721856 + }, + { + "epoch": 0.01, + "learning_rate": 2.180205495023137e-05, + "loss": 3.4361, + "step": 1722368 + }, + { + "epoch": 0.01, + "learning_rate": 2.179366900272085e-05, + "loss": 3.4457, + "step": 1722880 + }, + { + "epoch": 0.01, + "learning_rate": 2.178528305521033e-05, + "loss": 3.453, + "step": 1723392 + }, + { + "epoch": 0.01, + "learning_rate": 2.1776913486503538e-05, + "loss": 3.4459, + "step": 1723904 + }, + { + "epoch": 0.01, + "learning_rate": 2.1768527538993018e-05, + "loss": 3.4455, + "step": 1724416 + }, + { + "epoch": 0.02, + "learning_rate": 2.1760141591482498e-05, + "loss": 3.4439, + "step": 1724928 + }, + { + "epoch": 0.02, + "learning_rate": 2.175175564397198e-05, + "loss": 3.4525, + "step": 1725440 + }, + { + "epoch": 0.02, + "learning_rate": 2.174338607526519e-05, + "loss": 3.4373, + "step": 1725952 + }, + { + "epoch": 0.02, + "learning_rate": 2.173500012775467e-05, + "loss": 3.4413, + "step": 1726464 + }, + { + "epoch": 0.02, + "learning_rate": 2.172661418024415e-05, + "loss": 3.4487, + "step": 1726976 + }, + { + "epoch": 0.02, + "learning_rate": 2.171822823273363e-05, + "loss": 3.4587, + "step": 1727488 + }, + { + "epoch": 0.02, + "learning_rate": 2.1709858664026843e-05, + "loss": 3.4506, + "step": 1728000 + }, + { + "epoch": 0.02, + "learning_rate": 2.1701472716516323e-05, + "loss": 3.4297, + "step": 1728512 + }, + { + "epoch": 0.02, + "learning_rate": 2.1693086769005803e-05, + "loss": 3.4461, + "step": 1729024 + }, + { + "epoch": 0.02, + "learning_rate": 2.1684700821495283e-05, + "loss": 3.4454, + "step": 1729536 + }, + { + "epoch": 0.02, + "learning_rate": 2.1676331252788492e-05, + "loss": 3.452, + "step": 1730048 + }, + { + "epoch": 0.02, + "learning_rate": 2.166794530527797e-05, + "loss": 3.4429, + "step": 1730560 + }, + { + "epoch": 0.02, + "learning_rate": 2.165955935776745e-05, + "loss": 3.4441, + "step": 1731072 + }, + { + "epoch": 0.02, + "learning_rate": 2.165117341025693e-05, + "loss": 3.434, + "step": 1731584 + }, + { + "epoch": 0.02, + "learning_rate": 2.1642803841550144e-05, + "loss": 3.4357, + "step": 1732096 + }, + { + "epoch": 0.02, + "learning_rate": 2.1634417894039624e-05, + "loss": 3.4469, + "step": 1732608 + }, + { + "epoch": 0.02, + "learning_rate": 2.1626031946529104e-05, + "loss": 3.4424, + "step": 1733120 + }, + { + "epoch": 0.02, + "learning_rate": 2.161764599901858e-05, + "loss": 3.4273, + "step": 1733632 + }, + { + "epoch": 0.02, + "learning_rate": 2.1609276430311796e-05, + "loss": 3.4607, + "step": 1734144 + }, + { + "epoch": 0.02, + "learning_rate": 2.1600890482801276e-05, + "loss": 3.4341, + "step": 1734656 + }, + { + "epoch": 0.02, + "learning_rate": 2.1592504535290753e-05, + "loss": 3.4418, + "step": 1735168 + }, + { + "epoch": 0.02, + "learning_rate": 2.1584118587780233e-05, + "loss": 3.4359, + "step": 1735680 + }, + { + "epoch": 0.02, + "learning_rate": 2.1575749019073445e-05, + "loss": 3.4453, + "step": 1736192 + }, + { + "epoch": 0.02, + "learning_rate": 2.1567363071562925e-05, + "loss": 3.4442, + "step": 1736704 + }, + { + "epoch": 0.02, + "learning_rate": 2.1558977124052405e-05, + "loss": 3.4366, + "step": 1737216 + }, + { + "epoch": 0.02, + "learning_rate": 2.1550591176541885e-05, + "loss": 3.4458, + "step": 1737728 + }, + { + "epoch": 0.02, + "learning_rate": 2.1542221607835098e-05, + "loss": 3.4517, + "step": 1738240 + }, + { + "epoch": 0.02, + "learning_rate": 2.1533835660324578e-05, + "loss": 3.4441, + "step": 1738752 + }, + { + "epoch": 0.02, + "learning_rate": 2.1525449712814054e-05, + "loss": 3.4492, + "step": 1739264 + }, + { + "epoch": 0.02, + "learning_rate": 2.1517063765303534e-05, + "loss": 3.4404, + "step": 1739776 + }, + { + "epoch": 0.02, + "learning_rate": 2.150869419659675e-05, + "loss": 3.4481, + "step": 1740288 + }, + { + "epoch": 0.02, + "learning_rate": 2.1500308249086227e-05, + "loss": 3.4377, + "step": 1740800 + }, + { + "epoch": 0.02, + "learning_rate": 2.1491922301575707e-05, + "loss": 3.4494, + "step": 1741312 + }, + { + "epoch": 0.02, + "learning_rate": 2.1483536354065187e-05, + "loss": 3.4385, + "step": 1741824 + }, + { + "epoch": 0.02, + "learning_rate": 2.14751667853584e-05, + "loss": 3.4485, + "step": 1742336 + }, + { + "epoch": 0.02, + "learning_rate": 2.146678083784788e-05, + "loss": 3.4451, + "step": 1742848 + }, + { + "epoch": 0.02, + "learning_rate": 2.145839489033736e-05, + "loss": 3.4435, + "step": 1743360 + }, + { + "epoch": 0.02, + "learning_rate": 2.145000894282684e-05, + "loss": 3.4361, + "step": 1743872 + }, + { + "epoch": 0.02, + "learning_rate": 2.144163937412005e-05, + "loss": 3.4379, + "step": 1744384 + }, + { + "epoch": 0.02, + "learning_rate": 2.1433253426609528e-05, + "loss": 3.4412, + "step": 1744896 + }, + { + "epoch": 0.02, + "learning_rate": 2.1424867479099008e-05, + "loss": 3.4525, + "step": 1745408 + }, + { + "epoch": 0.02, + "learning_rate": 2.1416481531588488e-05, + "loss": 3.4423, + "step": 1745920 + }, + { + "epoch": 0.02, + "learning_rate": 2.14081119628817e-05, + "loss": 3.4542, + "step": 1746432 + }, + { + "epoch": 0.02, + "learning_rate": 2.139972601537118e-05, + "loss": 3.4316, + "step": 1746944 + }, + { + "epoch": 0.02, + "learning_rate": 2.139134006786066e-05, + "loss": 3.4486, + "step": 1747456 + }, + { + "epoch": 0.02, + "learning_rate": 2.138295412035014e-05, + "loss": 3.4488, + "step": 1747968 + }, + { + "epoch": 0.02, + "learning_rate": 2.137458455164335e-05, + "loss": 3.4507, + "step": 1748480 + }, + { + "epoch": 0.02, + "learning_rate": 2.1366198604132833e-05, + "loss": 3.4462, + "step": 1748992 + }, + { + "epoch": 0.02, + "learning_rate": 2.1357812656622313e-05, + "loss": 3.4431, + "step": 1749504 + }, + { + "epoch": 0.02, + "learning_rate": 2.1349426709111793e-05, + "loss": 3.4365, + "step": 1750016 + }, + { + "epoch": 0.02, + "learning_rate": 2.1341057140405e-05, + "loss": 3.4592, + "step": 1750528 + }, + { + "epoch": 0.02, + "learning_rate": 2.133267119289448e-05, + "loss": 3.4355, + "step": 1751040 + }, + { + "epoch": 0.02, + "learning_rate": 2.132428524538396e-05, + "loss": 3.4483, + "step": 1751552 + }, + { + "epoch": 0.02, + "learning_rate": 2.131589929787344e-05, + "loss": 3.441, + "step": 1752064 + }, + { + "epoch": 0.02, + "learning_rate": 2.1307529729166654e-05, + "loss": 3.4469, + "step": 1752576 + }, + { + "epoch": 0.02, + "learning_rate": 2.1299160160459867e-05, + "loss": 3.4458, + "step": 1753088 + }, + { + "epoch": 0.02, + "learning_rate": 2.1290774212949346e-05, + "loss": 3.446, + "step": 1753600 + }, + { + "epoch": 0.02, + "learning_rate": 2.1282388265438823e-05, + "loss": 3.4442, + "step": 1754112 + }, + { + "epoch": 0.02, + "learning_rate": 2.1274002317928303e-05, + "loss": 3.4274, + "step": 1754624 + }, + { + "epoch": 0.02, + "learning_rate": 2.1265616370417786e-05, + "loss": 3.4437, + "step": 1755136 + }, + { + "epoch": 0.03, + "eval_loss": 3.856121301651001, + "eval_runtime": 303.1492, + "eval_samples_per_second": 1258.757, + "eval_steps_per_second": 39.337, + "step": 1755360 + }, + { + "epoch": 1.0, + "learning_rate": 2.1257230422907266e-05, + "loss": 3.4351, + "step": 1755648 + }, + { + "epoch": 1.0, + "learning_rate": 2.1248844475396746e-05, + "loss": 3.4383, + "step": 1756160 + }, + { + "epoch": 1.0, + "learning_rate": 2.1240458527886226e-05, + "loss": 3.4467, + "step": 1756672 + }, + { + "epoch": 1.0, + "learning_rate": 2.1232088959179435e-05, + "loss": 3.4459, + "step": 1757184 + }, + { + "epoch": 1.0, + "learning_rate": 2.1223703011668915e-05, + "loss": 3.4575, + "step": 1757696 + }, + { + "epoch": 1.0, + "learning_rate": 2.1215317064158395e-05, + "loss": 3.4444, + "step": 1758208 + }, + { + "epoch": 1.0, + "learning_rate": 2.1206931116647875e-05, + "loss": 3.4378, + "step": 1758720 + }, + { + "epoch": 1.0, + "learning_rate": 2.1198561547941088e-05, + "loss": 3.441, + "step": 1759232 + }, + { + "epoch": 1.0, + "learning_rate": 2.1190175600430568e-05, + "loss": 3.4382, + "step": 1759744 + }, + { + "epoch": 1.0, + "learning_rate": 2.1181789652920048e-05, + "loss": 3.4447, + "step": 1760256 + }, + { + "epoch": 1.0, + "learning_rate": 2.1173403705409528e-05, + "loss": 3.4389, + "step": 1760768 + }, + { + "epoch": 1.0, + "learning_rate": 2.1165034136702737e-05, + "loss": 3.444, + "step": 1761280 + }, + { + "epoch": 1.0, + "learning_rate": 2.115664818919222e-05, + "loss": 3.4407, + "step": 1761792 + }, + { + "epoch": 1.0, + "learning_rate": 2.11482622416817e-05, + "loss": 3.4335, + "step": 1762304 + }, + { + "epoch": 1.0, + "learning_rate": 2.113987629417118e-05, + "loss": 3.4314, + "step": 1762816 + }, + { + "epoch": 1.0, + "learning_rate": 2.113150672546439e-05, + "loss": 3.4315, + "step": 1763328 + }, + { + "epoch": 1.0, + "learning_rate": 2.112312077795387e-05, + "loss": 3.4438, + "step": 1763840 + }, + { + "epoch": 1.0, + "learning_rate": 2.111473483044335e-05, + "loss": 3.4413, + "step": 1764352 + }, + { + "epoch": 1.0, + "learning_rate": 2.110634888293283e-05, + "loss": 3.4379, + "step": 1764864 + }, + { + "epoch": 1.0, + "learning_rate": 2.109797931422604e-05, + "loss": 3.4558, + "step": 1765376 + }, + { + "epoch": 1.0, + "learning_rate": 2.108959336671552e-05, + "loss": 3.448, + "step": 1765888 + }, + { + "epoch": 1.0, + "learning_rate": 2.1081207419205e-05, + "loss": 3.4413, + "step": 1766400 + }, + { + "epoch": 1.0, + "learning_rate": 2.1072821471694478e-05, + "loss": 3.4428, + "step": 1766912 + }, + { + "epoch": 1.0, + "learning_rate": 2.106445190298769e-05, + "loss": 3.4344, + "step": 1767424 + }, + { + "epoch": 1.0, + "learning_rate": 2.1056065955477174e-05, + "loss": 3.4405, + "step": 1767936 + }, + { + "epoch": 1.0, + "learning_rate": 2.1047680007966654e-05, + "loss": 3.4428, + "step": 1768448 + }, + { + "epoch": 1.0, + "learning_rate": 2.103929406045613e-05, + "loss": 3.4411, + "step": 1768960 + }, + { + "epoch": 1.0, + "learning_rate": 2.1030924491749343e-05, + "loss": 3.4458, + "step": 1769472 + }, + { + "epoch": 1.0, + "learning_rate": 2.1022538544238823e-05, + "loss": 3.4302, + "step": 1769984 + }, + { + "epoch": 1.0, + "learning_rate": 2.1014152596728303e-05, + "loss": 3.4299, + "step": 1770496 + }, + { + "epoch": 1.01, + "learning_rate": 2.1005766649217782e-05, + "loss": 3.4278, + "step": 1771008 + }, + { + "epoch": 1.01, + "learning_rate": 2.0997397080510995e-05, + "loss": 3.4432, + "step": 1771520 + }, + { + "epoch": 1.01, + "learning_rate": 2.0989011133000475e-05, + "loss": 3.4464, + "step": 1772032 + }, + { + "epoch": 1.01, + "learning_rate": 2.098062518548995e-05, + "loss": 3.4457, + "step": 1772544 + }, + { + "epoch": 1.01, + "learning_rate": 2.097223923797943e-05, + "loss": 3.4346, + "step": 1773056 + }, + { + "epoch": 1.01, + "learning_rate": 2.0963869669272644e-05, + "loss": 3.4331, + "step": 1773568 + }, + { + "epoch": 1.01, + "learning_rate": 2.0955483721762124e-05, + "loss": 3.4419, + "step": 1774080 + }, + { + "epoch": 1.01, + "learning_rate": 2.0947097774251604e-05, + "loss": 3.4307, + "step": 1774592 + }, + { + "epoch": 1.01, + "learning_rate": 2.0938711826741084e-05, + "loss": 3.4299, + "step": 1775104 + }, + { + "epoch": 1.01, + "learning_rate": 2.0930342258034296e-05, + "loss": 3.4354, + "step": 1775616 + }, + { + "epoch": 1.01, + "learning_rate": 2.0921956310523773e-05, + "loss": 3.4337, + "step": 1776128 + }, + { + "epoch": 1.01, + "learning_rate": 2.0913570363013256e-05, + "loss": 3.4415, + "step": 1776640 + }, + { + "epoch": 1.01, + "learning_rate": 2.0905184415502736e-05, + "loss": 3.4393, + "step": 1777152 + }, + { + "epoch": 1.01, + "learning_rate": 2.089681484679595e-05, + "loss": 3.4403, + "step": 1777664 + }, + { + "epoch": 1.01, + "learning_rate": 2.0888428899285425e-05, + "loss": 3.4369, + "step": 1778176 + }, + { + "epoch": 1.01, + "learning_rate": 2.0880042951774905e-05, + "loss": 3.4412, + "step": 1778688 + }, + { + "epoch": 1.01, + "learning_rate": 2.0871657004264385e-05, + "loss": 3.4413, + "step": 1779200 + }, + { + "epoch": 1.01, + "learning_rate": 2.0863287435557598e-05, + "loss": 3.428, + "step": 1779712 + }, + { + "epoch": 1.01, + "learning_rate": 2.0854901488047078e-05, + "loss": 3.4051, + "step": 1780224 + }, + { + "epoch": 1.01, + "learning_rate": 2.0846515540536558e-05, + "loss": 3.4528, + "step": 1780736 + }, + { + "epoch": 1.01, + "learning_rate": 2.0838129593026037e-05, + "loss": 3.4329, + "step": 1781248 + }, + { + "epoch": 1.01, + "learning_rate": 2.0829743645515517e-05, + "loss": 3.4438, + "step": 1781760 + }, + { + "epoch": 1.01, + "learning_rate": 2.0821374076808727e-05, + "loss": 3.4301, + "step": 1782272 + }, + { + "epoch": 1.01, + "learning_rate": 2.081298812929821e-05, + "loss": 3.4313, + "step": 1782784 + }, + { + "epoch": 1.01, + "learning_rate": 2.080460218178769e-05, + "loss": 3.4179, + "step": 1783296 + }, + { + "epoch": 1.01, + "learning_rate": 2.07962326130809e-05, + "loss": 3.4354, + "step": 1783808 + }, + { + "epoch": 1.01, + "learning_rate": 2.078784666557038e-05, + "loss": 3.4447, + "step": 1784320 + }, + { + "epoch": 1.01, + "learning_rate": 2.077946071805986e-05, + "loss": 3.4238, + "step": 1784832 + }, + { + "epoch": 1.01, + "learning_rate": 2.077107477054934e-05, + "loss": 3.4527, + "step": 1785344 + }, + { + "epoch": 1.01, + "learning_rate": 2.076270520184255e-05, + "loss": 3.4307, + "step": 1785856 + }, + { + "epoch": 1.01, + "learning_rate": 2.075431925433203e-05, + "loss": 3.4207, + "step": 1786368 + }, + { + "epoch": 1.01, + "learning_rate": 2.074593330682151e-05, + "loss": 3.4359, + "step": 1786880 + }, + { + "epoch": 1.01, + "learning_rate": 2.073754735931099e-05, + "loss": 3.4256, + "step": 1787392 + }, + { + "epoch": 1.01, + "learning_rate": 2.07291777906042e-05, + "loss": 3.4188, + "step": 1787904 + }, + { + "epoch": 1.01, + "learning_rate": 2.072079184309368e-05, + "loss": 3.4417, + "step": 1788416 + }, + { + "epoch": 1.01, + "learning_rate": 2.071240589558316e-05, + "loss": 3.4415, + "step": 1788928 + }, + { + "epoch": 1.01, + "learning_rate": 2.0704019948072643e-05, + "loss": 3.4276, + "step": 1789440 + }, + { + "epoch": 1.01, + "learning_rate": 2.0695650379365853e-05, + "loss": 3.4347, + "step": 1789952 + }, + { + "epoch": 1.01, + "learning_rate": 2.0687264431855333e-05, + "loss": 3.4194, + "step": 1790464 + }, + { + "epoch": 1.01, + "learning_rate": 2.0678878484344813e-05, + "loss": 3.4394, + "step": 1790976 + }, + { + "epoch": 1.01, + "learning_rate": 2.0670492536834292e-05, + "loss": 3.4307, + "step": 1791488 + }, + { + "epoch": 1.01, + "learning_rate": 2.0662122968127505e-05, + "loss": 3.4327, + "step": 1792000 + }, + { + "epoch": 1.01, + "learning_rate": 2.0653737020616985e-05, + "loss": 3.4409, + "step": 1792512 + }, + { + "epoch": 1.01, + "learning_rate": 2.0645351073106465e-05, + "loss": 3.4334, + "step": 1793024 + }, + { + "epoch": 1.01, + "learning_rate": 2.0636965125595945e-05, + "loss": 3.4512, + "step": 1793536 + }, + { + "epoch": 1.01, + "learning_rate": 2.0628595556889154e-05, + "loss": 3.4243, + "step": 1794048 + }, + { + "epoch": 1.01, + "learning_rate": 2.0620209609378634e-05, + "loss": 3.4414, + "step": 1794560 + }, + { + "epoch": 1.01, + "learning_rate": 2.0611823661868114e-05, + "loss": 3.4338, + "step": 1795072 + }, + { + "epoch": 1.01, + "learning_rate": 2.0603437714357597e-05, + "loss": 3.4251, + "step": 1795584 + }, + { + "epoch": 1.01, + "learning_rate": 2.0595068145650806e-05, + "loss": 3.4426, + "step": 1796096 + }, + { + "epoch": 1.01, + "learning_rate": 2.0586682198140286e-05, + "loss": 3.4473, + "step": 1796608 + }, + { + "epoch": 1.01, + "learning_rate": 2.0578296250629766e-05, + "loss": 3.4391, + "step": 1797120 + }, + { + "epoch": 1.01, + "learning_rate": 2.0569910303119246e-05, + "loss": 3.4518, + "step": 1797632 + }, + { + "epoch": 1.01, + "learning_rate": 2.056154073441246e-05, + "loss": 3.4257, + "step": 1798144 + }, + { + "epoch": 1.01, + "learning_rate": 2.055315478690194e-05, + "loss": 3.4236, + "step": 1798656 + }, + { + "epoch": 1.01, + "learning_rate": 2.054476883939142e-05, + "loss": 3.4345, + "step": 1799168 + }, + { + "epoch": 1.01, + "learning_rate": 2.05363828918809e-05, + "loss": 3.4453, + "step": 1799680 + }, + { + "epoch": 1.01, + "learning_rate": 2.0528013323174108e-05, + "loss": 3.4309, + "step": 1800192 + }, + { + "epoch": 1.01, + "learning_rate": 2.0519627375663588e-05, + "loss": 3.4401, + "step": 1800704 + }, + { + "epoch": 1.02, + "learning_rate": 2.0511241428153067e-05, + "loss": 3.4329, + "step": 1801216 + }, + { + "epoch": 1.02, + "learning_rate": 2.050285548064255e-05, + "loss": 3.4387, + "step": 1801728 + }, + { + "epoch": 1.02, + "learning_rate": 2.0494469533132027e-05, + "loss": 3.4293, + "step": 1802240 + }, + { + "epoch": 1.02, + "learning_rate": 2.048609996442524e-05, + "loss": 3.4265, + "step": 1802752 + }, + { + "epoch": 1.02, + "learning_rate": 2.047771401691472e-05, + "loss": 3.4393, + "step": 1803264 + }, + { + "epoch": 1.02, + "learning_rate": 2.0469328069404196e-05, + "loss": 3.4499, + "step": 1803776 + }, + { + "epoch": 1.02, + "learning_rate": 2.0460958500697412e-05, + "loss": 3.4395, + "step": 1804288 + }, + { + "epoch": 1.02, + "learning_rate": 2.0452572553186892e-05, + "loss": 3.4174, + "step": 1804800 + }, + { + "epoch": 1.02, + "learning_rate": 2.0444186605676372e-05, + "loss": 3.4345, + "step": 1805312 + }, + { + "epoch": 1.02, + "learning_rate": 2.043580065816585e-05, + "loss": 3.433, + "step": 1805824 + }, + { + "epoch": 1.02, + "learning_rate": 2.042743108945906e-05, + "loss": 3.4433, + "step": 1806336 + }, + { + "epoch": 1.02, + "learning_rate": 2.041904514194854e-05, + "loss": 3.4341, + "step": 1806848 + }, + { + "epoch": 1.02, + "learning_rate": 2.041065919443802e-05, + "loss": 3.4341, + "step": 1807360 + }, + { + "epoch": 1.02, + "learning_rate": 2.04022732469275e-05, + "loss": 3.4259, + "step": 1807872 + }, + { + "epoch": 1.02, + "learning_rate": 2.0393903678220714e-05, + "loss": 3.4221, + "step": 1808384 + }, + { + "epoch": 1.02, + "learning_rate": 2.0385517730710194e-05, + "loss": 3.4358, + "step": 1808896 + }, + { + "epoch": 1.02, + "learning_rate": 2.037713178319967e-05, + "loss": 3.4318, + "step": 1809408 + }, + { + "epoch": 1.02, + "learning_rate": 2.036874583568915e-05, + "loss": 3.4167, + "step": 1809920 + }, + { + "epoch": 1.02, + "learning_rate": 2.0360376266982366e-05, + "loss": 3.4473, + "step": 1810432 + }, + { + "epoch": 1.02, + "learning_rate": 2.0351990319471846e-05, + "loss": 3.4292, + "step": 1810944 + }, + { + "epoch": 1.02, + "learning_rate": 2.0343604371961322e-05, + "loss": 3.4275, + "step": 1811456 + }, + { + "epoch": 1.02, + "learning_rate": 2.0335218424450802e-05, + "loss": 3.428, + "step": 1811968 + }, + { + "epoch": 1.02, + "learning_rate": 2.0326848855744015e-05, + "loss": 3.4295, + "step": 1812480 + }, + { + "epoch": 1.02, + "learning_rate": 2.0318462908233495e-05, + "loss": 3.4376, + "step": 1812992 + }, + { + "epoch": 1.02, + "learning_rate": 2.0310076960722975e-05, + "loss": 3.4275, + "step": 1813504 + }, + { + "epoch": 1.02, + "learning_rate": 2.0301691013212455e-05, + "loss": 3.4373, + "step": 1814016 + }, + { + "epoch": 1.02, + "learning_rate": 2.0293321444505667e-05, + "loss": 3.4416, + "step": 1814528 + }, + { + "epoch": 1.02, + "learning_rate": 2.0284935496995144e-05, + "loss": 3.4323, + "step": 1815040 + }, + { + "epoch": 1.02, + "learning_rate": 2.0276549549484624e-05, + "loss": 3.4396, + "step": 1815552 + }, + { + "epoch": 1.02, + "learning_rate": 2.0268163601974104e-05, + "loss": 3.4282, + "step": 1816064 + }, + { + "epoch": 1.02, + "learning_rate": 2.025979403326732e-05, + "loss": 3.4393, + "step": 1816576 + }, + { + "epoch": 1.02, + "learning_rate": 2.0251408085756796e-05, + "loss": 3.4288, + "step": 1817088 + }, + { + "epoch": 1.02, + "learning_rate": 2.0243022138246276e-05, + "loss": 3.4324, + "step": 1817600 + }, + { + "epoch": 1.02, + "learning_rate": 2.0234636190735756e-05, + "loss": 3.4304, + "step": 1818112 + }, + { + "epoch": 1.02, + "learning_rate": 2.0226266622028965e-05, + "loss": 3.4383, + "step": 1818624 + }, + { + "epoch": 1.02, + "learning_rate": 2.0217880674518445e-05, + "loss": 3.4374, + "step": 1819136 + }, + { + "epoch": 1.02, + "learning_rate": 2.020949472700793e-05, + "loss": 3.4319, + "step": 1819648 + }, + { + "epoch": 1.02, + "learning_rate": 2.020110877949741e-05, + "loss": 3.4208, + "step": 1820160 + }, + { + "epoch": 1.02, + "learning_rate": 2.0192739210790618e-05, + "loss": 3.434, + "step": 1820672 + }, + { + "epoch": 1.02, + "learning_rate": 2.0184353263280097e-05, + "loss": 3.4284, + "step": 1821184 + }, + { + "epoch": 1.02, + "learning_rate": 2.0175967315769577e-05, + "loss": 3.4363, + "step": 1821696 + }, + { + "epoch": 1.02, + "learning_rate": 2.0167581368259057e-05, + "loss": 3.4329, + "step": 1822208 + }, + { + "epoch": 1.02, + "learning_rate": 2.015921179955227e-05, + "loss": 3.441, + "step": 1822720 + }, + { + "epoch": 1.02, + "learning_rate": 2.015082585204175e-05, + "loss": 3.4217, + "step": 1823232 + }, + { + "epoch": 1.02, + "learning_rate": 2.014243990453123e-05, + "loss": 3.4428, + "step": 1823744 + }, + { + "epoch": 1.02, + "learning_rate": 2.013405395702071e-05, + "loss": 3.4345, + "step": 1824256 + }, + { + "epoch": 1.02, + "learning_rate": 2.012568438831392e-05, + "loss": 3.4439, + "step": 1824768 + }, + { + "epoch": 1.02, + "learning_rate": 2.01172984408034e-05, + "loss": 3.435, + "step": 1825280 + }, + { + "epoch": 1.02, + "learning_rate": 2.0108912493292882e-05, + "loss": 3.4303, + "step": 1825792 + }, + { + "epoch": 1.02, + "learning_rate": 2.0100526545782362e-05, + "loss": 3.4271, + "step": 1826304 + }, + { + "epoch": 1.02, + "learning_rate": 2.009215697707557e-05, + "loss": 3.4482, + "step": 1826816 + }, + { + "epoch": 1.02, + "learning_rate": 2.008377102956505e-05, + "loss": 3.4212, + "step": 1827328 + }, + { + "epoch": 1.02, + "learning_rate": 2.0075401460858264e-05, + "loss": 3.4386, + "step": 1827840 + }, + { + "epoch": 1.02, + "learning_rate": 2.0067015513347744e-05, + "loss": 3.4338, + "step": 1828352 + }, + { + "epoch": 1.02, + "learning_rate": 2.0058629565837224e-05, + "loss": 3.4344, + "step": 1828864 + }, + { + "epoch": 1.02, + "learning_rate": 2.0050243618326704e-05, + "loss": 3.4324, + "step": 1829376 + }, + { + "epoch": 1.02, + "learning_rate": 2.0041857670816183e-05, + "loss": 3.4349, + "step": 1829888 + }, + { + "epoch": 1.02, + "learning_rate": 2.0033471723305663e-05, + "loss": 3.4327, + "step": 1830400 + }, + { + "epoch": 1.02, + "learning_rate": 2.0025085775795143e-05, + "loss": 3.4196, + "step": 1830912 + }, + { + "epoch": 1.02, + "learning_rate": 2.0016716207088352e-05, + "loss": 3.433, + "step": 1831424 + }, + { + "epoch": 1.03, + "eval_loss": 3.8573765754699707, + "eval_runtime": 303.0344, + "eval_samples_per_second": 1259.233, + "eval_steps_per_second": 39.352, + "step": 1831680 + }, + { + "epoch": 0.0, + "learning_rate": 2.0008330259577836e-05, + "loss": 3.4232, + "step": 1831936 + }, + { + "epoch": 0.0, + "learning_rate": 1.9999944312067316e-05, + "loss": 3.4276, + "step": 1832448 + }, + { + "epoch": 0.0, + "learning_rate": 1.9991558364556796e-05, + "loss": 3.4352, + "step": 1832960 + }, + { + "epoch": 0.0, + "learning_rate": 1.9983172417046272e-05, + "loss": 3.434, + "step": 1833472 + }, + { + "epoch": 0.0, + "learning_rate": 1.9974802848339485e-05, + "loss": 3.4505, + "step": 1833984 + }, + { + "epoch": 0.0, + "learning_rate": 1.9966416900828965e-05, + "loss": 3.4275, + "step": 1834496 + }, + { + "epoch": 0.0, + "learning_rate": 1.9958030953318445e-05, + "loss": 3.4305, + "step": 1835008 + }, + { + "epoch": 0.0, + "learning_rate": 1.9949645005807925e-05, + "loss": 3.4313, + "step": 1835520 + }, + { + "epoch": 0.0, + "learning_rate": 1.9941275437101137e-05, + "loss": 3.4246, + "step": 1836032 + }, + { + "epoch": 0.0, + "learning_rate": 1.9932889489590617e-05, + "loss": 3.4373, + "step": 1836544 + }, + { + "epoch": 0.0, + "learning_rate": 1.9924503542080094e-05, + "loss": 3.4278, + "step": 1837056 + }, + { + "epoch": 0.0, + "learning_rate": 1.9916117594569574e-05, + "loss": 3.4293, + "step": 1837568 + }, + { + "epoch": 0.0, + "learning_rate": 1.990774802586279e-05, + "loss": 3.4373, + "step": 1838080 + }, + { + "epoch": 0.0, + "learning_rate": 1.989936207835227e-05, + "loss": 3.4177, + "step": 1838592 + }, + { + "epoch": 0.0, + "learning_rate": 1.9890976130841746e-05, + "loss": 3.4205, + "step": 1839104 + }, + { + "epoch": 0.0, + "learning_rate": 1.9882590183331226e-05, + "loss": 3.4209, + "step": 1839616 + }, + { + "epoch": 0.0, + "learning_rate": 1.987422061462444e-05, + "loss": 3.4357, + "step": 1840128 + }, + { + "epoch": 0.0, + "learning_rate": 1.986583466711392e-05, + "loss": 3.4291, + "step": 1840640 + }, + { + "epoch": 0.0, + "learning_rate": 1.98574487196034e-05, + "loss": 3.4286, + "step": 1841152 + }, + { + "epoch": 0.0, + "learning_rate": 1.984906277209288e-05, + "loss": 3.4424, + "step": 1841664 + }, + { + "epoch": 0.0, + "learning_rate": 1.984069320338609e-05, + "loss": 3.4411, + "step": 1842176 + }, + { + "epoch": 0.0, + "learning_rate": 1.9832307255875567e-05, + "loss": 3.4299, + "step": 1842688 + }, + { + "epoch": 0.0, + "learning_rate": 1.9823921308365047e-05, + "loss": 3.4324, + "step": 1843200 + }, + { + "epoch": 0.0, + "learning_rate": 1.9815535360854527e-05, + "loss": 3.4274, + "step": 1843712 + }, + { + "epoch": 0.0, + "learning_rate": 1.9807165792147743e-05, + "loss": 3.4301, + "step": 1844224 + }, + { + "epoch": 0.0, + "learning_rate": 1.979877984463722e-05, + "loss": 3.4294, + "step": 1844736 + }, + { + "epoch": 0.0, + "learning_rate": 1.97903938971267e-05, + "loss": 3.4272, + "step": 1845248 + }, + { + "epoch": 0.0, + "learning_rate": 1.978200794961618e-05, + "loss": 3.4381, + "step": 1845760 + }, + { + "epoch": 0.0, + "learning_rate": 1.9773638380909392e-05, + "loss": 3.4202, + "step": 1846272 + }, + { + "epoch": 0.0, + "learning_rate": 1.976525243339887e-05, + "loss": 3.419, + "step": 1846784 + }, + { + "epoch": 0.01, + "learning_rate": 1.9756866485888352e-05, + "loss": 3.423, + "step": 1847296 + }, + { + "epoch": 0.01, + "learning_rate": 1.9748480538377832e-05, + "loss": 3.4276, + "step": 1847808 + }, + { + "epoch": 0.01, + "learning_rate": 1.974011096967104e-05, + "loss": 3.4332, + "step": 1848320 + }, + { + "epoch": 0.01, + "learning_rate": 1.973172502216052e-05, + "loss": 3.4398, + "step": 1848832 + }, + { + "epoch": 0.01, + "learning_rate": 1.972333907465e-05, + "loss": 3.4223, + "step": 1849344 + }, + { + "epoch": 0.01, + "learning_rate": 1.971495312713948e-05, + "loss": 3.4248, + "step": 1849856 + }, + { + "epoch": 0.01, + "learning_rate": 1.9706583558432693e-05, + "loss": 3.433, + "step": 1850368 + }, + { + "epoch": 0.01, + "learning_rate": 1.9698197610922173e-05, + "loss": 3.4175, + "step": 1850880 + }, + { + "epoch": 0.01, + "learning_rate": 1.9689811663411653e-05, + "loss": 3.4189, + "step": 1851392 + }, + { + "epoch": 0.01, + "learning_rate": 1.9681425715901133e-05, + "loss": 3.4273, + "step": 1851904 + }, + { + "epoch": 0.01, + "learning_rate": 1.9673056147194342e-05, + "loss": 3.4182, + "step": 1852416 + }, + { + "epoch": 0.01, + "learning_rate": 1.9664670199683822e-05, + "loss": 3.4273, + "step": 1852928 + }, + { + "epoch": 0.01, + "learning_rate": 1.9656284252173306e-05, + "loss": 3.4305, + "step": 1853440 + }, + { + "epoch": 0.01, + "learning_rate": 1.9647914683466515e-05, + "loss": 3.4324, + "step": 1853952 + }, + { + "epoch": 0.01, + "learning_rate": 1.9639528735955995e-05, + "loss": 3.4244, + "step": 1854464 + }, + { + "epoch": 0.01, + "learning_rate": 1.9631142788445475e-05, + "loss": 3.4324, + "step": 1854976 + }, + { + "epoch": 0.01, + "learning_rate": 1.9622756840934955e-05, + "loss": 3.4289, + "step": 1855488 + }, + { + "epoch": 0.01, + "learning_rate": 1.9614387272228167e-05, + "loss": 3.4203, + "step": 1856000 + }, + { + "epoch": 0.01, + "learning_rate": 1.9606001324717647e-05, + "loss": 3.3951, + "step": 1856512 + }, + { + "epoch": 0.01, + "learning_rate": 1.9597615377207127e-05, + "loss": 3.4375, + "step": 1857024 + }, + { + "epoch": 0.01, + "learning_rate": 1.9589229429696607e-05, + "loss": 3.421, + "step": 1857536 + }, + { + "epoch": 0.01, + "learning_rate": 1.9580859860989816e-05, + "loss": 3.4321, + "step": 1858048 + }, + { + "epoch": 0.01, + "learning_rate": 1.9572473913479296e-05, + "loss": 3.4241, + "step": 1858560 + }, + { + "epoch": 0.01, + "learning_rate": 1.9564087965968776e-05, + "loss": 3.4185, + "step": 1859072 + }, + { + "epoch": 0.01, + "learning_rate": 1.955570201845826e-05, + "loss": 3.4142, + "step": 1859584 + }, + { + "epoch": 0.01, + "learning_rate": 1.954733244975147e-05, + "loss": 3.4219, + "step": 1860096 + }, + { + "epoch": 0.01, + "learning_rate": 1.953894650224095e-05, + "loss": 3.4371, + "step": 1860608 + }, + { + "epoch": 0.01, + "learning_rate": 1.953056055473043e-05, + "loss": 3.4092, + "step": 1861120 + }, + { + "epoch": 0.01, + "learning_rate": 1.952217460721991e-05, + "loss": 3.4441, + "step": 1861632 + }, + { + "epoch": 0.01, + "learning_rate": 1.951380503851312e-05, + "loss": 3.4215, + "step": 1862144 + }, + { + "epoch": 0.01, + "learning_rate": 1.95054190910026e-05, + "loss": 3.4074, + "step": 1862656 + }, + { + "epoch": 0.01, + "learning_rate": 1.949703314349208e-05, + "loss": 3.427, + "step": 1863168 + }, + { + "epoch": 0.01, + "learning_rate": 1.948864719598156e-05, + "loss": 3.4149, + "step": 1863680 + }, + { + "epoch": 0.01, + "learning_rate": 1.948027762727477e-05, + "loss": 3.4116, + "step": 1864192 + }, + { + "epoch": 0.01, + "learning_rate": 1.947189167976425e-05, + "loss": 3.4255, + "step": 1864704 + }, + { + "epoch": 0.01, + "learning_rate": 1.946350573225373e-05, + "loss": 3.4317, + "step": 1865216 + }, + { + "epoch": 0.01, + "learning_rate": 1.9455119784743213e-05, + "loss": 3.4129, + "step": 1865728 + }, + { + "epoch": 0.01, + "learning_rate": 1.9446750216036422e-05, + "loss": 3.4299, + "step": 1866240 + }, + { + "epoch": 0.01, + "learning_rate": 1.9438364268525902e-05, + "loss": 3.4085, + "step": 1866752 + }, + { + "epoch": 0.01, + "learning_rate": 1.9429978321015382e-05, + "loss": 3.4266, + "step": 1867264 + }, + { + "epoch": 0.01, + "learning_rate": 1.9421592373504862e-05, + "loss": 3.4243, + "step": 1867776 + }, + { + "epoch": 0.01, + "learning_rate": 1.9413222804798074e-05, + "loss": 3.4218, + "step": 1868288 + }, + { + "epoch": 0.01, + "learning_rate": 1.9404836857287554e-05, + "loss": 3.4293, + "step": 1868800 + }, + { + "epoch": 0.01, + "learning_rate": 1.9396450909777034e-05, + "loss": 3.4222, + "step": 1869312 + }, + { + "epoch": 0.01, + "learning_rate": 1.9388064962266514e-05, + "loss": 3.4402, + "step": 1869824 + }, + { + "epoch": 0.01, + "learning_rate": 1.9379695393559723e-05, + "loss": 3.4159, + "step": 1870336 + }, + { + "epoch": 0.01, + "learning_rate": 1.9371309446049203e-05, + "loss": 3.4296, + "step": 1870848 + }, + { + "epoch": 0.01, + "learning_rate": 1.9362923498538683e-05, + "loss": 3.4226, + "step": 1871360 + }, + { + "epoch": 0.01, + "learning_rate": 1.9354537551028167e-05, + "loss": 3.4164, + "step": 1871872 + }, + { + "epoch": 0.01, + "learning_rate": 1.9346167982321376e-05, + "loss": 3.4327, + "step": 1872384 + }, + { + "epoch": 0.01, + "learning_rate": 1.9337782034810856e-05, + "loss": 3.4307, + "step": 1872896 + }, + { + "epoch": 0.01, + "learning_rate": 1.9329396087300336e-05, + "loss": 3.4305, + "step": 1873408 + }, + { + "epoch": 0.01, + "learning_rate": 1.9321010139789816e-05, + "loss": 3.4416, + "step": 1873920 + }, + { + "epoch": 0.01, + "learning_rate": 1.9312640571083028e-05, + "loss": 3.4178, + "step": 1874432 + }, + { + "epoch": 0.01, + "learning_rate": 1.9304254623572508e-05, + "loss": 3.4137, + "step": 1874944 + }, + { + "epoch": 0.01, + "learning_rate": 1.9295868676061988e-05, + "loss": 3.4235, + "step": 1875456 + }, + { + "epoch": 0.01, + "learning_rate": 1.9287482728551465e-05, + "loss": 3.4347, + "step": 1875968 + }, + { + "epoch": 0.01, + "learning_rate": 1.9279113159844677e-05, + "loss": 3.4201, + "step": 1876480 + }, + { + "epoch": 0.01, + "learning_rate": 1.9270727212334157e-05, + "loss": 3.4259, + "step": 1876992 + }, + { + "epoch": 0.02, + "learning_rate": 1.9262341264823637e-05, + "loss": 3.4275, + "step": 1877504 + }, + { + "epoch": 0.02, + "learning_rate": 1.9253955317313117e-05, + "loss": 3.4263, + "step": 1878016 + }, + { + "epoch": 0.02, + "learning_rate": 1.924558574860633e-05, + "loss": 3.4239, + "step": 1878528 + }, + { + "epoch": 0.02, + "learning_rate": 1.923719980109581e-05, + "loss": 3.416, + "step": 1879040 + }, + { + "epoch": 0.02, + "learning_rate": 1.922881385358529e-05, + "loss": 3.4274, + "step": 1879552 + }, + { + "epoch": 0.02, + "learning_rate": 1.9220427906074766e-05, + "loss": 3.4363, + "step": 1880064 + }, + { + "epoch": 0.02, + "learning_rate": 1.9212058337367982e-05, + "loss": 3.4304, + "step": 1880576 + }, + { + "epoch": 0.02, + "learning_rate": 1.9203672389857462e-05, + "loss": 3.4109, + "step": 1881088 + }, + { + "epoch": 0.02, + "learning_rate": 1.919528644234694e-05, + "loss": 3.4237, + "step": 1881600 + }, + { + "epoch": 0.02, + "learning_rate": 1.9186900494836418e-05, + "loss": 3.4215, + "step": 1882112 + }, + { + "epoch": 0.02, + "learning_rate": 1.917853092612963e-05, + "loss": 3.43, + "step": 1882624 + }, + { + "epoch": 0.02, + "learning_rate": 1.917014497861911e-05, + "loss": 3.4263, + "step": 1883136 + }, + { + "epoch": 0.02, + "learning_rate": 1.916175903110859e-05, + "loss": 3.4193, + "step": 1883648 + }, + { + "epoch": 0.02, + "learning_rate": 1.915337308359807e-05, + "loss": 3.4162, + "step": 1884160 + }, + { + "epoch": 0.02, + "learning_rate": 1.9145003514891283e-05, + "loss": 3.4105, + "step": 1884672 + }, + { + "epoch": 0.02, + "learning_rate": 1.9136617567380763e-05, + "loss": 3.4245, + "step": 1885184 + }, + { + "epoch": 0.02, + "learning_rate": 1.912823161987024e-05, + "loss": 3.421, + "step": 1885696 + }, + { + "epoch": 0.02, + "learning_rate": 1.911984567235972e-05, + "loss": 3.4106, + "step": 1886208 + }, + { + "epoch": 0.02, + "learning_rate": 1.9111476103652935e-05, + "loss": 3.4323, + "step": 1886720 + }, + { + "epoch": 0.02, + "learning_rate": 1.9103090156142412e-05, + "loss": 3.4143, + "step": 1887232 + }, + { + "epoch": 0.02, + "learning_rate": 1.9094704208631892e-05, + "loss": 3.4205, + "step": 1887744 + }, + { + "epoch": 0.02, + "learning_rate": 1.9086318261121372e-05, + "loss": 3.4137, + "step": 1888256 + }, + { + "epoch": 0.02, + "learning_rate": 1.9077948692414584e-05, + "loss": 3.4193, + "step": 1888768 + }, + { + "epoch": 0.02, + "learning_rate": 1.906956274490406e-05, + "loss": 3.4279, + "step": 1889280 + }, + { + "epoch": 0.02, + "learning_rate": 1.9061176797393544e-05, + "loss": 3.4138, + "step": 1889792 + }, + { + "epoch": 0.02, + "learning_rate": 1.9052790849883024e-05, + "loss": 3.4286, + "step": 1890304 + }, + { + "epoch": 0.02, + "learning_rate": 1.9044421281176237e-05, + "loss": 3.432, + "step": 1890816 + }, + { + "epoch": 0.02, + "learning_rate": 1.9036035333665713e-05, + "loss": 3.4203, + "step": 1891328 + }, + { + "epoch": 0.02, + "learning_rate": 1.9027649386155193e-05, + "loss": 3.4272, + "step": 1891840 + }, + { + "epoch": 0.02, + "learning_rate": 1.9019263438644673e-05, + "loss": 3.4193, + "step": 1892352 + }, + { + "epoch": 0.02, + "learning_rate": 1.9010893869937886e-05, + "loss": 3.4291, + "step": 1892864 + }, + { + "epoch": 0.02, + "learning_rate": 1.9002507922427366e-05, + "loss": 3.4219, + "step": 1893376 + }, + { + "epoch": 0.02, + "learning_rate": 1.8994121974916846e-05, + "loss": 3.42, + "step": 1893888 + }, + { + "epoch": 0.02, + "learning_rate": 1.8985736027406326e-05, + "loss": 3.419, + "step": 1894400 + }, + { + "epoch": 0.02, + "learning_rate": 1.8977366458699535e-05, + "loss": 3.4262, + "step": 1894912 + }, + { + "epoch": 0.02, + "learning_rate": 1.8968980511189015e-05, + "loss": 3.4296, + "step": 1895424 + }, + { + "epoch": 0.02, + "learning_rate": 1.8960594563678498e-05, + "loss": 3.417, + "step": 1895936 + }, + { + "epoch": 0.02, + "learning_rate": 1.8952208616167978e-05, + "loss": 3.4117, + "step": 1896448 + }, + { + "epoch": 0.02, + "learning_rate": 1.8943839047461187e-05, + "loss": 3.4179, + "step": 1896960 + }, + { + "epoch": 0.02, + "learning_rate": 1.8935453099950667e-05, + "loss": 3.4206, + "step": 1897472 + }, + { + "epoch": 0.02, + "learning_rate": 1.8927067152440147e-05, + "loss": 3.4276, + "step": 1897984 + }, + { + "epoch": 0.02, + "learning_rate": 1.8918681204929627e-05, + "loss": 3.4226, + "step": 1898496 + }, + { + "epoch": 0.02, + "learning_rate": 1.891031163622284e-05, + "loss": 3.4295, + "step": 1899008 + }, + { + "epoch": 0.02, + "learning_rate": 1.890192568871232e-05, + "loss": 3.4124, + "step": 1899520 + }, + { + "epoch": 0.02, + "learning_rate": 1.88935397412018e-05, + "loss": 3.4354, + "step": 1900032 + }, + { + "epoch": 0.02, + "learning_rate": 1.888515379369128e-05, + "loss": 3.4232, + "step": 1900544 + }, + { + "epoch": 0.02, + "learning_rate": 1.887678422498449e-05, + "loss": 3.428, + "step": 1901056 + }, + { + "epoch": 0.02, + "learning_rate": 1.886839827747397e-05, + "loss": 3.4247, + "step": 1901568 + }, + { + "epoch": 0.02, + "learning_rate": 1.886001232996345e-05, + "loss": 3.4191, + "step": 1902080 + }, + { + "epoch": 0.02, + "learning_rate": 1.885164276125666e-05, + "loss": 3.4176, + "step": 1902592 + }, + { + "epoch": 0.02, + "learning_rate": 1.884325681374614e-05, + "loss": 3.4375, + "step": 1903104 + }, + { + "epoch": 0.02, + "learning_rate": 1.883487086623562e-05, + "loss": 3.4117, + "step": 1903616 + }, + { + "epoch": 0.02, + "learning_rate": 1.88264849187251e-05, + "loss": 3.4269, + "step": 1904128 + }, + { + "epoch": 0.02, + "learning_rate": 1.8818115350018313e-05, + "loss": 3.4221, + "step": 1904640 + }, + { + "epoch": 0.02, + "learning_rate": 1.8809729402507793e-05, + "loss": 3.4223, + "step": 1905152 + }, + { + "epoch": 0.02, + "learning_rate": 1.8801359833801006e-05, + "loss": 3.4229, + "step": 1905664 + }, + { + "epoch": 0.02, + "learning_rate": 1.8792973886290482e-05, + "loss": 3.4259, + "step": 1906176 + }, + { + "epoch": 0.02, + "learning_rate": 1.8784587938779962e-05, + "loss": 3.4191, + "step": 1906688 + }, + { + "epoch": 0.02, + "learning_rate": 1.8776201991269442e-05, + "loss": 3.4172, + "step": 1907200 + }, + { + "epoch": 0.02, + "learning_rate": 1.8767816043758922e-05, + "loss": 3.4159, + "step": 1907712 + }, + { + "epoch": 0.03, + "eval_loss": 3.858869791030884, + "eval_runtime": 303.4817, + "eval_samples_per_second": 1257.377, + "eval_steps_per_second": 39.294, + "step": 1908000 + }, + { + "epoch": 1.0, + "learning_rate": 1.8759430096248405e-05, + "loss": 3.4147, + "step": 1908224 + }, + { + "epoch": 1.0, + "learning_rate": 1.8751044148737885e-05, + "loss": 3.4155, + "step": 1908736 + }, + { + "epoch": 1.0, + "learning_rate": 1.8742658201227362e-05, + "loss": 3.4243, + "step": 1909248 + }, + { + "epoch": 1.0, + "learning_rate": 1.8734288632520574e-05, + "loss": 3.4259, + "step": 1909760 + }, + { + "epoch": 1.0, + "learning_rate": 1.8725902685010054e-05, + "loss": 3.439, + "step": 1910272 + }, + { + "epoch": 1.0, + "learning_rate": 1.8717516737499534e-05, + "loss": 3.4164, + "step": 1910784 + }, + { + "epoch": 1.0, + "learning_rate": 1.8709130789989014e-05, + "loss": 3.4195, + "step": 1911296 + }, + { + "epoch": 1.0, + "learning_rate": 1.8700761221282227e-05, + "loss": 3.4213, + "step": 1911808 + }, + { + "epoch": 1.0, + "learning_rate": 1.8692375273771707e-05, + "loss": 3.4138, + "step": 1912320 + }, + { + "epoch": 1.0, + "learning_rate": 1.8683989326261187e-05, + "loss": 3.429, + "step": 1912832 + }, + { + "epoch": 1.0, + "learning_rate": 1.8675603378750663e-05, + "loss": 3.416, + "step": 1913344 + }, + { + "epoch": 1.0, + "learning_rate": 1.8667233810043876e-05, + "loss": 3.4226, + "step": 1913856 + }, + { + "epoch": 1.0, + "learning_rate": 1.865884786253336e-05, + "loss": 3.4279, + "step": 1914368 + }, + { + "epoch": 1.0, + "learning_rate": 1.8650461915022836e-05, + "loss": 3.4081, + "step": 1914880 + }, + { + "epoch": 1.0, + "learning_rate": 1.8642075967512316e-05, + "loss": 3.4073, + "step": 1915392 + }, + { + "epoch": 1.0, + "learning_rate": 1.8633706398805528e-05, + "loss": 3.4117, + "step": 1915904 + }, + { + "epoch": 1.0, + "learning_rate": 1.8625320451295008e-05, + "loss": 3.4269, + "step": 1916416 + }, + { + "epoch": 1.0, + "learning_rate": 1.8616934503784485e-05, + "loss": 3.4259, + "step": 1916928 + }, + { + "epoch": 1.0, + "learning_rate": 1.8608548556273968e-05, + "loss": 3.4117, + "step": 1917440 + }, + { + "epoch": 1.0, + "learning_rate": 1.860017898756718e-05, + "loss": 3.4309, + "step": 1917952 + }, + { + "epoch": 1.0, + "learning_rate": 1.859179304005666e-05, + "loss": 3.4301, + "step": 1918464 + }, + { + "epoch": 1.0, + "learning_rate": 1.8583407092546137e-05, + "loss": 3.4185, + "step": 1918976 + }, + { + "epoch": 1.0, + "learning_rate": 1.8575021145035617e-05, + "loss": 3.4222, + "step": 1919488 + }, + { + "epoch": 1.0, + "learning_rate": 1.856665157632883e-05, + "loss": 3.417, + "step": 1920000 + }, + { + "epoch": 1.0, + "learning_rate": 1.855826562881831e-05, + "loss": 3.4205, + "step": 1920512 + }, + { + "epoch": 1.0, + "learning_rate": 1.854987968130779e-05, + "loss": 3.4198, + "step": 1921024 + }, + { + "epoch": 1.0, + "learning_rate": 1.854149373379727e-05, + "loss": 3.416, + "step": 1921536 + }, + { + "epoch": 1.0, + "learning_rate": 1.8533124165090482e-05, + "loss": 3.4262, + "step": 1922048 + }, + { + "epoch": 1.0, + "learning_rate": 1.8524738217579958e-05, + "loss": 3.4113, + "step": 1922560 + }, + { + "epoch": 1.0, + "learning_rate": 1.8516352270069438e-05, + "loss": 3.4053, + "step": 1923072 + }, + { + "epoch": 1.01, + "learning_rate": 1.850796632255892e-05, + "loss": 3.4146, + "step": 1923584 + }, + { + "epoch": 1.01, + "learning_rate": 1.8499596753852134e-05, + "loss": 3.4189, + "step": 1924096 + }, + { + "epoch": 1.01, + "learning_rate": 1.849121080634161e-05, + "loss": 3.4186, + "step": 1924608 + }, + { + "epoch": 1.01, + "learning_rate": 1.848282485883109e-05, + "loss": 3.4312, + "step": 1925120 + }, + { + "epoch": 1.01, + "learning_rate": 1.847443891132057e-05, + "loss": 3.4135, + "step": 1925632 + }, + { + "epoch": 1.01, + "learning_rate": 1.8466069342613783e-05, + "loss": 3.413, + "step": 1926144 + }, + { + "epoch": 1.01, + "learning_rate": 1.8457683395103263e-05, + "loss": 3.4248, + "step": 1926656 + }, + { + "epoch": 1.01, + "learning_rate": 1.8449297447592743e-05, + "loss": 3.4026, + "step": 1927168 + }, + { + "epoch": 1.01, + "learning_rate": 1.8440911500082223e-05, + "loss": 3.4117, + "step": 1927680 + }, + { + "epoch": 1.01, + "learning_rate": 1.8432541931375432e-05, + "loss": 3.4171, + "step": 1928192 + }, + { + "epoch": 1.01, + "learning_rate": 1.8424155983864912e-05, + "loss": 3.4085, + "step": 1928704 + }, + { + "epoch": 1.01, + "learning_rate": 1.8415770036354392e-05, + "loss": 3.4125, + "step": 1929216 + }, + { + "epoch": 1.01, + "learning_rate": 1.8407384088843875e-05, + "loss": 3.4205, + "step": 1929728 + }, + { + "epoch": 1.01, + "learning_rate": 1.8399014520137084e-05, + "loss": 3.4232, + "step": 1930240 + }, + { + "epoch": 1.01, + "learning_rate": 1.8390628572626564e-05, + "loss": 3.4115, + "step": 1930752 + }, + { + "epoch": 1.01, + "learning_rate": 1.8382242625116044e-05, + "loss": 3.4214, + "step": 1931264 + }, + { + "epoch": 1.01, + "learning_rate": 1.8373856677605524e-05, + "loss": 3.4149, + "step": 1931776 + }, + { + "epoch": 1.01, + "learning_rate": 1.8365487108898737e-05, + "loss": 3.4111, + "step": 1932288 + }, + { + "epoch": 1.01, + "learning_rate": 1.8357101161388217e-05, + "loss": 3.3895, + "step": 1932800 + }, + { + "epoch": 1.01, + "learning_rate": 1.8348715213877697e-05, + "loss": 3.4263, + "step": 1933312 + }, + { + "epoch": 1.01, + "learning_rate": 1.8340329266367177e-05, + "loss": 3.411, + "step": 1933824 + }, + { + "epoch": 1.01, + "learning_rate": 1.8331959697660386e-05, + "loss": 3.4238, + "step": 1934336 + }, + { + "epoch": 1.01, + "learning_rate": 1.8323573750149866e-05, + "loss": 3.4083, + "step": 1934848 + }, + { + "epoch": 1.01, + "learning_rate": 1.8315187802639346e-05, + "loss": 3.406, + "step": 1935360 + }, + { + "epoch": 1.01, + "learning_rate": 1.830680185512883e-05, + "loss": 3.401, + "step": 1935872 + }, + { + "epoch": 1.01, + "learning_rate": 1.8298432286422038e-05, + "loss": 3.4107, + "step": 1936384 + }, + { + "epoch": 1.01, + "learning_rate": 1.8290046338911518e-05, + "loss": 3.4271, + "step": 1936896 + }, + { + "epoch": 1.01, + "learning_rate": 1.8281660391400998e-05, + "loss": 3.4028, + "step": 1937408 + }, + { + "epoch": 1.01, + "learning_rate": 1.8273274443890478e-05, + "loss": 3.4313, + "step": 1937920 + }, + { + "epoch": 1.01, + "learning_rate": 1.826490487518369e-05, + "loss": 3.413, + "step": 1938432 + }, + { + "epoch": 1.01, + "learning_rate": 1.825651892767317e-05, + "loss": 3.3978, + "step": 1938944 + }, + { + "epoch": 1.01, + "learning_rate": 1.824813298016265e-05, + "loss": 3.4145, + "step": 1939456 + }, + { + "epoch": 1.01, + "learning_rate": 1.823974703265213e-05, + "loss": 3.4004, + "step": 1939968 + }, + { + "epoch": 1.01, + "learning_rate": 1.823137746394534e-05, + "loss": 3.4076, + "step": 1940480 + }, + { + "epoch": 1.01, + "learning_rate": 1.822299151643482e-05, + "loss": 3.414, + "step": 1940992 + }, + { + "epoch": 1.01, + "learning_rate": 1.82146055689243e-05, + "loss": 3.4208, + "step": 1941504 + }, + { + "epoch": 1.01, + "learning_rate": 1.8206219621413783e-05, + "loss": 3.4033, + "step": 1942016 + }, + { + "epoch": 1.01, + "learning_rate": 1.819785005270699e-05, + "loss": 3.4178, + "step": 1942528 + }, + { + "epoch": 1.01, + "learning_rate": 1.818946410519647e-05, + "loss": 3.4001, + "step": 1943040 + }, + { + "epoch": 1.01, + "learning_rate": 1.818107815768595e-05, + "loss": 3.4174, + "step": 1943552 + }, + { + "epoch": 1.01, + "learning_rate": 1.817269221017543e-05, + "loss": 3.4121, + "step": 1944064 + }, + { + "epoch": 1.01, + "learning_rate": 1.8164322641468644e-05, + "loss": 3.4146, + "step": 1944576 + }, + { + "epoch": 1.01, + "learning_rate": 1.8155936693958124e-05, + "loss": 3.4127, + "step": 1945088 + }, + { + "epoch": 1.01, + "learning_rate": 1.8147550746447604e-05, + "loss": 3.4139, + "step": 1945600 + }, + { + "epoch": 1.01, + "learning_rate": 1.8139164798937084e-05, + "loss": 3.4291, + "step": 1946112 + }, + { + "epoch": 1.01, + "learning_rate": 1.8130795230230293e-05, + "loss": 3.4064, + "step": 1946624 + }, + { + "epoch": 1.01, + "learning_rate": 1.8122409282719773e-05, + "loss": 3.4217, + "step": 1947136 + }, + { + "epoch": 1.01, + "learning_rate": 1.8114023335209253e-05, + "loss": 3.4108, + "step": 1947648 + }, + { + "epoch": 1.01, + "learning_rate": 1.8105637387698733e-05, + "loss": 3.406, + "step": 1948160 + }, + { + "epoch": 1.01, + "learning_rate": 1.8097267818991945e-05, + "loss": 3.418, + "step": 1948672 + }, + { + "epoch": 1.01, + "learning_rate": 1.8088881871481425e-05, + "loss": 3.4227, + "step": 1949184 + }, + { + "epoch": 1.01, + "learning_rate": 1.8080495923970905e-05, + "loss": 3.4211, + "step": 1949696 + }, + { + "epoch": 1.01, + "learning_rate": 1.8072109976460382e-05, + "loss": 3.4324, + "step": 1950208 + }, + { + "epoch": 1.01, + "learning_rate": 1.8063740407753598e-05, + "loss": 3.4126, + "step": 1950720 + }, + { + "epoch": 1.01, + "learning_rate": 1.8055354460243078e-05, + "loss": 3.4017, + "step": 1951232 + }, + { + "epoch": 1.01, + "learning_rate": 1.8046968512732558e-05, + "loss": 3.4112, + "step": 1951744 + }, + { + "epoch": 1.01, + "learning_rate": 1.8038582565222034e-05, + "loss": 3.4213, + "step": 1952256 + }, + { + "epoch": 1.01, + "learning_rate": 1.8030212996515247e-05, + "loss": 3.4126, + "step": 1952768 + }, + { + "epoch": 1.01, + "learning_rate": 1.8021827049004727e-05, + "loss": 3.4169, + "step": 1953280 + }, + { + "epoch": 1.02, + "learning_rate": 1.8013441101494207e-05, + "loss": 3.418, + "step": 1953792 + }, + { + "epoch": 1.02, + "learning_rate": 1.8005055153983687e-05, + "loss": 3.4181, + "step": 1954304 + }, + { + "epoch": 1.02, + "learning_rate": 1.79966855852769e-05, + "loss": 3.4121, + "step": 1954816 + }, + { + "epoch": 1.02, + "learning_rate": 1.798829963776638e-05, + "loss": 3.4059, + "step": 1955328 + }, + { + "epoch": 1.02, + "learning_rate": 1.7979913690255856e-05, + "loss": 3.415, + "step": 1955840 + }, + { + "epoch": 1.02, + "learning_rate": 1.7971527742745335e-05, + "loss": 3.4283, + "step": 1956352 + }, + { + "epoch": 1.02, + "learning_rate": 1.7963158174038548e-05, + "loss": 3.4203, + "step": 1956864 + }, + { + "epoch": 1.02, + "learning_rate": 1.795477222652803e-05, + "loss": 3.3981, + "step": 1957376 + }, + { + "epoch": 1.02, + "learning_rate": 1.7946386279017508e-05, + "loss": 3.4138, + "step": 1957888 + }, + { + "epoch": 1.02, + "learning_rate": 1.7938000331506988e-05, + "loss": 3.4119, + "step": 1958400 + }, + { + "epoch": 1.02, + "learning_rate": 1.79296307628002e-05, + "loss": 3.4208, + "step": 1958912 + }, + { + "epoch": 1.02, + "learning_rate": 1.7921244815289677e-05, + "loss": 3.4151, + "step": 1959424 + }, + { + "epoch": 1.02, + "learning_rate": 1.791285886777916e-05, + "loss": 3.4098, + "step": 1959936 + }, + { + "epoch": 1.02, + "learning_rate": 1.790447292026864e-05, + "loss": 3.4071, + "step": 1960448 + }, + { + "epoch": 1.02, + "learning_rate": 1.7896103351561853e-05, + "loss": 3.4026, + "step": 1960960 + }, + { + "epoch": 1.02, + "learning_rate": 1.788771740405133e-05, + "loss": 3.4138, + "step": 1961472 + }, + { + "epoch": 1.02, + "learning_rate": 1.787933145654081e-05, + "loss": 3.4099, + "step": 1961984 + }, + { + "epoch": 1.02, + "learning_rate": 1.787094550903029e-05, + "loss": 3.4033, + "step": 1962496 + }, + { + "epoch": 1.02, + "learning_rate": 1.78625759403235e-05, + "loss": 3.4157, + "step": 1963008 + }, + { + "epoch": 1.02, + "learning_rate": 1.785418999281298e-05, + "loss": 3.4121, + "step": 1963520 + }, + { + "epoch": 1.02, + "learning_rate": 1.784580404530246e-05, + "loss": 3.4068, + "step": 1964032 + }, + { + "epoch": 1.02, + "learning_rate": 1.783741809779194e-05, + "loss": 3.4054, + "step": 1964544 + }, + { + "epoch": 1.02, + "learning_rate": 1.782904852908515e-05, + "loss": 3.4048, + "step": 1965056 + }, + { + "epoch": 1.02, + "learning_rate": 1.782066258157463e-05, + "loss": 3.4195, + "step": 1965568 + }, + { + "epoch": 1.02, + "learning_rate": 1.7812276634064114e-05, + "loss": 3.3976, + "step": 1966080 + }, + { + "epoch": 1.02, + "learning_rate": 1.7803890686553594e-05, + "loss": 3.4194, + "step": 1966592 + }, + { + "epoch": 1.02, + "learning_rate": 1.7795521117846803e-05, + "loss": 3.4218, + "step": 1967104 + }, + { + "epoch": 1.02, + "learning_rate": 1.7787135170336283e-05, + "loss": 3.4091, + "step": 1967616 + }, + { + "epoch": 1.02, + "learning_rate": 1.7778749222825763e-05, + "loss": 3.4139, + "step": 1968128 + }, + { + "epoch": 1.02, + "learning_rate": 1.7770363275315243e-05, + "loss": 3.4117, + "step": 1968640 + }, + { + "epoch": 1.02, + "learning_rate": 1.7761993706608455e-05, + "loss": 3.4168, + "step": 1969152 + }, + { + "epoch": 1.02, + "learning_rate": 1.7753607759097935e-05, + "loss": 3.4133, + "step": 1969664 + }, + { + "epoch": 1.02, + "learning_rate": 1.7745221811587415e-05, + "loss": 3.4106, + "step": 1970176 + }, + { + "epoch": 1.02, + "learning_rate": 1.7736835864076895e-05, + "loss": 3.4101, + "step": 1970688 + }, + { + "epoch": 1.02, + "learning_rate": 1.7728466295370104e-05, + "loss": 3.4132, + "step": 1971200 + }, + { + "epoch": 1.02, + "learning_rate": 1.7720080347859584e-05, + "loss": 3.4146, + "step": 1971712 + }, + { + "epoch": 1.02, + "learning_rate": 1.7711694400349068e-05, + "loss": 3.4121, + "step": 1972224 + }, + { + "epoch": 1.02, + "learning_rate": 1.7703308452838548e-05, + "loss": 3.4021, + "step": 1972736 + }, + { + "epoch": 1.02, + "learning_rate": 1.7694938884131757e-05, + "loss": 3.4117, + "step": 1973248 + }, + { + "epoch": 1.02, + "learning_rate": 1.7686552936621237e-05, + "loss": 3.4046, + "step": 1973760 + }, + { + "epoch": 1.02, + "learning_rate": 1.7678166989110717e-05, + "loss": 3.4203, + "step": 1974272 + }, + { + "epoch": 1.02, + "learning_rate": 1.7669781041600196e-05, + "loss": 3.4117, + "step": 1974784 + }, + { + "epoch": 1.02, + "learning_rate": 1.766141147289341e-05, + "loss": 3.4162, + "step": 1975296 + }, + { + "epoch": 1.02, + "learning_rate": 1.765302552538289e-05, + "loss": 3.4016, + "step": 1975808 + }, + { + "epoch": 1.02, + "learning_rate": 1.764463957787237e-05, + "loss": 3.424, + "step": 1976320 + }, + { + "epoch": 1.02, + "learning_rate": 1.763625363036185e-05, + "loss": 3.4107, + "step": 1976832 + }, + { + "epoch": 1.02, + "learning_rate": 1.7627884061655058e-05, + "loss": 3.4245, + "step": 1977344 + }, + { + "epoch": 1.02, + "learning_rate": 1.7619498114144538e-05, + "loss": 3.4148, + "step": 1977856 + }, + { + "epoch": 1.02, + "learning_rate": 1.7611112166634018e-05, + "loss": 3.4099, + "step": 1978368 + }, + { + "epoch": 1.02, + "learning_rate": 1.76027262191235e-05, + "loss": 3.4043, + "step": 1978880 + }, + { + "epoch": 1.02, + "learning_rate": 1.759435665041671e-05, + "loss": 3.4299, + "step": 1979392 + }, + { + "epoch": 1.02, + "learning_rate": 1.758597070290619e-05, + "loss": 3.399, + "step": 1979904 + }, + { + "epoch": 1.02, + "learning_rate": 1.757758475539567e-05, + "loss": 3.4189, + "step": 1980416 + }, + { + "epoch": 1.02, + "learning_rate": 1.756919880788515e-05, + "loss": 3.4133, + "step": 1980928 + }, + { + "epoch": 1.02, + "learning_rate": 1.7560829239178363e-05, + "loss": 3.4101, + "step": 1981440 + }, + { + "epoch": 1.02, + "learning_rate": 1.7552459670471572e-05, + "loss": 3.4139, + "step": 1981952 + }, + { + "epoch": 1.02, + "learning_rate": 1.754407372296105e-05, + "loss": 3.412, + "step": 1982464 + }, + { + "epoch": 1.02, + "learning_rate": 1.753568777545053e-05, + "loss": 3.4141, + "step": 1982976 + }, + { + "epoch": 1.02, + "learning_rate": 1.752730182794001e-05, + "loss": 3.4083, + "step": 1983488 + }, + { + "epoch": 1.02, + "learning_rate": 1.751891588042949e-05, + "loss": 3.4048, + "step": 1984000 + }, + { + "epoch": 1.03, + "eval_loss": 3.8615407943725586, + "eval_runtime": 303.4492, + "eval_samples_per_second": 1257.512, + "eval_steps_per_second": 39.298, + "step": 1984320 + }, + { + "epoch": 0.0, + "learning_rate": 1.751052993291897e-05, + "loss": 3.3998, + "step": 1984512 + }, + { + "epoch": 0.0, + "learning_rate": 1.7502143985408455e-05, + "loss": 3.4053, + "step": 1985024 + }, + { + "epoch": 0.0, + "learning_rate": 1.749375803789793e-05, + "loss": 3.4153, + "step": 1985536 + }, + { + "epoch": 0.0, + "learning_rate": 1.748537209038741e-05, + "loss": 3.4169, + "step": 1986048 + }, + { + "epoch": 0.0, + "learning_rate": 1.7477002521680624e-05, + "loss": 3.4287, + "step": 1986560 + }, + { + "epoch": 0.0, + "learning_rate": 1.74686165741701e-05, + "loss": 3.4099, + "step": 1987072 + }, + { + "epoch": 0.0, + "learning_rate": 1.7460230626659584e-05, + "loss": 3.4083, + "step": 1987584 + }, + { + "epoch": 0.0, + "learning_rate": 1.7451844679149064e-05, + "loss": 3.415, + "step": 1988096 + }, + { + "epoch": 0.0, + "learning_rate": 1.7443475110442276e-05, + "loss": 3.4032, + "step": 1988608 + }, + { + "epoch": 0.0, + "learning_rate": 1.7435089162931753e-05, + "loss": 3.41, + "step": 1989120 + }, + { + "epoch": 0.0, + "learning_rate": 1.7426703215421233e-05, + "loss": 3.4132, + "step": 1989632 + }, + { + "epoch": 0.0, + "learning_rate": 1.7418317267910713e-05, + "loss": 3.4123, + "step": 1990144 + }, + { + "epoch": 0.0, + "learning_rate": 1.7409947699203925e-05, + "loss": 3.4137, + "step": 1990656 + }, + { + "epoch": 0.0, + "learning_rate": 1.7401561751693405e-05, + "loss": 3.3998, + "step": 1991168 + }, + { + "epoch": 0.0, + "learning_rate": 1.7393175804182885e-05, + "loss": 3.3973, + "step": 1991680 + }, + { + "epoch": 0.0, + "learning_rate": 1.7384789856672365e-05, + "loss": 3.3985, + "step": 1992192 + }, + { + "epoch": 0.0, + "learning_rate": 1.7376420287965574e-05, + "loss": 3.4198, + "step": 1992704 + }, + { + "epoch": 0.0, + "learning_rate": 1.7368034340455054e-05, + "loss": 3.4112, + "step": 1993216 + }, + { + "epoch": 0.0, + "learning_rate": 1.7359648392944537e-05, + "loss": 3.4033, + "step": 1993728 + }, + { + "epoch": 0.0, + "learning_rate": 1.7351262445434017e-05, + "loss": 3.421, + "step": 1994240 + }, + { + "epoch": 0.0, + "learning_rate": 1.7342892876727226e-05, + "loss": 3.4205, + "step": 1994752 + }, + { + "epoch": 0.0, + "learning_rate": 1.7334506929216706e-05, + "loss": 3.4087, + "step": 1995264 + }, + { + "epoch": 0.0, + "learning_rate": 1.7326120981706186e-05, + "loss": 3.4109, + "step": 1995776 + }, + { + "epoch": 0.0, + "learning_rate": 1.7317735034195666e-05, + "loss": 3.4047, + "step": 1996288 + }, + { + "epoch": 0.0, + "learning_rate": 1.730936546548888e-05, + "loss": 3.4155, + "step": 1996800 + }, + { + "epoch": 0.0, + "learning_rate": 1.730097951797836e-05, + "loss": 3.4071, + "step": 1997312 + }, + { + "epoch": 0.0, + "learning_rate": 1.729259357046784e-05, + "loss": 3.4033, + "step": 1997824 + }, + { + "epoch": 0.0, + "learning_rate": 1.728420762295732e-05, + "loss": 3.4185, + "step": 1998336 + }, + { + "epoch": 0.0, + "learning_rate": 1.7275838054250528e-05, + "loss": 3.4023, + "step": 1998848 + }, + { + "epoch": 0.0, + "learning_rate": 1.7267452106740008e-05, + "loss": 3.393, + "step": 1999360 + }, + { + "epoch": 0.01, + "learning_rate": 1.725906615922949e-05, + "loss": 3.4076, + "step": 1999872 + }, + { + "epoch": 0.01, + "learning_rate": 1.725068021171897e-05, + "loss": 3.4067, + "step": 2000384 + }, + { + "epoch": 0.01, + "learning_rate": 1.724231064301218e-05, + "loss": 3.4132, + "step": 2000896 + }, + { + "epoch": 0.01, + "learning_rate": 1.723392469550166e-05, + "loss": 3.4189, + "step": 2001408 + }, + { + "epoch": 0.01, + "learning_rate": 1.722553874799114e-05, + "loss": 3.4015, + "step": 2001920 + }, + { + "epoch": 0.01, + "learning_rate": 1.721715280048062e-05, + "loss": 3.408, + "step": 2002432 + }, + { + "epoch": 0.01, + "learning_rate": 1.7208783231773833e-05, + "loss": 3.4142, + "step": 2002944 + }, + { + "epoch": 0.01, + "learning_rate": 1.7200397284263312e-05, + "loss": 3.3916, + "step": 2003456 + }, + { + "epoch": 0.01, + "learning_rate": 1.7192011336752792e-05, + "loss": 3.4033, + "step": 2003968 + }, + { + "epoch": 0.01, + "learning_rate": 1.7183625389242272e-05, + "loss": 3.4065, + "step": 2004480 + }, + { + "epoch": 0.01, + "learning_rate": 1.717525582053548e-05, + "loss": 3.3975, + "step": 2004992 + }, + { + "epoch": 0.01, + "learning_rate": 1.716686987302496e-05, + "loss": 3.4034, + "step": 2005504 + }, + { + "epoch": 0.01, + "learning_rate": 1.715848392551444e-05, + "loss": 3.4117, + "step": 2006016 + }, + { + "epoch": 0.01, + "learning_rate": 1.7150097978003925e-05, + "loss": 3.4142, + "step": 2006528 + }, + { + "epoch": 0.01, + "learning_rate": 1.7141728409297134e-05, + "loss": 3.4034, + "step": 2007040 + }, + { + "epoch": 0.01, + "learning_rate": 1.7133342461786614e-05, + "loss": 3.4051, + "step": 2007552 + }, + { + "epoch": 0.01, + "learning_rate": 1.7124956514276094e-05, + "loss": 3.4048, + "step": 2008064 + }, + { + "epoch": 0.01, + "learning_rate": 1.7116586945569306e-05, + "loss": 3.4008, + "step": 2008576 + }, + { + "epoch": 0.01, + "learning_rate": 1.7108200998058786e-05, + "loss": 3.3802, + "step": 2009088 + }, + { + "epoch": 0.01, + "learning_rate": 1.7099815050548266e-05, + "loss": 3.4149, + "step": 2009600 + }, + { + "epoch": 0.01, + "learning_rate": 1.7091429103037746e-05, + "loss": 3.4054, + "step": 2010112 + }, + { + "epoch": 0.01, + "learning_rate": 1.7083043155527226e-05, + "loss": 3.4123, + "step": 2010624 + }, + { + "epoch": 0.01, + "learning_rate": 1.7074673586820435e-05, + "loss": 3.4018, + "step": 2011136 + }, + { + "epoch": 0.01, + "learning_rate": 1.7066287639309915e-05, + "loss": 3.3937, + "step": 2011648 + }, + { + "epoch": 0.01, + "learning_rate": 1.7057901691799395e-05, + "loss": 3.395, + "step": 2012160 + }, + { + "epoch": 0.01, + "learning_rate": 1.704951574428888e-05, + "loss": 3.3998, + "step": 2012672 + }, + { + "epoch": 0.01, + "learning_rate": 1.7041146175582087e-05, + "loss": 3.414, + "step": 2013184 + }, + { + "epoch": 0.01, + "learning_rate": 1.7032760228071567e-05, + "loss": 3.3938, + "step": 2013696 + }, + { + "epoch": 0.01, + "learning_rate": 1.7024374280561047e-05, + "loss": 3.4176, + "step": 2014208 + }, + { + "epoch": 0.01, + "learning_rate": 1.7016004711854256e-05, + "loss": 3.4065, + "step": 2014720 + }, + { + "epoch": 0.01, + "learning_rate": 1.700761876434374e-05, + "loss": 3.3867, + "step": 2015232 + }, + { + "epoch": 0.01, + "learning_rate": 1.699923281683322e-05, + "loss": 3.4045, + "step": 2015744 + }, + { + "epoch": 0.01, + "learning_rate": 1.69908468693227e-05, + "loss": 3.3884, + "step": 2016256 + }, + { + "epoch": 0.01, + "learning_rate": 1.698247730061591e-05, + "loss": 3.3967, + "step": 2016768 + }, + { + "epoch": 0.01, + "learning_rate": 1.697409135310539e-05, + "loss": 3.3994, + "step": 2017280 + }, + { + "epoch": 0.01, + "learning_rate": 1.696570540559487e-05, + "loss": 3.4132, + "step": 2017792 + }, + { + "epoch": 0.01, + "learning_rate": 1.695731945808435e-05, + "loss": 3.3927, + "step": 2018304 + }, + { + "epoch": 0.01, + "learning_rate": 1.694893351057383e-05, + "loss": 3.4051, + "step": 2018816 + }, + { + "epoch": 0.01, + "learning_rate": 1.694056394186704e-05, + "loss": 3.3889, + "step": 2019328 + }, + { + "epoch": 0.01, + "learning_rate": 1.693217799435652e-05, + "loss": 3.4058, + "step": 2019840 + }, + { + "epoch": 0.01, + "learning_rate": 1.6923792046845998e-05, + "loss": 3.4049, + "step": 2020352 + }, + { + "epoch": 0.01, + "learning_rate": 1.691542247813921e-05, + "loss": 3.4062, + "step": 2020864 + }, + { + "epoch": 0.01, + "learning_rate": 1.6907036530628694e-05, + "loss": 3.4044, + "step": 2021376 + }, + { + "epoch": 0.01, + "learning_rate": 1.6898650583118173e-05, + "loss": 3.4018, + "step": 2021888 + }, + { + "epoch": 0.01, + "learning_rate": 1.689026463560765e-05, + "loss": 3.419, + "step": 2022400 + }, + { + "epoch": 0.01, + "learning_rate": 1.6881895066900863e-05, + "loss": 3.3989, + "step": 2022912 + }, + { + "epoch": 0.01, + "learning_rate": 1.6873509119390342e-05, + "loss": 3.4059, + "step": 2023424 + }, + { + "epoch": 0.01, + "learning_rate": 1.6865123171879822e-05, + "loss": 3.4007, + "step": 2023936 + }, + { + "epoch": 0.01, + "learning_rate": 1.6856737224369302e-05, + "loss": 3.4022, + "step": 2024448 + }, + { + "epoch": 0.01, + "learning_rate": 1.6848367655662515e-05, + "loss": 3.4104, + "step": 2024960 + }, + { + "epoch": 0.01, + "learning_rate": 1.6839981708151995e-05, + "loss": 3.4066, + "step": 2025472 + }, + { + "epoch": 0.01, + "learning_rate": 1.683159576064147e-05, + "loss": 3.4099, + "step": 2025984 + }, + { + "epoch": 0.01, + "learning_rate": 1.682320981313095e-05, + "loss": 3.4212, + "step": 2026496 + }, + { + "epoch": 0.01, + "learning_rate": 1.681482386562043e-05, + "loss": 3.4082, + "step": 2027008 + }, + { + "epoch": 0.01, + "learning_rate": 1.6806454296913647e-05, + "loss": 3.3888, + "step": 2027520 + }, + { + "epoch": 0.01, + "learning_rate": 1.6798068349403124e-05, + "loss": 3.3993, + "step": 2028032 + }, + { + "epoch": 0.01, + "learning_rate": 1.6789682401892604e-05, + "loss": 3.4113, + "step": 2028544 + }, + { + "epoch": 0.01, + "learning_rate": 1.6781296454382084e-05, + "loss": 3.4038, + "step": 2029056 + }, + { + "epoch": 0.01, + "learning_rate": 1.6772926885675296e-05, + "loss": 3.4044, + "step": 2029568 + }, + { + "epoch": 0.01, + "learning_rate": 1.6764540938164776e-05, + "loss": 3.4069, + "step": 2030080 + }, + { + "epoch": 0.02, + "learning_rate": 1.6756154990654256e-05, + "loss": 3.4053, + "step": 2030592 + }, + { + "epoch": 0.02, + "learning_rate": 1.6747769043143736e-05, + "loss": 3.4014, + "step": 2031104 + }, + { + "epoch": 0.02, + "learning_rate": 1.6739399474436945e-05, + "loss": 3.395, + "step": 2031616 + }, + { + "epoch": 0.02, + "learning_rate": 1.6731013526926425e-05, + "loss": 3.4096, + "step": 2032128 + }, + { + "epoch": 0.02, + "learning_rate": 1.6722627579415905e-05, + "loss": 3.4154, + "step": 2032640 + }, + { + "epoch": 0.02, + "learning_rate": 1.6714241631905385e-05, + "loss": 3.4114, + "step": 2033152 + }, + { + "epoch": 0.02, + "learning_rate": 1.6705872063198597e-05, + "loss": 3.3859, + "step": 2033664 + }, + { + "epoch": 0.02, + "learning_rate": 1.6697486115688077e-05, + "loss": 3.4031, + "step": 2034176 + }, + { + "epoch": 0.02, + "learning_rate": 1.6689100168177557e-05, + "loss": 3.4051, + "step": 2034688 + }, + { + "epoch": 0.02, + "learning_rate": 1.6680714220667037e-05, + "loss": 3.4096, + "step": 2035200 + }, + { + "epoch": 0.02, + "learning_rate": 1.6672344651960246e-05, + "loss": 3.4062, + "step": 2035712 + }, + { + "epoch": 0.02, + "learning_rate": 1.6663958704449726e-05, + "loss": 3.3974, + "step": 2036224 + }, + { + "epoch": 0.02, + "learning_rate": 1.665557275693921e-05, + "loss": 3.3963, + "step": 2036736 + }, + { + "epoch": 0.02, + "learning_rate": 1.664718680942869e-05, + "loss": 3.3932, + "step": 2037248 + }, + { + "epoch": 0.02, + "learning_rate": 1.66388172407219e-05, + "loss": 3.4032, + "step": 2037760 + }, + { + "epoch": 0.02, + "learning_rate": 1.663043129321138e-05, + "loss": 3.4008, + "step": 2038272 + }, + { + "epoch": 0.02, + "learning_rate": 1.662204534570086e-05, + "loss": 3.3939, + "step": 2038784 + }, + { + "epoch": 0.02, + "learning_rate": 1.661365939819034e-05, + "loss": 3.408, + "step": 2039296 + }, + { + "epoch": 0.02, + "learning_rate": 1.660528982948355e-05, + "loss": 3.3983, + "step": 2039808 + }, + { + "epoch": 0.02, + "learning_rate": 1.659690388197303e-05, + "loss": 3.3961, + "step": 2040320 + }, + { + "epoch": 0.02, + "learning_rate": 1.658851793446251e-05, + "loss": 3.3971, + "step": 2040832 + }, + { + "epoch": 0.02, + "learning_rate": 1.658013198695199e-05, + "loss": 3.3922, + "step": 2041344 + }, + { + "epoch": 0.02, + "learning_rate": 1.65717624182452e-05, + "loss": 3.4091, + "step": 2041856 + }, + { + "epoch": 0.02, + "learning_rate": 1.656337647073468e-05, + "loss": 3.3925, + "step": 2042368 + }, + { + "epoch": 0.02, + "learning_rate": 1.6554990523224163e-05, + "loss": 3.4028, + "step": 2042880 + }, + { + "epoch": 0.02, + "learning_rate": 1.6546604575713643e-05, + "loss": 3.4107, + "step": 2043392 + }, + { + "epoch": 0.02, + "learning_rate": 1.6538235007006852e-05, + "loss": 3.4007, + "step": 2043904 + }, + { + "epoch": 0.02, + "learning_rate": 1.6529849059496332e-05, + "loss": 3.4045, + "step": 2044416 + }, + { + "epoch": 0.02, + "learning_rate": 1.6521463111985812e-05, + "loss": 3.4055, + "step": 2044928 + }, + { + "epoch": 0.02, + "learning_rate": 1.6513077164475292e-05, + "loss": 3.405, + "step": 2045440 + }, + { + "epoch": 0.02, + "learning_rate": 1.6504707595768505e-05, + "loss": 3.4088, + "step": 2045952 + }, + { + "epoch": 0.02, + "learning_rate": 1.6496321648257985e-05, + "loss": 3.398, + "step": 2046464 + }, + { + "epoch": 0.02, + "learning_rate": 1.6487935700747465e-05, + "loss": 3.3984, + "step": 2046976 + }, + { + "epoch": 0.02, + "learning_rate": 1.6479549753236945e-05, + "loss": 3.4021, + "step": 2047488 + }, + { + "epoch": 0.02, + "learning_rate": 1.6471180184530154e-05, + "loss": 3.4057, + "step": 2048000 + }, + { + "epoch": 0.02, + "learning_rate": 1.6462794237019634e-05, + "loss": 3.4007, + "step": 2048512 + }, + { + "epoch": 0.02, + "learning_rate": 1.6454408289509117e-05, + "loss": 3.3927, + "step": 2049024 + }, + { + "epoch": 0.02, + "learning_rate": 1.6446038720802326e-05, + "loss": 3.3995, + "step": 2049536 + }, + { + "epoch": 0.02, + "learning_rate": 1.6437652773291806e-05, + "loss": 3.3952, + "step": 2050048 + }, + { + "epoch": 0.02, + "learning_rate": 1.6429266825781286e-05, + "loss": 3.4091, + "step": 2050560 + }, + { + "epoch": 0.02, + "learning_rate": 1.6420880878270766e-05, + "loss": 3.4012, + "step": 2051072 + }, + { + "epoch": 0.02, + "learning_rate": 1.6412494930760246e-05, + "loss": 3.4067, + "step": 2051584 + }, + { + "epoch": 0.02, + "learning_rate": 1.640412536205346e-05, + "loss": 3.3935, + "step": 2052096 + }, + { + "epoch": 0.02, + "learning_rate": 1.639573941454294e-05, + "loss": 3.4105, + "step": 2052608 + }, + { + "epoch": 0.02, + "learning_rate": 1.638735346703242e-05, + "loss": 3.3996, + "step": 2053120 + }, + { + "epoch": 0.02, + "learning_rate": 1.6378967519521895e-05, + "loss": 3.4154, + "step": 2053632 + }, + { + "epoch": 0.02, + "learning_rate": 1.6370597950815107e-05, + "loss": 3.4053, + "step": 2054144 + }, + { + "epoch": 0.02, + "learning_rate": 1.6362212003304587e-05, + "loss": 3.4009, + "step": 2054656 + }, + { + "epoch": 0.02, + "learning_rate": 1.635382605579407e-05, + "loss": 3.3953, + "step": 2055168 + }, + { + "epoch": 0.02, + "learning_rate": 1.6345440108283547e-05, + "loss": 3.4141, + "step": 2055680 + }, + { + "epoch": 0.02, + "learning_rate": 1.633707053957676e-05, + "loss": 3.3958, + "step": 2056192 + }, + { + "epoch": 0.02, + "learning_rate": 1.632868459206624e-05, + "loss": 3.4058, + "step": 2056704 + }, + { + "epoch": 0.02, + "learning_rate": 1.632029864455572e-05, + "loss": 3.4026, + "step": 2057216 + }, + { + "epoch": 0.02, + "learning_rate": 1.63119126970452e-05, + "loss": 3.4018, + "step": 2057728 + }, + { + "epoch": 0.02, + "learning_rate": 1.630355950714214e-05, + "loss": 3.403, + "step": 2058240 + }, + { + "epoch": 0.02, + "learning_rate": 1.629517355963162e-05, + "loss": 3.4006, + "step": 2058752 + }, + { + "epoch": 0.02, + "learning_rate": 1.62867876121211e-05, + "loss": 3.4029, + "step": 2059264 + }, + { + "epoch": 0.02, + "learning_rate": 1.627840166461058e-05, + "loss": 3.3984, + "step": 2059776 + }, + { + "epoch": 0.02, + "learning_rate": 1.627001571710006e-05, + "loss": 3.3929, + "step": 2060288 + }, + { + "epoch": 0.03, + "eval_loss": 3.861814022064209, + "eval_runtime": 302.0352, + "eval_samples_per_second": 1263.399, + "eval_steps_per_second": 39.482, + "step": 2060640 + }, + { + "epoch": 1.0, + "learning_rate": 1.626162976958954e-05, + "loss": 3.3913, + "step": 2060800 + }, + { + "epoch": 1.0, + "learning_rate": 1.625324382207902e-05, + "loss": 3.3953, + "step": 2061312 + }, + { + "epoch": 1.0, + "learning_rate": 1.62448578745685e-05, + "loss": 3.4049, + "step": 2061824 + }, + { + "epoch": 1.0, + "learning_rate": 1.6236488305861713e-05, + "loss": 3.4075, + "step": 2062336 + }, + { + "epoch": 1.0, + "learning_rate": 1.6228102358351193e-05, + "loss": 3.4178, + "step": 2062848 + }, + { + "epoch": 1.0, + "learning_rate": 1.621971641084067e-05, + "loss": 3.3979, + "step": 2063360 + }, + { + "epoch": 1.0, + "learning_rate": 1.621133046333015e-05, + "loss": 3.3985, + "step": 2063872 + }, + { + "epoch": 1.0, + "learning_rate": 1.6202960894623366e-05, + "loss": 3.405, + "step": 2064384 + }, + { + "epoch": 1.0, + "learning_rate": 1.6194574947112842e-05, + "loss": 3.3952, + "step": 2064896 + }, + { + "epoch": 1.0, + "learning_rate": 1.6186188999602322e-05, + "loss": 3.3972, + "step": 2065408 + }, + { + "epoch": 1.0, + "learning_rate": 1.6177803052091802e-05, + "loss": 3.4066, + "step": 2065920 + }, + { + "epoch": 1.0, + "learning_rate": 1.6169433483385015e-05, + "loss": 3.4006, + "step": 2066432 + }, + { + "epoch": 1.0, + "learning_rate": 1.6161047535874495e-05, + "loss": 3.4083, + "step": 2066944 + }, + { + "epoch": 1.0, + "learning_rate": 1.6152661588363975e-05, + "loss": 3.3888, + "step": 2067456 + }, + { + "epoch": 1.0, + "learning_rate": 1.6144275640853455e-05, + "loss": 3.3865, + "step": 2067968 + }, + { + "epoch": 1.0, + "learning_rate": 1.6135906072146667e-05, + "loss": 3.3906, + "step": 2068480 + }, + { + "epoch": 1.0, + "learning_rate": 1.6127520124636144e-05, + "loss": 3.4066, + "step": 2068992 + }, + { + "epoch": 1.0, + "learning_rate": 1.6119134177125624e-05, + "loss": 3.4066, + "step": 2069504 + }, + { + "epoch": 1.0, + "learning_rate": 1.6110748229615104e-05, + "loss": 3.3917, + "step": 2070016 + }, + { + "epoch": 1.0, + "learning_rate": 1.6102378660908316e-05, + "loss": 3.4063, + "step": 2070528 + }, + { + "epoch": 1.0, + "learning_rate": 1.6093992713397796e-05, + "loss": 3.4124, + "step": 2071040 + }, + { + "epoch": 1.0, + "learning_rate": 1.6085606765887276e-05, + "loss": 3.3949, + "step": 2071552 + }, + { + "epoch": 1.0, + "learning_rate": 1.6077220818376756e-05, + "loss": 3.4022, + "step": 2072064 + }, + { + "epoch": 1.0, + "learning_rate": 1.6068851249669965e-05, + "loss": 3.3979, + "step": 2072576 + }, + { + "epoch": 1.0, + "learning_rate": 1.606046530215945e-05, + "loss": 3.4066, + "step": 2073088 + }, + { + "epoch": 1.0, + "learning_rate": 1.605207935464893e-05, + "loss": 3.3943, + "step": 2073600 + }, + { + "epoch": 1.0, + "learning_rate": 1.6043693407138408e-05, + "loss": 3.3933, + "step": 2074112 + }, + { + "epoch": 1.0, + "learning_rate": 1.6035323838431617e-05, + "loss": 3.4107, + "step": 2074624 + }, + { + "epoch": 1.0, + "learning_rate": 1.6026937890921097e-05, + "loss": 3.3901, + "step": 2075136 + }, + { + "epoch": 1.0, + "learning_rate": 1.6018551943410577e-05, + "loss": 3.3839, + "step": 2075648 + }, + { + "epoch": 1.01, + "learning_rate": 1.6010165995900057e-05, + "loss": 3.3917, + "step": 2076160 + }, + { + "epoch": 1.01, + "learning_rate": 1.600179642719327e-05, + "loss": 3.3952, + "step": 2076672 + }, + { + "epoch": 1.01, + "learning_rate": 1.599341047968275e-05, + "loss": 3.4048, + "step": 2077184 + }, + { + "epoch": 1.01, + "learning_rate": 1.598502453217223e-05, + "loss": 3.41, + "step": 2077696 + }, + { + "epoch": 1.01, + "learning_rate": 1.597663858466171e-05, + "loss": 3.3875, + "step": 2078208 + }, + { + "epoch": 1.01, + "learning_rate": 1.596826901595492e-05, + "loss": 3.3996, + "step": 2078720 + }, + { + "epoch": 1.01, + "learning_rate": 1.5959883068444402e-05, + "loss": 3.4031, + "step": 2079232 + }, + { + "epoch": 1.01, + "learning_rate": 1.5951497120933882e-05, + "loss": 3.3807, + "step": 2079744 + }, + { + "epoch": 1.01, + "learning_rate": 1.5943111173423362e-05, + "loss": 3.3919, + "step": 2080256 + }, + { + "epoch": 1.01, + "learning_rate": 1.593474160471657e-05, + "loss": 3.3988, + "step": 2080768 + }, + { + "epoch": 1.01, + "learning_rate": 1.592635565720605e-05, + "loss": 3.3851, + "step": 2081280 + }, + { + "epoch": 1.01, + "learning_rate": 1.591796970969553e-05, + "loss": 3.3972, + "step": 2081792 + }, + { + "epoch": 1.01, + "learning_rate": 1.590958376218501e-05, + "loss": 3.4041, + "step": 2082304 + }, + { + "epoch": 1.01, + "learning_rate": 1.5901214193478223e-05, + "loss": 3.3999, + "step": 2082816 + }, + { + "epoch": 1.01, + "learning_rate": 1.5892828245967703e-05, + "loss": 3.3924, + "step": 2083328 + }, + { + "epoch": 1.01, + "learning_rate": 1.5884442298457183e-05, + "loss": 3.3993, + "step": 2083840 + }, + { + "epoch": 1.01, + "learning_rate": 1.5876056350946663e-05, + "loss": 3.3937, + "step": 2084352 + }, + { + "epoch": 1.01, + "learning_rate": 1.5867686782239872e-05, + "loss": 3.3939, + "step": 2084864 + }, + { + "epoch": 1.01, + "learning_rate": 1.5859300834729356e-05, + "loss": 3.3718, + "step": 2085376 + }, + { + "epoch": 1.01, + "learning_rate": 1.5850914887218836e-05, + "loss": 3.4021, + "step": 2085888 + }, + { + "epoch": 1.01, + "learning_rate": 1.5842528939708316e-05, + "loss": 3.398, + "step": 2086400 + }, + { + "epoch": 1.01, + "learning_rate": 1.5834159371001525e-05, + "loss": 3.3993, + "step": 2086912 + }, + { + "epoch": 1.01, + "learning_rate": 1.5825773423491005e-05, + "loss": 3.3915, + "step": 2087424 + }, + { + "epoch": 1.01, + "learning_rate": 1.5817387475980485e-05, + "loss": 3.387, + "step": 2087936 + }, + { + "epoch": 1.01, + "learning_rate": 1.5809001528469965e-05, + "loss": 3.3828, + "step": 2088448 + }, + { + "epoch": 1.01, + "learning_rate": 1.5800631959763177e-05, + "loss": 3.388, + "step": 2088960 + }, + { + "epoch": 1.01, + "learning_rate": 1.5792246012252657e-05, + "loss": 3.4073, + "step": 2089472 + }, + { + "epoch": 1.01, + "learning_rate": 1.5783860064742137e-05, + "loss": 3.3852, + "step": 2089984 + }, + { + "epoch": 1.01, + "learning_rate": 1.5775474117231617e-05, + "loss": 3.3997, + "step": 2090496 + }, + { + "epoch": 1.01, + "learning_rate": 1.5767104548524826e-05, + "loss": 3.3981, + "step": 2091008 + }, + { + "epoch": 1.01, + "learning_rate": 1.575871860101431e-05, + "loss": 3.3818, + "step": 2091520 + }, + { + "epoch": 1.01, + "learning_rate": 1.575033265350379e-05, + "loss": 3.3921, + "step": 2092032 + }, + { + "epoch": 1.01, + "learning_rate": 1.574194670599327e-05, + "loss": 3.3813, + "step": 2092544 + }, + { + "epoch": 1.01, + "learning_rate": 1.573357713728648e-05, + "loss": 3.3878, + "step": 2093056 + }, + { + "epoch": 1.01, + "learning_rate": 1.572519118977596e-05, + "loss": 3.3839, + "step": 2093568 + }, + { + "epoch": 1.01, + "learning_rate": 1.5716805242265438e-05, + "loss": 3.4037, + "step": 2094080 + }, + { + "epoch": 1.01, + "learning_rate": 1.5708419294754918e-05, + "loss": 3.3879, + "step": 2094592 + }, + { + "epoch": 1.01, + "learning_rate": 1.570004972604813e-05, + "loss": 3.3889, + "step": 2095104 + }, + { + "epoch": 1.01, + "learning_rate": 1.569166377853761e-05, + "loss": 3.3825, + "step": 2095616 + }, + { + "epoch": 1.01, + "learning_rate": 1.568327783102709e-05, + "loss": 3.3922, + "step": 2096128 + }, + { + "epoch": 1.01, + "learning_rate": 1.5674891883516567e-05, + "loss": 3.3947, + "step": 2096640 + }, + { + "epoch": 1.01, + "learning_rate": 1.566652231480978e-05, + "loss": 3.3925, + "step": 2097152 + }, + { + "epoch": 1.01, + "learning_rate": 1.5658136367299263e-05, + "loss": 3.3977, + "step": 2097664 + }, + { + "epoch": 1.01, + "learning_rate": 1.564975041978874e-05, + "loss": 3.3938, + "step": 2098176 + }, + { + "epoch": 1.01, + "learning_rate": 1.564136447227822e-05, + "loss": 3.4052, + "step": 2098688 + }, + { + "epoch": 1.01, + "learning_rate": 1.5632994903571432e-05, + "loss": 3.3871, + "step": 2099200 + }, + { + "epoch": 1.01, + "learning_rate": 1.5624608956060912e-05, + "loss": 3.3981, + "step": 2099712 + }, + { + "epoch": 1.01, + "learning_rate": 1.561622300855039e-05, + "loss": 3.3922, + "step": 2100224 + }, + { + "epoch": 1.01, + "learning_rate": 1.5607853439843604e-05, + "loss": 3.3899, + "step": 2100736 + }, + { + "epoch": 1.01, + "learning_rate": 1.5599467492333084e-05, + "loss": 3.4002, + "step": 2101248 + }, + { + "epoch": 1.01, + "learning_rate": 1.5591081544822564e-05, + "loss": 3.3949, + "step": 2101760 + }, + { + "epoch": 1.01, + "learning_rate": 1.558269559731204e-05, + "loss": 3.4025, + "step": 2102272 + }, + { + "epoch": 1.01, + "learning_rate": 1.5574326028605253e-05, + "loss": 3.4086, + "step": 2102784 + }, + { + "epoch": 1.01, + "learning_rate": 1.5565940081094733e-05, + "loss": 3.4021, + "step": 2103296 + }, + { + "epoch": 1.01, + "learning_rate": 1.5557554133584213e-05, + "loss": 3.3771, + "step": 2103808 + }, + { + "epoch": 1.01, + "learning_rate": 1.5549168186073693e-05, + "loss": 3.3914, + "step": 2104320 + }, + { + "epoch": 1.01, + "learning_rate": 1.5540798617366906e-05, + "loss": 3.3984, + "step": 2104832 + }, + { + "epoch": 1.01, + "learning_rate": 1.5532412669856386e-05, + "loss": 3.3968, + "step": 2105344 + }, + { + "epoch": 1.01, + "learning_rate": 1.5524026722345862e-05, + "loss": 3.3924, + "step": 2105856 + }, + { + "epoch": 1.01, + "learning_rate": 1.5515640774835342e-05, + "loss": 3.3972, + "step": 2106368 + }, + { + "epoch": 1.02, + "learning_rate": 1.5507271206128558e-05, + "loss": 3.3961, + "step": 2106880 + }, + { + "epoch": 1.02, + "learning_rate": 1.5498885258618038e-05, + "loss": 3.3862, + "step": 2107392 + }, + { + "epoch": 1.02, + "learning_rate": 1.5490499311107515e-05, + "loss": 3.3894, + "step": 2107904 + }, + { + "epoch": 1.02, + "learning_rate": 1.5482113363596995e-05, + "loss": 3.3971, + "step": 2108416 + }, + { + "epoch": 1.02, + "learning_rate": 1.5473743794890207e-05, + "loss": 3.4017, + "step": 2108928 + }, + { + "epoch": 1.02, + "learning_rate": 1.5465357847379687e-05, + "loss": 3.4037, + "step": 2109440 + }, + { + "epoch": 1.02, + "learning_rate": 1.5456971899869167e-05, + "loss": 3.3776, + "step": 2109952 + }, + { + "epoch": 1.02, + "learning_rate": 1.5448585952358647e-05, + "loss": 3.3943, + "step": 2110464 + }, + { + "epoch": 1.02, + "learning_rate": 1.544021638365186e-05, + "loss": 3.3941, + "step": 2110976 + }, + { + "epoch": 1.02, + "learning_rate": 1.5431830436141336e-05, + "loss": 3.3991, + "step": 2111488 + }, + { + "epoch": 1.02, + "learning_rate": 1.5423444488630816e-05, + "loss": 3.394, + "step": 2112000 + }, + { + "epoch": 1.02, + "learning_rate": 1.5415058541120296e-05, + "loss": 3.3891, + "step": 2112512 + }, + { + "epoch": 1.02, + "learning_rate": 1.5406688972413512e-05, + "loss": 3.3897, + "step": 2113024 + }, + { + "epoch": 1.02, + "learning_rate": 1.539830302490299e-05, + "loss": 3.378, + "step": 2113536 + }, + { + "epoch": 1.02, + "learning_rate": 1.5389917077392468e-05, + "loss": 3.3972, + "step": 2114048 + }, + { + "epoch": 1.02, + "learning_rate": 1.5381531129881948e-05, + "loss": 3.3866, + "step": 2114560 + }, + { + "epoch": 1.02, + "learning_rate": 1.5373161561175157e-05, + "loss": 3.3834, + "step": 2115072 + }, + { + "epoch": 1.02, + "learning_rate": 1.536477561366464e-05, + "loss": 3.3986, + "step": 2115584 + }, + { + "epoch": 1.02, + "learning_rate": 1.535638966615412e-05, + "loss": 3.3903, + "step": 2116096 + }, + { + "epoch": 1.02, + "learning_rate": 1.53480037186436e-05, + "loss": 3.3839, + "step": 2116608 + }, + { + "epoch": 1.02, + "learning_rate": 1.533963414993681e-05, + "loss": 3.3911, + "step": 2117120 + }, + { + "epoch": 1.02, + "learning_rate": 1.533124820242629e-05, + "loss": 3.3828, + "step": 2117632 + }, + { + "epoch": 1.02, + "learning_rate": 1.532286225491577e-05, + "loss": 3.4023, + "step": 2118144 + }, + { + "epoch": 1.02, + "learning_rate": 1.531447630740525e-05, + "loss": 3.3802, + "step": 2118656 + }, + { + "epoch": 1.02, + "learning_rate": 1.5306106738698462e-05, + "loss": 3.3958, + "step": 2119168 + }, + { + "epoch": 1.02, + "learning_rate": 1.5297720791187942e-05, + "loss": 3.3943, + "step": 2119680 + }, + { + "epoch": 1.02, + "learning_rate": 1.5289334843677422e-05, + "loss": 3.3968, + "step": 2120192 + }, + { + "epoch": 1.02, + "learning_rate": 1.5280948896166902e-05, + "loss": 3.3918, + "step": 2120704 + }, + { + "epoch": 1.02, + "learning_rate": 1.527257932746011e-05, + "loss": 3.393, + "step": 2121216 + }, + { + "epoch": 1.02, + "learning_rate": 1.5264193379949594e-05, + "loss": 3.3991, + "step": 2121728 + }, + { + "epoch": 1.02, + "learning_rate": 1.5255807432439073e-05, + "loss": 3.397, + "step": 2122240 + }, + { + "epoch": 1.02, + "learning_rate": 1.5247421484928554e-05, + "loss": 3.3868, + "step": 2122752 + }, + { + "epoch": 1.02, + "learning_rate": 1.5239051916221763e-05, + "loss": 3.389, + "step": 2123264 + }, + { + "epoch": 1.02, + "learning_rate": 1.5230665968711243e-05, + "loss": 3.3924, + "step": 2123776 + }, + { + "epoch": 1.02, + "learning_rate": 1.5222280021200725e-05, + "loss": 3.3963, + "step": 2124288 + }, + { + "epoch": 1.02, + "learning_rate": 1.5213894073690205e-05, + "loss": 3.3892, + "step": 2124800 + }, + { + "epoch": 1.02, + "learning_rate": 1.5205524504983416e-05, + "loss": 3.3854, + "step": 2125312 + }, + { + "epoch": 1.02, + "learning_rate": 1.5197138557472896e-05, + "loss": 3.3869, + "step": 2125824 + }, + { + "epoch": 1.02, + "learning_rate": 1.5188752609962376e-05, + "loss": 3.387, + "step": 2126336 + }, + { + "epoch": 1.02, + "learning_rate": 1.5180366662451856e-05, + "loss": 3.3967, + "step": 2126848 + }, + { + "epoch": 1.02, + "learning_rate": 1.5171997093745066e-05, + "loss": 3.3915, + "step": 2127360 + }, + { + "epoch": 1.02, + "learning_rate": 1.5163611146234546e-05, + "loss": 3.4027, + "step": 2127872 + }, + { + "epoch": 1.02, + "learning_rate": 1.5155225198724026e-05, + "loss": 3.3823, + "step": 2128384 + }, + { + "epoch": 1.02, + "learning_rate": 1.5146839251213508e-05, + "loss": 3.4011, + "step": 2128896 + }, + { + "epoch": 1.02, + "learning_rate": 1.5138469682506717e-05, + "loss": 3.393, + "step": 2129408 + }, + { + "epoch": 1.02, + "learning_rate": 1.5130083734996197e-05, + "loss": 3.3986, + "step": 2129920 + }, + { + "epoch": 1.02, + "learning_rate": 1.5121697787485679e-05, + "loss": 3.3956, + "step": 2130432 + }, + { + "epoch": 1.02, + "learning_rate": 1.5113311839975159e-05, + "loss": 3.3891, + "step": 2130944 + }, + { + "epoch": 1.02, + "learning_rate": 1.510494227126837e-05, + "loss": 3.3917, + "step": 2131456 + }, + { + "epoch": 1.02, + "learning_rate": 1.509655632375785e-05, + "loss": 3.4024, + "step": 2131968 + }, + { + "epoch": 1.02, + "learning_rate": 1.508817037624733e-05, + "loss": 3.3874, + "step": 2132480 + }, + { + "epoch": 1.02, + "learning_rate": 1.507978442873681e-05, + "loss": 3.392, + "step": 2132992 + }, + { + "epoch": 1.02, + "learning_rate": 1.507141486003002e-05, + "loss": 3.396, + "step": 2133504 + }, + { + "epoch": 1.02, + "learning_rate": 1.50630289125195e-05, + "loss": 3.3905, + "step": 2134016 + }, + { + "epoch": 1.02, + "learning_rate": 1.505465934381271e-05, + "loss": 3.3898, + "step": 2134528 + }, + { + "epoch": 1.02, + "learning_rate": 1.504627339630219e-05, + "loss": 3.3987, + "step": 2135040 + }, + { + "epoch": 1.02, + "learning_rate": 1.503788744879167e-05, + "loss": 3.3867, + "step": 2135552 + }, + { + "epoch": 1.02, + "learning_rate": 1.502950150128115e-05, + "loss": 3.3873, + "step": 2136064 + }, + { + "epoch": 1.02, + "learning_rate": 1.5021115553770632e-05, + "loss": 3.3857, + "step": 2136576 + }, + { + "epoch": 1.03, + "eval_loss": 3.8629088401794434, + "eval_runtime": 302.4413, + "eval_samples_per_second": 1261.703, + "eval_steps_per_second": 39.429, + "step": 2136960 + }, + { + "epoch": 0.0, + "learning_rate": 1.5012729606260109e-05, + "loss": 3.3895, + "step": 2137088 + }, + { + "epoch": 0.0, + "learning_rate": 1.5004343658749589e-05, + "loss": 3.3788, + "step": 2137600 + }, + { + "epoch": 0.0, + "learning_rate": 1.499595771123907e-05, + "loss": 3.3973, + "step": 2138112 + }, + { + "epoch": 0.0, + "learning_rate": 1.498757176372855e-05, + "loss": 3.3964, + "step": 2138624 + }, + { + "epoch": 0.0, + "learning_rate": 1.497920219502176e-05, + "loss": 3.4027, + "step": 2139136 + }, + { + "epoch": 0.0, + "learning_rate": 1.4970816247511241e-05, + "loss": 3.3907, + "step": 2139648 + }, + { + "epoch": 0.0, + "learning_rate": 1.4962430300000721e-05, + "loss": 3.3893, + "step": 2140160 + }, + { + "epoch": 0.0, + "learning_rate": 1.4954044352490201e-05, + "loss": 3.3936, + "step": 2140672 + }, + { + "epoch": 0.0, + "learning_rate": 1.4945674783783412e-05, + "loss": 3.3837, + "step": 2141184 + }, + { + "epoch": 0.0, + "learning_rate": 1.4937288836272892e-05, + "loss": 3.3884, + "step": 2141696 + }, + { + "epoch": 0.0, + "learning_rate": 1.4928902888762372e-05, + "loss": 3.3931, + "step": 2142208 + }, + { + "epoch": 0.0, + "learning_rate": 1.4920516941251852e-05, + "loss": 3.3936, + "step": 2142720 + }, + { + "epoch": 0.0, + "learning_rate": 1.4912147372545063e-05, + "loss": 3.3995, + "step": 2143232 + }, + { + "epoch": 0.0, + "learning_rate": 1.4903761425034543e-05, + "loss": 3.3806, + "step": 2143744 + }, + { + "epoch": 0.0, + "learning_rate": 1.4895375477524024e-05, + "loss": 3.3743, + "step": 2144256 + }, + { + "epoch": 0.0, + "learning_rate": 1.4886989530013504e-05, + "loss": 3.3772, + "step": 2144768 + }, + { + "epoch": 0.0, + "learning_rate": 1.4878619961306713e-05, + "loss": 3.4016, + "step": 2145280 + }, + { + "epoch": 0.0, + "learning_rate": 1.4870234013796195e-05, + "loss": 3.3896, + "step": 2145792 + }, + { + "epoch": 0.0, + "learning_rate": 1.4861848066285675e-05, + "loss": 3.3854, + "step": 2146304 + }, + { + "epoch": 0.0, + "learning_rate": 1.4853462118775155e-05, + "loss": 3.3972, + "step": 2146816 + }, + { + "epoch": 0.0, + "learning_rate": 1.4845092550068366e-05, + "loss": 3.404, + "step": 2147328 + }, + { + "epoch": 0.0, + "learning_rate": 1.4836706602557846e-05, + "loss": 3.3861, + "step": 2147840 + }, + { + "epoch": 0.0, + "learning_rate": 1.4828320655047325e-05, + "loss": 3.3911, + "step": 2148352 + }, + { + "epoch": 0.0, + "learning_rate": 1.4819934707536805e-05, + "loss": 3.3855, + "step": 2148864 + }, + { + "epoch": 0.0, + "learning_rate": 1.4811565138830016e-05, + "loss": 3.4007, + "step": 2149376 + }, + { + "epoch": 0.0, + "learning_rate": 1.4803179191319496e-05, + "loss": 3.3829, + "step": 2149888 + }, + { + "epoch": 0.0, + "learning_rate": 1.4794793243808978e-05, + "loss": 3.3818, + "step": 2150400 + }, + { + "epoch": 0.0, + "learning_rate": 1.4786407296298458e-05, + "loss": 3.4019, + "step": 2150912 + }, + { + "epoch": 0.0, + "learning_rate": 1.4778037727591667e-05, + "loss": 3.3743, + "step": 2151424 + }, + { + "epoch": 0.0, + "learning_rate": 1.4769651780081149e-05, + "loss": 3.3774, + "step": 2151936 + }, + { + "epoch": 0.01, + "learning_rate": 1.4761265832570628e-05, + "loss": 3.3825, + "step": 2152448 + }, + { + "epoch": 0.01, + "learning_rate": 1.4752879885060108e-05, + "loss": 3.3847, + "step": 2152960 + }, + { + "epoch": 0.01, + "learning_rate": 1.474451031635332e-05, + "loss": 3.3944, + "step": 2153472 + }, + { + "epoch": 0.01, + "learning_rate": 1.47361243688428e-05, + "loss": 3.3969, + "step": 2153984 + }, + { + "epoch": 0.01, + "learning_rate": 1.4727738421332279e-05, + "loss": 3.3825, + "step": 2154496 + }, + { + "epoch": 0.01, + "learning_rate": 1.4719352473821759e-05, + "loss": 3.3877, + "step": 2155008 + }, + { + "epoch": 0.01, + "learning_rate": 1.471098290511497e-05, + "loss": 3.3926, + "step": 2155520 + }, + { + "epoch": 0.01, + "learning_rate": 1.470259695760445e-05, + "loss": 3.3718, + "step": 2156032 + }, + { + "epoch": 0.01, + "learning_rate": 1.4694211010093931e-05, + "loss": 3.385, + "step": 2156544 + }, + { + "epoch": 0.01, + "learning_rate": 1.4685825062583411e-05, + "loss": 3.3836, + "step": 2157056 + }, + { + "epoch": 0.01, + "learning_rate": 1.467745549387662e-05, + "loss": 3.3766, + "step": 2157568 + }, + { + "epoch": 0.01, + "learning_rate": 1.4669069546366102e-05, + "loss": 3.3842, + "step": 2158080 + }, + { + "epoch": 0.01, + "learning_rate": 1.4660683598855582e-05, + "loss": 3.3971, + "step": 2158592 + }, + { + "epoch": 0.01, + "learning_rate": 1.4652297651345062e-05, + "loss": 3.3886, + "step": 2159104 + }, + { + "epoch": 0.01, + "learning_rate": 1.4643928082638273e-05, + "loss": 3.3834, + "step": 2159616 + }, + { + "epoch": 0.01, + "learning_rate": 1.4635542135127753e-05, + "loss": 3.3942, + "step": 2160128 + }, + { + "epoch": 0.01, + "learning_rate": 1.4627156187617233e-05, + "loss": 3.3838, + "step": 2160640 + }, + { + "epoch": 0.01, + "learning_rate": 1.4618770240106711e-05, + "loss": 3.3859, + "step": 2161152 + }, + { + "epoch": 0.01, + "learning_rate": 1.4610400671399924e-05, + "loss": 3.3576, + "step": 2161664 + }, + { + "epoch": 0.01, + "learning_rate": 1.4602014723889404e-05, + "loss": 3.3875, + "step": 2162176 + }, + { + "epoch": 0.01, + "learning_rate": 1.4593628776378883e-05, + "loss": 3.394, + "step": 2162688 + }, + { + "epoch": 0.01, + "learning_rate": 1.4585242828868362e-05, + "loss": 3.3868, + "step": 2163200 + }, + { + "epoch": 0.01, + "learning_rate": 1.4576873260161574e-05, + "loss": 3.3796, + "step": 2163712 + }, + { + "epoch": 0.01, + "learning_rate": 1.4568487312651056e-05, + "loss": 3.3799, + "step": 2164224 + }, + { + "epoch": 0.01, + "learning_rate": 1.4560101365140536e-05, + "loss": 3.3722, + "step": 2164736 + }, + { + "epoch": 0.01, + "learning_rate": 1.4551715417630012e-05, + "loss": 3.3744, + "step": 2165248 + }, + { + "epoch": 0.01, + "learning_rate": 1.4543345848923227e-05, + "loss": 3.4009, + "step": 2165760 + }, + { + "epoch": 0.01, + "learning_rate": 1.4534959901412707e-05, + "loss": 3.3764, + "step": 2166272 + }, + { + "epoch": 0.01, + "learning_rate": 1.4526573953902183e-05, + "loss": 3.3855, + "step": 2166784 + }, + { + "epoch": 0.01, + "learning_rate": 1.4518188006391665e-05, + "loss": 3.3898, + "step": 2167296 + }, + { + "epoch": 0.01, + "learning_rate": 1.4509818437684877e-05, + "loss": 3.3714, + "step": 2167808 + }, + { + "epoch": 0.01, + "learning_rate": 1.4501432490174357e-05, + "loss": 3.3811, + "step": 2168320 + }, + { + "epoch": 0.01, + "learning_rate": 1.4493046542663835e-05, + "loss": 3.3717, + "step": 2168832 + }, + { + "epoch": 0.01, + "learning_rate": 1.4484660595153315e-05, + "loss": 3.3761, + "step": 2169344 + }, + { + "epoch": 0.01, + "learning_rate": 1.4476291026446528e-05, + "loss": 3.3781, + "step": 2169856 + }, + { + "epoch": 0.01, + "learning_rate": 1.446790507893601e-05, + "loss": 3.3936, + "step": 2170368 + }, + { + "epoch": 0.01, + "learning_rate": 1.4459519131425486e-05, + "loss": 3.3838, + "step": 2170880 + }, + { + "epoch": 0.01, + "learning_rate": 1.4451133183914966e-05, + "loss": 3.3763, + "step": 2171392 + }, + { + "epoch": 0.01, + "learning_rate": 1.444276361520818e-05, + "loss": 3.3706, + "step": 2171904 + }, + { + "epoch": 0.01, + "learning_rate": 1.4434377667697657e-05, + "loss": 3.3834, + "step": 2172416 + }, + { + "epoch": 0.01, + "learning_rate": 1.4425991720187137e-05, + "loss": 3.382, + "step": 2172928 + }, + { + "epoch": 0.01, + "learning_rate": 1.4417605772676618e-05, + "loss": 3.3862, + "step": 2173440 + }, + { + "epoch": 0.01, + "learning_rate": 1.4409236203969831e-05, + "loss": 3.3832, + "step": 2173952 + }, + { + "epoch": 0.01, + "learning_rate": 1.4400850256459309e-05, + "loss": 3.385, + "step": 2174464 + }, + { + "epoch": 0.01, + "learning_rate": 1.4392464308948789e-05, + "loss": 3.3942, + "step": 2174976 + }, + { + "epoch": 0.01, + "learning_rate": 1.4384078361438269e-05, + "loss": 3.3797, + "step": 2175488 + }, + { + "epoch": 0.01, + "learning_rate": 1.437570879273148e-05, + "loss": 3.3806, + "step": 2176000 + }, + { + "epoch": 0.01, + "learning_rate": 1.436732284522096e-05, + "loss": 3.3861, + "step": 2176512 + }, + { + "epoch": 0.01, + "learning_rate": 1.435893689771044e-05, + "loss": 3.3805, + "step": 2177024 + }, + { + "epoch": 0.01, + "learning_rate": 1.435055095019992e-05, + "loss": 3.3859, + "step": 2177536 + }, + { + "epoch": 0.01, + "learning_rate": 1.434218138149313e-05, + "loss": 3.3875, + "step": 2178048 + }, + { + "epoch": 0.01, + "learning_rate": 1.433379543398261e-05, + "loss": 3.39, + "step": 2178560 + }, + { + "epoch": 0.01, + "learning_rate": 1.432540948647209e-05, + "loss": 3.4019, + "step": 2179072 + }, + { + "epoch": 0.01, + "learning_rate": 1.4317023538961572e-05, + "loss": 3.3905, + "step": 2179584 + }, + { + "epoch": 0.01, + "learning_rate": 1.4308653970254781e-05, + "loss": 3.3679, + "step": 2180096 + }, + { + "epoch": 0.01, + "learning_rate": 1.4300268022744263e-05, + "loss": 3.3791, + "step": 2180608 + }, + { + "epoch": 0.01, + "learning_rate": 1.4291882075233743e-05, + "loss": 3.3911, + "step": 2181120 + }, + { + "epoch": 0.01, + "learning_rate": 1.4283496127723223e-05, + "loss": 3.389, + "step": 2181632 + }, + { + "epoch": 0.01, + "learning_rate": 1.4275126559016434e-05, + "loss": 3.3802, + "step": 2182144 + }, + { + "epoch": 0.01, + "learning_rate": 1.4266740611505913e-05, + "loss": 3.3915, + "step": 2182656 + }, + { + "epoch": 0.02, + "learning_rate": 1.4258354663995393e-05, + "loss": 3.3862, + "step": 2183168 + }, + { + "epoch": 0.02, + "learning_rate": 1.4249968716484873e-05, + "loss": 3.3747, + "step": 2183680 + }, + { + "epoch": 0.02, + "learning_rate": 1.4241599147778084e-05, + "loss": 3.3779, + "step": 2184192 + }, + { + "epoch": 0.02, + "learning_rate": 1.4233213200267564e-05, + "loss": 3.3894, + "step": 2184704 + }, + { + "epoch": 0.02, + "learning_rate": 1.4224827252757044e-05, + "loss": 3.3884, + "step": 2185216 + }, + { + "epoch": 0.02, + "learning_rate": 1.4216441305246526e-05, + "loss": 3.3947, + "step": 2185728 + }, + { + "epoch": 0.02, + "learning_rate": 1.4208071736539735e-05, + "loss": 3.3748, + "step": 2186240 + }, + { + "epoch": 0.02, + "learning_rate": 1.4199685789029216e-05, + "loss": 3.3776, + "step": 2186752 + }, + { + "epoch": 0.02, + "learning_rate": 1.4191299841518696e-05, + "loss": 3.3858, + "step": 2187264 + }, + { + "epoch": 0.02, + "learning_rate": 1.4182913894008176e-05, + "loss": 3.3889, + "step": 2187776 + }, + { + "epoch": 0.02, + "learning_rate": 1.4174544325301387e-05, + "loss": 3.3869, + "step": 2188288 + }, + { + "epoch": 0.02, + "learning_rate": 1.4166158377790867e-05, + "loss": 3.3779, + "step": 2188800 + }, + { + "epoch": 0.02, + "learning_rate": 1.4157772430280347e-05, + "loss": 3.379, + "step": 2189312 + }, + { + "epoch": 0.02, + "learning_rate": 1.4149386482769827e-05, + "loss": 3.3699, + "step": 2189824 + }, + { + "epoch": 0.02, + "learning_rate": 1.4141016914063038e-05, + "loss": 3.3879, + "step": 2190336 + }, + { + "epoch": 0.02, + "learning_rate": 1.4132630966552518e-05, + "loss": 3.3742, + "step": 2190848 + }, + { + "epoch": 0.02, + "learning_rate": 1.4124245019041998e-05, + "loss": 3.375, + "step": 2191360 + }, + { + "epoch": 0.02, + "learning_rate": 1.411585907153148e-05, + "loss": 3.3861, + "step": 2191872 + }, + { + "epoch": 0.02, + "learning_rate": 1.4107489502824688e-05, + "loss": 3.3785, + "step": 2192384 + }, + { + "epoch": 0.02, + "learning_rate": 1.4099103555314168e-05, + "loss": 3.3793, + "step": 2192896 + }, + { + "epoch": 0.02, + "learning_rate": 1.409071760780365e-05, + "loss": 3.3808, + "step": 2193408 + }, + { + "epoch": 0.02, + "learning_rate": 1.408233166029313e-05, + "loss": 3.3686, + "step": 2193920 + }, + { + "epoch": 0.02, + "learning_rate": 1.4073962091586341e-05, + "loss": 3.3861, + "step": 2194432 + }, + { + "epoch": 0.02, + "learning_rate": 1.406557614407582e-05, + "loss": 3.3733, + "step": 2194944 + }, + { + "epoch": 0.02, + "learning_rate": 1.40571901965653e-05, + "loss": 3.3835, + "step": 2195456 + }, + { + "epoch": 0.02, + "learning_rate": 1.404880424905478e-05, + "loss": 3.3882, + "step": 2195968 + }, + { + "epoch": 0.02, + "learning_rate": 1.4040434680347992e-05, + "loss": 3.3895, + "step": 2196480 + }, + { + "epoch": 0.02, + "learning_rate": 1.4032048732837471e-05, + "loss": 3.3813, + "step": 2196992 + }, + { + "epoch": 0.02, + "learning_rate": 1.4023662785326951e-05, + "loss": 3.3841, + "step": 2197504 + }, + { + "epoch": 0.02, + "learning_rate": 1.4015276837816433e-05, + "loss": 3.3884, + "step": 2198016 + }, + { + "epoch": 0.02, + "learning_rate": 1.4006907269109642e-05, + "loss": 3.3842, + "step": 2198528 + }, + { + "epoch": 0.02, + "learning_rate": 1.3998521321599122e-05, + "loss": 3.3794, + "step": 2199040 + }, + { + "epoch": 0.02, + "learning_rate": 1.3990135374088604e-05, + "loss": 3.3847, + "step": 2199552 + }, + { + "epoch": 0.02, + "learning_rate": 1.398174942657808e-05, + "loss": 3.3801, + "step": 2200064 + }, + { + "epoch": 0.02, + "learning_rate": 1.3973379857871295e-05, + "loss": 3.3882, + "step": 2200576 + }, + { + "epoch": 0.02, + "learning_rate": 1.3964993910360774e-05, + "loss": 3.374, + "step": 2201088 + }, + { + "epoch": 0.02, + "learning_rate": 1.3956607962850254e-05, + "loss": 3.3785, + "step": 2201600 + }, + { + "epoch": 0.02, + "learning_rate": 1.3948238394143465e-05, + "loss": 3.3749, + "step": 2202112 + }, + { + "epoch": 0.02, + "learning_rate": 1.3939852446632945e-05, + "loss": 3.3812, + "step": 2202624 + }, + { + "epoch": 0.02, + "learning_rate": 1.3931466499122425e-05, + "loss": 3.3898, + "step": 2203136 + }, + { + "epoch": 0.02, + "learning_rate": 1.3923080551611905e-05, + "loss": 3.38, + "step": 2203648 + }, + { + "epoch": 0.02, + "learning_rate": 1.3914710982905116e-05, + "loss": 3.3912, + "step": 2204160 + }, + { + "epoch": 0.02, + "learning_rate": 1.3906325035394596e-05, + "loss": 3.3778, + "step": 2204672 + }, + { + "epoch": 0.02, + "learning_rate": 1.3897939087884076e-05, + "loss": 3.3872, + "step": 2205184 + }, + { + "epoch": 0.02, + "learning_rate": 1.3889553140373554e-05, + "loss": 3.3852, + "step": 2205696 + }, + { + "epoch": 0.02, + "learning_rate": 1.3881183571666767e-05, + "loss": 3.3893, + "step": 2206208 + }, + { + "epoch": 0.02, + "learning_rate": 1.3872797624156248e-05, + "loss": 3.3828, + "step": 2206720 + }, + { + "epoch": 0.02, + "learning_rate": 1.3864411676645728e-05, + "loss": 3.3818, + "step": 2207232 + }, + { + "epoch": 0.02, + "learning_rate": 1.3856025729135205e-05, + "loss": 3.3816, + "step": 2207744 + }, + { + "epoch": 0.02, + "learning_rate": 1.3847639781624686e-05, + "loss": 3.3923, + "step": 2208256 + }, + { + "epoch": 0.02, + "learning_rate": 1.3839270212917899e-05, + "loss": 3.3783, + "step": 2208768 + }, + { + "epoch": 0.02, + "learning_rate": 1.3830884265407379e-05, + "loss": 3.3808, + "step": 2209280 + }, + { + "epoch": 0.02, + "learning_rate": 1.3822498317896857e-05, + "loss": 3.3877, + "step": 2209792 + }, + { + "epoch": 0.02, + "learning_rate": 1.3814112370386337e-05, + "loss": 3.3783, + "step": 2210304 + }, + { + "epoch": 0.02, + "learning_rate": 1.380575918048328e-05, + "loss": 3.3778, + "step": 2210816 + }, + { + "epoch": 0.02, + "learning_rate": 1.379737323297276e-05, + "loss": 3.3897, + "step": 2211328 + }, + { + "epoch": 0.02, + "learning_rate": 1.378898728546224e-05, + "loss": 3.3764, + "step": 2211840 + }, + { + "epoch": 0.02, + "learning_rate": 1.378060133795172e-05, + "loss": 3.3816, + "step": 2212352 + }, + { + "epoch": 0.02, + "learning_rate": 1.3772215390441202e-05, + "loss": 3.3765, + "step": 2212864 + }, + { + "epoch": 0.03, + "eval_loss": 3.8634185791015625, + "eval_runtime": 328.9859, + "eval_samples_per_second": 1159.901, + "eval_steps_per_second": 36.248, + "step": 2213280 + }, + { + "epoch": 0.0, + "learning_rate": 1.3763829442930678e-05, + "loss": 3.3786, + "step": 2213376 + }, + { + "epoch": 0.0, + "learning_rate": 1.3755443495420158e-05, + "loss": 3.3718, + "step": 2213888 + }, + { + "epoch": 0.0, + "learning_rate": 1.374705754790964e-05, + "loss": 3.3859, + "step": 2214400 + }, + { + "epoch": 0.0, + "learning_rate": 1.373867160039912e-05, + "loss": 3.3914, + "step": 2214912 + }, + { + "epoch": 0.0, + "learning_rate": 1.3730302031692329e-05, + "loss": 3.3865, + "step": 2215424 + }, + { + "epoch": 0.0, + "learning_rate": 1.372191608418181e-05, + "loss": 3.3838, + "step": 2215936 + }, + { + "epoch": 0.0, + "learning_rate": 1.371353013667129e-05, + "loss": 3.3745, + "step": 2216448 + }, + { + "epoch": 0.0, + "learning_rate": 1.370514418916077e-05, + "loss": 3.3841, + "step": 2216960 + }, + { + "epoch": 0.0, + "learning_rate": 1.3696774620453981e-05, + "loss": 3.3758, + "step": 2217472 + }, + { + "epoch": 0.0, + "learning_rate": 1.3688388672943461e-05, + "loss": 3.383, + "step": 2217984 + }, + { + "epoch": 0.0, + "learning_rate": 1.3680002725432941e-05, + "loss": 3.3805, + "step": 2218496 + }, + { + "epoch": 0.0, + "learning_rate": 1.3671616777922421e-05, + "loss": 3.382, + "step": 2219008 + }, + { + "epoch": 0.0, + "learning_rate": 1.3663247209215632e-05, + "loss": 3.3882, + "step": 2219520 + }, + { + "epoch": 0.0, + "learning_rate": 1.3654861261705112e-05, + "loss": 3.3689, + "step": 2220032 + }, + { + "epoch": 0.0, + "learning_rate": 1.3646475314194592e-05, + "loss": 3.3665, + "step": 2220544 + }, + { + "epoch": 0.0, + "learning_rate": 1.3638089366684074e-05, + "loss": 3.37, + "step": 2221056 + }, + { + "epoch": 0.0, + "learning_rate": 1.3629719797977283e-05, + "loss": 3.3904, + "step": 2221568 + }, + { + "epoch": 0.0, + "learning_rate": 1.3621333850466764e-05, + "loss": 3.3773, + "step": 2222080 + }, + { + "epoch": 0.0, + "learning_rate": 1.3612947902956244e-05, + "loss": 3.3777, + "step": 2222592 + }, + { + "epoch": 0.0, + "learning_rate": 1.3604561955445724e-05, + "loss": 3.387, + "step": 2223104 + }, + { + "epoch": 0.0, + "learning_rate": 1.3596192386738935e-05, + "loss": 3.3941, + "step": 2223616 + }, + { + "epoch": 0.0, + "learning_rate": 1.3587806439228415e-05, + "loss": 3.3769, + "step": 2224128 + }, + { + "epoch": 0.0, + "learning_rate": 1.3579420491717895e-05, + "loss": 3.3782, + "step": 2224640 + }, + { + "epoch": 0.0, + "learning_rate": 1.3571034544207375e-05, + "loss": 3.3794, + "step": 2225152 + }, + { + "epoch": 0.0, + "learning_rate": 1.3562664975500586e-05, + "loss": 3.3902, + "step": 2225664 + }, + { + "epoch": 0.0, + "learning_rate": 1.3554279027990066e-05, + "loss": 3.3757, + "step": 2226176 + }, + { + "epoch": 0.0, + "learning_rate": 1.3545893080479546e-05, + "loss": 3.3726, + "step": 2226688 + }, + { + "epoch": 0.0, + "learning_rate": 1.3537507132969027e-05, + "loss": 3.3934, + "step": 2227200 + }, + { + "epoch": 0.0, + "learning_rate": 1.3529137564262236e-05, + "loss": 3.3646, + "step": 2227712 + }, + { + "epoch": 0.0, + "learning_rate": 1.3520751616751718e-05, + "loss": 3.3682, + "step": 2228224 + }, + { + "epoch": 0.01, + "learning_rate": 1.3512365669241198e-05, + "loss": 3.3706, + "step": 2228736 + }, + { + "epoch": 0.01, + "learning_rate": 1.3503979721730678e-05, + "loss": 3.3742, + "step": 2229248 + }, + { + "epoch": 0.01, + "learning_rate": 1.3495610153023889e-05, + "loss": 3.3828, + "step": 2229760 + }, + { + "epoch": 0.01, + "learning_rate": 1.3487224205513369e-05, + "loss": 3.3905, + "step": 2230272 + }, + { + "epoch": 0.01, + "learning_rate": 1.3478838258002849e-05, + "loss": 3.3734, + "step": 2230784 + }, + { + "epoch": 0.01, + "learning_rate": 1.3470452310492329e-05, + "loss": 3.3748, + "step": 2231296 + }, + { + "epoch": 0.01, + "learning_rate": 1.346208274178554e-05, + "loss": 3.385, + "step": 2231808 + }, + { + "epoch": 0.01, + "learning_rate": 1.345369679427502e-05, + "loss": 3.3651, + "step": 2232320 + }, + { + "epoch": 0.01, + "learning_rate": 1.34453108467645e-05, + "loss": 3.3732, + "step": 2232832 + }, + { + "epoch": 0.01, + "learning_rate": 1.3436924899253978e-05, + "loss": 3.3727, + "step": 2233344 + }, + { + "epoch": 0.01, + "learning_rate": 1.342855533054719e-05, + "loss": 3.3729, + "step": 2233856 + }, + { + "epoch": 0.01, + "learning_rate": 1.3420169383036672e-05, + "loss": 3.3696, + "step": 2234368 + }, + { + "epoch": 0.01, + "learning_rate": 1.3411783435526152e-05, + "loss": 3.3903, + "step": 2234880 + }, + { + "epoch": 0.01, + "learning_rate": 1.3403397488015628e-05, + "loss": 3.3757, + "step": 2235392 + }, + { + "epoch": 0.01, + "learning_rate": 1.3395027919308842e-05, + "loss": 3.378, + "step": 2235904 + }, + { + "epoch": 0.01, + "learning_rate": 1.3386641971798322e-05, + "loss": 3.3808, + "step": 2236416 + }, + { + "epoch": 0.01, + "learning_rate": 1.3378256024287802e-05, + "loss": 3.375, + "step": 2236928 + }, + { + "epoch": 0.01, + "learning_rate": 1.336987007677728e-05, + "loss": 3.3735, + "step": 2237440 + }, + { + "epoch": 0.01, + "learning_rate": 1.3361500508070493e-05, + "loss": 3.352, + "step": 2237952 + }, + { + "epoch": 0.01, + "learning_rate": 1.3353114560559973e-05, + "loss": 3.3727, + "step": 2238464 + }, + { + "epoch": 0.01, + "learning_rate": 1.3344728613049451e-05, + "loss": 3.3859, + "step": 2238976 + }, + { + "epoch": 0.01, + "learning_rate": 1.3336342665538931e-05, + "loss": 3.3791, + "step": 2239488 + }, + { + "epoch": 0.01, + "learning_rate": 1.3327973096832144e-05, + "loss": 3.3692, + "step": 2240000 + }, + { + "epoch": 0.01, + "learning_rate": 1.3319587149321625e-05, + "loss": 3.3663, + "step": 2240512 + }, + { + "epoch": 0.01, + "learning_rate": 1.3311201201811102e-05, + "loss": 3.371, + "step": 2241024 + }, + { + "epoch": 0.01, + "learning_rate": 1.3302815254300582e-05, + "loss": 3.3622, + "step": 2241536 + }, + { + "epoch": 0.01, + "learning_rate": 1.3294445685593796e-05, + "loss": 3.395, + "step": 2242048 + }, + { + "epoch": 0.01, + "learning_rate": 1.3286059738083276e-05, + "loss": 3.363, + "step": 2242560 + }, + { + "epoch": 0.01, + "learning_rate": 1.3277673790572753e-05, + "loss": 3.3805, + "step": 2243072 + }, + { + "epoch": 0.01, + "learning_rate": 1.3269287843062234e-05, + "loss": 3.3801, + "step": 2243584 + }, + { + "epoch": 0.01, + "learning_rate": 1.3260918274355447e-05, + "loss": 3.3581, + "step": 2244096 + }, + { + "epoch": 0.01, + "learning_rate": 1.3252532326844925e-05, + "loss": 3.3729, + "step": 2244608 + }, + { + "epoch": 0.01, + "learning_rate": 1.3244146379334405e-05, + "loss": 3.3626, + "step": 2245120 + }, + { + "epoch": 0.01, + "learning_rate": 1.3235776810627617e-05, + "loss": 3.3661, + "step": 2245632 + }, + { + "epoch": 0.01, + "learning_rate": 1.3227390863117097e-05, + "loss": 3.3686, + "step": 2246144 + }, + { + "epoch": 0.01, + "learning_rate": 1.3219004915606576e-05, + "loss": 3.3831, + "step": 2246656 + }, + { + "epoch": 0.01, + "learning_rate": 1.3210618968096056e-05, + "loss": 3.3744, + "step": 2247168 + }, + { + "epoch": 0.01, + "learning_rate": 1.3202249399389268e-05, + "loss": 3.3687, + "step": 2247680 + }, + { + "epoch": 0.01, + "learning_rate": 1.319386345187875e-05, + "loss": 3.3612, + "step": 2248192 + }, + { + "epoch": 0.01, + "learning_rate": 1.3185477504368226e-05, + "loss": 3.3734, + "step": 2248704 + }, + { + "epoch": 0.01, + "learning_rate": 1.3177091556857706e-05, + "loss": 3.375, + "step": 2249216 + }, + { + "epoch": 0.01, + "learning_rate": 1.316872198815092e-05, + "loss": 3.3775, + "step": 2249728 + }, + { + "epoch": 0.01, + "learning_rate": 1.3160336040640397e-05, + "loss": 3.3705, + "step": 2250240 + }, + { + "epoch": 0.01, + "learning_rate": 1.3151950093129877e-05, + "loss": 3.3761, + "step": 2250752 + }, + { + "epoch": 0.01, + "learning_rate": 1.3143564145619359e-05, + "loss": 3.3862, + "step": 2251264 + }, + { + "epoch": 0.01, + "learning_rate": 1.3135194576912571e-05, + "loss": 3.3712, + "step": 2251776 + }, + { + "epoch": 0.01, + "learning_rate": 1.312680862940205e-05, + "loss": 3.3716, + "step": 2252288 + }, + { + "epoch": 0.01, + "learning_rate": 1.311842268189153e-05, + "loss": 3.3734, + "step": 2252800 + }, + { + "epoch": 0.01, + "learning_rate": 1.311003673438101e-05, + "loss": 3.3747, + "step": 2253312 + }, + { + "epoch": 0.01, + "learning_rate": 1.3101667165674222e-05, + "loss": 3.3766, + "step": 2253824 + }, + { + "epoch": 0.01, + "learning_rate": 1.30932812181637e-05, + "loss": 3.3795, + "step": 2254336 + }, + { + "epoch": 0.01, + "learning_rate": 1.308489527065318e-05, + "loss": 3.3811, + "step": 2254848 + }, + { + "epoch": 0.01, + "learning_rate": 1.307650932314266e-05, + "loss": 3.3874, + "step": 2255360 + }, + { + "epoch": 0.01, + "learning_rate": 1.306813975443587e-05, + "loss": 3.3802, + "step": 2255872 + }, + { + "epoch": 0.01, + "learning_rate": 1.305975380692535e-05, + "loss": 3.36, + "step": 2256384 + }, + { + "epoch": 0.01, + "learning_rate": 1.305136785941483e-05, + "loss": 3.3673, + "step": 2256896 + }, + { + "epoch": 0.01, + "learning_rate": 1.3042981911904312e-05, + "loss": 3.3818, + "step": 2257408 + }, + { + "epoch": 0.01, + "learning_rate": 1.3034612343197521e-05, + "loss": 3.3786, + "step": 2257920 + }, + { + "epoch": 0.01, + "learning_rate": 1.3026226395687003e-05, + "loss": 3.373, + "step": 2258432 + }, + { + "epoch": 0.01, + "learning_rate": 1.3017840448176483e-05, + "loss": 3.3772, + "step": 2258944 + }, + { + "epoch": 0.02, + "learning_rate": 1.3009454500665963e-05, + "loss": 3.3826, + "step": 2259456 + }, + { + "epoch": 0.02, + "learning_rate": 1.3001084931959174e-05, + "loss": 3.3646, + "step": 2259968 + }, + { + "epoch": 0.02, + "learning_rate": 1.2992698984448654e-05, + "loss": 3.3678, + "step": 2260480 + }, + { + "epoch": 0.02, + "learning_rate": 1.2984313036938134e-05, + "loss": 3.381, + "step": 2260992 + }, + { + "epoch": 0.02, + "learning_rate": 1.2975927089427614e-05, + "loss": 3.3753, + "step": 2261504 + }, + { + "epoch": 0.02, + "learning_rate": 1.2967557520720824e-05, + "loss": 3.3864, + "step": 2262016 + }, + { + "epoch": 0.02, + "learning_rate": 1.2959171573210304e-05, + "loss": 3.3644, + "step": 2262528 + }, + { + "epoch": 0.02, + "learning_rate": 1.2950785625699784e-05, + "loss": 3.3664, + "step": 2263040 + }, + { + "epoch": 0.02, + "learning_rate": 1.2942399678189266e-05, + "loss": 3.3768, + "step": 2263552 + }, + { + "epoch": 0.02, + "learning_rate": 1.2934030109482475e-05, + "loss": 3.3794, + "step": 2264064 + }, + { + "epoch": 0.02, + "learning_rate": 1.2925644161971957e-05, + "loss": 3.3777, + "step": 2264576 + }, + { + "epoch": 0.02, + "learning_rate": 1.2917258214461437e-05, + "loss": 3.369, + "step": 2265088 + }, + { + "epoch": 0.02, + "learning_rate": 1.2908872266950917e-05, + "loss": 3.3665, + "step": 2265600 + }, + { + "epoch": 0.02, + "learning_rate": 1.2900502698244127e-05, + "loss": 3.3598, + "step": 2266112 + }, + { + "epoch": 0.02, + "learning_rate": 1.2892116750733607e-05, + "loss": 3.378, + "step": 2266624 + }, + { + "epoch": 0.02, + "learning_rate": 1.2883730803223087e-05, + "loss": 3.365, + "step": 2267136 + }, + { + "epoch": 0.02, + "learning_rate": 1.2875344855712567e-05, + "loss": 3.3671, + "step": 2267648 + }, + { + "epoch": 0.02, + "learning_rate": 1.2866975287005778e-05, + "loss": 3.3782, + "step": 2268160 + }, + { + "epoch": 0.02, + "learning_rate": 1.2858589339495258e-05, + "loss": 3.3707, + "step": 2268672 + }, + { + "epoch": 0.02, + "learning_rate": 1.2850203391984738e-05, + "loss": 3.3625, + "step": 2269184 + }, + { + "epoch": 0.02, + "learning_rate": 1.284181744447422e-05, + "loss": 3.3749, + "step": 2269696 + }, + { + "epoch": 0.02, + "learning_rate": 1.2833447875767429e-05, + "loss": 3.361, + "step": 2270208 + }, + { + "epoch": 0.02, + "learning_rate": 1.282506192825691e-05, + "loss": 3.3766, + "step": 2270720 + }, + { + "epoch": 0.02, + "learning_rate": 1.281667598074639e-05, + "loss": 3.3659, + "step": 2271232 + }, + { + "epoch": 0.02, + "learning_rate": 1.280829003323587e-05, + "loss": 3.372, + "step": 2271744 + }, + { + "epoch": 0.02, + "learning_rate": 1.2799920464529081e-05, + "loss": 3.3777, + "step": 2272256 + }, + { + "epoch": 0.02, + "learning_rate": 1.2791534517018561e-05, + "loss": 3.3761, + "step": 2272768 + }, + { + "epoch": 0.02, + "learning_rate": 1.2783148569508041e-05, + "loss": 3.3714, + "step": 2273280 + }, + { + "epoch": 0.02, + "learning_rate": 1.2774762621997521e-05, + "loss": 3.3741, + "step": 2273792 + }, + { + "epoch": 0.02, + "learning_rate": 1.2766393053290732e-05, + "loss": 3.3824, + "step": 2274304 + }, + { + "epoch": 0.02, + "learning_rate": 1.2758007105780212e-05, + "loss": 3.3701, + "step": 2274816 + }, + { + "epoch": 0.02, + "learning_rate": 1.2749621158269692e-05, + "loss": 3.3674, + "step": 2275328 + }, + { + "epoch": 0.02, + "learning_rate": 1.2741235210759173e-05, + "loss": 3.3724, + "step": 2275840 + }, + { + "epoch": 0.02, + "learning_rate": 1.2732865642052382e-05, + "loss": 3.3732, + "step": 2276352 + }, + { + "epoch": 0.02, + "learning_rate": 1.2724479694541862e-05, + "loss": 3.3745, + "step": 2276864 + }, + { + "epoch": 0.02, + "learning_rate": 1.2716093747031344e-05, + "loss": 3.3664, + "step": 2277376 + }, + { + "epoch": 0.02, + "learning_rate": 1.270770779952082e-05, + "loss": 3.3682, + "step": 2277888 + }, + { + "epoch": 0.02, + "learning_rate": 1.2699338230814035e-05, + "loss": 3.3679, + "step": 2278400 + }, + { + "epoch": 0.02, + "learning_rate": 1.2690952283303515e-05, + "loss": 3.3682, + "step": 2278912 + }, + { + "epoch": 0.02, + "learning_rate": 1.2682566335792995e-05, + "loss": 3.376, + "step": 2279424 + }, + { + "epoch": 0.02, + "learning_rate": 1.2674180388282473e-05, + "loss": 3.3757, + "step": 2279936 + }, + { + "epoch": 0.02, + "learning_rate": 1.2665810819575685e-05, + "loss": 3.3817, + "step": 2280448 + }, + { + "epoch": 0.02, + "learning_rate": 1.2657424872065165e-05, + "loss": 3.3651, + "step": 2280960 + }, + { + "epoch": 0.02, + "learning_rate": 1.2649038924554645e-05, + "loss": 3.3806, + "step": 2281472 + }, + { + "epoch": 0.02, + "learning_rate": 1.2640652977044124e-05, + "loss": 3.3719, + "step": 2281984 + }, + { + "epoch": 0.02, + "learning_rate": 1.2632283408337336e-05, + "loss": 3.3823, + "step": 2282496 + }, + { + "epoch": 0.02, + "learning_rate": 1.2623897460826816e-05, + "loss": 3.37, + "step": 2283008 + }, + { + "epoch": 0.02, + "learning_rate": 1.2615511513316294e-05, + "loss": 3.3728, + "step": 2283520 + }, + { + "epoch": 0.02, + "learning_rate": 1.2607125565805774e-05, + "loss": 3.3719, + "step": 2284032 + }, + { + "epoch": 0.02, + "learning_rate": 1.2598755997098988e-05, + "loss": 3.3834, + "step": 2284544 + }, + { + "epoch": 0.02, + "learning_rate": 1.2590370049588468e-05, + "loss": 3.3705, + "step": 2285056 + }, + { + "epoch": 0.02, + "learning_rate": 1.2581984102077945e-05, + "loss": 3.3696, + "step": 2285568 + }, + { + "epoch": 0.02, + "learning_rate": 1.2573598154567427e-05, + "loss": 3.3792, + "step": 2286080 + }, + { + "epoch": 0.02, + "learning_rate": 1.2565228585860639e-05, + "loss": 3.3703, + "step": 2286592 + }, + { + "epoch": 0.02, + "learning_rate": 1.255685901715385e-05, + "loss": 3.3691, + "step": 2287104 + }, + { + "epoch": 0.02, + "learning_rate": 1.254847306964333e-05, + "loss": 3.3809, + "step": 2287616 + }, + { + "epoch": 0.02, + "learning_rate": 1.254008712213281e-05, + "loss": 3.3625, + "step": 2288128 + }, + { + "epoch": 0.02, + "learning_rate": 1.253170117462229e-05, + "loss": 3.3756, + "step": 2288640 + }, + { + "epoch": 0.02, + "learning_rate": 1.2523315227111768e-05, + "loss": 3.3637, + "step": 2289152 + }, + { + "epoch": 0.03, + "eval_loss": 3.865683078765869, + "eval_runtime": 308.2985, + "eval_samples_per_second": 1237.732, + "eval_steps_per_second": 38.68, + "step": 2289600 + }, + { + "epoch": 0.0, + "learning_rate": 1.2514929279601248e-05, + "loss": 3.3731, + "step": 2289664 + }, + { + "epoch": 0.0, + "learning_rate": 1.2506543332090728e-05, + "loss": 3.3644, + "step": 2290176 + }, + { + "epoch": 0.0, + "learning_rate": 1.2498157384580208e-05, + "loss": 3.3736, + "step": 2290688 + }, + { + "epoch": 0.0, + "learning_rate": 1.248977143706969e-05, + "loss": 3.3831, + "step": 2291200 + }, + { + "epoch": 0.0, + "learning_rate": 1.24814018683629e-05, + "loss": 3.3806, + "step": 2291712 + }, + { + "epoch": 0.0, + "learning_rate": 1.247301592085238e-05, + "loss": 3.3757, + "step": 2292224 + }, + { + "epoch": 0.0, + "learning_rate": 1.246462997334186e-05, + "loss": 3.3605, + "step": 2292736 + }, + { + "epoch": 0.0, + "learning_rate": 1.245624402583134e-05, + "loss": 3.375, + "step": 2293248 + }, + { + "epoch": 0.0, + "learning_rate": 1.2447874457124551e-05, + "loss": 3.3692, + "step": 2293760 + }, + { + "epoch": 0.0, + "learning_rate": 1.2439488509614031e-05, + "loss": 3.3698, + "step": 2294272 + }, + { + "epoch": 0.0, + "learning_rate": 1.2431102562103511e-05, + "loss": 3.3709, + "step": 2294784 + }, + { + "epoch": 0.0, + "learning_rate": 1.2422716614592989e-05, + "loss": 3.3752, + "step": 2295296 + }, + { + "epoch": 0.0, + "learning_rate": 1.2414347045886202e-05, + "loss": 3.3789, + "step": 2295808 + }, + { + "epoch": 0.0, + "learning_rate": 1.2405961098375682e-05, + "loss": 3.3611, + "step": 2296320 + }, + { + "epoch": 0.0, + "learning_rate": 1.2397575150865162e-05, + "loss": 3.3535, + "step": 2296832 + }, + { + "epoch": 0.0, + "learning_rate": 1.2389189203354641e-05, + "loss": 3.3604, + "step": 2297344 + }, + { + "epoch": 0.0, + "learning_rate": 1.2380819634647852e-05, + "loss": 3.3769, + "step": 2297856 + }, + { + "epoch": 0.0, + "learning_rate": 1.2372433687137334e-05, + "loss": 3.3709, + "step": 2298368 + }, + { + "epoch": 0.0, + "learning_rate": 1.2364047739626814e-05, + "loss": 3.3677, + "step": 2298880 + }, + { + "epoch": 0.0, + "learning_rate": 1.2355661792116292e-05, + "loss": 3.3743, + "step": 2299392 + }, + { + "epoch": 0.0, + "learning_rate": 1.2347292223409505e-05, + "loss": 3.3877, + "step": 2299904 + }, + { + "epoch": 0.0, + "learning_rate": 1.2338906275898985e-05, + "loss": 3.3657, + "step": 2300416 + }, + { + "epoch": 0.0, + "learning_rate": 1.2330520328388463e-05, + "loss": 3.3696, + "step": 2300928 + }, + { + "epoch": 0.0, + "learning_rate": 1.2322134380877943e-05, + "loss": 3.3704, + "step": 2301440 + }, + { + "epoch": 0.0, + "learning_rate": 1.2313764812171155e-05, + "loss": 3.3817, + "step": 2301952 + }, + { + "epoch": 0.0, + "learning_rate": 1.2305378864660635e-05, + "loss": 3.3622, + "step": 2302464 + }, + { + "epoch": 0.0, + "learning_rate": 1.2296992917150115e-05, + "loss": 3.3653, + "step": 2302976 + }, + { + "epoch": 0.0, + "learning_rate": 1.2288606969639595e-05, + "loss": 3.3816, + "step": 2303488 + }, + { + "epoch": 0.0, + "learning_rate": 1.2280237400932806e-05, + "loss": 3.3585, + "step": 2304000 + }, + { + "epoch": 0.0, + "learning_rate": 1.2271851453422286e-05, + "loss": 3.3596, + "step": 2304512 + }, + { + "epoch": 0.01, + "learning_rate": 1.2263465505911766e-05, + "loss": 3.3584, + "step": 2305024 + }, + { + "epoch": 0.01, + "learning_rate": 1.2255079558401246e-05, + "loss": 3.369, + "step": 2305536 + }, + { + "epoch": 0.01, + "learning_rate": 1.2246709989694458e-05, + "loss": 3.3727, + "step": 2306048 + }, + { + "epoch": 0.01, + "learning_rate": 1.2238324042183937e-05, + "loss": 3.377, + "step": 2306560 + }, + { + "epoch": 0.01, + "learning_rate": 1.2229938094673417e-05, + "loss": 3.3693, + "step": 2307072 + }, + { + "epoch": 0.01, + "learning_rate": 1.2221552147162896e-05, + "loss": 3.3651, + "step": 2307584 + }, + { + "epoch": 0.01, + "learning_rate": 1.2213182578456109e-05, + "loss": 3.3764, + "step": 2308096 + }, + { + "epoch": 0.01, + "learning_rate": 1.2204796630945587e-05, + "loss": 3.3523, + "step": 2308608 + }, + { + "epoch": 0.01, + "learning_rate": 1.2196410683435069e-05, + "loss": 3.365, + "step": 2309120 + }, + { + "epoch": 0.01, + "learning_rate": 1.2188024735924549e-05, + "loss": 3.364, + "step": 2309632 + }, + { + "epoch": 0.01, + "learning_rate": 1.217965516721776e-05, + "loss": 3.3641, + "step": 2310144 + }, + { + "epoch": 0.01, + "learning_rate": 1.217126921970724e-05, + "loss": 3.3579, + "step": 2310656 + }, + { + "epoch": 0.01, + "learning_rate": 1.216288327219672e-05, + "loss": 3.3797, + "step": 2311168 + }, + { + "epoch": 0.01, + "learning_rate": 1.21544973246862e-05, + "loss": 3.3645, + "step": 2311680 + }, + { + "epoch": 0.01, + "learning_rate": 1.214612775597941e-05, + "loss": 3.3691, + "step": 2312192 + }, + { + "epoch": 0.01, + "learning_rate": 1.213774180846889e-05, + "loss": 3.3721, + "step": 2312704 + }, + { + "epoch": 0.01, + "learning_rate": 1.212935586095837e-05, + "loss": 3.3655, + "step": 2313216 + }, + { + "epoch": 0.01, + "learning_rate": 1.212096991344785e-05, + "loss": 3.3636, + "step": 2313728 + }, + { + "epoch": 0.01, + "learning_rate": 1.2112600344741061e-05, + "loss": 3.3448, + "step": 2314240 + }, + { + "epoch": 0.01, + "learning_rate": 1.2104214397230541e-05, + "loss": 3.3622, + "step": 2314752 + }, + { + "epoch": 0.01, + "learning_rate": 1.209582844972002e-05, + "loss": 3.3746, + "step": 2315264 + }, + { + "epoch": 0.01, + "learning_rate": 1.20874425022095e-05, + "loss": 3.3665, + "step": 2315776 + }, + { + "epoch": 0.01, + "learning_rate": 1.2079072933502712e-05, + "loss": 3.361, + "step": 2316288 + }, + { + "epoch": 0.01, + "learning_rate": 1.2070686985992193e-05, + "loss": 3.3537, + "step": 2316800 + }, + { + "epoch": 0.01, + "learning_rate": 1.2062301038481673e-05, + "loss": 3.3625, + "step": 2317312 + }, + { + "epoch": 0.01, + "learning_rate": 1.2053915090971151e-05, + "loss": 3.3502, + "step": 2317824 + }, + { + "epoch": 0.01, + "learning_rate": 1.2045545522264364e-05, + "loss": 3.3825, + "step": 2318336 + }, + { + "epoch": 0.01, + "learning_rate": 1.2037159574753844e-05, + "loss": 3.3579, + "step": 2318848 + }, + { + "epoch": 0.01, + "learning_rate": 1.2028773627243324e-05, + "loss": 3.3673, + "step": 2319360 + }, + { + "epoch": 0.01, + "learning_rate": 1.2020387679732804e-05, + "loss": 3.3712, + "step": 2319872 + }, + { + "epoch": 0.01, + "learning_rate": 1.2012018111026015e-05, + "loss": 3.3517, + "step": 2320384 + }, + { + "epoch": 0.01, + "learning_rate": 1.2003632163515495e-05, + "loss": 3.3615, + "step": 2320896 + }, + { + "epoch": 0.01, + "learning_rate": 1.1995246216004975e-05, + "loss": 3.3567, + "step": 2321408 + }, + { + "epoch": 0.01, + "learning_rate": 1.1986876647298185e-05, + "loss": 3.3541, + "step": 2321920 + }, + { + "epoch": 0.01, + "learning_rate": 1.1978490699787665e-05, + "loss": 3.3536, + "step": 2322432 + }, + { + "epoch": 0.01, + "learning_rate": 1.1970104752277147e-05, + "loss": 3.3748, + "step": 2322944 + }, + { + "epoch": 0.01, + "learning_rate": 1.1961718804766625e-05, + "loss": 3.3658, + "step": 2323456 + }, + { + "epoch": 0.01, + "learning_rate": 1.1953349236059836e-05, + "loss": 3.3592, + "step": 2323968 + }, + { + "epoch": 0.01, + "learning_rate": 1.1944963288549318e-05, + "loss": 3.3537, + "step": 2324480 + }, + { + "epoch": 0.01, + "learning_rate": 1.1936577341038798e-05, + "loss": 3.3611, + "step": 2324992 + }, + { + "epoch": 0.01, + "learning_rate": 1.1928191393528276e-05, + "loss": 3.3643, + "step": 2325504 + }, + { + "epoch": 0.01, + "learning_rate": 1.1919821824821488e-05, + "loss": 3.369, + "step": 2326016 + }, + { + "epoch": 0.01, + "learning_rate": 1.1911435877310968e-05, + "loss": 3.3618, + "step": 2326528 + }, + { + "epoch": 0.01, + "learning_rate": 1.1903049929800447e-05, + "loss": 3.3665, + "step": 2327040 + }, + { + "epoch": 0.01, + "learning_rate": 1.1894663982289928e-05, + "loss": 3.3733, + "step": 2327552 + }, + { + "epoch": 0.01, + "learning_rate": 1.1886294413583139e-05, + "loss": 3.367, + "step": 2328064 + }, + { + "epoch": 0.01, + "learning_rate": 1.1877908466072619e-05, + "loss": 3.3566, + "step": 2328576 + }, + { + "epoch": 0.01, + "learning_rate": 1.1869522518562099e-05, + "loss": 3.3664, + "step": 2329088 + }, + { + "epoch": 0.01, + "learning_rate": 1.1861136571051579e-05, + "loss": 3.3648, + "step": 2329600 + }, + { + "epoch": 0.01, + "learning_rate": 1.185276700234479e-05, + "loss": 3.3682, + "step": 2330112 + }, + { + "epoch": 0.01, + "learning_rate": 1.1844381054834271e-05, + "loss": 3.3716, + "step": 2330624 + }, + { + "epoch": 0.01, + "learning_rate": 1.183599510732375e-05, + "loss": 3.3684, + "step": 2331136 + }, + { + "epoch": 0.01, + "learning_rate": 1.182760915981323e-05, + "loss": 3.3795, + "step": 2331648 + }, + { + "epoch": 0.01, + "learning_rate": 1.1819239591106442e-05, + "loss": 3.368, + "step": 2332160 + }, + { + "epoch": 0.01, + "learning_rate": 1.181085364359592e-05, + "loss": 3.3529, + "step": 2332672 + }, + { + "epoch": 0.01, + "learning_rate": 1.18024676960854e-05, + "loss": 3.3581, + "step": 2333184 + }, + { + "epoch": 0.01, + "learning_rate": 1.1794081748574882e-05, + "loss": 3.3744, + "step": 2333696 + }, + { + "epoch": 0.01, + "learning_rate": 1.1785712179868093e-05, + "loss": 3.3682, + "step": 2334208 + }, + { + "epoch": 0.01, + "learning_rate": 1.1777326232357571e-05, + "loss": 3.365, + "step": 2334720 + }, + { + "epoch": 0.01, + "learning_rate": 1.1768940284847053e-05, + "loss": 3.3674, + "step": 2335232 + }, + { + "epoch": 0.02, + "learning_rate": 1.1760554337336532e-05, + "loss": 3.3711, + "step": 2335744 + }, + { + "epoch": 0.02, + "learning_rate": 1.1752184768629743e-05, + "loss": 3.3552, + "step": 2336256 + }, + { + "epoch": 0.02, + "learning_rate": 1.1743798821119223e-05, + "loss": 3.3632, + "step": 2336768 + }, + { + "epoch": 0.02, + "learning_rate": 1.1735412873608703e-05, + "loss": 3.3617, + "step": 2337280 + }, + { + "epoch": 0.02, + "learning_rate": 1.1727026926098183e-05, + "loss": 3.3677, + "step": 2337792 + }, + { + "epoch": 0.02, + "learning_rate": 1.1718657357391394e-05, + "loss": 3.3736, + "step": 2338304 + }, + { + "epoch": 0.02, + "learning_rate": 1.1710271409880874e-05, + "loss": 3.367, + "step": 2338816 + }, + { + "epoch": 0.02, + "learning_rate": 1.1701885462370354e-05, + "loss": 3.3513, + "step": 2339328 + }, + { + "epoch": 0.02, + "learning_rate": 1.1693499514859834e-05, + "loss": 3.3673, + "step": 2339840 + }, + { + "epoch": 0.02, + "learning_rate": 1.1685129946153045e-05, + "loss": 3.366, + "step": 2340352 + }, + { + "epoch": 0.02, + "learning_rate": 1.1676743998642525e-05, + "loss": 3.3687, + "step": 2340864 + }, + { + "epoch": 0.02, + "learning_rate": 1.1668358051132006e-05, + "loss": 3.3631, + "step": 2341376 + }, + { + "epoch": 0.02, + "learning_rate": 1.1659972103621484e-05, + "loss": 3.3563, + "step": 2341888 + }, + { + "epoch": 0.02, + "learning_rate": 1.1651602534914697e-05, + "loss": 3.3523, + "step": 2342400 + }, + { + "epoch": 0.02, + "learning_rate": 1.1643216587404177e-05, + "loss": 3.367, + "step": 2342912 + }, + { + "epoch": 0.02, + "learning_rate": 1.1634830639893657e-05, + "loss": 3.3564, + "step": 2343424 + }, + { + "epoch": 0.02, + "learning_rate": 1.1626444692383135e-05, + "loss": 3.3543, + "step": 2343936 + }, + { + "epoch": 0.02, + "learning_rate": 1.1618075123676348e-05, + "loss": 3.3674, + "step": 2344448 + }, + { + "epoch": 0.02, + "learning_rate": 1.1609689176165828e-05, + "loss": 3.3633, + "step": 2344960 + }, + { + "epoch": 0.02, + "learning_rate": 1.1601303228655306e-05, + "loss": 3.3539, + "step": 2345472 + }, + { + "epoch": 0.02, + "learning_rate": 1.1592917281144787e-05, + "loss": 3.3652, + "step": 2345984 + }, + { + "epoch": 0.02, + "learning_rate": 1.1584547712437998e-05, + "loss": 3.3527, + "step": 2346496 + }, + { + "epoch": 0.02, + "learning_rate": 1.1576161764927478e-05, + "loss": 3.3669, + "step": 2347008 + }, + { + "epoch": 0.02, + "learning_rate": 1.1567775817416958e-05, + "loss": 3.3557, + "step": 2347520 + }, + { + "epoch": 0.02, + "learning_rate": 1.1559389869906438e-05, + "loss": 3.3643, + "step": 2348032 + }, + { + "epoch": 0.02, + "learning_rate": 1.155102030119965e-05, + "loss": 3.3643, + "step": 2348544 + }, + { + "epoch": 0.02, + "learning_rate": 1.154263435368913e-05, + "loss": 3.3696, + "step": 2349056 + }, + { + "epoch": 0.02, + "learning_rate": 1.1534248406178609e-05, + "loss": 3.3612, + "step": 2349568 + }, + { + "epoch": 0.02, + "learning_rate": 1.1525862458668089e-05, + "loss": 3.3648, + "step": 2350080 + }, + { + "epoch": 0.02, + "learning_rate": 1.1517492889961301e-05, + "loss": 3.3688, + "step": 2350592 + }, + { + "epoch": 0.02, + "learning_rate": 1.150910694245078e-05, + "loss": 3.3622, + "step": 2351104 + }, + { + "epoch": 0.02, + "learning_rate": 1.150072099494026e-05, + "loss": 3.3567, + "step": 2351616 + }, + { + "epoch": 0.02, + "learning_rate": 1.1492335047429741e-05, + "loss": 3.3663, + "step": 2352128 + }, + { + "epoch": 0.02, + "learning_rate": 1.1483965478722952e-05, + "loss": 3.3622, + "step": 2352640 + }, + { + "epoch": 0.02, + "learning_rate": 1.1475579531212432e-05, + "loss": 3.3698, + "step": 2353152 + }, + { + "epoch": 0.02, + "learning_rate": 1.1467193583701912e-05, + "loss": 3.3566, + "step": 2353664 + }, + { + "epoch": 0.02, + "learning_rate": 1.1458807636191392e-05, + "loss": 3.357, + "step": 2354176 + }, + { + "epoch": 0.02, + "learning_rate": 1.1450438067484604e-05, + "loss": 3.3586, + "step": 2354688 + }, + { + "epoch": 0.02, + "learning_rate": 1.1442052119974083e-05, + "loss": 3.3625, + "step": 2355200 + }, + { + "epoch": 0.02, + "learning_rate": 1.1433666172463563e-05, + "loss": 3.3601, + "step": 2355712 + }, + { + "epoch": 0.02, + "learning_rate": 1.1425280224953042e-05, + "loss": 3.367, + "step": 2356224 + }, + { + "epoch": 0.02, + "learning_rate": 1.1416910656246253e-05, + "loss": 3.37, + "step": 2356736 + }, + { + "epoch": 0.02, + "learning_rate": 1.1408524708735733e-05, + "loss": 3.3573, + "step": 2357248 + }, + { + "epoch": 0.02, + "learning_rate": 1.1400138761225213e-05, + "loss": 3.367, + "step": 2357760 + }, + { + "epoch": 0.02, + "learning_rate": 1.1391752813714695e-05, + "loss": 3.3643, + "step": 2358272 + }, + { + "epoch": 0.02, + "learning_rate": 1.1383383245007904e-05, + "loss": 3.373, + "step": 2358784 + }, + { + "epoch": 0.02, + "learning_rate": 1.1374997297497386e-05, + "loss": 3.3597, + "step": 2359296 + }, + { + "epoch": 0.02, + "learning_rate": 1.1366611349986866e-05, + "loss": 3.3636, + "step": 2359808 + }, + { + "epoch": 0.02, + "learning_rate": 1.1358225402476344e-05, + "loss": 3.3672, + "step": 2360320 + }, + { + "epoch": 0.02, + "learning_rate": 1.1349855833769556e-05, + "loss": 3.3714, + "step": 2360832 + }, + { + "epoch": 0.02, + "learning_rate": 1.1341469886259036e-05, + "loss": 3.3619, + "step": 2361344 + }, + { + "epoch": 0.02, + "learning_rate": 1.1333083938748516e-05, + "loss": 3.3602, + "step": 2361856 + }, + { + "epoch": 0.02, + "learning_rate": 1.1324697991237994e-05, + "loss": 3.3679, + "step": 2362368 + }, + { + "epoch": 0.02, + "learning_rate": 1.1316328422531207e-05, + "loss": 3.3588, + "step": 2362880 + }, + { + "epoch": 0.02, + "learning_rate": 1.1307942475020687e-05, + "loss": 3.3566, + "step": 2363392 + }, + { + "epoch": 0.02, + "learning_rate": 1.12995729063139e-05, + "loss": 3.3745, + "step": 2363904 + }, + { + "epoch": 0.02, + "learning_rate": 1.1291186958803378e-05, + "loss": 3.3569, + "step": 2364416 + }, + { + "epoch": 0.02, + "learning_rate": 1.1282801011292858e-05, + "loss": 3.3654, + "step": 2364928 + }, + { + "epoch": 0.02, + "learning_rate": 1.127441506378234e-05, + "loss": 3.3528, + "step": 2365440 + }, + { + "epoch": 0.03, + "eval_loss": 3.866777181625366, + "eval_runtime": 305.2912, + "eval_samples_per_second": 1249.924, + "eval_steps_per_second": 39.061, + "step": 2365920 + }, + { + "epoch": 1.0, + "learning_rate": 1.1266029116271817e-05, + "loss": 3.3574, + "step": 2365952 + }, + { + "epoch": 1.0, + "learning_rate": 1.1257643168761297e-05, + "loss": 3.3556, + "step": 2366464 + }, + { + "epoch": 1.0, + "learning_rate": 1.1249257221250777e-05, + "loss": 3.363, + "step": 2366976 + }, + { + "epoch": 1.0, + "learning_rate": 1.124088765254399e-05, + "loss": 3.3733, + "step": 2367488 + }, + { + "epoch": 1.0, + "learning_rate": 1.1232501705033468e-05, + "loss": 3.3663, + "step": 2368000 + }, + { + "epoch": 1.0, + "learning_rate": 1.1224115757522948e-05, + "loss": 3.371, + "step": 2368512 + }, + { + "epoch": 1.0, + "learning_rate": 1.121572981001243e-05, + "loss": 3.3533, + "step": 2369024 + }, + { + "epoch": 1.0, + "learning_rate": 1.120736024130564e-05, + "loss": 3.3631, + "step": 2369536 + }, + { + "epoch": 1.0, + "learning_rate": 1.119897429379512e-05, + "loss": 3.3593, + "step": 2370048 + }, + { + "epoch": 1.0, + "learning_rate": 1.11905883462846e-05, + "loss": 3.3643, + "step": 2370560 + }, + { + "epoch": 1.0, + "learning_rate": 1.118220239877408e-05, + "loss": 3.3575, + "step": 2371072 + }, + { + "epoch": 1.0, + "learning_rate": 1.1173832830067291e-05, + "loss": 3.3664, + "step": 2371584 + }, + { + "epoch": 1.0, + "learning_rate": 1.1165446882556771e-05, + "loss": 3.3717, + "step": 2372096 + }, + { + "epoch": 1.0, + "learning_rate": 1.1157060935046251e-05, + "loss": 3.3532, + "step": 2372608 + }, + { + "epoch": 1.0, + "learning_rate": 1.1148674987535731e-05, + "loss": 3.3441, + "step": 2373120 + }, + { + "epoch": 1.0, + "learning_rate": 1.1140305418828942e-05, + "loss": 3.3472, + "step": 2373632 + }, + { + "epoch": 1.0, + "learning_rate": 1.1131919471318422e-05, + "loss": 3.3658, + "step": 2374144 + }, + { + "epoch": 1.0, + "learning_rate": 1.1123533523807902e-05, + "loss": 3.3622, + "step": 2374656 + }, + { + "epoch": 1.0, + "learning_rate": 1.1115147576297382e-05, + "loss": 3.3604, + "step": 2375168 + }, + { + "epoch": 1.0, + "learning_rate": 1.1106778007590593e-05, + "loss": 3.36, + "step": 2375680 + }, + { + "epoch": 1.0, + "learning_rate": 1.1098392060080074e-05, + "loss": 3.3843, + "step": 2376192 + }, + { + "epoch": 1.0, + "learning_rate": 1.1090006112569554e-05, + "loss": 3.3559, + "step": 2376704 + }, + { + "epoch": 1.0, + "learning_rate": 1.1081620165059032e-05, + "loss": 3.359, + "step": 2377216 + }, + { + "epoch": 1.0, + "learning_rate": 1.1073250596352245e-05, + "loss": 3.3631, + "step": 2377728 + }, + { + "epoch": 1.0, + "learning_rate": 1.1064864648841725e-05, + "loss": 3.3707, + "step": 2378240 + }, + { + "epoch": 1.0, + "learning_rate": 1.1056478701331203e-05, + "loss": 3.3488, + "step": 2378752 + }, + { + "epoch": 1.0, + "learning_rate": 1.1048092753820683e-05, + "loss": 3.359, + "step": 2379264 + }, + { + "epoch": 1.0, + "learning_rate": 1.1039723185113896e-05, + "loss": 3.369, + "step": 2379776 + }, + { + "epoch": 1.0, + "learning_rate": 1.1031337237603375e-05, + "loss": 3.3568, + "step": 2380288 + }, + { + "epoch": 1.0, + "learning_rate": 1.1022951290092855e-05, + "loss": 3.3472, + "step": 2380800 + }, + { + "epoch": 1.01, + "learning_rate": 1.1014565342582335e-05, + "loss": 3.3468, + "step": 2381312 + }, + { + "epoch": 1.01, + "learning_rate": 1.1006195773875546e-05, + "loss": 3.3579, + "step": 2381824 + }, + { + "epoch": 1.01, + "learning_rate": 1.0997809826365028e-05, + "loss": 3.3668, + "step": 2382336 + }, + { + "epoch": 1.01, + "learning_rate": 1.0989423878854506e-05, + "loss": 3.3653, + "step": 2382848 + }, + { + "epoch": 1.01, + "learning_rate": 1.0981037931343986e-05, + "loss": 3.3598, + "step": 2383360 + }, + { + "epoch": 1.01, + "learning_rate": 1.0972668362637199e-05, + "loss": 3.353, + "step": 2383872 + }, + { + "epoch": 1.01, + "learning_rate": 1.0964282415126677e-05, + "loss": 3.364, + "step": 2384384 + }, + { + "epoch": 1.01, + "learning_rate": 1.0955896467616157e-05, + "loss": 3.3462, + "step": 2384896 + }, + { + "epoch": 1.01, + "learning_rate": 1.0947510520105637e-05, + "loss": 3.3544, + "step": 2385408 + }, + { + "epoch": 1.01, + "learning_rate": 1.093914095139885e-05, + "loss": 3.353, + "step": 2385920 + }, + { + "epoch": 1.01, + "learning_rate": 1.0930755003888327e-05, + "loss": 3.3555, + "step": 2386432 + }, + { + "epoch": 1.01, + "learning_rate": 1.0922369056377809e-05, + "loss": 3.3486, + "step": 2386944 + }, + { + "epoch": 1.01, + "learning_rate": 1.0913983108867289e-05, + "loss": 3.3715, + "step": 2387456 + }, + { + "epoch": 1.01, + "learning_rate": 1.0905597161356767e-05, + "loss": 3.3553, + "step": 2387968 + }, + { + "epoch": 1.01, + "learning_rate": 1.089722759264998e-05, + "loss": 3.359, + "step": 2388480 + }, + { + "epoch": 1.01, + "learning_rate": 1.088884164513946e-05, + "loss": 3.3642, + "step": 2388992 + }, + { + "epoch": 1.01, + "learning_rate": 1.088045569762894e-05, + "loss": 3.3541, + "step": 2389504 + }, + { + "epoch": 1.01, + "learning_rate": 1.0872069750118418e-05, + "loss": 3.3544, + "step": 2390016 + }, + { + "epoch": 1.01, + "learning_rate": 1.086370018141163e-05, + "loss": 3.338, + "step": 2390528 + }, + { + "epoch": 1.01, + "learning_rate": 1.085531423390111e-05, + "loss": 3.3514, + "step": 2391040 + }, + { + "epoch": 1.01, + "learning_rate": 1.084692828639059e-05, + "loss": 3.3658, + "step": 2391552 + }, + { + "epoch": 1.01, + "learning_rate": 1.0838558717683801e-05, + "loss": 3.3587, + "step": 2392064 + }, + { + "epoch": 1.01, + "learning_rate": 1.0830172770173281e-05, + "loss": 3.3505, + "step": 2392576 + }, + { + "epoch": 1.01, + "learning_rate": 1.0821786822662763e-05, + "loss": 3.3445, + "step": 2393088 + }, + { + "epoch": 1.01, + "learning_rate": 1.0813400875152241e-05, + "loss": 3.3535, + "step": 2393600 + }, + { + "epoch": 1.01, + "learning_rate": 1.0805014927641721e-05, + "loss": 3.3443, + "step": 2394112 + }, + { + "epoch": 1.01, + "learning_rate": 1.0796645358934933e-05, + "loss": 3.3689, + "step": 2394624 + }, + { + "epoch": 1.01, + "learning_rate": 1.0788259411424413e-05, + "loss": 3.352, + "step": 2395136 + }, + { + "epoch": 1.01, + "learning_rate": 1.0779873463913892e-05, + "loss": 3.3571, + "step": 2395648 + }, + { + "epoch": 1.01, + "learning_rate": 1.0771503895207104e-05, + "loss": 3.3665, + "step": 2396160 + }, + { + "epoch": 1.01, + "learning_rate": 1.0763117947696584e-05, + "loss": 3.3396, + "step": 2396672 + }, + { + "epoch": 1.01, + "learning_rate": 1.0754732000186064e-05, + "loss": 3.3506, + "step": 2397184 + }, + { + "epoch": 1.01, + "learning_rate": 1.0746346052675544e-05, + "loss": 3.3486, + "step": 2397696 + }, + { + "epoch": 1.01, + "learning_rate": 1.0737960105165024e-05, + "loss": 3.344, + "step": 2398208 + }, + { + "epoch": 1.01, + "learning_rate": 1.0729590536458235e-05, + "loss": 3.3474, + "step": 2398720 + }, + { + "epoch": 1.01, + "learning_rate": 1.0721204588947715e-05, + "loss": 3.36, + "step": 2399232 + }, + { + "epoch": 1.01, + "learning_rate": 1.0712818641437195e-05, + "loss": 3.3617, + "step": 2399744 + }, + { + "epoch": 1.01, + "learning_rate": 1.0704432693926675e-05, + "loss": 3.3494, + "step": 2400256 + }, + { + "epoch": 1.01, + "learning_rate": 1.0696063125219887e-05, + "loss": 3.3406, + "step": 2400768 + }, + { + "epoch": 1.01, + "learning_rate": 1.0687677177709365e-05, + "loss": 3.3518, + "step": 2401280 + }, + { + "epoch": 1.01, + "learning_rate": 1.0679291230198845e-05, + "loss": 3.3554, + "step": 2401792 + }, + { + "epoch": 1.01, + "learning_rate": 1.0670905282688325e-05, + "loss": 3.3561, + "step": 2402304 + }, + { + "epoch": 1.01, + "learning_rate": 1.0662535713981538e-05, + "loss": 3.3566, + "step": 2402816 + }, + { + "epoch": 1.01, + "learning_rate": 1.0654149766471016e-05, + "loss": 3.3572, + "step": 2403328 + }, + { + "epoch": 1.01, + "learning_rate": 1.0645763818960498e-05, + "loss": 3.3653, + "step": 2403840 + }, + { + "epoch": 1.01, + "learning_rate": 1.0637377871449978e-05, + "loss": 3.3585, + "step": 2404352 + }, + { + "epoch": 1.01, + "learning_rate": 1.0629008302743187e-05, + "loss": 3.3455, + "step": 2404864 + }, + { + "epoch": 1.01, + "learning_rate": 1.0620622355232668e-05, + "loss": 3.3596, + "step": 2405376 + }, + { + "epoch": 1.01, + "learning_rate": 1.0612236407722148e-05, + "loss": 3.3544, + "step": 2405888 + }, + { + "epoch": 1.01, + "learning_rate": 1.060386683901536e-05, + "loss": 3.3532, + "step": 2406400 + }, + { + "epoch": 1.01, + "learning_rate": 1.0595480891504839e-05, + "loss": 3.3651, + "step": 2406912 + }, + { + "epoch": 1.01, + "learning_rate": 1.0587094943994319e-05, + "loss": 3.3597, + "step": 2407424 + }, + { + "epoch": 1.01, + "learning_rate": 1.0578708996483799e-05, + "loss": 3.3707, + "step": 2407936 + }, + { + "epoch": 1.01, + "learning_rate": 1.0570339427777012e-05, + "loss": 3.3595, + "step": 2408448 + }, + { + "epoch": 1.01, + "learning_rate": 1.056195348026649e-05, + "loss": 3.347, + "step": 2408960 + }, + { + "epoch": 1.01, + "learning_rate": 1.055356753275597e-05, + "loss": 3.3481, + "step": 2409472 + }, + { + "epoch": 1.01, + "learning_rate": 1.054518158524545e-05, + "loss": 3.3593, + "step": 2409984 + }, + { + "epoch": 1.01, + "learning_rate": 1.053681201653866e-05, + "loss": 3.3619, + "step": 2410496 + }, + { + "epoch": 1.01, + "learning_rate": 1.052842606902814e-05, + "loss": 3.3554, + "step": 2411008 + }, + { + "epoch": 1.01, + "learning_rate": 1.0520040121517622e-05, + "loss": 3.3563, + "step": 2411520 + }, + { + "epoch": 1.02, + "learning_rate": 1.0511654174007102e-05, + "loss": 3.3618, + "step": 2412032 + }, + { + "epoch": 1.02, + "learning_rate": 1.0503284605300313e-05, + "loss": 3.3473, + "step": 2412544 + }, + { + "epoch": 1.02, + "learning_rate": 1.0494898657789793e-05, + "loss": 3.3528, + "step": 2413056 + }, + { + "epoch": 1.02, + "learning_rate": 1.0486512710279273e-05, + "loss": 3.3521, + "step": 2413568 + }, + { + "epoch": 1.02, + "learning_rate": 1.0478126762768751e-05, + "loss": 3.3585, + "step": 2414080 + }, + { + "epoch": 1.02, + "learning_rate": 1.0469757194061963e-05, + "loss": 3.3673, + "step": 2414592 + }, + { + "epoch": 1.02, + "learning_rate": 1.0461371246551443e-05, + "loss": 3.3583, + "step": 2415104 + }, + { + "epoch": 1.02, + "learning_rate": 1.0452985299040923e-05, + "loss": 3.3427, + "step": 2415616 + }, + { + "epoch": 1.02, + "learning_rate": 1.0444599351530403e-05, + "loss": 3.3558, + "step": 2416128 + }, + { + "epoch": 1.02, + "learning_rate": 1.0436229782823614e-05, + "loss": 3.3567, + "step": 2416640 + }, + { + "epoch": 1.02, + "learning_rate": 1.0427843835313094e-05, + "loss": 3.3617, + "step": 2417152 + }, + { + "epoch": 1.02, + "learning_rate": 1.0419457887802574e-05, + "loss": 3.3488, + "step": 2417664 + }, + { + "epoch": 1.02, + "learning_rate": 1.0411071940292054e-05, + "loss": 3.3503, + "step": 2418176 + }, + { + "epoch": 1.02, + "learning_rate": 1.0402702371585265e-05, + "loss": 3.3397, + "step": 2418688 + }, + { + "epoch": 1.02, + "learning_rate": 1.0394316424074746e-05, + "loss": 3.359, + "step": 2419200 + }, + { + "epoch": 1.02, + "learning_rate": 1.0385930476564225e-05, + "loss": 3.3462, + "step": 2419712 + }, + { + "epoch": 1.02, + "learning_rate": 1.0377544529053705e-05, + "loss": 3.3496, + "step": 2420224 + }, + { + "epoch": 1.02, + "learning_rate": 1.0369174960346917e-05, + "loss": 3.3587, + "step": 2420736 + }, + { + "epoch": 1.02, + "learning_rate": 1.0360789012836397e-05, + "loss": 3.3499, + "step": 2421248 + }, + { + "epoch": 1.02, + "learning_rate": 1.0352403065325875e-05, + "loss": 3.3452, + "step": 2421760 + }, + { + "epoch": 1.02, + "learning_rate": 1.0344017117815357e-05, + "loss": 3.3524, + "step": 2422272 + }, + { + "epoch": 1.02, + "learning_rate": 1.0335647549108568e-05, + "loss": 3.3471, + "step": 2422784 + }, + { + "epoch": 1.02, + "learning_rate": 1.0327261601598048e-05, + "loss": 3.3572, + "step": 2423296 + }, + { + "epoch": 1.02, + "learning_rate": 1.0318875654087528e-05, + "loss": 3.3468, + "step": 2423808 + }, + { + "epoch": 1.02, + "learning_rate": 1.0310489706577008e-05, + "loss": 3.355, + "step": 2424320 + }, + { + "epoch": 1.02, + "learning_rate": 1.0302120137870218e-05, + "loss": 3.354, + "step": 2424832 + }, + { + "epoch": 1.02, + "learning_rate": 1.0293734190359698e-05, + "loss": 3.3625, + "step": 2425344 + }, + { + "epoch": 1.02, + "learning_rate": 1.0285348242849178e-05, + "loss": 3.351, + "step": 2425856 + }, + { + "epoch": 1.02, + "learning_rate": 1.0276962295338658e-05, + "loss": 3.3576, + "step": 2426368 + }, + { + "epoch": 1.02, + "learning_rate": 1.026859272663187e-05, + "loss": 3.3594, + "step": 2426880 + }, + { + "epoch": 1.02, + "learning_rate": 1.0260206779121349e-05, + "loss": 3.3536, + "step": 2427392 + }, + { + "epoch": 1.02, + "learning_rate": 1.0251820831610829e-05, + "loss": 3.3392, + "step": 2427904 + }, + { + "epoch": 1.02, + "learning_rate": 1.024343488410031e-05, + "loss": 3.3605, + "step": 2428416 + }, + { + "epoch": 1.02, + "learning_rate": 1.023506531539352e-05, + "loss": 3.3542, + "step": 2428928 + }, + { + "epoch": 1.02, + "learning_rate": 1.0226679367883e-05, + "loss": 3.3615, + "step": 2429440 + }, + { + "epoch": 1.02, + "learning_rate": 1.0218293420372481e-05, + "loss": 3.3444, + "step": 2429952 + }, + { + "epoch": 1.02, + "learning_rate": 1.0209907472861961e-05, + "loss": 3.3505, + "step": 2430464 + }, + { + "epoch": 1.02, + "learning_rate": 1.0201537904155172e-05, + "loss": 3.3485, + "step": 2430976 + }, + { + "epoch": 1.02, + "learning_rate": 1.0193151956644652e-05, + "loss": 3.3533, + "step": 2431488 + }, + { + "epoch": 1.02, + "learning_rate": 1.0184766009134132e-05, + "loss": 3.3488, + "step": 2432000 + }, + { + "epoch": 1.02, + "learning_rate": 1.017638006162361e-05, + "loss": 3.3605, + "step": 2432512 + }, + { + "epoch": 1.02, + "learning_rate": 1.0168010492916823e-05, + "loss": 3.3648, + "step": 2433024 + }, + { + "epoch": 1.02, + "learning_rate": 1.0159624545406303e-05, + "loss": 3.3495, + "step": 2433536 + }, + { + "epoch": 1.02, + "learning_rate": 1.0151238597895783e-05, + "loss": 3.3542, + "step": 2434048 + }, + { + "epoch": 1.02, + "learning_rate": 1.0142852650385263e-05, + "loss": 3.3586, + "step": 2434560 + }, + { + "epoch": 1.02, + "learning_rate": 1.0134483081678473e-05, + "loss": 3.3611, + "step": 2435072 + }, + { + "epoch": 1.02, + "learning_rate": 1.0126097134167953e-05, + "loss": 3.3553, + "step": 2435584 + }, + { + "epoch": 1.02, + "learning_rate": 1.0117711186657435e-05, + "loss": 3.3535, + "step": 2436096 + }, + { + "epoch": 1.02, + "learning_rate": 1.0109325239146913e-05, + "loss": 3.3576, + "step": 2436608 + }, + { + "epoch": 1.02, + "learning_rate": 1.0100955670440126e-05, + "loss": 3.3567, + "step": 2437120 + }, + { + "epoch": 1.02, + "learning_rate": 1.0092569722929606e-05, + "loss": 3.3538, + "step": 2437632 + }, + { + "epoch": 1.02, + "learning_rate": 1.0084183775419084e-05, + "loss": 3.3509, + "step": 2438144 + }, + { + "epoch": 1.02, + "learning_rate": 1.0075797827908564e-05, + "loss": 3.3588, + "step": 2438656 + }, + { + "epoch": 1.02, + "learning_rate": 1.0067428259201776e-05, + "loss": 3.3503, + "step": 2439168 + }, + { + "epoch": 1.02, + "learning_rate": 1.0059042311691256e-05, + "loss": 3.3447, + "step": 2439680 + }, + { + "epoch": 1.02, + "learning_rate": 1.0050672742984467e-05, + "loss": 3.3663, + "step": 2440192 + }, + { + "epoch": 1.02, + "learning_rate": 1.0042286795473947e-05, + "loss": 3.3494, + "step": 2440704 + }, + { + "epoch": 1.02, + "learning_rate": 1.0033900847963427e-05, + "loss": 3.3535, + "step": 2441216 + }, + { + "epoch": 1.02, + "learning_rate": 1.0025514900452907e-05, + "loss": 3.3453, + "step": 2441728 + }, + { + "epoch": 1.03, + "learning_rate": 1.0017128952942387e-05, + "loss": 3.3489, + "step": 2442240 + }, + { + "epoch": 1.03, + "eval_loss": 3.866668224334717, + "eval_runtime": 304.9468, + "eval_samples_per_second": 1251.336, + "eval_steps_per_second": 39.105, + "step": 2442240 + }, + { + "epoch": 0.0, + "learning_rate": 1.0008743005431867e-05, + "loss": 3.3419, + "step": 2442752 + }, + { + "epoch": 0.0, + "learning_rate": 1.0000357057921347e-05, + "loss": 3.3563, + "step": 2443264 + }, + { + "epoch": 0.0, + "learning_rate": 9.991971110410827e-06, + "loss": 3.3612, + "step": 2443776 + }, + { + "epoch": 0.0, + "learning_rate": 9.983601541704038e-06, + "loss": 3.3578, + "step": 2444288 + }, + { + "epoch": 0.0, + "learning_rate": 9.975215594193518e-06, + "loss": 3.3619, + "step": 2444800 + }, + { + "epoch": 0.0, + "learning_rate": 9.966829646683e-06, + "loss": 3.346, + "step": 2445312 + }, + { + "epoch": 0.0, + "learning_rate": 9.958443699172478e-06, + "loss": 3.351, + "step": 2445824 + }, + { + "epoch": 0.0, + "learning_rate": 9.950074130465688e-06, + "loss": 3.3461, + "step": 2446336 + }, + { + "epoch": 0.0, + "learning_rate": 9.94168818295517e-06, + "loss": 3.3558, + "step": 2446848 + }, + { + "epoch": 0.0, + "learning_rate": 9.933302235444648e-06, + "loss": 3.3514, + "step": 2447360 + }, + { + "epoch": 0.0, + "learning_rate": 9.924916287934128e-06, + "loss": 3.3583, + "step": 2447872 + }, + { + "epoch": 0.0, + "learning_rate": 9.91654671922734e-06, + "loss": 3.3573, + "step": 2448384 + }, + { + "epoch": 0.0, + "learning_rate": 9.90816077171682e-06, + "loss": 3.3481, + "step": 2448896 + }, + { + "epoch": 0.0, + "learning_rate": 9.899774824206299e-06, + "loss": 3.3372, + "step": 2449408 + }, + { + "epoch": 0.0, + "learning_rate": 9.89138887669578e-06, + "loss": 3.3439, + "step": 2449920 + }, + { + "epoch": 0.0, + "learning_rate": 9.883019307988991e-06, + "loss": 3.3468, + "step": 2450432 + }, + { + "epoch": 0.0, + "learning_rate": 9.874633360478471e-06, + "loss": 3.3526, + "step": 2450944 + }, + { + "epoch": 0.0, + "learning_rate": 9.866247412967951e-06, + "loss": 3.349, + "step": 2451456 + }, + { + "epoch": 0.0, + "learning_rate": 9.857861465457431e-06, + "loss": 3.3515, + "step": 2451968 + }, + { + "epoch": 0.0, + "learning_rate": 9.849491896750642e-06, + "loss": 3.3773, + "step": 2452480 + }, + { + "epoch": 0.0, + "learning_rate": 9.841105949240122e-06, + "loss": 3.3459, + "step": 2452992 + }, + { + "epoch": 0.0, + "learning_rate": 9.832720001729602e-06, + "loss": 3.3498, + "step": 2453504 + }, + { + "epoch": 0.0, + "learning_rate": 9.824334054219082e-06, + "loss": 3.3515, + "step": 2454016 + }, + { + "epoch": 0.0, + "learning_rate": 9.815964485512294e-06, + "loss": 3.3602, + "step": 2454528 + }, + { + "epoch": 0.0, + "learning_rate": 9.807578538001773e-06, + "loss": 3.3409, + "step": 2455040 + }, + { + "epoch": 0.0, + "learning_rate": 9.799192590491253e-06, + "loss": 3.3465, + "step": 2455552 + }, + { + "epoch": 0.0, + "learning_rate": 9.790806642980734e-06, + "loss": 3.3616, + "step": 2456064 + }, + { + "epoch": 0.0, + "learning_rate": 9.782437074273943e-06, + "loss": 3.3485, + "step": 2456576 + }, + { + "epoch": 0.0, + "learning_rate": 9.774051126763423e-06, + "loss": 3.3342, + "step": 2457088 + }, + { + "epoch": 0.01, + "learning_rate": 9.765665179252905e-06, + "loss": 3.3372, + "step": 2457600 + }, + { + "epoch": 0.01, + "learning_rate": 9.757279231742385e-06, + "loss": 3.3513, + "step": 2458112 + }, + { + "epoch": 0.01, + "learning_rate": 9.748909663035596e-06, + "loss": 3.3549, + "step": 2458624 + }, + { + "epoch": 0.01, + "learning_rate": 9.740523715525076e-06, + "loss": 3.3607, + "step": 2459136 + }, + { + "epoch": 0.01, + "learning_rate": 9.732137768014556e-06, + "loss": 3.3473, + "step": 2459648 + }, + { + "epoch": 0.01, + "learning_rate": 9.723751820504034e-06, + "loss": 3.3434, + "step": 2460160 + }, + { + "epoch": 0.01, + "learning_rate": 9.715382251797246e-06, + "loss": 3.3558, + "step": 2460672 + }, + { + "epoch": 0.01, + "learning_rate": 9.706996304286726e-06, + "loss": 3.3365, + "step": 2461184 + }, + { + "epoch": 0.01, + "learning_rate": 9.698610356776206e-06, + "loss": 3.349, + "step": 2461696 + }, + { + "epoch": 0.01, + "learning_rate": 9.690224409265686e-06, + "loss": 3.3417, + "step": 2462208 + }, + { + "epoch": 0.01, + "learning_rate": 9.681854840558897e-06, + "loss": 3.3484, + "step": 2462720 + }, + { + "epoch": 0.01, + "learning_rate": 9.673468893048377e-06, + "loss": 3.3387, + "step": 2463232 + }, + { + "epoch": 0.01, + "learning_rate": 9.665082945537859e-06, + "loss": 3.3602, + "step": 2463744 + }, + { + "epoch": 0.01, + "learning_rate": 9.656696998027337e-06, + "loss": 3.3449, + "step": 2464256 + }, + { + "epoch": 0.01, + "learning_rate": 9.64832742932055e-06, + "loss": 3.349, + "step": 2464768 + }, + { + "epoch": 0.01, + "learning_rate": 9.63994148181003e-06, + "loss": 3.355, + "step": 2465280 + }, + { + "epoch": 0.01, + "learning_rate": 9.631555534299508e-06, + "loss": 3.3487, + "step": 2465792 + }, + { + "epoch": 0.01, + "learning_rate": 9.623169586788988e-06, + "loss": 3.3454, + "step": 2466304 + }, + { + "epoch": 0.01, + "learning_rate": 9.6148000180822e-06, + "loss": 3.3338, + "step": 2466816 + }, + { + "epoch": 0.01, + "learning_rate": 9.60641407057168e-06, + "loss": 3.3378, + "step": 2467328 + }, + { + "epoch": 0.01, + "learning_rate": 9.59802812306116e-06, + "loss": 3.3571, + "step": 2467840 + }, + { + "epoch": 0.01, + "learning_rate": 9.58964217555064e-06, + "loss": 3.3485, + "step": 2468352 + }, + { + "epoch": 0.01, + "learning_rate": 9.58127260684385e-06, + "loss": 3.3392, + "step": 2468864 + }, + { + "epoch": 0.01, + "learning_rate": 9.57288665933333e-06, + "loss": 3.3373, + "step": 2469376 + }, + { + "epoch": 0.01, + "learning_rate": 9.56450071182281e-06, + "loss": 3.3446, + "step": 2469888 + }, + { + "epoch": 0.01, + "learning_rate": 9.55611476431229e-06, + "loss": 3.3354, + "step": 2470400 + }, + { + "epoch": 0.01, + "learning_rate": 9.547745195605503e-06, + "loss": 3.356, + "step": 2470912 + }, + { + "epoch": 0.01, + "learning_rate": 9.539359248094981e-06, + "loss": 3.3416, + "step": 2471424 + }, + { + "epoch": 0.01, + "learning_rate": 9.530973300584461e-06, + "loss": 3.3462, + "step": 2471936 + }, + { + "epoch": 0.01, + "learning_rate": 9.522587353073941e-06, + "loss": 3.3508, + "step": 2472448 + }, + { + "epoch": 0.01, + "learning_rate": 9.514217784367154e-06, + "loss": 3.3416, + "step": 2472960 + }, + { + "epoch": 0.01, + "learning_rate": 9.505831836856632e-06, + "loss": 3.3366, + "step": 2473472 + }, + { + "epoch": 0.01, + "learning_rate": 9.497445889346112e-06, + "loss": 3.3411, + "step": 2473984 + }, + { + "epoch": 0.01, + "learning_rate": 9.489059941835594e-06, + "loss": 3.3376, + "step": 2474496 + }, + { + "epoch": 0.01, + "learning_rate": 9.480690373128804e-06, + "loss": 3.3373, + "step": 2475008 + }, + { + "epoch": 0.01, + "learning_rate": 9.472304425618284e-06, + "loss": 3.3493, + "step": 2475520 + }, + { + "epoch": 0.01, + "learning_rate": 9.463918478107764e-06, + "loss": 3.3535, + "step": 2476032 + }, + { + "epoch": 0.01, + "learning_rate": 9.455532530597244e-06, + "loss": 3.3406, + "step": 2476544 + }, + { + "epoch": 0.01, + "learning_rate": 9.447162961890455e-06, + "loss": 3.3363, + "step": 2477056 + }, + { + "epoch": 0.01, + "learning_rate": 9.438777014379935e-06, + "loss": 3.3381, + "step": 2477568 + }, + { + "epoch": 0.01, + "learning_rate": 9.430391066869415e-06, + "loss": 3.3449, + "step": 2478080 + }, + { + "epoch": 0.01, + "learning_rate": 9.422005119358895e-06, + "loss": 3.3456, + "step": 2478592 + }, + { + "epoch": 0.01, + "learning_rate": 9.413635550652106e-06, + "loss": 3.3478, + "step": 2479104 + }, + { + "epoch": 0.01, + "learning_rate": 9.405249603141586e-06, + "loss": 3.3482, + "step": 2479616 + }, + { + "epoch": 0.01, + "learning_rate": 9.396863655631066e-06, + "loss": 3.3532, + "step": 2480128 + }, + { + "epoch": 0.01, + "learning_rate": 9.388477708120546e-06, + "loss": 3.3529, + "step": 2480640 + }, + { + "epoch": 0.01, + "learning_rate": 9.380108139413756e-06, + "loss": 3.3345, + "step": 2481152 + }, + { + "epoch": 0.01, + "learning_rate": 9.371722191903238e-06, + "loss": 3.3502, + "step": 2481664 + }, + { + "epoch": 0.01, + "learning_rate": 9.363336244392718e-06, + "loss": 3.3495, + "step": 2482176 + }, + { + "epoch": 0.01, + "learning_rate": 9.354950296882196e-06, + "loss": 3.3406, + "step": 2482688 + }, + { + "epoch": 0.01, + "learning_rate": 9.346580728175409e-06, + "loss": 3.3565, + "step": 2483200 + }, + { + "epoch": 0.01, + "learning_rate": 9.338194780664889e-06, + "loss": 3.3495, + "step": 2483712 + }, + { + "epoch": 0.01, + "learning_rate": 9.329808833154369e-06, + "loss": 3.361, + "step": 2484224 + }, + { + "epoch": 0.01, + "learning_rate": 9.321422885643847e-06, + "loss": 3.3525, + "step": 2484736 + }, + { + "epoch": 0.01, + "learning_rate": 9.31305331693706e-06, + "loss": 3.3335, + "step": 2485248 + }, + { + "epoch": 0.01, + "learning_rate": 9.30466736942654e-06, + "loss": 3.34, + "step": 2485760 + }, + { + "epoch": 0.01, + "learning_rate": 9.29628142191602e-06, + "loss": 3.3494, + "step": 2486272 + }, + { + "epoch": 0.01, + "learning_rate": 9.2878954744055e-06, + "loss": 3.3515, + "step": 2486784 + }, + { + "epoch": 0.01, + "learning_rate": 9.27952590569871e-06, + "loss": 3.3484, + "step": 2487296 + }, + { + "epoch": 0.01, + "learning_rate": 9.271139958188192e-06, + "loss": 3.3452, + "step": 2487808 + }, + { + "epoch": 0.02, + "learning_rate": 9.26275401067767e-06, + "loss": 3.3494, + "step": 2488320 + }, + { + "epoch": 0.02, + "learning_rate": 9.25436806316715e-06, + "loss": 3.3419, + "step": 2488832 + }, + { + "epoch": 0.02, + "learning_rate": 9.245998494460362e-06, + "loss": 3.3385, + "step": 2489344 + }, + { + "epoch": 0.02, + "learning_rate": 9.237612546949842e-06, + "loss": 3.3433, + "step": 2489856 + }, + { + "epoch": 0.02, + "learning_rate": 9.22922659943932e-06, + "loss": 3.3498, + "step": 2490368 + }, + { + "epoch": 0.02, + "learning_rate": 9.2208406519288e-06, + "loss": 3.361, + "step": 2490880 + }, + { + "epoch": 0.02, + "learning_rate": 9.212471083222013e-06, + "loss": 3.3435, + "step": 2491392 + }, + { + "epoch": 0.02, + "learning_rate": 9.204085135711491e-06, + "loss": 3.333, + "step": 2491904 + }, + { + "epoch": 0.02, + "learning_rate": 9.195699188200973e-06, + "loss": 3.3452, + "step": 2492416 + }, + { + "epoch": 0.02, + "learning_rate": 9.187313240690453e-06, + "loss": 3.3496, + "step": 2492928 + }, + { + "epoch": 0.02, + "learning_rate": 9.178943671983664e-06, + "loss": 3.3518, + "step": 2493440 + }, + { + "epoch": 0.02, + "learning_rate": 9.170557724473144e-06, + "loss": 3.3412, + "step": 2493952 + }, + { + "epoch": 0.02, + "learning_rate": 9.162171776962624e-06, + "loss": 3.3448, + "step": 2494464 + }, + { + "epoch": 0.02, + "learning_rate": 9.153785829452103e-06, + "loss": 3.3261, + "step": 2494976 + }, + { + "epoch": 0.02, + "learning_rate": 9.145416260745314e-06, + "loss": 3.348, + "step": 2495488 + }, + { + "epoch": 0.02, + "learning_rate": 9.137030313234794e-06, + "loss": 3.3396, + "step": 2496000 + }, + { + "epoch": 0.02, + "learning_rate": 9.128644365724274e-06, + "loss": 3.3371, + "step": 2496512 + }, + { + "epoch": 0.02, + "learning_rate": 9.120258418213754e-06, + "loss": 3.3434, + "step": 2497024 + }, + { + "epoch": 0.02, + "learning_rate": 9.111888849506965e-06, + "loss": 3.3439, + "step": 2497536 + }, + { + "epoch": 0.02, + "learning_rate": 9.103502901996445e-06, + "loss": 3.3358, + "step": 2498048 + }, + { + "epoch": 0.02, + "learning_rate": 9.095116954485927e-06, + "loss": 3.3449, + "step": 2498560 + }, + { + "epoch": 0.02, + "learning_rate": 9.086731006975405e-06, + "loss": 3.34, + "step": 2499072 + }, + { + "epoch": 0.02, + "learning_rate": 9.078361438268616e-06, + "loss": 3.3478, + "step": 2499584 + }, + { + "epoch": 0.02, + "learning_rate": 9.069975490758097e-06, + "loss": 3.3356, + "step": 2500096 + }, + { + "epoch": 0.02, + "learning_rate": 9.061589543247577e-06, + "loss": 3.3444, + "step": 2500608 + }, + { + "epoch": 0.02, + "learning_rate": 9.053203595737055e-06, + "loss": 3.3473, + "step": 2501120 + }, + { + "epoch": 0.02, + "learning_rate": 9.044834027030268e-06, + "loss": 3.351, + "step": 2501632 + }, + { + "epoch": 0.02, + "learning_rate": 9.036448079519748e-06, + "loss": 3.345, + "step": 2502144 + }, + { + "epoch": 0.02, + "learning_rate": 9.028062132009228e-06, + "loss": 3.3478, + "step": 2502656 + }, + { + "epoch": 0.02, + "learning_rate": 9.019676184498708e-06, + "loss": 3.3518, + "step": 2503168 + }, + { + "epoch": 0.02, + "learning_rate": 9.011306615791919e-06, + "loss": 3.3433, + "step": 2503680 + }, + { + "epoch": 0.02, + "learning_rate": 9.002920668281399e-06, + "loss": 3.3364, + "step": 2504192 + }, + { + "epoch": 0.02, + "learning_rate": 8.994534720770879e-06, + "loss": 3.3509, + "step": 2504704 + }, + { + "epoch": 0.02, + "learning_rate": 8.986148773260358e-06, + "loss": 3.344, + "step": 2505216 + }, + { + "epoch": 0.02, + "learning_rate": 8.97777920455357e-06, + "loss": 3.3489, + "step": 2505728 + }, + { + "epoch": 0.02, + "learning_rate": 8.969393257043051e-06, + "loss": 3.3386, + "step": 2506240 + }, + { + "epoch": 0.02, + "learning_rate": 8.96100730953253e-06, + "loss": 3.3393, + "step": 2506752 + }, + { + "epoch": 0.02, + "learning_rate": 8.952621362022009e-06, + "loss": 3.3365, + "step": 2507264 + }, + { + "epoch": 0.02, + "learning_rate": 8.944251793315222e-06, + "loss": 3.3431, + "step": 2507776 + }, + { + "epoch": 0.02, + "learning_rate": 8.935865845804702e-06, + "loss": 3.3404, + "step": 2508288 + }, + { + "epoch": 0.02, + "learning_rate": 8.92747989829418e-06, + "loss": 3.3506, + "step": 2508800 + }, + { + "epoch": 0.02, + "learning_rate": 8.919093950783661e-06, + "loss": 3.3558, + "step": 2509312 + }, + { + "epoch": 0.02, + "learning_rate": 8.910724382076872e-06, + "loss": 3.339, + "step": 2509824 + }, + { + "epoch": 0.02, + "learning_rate": 8.90233843456635e-06, + "loss": 3.3406, + "step": 2510336 + }, + { + "epoch": 0.02, + "learning_rate": 8.893952487055832e-06, + "loss": 3.3481, + "step": 2510848 + }, + { + "epoch": 0.02, + "learning_rate": 8.885582918349043e-06, + "loss": 3.3507, + "step": 2511360 + }, + { + "epoch": 0.02, + "learning_rate": 8.877196970838523e-06, + "loss": 3.3509, + "step": 2511872 + }, + { + "epoch": 0.02, + "learning_rate": 8.868811023328003e-06, + "loss": 3.349, + "step": 2512384 + }, + { + "epoch": 0.02, + "learning_rate": 8.860425075817483e-06, + "loss": 3.3426, + "step": 2512896 + }, + { + "epoch": 0.02, + "learning_rate": 8.852055507110694e-06, + "loss": 3.3465, + "step": 2513408 + }, + { + "epoch": 0.02, + "learning_rate": 8.843669559600175e-06, + "loss": 3.3452, + "step": 2513920 + }, + { + "epoch": 0.02, + "learning_rate": 8.835283612089654e-06, + "loss": 3.3415, + "step": 2514432 + }, + { + "epoch": 0.02, + "learning_rate": 8.826897664579134e-06, + "loss": 3.3515, + "step": 2514944 + }, + { + "epoch": 0.02, + "learning_rate": 8.818511717068615e-06, + "loss": 3.342, + "step": 2515456 + }, + { + "epoch": 0.02, + "learning_rate": 8.810142148361824e-06, + "loss": 3.3316, + "step": 2515968 + }, + { + "epoch": 0.02, + "learning_rate": 8.801772579655037e-06, + "loss": 3.3606, + "step": 2516480 + }, + { + "epoch": 0.02, + "learning_rate": 8.793386632144517e-06, + "loss": 3.3416, + "step": 2516992 + }, + { + "epoch": 0.02, + "learning_rate": 8.785000684633997e-06, + "loss": 3.3444, + "step": 2517504 + }, + { + "epoch": 0.02, + "learning_rate": 8.776614737123477e-06, + "loss": 3.3358, + "step": 2518016 + }, + { + "epoch": 0.02, + "learning_rate": 8.768228789612957e-06, + "loss": 3.338, + "step": 2518528 + }, + { + "epoch": 0.03, + "eval_loss": 3.866798162460327, + "eval_runtime": 304.7896, + "eval_samples_per_second": 1251.982, + "eval_steps_per_second": 39.125, + "step": 2518560 + }, + { + "epoch": 1.0, + "learning_rate": 8.759842842102437e-06, + "loss": 3.3342, + "step": 2519040 + }, + { + "epoch": 1.0, + "learning_rate": 8.751456894591915e-06, + "loss": 3.3493, + "step": 2519552 + }, + { + "epoch": 1.0, + "learning_rate": 8.743070947081396e-06, + "loss": 3.3555, + "step": 2520064 + }, + { + "epoch": 1.0, + "learning_rate": 8.734701378374607e-06, + "loss": 3.3408, + "step": 2520576 + }, + { + "epoch": 1.0, + "learning_rate": 8.726315430864087e-06, + "loss": 3.3595, + "step": 2521088 + }, + { + "epoch": 1.0, + "learning_rate": 8.717929483353567e-06, + "loss": 3.3354, + "step": 2521600 + }, + { + "epoch": 1.0, + "learning_rate": 8.709559914646778e-06, + "loss": 3.3453, + "step": 2522112 + }, + { + "epoch": 1.0, + "learning_rate": 8.701173967136258e-06, + "loss": 3.3368, + "step": 2522624 + }, + { + "epoch": 1.0, + "learning_rate": 8.69278801962574e-06, + "loss": 3.3465, + "step": 2523136 + }, + { + "epoch": 1.0, + "learning_rate": 8.684402072115218e-06, + "loss": 3.3433, + "step": 2523648 + }, + { + "epoch": 1.0, + "learning_rate": 8.676016124604698e-06, + "loss": 3.3459, + "step": 2524160 + }, + { + "epoch": 1.0, + "learning_rate": 8.66764655589791e-06, + "loss": 3.347, + "step": 2524672 + }, + { + "epoch": 1.0, + "learning_rate": 8.659260608387388e-06, + "loss": 3.3363, + "step": 2525184 + }, + { + "epoch": 1.0, + "learning_rate": 8.650874660876868e-06, + "loss": 3.3289, + "step": 2525696 + }, + { + "epoch": 1.0, + "learning_rate": 8.642505092170081e-06, + "loss": 3.3335, + "step": 2526208 + }, + { + "epoch": 1.0, + "learning_rate": 8.634119144659561e-06, + "loss": 3.3395, + "step": 2526720 + }, + { + "epoch": 1.0, + "learning_rate": 8.625733197149039e-06, + "loss": 3.345, + "step": 2527232 + }, + { + "epoch": 1.0, + "learning_rate": 8.61734724963852e-06, + "loss": 3.3404, + "step": 2527744 + }, + { + "epoch": 1.0, + "learning_rate": 8.608977680931732e-06, + "loss": 3.3437, + "step": 2528256 + }, + { + "epoch": 1.0, + "learning_rate": 8.600591733421212e-06, + "loss": 3.3679, + "step": 2528768 + }, + { + "epoch": 1.0, + "learning_rate": 8.592205785910691e-06, + "loss": 3.3379, + "step": 2529280 + }, + { + "epoch": 1.0, + "learning_rate": 8.583819838400171e-06, + "loss": 3.3399, + "step": 2529792 + }, + { + "epoch": 1.0, + "learning_rate": 8.575450269693382e-06, + "loss": 3.3423, + "step": 2530304 + }, + { + "epoch": 1.0, + "learning_rate": 8.567064322182862e-06, + "loss": 3.3474, + "step": 2530816 + }, + { + "epoch": 1.0, + "learning_rate": 8.558678374672342e-06, + "loss": 3.3333, + "step": 2531328 + }, + { + "epoch": 1.0, + "learning_rate": 8.550292427161822e-06, + "loss": 3.343, + "step": 2531840 + }, + { + "epoch": 1.0, + "learning_rate": 8.541922858455035e-06, + "loss": 3.3467, + "step": 2532352 + }, + { + "epoch": 1.0, + "learning_rate": 8.533536910944513e-06, + "loss": 3.3432, + "step": 2532864 + }, + { + "epoch": 1.0, + "learning_rate": 8.525150963433993e-06, + "loss": 3.3232, + "step": 2533376 + }, + { + "epoch": 1.01, + "learning_rate": 8.516765015923474e-06, + "loss": 3.3308, + "step": 2533888 + }, + { + "epoch": 1.01, + "learning_rate": 8.508395447216685e-06, + "loss": 3.3403, + "step": 2534400 + }, + { + "epoch": 1.01, + "learning_rate": 8.500009499706165e-06, + "loss": 3.3466, + "step": 2534912 + }, + { + "epoch": 1.01, + "learning_rate": 8.491623552195645e-06, + "loss": 3.3527, + "step": 2535424 + }, + { + "epoch": 1.01, + "learning_rate": 8.483237604685125e-06, + "loss": 3.3389, + "step": 2535936 + }, + { + "epoch": 1.01, + "learning_rate": 8.474868035978336e-06, + "loss": 3.3341, + "step": 2536448 + }, + { + "epoch": 1.01, + "learning_rate": 8.466482088467816e-06, + "loss": 3.3482, + "step": 2536960 + }, + { + "epoch": 1.01, + "learning_rate": 8.458096140957296e-06, + "loss": 3.3267, + "step": 2537472 + }, + { + "epoch": 1.01, + "learning_rate": 8.449710193446774e-06, + "loss": 3.3397, + "step": 2537984 + }, + { + "epoch": 1.01, + "learning_rate": 8.441340624739987e-06, + "loss": 3.3294, + "step": 2538496 + }, + { + "epoch": 1.01, + "learning_rate": 8.432954677229467e-06, + "loss": 3.3389, + "step": 2539008 + }, + { + "epoch": 1.01, + "learning_rate": 8.424568729718946e-06, + "loss": 3.332, + "step": 2539520 + }, + { + "epoch": 1.01, + "learning_rate": 8.416182782208426e-06, + "loss": 3.3516, + "step": 2540032 + }, + { + "epoch": 1.01, + "learning_rate": 8.407813213501637e-06, + "loss": 3.3372, + "step": 2540544 + }, + { + "epoch": 1.01, + "learning_rate": 8.399427265991117e-06, + "loss": 3.3387, + "step": 2541056 + }, + { + "epoch": 1.01, + "learning_rate": 8.391041318480599e-06, + "loss": 3.3429, + "step": 2541568 + }, + { + "epoch": 1.01, + "learning_rate": 8.382655370970077e-06, + "loss": 3.3422, + "step": 2542080 + }, + { + "epoch": 1.01, + "learning_rate": 8.37428580226329e-06, + "loss": 3.334, + "step": 2542592 + }, + { + "epoch": 1.01, + "learning_rate": 8.36589985475277e-06, + "loss": 3.3256, + "step": 2543104 + }, + { + "epoch": 1.01, + "learning_rate": 8.357513907242248e-06, + "loss": 3.3259, + "step": 2543616 + }, + { + "epoch": 1.01, + "learning_rate": 8.349127959731728e-06, + "loss": 3.3502, + "step": 2544128 + }, + { + "epoch": 1.01, + "learning_rate": 8.34075839102494e-06, + "loss": 3.3361, + "step": 2544640 + }, + { + "epoch": 1.01, + "learning_rate": 8.33237244351442e-06, + "loss": 3.3317, + "step": 2545152 + }, + { + "epoch": 1.01, + "learning_rate": 8.3239864960039e-06, + "loss": 3.3284, + "step": 2545664 + }, + { + "epoch": 1.01, + "learning_rate": 8.31560054849338e-06, + "loss": 3.3382, + "step": 2546176 + }, + { + "epoch": 1.01, + "learning_rate": 8.307230979786591e-06, + "loss": 3.3278, + "step": 2546688 + }, + { + "epoch": 1.01, + "learning_rate": 8.29884503227607e-06, + "loss": 3.3465, + "step": 2547200 + }, + { + "epoch": 1.01, + "learning_rate": 8.29045908476555e-06, + "loss": 3.3335, + "step": 2547712 + }, + { + "epoch": 1.01, + "learning_rate": 8.28207313725503e-06, + "loss": 3.3337, + "step": 2548224 + }, + { + "epoch": 1.01, + "learning_rate": 8.273703568548243e-06, + "loss": 3.345, + "step": 2548736 + }, + { + "epoch": 1.01, + "learning_rate": 8.265317621037722e-06, + "loss": 3.3273, + "step": 2549248 + }, + { + "epoch": 1.01, + "learning_rate": 8.256931673527201e-06, + "loss": 3.3279, + "step": 2549760 + }, + { + "epoch": 1.01, + "learning_rate": 8.248545726016681e-06, + "loss": 3.3363, + "step": 2550272 + }, + { + "epoch": 1.01, + "learning_rate": 8.240176157309894e-06, + "loss": 3.3237, + "step": 2550784 + }, + { + "epoch": 1.01, + "learning_rate": 8.231790209799372e-06, + "loss": 3.3263, + "step": 2551296 + }, + { + "epoch": 1.01, + "learning_rate": 8.223404262288854e-06, + "loss": 3.3386, + "step": 2551808 + }, + { + "epoch": 1.01, + "learning_rate": 8.215018314778334e-06, + "loss": 3.346, + "step": 2552320 + }, + { + "epoch": 1.01, + "learning_rate": 8.206648746071545e-06, + "loss": 3.3302, + "step": 2552832 + }, + { + "epoch": 1.01, + "learning_rate": 8.198262798561025e-06, + "loss": 3.3317, + "step": 2553344 + }, + { + "epoch": 1.01, + "learning_rate": 8.189876851050504e-06, + "loss": 3.3245, + "step": 2553856 + }, + { + "epoch": 1.01, + "learning_rate": 8.181490903539984e-06, + "loss": 3.3372, + "step": 2554368 + }, + { + "epoch": 1.01, + "learning_rate": 8.173121334833195e-06, + "loss": 3.3367, + "step": 2554880 + }, + { + "epoch": 1.01, + "learning_rate": 8.164735387322675e-06, + "loss": 3.3399, + "step": 2555392 + }, + { + "epoch": 1.01, + "learning_rate": 8.156349439812155e-06, + "loss": 3.3392, + "step": 2555904 + }, + { + "epoch": 1.01, + "learning_rate": 8.147963492301635e-06, + "loss": 3.3431, + "step": 2556416 + }, + { + "epoch": 1.01, + "learning_rate": 8.139593923594846e-06, + "loss": 3.3481, + "step": 2556928 + }, + { + "epoch": 1.01, + "learning_rate": 8.131207976084326e-06, + "loss": 3.3254, + "step": 2557440 + }, + { + "epoch": 1.01, + "learning_rate": 8.122822028573806e-06, + "loss": 3.3383, + "step": 2557952 + }, + { + "epoch": 1.01, + "learning_rate": 8.114436081063286e-06, + "loss": 3.3411, + "step": 2558464 + }, + { + "epoch": 1.01, + "learning_rate": 8.106066512356497e-06, + "loss": 3.3278, + "step": 2558976 + }, + { + "epoch": 1.01, + "learning_rate": 8.097680564845978e-06, + "loss": 3.3519, + "step": 2559488 + }, + { + "epoch": 1.01, + "learning_rate": 8.089294617335458e-06, + "loss": 3.3422, + "step": 2560000 + }, + { + "epoch": 1.01, + "learning_rate": 8.080908669824936e-06, + "loss": 3.3473, + "step": 2560512 + }, + { + "epoch": 1.01, + "learning_rate": 8.072539101118149e-06, + "loss": 3.3449, + "step": 2561024 + }, + { + "epoch": 1.01, + "learning_rate": 8.064153153607629e-06, + "loss": 3.3256, + "step": 2561536 + }, + { + "epoch": 1.01, + "learning_rate": 8.055767206097109e-06, + "loss": 3.3359, + "step": 2562048 + }, + { + "epoch": 1.01, + "learning_rate": 8.047381258586589e-06, + "loss": 3.3356, + "step": 2562560 + }, + { + "epoch": 1.01, + "learning_rate": 8.0390116898798e-06, + "loss": 3.3407, + "step": 2563072 + }, + { + "epoch": 1.01, + "learning_rate": 8.03062574236928e-06, + "loss": 3.3403, + "step": 2563584 + }, + { + "epoch": 1.01, + "learning_rate": 8.02223979485876e-06, + "loss": 3.3363, + "step": 2564096 + }, + { + "epoch": 1.02, + "learning_rate": 8.01385384734824e-06, + "loss": 3.3428, + "step": 2564608 + }, + { + "epoch": 1.02, + "learning_rate": 8.00548427864145e-06, + "loss": 3.3346, + "step": 2565120 + }, + { + "epoch": 1.02, + "learning_rate": 7.997098331130932e-06, + "loss": 3.3246, + "step": 2565632 + }, + { + "epoch": 1.02, + "learning_rate": 7.98871238362041e-06, + "loss": 3.3325, + "step": 2566144 + }, + { + "epoch": 1.02, + "learning_rate": 7.98032643610989e-06, + "loss": 3.345, + "step": 2566656 + }, + { + "epoch": 1.02, + "learning_rate": 7.971973246206833e-06, + "loss": 3.3517, + "step": 2567168 + }, + { + "epoch": 1.02, + "learning_rate": 7.963587298696313e-06, + "loss": 3.3363, + "step": 2567680 + }, + { + "epoch": 1.02, + "learning_rate": 7.955201351185793e-06, + "loss": 3.3211, + "step": 2568192 + }, + { + "epoch": 1.02, + "learning_rate": 7.946815403675273e-06, + "loss": 3.3376, + "step": 2568704 + }, + { + "epoch": 1.02, + "learning_rate": 7.938429456164753e-06, + "loss": 3.3401, + "step": 2569216 + }, + { + "epoch": 1.02, + "learning_rate": 7.930043508654231e-06, + "loss": 3.3423, + "step": 2569728 + }, + { + "epoch": 1.02, + "learning_rate": 7.921657561143713e-06, + "loss": 3.3341, + "step": 2570240 + }, + { + "epoch": 1.02, + "learning_rate": 7.913271613633193e-06, + "loss": 3.3321, + "step": 2570752 + }, + { + "epoch": 1.02, + "learning_rate": 7.904902044926404e-06, + "loss": 3.3235, + "step": 2571264 + }, + { + "epoch": 1.02, + "learning_rate": 7.896516097415884e-06, + "loss": 3.3359, + "step": 2571776 + }, + { + "epoch": 1.02, + "learning_rate": 7.888130149905364e-06, + "loss": 3.3296, + "step": 2572288 + }, + { + "epoch": 1.02, + "learning_rate": 7.879744202394844e-06, + "loss": 3.3309, + "step": 2572800 + }, + { + "epoch": 1.02, + "learning_rate": 7.871374633688056e-06, + "loss": 3.3326, + "step": 2573312 + }, + { + "epoch": 1.02, + "learning_rate": 7.862988686177534e-06, + "loss": 3.3377, + "step": 2573824 + }, + { + "epoch": 1.02, + "learning_rate": 7.854602738667014e-06, + "loss": 3.3273, + "step": 2574336 + }, + { + "epoch": 1.02, + "learning_rate": 7.846216791156494e-06, + "loss": 3.3363, + "step": 2574848 + }, + { + "epoch": 1.02, + "learning_rate": 7.837847222449705e-06, + "loss": 3.3311, + "step": 2575360 + }, + { + "epoch": 1.02, + "learning_rate": 7.829461274939185e-06, + "loss": 3.335, + "step": 2575872 + }, + { + "epoch": 1.02, + "learning_rate": 7.821075327428667e-06, + "loss": 3.3304, + "step": 2576384 + }, + { + "epoch": 1.02, + "learning_rate": 7.812689379918145e-06, + "loss": 3.3323, + "step": 2576896 + }, + { + "epoch": 1.02, + "learning_rate": 7.804319811211356e-06, + "loss": 3.3406, + "step": 2577408 + }, + { + "epoch": 1.02, + "learning_rate": 7.795933863700837e-06, + "loss": 3.3427, + "step": 2577920 + }, + { + "epoch": 1.02, + "learning_rate": 7.787547916190317e-06, + "loss": 3.3359, + "step": 2578432 + }, + { + "epoch": 1.02, + "learning_rate": 7.779178347483528e-06, + "loss": 3.3336, + "step": 2578944 + }, + { + "epoch": 1.02, + "learning_rate": 7.770792399973008e-06, + "loss": 3.3414, + "step": 2579456 + }, + { + "epoch": 1.02, + "learning_rate": 7.762406452462488e-06, + "loss": 3.3366, + "step": 2579968 + }, + { + "epoch": 1.02, + "learning_rate": 7.754020504951968e-06, + "loss": 3.3246, + "step": 2580480 + }, + { + "epoch": 1.02, + "learning_rate": 7.745650936245179e-06, + "loss": 3.3447, + "step": 2580992 + }, + { + "epoch": 1.02, + "learning_rate": 7.737264988734659e-06, + "loss": 3.3353, + "step": 2581504 + }, + { + "epoch": 1.02, + "learning_rate": 7.728879041224139e-06, + "loss": 3.3401, + "step": 2582016 + }, + { + "epoch": 1.02, + "learning_rate": 7.720493093713619e-06, + "loss": 3.3285, + "step": 2582528 + }, + { + "epoch": 1.02, + "learning_rate": 7.71212352500683e-06, + "loss": 3.3321, + "step": 2583040 + }, + { + "epoch": 1.02, + "learning_rate": 7.70373757749631e-06, + "loss": 3.3297, + "step": 2583552 + }, + { + "epoch": 1.02, + "learning_rate": 7.695351629985791e-06, + "loss": 3.3302, + "step": 2584064 + }, + { + "epoch": 1.02, + "learning_rate": 7.68696568247527e-06, + "loss": 3.3303, + "step": 2584576 + }, + { + "epoch": 1.02, + "learning_rate": 7.678596113768482e-06, + "loss": 3.3422, + "step": 2585088 + }, + { + "epoch": 1.02, + "learning_rate": 7.670210166257962e-06, + "loss": 3.3497, + "step": 2585600 + }, + { + "epoch": 1.02, + "learning_rate": 7.661824218747442e-06, + "loss": 3.3359, + "step": 2586112 + }, + { + "epoch": 1.02, + "learning_rate": 7.65343827123692e-06, + "loss": 3.3257, + "step": 2586624 + }, + { + "epoch": 1.02, + "learning_rate": 7.645068702530133e-06, + "loss": 3.3382, + "step": 2587136 + }, + { + "epoch": 1.02, + "learning_rate": 7.636682755019613e-06, + "loss": 3.342, + "step": 2587648 + }, + { + "epoch": 1.02, + "learning_rate": 7.628296807509092e-06, + "loss": 3.3421, + "step": 2588160 + }, + { + "epoch": 1.02, + "learning_rate": 7.619910859998572e-06, + "loss": 3.3391, + "step": 2588672 + }, + { + "epoch": 1.02, + "learning_rate": 7.611541291291783e-06, + "loss": 3.3368, + "step": 2589184 + }, + { + "epoch": 1.02, + "learning_rate": 7.603155343781264e-06, + "loss": 3.329, + "step": 2589696 + }, + { + "epoch": 1.02, + "learning_rate": 7.594769396270743e-06, + "loss": 3.3417, + "step": 2590208 + }, + { + "epoch": 1.02, + "learning_rate": 7.586383448760223e-06, + "loss": 3.3332, + "step": 2590720 + }, + { + "epoch": 1.02, + "learning_rate": 7.578013880053435e-06, + "loss": 3.3364, + "step": 2591232 + }, + { + "epoch": 1.02, + "learning_rate": 7.569627932542915e-06, + "loss": 3.3377, + "step": 2591744 + }, + { + "epoch": 1.02, + "learning_rate": 7.561241985032394e-06, + "loss": 3.3255, + "step": 2592256 + }, + { + "epoch": 1.02, + "learning_rate": 7.5528724163256054e-06, + "loss": 3.3491, + "step": 2592768 + }, + { + "epoch": 1.02, + "learning_rate": 7.544486468815086e-06, + "loss": 3.3352, + "step": 2593280 + }, + { + "epoch": 1.02, + "learning_rate": 7.5361005213045645e-06, + "loss": 3.3335, + "step": 2593792 + }, + { + "epoch": 1.02, + "learning_rate": 7.527714573794045e-06, + "loss": 3.3275, + "step": 2594304 + }, + { + "epoch": 1.02, + "learning_rate": 7.519328626283525e-06, + "loss": 3.3283, + "step": 2594816 + }, + { + "epoch": 1.03, + "eval_loss": 3.866793155670166, + "eval_runtime": 302.4432, + "eval_samples_per_second": 1261.695, + "eval_steps_per_second": 39.429, + "step": 2594880 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 1.798508503804207e+18, + "trial_name": null, + "trial_params": null +}